Energy utilization efficiency optimization method based on supercritical unit

Abstract

The invention provides an energy utilization efficiency optimization method based on a supercritical unit, and belongs to the technical field of efficiency optimization. The method comprises the steps of 1, obtaining energy operation parameters of a target thermodynamic system, and collecting energy operation original data based on a sensor; 2, performing parameter identification on the energy operation original data by adopting a genetic algorithm, and screening characteristic energy operation data in a preset load range; 3, based on the working principle of the supercritical unit, an energy efficiency model of the target thermodynamic system is established in combination with the characteristic energy operation data; 4, based on the energy efficiency model, analyzing the efficiency of the target thermodynamic system, and identifying and judging whether energy loss exists or not; and 5, if the energy loss exists, performing control optimization on each device of the target thermodynamic system by using a control algorithm. By optimizing the energy efficiency, the energy loss is reduced, and the operation performance and the energy-saving effect of the system are improved.

Description

Technical Field

[0001] The invention relates to the technical field of efficiency optimization, and in particular to an energy utilization efficiency optimization method based on a supercritical unit. Background Art

[0002] At present, with the continuous growth of global energy demand and the increasingly severe environmental problems, efficient use of energy and energy conservation and emission reduction have become key issues that need to be solved urgently. Especially in the power industry, the energy efficiency of the thermal system is directly related to energy consumption and environmental burden. However, the analysis efficiency of energy utilization by collecting parameters is poor for equipment and systems, and the analysis results are inaccurate.

[0003] Therefore, the present invention proposes an energy utilization efficiency optimization method based on a supercritical unit. Summary of the invention

[0004] The present invention provides an energy utilization efficiency optimization method based on a supercritical unit, which is used to perform parameter identification on energy data through a genetic algorithm, establish an efficiency model in combination with the principle of a supercritical unit, analyze energy loss, and use a control algorithm to optimize the system, thereby improving energy utilization efficiency and reducing energy waste.

[0005] In one aspect, the present invention provides a method for optimizing energy utilization efficiency based on a supercritical unit, comprising: Step 1: Obtain the energy operation parameters of the target thermal system and collect the raw data of energy operation based on sensors; Step 2: Use genetic algorithm to identify parameters of the original energy operation data and select characteristic energy operation data within the preset load range; Step 3: Based on the working principle of the supercritical unit and combined with the characteristic energy operation data, an energy efficiency model of the target thermal system is established; Step 4: Based on the energy efficiency model, analyze the efficiency of the target thermal system and identify whether there is energy loss; Step 5: If there is energy loss, use the control algorithm to optimize the control of each device in the target thermal system.

[0006] On the other hand, the energy operation parameters of the target thermal system are obtained, including: Identify the target thermal system for research and optimization; And according to the operating principle and research needs of the target thermal system, the target energy operating parameters to be monitored are determined.

[0007] On the other hand, sensors are used to collect raw data on energy operation, including: Match sensor type according to energy operation parameters; Obtain a structural design drawing of a target thermal system, obtain all configurable sensor positions of the target thermal system, obtain a matching degree between any sensor and a configurable sensor position, sort the configurable sensor positions by matching degree, and select an optimal sensor position according to a preset configuration quantity; A unique first identifier is configured for the sensor, a unique second identifier is configured for the optimal position of the sensor, the sensor is configured and installed according to the matching relationship between the first identifier and the second identifier, and the energy operation raw data of the target thermal system is collected based on the sensor.

[0008] On the other hand, genetic algorithms are used to identify parameters of the original energy operation data and filter characteristic energy operation data within the preset load range, including: Clean the raw data of any energy operation data and standardize them based on national standard units to obtain standard energy operation data; Encoding standard energy operation data of any parameter type into chromosomes, and setting a search space according to a preset load range of the standard energy operation data; Initialize the population, a set of parameter-type chromosomes represents an individual; Take two individuals as parents, perform gene combination, and the offspring parameters generated by crossover are: ;in Represents the offspring parameters, represents the preset cross coefficient, represents the first parent parameter, Represents the second parent parameter; The fitness function of the population is generated based on the standard operating threshold of the target thermal system. Any individual is input into the fitness function. If no individual in the current population meets the fitness threshold, the gene crossover combination is iterated until an individual that meets the fitness threshold appears in the population. The individual is the optimal solution, and the parameter type and parameter value corresponding to the individual are the characteristic energy operation data.

