High-temperature heat pump heat output optimization control method and system based on autoregression analysis

Abstract

The invention relates to the technical field of data analysis, in particular to a high-temperature heat pump heat output optimization control method and system based on autoregression analysis. The method comprises the following steps: establishing a high-temperature heat pump characteristic analysis model; analyzing high-temperature heat pump environment operation disturbance characteristic data according to the historical high-temperature heat pump environment parameters and the historical high-temperature heat pump operation data; performing environment disturbance sensitivity model parameter adjustment on the high-temperature heat pump characteristic analysis model based on the high-temperature heat pump environment operation disturbance characteristic data; the historical high-temperature heat pump control parameters and the historical high-temperature heat pump operation data are used for executing model error fitting optimization on the adjustment high-temperature heat pump characteristic analysis model; and the instant heat output optimization demand decision and the instant environment parameters are transmitted to an optimization high-temperature characteristic analysis model to analyze the dynamic scheduling control parameters of the high-temperature heat pump. According to the method, accurate modeling is carried out on the characteristics of the high-temperature heat pump equipment through the autoregression analysis technology, and intelligent optimization control over heat output of the high-temperature heat pump is achieved.

Description

Technical Field

[0001] The present invention relates to the technical field of data analysis, and in particular to a method and system for optimizing the heat output of a high-temperature heat pump based on autoregressive analysis. Background Art

[0002] With the rapid development of energy conservation, emission reduction and clean energy technologies, high-temperature heat pumps, as an efficient and environmentally friendly heating equipment, have been widely used in industrial production and civil heating. High-temperature heat pumps absorb unusable heat energy in the environment and convert it into usable heat energy. Through heat transfer, they effectively reduce energy waste, improve energy utilization, and achieve efficient energy utilization. In practical applications, due to the complex and changeable operating environment and the nonlinear dynamic characteristics of the equipment itself, the heat output efficiency and stability of the high-temperature heat pump system are affected by many factors. However, the existing high-temperature heat pump heat output control method relies on fixed control logic or empirical formulas, which is limited to meeting the basic operating requirements under certain specific working conditions. When faced with dynamically changing environmental parameters and diverse heat demands, it often exhibits problems such as delayed response, high energy consumption, and insufficient control accuracy, making it difficult to achieve precise heat output optimization control. Summary of the invention

[0003] Based on this, the present invention provides a high-temperature heat pump heat output optimization control method and system based on autoregressive analysis to solve at least one of the above technical problems.

[0004] To achieve the above purpose, a high temperature heat pump heat output optimization control method based on autoregressive analysis includes the following steps: Step S1: Obtain historical high-temperature heat pump control parameters, historical high-temperature heat pump operation data, and historical high-temperature heat pump environmental parameters; perform historical high-temperature heat pump operation characteristic analysis based on the historical high-temperature heat pump operation data to generate historical high-temperature heat pump operation characteristic data; map the historical high-temperature heat pump control parameters to the historical high-temperature heat pump operation characteristic data to perform correlation analysis on the control and operation characteristics of the historical high-temperature heat pump to generate historical high-temperature heat pump control-operation data; Step S2: establishing a high-temperature heat pump characteristic mapping relationship between control and operation based on historical high-temperature heat pump operation characteristic data to generate a high-temperature heat pump characteristic analysis model; Step S3: performing an operation disturbance mode analysis of the high-temperature heat pump environment according to historical high-temperature heat pump environmental parameters and historical high-temperature heat pump operating data, and generating high-temperature heat pump environment operation disturbance mode data; performing an operation disturbance feature analysis of the high-temperature heat pump environment based on the high-temperature heat pump environment operation disturbance mode data and historical high-temperature heat pump environmental parameters, and generating high-temperature heat pump environment operation disturbance feature data; Step S4: Based on the high-temperature heat pump environmental operation disturbance characteristic data, the model parameter adjustment processing of the high-temperature heat pump characteristic analysis model is performed to the environmental disturbance sensitivity, and the adjusted high-temperature heat pump characteristic analysis model is generated; the model error fitting optimization processing of the adjusted high-temperature heat pump characteristic analysis model is performed using the historical high-temperature heat pump control-operation data, and the optimized high-temperature heat pump characteristic analysis model is generated; Step S5: Obtain the instant high-temperature heat pump heat output optimization demand decision and the instant high-temperature heat pump environmental parameters; perform high-temperature heat pump dynamic scheduling control parameter analysis on the instant high-temperature heat pump heat output optimization demand decision and the instant high-temperature heat pump environmental parameters based on the optimized high-temperature characteristic analysis model, and generate high-temperature heat pump dynamic scheduling control parameters; perform high-temperature heat pump heat output optimization control operations through the high-temperature heat pump dynamic scheduling control parameters.

[0005] Further, step S1 includes the following steps: Step S11: acquiring historical high-temperature heat pump control parameters of the high-temperature heat pump control system, and monitoring and processing historical high-temperature heat pump operation and historical high-temperature heat pump environmental parameters of the high-temperature heat pump equipment through a distributed sensor network, so as to obtain historical high-temperature heat pump operation data and historical high-temperature heat pump environmental parameters; Step S12: performing historical high-temperature heat pump control change timing window analysis according to historical high-temperature heat pump control parameters to generate historical high-temperature heat pump control change timing window data; Step S13: using the historical high-temperature heat pump control change timing window to perform historical high-temperature heat pump window division processing on the historical high-temperature heat pump operation data to obtain historical high-temperature heat pump operation window data; Step S14: Analyze and process the operation characteristics of each window of the historical high-temperature heat pump operation window data to generate historical high-temperature heat pump operation characteristic data; Step S15: Mapping historical high-temperature heat pump control parameters to historical high-temperature heat pump operation characteristic data to perform correlation analysis between the control and operation characteristics of the historical high-temperature heat pump, and generating historical high-temperature heat pump control-operation data.

[0006] Further, step S2 includes the following steps: Step S21: using a preset autocorrelation function to perform autocorrelation order analysis of the heat pump operation characteristics on the historical high-temperature heat pump operation characteristic data to generate the heat pump operation characteristic autocorrelation order; Step S22: establishing a mapping relationship between control and operation of high-temperature heat pump characteristics through the autocorrelation order of heat pump operation characteristics to generate a high-temperature heat pump characteristic analysis model.

[0007] Further, step S3 includes the following steps: Step S31: performing an operation disturbance mode analysis of the high-temperature heat pump environment according to historical high-temperature heat pump environmental parameters and historical high-temperature heat pump operation data, and generating high-temperature heat pump environment operation disturbance mode data; Step S32: performing frequency domain data conversion processing on historical high-temperature heat pump environmental parameters to generate historical high-temperature heat pump environmental frequency domain data; Step S33: performing time series frequency domain data difference calculation of each environmental parameter type according to historical high temperature heat pump environment frequency domain data to generate heat pump environment time series frequency domain difference data; Step S34: performing an environmental parameter type influence weight analysis of each disturbance mode on the heat pump environment time series frequency domain difference data through the high-temperature heat pump environment operation disturbance mode data, and generating a disturbance mode environmental parameter type weight coefficient; Step S35: using the disturbance mode environmental parameter type weight coefficient to perform environmental type parameter weighted fusion processing on the historical high-temperature heat pump environmental frequency domain data to generate historical high-temperature heat pump environmental frequency domain fusion data; Step S36: Based on the historical high-temperature heat pump operation data and the historical high-temperature heat pump environment frequency domain fusion data, the operation disturbance characteristic analysis of the high-temperature heat pump environment is performed to generate the high-temperature heat pump environment operation disturbance characteristic data.

[0008] Further, step S4 includes the following steps: Step S41: using the Sobol technology to analyze the high-temperature heat pump environment operation disturbance mode data and the high-temperature heat pump environment operation disturbance characteristic data, and generate the high-temperature heat pump environment-operation disturbance interaction response coefficient; Step S42: using the high-temperature heat pump environment-operation disturbance response coefficient to adjust the model parameters of the high-temperature heat pump characteristic analysis model for environmental disturbance sensitivity, and generating an adjusted high-temperature heat pump characteristic analysis model; Step S43: Utilizing historical high-temperature heat pump control-operation data, the high-temperature heat pump characteristic analysis model is subjected to model error fitting optimization processing to generate an optimized high-temperature heat pump characteristic analysis model.

[0009] Further, step S43 includes the following steps: Step S431: transmitting historical high-temperature heat pump control-operation data to a high-temperature heat pump characteristic analysis model for high-temperature heat pump characteristic training analysis to generate high-temperature heat pump characteristic training data; Step S432: performing heterogeneous operation state division processing on the high temperature heat pump characteristic training data to generate heterogeneous operation state high temperature heat pump characteristic training data; Step S433: performing error distribution characteristic analysis of the high-temperature heat pump characteristics in a heterogeneous operating state based on the high-temperature heat pump characteristics training data in a heterogeneous operating state, and generating error distribution characteristic data of the high-temperature heat pump characteristics in a heterogeneous operating state; Step S434: performing model error fitting optimization processing on the high-temperature heat pump characteristic analysis model by using the high-temperature heat pump characteristic error distribution characteristic data in the heterogeneous operation state to generate an optimized high-temperature heat pump characteristic analysis model.

[0010] Further, step S433 includes the following steps: Performing heterogeneous operation state high temperature heat pump characteristic error data analysis based on heterogeneous operation state high temperature heat pump characteristic training data to generate heterogeneous operation state high temperature heat pump characteristic error data; Performing error clustering analysis on the high-temperature heat pump characteristic error data in heterogeneous operation states to generate high-temperature heat pump characteristic error clustering data in heterogeneous operation states; According to the high-temperature heat pump characteristic error clustering data in heterogeneous operation states, the high-temperature heat pump characteristic error distribution feature analysis in heterogeneous operation states is performed to generate the high-temperature heat pump characteristic error distribution feature data in heterogeneous operation states.

[0011] Further, step S5 includes the following steps: Step S51: obtaining an instant high-temperature heat pump heat output optimization demand decision; Step S52: monitoring and processing the real-time high-temperature heat pump environmental parameters of the high-temperature heat pump equipment through a distributed sensor network to obtain the real-time high-temperature heat pump environmental parameters; Step S53: designing a high-temperature heat pump heat output optimization control reward function according to the instant high-temperature heat pump heat output optimization demand decision; Step S54: transmitting the immediate high-temperature heat pump environmental parameters to the optimized high-temperature characteristic analysis model for immediate environmental response processing to obtain the immediate environmental response optimized high-temperature characteristic analysis model, and performing high-temperature heat pump dynamic scheduling control parameter analysis through the immediate environmental response optimized high-temperature characteristic analysis model and the high-temperature heat pump heat output optimization control reward function to generate the high-temperature heat pump dynamic scheduling control parameters; Step S55: Execute the high-temperature heat pump heat output optimization control operation through the high-temperature heat pump dynamic scheduling control parameters.

