METHOD AND SYSTEM FOR OPTIMIZING AND CONTROLLING A THERMAL SYSTEM

Abstract

The present invention discloses a method and a system for optimizing and controlling a thermal system. These include: acquiring historical operating data and historical energy efficiency data of a thermal system, analyzing this data, and determining historical characteristic parameters that influence the energy efficiency of the thermal system; creating an energy efficiency prediction model of a thermal system based on the historical characteristic parameters and a predefined neural network model, and performing predictions to obtain energy efficiency prediction data; acquiring real-time energy efficiency data of the thermal system and comparing and analyzing it with the energy efficiency prediction data; and evaluating and calculating the energy efficiency difference of the thermal system based on the results of the comparative analysis to obtain an energy efficiency difference evaluation value.Determining an optimization coefficient based on the energy efficiency difference rating value and optimizing and controlling the real-time characteristic parameters of the thermal system based on this optimization coefficient. The present invention improves the energy efficiency and operational efficiency of the thermal system through historical data analysis, the creation of predictive models, and real-time optimization control, achieves intelligent operation of the thermal system, and also improves the adaptability and intelligence of the thermal system.

Description

Technical field

[0001] The present invention relates to the technical field of thermal systems and in particular to a method and system for optimizing and controlling a thermal system. Background technology

[0002] In today's energy-saving and environmentally conscious world, the efficient operation and energy use of thermal systems have become crucial aspects in both industrial production and everyday life. Conventional, pre-optimized control methods for thermal systems lack adaptability, real-time performance, accuracy, and energy efficiency optimization. Therefore, they cannot meet today's energy efficiency and environmental protection requirements. The introduction of optimized control methods can address these shortcomings and improve the energy efficiency and operational efficiency of the system.

[0003] Conventional control methods for thermal systems typically employ static control strategies that often struggle to adapt to changing system operating conditions. This can result in the system not fully utilizing current operating conditions, leading to energy waste and reduced system efficiency. Furthermore, conventional methods often lack real-time optimization capabilities, preventing them from monitoring and adjusting the system's operating state in real time. Consequently, the system cannot respond promptly to changing environmental conditions, resulting in reduced energy efficiency and resource waste. Additionally, conventional control methods often rely on engineers' experience and rules, without requiring thorough analysis and utilization of extensive historical data.This can lead to the system's control strategies being inaccurate and inefficient, and unable to adapt to the control of multiple interacting parameters and constraints. Content of the invention

[0004] To solve the aforementioned technical problems, the present invention provides a method and system for optimizing and controlling a thermal system, comprising the following: Collecting historical operating data and historical energy efficiency data of a thermal system; analyzing the historical operating data and historical energy efficiency data to determine historical characteristic parameters that influence the energy efficiency of the thermal system; Creating an energy efficiency prediction model of the thermal system based on historical characteristic parameters and a preset neural network model; capturing the real-time characteristic parameters of the thermal system and inputting them into the energy efficiency prediction model to obtain energy efficiency prediction data; Acquisition of real-time energy efficiency data of the thermal system and performance of a comparative analysis between the real-time energy efficiency data and the energy efficiency forecast data; Evaluate and calculate the energy efficiency difference of the thermal system based on the results of the comparative analysis in order to obtain an energy efficiency difference rating value for the thermal system; Determining an optimization coefficient based on the energy efficiency difference rating value and optimizing and controlling the real-time characteristic parameters of the thermal system based on the optimization coefficient.

