CROSS-REFERENCE TO RELATED APPLICATION(S)

[0001] The present application claims the benefit of priority to U.S. Provisional Patent Application No. 62/953,817, filed on December 26, 2019, the disclosure of which is incorporated herein by reference in its entirety.

TECHNICAL FIELD

[0002] The present technology relates to coke ovens and in particular to systems and methods for optimizing the health and operations of coke ovens.

BACKGROUND

[0003] Coke is a vital component in the blast furnace production of steel. Coke is a solid carbon fuel and carbon source used to melt and reduce iron ore in the production of steel. Coke plants typically produce millions of tons of coke each year. The coke making process begins by receiving and charging metallurgical coal into ovens (using, for example, a levelling conveyer). The ovens heat up the coal to high temperatures (e.g., 2000°F), which causes the volatile matter to be released, captured, and burned off. This in turn keeps the bricks hot. Gases from the combustion are then drawn into openings in the oven walls, called downcomers, and are thermally destroyed as they mix with air and circulate in the sole flues beneath the oven floor. This heats the oven from below so that the coal is heated at an even rate between the top and bottom. Because the production of coke is a batch process, multiple coke ovens are operated simultaneously. To ensure that the coking rate is consistent throughout all of the ovens in a plant and to ensure that the quality of coke remains consistent between batches, the operating conditions of the coke ovens are closely monitored and controlled.

[0004] At the end of a coking cycle, the coke gets pushed out of the oven by a pusher-charger machine and on to a hot car to make room for a new charge. Once on the hot car, the coke is transported the length of the ovens for further processing. For instance, the coke is transported to a quench tower for quenching operations. In the quench tower, the coke is cooled off (e.g., using water released through a spray nozzle). The coke is then deposited to a wharf. Once cooled, the coke is then delivered to end users.

[0005] Coke making is a very expensive process, where multiple coke manufacturers are competing to manufacture the highest quality coke while optimizing the operations costs, optimizing environmental impacts, and maximizing energy efficiency. As such, ensuring reliable operation of coke oven gas plants is more important than ever in securing a stable supply of clean fuel for a manufacturer's end users (e.g., steelworks). Thus, the need exists for efficient coke making processes, and specifically for processes that optimize the health and operations of the coke making ovens to produce the highest quality coke while optimizing their environmental impacts.

BRIEF DESCRIPTION OF THE DRAWINGS

[0006] Figure 1 is a block diagram illustrating an environment within which to optimize oven health performance.

[0007] Figure 2 is a flow diagram illustrating a process of optimizing oven health performance.

[0008] Figure 3 is a block diagram illustrating some of the components of an oven health optimization system.

[0009] Figure 4 is a flow diagram showing steps typically performed by an oven health optimization system to automatically determine optimization values for ovens.

[0010] Figure 5 is a table diagram showing sample contents of an oven data table.

[0011] Figures 6-12 are example reports for visualizing various parameters and optimization results for ovens.

[0012] Figures 13A-13C are example reports for visualizing various inspection parameters for ovens.

[0013] Figure 13D illustrates an example summary report of mechanical inspection battery conditions.

[0014] In the drawings, some components and/or operations can be separated into different blocks or combined into a single block for discussion of some of the implementations of the present technology. Moreover, while the technology is amenable to various modifications and alternative forms, specific implementations have been shown by way of example in the drawings and are described in detail below. The intention, however, is not to limit the technology to the specific implementations described. On the contrary, the technology is intended to cover all modifications, equivalents, and alternatives falling within the scope of the technology as defined by the appended claims.

DETAILED DESCRIPTION

[0015] As discussed above, for coke manufacturers to stay competitive and profitable, it is imperative that they optimize their coke making operations. To do so, coke manufacturers have to constantly monitor the battery of coke ovens and constantly design/redesign, configure, and/or modify their coke making process. In particular, coke manufacturers need to ensure that each of their coke ovens is producing coke in a most efficient manner and not burdening other ovens in the battery of coke ovens. Since coke ovens tend to be very expensive, it is also imperative that the coke ovens be regularly maintained and repaired, as well as identified for retirement (e.g., when their repair/maintenance costs exceed their replacement costs).