[0012] Further, step S53 includes the following steps: Step S531: performing a multi-objective optimization operation analysis of the high-temperature heat pump according to the instant high-temperature heat pump heat output optimization demand decision, and generating multi-objective optimization operation data of the high-temperature heat pump; Step S532: Perform high-temperature heat pump operation constraint mapping processing on the high-temperature heat pump multi-objective optimization operation data to generate constraint mapping multi-objective optimization operation data, and use the constraint mapping multi-objective optimization operation data as the high-temperature heat pump heat output optimization control reward function.

[0013] This specification provides a high-temperature heat pump heat output optimization control system based on autoregressive analysis, which is used to execute the high-temperature heat pump heat output optimization control method based on autoregressive analysis as described above. The high-temperature heat pump heat output optimization control system based on autoregressive analysis includes: A historical high-temperature heat pump control-operation analysis module is used to obtain historical high-temperature heat pump control parameters, historical high-temperature heat pump operation data, and historical high-temperature heat pump environmental parameters; perform historical high-temperature heat pump operation characteristic analysis based on historical high-temperature heat pump operation data to generate historical high-temperature heat pump operation characteristic data; map historical high-temperature heat pump control parameters to historical high-temperature heat pump operation characteristic data to perform correlation analysis of historical high-temperature heat pump control and operation characteristics to generate historical high-temperature heat pump control-operation data; A high-temperature heat pump characteristic analysis model establishment module is used to establish a high-temperature heat pump characteristic mapping relationship between control and operation based on historical high-temperature heat pump operation characteristic data to generate a high-temperature heat pump characteristic analysis model; A high-temperature heat pump environment operation disturbance analysis module is used to analyze the operation disturbance mode of the high-temperature heat pump environment according to historical high-temperature heat pump environment parameters and historical high-temperature heat pump operation data, and generate high-temperature heat pump environment operation disturbance mode data; based on the high-temperature heat pump environment operation disturbance mode data and historical high-temperature heat pump environment parameters, the operation disturbance characteristic analysis of the high-temperature heat pump environment is performed to generate high-temperature heat pump environment operation disturbance characteristic data; The high-temperature heat pump characteristic analysis model optimization module is used to adjust the model parameters of the high-temperature heat pump characteristic analysis model for environmental disturbance sensitivity based on the high-temperature heat pump environmental operation disturbance characteristic data, and generate an adjusted high-temperature heat pump characteristic analysis model; the historical high-temperature heat pump control-operation data is used to perform model error fitting optimization processing on the adjusted high-temperature heat pump characteristic analysis model, and generate an optimized high-temperature heat pump characteristic analysis model; The high-temperature heat pump heat output optimization control module is used to obtain the instant high-temperature heat pump heat output optimization demand decision and the instant high-temperature heat pump environmental parameters; based on the optimized high-temperature characteristic analysis model, the instant high-temperature heat pump heat output optimization demand decision and the instant high-temperature heat pump environmental parameters are analyzed to generate the high-temperature heat pump dynamic scheduling control parameters; the high-temperature heat pump heat output optimization control operation is performed through the high-temperature heat pump dynamic scheduling control parameters.

[0014] The beneficial effect of the present application is that by systematically acquiring the control parameters, operating data and environmental parameters of historical high-temperature heat pumps, and combining the monitoring and processing of distributed sensor networks, various types of data related to high-temperature heat pumps can be collected comprehensively and accurately. Through the analysis of the historical high-temperature heat pump control change sequence and window division processing, the change law of the control system under different working conditions can be effectively identified, thereby providing data support for the performance evaluation and optimization of high-temperature heat pumps. Correlating the control parameters with the operating characteristic data helps to deeply understand the influence of the control factors on the operating effect of the heat pump, and lays the foundation for establishing a more accurate control model and optimization strategy. Based on the historical high-temperature heat pump operating characteristic data, the characteristic mapping relationship between control and operation can be established, which can effectively construct a characteristic analysis model of the high-temperature heat pump. Using the autocorrelation function to analyze the operating characteristic data by autocorrelation order helps to accurately grasp the periodicity and trend characteristics during the operation of the heat pump, and then extract the key factors that have a greater impact on the performance of the heat pump. By mapping the relationship between these characteristics and the control parameters, the response characteristics of the high-temperature heat pump under different working conditions can be better reflected, thereby improving the accuracy and adaptability of the control strategy. In addition, the generation of the high-temperature heat pump characteristic analysis model can not only provide a theoretical basis for optimization control, but also support the system to make more flexible and efficient decisions when facing dynamically changing environmental conditions and load demands. By analyzing the environmental disturbance pattern of historical high-temperature heat pump environmental parameters and operating data, the influence of various environmental factors on the performance of the heat pump during the operation of the high-temperature heat pump can be identified and quantified. Through frequency domain data conversion and time-series frequency domain difference calculation, the dynamic change law of environmental parameters and their interference effect on the operation of high-temperature heat pumps can be further revealed, especially when the environmental factors change greatly. By analyzing the influence weight of the environmental parameter type of the disturbance pattern, the influence degree of each disturbance factor on the operation effect of the heat pump can be accurately determined, thereby providing data support for the control and compensation of environmental disturbances. The disturbance feature analysis is performed using the environmental frequency domain data after weighted fusion to comprehensively evaluate the influence characteristics of different environmental disturbances on the heat pump, providing higher accuracy and reliability for subsequent optimization control, improving the adaptability of high-temperature heat pumps to environmental changes, and providing strong technical support for improving their stability, reducing energy consumption and optimizing heat output. The environmental disturbance characteristic data of the high-temperature heat pump is combined with the characteristic analysis model to achieve precise adjustment of the dynamic response of the high-temperature heat pump under different environmental conditions. The interactive response coefficient analysis of environmental disturbance and operation characteristics using Sobol technology can deeply understand the complex interaction between environment and operation, reveal the degree of influence of different environmental disturbance factors on the performance of the heat pump, and thus help to accurately adjust the relevant parameters in the characteristic analysis model and improve the adaptability and stability of the heat pump system under complex environmental conditions. The historical high-temperature heat pump control-operation data is used to optimize the model error fitting to ensure the effectiveness of the model in practical applications.Through multiple rounds of optimization and adjustment, the generated optimization model can more accurately predict the performance of the heat pump under various working conditions, providing more reliable data support for subsequent control decisions. By dividing the heterogeneous operating state data and analyzing the error distribution characteristics, the differences in heat pump performance and the source of errors under different operating conditions can be identified, providing a basis for fine-tuning, improving the operating efficiency of the heat pump system under heterogeneous conditions, and making the heat pump system more efficient and reliable when facing complex environments and load changes. By obtaining the instant high-temperature heat pump heat output optimization demand decision and environmental parameters, and combining the optimized high-temperature heat pump characteristic analysis model, the dynamic scheduling control parameters of the high-temperature heat pump can be analyzed in real time. This process ensures that the heat pump can continue to maintain efficient and stable operation under changing environmental conditions. By designing the high-temperature heat pump heat output optimization control reward function, the multi-objective optimization operation data of the heat pump system can be combined with the operating constraints, so that the control decision can meet the performance requirements while minimizing the operating cost and avoiding risks such as overload. This process realizes the refined management of the heat pump operation and optimizes the efficiency of resource use. The real-time environmental parameters are transmitted to the optimized high-temperature characteristic analysis model for environmental response optimization processing. The control parameters can be adjusted according to the current environmental conditions, so that the heat pump can quickly respond to changes in the external environment during actual operation. This dynamic scheduling mechanism not only improves the adaptability and flexibility of the heat pump system, but also provides guarantees for energy conservation and system reliability. It ensures that the heat pump system can continuously and stably optimize heat output control in a complex and changing environment, thereby optimizing the use of heat energy and ensuring the long-term and efficient operation of the equipment.

[0015] Therefore, the high-temperature heat pump heat output optimization control method based on autoregressive analysis of the present invention can construct a high-precision high-temperature heat pump characteristic analysis model based on the historical operating data and environmental parameters of the high-temperature heat pump by introducing the autoregressive analysis method, and through data-driven optimization adjustment and error fitting processing, the prediction accuracy of the model and the accuracy of operation control are greatly improved, and the dynamic changes of high-temperature heat pump control and high-temperature heat pump operating characteristics and environmental disturbances are accurately captured, and efficient energy allocation is carried out according to immediate needs, which effectively solves the problem of insufficient control accuracy of existing control methods under complex working conditions, so that the high-temperature heat pump can maintain stable and efficient operating performance under complex and changeable environmental conditions. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 It is a schematic diagram of the steps of the high-temperature heat pump heat output optimization control method based on autoregressive analysis of the present invention; Figure 2 for Figure 1 Detailed implementation steps of step S3 in FIG. Figure 3 for Figure 1Detailed implementation steps of step S4 in FIG. The realization of the purpose, functional features and advantages of the present invention will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0017] The technical method of the present invention is described clearly and completely below in conjunction with the accompanying drawings. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by technicians in this field without creative work are within the scope of protection of the present invention.

[0018] In addition, the accompanying drawings are only schematic illustrations of the present invention and are not necessarily drawn to scale. The same reference numerals in the figures represent the same or similar parts, and their repeated description will be omitted. Some of the block diagrams shown in the accompanying drawings are functional entities and do not necessarily correspond to physically or logically independent entities. The functional entities can be implemented in software form, or implemented in one or more hardware modules or integrated circuits, or implemented in different networks and / or processor methods and / or microcontroller methods.

[0019] It should be understood that, although the terms "first", "second", etc. may be used here to describe various units, these units should not be limited by these terms. These terms are used only to distinguish one unit from another unit. Without departing from the scope of the exemplary embodiments, the first unit may be referred to as the second unit, and similarly the second unit may be referred to as the first unit. The term "and / or" used herein includes any and all combinations of one or more of the listed associated items.

