Energy utilization efficiency optimization method based on supercritical units

Abstract

The present invention provides an energy utilization efficiency optimization method based on a supercritical unit, belonging to the technical field of efficiency optimization. The steps include: Step 1: Obtain the energy operation parameters of the target thermal system and collect the original energy operation data based on sensors; Step 2: Use the genetic algorithm to perform parameter identification on the original energy operation data and screen the characteristic energy operation data within a preset load range; Step 3: Based on the working principle of the supercritical unit, establish an energy efficiency model of the target thermal system in combination with the characteristic energy operation data; Step 4: Based on the energy efficiency model, analyze the efficiency of the target thermal system and identify and judge whether there is energy loss; Step 5: If there is energy loss, use the control algorithm to optimize the control of each device of the target thermal system. By optimizing the energy efficiency, reducing the energy loss, the operation performance and energy-saving effect of the system are improved.

Description

Technical Field

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

[0002] Currently, with the continuous growth of global energy demand and the increasingly severe environmental problems, the efficient utilization of energy and energy conservation and emission reduction have become key issues 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, by collecting parameters to analyze energy utilization efficiency, the analysis efficiency of equipment and systems is poor 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 the supercritical unit, analyze energy losses, and use a control algorithm to optimize the system to improve energy utilization efficiency and reduce energy waste.

[0005] On the one hand, the present invention provides an energy utilization efficiency optimization method based on a supercritical unit, including:

[0006] Step 1: Obtain the energy operation parameters of the target thermal system, and collect the original energy operation data based on sensors;

[0007] Step 2: Perform parameter identification on the original energy operation data through a genetic algorithm, and screen the characteristic energy operation data within a preset load range;

[0008] Step 3: Based on the working principle of the supercritical unit, establish an energy efficiency model of the target thermal system in combination with the characteristic energy operation data;

[0009] Step 4: Based on the energy efficiency model, analyze the efficiency of the target thermal system and identify and judge whether there are energy losses;

[0010] Step 5: If there are energy losses, use a control algorithm to control and optimize each device of the target thermal system.

[0011] On the other hand, obtaining the energy operation parameters of the target thermal system includes:

[0012] Define the target thermal system to be studied and optimized;

[0013] And determine the target energy operation parameters to be monitored according to the operation principle and research requirements of the target thermal system.

[0014] On the other hand, based on the raw energy operation data collected by sensors, including:

[0015] Match the sensor type according to the energy operation parameters;

[0016] Obtain the structural design drawing of the target thermal system, obtain all the configurable positions of the sensors in the target thermal system, obtain the matching degree between any sensor and the configurable position of the sensor, sort the configurable positions of the sensors according to the matching degree, and screen the optimal positions of the sensors according to the preset configuration quantity;

[0017] Configure a unique first identifier for the sensor, configure a unique second identifier for the optimal position of the sensor, configure and install the sensor according to the matching relationship between the first identifier and the second identifier, and collect the raw energy operation data of the target thermal system based on the sensor.

[0018] On the other hand, use the genetic algorithm to identify the parameters of the raw energy operation data, and screen the characteristic energy operation data within the preset load range, including:

[0019] Clean the operation raw data of any raw energy operation data, and standardize it based on the national standard unit to obtain the standard energy operation data;

[0020] Encode the standard energy operation data of any parameter type into a chromosome, and set the search space according to the preset load range of the standard energy operation data;

[0021] Initialize the population, and a set of chromosomes of a parameter type represents an individual;

[0022] Take two individuals as the parents, perform gene combination, and the parameters of the offspring generated by crossover are:

[0023] ; where represents the offspring parameters, represents the preset crossover coefficient, represents the parameters of the first parent, represents the parameters of the second parent;

[0024] Generate the fitness function of the population based on the standard operation threshold of the target thermal system, input any individual into the fitness function. If there is no individual in the current population whose fitness meets the adaptation threshold, continue to iterate the gene crossover combination until there is an individual in the population that meets the adaptation threshold. The individual is the optimal solution, and the parameter type and its parameter value corresponding to the individual are the characteristic energy operation data.