[0016] To solve these and other problems, the inventors have developed an overall oven health optimization system ("oven health optimization system") and method to compute one or more metrics to measure/compare oven health performance data, compute oven life indicator values, generate one or more oven health performance plans, and so on, based on oven operation and/or inspection data.

[0017] Specific details of several embodiments of the disclosed technology are described below with reference to a particular, representative configuration. The disclosed technology can be practiced in accordance with ovens, coke manufacturing facilities, and insulation and heat shielding structures having other suitable configurations. Specific details describing structures or processes that are well-known and often associated with coke ovens but that can unnecessarily obscure some significant aspects of the presently disclosed technology are not set forth in the following description for clarity. Moreover, although the following disclosure sets forth some embodiments of the different aspects of the disclosed technology, some embodiments of the technology can have configurations and/or components different than those described in this section. As such, the present technology can include some embodiments with additional elements and/or without several of the elements described below with reference to Figures 1-13D.

[0018] The phrases "in some implementations," "according to some implementations," "in the implementations shown," "in other implementations," and the like generally mean the specific feature, structure, or characteristic following the phrase is included in at least one implementation of the present technology and can be included in more than one implementation. In addition, such phrases do not necessarily refer to the same implementations or different implementations.

[0019] Figure 1 is a block diagram illustrating how an environment within the oven health optimization system operates. A coke generation process flow begins when coal is received and collected at one or more receptacles 105. Once a sufficient quantity and quality of coal is received and collected, it is then fed to one or more coke ovens 110a ... 110n. Typically, a coke generation plant operates a battery of coke ovens, arranged in a preconfigured manner, to produce a desired quantity of coke. In several implementations, the coke ovens are non-recovery ovens and/or heat-recovery ovens, which produce higher quality coke, using waste heat to generate derivative energy for resale, and reducing environmental impact. The coke generated by the coke ovens can then be subjected to further processing 115 (e.g., quenching operations). As the coal is fed to the coke ovens, as the ovens are operated, or as further post-processing occurs, values of one or more performance parameters and/or inspection parameters can be gathered and sent to an oven health optimization system 120. Examples of performance parameters include, but are not limited to, one or more of the following: production rate, oven health score, current spend on repairs, clinker amount, coke production over time, coking rate, surface losses, heat released, air leakage, output coke properties, draft, draft at the vent stack, draft at the end and mid ovens, draft loss per oven, oxygen levels, inlet temperature to the heat recovery steam generator (HRSG), leak rates from helium leak test (as described in co-pending U.S. Patent Application No. 16/729,201 , which is incorporated in its entirety herein), temperature profile of coking cycle (crown temperature, sole flue temperature, etc.), and so on. Values for the performance parameters can be sent as they are generated (in real time, e.g., seconds, minutes, etc.) and/or in an aggregated manner (in real time or intermittently, e.g., days, weeks, etc.). [0020] Values for the inspection parameters can be gathered using one or more of the following categories of inspection: mechanical inspections, refractory inspections, and oven oxygen reading. Mechanical inspections include, for example, thermography (e.g., boiler ceiling, common tunnel, and crossover), topography battery, door/lintel/jamb inspection, inspection tie rods and springs, inspection buckstay, inspection transition box/elbow, inspection air space, and so on. Refractory inspections include, for example, oxygen measurement inspection, sole flue inspection, oven chamber inspection (e.g., via photography), carbon inspection, oven refractory exterior, and so on. Examples of inspection parameters include, but are not limited to, one or more of the following: configuration of at least one heat-recovery coke oven, age of the at least one heat- recovery coke oven, condition of the at least one heat-recovery coke oven, maintenance records of the at least one heat-recovery coke oven, operation data of the at least one heat-recovery coke oven, repair status of the at least one heat-recovery coke oven, burners used, coal properties, regulatory compliance requirements, soak time, ambient conditions, logistical parameters, mechanical production parameters, helium detection, damper block condition, leaks, severity of operation, number of cycles, fissure line formation, mass flow rate, burn loss, power production, complete coking time, elapsed coking time, cycle length, cycle time, crown temperature, coke-side temperature, pusher- side temperature, sole flue temperature (e.g., end sole flue coke time temperature, end sole flue push side temperature), sole flue (SF) peak temperature, draft, SF peak time, first crossover time, last crossover time, crown peak time, position control scheme, charge weight, wharf performance, burner feedback, door fires, lance usage, uptake, oxygen intake, downtime, measuring smell and chemicals outside the plant (for example, as described in co-pending U.S. Patent Application No. 62/345,717, which is incorporated in its entirety herein), and so on.

