Intelligent operation method and system for thermal power plant, device, and storage medium

Abstract

The present application relates to the technical field of thermal power plants, and discloses an intelligent operation method and system for a thermal power plant, a device, and a storage medium. The method comprises: measuring operation parameters of a thermal power plant in real time by means of advanced detection and soft sensing techniques; establishing a fault monitoring model to monitor the operation process of the thermal power plant on the basis of the real-time detected operation parameters, and generating an early warning signal when a fault occurs; performing fault diagnosis, and generating a fault self-healing instruction; and evaluating the operation status of the thermal power plant by means of a performance evaluation model, and then obtaining optimal operation modes and optimal operation parameter setpoints by means of a multi-objective optimization algorithm. The present application achieves high-performance real-time intelligent closed-loop control, improving the adaptability to complex working conditions and the disturbance rejection capability of a thermal power plant production process control system, and the overall performance of a thermal power plant production process; and efficient human-computer interaction is achieved by means of artificial intelligence-based early warning diagnosis and closed-loop self-healing.

Description

A method, system, device and storage medium for intelligent operation of a thermal power plant

[0001] The present application claims priority to the Chinese patent application No. 202410872632.0, filed on July 1, 2024, and entitled "A method, system, device and storage medium for intelligent operation of a thermal power plant", the entire content of which is incorporated herein by reference. TECHNICAL FIELD

[0002] The present application belongs to the technical field of thermal power plants and relates to a method, system, device and storage medium for intelligent operation of a thermal power plant. BACKGROUND

[0003] As a core unit of power production, the intelligentization and wisdom of the production and operation process of a thermal power plant is not only an inevitable trend of technological innovation, but also a key to ensuring stable, efficient and environmentally friendly power supply.

[0004] Under the new power system environment, with a high proportion of random and volatile new energy connected to the power grid, thermal power units are deep in peak regulation and fast peak regulation, and need to face multiple pressures such as energy saving and consumption reduction, environmental protection monitoring, and network regulation assessment, which puts higher requirements on the operation performance of thermal power units. The design and transformation of the unit body and auxiliary equipment are the foundation, and the intelligentization and wisdom of the production and operation process are the key. However, the existing wisdom support architecture of the thermal power control system is not perfect, the big data learning network and the real-time control network are not balanced and matched; the existing controller algorithm and computing power are insufficient, which is difficult to support the rapid development of the wisdom application of thermal power units; the existing unmanned intervention and few-man on-duty wisdom operation function is not perfect, and manual intervention is frequent and labor-intensive in the production process of thermal power.

[0005] In summary, it is of great significance to analyze the requirements of the wisdom of the production process of the thermal power plant on the industrial control system network, data, algorithm, computing power, and the urgent need for unmanned intervention and few-man on-duty, and to study a wisdom operation architecture and function of the thermal power plant. SUMMARY

[0006] The present application provides a method, system, device and storage medium for intelligent operation of a thermal power plant to solve the technical problems of imperfect wisdom operation function, frequent manual intervention and high labor intensity in the prior art.

[0007] To achieve the above-mentioned purpose, the present application adopts the following technical solution:

[0008] In a first aspect, the present application provides a method for intelligent operation of a thermal power plant, comprising the following steps:

[0009] detecting and calculating the operation parameters of the thermal power plant;

[0010] According to the operation parameters of the thermal power plant, monitoring is performed through a fault monitoring model, and a warning is generated when a fault occurs;

[0011] According to the warning data, fault diagnosis is performed, the fault is located, and a fault self-recovery instruction is generated;

[0012] According to the fault self-recovery instruction and the operation parameters, the safety and stability, the economic and environmental performance, and the flexibility and maneuverability of the thermal power plant are evaluated through a performance evaluation model;

[0013] The evaluation results are weighted, and the optimal operation mode and the best operation parameter set value are obtained through a multi-objective optimization algorithm.

