Thermodynamic system optimization control method and system

Abstract

The invention discloses a thermodynamic system optimization control method and system, and the method comprises the steps: obtaining historical operation data and historical energy efficiency data of a thermodynamic system, analyzing the historical operation data and historical energy efficiency data, and determining historical feature parameters affecting the energy efficiency of the thermodynamic system; constructing an energy efficiency prediction model of the thermodynamic system based on the historical feature parameters and a preset neural network model, and performing prediction to obtain energy efficiency prediction data; acquiring real-time energy efficiency data of the thermodynamic system, and comparing and analyzing the real-time energy efficiency data with the energy efficiency prediction data; evaluating and calculating the energy efficiency difference of the thermodynamic system according to the comparative analysis result to obtain an energy efficiency difference evaluation value; and determining an optimization coefficient according to the energy efficiency difference evaluation value, and performing optimization control on the real-time characteristic parameters of the thermodynamic system according to the optimization coefficient. Through historical data analysis, prediction model construction and real-time optimization control, the energy efficiency and the operation efficiency of the thermodynamic system are improved, intelligent operation of the thermodynamic system is realized, and the self-adaptability and the intelligent level of the thermodynamic system are also improved.

Description

Technical Field

[0001] The present invention relates to the technical field of thermal systems, and in particular to a thermal system optimization control method and system. Background Art

[0002] In the context of today's energy shortage and environmental protection, efficient operation and energy utilization of thermal systems have become important issues of concern in industrial production and life. Traditional thermal system control methods before optimization have certain deficiencies in adaptability, real-time performance, accuracy and energy efficiency optimization, and are difficult to meet today's requirements for energy efficiency and environmental protection. Therefore, the introduction of optimization control methods can make up for these deficiencies and improve the energy efficiency and operation efficiency of the system.

[0003] Traditional thermal system control methods usually adopt static control strategies, which are often difficult to adapt to changes in the system's operating status. This makes it possible for the system to fail to fully utilize the current operating conditions, resulting in energy waste and reduced system efficiency. At the same time, traditional methods often lack real-time optimization capabilities and are unable to monitor and adjust the system's operating status in real time, which means that the system cannot respond in time when facing changing environmental conditions, resulting in reduced operating energy efficiency and waste of resources. In addition, traditional control methods are usually based on engineers' experience and rules, and lack in-depth analysis and utilization of large amounts of historical data. This makes the system's control strategy likely to be inaccurate and inefficient, and unable to adapt to the control of multiple mutually influencing parameters and constraints. Summary of the invention

[0004] In order to solve the above technical problems, the present invention provides a thermal system optimization control method and system, including: Obtain historical operation data and historical energy efficiency data of the thermal system, analyze the historical operation data and historical energy efficiency data, and determine the historical characteristic parameters that affect the energy efficiency of the thermal system; An energy efficiency prediction model for the thermal system is constructed based on historical characteristic parameters and a preset neural network model, and real-time characteristic parameters of the thermal system are obtained and input into the energy efficiency prediction model for prediction to obtain energy efficiency prediction data; Obtain real-time energy efficiency data of the thermal system, and compare and analyze the real-time energy efficiency data with the energy efficiency prediction data; According to the comparative analysis results, the energy efficiency difference of the thermal system is evaluated and calculated to obtain the energy efficiency difference evaluation value of the thermal system; The optimization coefficient is determined according to the energy efficiency difference evaluation value, and the real-time characteristic parameters of the thermal system are optimized and controlled according to the optimization coefficient.

[0005] Furthermore, the acquisition of historical operation data and historical energy efficiency data of the thermal system, and analysis of the historical operation data and historical energy efficiency data to determine historical characteristic parameters affecting the energy efficiency of the thermal system include: Acquire historical operation data and historical energy efficiency data of the thermal system, and divide the historical operation data into several groups of historical operation parameter data according to parameter types; Determine the i-th historical operating parameter data group from a plurality of historical operating parameter data groups, and select the historical energy efficiency data when other historical operating parameters are the same; The change in historical energy efficiency data corresponding to the i-th historical operating parameter data group is analyzed, and the parameter corresponding to the i-th historical operating parameter data group whose change is greater than a preset change threshold is determined as a historical characteristic parameter affecting the energy efficiency of the thermal system.

[0006] Furthermore, the energy efficiency prediction model of the thermal system is constructed based on the historical characteristic parameters and the preset neural network model, and the real-time characteristic parameters of the thermal system are obtained and input into the energy efficiency prediction model for prediction to obtain energy efficiency prediction data, including: A data set is constructed based on historical characteristic parameters and corresponding historical energy efficiency data, and the data set is input into a preset neural network model to construct an initial energy efficiency prediction model; The data set is divided into a training set and a test set according to a certain ratio, and the training set and the test set are input into the initial energy efficiency prediction model; The energy efficiency prediction initial model is trained and tested until the energy efficiency prediction initial model meets the preset convergence conditions, thereby obtaining the energy efficiency prediction model; The real-time characteristic parameters of the thermal system are obtained, and the real-time characteristic parameters are input into the energy efficiency prediction model. The energy efficiency prediction model performs prediction to obtain energy efficiency prediction data of the thermal system.