[0021] In several implementations, online (and/or real-time) inspection data is combined with off-line (and/or non-real-time) inspection data to compute oven life. Examples of off-line (and/or non-real-time) inspection data include data collected by inspections done by inspectors. For example, off-line (and/or non-real-time) inspection data comprises oven chamber inspection data, oven crown inspection data, oven mechanical inspection data, and so on. Oven chamber inspection data comprises data related to left downcomer arches, right downcomer arches, carbon, left downcomer cracks, right downcomer cracks, left uptake cracks, right uptake cracks, crown, wall erosion, coke side lintel, left coke side jamb, right coke side jamb, coke side sill, pusher side lintel, left pusher side jamb, right pusher side jamb, pusher side sill, and so on (see Figure 13A for examples). Examples of oven crown inspection data comprise data related to coke side and/or pusher side elbow damper, transition, crown gunnite cracks, gas leaks, uptake pier cracks, and so on (see Figure 13B for examples). Oven mechanical inspection data comprises data related to coke side and/or pusher side air space beam, left buckstay, right buckstay, end wall beam, left jamb plate, right jamb plate, lintel plate, bench, door, sill beam, sole flue damper, top tie rods, bottom tie rods, and so on (see Figure 13C for examples). Figure 13D illustrates an example summary report of mechanical inspection battery conditions.

[0022] The oven health optimization system 120 can receive this data at various frequencies and/or granularities. For example, the oven health optimization system 120 can receive real-time data (e.g., represented in seconds), near-term data (e.g., represented in days), inspection data (typically generated/stored at a frequency of 4-6 months), survey data (typically generated or stored at a frequency of months or years), and so on. The oven health optimization system 120 can process this wide variety of data, received and/or stored at different frequencies, to compute values of one or more oven optimization results 125. In several implementations, the optimization results 125 are fed back to enhance/optimize one or more aspects of the coke generation process (as discussed in more detail below).

[0023] Figure 1 and the discussion herein provide a brief, general description of a suitable environment in which the oven health optimization system 120 can be supported and implemented. Although not required, aspects of the oven health optimization system 120 are described in the general context of computer-executable instructions, such as routines executed by a computer (e.g., mobile device, a server computer, or personal computer). The system can be practiced with other communications, data processing, or computer system configurations, including Internet appliances, hand-held devices (including tablet computers and/or personal digital assistants (PDAs)), Internet of Things (loT) devices, all manner of cellular or mobile phones, multi-processor systems, microprocessor-based or programmable consumer electronics, set-top boxes, network PCs, mini-computers, mainframe computers, and the like. Indeed, the terms "computer," "host," "host computer," "mobile device," and "handset” are generally used interchangeably herein and refer to any of the above devices and systems, as well as any data processor.

[0024] Aspects of the system can be embodied in a special-purpose computing device or data processor that is specifically programmed, configured, or constructed to perform one or more of the computer-executable instructions explained in detail herein. Aspects of the system can also be practiced in distributed computing environments where tasks or modules are performed by remote processing devices, which are linked through a communications network, such as a Local Area Network (LAN), Wide Area Network (WAN), or the Internet. In a distributed computing environment, program modules can be located in both local and remote memory storage devices.

[0025] Aspects of the system can be stored or distributed on computer-readable media (e.g., physical and/or tangible non-transitory computer-readable storage media), including magnetically or optically readable computer discs, hard-wired or preprogrammed chips (e.g., EEPROM semiconductor chips), nanotechnology memory, or other data storage media. Indeed, computer-implemented instructions, data structures, screen displays, and other data under aspects of the system can be distributed over the Internet or over other networks (including wireless networks), on a propagated signal on a propagation medium (e.g., an electromagnetic wave(s), a sound wave(s), etc.) over a period of time, or they can be provided on any analog or digital network (packet switched, circuit switched, or other scheme). Portions of the system reside on a server computer, while corresponding portions reside on a client computer such as a mobile or portable device, and thus, while certain hardware platforms are described herein, aspects of the system are equally applicable to nodes on a network. In alternative implementations, the mobile device or portable device can represent the server portion, while the server can represent the client portion.

