FIELD

The present technology is directed to industrial machine tools that include sensors for reporting exceedances. More specifically, it is directed to stationary and rotating tools that have temperature, force, acoustic emission and vibration sensors which communicate sensor data wirelessly to a data analysis and storage system.

BACKGROUND

Industrial machine tool wear can lead to significant downtime in a machine shop. Hence inspecting these tools is essential to normal machine shop operation. Visual inspection can only identify problems when they are well advanced. A monitoring and predictive maintenance solution could not only guarantee the reliability of industrial machine tools but also reduce the maintenance cost during their lifecycle management. However, the implementation of such a system for predictive maintenance is commonly restricted by insufficient measurement data. More recently, sensors have been used to provide this data. Most sensor systems are not integrated into the tool, however, in some cases, they are. For example, United States Patent Application Publication No. 20210032936 discloses systems, methods, and apparatuses for obtaining sensor data from sensors incorporated into a drill bit during a drilling operation to form a wellbore. The obtained sensor data may be used to control an aspect of the drilling operation. The sensors may be incorporated into drill bit cutters of a drill bit, a drill bit body of a drill bit, or both. Example sensors include acoustic sensors, pressure sensor, vibration sensor, accelerometers, gyroscopic sensors, magnetometer sensors, and temperature sensors.

United States Patent Application Publication No. 20200174464 discloses systems and methods for detecting operating characteristics of an industrial machine. The detecting can include generating one or more image data sets using raw data captured by one or more data capture devices and identifying one or more values corresponding to a portion of the industrial machine within a point of interest represented by the one or more image data sets. The one or more values can be compared to corresponding predicted values and a variance data set can be generated based on the comparison of the one or more values and the corresponding predicted values. An operating characteristic of the industrial machine can be identified based on the variance data and data indicating a detection of the operating characteristic can be generated. This uses a separate data capture device and is focused on the health of the industrial machine and not the industrial machine tool.

United States Patent Application Publication No. 20200174463 discloses an industrial machine predictive maintenance system may include an industrial machine data analysis facility that generates streams of industrial machine health monitoring data by applying machine learning to data representative of conditions of portions of industrial machines received via a data collection network. The system can utilize a distributed ledger to track one or more transactions executed in an automated data marketplace for industrial Internet of Things data. The distributed ledger distributes storage for data indicative of the one or more transactions across one or more devices, wherein the data indicative of the one or more transactions corresponds to transaction records. A transaction record stored in the distributed ledger represents one or more of sensor data, the condition of an industrial machine, orders or the requests for service and parts, an issue associated with the condition of a machine, or a hash used to identify the transaction record. This is focused on the industrial machine health and not the health of the industrial machine tools.

United States Patent Application Publication No. 20200166923 discloses a system and method for causing a mobile data collector to perform a maintenance action on an industrial machine. The mobile data collector can be deployed for detecting and monitoring vibration activity of a portion of an industrial machine. The mobile data collector can be controlled to approach a location of the industrial machine such that a vibration sensor of the mobile data collector can record a measurement of the vibration activity, which can be transmitted as vibration data to a server over a network. The server can determine a seventy of the vibration activity and predict a maintenance action to perform. A signal indicative of the maintenance action can be transmitted to the mobile data collector to cause the mobile data collector to perform the maintenance action. A record of the predicted maintenance action can be stored within a ledger associated with the industrial machine. This relies on a separate data collector, which is mobile.

United States Patent Application Publication No. 20200166922 discloses an industrial machine predictive maintenance system that may include an industrial machine data analysis facility that generates streams of industrial machine health monitoring data by applying machine learning to data representative of conditions of portions of industrial machines received via a data collection network. The system may include an industrial machine predictive maintenance facility that produces industrial machine service recommendations responsive to the health monitoring data by applying machine fault detection and classification algorithms thereto. The system detects an operating characteristic of an industrial machine, such as vibration, using one or more sensors of a mobile data collector and identify, as a condition of the industrial machine, a characteristic for the industrial machine within the knowledge base. The system can determine seventy of the condition and predict and execute a maintenance action to perform against the industrial machine based on the severity of the condition. This is focused on the machine and not the machine tools.