[0007] Furthermore, the real-time energy efficiency data of the thermal system is obtained, and the real-time energy efficiency data is compared and analyzed with the energy efficiency prediction data, including: Obtain real-time energy efficiency data of the thermal system and analyze the similarity between real-time energy efficiency data and energy efficiency prediction data; The real-time energy efficiency data is subtracted from the energy efficiency prediction data to obtain energy efficiency difference data, and a curve graph with time as the axis is drawn according to the energy efficiency difference data to obtain an energy efficiency difference curve; Determine a curve segment whose energy efficiency difference is not zero from the energy efficiency difference curve, and divide the curve segment into a plurality of first curve segments whose values ​​are greater than zero and continuous and second curve segments whose values ​​are less than zero and continuous; Classifying all first curve segments as first-category curve segments, and classifying all second curve segments as second-category curve segments; The average values ​​of the first type of curve segments and the second type of curve segments are calculated respectively to obtain a first average value and a second average value, and the number of first curve segments in the first type of curve segments and the number of second curve segments in the second type of curve segments are determined to obtain a first number and a second number.

[0008] Furthermore, the analyzing the similarity between the real-time energy efficiency data and the energy efficiency prediction data includes: The real-time energy efficiency data and the energy efficiency prediction data are plotted into curve graphs respectively, and the two curve graphs are subjected to Fourier transformation; Obtain a spectrum diagram of the Fourier transformed curve graph, and extract main frequency features, spectrum shape features, and spectrum energy distribution features from the spectrum diagram; Calculating the cosine similarity of the main frequency features, the spectrum shape features, and the spectrum energy distribution features between the two spectrum graphs, and determining the preset weights of the main frequency features, the spectrum shape features, and the spectrum energy distribution features; The cosine similarities of the main frequency features, spectrum shape features and spectrum energy distribution features between the two spectrum graphs are weighted and added with the corresponding preset weights to obtain the similarity between the real-time energy efficiency data and the energy efficiency prediction data.

[0009] Furthermore, the energy efficiency difference of the thermal system is evaluated and calculated according to the comparative analysis results to obtain the energy efficiency difference evaluation value of the thermal system, including: Obtaining the similarity between the real-time energy efficiency data and the energy efficiency prediction data, as well as a first average value and a first number of first-type curve segments, and a second average value and a second number of second-type curve segments; Evaluate and obtain the first average value of the first type of curve segments and the second average value of the second type of curve segments respectively to obtain a first difference evaluation value and a second difference evaluation value; The energy efficiency difference evaluation value of the thermal system is calculated based on the similarity between the real-time energy efficiency data and the energy efficiency prediction data, the first difference evaluation value and the first quantity of the first type of curve segment, and the second difference evaluation value and the second quantity of the second type of curve segment. The energy efficiency difference evaluation value calculation formula of the thermal system is: L=S ( ), Among them, L is the energy efficiency difference evaluation value of the thermal system, S is the similarity between the real-time energy efficiency data and the energy efficiency prediction data, g1 is the preset weight of the first type of curve segment, X is the first difference evaluation value of the first type of curve segment, m is the first number of the first type of curve segments, g2 is the preset weight of the second type of curve segment, Y is the second difference evaluation value of the second type of curve segment, and n is the second number of the second type of curve segments.

[0010] Furthermore, determining the optimization coefficient according to the energy efficiency difference evaluation value, and optimizing and controlling the real-time characteristic parameters of the thermal system according to the optimization coefficient, includes: The correspondence between the optimization coefficient and the energy efficiency difference evaluation value interval is preset, and the correspondence between the optimization coefficient and the energy efficiency difference evaluation value interval is associated with a corresponding optimization coefficient for each energy efficiency difference evaluation value interval; Obtaining an energy efficiency difference evaluation value, and based on a mapping relationship between an energy efficiency difference evaluation value interval to which the energy efficiency difference evaluation value belongs and an optimization coefficient corresponding to the energy efficiency difference evaluation value interval corresponding relationship, selecting an optimization coefficient corresponding to the energy efficiency difference evaluation value interval; The real-time characteristic parameters are adjusted according to the optimization coefficients, and the operation of the thermal system is controlled according to the adjusted real-time characteristic parameters.

[0011] The present invention also provides a thermal system optimization control system, comprising: An acquisition module is used to acquire historical operation data and historical energy efficiency data of the thermal system, analyze the historical operation data and historical energy efficiency data, and determine historical characteristic parameters that affect the energy efficiency of the thermal system; The prediction module is used to build an energy efficiency prediction model of the thermal system based on historical characteristic parameters and a preset neural network model, and obtain real-time characteristic parameters of the thermal system, and input them into the energy efficiency prediction model for prediction to obtain energy efficiency prediction data; The comparison module is used to obtain the real-time energy efficiency data of the thermal system and compare and analyze the real-time energy efficiency data with the energy efficiency prediction data; A calculation module is used to evaluate and calculate the energy efficiency difference of the thermal system according to the comparative analysis results to obtain the energy efficiency difference evaluation value of the thermal system; The optimization module is used to determine the optimization coefficient according to the energy efficiency difference evaluation value, and optimize the real-time characteristic parameters of the thermal system according to the optimization coefficient.