[0020] To achieve this, please refer to Figures 1 to 3 The present invention provides a high-temperature heat pump heat output optimization control method based on autoregressive analysis. In the embodiment of the present invention, please refer to Figure 1 FIG. 1 is a schematic diagram of the steps of the high-temperature heat pump heat output optimization control method based on autoregressive analysis of the present invention. The high-temperature heat pump heat output optimization control method based on autoregressive analysis includes the following steps: Step S1: Obtain historical high-temperature heat pump control parameters, historical high-temperature heat pump operation data, and historical high-temperature heat pump environmental parameters; perform historical high-temperature heat pump operation characteristic analysis based on the historical high-temperature heat pump operation data to generate historical high-temperature heat pump operation characteristic data; map the historical high-temperature heat pump control parameters to the historical high-temperature heat pump operation characteristic data to perform correlation analysis on the control and operation characteristics of the historical high-temperature heat pump to generate historical high-temperature heat pump control-operation data; In an embodiment of the present invention, the data interface authority of the high-temperature heat pump control system is obtained, and the historical high-temperature heat pump control parameters are collected through the data interface authority. By deploying multiple temperature, pressure and humidity sensors at different locations of the high-temperature heat pump equipment, real-time operation data and environmental data are collected. For example, the sensor network can be installed at the inlet and outlet, compressor, evaporator and condenser of the high-temperature heat pump to monitor parameters such as temperature, pressure and flow in real time. In addition, sensors can also be arranged in the surrounding environment to monitor environmental parameters such as outdoor air temperature, humidity and pressure. Through the continuous monitoring of these sensors, all-round data including equipment status, environmental conditions and energy consumption can be collected, thereby providing basic data for subsequent analysis. And the historical high-temperature heat pump control parameters, historical high-temperature heat pump operation data and historical high-temperature heat pump environmental parameters are aligned according to the timestamp. By performing a time series window analysis on the historical control parameters of the high-temperature heat pump (for example, temperature setting value, compressor start and stop status, power output, etc.), it is divided into multiple time periods or windows for analysis. If the historical control parameters include the on / off status of the compressor and the temperature setting value changes within a certain time period, these parameters can be gradually expanded in multiple time series windows, and the control change trends within different time periods can be better extracted through windowing. Combine historical operation data (such as temperature, pressure, power consumption, etc.) with the control change time series window to divide the operation data. For example, when there are control parameter changes (such as temperature setting value adjustment or compressor start / stop), the operation data of the time period corresponding to these changes are separated by the window division method. According to different control behaviors, the corresponding operation data patterns are extracted, and then the operation efficiency, response speed and energy consumption of the heat pump system under different control strategies are analyzed. The operation characteristics of each window of the historical high-temperature heat pump operation window data are analyzed and processed to generate historical high-temperature heat pump operation characteristic data. The historical high-temperature heat pump control parameters are mapped to the historical high-temperature heat pump operation characteristic data for correlation analysis to generate historical high-temperature heat pump control-operation data. The control parameters of the historical high-temperature heat pump are correlated with the operation characteristic data to explore how the control parameters affect the system's operation performance. The correlation between the control parameters and the operation characteristics is analyzed by machine learning technology to identify the impact of the control strategy on the performance of the heat pump. For example, the random forest algorithm can be used to identify the complex nonlinear relationship between control parameters and operating characteristics through the integration of multiple decision trees.

[0021] Step S2: establishing a high-temperature heat pump characteristic mapping relationship between control and operation based on historical high-temperature heat pump operation characteristic data to generate a high-temperature heat pump characteristic analysis model; In an embodiment of the present invention, the autocorrelation function of the high-temperature heat pump is calculated based on the historical operating characteristic data (such as temperature, pressure, power consumption, etc.). The autocorrelation function is used to measure the correlation between the time series data and its own delay value. The autocorrelation order is used to characterize the autocorrelation of the data at different time lags, that is, the autocorrelation order is calculated to analyze the change of the time series of the high-temperature heat pump equipment under the control-operation state. The autocorrelation order refers to the maximum lag value in the data sequence where the autocorrelation value is significantly greater than 0. The mapping relationship between the heat pump control parameters and the operating characteristics is established using the heat pump operating characteristic autocorrelation order data. The mapping relationship can be achieved through a machine learning model (such as linear regression, support vector machine, neural network, etc.) to generate a high-temperature heat pump characteristic analysis model. The autocorrelation order is used as one of the input features, and other parameters that affect the operating performance of the heat pump (such as temperature setting value, heating power, etc.) are also used as input features. The output target is the operating characteristic data of the heat pump (such as energy efficiency, temperature fluctuation range, etc.). Select a suitable machine learning model to fit the relationship between the control parameters and the operating characteristics. For example, polynomial regression is used to fit nonlinear relationships, or support vector machine regression is used to process high-dimensional, nonlinear data. On this basis, control parameters (such as temperature setting and heating power) are mapped with operating characteristic data (such as temperature and energy efficiency) to combine historical control parameters with corresponding operating characteristic data, further refine the mapping relationship between control and operation, and reflect the impact of different control strategies (such as temperature setting and heating power) on operation.

[0022] Step S3: performing an operation disturbance mode analysis of the high-temperature heat pump environment according to historical high-temperature heat pump environmental parameters and historical high-temperature heat pump operating data, and generating high-temperature heat pump environment operation disturbance mode data; performing an operation disturbance feature analysis of the high-temperature heat pump environment based on the high-temperature heat pump environment operation disturbance mode data and historical high-temperature heat pump environmental parameters, and generating high-temperature heat pump environment operation disturbance feature data; In an embodiment of the present invention, historical high-temperature heat pump environmental parameters (such as temperature, humidity, external pressure, etc.) and operating data (such as energy efficiency, load, heat output, etc.) are obtained. These data are used to analyze environmental disturbance patterns. The process includes the following implementation steps: Collect environmental parameter data and operating data from the sensor network over a period of time in the past. Analyze the collected environmental parameters and operating data to identify disturbance patterns that occur in the heat pump system under specific conditions. The disturbance pattern is caused by sudden environmental changes (such as drastic temperature fluctuations) or equipment performance fluctuations (such as reduced compressor efficiency). Classify the disturbances in the historical data and divide them into different types of disturbance patterns. Each type of disturbance pattern will record its impact characteristics on the operation of the system to generate operational disturbance pattern data of the high-temperature heat pump environment. Fast Fourier transform (FFT) is used to perform frequency domain conversion processing on historical high-temperature heat pump environmental parameters (such as temperature, humidity, etc.). Assume that data is collected every minute for a continuous period of 1 hour during the data collection process, and a total of 60 data points are collected. By performing FFT conversion on these 60 data points, the time domain data is converted into frequency domain data. In the frequency domain, the frequency components of periodic changes can be identified, such as certain environmental factors that repeatedly fluctuate at a specific frequency. The frequency domain data will be displayed as different frequency components and their corresponding amplitudes, thereby revealing the periodic characteristics of environmental disturbances. Based on the historical high-temperature heat pump environment frequency domain data, the time series frequency domain difference calculation is performed for each type of environmental parameter. For example, assuming that the frequency domain data of temperature is A, and the frequency domain data of temperature after time series t is B, the difference between the two frequency domain data at time t is calculated respectively. Quantify the difference in the impact of different environmental parameters on the operation of the heat pump under time series time changes, and generate time series frequency domain difference data. Using the regression analysis method, the high-temperature heat pump environment operation disturbance mode data is combined with the heat pump environment time series frequency domain difference data, and the weight analysis of the impact of environmental parameter types under different disturbance modes is performed. And the corresponding temperature environment impact parameters and humidity environment impact parameters are assigned accordingly. This process is calculated by a weighted regression model, which is used to quantify the relative influence of different environmental factors under each disturbance mode. According to the weight coefficient of the disturbance mode environmental parameter type, the historical high-temperature heat pump environment frequency domain data is weighted fused. For example, it is assumed that the weight coefficients corresponding to the historical temperature frequency domain data and humidity frequency domain data are weighted fused to evaluate the impact of the overall environmental parameters on the operation of the high-temperature heat pump and generate historical high-temperature heat pump environmental frequency domain fusion data. Combining the historical high-temperature heat pump operation data with the historical high-temperature heat pump environmental frequency domain fusion data, the time series analysis method is used to analyze the environmental disturbance characteristics. By using the relationship between the performance parameters (such as output power, COP, etc.) in the high-temperature heat pump operation data and the environmental frequency domain fusion data, by analyzing the relationship between the environmental frequency domain fusion data and the historical operation data, key disturbance characteristics are identified, such as the start-up delay of the heat pump when the temperature changes greatly, and the change in the energy efficiency of the heat pump when the humidity fluctuates greatly.Find out the specific impact of environmental parameters on the performance of heat pumps. For example, use supervised learning algorithms to analyze the impact characteristics of environmental frequency domain fusion data on the output power of heat pumps, that is, by evaluating the specific numerical impact characteristics of the set heat pump operation under ideal conditions or various environmental impact conditions. For example, through the historical high-temperature heat pump environmental frequency domain fusion data, the ambient temperature is A, the humidity is B, etc., and the corresponding numerical impact characteristics of the historical high-temperature heat pump operation data are analyzed. The generated high-temperature heat pump environmental operation disturbance characteristic data includes indicators such as the operating efficiency, stability, and energy consumption of the heat pump under different environmental disturbance modes.

[0023] Step S4: Based on the high-temperature heat pump environmental operation disturbance characteristic data, the model parameter adjustment processing of the high-temperature heat pump characteristic analysis model is performed to the environmental disturbance sensitivity, and the adjusted high-temperature heat pump characteristic analysis model is generated; the model error fitting optimization processing of the adjusted high-temperature heat pump characteristic analysis model is performed using the historical high-temperature heat pump control-operation data, and the optimized high-temperature heat pump characteristic analysis model is generated; In the embodiment of the present invention, the Sobol sensitivity analysis method is adopted. Through the high-temperature heat pump environmental operation disturbance characteristic data corresponding to each high-temperature heat pump environmental operation disturbance mode, that is, the corresponding characteristics of the sensitivity values ​​of environmental parameters to the high-temperature heat pump operation under each environmental disturbance mode, the Sobol method decomposes the variance of the system output and attributes the output change to the change of different input parameters. The Sobol method is used to quantify the relationship between environmental disturbance parameters (such as temperature fluctuations, humidity changes, etc.) and the output variables of the high-temperature heat pump (such as heat output, system efficiency, etc.), and the output variance is decomposed according to the input changes of each environmental parameter to generate the environment-operation interaction response coefficient. Through the Sobol method analysis, the interaction response coefficient between the environmental parameters and the high-temperature heat pump operation data under each disturbance mode is obtained. Using the high-temperature heat pump environment-operation disturbance interaction response coefficient, these coefficients are input into the initial high-temperature heat pump characteristic analysis model. The model contains a set of core parameters for simulating the operation characteristics of the heat pump, including the heat output function of the heat pump, the system energy efficiency ratio, the compressor operating frequency, the refrigerant flow adjustment coefficient, etc. For each environmental disturbance parameter (such as temperature, humidity, and pressure), the sensitivity of the relevant parameters in the model is evaluated in combination with the corresponding disturbance response coefficient. For example, the response sensitivity of the compressor frequency to temperature disturbance is tested in the model. If the response coefficient of the temperature disturbance is high, it means that the compressor frequency has a greater impact on the temperature change. The sensitive parameters are dynamically adjusted according to the environmental disturbance response coefficient. The weight of the temperature input factor in the heat output function of the heat pump is adjusted to match the response coefficient, that is, the temperature-related weight in the function is increased. The humidity adjustment parameters in the energy efficiency calculation model are optimized to make it more sensitive to changes under the disturbance conditions of temperature and humidity. The adjusted model is verified by historical operation data. If the output error of the adjusted model is significantly reduced, the adjustment is determined to be successful. The final generated adjustment high-temperature heat pump characteristic analysis model can provide more accurate operation characteristic simulation under complex environmental disturbances, providing basic support for subsequent optimization control. By performing error fitting processing on the historical high-temperature heat pump control-operation data, the characteristic analysis model is optimized to further improve the accuracy and reliability of the model. The historical high-temperature heat pump control-operation data is obtained, including historical control parameters and operation status data. These data represent the actual operating performance of the high-temperature heat pump under different environmental conditions. Calculate the overall error distribution and divide it according to the error subtype of each operating state to obtain the distribution of each error. Optimize and adjust the model parameters through the least squares method to reduce the error value, such as optimizing the temperature and pressure response coefficients in the heat output function. According to the results of the error fitting, optimize the parameters in the model. For example, if the output heat predicted by the model is significantly different from the actual heat, adjust the heat output function, efficiency coefficient and other parameters in the model to reduce the error. Through repeated optimization and error fitting processing, the final optimized high-temperature heat pump characteristic analysis model is generated.The optimized model can more accurately reflect the actual operating conditions and provide more precise predictions in future control decisions.

