Intelligent collaborative operation method for thermal power plant, and related apparatus

Abstract

The present application belongs to the field of energy digitalization and intelligence. Disclosed are an intelligent collaborative operation method for a thermal power plant, and a related apparatus. The method comprises the following steps: processing real-time operation data by means of a fault monitoring model to obtain monitoring indicators, determining whether the monitoring indicators exceed a preset threshold value, and if so, issuing an early warning; extracting features of the real-time operation data during the issuing of the early warning, and comparing same with a fault feature library to obtain a fault self-healing instruction; on the basis of an intelligent cruise model, obtaining optimal operation modes and optimal operation parameters of a thermal power unit; and on the basis of the fault self-healing instruction, completing closed-loop fault self-healing of the thermal power unit, and on the basis of the optimal operation modes and the optimal operation parameters, adjusting operation parameters and a control scheme of the thermal power unit, so as to complete an intelligent collaborative operation of a thermal power plant. The present application can solve the problem of low integration and interactivity among operation modules when a thermal power plant uses the prior art to operate.

Description

A method and related device for intelligent collaborative operation of a thermal power plant

[0001] The present application claims priority to the Chinese patent application No. 202410872643.9, filed on July 1, 2024, and entitled "A method and related device for intelligent collaborative 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 field of energy digitization and intelligence, and specifically relates to a method and related device for intelligent collaborative operation of a thermal power plant. BACKGROUND

[0003] Under the new power system environment, thermal power peak shaving and frequency modulation has become the norm. In the face of multiple pressures such as energy saving and consumption reduction, environmental protection monitoring, and network regulation evaluation, there are frequent manual interventions to key systems, equipment, and parameters, resulting in high labor intensity. At present, although research institutes, universities and colleges, and control equipment manufacturers at home and abroad have carried out a lot of research and application in detection, control, diagnosis, optimization, etc., and have formed corresponding functional modules, but each functional module is relatively independent, and the fusion interaction is insufficient, which is difficult to support the goal of unmanned intervention and few people on duty in the production process of the thermal power plant.

[0004] Therefore, it is of great significance to deeply analyze the expected goals and connection relationships of each functional module in the production process of the thermal power plant, and to study a collaborative method of a thermal power plant intelligent operation module. SUMMARY

[0005] The present application provides a method and related device for intelligent collaborative operation of a thermal power plant to solve the problem of low fusion interaction of each operation module when the thermal power plant uses the prior art.

[0006] To achieve the above-mentioned purpose, the present application adopts the following technical solution:

[0007] A method for intelligent collaborative operation of a thermal power plant, comprising the following steps:

[0008] Collecting real-time operation data of a thermal power unit, the real-time operation data obtaining a monitoring index through a fault monitoring model, judging whether the monitoring index exceeds a preset threshold, if yes, performing a warning, and if no, the thermal power unit maintaining normal operation;

[0009] Extracting features of the real-time operation data when performing a warning, and comparing with a fault feature library to obtain a fault self-healing instruction;

[0010] Establishing an intelligent cruise model, and obtaining optimal operation mode and optimal operation parameters of the thermal power unit according to the intelligent cruise model;

[0011] According to the fault self-healing instruction, the fault closed-loop self-healing of the thermal power generating unit is completed, and meanwhile, the operation parameters and the control scheme of the thermal power generating unit are adjusted according to the optimal operation mode and the optimal operation parameters, so as to complete the intelligent collaborative operation of the thermal power plant.

[0012] In some embodiments, the fault monitoring model is obtained by the following steps:

[0013] The historical operation data of the thermal power generating unit are collected, and the fault monitoring model is established according to the historical operation data and by using a neural network fitting algorithm.

[0014] The fault feature library is obtained by the following steps:

[0015] The common fault information of the thermal power generating unit is obtained according to the historical operation data and by using self-encoding fault feature extraction, and the fault feature library is established according to the common fault information of the thermal power generating unit.

[0016] In some embodiments, the intelligent cruise model is established by the following steps:

[0017] The non-operable parameters and the operable parameters of the thermal power generating unit are collected, the non-operable parameters and the operable parameters are processed by using historical data mining, and the intelligent cruise model is established.