[0012] Compared with the prior art, the thermal system optimization control method and system of the embodiment of the present invention have the following beneficial effects: The present invention determines the historical characteristic parameters that affect the energy efficiency of the thermal system by analyzing the historical operation data and historical energy efficiency data, and constructs an energy efficiency prediction model, which can help system managers gain a deep understanding of the laws and influencing factors of the operation of the thermal system and provide a basis for future system optimization. The energy efficiency prediction model constructed by the present invention based on historical characteristic parameters and a preset neural network model can help system managers obtain energy efficiency prediction data of the thermal system in real time and provide a reference for real-time decision-making; The present invention can help system managers to timely discover energy efficiency fluctuations and abnormal situations by acquiring real-time characteristic parameters and real-time energy efficiency data of the thermal system and comparing and analyzing them with energy efficiency prediction data, and provide guidance for timely adjustments; The present invention evaluates and calculates the energy efficiency difference of the thermal system according to the comparative analysis results, obtains the energy efficiency difference evaluation value, determines the optimization coefficient, and optimizes and controls the real-time characteristic parameters of the thermal system according to the optimization coefficient, which can help system managers to achieve real-time optimization and regulation of the thermal system and improve the energy efficiency and operation efficiency of the system. In summary, the present invention can realize the intelligent operation of the thermal system through historical data analysis, prediction model construction and real-time optimization control, improve the system's adaptability and intelligence level, and at the same time optimize energy efficiency, improve resource utilization efficiency, and reduce operating costs, which is helpful to improve the operating efficiency and sustainable development capabilities of the thermal system. BRIEF DESCRIPTION OF THE DRAWINGS

[0013] Figure 1 1 is a schematic diagram of the flow structure of the thermal system optimization control method according to an embodiment of the present invention; Figure 2 It is a schematic diagram of the composition of the thermal system optimization control system in an embodiment of the present invention. DETAILED DESCRIPTION

[0014] The specific implementation methods of the present application are further described in detail below in conjunction with the accompanying drawings and examples. The following examples are used to illustrate the present invention, but are not intended to limit the scope of the present invention.

[0015] In the description of the present application, it should be understood that the terms "center", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside", etc., indicating orientations or positional relationships, are based on the orientations or positional relationships shown in the accompanying drawings, and are only for the convenience of describing the present application and simplifying the description, and do not indicate or imply that the platform or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore should not be understood as a limitation on the present application.

[0016] The terms "second" and "second" are used for descriptive purposes only and should not be understood as indicating or implying a relative degree of importance or implicitly indicating the number of the indicated technical features. Thus, a feature defined with "second" or "second" may explicitly or implicitly include one or more of the features. In the description of this application, unless otherwise specified, "multiple" means two or more.

[0017] In the description of this application, it should be noted that, unless otherwise clearly specified and limited, the terms "installed", "connected", and "connected" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be indirectly connected through an intermediate medium, or it can be the internal communication of two components. For ordinary technical personnel in this field, the specific meanings of the above terms in this application can be understood according to specific circumstances.

[0018] like Figure 1 As shown, in an embodiment of the present application, a thermal system optimization control method is provided, including: S100: obtaining historical operation data and historical energy efficiency data of the thermal system, and analyzing the historical operation data and historical energy efficiency data to determine the historical characteristic parameters that affect the energy efficiency of the thermal system; S200: constructing an energy efficiency prediction model of the thermal system based on the historical characteristic parameters and a preset neural network model, and obtaining real-time characteristic parameters of the thermal system, and inputting them into the energy efficiency prediction model for prediction to obtain energy efficiency prediction data; S300: obtaining real-time energy efficiency data of the thermal system, and comparing and analyzing the real-time energy efficiency data with the energy efficiency prediction data; S400: evaluating and calculating the energy efficiency difference of the thermal system according to the comparative analysis results, and obtaining an energy efficiency difference evaluation value of the thermal system; S500: determining an optimization coefficient according to the energy efficiency difference evaluation value, and optimizing and controlling the real-time characteristic parameters of the thermal system according to the optimization coefficient.