[0025] On the other hand, based on the working principle of the supercritical unit, establish the energy efficiency model of the target thermal system in combination with the characteristic energy operation data, including:

[0026] Based on the working principle of the supercritical unit, construct the supercritical parameter values of the target thermal system;

[0027] Take the characteristic energy operation data as the input variable and the energy efficiency of the target thermal system as the output variable;

[0028] According to the parameter type of any input variable, define the fuzzy set and membership function, and formulate fuzzy rules based on the supercritical parameter values. The fuzzy rules and membership function constitute the fuzzy inference layer;

[0029] Input the input variable into the fuzzy inference layer to obtain the fuzzy output. The fuzzy output is transmitted to the neural network layer for processing, and the fuzzy inference result is mapped to the actual energy efficiency value;

[0030] The energy efficiency model of the target thermal system obtained according to the mapping function is:

[0031] ; where represents the actual energy efficiency value, ( ) represents the mapping function based on the neural network layer, represents the input variable, represents the characteristic energy operation data of the first parameter type, represents the characteristic energy operation data of the nth parameter type.

[0032] On the other hand, based on the energy efficiency model, analyze the efficiency of the target thermal system, including:

[0033] Adjust a single input variable, and based on the energy efficiency model, output the corresponding energy efficiency value to generate a single change curve of energy efficiency value - input variable.

[0034] On the other hand, identify and judge whether there is energy loss, including:

[0035] According to the single change curves of energy efficiency value - input variable of all parameter types, analyze the energy loss rate as:

[0036] ; where, represents the energy loss rate, represents the output power, represents the input variables of all parameter types, represents the input power, represents the mean slope of the single change curve of output energy efficiency value - input variable of the ith input variable, represents the mean slope of the single change curve of input energy efficiency value - input variable of the ith input variable;

[0037] If the energy loss rate is greater than a preset threshold, it is determined that there is energy loss in the target thermal system.

[0038] On the other hand, if there is energy loss, a control algorithm is used to optimize the control of each device in the target thermal system, including:

[0039] If there is energy loss in the target thermal system, taking the optimal efficiency threshold of the target thermal system as a constraint condition, and taking all parameter types as the optimization objectives of the cost function, a cost function is constructed;

[0040] Based on the control algorithm, perform first-parameter control on the cost function, output the first cost result, obtain the difference between the first cost result and the constraint condition, input the difference into the control algorithm to output the first control parameter, and iterate until the absolute value of the difference between the first cost result and the constraint condition is less than the minimum threshold, and determine that the control optimization is completed;

[0041] The control parameter is the optimal control parameter, and the control of each device in the target thermal system is optimized and adjusted according to the control parameter.

[0042] Compared with the prior art, the beneficial effects of the present invention are:

[0043] The present invention provides an energy utilization efficiency optimization method based on a supercritical unit, which is used to identify parameters of energy data through a genetic algorithm, establish an efficiency model in combination with the principle of the supercritical unit, analyze energy loss, and use a control algorithm to optimize the system, improve energy utilization efficiency, and reduce energy waste. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the following will briefly introduce the drawings required for the description of the embodiments or the prior art. Obviously, the drawings in the following description are some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings.

[0045] Figure 1 It is a schematic flow chart of an energy utilization efficiency optimization method based on a supercritical unit provided by an embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0046] In order to make the objectives, technical solutions, and advantages of the present invention clearer, the following will clearly and completely describe the technical solutions in the present invention in conjunction with the drawings in the present invention. Obviously, the described embodiments are some, but not all, of the embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0047] Example 1:

[0048] As Figure 1 shown, the energy utilization efficiency optimization method based on a supercritical unit provided by an embodiment of the present invention includes:

[0049] Step 1: Obtain the energy operation parameters of the target thermal system, and collect the original energy operation data based on sensors;

[0050] Step 2: Use a genetic algorithm to perform parameter identification on the original energy operation data, and screen the characteristic energy operation data within a preset load range;

[0051] Step 3: Based on the working principle of the supercritical unit, establish an energy efficiency model of the target thermal system in combination with the characteristic energy operation data;

[0052] Step 4: Based on the energy efficiency model, analyze the efficiency of the target thermal system, and identify and determine whether there is energy loss;

[0053] Step 5: If there is energy loss, use a control algorithm to optimize the control of each device in the target thermal system.

