Air source heat pump automatic control system and system protection method

Abstract

An automatic control system of an air source heat pump analyzes collected multi-dimensional operation parameters in real time based on a machine learning algorithm, constructs a high-precision thermal load prediction model, predicts thermal load requirements in the future 1-24 hours, controls prediction errors within 5%, and achieves minimization of energy consumption and maximization of heat storage efficiency on the premise of meeting operation constraints. The overall energy consumption is reduced by 15%-25% compared with that of a traditional system, the heat loss is reduced by dynamically adjusting the flow of a heat storage medium and optimizing the thermodynamic process of heat storage and heat release, and the heat storage efficiency is improved by 10%-15%. According to the invention, the advanced machine learning algorithm is adopted through the big data analysis module, the multi-dimensional operation parameters are analyzed in real time, a high-precision thermal load prediction model is constructed, the thermal load demand in the future 1-24 hours is predicted, and the prediction error is controlled within 5%.

Description

Technical Field

[0001] The present invention belongs to the technical field of air source heat pump systems, and in particular relates to an air source heat pump automatic control system and a system protection method. Background Art

[0002] An air-source heat pump is an energy-saving device that uses high-level energy to transfer heat from a low-level heat source to a higher-level heat source. Known as "Nature's Energy Transporter," it offers multiple advantages, including low cost, ease of operation, effective heating, safety, and cleanliness.

[0003] Air source heat pumps use the energy in the air as their main power source, and the electricity consumed is only used to drive the compressor to achieve energy transfer. They do not require complex configuration, expensive water intake, recharge or soil heat exchange systems and dedicated machine rooms. They can gradually reduce the large amount of pollutant emissions brought to the atmospheric environment by traditional heating, ensuring heating efficacy while achieving energy conservation and environmental protection.

[0004] In existing related technologies, traditional air source heat pump systems usually rely on fixed control strategies or prediction models based on simple experience, which cannot effectively explore the complex nonlinear relationship between operating parameters, resulting in large errors in heat load prediction and difficulty in accurately predicting heat load demand in the next 1-24 hours. Prediction deviations often lead to energy waste or insufficient heating, reducing the overall energy efficiency and heating reliability of the system.

[0005] Traditional heat pump systems usually use fixed or semi-fixed operating parameters (such as compressor frequency, circulating pump flow, etc.), which make it difficult to adapt to dynamically changing heat load demands and external environmental conditions in real time. As a result, when the system faces load fluctuations or complex working conditions, the energy consumption is high, the heat storage efficiency is low, and the overall energy efficiency is difficult to achieve the optimal state.

[0006] The heat storage devices of traditional heat pump systems mostly use a single phase change material or fixed flow control, which makes it difficult to cover a wide range of heating needs or adapt to complex working conditions. The heat storage temperature range of a single phase change material is limited, and the fixed flow control cannot be dynamically adjusted according to the real-time working conditions, resulting in low heat storage efficiency, large irreversible losses in the thermodynamic process, and serious heat waste. Summary of the Invention

[0007] In view of the above situation, in order to overcome the defects of the prior art, the present invention provides an air source heat pump automatic control system and a system protection method to at least partially solve the above technical problems.

[0008] The technical solution adopted by the present invention is as follows:

[0009] The present invention proposes an air source heat pump automatic control system, comprising:

[0010] Data acquisition module, big data analysis module, dynamic optimization module, heat storage control module, heat exchange enhancement module, operation mode switching module, feedback correction module, cloud storage and communication module and system protection module, including:

[0011] The data acquisition module is used to collect multi-dimensional operating parameters in real time, including environmental parameters (outdoor temperature, humidity, wind speed), heat pump operating parameters (compressor frequency, circulating pump flow, refrigerant pressure), thermal storage device status parameters (thermal storage medium temperature, flow, phase change state), and user-side heat load demand parameters;

[0012] The big data analysis module uses machine learning algorithms (such as long short-term memory networks (LSTMs) or gradient boosting trees) to analyze collected multi-dimensional operating parameters in real time, build a high-precision heat load forecasting model, and predict heat load demand for the next 1-24 hours with a prediction error of less than 5%.

[0013] The dynamic optimization module uses genetic algorithms or particle swarm optimization algorithms to dynamically optimize the compressor frequency, circulation pump flow rate, and thermal storage medium distribution ratio. While meeting operational constraints (such as equipment power limit and temperature range), it minimizes energy consumption and maximizes thermal storage efficiency. Overall energy consumption is reduced by 15%-25% compared to traditional systems.

[0014] The heat storage control module includes multi-stage phase-change thermal storage materials (phase change temperature range 20°C-80°C) and an intelligent distribution valve. By dynamically adjusting the flow of the thermal storage medium, it optimizes the thermodynamic process of heat storage and release, reduces heat loss, and improves heat storage efficiency by 10%-15%.

[0015] Heat exchange enhancement module, including a nano-scale hydrophilic coating on the surface of the heat exchange fins, is used to reduce the adhesion of condensed water droplets, reduce heat exchange thermal resistance, and improve heat exchange efficiency by 10%-15%;

[0016] An operating mode switching module is used to achieve seamless switching between high-efficiency heat storage mode, stable heating mode, and fast response mode. The fast response mode shortens the system response time to less than 5 minutes, and the stable heating mode reduces operating fluctuations by maintaining a constant temperature in the heat storage device.

[0017] The feedback correction module performs online correction of the heat load prediction model and dynamic optimization model based on the real-time collected state parameters of the heat storage device and the actual heat load value in a cycle of 5-15 minutes, and the correction error is controlled within 3%;

[0018] Cloud storage and communication module, used to store real-time operation data, training data sets and model parameters, and regularly update prediction models and optimization models through the cloud to ensure high accuracy and stability of long-term system operation;

[0019] The system protection module, including the overload protection unit, the anomaly detection unit and the fault warning unit, is used to monitor the system operation status in real time, identify abnormal working conditions and implement protection measures to prevent equipment damage or operation failure.

[0020] In one embodiment of the present invention, the air source heat pump automatic control system, the big data analysis module further includes a feature extraction unit and a model training unit, wherein:

[0021] The feature extraction unit extracts highly correlated features (such as the correlation coefficient between ambient temperature and heat load, and the correlation coefficient between compressor frequency and energy consumption) from multi-dimensional operating parameters through principal component analysis (PCA) or correlation analysis, thereby reducing the computational complexity of the model.

[0022] The model training unit adopts an online learning mechanism to dynamically update the parameters of the heat load prediction model based on real-time collected data and historical operation data to adapt to changes in climate conditions, operating scenarios or equipment performance. The model prediction accuracy remains above 95% in long-term operation.

[0023] In one embodiment of the present invention, the air source heat pump automatic control system, the dynamic optimization module further includes a multi-objective optimization unit and a constraint processing unit, wherein:

[0024] The multi-objective optimization unit takes minimizing energy consumption and maximizing heat storage efficiency as its optimization goals, comprehensively considers the electricity cost during off-peak electricity price periods, and prioritizes the high-efficiency heat storage mode, reducing operating costs by 20%-30%;

[0025] The constraint processing unit generates a dynamic optimization plan based on the equipment operating limits (such as the maximum frequency of the compressor and the maximum flow of the circulation pump) and user-side requirements (such as the minimum heating temperature) to ensure system operation safety and heating quality.

[0026] In one embodiment of the present invention, the air source heat pump automatic control system, the thermal storage control module further includes a phase change material selection unit and a flow distribution unit, wherein:

[0027] Phase change material selection unit selects thermal storage material combinations with different phase change temperatures (such as paraffin-based materials and salt materials) according to operating conditions (such as heating temperature range of 20℃-80℃), achieving efficient thermal storage in a wide temperature range;

[0028] The flow distribution unit dynamically adjusts the medium flow of the multi-stage phase change thermal storage material through an intelligent distribution valve according to the real-time heat load demand and the status of the heat storage device, reducing heat loss and improving the heat storage efficiency by 15%-20% compared with the traditional single phase change material system.