[0019] Furthermore, the present invention can help system managers gain an in-depth understanding of the laws and influencing factors of thermal system operation and provide a basis for future system optimization by analyzing historical operating data and historical energy efficiency data, determining historical characteristic parameters that affect the energy efficiency of the thermal system, and constructing an energy efficiency prediction model, thereby providing a basis for future system optimization; the energy efficiency prediction model constructed based on historical characteristic parameters and a preset neural network model can help system managers obtain energy efficiency prediction data of the thermal system in real time and provide a reference for real-time decision-making; the present invention can help system managers promptly discover energy efficiency fluctuations and abnormal situations by obtaining real-time characteristic parameters and real-time energy efficiency data of the thermal system and comparing and analyzing them with energy efficiency prediction data, Provide guidance for timely adjustment; the present invention evaluates and calculates the energy efficiency difference of the thermal system according to the comparative analysis results, obtains the energy efficiency difference evaluation value, determines the optimization coefficient, and optimizes and controls the real-time characteristic parameters of the thermal system according to the optimization coefficient, which can help system managers to achieve real-time optimization and regulation of the thermal system and improve the energy efficiency and operation efficiency of the system; in summary, the present invention can realize the intelligent operation of the thermal system through historical data analysis, prediction model construction and real-time optimization control, improve the system's adaptability and intelligence level, and at the same time optimize energy efficiency, improve resource utilization efficiency, and reduce operating costs, which is helpful to improve the operating efficiency and sustainable development capabilities of the thermal system.

[0020] In an embodiment of the present application, a thermal system optimization control method is provided, which obtains historical operation data and historical energy efficiency data of the thermal system, analyzes the historical operation data and historical energy efficiency data, and determines historical characteristic parameters that affect the energy efficiency of the thermal system, including: obtaining historical operation data and historical energy efficiency data of the thermal system, and dividing the historical operation data into several groups of historical operation parameter data groups according to parameter type; determining the i-th historical operation parameter data group from several historical operation parameter data groups, and screening historical energy efficiency data when other historical operation parameters are the same; analyzing the change amount of historical energy efficiency data corresponding to the i-th historical operation parameter data group, and determining the parameter corresponding to the i-th historical operation parameter data group whose change amount is greater than a preset change amount threshold as the historical characteristic parameter that affects the energy efficiency of the thermal system.

[0021] Specifically, the historical operation data and historical energy efficiency data of the thermal system are collected and sorted to ensure the accuracy and completeness of the data; the historical operation data are divided into several groups of historical operation parameter data groups according to the parameter type, such as different types of parameter data groups such as temperature, pressure, flow, etc.; the specific historical operation parameter data group to be analyzed is selected, recorded as the i-th historical operation parameter data group, and the historical energy efficiency data corresponding to the i-th historical operation parameter data group is screened out from the historical energy efficiency data when other historical operation parameters are the same; the historical energy efficiency data corresponding to the i-th historical operation parameter data group is analyzed, its change amount is calculated, and compared with the preset change amount threshold, when the change amount is greater than the preset change amount threshold, the parameter corresponding to the i-th historical operation parameter data group is determined as the historical characteristic parameter affecting the energy efficiency of the thermal system. This step uses historical data for analysis to find out the characteristic parameters that are closely related to energy efficiency changes, providing guidance for subsequent energy efficiency optimization.

[0022] In an embodiment of the present application, a thermal system optimization control method is provided, wherein an energy efficiency prediction model of the thermal system is constructed based on historical characteristic parameters and a preset neural network model, and real-time characteristic parameters of the thermal system are obtained, and input into the energy efficiency prediction model for prediction to obtain energy efficiency prediction data, including: constructing a data set based on historical characteristic parameters and corresponding historical energy efficiency data, and inputting the data set into a preset neural network model to construct an initial energy efficiency prediction model; dividing the data set into a training set and a test set according to a certain ratio, and inputting the training set and the test set into the initial energy efficiency prediction model; training and testing the initial energy efficiency prediction model until the initial energy efficiency prediction model meets the preset convergence conditions to obtain the energy efficiency prediction model; obtaining the real-time characteristic parameters of the thermal system, and inputting the real-time characteristic parameters into the energy efficiency prediction model, and the energy efficiency prediction model performs prediction to obtain energy efficiency prediction data of the thermal system.

[0023] Specifically, a data set is constructed based on historical characteristic parameters and corresponding historical energy efficiency data, wherein the historical characteristic parameters are used as input features and the historical energy efficiency data are used as output labels; the constructed data set is input into a preset neural network model to construct an initial model for energy efficiency prediction; the data set is divided into a training set and a test set according to a certain ratio to ensure the independence and effectiveness of model training and testing; the training set and the test set are input into the initial model for energy efficiency prediction, and the model is trained and tested until the model meets the preset convergence conditions to obtain an energy efficiency prediction model; the real-time characteristic parameters of the thermal system are obtained, and the real-time characteristic parameters are input into the energy efficiency prediction model, and the model is used for prediction to obtain energy efficiency prediction data for the thermal system. This step uses a neural network model to learn and model historical data, thereby realizing real-time prediction of the energy efficiency of the thermal system. By continuously obtaining real-time characteristic parameters and inputting them into the model, continuous monitoring and prediction of the energy efficiency of the thermal system can be achieved.

