Operation and maintenance regulation method for thermal power plant comprehensive energy system based on BP neural network

Abstract

The application relates to a method for operating and maintaining a comprehensive energy system of a thermal power plant based on a BP neural network, wherein the method comprises the following steps: collecting real-time data and load demand of at least one device in the comprehensive energy system of the thermal power plant; generating at least one prediction data of target steam quantity, target fuel quantity and target electric load according to the real-time data; comparing the at least one prediction data with the real-time data; regulating the operation of the comprehensive energy system according to fault information, the at least one prediction data, the real-time data and the load demand; and regulating the comprehensive energy system according to load fluctuation, the real-time data and the at least one prediction data to generate a regulation scheme of the comprehensive energy system. Thus, the method solves the problem that related technologies do not consider solving the problems of a decrease in power generation hours and insufficient profitability of the power plant at the present stage by combining the comprehensive energy system, and the problem that only a neural network model is used for prediction, the prediction accuracy is not enough, and the design is not made from the perspective of the operation and maintenance of the power plant.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of integrated energy system, and particularly relates to a method for operation and maintenance regulation of an integrated energy system of a thermal power plant based on a BP neural network. BACKGROUND

[0002] At present, energy utilization technologies that are efficient, energy-saving and environmentally friendly are important development trends at the present stage, and the proportion of renewable energy power generation is increasing year by year. In the future, the annual utilization hours of thermal power units will be greatly reduced. If the thermal power units continue to rely solely on power supply services, they will be difficult to bear higher costs, and they will also be unable to adapt to the realistic needs of energy transformation and energy saving and emission reduction in China.

[0003] The integrated energy system of the thermal power plant is based on the source side of the thermal power plant. By coupling various new energy conversion technologies and energy storage technologies, the integrated energy system realizes multi-energy coupling supply, energy cascade utilization, hydrogen production and carbon capture in the region, and can not only improve the profitability of the thermal power plant itself, but also reduce the energy cost of enterprises in the region, improve energy utilization efficiency, and reduce carbon dioxide emissions. The integrated energy system of the thermal power plant is an integrated energy production and supply system, involving multiple types of technologies, a large number of types of equipment, and a complex production process. Some parameter adjustments have a long effect period, making it very difficult to produce and regulate and diagnose faults. Therefore, it is of great significance to study the operation and maintenance and fault diagnosis regulation of the thermal power plant based on digital twinning and BP neural network technology.

[0004] In related technologies, neural network technology can be used to filter the collected real-time data of the thermal power plant, use a neural network model prediction module to make predictions, and then use a fault diagnosis module to diagnose faults based on the predicted data.

[0005] However, related technologies do not consider combining the integrated energy system to solve the problems of a decrease in power generation hours and insufficient profitability that power plants face at the present stage. Only using a neural network model for prediction, the prediction accuracy is not enough, and only predicted data is obtained without designing from the perspective of plant operation and maintenance, which needs to be improved. SUMMARY

[0006] The present application provides a method for operation and maintenance regulation of an integrated energy system of a thermal power plant based on a BP neural network, to solve the problems that related technologies do not consider combining the integrated energy system to solve the problems of a decrease in power generation hours and insufficient profitability that power plants face at the present stage, only use a neural network model for prediction, the prediction accuracy is not enough, and only predicted data is obtained without designing from the perspective of plant operation and maintenance.

[0007] The first aspect of the present application provides a method for operating and regulating a comprehensive energy system of a thermal power plant based on a BP neural network, comprising the following steps: collecting real-time data and load demand of at least one device in the comprehensive energy system of the thermal power plant; generating at least one prediction data of target steam volume, target fuel volume and target electric load according to the real-time data; comparing the at least one prediction data with the real-time data to generate a comparison result, and determining fault information of the comprehensive energy system of the thermal power plant according to the comparison result; regulating the operation of the comprehensive energy system according to the fault information, the at least one prediction data, the real-time data and the load demand to generate an operation result; determining a load fluctuation condition according to the load demand based on the operation result, and regulating the comprehensive energy system according to the load fluctuation condition, the real-time data and the at least one prediction data to generate a regulation scheme of the comprehensive energy system.

[0008] Optionally, in an embodiment of the present application, the generating at least one prediction data of target steam volume, target fuel volume and target electric load according to the real-time data comprises: mechanismally optimizing a generator set neural network loss function to generate a mechanismally optimized neural network, and predicting an operating parameter in a production process by using the mechanismally optimized neural network to generate first prediction data; processing operating data of each device of the comprehensive energy system of the thermal power plant to obtain processed operating data, and predicting the operating parameter in the production process by using a preset neural network based on the processed operating data to generate second prediction data; and determining the at least one prediction data according to the first prediction data and the second prediction data.

[0009] Optionally, in an embodiment of the present application, a calculation formula of the generator set neural network loss function is:

[0010] LOSS = αLOSS phys + αLOSS math ,

[0011] wherein, LOSS phys is a physical loss function, and LOSS math is a mathematical, i.e., neural network loss function.

[0012] Optionally, in an embodiment of the present application, the determining fault information of the comprehensive energy system of the thermal power plant according to the comparison result comprises: judging whether the real-time data satisfies a preset abnormal condition according to a value of a decision coefficient and a value of a mean square error based on the comparison result; if the value of the decision coefficient and the value of the mean square error both exceed a preset threshold value, it is determined that the real-time data satisfies the preset abnormal condition, and it is determined that the comprehensive energy system of the thermal power plant has a fault, otherwise it is determined that the comprehensive energy system of the thermal power plant has no fault.

[0013] Optionally, in an embodiment of the present application, the calculation formula of the value of the determination coefficient is:

[0014]

[0015] wherein y real is the actual value of the data, y pred is the predicted value obtained based on the model, is the average value of the actual value;

[0016] The calculation formula of the value of the mean square error is:

[0017]

[0018] wherein m is the total number of samples, y real is the actual value of the data, y pred is the predicted value obtained based on the model.

[0019] Optionally, in an embodiment of the present application, the regulating the integrated energy system according to the load fluctuation, the real-time data and the at least one predicted data to generate a regulation scheme of the integrated energy system comprises: judging whether the output electric energy of the energy supply side of the integrated energy system is greater than or equal to the electric load of the user demand side; if the output electric energy of the energy supply side of the integrated energy system is greater than or equal to the electric load of the user demand side, and the output steam of the energy supply side is greater than or equal to the steam amount required by the cold load and the heat load, then the first electric energy meeting a preset excess condition is stored in a target energy storage device to obtain cold energy and heat energy; if the output electric energy of the energy supply side of the integrated energy system is greater than or equal to the electric load of the user demand side, and the output steam of the energy supply side is less than the steam amount required by the cold load and the heat load, then the output electric energy of the energy supply side meeting a first preset partial condition is supplied to the user side, and the output electric energy of the energy supply side meeting a second preset partial condition is converted into the cold energy and the heat energy; if the output electric energy of the energy supply side of the integrated energy system is less than the electric load of the user demand side, and the output steam of the energy supply side is greater than or equal to the steam amount required by the cold load and the heat load, then the output steam of the energy supply side is supplied to a target device to obtain the cold load and the heat load; if the output electric energy of the energy supply side of the integrated energy system is less than the electric load of the user demand side, and the output steam of the energy supply side is less than the steam amount required by the cold load and the heat load, then the output steam of the energy supply side is supplied to the target device to obtain the cold load and the heat load; and a regulation scheme of the integrated energy system is determined according to the cold energy, the heat energy, the cold load and the heat load.