[0024] Step S5: Obtain the instant high-temperature heat pump heat output optimization demand decision and the instant high-temperature heat pump environmental parameters; perform high-temperature heat pump dynamic scheduling control parameter analysis on the instant high-temperature heat pump heat output optimization demand decision and the instant high-temperature heat pump environmental parameters based on the optimized high-temperature characteristic analysis model, and generate high-temperature heat pump dynamic scheduling control parameters; perform high-temperature heat pump heat output optimization control operations through the high-temperature heat pump dynamic scheduling control parameters.

[0025] In an embodiment of the present invention, the heat output demand of the high-temperature heat pump system is determined, and the demand is usually determined by the external load demand or the energy efficiency optimization target of the system. The immediate heat output demand is generated by using the external temperature, humidity, load demand and internal control strategy. When the external environment temperature is low and the load demand is high, the system automatically adjusts the demand and increases the heat output. At this time, through the demand decision algorithm or model, the system determines whether it is necessary to increase the heat output or adjust the control strategy through real-time data. Generate an immediate high-temperature heat pump heat output optimization demand decision. The high-temperature heat pump equipment is monitored for environmental parameters based on a distributed sensor network. Real-time data is collected by sensors installed at key positions to obtain environmental parameters of the high-temperature heat pump equipment. According to the immediate high-temperature heat pump heat output optimization demand decision, a high-temperature heat pump heat output optimization control reward function is designed, which guides the optimization process by quantifying the relationship between the demand decision and the heat pump operation target. According to the heat output optimization demand decision, multiple control targets are defined, such as minimizing energy consumption, maximizing heat output, etc. When designing the control reward function, the weight of each target is taken into account to construct a multi-objective optimization model. When the demand decision is a higher heat output, the system's reward function will give a higher heat output weight while suppressing the increase in energy consumption. Through the relationship between the reward function and the control target, the system can adjust the operation strategy in real time to achieve the optimal heat output effect. Using the real-time high-temperature heat pump environmental parameters, the environmental response processing is performed based on the optimized high-temperature characteristic analysis model, and the dynamic scheduling control parameters are generated. The transmitted environmental parameters are input into the optimized high-temperature characteristic analysis model, which can respond to the current environmental conditions and obtain the best operation strategy to adapt to the environment. The model analyzes the real-time environmental data, predicts the response of the system under different environmental conditions, and generates dynamic scheduling control parameters of high-temperature heat pumps that adapt to the environment. According to the results of the environmental response analysis and the optimization of the control reward function, the final dynamic scheduling control parameters of the high-temperature heat pump are generated. The dynamic scheduling control parameters of the high-temperature heat pump are used to perform heat output optimization control. The control system directly adjusts the operating state of the high-temperature heat pump equipment according to the optimized scheduling parameters. By changing the control variables such as the compressor speed and heat exchanger flow of the equipment, the heat output can be accurately adjusted. If the dynamic scheduling parameters show high load demand, the system will adjust the equipment to a higher output level, and when the demand is low, it will automatically reduce the output power and optimize the energy efficiency. Ensure that the high-temperature heat pump can operate stably under various environmental conditions and achieve the goal of heat output optimization.

[0026] Further, step S1 includes the following steps: Step S11: acquiring historical high-temperature heat pump control parameters of the high-temperature heat pump control system, and monitoring and processing historical high-temperature heat pump operation and historical high-temperature heat pump environmental parameters of the high-temperature heat pump equipment through a distributed sensor network, so as to obtain historical high-temperature heat pump operation data and historical high-temperature heat pump environmental parameters; Step S12: performing historical high-temperature heat pump control change timing window analysis according to historical high-temperature heat pump control parameters to generate historical high-temperature heat pump control change timing window data; Step S13: using the historical high-temperature heat pump control change timing window to perform historical high-temperature heat pump window division processing on the historical high-temperature heat pump operation data to obtain historical high-temperature heat pump operation window data; Step S14: Analyze and process the operation characteristics of each window of the historical high-temperature heat pump operation window data to generate historical high-temperature heat pump operation characteristic data; Step S15: Mapping historical high-temperature heat pump control parameters to historical high-temperature heat pump operation characteristic data to perform correlation analysis between the control and operation characteristics of the historical high-temperature heat pump, and generating historical high-temperature heat pump control-operation data.

[0027] In an embodiment of the present invention, the data interface authority of the high-temperature heat pump control system is obtained, and the historical high-temperature heat pump control parameters are collected through the data interface authority. By deploying multiple temperature, pressure and humidity sensors at different locations of the high-temperature heat pump equipment, real-time operation data and environmental data are collected. For example, the sensor network can be installed at the inlet and outlet, compressor, evaporator and condenser of the high-temperature heat pump to monitor parameters such as temperature, pressure and flow in real time. In addition, sensors can also be arranged in the surrounding environment to monitor environmental parameters such as outdoor air temperature, humidity and pressure. Through the continuous monitoring of these sensors, all-round data including equipment status, environmental conditions and energy consumption can be collected, thereby providing basic data for subsequent analysis. And the historical high-temperature heat pump control parameters, historical high-temperature heat pump operation data and historical high-temperature heat pump environmental parameters are aligned according to the timestamp. By performing a time series window analysis on the historical control parameters of the high-temperature heat pump (for example, temperature setting value, compressor start and stop status, power output, etc.), it is divided into multiple time periods or windows for analysis. If the historical control parameters include the switch state of the compressor and the temperature setting value changes in a certain time period, these parameters can be gradually expanded in multiple time series windows, and the control change trends in different time periods can be better extracted through windowing. For example, if the compressor starts and stops frequently in a certain period of time, the impact on system stability and energy consumption can be identified through time series analysis, thereby providing a basis for model optimization. Combine historical operating data (such as temperature, pressure, power consumption, etc.) with the control change time series window to divide the operating data. For example, when there are control parameter changes (such as temperature setting value adjustment or compressor start / stop), the operating data of the time period corresponding to these changes are separated by the window division method. In this way, the corresponding operating data mode can be extracted according to different control behaviors, and then the operating efficiency, response speed and energy consumption of the heat pump system under different control strategies can be analyzed. For example, if the temperature setting value changes frequently in a certain period of time, then after dividing the operating data in this period of time, the working efficiency change of the heat pump under the control change in this period can be analyzed. The operating characteristics of each window of the historical high-temperature heat pump operation window data are analyzed and processed to generate historical high-temperature heat pump operation characteristic data. The key goal is to extract the operating characteristics in each divided window and evaluate the performance of the system under different control conditions. For each operating window, features can be extracted through statistical analysis methods (such as mean, variance, peak, etc.) or signal processing techniques (such as spectrum analysis). For example, assuming that in a certain window, the temperature fluctuation range is [40°C, 55°C]. By calculating the temperature mean and standard deviation during this period (for example, the mean is 48°C and the standard deviation is 3°C), the operating stability during this period can be evaluated. If the standard deviation is large, it means that there are large fluctuations in the window and the control strategy needs to be adjusted.Assuming that the power consumption data of the heat pump is [10 kW, 15kW] during this time period, the energy efficiency of the system can be evaluated by calculating the average power consumption and the maximum power value. For example, the average power is 12kW and the maximum power is 15 kW. If the fluctuation of power consumption is too large, it means that the system needs to be optimized and controlled to improve the operating efficiency. And analyze the response time characteristics of the heat pump during this period. If the amplitude of the signal is too high during a certain period of time, it indicates that the heat pump system responds slowly or excessively to external disturbances. Through these feature analyses, historical operating characteristic data of each window can be generated to reflect the performance of the heat pump under different control and environmental conditions, providing valuable information for subsequent correlation analysis. The historical high-temperature heat pump control parameters are mapped to the historical high-temperature heat pump operation characteristic data for correlation analysis to generate historical high-temperature heat pump control-operation data. The control parameters of the historical high-temperature heat pump are correlated with the operation characteristic data to explore how the control parameters affect the system's operating performance. The correlation between the control parameters and the operation characteristics is analyzed by machine learning technology to identify the impact of the control strategy on the performance of the heat pump. Temperature setpoint (such as the set temperature is 45°C), compressor start and stop status (such as start and stop status is 0 and 1, 0 means stop, 1 means start), heating power (such as 10 kW). Temperature fluctuation range, energy efficiency (such as average power consumption) and system stability (such as standard deviation). Using the random forest algorithm, through the integration of multiple decision trees, the complex nonlinear relationship between control parameters and operating characteristics is identified. For example, the random forest model found that when the temperature setpoint reaches 45°C, the energy efficiency of the heat pump is the highest, and when the compressor is frequently started and stopped, the energy efficiency of the system will decrease.

[0028] Further, step S2 includes the following steps: Step S21: using a preset autocorrelation function to perform autocorrelation order analysis of the heat pump operation characteristics on the historical high-temperature heat pump operation characteristic data to generate the heat pump operation characteristic autocorrelation order; Step S22: establishing a mapping relationship between control and operation of high-temperature heat pump characteristics through the autocorrelation order of heat pump operation characteristics to generate a high-temperature heat pump characteristic analysis model.