United States Patent Application Publication No. 20200159207 discloses a system and method for causing a mobile data collector to perform a maintenance action on an industrial machine. The mobile data collector can be deployed for detecting and monitoring vibration activity of a portion of an industrial machine. The mobile data collector can be controlled to approach a location of the industrial machine such that a vibration sensor of the mobile data collector can record a measurement of the vibration activity. The measurement of the vibration activity can be transmitted as vibration data to a server over a network, which can determine a seventy of the vibration activity and predict a maintenance action to perform based on the severity of the vibration activity. A signal indicative of the maintenance action can be transmitted to the mobile data collector to cause the mobile data collector to perform the maintenance action. This relies on a separate data collector, which is mobile and is focused on the industrial machine health and not the industrial machine tool health. United States Patent Application Publication No. 20200159206 discloses that an industrial machine predictive maintenance system may collect data indicative of operating characteristics of an industrial machine. The system can include a computerized maintenance management system (CMMS) that produces orders and/or requests for service and parts responsive to industrial machine service recommendations, including a mobile data collector that indicates the industrial machine service recommendation or the produced orders or requests for service and parts to a worker who uses the mobile data collector. A self-organizing data collector can cause a new record to be stored in a ledger, the new record indicating at least one of the industrial machine service recommendation or the produced orders or requests for service and parts. The ledger can use a blockchain structure to track records of transactions for each of the orders and requests for service and parts, wherein each record is stored as a block in the blockchain structure. This is focused on the industrial machine health and not the health of the industrial machine tool.

United States Patent Application Publication No. 20200150645 discloses that an industrial machine predictive maintenance method and system may include an industrial machine data analysis facility that collects data representative of conditions of portions of industrial machines received via a data collection network. Vibration data representative of a vibration of at least a portion of an industrial machine can be received from a wearable device including at least one vibration sensor used to capture the vibration data. A frequency of the captured vibration can be determined by processing the captured vibration data and, based on the frequency, a segment of a multi-segment vibration frequency spectra that bounds the captured vibration can be determined. A seventy unit for the captured vibration can be calculated based on the determined segment a signal in a predictive maintenance circuit for executing a maintenance action on at least the portion of the industrial machine based on the seventy unit can be generated. While a wearable device is disclosed, there is no integration of the sensors into the industrial machine tools.

United States Patent Application Publication No. 20200150644 discloses an industrial machine predictive maintenance system and method for determining a normalized severity measure of an impact of vibration of a component of an industrial machine. Vibration data can be captured from at least one vibration sensor disposed to capture vibration of a portion of an industrial machine and a frequency, a peak amplitude and gravitational force of the captured vibration can be determined. A frequency rangespecific segment of a multi-segment vibration frequency spectra that bounds the captured vibration based on the determined frequency can be determined, and a vibration severity level for the captured vibration data can be determined based on the determined segment and at least one of the peak amplitude and the gravitational force. A signal in a predictive maintenance circuit for executing a maintenance action on the portion of the industrial machine based on the vibration severity level can be generated. There is no integration of the sensors into the industrial machine tools.

United States Patent Application Publication No. 20200150643 discloses that an industrial machine predictive maintenance system may include an industrial machine data analysis facility that generates streams of industrial machine health monitoring data by applying machine learning to data representative of conditions of portions of industrial machines received via a data collection network. The system may include an industrial machine predictive maintenance facility that produces industrial machine service recommendations responsive to the health monitoring data by applying machine fault detection and classification algorithms thereto. The system may perform a method of predicting a service event from vibration data captured data from at least one vibration sensor disposed to capture vibration of a portion of an industrial machine. A signal in a predictive maintenance circuit for executing a maintenance action on the portion of the industrial machine can be generated based on a severity unit calculated for the captured vibration. This is focused on the industrial machine health and not the health of the industrial machine tool health.

United States Patent Application Publication No. 20200133257 discloses methods and systems for detecting operating characteristics of an industrial machine in which the systems include at least one data capture device configured to capture raw data of a point of interest of the industrial machine and a computer vision system. The computer vision system can generate one or more image data sets using the raw data captured, identify one or more values corresponding to a portion of the industrial machine within the point of interest represented by the one or more image data sets, compare the one or more values to corresponding predicted values, generate a variance data set based on the comparison of the one or more values and the corresponding predicted values, detect an operating characteristic of the industrial machine based on the variance data, and generate data indicating the detection of the operating characteristic. This is focused on the industrial machine health and not the health of the industrial machine tool health.

