Outlet water temperature regulation and control method and device of heat pump and heat pump

Abstract

The invention relates to the field of electric appliances, and provides an outlet water temperature regulation and control method and device of a heat pump and the heat pump, and the method comprises the steps that meteorological parameters of the current environment and historical heat load data of the heat pump are obtained; predicting the thermal load of the next time period according to the meteorological parameters and the historical thermal load data, and obtaining a predicted thermal load value; according to the predicted heat load value, the predicted supply and return water temperature difference of the heat pump is calculated; and the optimal water outlet temperature of the heat pump is determined according to the predicted water supply and return temperature difference, and operation parameters of the heat pump are dynamically adjusted based on the optimal water outlet temperature. According to the invention, the reasonability of setting the outlet water temperature can be improved, the accurate matching of the thermal load demand and the system output is realized, the operation energy efficiency and the energy-saving level of the system are improved, and the response capability to the environmental change is enhanced.

Description

Technical Field

[0001] This invention relates to the field of electrical technology, and in particular to a method for regulating the outlet water temperature of a heat pump, an outlet water temperature regulating device, and a heat pump. Background Technology

[0002] In existing technologies, the outlet water temperature in conventional heat pump systems is typically controlled using a fixed setpoint or a simple feedback control strategy based on the current indoor temperature. For example, in heating mode, the outlet water temperature is often set to 45°C and remains constant over a long period; or the pump or compressor operation is fine-tuned using proportional-integral regulation based solely on the deviation between the return water temperature and the setpoint.

[0003] This type of control method has obvious defects: First, it does not consider the dynamic impact of external environmental meteorological parameters on building heat load, resulting in the water supply temperature failing to match the actual heat demand when the environment changes drastically; Second, it ignores the load change patterns contained in the historical heat load data of the heat pump, lacks the ability to predict the heat load in the next period, and can only passively respond to the current deviation, with obvious adjustment lag.

[0004] The aforementioned defects directly lead to insufficient heating in cold weather and excessive heating in mild weather due to excessively high outlet water temperatures, which not only reduces user comfort but also significantly increases unnecessary energy consumption. Furthermore, due to the lack of a predictive proactive adjustment mechanism, the heat pump operating parameters are difficult to dynamically match with the actual load, resulting in low overall system energy efficiency. Summary of the Invention

[0005] This invention provides a method for regulating the outlet water temperature of a heat pump, an outlet water temperature regulating device, and a heat pump, to overcome the deficiencies in the prior art and achieve the following effects: improving the rationality of the outlet water temperature setting, achieving precise matching between heat load demand and system output, improving system operating energy efficiency and energy saving level, and enhancing the responsiveness to environmental changes.

[0006] In a first aspect, the present invention protects a method for regulating the outlet water temperature of a heat pump, comprising: Obtain current environmental meteorological parameters and historical heat load data of the heat pump; Based on the meteorological parameters and the historical heat load data, the heat load for the next time period is predicted, and the predicted heat load value is obtained. Based on the predicted heat load value, calculate the predicted supply and return water temperature difference of the heat pump; The optimal outlet water temperature of the heat pump is determined based on the predicted supply and return water temperature difference, and the operating parameters of the heat pump are dynamically adjusted based on the optimal outlet water temperature.

[0007] According to some embodiments of the present invention, the step of predicting the heat load for the next time period based on the meteorological parameters and the historical heat load data, and obtaining the predicted heat load value, includes: A bidirectional long short-term memory network model with incremental learning is used to predict the heat load based on the meteorological parameters and the historical heat load data, and the predicted heat load parameters are obtained. The hyperparameters of the bidirectional long short-term memory network model are automatically optimized using the whale optimization algorithm. The hyperparameters include the number of hidden layer neurons, the learning rate, and the number of training iterations.

[0008] According to some embodiments of the present invention, the meteorological parameters include at least one of indoor temperature, outdoor temperature, indoor humidity, outdoor humidity, light intensity, and seasonal factors.

[0009] According to some embodiments of the present invention, the step of calculating the predicted supply and return water temperature difference of the heat pump based on the predicted heat load value includes: The predicted supply and return water temperature difference is calculated based on the predicted heat load value using an empirical formula for heat pump units; wherein the empirical formula for heat exchange is in binomial form: In the formula, The predicted heat load value, The outlet water temperature, The inlet water temperature, That is, the predicted supply and return water temperature difference, coefficient. These are empirical parameters obtained by fitting measured data from heat pump units.

[0010] According to some embodiments of the present invention, the step of determining the optimal outlet water temperature of the heat pump based on the predicted supply and return water temperature difference includes: Obtain the range of inlet water temperature and the current outdoor temperature; Using the energy consumption model of the heat pump, based on the range of the inlet water temperature and the predicted supply and return water temperature difference, the outlet water temperature is optimized under the condition that the outdoor temperature remains unchanged, and the optimal outlet water temperature that minimizes the energy consumption of the heat pump is calculated. In the energy consumption model, the energy consumption of the heat pump is determined by the inlet water temperature and the outdoor temperature.

[0011] According to some embodiments of the present invention, the step of using the energy consumption model of the heat pump, based on the range of the inlet water temperature and the predicted supply and return water temperature difference, to perform optimization calculations on the outlet water temperature under the condition that the outdoor temperature remains constant, and calculating the optimal outlet water temperature that minimizes the energy consumption of the heat pump, includes: Iterate through multiple candidate inlet water temperature values ​​within the range of the inlet water temperature, and for each candidate inlet water temperature value, calculate the corresponding candidate outlet water temperature based on the predicted supply and return water temperature difference; The candidate inlet water temperature and the outdoor temperature are input into the energy consumption model to obtain the corresponding energy consumption. The candidate outlet water temperature that minimizes the energy consumption is selected as the optimal outlet water temperature.

[0012] According to some embodiments of the present invention, the energy consumption model is a multivariate nonlinear regression model obtained by fitting actual heat pump operating data, and its expression is: in, This indicates the energy consumption of the heat pump. The inlet water temperature, Outdoor temperature The energy consumption set coefficient is obtained by fitting historical energy consumption data, outdoor temperature, and heat pump inlet water temperature; the energy consumption set coefficient Dynamic fitting and optimization are performed using the quantum particle swarm optimization algorithm.

[0013] According to some embodiments of the present invention, the step of dynamically adjusting the operating parameters of the heat pump based on the optimal outlet water temperature includes: Based on the energy consumption model and the optimal outlet water temperature, the minimum energy consumption of the heat pump is calculated, and the compressor speed of the heat pump is dynamically adjusted based on the minimum energy consumption. And / or, using a heat exchange model between the heat pump and the indoor environment, based on the predicted supply and return water temperature difference and the predicted heat load, calculate the optimal inlet water flow rate of the heat pump, and dynamically adjust the opening of the heat pump's water valve based on the optimal inlet water flow rate. The heat transfer model is as follows: ,in To predict heat load, The outlet water temperature, The inlet water temperature, This refers to the predicted supply and return water temperature difference, where m is the optimal inlet water flow rate and c is the specific heat capacity of water.

