Efficient circulating water heating system based on heat pump and control method thereof

Abstract

The invention discloses an efficient circulating water heating system based on a heat pump and a control method thereof.The system comprises a multi-stage heat pump system, a circulating water heating loop and an intelligent control unit, and the multi-stage heat pump system is used for increasing heat energy of a low-temperature heat source stage by stage to heat circulating water; the intelligent control unit is integrated with a data acquisition module, a load prediction module, a system modeling module, a parameter optimization module, an instruction issuing module and a performance evaluation module, and can realize thermal load dynamic prediction and thermal performance modeling and optimization control of the heat pump system. The control method is based on deep learning and model prediction control, combines real-time data and an external scheduling instruction, calculates an optimal operation parameter to improve the system energy efficiency ratio or reduce the operation cost, and continuously optimizes prediction and modeling precision through an adaptive learning mechanism. The system has the capacity of intelligent prediction, accurate control, efficient heat transfer and self-optimization, is suitable for occasions such as industries and buildings with high requirements for hot water supply energy efficiency, and remarkably improves the operation efficiency and stability of the system.

Description

Technical Field

[0001] The present invention relates to the technical field of heating systems, and particularly to a high-efficiency circulating water heating system based on a heat pump and its control method. Background Art

[0002] As an efficient and environmentally friendly heat energy conversion means, heat pump technology is widely used in fields such as building heating, domestic hot water, and industrial heat energy recovery. However, most existing heat pump systems adopt a single-stage compression structure, which generally has problems such as limited temperature rise capacity, large energy efficiency fluctuations, simple control strategies, and uncontrollable operating costs when facing high-temperature output requirements, complex operating environments, and fluctuating load scenarios. Especially in cold climates or industrial high-load conditions, single-stage heat pumps often struggle to balance heat output and stable energy efficiency ratio, resulting in limited comprehensive performance of the system.

[0003] To make up for the deficiencies of the single-stage structure, multi-stage heat pump systems such as cascade heat pumps have gradually become the mainstream solution to improve temperature rise capacity and energy efficiency performance. However, their control difficulty has increased significantly. The system has high-dimensional parameters, strong inter-stage coupling, and high operating response requirements. Traditional experience-based control methods are difficult to achieve global optimal control of the system operating state, lacking refined adjustment means and adaptive scheduling capabilities. Therefore, there is an urgent need for a new type of circulating water heating system that combines a multi-stage heat pump structure with an intelligent control mechanism to achieve dynamic response to heat load changes, long-term optimization of system energy efficiency, and effective control of operating costs, thereby breaking through the application bottleneck of existing technologies in high-energy consumption scenarios. Summary of the Invention

[0004] In view of the deficiencies of the prior art, the present invention provides a high-efficiency circulating water heating system based on a heat pump and its control method, which solves the above problems.

[0005] To achieve the above objectives, the present invention is realized through the following technical solutions:

[0006] A high-efficiency circulating water heating system based on a heat pump, comprising:

[0007] A multi-stage heat pump system: composed of at least N stages of heat pumps connected in series or in cascade, where N is an integer greater than or equal to 2, for gradually absorbing heat from a low-temperature heat source and raising it to a target high temperature to heat the circulating water;

[0008] A circulating water heating circuit: connected to the multi-stage heat pump system for carrying the heated circulating water; and

[0009] An intelligent control unit: connected to the multi-stage heat pump system and the circulating water heating circuit for monitoring, predicting, optimizing, and controlling the operation of the entire system. The intelligent control unit includes:

[0010] Data acquisition module: used to collect in real time the operating parameters of each stage of the multi-stage heat pump system, the parameters of the circulating water heating circuit, and the external environment parameters;

[0011] Data prediction module: used to predict the future circulating water heating load and the trend of external environment changes based on the collected parameters, historical operating data, and external scheduling instructions;

[0012] System performance modeling module: used to construct and dynamically update the thermodynamic performance model of the multi-stage heat pump system under different combinations of operating parameters and the set intermediate temperatures between stages, and be able to predict the local energy efficiency ratio of each stage of the heat pump and the inter-stage energy transfer efficiency;