[0029] In one embodiment of the present invention, the air source heat pump automatic control system, the heat exchange enhancement module further includes a heat exchange structure optimization unit, wherein:

[0030] The heat exchange fins adopt micro-channel design, which increases the heat exchange area by 10%-15% and improves the heat exchange efficiency;

[0031] The surface energy of the nano-scale hydrophilic coating is less than 20mN / m, and the contact angle of condensed water droplets is less than 10°, which effectively reduces the residence time of condensed water droplets and reduces the heat transfer thermal resistance. The overall heat transfer efficiency is increased by 12%-18% compared with traditional heat exchangers.

[0032] In one embodiment of the present invention, the air source heat pump automatic control system, the operation mode switching module further includes a mode decision unit and a response execution unit, wherein:

[0033] The mode decision unit automatically selects the high-efficiency heat storage mode, stable heating mode or fast response mode based on the real-time heat load forecast results and electricity price period;

[0034] The response execution unit achieves rapid response of mode switching by adjusting the compressor frequency and circulation pump flow. The switching of the rapid response mode takes 3-5 minutes, and the operating fluctuation is controlled within ±2℃.

[0035] In one embodiment of the present invention, the air source heat pump automatic control system, the system protection module further comprises:

[0036] The overload protection unit monitors the compressor current, refrigerant pressure, and circulating pump power in real time. When the parameters exceed the safety threshold (such as the current exceeds 120% of the rated value), it automatically reduces the operating load or shuts down for protection.

[0037] The anomaly detection unit, based on an anomaly detection algorithm (such as the isolation forest algorithm), identifies abnormal fluctuations in operating parameters (such as sudden changes in refrigerant pressure and abnormal heat storage medium flow) and triggers an early warning;

[0038] The fault warning unit predicts potential faults (such as compressor aging and heat exchanger fouling) by analyzing historical operating data and real-time status, and sends maintenance recommendations in advance, reducing the system failure rate by 20%-30%.

[0039] In one embodiment of the present invention, a protection method for an air source heat pump automatic control system comprises the following steps:

[0040] Step 1: Real-time monitoring: Real-time collection of environmental parameters, heat pump operating parameters and heat storage device status parameters through the data acquisition module;

[0041] Step 2: Anomaly Identification: Utilize the anomaly detection unit, based on the isolation forest algorithm or support vector machine algorithm, to analyze abnormal fluctuations in operating parameters and identify potential faults or operational risks.

[0042] Step 3: Protection execution: When an abnormal operating condition is detected (such as compressor overload, abnormal refrigerant pressure), the system protection module automatically executes protection measures, including reducing the operating load, adjusting the operating mode or shutting down for protection;

[0043] Step 4: Fault Warning: Based on historical operating data and real-time status, predict the risk of equipment aging or performance degradation and push maintenance recommendations in advance, with a warning accuracy rate of over 90%;

[0044] Step 5. Log Recording: Through the cloud storage and communication module, record abnormal events and the implementation of protection measures to provide data support for subsequent system optimization.

[0045] In one embodiment of the present invention, the protection method of the air source heat pump automatic control system, the abnormality identification step further comprises:

[0046] S1. Establish a baseline model of normal operating parameters based on the statistical distribution of historical operating data (e.g., mean, standard deviation);

[0047] S2. Calculate the deviation between the operating parameters and the baseline model in real time. When the deviation exceeds a preset threshold (e.g., the refrigerant pressure deviation exceeds ±10%), it is determined to be an abnormal operating condition.

[0048] S3. Classify abnormal operating conditions (such as transient abnormalities and continuous abnormalities) and trigger different levels of protection measures (such as warnings, load reduction or shutdown) according to the abnormality type.

[0049] In one embodiment of the present invention, the protection method of the air source heat pump automatic control system, the protection execution step further includes a dynamic adjustment mechanism, wherein:

[0050] When a slight anomaly is detected (such as fluctuations in the circulation pump flow), the system adjusts operating parameters (such as reducing the pump speed by 10%-20%) through the dynamic optimization module to maintain system operation;

[0051] When a serious anomaly is detected (such as compressor overload), the system automatically switches to safe mode, suspends high-load operation, and returns to a stable state within 5 minutes;

[0052] After the protection is executed, the feedback correction module evaluates the response effect of the abnormal event, optimizes the subsequent protection strategy, and reduces the false protection rate to below 5%.

[0053] The beneficial effects of the technical solution of the present invention are:

[0054] The present invention uses advanced machine learning algorithms (such as long short-term memory networks (LSTMs) or gradient boosting trees) through a big data analysis module to perform real-time analysis of multi-dimensional operating parameters, construct a high-precision heat load forecasting model, and predict heat load demand for the next 1-24 hours, with a prediction error within 5%. Compared to the defects of traditional heat pump systems that rely on fixed control strategies or simple empirical models, this module uses a deep learning algorithm to explore the complex nonlinear relationships between operating parameters, significantly improving the accuracy and robustness of heat load forecasting. The prediction error is controlled within 5%, enabling the system to optimize operating strategies in advance, reducing energy waste or insufficient heating caused by load forecast deviations, and providing accurate decision-making basis for the dynamic optimization module and thermal storage control module.

[0055] The present invention uses a genetic algorithm or particle swarm optimization algorithm through a dynamic optimization module to dynamically adjust the compressor frequency, circulation pump flow rate, and heat storage medium distribution ratio. Under the premise of meeting operating constraints (such as equipment power limit and temperature range), it minimizes energy consumption and maximizes heat storage efficiency. The overall energy consumption is reduced by 15%-25% compared to traditional systems. Traditional heat pump systems usually use fixed or semi-fixed operating parameters, which are difficult to adapt to dynamically changing load demands and environmental conditions, resulting in high energy consumption or low heat storage efficiency. By optimizing the core operating parameters in real time, it is ensured that the system always operates at the optimal energy efficiency state while taking into account the improvement of heat storage efficiency.

[0056] This invention optimizes the thermodynamic process of heat storage and release through the synergistic effect of multi-stage phase-change thermal storage materials (phase change temperature range 20°C-80°C) and intelligent distribution valves, increasing heat storage efficiency by 10%-15% and significantly reducing heat loss. Traditional heat pump systems' thermal storage devices typically use a single phase-change material or fixed flow control, making them difficult to adapt to a wide range of heating needs or complex operating conditions, resulting in low heat storage efficiency or heat waste. This module, through the rational configuration of multi-stage phase-change materials, covers heat storage needs in different temperature ranges. Simultaneously, the intelligent distribution valve dynamically adjusts the flow of the thermal storage medium based on real-time operating conditions, further reducing irreversible losses in the thermodynamic process.

[0057] The present invention reduces the adhesion of condensed water droplets and reduces the heat exchange thermal resistance by coating the surface of the heat exchange fins. The heat exchange efficiency is improved by 10%-15%. When a traditional heat pump system operates in a humid environment, condensed water droplets are easily retained on the surface of the heat exchanger, forming thermal resistance and reducing the heat exchange efficiency. The hydrophilic coating technology of this module improves the wetting properties of the heat exchange surface, allowing the condensed water to slide off quickly, keeping the heat exchanger surface clean, thereby significantly improving the heat exchange efficiency.