[0005] The present invention also provides a system for optimizing and controlling a thermal system, comprising the following: A data acquisition module for recording historical operating data and historical energy efficiency data of the thermal system, analyzing the historical operating data and historical energy efficiency data to determine historical characteristic parameters that influence the energy efficiency of the thermal system; A forecasting module for creating an energy efficiency forecasting model of the thermal system based on historical characteristic parameters and a preset neural network model, capturing the real-time characteristic parameters of the thermal system and their input into the energy efficiency forecasting model to obtain energy efficiency forecast data; A comparison module for capturing real-time energy efficiency data of the thermal system and for performing a comparative analysis between the real-time energy efficiency data and the energy efficiency forecast data; A calculation module for evaluating and calculating the energy efficiency difference of the thermal system based on the results of the comparative analysis, in order to obtain an energy efficiency difference evaluation value of the thermal system; An optimization module for determining an optimization coefficient based on the energy efficiency difference rating value and optimization and control of the real-time characteristic parameters of the thermal system based on the optimization coefficient. Compared to existing technologies, the method and system for optimizing and controlling a thermal system of the embodiments of the present invention offer the following advantages: By analyzing historical operating data and historical energy efficiency data, the present invention determines historical characteristic parameters that influence the energy efficiency of the thermal system and creates an energy efficiency prediction model. This helps system managers to better understand the operating patterns and influencing factors of the thermal system and provides a basis for future system optimizations. Based on an energy efficiency prediction model that relies on historical parameters and a preset neural network model, the present invention assists system managers in determining real-time energy efficiency prediction data for the thermal system and provides a reference for real-time decisions; By capturing real-time characteristic parameters and energy efficiency data of the thermal system and comparing and analyzing them with energy efficiency forecast data, the present invention can help system managers to detect fluctuations and anomalies in energy efficiency at an early stage and to make timely adjustments; Based on the results of the comparative analysis, the energy efficiency difference of the thermal system is evaluated and calculated to determine an optimization coefficient. By optimizing and controlling the real-time characteristic parameters of the thermal system based on the optimization coefficient, the present invention supports system managers in the real-time optimization and control of the thermal system and improves the energy efficiency and operational efficiency of the system. In summary, this invention enables intelligent operation of the thermal system through historical data analysis, predictive modeling, and real-time optimization and control, improving the system's adaptability and intelligence. It simultaneously optimizes energy efficiency, improves resource utilization, and reduces operating costs. This contributes to improved operational efficiency and the sustainable development of thermal systems. Illustration of the attached drawings Fig. Figure 1 shows a schematic diagram of the flowchart of the method for optimizing and controlling a thermal system according to an embodiment of the present invention. Fig. Figure 2 shows a schematic diagram of the components of the system for optimizing and controlling a thermal system according to an embodiment of the present invention. Specific embodiments

[0006] Further details of the specific embodiments of the present application are described below in conjunction with the accompanying drawings and examples. The following embodiments are intended to illustrate the present invention, but not to limit its scope.

[0007] In the description of this application, it should be noted that the terms "middle," "top," "bottom," "front," "back," "left," "right," "vertical," "horizontal," "above," "below," "inside," and "outside," etc., which indicate positions or locations, are based on the positions or locations shown in the accompanying drawings. This is solely for the convenience of simplifying the present application. They do not imply that the platform or component in question must have a particular orientation, be constructed, or be operated in a particular orientation, and should therefore not be construed as limiting the present application.

[0008] The terms “first” and “second” are used solely for descriptive purposes and are not to be interpreted as having a relative meaning or as implicitly indicating the number of the technical features mentioned. Therefore, features designated as “first” or “second” may explicitly or implicitly include one or more of these features. In the description of this application, “plural” means two or more unless otherwise specified.

[0009] In the description of this application, it should be noted that the terms "assembled," "connected," and "attached" are to be understood in their broadest sense, unless expressly stated otherwise or limited. They may, for example, refer to fixed connections, detachable connections, or integral connections; they may refer to mechanical or electrical connections; they may refer to direct connections, indirect connections, or indirect connections via an intermediate medium; and they may refer to connections within two components. Those skilled in the art will understand the specific meaning of the above terms in this application according to the particular circumstances.

[0010] As in Fig. As shown in Figure 1, an embodiment of the present application provides a method for optimizing and controlling a thermal system, comprising: S100: Acquiring historical operating data and historical energy efficiency data of a thermal system, analyzing the historical operating data and historical energy efficiency data to determine historical characteristic parameters that influence the energy efficiency of the thermal system; S200: Creating an energy efficiency prediction model of the thermal system based on the historical characteristic parameters and a preset neural network model, acquiring the real-time characteristic parameters of the thermal system and inputting them into the energy efficiency prediction model to obtain energy efficiency prediction data;S300: Acquisition of real-time energy efficiency data of the thermal system and performance of a comparative analysis between the real-time energy efficiency data and the energy efficiency forecast data; S400: Evaluation and calculation of the energy efficiency difference of the thermal system based on the results of the comparative analysis to obtain an energy efficiency difference rating of the thermal system; S500: Determination of an optimization coefficient based on the energy efficiency difference rating and optimization and control of the real-time characteristic parameters of the thermal system based on the optimization coefficient.