[0020] The second aspect embodiment of the present application provides a device for operation and maintenance and regulation of a comprehensive energy system of a thermal power plant based on a BP neural network, comprising: an acquisition module configured to acquire real-time data and load demand of at least one device in the comprehensive energy system of the thermal power plant; a prediction module configured to generate at least one prediction data of target steam quantity, target fuel quantity and target electric load according to the real-time data; a detection module configured to compare the at least one prediction data with the real-time data to generate a comparison result, and determine fault information of the comprehensive energy system of the thermal power plant according to the comparison result; an operation and maintenance module configured to regulate operation of the comprehensive energy system according to the fault information, the at least one prediction data, the real-time data and the load demand to generate an operation result; and a regulation module configured to determine a load fluctuation condition according to the load demand based on the operation result, and regulate the comprehensive energy system according to the load fluctuation condition, the real-time data and the at least one prediction data to generate a regulation scheme of the comprehensive energy system.

[0021] Optionally, in an embodiment of the present application, the prediction module comprises: a first prediction unit configured to optimize a neural network loss function of a mechanism-optimized generator set to generate a mechanism-optimized neural network, and predict an operating parameter in a production process by using the mechanism-optimized neural network to generate first prediction data; a second prediction unit configured to process operating data of each device in the comprehensive energy system of the thermal power plant to obtain processed operating data, and predict the operating parameter in the production process by using a preset neural network based on the processed operating data to generate second prediction data; and a determination unit configured to determine the at least one prediction data according to the first prediction data and the second prediction data.

[0022] Optionally, in an embodiment of the present application, a calculation formula of the neural network loss function of the generator set is as follows:

[0023] LOSS = αLOSS phys + αLOSS math ,

[0024] wherein, LOSS phys is a physical loss function, and LOSS math is a mathematical, i.e., neural network loss function.

[0025] Optionally, in an embodiment of the present application, the detection module comprises: a detection unit configured to detect whether the real-time data satisfies a preset abnormal condition according to a value of a determination coefficient and a value of a mean square error based on the comparison result; and a determination unit configured to determine that the real-time data satisfies the preset abnormal condition and determine that the integrated energy system of the thermal power plant has a fault if the value of the determination coefficient and the value of the mean square error both exceed a preset threshold, and otherwise determine that the integrated energy system of the thermal power plant has no fault.

[0026] Optionally, in an embodiment of the present application, the value of the determination coefficient is calculated according to the following formula:

[0027]

[0028] wherein y real is an actual value of data, y pred is a predicted value obtained based on a model, is an average value of the actual value;

[0029] The value of the mean square error is calculated according to the following formula:

[0030]

[0031] wherein m is a total number of samples, y real is the actual value of the data, and y pred is the predicted value obtained based on the model.

[0032] Optionally, in an embodiment of the present application, the regulation module comprises: a judging unit configured to judge whether the electric energy output by the energy supply side of the integrated energy system is greater than or equal to the electric load of the user demand side; a storage unit configured to store the first electric energy that meets the preset excess condition to a target energy storage device to obtain cold energy and heat energy when the electric energy output by the energy supply side of the integrated energy system is greater than or equal to the electric load of the user demand side and the steam output by the energy supply side is greater than or equal to the amount of steam required by the cold load and the heat load; a conversion unit configured to supply the energy supply side output electric energy that meets the first preset partial condition to the user side and convert the energy supply side output electric energy that meets the second preset partial condition into the cold energy and the heat energy when the electric energy output by the energy supply side of the integrated energy system is greater than or equal to the electric load of the user demand side and the steam output by the energy supply side is less than the amount of steam required by the cold load and the heat load; a first obtaining unit configured to supply the steam output by the energy supply side to a target device to obtain the cold load and the heat load when the electric energy output by the energy supply side of the integrated energy system is less than the electric load of the user demand side and the steam output by the energy supply side is greater than or equal to the amount of steam required by the cold load and the heat load; a second obtaining unit configured to supply the steam output by the energy supply side to the target device to obtain the cold load and the heat load when the electric energy output by the energy supply side of the integrated energy system is less than the electric load of the user demand side and the steam output by the energy supply side is less than the amount of steam required by the cold load and the heat load; and a scheme determining unit configured to determine a regulation scheme of the integrated energy system according to the cold energy, the heat energy, the cold load and the heat load.

[0033] The third aspect of the present application provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the method for operating and maintaining the integrated energy system of the thermal power plant based on the BP neural network as described in the above embodiments.

[0034] The fourth aspect of the present application provides a computer readable storage medium, which stores a computer program, and the program is executed by a processor to implement the method for operating and maintaining the integrated energy system of the thermal power plant based on the BP neural network as described above.

[0035] The fifth aspect of the present application provides a computer program product, which stores a computer program, and the program is executed by a processor to implement the method for operating and maintaining the integrated energy system of the thermal power plant based on the BP neural network as described above.

[0036] The embodiment of the application can greatly improve the prediction accuracy of the power generation side digital twin model by mechanism correction of the neural network loss function of the power generation side of the digital twin model, while ensuring efficient operation of the model; the corresponding result is quickly predicted through the neural network, and real-time feedback is provided to the digital twin model control platform, so that real-time monitoring and prediction of various data are realized; in combination with the digital twin model evaluation index, the prediction data of the digital twin model and various data of the comprehensive energy system of the power plant are compared in real time, abnormal data is reported, and discovery and diagnosis of equipment failure of the comprehensive energy system are realized; through the rapid prediction of the system operation state after the operation parameter adjustment of the digital twin model, the data difficult to measure in the comprehensive energy system are efficiently predicted, and rapid and accurate adjustment of the operation parameters of the comprehensive energy system of the power plant is realized; the operation state of the equipment is judged based on the matching relationship of energy supply and demand, and the intelligent operation and maintenance of the comprehensive energy system of the power plant is realized. Therefore, the related art does not consider solving the problems of the power plant at the present stage, such as the decrease of power generation hours and the insufficient profitability, only uses the neural network model for prediction, and the prediction accuracy is not enough, and only the prediction data is considered, without designing from the operation and maintenance point of view of the power plant.