[0014] According to some embodiments of the present invention, after the step of dynamically adjusting the operating parameters of the heat pump based on the optimal outlet water temperature, the method further includes: Establish and update the operation database, which stores the relationship between the meteorological parameters and the optimal operation parameters, including the compressor speed and the water pump valve opening. When the heat pump starts up or meteorological parameters change abruptly, the system retrieves the historical operating conditions that are closest to the current meteorological parameters from the operating database, retrieves the corresponding optimal operating parameters as the initial operating parameters, and makes dynamic adjustments in combination with a real-time optimization algorithm. After each adjustment is completed, the actual operating parameters are fed back to the operating database, and the optimal operating parameters under the corresponding meteorological parameters are updated.

[0015] Secondly, the present invention also protects a heat pump outlet water temperature control device, comprising: The acquisition module is used to acquire the current environmental meteorological parameters and the historical heat load data of the heat pump; The prediction module is used to predict the heat load for the next time period based on the meteorological parameters and the historical heat load data, and to obtain the predicted heat load value. The calculation module is used to calculate the predicted supply and return water temperature difference of the heat pump based on the predicted heat load value. The control module is used to determine the optimal outlet water temperature of the heat pump based on the predicted supply and return water temperature difference, and to dynamically adjust the operating parameters of the heat pump based on the optimal outlet water temperature.

[0016] Thirdly, the present invention also protects a heat pump, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the outlet water temperature control method of the heat pump as described in the first aspect of the present invention.

[0017] The heat pump outlet water temperature control method according to embodiments of the present invention has advantages over the prior art, such as improving the rationality of outlet water temperature setting, achieving precise matching between heat load demand and system output, improving system operating energy efficiency and energy saving level, and enhancing the ability to respond to environmental changes.

[0018] Specifically, firstly, this invention predicts the heat load for the next time period by incorporating current meteorological parameters and historical heat load data of the heat pump. This allows the outlet water temperature setting to no longer rely on fixed values ​​or delayed feedback, but rather on predictions of future heat demand, significantly enhancing the initiative and adaptability of regulation. Secondly, this invention calculates the predicted supply and return water temperature difference based on the predicted heat load value and determines the optimal outlet water temperature accordingly. This makes the heat pump's heating capacity more consistent with the actual load demand in terms of time and magnitude, effectively avoiding overheating or underheating. Thirdly, this invention dynamically adjusts operating parameters to match the optimal outlet water temperature driven by prediction, reducing ineffective energy consumption caused by temperature settings deviating from actual demand, thereby reducing overall energy consumption while meeting user comfort. Fourthly, this invention uses meteorological parameters as one of the control bases, enabling the system to promptly sense and respond to dynamic changes in the outdoor environment. It maintains stable and efficient operating performance even under conditions such as sudden drops in temperature and sudden changes in sunlight, overcoming the blind spots of traditional methods under complex meteorological conditions. Attached Figure Description

[0019] To more clearly illustrate the technical solutions in this invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of this invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0020] Figure 1 This is one of the flowcharts illustrating the heat pump outlet water temperature control method provided by the present invention.

[0021] Figure 2 This is the second schematic diagram of the heat pump outlet water temperature control method provided by the present invention.

[0022] Figure 3 This is a flowchart of the incremental load prediction process provided by the present invention.

[0023] Figure 4 This is a schematic diagram of the Bi-LSTM provided by the present invention.

[0024] Figure 5 This is a flowchart of the WOA parameter optimization LSTM provided by the present invention.

[0025] Figure 6 This is the third flowchart of the heat pump outlet water temperature control method provided by the present invention.

[0026] Figure 7 This is one of the schematic diagrams of a partial process for controlling the outlet water temperature of a heat pump provided by the present invention.

[0027] Figure 8This is a flowchart of the QPSO algorithm optimization process provided by the present invention.

[0028] Figure 9 This is a partial flowchart of the heat pump outlet water temperature control method provided by the present invention.

[0029] Figure 10 This is a schematic diagram of the outlet water temperature control device of the heat pump provided by the present invention.

[0030] Figure 11 This is a schematic diagram of the structure of the heat pump provided by the present invention. Detailed Implementation

[0031] To make the objectives, technical solutions, and advantages of this invention clearer, the technical solutions of this invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of this invention. All other embodiments obtained by those skilled in the art based on the embodiments of this invention without creative effort are within the scope of protection of this invention.

[0032] In the description of this specification, the references to terms such as "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., refer to specific features, structures, materials, or characteristics described in connection with that embodiment or example, which are included in at least one embodiment or example of the present invention. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples. Moreover, without contradiction, those skilled in the art can combine and integrate the different embodiments or examples described in this specification, as well as the features of different embodiments or examples.

[0033] The method for regulating the outlet water temperature of a heat pump proposed in this invention is described below with reference to the accompanying drawings. Before providing a detailed description of the embodiments of this invention, the overall application scenario is first described. The heat pump outlet water temperature regulation method, regulation device, electronic device, and computer-readable storage medium of this invention can be applied locally to the heat pump, to cloud platforms in the Internet field, or to other types of cloud platforms in the Internet field, or to third-party devices. These third-party devices may include various types such as mobile phones, tablets, laptops, in-vehicle computers, and other smart terminals.

[0034] The following description uses only the outlet water temperature control method applicable to heat pumps as an example. It should be understood that the control method of this embodiment can also be applied to cloud platforms and third-party devices.

[0035] like Figures 1 to 9 As shown, the method for regulating the outlet water temperature of a heat pump according to a first aspect embodiment of the present invention includes: Step S1: Obtain the current environmental meteorological parameters and the historical heat load data of the heat pump.

[0036] Meteorological parameters refer to external environmental variables that affect building heat load, including but not limited to outdoor temperature, outdoor relative humidity, solar radiation intensity, wind speed, and seasonal factors. Historical heat load data for a heat pump refers to the amount of heat or cooling provided to the indoor environment per unit time during past operation of the heat pump system. It is typically measured in kilowatts (kW) and recorded in a time series, with a time resolution generally ranging from 5 minutes to 1 hour. For example, the system collects current meteorological parameters in real time through outdoor temperature and humidity sensors and light sensors; simultaneously, it reads heat load data recorded every 10 minutes over the past 7 days from a local controller or cloud database, forming a historical dataset containing timestamps, load values, and corresponding meteorological conditions.

[0037] It is understandable that step S1 provides basic input data for subsequent heat load forecasting. Meteorological parameters reflect the dynamic impact of the external environment on building heat demand, while historical heat load data reflects the inherent laws of system operation. Combining the two can effectively improve the forecasting model's adaptability to complex operating conditions, which is a prerequisite for achieving intelligent control.

[0038] Step S2: Based on meteorological parameters and historical heat load data, predict the heat load for the next time period and obtain the predicted heat load value.

[0039] The "next time period" refers to the future time window in which the heat pump control system will implement regulation, typically 15 minutes, 30 minutes, or 1 hour, consistent with the control cycle. The predicted heat load value is an estimate, expressed in kW, of the building's required heating (or cooling) capacity for that future time period based on current and historical information. For example, by inputting currently collected outdoor temperature, humidity, and light intensity along with the historical heat load sequence of the past 48 hours into a pre-trained bidirectional long short-term memory network model, the model outputs the predicted heat load value for the next hour.

[0040] Thus, step S2, by integrating meteorological disturbances and load timing characteristics, achieves a forward-looking prediction of heat demand, avoiding over- or under-adjustment problems caused by delayed response in traditional control. It should be noted that accurate heat load forecasting is the foundation for subsequent calculations of the optimal outlet water temperature, directly determining system energy efficiency and comfort.