[0011] By analyzing historical operating data and historical energy efficiency data, the present invention further determines historical characteristic parameters that influence the energy efficiency of the thermal system and creates an energy efficiency prediction model. This helps system managers to better understand the operating patterns and influencing factors of the thermal system and provides a basis for future system optimizations. Based on an energy efficiency prediction model derived from historical characteristic parameters and a predefined neural network model, the present invention supports system managers in obtaining real-time energy efficiency prediction data for the thermal system and provides a reference for real-time decision-making.By acquiring real-time characteristic parameters and energy efficiency data of the thermal system and comparing and analyzing them with energy efficiency forecast data, the present invention can help system managers to detect fluctuations and anomalies in energy efficiency at an early stage and to make timely adjustments. Based on the results of the comparative analysis, the energy efficiency difference of the thermal system is evaluated and calculated to determine an optimization coefficient. By optimizing and controlling the real-time characteristic parameters of the thermal system based on the optimization coefficient, the present invention supports system managers in the real-time optimization and control of the thermal system and improves the energy efficiency and operational efficiency of the system.In summary, this invention enables intelligent operation of the thermal system through historical data analysis, predictive modeling, and real-time optimization and control, improving the system's adaptability and intelligence. It simultaneously optimizes energy efficiency, improves resource utilization, and reduces operating costs. This contributes to improved operational efficiency and the sustainable development of thermal systems.

[0012] In one embodiment of the present application, a method for optimizing and controlling a thermal system is provided, comprising: acquiring historical operating data and historical energy efficiency data of the thermal system; analyzing the historical operating data and historical energy efficiency data to determine historical characteristic parameters that influence the energy efficiency of the thermal system; acquiring historical operating data and historical energy efficiency data of the thermal system and dividing the historical operating data into several groups of historical operating parameter data sets based on the parameter type; determining the i-th historical operating parameter data sets from the several historical operating parameter data sets and selecting historical energy efficiency data where the other historical operating parameters are the same;Analyzing the change in historical energy efficiency data according to the i-th historical operating parameter data sets and determining the parameter, according to the i-th historical operating parameter data sets, whose change exceeds a preset change threshold, as a historical characteristic parameter that influences the energy efficiency of the thermal system.

[0013] Specifically, historical operating data and historical energy efficiency data of the thermal system are collected and structured to ensure data accuracy and completeness; the historical operating data are divided into several groups of historical operating parameter data sets based on parameter types, such as temperature, pressure, flow rate, and other parameter data sets; the group of historical operating parameter data sets to be analyzed is selected and referred to as the i-th historical operating parameter data sets.The historical energy efficiency data corresponding to the i-th historical operating parameter datasets is filtered out from the historical energy efficiency data when other historical operating parameters are equal. The historical energy efficiency data corresponding to the i-th historical operating parameter datasets are analyzed, their change is calculated, and compared to the preset change threshold. If the change is greater than the preset change threshold, the parameter corresponding to the i-th historical operating parameter datasets is determined to be the historical characteristic parameter influencing the energy efficiency of the thermal system. In this step, historical data is used for analysis to identify characteristic parameters closely related to changes in energy efficiency, thus providing guidance for subsequent energy efficiency optimization.

[0014] In one embodiment of the present application, a method for optimizing and controlling a thermal system is provided, creating an energy efficiency prediction model of the thermal system based on historical characteristic parameters and a preset neural network model, acquiring the real-time characteristic parameters of the thermal system and inputting them into the energy efficiency prediction model to obtain energy efficiency prediction data, comprising: creating a dataset based on historical characteristic parameters and corresponding historical energy efficiency data, inputting the dataset into a preset neural network model to create an energy efficiency prediction originator model; splitting the dataset into training sets and test sets according to a specific ratio and inputting the training sets and test sets into the energy efficiency prediction originator model;Training and testing the energy efficiency prediction original model until it meets the preset convergence conditions, thereby creating the energy efficiency prediction model; acquiring the real-time characteristic parameters of the thermal system and inputting these real-time characteristic parameters into the energy efficiency prediction model, and executing predictions by the energy efficiency prediction model to obtain energy efficiency prediction data of the thermal system.