[0037] Additional aspects and advantages of the application will be set forth in part in the description that follows, and in part will become apparent to those skilled in the art upon examination of the following and / or can be learned by practice of the application. BRIEF DESCRIPTION OF DRAWINGS

[0038] The above and / or additional aspects and advantages of the application will become apparent and be readily appreciated from the following description, taken in conjunction with the accompanying drawings, in which:

[0039] Figure 1 A flowchart of a method for operating and maintaining a comprehensive energy system of a power plant based on a BP neural network according to an embodiment of the application;

[0040] Figure 2 A schematic diagram of a structure of a comprehensive energy system of a power plant according to an embodiment of the application;

[0041] Figure 3 A model diagram of a digital twin model of a comprehensive energy system of a power plant according to an embodiment of the application;

[0042] Figure 4 A schematic diagram of a device for operating and maintaining a comprehensive energy system of a power plant based on a BP neural network according to an embodiment of the application;

[0043] Figure 5 A schematic diagram of an electronic device according to an embodiment of the application. DETAILED DESCRIPTION

[0044] Embodiments of the present application are described below in detail with reference to the accompanying drawings, examples of which are shown in the drawings, wherein the same or similar notations represent the same or similar elements or elements having the same or similar functions throughout. The embodiments described below by reference to the accompanying drawings are exemplary and are intended to explain the present application, and cannot be understood as a limitation of the present application.

[0045] A BP neural network-based operation and maintenance regulation method for a thermal power plant comprehensive energy system of an embodiment of the present application is described below with reference to the accompanying drawings. In view of the problems that the related technologies mentioned in the background art do not consider solving the problems of the power plant, such as the decrease in generating hours and insufficient profitability, by combining a comprehensive energy system, only a neural network model is used for prediction, which has the problems of insufficient prediction accuracy and only considering obtaining prediction data without designing from the perspective of operation and maintenance of the power plant, the present application provides a BP neural network-based operation and maintenance regulation method for a thermal power plant comprehensive energy system. In the method, the neural network loss function of the power plant generation side in the digital twin model is mechanismally corrected, which greatly improves the prediction accuracy of the digital twin model of the power generation side while ensuring efficient operation of the model; the corresponding results are rapidly predicted by the neural network, and real-time feedback is provided to the digital twin model control platform to realize real-time monitoring and prediction of various data; in combination with the evaluation index of the digital twin model, the prediction data of the digital twin model and various data of the thermal power plant comprehensive energy system are compared in real time to report abnormal data and realize the discovery and diagnosis of equipment faults of the comprehensive energy system; the digital twin model is used to rapidly predict the system operation state after adjustment of the operation parameters, efficiently predict the data that are difficult to measure in the comprehensive energy system, and realize rapid and accurate adjustment of the operation parameters of the thermal power plant comprehensive energy system; the equipment operation state is judged based on the matching relationship of energy supply and demand to realize the intelligent operation and maintenance of the thermal power plant comprehensive energy system. Thus, the problems that the related technologies do not consider solving the problems of the power plant, such as the decrease in generating hours and insufficient profitability, by combining a comprehensive energy system, only a neural network model is used for prediction, which has the problems of insufficient prediction accuracy and only considering obtaining prediction data without designing from the perspective of operation and maintenance of the power plant are solved.

[0046] Specifically, Figure 1 A flowchart of a BP neural network-based operation and maintenance regulation method for a thermal power plant comprehensive energy system provided by an embodiment of the present application is shown in FIG. 1.

[0047] As Figure 1 shown, the BP neural network-based operation and maintenance regulation method for a thermal power plant comprehensive energy system includes the following steps:

[0048] In step S101, real-time data and load demand of at least one device in the thermal power plant comprehensive energy system are collected.

[0049] It can be understood that, asFigure 2 As shown, at least one device in the thermal power plant comprehensive energy system comprises:

[0050] 1: a thermal power unit, comprising a steam turbine unit, a generator and a coal-fired boiler, for realizing the whole process from fuel to generated electric energy. The coal-fired boiler is used for burning coal powder and other gaseous fuels to generate high-temperature flue gas to heat water to form high-temperature steam; the steam turbine unit realizes the process of converting steam heat energy into mechanical energy; the generator converts the mechanical energy generated by the steam turbine into electric energy. First electric energy is generated.

[0051] 2: a garbage gasification furnace, used for converting household garbage into gaseous fuel for the boiler to burn.

[0052] 3: a biomass gasification furnace, used for converting biomass into gaseous fuel for the boiler to burn.

[0053] 4: a coal mill, used for grinding coal into coal powder for the boiler to burn.

[0054] 5: an electrically driven compression refrigeration device, which is a refrigeration device driven by electric energy and is used for providing cold load. First cold energy is generated.

[0055] 6: an electrically driven compression heat pump device, which is a heat pump device driven by electric energy and is used for providing heat load. First heat energy is generated.

[0056] 7: an absorption refrigeration unit device, which is a refrigeration device driven by high-temperature steam and is used for providing cold load. Second cold energy is generated.

[0057] 8: a heat exchanger heat supply device, which reduces the temperature of steam by heat exchange to provide heat load for users. Second heat energy is generated.

[0058] 9: an energy storage device, including an electric energy storage device, a heat storage device and a cold storage device, used for storing excess capacity in a low valley of load demand and providing stored capacity to meet the load in a peak period.

[0059] 10: a new energy power generation device, used for converting wind, light and other new energy into second electric energy.

[0060] In actual execution, the embodiments of the present application can collect real-time data of the devices 1-10 in the comprehensive energy system and load demand, and feed back to the digital twin prediction module, fault detection module and comprehensive operation and maintenance module in the Figure 3 , to realize real-time monitoring and prediction of various data.

[0061] In step S102, at least one of the predicted data of the target steam quantity, the target fuel quantity and the target electric load is generated according to the real-time data.

[0062] It can be understood that the predicted data in the embodiments of the present application includes: the steam quantity required under the condition of constant cold and heat load, the fuel quantity required when the output electric energy of the energy supply side is less than the electric load of the user demand side, the supplemental electric load, the electric load of the thermal power unit when the electrically driven compression refrigeration equipment and the electrically driven compression heat pump equipment make up for the insufficient cold and heat load, and the like.

[0063] In actual execution, the embodiments of the present application can generate the target steam quantity, the target fuel quantity and the target electric load in the middle of the predicted data according to real-time data. The embodiments of the present application can design an efficient and accurate digital twin model based on the comprehensive energy system of the thermal power plant, realize efficient operation and maintenance, accurate prediction and fault warning of the comprehensive energy system of the thermal power plant, not only can reduce the operation and maintenance cost and difficulty of the thermal power plant, reduce the operation cost of the thermal power plant, but also can improve the production and operation stability of the thermal power plant, ensure the stability of regional energy consumption, and has important significance for improving the economy and environmental protection of the existing thermal power plant.

[0064] Optionally, in an embodiment of the present application, generating at least one predicted data of the target steam quantity, the target fuel quantity and the target electric load according to real-time data includes: mechanism-optimizing a generator set neural network loss function to generate a mechanism-optimized neural network, and using the mechanism-optimized neural network to predict the operating parameters in the production process to generate first predicted data; processing the operating data of each device of the comprehensive energy system of the thermal power plant to obtain processed operating data, and using a preset neural network to predict the operating parameters in the production process based on the processed operating data to generate second predicted data; and determining the at least one predicted data according to the first predicted data and the second predicted data.

[0065] It can be understood that the embodiments of the present application can realize the processing of real-time data of the thermal power unit and the real-time prediction of the fuel quantity required under the condition of load fluctuation.