United States Patent Application Publication No. 20200133256 discloses that industrial machine predictive maintenance system may include an industrial machine data analysis facility that generates streams of industrial machine health monitoring data by applying machine learning to data representative of conditions of portions of industrial machines received via a data collection network. The system may perform a method of sampling a signal at a streaming sample rate to produce a plurality of samples of the signal. Portions of the plurality of samples can be allocated to first and second signal analysis circuits based on signal analysis sampling rates less than the streaming sample rate, and the samples and the outputs of the signal analysis circuits can be stored. The system can include a sensor detecting a condition of an industrial machine to output a signal, which can be sampled at a streaming sample rate that is at least twice a dominant frequency of the signal. This is focused on the industrial machine health and not the health of the industrial machine tool health.

United States Patent Application Publication No. 20200133255 discloses that an industrial machine predictive maintenance system may include an industrial machine data analysis facility that generates streams of industrial machine health monitoring data by applying machine learning to data representative of conditions of portions of industrial machines received via a data collection network. The system may include an industrial machine predictive maintenance facility that produces industrial machine service recommendations responsive to the health monitoring data by applying machine fault detection and classification algorithms thereto. The system may predict a service event from vibration data from at least one vibration sensor disposed to capture vibration of a portion of an industrial machine signal a predictive maintenance server to execute a corresponding maintenance action on the portion of the industrial machine. This is focused on the industrial machine health and not the health of the industrial machine tool health.

United States Patent Application Publication No. 20200133254 discloses that an industrial machine predictive maintenance system may include an industrial machine data analysis facility that generates streams of industrial machine health monitoring data by applying machine learning to data representative of conditions of portions of industrial machines received via a data collection network. The system may perform a method of image capture of a portion of an industrial machine in which an image capture template is provided and aligned via augmented reality with a live image in order to update a procedure for performing a service that implements a predicted maintenance action on an industrial machine. The system may perform a method of machine learning-based part recognition in which a captured image is analyzed and used to adapt a target part template, image analysis rules, or part recognition. The system may detect operating characteristics of an industrial machine via a machine learning aspect trained based on image data sets. This is focused on the industrial machine health and not the health of the industrial machine tool health.

United States Patent Application Publication No. 20200117180 discloses methods and systems for noise detection and removal in a mixer/agitator. An example monitoring system for data collection in an industrial environment may include a data collector coupled to a plurality of input channels connected to data collection points coupled to at least one of a mixer or an agitator and a data storage to store a plurality of stored system response patterns associated with noise detection during operation. The system may further include a data acquisition circuit to interpret a plurality of detection corresponding to the input channels and a data analysis circuit to remove a background noise from the detection values, analyze the collected data to determine a measured noise pattern; and compare the measured noise pattern to the stored system response patterns to determine an identified noise pattern. This does not integrate the sensors into the industrial machine tools.

United States Patent Application Publication No. 20200110398 discloses a system for changing a sensed parameter group for oil and gas production equipment includes a data collector communicatively coupled to a plurality of input sensors, each of the plurality of input sensors operatively coupled to a component comprising equipment for an oil and gas production environment; a controller, comprising: a data acquisition circuit structured to interpret a plurality of detection values corresponding to a sensed parameter group, wherein the sensed parameter group comprises at least a portion of the plurality of input sensors; a pattern recognition circuit structured to determine a recognized pattern value in response to the plurality of detection values; and a sensor learning circuit structured to update the sensed parameter group in response to the recognized pattern value. This does not integrate the sensors into the industrial machine tools.

United States Patent Application Publication No. 20200110397 discloses methods and systems for detection in an industrial internet of things data collection environment with intelligent data collection and equipment package adjustment for a production line. An example system includes a data collector communicatively coupled to a plurality of input channels connected to data collection points operatively coupled to at least one piece of equipment of an equipment package of the production environment and a data acquisition circuit structured to interpret a plurality of detection values from the plurality of input channels. A data analysis circuit utilizes an expert system diagnostic tool to identify an off-nominal process state in response to the plurality of detection values and a response circuit adjusts an equipment package parameter in response to the off-nominal process state. This does not integrate the sensors into the industrial machine tools.