[0014] Optionally, the step of detecting and calculating the operation parameters of the thermal power plant specifically includes detecting coal quality, coal flow, furnace conditions, boiler flue gas, oil, and equipment vibration; and calculating boiler heat storage coefficient, coal calorific value, raw coal moisture, flue gas oxygen content, furnace coking, air preheater blockage, steam flow, low-pressure cylinder exhaust enthalpy, and dryness.

[0015] Optionally, the step of monitoring according to the operation parameters of the thermal power plant through a fault monitoring model and generating a warning when a fault occurs specifically includes comparing the operation parameters of the thermal power plant with historical operation parameters through the fault monitoring model to generate a monitoring index; if the monitoring index does not exceed a preset threshold, the unit is operating normally; and if the monitoring index exceeds the preset threshold, a warning is generated.

[0016] Optionally, the fault monitoring model is a fault monitoring model established based on a neural network fitting algorithm.

[0017] Optionally, the step of performing fault diagnosis according to the warning data, locating the fault, and generating a fault self-recovery instruction specifically includes:

[0018] A self-encoding fault feature extraction method is used to extract historical operation parameters of the thermal power plant to form a fault feature library.

[0019] A self-encoding fault feature extraction method is used to extract data features in the warning data, and the data features are compared with fault data features in the fault feature library to locate the fault and generate a fault self-recovery instruction.

[0020] For fault types not included in the fault feature library, the fault feature library is updated.

[0021] Optionally, the indicators of safety and stability include control quality evaluation, actuator performance evaluation, equipment health degree evaluation, and heated surface state evaluation; the indicators of economic and environmental performance include performance calculation, consumption difference analysis, and pollution removal performance evaluation; and the indicators of flexibility and maneuverability include two detailed rule indicators of AGC and primary frequency modulation.

[0022] Optionally, the step of performing multi-objective weighting on the evaluation results to obtain the optimal operation mode and the optimal operation parameter value by a multi-objective optimization algorithm specifically comprises: performing multi-objective weighting on the safety and stability, the economy and environmental protection, and the flexibility and maneuverability of the thermal power plant, and performing traversal optimization according to the weighted optimization target by using a genetic algorithm, a particle swarm algorithm, a simulated annealing algorithm, a dynamic programming algorithm, or a gradient descent algorithm to obtain the optimal operation mode and the optimal operation parameter value under different load conditions.

[0023] In a second aspect, the present application provides a smart operation system for a thermal power plant, comprising:

[0024] a detection module configured to detect and calculate operation parameters of the thermal power plant;

[0025] a warning module configured to monitor the thermal power plant by a fault monitoring model according to the operation parameters of the thermal power plant, and generate a warning when a fault occurs;

[0026] a diagnosis module configured to perform fault diagnosis according to the warning data, locate the fault, and generate a fault self-healing instruction;

[0027] an evaluation module configured to evaluate the safety and stability, the economy and environmental protection, and the flexibility and maneuverability of the thermal power plant by a performance evaluation model according to the fault self-healing instruction and the operation parameters;

[0028] an optimization module configured to perform multi-objective weighting on the evaluation results, and obtain the optimal operation mode and the optimal operation parameter value by a multi-objective optimization algorithm.

[0029] In a third aspect, the present application provides a computer device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the above method when executing the computer program.

[0030] In a fourth aspect, the present application provides a computer readable storage medium, wherein the computer readable storage medium stores a computer program, and the computer program implements the steps of the above method when executed by a processor.

[0031] Compared with the prior art, the present application has the following beneficial effects:

[0032] The application discloses a thermal power plant intelligent operation method, system, device and storage medium, real-time measurement of the operation parameters of the thermal power plant is performed through advanced detection and soft measurement technology; a fault monitoring model is established, the operation process of the thermal power plant is monitored according to the real-time detected operation parameters, a warning signal is generated when a fault occurs; fault diagnosis is performed to generate a fault self-healing instruction; the operation condition of the thermal power plant is evaluated through a performance evaluation model, and then the optimal operation mode and the best operation parameter set value are obtained through a multi-objective optimization algorithm. The application clearly divides the application functions of intelligent operation from four dimensions of thermal power plant production process detection, control, optimization and decision, forms four application function systems of autonomous perception, flexible adjustment, operation optimization and intelligent decision, realizes high-performance real-time intelligent closed-loop control, improves the complex working condition adaptability and anti-disturbance capability of the thermal power plant production process control system and the comprehensive performance of the thermal power plant production process; and realizes efficient human-computer interaction through artificial intelligence early warning diagnosis and closed-loop self-healing. BRIEF DESCRIPTION OF DRAWINGS

[0033] In order to more clearly illustrate the technical solutions of the embodiments of the application, the following will briefly introduce the drawings needed to be used in the embodiments. It should be understood that the following drawings only show some of the embodiments of the application, and therefore should not be regarded as a limitation on the scope. For those skilled in the art, other related drawings can also be obtained without creative labor on the basis of these drawings.

[0034] Fig. 1 is a flow chart of the method of the application;

[0035] Fig. 2 is a schematic diagram of the system of the application;

[0036] Fig. 3 is a schematic diagram of the operation parameter detection of the thermal power plant in the embodiment of the application;

[0037] Fig. 4 is a schematic diagram of the performance evaluation in the embodiment of the application;

[0038] Fig. 5 is a schematic diagram of the early warning diagnosis in the embodiment of the application;

[0039] Fig. 6 is a whole function architecture diagram of the embodiment of the application;

[0040] Fig. 7 is a schematic diagram of the network architecture in the embodiment of the application;

[0041] Fig. 8 is a schematic diagram of the closed-loop control in the embodiment of the application;

[0042] Fig. 9 is a schematic diagram of the computer device structure of the application. DETAILED DESCRIPTION

[0043] In order to make the purpose, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only some of the embodiments of the present application, rather than all the embodiments of the present application. The components of the embodiments of the present application described and shown in the drawings can be arranged and designed in various different configurations.

[0044] Therefore, the detailed description of the embodiments of the present application provided below in the drawings is not intended to limit the scope of the claimed present application, but only represents selected embodiments of the present application. All other embodiments obtained by those of ordinary skill in the art based on the embodiments in the present application without making creative efforts fall within the scope of protection of the present application.

[0045] It should be noted that: similar reference numbers and letters represent similar items in the following drawings, therefore, once an item is defined in one drawing, it does not need to be alternatively defined and explained in subsequent drawings.

[0046] In the description of the embodiments of the present application, it should be noted that, if the orientation or position relationship indicated by the terms "upper", "lower", "horizontal", "inner" and the like is based on the orientation or position relationship shown in the drawings, or is the orientation or position relationship when the product of the present application is usually placed, which is only for the convenience of describing the present application and simplifying the description, and does not indicate or imply that the indicated device or element must have a particular orientation, be constructed and operated in a particular orientation, therefore, it cannot be understood as a limitation on the present application. In addition, the terms "first", "second" and the like are only used for differentiation in description, and cannot be understood as indicating or implying relative importance.

[0047] In addition, if the term "horizontal" appears, it does not mean that the component must be absolutely horizontal, but can be slightly inclined. For example, "horizontal" only means that its direction is relatively more horizontal than "vertical", and does not mean that the structure must be completely horizontal, but can be slightly inclined.

[0048] In the description of the embodiments of the present application, it should also be noted that, unless otherwise explicitly specified and limited, if the terms "arrange", "mount", "connect", "connect" appear, they should be understood in a broad sense, for example, can be fixedly connected, can be detachably connected, or integrally connected; can be mechanically connected, can be electrically connected; can be directly connected, can be indirectly connected through an intermediate medium, can be the communication inside two elements. For those of ordinary skill in the art, the specific meaning of the above terms in the present application can be understood according to the specific circumstances.