[0029] In an embodiment of the present invention, the autocorrelation function of the high-temperature heat pump is calculated based on the historical operating characteristic data (such as temperature, pressure, power consumption, etc.). The autocorrelation function is used to measure the correlation between the time series data and its own delay value. The autocorrelation order is used to characterize the autocorrelation of the data at different time lags. Assume that there is a period of historical high-temperature heat pump operation data, represented as a time series [x1, x2, ..., xn], where each [x1, x2, ..., xn] represents the system characteristic data (such as temperature value, pressure value, etc.) at a certain moment. For this data sequence, the autocorrelation function (ACF, Autocorrelation Function) is used for calculation. The autocorrelation order is determined by calculating the autocorrelation values ​​at different lags. The autocorrelation order refers to the maximum lag value in the data sequence where the autocorrelation value is significantly greater than 0. For example, if the autocorrelation value is still significant at a lag of 3, it means that the moment has a strong correlation with the value 3 time points ago, so its autocorrelation order is 3. Assuming that the autocorrelation function of the temperature data in a certain period is calculated to be [0.9, 0.8, 0.7, 0.6, 0.5, 0.3], it can be observed that at a lag of 3, the autocorrelation value begins to drop significantly to 0.6, indicating that the autocorrelation order is 3. Using the autocorrelation order data of the heat pump operation characteristics, the mapping relationship between the heat pump control parameters and the operation characteristics is established. This mapping relationship can be achieved through machine learning models (such as linear regression, support vector machine, neural network, etc.) to generate a high-temperature heat pump characteristic analysis model. The autocorrelation order is used as one of the input features, and other parameters that affect the operation performance of the heat pump (such as temperature set point, heating power, etc.) are also used as input features. The output target is the operation characteristic data of the heat pump (such as energy efficiency, temperature fluctuation range, etc.). Select a suitable machine learning model to fit the relationship between the control parameters and the operation characteristics. For example, use polynomial regression to fit nonlinear relationships, or use support vector machine regression to process high-dimensional, nonlinear data. On this basis, control parameters (such as temperature setting and heating power) are mapped with operating characteristic data (such as temperature and energy efficiency) to combine historical control parameters with corresponding operating characteristic data, further refine the mapping relationship between control and operation, and reflect the impact of different control strategies (such as temperature setting and heating power) on operation.

[0030] Further, as an embodiment of the present invention, refer to Figure 2 As shown, Figure 1 Detailed step flow diagram of step S3 in the embodiment, step S3 includes the following steps: Step S31: performing an operation disturbance mode analysis of the high-temperature heat pump environment according to historical high-temperature heat pump environmental parameters and historical high-temperature heat pump operation data, and generating high-temperature heat pump environment operation disturbance mode data; In an embodiment of the present invention, historical high-temperature heat pump environmental parameters (such as temperature, humidity, external pressure, etc.) and operating data (such as energy efficiency, load, heat output, etc.) are obtained. These data are used to analyze environmental disturbance patterns. The process includes the following implementation steps: Collect environmental parameter data and operating data from the sensor network over a period of time. For example, the historical temperature data is [44.5°C, 45.0°C, 45.2°C, 44.8°C], and the operating data is [12 kW, 11.8 kW, 12.1 kW], etc. Analyze the collected environmental parameters and operating data to identify the disturbance patterns that occur in the heat pump system under specific conditions. The disturbance pattern is caused by sudden environmental changes (such as drastic temperature fluctuations) or equipment performance fluctuations (such as reduced compressor efficiency). For example, when the ambient temperature changes by more than 3°C, it will cause a significant change in the heat pump load, thereby generating a disturbance pattern. The disturbances in the historical data are classified into different disturbance pattern types, and each disturbance pattern type will record its impact characteristics on the system operation. Generates operational disturbance mode data for a high temperature heat pump environment, such as maintaining the temperature above 45°C as the system load increases, or decreasing the temperature below 44°C as the system load decreases.

[0031] Step S32: performing frequency domain data conversion processing on historical high-temperature heat pump environmental parameters to generate historical high-temperature heat pump environmental frequency domain data; In an embodiment of the present invention, a fast Fourier transform (FFT) is used to perform frequency domain conversion processing on historical high-temperature heat pump environmental parameters (such as temperature, humidity, etc.). Assume that data is collected every minute for 1 hour continuously during the data collection process, and a total of 60 data points are collected. By performing FFT conversion on these 60 data points, the time domain data is converted into frequency domain data. In the frequency domain, periodically changing frequency components can be identified, such as certain environmental factors that repeatedly fluctuate at a specific frequency. The frequency domain data will be displayed as different frequency components and their corresponding amplitudes, thereby revealing the periodic characteristics of environmental disturbances.

[0032] Step S33: performing time series frequency domain data difference calculation of each environmental parameter type according to historical high temperature heat pump environment frequency domain data to generate heat pump environment time series frequency domain difference data; In an embodiment of the present invention, based on the historical high-temperature heat pump environmental frequency domain data, the time series frequency domain difference calculation is performed for each type of environmental parameter. For example, assuming that the frequency domain data of the temperature is A, and the frequency domain data of the temperature after the time series t is B, the difference between the two frequency domain data at time t is calculated respectively. The difference in the impact of different environmental parameters on the operation of the heat pump under the time series time change is quantified, and the time series frequency domain difference data is generated. These difference data reflect the changing trend of the environmental disturbance mode and are helpful for the subsequent disturbance mode impact analysis.

[0033] Step S34: performing an environmental parameter type influence weight analysis of each disturbance mode on the heat pump environment time series frequency domain difference data through the high-temperature heat pump environment operation disturbance mode data, and generating a disturbance mode environmental parameter type weight coefficient; In an embodiment of the present invention, a regression analysis method is used to combine the high-temperature heat pump environment operation disturbance mode data with the heat pump environment time-series frequency domain difference data, and a weight analysis is performed on the impact of environmental parameter types under different disturbance modes. "High temperature disturbance mode" and "humidity fluctuation disturbance mode" are selected as analysis objects, and their impact coefficients on the operation of the heat pump are calculated. For example, if the impact of the "high temperature disturbance mode" on the heat pump efficiency is 0.7, and the impact of the "humidity fluctuation disturbance mode" on the efficiency is 0.3, then the environmental parameter weight coefficients of the disturbance mode are obtained as 0.7 and 0.3, and are correspondingly allocated to the corresponding temperature environment impact parameters and humidity environment impact parameters. This process is calculated through a weighted regression model, which is used to quantify the relative influence of different environmental factors under each disturbance mode.

[0034] Step S35: using the disturbance mode environmental parameter type weight coefficient to perform environmental type parameter weighted fusion processing on the historical high-temperature heat pump environmental frequency domain data to generate historical high-temperature heat pump environmental frequency domain fusion data; In the embodiment of the present invention, the historical high-temperature heat pump environment frequency domain data is weighted and fused according to the weight coefficient of the disturbance mode environment parameter type. For example, it is assumed that the weight coefficients corresponding to the historical temperature frequency domain data and the humidity frequency domain data are weighted and fused to evaluate the impact of the overall environment parameters on the operation of the high-temperature heat pump and generate the historical high-temperature heat pump environment frequency domain fusion data.

[0035] Step S36: Based on the historical high-temperature heat pump operation data and the historical high-temperature heat pump environment frequency domain fusion data, the operation disturbance characteristic analysis of the high-temperature heat pump environment is performed to generate the high-temperature heat pump environment operation disturbance characteristic data.

[0036] In the embodiment of the present invention, the historical high-temperature heat pump operation data and the historical high-temperature heat pump environmental frequency domain fusion data are combined to use the time series analysis method to analyze the environmental disturbance characteristics. By using the relationship between the performance parameters (such as output power, COP, etc.) in the high-temperature heat pump operation data and the environmental frequency domain fusion data, the key disturbance characteristics are identified by analyzing the relationship between the environmental frequency domain fusion data and the historical operation data, such as the start-up delay of the heat pump under the condition of large temperature changes, the change of heat pump energy efficiency under the condition of large humidity fluctuations, etc. Find out the specific impact of environmental parameters on the performance of the heat pump, for example, use the supervised learning algorithm to analyze the impact characteristics of the environmental frequency domain fusion data on the output power of the heat pump, that is, by evaluating the specific numerical impact characteristics of the set heat pump operation under the ideal state or each environmental impact state, such as the environmental temperature of the historical high-temperature heat pump environmental frequency domain fusion data is A, the humidity is B, etc., and the corresponding historical high-temperature heat pump operation data is analyzed. The generated high-temperature heat pump environmental operation disturbance characteristic data includes the operating efficiency, stability, energy consumption and other indicators of the heat pump under different environmental disturbance modes.

[0037] Further, as an embodiment of the present invention, refer to Figure 3 As shown, Figure 1 Detailed step flow diagram of step S4 in FIG. 1 , in this embodiment, step S4 includes the following steps: Step S41: using the Sobol technology to analyze the high-temperature heat pump environment operation disturbance mode data and the high-temperature heat pump environment operation disturbance characteristic data, and generate the high-temperature heat pump environment-operation disturbance interaction response coefficient; In the embodiment of the present invention, the Sobol sensitivity analysis method is adopted. Through the high-temperature heat pump environmental operation disturbance characteristic data corresponding to each high-temperature heat pump environmental operation disturbance mode, that is, the corresponding characteristics of the sensitivity values ​​of environmental parameters to the high-temperature heat pump operation under each environmental disturbance mode, the Sobol method decomposes the variance of the system output and attributes the output change to the change of different input parameters. The Sobol method is used to quantify the relationship between environmental disturbance parameters (such as temperature fluctuations, humidity changes, etc.) and the output variables of the high-temperature heat pump (such as heat output, system efficiency, etc.). The output variance is decomposed according to the input changes of each environmental parameter to generate the environment-operation interaction response coefficient. Through the Sobol method analysis, the interaction response coefficient between the environmental parameters and the high-temperature heat pump operation data under each disturbance mode is obtained. Through the Sobol sensitivity analysis method, the relationship between the environmental disturbance parameters (such as temperature T, humidity H, air pressure P, etc.) under different high-temperature heat pump environmental operation disturbance mode data and the output variables of the heat pump (such as heat output Q, system efficiency U) is quantified. The Sobol method decomposes the variance of the system output to obtain the contribution of each environmental disturbance parameter (i.e., the partial attribution of the variance) and the impact of the interaction between environmental disturbance modes on the system output. For the heat pump output variable (such as Q or U), the contribution of the change of each environmental disturbance parameter to the system output variance is calculated through multiple experimental simulations or simulations.

[0038] Step S42: using the high-temperature heat pump environment-operation disturbance response coefficient to adjust the model parameters of the high-temperature heat pump characteristic analysis model for environmental disturbance sensitivity, and generating an adjusted high-temperature heat pump characteristic analysis model; In an embodiment of the present invention, the high-temperature heat pump environment-operation disturbance interaction response coefficients are used to input these coefficients into the initial high-temperature heat pump characteristic analysis model. The model contains a set of core parameters for simulating the operating characteristics of the heat pump, including the heat output function of the heat pump, the system energy efficiency ratio, the compressor operating frequency, the refrigerant flow adjustment coefficient, etc. For each environmental disturbance parameter (such as temperature, humidity, pressure), combined with the corresponding disturbance response coefficient, the sensitivity of the relevant parameters in the model is evaluated. For example, the response sensitivity of the compressor frequency to the temperature disturbance is tested in the model. If the response coefficient of the temperature disturbance is high, it means that the compressor frequency has a greater impact on the temperature change. The sensitive parameters are dynamically adjusted according to the environmental disturbance response coefficient. The weight of the temperature input factor in the heat output function of the heat pump is adjusted to match the response coefficient, that is, the temperature-related weight in the function is increased. The humidity adjustment parameters in the energy efficiency calculation model are optimized, for example, the refrigerant flow distribution curve is redistributed to adapt to the humidity change response. The compressor frequency adjustment formula is optimized to respond more sensitively to changes under the disturbance conditions of temperature and humidity. The adjusted model is verified by historical operating data, for example, by comparing the model prediction output before and after the adjustment with the actual operating data to verify the accuracy of the optimized model under different environmental disturbance conditions. If the output error of the adjusted model is significantly reduced, the adjustment is considered successful. The final generated adjustment high-temperature heat pump characteristic analysis model can provide more accurate operation characteristic simulation under complex environmental disturbances, providing basic support for subsequent optimization control.