[0015] Specifically, a dataset is created based on historical characteristic parameters and corresponding historical energy efficiency data, with the historical characteristic parameters serving as input features and the historical energy efficiency data as output labels; the created dataset is fed into a predefined neural network model to create an energy efficiency prediction original model; the dataset is divided into training sets and test sets according to a specific ratio to ensure the independence and effectiveness of model training and testing; the training sets and test sets are fed into the energy efficiency prediction original model, which is trained and tested until the model meets the predefined convergence criteria, resulting in an energy efficiency prediction model;Real-time parameters of the thermal system are determined and fed into the energy efficiency prediction model. The model then performs predictions to obtain energy efficiency prediction data for the thermal system. In this step, the neural network model is used to learn and model historical data and achieve a real-time prediction of the thermal system's energy efficiency. Continuous monitoring and prediction of the thermal system's energy efficiency can be achieved through the continuous acquisition of real-time parameters and their input into the model.

[0016] In one embodiment of the present application, a method for optimizing and controlling thermal systems is provided, acquiring real-time energy efficiency data of the thermal system and performing a comparative analysis between the real-time energy efficiency data and the energy efficiency forecast data, comprising: acquiring real-time energy efficiency data of the thermal system and analyzing the similarity between the real-time energy efficiency data and the energy efficiency forecast data; subtracting the real-time energy efficiency data from the energy efficiency forecast data to determine energy efficiency difference data and creating a time-based curve diagram based on the energy efficiency difference data to determine an energy efficiency difference curve;Determine curve segments with non-zero energy efficiency differences from an energy efficiency difference curve and divide each curve segment into several first curve segments greater than zero and continuous, and second curve segments less than zero and continuous; classify all first curve segments as first-category curve segments and all second curve segments as second-category curve segments; calculate the average values ​​of the first-category curve segments and the second-category curve segments to obtain a first average value and a second average value, and determine the number of first curve segments in the first-category curve segments and the number of second curve segments in the second-category curve segments to obtain a first count and a second count.

[0017] Specifically, real-time energy efficiency data of the thermal system are obtained to ensure its accuracy and completeness; real-time energy efficiency data and energy efficiency forecast data are compared and analyzed for similarities to assess the accuracy and reliability of the forecasting model; the real-time energy efficiency data is subtracted from the energy efficiency forecast data to obtain energy efficiency difference data; based on the energy efficiency difference data, a time-based curve diagram is created to obtain an energy efficiency difference curve; curve segments with non-zero energy efficiency differences are identified from an energy efficiency difference curve, and the curve segments are divided into first curve segments greater than zero and second curve segments less than zero.Classify all first curve segments as category 1 curve segments and all second curve segments as category 2 curve segments; calculate the average values ​​of the category 1 and category 2 curve segments to obtain a first average and a second average, and determine the number of first curve segments in the category 1 curve segments and the number of second curve segments in the category 2 curve segments to obtain a first count and a second count. This step enables an in-depth analysis of the difference between real-time energy efficiency data and forecast data, a better understanding of energy efficiency fluctuations during system operation, and provides a basis for further optimizations and adjustments.

[0018] In one embodiment of the present application, a method for optimizing and controlling thermal systems is provided, analyzing the similarity between real-time energy efficiency data and energy efficiency forecast data, comprising: recording the real-time energy efficiency data and the energy efficiency forecast data each as curve diagrams and performing a Fourier transform on both curve diagrams; creating a spectrum graph of the Fourier-transformed curve diagram and extracting primary frequency features, spectrum shape features, and spectrum energy distribution features from the spectrum graphs; calculating the cosine similarity of the primary frequency features, the spectrum shape features, and the spectrum energy distribution features between the two spectrum graphs and determining preset weights for the primary frequency features, the spectrum shape features, and the spectrum energy distribution features;Calculating the weighted sum of the cosine similarities of the primary frequency features, the spectrum shape features, and the spectrum energy distribution features between the two spectrum graphs with the corresponding preset weights to calculate the similarity between the real-time energy efficiency data and the energy efficiency forecast data.