[0026] Further details regarding the operation and implementation of the oven health optimization system 120 will now be described. Figure 2 is a flow diagram illustrating a process 200 of optimizing oven health performance performed by the oven health optimization system 120. Process 200 begins at block 205 by receiving a selection of at least one output parameter to be optimized. The output parameters can reflect one or more measurements of oven profitability. Examples of the output parameters include, but are not limited to, one or more of the following: return on investment (ROI) on repair of at least one heat-recovery coke oven, coke production over time, coking rate, cost to repair the at least one heat-recovery coke oven, cost to rebuild the at least one heat- recovery coke oven, cost to abandon the at least one heat-recovery coke oven, profitability of the at least one heat-recovery coke oven, remaining life of the at least one heat-recovery coke oven, damage to the at least one heat-recovery coke oven, rate of aging, aging as a function of tons run through the at least one heat-recovery coke oven, aging as a function of the operating conditions in the at least one heat-recovery coke oven, closing gain, opening gain, damage score, environmental score, permit requirements, output quality, power production, and so on.

[0027] At block 210, process 200 selects one or more key performance indicators or KPIs from a set of performance parameters (discussed above) based on the selected output parameter(s). For example, based on the specific output parameter selected to be optimized, process 200 can determine one or more strongly correlated performance parameters (KPIs) that are most pertinent to the selected output parameter. In several implementations, process 200 can select the KPIs from a larger set of available performance indicators, each of which provides an indication of how the coke ovens are operating/performing. The KPI values can be per oven and/or per set of ovens.

[0028] In several implementations, process 200 selects the KPIs based on knowledge of oven operation. Process 200 can maintain and access a correlation between the output parameters and the performance indicators to select the top n indicators as KPIs. For example, process 200 evaluates soak time as an important parameter. The soak time is a function of the charge, the crown and sole temperatures, and coke rate — consequently, process 200 selects one or more of the temperatures and the temperature profile. Figures 6 and 7 illustrate an example where correlation of parameters is used to evaluate oven performance. As illustrated in Figures 6 and 7, each parameter is associated with a target range. Each oven is evaluated based on the values of its parameters falling within their respective ranges. Then all parameters within the range are consolidated (e.g., by summing up their values). As more data is collected, process 200 can reevaluate the ranges, and then redo the correlation. As another example, Figures 9, 10, and 11 illustrate the use of a complex correlation that combines online oven health with quarterly inspection to give a ranking. This can then be correlated to oven health and age. [0029] At block 215, process 200 generates values for a set of operation optimization parameters using values of the set of selected performance parameters. The set of operation optimization parameters can be selected from a larger set based on the selected output parameter to be optimized. Examples of optimization parameters include, but are not limited to, one or more of the following: coke push grade, soak time, environmental factors, oven performance, quality, yield, rate, power, and so on. For example, an important optimization parameter is the coke production rate (i.e., tons of coke/hour). The coke production reflects the existing current operation and health. If an oven is running well, it will have a higher coke production rate. The coke production rate is then mixed with the oven inspection, which is more of a long-term health factor. A combination of current operating performance and inspection leads to the ability to predict current oven life, and from that, current and future repair costs can be estimated.

[0030] At block 220, process 200 selects a set of inspection parameters (discussed above) based on the selected output parameter(s) (selected at block 205). For example, based on the specific output parameter selected to be optimized, process 200 can determine one or more strongly correlated inspection parameters that are most pertinent to the selected output parameter. In several implementations, process 200 can select the inspection parameters from a larger set of available inspection indicators, each of which provide an indication of how the coke ovens are operating/performing.