[0058] The present invention realizes seamless switching among efficient heat storage mode, stable heating mode and fast response mode through the operation mode switching module. The fast response mode shortens the system response time to less than 5 minutes, and the stable heating mode reduces operation fluctuations by maintaining the constant temperature of the heat storage device. This module automatically switches modes according to real-time load demand and operating conditions through intelligent control logic, significantly improving the flexibility and adaptability of the system. The implementation of the fast response mode shortens the system's response time to sudden load changes, and is particularly suitable for scenarios where the user's heat load fluctuates violently; the stable heating mode reduces operation fluctuations through constant temperature control, thereby improving the heating quality and user comfort.

[0059] This invention uses a feedback correction module to perform online corrections of the heat load prediction model and dynamic optimization model every 5-15 minutes based on real-time data collected from the thermal storage device's status parameters and actual heat load. This correction error is kept within 3%. Traditional heat pump system control models are typically static or semi-static, making them difficult to adapt to model drift caused by equipment aging or environmental changes during long-term operation. This module uses an online correction mechanism to update the parameters of the prediction and optimization models in real time, ensuring the system maintains high accuracy and stability over long-term operation.

[0060] Additional aspects and advantages of the present invention will be set forth in part in the description which follows and, in part, will be obvious from the description which follows, or may be learned through practice of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0061] The above and / or additional aspects and advantages of the present invention will become apparent and readily understood from the following description of the embodiments in conjunction with the accompanying drawings, in which:

[0062] Figure 1 A schematic diagram of an air source heat pump automatic control system according to an embodiment of the present invention;

[0063] Figure 2 This is a schematic diagram of a protection method for an air source heat pump automatic control system proposed in an embodiment of the present invention. DETAILED DESCRIPTION

[0064] The following describes embodiments of the present invention in detail, examples of which are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are intended to be used to explain the present invention, and are not to be construed as limiting the present invention.

[0065] An air source heat pump automatic control system and a system protection method according to an embodiment of the present invention will be described below with reference to the accompanying drawings.

[0066] like Figures 1 to 2As shown, an embodiment of the present invention provides an air source heat pump automatic control system, comprising:

[0067] Data acquisition module, big data analysis module, dynamic optimization module, heat storage control module, heat exchange enhancement module, operation mode switching module, feedback correction module, cloud storage and communication module and system protection module, including:

[0068] The data acquisition module is used to collect multi-dimensional operating parameters in real time, including environmental parameters (outdoor temperature, humidity, wind speed), heat pump operating parameters (compressor frequency, circulating pump flow, refrigerant pressure), thermal storage device status parameters (thermal storage medium temperature, flow, phase change state), and user-side heat load demand parameters;

[0069] The big data analysis module uses machine learning algorithms (such as long short-term memory networks (LSTMs) or gradient boosting trees) to analyze collected multi-dimensional operating parameters in real time, build a high-precision heat load forecasting model, and predict heat load demand for the next 1-24 hours with a prediction error of less than 5%.

[0070] The dynamic optimization module uses genetic algorithms or particle swarm optimization algorithms to dynamically optimize the compressor frequency, circulation pump flow rate, and thermal storage medium distribution ratio. While meeting operational constraints (such as equipment power limit and temperature range), it minimizes energy consumption and maximizes thermal storage efficiency. Overall energy consumption is reduced by 15%-25% compared to traditional systems.

[0071] The heat storage control module includes multi-stage phase-change thermal storage materials (phase change temperature range 20°C-80°C) and an intelligent distribution valve. By dynamically adjusting the flow of the thermal storage medium, it optimizes the thermodynamic process of heat storage and release, reduces heat loss, and improves heat storage efficiency by 10%-15%.

[0072] Heat exchange enhancement module, including a nano-scale hydrophilic coating on the surface of the heat exchange fins, is used to reduce the adhesion of condensed water droplets, reduce heat exchange thermal resistance, and improve heat exchange efficiency by 10%-15%;

[0073] An operating mode switching module is used to achieve seamless switching between high-efficiency heat storage mode, stable heating mode, and fast response mode. The fast response mode shortens the system response time to less than 5 minutes, and the stable heating mode reduces operating fluctuations by maintaining a constant temperature in the heat storage device.

[0074] The feedback correction module performs online correction of the heat load prediction model and dynamic optimization model based on the real-time collected state parameters of the heat storage device and the actual heat load value in a cycle of 5-15 minutes, and the correction error is controlled within 3%;

[0075] Cloud storage and communication module, used to store real-time operation data, training data sets and model parameters, and regularly update prediction models and optimization models through the cloud to ensure high accuracy and stability of long-term system operation;

[0076] The system protection module, including the overload protection unit, the anomaly detection unit and the fault warning unit, is used to monitor the system operation status in real time, identify abnormal working conditions and implement protection measures to prevent equipment damage or operation failure.

[0077] In specific applications of the embodiments of the present invention, the data acquisition module collects multi-dimensional operating parameters in real time, including environmental parameters (outdoor temperature, humidity, wind speed), heat pump operating parameters (compressor frequency, circulating pump flow, refrigerant pressure), heat storage device state parameters (heat storage medium temperature, flow, phase change state) and user-side heat load demand parameters. The parameters are collected through high-precision sensors (such as temperature sensor accuracy of ±.1°C and pressure sensor accuracy of ±.5%) to ensure that the data is comprehensive and accurate, providing a reliable basis for subsequent analysis and optimization. The acquisition frequency can be dynamically adjusted according to the system operation mode (such as the acquisition frequency is increased to 1 time per second in fast response mode) to adapt to data requirements under different working conditions.

[0078] Based on the collected multidimensional data, the big data analysis module uses advanced machine learning algorithms (such as long short-term memory networks (LSTMs) or gradient boosted trees (GBDTs)) for real-time analysis. By deeply mining historical and real-time data, it builds a high-precision heat load forecasting model that can predict user heat load demand for the next 1-24 hours with a prediction error of less than 5%. The forecasting model considers the nonlinear effects of environmental parameters, the dynamic changes in heat pump operating parameters, and the cyclical characteristics of user-side demand. Through multi-dimensional feature fusion and time series analysis, it significantly improves the robustness and accuracy of the forecast. For example, by capturing long-term dependencies, the LSTM model can effectively respond to sudden changes in heat load caused by outdoor temperature fluctuations or changes in user behavior.

[0079] Based on the prediction results, the dynamic optimization module uses genetic algorithms or particle swarm optimization algorithms to dynamically optimize the operating parameters of the heat pump system, including compressor frequency, circulating pump flow rate, and thermal storage medium distribution ratio. The optimization goal is to minimize energy consumption and maximize thermal storage efficiency while meeting operational constraints (such as equipment power limit and temperature range). The optimization process fully considers the nonlinear characteristics of the heat pump system and generates a Pareto optimal solution set through multi-objective optimization (such as energy consumption, efficiency, and stability), from which the optimal control strategy is selected. Compared with traditional fixed parameter control, this module can reduce overall energy consumption by 15%-25% while improving the system's operating efficiency and stability.

[0080] The heat storage control module includes multi-stage phase change heat storage materials (phase change temperature range 20℃-80℃) and intelligent distribution valves. The module dynamically adjusts the flow of heat storage medium to optimize the thermodynamic process of heat storage and release, thereby reducing heat loss. The selection of phase change materials takes into account the heat load requirements of different temperature ranges (such as low temperature 20℃-40℃, medium temperature 40℃-60℃, and high temperature 60℃-80℃). Through multi-stage phase change, hierarchical storage and efficient release of heat are achieved. The intelligent distribution valve accurately controls the distribution ratio of the heat storage medium according to the instructions of the dynamic optimization module, thereby improving the heat storage efficiency by 10%-15%.