[0024] In an embodiment of the present application, a thermal system optimization control method is provided, wherein the real-time energy efficiency data of the thermal system is obtained, and the real-time energy efficiency data is compared and analyzed with the energy efficiency prediction data, including: obtaining the real-time energy efficiency data of the thermal system, and analyzing the similarity between the real-time energy efficiency data and the energy efficiency prediction data; subtracting the real-time energy efficiency data from the energy efficiency prediction data to obtain energy efficiency difference data, and drawing a curve graph with time as the axis according to the energy efficiency difference data to obtain an energy efficiency difference curve; determining curve segments whose energy efficiency differences are not zero from the energy efficiency difference curve, and dividing the curve segments into a plurality of first curve segments that are greater than zero and continuous and second curve segments that are less than zero and continuous; classifying all the first curve segments as first-category curve segments, and classifying all the second curve segments as second-category curve segments; calculating the average values ​​of the first-category curve segments and the second-category curve segments respectively to obtain a first average value and a second average value, and determining 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 number and a second number.

[0025] Specifically, the real-time energy efficiency data of the thermal system is obtained to ensure the accuracy and completeness of the data; the real-time energy efficiency data and the energy efficiency prediction data are compared and analyzed for similarity to evaluate the accuracy and reliability of the prediction model; the real-time energy efficiency data is subtracted from the energy efficiency prediction data to obtain the energy efficiency difference data; according to the energy efficiency difference data, a curve graph with time as the axis is drawn to obtain the energy efficiency difference curve; the curve segments with energy efficiency differences not being zero are determined from the energy efficiency difference curve, and they are divided into first curve segments greater than zero and second curve segments less than zero; all first curve segments are classified as first-class curve segments, and all second curve segments are classified as second-class curve segments; the average values ​​of the first-class curve segments and the second-class curve segments are calculated respectively to obtain the first average value and the second average value, and the number of the first curve segments in the first-class curve segments and the number of the second curve segments in the second-class curve segments are determined to obtain the first number and the second number. Through this step, the difference between the real-time energy efficiency data and the prediction data can be deeply analyzed, the energy efficiency fluctuations in the system operation can be further understood, and a basis for further optimization and adjustment can be provided.

[0026] In an embodiment of the present application, a thermal system optimization control method is provided, and the analysis of the similarity between real-time energy efficiency data and energy efficiency prediction data includes: plotting the real-time energy efficiency data and the energy efficiency prediction data into curve graphs respectively, and performing Fourier transform on the two curve graphs; obtaining a spectrum graph of the curve graph after Fourier transform, and extracting main frequency features, spectrum shape features, and spectrum energy distribution features from the spectrum graph; calculating the cosine similarity of the main frequency features, spectrum shape features, and spectrum energy distribution features between the two spectrum graphs, and determining the preset weights of the main frequency features, spectrum shape features, and spectrum energy distribution features; performing weighted addition calculation on the cosine similarities of the main frequency features, spectrum shape features, and spectrum energy distribution features between the two spectrum graphs and the corresponding preset weights, respectively, to obtain the similarity between the real-time energy efficiency data and the energy efficiency prediction data.

[0027] Specifically, the real-time energy efficiency data and the energy efficiency prediction data are plotted into curve graphs respectively, and the two curve graphs are Fourier transformed to convert them into the frequency domain; the spectrum graph is obtained from the result after the Fourier transform, which shows the energy distribution of the signal in the frequency domain; the main frequency features, spectrum shape features and spectrum energy distribution features are extracted from the spectrum graph, which can help understand the characteristics of the signal in the frequency domain; the cosine similarity of the main 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; the preset weights of the main frequency features, spectrum shape features and spectrum energy distribution features are determined so that they can be taken into account in the similarity calculation; the cosine similarity of the main frequency features, spectrum shape features and spectrum energy distribution features between the two spectrum graphs is weighted and added with the corresponding preset weights to obtain the similarity between the real-time energy efficiency data and the energy efficiency prediction data. Through this step, the real-time energy efficiency data and the energy efficiency prediction data can be compared in the frequency domain to obtain their similarity in the frequency domain, which helps to more comprehensively understand the relationship between the two signals and provide support for further analysis and decision-making.

[0028] In an embodiment of the present application, a thermal system optimization control method is provided, wherein the energy efficiency difference of the thermal system is evaluated and calculated according to the comparative analysis results to obtain the energy efficiency difference evaluation value of the thermal system, including: obtaining the similarity between the real-time energy efficiency data and the energy efficiency prediction data, as well as the first average value and the first number of the first type of curve segments, the second average value and the second number of the second type of curve segments; evaluating and obtaining the first average value of the first type of curve segments and the second average value of the second type of curve segments respectively to obtain the first difference evaluation value and the second difference evaluation value; calculating the energy efficiency difference evaluation value of the thermal system based on the similarity between the real-time energy efficiency data and the energy efficiency prediction data, as well as the first difference evaluation value and the first number of the first type of curve segments, and the second difference evaluation value and the second number of the second type of curve segments, wherein the energy efficiency difference evaluation value calculation formula of the thermal system is: L=S ( ), Among them, L is the energy efficiency difference evaluation value of the thermal system, S is the similarity between the real-time energy efficiency data and the energy efficiency prediction data, g1 is the preset weight of the first type of curve segment, X is the first difference evaluation value of the first type of curve segment, m is the first number of the first type of curve segments, g2 is the preset weight of the second type of curve segment, Y is the second difference evaluation value of the second type of curve segment, and n is the second number of the second type of curve segments.