[0049] The present application will be described in further detail below with reference to the drawings:

[0050] Referring to FIG. 1, the embodiment of the present application discloses a method for intelligent operation of a thermal power plant, comprising the following steps:

[0051] S1, detecting and calculating the operation parameters of the thermal power plant;

[0052] The operation parameters of the thermal power plant are obtained through advanced detection and soft measurement. Referring to FIG. 3, the advanced detection takes advanced sensors as carriers, and uses microwaves, lasers, infrared rays, static electricity, sound waves, capacitance, charge, etc. to realize online accurate measurement and uploading of traditionally difficult-to-measure parameters of the thermal power plant. The advanced detection range includes coal quality (coal moisture, coal element, composition), coal powder flow (concentration, fineness, flow rate), in-furnace working condition (temperature field, flue gas composition), boiler flue gas (carbon content of fly ash, ammonia escape, flue gas composition), oil (viscosity, moisture, abrasive particle concentration, cleanliness, conductivity, dielectric constant), equipment vibration, etc. The soft measurement takes intelligent computing servers as carriers, and uses soft computing, information fusion, etc. to realize online calculation and evaluation of intermediate difficult-to-measure parameters in the production process of the thermal power plant. The soft measurement range includes boiler heat storage coefficient, coal calorific value, raw coal moisture, flue gas oxygen content, in-furnace coking, air preheater blockage, steam flow, low-pressure cylinder exhaust enthalpy and dryness, etc. The advanced detection and soft measurement provide accurate data sources for subsequent early warning diagnosis and optimization, and lay an important foundation for guaranteeing safe and stable operation of the boiler, improving the quality of the control system, and reducing energy consumption and material consumption.

[0053] S2, monitoring through a fault monitoring model according to the operation parameters of the thermal power plant, and generating an early warning when a fault occurs;

[0054] Referring to FIG. 4, the fault monitoring model is established based on a neural network fitting algorithm. The step of monitoring through the fault monitoring model and generating an early warning when a fault occurs specifically comprises: comparing the operation parameters of the thermal power plant with historical operation parameters through the fault monitoring model to generate a monitoring index; if the monitoring index does not exceed a preset threshold, the unit is running normally; and if the monitoring index exceeds the preset threshold, an early warning is generated.

[0055] S3, performing fault diagnosis according to the early warning data, locating the fault, and generating a fault self-recovery instruction, as shown in FIG. 4;

[0056] S301, extracting historical operation parameters of the thermal power plant through a self-encoding fault feature extraction method to form a fault feature library;

[0057] S302, extracting data features in the early warning data through the self-encoding fault feature extraction method, and comparing the data features with fault data features in the fault feature library to locate the fault and generate a fault self-recovery instruction;

[0058] S303, updating the fault feature library for a fault type not contained in the fault feature library.

[0059] S4, according to the fault self-healing instruction and the operation parameter, evaluating the safety and stability, the economic and environmental performance and the flexible maneuverability of the thermal power plant through a performance evaluation model, as shown in Fig. 5;

[0060] The present application performs online evaluation through a performance evaluation model, and the evaluation content includes safety and stability, economic and environmental performance and flexible maneuverability. The safety and stability indicators should include control quality evaluation, actuator performance evaluation, equipment health evaluation, and heating surface state evaluation. The economic and environmental performance indicators should include performance calculation and consumption difference analysis, and pollution removal performance evaluation. The flexible maneuverability indicators should include AGC and the "two rules" indicators of primary frequency modulation.

[0061] S5, multi-objective weighting is performed on the evaluation results, and the optimal operation mode and the best operation parameter setting value are obtained through a multi-objective optimization algorithm, as shown in Fig. 5.

[0062] The safety and stability, the economic and environmental performance and the flexible maneuverability of the thermal power plant are multi-objective weighted, and a genetic algorithm, a particle swarm algorithm, a simulated annealing algorithm, a dynamic programming algorithm or a gradient descent algorithm is used to perform traversal optimization according to the weighted optimization target, so as to obtain the best operation mode and the best operation parameter setting value under different load conditions, and realize multi-objective optimization.