[0009] On the other hand, based on the working principle of supercritical units and combined with characteristic energy operation data, an energy efficiency model of the target thermal system is established, including: Based on the working principle of supercritical units, the supercritical parameter values ​​of the target thermal system are constructed; The characteristic energy operation data is used as input variables, and the energy efficiency of the target thermal system is used as output variables; According to the parameter type of any input variable, a fuzzy set and a membership function are defined, and fuzzy rules are formulated according to supercritical parameter values, wherein the fuzzy rules and the membership function constitute a fuzzy reasoning layer; Input variables are fed into the fuzzy inference layer to obtain fuzzy outputs, which are then transferred to the neural network layer for processing, and the fuzzy inference results are mapped to actual energy efficiency values; The energy efficiency model of the target thermal system obtained according to the mapping function is: ;in Indicates the actual energy efficiency value, ( ) represents the mapping function based on the neural network layer, represents the input variable, Indicates the characteristic energy operation data of the first parameter type, Indicates the characteristic energy operation data of the nth parameter type.

[0010] On the other hand, based on the energy efficiency model, the efficiency of the target thermal system is analyzed, including: Adjust a single input variable, output the corresponding energy efficiency value based on the energy efficiency model, and generate a single change curve of energy efficiency value-input variable.

[0011] On the other hand, it is also necessary to identify whether there is energy loss, including: Based on the energy efficiency values ​​of all parameter types - a single variation curve of the input variables, the energy loss rate is analyzed as: ;in, represents the energy loss rate, Indicates the output power, Represents input variables of all parameter types, represents the input power, It represents the mean slope of the single change curve of the output energy efficiency value of the i-th input variable - the input variable, It represents the input energy efficiency value of the i-th input variable - the mean slope of the single change curve of the input variable; If the energy loss rate is greater than a preset threshold, it is determined that energy loss exists in the target thermal system.

[0012] On the other hand, if there is energy loss, the control algorithm is used to optimize the control of each device in the target thermal system, including: If the target thermal system has energy loss, the cost function is constructed based on the optimal efficiency threshold of the target thermal system as a constraint condition and all parameter types as the optimization target of the cost function; Based on the control algorithm, the cost function is controlled by a first parameter, a first cost result is output, a difference between the first cost result and the constraint condition is obtained, the difference is input into the control algorithm to output a first control parameter, and it is iterated until the absolute value of the difference between the first cost result and the constraint condition is less than a minimum threshold, and it is determined that the control optimization is completed; The control parameters are optimal control parameters, and each device of the target thermal system is controlled and optimized according to the control parameters.

[0013] Compared with the prior art, the present invention has the following beneficial effects: The present invention provides an energy utilization efficiency optimization method based on a supercritical unit, which is used to perform parameter identification on energy data through a genetic algorithm, establish an efficiency model in combination with the principle of a supercritical unit, analyze energy loss, and use a control algorithm to optimize the system, thereby improving energy utilization efficiency and reducing energy waste. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0015] Figure 1 It is a flow chart of a method for optimizing energy utilization efficiency based on a supercritical unit provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0016] In order to make the purpose, technical solution and advantages of the present invention clearer, the technical solution of the present invention will be clearly and completely described below in conjunction with the drawings of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0017] Embodiment 1: like Figure 1 As shown, the energy utilization efficiency optimization method based on a supercritical unit provided in an embodiment of the present invention includes: Step 1: Obtain the energy operation parameters of the target thermal system and collect the raw data of energy operation based on sensors; Step 2: Use genetic algorithm to identify parameters of the original energy operation data and select characteristic energy operation data within the preset load range; Step 3: Based on the working principle of the supercritical unit and combined with the characteristic energy operation data, an energy efficiency model of the target thermal system is established; Step 4: Based on the energy efficiency model, analyze the efficiency of the target thermal system and identify whether there is energy loss; Step 5: If there is energy loss, use the control algorithm to optimize the control of each device in the target thermal system.