[0054] In this embodiment, the target thermal system refers to the thermal system that needs to perform energy efficiency optimization, energy loss analysis, and control optimization.

[0055] In this embodiment, the energy operation parameters refer to various key indicators related to energy production, transmission, and utilization in the target thermal system, including: temperature, pressure, flow rate, fuel consumption, etc.

[0056] In this embodiment, the sensor is a device used to sense, detect, measure physical and chemical quantities, and convert these signals into data that can be read.

[0057] In this embodiment, the original energy operation data refers to the basic data that reflects the operation status of the target thermal system and is collected in real time through sensors or other measurement devices.

[0058] In this embodiment, the genetic algorithm is an optimization algorithm that simulates natural selection and genetic principles, belonging to the category of evolutionary algorithms, and finds the optimal solution to the problem by simulating the evolution process of organisms in nature.

[0059] In this embodiment, parameter identification refers to the process of estimating the unknown parameter values in the system through existing experimental data or observation data.

[0060] In this embodiment, the preset load range refers to a load range set in advance during the system operation or analysis process, and is used to screen and analyze the energy operation data.

[0061] In this embodiment, characteristic energy operation data refers to the data that can effectively reflect the operation status and performance of the system after screening and extraction during the energy operation process.

[0062] In this embodiment, a supercritical unit is a highly efficient thermal power generation unit widely used in the field of electric power production. Especially in thermal power plants, it refers to a thermal unit adopting supercritical steam parameters. Its main feature is that the working medium reaches the 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 also higher than the critical temperature (374°C).

[0063] In this embodiment, the energy efficiency model is a mathematical model that describes the energy conversion process and efficiency performance of a system under different working conditions.

[0064] In this embodiment, energy loss refers to the situation where energy is not effectively converted into useful work during the energy conversion, transmission, or use process due to various reasons.

[0065] In this embodiment, the control algorithm adjusts the operation status of the system based on the system model, real-time operation data, and optimization objectives.

[0066] The working principle and beneficial effects of the above technical solution are as follows: Through sensor data acquisition and genetic algorithm identification, an efficiency model is established in combination with the principle of supercritical units, energy losses are analyzed and identified, and finally the operation of the thermal system is optimized through the control algorithm to improve energy efficiency, reduce energy waste, and enhance system performance.

[0067] Embodiment 2:

[0068] Based on the above Embodiment 1, obtain the energy operation parameters of the target thermal system, including:

[0069] Define the target thermal system to be studied and optimized;

[0070] And determine the target energy operation parameters to be monitored according to the operation principle and research requirements of the target thermal system.

[0071] In this embodiment, research requirements refer to the specific goals expected to be achieved during the optimization research of the thermal system.

[0072] In this embodiment, target energy operation parameters refer to the key energy-related data that need to be monitored, recorded, and analyzed in the thermal system.

[0073] The working principle and beneficial effects of the above technical solution are as follows: Define the target thermal system, determine the key energy operation parameters according to the operation principle and research requirements, and adopt genetic algorithms and control optimization technologies to achieve precise monitoring and improvement of the system energy efficiency, optimize the energy utilization efficiency, reduce energy losses, and enhance system stability.

[0074] Example 3:

[0075] Based on Example 2 above, raw energy operation data is collected by sensors, including:

[0076] Match the sensor type according to the energy operation parameters;

[0077] Obtain the structural design drawing of the target thermal system, obtain all configurable positions of sensors in the target thermal system, obtain the matching degree between any sensor and the configurable position of the sensor, sort the configurable positions of the sensors according to the matching degree, and screen the optimal positions of the sensors according to the preset configuration quantity;

[0078] Configure a unique first identifier for the sensor, configure a unique second identifier for the optimal position of the sensor, install the sensor according to the matching relationship between the first identifier and the second identifier, and collect the raw energy operation data of the target thermal system based on the sensor.

