Lightweight thermal power generating unit parameter optimization method and device
By using a simplified method for optimizing thermal power unit parameters, and combining current and historical data with load status, the problem of high resource consumption was solved, and the real-time and effectiveness of parameter optimization was achieved, ensuring deployment in production area 1.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- HUADIAN ELECTRIC POWER SCI INST CO LTD
- Filing Date
- 2025-12-12
- Publication Date
- 2026-04-21
Smart Images
Figure CN121906480A_ABST
Abstract
Description
Technical Field
[0001] This application relates to the field of unit operation optimization technology, and in particular to a lightweight method and apparatus for optimizing parameters of thermal power units. Background Technology
[0002] Optimizing operating parameters to improve unit performance is a key means of energy conservation and consumption reduction in power plants. Currently, the parameter optimization methods used in the industry are usually based on complex mathematical models built using high-level languages such as Python. These models are computationally intensive and resource-intensive. Due to the management regulations on safety production zoning in thermal power plants, they cannot be directly deployed in production zone 1 (i.e., the area where the DCS system is located) and must be deployed in production zone 3.
[0003] The physical isolation between Production Zone 3 and Production Zone 1 prevents the optimization model from directly and in real-time acquiring unit operating data, resulting in data lag. Furthermore, the output optimization commands are difficult to feed back to the DCS control system for execution in real time, preventing the optimization process from achieving true "online" and "closed-loop" operation and reducing optimization effectiveness. In addition, the complex model places specific demands on the computing platform, and the DCS system in Production Zone 1 cannot provide such advanced compilers and server resources, limiting the direct application of advanced optimization algorithms. Summary of the Invention
[0004] This application provides a lightweight method, apparatus, electronic device, and storage medium for optimizing parameters of thermal power units, in order to at least solve the problem that parameter optimization methods in related technologies consume high resources and cannot be directly deployed in production areas.
[0005] In a first aspect, embodiments of this application provide a lightweight method for optimizing parameters of thermal power units. This method is applied to a distributed control system of a thermal power unit and includes: Acquire the current and historical operating data of the thermal power unit, wherein the historical operating data includes the historical average and historical best values of the parameters; The load status and fluctuation status of the thermal power unit are determined based on the current operating data, and an optimization activation flag is determined based on the fluctuation status, the current operating data, and the historical average value. The target value of the parameter is determined based on the optimization activation flag, the load status, the current operating data, and the historical best value.
[0006] In some embodiments, the current operating data includes the current values of parameters; determining the optimization activation flag based on the fluctuation state, the current operating data, and the historical average includes: If the current value is less than the historical average value and the fluctuation state is in a steady state, the optimization activation flag is set to the first flag value. If the current value is greater than or equal to the historical average value, or if the fluctuation state is not steady, the optimization activation flag is set to the second flag value.
[0007] In some embodiments, determining the target value of the parameter based on the optimization activation flag, the load status, the current operating data, and the historical best value includes: Based on the load status, determine whether the power generation of the thermal power unit is within the reference load range; When the optimization activation flag is the first flag value and the power generation is within the reference load range, the target value is determined based on the current value and the historical best value. If the optimization activation flag is the second flag value, or if the power generation is not within the reference load range, the current value is set to the target value.
[0008] In some embodiments, determining the target value based on the current value and the historical best value includes: If the current value is less than the historical best value, the current value is set as the target value; If the current value is greater than or equal to the historical best value, the historical best value is set as the target value.
[0009] In some embodiments, the method further includes: In response to the initialization signal, the historical average value is initialized to a preset first initial value, and the historical best value is initialized to a preset second initial value.
[0010] Secondly, embodiments of this application provide a lightweight thermal power unit parameter optimization device, which is installed in the distributed control system of the thermal power unit, and the device includes: The data acquisition module is used to acquire the current operating data and historical operating data of the thermal power unit. The historical operating data includes the historical average value and historical best value of the parameters. The analysis module is used to determine the load status and fluctuation status of the thermal power unit based on the current operating data, and to determine the optimization activation flag based on the fluctuation status, the current operating data and the historical average value. The target value determination module is used to determine the target value of the parameter based on the optimization activation flag, the load status, the current operating data, and the historical best value.