[0081] To improve heat exchange efficiency, the heat exchange enhancement module applies a nano-scale hydrophilic coating to the surface of the heat exchange fins. This coating significantly reduces the heat exchange resistance by reducing the adhesion of condensed water droplets. Experiments have shown that this coating can increase heat exchange efficiency by 10%-15%, while also reducing the risk of frost on the heat exchanger surface. Combined with optimized circulation pump flow and refrigerant pressure control, the module further improves the overall thermodynamic performance of the system. The operating mode switching module enables seamless switching between high-efficiency heat storage mode, stable heating mode, and rapid response mode to meet operating requirements under different operating conditions. In high-efficiency heat storage mode, the system prioritizes storing excess heat in the heat storage device; in stable heating mode, by maintaining a constant temperature in the heat storage device, operating fluctuations are reduced, ensuring the quality of heating on the user side; in rapid response mode, the system shortens the response time to less than 5 minutes by increasing the compressor frequency and circulation pump flow, making it suitable for scenarios with sudden changes in heat load (such as a sudden increase in user heating demand).

[0082] To ensure the long-term accuracy of prediction and optimization, the feedback correction module performs online correction of the heat load prediction model and dynamic optimization model in a cycle of 5-15 minutes based on the real-time collected state parameters of the heat storage device and the actual heat load value. The correction process uses an adaptive learning algorithm (such as online gradient descent) to control the correction error within 3%. The module dynamically adjusts the model parameters through a closed-loop feedback mechanism to adapt to the influence of factors such as system aging, environmental changes or changes in user behavior, thereby ensuring the long-term high-precision operation of the system.

[0083] The cloud storage and communication module stores real-time operating data, training datasets, and model parameters in the cloud and interacts with the local system via secure communication protocols (such as TLS 1.3). The cloud regularly updates the prediction and optimization models (e.g., monthly), further improving model performance through transfer learning or incremental learning techniques, combined with the latest operating data. Furthermore, the module supports remote monitoring and diagnostics, allowing users to view system operating status in real time via mobile devices or PCs, enhancing system operability and user experience. The system protection module ensures the safety and reliability of system operation through an overload protection unit, anomaly detection unit, and fault warning unit. The overload protection unit monitors the operating status of key components such as the compressor and circulating pump in real time, automatically reducing the load or shutting down the system when current or temperature exceeds the limit. The anomaly detection unit uses statistical analysis and machine learning methods to identify abnormal operating conditions (such as refrigerant leaks and heat exchanger frost). The fault warning unit uses trend analysis to predict potential failures (such as bearing wear and reduced heat exchange efficiency) in advance and sends warnings to users or maintenance personnel.

[0084] In one possible implementation, the air source heat pump automatic control system, the big data analysis module further includes a feature extraction unit and a model training unit, wherein:

[0085] The feature extraction unit extracts highly correlated features (such as the correlation coefficient between ambient temperature and heat load, and the correlation coefficient between compressor frequency and energy consumption) from multi-dimensional operating parameters through principal component analysis (PCA) or correlation analysis, thereby reducing the computational complexity of the model.

[0086] The model training unit adopts an online learning mechanism to dynamically update the parameters of the heat load prediction model based on real-time collected data and historical operation data to adapt to changes in climate conditions, operating scenarios or equipment performance. The model prediction accuracy remains above 95% in long-term operation.

[0087] In specific applications of embodiments of the present invention, a feature extraction unit extracts highly correlated features from multidimensional operating parameters collected during air source heat pump operation through principal component analysis (PCA) or correlation analysis. This reduces data dimensionality and model computational complexity while retaining key feature information critical to heat load prediction. These operating parameters include, but are not limited to, ambient temperature, humidity, heat load demand, compressor operating frequency, refrigerant flow rate, heat exchanger temperature difference, and system energy consumption. Using principal component analysis (PCA), the feature extraction unit performs dimensionality reduction on the multidimensional operating parameters, projecting the raw data into a low-dimensional space to generate a set of orthogonal principal component vectors that retain at least 90% of the data variance, thereby extracting features sensitive to heat load variations. For example, key features such as the correlation coefficient between ambient temperature and heat load, and the correlation coefficient between compressor frequency and energy consumption are prioritized. Furthermore, correlation analysis methods are further used to identify statistical correlations between operating parameters. For example, the Pearson correlation coefficient or the Spearman correlation coefficient is applied to quantify linear or nonlinear relationships between the parameters, thereby selecting the feature set that contributes most to heat load prediction. Through the above method, the feature extraction unit can reduce the dimension of the input data by 30%-50% while ensuring information integrity, significantly reducing the computational burden of subsequent model training while avoiding the risk of overfitting.

[0088] The model training unit is based on an online learning mechanism, combining real-time collected data and historical operating data to dynamically update the parameters of the heat load prediction model to adapt to changes in climatic conditions, operating scenarios or equipment performance, ensuring that the model prediction accuracy remains stable at above 95% in long-term operation. The unit uses machine learning algorithms (such as gradient boosting tree, long short-term memory network LSTM or support vector regression SVR) to build a heat load prediction model and realizes real-time optimization of model parameters through an online learning framework.

[0089] In the specific implementation, the model training unit first uses historical operating data (including environmental parameters, equipment operating status and actual heat load data) to perform initial model training and establish a baseline model for heat load prediction. Subsequently, the model training unit uses an incremental learning algorithm (such as online gradient descent or recursive least squares method) to dynamically adjust the model parameters based on the operating parameters obtained in real time by the data acquisition module (low-dimensional feature data processed by the feature extraction unit). For example, when the ambient temperature changes seasonally or the performance of the equipment degrades due to long-term operation, the model can quickly update the weight parameters through real-time data streams to capture new operating modes. In addition, the model training unit also introduces an adaptive learning rate mechanism to dynamically adjust the parameter update step size according to the severity of the data changes, thereby quickly responding to new data while avoiding model oscillations. The model training unit combines the weighted fusion strategy of historical data and real-time data, adjusts the weight of historical data through the time decay factor, and gives priority to the contribution of recent operating data to model updates. At the same time, the model training unit regularly evaluates the prediction error (such as mean square error (MSE) or mean absolute percentage error (MAPE). When the error exceeds the preset threshold, it triggers model retraining or structural optimization (such as adjusting the number of neural network layers or the depth of the decision tree) to ensure that the prediction accuracy remains stable at above 95% in the long term.

[0090] The feature extraction unit and the model training unit achieve highly collaborative operation through data flow and feedback loops. The output of the feature extraction unit (i.e., the set of highly correlated features after dimensionality reduction) directly serves as input to the model training unit, reducing the interference of redundant information on model training. Conversely, the model training unit analyzes the distribution characteristics of prediction errors and provides feedback to the feature extraction unit on the effectiveness of feature selection. For example, if a feature has a low contribution to the prediction, the feature extraction unit will adjust the principal component weights of the PCA or the threshold of the correlation analysis to optimize the composition of the feature set.

[0091] In a possible implementation, the air source heat pump automatic control system, the dynamic optimization module further includes a multi-objective optimization unit and a constraint processing unit, wherein:

[0092] The multi-objective optimization unit takes minimizing energy consumption and maximizing heat storage efficiency as its optimization goals, comprehensively considers the electricity cost during off-peak electricity price periods, and prioritizes the high-efficiency heat storage mode, reducing operating costs by 20%-30%;

[0093] The constraint processing unit generates a dynamic optimization plan based on the equipment operating limits (such as the maximum frequency of the compressor and the maximum flow of the circulation pump) and user-side requirements (such as the minimum heating temperature) to ensure system operation safety and heating quality.