[0066] Specifically, as shown in Figure 3 The embodiments of the present application can process the real-time data of the thermal power unit equipment collected by the data acquisition module, use the mechanism-optimized neural network to predict the related operating parameters in the production process, and the predicted data is supplied to the fault detection module for comparison with the actual operating parameters. The real-time demand of the fluctuating load of the comprehensive energy system is received, the mechanism-optimized neural network is used to predict the related data and fuel quantity in the production process. The load data issued by the comprehensive operation and maintenance module is received, the mechanism-optimized neural network is used to predict the related data and fuel quantity under the instruction load, to generate first predicted data, and the first predicted data is supplied to the comprehensive operation and maintenance module.

[0067] Further, the embodiments of the present application adopt a mechanism-optimized loss function to improve the prediction accuracy. The generator set neural network loss function is mechanism-optimized, wherein in an embodiment of the present application, the calculation formula of the generator set neural network loss function is:

[0068] LOSS = aLOSS phys + bLOSS math ,

[0069] wherein LOSS phys is a physical loss function, LOSS math is a mathematical, i.e., neural network loss function, and a + b = 1 is the weight of the two loss functions.

[0070] By using the constraint of the physical conservation equation in the mechanism model, the sum of the square logarithmic errors of the difference between the predicted value and the equilibrium is defined as the loss function at the physical model level. The weights of the mathematical loss and the physical loss are pre-adjusted by hyperparameters: by training and verifying on different training sets and verification sets, the optimal weights of the mathematical loss and the physical loss are obtained.

[0071] Further, as shown in Figure 3 , the embodiments of the present application can process the operation data of each device of the integrated energy system collected by the data acquisition module, and use the neural network to predict the related operation parameters in the production process. The real-time demand of the fluctuating load of the integrated energy system is received, and the neural network is used to predict the related data, fuel quantity, etc. of each device in the production process. The load data issued by the integrated operation and maintenance module is received, and the mechanism-optimized neural network is used to predict the related data, fuel quantity, etc. of the production under the instruction load, to generate second prediction data, which is provided to the integrated operation and maintenance module for use, to ensure that at least one prediction data is determined according to the first prediction data and the second prediction data.

[0072] The embodiments of the present application can greatly improve the prediction accuracy of the digital twin model of the power plant generation side by mechanism correction of the neural network loss function of the digital twin model of the power plant generation side, while ensuring efficient operation of the model, ensuring that the digital twin model of the power plant generation side is synchronized with the normal working state, and the digital twin model receives each item of data of the integrated energy system of the power plant in real time, rapidly predicts the corresponding results through the neural network, and feeds back to the digital twin model control platform in real time, to realize real-time monitoring and prediction of each item of data.

[0073] In step S103, at least one prediction data is compared with real-time data to generate a comparison result, and the fault information of the integrated energy system of the power plant is determined according to the comparison result.

[0074] As a possible implementation manner, as shown in Figure 3As shown, the embodiment of the present application can receive relevant operating parameters in the power generation process, fuel quantity, etc. in the data acquisition module and the thermal power unit prediction module, compare at least one prediction data in the thermal power unit prediction module with real-time data in the data acquisition module, determine whether the fault of the thermal power plant comprehensive energy system occurs according to the comparison result, and prompt the fault condition in the case of fault.

[0075] The embodiment of the present application can combine the digital twin model evaluation index, monitor and compare the prediction data of the digital twin model and each data of the thermal power plant comprehensive energy system in real time, report abnormal data, and realize the discovery and diagnosis of the fault of the comprehensive energy system equipment.

[0076] Optionally, in an embodiment of the present application, the fault information of the thermal power plant comprehensive energy system is determined according to the comparison result, including: based on the comparison result, judging whether the real-time data meets the preset abnormal condition according to the value of the determination coefficient and the value of the mean square error; if the value of the determination coefficient and the value of the mean square error both exceed the preset threshold value, it is determined that the real-time data meets the preset abnormal condition, and it is determined that the fault of the thermal power plant comprehensive energy system occurs, otherwise it is determined that the fault of the thermal power plant comprehensive energy system does not occur.

[0077] It can be understood that the preset abnormal condition in the embodiment of the present application can be real-time data abnormality.

[0078] In actual execution process, as shown, Figure 3 the embodiment of the present application can calculate the value of the determination coefficient R 2 and the value of the mean square error value MSE to judge whether the real-time data is abnormal, when the value of the determination coefficient and the value of the mean square error both exceed the set threshold value, it is determined that the real-time data is abnormal, the abnormality is immediately fed back to the comprehensive operation and maintenance module, and it is determined that the fault of the thermal power plant comprehensive energy system occurs, the fault condition is prompted, otherwise it is determined that the fault of the thermal power plant comprehensive energy system does not occur.

[0079] The embodiment of the present application can further report abnormal data, and realize the discovery and diagnosis of the fault of the comprehensive energy system equipment.

[0080] It should be noted that the preset abnormal condition can be set by those skilled in the art according to the actual situation, which is not limited here.

[0081] In an embodiment of the present application, the calculation formula of the determination coefficient is:

[0082]

[0083] Wherein, y real is the actual value of the data, y pred is the prediction value based on the model, is the average value of the actual value.

[0084] The formula for calculating the mean square error value is:

[0085]

[0086] Wherein, m is the total number of samples, y real is the actual value of the data, y pred is the predicted value obtained based on the model.

[0087] For other devices of the integrated energy system, it is also necessary to determine whether the physical parameters at the link of each device are consistent.

[0088] In step S104, the integrated energy system is regulated according to the fault information, at least one predicted data, real-time data and load demand to generate an operation result.

[0089] Specifically, as shown in Figure 3 The embodiment of the present application can receive real-time data and load demand in the data acquisition module, at least one predicted data in the digital twin prediction module, and fault information transmitted by the fault detection module, analyze the received data through a neural network, judge the state of each device of the integrated energy system under the current load and feedback, regulate the operation of the integrated energy system, and generate an operation result. The received relevant data can be visualized and displayed in real time, and the staff can monitor the operation of the integrated energy system in real time according to each predicted result, timely adjust the energy supply, and eliminate system faults.

[0090] The embodiment of the present application can quickly predict the system operation state after adjusting the operation parameters through the digital twin model, efficiently predict the data that is difficult to measure in the integrated energy system, and thus realize the rapid and accurate adjustment of the operation parameters of the integrated energy system of the thermal power plant. Based on the matching relationship between energy supply and demand, the operation state of the equipment is determined, and the intelligent operation and maintenance of the integrated energy system of the thermal power plant is realized.

[0091] In step S105, based on the operation result, the load fluctuation is determined according to the load demand, and the integrated energy system is regulated according to the load fluctuation, real-time data and at least one predicted data to generate a regulation scheme of the integrated energy system.

[0092] In the actual execution process, as shown in Figure 3 The embodiment of the present application can determine the load fluctuation according to the load demand based on the operation result, and regulate the integrated energy system according to the load fluctuation, real-time data and predicted data such as fuel quantity predicted by the digital twin prediction module in the data acquisition module to generate a regulation scheme of the integrated energy system.