[0018] In some embodiments, the step of obtaining the optimal operation mode and the optimal operation parameters of the thermal power generating unit according to the intelligent cruise model specifically comprises:

[0019] After the intelligent cruise model outputs the safety and stability data, the economic and environmental protection data and the flexible and maneuverability data, the weighted evaluation or fitness calculation is performed to obtain the optimal operation mode and the optimal operation parameters;

[0020] When the weighted evaluation is used, if the preset iteration number is met, the optimal operation mode and the optimal operation parameters are obtained, and if the preset iteration number is not met, the operable parameters are optimized and traversed to update the intelligent cruise model;

[0021] When the fitness calculation is used, if the calculated fitness meets the preset fitness, the optimal operation mode and the optimal operation parameters are obtained, and if the calculated fitness does not meet the preset fitness, the operable parameters are optimized and traversed to update the intelligent cruise model.

[0022] In some embodiments, the optimization and traversal use a particle swarm algorithm or a genetic algorithm.

[0023] In some embodiments, when the pre-warning is performed, the features of the real-time operation data are extracted and compared with the fault feature library to obtain the fault self-healing instruction, and the step further comprises the following steps:

[0024] When the features of the real-time operation data extracted during the early warning are compared and not in the fault feature library, the features of the real-time operation data are updated into the fault feature library.

[0025] In some embodiments, the method further comprises the following steps:

[0026] The PID control of the thermal power unit is replaced by predictive control, fuzzy control, decoupling control or variable structure control, and the operation parameters and control scheme of the thermal power unit are adjusted in combination with the optimal operation mode and optimal operation parameters.

[0027] A smart collaborative operation system for a thermal power plant, comprising:

[0028] An intelligent monitoring module for collecting real-time operation data of a thermal power unit, the real-time operation data being monitored by a fault monitoring model to obtain a monitoring index, and determining whether the monitoring index exceeds a preset threshold, and if so, performing early warning, and if not, the thermal power unit remains in normal operation; the intelligent monitoring module is also used to extract features of the real-time operation data during early warning, and compare the features with a fault feature library to obtain a fault self-healing instruction.

[0029] An intelligent cruise module for establishing an intelligent cruise model, and obtaining an optimal operation mode and optimal operation parameters of the thermal power unit according to the intelligent cruise model.

[0030] An intelligent control module for completing fault closed-loop self-healing of the thermal power unit according to the fault self-healing instruction, and adjusting operation parameters and control scheme of the thermal power unit according to the optimal operation mode and optimal operation parameters, to complete smart collaborative operation of the thermal power plant.

[0031] An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable in the processor, wherein the processor executes the computer program to implement the steps of the smart collaborative operation method for a thermal power plant.

[0032] A computer readable storage medium storing a computer program, wherein the computer program is executed by a processor to implement the steps of the smart collaborative operation method for a thermal power plant.

[0033] Compared with the prior art, the present application has the following beneficial effects:

[0034] The application provides a smart collaborative operation method of a thermal power plant. Real-time operation data is monitored by a fault monitoring model to obtain a monitoring index. It is determined whether the monitoring index exceeds a preset threshold. If yes, a warning is given. If no, the thermal power unit remains normal operation. When the warning is given, features of the real-time operation data are extracted and compared with a fault feature library to obtain a fault self-healing instruction. Then, an intelligent cruise model is established to obtain an optimal operation mode and optimal operation parameters of the thermal power unit according to the intelligent cruise model. The fault closed-loop self-healing of the thermal power unit is completed according to the fault self-healing instruction. Meanwhile, the operation parameters and control scheme of the thermal power unit are adjusted according to the optimal operation mode and optimal operation parameters to complete the smart collaborative operation of the thermal power plant. The application can discover potential abnormalities and faults of equipment in advance, complete online early warning and closed-loop fault self-healing, improve the efficiency of human-machine interaction, avoid the expansion of the fault range, reduce the risk of unplanned shutdown, ensure the long-period safe and stable operation of the thermal power unit, and output the optimal operation mode and optimal operation parameters through the intelligent cruise model to adaptively adjust the parameters and intelligently change the strategy of the thermal power unit, thereby effectively improving the adaptability of the control system to complex working conditions and complex disturbances and ensuring the stability and convergence of the control system. Therefore, the application can solve the problem of low fusion and interaction of each operation module of the thermal power plant and organically support the goal of unmanned intervention and few people on duty in the production process of the thermal power plant.