[0094] The thermal storage control module further includes a phase change material selection unit and a flow distribution unit, wherein:

[0095] Phase change material selection unit selects thermal storage material combinations with different phase change temperatures (such as paraffin-based materials and salt materials) according to operating conditions (such as heating temperature range of 20℃-80℃), achieving efficient thermal storage in a wide temperature range;

[0096] The flow distribution unit dynamically adjusts the medium flow of the multi-stage phase change thermal storage material through an intelligent distribution valve according to the real-time heat load demand and the status of the heat storage device, reducing heat loss and improving the heat storage efficiency by 15%-20% compared with the traditional single phase change material system.

[0097] In the specific application of the embodiment of the present invention, the multi-objective optimization unit takes minimizing energy consumption and maximizing heat storage efficiency as the main optimization objectives, while comprehensively considering the electricity cost during the off-peak electricity price period, and giving priority to scheduling the high-efficiency heat storage mode. Specifically, the unit adopts a multi-objective optimization algorithm (such as the non-dominated sorting genetic algorithm NSGA-II or the particle swarm optimization PSO) to construct a multidimensional objective function that includes energy consumption, heat storage efficiency and operating cost. The energy consumption target is achieved by quantifying the compressor frequency, the circulating pump power and the power consumption of the auxiliary heating equipment; the heat storage efficiency target is determined by evaluating the heat storage and release efficiency of the phase change heat storage material; the operating cost is determined by combining the electricity price structure during the off-peak electricity price period, giving priority to arranging the heat storage device to perform high-intensity heat storage operation during the off-peak electricity price period (such as at night), thereby reducing the electricity consumption during the peak electricity price period. In order to achieve the optimization goal, the unit dynamically adjusts the compressor frequency, the circulating pump flow and the start-stop strategy of the heat storage device based on the real-time collected operating parameters (such as ambient temperature, heat load demand) and historical data. For example, during off-peak electricity price periods, the system prioritizes increasing the compressor operating frequency to increase heat storage, thereby reducing direct power supply demand during peak electricity price periods, ultimately reducing operating costs by 20%-30%.

[0098] The constraint processing unit is responsible for generating dynamic optimization solutions based on the equipment operation limits and user side requirements. The equipment operation limits include the maximum frequency of the compressor (such as 150Hz), the maximum flow rate of the circulating pump (such as 10m 3 / h) and the operating temperature range of the heat exchanger; user-side requirements include the minimum heating temperature (such as 45°C) and heating stability requirements (such as temperature fluctuations not exceeding ±1°C). The unit adopts a constrained optimization method (such as the Lagrange multiplier method or the penalty function method) to integrate the above hard constraints (such as equipment limits) and soft constraints (such as user comfort) into the multi-objective optimization framework. In the specific implementation, the constraint processing unit monitors the equipment operating status (such as compressor current, heat exchanger pressure difference) and user-side feedback (such as indoor temperature) in real time, and ensures that all constraints are met by dynamically adjusting the optimization variables (such as compressor frequency, circulating pump speed). For example, when the heat load demand surges and the heating temperature approaches the lower limit, the unit will limit the heat release rate of the heat storage device, give priority to the user-side heating demand, and thus take into account both safety and heating quality.

[0099] The multi-objective optimization unit and the constraint processing unit collaborate through iterative optimization and feedback mechanisms. The multi-objective optimization unit generates preliminary optimization solutions (such as compressor frequency and heat storage time allocation). The constraint processing unit verifies the feasibility of these solutions, eliminates solutions that violate equipment limits or user requirements, and feeds the corrected constraints back to the optimization unit, triggering a new round of optimization iterations. This closed-loop mechanism ensures that the optimization solution not only optimizes energy consumption and costs, but also meets operational safety and heating quality requirements. The thermal storage control module, through the collaborative work of the phase change material selection unit and the flow distribution unit, optimizes the heat storage and release process of the phase change thermal storage material, achieving efficient heat storage across a wide temperature range and minimizing heat loss.

[0100] The phase change material selection unit dynamically selects a combination of thermal storage materials with different phase change temperatures (such as paraffin-based materials and salt materials) according to the operating conditions (such as the heating temperature range of 20℃-80℃) to achieve efficient thermal storage in a wide temperature range. Phase change materials can store or release a large amount of latent heat due to their phase change at a specific temperature. The unit uses a material database and matching algorithm based on real-time data of the operating conditions (such as heat load demand, heating temperature) and the status of the thermal storage device to dynamically select the best phase change material combination. For example, under low-temperature heating conditions (20℃-40℃), paraffin-based materials with lower phase change temperatures are preferred to increase the thermal storage response speed; under high-temperature heating conditions (60℃-80℃), salt materials with higher phase change temperatures are combined to increase the thermal storage capacity.

[0101] The flow distribution unit dynamically adjusts the medium flow of the multi-stage phase change thermal storage material through the intelligent distribution valve according to the real-time heat load demand and the state of the heat storage device, thereby reducing heat loss and improving heat storage efficiency. The unit adopts a flow optimization algorithm (such as model predictive control MPC), combined with the heat distribution state of the heat storage device (such as the heat storage saturation of each phase change material unit) and the user-side heat load demand, to calculate and adjust the flow distribution of the medium (such as water or heat transfer oil) between different phase change material units in real time. For example, when a phase change material unit is close to heat storage saturation, the unit reduces its medium flow through the intelligent distribution valve, and preferentially distributes heat to other unsaturated material units, thereby optimizing the overall heat storage efficiency. In addition, the flow distribution unit dynamically adjusts the valve opening to reduce pipeline heat loss and pumping energy consumption by monitoring the real-time data of the heat exchanger temperature difference and medium flow. The phase-change material selection unit and the flow distribution unit collaborate through information sharing and dynamic adjustment. After selecting the appropriate material combination based on the operating conditions, the phase-change material selection unit transmits parameters such as phase change temperature and heat storage capacity to the flow distribution unit. The flow distribution unit optimizes the medium flow distribution strategy based on these parameters and the real-time heat load demand. Conversely, the flow distribution unit's operating data (such as the heat storage efficiency of each material unit) is fed back to the phase-change material selection unit to adjust the material combination strategy.

[0102] The dynamic optimization module and the thermal storage control module form an overall collaborative mechanism through the interaction of data flows and control instructions. The optimization scheme generated by the dynamic optimization module (such as compressor frequency and thermal storage time distribution) directly guides the operation strategy of the thermal storage control module. The operating status of the thermal storage control module (such as the thermal storage saturation of the phase change material and the medium flow distribution) is input into the dynamic optimization module as feedback data to modify the optimization objectives and constraints. For example, during off-peak electricity price periods, the dynamic optimization module prioritizes high-intensity thermal storage mode, and the thermal storage control module achieves efficient thermal storage by selecting high-temperature phase change materials and optimizing flow distribution. When the heat load demand on the user side increases, the dynamic optimization module adjusts the thermal storage release priority, and the thermal storage control module quickly responds to the heat release demand through the flow distribution unit.

[0103] In one possible embodiment, the air source heat pump automatic control system, the heat exchange enhancement module further includes a heat exchange structure optimization unit, wherein:

[0104] The heat exchange fins adopt micro-channel design, which increases the heat exchange area by 10%-15% and improves the heat exchange efficiency;

[0105] The surface energy of the nano-scale hydrophilic coating is less than 20mN / m, and the contact angle of condensed water droplets is less than 10°, which effectively reduces the residence time of condensed water droplets and reduces the heat transfer thermal resistance. The overall heat transfer efficiency is increased by 12%-18% compared with traditional heat exchangers.

[0106] The operation mode switching module further includes a mode decision unit and a response execution unit, wherein:

[0107] The mode decision unit automatically selects the high-efficiency heat storage mode, stable heating mode or fast response mode based on the real-time heat load forecast results and electricity price period;

[0108] The response execution unit achieves rapid response of mode switching by adjusting the compressor frequency and circulation pump flow. The switching of the rapid response mode takes 3-5 minutes, and the operating fluctuation is controlled within ±2℃.