[0018] In this embodiment, the target thermal system refers to a thermal system that requires energy efficiency optimization, energy loss analysis, and control optimization.

[0019] In this embodiment, energy operation parameters refer to various key indicators related to energy production, transmission, and utilization in the target thermal system, including: temperature, pressure, flow, fuel consumption, etc.

[0020] In this embodiment, the sensor is a device used to sense, detect, measure physical quantities and chemical quantities and convert these signals into readable data.

[0021] In this embodiment, the energy operation raw data refers to basic data reflecting the operating status of the target thermal system collected in real time by sensors or other measuring devices.

[0022] In this embodiment, the genetic algorithm is an optimization algorithm that simulates the principles of natural selection and genetics, and belongs to the category of evolutionary algorithms. It searches for the optimal solution to a problem by simulating the evolution process of organisms in nature.

[0023] In this embodiment, parameter identification refers to the process of estimating unknown parameter values ​​in the system through existing experimental data or observation data.

[0024] In this embodiment, the preset load range refers to a load range set in advance during the system operation or analysis process, which is used to screen and analyze energy operation data.

[0025] In this embodiment, characteristic energy operation data refers to data that can effectively reflect the system operation status and performance after screening and extraction during the energy operation process.

[0026] In this embodiment, the supercritical unit is a highly efficient thermal power generating unit, which is widely used in the field of power generation, especially in thermal power plants. It refers to a thermal power unit using supercritical steam parameters. The main feature is that the working medium reaches a supercritical state after being heated in the boiler, that is, the pressure is higher than the critical pressure (22.06 MPa), and the temperature is usually higher than the critical temperature (374°C).

[0027] In this embodiment, the energy efficiency model is a mathematical model of the energy conversion process and efficiency performance of a system under different working conditions.

[0028] In this embodiment, energy loss refers to the fact that energy is not effectively converted into useful work due to various reasons during the process of energy conversion, transmission or use.

[0029] In this embodiment, the control algorithm adjusts the operating state of the system based on the system model, real-time operating data and optimization objectives.

[0030] The working principle and beneficial effects of the above technical solution are: through sensor data collection and genetic algorithm identification, combined with the principle of supercritical units, an efficiency model is established, energy losses are analyzed and identified, and finally the operation of the thermal system is optimized through the control algorithm, energy efficiency is improved, energy waste is reduced, and system performance is improved.

[0031] Embodiment 2: Based on the above embodiment 1, the energy operation parameters of the target thermal system are obtained, including: Identify the target thermal system for research and optimization; And according to the operating principle and research needs of the target thermal system, the target energy operating parameters to be monitored are determined.

[0032] In this embodiment, the research requirement refers to the specific goal that is desired to be achieved when conducting a thermal system optimization study.

[0033] In this embodiment, the target energy operating parameters refer to key energy-related data that need to be monitored, recorded and analyzed in the thermal system.

[0034] The working principle and beneficial effects of the above technical solution are: clarify the target thermal system, determine the key energy operation parameters based on the operation principle and research needs, use genetic algorithms and control optimization technology to achieve accurate monitoring and improvement of system energy efficiency, optimize energy utilization efficiency, reduce energy loss, and improve system stability.

[0035] Embodiment 3: Based on the above embodiment 2, the energy operation raw data is collected based on the sensor, including: Match sensor type according to energy operation parameters; Obtain a structural design drawing of a target thermal system, obtain all configurable sensor positions of the target thermal system, obtain a matching degree between any sensor and a configurable sensor position, sort the configurable sensor positions by matching degree, and select an optimal sensor position according to a preset configuration quantity; A unique first identifier is configured for the sensor, a unique second identifier is configured for the optimal position of the sensor, the sensor is configured and installed according to the matching relationship between the first identifier and the second identifier, and the energy operation raw data of the target thermal system is collected based on the sensor.

[0036] In this embodiment, the structural design drawing is a technical drawing that describes in detail the relationship between the components and equipment of the thermal system.