[0031] In several implementations, by reviewing many process parameters, process 200 can statistically determine the important process parameters to monitor. For example, when the main output is production and oven life, process 200 can monitor the tons of coke/hour, oven temperatures, soak time, push quality, and the oven inspection to determine when an oven is running well and its expected life. This information can then be used to determine what repairs are needed. This process can be reconfigured by reevaluating the process parameters and changing the weighting. For example, process 200 can evaluate the soak time. An oven with a short soak time in general will have an issue. This typically will then lead to also looking at the oven peak and average temperatures. Short soak time, at normal charges and low oven temperatures, means poor oven operation, leaks, or poor draft. This then allows process 200 to determine whether these are also present and comes into an oven having a poor score in all these areas. Process 200 can then hook this to an advisory system that can advise options such as repairs and operator actions. [0032] In several implementations, process 200 can compute values for composite oven inspection KPIs by, for example, selecting two or more inspection parameters and computing a weighted average of their respective values. For example, a composite oven inspection KPI can be calculated by adding all the values from the multiplication of the inspection tag and the respective weights:

[0033] The weighted values in the above example are the inspection monitoring health parameters. The weighted score for the inspection parameters is added to the current oven operational score that looks at the current oven operation and/or last several cycles of oven operation. These two values are then put into a correlation that predicts the current oven life. This indicates what extra work is needed on the oven as well as the existing life of the oven. By doing more work on an oven, the oven life can be further improved. Consequently, this indicates which ovens need the most work to regain the oven life.

[0034] At block 225, process 200 generates collective optimized values based on the generated values of the set of optimization parameters and the selected set of inspection parameters. The collective optimized values can be generated per oven and/or per set of ovens. Examples of optimized values include, but are not limited to, one or more of the following: oven life indicator value, oven repair plan, and so on. For example, as part of the oven repair plan, process 200 can set a priority of repair for the ovens. To do so, process 200 generates oven life indicator values for a set of ovens using generated values for the set of operation optimization parameters for the set of ovens and values of the selected set of inspection parameters for the set of ovens. Then process 200 generates a priority of repair for ovens in the set of ovens by comparing the generated oven life indicator values for the set of ovens (e.g., ovens with lower life indicator values are prioritized higher for replacement/repair).

[0035] In several implementations, process 200 receives values of historical trends parameters from a set of historical trends parameters related to the ovens. For example, process 200 receives historical values of one or more performance and inspection parameters for a certain time period (e.g., last month, last year, etc.). Process 200 can then revise the generated collective optimized values (e.g., the oven life indicator value, the oven repair plan, or both) by subjecting a subset of the values of the historical trends parameters to a historical trends model. [0036] In several implementations, process 200 receives values of miscellaneous parameters from a set of miscellaneous parameters related to the ovens. Examples of miscellaneous parameters include, but are not limited to, one or more of the following: cost to repair oven, cost to rebuild oven, cost to abandon oven, average oven life, and so on. Process 200 can then revise the generated collective optimized values (e.g., the oven life indicator value, the oven repair plan, or both) based on the received values of the miscellaneous parameters.

[0037] In several implementations, process 200 receives values of fuel parameters related to the ovens. Examples of fuel parameters include, but are not limited to, one or more of the following: natural gas parameters, nuclear power parameters, and so on. Process 200 can then revise the generated collective optimized values (e.g., the oven life indicator value, the oven repair plan, or both) based on the received values of the fuel parameters.

[0038] Process 200 can generate one or more reports to display the generated collective optimized values (and/or any intermediate computations) (at block 230). Figures 6-12 are example reports for visualizing various parameters and optimization results for ovens. Figure 6 illustrates online performance of a plant’s ovens. It lists the ovens within each target and then lists the worst ovens for each target. This allows process 200 to identify the worst ovens. In this example there are 268 ovens — conventional processes cannot evaluate them all efficiently and in a timely manner to identify any current and/or future problems. In contrast, as seen in Figure 6, process 200 enables quick visualization to determine what ovens are the top ovens in trouble and should be the focus of attention for repair. Figure 6 can be used by the operators in the field and by the plant supervisors. Figure 7 is a more detailed version of Figure 6 that is used by the engineers and some supervisors. It includes more details and a more granular look at the ovens. It allows for the system to provide sufficient information to enable engineers and supervisors to further coach the operators on actions to be taken. Figure 8 also links to Figures 6 and 7. Figure 8 illustrates the trends in the monitoring parameters and where the trend is out of range. The reason is that a single measurement does not always mean there is an issue. A trend indicates if it is a longer-term and actual issue. Figure 9 folds in the inspection data (e.g., manual inspection data) that can be received periodically (e.g., quarterly, every 6 or 12 months, etc.). In general, if there are trending performance issues, they can be found in the inspection data of the oven(s). Figures 10 and 11 then combine the online operational data and its trends with the inspection reports. This can be then run through a correlation by process 200 to predict the life of every oven. This then allows the system to rank the poorest ovens and identify where work needs to be focused.