[0011] In some embodiments, the current running data includes the current values of parameters; the analysis module includes: The first labeling determination module is used to set the optimization activation flag to a first flag value when the current value is less than the historical average value and the fluctuation state is a steady state. The second labeling determination module is used to set the optimization activation flag to a second flag value when the current value is greater than or equal to the historical average value, or when the fluctuation state is not steady.
[0012] In some embodiments, the target value determination module includes: The judgment module is used to determine whether the power generation capacity of the thermal power unit is within the reference load range based on the load status. The first target value determination module is used to determine the target value based on the current value and the historical best value when the optimization activation flag is the first flag value and the power generation is within the reference load range. The second target value determination module is used to set the current value as the target value when the optimization activation flag is the second flag value or the power generation is not within the reference load range.
[0013] Thirdly, embodiments of this application provide a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it implements the lightweight thermal power unit parameter optimization method as described in the first aspect above.
[0014] Fourthly, embodiments of this application provide a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the lightweight thermal power unit parameter optimization method as described in the first aspect above.
[0015] Compared to related technologies, the lightweight parameter optimization method for thermal power units provided in this application only calls the current operating data, historical average value, and historical best value, without the need to store and process all high-frequency original historical data, thus reducing storage resource consumption. The optimization process is broken down into three simple logical steps: state judgment, activation flag determination, and target value output. There is no complex iterative calculation or model reasoning process, and the CPU utilization rate can be controlled within the low threshold allowed by production area 1. It will not compete for resources with the real-time control tasks of DCS, thus solving the problem that parameter optimization methods have high resource consumption and cannot be directly deployed in production area 1. Attached Figure Description
[0016] The accompanying drawings, which are included to provide a further understanding of this application and form part of this application, illustrate exemplary embodiments of this application and are used to explain this application, but do not constitute an undue limitation of this application. In the drawings: Figure 1 This is a flowchart of a lightweight thermal power unit parameter optimization method according to an embodiment of this application; Figure 2 This is a flowchart of a method for optimizing thermal power unit parameters based on real-time data rolling, according to an embodiment of this application. Figure 3 This is a structural block diagram of a lightweight thermal power unit parameter optimization device according to an embodiment of this application; Figure 4 This is a schematic diagram of the internal structure of an electronic device according to an embodiment of this application. Detailed Implementation
[0017] To make the objectives, technical solutions, and advantages of this application clearer, the application is described and illustrated below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application. All other embodiments obtained by those skilled in the art based on the embodiments provided in this application without inventive effort are within the scope of protection of this application.
[0018] Obviously, the accompanying drawings described below are merely some examples or embodiments of this application. Those skilled in the art can apply this application to other similar scenarios based on these drawings without any inventive effort. Furthermore, it is understood that although the efforts made in this development process may be complex and lengthy, for those skilled in the art related to the content disclosed in this application, any changes to design, manufacturing, or production based on the technical content disclosed in this application are merely conventional technical means and should not be construed as insufficient disclosure of the content of this application.
[0019] In this application, the reference to "embodiment" means that a specific feature, structure, or characteristic described in connection with an embodiment may be included in at least one embodiment of this application. The appearance of this phrase in various places in the specification does not necessarily refer to the same embodiment, nor is it a separate or alternative embodiment that is mutually exclusive with other embodiments. It will be explicitly and implicitly understood by those skilled in the art that the embodiments described in this application may be combined with other embodiments without conflict.
[0020] Unless otherwise defined, the technical or scientific terms used in this application shall have the ordinary meaning understood by one of ordinary skill in the art to which this application pertains. The terms “a,” “an,” “a,” “the,” and similar words used in this application do not indicate quantity limitation and may indicate singular or plural. The terms “comprising,” “including,” “having,” and any variations thereof used in this application are intended to cover non-exclusive inclusion; for example, a process, method, apparatus, product, or device that includes a series of steps or modules (units) is not limited to the listed steps or units, but may also include steps or units not listed, or may include other steps or units inherent to these processes, methods, products, or devices. The terms “connected,” “linked,” “coupled,” and similar words used in this application are not limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. “Multiple” used in this application refers to two or more. “And / or” describes the relationship between related objects, indicating that three relationships may exist; for example, “A and / or B” can represent: A alone, A and B simultaneously, and B alone. The character " / " generally indicates that the preceding and following objects are in an "or" relationship. The terms "first," "second," and "third" used in this application are merely to distinguish similar objects and do not represent a specific ordering of the objects.