[0019] Specifically, the real-time energy efficiency data and the energy efficiency forecast data are each represented as curve diagrams and subjected to Fourier transformation of both curve diagrams to convert them into the frequency domain; from the results of the Fourier transformation, spectrum graphs are obtained, which represent the energy distribution of the signal in the frequency domain; primary frequency features, spectrum shape features and spectrum energy distribution features are extracted from the spectrum graphs.These features help to understand the signal characteristics in the frequency domain; the cosine similarity of the primary frequency features, spectrum shape features, and spectrum energy distribution features between the two spectrum graphs is calculated to evaluate their similarity in the frequency domain; preset weights for primary frequency features, spectrum shape features, and spectrum energy distribution features are determined to include them in the similarity calculation; the weighted sum of the cosine similarities of the primary frequency features, spectrum shape features, and spectrum energy distribution features between the two spectrum graphs is calculated with the corresponding preset weights to calculate the similarity between the real-time energy efficiency data and the energy efficiency forecast data.

[0020] This step allows for a comparison of real-time energy efficiency data and energy efficiency forecast data in the frequency domain to determine their similarity. This contributes to a more comprehensive understanding of the relationship between the two signals and provides support for further analysis and decision-making.

[0021] In one embodiment of the present application, a method for optimizing and controlling thermal systems is provided, which involves evaluating and calculating the energy efficiency difference of the thermal system based on the results of the comparative analysis in order to obtain an energy efficiency difference rating of the thermal system; determining the similarity between the real-time energy efficiency data and the energy efficiency forecast data, as well as a first average value and a first number of curve segments of the first category and a second average value and a second number of curve segments of the second category; evaluating and calculating, respectively, the first average value of the curve segment of the first category and the second average value of the curve segment of the second category to determine a first difference rating and a second difference rating.Calculating the assessment value of the energy efficiency difference of the thermal system based on the similarity between the real-time energy efficiency data and the energy efficiency forecast data, the first difference assessment value and the first number of curve segments of the first category, and the second difference assessment value and the second number of curve segments of the second category; The formula for calculating the assessment value of the energy efficiency difference of the thermal system is:; L=S×(g1×Xm+g2×Yn), where L is the energy efficiency difference rating of the thermal system, S is the similarity between the real-time energy efficiency data and the energy efficiency forecast data, g1 is the preset weighting of the curve segment of the first category, X is the first difference rating of the curve segment of the first category, m is the first number of curve segments of the first category, g2 is the preset weighting of the curve segment of the second category, Y is the second difference rating of the curve segment of the second category, and n is the second number of curve segments of the second category.

[0022] Specifically, the first average value of the curve segment of the first category and the second average value of the curve segment of the second category are evaluated to obtain the first difference assessment value and the second difference assessment value;

[0023] The similarity between the real-time energy efficiency data and the energy efficiency forecast data is used as S; the preset weight of the curve segment of the first category is used as g1, the first difference score of the curve segment of the first category is used as X, and the first number of curve segments of the first category is used as m. The preset weight of the curve segment of the second category is used as g2, the second difference score of the curve segment of the second category is used as Y, and the second number of curve segments of the second category is used as n; the energy efficiency difference score L of the thermal system is calculated.In this step, the similarities between the real-time energy efficiency data and the energy efficiency forecast data, as well as the difference rating and the number of curve segments in the first category and the second category, are comprehensively considered to determine the energy efficiency difference rating of the thermal system. This rating can help you better understand energy efficiency fluctuations during system operation and provides a basis for further optimizations and adjustments.

[0024] In one embodiment of the present application, a method for optimizing and controlling thermal systems is provided, determining an optimization coefficient based on the energy efficiency difference rating value and optimizing and controlling the real-time characteristic parameters of the thermal system based on the optimization coefficient, comprising: specifying a corresponding relationship of the optimization coefficient-energy efficiency difference rating value interval, and assigning the corresponding relationship of the optimization coefficient-energy efficiency difference rating value interval to a corresponding optimization coefficient for each energy efficiency difference rating value interval;Determining the energy efficiency difference rating value and selecting the optimization coefficient corresponding to the energy efficiency difference rating value interval, based on an assignment relationship of the energy efficiency difference rating value interval to which the energy efficiency difference rating value belongs, within the corresponding relationship of the optimization coefficient-energy efficiency difference rating value interval; adjusting the real-time characteristic parameters based on the optimization coefficient and controlling the operation of the thermal system based on the adjusted real-time characteristic parameters.

