STORAGE MEDIUM TECHNICAL FIELD

[0001] Embodiments of the present disclosure relate to the field of computers, and in particular relate to a method and an apparatus for generating a maintenance plan of wind turbines, a device, and a storage medium. BACKGROUND

[0002] In production work, wind turbine equipment may break down and thus require regular maintenance performed by technicians. An accurate prediction of a maintenance window period may help the technicians to arrange maintenance operations reasonably. [0003] In related arts, a computer device obtains the maintenance window period of wind turbine equipment to be maintained in a target region by firstly acquiring historical weather information of locations of the wind turbine equipment to be maintained, predicting operable dates in the next year, and making corrections based on the predicted dates according to working days and holidays, and then making further corrections according to third-party weather forecast data. [0004] However, in methods for predicting the maintenance window period in the related arts, operable working days are determined as the maintenance window period merely according to the historical weather information in the target region, but the accurate maintenance window period of each wind turbine equipment to be maintained cannot be predicted specifically, thereby resulting in a poor prediction accuracy and a low utilization rate of the maintenance window period.

SUMMARY

[0005] Embodiments of the present disclosure provide a method and an apparatus for generating a maintenance plan of wind turbines, a device and a storage medium. The technical solutions of the present disclosure are described below.

[0006] According to an aspect of the embodiments of the present disclosure, a method for generating a maintenance plan of wind turbines is provided. The method includes: [0007] determining a prediction window period corresponding to wind turbine equipment to be maintained according to prediction weather information of locations of the wind turbine equipment to be maintained in a wind turbine maintenance period, wherein a prediction weather condition within the prediction window period is in conformity with a weather condition for maintenance operations

[0008] determining a target window period corresponding to each the wind turbine equipment to be maintained from the prediction window period according to equipment maintenance information corresponding to each the wind turbine equipment to be maintained; and [0009] generating a maintenance schedule according to the target window period and information of maintenance persons, wherein the maintenance schedule is configured to instruct a maintenance time period for each the wind turbine equipment to be maintained and the maintenance persons assigned to the wind turbine equipment to be maintained; and the maintenance time period belongs to the target window period . [0010] According to another aspect of the embodiments of the present disclosure, an apparatus for generating a maintenance plan of wind turbines is provided. The apparatus includes:

[0011] a first determination module configured to determine a prediction window period corresponding to wind turbine equipment to be maintained according to prediction weather information of locations of the wind turbine equipment to be maintained in a wind turbine maintenance period, wherein prediction weather conditions within the prediction window period are in conformity with a weather condition for maintenance operations; [0012] a second determination module configured to determine a target window period corresponding to each the wind turbine equipment to be maintained from the prediction window period according to equipment maintenance information corresponding to each the wind turbine equipment to be maintained; and

[0013] a generation module configured to generate a maintenance schedule according to the target window period and information of maintenance persons, wherein the maintenance schedule is configured to instruct a maintenance time period for each the wind turbine equipment to be maintained and the maintenance persons assigned to the wind turbine equipment to be maintained, and the maintenance time period belongs to the target window period.

[0014] According to another aspect of the embodiments of the present disclosure, a computer device is provided. The computer device includes a processor and a memory storing at least one instruction therein, wherein the at least one instruction is configured to be executed by the processor to implement the method for generating the maintenance plan of the wind turbines according to the aspects as described above.

[0015] According to another aspect of the embodiments of the present disclosure, a computer-readable storage medium is provided. The computer-readable storage medium stores at least one instruction therein, and the at least one instruction is configured to be executed by a processor to implement the method for generating the maintenance plan of the wind turbines according to the aspects as described above.

[0016] According to another aspect of the embodiments of the present disclosure, a computer program product is further provided. The computer program product is stored with at least one instruction configured to be loaded and executed by a processor to implement the method for generating the maintenance plan of the wind turbines according to the aspects as described above.

[0017] The technical solutions provided by the embodiments of the present disclosure at least have the following beneficial effects.

[0018] The time period in conformity with the weather condition of maintenance operations is determined as the prediction window period by acquiring the weather information of the location of each wind turbine equipment to be maintained, and the prediction window period satisfied with a time length of the maintenance operation is determined as the target window period according to the equipment maintenance information of each wind turbine equipment to be maintained, such that the maintenance schedule is generated to instruct the corresponding maintenance persons to perform the maintenance operation in the target window period. The window period for each wind turbine equipment to be maintained is predicted according to the prediction weather information in different regions, thereby improving the prediction accuracy. And the maintenance schedule is generated according to the equipment maintenance information, the prediction window period and the information of the maintenance persons, thereby improving the utilization rate of the window period and the efficiency of the maintenance operation.