[0093] Optionally, in one embodiment of this application, the integrated energy system is regulated based on load fluctuations, real-time data, and at least one predictive data to generate a regulation scheme for the integrated energy system. This includes: determining whether the electrical output from the supply side of the integrated energy system is greater than or equal to the user's demand side electrical load; if the electrical output from the supply side of the integrated energy system is greater than or equal to the user's demand side electrical load, and the steam output from the supply side is greater than or equal to the steam required for the cooling and heating loads, then the first electrical energy meeting the preset excess conditions is stored in a target energy storage device to obtain cooling and heating energy; if the electrical output from the supply side of the integrated energy system is greater than or equal to the user's demand side electrical load, and the steam output from the supply side is less than the steam required for the cooling and heating loads, then... The system will supply electrical energy from the energy supply side that meets the first preset condition to the user side, and convert electrical energy from the energy supply side that meets the second preset condition into cold energy and heat energy. If the electrical energy output from the energy supply side in the integrated energy system is less than the electrical load on the user's demand side, and the steam output from the energy supply side is greater than or equal to the steam required for the cold load and heat load, then the steam output from the energy supply side will be supplied to the target equipment to obtain the cold load and heat load. If the electrical energy output from the energy supply side in the integrated energy system is less than the electrical load on the user's demand side, and the steam output from the energy supply side is less than the steam required for the cold load and heat load, then the steam output from the energy supply side will be supplied to the target equipment to obtain the cold load and heat load. The control scheme of the integrated energy system is determined based on the cold energy, heat energy, cold load, and heat load.

[0094] It is understandable that this application operates under the following conditions during operation and maintenance:

[0095] (a) such as Figure 3 As shown, the data acquisition module receives real-time data from various devices in the integrated energy system of the thermal power plant and transmits the data to the digital twin prediction module and the integrated control module.

[0096] The data transmitted to the digital twin prediction module includes: cooling load, heating load, and electrical load.

[0097] The data transmitted to the integrated control module includes: electrical load, primary electrical energy, secondary electrical energy, and output steam quantity.

[0098] (ii) The digital twin prediction module processes the received data, obtains the prediction results, and transmits them to the integrated control module.

[0099] The data predicted by the digital twin prediction module includes: the amount of steam required under certain cooling and heating loads; the amount of fuel required when the power output on the energy supply side is less than the power load on the user demand side; the supplementary power load; and the power load of thermal power units when electric-driven compression refrigeration equipment and electric-driven compression heat pump equipment supplement the insufficient cooling and heating loads.

[0100] (III) The integrated control module gives a control scheme for the integrated energy system according to the data in the data acquisition module and the digital twin prediction module.

[0101] Among them, the first electric energy and the second electric energy generated in the thermal power generating unit and the new energy power generation equipment are collectively referred to as the energy supply side output electric energy; the first cold energy and the second cold energy generated by the electric drive compression type refrigeration equipment and the absorption type refrigeration unit equipment are collectively referred to as the output cold energy; and the first heat energy and the second heat energy generated by the electric drive compression type heat pump equipment and the heat exchanger heat supply equipment are collectively referred to as the output heat energy.

[0102] The control logic of the integrated control module is as follows:

[0103] As shown in Figure 2 When the energy supply side output electric energy in the integrated energy system is greater than or equal to the user demand side electric load, and the energy supply side output steam is greater than or equal to the steam amount required by the cold and heat load, the excess first electric energy is stored in the electric storage equipment. If the electric storage equipment is full, the electric energy is converted into cold energy and heat energy by the electric drive compression type refrigeration equipment and the electric drive compression type heat pump equipment, and is stored in the corresponding cold storage and heat storage equipment. At the same time, the output steam is converted into cold energy and heat energy by the absorption type refrigeration unit equipment and the heat exchanger heat supply equipment, and is stored in the corresponding cold storage and heat storage equipment.

[0104] When the energy supply side output electric energy in the integrated energy system is greater than or equal to the user demand side electric load, but the energy supply side output steam is less than the steam amount required by the cold and heat load, part of the energy supply side output electric energy is supplied to the user side to meet the user side electric load, and the rest of the electric energy is all used to drive the electric drive compression type refrigeration equipment and the electric drive compression type heat pump equipment to convert the electric energy into cold energy and heat energy; the energy supply side output steam is all used for the absorption type refrigeration unit equipment and the heat exchanger heat supply equipment to convert into cold energy and heat energy to meet the user cold and heat load. If the output cold energy and heat energy are higher than the user side cold and heat load, the excess cold and heat energy is stored in the corresponding cold storage and heat storage equipment.

[0105] When the energy supply side output electric energy in the integrated energy system is less than the user demand side electric load, but the energy supply side output steam is greater than or equal to the steam amount required by the cold and heat load, the energy supply side output steam is provided to the absorption type refrigeration unit equipment and the heat exchanger heat supply equipment to provide the cold and heat load. The energy supply side output electric energy is all supplied to the user side, and the electric storage equipment provides electric energy to the outside. If the remaining electric energy in the electric storage equipment cannot cover the user side electric load, the user demand side electric load, the electric storage equipment output electric energy and the energy supply side output electric energy data are transmitted to the digital twin prediction module, the digital twin prediction module is used to predict the load amount and fuel amount required by the thermal power generating unit, and the load of the thermal power generating unit is increased according to the prediction.

[0106] When the output power of the energy supply side in the integrated energy system is less than the electric load of the user demand side, but the output steam of the energy supply side is less than the steam required by the cold and heat load, all the output steam of the energy supply side is provided to the absorption refrigeration unit and the heat exchanger heat supply device to provide cold and heat load, and the output power of the energy supply side is all supplied to the user side. If the energy provided by the energy storage, cold storage and heat storage devices cannot meet the electric load and cold and heat load of the user side, the digital twin prediction module is transmitted with the electric load of the user demand side, the output power of the energy storage device and the output power of the energy supply side, and the cold and heat load of the user demand side, the output cold and heat of the energy storage device and the output cold and heat. The digital twin prediction module is used to predict the load and fuel required by the thermal power unit to meet the electric load of the user side, and to calculate the corresponding output steam quantity. If the predicted output steam quantity can meet the cold and heat load of the user side, the thermal power unit load is increased according to the prediction result. If the predicted output steam quantity cannot meet the cold and heat load of the user side, the digital twin prediction module is transmitted with the insufficient cold and heat load, and the electric quantity required by the electrically driven compression refrigeration device and the electrically driven compression heat pump device to achieve the required cold and heat load and the corresponding thermal power unit load are calculated.

[0107] Further, as shown in Figure 3 the embodiments of the present application can include a data acquisition module, a thermal power unit prediction unit, an integrated energy system device prediction unit, a digital twin prediction module, a fault detection module and an integrated operation and maintenance module.

[0108] The running mode of the present application in the real-time monitoring and fault detection state is:

[0109] (1) The data acquisition module receives the real-time data of each device of the integrated energy system of the thermal power plant, and transmits the data to the digital twin prediction module, the fault detection module and the integrated operation and maintenance module;

[0110] Among them, the real-time data received and transmitted to the digital twin prediction module include: cold load, heat load, air extraction load, electric load, cold air extraction amount, heat air extraction amount, garbage incineration amount, biomass gasification amount.