United States Patent Application Publication No. 20200103894 discloses an industrial machine predictive maintenance system may include an industrial machine data analysis facility that generates streams of industrial machine health monitoring data by applying machine learning to data representative of conditions of portions of industrial machines received via a data collection network. The system may include an industrial machine predictive maintenance facility that produces industrial machine service recommendations responsive to the health monitoring data by applying machine fault detection and classification algorithms thereto. A computerized maintenance management system (CMMS) that produces orders and/or requests for service and parts responsive to the industrial machine service recommendations can be included. The system may include a service and delivery coordination facility that processes information regarding services performed on industrial machines responsive to the orders and/or requests for service and parts, thereby validating the services performed while producing a ledger of service activity and results for individual industrial machines. This is focused on the industrial machine health and not the health of the industrial machine tool health.

United States Patent Application Publication No. 20200103890 discloses methods and systems for detection in an industrial Internet of Things data collection and production environment using a distributed ledger. An example monitoring system for data collection in a production environment may include a data collector communicatively coupled to a plurality of input channels, each input channel operatively coupled to at least one piece of equipment of the production environment. The system may further include a distributed ledger to store the detection values and a data acquisition circuit to interpret at least a portion of the detection values. The system may further include a data analysis circuit to identify a status corresponding to the production environment in response to the portion of the detection values and a response circuit to adjust a parameter of the production environment in response to the status. This does not integrate the sensors into the industrial machine tools.

United States Patent Application Publication No. 20190095781 discloses techniques, including systems and methods for monitoring a rotating equipment. A sensor that is in proximity of the rotating equipment senses vibrations of the rotating equipment. The sensor generates a digital signal corresponding to the vibrations of the rotating equipment and transmits the digital signal over a communication network. A server receives the digital signal and pre-processes the digital signal using ensemble empirical mean decomposition (EEMD) technique. The server processes the digital signal using wavelet neural network (WNN) to detect faults in the rotating equipment. Further, the server processes the digital signal using the wavelet neural network to predict remaining useful life (RUL) of the rotating equipment. This does not integrate the sensors into the industrial machine tools.

United States Patent Application Publication No. 20200225655 discloses a method for receiving, by the processing system, reporting packets from one or more respective sensors of the plurality of sensors. Each reporting packet is sent from a respective sensor and indicates sensor data captured by the respective sensor; performing, by the processing system, one or more edge operations on one or more instances of sensor data received in the reporting packets. Generating one or more sensor kit packets based on the instances of sensor data. Each sensor kit packet includes at least one instance of sensor data. Outputting the sensor kit packets to the data handling platform. Receiving the sensor kit packets from the edge device. Generating the digital twin of said industrial setting including a digital replica of at least one industrial component of said industrial setting and being at least partially based on the sensor kit packets. This system is overly reliant on the internet and as such, would not be terribly reliable.

What are needed are industrial machine tools that have sensors integrated into them. It would be preferable if one or more of force, vibration, temperature and acoustic emission sensors. It would be preferable to include a temperature sensor with one or more of the other sensors in the tool. It would be preferable if a system was provided that included a computing unit. It would be preferable if the system allowed for monitoring of an industrial machine tool under normal operating conditions. It would be further preferable if the sensor data were communicated wirelessly to the computing unit. It would be further preferable if the computing unit included software configured to analyze the sensor data, archive the sensor data, archive the analyzed data and develop predictive models using the analyzed data. It would be still further preferable if the software was further configured to communicate error messages back to the industrial machine when exceedances were sensed.

SUMMARY

The present technologies are industrial machine tools that have sensors integrated into them. The sensors are one or more of force, vibration, temperature and acoustic emission sensors. A temperature sensor is included with one or more of the other sensors in the tool. A system is provided that includes a computing unit. The system allows for monitoring of an industrial machine tool under normal operating conditions. The sensor data are communicated wirelessly to the computing unit. The computing unit includes software configured to analyze the sensor data, archive the sensor data, archive the analyzed data and develop predictive models using the analyzed data. The software is further configured to communicate error messages back to the industrial machine when exceedances are sensed. Original Equipment Manufacturer (OEM) industrial machine data is also communicated to the software, including but not limited to g-code, m-code, spindle torque, and spindle current draw. OEM industrial machine data is then married to the sensor data to develop a more complete picture of the manufacturing process.