[0041] Step S3: Calculate the predicted supply and return water temperature difference of the heat pump based on the predicted heat load value.

[0042] The predicted supply and return water temperature difference refers to the difference between the heat pump outlet water temperature (supply water temperature) and the return water temperature (inlet water temperature), expressed in °C. This temperature difference reflects the amount of heat carried per unit flow rate of water. The predicted supply and return water temperature difference is a theoretical temperature difference derived from the predicted heat load value, combined with the water flow rate and specific heat capacity of water, through a heat balance relationship. Step S3 above is used to transform the abstract heat load demand into executable thermal parameters for the heat pump water system.

[0043] Step S4: Determine the optimal outlet water temperature of the heat pump based on the predicted supply and return water temperature difference, and dynamically adjust the operating parameters of the heat pump based on the optimal outlet water temperature.

[0044] The optimal outlet water temperature refers to the setpoint value that minimizes the overall energy consumption of the heat pump system while meeting the predicted heat load, and is measured in °C. Operating parameters mainly include compressor speed, pump frequency, and water valve opening, which are used to adjust the heat pump's heating capacity and water flow rate.

[0045] It is understandable that step S4 above is used to achieve closed-loop control from "prediction" to "execution". In this way, through energy efficiency-oriented temperature optimization, the heat pump is ensured to operate within its high-efficiency range while meeting user comfort needs. Simultaneously, dynamically adjusting operating parameters allows for rapid response to load changes, improving system stability and energy-saving performance.

[0046] In existing heat pump control technologies, the outlet water temperature is typically set to a fixed value or adjusted based solely on the current indoor conditions, failing to consider changes in environmental meteorological conditions and historical variations in heat load. This control method struggles to adapt to dynamic load fluctuations during actual operation, easily leading to system lag, low energy efficiency, or supply water temperature deviating from actual requirements.

[0047] To address the problems existing in the aforementioned related technologies, this invention provides a method for regulating the outlet water temperature of a heat pump. By acquiring the meteorological parameters of the current environment and the historical heat load data of the heat pump, the heat load value for the next time period is predicted, and based on this, the predicted supply and return water temperature difference is calculated to determine the optimal outlet water temperature, thereby achieving dynamic adjustment of the heat pump operating parameters.

[0048] Specifically, firstly, meteorological parameters reflect the immediate impact of the external environment on heat demand, while historical heat load data demonstrates the temporal evolution of the system load; both serve as the basis for prediction, making the estimate of heat load for the next time period closer to actual demand. Secondly, based on this predicted heat load value, the predicted supply and return water temperature difference required to meet this heat demand can be derived, thus transforming the abstract load demand into executable thermal parameters for the heat pump water system. Finally, combining this temperature difference, the optimal outlet water temperature that can meet the heat load and achieve better operating performance is determined, and the operating parameters of the heat pump are dynamically adjusted accordingly to ensure that the system output accurately matches the actual demand.

[0049] Therefore, the basic principle of the heat pump outlet water temperature control method of the present invention is as follows: the heat load is not static and constant, but is driven by meteorological conditions and has historical dependence. By predicting the heat load in advance and setting the outlet water temperature accordingly, overheating or cooling caused by response lag or rigid settings in traditional control can be avoided. At the same time, the operating parameters are dynamically adjusted based on the prediction results, so that the heat pump always operates in a state adapted to the current load, thereby improving the regulation accuracy and operating efficiency. Therefore, compared with the control methods in the background technology that ignore meteorological changes and load history, this method can more accurately predict heat demand, set a more reasonable outlet water temperature, reduce ineffective energy consumption, and improve the system's adaptability to environmental changes.

[0050] Furthermore, based on the above working principle, the basic working process of the outlet water temperature control method of the present invention is described as follows: First, during the operation of the heat pump system, the system acquires real-time meteorological parameters of the current environment, including outdoor temperature, humidity, and light intensity, which reflect the external thermal environment status. At the same time, it reads historical heat load data accumulated by the heat pump in previous operating cycles from the system storage unit. This data records the actual heat load demand at different points in time.

[0051] Subsequently, the acquired meteorological parameters and historical heat load data are used as inputs to predict the heat load for the next time period using a data-driven approach, resulting in a quantified predicted heat load value. This prediction process comprehensively considers the immediate impact of external meteorological changes on heat demand as well as the evolution trend of historical loads, making the prediction results closer to actual operational needs.

[0052] Next, based on the predicted heat load value and the heat balance relationship of the heat pump water system, the predicted supply and return water temperature difference required to meet this heat load is calculated. This temperature difference reflects the temperature difference that should be maintained between the supply and return water under the current predicted load.

[0053] Finally, based on the predicted supply and return water temperature difference, the optimal outlet water temperature that meets the heat load requirements and optimizes system performance is determined, and the heat pump's operating parameters are dynamically adjusted accordingly. This adjustment ensures that the actual output of the heat pump matches the predicted heat load, avoiding energy waste or insufficient heating caused by setting the outlet water temperature too high or too low.

[0054] As shown above, the entire process forms a closed-loop control logic that is prediction-oriented, temperature difference-based, and aims at the optimal outlet water temperature. This effectively overcomes the problems of regulation lag and low energy efficiency caused by traditional control methods that ignore meteorological dynamics and load history.

[0055] In summary, the heat pump outlet water temperature control method according to the embodiments of the present invention has advantages over the prior art, such as improving the rationality of the outlet water temperature setting, achieving precise matching between heat load demand and system output, improving system operating energy efficiency and energy saving level, and enhancing the ability to respond to environmental changes.

[0056] Specifically, firstly, this invention predicts the heat load for the next time period by incorporating current meteorological parameters and historical heat load data of the heat pump. This allows the outlet water temperature setting to no longer rely on fixed values ​​or delayed feedback, but rather on predictions of future heat demand, significantly enhancing the initiative and adaptability of regulation. Secondly, this invention calculates the predicted supply and return water temperature difference based on the predicted heat load value and determines the optimal outlet water temperature accordingly. This makes the heat pump's heating capacity more consistent with the actual load demand in terms of time and magnitude, effectively avoiding overheating or underheating. Thirdly, this invention dynamically adjusts operating parameters to match the optimal outlet water temperature driven by prediction, reducing ineffective energy consumption caused by temperature settings deviating from actual demand, thereby reducing overall energy consumption while meeting user comfort. Fourthly, this invention uses meteorological parameters as one of the control bases, enabling the system to promptly sense and respond to dynamic changes in the outdoor environment. It maintains stable and efficient operating performance even under conditions such as sudden drops in temperature and sudden changes in sunlight, overcoming the blind spots of traditional methods under complex meteorological conditions.

[0057] According to some embodiments of the present invention, the step of predicting the heat load for the next time period based on meteorological parameters and historical heat load data, and obtaining the predicted heat load value, includes: A bidirectional long short-term memory network model based on incremental learning is used to predict heat load based on meteorological parameters and historical heat load data, and the predicted heat load parameters are obtained.

[0058] The hyperparameters of the bidirectional long short-term memory network model are automatically optimized using the whale optimization algorithm. The hyperparameters include the number of hidden layer neurons, the learning rate, and the number of training iterations.