[0035] Further, after the intelligent cruise model outputs the safety and stability data, the economic and environmentally friendly data and the flexible maneuverability data, the application performs weighted evaluation or fitness calculation to obtain the optimal operation mode and optimal operation parameters, can obtain the best start-stop, parallel-retirement and rotation time of the thermal power unit, and complete automatic start-stop of equipment and automatic closed-loop optimization of parameter setting, thereby improving the comprehensive performance of the unit and effectively reducing the intensity of manual intervention.

[0036] Further, the application replaces the PID control with the predictive control to optimize the control system and improve the adaptability of the control system to complex working conditions.

[0037] The application provides a smart collaborative operation system of a thermal power plant. The system includes an intelligent monitoring module, an intelligent cruise module and an intelligent control module. The system clearly divides the intelligent function modules from three dimensions of monitoring, optimization and control of the production process of the thermal power plant. The modules have clear division of labor and connection relationship and can organically support the goal of unmanned intervention and few people on duty in the production process of the thermal power plant. BRIEF DESCRIPTION OF DRAWINGS

[0038] Fig. 1 is a functional schematic diagram of the intelligent monitoring module in embodiment one;

[0039] Fig. 2 is a functional schematic diagram of the intelligent cruise module in embodiment one;

[0040] Fig. 3 is a functional schematic diagram of the intelligent control module in embodiment one;

[0041] Fig. 4 is a schematic diagram of the organic integration of the intelligent monitoring module, the intelligent cruise module and the intelligent control in embodiment one;

[0042] Fig. 5 is a flowchart of a method for the intelligent collaborative operation of a thermal power plant provided in embodiment one;

[0043] Fig. 6 is a structural schematic diagram of an intelligent collaborative operation system for a thermal power plant provided in embodiment one;

[0044] Fig. 7 is a structural diagram of an electronic device used in the present application. DETAILED DESCRIPTION

[0045] In order to enable those skilled in the art to better understand the scheme of the present application, the technical scheme of the present application will be further described in detail below in conjunction with the drawings, and the content is an explanation of the present application rather than a limitation.

[0046] It should be noted that the terms "comprise" and "have" and any variations thereof in the specification and claims of the present application are intended to cover non-exclusive inclusion, for example, a process, method, system, product or device comprising a series of steps or units does not have to be limited to only those steps or units clearly listed, but can include other steps or units not clearly listed or inherent to the process, method, system, product or device.

[0047] Embodiment one

[0048] As shown in Fig. 5, the present embodiment provides a method for the intelligent collaborative operation of a thermal power plant, comprising the following steps:

[0049] Step 1: Build a 1+6+N intelligent thermal power plant intelligent operation necessary function module to form an intelligent monitoring, intelligent cruise and intelligent control three function system. The intelligent monitoring is used to discover potential abnormalities or faults of equipment in advance and report them through online early warning to improve the efficiency of human-machine interaction. At the same time, for the diagnosed potential faults, the artificial operation is simulated to actively intervene and realize the closed-loop fault self-healing. The intelligent cruise optimizes the optimal operation mode and the best operation set value of the system, equipment and parameters, generates the best start-stop, shutdown and rotation time of the equipment, completes the self-start-stop of the equipment, generates the best operation parameter set value and completes the real-time closed-loop optimization. The intelligent control improves the adaptability of the control system to complex working conditions through online identification of the model and adaptive update of the parameters; at the same time, the intelligent heterogeneous of the control strategy is realized according to the coupling correlation of the production process parameters, and the adaptability of the control system to complex disturbances is improved.