[0037] In this embodiment, the configurable position refers to a specific position where the sensor can be installed.

[0038] In this embodiment, the matching degree is an indicator used to quantify and measure the adaptability or suitability between the sensor and its installation location.

[0039] In this embodiment, the preset configuration quantity refers to a preset given quantity range.

[0040] In this embodiment, the optimal position refers to the position that best meets the requirements and can most effectively obtain the energy operation data of the target thermal system, which is selected among all configurable sensor positions after sorting the matching degrees with different sensors.

[0041] In this embodiment, the first identification refers to a unique identifier assigned to each sensor.

[0042] In this embodiment, the second identifier refers to a unique identifier assigned to the optimal position of each sensor.

[0043] The working principle and beneficial effects of the above technical solution are: by matching the sensor type with the energy operation parameters, combining the target thermal system structure and the sensor configuration position, optimizing the sensor installation position and marking it, ensuring accurate data collection, providing efficient data support for system operation monitoring, and improving system performance and energy utilization efficiency.

[0044] Embodiment 4: On the basis of the above-mentioned embodiment 1, a genetic algorithm is used to perform parameter identification on the original energy operation data, and characteristic energy operation data is screened within a preset load range, including: Clean the raw data of any energy operation data and standardize them based on national standard units to obtain standard energy operation data; Encoding standard energy operation data of any parameter type into chromosomes, and setting a search space according to a preset load range of the standard energy operation data; Initialize the population, a set of parameter-type chromosomes represents an individual; Take two individuals as parents, perform gene combination, and the offspring parameters generated by crossover are: ;in Represents the offspring parameters, represents the preset cross coefficient, represents the first parent parameter, Represents the second parent parameter; The fitness function of the population is generated based on the standard operating threshold of the target thermal system. Any individual is input into the fitness function. If no individual in the current population meets the fitness threshold, the gene crossover combination is iterated until an individual that meets the fitness threshold appears in the population. The individual is the optimal solution, and the parameter type and parameter value corresponding to the individual are the characteristic energy operation data.

[0045] In this embodiment, data cleaning refers to the process of processing and correcting original data to improve data quality.

[0046] In this embodiment, the national standard unit refers to a standard measurement unit uniformly stipulated by the state, which is used to ensure the accuracy and consistency of various types of data and information in different fields and regions.

[0047] In this embodiment, standardization is a technology in data preprocessing, and its main purpose is to convert data of different ranges or different units into a unified standard format.

[0048] In this embodiment, the standard energy operation data refers to the energy operation data after data cleaning and unit standardization.

[0049] In this embodiment, the chromosome is a code for a set of parameters, which is used to represent the parameters of the energy operation system.

[0050] In this embodiment, the search space refers to the set of all possible solutions that the algorithm can explore and optimize.

[0051] In this embodiment, a population refers to a group of individuals existing in a certain generation, and each individual is a solution composed of multiple parameters (ie, chromosomes).

[0052] In this embodiment, an individual refers to an element in a population, which is a specific solution and includes all parameter types and values ​​that need to be optimized.

[0053] In this embodiment, the parents refer to certain individuals in the current population, which are selected to perform a gene crossover operation to produce new offspring.

[0054] In this embodiment, gene combination is used to generate a new individual (offspring) in a process where a new solution can be generated by crossing the genes (i.e., the parameters) of the parent individuals.

[0055] In this embodiment, the offspring parameters refer to the parameters of new individuals generated by the gene crossover operation.

[0056] In this embodiment, the standard operation threshold refers to a preset indicator used to determine whether the energy system meets the standard operation requirements.

[0057] In this embodiment, the fitness function is an indicator used to measure the performance of each individual in the current problem.

[0058] The working principle and beneficial effects of the above technical solution are: energy operation data is processed through data cleaning and standardization, encoded into chromosomes and optimized using genetic algorithms, iterated based on the fitness function, and finally found the optimal solution that meets the threshold, providing accurate characteristic energy operation data and improving system optimization efficiency and accuracy.