[0063] It should be noted that the method of the present application designs the application function and function architecture of intelligent operation from the four dimensions of detection, control, optimization and decision of the production process of the thermal power plant. The functions include autonomous perception, flexible adjustment, operation optimization and intelligent decision. The autonomous perception is completed by online measurement and calculation of advanced sensors or soft measurement technology. The flexible adjustment is completed by advanced intelligent algorithms and configuration strategies in the intelligent controller. The operation optimization is completed by the performance evaluation model and the multi-objective optimization algorithm in the intelligent calculation server. The intelligent decision is completed by the artificial intelligence monitoring model, the fault feature extraction and the fault feature library in the big data analysis server. The function architecture refers to the connection relationship among the four, the autonomous perception provides a reliable data source for the flexible adjustment, the operation optimization and the intelligent decision, the flexible adjustment executes the optimal operation mode and the best operation parameter setting value output by the operation optimization, and completes the automatic start and stop, the withdrawal, the rotation and the line pressure control of the key simulation parameters of the equipment. The intelligent decision performs online early warning according to the abnormal state and the fault of the system, the equipment and the parameters, and actively decides to adjust the operation optimization mode, intervenes the control loop, and completes the closed-loop fault self-healing, as shown in Fig. 6.

[0064] Referring to Fig. 2, the embodiment of the present application discloses an intelligent operation system of a thermal power plant, which comprises:

[0065] A detection module is configured to detect and calculate the operation parameters of the thermal power plant.

[0066] An early warning module is configured to monitor the power plant operation parameters through a fault monitoring model and generate an early warning when a fault occurs;

[0067] A diagnosis module is configured to perform fault diagnosis according to the early warning data, locate the fault and generate a fault self-recovery instruction;

[0068] An evaluation module is configured to evaluate the safety and stability, economic and environmental performance and flexibility and maneuverability of the power plant through a performance evaluation model according to the fault self-recovery instruction and the operation parameters;

[0069] An optimization module is configured to perform multi-objective weighting on the evaluation results and obtain optimal operation modes and optimal operation parameter settings through a multi-objective optimization algorithm.

[0070] It should be noted that, as shown in FIG. 7, according to the requirements of the intelligentization of the production process of the thermal power plant on the industrial control system network, data, algorithms, and computing power, the application designs a high-performance intelligent operation system hardware and network. The hardware includes advanced sensors, intelligent controllers, database servers, intelligent computing servers, data analysis servers, and visualization display servers. The advanced sensors are used for online measurement of difficult-to-measure parameters in the thermal power production process. The intelligent controllers are used for high-performance real-time closed-loop control of the thermal power on-off quantity and analog quantity control loop. The database servers are used for collection and storage of thermal power production process data. The intelligent computing servers are used for online evaluation and multi-objective optimization of the thermal power production process performance. The data analysis servers are used for early warning, diagnosis, and decision-making of abnormal states or faults of the thermal power system, equipment, and parameters. The visualization display servers are used for visualization display of thermal power production indicators and early warning diagnosis information. The network includes a high-performance real-time control network, a data high-speed communication network, and an anti-impact tidal network. The high-performance real-time control network realizes efficient interaction of control instructions between the intelligent controllers and other controllers. The data high-speed communication network realizes high-reliability and high-speed communication of data between the DCS and external high-performance storage, computing, and analysis environment. The anti-impact tidal network realizes batch and concurrent efficient interaction of historical data between the high-performance database and the analysis and publishing engine. The data high-speed communication network and the anti-impact tidal network perform their respective functions without occupying the load of the high-performance real-time control network. Based on the closed-loop application requirements of the intelligentization of the thermal power plant production process and the requirements of the safety and reliability partition of the thermal power plant by the Ministry of Industry and Information Technology, the application designs a safety protection method for the intelligent operation closed-loop control network. The intelligent operation and the DCS have the same safety and reliability level and are set in the safety and reliability area of the thermal power plant. By setting a firewall between the intelligent operation system and the DCS, network security isolation between the intelligent operation system and the DCS is realized. At the same time, by using distributed network space asset detection and host environment forced access control technology, security protection functions such as active white list, efficient host guard, and active intrusion detection are realized, unknown vulnerabilities, Trojan horses, and virus attacks and intrusions are effectively prevented, the possibility of important data being tampered with or stolen is eliminated, and the network safety and reliability of the intelligent operation is ensured, and the ability of the intelligent operation to resist internal and external risks is strengthened.