[0013] Parameter optimization module: used to calculate the optimal operating parameters of each stage of the heat pump and the optimal inter-stage temperature setting value that maximize the overall energy efficiency ratio of the system or minimize the total operating cost under the premise of meeting the predicted heat load by solving an optimization problem based on the predicted load, system performance model, and preset constraint conditions;

[0014] Instruction issuing module: used to transmit the calculated optimal operating parameters to the actuators of each stage of the multi-stage heat pump system, including but not limited to the actuators of the compressor frequency converter, electronic expansion valve, and circulating water pump; and

[0015] Performance evaluation and adaptive learning module: used to compare the actual operating performance of the system with the predicted performance of the parameter optimization module, and based on the deviation feedback, iteratively optimize the data prediction module and the system performance modeling module in real time to achieve long-term self-adaptation and continuous optimization of the system operation.

[0016] Preferably, the parameters collected by the data acquisition module include but are not limited to: the inlet temperature of the circulating water, the outlet temperature of the circulating water, the circulating water flow rate, the compressor speed corresponding to each stage of the heat pump, the opening of the electronic expansion valve, the temperature and pressure of the refrigerant in each evaporator and condenser, the real-time electric power of each stage of the compressor, the real-time electric power of the circulating water pump, as well as the outdoor ambient temperature and ambient humidity.

[0017] Preferably, the data prediction module adopts a time series prediction model based on deep learning, which is a long short-term memory network LSTM, Transformer, or a combination thereof, to capture complex time dependencies and the impact of the external environment on the load.

[0018] Preferably, the system performance modeling module adopts a deep neural network DNN or a physics-informed neural network PINN to construct the thermodynamic performance model, which can simultaneously predict the thermodynamic state, energy efficiency ratio, and output heat of the multi-stage heat pump system as a whole and each stage, and accurately characterize the dynamic changes in the coupling relationship between stages.

[0019] Preferably, the parameter optimization module adopts a Model Predictive Control (MPC) framework, combines reinforcement learning, genetic algorithm or particle swarm optimization algorithm to search for the optimal solution in a multi-dimensional parameter space, and focuses on optimizing the compressor speed of each stage of the heat pump, the opening degree of the electronic expansion valve, and the intermediate temperature gradient between each stage.

[0020] Preferably, the optimization objective of the parameter optimization module can be dynamically switched or weighted combined between maximizing the overall energy efficiency ratio of the system and minimizing the total operating cost of the system, where the calculation of the total operating cost takes into account the real-time electricity price information.

[0021] Preferably, the instruction issuing module communicates and controls the frequency converters of the compressors at all levels of the multi-stage heat pump system, the electronic expansion valves at all levels, and the frequency converters of the circulating water pumps through Industrial Ethernet, OPC Unified Architecture or Modbus TCP / IP protocol.

[0022] Preferably, the performance evaluation and adaptive learning module triggers the retraining or parameter fine-tuning of the data prediction module and the system performance modeling module by comparing the deviation between the actual overall energy efficiency ratio of the system and the predicted overall energy efficiency ratio, the actual water outlet temperature and the predicted target temperature, and the actual operating conditions and predicted conditions at all levels, so as to ensure that the system performance remains optimal during long-term operation.

[0023] Preferably, the performance evaluation and adaptive learning module also includes an anomaly detection function for identifying and warning potential system failures or performance degradations.