[0059] Embodiment 5: On the basis of the above-mentioned embodiment 1, based on the working principle of the supercritical unit and combined with the characteristic energy operation data, an energy efficiency model of the target thermal system is established, including: Based on the working principle of supercritical units, the supercritical parameter values ​​of the target thermal system are constructed; The characteristic energy operation data is used as input variables, and the energy efficiency of the target thermal system is used as output variables; According to the parameter type of any input variable, a fuzzy set and a membership function are defined, and fuzzy rules are formulated according to supercritical parameter values, wherein the fuzzy rules and the membership function constitute a fuzzy reasoning layer; Input variables are fed into the fuzzy inference layer to obtain fuzzy outputs, which are then transferred to the neural network layer for processing, and the fuzzy inference results are mapped to actual energy efficiency values; The energy efficiency model of the target thermal system obtained according to the mapping function is: ;in Indicates the actual energy efficiency value, ( ) represents the mapping function based on the neural network layer, represents the input variable, Indicates the characteristic energy operation data of the first parameter type, Indicates the characteristic energy operation data of the nth parameter type.

[0060] In this embodiment, the supercritical parameter value refers to the value of the key thermodynamic parameter involved when the system reaches a supercritical state under the working principle of the supercritical unit.

[0061] In this embodiment, a fuzzy set is a set whose membership degree of its members is a continuous range.

[0062] In this embodiment, the membership function is used to describe the membership of each input variable in the fuzzy set.

[0063] In this embodiment, the fuzzy reasoning layer is a core part, which infers the input data through fuzzy logic rules and membership functions, and then derives the fuzzy output.

[0064] In this embodiment, the fuzzy output is a result obtained through the fuzzy reasoning layer, representing a fuzzy value of the energy efficiency of the target thermal system.

[0065] In this embodiment, the neural network layer is a key component in a deep learning model, which is used to further process and map the input data.

[0066] In this embodiment, the energy efficiency value refers to the efficiency of converting energy into useful work.

[0067] In this embodiment, the mapping function is the core part of the neural network layer, which converts the fuzzy output obtained by the fuzzy reasoning layer into an actual energy efficiency value. The neural network layer generates a corresponding mapping function by learning the complex relationship between the input variables and the output variables.

[0068] The working principle and beneficial effects of the above technical solution are: by combining the principle of supercritical units, fuzzy reasoning and neural networks, the characteristic energy operation data is converted into an energy efficiency model, and the actual energy efficiency is mapped through fuzzy rules and neural network layers to improve the accuracy and reliability of thermal system energy efficiency prediction.

[0069] Embodiment 6: On the basis of the above-mentioned embodiment 1, the efficiency of the target thermal system is analyzed based on the energy efficiency model, including: Adjust a single input variable, output the corresponding energy efficiency value based on the energy efficiency model, and generate a single change curve of energy efficiency value-input variable.

[0070] In this embodiment, the single change curve of energy efficiency value-input variable refers to a curve obtained by adjusting the value of a single input variable while keeping other input variables unchanged, and observing how the corresponding energy efficiency value (output variable) changes.

[0071] The working principle and beneficial effects of the above technical solution are: by adjusting a single input variable, using the energy efficiency model to output the corresponding energy efficiency value, generating a change curve between the input variable and the energy efficiency value, helping to analyze the impact of input variable changes on energy efficiency, and achieving system optimization and precise control.

[0072] Embodiment 7: On the basis of the above-mentioned embodiment 6, identifying and judging whether there is energy loss includes: Based on the energy efficiency values ​​of all parameter types - a single variation curve of the input variables, the energy loss rate is analyzed as: ;in, represents the energy loss rate, Indicates the output power, Represents input variables of all parameter types, represents the input power, It represents the mean slope of the single change curve of the output energy efficiency value of the i-th input variable - the input variable, It represents the input energy efficiency value of the i-th input variable - the mean slope of the single change curve of the input variable; If the energy loss rate is greater than a preset threshold, it is determined that energy loss exists in the target thermal system.

[0073] In this embodiment, the energy loss rate refers to the degree of energy loss in an energy system due to various reasons (such as reduced efficiency, heat loss, friction, etc.).