BRIEF DESCRIPTION OF THE DRAWINGS [0019] FIG. 1 is a schematic diagram showing an implementation environment according to an exemplary embodiment;

[0020] FIG. 2 is a flowchart showing a method for generating a maintenance plan of wind turbines according to an exemplary embodiment;

[0021] FIG. 3 is a flowchart showing a method for generating a maintenance plan of wind turbines according to another exemplary embodiment;

[0022] FIG. 4 is a flowchart showing determination of a prediction window period according to an exemplary embodiment;

[0023] FIG. 5 is a flowchart showing a method for generating a maintenance plan of wind turbines according to still another exemplary embodiment;

[0024] FIG. 6 is a flowchart showing calculation of power-generation power of a wind turbine according to an exemplary embodiment; [0025] FIG. 7 is a flowchart showing arrangement of maintenance operations according to an exemplary embodiment;

[0026] FIG. 8 is a structural block diagram showing an apparatus for generating a maintenance plan of wind turbines according to an exemplary embodiment; and [0027] FIG. 9 is a structural schematic diagram showing a computer device according to an exemplary embodiment.

DETAILED DESCRIPTION

[0028] In order to make the objectives, technical solutions, and advantages of the present disclosure clearer, the embodiments of the present disclosure are described in detail hereafter with reference to the accompanying drawings.

[0029] The term “plurality” herein refers to two or more. "And/or" herein describes association relationships of the associated objects, indicating three kinds of relationships, For example, A and/or B may indicate three kinds of cases that A exists alone, A and B exist concurrently, and B exists alone. The character "/" generally indicates that the associated objects are in an "or" relationship.

[0030] Wind turbine equipment in a wind field may break down during operation, thereby requiring regular maintenance and overhaul by maintenance persons. In the related arts, there is yet no relevant prediction for a maintenance process, but the window period prediction during implementing and hoisting wind turbines in the wind field. That is, a computer device predicts window periods in the next year according to weather information over the historical years of the location of the wind field. The computer device predicts dates available for the maintenance operation in the next year by acquiring historical weather information of the location of the wind field, and makes corrections on the predicted dates according to working days by excluding holidays, and then makes secondary corrections according to third-party weather forecast information to finally obtain working days that weather conditions is satisfied with the requirements of the maintenance operation, i.e., window periods.

[0031] Further, in the related arts, the computer device can only predict the window period of the entire wind field rather than the window period for each wind turbine equipment, which results in rough spatial granularity, and can only predict the approximate working days. Actually, the maintenance operation of wind turbines is affected by complex weather conditions and the status of each wind turbine equipment is different, thereby requiring different maintenance operations. In the related arts, inaccurate window period prediction and rough maintenance operation plans cause a poor accuracy of the window period, a low man-hour utilization rate of the maintenance persons and a low efficiency of the maintenance operation, thereby resulting in high maintenance costs of wind turbines. [0032] In order to solve the above problems, embodiments of the present disclosure provide a method for generating a maintenance plan of wind turbines. FIG. 1 is a schematic diagram showing an implementation environment according to an exemplary embodiment of the present disclosure. Wind turbine equipment to be maintained 101, a server 102 and a computer device 103 are included in the implementation environment.

[0033] The wind turbine equipment to be maintained 101 is wind turbine equipment that requires a maintenance operation in the wind field. The wind turbine equipment to be maintained 101 stops working during the maintenance operation, and works normally to generate power or stop working due to breakdown in other time. Data (such as power, power generation amount and breakdown information) generated thereof is sent to the server 102. [0034] The wind turbine equipment to be maintained 101 is in communication with the server 102 through a wired or wireless network. In a possible application scenario, the wind turbine equipment to be maintained 101 sends data to the server 102 via a gateway device.

[0035] The server 102 is configured to process and store the data sent by the wind turbine equipment to be maintained 101. The server 102 may be a server, or a server cluster consisting of several servers, or a cloud computing center. [0036] The server 102 is in communication with the computer device 103 through a wired or wireless network. In a possible application scenario, the server 102 sends the data to the computer device 103 via a gateway device.

[0037] The computer device 103 obtains the data (such as locations of the wind turbine equipment to be maintained 101, historical weather data and power corresponding to different weather conditions) from the server 102, and obtains prediction weather data of the locations of the wind turbine equipment to be maintained 101 from a third-party weather forecast, and obtains a more refined predicted weather result by recalculating in the cloud computing center, and then predicts window period for each wind turbine equipment 101 to be maintained according to the obtained data, so as to generate a maintenance schedule.

[0038] Referring to FIG. 2, it is a flowchart showing of a method for generating a maintenance plan of wind turbines according to an exemplary embodiment of the present disclosure. In this embodiment, descriptions are made by taking the method used for a computer device as an example, and the method includes the following steps. [0039] In step 201, a prediction window period corresponding to wind turbine equipment to be maintained is determined according to prediction weather information of locations of the wind turbine equipment to be maintained in a wind turbine maintenance period, wherein predicted weather conditions within the prediction window period are in conformity with weather conditions for a maintenance operation. [0040] The maintenance operation of wind turbine equipment is closely related to the weather. The weather such as strong wind, rainfall and heavy fog may affect the efficiency of the maintenance and may further have hidden danger of safety, making maintenance operations unsuitable.

[0041] In a possible implementation, a geographical location of each wind turbine equipment to be maintained is stored in the computer device, so that the prediction window period of each wind turbine equipment to be maintained may be determined according to the prediction weather information of the relevant location released by a professional weather forecast. The prediction window period is a time period of which the predicted weather condition is conformity with the weather condition for the maintenance operation, and the time period may be accurate to minutes. In actual applications, the difference in the prediction window periods corresponding to the closer wind turbine equipment to be maintained is very small, that is, one prediction window period may correspond to a plurality of wind turbine equipment to be maintained.