[0029] Specifically, the first average value of the first type of curve segment and the second average value of the second type of curve segment are evaluated and obtained to obtain the first difference evaluation value and the second difference evaluation value; the similarity between the real-time energy efficiency data and the energy efficiency prediction data is used as S; the preset weight of the first type of curve segment is used as g1, the first difference evaluation value of the first type of curve segment is used as X, the first number of the first type of curve segment is used as m, the preset weight of the second type of curve segment is used as g2, the second difference evaluation value of the second type of curve segment is used as Y, and the second number of the second type of curve segment is used as n; the energy efficiency difference evaluation value L of the thermal system is calculated. Through this step, the similarity between the real-time energy efficiency data and the energy efficiency prediction data and the difference evaluation value and number of the first type of curve segment and the second type of curve segment can be comprehensively considered to obtain the energy efficiency difference evaluation value of the thermal system. This evaluation value can help you more comprehensively understand the energy efficiency fluctuations in the operation of the system and provide a basis for further optimization and adjustment.

[0030] In an embodiment of the present application, a thermal system optimization control method is provided, wherein an optimization coefficient is determined according to an energy efficiency difference evaluation value, and real-time characteristic parameters of the thermal system are optimized and controlled according to the optimization coefficient, including: presetting an optimization coefficient-energy efficiency difference evaluation value interval correspondence relationship, wherein the optimization coefficient-energy efficiency difference evaluation value interval correspondence relationship is associated with a corresponding optimization coefficient for each energy efficiency difference evaluation value interval; obtaining the energy efficiency difference evaluation value, and based on a mapping relationship between the energy efficiency difference evaluation value interval to which the energy efficiency difference evaluation value belongs within the optimization coefficient-energy efficiency difference evaluation value interval correspondence relationship, selecting the optimization coefficient corresponding to the energy efficiency difference evaluation value interval; adjusting the real-time characteristic parameters according to the optimization coefficient, and controlling the operation of the thermal system according to the adjusted real-time characteristic parameters.

[0031] Specifically, the energy efficiency difference evaluation value is divided into different intervals, and corresponding optimization coefficients are pre-set for each interval. These optimization coefficients can be proportional coefficients used to adjust system parameters so that different optimization measures can be taken according to different situations of energy efficiency difference evaluation values; during the operation of the system, the real-time energy efficiency difference evaluation value is obtained, and the real-time energy efficiency difference evaluation value is compared with the pre-set energy efficiency difference evaluation value interval correspondence relationship to determine the interval to which it belongs, and the optimization coefficient corresponding to the energy efficiency difference evaluation value interval is selected according to the mapping relationship between the interval to which the energy efficiency difference evaluation value belongs in the optimization coefficient-energy efficiency difference evaluation value interval correspondence relationship; according to the selected optimization coefficient, the real-time characteristic parameters are adjusted, and these real-time characteristic parameters can be control parameters in the system, such as temperature, flow, etc.; The adjusted real-time characteristic parameters can be used to control the operation of the thermal system to achieve energy efficiency optimization. Through this step, the corresponding optimization coefficient can be selected according to the real-time energy efficiency difference evaluation value, and the real-time characteristic parameters can be adjusted accordingly to control the operation of the thermal system. This real-time adjustment and optimization method can help the system better adapt to the operation requirements under different energy efficiency conditions, thereby improving the energy efficiency performance of the system.

[0032] like Figure 2 As shown, in an embodiment of the present application, a thermal system optimization control system is provided, including: an acquisition module, which is used to acquire historical operation data and historical energy efficiency data of the thermal system, and analyze the historical operation data and historical energy efficiency data to determine the historical characteristic parameters that affect the energy efficiency of the thermal system; a prediction module, which is used to construct an energy efficiency prediction model of the thermal system based on the historical characteristic parameters and a preset neural network model, and acquire the real-time characteristic parameters of the thermal system, and input them into the energy efficiency prediction model for prediction to obtain energy efficiency prediction data; a comparison module, which is used to acquire the real-time energy efficiency data of the thermal system, and compare and analyze the real-time energy efficiency data with the energy efficiency prediction data; a calculation module, which is used to evaluate and calculate the energy efficiency difference of the thermal system according to the comparison and analysis results, and obtain the energy efficiency difference evaluation value of the thermal system; an optimization module, which is used to determine the optimization coefficient according to the energy efficiency difference evaluation value, and optimize and control the real-time characteristic parameters of the thermal system according to the optimization coefficient.