[0059] Before introducing the specific steps of this embodiment, the terms in this embodiment are explained: (1) Incremental Learning Bi-LSTM Model: refers to a deep neural network model that supports online updates. It can continuously receive newly collected historical load data and meteorological parameters without retraining the entire model, and gradually adjust the model weights to adapt to changes in the system operating environment. (2) Bi-directional Long-Short Term Memory (Bi-LSTM): is an improved recurrent neural network composed of two independent LSTM structures, forward and backward, which process information before and after the current time in the time series, respectively. This allows it to simultaneously capture the past dependence and future trend of load data, improving the ability to model time series features. (3) Whale Optimization Algorithm (WOA): a global optimization algorithm based on swarm intelligence that simulates whale predation behavior and automatically optimizes the hyperparameters of the Bi-LSTM model by iteratively searching for the optimal solution in the space. (4) Hyperparameters: These are parameters that need to be set in advance during model training but do not affect the internal weights of the model, such as the number of neurons in the hidden layer, the learning rate, and the number of training iterations. These hyperparameters directly affect the convergence speed and prediction accuracy of the model.

[0060] It should be noted that this embodiment can construct a high-precision, adaptive, and robust heat load prediction system by integrating incremental learning mechanism, Bi-LSTM model structure and WOA parameter optimization strategy.

[0061] In related technologies, traditional single LSTM models can only transmit information unidirectionally from front to back, making it difficult to fully exploit the bidirectional temporal correlations inherent in load sequences. However, the Bi-LSTM used in this embodiment processes forward and reverse sequences in parallel, enabling the model to utilize historical variation patterns and refer to trend information from subsequent periods when predicting load at a given time, significantly enhancing its ability to identify periodic and abrupt load patterns. For example, Figure 4 The basic structure of Bi-LSTM is shown, such as Figure 4 As shown, the input layer receives time series data, the forward layer propagates information in chronological order, and the backward layer propagates in reverse order. The two are merged in the hidden layer to output the predicted value, effectively capturing multi-directional temporal dependencies.

[0062] Furthermore, since the performance of Bi-LSTM models is highly dependent on hyperparameter settings, manual parameter tuning is inefficient and prone to getting trapped in local optima. Therefore, this invention further introduces the Whale Optimization Algorithm (WOA) to automatically optimize key hyperparameters. WOA initializes a set of candidate parameters, simulates whale hunting behavior in the search space, continuously updates the individual positions and calculates the fitness (i.e., model prediction error), and ultimately finds the optimal parameter combination that maximizes prediction accuracy. Figure 5 The WOA parameter optimization process is described, such as Figure 5 As shown, the population is first initialized, and the maximum number of iterations Tmax is set; then the fitness (such as mean squared error MSE) of each individual is calculated; the individual position is adjusted according to the WOA update rule; when the termination condition is met, the optimal parameter combination is output to build the final Bi-LSTM model.

[0063] Building upon this, an incremental learning mechanism is employed, enabling the trained Bi-LSTM model to be fine-tuned using only newly added samples when new data arrives, avoiding repeated training on all historical data and thus achieving real-time updates and long-term evolution. This mechanism is particularly suitable for real-world scenarios where the operating environment of heat pump systems dynamically changes with seasons, climate, and user habits.

[0064] The general working process of this embodiment can be described as follows: Figure 3 As shown, the raw data is preprocessed and then input into the Bi-LSTM model for training; at the same time, the WOA algorithm runs independently to optimize the model's hyperparameters; the optimized parameters are fed back to the model to update its structural configuration; after the model outputs the prediction results, if new data exists, it enters the next round of incremental updates, forming a closed-loop learning process.

[0065] Furthermore, in actual operation, the specific working process of this embodiment includes: (1) Align the collected historical heat load data with the meteorological parameters (such as outdoor temperature, humidity, and light intensity) at the corresponding time to form a time series dataset, and divide it into a training set and a test set.

[0066] (2) Construct a basic Bi-LSTM network structure and set the initial hyperparameters.

[0067] (3) The whale optimization algorithm is launched, with the objective function of minimizing the prediction error, and a global search is performed on hyperparameters such as the number of hidden layer neurons, learning rate, and number of training iterations. Each generation of individuals represents a set of parameter combinations. The Bi-LSTM model is trained and its prediction error on the test set is calculated as the fitness value to guide the population evolution.

[0068] (4) Apply the optimal parameters obtained by WOA optimization to the Bi-LSTM model and train it using historical data. When new load and meteorological data are generated during system operation, there is no need to retrain the full dataset. Instead, the model is incrementally updated using the new data to achieve continuous model optimization.

[0069] (5) Input the meteorological parameters at the current time and the historical load data of the recent period into the optimized and updated Bi-LSTM model, and output the predicted heat load value for the next period.

[0070] In summary, the technical solution described in this embodiment significantly improves the accuracy and flexibility of heat load prediction by introducing an incremental learning Bi-LSTM model and a WOA parameter optimization mechanism. It solves the problems of adjustment lag, supply-demand mismatch and low energy efficiency in traditional control methods, thereby not only improving the system's adaptability and response speed, but also providing a solid foundation for realizing intelligent heat pump control.

[0071] like Figure 2 As shown, in some specific embodiments of the present invention, the meteorological parameters include at least one of indoor temperature, outdoor temperature, indoor humidity, outdoor humidity, light intensity, and seasonal factors.

[0072] The meteorological parameters mentioned above are key environmental variables affecting building heat load. During heat load forecasting, these parameters can be used as feature inputs to the prediction model, forming a multi-dimensional input vector together with historical heat load data. By fusing this multi-source meteorological information, the model can more comprehensively perceive the combined impact of the external environment on heat demand, thereby improving the accuracy of predicting heat load trends for the next time period.

[0073] For example, on a clear winter morning, although the outdoor temperature is low, the high intensity of sunlight can significantly reduce the actual heat load. If the sunlight factor is ignored and only temperature is used for prediction, the outlet water temperature will be set too high, resulting in energy waste. Conversely, in cold and humid weather, even if the temperature does not drop significantly, the human body's perception of cold is enhanced, and the actual heat demand may increase. In this case, incorporating humidity and sunlight information can effectively avoid prediction errors.

[0074] like Figure 6 As shown, according to some embodiments of the present invention, the step of calculating the predicted supply and return water temperature difference of the heat pump based on the predicted heat load value includes: The predicted supply and return water temperature difference is calculated using the empirical formula for heat pump units, based on the predicted heat load value; the empirical formula for heat exchange is in binomial form: In the formula, The predicted heat load value, The outlet water temperature, The inlet water temperature, That is, the predicted supply and return water temperature difference, coefficient. These are empirical parameters obtained by fitting measured data from heat pump units.

[0075] In this embodiment, the binomial form of the empirical formula for heat transfer is derived from the actual thermal characteristics of the heat pump and the terminal heat exchange system. In specific implementation, the system obtains the predicted heat load value... Then, substitute this value into the above binomial equation, and... Treating it as an unknown, solve for the following: The quadratic equation: Within a reasonable operating range, the above equation has a unique positive real solution that conforms to physical meaning. The system can select this effective solution as the predicted supply and return water temperature difference for subsequent determination of the optimal outlet water temperature. It should be noted that empirical coefficients... The accuracy of the temperature difference calculation directly affects its reliability. Therefore, before the heat pump leaves the factory or during the initial operation, it is necessary to perform actual measurements and calibrations under various typical operating conditions. The fitting parameters can be continuously updated based on the operating data to adapt to performance changes caused by equipment aging or system modifications.