In one embodiment, a system is provided for use in machining parts, the system comprising: an industrial machine which includes a control panel, a computing unit which includes a signal reception and integration module and a data analysis module, wherein the signal reception and integration module is configured to receive a temperature data set and a force data set and the data analysis module is configured to process the temperature data set and adjust the force data set for thermal drift; and a tool, the tool releasably mounted in the industrial machine, the tool including at least one sensor and a printed circuit board (PCB) which includes a multi-sensor fusion and transmission module which is in electronic communication with the sensor and the wireless radio of the computing unit.

In the system the data analysis module may be further configured to model tool wear.

In the system, the tool may further comprise an acoustic emission sensor in electronic communication with the PCB.

In the system, the tool may be a stationary tool.

In the system, the tool may be a rotating tool.

In the system, the rotating tool may further comprise a vibration sensor.

In another embodiment, a system is provided for monitoring wear or damage to a tool for use in an industrial machine, the system comprising: the tool, which is mounted in the industrial machine and is configured to generate and transmit temperature data and force data; and a computing unit wherein the computing unit is configured to receive the temperature data and the force data, determine changes in the temperature data over time, and adjust the force data to compensate for thermal drift. The system may be configured to operate autonomously.

In the system, the tool may be further configured to generate and send acoustic data to the computing unit and the computing unit is further configured to adjust the acoustic data to compensate for thermal drift.

In the system, the tool may be a rotating tool and may be further configured to generate and send vibration data to the computing unit and the computing unit may be further configured to adjust the vibration data to compensate for thermal drift.

The system may be configured to stop the industrial machine when an exceedance is reported.

In another embodiment a system is provided for developing a predictive model of wear or damage to a tool for use in an industrial machine, the system comprising: the tool, which is configured to generate and transmit temperature data and force data; and a computing unit which is in electronic or wireless communication with the tool and which includes a memory and a processor, the processor under control of the memory, wherein the memory is configured to receive the temperature data and the force data, determine changes in both the temperature data and the force data over time, statistically analyze the changes in relation to time to provide a set of time-based features, apply the timebased features as input values to a selected transformation, and develop a predictive model of health and remaining useful life of the tool using the selected transformation.

In the system, the tool may be further configured to generate and send acoustic data to the computing unit.

In the system, the tool may be a rotating tool.

In the system, the rotating tool may be further configured to generate and send vibration data to the computing unit. In yet another embodiment, a system is provided for predictive modeling of wear or damage to a tool of an industrial machine, the system comprising: the tool, which includes at least one sensor, which is positioned and configured to generate and transmit temperature data or force data; and a computing unit which is in wireless communication with the tool, and which includes a memory and a processor, the processor under control of the memory, wherein the memory retains a predictive model of health and remaining useful life of the tool and is configured to receive the temperature and force data, determine changes in the temperature and force data over time, statistically analyze the changes in relation to the predictive model of health and remaining useful life of the tool and provide a prediction of health and remaining useful life of the tool.

In the system, the tool may further comprise a vibration sensor, the vibration sensor configured to generate and send vibration data to the computing unit.

In the system, the tool may be a rotating tool and may further comprise an acoustic emissions sensor, the acoustic emissions sensor configured to generate and send acoustic emission data to the computing unit.

In yet another embodiment, a method is provided for developing a predictive model of wear or damage for a tool of an industrial machine, the method comprising: selecting a system comprising the tool, which includes at least one sensor, the industrial machine, and a computing unit which is in wireless communication with the sensor and which includes a memory and a processor, the processor under control of the memory; the sensor generating and transmitting temperature data and force data to the computing unit; the computing unit analyzing, compiling and storing the temperature data and the force data as a data set; the computing unit determining changes in the data set over time, statistically analyzing the changes in relation to time to provide a set of time-based features, applying the time-based features as input values to a selected transformation, and developing a predictive model of health and remaining useful life of the tool using the selected transformation. In the method, a vibration sensor may be generating and sending vibration data to the computing unit.

In the method, an acoustic emissions sensor may be generating and sending acoustic data to the computing unit.

In the method, the computing unit may be housed in the industrial machine.