[0042] As the weather is complex and changeable (especially, many weather factors in special geographical locations such as an offshore wind field), and there are errors in the weather forecast, the prediction window period may be inaccurate. Optionally, the computer device determines the prediction window period of each wind turbine equipment to be maintained in a predetermined time length by recalculating based on acquired the latest weather forecast every predetermined time interval. [0043] Illustratively, for all wind turbine equipment in the offshore wind field, a wind turbine maintenance period is preset to 7 days, and the computer device may acquire prediction weather information of the next 7 days every 24 hours. The prediction weather information includes wind speed, wave height, rainfall amount, visibility and extreme weather forecasting and warning, and the like. The prediction window period of each wind turbine equipment to be maintained is determined according to the prediction weather information.

[0044] In step 202, a target window period corresponding to each the wind turbine equipment to be maintained is determined from the prediction window period according to equipment maintenance information corresponding to each the wind turbine equipment to be maintained.

[0045] Since the contents of the maintenance operation required for each wind turbine equipment to be maintained are different, the prediction window period may fail to satisfy the requirements of the maintenance operation. [0046] In a possible implementation, after determining the prediction window period, the computer device acquires the equipment maintenance information of each wind turbine equipment to be maintained and determines the prediction window period in conformity with the requirements of the maintenance operation as the target window period of wind turbine equipment to be maintained. When the prediction window period is changed, the computer device re-determines the target window period.

[0047] In step 203, a maintenance schedule is generated according to the target window period and information of maintenance persons, wherein the maintenance schedule is configured to instruct a maintenance time period of each of the wind turbine equipment to be maintained and the maintenance persons assigned to the wind turbine equipment to be maintained.

[0048] In a possible implementation, the computer device acquires the information of maintenance persons, the information includes a list of the maintenance persons and the corresponding idle times. Then the maintenance schedule is generated according to the target window period and the information of the maintenance persons, so as to assign the maintenance persons and the maintenance time period for each wind turbine equipment to be maintained, wherein the maintenance time period belongs to the target window period. The computer device calculates the prediction window period every predetermined time interval and updates the target window period and the maintenance schedule.

[0049] In summary, according to the embodiments of the present disclosure, the time period in conformity with the weather condition of maintenance operations is determined as the prediction window period by acquiring the weather information of the location of each wind turbine equipment to be maintained, and the prediction window period satisfied with a time length of the maintenance operation is determined as the target window period according to the equipment maintenance information of each wind turbine equipment to be maintained, such that the maintenance schedule is generated to instruct the corresponding maintenance persons to perform the maintenance operation in the target window period. The window period for each wind turbine equipment to be maintained is predicted according to the prediction weather information in different regions, thereby improving the prediction accuracy. And the maintenance schedule is generated according to the equipment maintenance information, the prediction window period and the information of the maintenance persons, thereby improving the utilization rate of the window period and the efficiency of the maintenance operation.

[0050] Referring to FIG. 3, it is a flowchart showing a method for generating a maintenance plan of wind turbines according to another exemplary embodiment of the present disclosure. In this embodiment, descriptions are made by taking the method used for a computer device as an example, and the method includes the following steps.

[0051] In step 301, a j ^th type prediction window period is determined according to the prediction weather information in a wind turbine prediction period and an i ^th type weather conditions for maintenance operation, wherein the prediction weather information within the j ^th type prediction window period is in conformity with the i ^th type weather conditions for the maintenance operation, and both j and i are integers greater than or equal to 1.

[0052] The maintenance operation of wind turbine equipment is affected by the weather. However, since the weather is complex and changeable, it is very difficult for the computer device to determine the specific prediction window period, and it is required to manually preset weather conditions in conformity with the maintenance operation.

[0053] In a possible implementation, relevant technicians preset a plurality of levels of weather conditions for maintenance operation. After acquiring the prediction weather information of the location of each wind turbine equipment to be maintained, the computer device firstly filters out a first type prediction window period according to the weather conditions for maintenance operation with the highest priority, i.e., a first type weather condition for maintenance operation.

[0054] Illustratively, as shown in FIG. 4, the computer device firstly performs step a of acquiring a weather forecast. For example, for wind turbine equipment to be maintained in the offshore wind field, the computer device needs to acquire weather information such as wind speed, wave height, rainfall amount, visibility and extreme weather. The computer device continues to perform step b of calculating the prediction window period, that is, calculating the first type prediction window period according to the preset first type weather condition for maintenance operation.

[0055] In step 302, if a number of the j ^th type prediction window period is less than a number threshold, and/or the window time length of the j ^th type prediction window period is less than a time length threshold, a (j+l) ^th type prediction window period is determined according to the prediction weather information and an (i+l) ^th type weather conditions for maintenance operation.