[0050] Step 2: As shown in FIG. 1, the 1+6+N intelligent power plant intelligent monitoring disc online early warning and closed-loop fault self-healing collects massive historical operation data of the thermal power unit, extracts common faults of the unit system, equipment and parameters through a self-encoding fault feature extraction method, and forms a fault feature library. At the same time, based on massive historical operation data, a fault monitoring model is established by using a neural network fitting algorithm. By comparing the fault monitoring model with real-time operation data, a monitoring index is generated. If the monitoring index does not exceed a certain threshold, the thermal power unit operates normally; if the monitoring index exceeds a certain threshold, an early warning is generated, and at the same time, the self-encoding fault feature extraction method is used to extract the data features of the historical operation data, and the fault data features in the fault feature library are compared to locate the fault and generate a fault self-healing instruction. At the same time, for typical fault types not included in the fault feature library, the fault feature library is updated.

[0051] Step 3: As shown in FIG. 2, the 1+6+N intelligent power plant intelligent cruise device self-starting and stopping and value automatic optimization divides the operation parameters of the thermal power unit into non-operable parameters and operable parameters. The non-operable parameters include unit load, coal calorific value, environmental temperature, etc., and the operable parameters include climbing rate, steam pressure set value, mill group mode, boiler oxygen content, etc. The non-operable parameters and operable parameters are taken as inputs, and an intelligent cruise model is established based on historical data mining. The output of the model includes safety and stability data, economic and environmental data, and flexibility data of the unit operation. The fitness calculation method is used to evaluate the comprehensive performance of the unit operation. If the fitness index meets the preset fitness requirement, the optimal operation mode and optimal operation parameters of the thermal power unit are output, including the optimal mill group combination mode, the optimal circulating water pump combination mode, the optimal sliding pressure set value, the optimal oxygen content set value, etc. For devices that need to be started and stopped, and retired, and rotated, sequence control and analog quantity control optimization is performed to realize the self-starting and stopping of the devices during the cruise operation of the unit in a wide load range. If the fitness index cannot meet the fitness requirement, a genetic algorithm is used to further optimize and traverse the operable parameters of the thermal power unit.

[0052] Step 4: As shown in FIG. 3, the 1+6+N intelligent power plant intelligent control parameter adaptive adjustment and strategy intelligent heterogeneity, under the intelligent coordination mode, constructs a unit energy balance strategy according to the main steam pressure setting, the actual main steam pressure, the pre-decrease steam temperature, the separator outlet pressure, the speed-limited load instruction, etc., and forms energy instructions and heat signals suitable for once-through boilers. Predictive control is used instead of PID control as a boiler feedback controller, and the speed-limited load instruction is used as a feedforward to form a boiler main control instruction.

[0053] On the basis of the boiler master control instruction, combined with the main steam pressure setting and the actual main steam pressure correction, a fuel master control static feedforward is constructed; according to the target load, the speed-limited post-load instruction, the energy instruction, the heat signal and the variable load rate, a fuel master control dynamic feedforward is constructed; and combined with the main steam pressure setting, the intermediate point temperature setting and the speed-limited post-load instruction, an energy storage dynamic compensation feedforward is constructed; according to the intermediate point temperature setting, the actual intermediate point temperature and the speed-limited post-load instruction, a unit temperature balance loop is constructed to form a temperature instruction and a temperature signal, and the intensity of the coal and water regulation of the superheat degree is determined by using the distribution coefficient. The predictive control is used instead of the PID control as a water-fuel ratio feedback controller, combined with the three feedforwards, to form the fuel master control instruction.

[0054] On the basis of the boiler master control instruction, combined with the intermediate point temperature setting, the actual intermediate point temperature and the correction of the speed-limited post-load instruction, a feedwater master control static feedforward is constructed. According to the one-minus-previous-steam temperature and the speed-limited post-load instruction, a feedwater master control dynamic feedforward is constructed, and the predictive control is used instead of the PID control as a superheat degree feedback controller, combined with the two feedforwards, to form the feedwater master control instruction.