[0074] In this embodiment, the preset threshold is a value set according to system design, operation standards or industry specifications.

[0075] The working principle and beneficial effects of the above technical solution are: by analyzing the single change curve of all input variables, calculating the energy loss rate, and determining whether there is energy loss based on the set threshold, the energy efficiency problem of the thermal system is identified, and system optimization and energy-saving management are promoted.

[0076] Embodiment 8: Based on the above-mentioned embodiment 7, if there is energy loss, the control algorithm is used to optimize the control of each device of the target thermal system, including: If the target thermal system has energy loss, the cost function is constructed based on the optimal efficiency threshold of the target thermal system as a constraint condition and all parameter types as the optimization target of the cost function; Based on the control algorithm, the cost function is controlled by a first parameter, a first cost result is output, a difference between the first cost result and the constraint condition is obtained, the difference is input into the control algorithm to output a first control parameter, and it is iterated until the absolute value of the difference between the first cost result and the constraint condition is less than a minimum threshold, and it is determined that the control optimization is completed; The control parameters are optimal control parameters, and each device of the target thermal system is controlled and optimized according to the control parameters.

[0077] In this embodiment, the optimal efficiency threshold means that in a thermal system, when the energy efficiency of the system reaches or exceeds this value, the efficiency of the system operation is considered to be optimal.

[0078] In this embodiment, the constraint condition refers to a restriction related to an optimal efficiency threshold of the target thermal system.

[0079] In this embodiment, the cost function is a mathematical expression that measures the performance of the system and is related to control parameters (such as operating conditions of the equipment, adjustment parameters, etc.) and energy loss and efficiency of the system.

[0080] In this embodiment, the optimization goal is to optimize the various control parameters of the target thermal system through a control algorithm to minimize the cost function while satisfying the optimal efficiency threshold constraint of the system.

[0081] In this embodiment, the first parameter control refers to performing control adjustment according to a control algorithm.

[0082] In this embodiment, the first cost result refers to an output result of the cost function obtained after performing first parameter control on the target thermal system based on the control algorithm.

[0083] In this embodiment, the first control parameter refers to a parameter that is initially adjusted in the control algorithm and is used to optimize the performance of the target thermal system.

[0084] In this embodiment, the optimal control parameters refer to parameters obtained through iterative optimization of the control algorithm and capable of enabling the target thermal system to reach or approach the optimal efficiency.

[0085] The working principle and beneficial effects of the above technical solution are: by constructing a cost function and optimizing the operation of the target thermal system based on the control algorithm, the control parameters are iteratively adjusted until the optimal efficiency threshold is met, and finally the optimal control of each device in the thermal system is achieved, thereby improving the system energy efficiency and reducing energy losses.

[0086] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. The energy utilization efficiency optimization method based on supercritical units is characterized by: include: Step 1: Obtain the energy operation parameters of the target thermal system and collect the raw data of energy operation based on sensors; Step 2: Use genetic algorithm to identify parameters of the original energy operation data and select characteristic energy operation data within the preset load range; Step 3: Based on the working principle of the supercritical unit and combined with the characteristic energy operation data, an energy efficiency model of the target thermal system is established; Step 4: Based on the energy efficiency model, analyze the efficiency of the target thermal system and identify whether there is energy loss; Step 5: If there is energy loss, use the control algorithm to optimize the control of each device in the target thermal system.

2. The method for optimizing energy utilization efficiency based on supercritical units according to claim 1, characterized in that: Obtain the energy operation parameters of the target thermal system, including: Identify the target thermal system for research and optimization; And according to the operating principle and research needs of the target thermal system, the target energy operating parameters to be monitored are determined.

3. The method for optimizing energy utilization efficiency based on supercritical units according to claim 2, characterized in that: Collect raw data of energy operation based on sensors, including: Match sensor type according to energy operation parameters; Obtain a structural design drawing of a target thermal system, obtain all configurable sensor positions of the target thermal system, obtain a matching degree between any sensor and a configurable sensor position, sort the configurable sensor positions by matching degree, and select an optimal sensor position according to a preset configuration quantity; A unique first identifier is configured for the sensor, a unique second identifier is configured for the optimal position of the sensor, the sensor is configured and installed according to the matching relationship between the first identifier and the second identifier, and the energy operation raw data of the target thermal system is collected based on the sensor.