In yet another embodiment, a method of predictive modeling of wear or damage to a tool of an industrial machine is provided, the method comprising: selecting the industrial machine with the tool, the tool including at least one sensor which is positioned and configured to generate and transmit temperature data and force data; selecting a computing unit which is in electronic or wireless communication with the sensor, and which includes a memory and a processor, the processor under control of the memory, wherein the memory retains a predictive model of health and remaining useful life of the tool and is configured to receive the temperature and force data; determining changes in the temperature and force data over time; statistically analyzing the changes in relation to the predictive model of health and remaining useful life of the tool; and providing a prediction of health and remaining useful life of the tool.

The method may be conducted autonomously.

In the method, the computing unit may be integral with the industrial machine.

FIGURES

Figure 1 is a perspective view of an industrial machine with a smart tool.

Figure 2 is a schematic of the printed circuit boards for the smart tool monitoring system.

DESCRIPTION

Techniques operating according to the principles described herein may be implemented in any suitable manner. The processing and decision blocks of the flow charts above represent steps and acts that may be included in algorithms and/or circuitry that carry out these various processes. Unless otherwise indicated herein, the particular sequence of steps and/or acts described in each flow chart is merely illustrative of the algorithms that may be implemented and can be varied in implementations and embodiments of the principles described herein.

The acts performed as part of a method may be ordered in any suitable way. Accordingly, embodiments may be constructed in which acts are performed in an order different than illustrated, which may include performing some acts simultaneously, even though shown as sequential acts in illustrative embodiments.

Except as otherwise expressly provided, the following rules of interpretation apply to this specification (written description and claims): (a) all words used herein shall be construed to be of such gender or number (singular or plural) as the circumstances require; (b) the singular terms "a", "an", and "the", as used in the specification and the appended claims include plural references unless the context clearly dictates otherwise; (c) the antecedent term "about" applied to a recited range or value denotes an approximation within the deviation in the range or value known or expected in the art from the measurements method; (d) the words "herein", "hereby", "hereof", "hereto", "hereinbefore", and "hereinafter", and words of similar import, refer to this specification in its entirety and not to any particular paragraph, claim or other subdivision, unless otherwise specified; (e) descriptive headings are for convenience only and shall not control or affect the meaning or construction of any part of the specification; and (f) "or" and "any" are not exclusive and "include" and "including" are not limiting. Further, the terms "comprising," "having," "including," and "containing" are to be construed as open-ended terms (i.e., meaning "including, but not limited to,") unless otherwise noted.

Recitation of ranges of values herein are merely intended to serve as a shorthand method of referring individually to each separate value falling within the range, unless otherwise indicated herein, and each separate value is incorporated into the specification as if it were individually recited herein. Where a specific range of values is provided, it is understood that each intervening value, to the tenth of the unit of the lower limit unless the context clearly dictates otherwise, between the upper and lower limit of that range and any other stated or intervening value in that stated range, is included therein. All smaller sub ranges are also included. The upper and lower limits of these smaller ranges are also included therein, subject to any specifically excluded limit in the stated range.

Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the relevant art. Although any methods and materials similar or equivalent to those described herein can also be used, the acceptable methods and materials are now described.

DEFINITIONS

Thin-film deposition and thin-film coating - in the context of the present technology th infilm deposition or thin-film coating may be three-dimensional printing.

Non-interfering, dynamic monitoring - in the context of the present technology, noninterfering, dynamic monitoring includes monitoring of the tool with sensors that can monitor continuously but may report continuously or periodically. The industrial machine may operate under normal operating conditions. This includes advanced sensing.

Autonomous, non-interfering dynamic monitoring - in the context of the present technology, autonomous, non-interfering dynamic monitoring is effected by sensors and a printed circuit board that are integrated into the tool and operate without the assistance of a machine operator.

Computing unit - in the context of the present technology, a computing unit includes at least one processor, and computer-readable storage media. A computing unit may be, for example, a desktop or laptop personal computer, a personal digital assistant (PDA), a smart mobile phone, a server, a virtual graphics processing unit or any other suitable computing unit. A network adapter may be any suitable hardware and/or software to enable the computing unit to communicate wired and/or wirelessly with any other suitable computing unit over any suitable computing network. The computing network may include wireless access points, switches, routers, gateways, and/or other networking equipment as well as any suitable wired and/or wireless communication medium or media for exchanging data between two or more computers, including the Internet. Computer- readable media may be adapted to store data to be processed and/or instructions to be executed by processor. The processor enables processing of data and execution of instructions. The data and instructions may be stored on the computer-readable storage media.