[0079] In this embodiment, the structural design drawing is a technical drawing that details the relationship between the components and equipment of the thermal system.

[0080] In this embodiment, the configurable position refers to the specific position where the sensor can be installed.

[0081] In this embodiment, the matching degree is an index used to quantify and measure the adaptability or fitness between the sensor and its installation position.

[0082] In this embodiment, the preset configuration quantity refers to a preset given quantity range.

[0083] 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 among all the configurable positions of the sensors after sorting the matching degrees with different sensors.

[0084] In this embodiment, the first identifier refers to a unique identifier assigned to each sensor.

[0085] In this embodiment, the second identifier refers to a unique identifier assigned to each optimal position of the sensor.

[0086] The working principle and beneficial effects of the above technical solution are: by matching the sensor type with the energy operation parameters, combining the structure of the target thermal system and the sensor configuration position, optimizing the sensor installation position and identification, ensuring accurate data collection, providing efficient data support for system operation monitoring, and improving system performance and energy utilization efficiency.

[0087] Example 4:

[0088] Based on the above-mentioned Embodiment 1, a genetic algorithm is used to identify parameters for the original energy operation data, and characteristic energy operation data is screened within a preset load range, including:

[0089] Clean the operation original data of any energy operation original data, and standardize it based on the national standard unit to obtain standard energy operation data;

[0090] Encode the standard energy operation data of any parameter type into a chromosome, and set the search space according to the preset load range of the standard energy operation data;

[0091] Initialize the population, where a set of chromosomes of parameter types represents an individual;

[0092] Take two individuals as parents, perform gene combination, and the parameters of the offspring generated by crossover are:

[0093] ; where represents the offspring parameters, represents the preset crossover coefficient, represents the first parent parameters, represents the second parent parameters;

[0094] Generate a fitness function for the population based on the standard operation threshold of the target thermal system. Input any individual into the fitness function. If there is no individual in the current population whose fitness meets the adaptation threshold, continue to iterate the gene crossover combination until an individual that meets the adaptation threshold appears in the population. The individual is the optimal solution, and the parameter type and its parameter value corresponding to the individual are the characteristic energy operation data.

[0095] In this embodiment, data cleaning refers to the process of processing and correcting the original data to improve data quality.

[0096] In this embodiment, the national standard unit refers to the standard measurement unit uniformly stipulated by the state, which is used to ensure the accuracy and consistency of various data and information in different fields and regions.

[0097] In this embodiment, standardization is a technique in data preprocessing, and its main purpose is to convert data with different ranges or different units into a unified standard format.

[0098] In this embodiment, the standard energy operation data refers to the energy operation data after data cleaning and unit standardization processing.

[0099] In this embodiment, a chromosome is an encoding of a set of parameters, which is used to represent the parameters of the energy operation system.

[0100] In this embodiment, the search space refers to the set of all possible solutions that the algorithm can explore and optimize.

[0101] 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 (i.e., chromosomes).

[0102] In this embodiment, an individual refers to an element in a population, which is a specific solution containing all types of parameters to be optimized and their values.

[0103] In this embodiment, parents refer to certain individuals in the current population that are selected for gene crossover operations to produce new offspring.

[0104] In this embodiment, gene combination is a process for generating new individuals (offspring). By crossing the genes (i.e., their parameters) of parent individuals, new solutions can be produced.

[0105] In this embodiment, offspring parameters refer to the parameters of new individuals generated through gene crossover operations.

[0106] In this embodiment, the standard operation threshold refers to a preset indicator used to determine whether an energy system meets the standard operation requirements.

[0107] In this embodiment, the fitness function is an indicator used to measure the performance results of each individual in the current problem.

[0108] The working principle and beneficial effects of the above technical solution are as follows: By cleaning and standardizing energy operation data, encoding it into chromosomes, optimizing parameters using a genetic algorithm, iterating based on the fitness function, finally finding the optimal solution that meets the threshold, providing accurate characteristic energy operation data, and improving the system optimization efficiency and accuracy.