[0021] This embodiment provides a lightweight method for optimizing the parameters of thermal power units, which is applied to the distributed control system of thermal power units. Figure 1 This is a flowchart of a lightweight thermal power unit parameter optimization method according to an embodiment of this application, such as... Figure 1 As shown, the process includes the following steps: Step S101: Obtain the current operating data and historical operating data of the thermal power unit. The historical operating data includes the historical average value and historical best value of the parameters.
[0022] It should be noted that the historical best value refers to the historical average value of the top performers. It is a sample set of corresponding optimal operating conditions selected from historical data, and then the average value of the sample set is calculated as the quantitative carrier of the historical best value.
[0023] This embodiment only needs to obtain three types of operational data: current operational data, historical average, and head historical average (historical best value), without redundant statistical dimensions. Moreover, the head historical average is essentially a preliminary statistical result of historical data, so there is no need to repeatedly calculate the optimal value during the optimization phase; it can be directly called, saving the computational cost of traversing and sorting the entire historical data.
[0024] In some embodiments, the method further includes: in response to an initialization signal, initializing the historical average value to a preset first initial value, and initializing the historical best value to a preset second initial value.
[0025] The DCS system in Production Zone 1 may enter a "cold start" state due to scenarios such as unit startup, system upgrade and restart, or the first deployment of parameter optimization function. At this time, there is no available historical operating data. If there is no initialization mechanism, the optimization process will be interrupted due to the lack of reference data, or it will be forced to temporarily call all the original data to generate reference values.
[0026] By presetting the first / second initial values, when the initialization signal is triggered (such as when the unit start-up command is issued), the historical average value and the historical best value are directly assigned a benchmark value that conforms to the unit design specifications / operation and maintenance experience. There is no need to wait for the system to accumulate enough historical data. The optimization logic can take effect synchronously at the moment the unit starts up, which meets the real-time requirement of "start-up control" in Production Zone 1.
[0027] The first / second initial values can be preset based on the design rated parameters of the thermal power unit and the best operation and maintenance experience of similar units. This avoids the target value from deviating from the reasonable range due to the lack of reference values during the cold start phase, and ensures the operational stability of the unit during the start-up phase.
[0028] Step S102: Determine the load status and fluctuation status of the thermal power unit based on the current operating data, and determine the optimization activation flag based on the fluctuation status, current operating data and historical average values.
[0029] In some embodiments, the current running data includes the current values of the parameters; step S102, based on the fluctuation state, the current running data, and the historical average value, determines the optimization activation flag, including: Step S1021: When the current value is less than the historical average and the fluctuation state is in a steady state, the optimization activation flag is set to the first flag value.
[0030] Step S1022: If the current value is greater than or equal to the historical average, or if the fluctuation state is not steady, set the optimization activation flag to the second flag value.
[0031] When the operating conditions are not steady (such as sudden changes in unit load or large fluctuations in parameters): the optimization results are prone to failure due to operating condition drift. Set a second flag value (not activated) to save meaningless optimization calculations. When the current value is greater than or equal to the historical average (the parameter has reached or exceeded the conventional benchmark): set a second flag value (do not activate) to avoid wasting computing power caused by repeated optimization.
[0032] The flag is set to the first value (activating optimization) only when the current value is less than the historical average (the parameters have room for optimization) and the fluctuation state is in a steady state (the optimization result can be implemented). This logic accurately locks in scenarios with optimization value and stable operating conditions, avoiding ineffective optimization.
[0033] Determining the optimal activation flag only requires two basic operations: comparing numerical values and judging the status. There are no complex algorithms or data calculations, which ensures accurate triggering timing without consuming additional computing power in the production zone.