4. The method for optimizing energy utilization efficiency based on supercritical units according to claim 1, characterized in that: Genetic algorithms are used to identify parameters of the original energy operation data, and characteristic energy operation data are screened within the preset load range, including: Clean the raw data of any energy operation data and standardize them based on national standard units to obtain standard energy operation data; Encoding standard energy operation data of any parameter type into chromosomes, and setting a search space according to a preset load range of the standard energy operation data; Initialize the population, a set of parameter-type chromosomes represents an individual; Take two individuals as parents, perform gene combination, and the offspring parameters generated by crossover are: ;in Represents the offspring parameters, represents the preset cross coefficient, represents the first parent parameter, Represents the second parent parameter; The fitness function of the population is generated based on the standard operating threshold of the target thermal system. Any individual is input into the fitness function. If no individual in the current population meets the fitness threshold, the gene crossover combination is iterated until an individual that meets the fitness threshold appears in the population. The individual is the optimal solution, and the parameter type and parameter value corresponding to the individual are the characteristic energy operation data.

5. The method for optimizing energy utilization efficiency based on supercritical units according to claim 1, characterized in that: Based on the working principle of supercritical units and combined with characteristic energy operation data, an energy efficiency model of the target thermal system is established, including: Based on the working principle of supercritical units, the supercritical parameter values ​​of the target thermal system are constructed; The characteristic energy operation data is used as input variables, and the energy efficiency of the target thermal system is used as output variables; According to the parameter type of any input variable, a fuzzy set and a membership function are defined, and fuzzy rules are formulated according to supercritical parameter values, wherein the fuzzy rules and the membership function constitute a fuzzy reasoning layer; Input variables are fed into the fuzzy inference layer to obtain fuzzy outputs, which are then transferred to the neural network layer for processing, and the fuzzy inference results are mapped to actual energy efficiency values; The energy efficiency model of the target thermal system obtained according to the mapping function is: ;in Indicates the actual energy efficiency value, ( ) represents the mapping function based on the neural network layer, represents the input variable, Indicates the characteristic energy operation data of the first parameter type, Indicates the characteristic energy operation data of the nth parameter type.

6. The method for optimizing energy utilization efficiency based on supercritical units according to claim 1, characterized in that: Analyze the efficiency of the target thermal system based on the energy efficiency model, including: Adjust a single input variable, output the corresponding energy efficiency value based on the energy efficiency model, and generate a single change curve of energy efficiency value-input variable.

7. The method for optimizing energy utilization efficiency based on supercritical units according to claim 6, characterized in that: Identify whether there is energy loss, including: Based on the energy efficiency values ​​of all parameter types - a single variation curve of the input variables, the energy loss rate is analyzed as: ;in, represents the energy loss rate, Indicates the output power, Represents input variables of all parameter types, represents the input power, It represents the mean slope of the single change curve of the output energy efficiency value of the i-th input variable - the input variable, It represents the input energy efficiency value of the i-th input variable - the mean slope of the single change curve of the input variable; If the energy loss rate is greater than a preset threshold, it is determined that energy loss exists in the target thermal system.

8. The method for optimizing energy utilization efficiency based on supercritical units according to claim 7, characterized in that: If there is energy loss, the control algorithm is used to optimize the control of each device in the target thermal system, including: If the target thermal system has energy loss, the cost function is constructed based on the optimal efficiency threshold of the target thermal system as a constraint condition and all parameter types as the optimization target of the cost function; Based on the control algorithm, the cost function is controlled by a first parameter, a first cost result is output, a difference between the first cost result and the constraint condition is obtained, the difference is input into the control algorithm to output a first control parameter, and it is iterated until the absolute value of the difference between the first cost result and the constraint condition is less than a minimum threshold, and it is determined that the control optimization is completed; The control parameters are optimal control parameters, and each device of the target thermal system is controlled and optimized according to the control parameters.

Images