[0109] The system protection module further includes:

[0110] The overload protection unit monitors the compressor current, refrigerant pressure, and circulating pump power in real time. When the parameters exceed the safety threshold (such as the current exceeds 120% of the rated value), it automatically reduces the operating load or shuts down for protection.

[0111] The anomaly detection unit, based on an anomaly detection algorithm (such as the isolation forest algorithm), identifies abnormal fluctuations in operating parameters (such as sudden changes in refrigerant pressure and abnormal heat storage medium flow) and triggers an early warning;

[0112] The fault warning unit predicts potential faults (such as compressor aging and heat exchanger fouling) by analyzing historical operating data and real-time status, and sends maintenance recommendations in advance, reducing the system failure rate by 20%-30%.

[0113] In specific applications, the embodiments of the present invention significantly improve heat exchange performance in the heat exchange enhancement module by improving the design and surface characteristics of the heat exchange fins. The heat exchange fins use microchannels to form multiple tiny flow channels in a limited space, which increases the heat exchange area by 10%-15% compared to the traditional fin structure, thereby enhancing the heat transfer capacity. At the same time, the surface of the heat exchange fins is coated with a nano-scale hydrophilic coating. The surface energy of the coating is controlled to be less than 20mN / m, so that the contact angle between the condensed water droplets and the fin surface is less than 10°. The ultra-low contact angle characteristic can significantly reduce the residence time of the condensed water droplets on the heat exchange surface and reduce the heat exchange thermal resistance formed by the accumulation of water droplets. Compared with traditional heat exchangers, this heat exchange structure optimization unit improves the overall heat exchange efficiency by 12%-18% through the synergistic effect of microchannel design and nano-coating, effectively improving the heat output capacity of the air source heat pump and reducing energy consumption.

[0114] In the operation mode switching module, the mode decision unit automatically selects the appropriate operation mode based on the real-time heat load forecast results and the dynamic changes in electricity prices during the period, including high-efficiency heat storage mode, stable heating mode and fast response mode. Among them, the high-efficiency heat storage mode is suitable for periods of low electricity prices, reducing operating costs by increasing the amount of heat stored; the stable heating mode is suitable for conventional heat load requirements, ensuring the continuous stability of temperature output; the fast response mode provides instant adjustment capabilities for sudden changes in heat load. The response execution unit achieves rapid switching of the above modes by precisely controlling the compressor frequency and circulating pump flow. Among them, the switching of the fast response mode is within 3-5 minutes, and the temperature fluctuation during operation is controlled within ±2°C. The fast and stable mode switching capability not only improves the adaptability of the system, but also significantly improves the user's comfort experience and the energy efficiency of the system.

[0115] The overload protection unit monitors key parameters such as compressor current, refrigerant pressure, and circulating pump power in real time. When it detects that a parameter exceeds a safety threshold (for example, the compressor current exceeds 120% of the rated value), it automatically reduces the operating load or performs shutdown protection to prevent equipment overload damage. The anomaly detection unit uses anomaly detection technologies such as the isolation forest algorithm to identify abnormal fluctuations in operating parameters (such as sudden changes in refrigerant pressure or abnormal heat storage medium flow) in real time and triggers early warning signals when an anomaly occurs, providing a timely basis for system maintenance. The fault warning unit predicts potential failure risks, such as compressor aging or heat exchanger scaling, through a comprehensive analysis of historical operating data and real-time status, and provides maintenance recommendations in advance.

[0116] In one possible implementation, a method for protecting an air source heat pump automatic control system includes the following steps:

[0117] Step 1: Real-time monitoring: Real-time collection of environmental parameters, heat pump operating parameters and heat storage device status parameters through the data acquisition module;

[0118] Step 2: Anomaly Identification: Utilize the anomaly detection unit, based on the isolation forest algorithm or support vector machine algorithm, to analyze abnormal fluctuations in operating parameters and identify potential faults or operational risks.

[0119] Step 3: Protection execution: When an abnormal operating condition is detected (such as compressor overload, abnormal refrigerant pressure), the system protection module automatically executes protection measures, including reducing the operating load, adjusting the operating mode or shutting down for protection;

[0120] Step 4: Fault Warning: Based on historical operating data and real-time status, predict the risk of equipment aging or performance degradation and push maintenance recommendations in advance, with a warning accuracy rate of over 90%;

[0121] Step 5. Log Recording: Through the cloud storage and communication module, record abnormal events and the implementation of protection measures to provide data support for subsequent system optimization.

[0122] In specific applications, the embodiments of the present invention use a data acquisition module to comprehensively collect key parameters of system operation through real-time monitoring steps, including environmental parameters (such as ambient temperature and humidity), heat pump operating parameters (such as compressor current, refrigerant pressure, and circulating pump power), and heat storage device status parameters (such as heat storage medium temperature and flow). The data acquisition module uses high-frequency sampling technology with a sampling frequency of 1-5 times per second to ensure the real-time and accuracy of the data, providing a reliable data basis for subsequent abnormality identification and protection execution.

[0123] In the abnormality identification step, the present invention utilizes an abnormality detection unit to perform real-time analysis of the collected operating parameters based on the isolation forest algorithm or the support vector machine algorithm to identify potential faults or operational risks. The isolation forest algorithm quickly isolates abnormal data points by constructing a random tree structure and is suitable for anomaly detection of high-dimensional data; the support vector machine algorithm accurately distinguishes between normal operating conditions and abnormal working conditions by constructing a classification hyperplane. The combination of the two algorithms enables abnormality identification to achieve high sensitivity and low false alarm rate in complex operating environments. For example, when a sudden change in refrigerant pressure is detected (such as a pressure value exceeding the normal range of ±10%) or an abnormal flow of heat storage medium is detected (such as a flow drop of more than 20%), the abnormality detection unit can complete the identification and generate an abnormal signal within 1-3 seconds.

[0124] In the protection execution step, the system protection module automatically executes corresponding protection measures based on the abnormality identification results to ensure equipment safety and system stability. When an abnormal operating condition is detected (such as the compressor current exceeds 120% of the rated value or the refrigerant pressure exceeds the safety threshold), the protection module first attempts to restore the system to a safe operating state by reducing the operating load (such as reducing the compressor frequency by 10%-20%) or adjusting the operating mode (such as switching from fast response mode to stable heating mode). If the abnormal operating condition persists or the parameters deteriorate further (such as the refrigerant pressure continues to exceed the standard for more than 5 seconds), the protection module will execute shutdown protection, cut off the power supply to key components, and avoid equipment overload damage. The response of the protection execution step is within 3-5 seconds, and the fluctuation of the operating parameters is controlled within ±2%, ensuring that the protection process minimizes interference with system operation.

[0125] In the fault warning step, the risk of equipment aging or performance degradation is predicted, and maintenance recommendations are pushed in advance. The fault warning unit uses a data-driven prediction model to identify potential fault signs, such as compressor bearing wear, heat exchanger scaling, or refrigerant leakage, by analyzing historical operating data (such as compressor operating time, heat exchanger thermal resistance change trend) and real-time status (such as refrigerant circulation efficiency, heat storage medium flow stability). The prediction accuracy of the warning model reaches more than 90%, and it can push maintenance recommendations (such as recommendations to clean the heat exchanger or replace the compressor lubricant) within 1-4 weeks before the failure occurs. Compared with traditional strategies based on fixed maintenance cycles, the fault warning step of the present invention significantly reduces maintenance costs through predictive maintenance, and reduces the system failure rate by 20%-30%, effectively extending the service life of the equipment.