[0109] Example 5:

[0110] Based on the working principle of a supercritical unit and combined with characteristic energy operation data on the basis of the above Example 1, an energy efficiency model of the target thermal system is established, including:

[0111] Based on the working principle of a supercritical unit, construct the supercritical parameter values of the target thermal system;

[0112] Use the characteristic energy operation data as input variables and the energy efficiency of the target thermal system as output variables;

[0113] According to the parameter type of any input variable, define fuzzy sets and membership functions, and formulate fuzzy rules based on the supercritical parameter values. The fuzzy rules and membership functions constitute the fuzzy inference layer;

[0114] The input variable is input into the fuzzy inference layer to obtain a fuzzy output, and the fuzzy output is transmitted to the neural network layer for processing, mapping the fuzzy inference result to the actual energy efficiency value;

[0115] The energy efficiency model of the target thermal system is obtained according to the mapping function as follows:

[0116] ; where represents the actual energy efficiency value, ( ) represents the mapping function based on the neural network layer, represents the input variable, represents the characteristic energy operation data of the first parameter type, represents the characteristic energy operation data of the nth parameter type.

[0117] In this embodiment, the supercritical parameter value refers to the value of the key thermodynamic parameters involved when the system reaches the supercritical state under the working principle of the supercritical unit.

[0118] In this embodiment, the fuzzy set is a set whose membership degrees of members are in a continuous range.

[0119] In this embodiment, the membership function is used to describe the membership degree of each input variable in the fuzzy set.

[0120] In this embodiment, the fuzzy inference layer is a core part that infers the input data through fuzzy logic rules and membership functions, and then derives a fuzzy output.

[0121] In this embodiment, the fuzzy output is the result obtained through the fuzzy inference layer, representing the fuzzy value of the energy efficiency of the target thermal system.

[0122] In this embodiment, the neural network layer is a key component in a deep learning model, used to further process and map the input data.

[0123] In this embodiment, the energy efficiency value refers to the effective degree of energy conversion into useful work.

[0124] In this embodiment, the mapping function is the core part of the neural network layer, which converts the fuzzy output obtained by the fuzzy inference layer into the actual energy efficiency value. The neural network layer generates the corresponding mapping function by learning the complex relationship between the input variable and the output variable.

[0125] The working principle and beneficial effects of the above technical solution are as follows: By combining the supercritical unit principle, fuzzy inference, and neural network, the characteristic energy operation data is converted into an energy efficiency model, and the actual energy efficiency is mapped through fuzzy rules and the neural network layer, improving the accuracy and reliability of the energy efficiency prediction of the thermal system.

[0126] Example 6:

[0127] Based on the above Example 1, analyze the efficiency of the target thermal system based on the energy efficiency model, including:

[0128] Adjust a single input variable, and based on the energy efficiency model, output the corresponding energy efficiency value, and generate a single-variable change curve of energy efficiency value - input variable.

[0129] In this example, the single-variable change curve of energy efficiency value - input variable refers to the curve that adjusts the value of a single input variable while keeping other input variables unchanged and observes how the corresponding energy efficiency value (output variable) changes.

[0130] 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 realizing system optimization and precise control.

[0131] Example 7:

[0132] Based on the above Example 6, identify and determine whether there is energy loss, including:

[0133] According to the single-variable change curves of energy efficiency value - input variable for all parameter types, analyze the energy loss rate as:

[0134] ; where represents the energy loss rate, represents the output power, represents all parameter types of input variables, represents the input power, represents the mean slope of the single-variable change curve of output energy efficiency value - input variable for the i-th input variable, represents the mean slope of the single-variable change curve of input energy efficiency value - input variable for the i-th input variable;

[0135] If the energy loss rate is greater than the preset threshold, it is determined that there is energy loss in the target thermal system.

[0136] In this example, the energy loss rate refers to the degree of energy loss in an energy system due to various reasons (such as efficiency reduction, heat loss, friction, etc.).

[0137] In this example, the preset threshold is a value set according to system design, operation standards, or industry specifications.