[0039] Step S43: Utilizing historical high-temperature heat pump control-operation data, the high-temperature heat pump characteristic analysis model is subjected to model error fitting optimization processing to generate an optimized high-temperature heat pump characteristic analysis model.

[0040] In an embodiment of the present invention, the historical high-temperature heat pump control-operation data is subjected to error fitting processing to optimize the characteristic analysis model, thereby further improving the accuracy and reliability of the model. The historical high-temperature heat pump control-operation data is obtained, including historical control parameters and operation status data. These data represent the actual operation performance of the high-temperature heat pump under different environmental conditions. For example, the output value of the adjustment model is compared with the historical data by using multiple linear regression to calculate the error between the actual output heat and the model predicted output. Assuming that the actual output heat in a certain set of data is 12kW, and the model predicted value is 10.8kW, the error is 1.2kW, and the overall error distribution is calculated in this way, and the error subtypes of each operating state are divided to obtain the distribution of each error. The model parameters are optimized and adjusted by the least squares method to reduce the error value, such as optimizing the temperature and pressure response coefficients in the heat output function. According to the results of the error fitting, the parameters in the model are optimized. For example, if the output heat predicted by the model differs greatly from the actual heat, the heat output function, efficiency coefficient and other parameters in the model are adjusted to reduce the error. Through repeated optimization and error fitting processing, the finally optimized high-temperature heat pump characteristic analysis model is generated. The optimized model can more accurately reflect the actual operating conditions and provide more precise predictions in future control decisions.

[0041] Further, step S43 includes the following steps: Step S431: transmitting historical high-temperature heat pump control-operation data to a high-temperature heat pump characteristic analysis model for high-temperature heat pump characteristic training analysis to generate high-temperature heat pump characteristic training data; Step S432: performing heterogeneous operation state division processing on the high temperature heat pump characteristic training data to generate heterogeneous operation state high temperature heat pump characteristic training data; Step S433: performing error distribution characteristic analysis of the high-temperature heat pump characteristics in a heterogeneous operating state based on the high-temperature heat pump characteristics training data in a heterogeneous operating state, and generating error distribution characteristic data of the high-temperature heat pump characteristics in a heterogeneous operating state; Step S434: performing model error fitting optimization processing on the high-temperature heat pump characteristic analysis model by using the high-temperature heat pump characteristic error distribution characteristic data in the heterogeneous operation state to generate an optimized high-temperature heat pump characteristic analysis model.

[0042] In an embodiment of the present invention, historical high-temperature heat pump control-operation data is obtained, and the data includes multiple key parameters, such as historical control parameters (such as compressor speed, refrigerant flow, inlet water temperature) and operating status data (such as output heat, thermal efficiency, exhaust temperature). These data are arranged according to timestamps to form a complete set of time series data sets. This data is transmitted to the high-temperature heat pump characteristic analysis model for adjusting the characteristics, and the built-in training mechanism of the model is used for characteristic analysis. During the training process, the model learns how each control parameter affects the operating performance of the heat pump by fitting the relationship between the input and output of the historical data. For example, under the conditions of given refrigerant flow and compressor speed, the model can predict heat output and efficiency. During the training process, the gradient descent method is used to adjust the internal parameters of the model (such as efficiency coefficient and thermodynamic characteristic parameters) so that the output of the model gradually approaches the real data. After multiple iterations, the model can accurately reflect the operating laws of historical data and generate high-temperature heat pump characteristic training data. The training data contains the prediction results of the model for each set of historical data and its corresponding control parameters, which are used for subsequent state division and error analysis. The high-temperature heat pump characteristic training data is processed for heterogeneous operation state division. Heterogeneous operating states refer to different operating states of high-temperature heat pumps under different control strategies. For example, in some control situations, high-temperature heat pumps operate at higher compressor frequencies, and the operating states under these different control strategies are classified. In operation, the training data is divided into multiple groups according to control parameters (such as compressor frequency, refrigerant flow, inlet water temperature, etc.), and each group represents a specific operating state. According to the changes in control parameters, each type of operating state is divided to generate heterogeneous operating state high-temperature heat pump characteristic training data. Each data group contains the operating characteristic data of the heat pump in this state, providing a strong basis for subsequent error analysis. Based on the heterogeneous operating state high-temperature heat pump characteristic training data, the high-temperature heat pump characteristic error distribution characteristic analysis is performed. For each heterogeneous operating state group, the error between the actual output of the high-temperature heat pump in the group and the model predicted output is calculated, and the distribution characteristics of these errors are analyzed. For example, in some operating states, the prediction error of the model is large, while in other states, the error is small. Use statistical analysis methods and machine learning, such as using Gaussian models combined with variance analysis, to process the error data, evaluate the distribution characteristics of model errors under different operating states, and find out which factors lead to large error distribution phenomena. According to the distribution characteristics of the errors, we can further understand the weaknesses of the model and provide data support for the next step of optimization. Based on the error distribution characteristic data of the high-temperature heat pump characteristics under heterogeneous operating conditions, the adjusted high-temperature heat pump characteristic analysis model is optimized through model error fitting optimization processing. Using the error distribution characteristic data of the high-temperature heat pump characteristics under heterogeneous operating conditions, we can find out the specific operating conditions with large errors and their related factors. For example, if the model error is large under certain high-pressure and high-flow control conditions, the performance of the model under these conditions needs to be corrected.The parameters of the model are further adjusted using error correction algorithms (such as weighted least squares, ridge regression, etc.). By comparing the error data with the model output, the characteristic parameters in the model are optimized, the model prediction output is adjusted, and the error is reduced. Finally, through multiple optimization iterations, an optimized high-temperature heat pump characteristic analysis model is generated, which can more accurately reflect the actual operation and provide higher accuracy in subsequent control.

[0043] Further, step S433 includes the following steps: Performing heterogeneous operation state high temperature heat pump characteristic error data analysis based on heterogeneous operation state high temperature heat pump characteristic training data to generate heterogeneous operation state high temperature heat pump characteristic error data; Performing error clustering analysis on the high-temperature heat pump characteristic error data in heterogeneous operation states to generate high-temperature heat pump characteristic error clustering data in heterogeneous operation states; According to the high-temperature heat pump characteristic error clustering data in heterogeneous operation states, the high-temperature heat pump characteristic error distribution feature analysis in heterogeneous operation states is performed to generate the high-temperature heat pump characteristic error distribution feature data in heterogeneous operation states.

[0044] In an embodiment of the present invention, for the high-temperature heat pump characteristic training data in heterogeneous operating states, the error between the model predicted output value and the actual observed value in each set of operating state data is calculated. The model predicted value and the corresponding actual value are extracted from the heterogeneous operating state training data to calculate the error value. The error size is quantified using indicators such as Absolute Error (AE) or Mean Squared Error (MSE). Taking the compressor frequency as an example, the difference between the predicted output heat and the actual output heat is calculated under the high-frequency operating state to generate an error value data set under the heterogeneous operating state. Finally, an error data table corresponding to each operating state is formed to provide a basis for subsequent analysis. The error data is analyzed and processed using a clustering algorithm to identify the regularity and distribution characteristics of the error. The error data corresponding to each heterogeneous operating state is used as a clustering input feature, and the K-means clustering algorithm is used to classify the error data. For example, the operating state parameters such as compressor frequency, water inlet temperature, and heat pump load and the error value are used as input features, and the clustering algorithm is executed to divide the high error interval, the low error interval, and the intervals of other characteristic categories. The clustering results form a data set of distribution characteristics of errors under heterogeneous operating conditions. Each cluster category contains a set of corresponding operating conditions and error characteristics, which is convenient for subsequent targeted optimization analysis. For example, according to the distribution characteristics of the error data, select an appropriate K value. The best K value is usually determined by the Elbow Method. Assume that K=3 is initially set, that is, it is divided into 3 cluster categories (such as high error interval, medium error interval, and low error interval). The K-means++ algorithm is used for initial center selection to optimize the convergence speed and result accuracy of clustering. It is set to 100 times to ensure that the clustering process converges within a reasonable time. It is set to 1e-4, indicating that the clustering is considered to have converged when the change in the position of the cluster center is lower than this value. All input features are standardized and Z-score normalization is used (each feature minus the mean divided by the standard deviation) to ensure that all features are within the same scale range, thereby avoiding some features dominating the clustering results. The standardized error data is clustered using the K-means algorithm. In each round of iteration, the K-means algorithm calculates the distance from each data point to the current cluster center and assigns the data point to the nearest cluster center. Then, the center of each cluster is recalculated and the process is repeated until the maximum number of iterations is reached or the change in the cluster center is less than the set tolerance.Assuming that a certain operating state is under the clustering condition of K=3, the clustering results are as follows: Cluster 1 (low error interval): compressor frequency 40-50 Hz, inlet water temperature 55°C, heat pump load 60%-70%, error mean 0.5 kW; Cluster 2 (medium error interval): compressor frequency 50-60 Hz, inlet water temperature 65°C, heat pump load 75%-85%, error mean 1.5 kW; Cluster 3 (high error interval): compressor frequency 60-70 Hz, inlet water temperature 70°C, heat pump load 90%-100%, error mean 3.0 kW. Based on the clustering data of high-temperature heat pump characteristics under heterogeneous operating states, the error distribution characteristics of different clustering categories are analyzed. The error value distribution range within each clustering category is counted, such as the maximum error value, minimum error value, mean and variance; the error distribution diagram is drawn to show the error distribution trend. The concentration degree and distribution law of errors under different operating states are found. For example, the high compressor frequency operation state has a higher error mean and a larger variance, while the low frequency operation state has a more concentrated error distribution. Finally, a data table of the error distribution characteristics of the high temperature heat pump characteristics in the heterogeneous operation state is generated, recording the key error distribution indicators of each cluster category, providing data support for optimizing model parameters.

[0045] Further, step S5 includes the following steps: Step S51: obtaining an instant high-temperature heat pump heat output optimization demand decision; Step S52: monitoring and processing the real-time high-temperature heat pump environmental parameters of the high-temperature heat pump equipment through a distributed sensor network to obtain the real-time high-temperature heat pump environmental parameters; Step S53: designing a high-temperature heat pump heat output optimization control reward function according to the instant high-temperature heat pump heat output optimization demand decision; Step S54: transmitting the immediate high-temperature heat pump environmental parameters to the optimized high-temperature characteristic analysis model for immediate environmental response processing to obtain the immediate environmental response optimized high-temperature characteristic analysis model, and performing high-temperature heat pump dynamic scheduling control parameter analysis through the immediate environmental response optimized high-temperature characteristic analysis model and the high-temperature heat pump heat output optimization control reward function to generate the high-temperature heat pump dynamic scheduling control parameters; Step S55: Execute the high-temperature heat pump heat output optimization control operation through the high-temperature heat pump dynamic scheduling control parameters.