[0055] Step 5: According to the fault self-healing instruction, the fault closed-loop self-healing of the thermal power generating unit is completed, and according to the optimal operation mode and the optimal operation parameter, the operation parameter and the control scheme of the thermal power generating unit are adjusted to complete the intelligent collaborative operation of the thermal power plant. As shown in FIG. 4, taking the self-starting and stopping process of the coal mill as an example for illustration. The intelligent cruise can decide the best starting and stopping time of the mill according to the unit load working condition, the coal calorific value and the coal mill power consumption, trigger the one-key starting and stopping mill program control through the sequential control and analog quantity control design. At the same time, the best coal adding and reducing rate is optimized and given by comprehensively considering the deviation of the main steam pressure and the intermediate point temperature, and the mill is started and stopped at the appropriate time. According to the output demand of the coal mill, the warm-up rate, the coal adding rate and the mill outlet temperature control requirement, the intelligent control adopts the predictive control to construct an intelligent control system of the cold and hot air door, the coal supply amount and the rotating separation speed, and improves the adaptability of the mill starting and stopping process control to complex working conditions and complex disturbances. The intelligent monitoring and inspection monitor whether the coal mill has abnormal working conditions such as coal breakage, mill blockage, spontaneous combustion and air door jamming, simulate the operation of the operator, such as starting the rapping, increasing the primary air pressure, reducing the mill inlet air temperature, quickly opening and closing the cold and hot air door, actively intervene in the intelligent control system of the coal mill, and realize the fault closed-loop self-healing. Thus, the intelligent collaborative operation of the thermal power plant is completed.

[0056] As shown in FIG. 6, the embodiment also provides a smart collaborative operation system of a thermal power plant, comprising an intelligent monitoring module, an intelligent cruise module and an intelligent control module. The intelligent monitoring module collects real-time operation data of a thermal power unit. The real-time operation data is used to obtain a monitoring index through a fault monitoring model. It is determined whether the monitoring index exceeds a preset threshold. If yes, a warning is given. If no, the thermal power unit keeps normal operation. Meanwhile, when a warning is given, features of the real-time operation data are extracted and compared with a fault feature library to obtain a fault self-healing instruction. The intelligent cruise module establishes an intelligent cruise model to obtain an optimal operation mode and optimal operation parameters of the thermal power unit according to the intelligent cruise model. The intelligent control module completes fault closed-loop self-healing of the thermal power unit according to the fault self-healing instruction, adjusts operation parameters and control schemes of the thermal power unit according to the optimal operation mode and optimal operation parameters, and completes smart collaborative operation of the thermal power plant.

[0057] Therefore, the embodiment adopts 1+6+N smart thermal power plant intelligent monitoring online early warning and closed-loop fault self-healing. Through big data analysis and artificial intelligence, production process data of the thermal power plant is analyzed and processed. The advantages and disadvantages of the system, equipment and parameters are transparent. The online early warning mode is reported to improve the efficiency of human-computer interaction. Meanwhile, potential faults are diagnosed. Artificial operation is simulated to actively intervene and realize closed-loop fault self-healing.

[0058] In the 1+6+N smart thermal power plant intelligent cruise device self-starting and stopping and fixed value automatic optimization, historical data mining is used to optimize the starting and stopping, switching and rotation time of production equipment. Combined with sequence control and analog quantity control optimization, the device self-starting and stopping of the unit in wide load range cruise operation is realized. Meanwhile, the safety and stability, economic and environmental performance and flexible maneuverability of the unit operation are comprehensively considered. Multi-objective optimization is used to optimize the best operation parameter fixed value to improve the comprehensive performance of the unit in wide load range cruise operation.

[0059] In the 1+6+N smart thermal power plant intelligent control parameter adaptive adjustment and strategy intelligent heterogeneity, predictive control is used to replace the traditional PID control algorithm to optimize the control system. Through model online identification and parameter adaptive update, the adaptability of the control system to complex working conditions is improved. Meanwhile, the coupling correlation of production process parameters is comprehensively considered to intelligently heterogenize the control strategy to improve the adaptability of the control system to complex disturbances.

[0060] Finally, the intelligent monitoring module, the intelligent cruise module and the intelligent control module are organically cooperated in a "three-in-one" mode, the optimal operation mode and the optimal operation parameter are sent to the intelligent control under the intelligent cruise to be executed, and the execution result is fed back to the intelligent cruise for further iteration optimization; the intelligent monitoring module discovers the system, device and parameter abnormalities or faults in advance, and actively adjusts the intelligent cruise mode to intervene the control loop to realize the fault closed-loop self-healing; the intelligent control executes the intelligent monitoring instruction first, and then executes the intelligent cruise instruction. The problem of insufficient fusion and interaction between modules can be fully solved, and the goal of unmanned intervention and few people on duty in the production process of the thermal power plant can be fully supported.