[0111] The real-time data received and transmitted to the fault detection module include: coal flow, steam pressure and temperature of the thermal power unit, fuel flow, heat pump inlet and outlet temperature and flow, absorption refrigeration unit inlet and outlet temperature and flow, cold load, heat load, air extraction load, electric load, heat air extraction amount, cold air extraction amount, coal consumption, main steam flow, three-stage air extraction parameters, regenerative heater outlet parameters, regenerative air extraction parameters.

[0112] The real-time data received and transmitted to the integrated operation and maintenance module include: garbage gasification furnace temperature and pressure, garbage incineration amount, feed flow, biomass gasification furnace temperature and pressure, feed flow, biomass gasification amount, coal mill temperature, pulverized coal flow, steam pressure and temperature of the thermal power generating unit, fuel flow, heat pump inlet and outlet temperature and flow, absorption refrigeration unit inlet and outlet temperature and flow, energy storage state, cold load, heat load, air extraction load, electric load, hot air extraction amount, cold air extraction amount, new energy power generation amount, coal consumption amount, main steam flow, three-stage air extraction parameters, regenerative heater outlet parameters, and regenerative air extraction parameters.

[0113] (ii) The thermal power generating unit prediction unit and the integrated energy system equipment prediction unit (i.e., the digital twin prediction module) process the received data to obtain prediction results, which are respectively transmitted to the fault detection module and the integrated operation and maintenance module.

[0114] The predicted data include: coal consumption amount, main steam flow, three-stage air extraction parameters, regenerative heater outlet parameters, and regenerative air extraction parameters.

[0115] (iii) The prediction results of the thermal power generating unit prediction unit are transmitted to the fault detection module, and it is determined whether there is a fault by comparing the data, and the results are transmitted to the integrated operation and maintenance module.

[0116] (iv) The integrated operation and maintenance module receives various data and states, which are displayed in the visualization module of the integrated operation and maintenance according to different partitions.

[0117] According to the method for operating and regulating the integrated energy system of a thermal power plant based on a BP neural network, the mechanism of the neural network loss function of the digital twin model of the power generation side of the thermal power plant is corrected, the prediction accuracy of the digital twin model of the power generation side is greatly improved while ensuring efficient operation of the model, the corresponding results are rapidly predicted by the neural network, and real-time feedback is provided to the digital twin model control platform, thereby realizing real-time monitoring and prediction of various data; the prediction data of the digital twin model and various data of the integrated energy system of the thermal power plant are compared in real time based on the evaluation index of the digital twin model, abnormal data are reported, and discovery and diagnosis of faults of the equipment of the integrated energy system are realized; the system operating state after adjustment of the operating parameters is rapidly predicted by the digital twin model, data that are difficult to measure in the integrated energy system are efficiently predicted, and rapid and accurate adjustment of the operating parameters of the integrated energy system of the thermal power plant is realized; the operating state of the equipment is judged based on the matching relationship between energy supply and demand, and intelligent operation and maintenance of the integrated energy system of the thermal power plant is realized. Thus, the problems that related technologies do not consider solving the problems of a power plant at the present stage, such as a decrease in power generation hours and insufficient profitability, and that only use a neural network model for prediction, which has insufficient prediction accuracy and only considers obtaining prediction data without designing from the perspective of operation and maintenance of the power plant, are solved.

[0118] Secondly, the device for operation and maintenance and regulation and control of a thermal power plant comprehensive energy system based on a BP neural network according to an embodiment of the present application is described with reference to the accompanying drawings.

[0119] Figure 4 is a structural schematic diagram of the device for operation and maintenance and regulation and control of a thermal power plant comprehensive energy system based on a BP neural network according to an embodiment of the present application.

[0120] As shown in Figure 4 , the device for operation and maintenance and regulation and control of a thermal power plant comprehensive energy system based on a BP neural network 10 comprises a collection module 100, a prediction module 200, a detection module 300, an operation and maintenance module 400, and a regulation and control module 500.

[0121] Specifically, the collection module 100 is configured to collect real-time data and load demand of at least one device in the thermal power plant comprehensive energy system.

[0122] The prediction module 200 is configured to generate at least one prediction data of a target steam amount, a target fuel amount, and a target electric load according to the real-time data.

[0123] The detection module 300 is configured to compare the at least one prediction data with the real-time data to generate a comparison result, and determine fault information of the thermal power plant comprehensive energy system according to the comparison result.

[0124] The operation and maintenance module 400 is configured to regulate the operation of the comprehensive energy system according to the fault information, the at least one prediction data, the real-time data, and the load demand to generate an operation result.

[0125] The regulation and control module 500 is configured to determine a load fluctuation condition according to the load demand based on the operation result, and regulate the comprehensive energy system according to the load fluctuation condition, the real-time data, and the at least one prediction data to generate a regulation and control scheme of the comprehensive energy system.

[0126] Optionally, in an embodiment of the present application, the prediction module 200 comprises a first prediction unit, a second prediction unit, and a determination unit.

[0127] The first prediction unit is configured to optimize a neural network loss function of a mechanism to generate a mechanism-optimized neural network, and predict an operating parameter in a production process by using the mechanism-optimized neural network to generate first prediction data.

[0128] The second prediction unit is configured to process operating data of each device in the thermal power plant comprehensive energy system to obtain processed operating data, and predict an operating parameter in a production process by using a preset neural network based on the processed operating data to generate second prediction data.

[0129] The determination unit is configured to determine the at least one prediction data according to the first prediction data and the second prediction data.

[0130] Optionally, in an embodiment of the present application, the calculation formula of the generator set neural network loss function is:

[0131] LOSS = aLOSS phys + bLOSS math ,

[0132] wherein LOSS phys is a physical loss function, and LOSS math is a mathematical, i.e., neural network loss function.

[0133] Optionally, in an embodiment of the present application, the fault detection module 300 comprises a detection unit and a determination unit.

[0134] The detection unit is configured to detect, based on the comparison result, whether the real-time data satisfies the preset abnormal condition according to the value of the determination coefficient and the value of the mean square error.

[0135] The determination unit is configured to determine that the real-time data satisfies the preset abnormal condition and determine that the integrated energy system of the thermal power plant has a fault in a case where both the value of the determination coefficient and the value of the mean square error exceed the preset threshold value, and otherwise determine that the integrated energy system of the thermal power plant does not have a fault.

[0136] Optionally, in an embodiment of the present application, the calculation formula of the value of the determination coefficient is:

[0137]

[0138] wherein y real is an actual value of the data, y pred is a predicted value obtained based on a model, is an average value of the actual value; and

[0139] The calculation formula of the value of the mean square error is:

[0140]

[0141] wherein m is a total number of samples, y real is an actual value of the data, and y pred is a predicted value obtained based on a model.

[0142] Optionally, in an embodiment of the present application, the regulation and control module 500 comprises:

[0143] The determination unit is configured to determine whether the output electric energy of the energy supply side of the integrated energy system is greater than or equal to the electric load of the user demand side.