[0039] In several implementations, process 200, at block 235, can provide information to alter the state of one or more ovens based on the collective optimization values. As an example, for an oven with a low coke life, process 200 would look at the coke parameter and the inspection parameter. Process 200 would typically focus on the 10 worst ovens. Process 200 can then evaluate whether the ovens are from the same area on the battery and what repairs are needed. From the two correlations, process 200 can then determine the repairs needed. As an example, process 200 can find that there is oven damage. If the oven damage is severe, process 200 would also see poor performance. Consequently, process 200 would then evaluate repairing the oven and how much production will be gained back and how much oven life will be gained. This allows oven repair prioritization. This also allows process 200 to determine whether it is a local one-oven issue or a problem with the whole battery of ovens. An example of the latter can be all ovens in a battery section having a poor coke production factor but satisfactory inspection. This means there may be a systemic issue, such as low draft to the ovens in that area, which will be seen then in the temperature profiles, which is one of the monitored parameters.

[0040] In several implementations, the oven health optimization system 120 can compare an oven's performance to that of another oven, a stack of ovens, a battery of ovens, and so on. For example, the oven health optimization system 120 can generate (and/or access) an oven life indicator value for a first oven using generated values for the set of operation optimization parameters for the first oven and values of the selected set of inspection parameters for the first oven. It can also generate (and/or access) oven life indicator values for a set of ovens other than the first oven using generated values for the set of operation optimization parameters for the set of ovens other than the first oven and values of the selected set of inspection parameters for the set of ovens other than the first oven. Then it can generate a comparative performance measure for the first oven by comparing the generated oven life indicator value for the first oven and the generated oven life indicator values for the set of ovens other than the first oven. For example, the oven health optimization system 120 can list the worst and best ovens and a score for all ovens. The oven health optimization system 120 can plot the oven life for each oven versus its location. It can visually see if there are groupings of ovens with issues that could indicate the source of the problem. The oven health optimization system 120 can enable solving one or more problems that are impacting several ovens, resulting in increased efficiencies in time and costs and thus creating a big win for coke oven operators and managers. An example would be a group of ovens at the same HRSG with low coke production ratings but good inspections. If the temperature profiles are poor, then could be low draft at the ovens, which then could be a fouled HRSG.

[0041] Those skilled in the art will appreciate that the steps shown in Figure 2 and in each of the flow diagrams discussed below may be altered in a variety of ways. For example, the order of the steps may be rearranged; substeps may be performed in parallel; shown steps may be omitted, or other steps may be included; etc.