[0034] Step S103: Determine the target value of the parameter based on the optimization activation flag, load status, current operating data, and historical best value.
[0035] In some embodiments, step S103 specifically includes: Step S1031: Determine whether the power generation of the thermal power unit is within the reference load range based on the load status.
[0036] Step S1032: When the optimization activation flag is the first flag value and the power generation is within the reference load range, determine the target value based on the current value and the historical best value.
[0037] Step S1033: If the optimization activation flag is the second flag value, or the power generation is not within the reference load range, set the current value to the target value.
[0038] First, lock in the optimal parameter range that matches the current load. Only when the power generation falls into the reference load range should the target value be adjusted based on the historical best value. This ensures that the historical best value for optimization reference is the best result verified within the same load segment, rather than an invalid reference across loads. This avoids mismatch between the optimal value and the current load from the source, which could lead to parameter adjustment failure.
[0039] If the power generation exceeds the reference load range (such as special load conditions like unit start-up and shutdown, deep peak shaving, etc.), the current value is directly set as the target value to avoid forcibly adjusting parameters under unstable / atypical load conditions. This ensures the safe operation of the unit and avoids control disturbances caused by ineffective optimization.
[0040] In some embodiments, determining the target value based on the current value and the historical best value in step S1032 includes: Step S201: If the current value is less than the historical best value, set the current value as the target value.
[0041] Step S202: If the current value is greater than or equal to the historical best value, set the historical best value as the target value.
[0042] It only relies on two scalar data points, the current value and the historical best value, both of which are core parameters already stored locally in the DCS. There is no need to retrieve additional data (such as load correction coefficients and operating condition compensation values), thus avoiding data reading latency and resource overhead, and further compressing the overall time consumption of the optimization link.
[0043] The historical best value (the historical average value of the top-performing unit) is the optimal parameter level verified under the same load and steady-state operating conditions. If the current value is greater than or equal to the historical best value, the historical best value is directly set as the target value—this is equivalent to pulling the parameters back to the safe and optimal range verified in practice, ensuring optimal energy efficiency while avoiding deviations from the verified safe range. If the current value is less than the historical best value, the current value is used as the target value—this indicates that the current operating parameters of the unit are already better than the historical best level, and there is no need for forced adjustment (to avoid operating condition fluctuations caused by adjustment). At the same time, this better value is retained as the actual control target to maximize the potential of the unit's energy efficiency.
[0044] Based on a two-layer reference threshold consisting of historical average values (conventional baseline) and historical best values (optimal baseline), combined with dynamic comparison and sliding updates of real-time data, hierarchical decision-making for parameter optimization and control is achieved.
[0045] Historical averages are the moving averages of thermal power unit parameters over a certain time window, reflecting the unit's normal stable operating level. They serve as a basic threshold for judging whether there is room for optimization. This average is updated in real-time as the time window slides, ensuring the benchmark value closely matches the unit's recent operating characteristics and avoiding the lag of static benchmarks. Historical best values (top historical averages) are the moving averages of the top N% of samples with the best parameters within the same time window and load range. They reflect the unit's verified optimal operating level and serve as the core reference threshold for the optimization target value. This best value is also updated as the time window slides, incorporating only recent optimal operating data to avoid interference from outdated, failed data on the optimal benchmark.
[0046] The optimization activation is triggered by comparing the current value with the historical average (first layer), and the final target value is determined by comparing the current value with the historical best value (second layer). This two-layer progressive judgment, combined with load / fluctuation state screening, realizes the control algorithm of sliding benchmark and hierarchical decision-making, which deeply integrates the statistical benchmark of sliding average with the decision logic of optimization control.
[0047] Through the above steps, only the current running data, historical average value, and historical best value are called, without the need to store and process the full amount of high-frequency original historical data, thus reducing storage resource consumption. The optimization process is broken down into three simple steps: state judgment, activation flag determination, and target value output. There is no complex iterative calculation or model reasoning process. The CPU utilization rate can be controlled within the low threshold allowed by production zone 1. It will not compete for resources with the real-time control tasks of DCS, thus solving the problem that the parameter optimization method has high resource consumption and cannot be directly deployed in production zone 1.