[0076] In summary, this implementation method, by introducing a binomial heat transfer empirical formula calibrated based on measured data, achieves an accurate, calculable, and engineerable mapping from predicted heat load values ​​to predicted supply and return water temperature differences, thereby ensuring the accurate determination of the optimal outlet water temperature.

[0077] like Figure 6 As shown, according to some embodiments of the present invention, the step of determining the optimal outlet water temperature of the heat pump based on the predicted supply and return water temperature difference includes: Obtain the range of inlet water temperature and the current outdoor temperature; Using a heat pump energy consumption model, based on the range of inlet water temperature and the predicted supply and return water temperature difference, the outlet water temperature is optimized under the condition that the outdoor temperature remains constant, and the optimal outlet water temperature that minimizes the heat pump energy consumption is calculated.

[0078] In the energy consumption model, the energy consumption of the heat pump is determined by the inlet water temperature and the outdoor temperature.

[0079] In this embodiment, to determine the optimal outlet water temperature, the system first needs to obtain the range of allowable inlet water temperatures for the heat pump system and the current outdoor temperature. The range of inlet water temperatures is determined by factors such as the safe operating boundaries of the heat pump unit, user comfort requirements, and the applicable temperature range of the terminal heat dissipation equipment; the outdoor temperature is collected in real time by environmental sensors and serves as a key input variable for the energy consumption model.

[0080] Subsequently, using a pre-established heat pump energy consumption model, and assuming a constant outdoor temperature, the outlet water temperature was optimized based on the previously calculated predicted supply and return water temperature difference. This optimization was performed due to the outlet water temperature... With inlet water temperature Satisfying Relationships (in To predict the supply and return water temperature difference, therefore, given... Under these conditions, the outlet water temperature is entirely determined by the inlet water temperature. The system traverses or optimizes the search within the range of inlet water temperatures, substitutes each candidate inlet water temperature into the energy consumption model, calculates the corresponding heat pump energy consumption, and selects the combination that minimizes energy consumption. The corresponding outlet water temperature is the optimal outlet water temperature.

[0081] The aforementioned energy consumption model characterizes the energy consumption characteristics of a heat pump under specific operating conditions. The energy consumption of the heat pump is determined by both the inlet water temperature and the outdoor temperature. This energy consumption model reflects the energy efficiency performance of the heat pump under different combinations of temperatures on the heat source side (i.e., the outdoor side) and the user side (i.e., the inlet water side). For example, when the outdoor temperature is low, increasing the inlet water temperature will significantly increase the compressor load, leading to increased energy consumption; conversely, in mild weather, appropriately lowering the inlet water temperature can maintain sufficient heating while reducing energy consumption.

[0082] In summary, by optimizing energy consumption using only the inlet water temperature as a variable under the constraints of a fixed outdoor temperature and a fixed supply and return water temperature difference, this embodiment achieves a refined energy efficiency assessment of operating conditions. The above process ensures that the determined optimal outlet water temperature not only meets the predicted heat load demand but also allows the system to operate at its lowest energy consumption point under current environmental conditions, thus balancing heating reliability and operational economy.

[0083] like Figure 7 As shown, in some specific embodiments of the present invention, the energy consumption model of a heat pump is used to perform optimization calculations on the outlet water temperature based on the range of inlet water temperature and the predicted supply and return water temperature difference, under the condition that the outdoor temperature remains constant, to calculate the optimal outlet water temperature that minimizes the energy consumption of the heat pump. This step includes: Iterate through multiple candidate inlet water temperature values ​​within the range of inlet water temperature values, and for each candidate inlet water temperature value, calculate the corresponding candidate outlet water temperature based on the predicted supply and return water temperature difference; Input the candidate inlet water temperature and outdoor temperature into the energy consumption model to obtain the corresponding energy consumption; The candidate outlet water temperature that minimizes energy consumption is selected as the optimal outlet water temperature.

[0084] For example, within the permissible safe and comfortable operating boundaries of the heat pump system, the range of values ​​for the inlet water temperature can be determined, such as a range. Within this range, multiple candidate inlet water temperature values ​​are generated according to a preset step size (such as 0.5℃ or 1℃).

[0085] Secondly, for each candidate inlet water temperature value Combined with the obtained predicted supply and return water temperature difference Calculate the corresponding candidate effluent temperatures The calculation relationship is as follows: This step ensures that each candidate operating condition meets the supply and return water temperature difference required by the predicted heat load, thereby guaranteeing that the heating capacity matches the actual demand.

[0086] Subsequently, the candidate inlet water temperature value Compared with the current measured outdoor temperature Both are input into a pre-established heat pump energy consumption model. This model is fitted based on measured operating data of the heat pump under different operating conditions, and can accurately reflect the input electrical power or comprehensive energy consumption of the heat pump under given inlet water temperature and outdoor temperature conditions. The model output is the energy consumption value corresponding to the candidate operating condition. .

[0087] Repeat the above process to calculate the energy consumption for each candidate influent temperature value within the range, forming a set of... The data is correct. Finally, the water temperature with the lowest energy consumption among all candidate solutions is selected as the final optimal water temperature.

[0088] In summary, this implementation method, through systematic traversal and energy consumption assessment within a reasonable temperature range, ensures that the determined optimal outlet water temperature not only meets the heat load requirements but also minimizes energy consumption under current outdoor environmental conditions, thereby effectively supporting the energy-saving, precise, and adaptive control objectives of this invention.

[0089] In some specific embodiments of the present invention, the energy consumption model is a multivariate nonlinear regression model obtained by fitting actual heat pump operating data, and its expression is: in, This indicates the energy consumption of the heat pump. The inlet water temperature, Outdoor temperature The energy consumption set coefficient is obtained by fitting historical energy consumption data, outdoor temperature, and heat pump inlet water temperature.

[0090] It's important to explain that in an air-source heat pump water heating system, the energy consumption of the heat pump unit is primarily affected by two key temperature parameters: the inlet water temperature and the outdoor temperature. The inlet water temperature directly affects the system's condensing temperature, while the outdoor temperature determines the evaporating temperature. These two temperatures together determine the pressure ratio and heat exchange efficiency of the heat pump cycle, thus dominating the compressor's power consumption. Given that the compressor is the main energy-consuming component in the system, the total energy consumption of the heat pump unit can be reasonably approximated. equals compressor energy consumption Based on the above energy consumption model and its physical principles, a simplified energy consumption model can be obtained from related technologies, expressed as: Among them, coefficient The energy consumption set coefficient is obtained through regression fitting using historical data accumulated during the actual operation of the heat pump (including measured energy consumption, corresponding inlet water temperature, and outdoor temperature). It can be understood that although the above model is an empirical formula, it can effectively reflect the energy consumption trend of air source heat pumps under typical operating conditions.