[0025] Specifically, the energy efficiency difference rating is divided into different intervals, for each of which corresponding optimization coefficients are preset. These optimization coefficients can be proportional coefficients used to adjust the system parameters, allowing different optimization measures to be taken based on the different energy efficiency difference ratings. During system operation, the real-time energy efficiency difference rating is determined and compared with the corresponding relationship between the predefined optimization coefficient and energy efficiency difference rating interval to determine the associated interval.Select the optimization coefficient that corresponds to the energy efficiency difference rating interval based on a mapping relationship of the interval to which the energy efficiency difference rating belongs within the corresponding relationship of the optimization coefficient-energy efficiency difference rating interval. Based on the selected optimization coefficient, real-time characteristic parameters are adjusted. These real-time characteristic parameters can be control parameters in the system, such as temperature and flow rate, etc. The adjusted real-time characteristic parameters can be used to control the operation of the thermal system to achieve energy efficiency optimization. This step enables the selection of appropriate optimization coefficients based on the real-time energy efficiency difference rating and the corresponding adjustment of the real-time characteristic parameters to control the operation of the thermal system.This real-time adaptation and optimization method can help the system to better adapt to the operating requirements of different energy efficiency conditions and improve the system's energy efficiency performance.

[0026] As in Fig.As shown in Figure 2, in one embodiment of the present application, a system for optimizing and controlling a thermal system is provided, comprising: a data acquisition module for acquiring historical operating data and historical energy efficiency data of the thermal system, analyzing the historical operating data and historical energy efficiency data to determine historical characteristic parameters that influence the energy efficiency of the thermal system; a forecasting module for creating an energy efficiency forecasting model of the thermal system based on the historical characteristic parameters and a preset neural network model, acquiring the real-time characteristic parameters of the thermal system and inputting them into the energy efficiency forecasting model to obtain energy efficiency forecast data;A comparison module for acquiring real-time energy efficiency data of the thermal system and for performing a comparative analysis between the real-time energy efficiency data and the energy efficiency forecast data; a calculation module for evaluating and calculating the energy efficiency difference of the thermal system based on the results of the comparative analysis in order to obtain an energy efficiency difference rating value for the thermal system; an optimization module for determining an optimization coefficient based on the energy efficiency difference rating value and for optimizing and controlling the real-time characteristic parameters of the thermal system based on the optimization coefficient.

[0027] In summary, embodiments of the present invention provide a method and a system for optimizing and controlling a thermal system. These include: acquiring historical operating data and historical energy efficiency data of a thermal system, analyzing this data, and determining historical characteristic parameters that influence the energy efficiency of the thermal system; creating an energy efficiency prediction model of a thermal system based on the historical characteristic parameters and a predefined neural network model, and performing predictions to obtain energy efficiency prediction data; acquiring real-time energy efficiency data of the thermal system and comparing and analyzing it with the energy efficiency prediction data; and evaluating and calculating the energy efficiency difference of the thermal system based on the results of the comparative analysis to obtain an energy efficiency difference evaluation value.Determining an optimization coefficient based on the energy efficiency difference rating value and optimizing and controlling the real-time characteristic parameters of the thermal system based on this optimization coefficient. The present invention improves the energy efficiency and operational efficiency of the thermal system through historical data analysis, the creation of predictive models, and real-time optimization control, achieves intelligent operation of the thermal system, and also improves the adaptability and intelligence of the thermal system.

[0028] Finally, it should be noted that those skilled in the art can obviously make various modifications and variations to the present invention without departing from the spirit and scope of the present invention. If these modifications and variations of the present invention fall within the scope of protection of the claims of the present invention and its equivalent technology, the present invention shall also encompass these modifications and variations.

[0029] The above description represents only one embodiment of the present invention and is not intended to limit its scope. All structural modifications made according to the present invention fall within its scope of protection and are subject to limitations, provided they do not deviate from the essence of the present invention. For technical personnel in the relevant technical field, it is clear that, for the sake of expediency and brevity, the specific operating procedure and related instructions for the platform described above can be referred to the corresponding procedure in the platform embodiment mentioned above and are not repeated here.

[0030] The term “include” or any other similar term is intended to cover non-exclusive inclusion, such that a process, platform, article or device / platform that includes a list of elements includes not only those elements but also other elements not expressly listed or inherent in such process, platform, article or device / platform.