[0138] The working principle and beneficial effects of the above technical solution are as follows: By analyzing the single change curves of all input variables, calculating the energy loss rate, and determining whether there is energy loss according to the set threshold, the energy efficiency problems of the thermal system can be identified, promoting system optimization and energy-saving management.

[0139] Example 8:

[0140] Based on the above Example 7, if there is energy loss, use the control algorithm to control and optimize each device of the target thermal system, including:

[0141] If there is energy loss in the target thermal system, taking the optimal efficiency threshold of the target thermal system as a constraint condition, taking all parameter types as the optimization objectives of the cost function, and constructing the cost function;

[0142] Based on the control algorithm, perform the first parameter control on the cost function, output the first cost result, obtain the difference between the first cost result and the constraint condition, input the difference into the control algorithm to output the first control parameter, and iterate until the absolute value of the difference between the first cost result and the constraint condition is less than the minimum threshold, and determine that the control optimization is completed;

[0143] The control parameter is the optimal control parameter, and each device of the target thermal system is controlled and optimized according to the control parameter.

[0144] In this embodiment, the optimal efficiency threshold refers to the value at which, in the thermal system, when the energy efficiency of the system reaches or exceeds this value, the performance of the system operation is considered optimal.

[0145] In this embodiment, the constraint condition refers to the limitation related to the optimal efficiency threshold of the target thermal system.

[0146] In this embodiment, the cost function is a mathematical expression for measuring the system performance, which is related to control parameters (such as the operating conditions of devices, adjustment parameters, etc.), as well as the energy loss and efficiency of the system.

[0147] In this embodiment, the optimization objective is to optimize each control parameter of the target thermal system through the control algorithm to minimize the cost function while satisfying the optimal efficiency threshold constraint of the system.

[0148] In this embodiment, the first parameter control refers to the control adjustment according to the control algorithm.

[0149] In this embodiment, the first cost result refers to the output result of the cost function obtained after performing the first parameter control on the target thermal system based on the control algorithm.

[0150] In this embodiment, the first control parameter refers to the parameter initially adjusted in the control algorithm for optimizing the performance of the target thermal system.

[0151] In this embodiment, the optimal control parameter refers to the parameter obtained through iterative optimization of the control algorithm, which can enable the target thermal system to reach or approach the optimal efficiency.

[0152] The working principle and beneficial effects of the above technical solution are as follows: By constructing a cost function and optimizing the operation of the target thermal system based on the control algorithm, iteratively adjusting the control parameters until the optimal efficiency threshold is met, ultimately realizing the optimal control of each device in the thermal system, improving the system energy efficiency and reducing energy loss.

[0153] 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 them; although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions recorded in the foregoing embodiments, or perform equivalent replacements for some of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the various embodiments of the present invention.

Claims

1. An energy utilization efficiency optimization method based on a supercritical unit, characterized in that Including: Step 1: Obtain the energy operation parameters of the target thermal system, and collect the original energy operation data based on sensors; Step 2: Use the genetic algorithm to identify the parameters of the original energy operation data, and screen the characteristic energy operation data within the preset load range; Step 3: Based on the working principle of the supercritical unit, establish an energy efficiency model of the target thermal system in combination with the characteristic energy operation data; Step 4: Based on the energy efficiency model, analyze the efficiency of the target thermal system, and identify and judge whether there is energy loss; Step 5: If there is energy loss, use the control algorithm to optimize the control of each device of the target thermal system; Among them, based on the energy efficiency model, analyzing the efficiency of the target thermal system includes: Adjust a single input variable, and based on the energy efficiency model, output the corresponding energy efficiency value, and generate a single change curve of the energy efficiency value - input variable; Among them, identifying and judging whether there is energy loss includes: According to the single change curves of the energy efficiency value - input variable of all parameter types, analyze the energy loss rate as: ; where represents the energy loss rate, represents the output power, represents the input variables of all parameter types, represents the input power, represents the mean slope of the single-variable change curve of the output energy efficiency value of the i-th input variable, represents the mean slope of the single-variable change curve of the input energy efficiency value of the i-th input variable; If the energy loss rate is greater than the preset threshold, it is determined that there is energy loss in the target thermal system.