[0091] In actual control processes, since the outdoor temperature changes very little within a short time scale (e.g., 1 minute), it can be considered constant. Therefore, when optimizing the outlet water temperature, the outdoor temperature measured at the current or previous moment is used. As a fixed input, the range of inlet water temperature is illustrated below: Based on engineering practice of air source heat pumps in heating mode, the outlet water temperature is typically set between 35℃ and 50℃, while the supply and return water temperature difference is generally 5℃ to 10℃. Therefore, the inlet water temperature can be deduced. The reasonable range for the inlet water temperature is 25℃ to 45℃. Within this range, the system iterates through multiple candidate inlet water temperature values. For each Substitute the values ​​into the empirical formula of the energy consumption model to calculate the corresponding energy consumption. .

[0092] Due to compressor energy consumption It can be approximated as equal to Therefore, it can also be expressed by formula. Verification was conducted, among which This refers to the compressor speed. The load torque is obtained by fitting historical data, so the energy consumption calculation has a dual basis, thus ensuring the reliability of the results.

[0093] Ultimately, the selection made Minimum candidate inlet water temperature In conjunction with the optimal supply and return water temperature difference determined earlier based on predicted heat load, The optimal outlet water temperature was calculated.

[0094] Furthermore, the energy consumption aggregation coefficient Dynamic fitting and optimization are performed using the quantum particle swarm optimization algorithm.

[0095] It should be noted that the coefficients in the energy consumption model These are key parameters that determine the accuracy of the model's predictions. These coefficients need to be fitted based on historical operating data of the heat pump system (including measured energy consumption, inlet water temperature, and outdoor temperature). If the traditional least squares method or gradient descent method is used for parameter estimation, it may get stuck in local optima due to data noise, nonlinear coupling, or improper selection of initial values, resulting in insufficient model generalization ability and affecting the accuracy of subsequent calculations of the optimal outlet water temperature.

[0096] To address this, this invention introduces the Quantum Particle Swarm Optimization (QPSO) algorithm to dynamically fit and optimize the aforementioned energy consumption set coefficients. It should be noted that QPSO is an improved swarm intelligence optimization algorithm that inherits the global search capability of the classical particle swarm optimization algorithm and enhances its exploration capability by introducing quantum behavior mechanisms. This allows it to efficiently search for optimal solutions in high-dimensional parameter spaces, avoiding premature convergence.

[0097] like Figure 8 As shown, the specific implementation process of this embodiment based on the QPSO algorithm flow is described as follows: (1) Initialize the particle swarm: Construct a four-dimensional parameter vector from the four coefficients to be fitted, which serves as the position variable of each particle in the QPSO algorithm. Initialize a set of particle swarms, each particle representing a set of candidate coefficient combinations. (2) Calculate the fitness value: Calculate the prediction error (such as mean square error MSE) of the model corresponding to each particle based on historical running data, and use this as the individual fitness value. (3) Determine whether the termination condition is met: If not, continue iterating. (4) Calculate the average best position and random point, and update the position according to the evolution equation: After entering the iteration process, the algorithm updates the position of each particle according to the evolution equation of QPSO, where the position update depends on the average best position and random point, thereby realizing the global exploration of the parameter space. (5) Update the individual optimal and the group optimal: Recalculate the fitness value after each iteration, and update the individual optimal and the group optimal solutions. (6) When the preset termination condition is met (such as reaching the maximum number of iterations or the fitness change is less than the threshold), the algorithm stops and outputs the globally optimal coefficient combination.

[0098] In summary, the quantum particle swarm optimization algorithm used in this embodiment can effectively overcome the limitations of traditional methods in fitting parameters of complex nonlinear models, significantly improving the fitting accuracy and robustness of the energy consumption model. Furthermore, because this algorithm supports online updates, it can dynamically adjust coefficients based on newly added data during long-term operation of the heat pump, enabling the model to continuously adapt to actual operating conditions such as equipment aging and environmental changes, further enhancing the system's adaptive capabilities.

[0099] like Figure 6 As shown, according to some embodiments of the present invention, the step of dynamically adjusting the operating parameters of the heat pump based on the optimal outlet water temperature includes: Based on the energy consumption model and the optimal outlet water temperature, the minimum energy consumption of the heat pump is calculated, and the compressor speed of the heat pump is dynamically adjusted based on the minimum energy consumption. And / or, using a heat exchange model between the heat pump and the indoor environment, the optimal inlet flow rate of the heat pump is calculated based on the predicted supply and return water temperature difference and the predicted heat load, and the opening degree of the heat pump's water valve is dynamically adjusted based on the optimal inlet flow rate.

[0100] The heat transfer model is as follows: ,in To predict heat load, The outlet water temperature, The inlet water temperature, This refers to the predicted supply and return water temperature difference, where m is the optimal inlet water flow rate and c is the specific heat capacity of water.

[0101] In this embodiment, the above steps provide two technical operations for dynamically adjusting the operating parameters of the heat pump. One operation is to adjust the speed of the compressor, and the other is to adjust the opening degree of the water pump valve.

[0102] The general process for adjusting compressor speed is as follows: Based on the energy consumption model and the determined optimal outlet water temperature, the minimum energy consumption of the heat pump under this operating condition is calculated, and the compressor speed is dynamically adjusted accordingly. Since the optimal outlet water temperature that minimizes system energy consumption has already been obtained through optimization using the energy consumption model in the preceding steps... Meanwhile, the corresponding inlet water temperature is known. With outdoor temperature These parameters can be substituted into the energy consumption model to calculate the theoretical minimum energy consumption value. In an air-source heat pump system, the compressor is the main energy-consuming component, and its power consumption is closely related to its speed. Therefore, the control system calculates the required compressor load state based on the minimum energy consumption target and dynamically adjusts the compressor speed. To make it run in conjunction with A matching high-efficiency operating point is used to achieve optimal energy-efficient drive control.

[0103] The general process for adjusting the water pump valve opening is as follows: Using a heat pump and indoor environment heat exchange model, based on the predicted supply and return water temperature difference and predicted heat load, the optimal inlet water flow rate of the heat pump is calculated, and the water pump valve opening is dynamically adjusted accordingly. This heat exchange model is expressed as: in, The predicted heat load (unit: kW) is obtained from the prediction model; c is the specific heat capacity of water (taken as a constant 4.18 kJ / (kg·℃)). The predicted supply and return water temperature difference is already determined; m is the water mass flow rate (kg / s), i.e., the optimal inlet water flow rate. Given... and Under the premise that the required optimal influent flow rate can be directly solved: The optimal inlet flow rate described above reflects the water circulation rate required to meet the predicted heat load while maintaining the optimal supply and return water temperature difference. Based on this calculation, and combining the pump characteristic curve with the valve opening-flow relationship, the control system dynamically adjusts the pump frequency and valve opening to precisely match the actual water flow rate (m). This avoids excessive flow leading to ineffective pump energy consumption, or insufficient flow causing inadequate heat exchange, thus achieving precise coordination between the hydraulic and thermal demands.

[0104] It should be noted that the two adjustment actions mentioned above can be performed independently or simultaneously: the former optimizes the energy efficiency on the thermal cycle side, while the latter optimizes the matching on the hydraulic distribution side. Together, they constitute a closed-loop dynamic control of the core operating parameters of the heat pump system, ensuring that the overall energy efficiency is maximized while meeting the user's thermal comfort needs.

[0105] In summary, this method significantly improves the precision and intelligence of heat pump system regulation by converting the optimal outlet water temperature into specific compressor speed and water pump valve opening control commands, and by relying on energy consumption and heat exchange models to convert parameters into specific execution operations.