[0144] a storage unit, configured to store first electric energy meeting a preset excess condition to a target energy storage device to obtain cold energy and heat energy when the electric energy output by the energy supply side of the integrated energy system is greater than or equal to the electric load of the user demand side, and the steam output by the energy supply side is greater than or equal to the amount of steam required by the cold load and the heat load;

[0145] a conversion unit, configured to supply the user side with the electric energy output by the energy supply side meeting a first preset partial condition, and convert the electric energy output by the energy supply side meeting a second preset partial condition into cold energy and heat energy when the electric energy output by the energy supply side of the integrated energy system is greater than or equal to the electric load of the user demand side, and the steam output by the energy supply side is less than the amount of steam required by the cold load and the heat load;

[0146] a first obtaining unit, configured to supply the target device with the steam output by the energy supply side to obtain the cold load and the heat load when the electric energy output by the energy supply side of the integrated energy system is less than the electric load of the user demand side, and the steam output by the energy supply side is greater than or equal to the amount of steam required by the cold load and the heat load;

[0147] a second obtaining unit, configured to supply the target device with the steam output by the energy supply side to obtain the cold load and the heat load when the electric energy output by the energy supply side of the integrated energy system is less than the electric load of the user demand side, and the steam output by the energy supply side is less than the amount of steam required by the cold load and the heat load;

[0148] a scheme determining unit, configured to determine a regulation scheme of the integrated energy system according to the cold energy, the heat energy, the cold load and the heat load.

[0149] It should be noted that the foregoing explanation and description of the embodiment of the method for operating and regulating the integrated energy system of the thermal power plant based on the BP neural network also applies to the embodiment of the device for operating and regulating the integrated energy system of the thermal power plant based on the BP neural network, which will not be described here.

[0150] The power plant comprehensive energy system operation and maintenance regulation and control device based on the BP neural network provided in the embodiment of the application can greatly improve the prediction accuracy of the power generation side digital twin model by mechanism correction of the neural network loss function of the power generation side of the digital twin model while ensuring efficient operation of the model; the corresponding result is rapidly predicted by the neural network, and real-time feedback is provided to the digital twin model control platform, so that real-time monitoring and prediction of various data are realized; in combination with the digital twin model evaluation index, the prediction data of the digital twin model and various data of the power plant comprehensive energy system are compared in real time, abnormal data are reported, and discovery and diagnosis of equipment faults of the comprehensive energy system are realized; the system operation state after adjustment of the operation parameters is rapidly predicted by the digital twin model, data that are difficult to measure in the comprehensive energy system are efficiently predicted, and rapid and accurate adjustment of the operation parameters of the power plant comprehensive energy system and the like is realized; the operation state of the equipment is judged based on the matching relationship of energy supply and demand, and intelligent operation and maintenance of the power plant comprehensive energy system is realized. Thus, the problems that related technologies do not consider solving the problems of power plants at the present stage, such as reduction of power generation hours and insufficient profitability, and that only the neural network model is used for prediction, the prediction accuracy is not enough, and only prediction data are obtained without design from the operation and maintenance point of view of the power plant are solved.

[0151] Figure 5 The structure schematic diagram of the electronic device provided in the embodiment of the application is provided. The electronic device can include:

[0152] The memory 501, the processor 502, and the computer program stored in the memory 501 and executable on the processor 502.

[0153] The processor 502 implements the power plant comprehensive energy system operation and maintenance regulation and control method based on the BP neural network provided in the above embodiment when executing the program.

[0154] Further, the electronic device further includes:

[0155] The communication interface 503 is used for communication between the memory 501 and the processor 502.

[0156] The memory 501 is used for storing the computer program executable on the processor 502.

[0157] The memory 501 can include a high-speed RAM memory, and can also include a non-volatile memory, for example, at least one disk memory.

[0158] If the memory 501, the processor 502 and the communication interface 503 are implemented independently, the communication interface 503, the memory 501 and the processor 502 can be connected with each other through a bus and complete communication between each other. The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. The bus can be divided into an address bus, a data bus, a control bus, etc. For convenience of representation, Figure 5 Only one thick line is used to represent the bus in the figure, but it does not mean that there is only one bus or only one type of bus.

[0159] Optionally, in a specific implementation, if the memory 501, the processor 502 and the communication interface 503 are integrated on a chip, the memory 501, the processor 502 and the communication interface 503 can complete communication between each other through an internal interface.

[0160] The processor 502 can be a Central Processing Unit (CPU), or an Application Specific Integrated Circuit (ASIC), or one or more integrated circuits configured to implement one or more embodiments of the present application.

[0161] The embodiment further provides a computer readable storage medium, having stored thereon a computer program, which, when executed by a processor, implements the method for operation and maintenance regulation and control of a thermal power plant comprehensive energy system based on a BP neural network as above.

[0162] The embodiment of the present application further provides a computer program product, having stored thereon a computer program, which, when executed by a processor, implements the method for operation and maintenance regulation and control of a thermal power plant comprehensive energy system based on a BP neural network as above.

[0163] In the description of the application, reference to "one embodiment", "some embodiments", "an example", "a specific example", or "some examples" means that a particular feature, structure, material, or characteristic being described is included in at least one embodiment or example of the application. The appearances of the phrase in various places in the specification are not necessarily all referring to the same embodiment or example. Furthermore, the described specific features, structures, materials, or characteristics can be combined in any suitable manner in one or more embodiments or examples. In addition, the usage of "N" means at least two, for example, two, three or the like, unless explicitly stated otherwise.

[0164] Furthermore, the terms "first", "second", or the like, are used merely as a designation of certain elements or features of the application, and do not imply or connote relative importance or a specific order of precedence. Thus, features defined with "first", "second", etc. can include at least one of the features, either explicitly or implicitly.

[0165] Any process or method descriptions or blocks in flow charts or otherwise described herein represent embodiments of modules, segments, or portions of code which include one or more executable instructions for implementing specific logic functions or steps, and alternate implementations are possible. In some embodiments, the processes or methods described in flow charts or otherwise described herein are not necessarily performed in the order shown or discussed, including, for example, performing or depending from other operations or stages, in parallel, in reverse order, or in some other suitable manner. Blocks can also be skipped or performed more than once depending on the logic of the method or process.

[0166] The logic and / or steps represented in the flowcharts and / or described herein, for example, can be considered as a sequence of executable instructions stored in a computer readable medium, which can be executed by an instruction execution system, apparatus or device, such as a computer-based system, a processor-based system, or other system that can fetch the instructions from the instruction execution system, apparatus or device and execute the instructions, or a combination of the above. For the purposes of this specification, a "computer readable medium" can be any apparatus that can contain, store, communicate, propagate, or transport the program for use by or in connection with the instruction execution system, apparatus or device. The computer readable medium can be a computer readable storage medium or a computer readable signal medium. The computer readable storage medium can include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or a propagation medium. The computer readable signal medium can include, but is not limited to, a computer readable medium that facilitates transfer of the program from one place to another. A specific example of a computer readable medium is a non-transitory computer-readable storage medium. A specific example of a computer readable signal medium is a source or destination of the computer readable medium. Another specific example of a computer readable signal medium is a computer readable signal travelling through space. Thus, a computer readable medium can take many forms of hardware to carry out the program for use by or in connection with the instruction execution system, apparatus or device.