[0056] In a possible implementation, since not all prediction window periods may satisfy the requirements of the maintenance operation, when the number of the j ^th type prediction window period is less or the window time length of the j ^th type prediction window period is short, maintenance of the wind turbine equipment to be maintained may not be ensured in time. Therefore, the relevant technicians may determine the (j+l) ^th type prediction window period by setting the (i+l) ^th type weather conditions for maintenance operation with lowered standards according to actual situations. The prediction weather information within the j ^th type prediction window period in conformity with the (i+l) ^th type weather conditions for maintenance operation, and the i ^th type weather condition for maintenance operations is superior to the (i+l) ^th type weather condition for maintenance operations.

[0057] Illustratively, the relevant technicians determine a second prediction window period according to a second weather condition for maintenance operations, wherein the first weather condition for maintenance operations is superior to the second weather condition for maintenance operations. For example, if the rainfall amount is required to be 0 in the first weather condition for maintenance operations, the rainfall amount is required to be less than or equal to 10 mm in the second weather condition for maintenance operations, or the wind speed in the second weather condition for maintenance operations is greater than that in the first weather condition for maintenance operations . [0058] As shown in FIG. 4, the computer device performs step b of calculating the prediction window period. When the number of the first prediction window period is less than the number threshold, and/or the window time length of the first prediction window period is less than the time length threshold, the computer device determines the second prediction window period according to the second weather condition for maintenance operations, and continues to determine the (j+l) ^th type prediction window period according to the (i+l) ^th type weather condition for maintenance operations until the number of the prediction window periods reaches the number threshold or the window time length of the prediction window period reaches the time length threshold, the computer device performs step c of determining the prediction window period, wherein the prediction window period includes the first prediction window period to the (j+l) ^th type prediction window period obtained in the above step b.

[0059] Illustratively, the number threshold is set to 5, and the time length threshold is set to 10 hours. If the number of the first prediction window periods is less than 5, and/or the window time length of the first prediction window period is less than 10 hours, the computer device determines the second prediction window period according to the second weather condition for maintenance operations; if the numbers of the first prediction window periods and the second prediction window period are greater than or equal to 5, and/or the window time lengths of the first prediction window period and the second prediction window period are greater than or equal to 10 hours, the prediction window period is determined; otherwise, the computer device continues to determine a third prediction window period according to a third weather condition for maintenance operations.

[0060] In step 303, the target window period of an n ^th level wind turbine equipment to be maintained in the wind turbine equipment to be maintained is determined from the prediction window period, wherein the n ^th level wind turbine equipment to be maintained are wind turbine equipment to be maintained with an n ^th maintenance priority, and n is an integer greater than or equal to 1 .

[0061] In a possible implementation, the equipment maintenance information includes maintenance priority. The computer device determines the target window period according to the maintenance priority of the wind turbine equipment to be maintained. For example, the computer device firstly filters out wind turbine equipment to be maintained with the first maintenance priority, i.e., a first level wind turbine equipment to be maintained, and then determines the target window period of the first level wind turbine equipment to be maintained according to the equipment maintenance information and the prediction window period of each first level wind turbine equipment to be maintained.

[0062] In step 304, after the target window period of the n ^th level wind turbine equipment to be maintained is determined, the target window period of an (n+l) ^th level wind turbine equipment to be maintained in the wind turbine equipment to be maintained is determined from the prediction window period, wherein the (n+l) ^th level wind turbine equipment to be maintained is the wind turbine equipment to be maintained with an (n+l) ^th maintenance priority, and the n ^th maintenance priority is higher than the (n+l) ^th maintenance priority.

[0063] After the target window period of the first level wind turbine equipment to be maintained is determined, the computer device continues to determine wind turbine equipment to be maintained with a next priority until the target window period of wind turbine equipment to be maintained with the last priority is determined, that is, the prediction of the target window periods of all wind turbine equipment to be maintained is completed.

[0064] In step 305, the number of available maintenance persons in the target window period is acquired.

[0065] After the computer device determines the target window period of each wind turbine equipment to be maintained, it is required to arrange maintenance persons to perform the maintenance operation for the wind turbine equipment to be maintained in the target window period.

[0066] In a possible implementation, the computer device acquires the information of the maintenance persons. The information of the maintenance persons includes the number of the maintenance persons in each time period. The computer device firstly acquires the number of the available maintenance persons in each target window period.

[0067] In step 306, if the number of the available maintenance persons is greater than a number of the n ^th level wind turbine equipment to be maintained, the maintenance persons are assigned to the n ^th level wind turbine equipment to be maintained according to the number of the n ^th level wind turbine equipment to be maintained, and updates the number of the available maintenance persons in the target window period.