[0106] like Figure 9 As shown, according to some embodiments of the present invention, after the step of dynamically adjusting the operating parameters of the heat pump based on the optimal outlet water temperature, the method further includes: Establish and update the operating database, which stores the relationship between meteorological parameters and optimal operating parameters, including compressor speed and water pump valve opening. When the heat pump starts up or meteorological parameters change abruptly, the system retrieves the historical operating conditions that are closest to the current meteorological parameters from the operating database, retrieves the corresponding optimal operating parameters as the initial operating parameters, and makes dynamic adjustments in combination with real-time optimization algorithms. After each adjustment is completed, the actual operating parameters are fed back to the operating database, and the optimal operating parameters under the corresponding meteorological parameters are updated.

[0107] For example, the optimal outlet water temperature setpoint is transmitted to the unit's optimization algorithm, which then optimizes and dynamically adjusts parameters such as compressor speed and water pump valve opening. Finally, a database of meteorological parameters, compressor speed, and water pump valve opening is established to achieve adaptive adjustment of the heat pump outlet water temperature. The specific steps are as follows: (1) Transmit the optimal outlet water temperature to the control system of the heat pump unit: The optimal outlet water temperature is sent to the heat pump controller through the control system interface.

[0108] (2) The compressor speed is adjusted by the control system according to the set value: The control system adjusts the compressor speed in real time according to the set value to achieve the optimal outlet water temperature.

[0109] (3) Adjust the opening of the water pump valve according to the set value: The control system synchronously adjusts the opening of the water pump valve to ensure that the water flow rate matches the heat demand.

[0110] (4) Monitor the compressor speed and water pump valve opening in real time, record and establish a database of meteorological parameters, compressor speed, and water pump valve opening. The data acquisition frequency is once every 5 minutes, and a detailed operation database is established.

[0111] (5) The database is stored according to meteorological parameters and geographical location. Each data is associated with a set of optimal operating parameters (such as compressor speed and water valve opening). When the weather changes suddenly, the real-time algorithm response may take time. The database can quickly provide approximate operating condition parameters for transition. Sub-databases are established for different climate zones (such as coastal high humidity and inland dryness) to improve regional adaptability.

[0112] (6) Dynamic optimization and adjustment based on historical and real-time data in the database: Real-time optimization algorithms (such as model predictive control and reinforcement learning) lack historical data support during initial operation, which may lead to low efficiency in the early stages. The database provides historically optimal parameter combinations as initial values ​​to accelerate convergence. The actual operating effect after each optimization (such as energy efficiency ratio COP and temperature deviation) is fed back to the database to update the optimal parameters under the corresponding meteorological conditions, forming a closed-loop learning system. Using the database, the compressor speed and water pump valve opening are continuously adjusted through optimization algorithms to ensure efficient system operation.

[0113] In summary, the heat pump outlet water temperature control method of this invention has the following improvements: Firstly, the bidirectional load forecasting technology based on incremental learning, combined with meteorological parameters, can improve the accuracy of load forecasting. Secondly, this method uses a bidirectional LSTM network and the Whale Optimization Algorithm (WOA) to optimize the model parameters. Furthermore, this method uses the Quantum Particle Swarm Optimization Algorithm (QPSO) to optimize the heat pump operating parameters. In addition, this method establishes a database of meteorological parameters, compressor speed, and water valve opening, thereby realizing adaptive adjustment of the heat pump outlet water temperature and achieving a mechanism of dynamic optimization, database construction, and closed-loop update.

[0114] Furthermore, the method of the present invention can achieve the following technical effects based on the above-mentioned improvements: (1) Improved accuracy of heat pump outlet water temperature regulation: By comprehensively considering outdoor temperature and humidity, light intensity and load data, the load is accurately modeled and the optimal outlet water temperature setting value is predicted, so that the heat pump system can more accurately regulate the outlet water temperature, reduce energy waste and improve system operating efficiency.

[0115] (2) Dynamic response to changes in external environment and load: This invention monitors meteorological parameters and load data in real time and uses optimization algorithms to dynamically adjust compressor speed and water valve opening, which can quickly respond to changes in external environment and real-time load, adapt to complex and ever-changing actual operating conditions, and ensure stable operation of the system and user comfort.

[0116] (3) Establish a comprehensive database to support intelligent optimization control: By establishing a database of meteorological parameters, compressor speed and water valve opening, this invention realizes the effective use of heat pump system operation data, provides comprehensive data support for intelligent optimization control, and further improves the intelligence and efficiency of the system.

[0117] (4) Improved energy-saving effect of the system: By optimizing the heat pump outlet water temperature setting value, the present invention reduces the energy consumption of the system and achieves more efficient energy-saving operation, which not only meets the user's comfort needs, but also reduces energy consumption, and has significant energy-saving and environmental protection effects.

[0118] (5) Enhanced system safety and stability: When setting the upper and lower temperature limits, the present invention no longer relies entirely on experience accumulation, but on precise modeling and optimization algorithms to further optimize the upper and lower temperature limits, thereby enhancing the safety and stability of the control system and reducing the risks and failure rates in system operation.

[0119] The control device for the heat pump provided by the present invention will be described below. The control device for the heat pump described below can be referred to in correspondence with the control method for the heat pump described above.

[0120] like Figure 10 As shown, the outlet water temperature control device of the heat pump according to a second aspect embodiment of the present invention includes: The acquisition module 110 is used to acquire the meteorological parameters of the current environment and the historical heat load data of the heat pump; The prediction module 120 is used to predict the heat load for the next time period based on meteorological parameters and historical heat load data, and obtain the predicted heat load value. The calculation module 130 is used to calculate the predicted supply and return water temperature difference of the heat pump based on the predicted heat load value. The control module 140 is used to determine the optimal outlet water temperature of the heat pump based on the predicted supply and return water temperature difference, and to dynamically adjust the operating parameters of the heat pump based on the optimal outlet water temperature.

[0121] Figure 11 An example is a schematic diagram of the physical structure of an electronic device, such as... Figure 11As shown, the electronic device may include a processor 810, a communication interface 820, a memory 830, and a communication bus 840. The processor 810, communication interface 820, and memory 830 communicate with each other via the communication bus 840. The processor 810 can call logical instructions in the memory 830 to execute a heat pump outlet water temperature control method, including: acquiring current environmental meteorological parameters and historical heat load data of the heat pump; predicting the heat load for the next time period based on the meteorological parameters and historical heat load data, and obtaining a predicted heat load value; calculating the predicted supply and return water temperature difference of the heat pump based on the predicted heat load value; determining the optimal outlet water temperature of the heat pump based on the predicted supply and return water temperature difference, and dynamically adjusting the heat pump's operating parameters based on the optimal outlet water temperature.

[0122] Furthermore, the logical instructions in the aforementioned memory 830 can be implemented as software functional units and, when sold or used as independent products, can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0123] On the other hand, the present invention also provides a computer program product, which includes a computer program stored on a non-transitory computer-readable storage medium. The computer program includes program instructions, and when the program instructions are executed by the computer, the computer is able to execute the heat pump outlet water temperature control method provided by the above methods, including: acquiring meteorological parameters of the current environment and historical heat load data of the heat pump; predicting the heat load for the next time period based on the meteorological parameters and historical heat load data, and obtaining a predicted heat load value; calculating the predicted supply and return water temperature difference of the heat pump based on the predicted heat load value; determining the optimal outlet water temperature of the heat pump based on the predicted supply and return water temperature difference, and dynamically adjusting the operating parameters of the heat pump based on the optimal outlet water temperature.