[0033] In summary, the embodiment of the present invention provides a thermal system optimization control method and system, which includes: obtaining historical operation data and historical energy efficiency data of the thermal system, analyzing them, and determining historical characteristic parameters that affect the energy efficiency of the thermal system; constructing an energy efficiency prediction model of the thermal system based on the historical characteristic parameters and a preset neural network model, and predicting to obtain energy efficiency prediction data; obtaining real-time energy efficiency data of the thermal system, and comparing and analyzing it with the energy efficiency prediction data; evaluating and calculating the energy efficiency difference of the thermal system according to the comparative analysis results, and obtaining an energy efficiency difference evaluation value; determining an optimization coefficient according to the energy efficiency difference evaluation value, and optimizing and controlling the real-time characteristic parameters of the thermal system according to it. The present invention improves the energy efficiency and operation efficiency of the thermal system through historical data analysis, prediction model construction and real-time optimization control, realizes the intelligent operation of the thermal system, and also improves the adaptability and intelligence level of the thermal system.

[0034] Finally, it should be noted that: Obviously, a person skilled in the art may make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the present invention and its equivalent technology, the present invention is also intended to include these modifications and variations.

[0035] The above is only an example of implementation of the present invention, but it cannot be used to limit the scope of the present invention. Any structural changes made according to the present invention, as long as they do not lose the essence of the present invention, should be regarded as falling within the scope of protection of the present invention and being restricted. Technical personnel in the relevant technical field can clearly understand that for the convenience and simplicity of description, the specific working process and related instructions of the platform described above can refer to the corresponding process in the aforementioned platform embodiment, and will not be repeated here.

[0036] The term "comprises" or any other similar term is intended to cover a non-exclusive inclusion such that a process, platform, article, or apparatus / platform that includes a list of elements includes not only those elements but also other elements not expressly listed or inherent to such process, platform, article, or apparatus / platform.

[0037] So far, the technical solutions of the present invention have been described in conjunction with the further embodiments shown in the accompanying drawings. However, it is easy for a person skilled in the art to understand that the protection scope of the present invention is obviously not limited to these specific embodiments. Without departing from the principle of the present invention, a person skilled in the art can make equivalent changes or substitutions to closely related technical features, and the technical solutions after these changes or substitutions will fall within the protection scope of the present invention.

[0038] The above description is only a preferred embodiment of the present invention and is not intended to limit the protection scope of the present invention.

Claims

1. A thermal system optimization control method, characterized in that: include: Obtain historical operation data and historical energy efficiency data of the thermal system, analyze the historical operation data and historical energy efficiency data, and determine the historical characteristic parameters that affect the energy efficiency of the thermal system; An energy efficiency prediction model for the thermal system is constructed based on historical characteristic parameters and a preset neural network model, and real-time characteristic parameters of the thermal system are obtained and input into the energy efficiency prediction model for prediction to obtain energy efficiency prediction data; Obtain real-time energy efficiency data of the thermal system, and compare and analyze the real-time energy efficiency data with the energy efficiency prediction data; According to the comparative analysis results, the energy efficiency difference of the thermal system is evaluated and calculated to obtain the energy efficiency difference evaluation value of the thermal system; The optimization coefficient is determined according to the energy efficiency difference evaluation value, and the real-time characteristic parameters of the thermal system are optimized and controlled according to the optimization coefficient.

2. A thermal system optimization control method according to claim 1, characterized in that: The obtaining of historical operation data and historical energy efficiency data of the thermal system, and analyzing the historical operation data and historical energy efficiency data to determine historical characteristic parameters that affect the energy efficiency of the thermal system include: Acquire historical operation data and historical energy efficiency data of the thermal system, and divide the historical operation data into several groups of historical operation parameter data according to parameter types; Determine the i-th historical operating parameter data group from a plurality of historical operating parameter data groups, and select the historical energy efficiency data when other historical operating parameters are the same; The change in historical energy efficiency data corresponding to the i-th historical operating parameter data group is analyzed, and the parameter corresponding to the i-th historical operating parameter data group whose change is greater than a preset change threshold is determined as a historical characteristic parameter affecting the energy efficiency of the thermal system.

3. A thermal system optimization control method according to claim 2, characterized in that: The energy efficiency prediction model of the thermal system is constructed based on the historical characteristic parameters and the preset neural network model, and the real-time characteristic parameters of the thermal system are obtained and input into the energy efficiency prediction model for prediction to obtain energy efficiency prediction data, including: A data set is constructed based on historical characteristic parameters and corresponding historical energy efficiency data, and the data set is input into a preset neural network model to construct an initial energy efficiency prediction model; The data set is divided into a training set and a test set according to a certain ratio, and the training set and the test set are input into the initial energy efficiency prediction model; The energy efficiency prediction initial model is trained and tested until the energy efficiency prediction initial model meets the preset convergence conditions, thereby obtaining the energy efficiency prediction model; The real-time characteristic parameters of the thermal system are obtained, and the real-time characteristic parameters are input into the energy efficiency prediction model. The energy efficiency prediction model performs prediction to obtain energy efficiency prediction data of the thermal system.