[0024] A control method for an efficient circulating water heating system based on a heat pump, comprising the following steps:

[0025] a. Data acquisition: Real-time acquisition of the operating parameters of all levels of the multi-stage heat pump system, the parameters of the circulating water heating circuit, and the external environment parameters;

[0026] b. Demand prediction and performance modeling: Based on the collected parameters and historical data, predict the future circulating water heating load and environmental changes, and simultaneously construct and dynamically update the thermodynamic performance model of the multi-stage heat pump system under different operating parameters and inter-stage temperatures;

[0027] c. Parameter intelligent optimization: According to the predicted load and the thermodynamic performance model, calculate the optimal operating parameters of each stage of the heat pump and the optimal inter-stage temperature setting value that meet the predicted load and maximize the overall energy efficiency ratio of the system or minimize the operating cost;

[0028] d. Instruction issuing and execution: Transmit the optimal operating parameters to the actuator of each stage of the heat pump and perform precise control;

[0029] e. Performance evaluation and model adaptation: Compare the actual operating performance of the system with the predicted performance, and iteratively optimize the demand prediction model and the thermodynamic performance model according to the deviation feedback.

[0030] Beneficial effects

[0031] The present invention provides a high-efficiency circulating water heating system based on a heat pump and its control method. Compared with the prior art, it has the following beneficial effects:

[0032] By introducing a multi-stage heat pump cascade structure and combining deep learning prediction, system modeling, and intelligent optimization control strategies, the present invention realizes efficient energy conversion from a low-temperature heat source to high-temperature circulating water, significantly improving the temperature rise capacity and overall energy efficiency level of the system; through the data acquisition and time series prediction module, the change trend of the heat load can be predicted in advance to ensure that the heat pump system responds as required; by constructing a digital twin of the system thermal performance with a neural network model, the dynamic estimation of the energy efficiency ratio and energy transfer efficiency of each stage can be realized; the parameter optimization module, based on the model predictive control algorithm combined with the genetic optimization strategy, can dynamically solve the control parameters that maximize the system COP or minimize the operating cost under the premise of meeting the predicted load; at the same time, the system supports the access and response to real-time electricity prices and has cost-sensitive scheduling capabilities; the performance evaluation module continuously corrects the prediction model and control strategy through deviation analysis and adaptive feedback mechanisms, so as to achieve continuous self-learning and performance optimization of the system during long-term operation; in addition, the system also has multi-level anomaly detection and warning functions, which can quickly respond and prompt the fault risk when there are abnormal operating efficiencies or equipment performance degradations, improving the reliability, safety, and intelligent level of the system as a whole, being widely applicable to high-efficiency energy-saving heating demand scenarios, and having significant promotion value and application prospects. Description of the drawings

[0033] Figure 1 is the overall structural block diagram of the intelligent control unit of the present invention;

[0034] Figure 2 is the working flow chart of the intelligent control unit of the present invention;

[0035] Figure 3 is the flow chart of the control method of the high-efficiency circulating water heating system based on a heat pump of the present invention.

[0036] In the figure, 100 is the intelligent control unit; 101 is the data acquisition module; 102 is the data prediction module; 103 is the system performance modeling module; 104 is the parameter optimization module; 105 is the instruction issuing module; 106 is the performance evaluation and adaptive learning module. Detailed implementation manners

[0037] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all of the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0038] Embodiment:

[0039] Please refer to Figures 1-3 , including:

[0040] Multi-stage heat pump system: Composed of at least N-stage heat pumps connected in series or cascaded, where N is an integer greater than or equal to 2, used to absorb heat from a low-temperature heat source step by step and raise it to a target high temperature to heat the circulating water.

[0041] The system includes N-stage heat pumps, N≥2. According to the specific application scenario, the value of N can be adjusted according to the required outlet water temperature. Each stage of the heat pump system absorbs heat from the downstream and raises it to the target temperature step by step. The inlet and outlet temperatures of each stage of the heat pump can be dynamically adjusted according to the hot water demand. Assume that the outlet temperature of the first-stage heat pump is T1, the second stage is T2, and so on. The system adjusts the temperature difference between each stage through the parameter optimization module 104 of the intelligent control unit 100 to ensure the optimal thermal efficiency of the system operation. Each stage of the heat pump is an air-source or water-source heat pump, and the specific selection is adjusted according to the characteristics of the external heat source and the heating efficiency. Generally, the low-temperature heat source gradually increases the temperature through multiple stages and finally reaches the required high-temperature output. Each heat pump system includes components such as a compressor, an expansion valve, an evaporator, and a condenser. The control of the heat pump system is dynamically adjusted by the intelligent control unit according to the real-time collected data and the predicted load to ensure that the system operates in an optimal state.