[0068] In a possible implementation, the computer device firstly assigns maintenance persons to the first level wind turbine equipment to be maintained. If the number of the available maintenance persons is greater than the number of the first level wind turbine equipment to be maintained in a first target window period of the first level wind turbine equipment to be maintained, the computer device selects the maintenance persons according to the number of the first level wind turbine equipment to be maintained, assigns the maintenance persons to perform the maintenance operation for each of the first level wind turbine equipment to be maintained, updates the number of the available maintenance persons in the target window period, and continues to assign the maintenance persons to other levels wind turbine equipment to be maintained. [0069] Illustratively, there are three first level wind turbine equipment to be maintained, i.e., A, B and C, the target window periods of A and B are window period 1, and the target window period of C is window period 2; there are two second level wind turbine equipment to be maintained, i.e., D and E, the target window period of D is the window period 1, and the target window period of E is the window period 2; three maintenance persons have no work arrangement in the window period 1 and the window period 2. The computer device firstly assigns maintenance persons to A, B and C by firstly selecting two maintenance persons to perform the maintenance operation for the wind turbine equipment to be maintained A and B in the window period 1 respectively and updating the number of the available maintenance persons of the window period 1 to one, and then selecting one of the maintenance persons to perform the maintenance operation for the wind turbine equipment to be maintained C in the window period 2 and updating the number of the available maintenance persons of the window period 2 to two.

[0070] The computer device continues to assign a maintenance person to the wind turbine equipment to be maintained D and E by firstly assigning the remaining one of the maintenance persons in the window period 1 to perform the maintenance operation for the wind turbine equipment to be maintained D, and then selecting one of two remaining maintenance persons in the window period 2 to perform the maintenance operation for the wind turbine equipment to be maintained E. [0071] In step 307, if the number of the available maintenance persons is less than the number of the n ^th level wind turbine equipment to be maintained, the maintenance persons are assigned to the n ^th level wind turbine equipment to be maintained according to the number of the available maintenance persons, and updates the number of the available maintenance persons in the target window period. [0072] In a possible implementation, the computer device firstly assigns maintenance persons to the first level wind turbine equipment to be maintained. If the number of the available maintenance persons is less than the number of the first level wind turbine equipment to be maintained in the first target window period of the first level wind turbine equipment to be maintained, the computer device assigns all maintenance persons to perform the maintenance operation for the first level wind turbine equipment to be maintained in the first target window period, and then assigns maintenance persons for the remaining first level wind turbine equipment to be maintained in a second target window period and assigns maintenance persons to other levels wind turbine equipment to be maintained. [0073] If the maintenance operation at the current stage is completed, continue to perform step 303 to assign a maintenance person to other levels wind turbine equipment to be maintained until all maintenance operations are completed, that is, the maintenance of all wind turbine equipment is completed or the available prediction window periods are exhausted.

[0074] Illustratively, there are four first level wind turbine equipment to be maintained, i.e., A, B, C and D, the target window periods of A, B and C are the window period 1, and the target window period of D is the window period 2; there are two second level wind turbine equipment to be maintained, i.e., E and F, and the target window periods of E and F are both the window period 2; three maintenance persons have no work arrangement in the window period 1 and the window period 2. Firstly, the computer device assigns maintenance persons to A, B, C and D by firstly assigning three maintenance persons to perform the maintenance operation for the wind turbine equipment to be maintained A, B and C in the window period 1 respectively and updating the number of the available maintenance persons of the window period 1 to zero, and then assigning three maintenance persons to perform the maintenance operation for the wind turbine equipment to be maintained D, E and F in the window period 2 respectively and updating the number of the available maintenance persons of the window period 2 to zero.

[0075] In some embodiments of the present disclosure, different levels of prediction window periods are determined by dividing different levels of weather conditions for maintenance operations, and maintenance persons may adjust the target window period of the wind turbine equipment to be maintained according to actual situations, so as to ensure the efficiency of the maintenance operation and the utilization rate of the window period; the computer device performs assigning operations according to the maintenance priority of the wind turbine equipment to be maintained to ensure that the wind turbine equipment to be maintained with the highest maintenance priority can be maintained in time; the computer device assigns the maintenance operations according to the information of the maintenance persons and the target window period of the wind turbine equipment to be maintained, and updates the number of the available maintenance persons in each window period in real time, thereby improving the utilization rate of maintenance persons and the efficiency of the maintenance operation, and reducing time costs of the maintenance operation.

[0076] The computer device determines the prediction window period for each wind turbine equipment to be maintained according to the weather condition for the maintenance operation and the prediction weather information. However, the prediction window period may fail to satisfy the maintenance operation due to different statuses of the wind turbine equipment to be maintained and different requirements of the maintenance operation, so that the computer device needs to determine the target window period of each wind turbine equipment to be maintained according to the equipment maintenance information. [0077] In a possible implementation, on the basis of FIG. 3, the above step 303 includes step 303a to step 303c as shown in FIG. 5,.

[0078] In step 303a, the maintenance time length of the n ^th level wind turbine equipment to be maintained is acquired.

[0079] Different wind turbine equipment to be maintained has different working statuses and also require different maintenance operations. Therefore, in a possible implementation, maintenance time lengths corresponding to different maintenance operations are preset.

[0080] Optionally, the equipment maintenance information further includes a maintenance time length. Before determining the target window period of the wind turbine equipment to be maintained, the computer device firstly acquires the maintenance time length of each wind turbine equipment to be maintained.

[0081] In step 303b, the prediction window period with a window time length greater than or equal to the maintenance time length is determined as a candidate window period. [0082] The computer device compares the maintenance time length of each wind turbine equipment to be maintained with the window time length of the prediction window period and filters out a prediction window period with the window time length greater than or equal to the maintenance time length. The prediction window period is determined as the candidate window period.