A computing unit may additionally have one or more components and peripherals, including input and output devices. Examples of output devices that can be used to provide a user interface include printers or display screens for visual presentation of output and speakers or other sound generating devices for audible presentation of output. Examples of input devices that can be used for a user interface include keyboards, and pointing devices, such as mice, touch pads, and digitizing tablets.

Communication network - in the context of the present technology a communication network includes but is not limited to a wireless fidelity (Wi-Fi [IEEE 802.11 ]) network, a light fidelity (Li-Fi) network, a satellite network, the internet, a cellular data network, a local area network (LAN), Bluetooth®, a Bluetooth mesh networking, a wireless local area network (WLAN), or any combination thereof. The network adapter of the computing unit communicates via the communication network.

DETAILED DESCRIPTION

By using online monitoring (autonomous non-interfering dynamic monitoring) of tools under normal operating conditions with sensors that are integrated into the tools, a system was developed that can provide reliable condition assessment, remaining useful life prediction as well as an optimized schedule for industrial machine tool maintenance. The sensing signals were collected from the real-time monitoring of the tool with at least two sensors integrated into the tool. A condition indicator was created to assess tool degeneration and/or exceedances from the acquired signals.

The tools may include machine cutting tools, holding tools, and work holding tools and may be stationary or rotating.

As shown in Figure 1 , an industrial machine, generally referred to as 10 includes a control panel 12 and a smart tool 14 which is releasably retained in the industrial machine. The smart tool 14 may be a cutting tool, a rotating tool, a stationary tool, an oscillating tool and the like. The industrial machine may be a computer numerical controlled (CNC) machine. A computing unit 16 is located outside the industrial machine, near the control panel 12. The computing unit 16 includes a wireless radio 18, a processor 20 and a memory 22 to receive sensor data, to analyze and monitor sensor data, to record sensor data and to communicate exceedances to the control panel 12. The computing unit 16 may be in wired communication with the control panel 12. The processor 20 and the memory 22 are collectively the data analysis module 29.

As shown in Figure 2, the smart tool 14 includes a PCB 24 with a multi-sensor fusion and transmission module 27, which includes a Bluetooth transmitter 26 to send data to the computing unit 16 via the signal reception and integration module 18 (wireless radio 18) of the computing unit 16. The data are from a temperature sensor 28 and at least one other sensor 30. The temperature sensor 28 is preferably a K-type thermocouple. Sensors contemplated include, but are not limited to accelerometers, acoustic emission sensors, vibration sensors, force sensors, weight sensors, load sensors, strain sensors and gyroscopes. The sensors may be Microelectromechanical (MEMS) systems. In an alternative embodiment the sensors may be thin-film resistance-based sensors. The smart tool 14 includes terminals 32 for retaining a battery 34 and the PCB 24. In another embodiment, the battery 34 may be supplemented or replaced with a method of wireless power transfer, including, but not limited to RF wireless power transfer. The wireless connection between the signal reception and integration module 18 and the smart tool PCB 24, and the wired connection between the smart tool PCB 24 and both the temperature sensor 28 and the at least one other sensor 30 allows for continuous communication of sensor data to the signal reception and integration module 18 and then to the computing unit 16. This allows the data analysis module 29 to determine and monitor any thermal drift of the other sensors 30 operating parameters. The data analysis module 29 then communicates instructions via the wireless radio 18 to the control panel 12 thereby increasing overall accuracy and precision of the machining process. In an alternative embodiment the connection between the PCB 24 and the computing unit 16 is a wired connection.

In one embodiment, an acoustic emission sensor 36 is directly electronically connected to the multi-sensor fusion and transmission module 27 of the PCB 24. Data from the temperature sensor 28 in the stationary tool 14 are analyzed by the computing unit 16 and the data from another sensor 30 (accelerometers, acoustic emission sensors, vibration sensors, force sensors, weight sensors, load sensors, strain sensors and gyroscopes) is corrected for thermal drift. Data collection and analysis is in real-time.