[0042] Circulating water heating circuit: Connected to the multi-stage heat pump system, used to carry the heated circulating water. The heating water enters the evaporator of the heat pump through the inlet pipe, and after being heated step by step, finally returns through the outlet pipe to form a closed-loop cycle. The heat exchanger in the heating circuit is designed as a laminated or coiled heat exchanger to improve the heat exchange efficiency between water and the heat source. The condenser of each stage of the heat pump exchanges heat with the heating water through an internal heat exchanger. According to different operating conditions, series or parallel heat exchange methods can be selected to ensure efficient heat exchange. The flow rate of the heating water is controlled by a pump, and the pump speed is adjusted by the intelligent control unit 100. The water flow rate is proportional to the heat load to ensure that the heat output of each stage of the heat pump matches the load demand.

[0043] Intelligent control unit 100: Connected to the multi-stage heat pump system and the circulating water heating circuit, used to monitor, predict, optimize, and control the operation of the entire system. The intelligent control unit 100 includes:

[0044] Data acquisition module 101: It is used to collect the operating parameters of each stage of the multi-stage heat pump system, the parameters of the circulating water heating circuit, and the external environment parameters in real time. The collected data includes but is not limited to:

[0045] The compressor speed (n i ) of the heat pump system;

[0046] The inlet and outlet temperatures (T e，i , T c，i ) of the evaporators and condensers of each stage of the heat pump;

[0047] The pressures (P e，i , P c，i ) of the refrigerant;

[0048] The flow rate (Q w ) and temperature (T in , T out ) of the circulating water;

[0049] The external environment temperature (T amb ) and humidity (H amb );

[0050] The electric powers (P el，i , P pump ) of the compressor and the water pump.

[0051] All the collected data will form a time series for further processing by the data prediction module 102 and the performance evaluation module and the adaptive learning module 106.

[0052] To improve the subsequent model processing accuracy and training stability, all continuous numerical parameters collected need to be normalized. The Min-Max standard normalization method is used to uniformly map the data to the [0, 1] interval. The normalization formula is as follows:

[0053]

[0054] Among them, x is the original data, x min and x max represent the minimum and maximum values of this variable in the historical data respectively, and x norm is the normalized data. This processing ensures that parameters with different dimensions have a unified numerical scale in model training and prediction, and improves the model convergence speed and prediction accuracy.

[0055] Data prediction module 102: It is used to predict the future circulating water heating load and the external environment change trend based on the collected parameters, historical operation data, and external scheduling instructions. The prediction method uses a time series prediction model based on deep learning (such as LSTM or Transformer), through the training and prediction formula:

[0056]

[0057] Among them, is the predicted heat load at the future time t + k, and D(t - k:t) is the time series data of the past k steps, is the predicted external environmental temperature. The prediction results are used for subsequent system regulation and optimization.

[0058] System performance modeling module 103: It is used to build and dynamically update the thermodynamic performance model of the multi-stage heat pump system under different combinations of operating parameters and intermediate temperature settings between levels, and can predict the local energy efficiency ratio of each stage of the heat pump and the inter-stage energy transfer efficiency. This module uses a deep neural network (DNN) or a physics-informed neural network (PINN) to build the thermodynamic performance model of the multi-stage heat pump system, and predicts the energy efficiency ratio (COP i ) of each stage of the heat pump, the heat output (Q i ) and the inter-stage energy transfer efficiency (η ij ). The calculation formulas are as follows:

[0059]

[0060] Among them, m r is the refrigerant mass flow rate, c r is the specific heat of the refrigerant, is the outlet temperature of the condenser of the i-th stage heat pump, is the inlet temperature of the evaporator of the i-th stage heat pump. This module adjusts the model in real time according to the collected various parameters to ensure the consistency between the prediction and the actual operation.