[0031] The technical solutions of the present invention have so far been described with reference to the further embodiments illustrated in the accompanying drawings. However, it is clear to those skilled in the art that the scope of protection of the present invention is not limited to these specific embodiments. Without departing from the principles of the present invention, technical personnel in this field may make equivalent modifications or substitutions to closely related technical features, and the technical solutions resulting from these modifications or substitutions fall within the scope of protection of the present invention.

[0032] The foregoing description merely represents a preferred embodiment of the present invention and is not intended to limit the scope of protection of the present invention.

Claims

[1] Methods for optimizing and controlling a thermal system, characterized by , that the following is comprehensive: Collecting historical operating data and historical energy efficiency data of a thermal system; analyzing the historical operating data and historical energy efficiency data to determine historical characteristic parameters that influence the energy efficiency of the thermal system; Creating an energy efficiency prediction model of the thermal system based on historical characteristic parameters and a preset neural network model; capturing the real-time characteristic parameters of the thermal system and inputting them into the energy efficiency prediction model to obtain energy efficiency prediction data; Acquisition of real-time energy efficiency data of the thermal system and performance of a comparative analysis between the real-time energy efficiency data and the energy efficiency forecast data; Evaluate and calculate the energy efficiency difference of the thermal system based on the results of the comparative analysis in order to obtain an energy efficiency difference rating value for the thermal system; Determining an optimization coefficient based on the energy efficiency difference rating value and optimizing and controlling the real-time characteristic parameters of the thermal system based on the optimization coefficient. [2] Method for optimizing and controlling a thermal system according to claim 1, characterized by , that the acquisition of historical operating data and historical energy efficiency data of the thermal system, and the analysis of historical operating data and historical energy efficiency data to determine historical characteristic parameters that influence the energy efficiency of the thermal system, includes the following: Recording historical operating data and historical energy efficiency data of the thermal system and dividing the historical operating data into several groups of historical operating parameter data sets based on the parameter type; Determine the i-th historical operating parameter data sets from the multiple historical operating parameter data sets and select historical energy efficiency data where the other historical operating parameters are the same; Analyzing the change in historical energy efficiency data according to the i-th historical operating parameter data sets and determining the parameter according to the i-th historical operating parameter data sets whose change exceeds a preset change threshold, as a historical characteristic parameter that influences the energy efficiency of the thermal system. [3] Method for optimizing and controlling thermal systems according to claim 2, characterized by , that creating an energy efficiency prediction model of the thermal system based on historical characteristic parameters and a preset neural network model, acquiring the real-time characteristic parameters of the thermal system and inputting them into the energy efficiency prediction model to obtain energy efficiency prediction data, includes the following: Creating a dataset based on historical characteristic parameters and corresponding historical energy efficiency data, inputting the dataset into a preset neural network model to create an energy efficiency prediction original model; Splitting the dataset into training sets and test sets according to a specific ratio and inputting the training sets and test sets into the energy efficiency prediction original model; Training and testing the energy efficiency forecast originator model until the energy efficiency forecast originator model meets the preset convergence conditions, thereby creating the energy efficiency forecast model; Acquiring the real-time characteristic parameters of the thermal system and inputting these real-time characteristic parameters into the energy efficiency prediction model, and executing predictions through the energy efficiency prediction model to obtain energy efficiency prediction data of the thermal system. [4] Method for optimizing and controlling a thermal system according to claim 3, characterized by , that the acquisition of real-time energy efficiency data of the thermal system and the performance of a comparative analysis between the real-time energy efficiency data and the energy efficiency forecast data includes the following: Acquiring real-time energy efficiency data of the thermal system and analyzing the similarity between the real-time energy efficiency data and the energy efficiency forecast data; Subtracting the real-time energy efficiency data from the energy efficiency forecast data to determine energy efficiency difference data and creating a time-based curve diagram based on the energy efficiency difference data to determine an energy efficiency difference curve; Determining curve segments with non-zero energy efficiency differences from an energy efficiency difference curve and dividing the curve segments into several first curve segments greater than zero and continuous, and second curve segments less than zero and continuous; Classification of all first curve segments as first category curve segments and all second curve segments as second category curve segments; Calculate the average values ​​of the curve segments of the first category and the curve segments of the second category to obtain a first average value and a second average value, and determine the number of first curve segments in the