[0167] It should be understood that aspects of the application can be implemented in hardware, software, firmware or a combination thereof. In the above embodiments, the N steps or methods can be implemented in software or firmware stored in a memory and executed by a suitable instruction execution system. As such, if implemented in hardware, and in another embodiment, any of the following technologies, known in the art, or their combinations can be used: discrete logic circuitry having logic gates for implementing logic functions on data signals, application specific integrated circuits having appropriate combinational logic gates, programmable gate arrays (PGA), field programmable gate arrays (FPGA), and the like.

[0168] Those skilled in the art can understand that all or part of the steps carried out by the above-mentioned embodiment methods can be completed by programs instructing related hardware, and the programs can be stored in a computer readable storage medium. When the programs are executed, one or a combination of the steps of the method embodiments is included.

[0169] In addition, each of the functional units in the various embodiments of the present application can be integrated in one processing module, or each of the units can be physically present separately, or two or more units can be integrated in one module. The integrated module can be implemented in the form of hardware or in the form of a software functional module. When the integrated module is implemented in the form of a software functional module and sold or used as an independent product, it can also be stored in a computer readable storage medium.

[0170] The storage medium mentioned above can be a read-only memory, a magnetic disk or an optical disk, etc. Although the embodiments of the present application have been shown and described above, it should be understood that the above embodiments are exemplary and should not be construed as limiting the present application, and those skilled in the art can make changes, modifications, replacements and variations to the above embodiments within the scope of the present application.

Claims

1. A method for operation and maintenance regulation of a comprehensive energy system of a thermal power plant based on a BP neural network, characterized in that, The method comprises the following steps: Collecting real-time data and load demand of at least one device in a thermal power plant comprehensive energy system; Generating at least one prediction data of target steam quantity, target fuel quantity and target electric load according to the real-time data; Comparing the at least one prediction data with the real-time data to generate a comparison result, and determining fault information of the thermal power plant comprehensive energy system according to the comparison result; Controlling operation of the comprehensive energy system according to the fault information, the at least one prediction data, the real-time data and the load demand to generate an operation result; Determining load fluctuation according to the load demand based on the operation result, and controlling the comprehensive energy system according to the load fluctuation, the real-time data and the at least one prediction data to generate a control scheme of the comprehensive energy system; The method comprises the following steps: The calculation formula of the generator set neural network loss function is: ， wherein, is a physical loss function, is a mathematical, i.e. neural network loss function; The method comprises the following steps: The calculation formula of the determination coefficient is: ， wherein, is the actual value of the data, is the predicted value derived based on the model, is the average value of the actual values; The calculation formula of the mean square error is: ， wherein, is the total number of samples, is the actual value of the data, is the predicted value derived based on the model.

2. The method of claim 1, wherein, The method comprises the following steps: Determining whether the output electric energy of the energy supply side of the comprehensive energy system is greater than or equal to the electric load of the user demand side; If the output electric energy of the energy supply side of the comprehensive energy system is greater than or equal to the electric load of the user demand side, and the output steam of the energy supply side is greater than or equal to the steam quantity required by the cold load and the heat load, then the first electric energy meeting the preset excess condition is stored in the target energy storage device to obtain cold energy and heat energy; If the output electric energy of the energy supply side in the integrated energy system is greater than or equal to the electric load of the user demand side, and the output steam of the energy supply side is less than the steam required by the cold load and the heat load, the first preset part condition of the energy supply side output electric energy is met, the user side is supplied with the energy supply side output electric energy, and the energy supply side output electric energy meeting the second preset part condition is converted into the cold energy and the heat energy; If the output electric energy of the energy supply side in the integrated energy system is less than the electric load of the user demand side, and the output steam of the energy supply side is greater than or equal to the steam required by the cold load and the heat load, the output steam of the energy supply side is supplied to the target device to obtain the cold load and the heat load; If the output electric energy of the energy supply side in the integrated energy system is less than the electric load of the user demand side, and the output steam of the energy supply side is less than the steam required by the cold load and the heat load, the output steam of the energy supply side is supplied to the target device to obtain the cold load and the heat load; The control scheme of the integrated energy system is determined according to the cold energy, the heat energy, the cold load and the heat load.

3. A device for operation and maintenance regulation and control of a comprehensive energy system of a thermal power plant based on a BP neural network, characterized in that, The BP neural network-based operation and maintenance control method for the integrated energy system of the thermal power plant according to any one of claims 1-2 comprises: A collection module for collecting real-time data and load demand of at least one device in the integrated energy system of the thermal power plant; A prediction module for generating at least one prediction data of target steam quantity, target fuel quantity and target electric load according to the real-time data; A detection module for comparing the at least one prediction data with the real-time data to generate a comparison result, and determining fault information of the integrated energy system of the thermal power plant according to the comparison result; An operation and maintenance module for controlling the operation of the integrated energy system according to the fault information, the at least one prediction data, the real-time data and the load demand to generate an operation result; A control module for determining load fluctuation according to the load demand based on the operation result, and controlling the integrated energy system according to the load fluctuation, the real-time data and the at least one prediction data to generate a control scheme of the integrated energy system; The prediction module comprises: a first prediction unit for mechanism-optimized generator set neural network loss function to generate a mechanism-optimized neural network, and predict the operating parameters in the production process by using the mechanism-optimized neural network to generate first prediction data; a second prediction unit for processing operating data of each device in the integrated energy system of the thermal power plant to obtain processed operating data, and predicting the operating parameters in the production process by using a preset neural network based on the processed operating data to generate second prediction data; and a determination unit for determining the at least one prediction data according to the first prediction data and the second prediction data; The calculation formula of the generator set neural network loss function is: ， wherein, is a physical loss function, is a mathematical, i.e. neural network loss function; The detection module comprises: a detection unit, configured to detect whether the real-time data satisfies a preset abnormal condition according to a value of a determination coefficient and a value of a mean square error based on the comparison result; and a judgment unit, configured to determine that the real-time data satisfies the preset abnormal condition and determine that the integrated energy system of the thermal power plant has a fault in a case where the value of the determination coefficient and the value of the mean square error both exceed a preset threshold value, and otherwise, determine that the integrated energy system of the thermal power plant does not have a fault. The value of the determination coefficient is calculated according to the following formula: ， wherein, is the actual value of the data, is the predicted value derived based on the model, is the average value of the actual values; The value of the mean square error is calculated according to the following formula: ， wherein, is the total number of samples, is the actual value of the data, is the predicted value derived based on the model.

4. An electronic device, comprising: Comprise: A memory, a processor, and a computer program stored on the memory and executable on the processor, the processor executing the program to implement the method for operation and regulation of an integrated energy system of a thermal power plant based on a BP neural network according to any one of claims 1-2.

5. A computer-readable storage medium having stored thereon a computer program, characterized in that, The program is executed by the processor to implement the method for operation and regulation of an integrated energy system of a thermal power plant based on a BP neural network according to any one of claims 1-2.

6. A computer program product comprising a computer program, characterized in that, The computer program is executed to implement the method for operation and regulation of an integrated energy system of a thermal power plant based on a BP neural network according to any one of claims 1-2.

Images