[0061] Parameter optimization module 104: It is used to calculate the optimal operating parameters of each stage of the heat pump and the optimal inter-stage temperature setting value that maximize the overall energy efficiency ratio or minimize the total operating cost of the system under the premise of meeting the predicted heat load based on the predicted load, system performance model and preset constraint conditions; this module optimizes the control parameters of the multi-stage heat pump through model predictive control (MPC) combined with a genetic algorithm or a particle swarm optimization algorithm. The optimization objectives include maximizing the energy efficiency ratio (COP) and minimizing the operating cost. The specific optimization formulas are:

[0062] Or

[0063] Among them, u is the control variable, and c el (t) is the real-time electricity price.

[0064] Instruction Issuing Module 105: It is used to transmit the calculated optimal operating parameters to the actuators at all levels of the multi-stage heat pump system, including but not limited to the actuators of the compressor frequency converter, electronic expansion valve, and circulating water pump. The Instruction Issuing Module 105 communicates and controls with the frequency converters of the compressors at all levels, the electronic expansion valves at all levels, and the frequency converters of the circulating water pump through industrial Ethernet, OPC Unified Architecture, or Modbus TCP / IP protocol.

[0065] Performance Evaluation and Adaptive Learning Module 106: It is used to compare the actual operating performance of the system with the predicted performance of the Parameter Optimization Module 104, and based on the deviation feedback, iteratively optimize the Data Prediction Module 102 and the System Performance Modeling Module 103 in real time to achieve long-term adaptability and continuous optimization of the system operation. This module conducts real-time evaluation on the following key performance parameters:

[0066] Comparison between the predicted and actual overall system coefficient of performance (COP):

[0067]

[0068] Outlet water temperature error:

[0069]

[0070] Heat load error:

[0071]

[0072] Where: COP real (t) is the actual coefficient of performance of the system at time t, and COP pred( t) is the predicted coefficient of performance of the system, is the real-time outlet water temperature, is the target outlet water temperature, and Q real (t) is the actual heat output of the system, and Q pred (t) is the heat output predicted by the model.

[0073] When the system detects that any of the following conditions is met, it is regarded as the system performance degradation or the prediction model being inaccurate:

[0074] |δ COP (t)| > ∈ COP

[0075] |δ T (t)| > ∈ T

[0076] |δ Q (t)| > ∈ Q

[0077] Where: ∈COP , ∈ T , ∈ Q is the acceptable error threshold set for the system. If the threshold is exceeded, the system will: package the current data as a training set sample, initiate model fine-tuning or retraining, and evaluate the change in the accuracy of the retrained model. The retrained model combines online incremental training (rapidly fine-tuning the LSTM / PINN model parameters during operation) with offline batch training (performing batch training on historical data during low-load operation periods to enhance the long-term stability of the model).

[0078] The control method of the high-efficiency circulating water heating system based on a heat pump in the present invention includes the following steps:

[0079] a. Data acquisition: Real-time acquisition of the operating parameters of each stage of the multi-stage heat pump system, the parameters of the circulating water heating circuit, and the external environmental parameters;

[0080] b. Demand prediction and performance modeling: Based on the collected parameters and historical data, predict the future circulating water heating load and environmental changes, and simultaneously construct and dynamically update the thermodynamic performance model of the multi-stage heat pump system under different operating parameters and inter-stage temperatures;

[0081] c. Parameter intelligent optimization: According to the predicted load and the thermodynamic performance model, calculate the optimal operating parameters of each stage of the heat pump and the optimal inter-stage temperature setting value that meet the predicted load and maximize the overall energy efficiency ratio or minimize the operating cost of the system;

[0082] d. Instruction issuance and execution: Transmit the optimal operating parameters to the actuator of each stage of the heat pump and perform precise control;

[0083] e. Performance evaluation and model adaptation: Compare the actual operating performance of the system with the predicted performance, and iteratively optimize the demand prediction model and the thermodynamic performance model according to the deviation feedback.