4. A thermal system optimization control method according to claim 3, characterized in that: The real-time energy efficiency data of the thermal system is obtained, and the real-time energy efficiency data is compared and analyzed with the energy efficiency prediction data, including: Obtain real-time energy efficiency data of the thermal system and analyze the similarity between real-time energy efficiency data and energy efficiency prediction data; The real-time energy efficiency data is subtracted from the energy efficiency prediction data to obtain energy efficiency difference data, and a curve graph with time as the axis is drawn according to the energy efficiency difference data to obtain an energy efficiency difference curve; Determine a curve segment whose energy efficiency difference is not zero from the energy efficiency difference curve, and divide the curve segment into a plurality of first curve segments whose values ​​are greater than zero and continuous and second curve segments whose values ​​are less than zero and continuous; Classifying all first curve segments as first-category curve segments, and classifying all second curve segments as second-category curve segments; The average values ​​of the first type of curve segments and the second type of curve segments are calculated respectively to obtain a first average value and a second average value, and the number of first curve segments in the first type of curve segments and the number of second curve segments in the second type of curve segments are determined to obtain a first number and a second number.

5. A thermal system optimization control method according to claim 4, characterized in that: The analyzing the similarity between the real-time energy efficiency data and the energy efficiency prediction data includes: The real-time energy efficiency data and the energy efficiency prediction data are plotted into curve graphs respectively, and the two curve graphs are subjected to Fourier transformation; Obtain a spectrum diagram of the Fourier transformed curve graph, and extract main frequency features, spectrum shape features, and spectrum energy distribution features from the spectrum diagram; Calculating the cosine similarity of the main frequency features, the spectrum shape features, and the spectrum energy distribution features between the two spectrum graphs, and determining the preset weights of the main frequency features, the spectrum shape features, and the spectrum energy distribution features; The cosine similarities of the main frequency features, spectrum shape features and spectrum energy distribution features between the two spectrum graphs are weighted and added with the corresponding preset weights to obtain the similarity between the real-time energy efficiency data and the energy efficiency prediction data.

6. A thermal system optimization control method according to claim 4, characterized in that: The energy efficiency difference of the thermal system is evaluated and calculated according to the comparative analysis results to obtain the energy efficiency difference evaluation value of the thermal system, including: Obtaining the similarity between the real-time energy efficiency data and the energy efficiency prediction data, as well as a first average value and a first number of first-type curve segments, and a second average value and a second number of second-type curve segments; Evaluate and obtain the first average value of the first type of curve segments and the second average value of the second type of curve segments respectively to obtain a first difference evaluation value and a second difference evaluation value; The energy efficiency difference evaluation value of the thermal system is calculated based on the similarity between the real-time energy efficiency data and the energy efficiency prediction data, the first difference evaluation value and the first quantity of the first type of curve segment, and the second difference evaluation value and the second quantity of the second type of curve segment. The energy efficiency difference evaluation value calculation formula of the thermal system is: L=S ( ), Among them, L is the energy efficiency difference evaluation value of the thermal system, S is the similarity between the real-time energy efficiency data and the energy efficiency prediction data, g1 is the preset weight of the first type of curve segment, X is the first difference evaluation value of the first type of curve segment, m is the first number of the first type of curve segments, g2 is the preset weight of the second type of curve segment, Y is the second difference evaluation value of the second type of curve segment, and n is the second number of the second type of curve segments.

7. A thermal system optimization control method according to claim 6, characterized in that: Determining the optimization coefficient according to the energy efficiency difference evaluation value, and optimizing and controlling the real-time characteristic parameters of the thermal system according to the optimization coefficient, includes: The correspondence between the optimization coefficient and the energy efficiency difference evaluation value interval is preset, and the correspondence between the optimization coefficient and the energy efficiency difference evaluation value interval is associated with a corresponding optimization coefficient for each energy efficiency difference evaluation value interval; Obtaining an energy efficiency difference evaluation value, and based on a mapping relationship between an energy efficiency difference evaluation value interval to which the energy efficiency difference evaluation value belongs and an optimization coefficient corresponding to the energy efficiency difference evaluation value interval corresponding relationship, selecting an optimization coefficient corresponding to the energy efficiency difference evaluation value interval; The real-time characteristic parameters are adjusted according to the optimization coefficients, and the operation of the thermal system is controlled according to the adjusted real-time characteristic parameters.

8. A thermal system optimization control system, characterized in that: include: An acquisition module is used to acquire historical operation data and historical energy efficiency data of the thermal system, analyze the historical operation data and historical energy efficiency data, and determine historical characteristic parameters that affect the energy efficiency of the thermal system; The prediction module is used to build an energy efficiency prediction model of the thermal system based on historical characteristic parameters and a preset neural network model, and obtain real-time characteristic parameters of the thermal system, and input them into the energy efficiency prediction model for prediction to obtain energy efficiency prediction data; The comparison module is used to obtain the real-time energy efficiency data of the thermal system and compare and analyze the real-time energy efficiency data with the energy efficiency prediction data; A calculation module is used to evaluate and calculate the energy efficiency difference of the thermal system according to the comparative analysis results to obtain the energy efficiency difference evaluation value of the thermal system; The optimization module is used to determine the optimization coefficient according to the energy efficiency difference evaluation value, and optimize the real-time characteristic parameters of the thermal system according to the optimization coefficient.

Images