[0048] Figure 2 This is a flowchart of a method for optimizing thermal power unit parameters based on real-time data rolling, according to an embodiment of this application. Figure 2 As shown, first input the unit's real-time data, initialization parameters, and steady-state parameters.
[0049] The base reference value (Y1) is calculated. When the algorithm initialization signal is issued, Y1 is the initial value; otherwise, Y1 is output as the historical average value (Y3). The base reference value (Y1) is the starting point and foundation of all calculations. When the system is initialized, it provides the initial value; when other advanced conditions are not met, it serves as the default output value and is the reference benchmark for the entire algorithm.
[0050] Calculate the operating condition screening value (Y2). If the load is within the effective load range, output the real-time value (current value); otherwise, output Y1. The operating condition screening value (Y2) acts as an "operating condition filter." It filters data based on whether the unit is in an effective load range, deciding whether to pass real-time data forward or use the baseline reference value, ensuring that optimization is performed only under appropriate operating conditions.
[0051] Calculate the historical average value (Y3). When the unit is in steady state, output Y3 = (Y2 + Y1 * 9999) / 10000; otherwise, output Y1. The historical average value (Y3) represents the average level of this parameter under stable operating conditions over a period of time and serves as a baseline for judging whether the current performance is "better than usual".
[0052] It should be noted that when the unit is in steady state, the output Y3=(Y2+Y1*9999) / 10000. The new Y3 value will be infinitely close to the old Y1 value, but will have an extremely small offset in the direction of Y2, so as to achieve the "smooth initialization" and "gradual update under steady state" of the historical average value (Y3), thereby ensuring the stability and continuity of the baseline.
[0053] The optimization activation flag (Y4) is calculated. When the real-time value of the unit is less than the historical average value Y3 and the unit is in steady state, the output is 1; otherwise, the output is 0. The optimization activation flag (Y4) is a key logical judgment signal, like a "switch". When it is "1", it means that the two core conditions of "unit steady state" and "current performance is better than the historical average" are met at the same time, allowing the system to challenge and update the historical best record.
[0054] The historical best value (Y5) is calculated. When the unit initialization signal is issued, Y5 is the initial value; otherwise, Y5 is the historical average value. The historical best value (Y5) dynamically stores the best parameter value (such as minimum coal consumption) found by the system under effective operating conditions to date. It is the "record holder" that the system constantly challenges and refreshes.
[0055] Calculate the updated historical best value (Y6), which is the target value. When Y4 is 1 (true) and within the load range, determine if the current real-time value is less than Y5. If it is, then Y6 is the real-time value; otherwise, Y6 is output as Y6=(A+Y5*9999) / 10000, where A is a preset value. When Y4 is 1 (true) and within the load range (not true), Y6 is the real-time value. When the "optimization activation flag" is valid and a better real-time value appears, Y6 will be updated to this new value.
[0056] It should be noted that when Y4 is 1 and within the load range, and the current real-time value is greater than or equal to Y5, the output of Y6 is Y6 = (A + Y5 * 9999) / 10000, instead of directly outputting Y5. As a gentle attenuation or reset mechanism, the new Y6 value will be infinitely close to the old Y5 value, but will have an extremely small, almost imperceptible offset in the direction of A. When the system fails to refresh the historical best record for a long time, the standard is gradually relaxed to allow the algorithm to adapt to the long-term drift of unit performance.
[0057] It should be noted that the steps shown in the above process or in the flowchart of the accompanying figures can be executed in a computer system such as a set of computer-executable instructions, and although a logical order is shown in the flowchart, in some cases the steps shown or described may be executed in a different order than that shown here.
[0058] This embodiment also provides a lightweight thermal power unit parameter optimization device, which is used to implement the above embodiments and preferred embodiments, and will not be repeated as already described. As used below, the terms "module," "unit," "subunit," etc., can refer to a combination of software and / or hardware that performs a predetermined function. Although the device described in the following embodiments is preferably implemented in software, hardware implementation, or a combination of software and hardware, is also possible and contemplated.