[0083] In a possible implementation, the computer device firstly determines a first prediction window period with the window time length greater than or equal to the maintenance time length as the candidate window period by comparing the window time length of the first prediction window period with the maintenance time length. If the window time lengths of the first prediction window periods are all less than the maintenance time length, the computer device continues to filter the candidate window period from the next level prediction window periods.

[0084] Illustratively, there are the first prediction window period 1 and 2 and the second prediction window periods 3 and 4 corresponding to the wind turbine equipment to be maintained A in a time sequence. The window time length of the prediction window period 1 is 3 hours, the window time lengths of the prediction window periods 2 and 3 are 5 hours, the window time length of the prediction window period 4 is 4 hours. The maintenance time length of the wind turbine equipment to be maintained A is 4 hours. In the first prediction window period, since the time length of the prediction window period 2 is greater than the maintenance time length, such that the prediction window period 2 is determined as the target window period.

[0085] In step 303c, the target window period is determined from the candidate window period.

[0086] In a possible implementation, step 303c includes the following steps.

[0087] (1) If at least two candidate window periods are included, a latest candidate window period in the candidate window periods is acquired.

[0088] Optionally, when there is only one candidate window period, the candidate window period is determined as the target window period corresponding to the wind turbine equipment to be maintained; when there are at least two candidate window periods, the latest candidate window period in the candidate window periods is determined as the target window period for a first wind turbine equipment to be maintained and the candidate window period with a minimum power loss in the candidate window periods is determined as the target window period for the wind turbine equipment to be maintained with other maintenance priority.

[0089] When the maintenance persons perform the maintenance operation, it is required to turn off the wind turbine equipment. At this time, the wind turbines stop generating power, thereby causing certain power generation loss. In a possible implementation, in order to minimize the power generation loss caused by the maintenance operation as much as possible, the computer device firstly calculates the power loss of each wind turbine equipment to be maintained in each candidate window period before determining the target window period.

[0090] Optionally, as shown in FIG. 6, the computer device acquires wind turbine operation data and weather data corresponding to the candidate window period. The weather data includes wind direction and wind speed, and the wind turbine operation data includes real-time data and historical data. The historical data is operation data of the wind turbine in a same condition as the weather data of the candidate window period in a historical record, such as power and wind speed of the wind turbine . The computer device inputs the weather data and the wind turbine operation data in a power predicting algorithm to calculate power-generation power of the wind turbine in each candidate window period, thereby obtaining the predicted power loss. [0091] Illustratively, the computer device predicts the power-generation power of the wind turbine equipment to be maintained in the candidate window period every 15 minutes. The power predicting algorithm includes a plurality of machine learning algorithms, such as linear regression, a support vector machine, a regression tree and decision tree algorithm, boost and other algorithms with supervised learning. The power-generation power of the wind turbine is a calculation result after integration of a plurality of algorithms with the accuracy being more than 85%.

[0092] (2) If the window time length of the latest candidate window period is greater than the maintenance time length, the power loss of the n ^th level wind turbine equipment to be maintained in the latest candidate window period is determined.

[0093] For the first wind turbine equipment to be maintained, after acquiring its latest candidate window period, the computer device calculates the power loss of each time period in the latest candidate window period the computer device if the window time length of the latest candidate window period is greater than the maintenance time length. The computer device firstly acquires wind force prediction information in the latest candidate window period, wherein the wind force prediction information includes wind direction prediction information and wind speed prediction information. The wind force prediction information is input in a power generation amount predicting model corresponding to the first wind turbine equipment to be maintained, and a predicted power generation amount output by the power generation amount predicting model is determined as the power loss. The power generation amount predicting model is obtained by training with sample input and sample output, wherein the sample input is historical wind force information, and the sample output is a historical power generation amount of the n ^th level wind turbine equipment to be maintained.

[0094] (3) A window sub-period corresponding to the minimum power loss is determined as the target window period, wherein the window sub-period belongs to the latest candidate window period, and the window time length of the window sub-period is equal to the maintenance time length.

[0095] Illustratively, the latest candidate window period of the wind turbine equipment to be maintained A is 10:00:00 to 15:00:00, and the maintenance time length is 3 hours. Thus, the computer device calculates the power loss every 15 minutes from 10:00:00 to 15:00:00, and sums up the power loss of three consecutive hours, calculating out that the power loss within 10:30:00 to 13:30:00 is minimum, so as to determine that 10:30:00 to 13:30:00 is the target window period of the wind turbine equipment to be maintained A. [0096] In some embodiments of the present disclosure, the computer device firstly determines the target window period of the wind turbine equipment to be maintained with the highest maintenance priority, i.e., the latest candidate window period, and determines the time period with the minimum power loss in the target window period as the target window period, and then determines the target window period of the wind turbines device to be maintained with other priority according to the power loss of each candidate window period. Based on this, the computer device assigns maintenance persons to perform the maintenance operation, thereby reducing the maintenance cost and loss on the premise of ensuring the timeliness of the maintenance operation. [0097] Since the number of the wind turbine equipment to be maintained is usually greater than the number of the maintenance persons, the computer device is required to plan and arrange the maintenance operation reasonably. Referring to FIG. 7, it is a flowchart of arranging of maintenance operations by a computer.