Data from the temperature sensor 28 in the rotating tool 14 is analyzed by the computing unit 16 and the data from another sensor 30 (accelerometers, acoustic emission sensors, vibration sensors, weight sensors, force sensors, load sensors, strain sensors and gyroscopes) is corrected for thermal drift. Data collection and analysis is in real-time. In one embodiment, the rotating tool 14 includes a vibration sensor.

The computing unit’s 16 data analysis module 29 includes a thermal drift compensation algorithm which reads the input temperature from the temperature sensor 28 and extracts the actual temperature with respect to a reference temperature, therefore indicating a calculated change in the processing temperature. Assuming there is a temperature change, the algorithm will compensate for thermal drift for each sensor 30 based on the calculated temperature change, thereby providing more accurate results.

The computing unit’s 16 data analysis module 29 includes a signal processing algorithm which reads the extracted signal produced by the tool, and, via brute force analysis, determines if any significant exceedance has occurred finally stopping the machine tool. Excessive exceedances may include excessive acoustic emissions, excessive temperature, excessive force, or excessive vibration. Excessive thresholds may be determined by those constraints of the machine system, such as the cutting tool material. Some cutting tool materials may only operate between 0 - 500 degrees Celsius before serious degradation, with this known, the temperature sensor may alarm if processing occurs beyond this threshold.

The computing unit’s 16 data analysis module 29 includes a machine learning algorithm which reads the extracted signal produced by the tool, compares the extracted signal with that which closely relates to one pre-determined in a signal database. At this point, the machine learning algorithm may decide the condition of the tool based on the signal database. With the condition of the tool known, the process may begin over in closed- loop fashion. In order to train the machine learning algorithm, controlled runs were conducted, measurements of wear made, and the data were tabulated and analyzed. Based on the signal data acquired by the signal reception and integration module, the data analysis module builds a model based on controlled machine trails to make predictions or decisions about current cutting conditions and tool wear levels autonomously or without being explicitly programmed to do so. The system can autonomously shut the industrial machine down if the data indicates a serious exceedance.

The computing unit’s 16 data analysis module 29 also includes a self-learning algorithm. This algorithm expands on the learned database, by automatically expanding its learned baseline to include other tool condition events, such as new, semi-worn, or fully worn tool condition events.

Online monitoring (non-interfering dynamic monitoring) can provide a continuous update of the monitored health condition of the tool during its operation. In order to do so, controlled machine runs were conducted in which the health of the tool was visually assessed and manually measured to determine wear, while the sensor data were being collected and statistically analyzed by the system to provide a prediction of health. Once the system learned the relationship between sensor data and health of the tool, online monitoring allowed for an assessment of the health condition of the tool, remaining useful life, and if applicable, inspection schedule. This monitoring included autonomous, noninterfering dynamic monitoring.

Those data from the tool that had a predictable relationship with the tool health data were graphed and the upper and lower thresholds defining a healthy tool and an unhealthy tool were defined. An early predictive model of health was determined and used to develop a preventative maintenance schedule for the tool. The addition of new data allows for the system to continue to be trained.

Online monitoring can give a general trend of tool degeneration process, while the visual inspection and manual measuring were used to fine-tune the condition indicator. Thus, a more reliable and robust degeneration trend can be estimated. According to the estimated trend, the real-time tool health status can be concluded by checking the tuned condition indicator over time. The data can be statistically analyzed to show the changes in relation to time to provide a set of time-based features and apply the time-based features as input values to a selected transformation. The transformations may be, but are not limited to, Kalman filtering, particle filtering, and Bayesian model. A prediction model was built to forecast the remaining useful life, warning of potential failure, and failure time interval.

While example embodiments have been described in connection with what is presently considered to be an example of a possible most practical and/or suitable embodiment, it is to be understood that the descriptions are not to be limited to the disclosed embodiments, but on the contrary, is intended to cover various modifications and equivalent arrangements included within the spirit and scope of the example embodiment. Those skilled in the art will recognize or be able to ascertain using no more than routine experimentation, many equivalents to the specific example embodiments specifically described herein. Such equivalents are intended to be encompassed in the scope of the claims, if appended hereto or subsequently filed.