[0126] In the log recording step, the present invention uses a cloud storage and communication module to comprehensively record abnormal events, the execution of protection measures and system operating parameters. The log data is stored in the form of a timestamp, including the time, type, parameter value of the abnormality, as well as the execution results of the protection measures and the system recovery status. The cloud storage module supports encrypted transmission and long-term storage of data to ensure data security and traceability. The log data not only provides detailed fault analysis basis for operation and maintenance personnel, but also can further optimize the abnormality detection model and fault prediction model through machine learning algorithms, thereby achieving continuous improvement of the system.

[0127] In one possible implementation, the protection method of the air source heat pump automatic control system, the abnormality identification step further includes:

[0128] S1. Establish a baseline model of normal operating parameters based on the statistical distribution of historical operating data (e.g., mean, standard deviation);

[0129] S2. Calculate the deviation between the operating parameters and the baseline model in real time. When the deviation exceeds a preset threshold (e.g., the refrigerant pressure deviation exceeds ±10%), it is determined to be an abnormal operating condition.

[0130] S3. Classify abnormal operating conditions (such as transient abnormalities and continuous abnormalities) and trigger different levels of protection measures (such as warnings, load reduction or shutdown) according to the abnormality type.

[0131] The protection execution step further includes a dynamic adjustment mechanism, wherein:

[0132] When a slight anomaly is detected (such as fluctuations in the circulation pump flow), the system adjusts operating parameters (such as reducing the pump speed by 10%-20%) through the dynamic optimization module to maintain system operation;

[0133] When a serious anomaly is detected (such as compressor overload), the system automatically switches to safe mode, suspends high-load operation, and returns to a stable state within 5 minutes;

[0134] After the protection is executed, the feedback correction module evaluates the response effect of the abnormal event, optimizes the subsequent protection strategy, and reduces the false protection rate to below 5%.

[0135] In a specific application, the embodiment of the present invention establishes a baseline model of normal operating parameters (S1): the present invention uses historical operating data and constructs a baseline model of normal operating parameters through statistical analysis methods (such as mean, standard deviation, probability density distribution). The baseline model covers key operating parameters, such as refrigerant pressure (unit: MPa), compressor current (unit: A), circulating pump flow (unit: m 3 / h) and heat storage medium temperature (unit: °C). The model construction process is based on at least 30 days of historical data sampling with a sampling frequency of once per minute to ensure that the model can reflect the normal behavior characteristics of the system under different environmental conditions (such as ambient temperature -10 °C to 35 °C) and operating modes (such as high load, low load).

[0136] Real-time calculation of the deviation between operating parameters and the baseline model (S2): During system operation, the data acquisition module collects operating parameters in real time at a frequency of 1-5 times per second, compares them with the baseline model, and calculates the deviation value. For example, if the deviation between the real-time refrigerant pressure value and the baseline model mean exceeds ±10% (for example, if the baseline mean is 1.5MPa and the real-time value exceeds 1.65MPa or falls below 1.35MPa), or if the circulating pump flow rate deviation exceeds ±15%, the system determines that the parameter has entered an abnormal state. The deviation calculation uses a weighted average algorithm, comprehensively considering the parameter's fluctuation trend and duration to avoid misjudgment due to transient noise.

[0137] Abnormal operating condition classification and protection triggering (S3): The present invention classifies the detected abnormal operating conditions, including instantaneous abnormalities (such as short-term fluctuations in refrigerant pressure, lasting less than 5 seconds) and continuous abnormalities (such as compressor current continuously exceeding the standard for more than 10 seconds). The abnormality detection unit is based on the isolation forest algorithm or the support vector machine algorithm to further analyze the characteristic vectors of the abnormality (such as fluctuation amplitude, duration, and changes in related parameters) to achieve accurate classification of abnormality types. According to the classification results, the system triggers different levels of protection measures: instantaneous abnormalities trigger warning signals to prompt the operation and maintenance personnel to pay attention; continuous abnormalities trigger load reduction protection (such as reducing the compressor frequency by 15%); serious abnormalities (such as refrigerant pressure continuously exceeding the standard for 20 seconds) trigger shutdown protection. The response time of abnormality classification is controlled within 1-2 seconds, and the classification accuracy rate reaches more than 95%.

[0138] When a mild anomaly is detected (such as a 10%-15% fluctuation in the circulation pump flow), the system adjusts the operating parameters in real time through the dynamic optimization module. For example, the dynamic optimization module can reduce the circulation pump speed by 10%-20% (such as from 300rpm to 240-270rpm) according to the amplitude of the flow fluctuation, while increasing the cycle period of the heat exchanger to maintain the thermal balance of the system. The response of the adjustment process is within 3 seconds, and the parameter fluctuation is controlled within ±2%, ensuring that the system can continue to operate stably after the abnormality occurs. The dynamic adjustment mechanism uses a closed-loop control algorithm to dynamically optimize the adjustment range according to real-time feedback data (such as flow recovery), significantly reducing the impact of mild anomalies on system performance, and improving the continuity of system operation by about 25%.

[0139] When a serious anomaly is detected (such as the compressor current exceeding 120% of the rated value for more than 5 seconds), the system automatically switches to safe mode, suspends the operation of high-load components (such as the compressor and circulation pump), and switches the system to a low-load standby state. In safe mode, the system prioritizes the safety of key components (such as releasing excessive pressure through the refrigerant bypass valve) and assesses whether it can be restored to a stable operating state through parameter monitoring within 5 minutes (such as the refrigerant pressure returning to the normal range). The safe mode switch is executed within 5 seconds, and the recovery success rate is over 90%.

[0140] After the protection is executed, the feedback correction module evaluates the effectiveness of the response to the abnormal event, including the execution time of the protection measures, parameter recovery, and system operational stability. The evaluation results are used to optimize subsequent protection strategies, such as adjusting the deviation threshold (such as optimizing the refrigerant pressure deviation threshold from ±10% to ±8%) or updating the abnormality classification rules (such as adjusting the duration threshold of transient abnormalities from 5 seconds to 3 seconds). The feedback correction module uses machine learning algorithms (such as reinforcement learning) based on historical protection data and real-time feedback to continuously optimize the execution of protection strategies and reduce the false protection rate to below 5%.

[0141] It should be noted that, in this document, relational terms such as first and second, etc., are used only 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 "comprises," "comprising," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that includes a list of elements includes not only those elements but also other elements not explicitly listed, or elements inherent to such process, method, article, or apparatus.

[0142] The present invention and its embodiments are described above. This description is not restrictive. The drawings show only one embodiment of the present invention, and the actual structure is not limited thereto. In short, if a person skilled in the art is inspired by this and, without departing from the purpose of the present invention, designs structures and embodiments similar to this technical solution without inventiveness, they shall fall within the scope of protection of the present invention.