[0084] The present invention realizes efficient energy conversion from a low-temperature heat source to high-temperature circulating water by introducing a multi-stage heat pump cascade structure and combining deep learning prediction, system modeling, and intelligent optimization control strategies, significantly improving the temperature rise capacity and overall energy efficiency level of the system; through the data acquisition and time series prediction module, the change trend of the heat load can be predicted in advance to ensure that the heat pump system responds as required; with the help of a neural network model to construct a digital twin of the system's thermal performance, the dynamic estimation of the energy efficiency ratio and energy transfer efficiency at each level is realized; the parameter optimization module, based on the model predictive control algorithm combined with the genetic optimization strategy, can dynamically solve the control parameters that maximize the system COP or minimize the operating cost under the premise of meeting the predicted load; at the same time, the system supports the access and response to real-time electricity prices and has cost-sensitive scheduling capabilities; the performance evaluation module continuously corrects the prediction model and control strategy through deviation analysis and adaptive feedback mechanisms, so as to achieve continuous self-learning and performance optimization of the system during long-term operation; in addition, the system also has multi-level anomaly detection and warning functions, which can quickly respond and prompt the fault risk when there are abnormal operating efficiencies or equipment performance degradations, improving the reliability, safety, and intelligent level of the system as a whole, being widely applicable to scenarios with high-efficiency energy-saving heating requirements, and having significant promotion value and application prospects.

[0085] Meanwhile, the content not described in detail in this specification belongs to the prior art well-known to those skilled in the art.

[0086] It should be noted that in this text, relational terms such as first and second are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variant thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements not only includes those elements, but also includes other elements not expressly listed, or also includes elements inherent to such process, method, article or device.

[0087] Although the embodiments of the present invention have been shown and described, it will be understood by those of ordinary skill in the art that various changes, modifications, substitutions, and variations can be made to these embodiments without departing from the principles and spirit of the present invention, and the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. An efficient circulating water heating system based on a heat pump, characterized in that, Comprising: A multi-stage heat pump system: composed of at least N stages of heat pumps connected in series or cascaded, where N is an integer greater than or equal to 2, used to absorb heat from a low-temperature heat source step by step and raise it to a target high temperature to heat the circulating water; A circulating water heating circuit: connected to the multi-stage heat pump system, used to carry the heated circulating water; And An intelligent control unit (100): connected to the multi-stage heat pump system and the circulating water heating circuit, used to monitor, predict, optimize and control the operation of the entire system. The intelligent control unit (100) includes: A data acquisition module (101): used to collect in real time the operating parameters of each stage of the multi-stage heat pump system, the parameters of the circulating water heating circuit, and the external environment parameters; A data prediction module (102): used to predict the future circulating water heating load and the changing trend of the external environment based on the collected parameters, historical operating data, and external scheduling instructions; A system performance modeling module (103): used to construct and dynamically update the thermodynamic performance model of the multi-stage heat pump system under different combinations of operating parameters and the setting of intermediate temperatures between stages, and capable of predicting the local energy efficiency ratio of each stage of the heat pump and the inter-stage energy transfer efficiency; A parameter optimization module (104): used to calculate the optimal operating parameters of each stage of the heat pump and the optimal inter-stage temperature setting value that maximize the overall energy efficiency ratio of the system or minimize the total operating cost under the premise of meeting the predicted heat load by solving an optimization problem based on the predicted load, system performance model, and preset constraint conditions; An instruction issuing module (105): used to transmit the calculated optimal operating parameters to the actuators of each stage of the multi-stage heat pump system, including but not limited to the actuators of the compressor frequency converter, electronic expansion valve, and circulating water pump; and A performance evaluation and adaptive learning module (106): used to compare the actual operating performance of the system with the predicted performance of the parameter optimization module (104), and based on the deviation feedback, iteratively optimize the data prediction module (102) and the system performance modeling module (103) in real time to achieve long-term self-adaptation and continuous optimization of the system operation.