[0098] In step 701, maintenance persons are assigned to the wind turbine equipment to be maintained. The computer device assigns the maintenance persons according to the priority of the wind turbine equipment to be maintained, so as to ensure prior maintenance of the wind turbine equipment to be maintained with the highest priority.

[0099] In step 702, whether the maintenance of all wind turbine equipment is completed or there is no available window period is judged. When there are maintenance persons completing the maintenance operation for one wind turbine equipment, the computer device needs to judge whether there are other wind turbine equipment to be maintained. If yes, whether there is an available window period is determined; when the maintenance of all wind turbine equipment is completed or there is no available prediction window period, perform step 703; otherwise, return to step 701, and continue to assign maintenance persons and maintenance time to other wind turbine equipment to be maintained according to the priority.

[00100] In step 703, the maintenance operation is completed.

[00101] FIG. 8 is a structural block diagram showing an apparatus for generating a maintenance plan of wind turbines according to an exemplary embodiment of the present disclosure. The apparatus may be disposed in the computer device as described in the above embodiments. As shown in FIG. 8, the apparatus includes:

[00102] a first determination module 801, configured to determine a prediction window period corresponding to wind turbine equipment to be maintained according to prediction weather information of locations of the wind turbine equipment to be maintained in a wind turbine maintenance period, wherein a predicted weather condition in the prediction window period conforms to a weather condition of a maintenance operation; [00103] a second determination module 802, configured to determine a target window period corresponding to each of the wind turbine equipment to be maintained from the prediction window period according to equipment maintenance information corresponding to each of the wind turbine equipment to be maintained; and

[00104] a generation module 803, configured to generate a maintenance schedule according to the target window period and information of maintenance persons, wherein the maintenance schedule is used to instruct a maintenance time period of each of the wind turbine equipment to be maintained the maintenance persons assigned to the wind turbine equipment to be maintained, and the maintenance time period belongs to the target window period.

[00105] Optionally, the equipment maintenance information includes maintenance priority. The second determination module 802 includes:

[00106] a first determination unit, configured to determine the target window period corresponding to each the wind turbine equipment to be maintained from the prediction window period according to the equipment maintenance information corresponding to each of the wind turbine equipment to be maintained, including:

[00107] a second determination unit, configured to determine the target window period of an n ^th level wind turbine equipment to be maintained in the wind turbine equipment to be maintained from the prediction window period, wherein the n ^th level wind turbine equipment to be maintained is the wind turbine equipment to be maintained with an n ^th maintenance priority, and n is an integer greater than or equal to 1 ; and [00108] a third determination unit, configured to determine the target window period of an (n+l) ^th level wind turbine equipment to be maintained in the wind turbine equipment to be maintained from the prediction window period, wherein the (n+l) ^th level wind turbine equipment to be maintained is the wind turbine equipment to be maintained with an (n+l) ^th maintenance priority, and the n ^th maintenance priority is higher than the (n+l) ^th maintenance priority.

[00109] Optionally, the equipment maintenance information further includes a maintenance time length. The second determination unit is further configured to:

[00110] acquire the maintenance time length for the n ^th level wind turbine equipment to be maintained;

[00111] determine the prediction window period with a window time length greater than or equal to the maintenance time length as a candidate window period; and [00112] determine the target window period from the candidate window period. [00113] Optionally, the second determination unit is further configured to:

[00114] acquire a latest candidate window period from the candidate window periods when there are at least two candidate window periods;

[00115] determine a power loss of the n ^th level wind turbine equipment to be maintained in the latest candidate window period if the window time length of the latest candidate window period is greater than the maintenance time length; and [00116] determine a window sub-period corresponding to the minimum power loss as the target window period, wherein the window sub -period belongs to the latest candidate window period, and the window time length of the window sub -period is equal to the maintenance time length.

[00117] Optionally, the second determination unit is further configured to:

[00118] acquire wind force prediction information in the latest candidate window period, wherein the wind force prediction information includes wind direction prediction information and wind speed prediction information;

[00119] input the wind force prediction information in a power generation amount predicting model corresponding to the n ^th level wind turbine equipment to be maintained, wherein the power generation amount predicting model is obtained by training with sample input and sample output, the sample input is historical wind force information, and the sample output is a historical power generation amount of the n ^th level wind turbine equipment to be maintained; and

[00120] determine a prediction power generation amount output by the power generation amount predicting model as the power loss. [00121] Optionally, the information of the maintenance persons includes the number of the maintenance persons. The generation module 803 includes:

[00122] an acquisition unit, configured to acquire a number of available maintenance persons in the target window period;

[00123] a first assignment unit, configured to assign the maintenance persons to the n ^th level wind turbine equipment to be maintained according to a number of the n ^th level wind turbine equipment to be maintained and updating the number of the available maintenance persons in the target window period if the number of the available maintenance persons is greater than the number of the n ^th level wind turbine equipment to be maintained; and [00124] a second assignment unit, configured to assign the maintenance persons to the n ^th level wind turbine equipment to be maintained according to the number of the available maintenance persons and updating the number of the available maintenance persons in the target window period if the number of the available maintenance persons is less than the number of the n ^th level wind turbine equipment to be maintained.