[0059] Figure 3 This is a structural block diagram of a lightweight thermal power unit parameter optimization device according to an embodiment of this application. The device is installed in the distributed control system of the thermal power unit, such as... Figure 3 As shown, the device includes: The data acquisition module 31 is used to acquire the current operating data and historical operating data of the thermal power unit. The historical operating data includes the historical average value and historical best value of the parameters.
[0060] Analysis module 32 is used to determine the load status and fluctuation status of thermal power units based on current operating data, and to determine the optimization activation flag based on the fluctuation status, current operating data and historical average values.
[0061] The target value determination module 33 is used to determine the target value of the parameter based on the optimization activation flag, load status, current operating data and historical best value.
[0062] In some embodiments, the current running data includes the current values of the parameters; the analysis module includes: The first label determination module is used to set the optimization activation flag to the first flag value when the current value is less than the historical average and the fluctuation state is in a steady state.
[0063] The second labeling determination module is used to set the optimization activation flag to the second flag value when the current value is greater than or equal to the historical average value, or when the fluctuation state is not steady.
[0064] In some embodiments, the target value determination module includes: The judgment module is used to determine whether the power generation of the thermal power unit is within the reference load range based on the load status. The first target value determination module is used to determine the target value based on the current value and the historical best value when the optimization activation flag is the first flag value and the power generation is within the reference load range. The second target value determination module is used to set the current value as the target value when the optimization activation flag is the second flag value or the power generation is not within the reference load range.
[0065] In some embodiments, the first target value determination module includes: The first setting module is used to set the current value as the target value if the current value is less than the historical best value.
[0066] The second setting module is used to set the historical best value as the target value when the current value is greater than or equal to the historical best value.
[0067] In some embodiments, the system further includes an initialization module, configured to initialize the historical average value to a preset first initial value and the historical best value to a preset second initial value in response to an initialization signal.
[0068] The above-mentioned device only calls the current running data, historical average value and historical best value, without storing and processing the full amount of high-frequency original historical data, thus reducing storage resource consumption. The optimization process is broken down into three simple steps: state judgment, activation flag determination and target value output. There is no complex iterative calculation or model reasoning process. The CPU utilization rate can be controlled within the low threshold allowed by production zone 1. It will not compete for resources with the real-time control tasks of DCS, thus solving the problem that the parameter optimization method has high resource consumption and cannot be directly deployed in production zone 1.
[0069] It should be noted that the above modules can be functional modules or program modules, and can be implemented through software or hardware. For modules implemented through hardware, the above modules can reside in the same processor; or the above modules can be located in different processors in any combination.
[0070] This embodiment also provides an electronic device, including a memory and a processor, wherein the memory stores a computer program and the processor is configured to run the computer program to perform the steps in any of the above method embodiments.
[0071] Optionally, the electronic device may further include a transmission device and an input / output device, wherein the transmission device is connected to the processor and the input / output device is connected to the processor.
[0072] Optionally, in this embodiment, the processor can be configured to perform the following steps via a computer program: S1, obtain the current operating data and historical operating data of the thermal power unit. The historical operating data includes the historical average value and historical best value of the parameters.
[0073] S2, based on the current operating data, judges the load status and fluctuation status of the thermal power unit, and determines the optimization activation flag based on the fluctuation status, current operating data and historical average value.
[0074] S3 determines the target value of the parameters based on the optimization activation flag, load status, current operating data, and historical best values.
[0075] It should be noted that the specific examples in this embodiment can refer to the examples described in the above embodiments and optional implementations, and will not be repeated here.
[0076] In one embodiment, Figure 4 This is a schematic diagram of the internal structure of an electronic device according to an embodiment of this application, such as... Figure 4 As shown, an electronic device is provided, which can be a server, and its internal structure diagram can be as follows. Figure 4 As shown, this electronic device includes a processor, memory, network interface, and database connected via a device bus. The processor provides computing and control capabilities. The memory includes a non-volatile storage medium and internal memory. The non-volatile storage medium stores the operating system, computer programs, and database. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage medium. The database stores data. The network interface communicates with external terminals via a network connection. When the computer program is executed by the processor, it implements a lightweight method for optimizing thermal power unit parameters.