Claims

1. An air source heat pump automatic control system, characterized in that: include: Data acquisition module, big data analysis module, dynamic optimization module, heat storage control module, heat exchange enhancement module, operation mode switching module, feedback correction module, cloud storage and communication module and system protection module, including: The data acquisition module is used to collect multi-dimensional operating parameters in real time, including environmental parameters (outdoor temperature, humidity, wind speed), heat pump operating parameters (compressor frequency, circulating pump flow, refrigerant pressure), thermal storage device status parameters (thermal storage medium temperature, flow, phase change state), and user-side heat load demand parameters; The big data analysis module uses machine learning algorithms (such as long short-term memory networks (LSTMs) or gradient boosting trees) to analyze collected multi-dimensional operating parameters in real time, build a high-precision heat load forecasting model, and predict heat load demand for the next 1-24 hours with a prediction error of less than 5%. The dynamic optimization module uses genetic algorithms or particle swarm optimization algorithms to dynamically optimize the compressor frequency, circulation pump flow rate, and thermal storage medium distribution ratio. While meeting operational constraints (such as equipment power limit and temperature range), it minimizes energy consumption and maximizes thermal storage efficiency. Overall energy consumption is reduced by 15%-25% compared to traditional systems. The heat storage control module includes multi-stage phase-change thermal storage materials (phase change temperature range 20°C-80°C) and an intelligent distribution valve. By dynamically adjusting the flow of the thermal storage medium, it optimizes the thermodynamic process of heat storage and release, reduces heat loss, and improves heat storage efficiency by 10%-15%. Heat exchange enhancement module, including a nano-scale hydrophilic coating on the surface of the heat exchange fins, is used to reduce the adhesion of condensed water droplets, reduce heat exchange thermal resistance, and improve heat exchange efficiency by 10%-15%; An operating mode switching module is used to achieve seamless switching between high-efficiency heat storage mode, stable heating mode, and fast response mode. The fast response mode shortens the system response time to less than 5 minutes, and the stable heating mode reduces operating fluctuations by maintaining a constant temperature in the heat storage device. The feedback correction module performs online correction of the heat load prediction model and dynamic optimization model based on the real-time collected state parameters of the heat storage device and the actual heat load value in a cycle of 5-15 minutes, and the correction error is controlled within 3%; Cloud storage and communication module, used to store real-time operation data, training data sets and model parameters, and regularly update prediction models and optimization models through the cloud to ensure high accuracy and stability of long-term system operation; The system protection module, including the overload protection unit, the anomaly detection unit and the fault warning unit, is used to monitor the system operation status in real time, identify abnormal working conditions and implement protection measures to prevent equipment damage or operation failure.

2. The air source heat pump automatic control system according to claim 1, characterized in that: The big data analysis module further includes a feature extraction unit and a model training unit, wherein: The feature extraction unit extracts highly correlated features (such as the correlation coefficient between ambient temperature and heat load, and the correlation coefficient between compressor frequency and energy consumption) from multi-dimensional operating parameters through principal component analysis (PCA) or correlation analysis, thereby reducing the computational complexity of the model. The model training unit adopts an online learning mechanism to dynamically update the parameters of the heat load prediction model based on real-time collected data and historical operation data to adapt to changes in climate conditions, operating scenarios or equipment performance. The model prediction accuracy remains above 95% in long-term operation.

3. The air source heat pump automatic control system according to claim 1, characterized in that: The dynamic optimization module further includes a multi-objective optimization unit and a constraint processing unit, wherein: The multi-objective optimization unit takes minimizing energy consumption and maximizing heat storage efficiency as its optimization goals, comprehensively considers the electricity cost during off-peak electricity price periods, and prioritizes the high-efficiency heat storage mode, reducing operating costs by 20%-30%; The constraint processing unit generates a dynamic optimization plan based on the equipment operating limits (such as the maximum frequency of the compressor and the maximum flow of the circulation pump) and user-side requirements (such as the minimum heating temperature) to ensure system operation safety and heating quality.

4. The air source heat pump automatic control system according to claim 1, characterized in that: The thermal storage control module further includes a phase change material selection unit and a flow distribution unit, wherein: Phase change material selection unit selects thermal storage material combinations with different phase change temperatures (such as paraffin-based materials and salt materials) according to operating conditions (such as heating temperature range of 20℃-80℃), achieving efficient thermal storage in a wide temperature range; The flow distribution unit dynamically adjusts the medium flow of the multi-stage phase change thermal storage material through an intelligent distribution valve according to the real-time heat load demand and the status of the heat storage device, reducing heat loss and improving the heat storage efficiency by 15%-20% compared with the traditional single phase change material system.

5. The air source heat pump automatic control system according to claim 1, characterized in that: The heat exchange enhancement module further includes a heat exchange structure optimization unit, wherein: The heat exchange fins adopt micro-channel design, which increases the heat exchange area by 10%-15% and improves the heat exchange efficiency; The surface energy of the nano-scale hydrophilic coating is less than 20mN / m, and the contact angle of condensed water droplets is less than 10°, which effectively reduces the residence time of condensed water droplets and reduces the heat transfer thermal resistance. The overall heat transfer efficiency is increased by 12%-18% compared with traditional heat exchangers.

6. The air source heat pump automatic control system according to claim 1, characterized in that: The operation mode switching module further includes a mode decision unit and a response execution unit, wherein: The mode decision unit automatically selects the high-efficiency heat storage mode, stable heating mode or fast response mode based on the real-time heat load forecast results and electricity price period; The response execution unit achieves rapid response of mode switching by adjusting the compressor frequency and circulation pump flow. The switching of the rapid response mode takes 3-5 minutes, and the operating fluctuation is controlled within ±2℃.

7. The air source heat pump automatic control system according to claim 1, characterized in that: The system protection module further includes: The overload protection unit monitors the compressor current, refrigerant pressure, and circulating pump power in real time. When the parameters exceed the safety threshold (such as the current exceeds 120% of the rated value), it automatically reduces the operating load or shuts down for protection. The anomaly detection unit, based on an anomaly detection algorithm (such as the isolation forest algorithm), identifies abnormal fluctuations in operating parameters (such as sudden changes in refrigerant pressure and abnormal heat storage medium flow) and triggers an early warning; The fault warning unit predicts potential faults (such as compressor aging and heat exchanger fouling) by analyzing historical operating data and real-time status, and sends maintenance recommendations in advance, reducing the system failure rate by 20%-30%.

8. The protection method for an air source heat pump automatic control system according to any one of claims 1 to 7, characterized in that: The following steps are involved: Step 1: Real-time monitoring: Real-time collection of environmental parameters, heat pump operating parameters and heat storage device status parameters through the data acquisition module; Step 2: Anomaly Identification: Utilize the anomaly detection unit, based on the isolation forest algorithm or support vector machine algorithm, to analyze abnormal fluctuations in operating parameters and identify potential faults or operational risks. Step 3: Protection execution: When an abnormal operating condition is detected (such as compressor overload, abnormal refrigerant pressure), the system protection module automatically executes protection measures, including reducing the operating load, adjusting the operating mode or shutting down for protection; Step 4: Fault Warning: Based on historical operating data and real-time status, predict the risk of equipment aging or performance degradation and push maintenance recommendations in advance, with a warning accuracy rate of over 90%; Step 5. Log Recording: Through the cloud storage and communication module, record abnormal events and the implementation of protection measures to provide data support for subsequent system optimization.

9. The protection method of the air source heat pump automatic control system according to claim 8, characterized in that: The abnormality identification step further comprises: S1. Establish a baseline model of normal operating parameters based on the statistical distribution of historical operating data (e.g., mean, standard deviation); S2. Calculate the deviation between the operating parameters and the baseline model in real time. When the deviation exceeds a preset threshold (e.g., the refrigerant pressure deviation exceeds ±10%), it is determined to be an abnormal operating condition. S3. Classify abnormal operating conditions (such as transient abnormalities and continuous abnormalities) and trigger different levels of protection measures (such as warnings, load reduction or shutdown) according to the abnormality type.

10. The protection method of the air source heat pump automatic control system according to claim 8, characterized in that: The protection execution step further includes a dynamic adjustment mechanism, wherein: When a slight anomaly is detected (such as fluctuations in the circulation pump flow), the system adjusts operating parameters (such as reducing the pump speed by 10%-20%) through the dynamic optimization module to maintain system operation; When a serious anomaly is detected (such as compressor overload), the system automatically switches to safe mode, suspends high-load operation, and returns to a stable state within 5 minutes; After the protection is executed, the feedback correction module evaluates the response effect of the abnormal event, optimizes the subsequent protection strategy, and reduces the false protection rate to below 5%.

Images