[00125] Optionally, the first determination module 801 includes:

[00126] a fourth determination unit, configured to determine a j ^th type prediction window period according to the prediction weather information and an i ^th type weather condition for maintenance operations, wherein the prediction weather information within the j ^th type prediction window period is in conformity with the i ^th type weather condition for maintenance operations, and both j and i are integers greater than or equal to 1; and [00127] a fifth determination unit, configured to determine a (j+l) ^th type prediction window period according to the prediction weather information and an (i+l) ^th type weather condition for maintenance operations if a number of the j ^th type prediction window periods is less than a number threshold, and/or, the window time length of the j ^th type prediction window period is less than a time length threshold, wherein the prediction weather information within the j ^th type prediction window period is in conformity with the (i+l) ^th type weather condition for the maintenance operations, and the i ^th type weather condition for maintenance operations are superior to than the (i+l) ^th type weather condition for maintenance operations.

[00128] Referring to FIG. 9, it is a structural schematic diagram showing a computer device according to an exemplary embodiment of the present disclosure. Specifically, the computer device 900 includes a central processing unit (CPU) 901, a system memory 904 including a random access memory (RAM) 902 and a read-only memory (ROM) 903, and a system bus 905 that connects the system memory 904 and the CPU 901. The computer device 900 further includes a basic input/output (I/O) system 906 that facilitates transmission of information between different components in the computer device, and a mass storage device 907 for storing an operating system 913, an application 914, and other program modules 915.

[00129] The basic input/output system 906 includes a display 908 for displaying information and an input device 909 such as a mouse or keyboard for user input of information. The display 908 and the input device 909 are both connected to the CPU 901 via an input/output controller 910 connected to the system bus 905. The basic I/O system 906 may further include an input/output controller 910 for receiving and processing input from a plurality of other devices such as a keyboard, mouse or electronic stylus. Similarly, the input/output controller 910 further provides output to a display screen, printer, or other types of output devices.

[00130] The mass storage device 907 is connected to the CPU 901 by a mass storage controller (not shown) connected to the system bus 905. The mass storage device 907 and its associated computer-readable storage medium provide non-volatile storage for the computer device 900. That is, the mass storage device 907 may include a computer-readable storage medium (not shown) such as a hard disk or compact disc read-only memory (CD-ROM) drive.

[00131] Without loss of generality, the computer-readable storage medium may include a computer storage medium and a communication medium. The computer storage medium includes volatile, nonvolatile, removable and non-removable mediums implemented by any method or technology for storing information such as computer-readable storage instructions, data structures, program modules or other data. The computer storage medium includes an RAM, an ROM, an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), a flash memory or other solid-state memory technology, a CD-ROM, a digital versatile disc (DVD) or other optical storage, a tape cassette, a magnetic tape, magnetic disk storage or other magnetic storage devices. Of course, persons skilled in the art may appreciate that the computer storage medium is not limited to the above ones. The system memory 904 and the mass storage device 907 described above may be collectively referred to as memories.

[00132] The memory is stored with one or more programs configured to be executed by one or more CPUs 901. The one or more programs include instructions for implementing the method for generating the maintenance plan of the wind turbines described above, and the CPU 901 executes the one or more programs to implement the method for generating the maintenance plan of the wind turbines provided by each embodiment of the methods described above.

[00133] According to various embodiments of the present disclosure, the computer device 900 may also be operated by being connected via a network such as the Internet to a remote network computer device. That is, the computer device 900 may be connected to a network 912 by a network interface unit 911 connected on the system bus 905, or that is, the computer device 900 may also be connected to other types of networks or remote computer device systems (not shown) by using the network interface unit 911.

[00134] The memory further includes one or more programs stored therein. The one or more programs include steps performed by the computer device in the method provided by the embodiments of the present disclosure.

[00135] Embodiments of the present disclosure further provide a computer-readable storage medium storing at least one instruction therein, and the at least one instruction is loaded and executed by a processor to implement the method for generating the maintenance plan of the wind turbines in each embodiment of the present disclosure as described above. [00136] Embodiments of the present disclosure further provide a computer program product storing at least one instruction therein, and the at least one instruction is loaded and executed by a processor to implement the method for generating the maintenance plan of the wind turbines in each embodiment of the present disclosure as described above. [00137] Persons skilled in the art may realize that functions described in the above one or more examples of the present disclosure may be implemented by hardware, software, firmware, or any combination thereof. When being implemented by software, these functions may be stored in a computer-readable storage medium or may be transmitted as one or more instructions or codes on the computer-readable storage medium. The computer-readable storage medium includes a computer storage medium and a communication medium. The communication medium includes any medium that facilitates transmitting computer programs from one place to another. The storage medium may be any available medium accessible by a general-purpose or dedicated computer.

[00138] The above descriptions are only optional embodiments of the present disclosure, and are not intended to limit the present disclosure. Any modifications, equivalent replacements, improvements, and the like made within the spirit and principles of the present disclosure should be included within the scope of protection of the present disclosure.