[0061] The division of the modules in the embodiments of the present application is illustrative, and is only a logical function division. In actual implementation, another division manner can be used. In addition, each function module in each embodiment of the present application can be integrated in one processor, or can be a separate physical existence, or two or more modules can be integrated in one module. The integrated module can be realized in the form of hardware or in the form of a software function module.

[0062] As shown in FIG. 7, the present embodiment further provides a computer device, which includes a processor and a memory. The memory is used to store a computer program (the computer program in the present embodiment includes a calculation component and an iteration component, and can perform model calculation and model updating). The computer program includes program instructions, and the processor is used to execute the program instructions stored in the computer storage medium. The processor can be a central processing unit (CPU), and can also be other general-purpose processors, digital signal processors (DSP), application specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components, etc. The processor is the computing core and control core of the terminal, and is suitable for implementing one or more instructions, and is specifically suitable for loading and executing one or more instructions in the computer storage medium to implement a corresponding method flow or a corresponding function. The processor in the embodiments of the present application can be used for the operation of the intelligent collaborative operation method of the thermal power plant.

[0063] The embodiment also provides a storage medium, specifically a computer readable storage medium (Memory). The computer readable storage medium is a memory device in a computer device, and is used to store programs and data. It can be understood that the computer readable storage medium herein can include an internal storage medium in the computer device, and of course can also include an extended storage medium supported by the computer device. The computer readable storage medium provides a storage space, and the storage space stores an operating system of the terminal. In addition, one or more instructions suitable for being loaded and executed by the processor are also stored in the storage space, and the instructions can be one or more computer programs (including program codes). It should be noted that the computer readable storage medium herein can be a high-speed RAM memory, or a non-volatile memory such as at least one disk memory. The processor can load and execute one or more instructions stored in the computer readable storage medium to implement the corresponding steps of the power plant intelligent collaborative operation method in the above embodiment.

[0064] Embodiment two

[0065] The difference from the embodiment one is that in step 3 of the power plant intelligent collaborative operation method, the fitness calculation is replaced by a weighted evaluation. When the weighted evaluation is adopted, if the preset iteration number is met, the optimal operation mode and the optimal operation parameter are obtained, and if the preset iteration number is not met, the particle swarm algorithm is used to optimize and traverse the operable parameters to update the intelligent cruise model.

[0066] The prediction control in step 4 is replaced by any one of the fuzzy control, the decoupling control or the variable structure control.

[0067] Those skilled in the art should understand that the embodiments of the present application can be provided as a method, a system or a computer program product. Therefore, the present application can adopt a complete hardware embodiment, a complete software embodiment or an embodiment combining software and hardware aspects. Moreover, the present application can adopt a computer program product implemented on one or more computer usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer usable program codes.

[0068] The computer program instructions can also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart block or blocks or in the flowchart one or more blocks.

[0069] These computer program instructions can also be stored in a computer readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer readable memory produce an article of manufacture including instructions which implement the function specified in the flowchart block or blocks or in the flowchart one or more blocks.

[0070] These computer program instructions can also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart block or blocks or in the flowchart one or more blocks.

[0071] Finally, it should be noted that the above-mentioned embodiments are merely used to illustrate the technical solutions of the present application, rather than limit the technical solutions of the present application. Although the present application is described in detail with reference to the above embodiments, those skilled in the art should understand that the technical solutions of the present application can be modified or equivalent replaced without departing from the spirit and scope of the present application, and any modification or equivalent replacement without departing from the spirit and scope of the present application should be covered in the protection scope of the claims of the present application.