[0071] Referring to FIG. 9, the embodiment of the application discloses a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, and the processor implements the steps of the above method when executing the computer program.

[0072] The embodiment of the application discloses a computer readable storage medium, which stores a computer program, and the computer program is executed by a processor to implement the steps of the above method.

[0073] It should be noted that, referring to Fig. 8, based on the dynamic characteristics of the production process of the thermal power plant, the application designs a high-performance real-time intelligent closed-loop control method for smart operation with an intelligent controller as a carrier, including advanced intelligent algorithm and control strategy intelligent heterogeneity. In terms of advanced intelligent algorithm, the highly open application development environment of the intelligent controller is used to complete the packaging of advanced intelligent algorithm modules such as predictive control, fuzzy control, internal model control, Smith prediction, tracking differentiation, Kalman filtering, state observation, phase compensation, and step sequence control. The advanced intelligent algorithm modules and the traditional modules use a unified configuration debugging environment and a redundancy mechanism to ensure the reliability of the high-performance real-time intelligent closed-loop control and reduce the maintenance difficulty of the operating personnel. In terms of control strategy intelligent heterogeneity, the flexible configuration of the advanced intelligent algorithm module is used to complete the design of the specific process control strategy of the thermal power plant, including the highly automated control (start-stop, parallel-retreat, and conversion) of the core subsystems (coal mills, water pumps, and dry-wet states), and the intelligent control of key analog systems such as coordination, steam temperature, and environmental protection. This reduces the labor intensity of the operating personnel, realizes the line pressure operation of the process parameters, and improves the stability, economy, and rapidity of the unit operation.

[0074] Those skilled in the art will understand that the embodiments of the application can be provided as methods, systems, or computer program products. Therefore, the application can take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Moreover, the application can take the form of a computer program product implemented on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROMs, optical storage, etc.) containing computer-usable program code.

[0075] The application is described with reference to flowcharts and / or block diagrams according to the methods, devices (systems), and computer program products of the embodiments of the application. It should be understood that each flow and / or block in the flowcharts and / or block diagrams, and the combination of flows and / or blocks in the flowcharts and / or block diagrams can be implemented by computer program instructions. These computer program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing devices to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing devices produce the functions specified in one or more flows in the flowcharts and / or one or more blocks in the block diagrams.

[0076] These computer program instructions can also be stored in a computer-readable storage medium that can guide the computer or other programmable data processing devices to work in a specific manner, so that the instructions stored in the computer-readable storage medium produce a product including instruction devices that implement the functions specified in one or more flows in the flowcharts and / or one or more blocks in the block diagrams.

[0077] These computer program instructions can also be loaded into computer or other programmable data processing devices, so that a series of operational steps are performed on the computer or other programmable data processing devices to generate computer-implemented processes, thus the instructions executed on the computer or other programmable data processing devices provide steps for implementing the functions specified in one or more flows in the flowchart and / or one or more blocks in the block diagram.

[0078] Finally, it should be noted that: the above examples are only used to illustrate the technical solutions of the present application, but not to limit it, although the present application has been described in detail with reference to the above examples, those skilled in the art should understand: the specific embodiments of the present application can still be modified or replaced by the equivalent, without departing from the spirit and scope of the present application, any modification or equivalent replacement, which should be covered within the protection scope of the claims of the present application.