[0046] In an embodiment of the present invention, the heat output demand of the high-temperature heat pump system is determined, and the demand is usually determined by the external load demand or the energy efficiency optimization target of the system. The external temperature, humidity, load demand and internal control strategy are used to generate the immediate heat output demand. When the external environment temperature is low and the load demand is high, the system automatically adjusts the demand to increase the heat output. At this time, through the demand decision algorithm or model, the system determines whether it is necessary to increase the heat output or adjust the control strategy through real-time data. Finally, an immediate high-temperature heat pump heat output optimization demand decision is generated. The environmental parameters of the high-temperature heat pump equipment are monitored based on a distributed sensor network. Real-time data is collected by sensors installed at key locations (such as water inlet, water outlet, compressor, heat exchanger, etc.) to obtain the environmental parameters of the high-temperature heat pump equipment. Common environmental parameters include water temperature, air temperature, pressure, humidity, flow, etc. The sensor transmits these data in real time, and the data of each sensor is processed by the data acquisition system and transmitted to the control system through the wireless network. If the sensor data indicates that the compressor pressure is too high, the equipment parameters are adjusted by the control system to ensure stable operation of the equipment. According to the real-time high-temperature heat pump heat output optimization demand decision, a high-temperature heat pump heat output optimization control reward function is designed. This function guides the optimization process by quantifying the relationship between the demand decision and the heat pump operation target. According to the heat output optimization demand decision, multiple control targets are defined, such as minimizing energy consumption and maximizing heat output. When designing the control reward function, the weight of each target is taken into account to build a multi-target optimization model. When the demand decision is a higher heat output, the system's reward function will give a higher heat output weight while suppressing the increase in energy consumption. Through the relationship between the reward function and the control target, the system can adjust the operation strategy in real time to achieve the optimal heat output effect. Using the real-time high-temperature heat pump environmental parameters, environmental response processing is performed based on the optimized high-temperature characteristic analysis model, and dynamic scheduling control parameters are generated. The transmitted environmental parameters are input into the optimized high-temperature characteristic analysis model, which can respond to the current environmental conditions and obtain the best operating strategy to adapt to the environment. The model analyzes real-time environmental data, predicts the response of the system under different environmental conditions, and generates dynamic scheduling control parameters for high-temperature heat pumps that adapt to the environment. For example, in a low-temperature environment, the control parameters tend to increase the heat output of the heat pump to meet the demand, while in a high-temperature environment, energy-saving scheduling is performed. Based on the results of the environmental response analysis and the optimization of the control reward function, the final dynamic scheduling control parameters of the high-temperature heat pump are generated. The dynamic scheduling control parameters of the high-temperature heat pump are used to perform heat output optimization control. The control system directly adjusts the operating state of the high-temperature heat pump equipment according to the optimized scheduling parameters. By changing the control variables such as the compressor speed and heat exchanger flow of the equipment, the heat output can be accurately adjusted. If the dynamic scheduling parameters show high load demand, the system will adjust the equipment to a higher output level, and when the demand is low, it will automatically reduce the output power and optimize energy efficiency.Ultimately, it ensures that the high-temperature heat pump can operate stably under various environmental conditions and achieve the goal of optimizing heat output.

[0047] Further, step S53 includes the following steps: Step S531: performing a multi-objective optimization operation analysis of the high-temperature heat pump according to the instant high-temperature heat pump heat output optimization demand decision, and generating multi-objective optimization operation data of the high-temperature heat pump; Step S532: Perform high-temperature heat pump operation constraint mapping processing on the high-temperature heat pump multi-objective optimization operation data to generate constraint mapping multi-objective optimization operation data, and use the constraint mapping multi-objective optimization operation data as the high-temperature heat pump heat output optimization control reward function.

[0048] In an embodiment of the present invention, a multi-objective optimization operation analysis of a high-temperature heat pump is performed according to an instant heat output optimization demand decision. According to the heat output optimization demand decision, multiple objectives to be optimized are determined, such as minimizing energy consumption, maximizing heat output, ensuring system stability, etc. A weight is assigned to each objective to construct a multi-objective optimization problem. A multi-objective optimization algorithm (such as a genetic algorithm, a particle swarm optimization algorithm, etc.) is used to analyze the operation of the heat pump and generate multi-objective optimization data. These data reflect the operation effect of the heat pump under different control conditions and take into account the comprehensive influence of multiple optimization objectives. For example, when the load demand is high, the optimization algorithm tends to increase the output, while when the energy efficiency requirement is high, the optimization algorithm controls the heat pump output to save energy. For example, a particle swarm optimization (PSO) algorithm is used to solve the multi-objective optimization problem. The initial number of particles in the particle swarm is 50, and the dimension of each particle is 3, which corresponds to energy consumption, heat output, and system stability, respectively. The maximum number of iterations is set to 200, and the goal is to find the optimal parameter combination that meets each objective condition. The goal of minimizing energy consumption is given a weight of 40%, the goal of maximizing heat output is given a weight of 40%, and the goal of system stability is given a weight of 20%. This means that in the optimization process, energy efficiency and heat output will be optimized with higher priority, while stability is less important. During the execution of the particle swarm optimization algorithm, the optimization operation plan under each goal is generated based on the input control parameters (such as input voltage, operating time, flow, etc.) and the real-time environmental conditions of the equipment (such as temperature, humidity, equipment failure rate, etc.). The generated multi-objective optimization operation data contains the optimization plan under each goal and its corresponding operation parameters. Based on the operation constraints of the high-temperature heat pump, the multi-objective optimization operation data is constrained and mapped to generate multi-objective optimization operation data with constraint mapping. According to the operation restrictions of the system (such as the maximum output power of the equipment, the minimum water temperature, the maximum operating pressure, etc.), the multi-objective optimization data is constrained and mapped. For each target optimization result, it is judged whether it meets the constraints of the equipment and the system. If some optimization plans exceed the capacity of the equipment, they are adjusted or excluded. If a certain optimization plan requires exceeding the maximum power limit of the heat pump, the plan is modified to adapt to the maximum power limit of the equipment. After this constraint mapping process, the generated constraint mapping multi-objective optimization operation data can reflect the optimization scheme that meets the operation constraints in actual operation. These processed data will be used to construct the heat output optimization control reward function. The reward function assigns different scores to the constraint execution of each optimization scheme, and finally generates the optimization control reward function, which can be used in subsequent optimization control decisions to ensure that the system meets the heat output target and operation constraints in the best operating state.

[0049] This specification provides a high-temperature heat pump heat output optimization control system based on autoregressive analysis, which is used to execute the high-temperature heat pump heat output optimization control method based on autoregressive analysis as described above. The high-temperature heat pump heat output optimization control system based on autoregressive analysis includes: A historical high-temperature heat pump control-operation analysis module is used to obtain historical high-temperature heat pump control parameters, historical high-temperature heat pump operation data, and historical high-temperature heat pump environmental parameters; perform historical high-temperature heat pump operation characteristic analysis based on historical high-temperature heat pump operation data to generate historical high-temperature heat pump operation characteristic data; map historical high-temperature heat pump control parameters to historical high-temperature heat pump operation characteristic data to perform correlation analysis of historical high-temperature heat pump control and operation characteristics to generate historical high-temperature heat pump control-operation data; A high-temperature heat pump characteristic analysis model establishment module is used to establish a high-temperature heat pump characteristic mapping relationship between control and operation based on historical high-temperature heat pump operation characteristic data to generate a high-temperature heat pump characteristic analysis model; A high-temperature heat pump environment operation disturbance analysis module is used to analyze the operation disturbance mode of the high-temperature heat pump environment according to historical high-temperature heat pump environment parameters and historical high-temperature heat pump operation data, and generate high-temperature heat pump environment operation disturbance mode data; based on the high-temperature heat pump environment operation disturbance mode data and historical high-temperature heat pump environment parameters, the operation disturbance characteristic analysis of the high-temperature heat pump environment is performed to generate high-temperature heat pump environment operation disturbance characteristic data; The high-temperature heat pump characteristic analysis model optimization module is used to adjust the model parameters of the high-temperature heat pump characteristic analysis model for environmental disturbance sensitivity based on the high-temperature heat pump environmental operation disturbance characteristic data, and generate an adjusted high-temperature heat pump characteristic analysis model; the historical high-temperature heat pump control-operation data is used to perform model error fitting optimization processing on the adjusted high-temperature heat pump characteristic analysis model, and generate an optimized high-temperature heat pump characteristic analysis model; The high-temperature heat pump heat output optimization control module is used to obtain the instant high-temperature heat pump heat output optimization demand decision and the instant high-temperature heat pump environmental parameters; based on the optimized high-temperature characteristic analysis model, the instant high-temperature heat pump heat output optimization demand decision and the instant high-temperature heat pump environmental parameters are analyzed to generate the high-temperature heat pump dynamic scheduling control parameters; the high-temperature heat pump heat output optimization control operation is performed through the high-temperature heat pump dynamic scheduling control parameters.

[0050] Therefore, the embodiments should be regarded as illustrative and non-restrictive from all points, and the scope of the present invention is limited by the appended claims rather than the above description, and it is intended that all changes falling within the meaning and range of equivalent elements of the application documents are included in the present invention.

[0051] The above description is only a specific embodiment of the present invention, so that those skilled in the art can understand or implement the present invention. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to the embodiments shown herein, but should conform to the widest scope consistent with the principles and novel features invented herein.

Claims

1. A high-temperature heat pump heat output optimization control method based on autoregressive analysis, characterized in that: The following steps are involved: Step S1: Obtain historical high-temperature heat pump control parameters, historical high-temperature heat pump operation data, and historical high-temperature heat pump environmental parameters; perform historical high-temperature heat pump operation characteristic analysis based on the historical high-temperature heat pump operation data to generate historical high-temperature heat pump operation characteristic data; map the historical high-temperature heat pump control parameters to the historical high-temperature heat pump operation characteristic data to perform correlation analysis on the control and operation characteristics of the historical high-temperature heat pump to generate historical high-temperature heat pump control-operation data; Step S2: establishing a high-temperature heat pump characteristic mapping relationship between control and operation based on historical high-temperature heat pump operation characteristic data to generate a high-temperature heat pump characteristic analysis model; Step S3: performing an operation disturbance mode analysis of the high-temperature heat pump environment according to historical high-temperature heat pump environmental parameters and historical high-temperature heat pump operating data, and generating high-temperature heat pump environment operation disturbance mode data; performing an operation disturbance feature analysis of the high-temperature heat pump environment based on the high-temperature heat pump environment operation disturbance mode data and historical high-temperature heat pump environmental parameters, and generating high-temperature heat pump environment operation disturbance feature data; Step S4: Based on the high-temperature heat pump environmental operation disturbance characteristic data, the model parameter adjustment processing of the high-temperature heat pump characteristic analysis model is performed to the environmental disturbance sensitivity, and the adjusted high-temperature heat pump characteristic analysis model is generated; the model error fitting optimization processing of the adjusted high-temperature heat pump characteristic analysis model is performed using the historical high-temperature heat pump control-operation data, and the optimized high-temperature heat pump characteristic analysis model is generated; Step S5: Obtain the instant high-temperature heat pump heat output optimization demand decision and the instant high-temperature heat pump environmental parameters; perform high-temperature heat pump dynamic scheduling control parameter analysis on the instant high-temperature heat pump heat output optimization demand decision and the instant high-temperature heat pump environmental parameters based on the optimized high-temperature characteristic analysis model, and generate high-temperature heat pump dynamic scheduling control parameters; perform high-temperature heat pump heat output optimization control operations through the high-temperature heat pump dynamic scheduling control parameters.