[0124] In another aspect, the present invention also provides a non-transitory computer-readable storage medium storing a computer program thereon, which, when executed by a processor, implements the above-described heat pump outlet water temperature control methods, including: acquiring meteorological parameters of the current environment and historical heat load data of the heat pump; predicting the heat load for the next time period based on the meteorological parameters and historical heat load data, and obtaining a predicted heat load value; calculating the predicted supply and return water temperature difference of the heat pump based on the predicted heat load value; determining the optimal outlet water temperature of the heat pump based on the predicted supply and return water temperature difference, and dynamically adjusting the operating parameters of the heat pump based on the optimal outlet water temperature.

[0125] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs. Those skilled in the art can understand and implement this without any creative effort.

[0126] Through the above description of the embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus necessary general-purpose hardware platforms, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solutions, in essence or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., including several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods of various embodiments or some parts of embodiments.

[0127] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for regulating the outlet water temperature of a heat pump, characterized in that, include: Obtain current environmental meteorological parameters and historical heat load data of the heat pump; The operating parameters of the heat pump are adjusted based on the meteorological parameters and the historical heat load data.

2. The method for regulating the outlet water temperature of a heat pump according to claim 1, characterized in that, The step of adjusting the operating parameters of the heat pump based on the meteorological parameters and the historical heat load data includes: Based on the meteorological parameters and the historical heat load data, the heat load for the next time period is predicted, and the predicted heat load value is obtained. Based on the predicted heat load value, calculate the predicted supply and return water temperature difference of the heat pump; The optimal outlet water temperature of the heat pump is determined based on the predicted supply and return water temperature difference, and the operating parameters of the heat pump are dynamically adjusted based on the optimal outlet water temperature.

3. The method for regulating the outlet water temperature of a heat pump according to claim 2, characterized in that, The step of predicting the heat load for the next time period based on the meteorological parameters and the historical heat load data, and obtaining the predicted heat load value, includes: A bidirectional long short-term memory network model with incremental learning is used to predict the heat load based on the meteorological parameters and the historical heat load data, and the predicted heat load parameters are obtained. The hyperparameters of the bidirectional long short-term memory network model are automatically optimized using the whale optimization algorithm. The hyperparameters include the number of hidden layer neurons, the learning rate, and the number of training iterations.

4. The method for regulating the outlet water temperature of a heat pump according to claim 3, characterized in that, The meteorological parameters include at least one of indoor temperature, outdoor temperature, indoor humidity, outdoor humidity, light intensity, and seasonal factors.

5. The method for regulating the outlet water temperature of a heat pump according to claim 2, characterized in that, The step of calculating the predicted supply and return water temperature difference of the heat pump based on the predicted heat load value includes: The predicted supply and return water temperature difference is calculated based on the predicted heat load value using an empirical formula for heat pump units; wherein the empirical formula for heat exchange is in binomial form: In the formula, The predicted heat load value, The outlet water temperature, The inlet water temperature, That is, the predicted supply and return water temperature difference, coefficient. These are empirical parameters obtained by fitting measured data from heat pump units.

6. The method for regulating the outlet water temperature of a heat pump according to claim 2, characterized in that, The step of determining the optimal outlet water temperature of the heat pump based on the predicted supply and return water temperature difference includes: Obtain the range of inlet water temperature and the current outdoor temperature; Using the energy consumption model of the heat pump, based on the range of the inlet water temperature and the predicted supply and return water temperature difference, the outlet water temperature is optimized under the condition that the outdoor temperature remains unchanged, and the optimal outlet water temperature that minimizes the energy consumption of the heat pump is calculated. In the energy consumption model, the energy consumption of the heat pump is determined by the inlet water temperature and the outdoor temperature.

7. The method for regulating the outlet water temperature of a heat pump according to claim 6, characterized in that, The step of using the heat pump's energy consumption model, based on the range of the inlet water temperature and the predicted supply and return water temperature difference, to perform optimization calculations on the outlet water temperature under the condition that the outdoor temperature remains constant, and calculating the optimal outlet water temperature that minimizes the heat pump's energy consumption, includes: Iterate through multiple candidate inlet water temperature values ​​within the range of the inlet water temperature, and for each candidate inlet water temperature value, calculate the corresponding candidate outlet water temperature based on the predicted supply and return water temperature difference; The candidate inlet water temperature and the outdoor temperature are input into the energy consumption model to obtain the corresponding energy consumption. The candidate outlet water temperature that minimizes the energy consumption is selected as the optimal outlet water temperature.

8. The method for regulating the outlet water temperature of a heat pump according to claim 6, characterized in that, The energy consumption model is a multivariate nonlinear regression model obtained by fitting actual heat pump operating data, and its expression is as follows: in, This indicates the energy consumption of the heat pump. The inlet water temperature, Outdoor temperature The energy consumption set coefficient is obtained by fitting historical energy consumption data, outdoor temperature, and heat pump inlet water temperature; the energy consumption set coefficient Dynamic fitting and optimization are performed using the quantum particle swarm optimization algorithm.

9. The method for regulating the outlet water temperature of a heat pump according to any one of claims 6 to 8, characterized in that, The step of dynamically adjusting the operating parameters of the heat pump based on the optimal outlet water temperature includes: Based on the energy consumption model and the optimal outlet water temperature, the minimum energy consumption of the heat pump is calculated, and the compressor speed of the heat pump is dynamically adjusted based on the minimum energy consumption. And / or, using a heat exchange model between the heat pump and the indoor environment, based on the predicted supply and return water temperature difference and the predicted heat load, calculate the optimal inlet water flow rate of the heat pump, and dynamically adjust the opening of the heat pump's water valve based on the optimal inlet water flow rate. The heat transfer model is as follows: ,in To predict heat load, The outlet water temperature, The inlet water temperature, This refers to the predicted supply and return water temperature difference, where m is the optimal inlet water flow rate and c is the specific heat capacity of water.

10. The method for regulating the outlet water temperature of a heat pump according to any one of claims 2 to 8, characterized in that, Following the step of dynamically adjusting the operating parameters of the heat pump based on the optimal outlet water temperature, the method further includes: Establish and update the operation database, which stores the relationship between the meteorological parameters and the optimal operation parameters, including the compressor speed and the water pump valve opening. When the heat pump starts up or meteorological parameters change abruptly, the system retrieves the historical operating conditions that are closest to the current meteorological parameters from the operating database, retrieves the corresponding optimal operating parameters as the initial operating parameters, and makes dynamic adjustments in combination with a real-time optimization algorithm. After each adjustment is completed, the actual operating parameters are fed back to the operating database, and the optimal operating parameters under the corresponding meteorological parameters are updated.

11. A heat pump outlet water temperature control device, characterized in that, include: The acquisition module is used to acquire the current environmental meteorological parameters and the historical heat load data of the heat pump; The control module is used to adjust the operating parameters of the heat pump based on the meteorological parameters and the historical heat load data.

12. A heat pump, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the heat pump outlet water temperature control method as described in any one of claims 1 to 10.

Images