curve segments of the first category and the number of second curve segments in the curve segments of the second category to obtain a first count and a second count. [5] Method for optimizing and controlling a thermal system according to claim 4, characterized by , that analyzing the similarity between real-time energy efficiency data and energy efficiency forecast data includes the following: Recording the real-time energy efficiency data and the energy efficiency forecast data, each in a curve diagram, and performing a Fourier transformation of both curve diagrams; Creating a spectrum graph of the fourier-transformed curve diagram and extracting primary frequency features, spectrum shape features, and spectrum energy distribution features from the spectrum graphs; Calculating the cosine similarity of the primary frequency features, the spectrum shape features, and the spectrum energy distribution features between the two spectrum graphs and determining preset weights for the primary frequency features, the spectrum shape features, and the spectrum energy distribution features; Calculating the weighted sum of the cosine similarities of the primary frequency features, the spectrum shape features, and the spectrum energy distribution features between the two spectrum graphs with the corresponding preset weights to calculate the similarity between the real-time energy efficiency data and the energy efficiency forecast data. [6] Method for optimizing and controlling a thermal system according to claim 4, characterized by , that assessing and calculating the energy efficiency difference of the thermal system based on the results of the comparative analysis in order to obtain an energy efficiency difference assessment value of the thermal system; Determining the similarity between real-time energy efficiency data and energy efficiency forecast data, as well as a first average value and a first number of curve segments of the first category and a second average value and a second number of curve segments of the second category; Evaluate and calculate the first average value of the curve segment of the first category and the second average value of the curve segment of the second category to determine a first difference assessment value and a second difference assessment value; Calculating the assessment value of the energy efficiency difference of the thermal system based on the similarity between the real-time energy efficiency data and the energy efficiency forecast data, the first difference assessment value and the first number of curve segments of the first category, and the second difference assessment value and the second number of curve segments of the second category; The formula for calculating the assessment value of the energy efficiency difference of the thermal system is: L=S×(g1×Xm+g2×Yn), where L is the energy efficiency difference rating of the thermal system, S is the similarity between the real-time energy efficiency data and the energy efficiency forecast data, g1 is the preset weighting of the curve segment of the first category, X is the first difference rating of the curve segment of the first category, m is the first number of curve segments of the first category, g2 is the preset weighting of the curve segment of the second category, Y is the second difference rating of the curve segment of the second category, and n is the second number of curve segments of the second category. [7] Method for optimizing and controlling a thermal system according to claim 6, characterized by , that determining an optimization coefficient based on the energy efficiency difference rating value and optimizing and controlling the real-time characteristic parameters of the thermal system based on the optimization coefficient includes the following: Specifying a corresponding relationship of the optimization coefficient-energy efficiency difference rating interval, for each energy efficiency difference rating interval the corresponding relationship of the optimization coefficient-energy efficiency difference rating interval is assigned to a corresponding optimization coefficient; Determining the energy efficiency difference rating value and selecting the optimization coefficient that corresponds to the energy efficiency difference rating value interval, based on an assignment relationship of the energy efficiency difference rating value interval to which the energy efficiency difference rating value belongs, within the corresponding relationship of the optimization coefficient-energy efficiency difference rating value interval; Adjusting the real-time characteristic parameters based on the optimization coefficient and controlling the operation of the thermal system based on the adjusted real-time characteristic parameters. [8] Optimization control system for thermal systems, characterized by , which includes the following: A data acquisition module for recording historical operating data and historical energy efficiency data of the thermal system, analyzing the historical operating data and historical energy efficiency data to determine historical characteristic parameters that influence the energy efficiency of the thermal system; A forecasting module for creating an energy efficiency forecasting model of the thermal system based on historical characteristic parameters and a preset neural network model, capturing the real-time characteristic parameters of the thermal system and their input into the energy efficiency forecasting model to obtain energy efficiency forecast data; A comparison module for capturing real-time energy efficiency data of the thermal system and for performing a comparative analysis between the real-time energy efficiency data and the energy efficiency forecast data; A calculation module for evaluating and calculating the energy efficiency difference of the thermal system based on the results of the comparative analysis, in order to obtain an energy efficiency difference evaluation value of the thermal system; An optimization module for determining an optimization coefficient based on the energy efficiency difference rating value and optimization and control of the real-time characteristic parameters of the thermal system based on the optimization coefficient.

Images