Claims

1. A method for intelligent collaborative operation of a thermal power plant, characterized in that, The method comprises the following steps: Collecting real-time operation data of the thermal power unit, obtaining a monitoring index through a fault monitoring model, judging whether the monitoring index exceeds a preset threshold, and if so, issuing a warning, and if not, keeping the thermal power unit in normal operation; Extracting features of the real-time operation data when a warning is issued, and comparing them with a fault feature library to obtain a fault self-healing instruction; Establishing an intelligent cruise model to obtain an optimal operation mode and optimal operation parameters of the thermal power unit according to the intelligent cruise model; According to the fault self-healing instruction, completing fault closed-loop self-healing of the thermal power unit, and adjusting the operation parameters and control scheme of the thermal power unit according to the optimal operation mode and optimal operation parameters to complete intelligent collaborative operation of the thermal power plant.

2. The method of claim 1, wherein, The fault monitoring model is obtained through the following steps: Collecting historical operation data of the thermal power unit, and establishing a fault monitoring model according to the historical operation data and using a neural network fitting algorithm; The fault feature library is obtained through the following steps: According to the historical operation data, obtaining common fault information of the thermal power unit by self-encoding fault feature extraction, and establishing a fault feature library according to the common faults of the thermal power unit.

3. The method of claim 1, wherein, The intelligent cruise model is established through the following steps: Collecting non-operable parameters and operable parameters of the thermal power unit, and using historical data mining to process the non-operable parameters and operable parameters to establish an intelligent cruise model.

4. The method of claim 3, wherein, The step of obtaining the optimal operation mode and optimal operation parameters of the thermal power unit according to the intelligent cruise model comprises: After the intelligent cruise model outputs safety and stability data, economic and environmental data, and flexibility and maneuverability data, weighted evaluation or fitness calculation is performed to obtain the optimal operation mode and optimal operation parameters; When weighted evaluation is used, if a preset number of iterations is met, the optimal operation mode and optimal operation parameters are obtained, and if the preset number of iterations is not met, the operable parameters are optimized and traversed to update the intelligent cruise model; When fitness calculation is used, if the calculated fitness meets a preset fitness, the optimal operation mode and optimal operation parameters are obtained, and if the calculated fitness does not meet the preset fitness, the operable parameters are optimized and traversed to update the intelligent cruise model.

5. The method of claim 4, wherein, The optimization and traversal use a particle swarm algorithm or a genetic algorithm.

6. The method of claim 1, wherein, The step of extracting features of the real-time operation data when a warning is issued, and comparing them with a fault feature library to obtain a fault self-healing instruction further comprises the following steps: When the features of the real-time operation data extracted when a warning is issued are compared and not found in the fault feature library, the features of the real-time operation data are updated in the fault feature library.

7. The method of claim 1, wherein, Further comprising the following steps: Replacing the PID control of the thermal power unit with predictive control, fuzzy control, decoupling control or variable structure control, and adjusting the operation parameters and control scheme of the thermal power unit in combination with the optimal operation mode and optimal operation parameters.

8. A smart collaborative operation system for a thermal power plant, characterized in that, Comprise: The intelligent monitoring module is used for collecting real-time operation data of the thermal power unit, obtaining a monitoring index through a fault monitoring model from the real-time operation data, judging whether the monitoring index exceeds a preset threshold, and if so, performing early warning, and if not, keeping the thermal power unit in normal operation; meanwhile, the intelligent monitoring module is used for extracting features of the real-time operation data and comparing the features with a fault feature library to obtain a fault self-recovery instruction when early warning is performed; The intelligent cruise module is used for establishing an intelligent cruise model to obtain an optimal operation mode and optimal operation parameters of the thermal power unit according to the intelligent cruise model; The intelligent control module is used for completing fault closed-loop self-recovery of the thermal power unit according to the fault self-recovery instruction, adjusting operation parameters and a control scheme of the thermal power unit according to the optimal operation mode and the optimal operation parameters, and completing intelligent collaborative operation of the thermal power plant.

9. An electronic device, comprising: The computer readable storage medium stores a computer program, and the computer program is executed by the processor to implement the steps of the intelligent collaborative operation method of the thermal power plant in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, The computer readable storage medium stores a computer program, and the computer program is executed by the processor to implement the steps of the intelligent collaborative operation method of the thermal power plant in any one of claims 1 to 7.

Images