[0042] Figure 3 is a block diagram illustrating some of the components of the oven health optimization system 120. In several implementations, the oven health optimization system 120 can generate values for the set of operation optimization parameters (estimated optimization results) 31 Of by subjecting one or more input parameters 305 to various models 310a ... 31 Od. The oven health optimization system 120 can subject one or more subsets of input parameters (e.g., performance and/or inspection parameters) to different models, depending on a type of the input parameter. For example, the oven health optimization system 120 can subject parameters of predictive indicators type to a predictive indicators model 310a, parameters of performance measurements type to a performance measurements model 310b, parameters of miscellaneous type to a miscellaneous factors model 310c, and historical parameters to a historical trends model 31 Od. After generating results from each model, the oven health optimization system 120 can aggregate the results of these models using an aggregator 31 Oe to generate values for the set of operation optimization parameters 31 Of. In some implementations, the model used by the oven health optimization system 120 is a complex model made up of (a) a number of different sub-models, each producing a set of optimization values based on one or more input parameter values, together with (b) a meta-model that uses input parameter values to determine a relative weighting of the sub-model valuations, which the oven health optimization system combines to obtain optimization values of ovens by the complex model. [0043] In some implementations, the oven health optimization system constructs and/or applies models or sub-models that each constitute a forest of classification trees. Figure 4 is a flow diagram showing steps typically performed by the oven health optimization system to automatically determine optimization values for ovens. At block 405, the oven health optimization system randomly selects a fraction of the ovens in the oven stack/battery/plant to which the tree corresponds, as well as a fraction of the available oven-related attributes, as a basis for the tree. Figure 5 is a table diagram showing sample contents of an oven data table. The oven data table 500 is made up of rows, each representing an oven in a stack/battery/plant of ovens. Each row is divided into the following columns: identifier, oven model, age, production rate, coking rate, and remaining life. Attributes that may be used include, for example, one or more of the performance parameters, inspection parameters, miscellaneous parameters, and/or fuel parameters discussed above. While Figure 5 shows an oven data table 500 whose contents and organization are designed to make them more comprehensible by a human reader, those skilled in the art will appreciate that actual data structures used by the oven health optimization system to store this information may differ from the table shown, in that they, for example, may be organized in a different manner; may contain more or less information than shown; may be compressed and/or encrypted; may contain a much larger number of rows/columns than shown; etc.

[0044] Returning to Figure 4, at blocks 410-420, the oven health optimization system constructs and scores a number of trees. The number of trees is configurable, with larger numbers typically yielding better results but requiring the application of greater computing resources. At block 415, the oven health optimization system constructs a tree. In some embodiments, the oven health optimization system constructs and applies random forest valuation models.

[0045] At blocks 425-430, the oven health optimization system uses the forest of trees constructed and scored at blocks 405-420 to process requests for oven health evaluations. Such requests may be individually issued by users or issued by a program, such as a program that automatically requests oven health-related data for all ovens or substantially all ovens in a stack/battery/plant at a standard frequency, such as daily. At block 425, the oven health optimization system receives a request for oven health evaluation identifying the oven to be evaluated. At block 430, the facility applies the trees constructed at block 415, weighted by the scores, to the attributes of the oven identified in the received request in order to obtain an oven health evaluation for the oven identified in the request. After block 430, the oven health optimization system continues at block 425 to receive the next request.

[0046] In some implementations, a system for optimizing oven profitability is disclosed. The system comprises at least one coke oven for treating coal, wherein the at least one coke oven processes coal to produce coke. The system further comprises at least one oven health optimization system for optimizing profitability of the at least one coke oven, the at least one oven health optimization system comprising at least one hardware processor and at least one non-transitory memory, coupled to the at least one hardware processor and storing instructions, which, when executed by the at least one hardware processor, perform a process. The process comprises receiving a selection of at least one output parameter that measures oven profitability. The process further comprises selecting a set of performance parameters based on the selected at least one output parameter. The process then generates values for a set of operation optimization parameters using values of the set of selected performance parameters, wherein the set of operation optimization parameters comprises at least one of the following coke push grade, soak time, or environmental factors. The process selects a set of inspection parameters based on the selected at least one output parameter. The process generates an oven life indicator value, an oven repair plan, or both, using the generated values for the set of operation optimization parameters and values of the selected set of inspection parameters.

[0047] In some implementations, a computer-implemented method for optimizing oven profitability is disclosed. The method comprises receiving a selection of at least one output parameter that measures oven profitability of at least one coke oven for treating coal, wherein the at least one coke oven processes coal to produce coke. The method selects a set of performance parameters based on the selected at least one output parameter. The method generates values for a set of operation optimization parameters using values of the set of selected performance parameters, wherein the set of operation optimization parameters comprises at least one of coke push grade, soak time, or environmental factors. The method selects a set of inspection parameters based on the selected at least one output parameter. The method generates an oven life indicator value, an oven repair plan, or both, using the generated values for the set of operation optimization parameters and values of the selected set of inspection parameters.