Claims

1. A method for intelligent operation of a thermal power plant, characterized in that, The method comprises the following steps: detecting and calculating the operation parameters of the thermal power plant; monitoring through a fault monitoring model according to the operation parameters of the thermal power plant, and generating a warning when a fault occurs; diagnosing a fault according to the warning data, locating the fault, and generating a fault self-recovery instruction; evaluating the safety and stability, the economy and environmental protection, and the flexibility and maneuverability of the thermal power plant through a performance evaluation model according to the fault self-recovery instruction and the operation parameters; multi-objectively weighting the evaluation results, and obtaining the optimal operation mode and the best operation parameter set value through a multi-objective optimization algorithm.

2. The method of claim 1, wherein, The step of detecting and calculating the operation parameters of the thermal power plant specifically comprises: detecting the coal quality, the coal powder flow, the furnace working condition, the boiler flue gas, the oil liquid, and the equipment vibration; and calculating the boiler heat storage coefficient, the coal calorific value, the raw coal moisture, the flue gas oxygen content, the furnace coking, the air preheater blockage, the steam flow, the low-pressure cylinder exhaust steam enthalpy, and the dryness.

3. The method of claim 1, wherein, The step of monitoring through the fault monitoring model according to the operation parameters of the thermal power plant, and generating a warning when a fault occurs specifically comprises: comparing the operation parameters of the thermal power plant with the historical operation parameters through the fault monitoring model, generating a monitoring index, and if the monitoring index does not exceed a preset threshold value, the unit is running normally, and if the monitoring index exceeds the preset threshold value, a warning is generated.

4. The method of claim 3, wherein, The fault monitoring model is a fault monitoring model established based on a neural network fitting algorithm.

5. The method of claim 1, wherein, The step of diagnosing a fault according to the warning data, locating the fault, and generating a fault self-recovery instruction specifically comprises: extracting the historical operation parameters of the thermal power plant through a self-encoding fault feature extraction method, and forming a fault feature library; extracting the data features in the warning data through the self-encoding fault feature extraction method, comparing the data features with the fault data features in the fault feature library, locating the fault, and generating a fault self-recovery instruction; updating the fault feature library for a fault type not contained in the fault feature library.

6. The method of claim 1, wherein, The indexes of the safety and stability include control quality evaluation, actuator performance evaluation, equipment health degree evaluation, and heated surface state evaluation; the indexes of the economy and environmental protection include performance calculation, consumption difference analysis, and pollution removal performance evaluation; and the indexes of the flexibility and maneuverability include two detailed rule indexes of AGC and primary frequency modulation.

7. The method of claim 1, wherein, The step of multi-objectively weighting the evaluation results, and obtaining the optimal operation mode and the best operation parameter set value through a multi-objective optimization algorithm specifically comprises: multi-objectively weighting the safety and stability, the economy and environmental protection, and the flexibility and maneuverability of the thermal power plant, and using a genetic algorithm, a particle swarm algorithm, a simulated annealing algorithm, a dynamic programming algorithm, or a gradient descent algorithm to traverse and optimize according to the weighted optimization target, so as to obtain the best operation mode and the best operation parameter set value under different load conditions.

8. A smart operation system for a thermal power plant, characterized in that, The method comprises: a detection module for detecting and calculating the operation parameters of the thermal power plant; a warning module for monitoring through a fault monitoring model according to the operation parameters of the thermal power plant, and generating a warning when a fault occurs; a diagnosis module for diagnosing a fault according to the warning data, locating the fault, and generating a fault self-recovery instruction; an evaluation module for evaluating the safety and stability, the economy and environmental protection, and the flexibility and maneuverability of the thermal power plant through a performance evaluation model according to the fault self-recovery instruction and the operation parameters; and An optimization module is configured to perform multi-objective weighting on the evaluation results, and obtain an optimal operation mode and optimal operation parameter setting value through a multi-objective optimization algorithm.

9. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, The computer program, when executed by the processor, implements the steps of the method according to any one of claims 1-7.

10. A computer-readable storage medium storing a computer program, the computer program comprising instructions that, when executed by a computer, cause the computer to perform the method of any one of claims 1 to 9. The computer program, when executed by the processor, implements the steps of the method according to any one of claims 1-7.

Images