2. The high-temperature heat pump heat output optimization control method based on autoregressive analysis according to claim 1 is characterized in that: Step S1 includes the following steps: Step S11: acquiring historical high-temperature heat pump control parameters of the high-temperature heat pump control system, and monitoring and processing historical high-temperature heat pump operation and historical high-temperature heat pump environmental parameters of the high-temperature heat pump equipment through a distributed sensor network, so as to obtain historical high-temperature heat pump operation data and historical high-temperature heat pump environmental parameters; Step S12: performing historical high-temperature heat pump control change timing window analysis according to historical high-temperature heat pump control parameters to generate historical high-temperature heat pump control change timing window data; Step S13: using the historical high-temperature heat pump control change timing window to perform historical high-temperature heat pump window division processing on the historical high-temperature heat pump operation data to obtain historical high-temperature heat pump operation window data; Step S14: Analyze and process the operation characteristics of each window of the historical high-temperature heat pump operation window data to generate historical high-temperature heat pump operation characteristic data; Step S15: Mapping historical high-temperature heat pump control parameters to historical high-temperature heat pump operation characteristic data to perform correlation analysis between the control and operation characteristics of the historical high-temperature heat pump, and generating historical high-temperature heat pump control-operation data.

3. The high temperature heat pump heat output optimization control method based on autoregressive analysis according to claim 1 is characterized in that: Step S2 includes the following steps: Step S21: using a preset autocorrelation function to perform autocorrelation order analysis of the heat pump operation characteristics on the historical high-temperature heat pump operation characteristic data to generate the heat pump operation characteristic autocorrelation order; Step S22: establishing a mapping relationship between control and operation of high-temperature heat pump characteristics through the autocorrelation order of heat pump operation characteristics to generate a high-temperature heat pump characteristic analysis model.

4. The high temperature heat pump heat output optimization control method based on autoregressive analysis according to claim 1 is characterized in that: Step S3 includes the following steps: Step S31: performing an operation disturbance mode analysis of the high-temperature heat pump environment according to historical high-temperature heat pump environmental parameters and historical high-temperature heat pump operation data, and generating high-temperature heat pump environment operation disturbance mode data; Step S32: performing frequency domain data conversion processing on historical high-temperature heat pump environmental parameters to generate historical high-temperature heat pump environmental frequency domain data; Step S33: performing time series frequency domain data difference calculation of each environmental parameter type according to historical high temperature heat pump environment frequency domain data to generate heat pump environment time series frequency domain difference data; Step S34: performing an environmental parameter type influence weight analysis of each disturbance mode on the heat pump environment time series frequency domain difference data through the high-temperature heat pump environment operation disturbance mode data, and generating a disturbance mode environmental parameter type weight coefficient; Step S35: using the disturbance mode environmental parameter type weight coefficient to perform environmental type parameter weighted fusion processing on the historical high-temperature heat pump environmental frequency domain data to generate historical high-temperature heat pump environmental frequency domain fusion data; Step S36: Based on the historical high-temperature heat pump operation data and the historical high-temperature heat pump environment frequency domain fusion data, the operation disturbance characteristic analysis of the high-temperature heat pump environment is performed to generate the high-temperature heat pump environment operation disturbance characteristic data.

5. The high temperature heat pump heat output optimization control method based on autoregressive analysis according to claim 1 is characterized in that: Step S4 includes the following steps: Step S41: using the Sobol technology to analyze the high-temperature heat pump environment operation disturbance mode data and the high-temperature heat pump environment operation disturbance characteristic data, and generate the high-temperature heat pump environment-operation disturbance interaction response coefficient; Step S42: using the high-temperature heat pump environment-operation disturbance response coefficient to adjust the model parameters of the high-temperature heat pump characteristic analysis model for environmental disturbance sensitivity, and generating an adjusted high-temperature heat pump characteristic analysis model; Step S43: Utilizing historical high-temperature heat pump control-operation data, the high-temperature heat pump characteristic analysis model is subjected to model error fitting optimization processing to generate an optimized high-temperature heat pump characteristic analysis model.

6. The high temperature heat pump heat output optimization control method based on autoregressive analysis according to claim 5 is characterized in that: Step S43 includes the following steps: Step S431: transmitting historical high-temperature heat pump control-operation data to a high-temperature heat pump characteristic analysis model for high-temperature heat pump characteristic training analysis to generate high-temperature heat pump characteristic training data; Step S432: performing heterogeneous operation state division processing on the high temperature heat pump characteristic training data to generate heterogeneous operation state high temperature heat pump characteristic training data; Step S433: performing error distribution characteristic analysis of the high-temperature heat pump characteristics in a heterogeneous operating state based on the high-temperature heat pump characteristics training data in a heterogeneous operating state, and generating error distribution characteristic data of the high-temperature heat pump characteristics in a heterogeneous operating state; Step S434: performing model error fitting optimization processing on the high-temperature heat pump characteristic analysis model by using the high-temperature heat pump characteristic error distribution characteristic data in the heterogeneous operation state to generate an optimized high-temperature heat pump characteristic analysis model.

7. The high temperature heat pump heat output optimization control method based on autoregressive analysis according to claim 6 is characterized in that: Step S433 includes the following steps: Performing heterogeneous operation state high temperature heat pump characteristic error data analysis based on heterogeneous operation state high temperature heat pump characteristic training data to generate heterogeneous operation state high temperature heat pump characteristic error data; Performing error clustering analysis on the high-temperature heat pump characteristic error data in heterogeneous operation states to generate high-temperature heat pump characteristic error clustering data in heterogeneous operation states; According to the high-temperature heat pump characteristic error clustering data in heterogeneous operation states, the high-temperature heat pump characteristic error distribution feature analysis in heterogeneous operation states is performed to generate the high-temperature heat pump characteristic error distribution feature data in heterogeneous operation states.

8. The high temperature heat pump heat output optimization control method based on autoregressive analysis according to claim 1 is characterized in that: Step S5 includes the following steps: Step S51: obtaining an instant high-temperature heat pump heat output optimization demand decision; Step S52: monitoring and processing the real-time high-temperature heat pump environmental parameters of the high-temperature heat pump equipment through a distributed sensor network to obtain the real-time high-temperature heat pump environmental parameters; Step S53: designing a high-temperature heat pump heat output optimization control reward function according to the instant high-temperature heat pump heat output optimization demand decision; Step S54: transmitting the immediate high-temperature heat pump environmental parameters to the optimized high-temperature characteristic analysis model for immediate environmental response processing to obtain the immediate environmental response optimized high-temperature characteristic analysis model, and performing high-temperature heat pump dynamic scheduling control parameter analysis through the immediate environmental response optimized high-temperature characteristic analysis model and the high-temperature heat pump heat output optimization control reward function to generate the high-temperature heat pump dynamic scheduling control parameters; Step S55: Execute the high-temperature heat pump heat output optimization control operation through the high-temperature heat pump dynamic scheduling control parameters.

9. The high temperature heat pump heat output optimization control method based on autoregressive analysis according to claim 8, characterized in that: Step S53 includes the following steps: Step S531: performing a multi-objective optimization operation analysis of the high-temperature heat pump according to the instant high-temperature heat pump heat output optimization demand decision, and generating multi-objective optimization operation data of the high-temperature heat pump; Step S532: Perform high-temperature heat pump operation constraint mapping processing on the high-temperature heat pump multi-objective optimization operation data to generate constraint mapping multi-objective optimization operation data, and use the constraint mapping multi-objective optimization operation data as the high-temperature heat pump heat output optimization control reward function.

10. A high-temperature heat pump heat output optimization control system based on autoregressive analysis, characterized in that: Used to execute the high-temperature heat pump heat output optimization control method based on autoregressive analysis as claimed in claim 1, the high-temperature heat pump heat output optimization control system based on autoregressive analysis comprises: A historical high-temperature heat pump control-operation analysis module is used to obtain historical high-temperature heat pump control parameters, historical high-temperature heat pump operation data, and historical high-temperature heat pump environmental parameters; perform historical high-temperature heat pump operation characteristic analysis based on historical high-temperature heat pump operation data to generate historical high-temperature heat pump operation characteristic data; map historical high-temperature heat pump control parameters to historical high-temperature heat pump operation characteristic data to perform correlation analysis of historical high-temperature heat pump control and operation characteristics to generate historical high-temperature heat pump control-operation data; A high-temperature heat pump characteristic analysis model establishment module is used to establish a high-temperature heat pump characteristic mapping relationship between control and operation based on historical high-temperature heat pump operation characteristic data to generate a high-temperature heat pump characteristic analysis model; A high-temperature heat pump environment operation disturbance analysis module is used to analyze the operation disturbance mode of the high-temperature heat pump environment according to historical high-temperature heat pump environment parameters and historical high-temperature heat pump operation data, and generate high-temperature heat pump environment operation disturbance mode data; based on the high-temperature heat pump environment operation disturbance mode data and historical high-temperature heat pump environment parameters, the operation disturbance characteristic analysis of the high-temperature heat pump environment is performed to generate high-temperature heat pump environment operation disturbance characteristic data; The high-temperature heat pump characteristic analysis model optimization module is used to adjust the model parameters of the high-temperature heat pump characteristic analysis model for environmental disturbance sensitivity based on the high-temperature heat pump environmental operation disturbance characteristic data, and generate an adjusted high-temperature heat pump characteristic analysis model; the historical high-temperature heat pump control-operation data is used to perform model error fitting optimization processing on the adjusted high-temperature heat pump characteristic analysis model, and generate an optimized high-temperature heat pump characteristic analysis model; The high-temperature heat pump heat output optimization control module is used to obtain the instant high-temperature heat pump heat output optimization demand decision and the instant high-temperature heat pump environmental parameters; based on the optimized high-temperature characteristic analysis model, the instant high-temperature heat pump heat output optimization demand decision and the instant high-temperature heat pump environmental parameters are analyzed to generate the high-temperature heat pump dynamic scheduling control parameters; the high-temperature heat pump heat output optimization control operation is performed through the high-temperature heat pump dynamic scheduling control parameters.

Images