[0048] In some implementations, a non-transitory computer-readable medium storing instructions is disclosed. The instructions, which when executed by at least one computing device, perform a method for optimizing oven profitability. The method comprises receiving a selection of at least one output parameter that measures oven profitability of at least one coke oven for treating coal, wherein the at least one coke oven processes coal to produce coke. The method selects a set of performance parameters based on the selected at least one output parameter. The method generates values for a set of operation optimization parameters using values of the set of selected performance parameters, wherein the set of operation optimization parameters comprises at least one of coke push grade, soak time, or environmental factors. The method selects a set of inspection parameters based on the selected at least one output parameter. The method generates an oven life indicator value, an oven repair plan, or both, using the generated values for the set of operation optimization parameters and values of the selected set of inspection parameters.

Conclusion

[0049] Unless the context clearly requires otherwise, throughout the description and the claims, the words "comprise," "comprising," and the like are to be construed in an inclusive sense, as opposed to an exclusive or exhaustive sense; that is to say, in the sense of "including, but not limited to." As used herein, the term "connected" or "coupled," or any variant thereof, means any connection or coupling, either direct or indirect, between two or more elements; the coupling or connection between the elements can be physical, logical, or a combination thereof. Additionally, the words "herein," "above," "below," and words of similar import, when used in this application, shall refer to this application as a whole and not to any particular portions of this application. Where the context permits, words in the above Detailed Description using the singular or plural number can also include the plural or singular number, respectively. The word "or," in reference to a list of two or more items, covers all of the following interpretations of the word: any of the items in the list, all of the items in the list, and any combination of the items in the list.

[0050] The above detailed description of implementations of the system is not intended to be exhaustive or to limit the system to the precise form disclosed above. While specific implementations of, and examples for, the system are described above for illustrative purposes, various equivalent modifications are possible within the scope of the system, as those skilled in the relevant art will recognize. For example, some network elements are described herein as performing certain functions. Those functions could be performed by other elements in the same or differing networks, which could reduce the number of network elements. Alternatively, or additionally, network elements performing those functions could be replaced by two or more elements to perform portions of those functions. In addition, while processes, message/data flows, or blocks are presented in a given order, alternative implementations can perform routines having blocks, or employ systems having blocks, in a different order, and some processes or blocks can be deleted, moved, added, subdivided, combined, and/or modified to provide alternative combinations or subcombinations. Each of these processes, message/data flows, or blocks can be implemented in a variety of different ways. Also, while processes or blocks are at times shown as being performed in series, these processes or blocks can instead be performed in parallel or can be performed at different times. Further, any specific numbers noted herein are only examples: alternative implementations can employ differing values or ranges.

[0051] The teachings of the methods and system provided herein can be applied to other systems, not necessarily the system described above. The elements, blocks, and acts of the various implementations described above can be combined to provide further implementations.

[0052] Any patents and applications and other references noted above, including any that can be listed in accompanying filing papers, are incorporated herein by reference. Aspects of the technology can be modified, if necessary, to employ the systems, functions, and concepts of the various references described above to provide yet further implementations of the technology.

[0053] These and other changes can be made to the invention in light of the above Detailed Description. While the above description describes certain implementations of the technology, and describes the best mode contemplated, no matter how detailed the above appears in text, the invention can be practiced in many ways. Details of the system can vary considerably in its implementation details, while still being encompassed by the technology disclosed herein. As noted above, particular terminology used when describing certain features or aspects of the technology should not be taken to imply that the terminology is being redefined herein to be restricted to any specific characteristics, features, or aspects of the technology with which that terminology is associated. In general, the terms used in the following claims should not be construed to limit the invention to the specific implementations disclosed in the specification, unless the above Detailed Description section explicitly defines such terms. Accordingly, the actual scope of the invention encompasses not only the disclosed implementations, but also all equivalent ways of practicing or implementing the invention under the claims.

[0054] While certain aspects of the technology are presented below in certain claim forms, the inventors contemplate the various aspects of the technology in any number of claim forms. For example, while only one aspect of the invention is recited as implemented in a computer-readable medium, other aspects can likewise be implemented in a computer-readable medium. Accordingly, the inventors reserve the right to add additional claims after filing the application to pursue such additional claim forms for other aspects of the technology.