2. The energy utilization efficiency optimization method based on a supercritical unit according to claim 1, wherein Obtaining the energy operation parameters of the target thermal system includes: Clarify the target thermal system to be studied and optimized; And according to the operation principle and research requirements of the target thermal system, determine the target energy operation parameters to be monitored.

3. The energy utilization efficiency optimization method based on a supercritical unit according to claim 2, characterized in that Collecting the original energy operation data based on sensors includes: Match the sensor type according to the energy operation parameters; Obtain the structural design drawing of the target thermal system, obtain all the configurable positions of the sensors of the target thermal system, obtain the matching degree between any sensor and the configurable position of the sensor, sort the configurable positions of the sensors according to the matching degree, and screen the optimal positions of the sensors according to the preset configuration quantity; Configure a unique first identifier for the sensor, configure a unique second identifier for the optimal position of the sensor, configure and install the sensor according to the matching relationship between the first identifier and the second identifier, and collect the original energy operation data of the target thermal system based on the sensor.

4. The energy utilization efficiency optimization method based on a supercritical unit according to claim 1, characterized in that Using the genetic algorithm to identify the parameters of the original energy operation data and screening the characteristic energy operation data within the preset load range includes: Clean the operation original data of any original energy operation data, and standardize it based on the national standard unit to obtain the standard energy operation data; Encode the standard energy operation data of any parameter type into a chromosome, and set the search space according to the preset load range of the standard energy operation data; Initialize the population, and a set of chromosomes of parameter types represents an individual; Take two individuals as parents, perform gene combination, and the generated offspring parameters after crossover are: ; where represents the offspring parameter, represents the preset crossover coefficient, represents the first parent parameter, represents the second parent parameter; Generate the fitness function of the population based on the standard operation threshold of the target thermal system, input any individual into the fitness function. If there is no individual in the current population whose fitness meets the adaptation threshold, continue to iterate the gene crossover combination until there is an individual in the population whose fitness meets the adaptation threshold. The individual is the optimal solution, and the parameter type and its parameter value corresponding to the individual are the characteristic energy operation data.

5. The energy utilization efficiency optimization method based on a supercritical unit according to claim 1, wherein Based on the working principle of the supercritical unit, establishing an energy efficiency model of the target thermal system in combination with the characteristic energy operation data includes: Based on the working principle of the supercritical unit, construct the supercritical parameter values of the target thermal system; Use the characteristic energy operation data as the input variable and the energy efficiency of the target thermal system as the output variable; According to the parameter type of any input variable, define the fuzzy set and membership function, and formulate fuzzy rules based on the supercritical parameter values. The fuzzy rules and membership function constitute the fuzzy inference layer; Input the input variable into the fuzzy inference layer to obtain a fuzzy output. The fuzzy output is transmitted to the neural network layer for processing, and the fuzzy inference result is mapped to the actual energy efficiency value; The energy efficiency model of the target thermal system obtained according to the mapping function is: ; where represents the actual energy efficiency value, ( ) represents the mapping function based on the neural network layer, represents the input variable, represents the characteristic energy operation data of the first parameter type, represents the characteristic energy operation data of the nth parameter type.

6. The energy utilization efficiency optimization method based on a supercritical unit according to claim 1, wherein If there is an energy loss utilization control algorithm to control and optimize each device of the target thermal system, including: If there is energy loss in the target thermal system, construct a cost function with the optimal efficiency threshold of the target thermal system as the constraint condition and all parameter types as the optimization objective of the cost function; Perform the first parameter control on the cost function based on the control algorithm, output the first cost result, obtain the difference between the first cost result and the constraint condition, input the difference into the control algorithm to output the first control parameter, and iterate until the absolute value of the difference between the first cost result and the constraint condition is less than the minimum threshold, and determine that the control optimization is completed; The control parameter is the optimal control parameter, and each device of the target thermal system is controlled and optimized according to the control parameter.

Images