[0077] Those skilled in the art will understand that Figure 4 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the electronic device to which the present application is applied. The specific electronic device may include more or fewer components than shown in the figure, or combine certain components, or have different component arrangements.
[0078] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. This computer program can be stored in a non-volatile computer-readable storage medium. When executed, the computer program can include the processes of the embodiments of the above methods. Any references to memory, storage, databases, or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), dual data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), RAMbus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.
[0079] Those skilled in the art should understand that the technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments have been described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.
[0080] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the invention patent. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this patent application should be determined by the appended claims.
Claims
1. A lightweight thermal power unit parameter optimization method, characterized in that, The method is applied to the distributed control system of a thermal power unit, and the method includes: Acquire the current and historical operating data of the thermal power unit, wherein the historical operating data includes the historical average and historical best values of the parameters; The load status and fluctuation status of the thermal power unit are determined based on the current operating data, and an optimization activation flag is determined based on the fluctuation status, the current operating data, and the historical average value. The target value of the parameter is determined based on the optimization activation flag, the load status, the current operating data, and the historical best value.
2. The method according to claim 1, characterized in that, The current operating data includes the current values of the parameters; determining the optimization activation flag based on the fluctuation state, the current operating data, and the historical average includes: If the current value is less than the historical average value and the fluctuation state is in a steady state, the optimization activation flag is set to the first flag value. If the current value is greater than or equal to the historical average value, or if the fluctuation state is not steady, the optimization activation flag is set to the second flag value.
3. The method according to claim 2, characterized in that, The step of determining the target value of the parameter based on the optimization activation flag, the load status, the current operating data, and the historical best value includes: Based on the load status, determine whether the power generation of the thermal power unit is within the reference load range; When the optimization activation flag is the first flag value and the power generation is within the reference load range, the target value is determined based on the current value and the historical best value. If the optimization activation flag is the second flag value, or if the power generation is not within the reference load range, the current value is set to the target value.
4. The method according to claim 3, characterized in that, Determining the target value based on the current value and the historical best value includes: If the current value is less than the historical best value, the current value is set as the target value; If the current value is greater than or equal to the historical best value, the historical best value is set as the target value.
5. The method according to claim 1, characterized in that, The method further includes: In response to the initialization signal, the historical average value is initialized to a preset first initial value, and the historical best value is initialized to a preset second initial value.
6. A lightweight thermal power unit parameter optimization device, characterized in that, The device is installed in the distributed control system of the thermal power unit, and the device includes: The data acquisition module is used to acquire the current operating data and historical operating data of the thermal power unit. The historical operating data includes the historical average value and historical best value of the parameters. The analysis module is used to determine the load status and fluctuation status of the thermal power unit based on the current operating data, and to determine the optimization activation flag based on the fluctuation status, the current operating data and the historical average value. The target value determination module is used to determine the target value of the parameter based on the optimization activation flag, the load status, the current operating data, and the historical best value.
7. The apparatus according to claim 6, characterized in that, The current running data includes the current values of the parameters; The analysis module includes: The first labeling determination module is used to set the optimization activation flag to a first flag value when the current value is less than the historical average value and the fluctuation state is a steady state. The second labeling determination module is used to set the optimization activation flag to a second flag value when the current value is greater than or equal to the historical average value, or when the fluctuation state is not steady.
8. The apparatus according to claim 7, characterized in that, The target value determination module includes: The judgment module is used to determine whether the power generation of the thermal power unit is within the reference load range based on the load status. The first target value determination module is used to determine the target value based on the current value and the historical best value when the optimization activation flag is the first flag value and the power generation is within the reference load range. The second target value determination module is used to set the current value as the target value when the optimization activation flag is the second flag value or the power generation is not within the reference load range.
9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the lightweight thermal power unit parameter optimization method as described in any one of claims 1 to 5.
10. A storage medium having a computer program stored thereon, characterized in that, When the program is executed by the processor, it implements the lightweight thermal power unit parameter optimization method as described in any one of claims 1 to 5.