2. An efficient circulating water heating system based on a heat pump according to claim 1, characterized in that, The parameters collected by the data acquisition module (101) include but are not limited to: the inlet temperature of the circulating water, the outlet temperature of the circulating water, the circulating water flow rate, the compressor speed corresponding to each stage of the heat pump, the opening of the electronic expansion valve, the temperature and pressure of the refrigerant in each evaporator and condenser, the real-time electric power of each stage of the compressor, the real-time electric power of the circulating water pump, and the outdoor ambient temperature and ambient humidity.

3. The high-efficiency circulating water heating system based on a heat pump according to claim 1, wherein The data prediction module (102) adopts a time series prediction model based on deep learning, which is a long short-term memory network LSTM, Transformer, or a combination thereof, to capture complex time dependencies and the impact of the external environment on the load.

4. An efficient circulating water heating system based on a heat pump according to claim 1, characterized in that, The system performance modeling module (103) uses a deep neural network DNN or a physics-informed neural network PINN to construct the thermodynamic performance model, capable of simultaneously predicting the thermodynamic state, energy efficiency ratio, and output heat of the multi-stage heat pump system as a whole and each stage, and accurately characterizing the dynamic changes in the coupling relationship between stages.

5. An efficient circulating water heating system based on a heat pump according to claim 1, characterized in that, The parameter optimization module (104) adopts a model predictive control (MPC) framework and combines reinforcement learning, genetic algorithm or particle swarm optimization algorithm to search for the optimal solution in a multi-dimensional parameter space, and focuses on optimizing the compressor speed of each stage of the heat pump, the opening degree of the electronic expansion valve, and the intermediate temperature gradient between each stage.

6. A high-efficiency circulating water heating system based on a heat pump and its control method according to claim 1, characterized in that The optimization objective of the parameter optimization module (104) can be dynamically switched or weighted combined between maximizing the total energy efficiency ratio of the system and minimizing the total operating cost of the system, where the calculation of the total operating cost takes into account real-time electricity price information.

7. An efficient circulating water heating system based on a heat pump according to claim 1, characterized in that The instruction issuing module (105) communicates and controls with the frequency converters of the compressors at all levels of the multi-stage heat pump system, the electronic expansion valves at all levels, and the frequency converter of the circulating water pump through industrial Ethernet, OPC Unified Architecture or Modbus TCP / IP protocol.

8. An efficient circulating water heating system based on a heat pump according to claim 1, characterized in that, The performance evaluation and adaptive learning module (106) triggers the retraining or parameter fine-tuning of the data prediction module (102) and the system performance modeling module (103) by comparing the deviation between the actual total energy efficiency ratio and the predicted total energy efficiency ratio of the system, the actual water outlet temperature and the predicted target temperature, and the actual operating conditions and the predicted conditions at all levels, so as to ensure that the system performance remains optimal during long-term operation.

9. An efficient circulating water heating system based on a heat pump according to claim 1, wherein the performance evaluation and adaptive learning module (106) further includes an anomaly detection function for identifying and warning potential system failures or performance degradation.

10. A control method for an efficient circulating water heating system based on a heat pump according to any one of claims 1-9, characterized in that, Including the following steps: a. Data acquisition: Real-time acquisition of the operating parameters of all levels of the multi-stage heat pump system, the parameters of the circulating water heating circuit and the external environment parameters; b. Demand prediction and performance modeling: Based on the collected parameters and historical data, predict the future circulating water heating load and environmental changes, and at the same time construct and dynamically update the thermodynamic performance model of the multi-stage heat pump system under different operating parameters and inter-stage temperatures; c. Parameter intelligent optimization: According to the predicted load and the thermodynamic performance model, calculate the optimal operating parameters of each stage of the heat pump and the optimal inter-stage temperature setting value that meet the predicted load and maximize the total energy efficiency ratio of the system or minimize the operating cost; d. Instruction issuing and execution: Transmit the optimal operating parameters to the actuator of each stage of the heat pump and perform precise control; e. Performance evaluation and model adaptation: Compare the actual operating performance of the system with the predicted performance, and iteratively optimize the demand prediction model and the thermodynamic performance model according to the deviation feedback.

Images