Air-cooled heat pump control method and air-cooled heat pump

Abstract

The present invention relates to the technical field of heat pump control methods, and more specifically, to a system air-cooled heat pump control method and an air-cooled heat pump, comprising the following steps: collecting ambient temperature, compressor suction pressure, exhaust pressure and refrigerant flow parameters; calculating the dynamic load rate by piecewise polynomial fitting; smoothing the load rate by Laplace transform; optimizing the load rate change path by variational method; optimizing the load rate based on a multidimensional coupling matrix; and regulating the refrigerant flow by Gaussian process regression, wherein the refrigerant flow regulated by Gaussian process regression is used to dynamically adjust the refrigerant circulation path to optimize system operating parameters, polynomial fitting provides sensitive capture of dynamic changes in the load rate, and Laplace transform eliminates short-term fluctuations by frequency domain smoothing, and the variational method further optimizes the load rate path, and through global optimal path planning, the load rate achieves an optimal balance between smoothness and accuracy.

Description

Technical Field

[0001] The present invention relates to the technical field of heat pump control methods, and more specifically, to a system air-cooled heat pump control method and an air-cooled heat pump. Background Art

[0002] As an efficient refrigeration and heating equipment, air-cooled heat pump systems are widely used in commercial and residential areas. Existing air-cooled heat pump systems usually rely on a fixed-frequency compressor operation mode combined with a simple refrigerant flow control strategy to achieve load regulation. However, this traditional control method has obvious limitations. In actual operation, due to the dynamic changes in ambient temperature, load demand and equipment status, fixed control strategies often cannot adapt in real time, resulting in a decrease in system performance and energy efficiency.

[0003] At present, the more advanced air-cooled heat pump control technology attempts to optimize system efficiency under different load conditions by jointly regulating the compressor operating frequency and refrigerant flow. However, most of these technologies use static or simple dynamic algorithms, such as logical judgment based on fixed thresholds or linear regulation models. This method has the following problems in practical applications:

[0004] First, the dynamic response of load factor calculation is insufficient. Existing technologies usually use a simple ratio calculation method, which cannot accurately reflect the real-time changes of load factor under complex working conditions. For example, when the ambient temperature or system load changes suddenly, the lag and lack of accuracy of load factor calculation will cause the compressor to deviate from the optimal working condition, resulting in reduced energy efficiency and increased equipment wear.

[0005] Secondly, the accuracy of refrigerant flow control is insufficient. Traditional methods mostly use fixed refrigerant flow or static optimization strategies based on a small number of parameters, which makes it difficult to optimize the refrigerant flow in real time under different load conditions. This not only affects the heat exchange efficiency of the system, but may also cause compressor overload or poor refrigerant flow, further reducing system performance.

[0006] In addition, existing methods lack the synergistic optimization between multiple variables. In air-cooled heat pump systems, there are complex nonlinear coupling relationships between multiple variables such as ambient temperature, compressor suction pressure, exhaust pressure, and refrigerant flow. Traditional single variable or simple weighted optimization cannot fully tap the synergy between these variables, resulting in insufficient global optimization capabilities of the system.

[0007] Based on the above problems, there are still the following key technical difficulties in this field: the algorithm mechanism contradiction between load rate calculation and refrigerant flow control. Load rate calculation needs to take into account dynamic response and calculation stability, while refrigerant flow control needs to ensure optimal flow distribution under complex working conditions. It is often difficult to balance the two. For example, if the load rate calculation is too sensitive, it will lead to frequent adjustments to the refrigerant flow, increasing the complexity of the control system; and if the calculation is too lagging, it will not be able to accurately respond to load changes, reducing system efficiency. Summary of the invention

[0008] In view of the deficiencies in the prior art, the present invention provides an air-cooled heat pump control method and an air-cooled heat pump.

[0009] The present invention provides a system air-cooling heat pump control method, comprising the following steps:

[0010] Collect ambient temperature, compressor suction pressure, exhaust pressure and refrigerant flow parameters;

[0011] Dynamic load rate is calculated by piecewise polynomial fitting;

[0012] Laplace transform is used to smooth the load factor;

[0013] Optimize the load rate change path using the variational method;

[0014] Optimize the load factor based on the multi-dimensional coupling matrix;

[0015] The refrigerant flow rate is regulated by Gaussian process regression.

[0016] The refrigerant flow rate regulated by Gaussian process regression is used to dynamically adjust the refrigerant circulation path to optimize system operating parameters.

[0017] Preferably, the calculation of the dynamic load rate is based on a piecewise polynomial fitting model, specifically:

[0018]

[0019] Among them, L1(t) is the dynamic load rate at time t, a i is the fitting coefficient, t i For segmented time nodes, the fitting coefficients are dynamically updated by the least square method to ensure the accuracy of load rate calculation.

[0020] Preferably, the dynamic load rate is smoothed by Laplace transform, specifically:

[0021]

[0022] Wherein, L2(s) is the load rate in the Laplace domain, s is a complex variable used to characterize the frequency characteristics of the load rate, and the Laplace transform is used to eliminate transient fluctuations in dynamic calculations.

[0023] As a preferred method, based on the smoothed load rate, the load rate path is optimized by using the variational method, and the calculation formula for the optimized load rate is as follows:

[0024]

[0025] Among them, L3(t) is the optimized load rate at time t, λ is the penalty factor, and L is the first-order derivative of the load rate, which is used to balance the smoothness and deviation of the load rate change.

[0026] Preferably, the optimized load rate is further optimized by a multi-dimensional coupling matrix, specifically:

[0027]

[0028] Where M is the coupling matrix, which is defined as follows:

[0029]

[0030] μ ij is the coupling factor, which indicates the influence of the i-th parameter on the j-th parameter and is used to describe the interaction between the parameters. e is the ambient temperature, P s is the inspiratory pressure, P d is the exhaust pressure, Q is the refrigerant flow rate.

[0031] Preferably, the refrigerant flow rate is dynamically regulated by a Gaussian process regression model, and the calculation formula of the model is:

[0032] Q adjusted =G(L4,T e ,P s ,P d )

[0033] Among them, Q adjusted is the optimized refrigerant flow, G is the Gaussian process regression model, and the accurate prediction and optimization of the refrigerant flow can be achieved by updating the kernel function parameters in real time.

[0034] Preferably, the Gaussian process regression model dynamically updates a kernel function using historical operating data and real-time parameters, and the kernel function is used to characterize complex nonlinear relationships to improve the accuracy of refrigerant flow prediction.

[0035] Preferably, the optimized refrigerant flow is used to control the opening of an electronic expansion valve, and the electronic expansion valve adjusts the flow path of the refrigerant in the heat exchanger according to the refrigerant flow.

[0036] Preferably, the optimized compressor load rate and refrigerant flow rate are used to dynamically adjust the refrigerant circulation path between the indoor heat exchanger and the outdoor heat exchanger, and the path switching is achieved by the control module according to the real-time operating parameters of the system.

[0037] An air-cooled heat pump that executes the method includes a compression device, an indoor heat exchanger, an outdoor heat exchanger and a control module. The control module dynamically optimizes the system operating state based on the method to improve the overall energy efficiency.

[0038] The beneficial effects of the present invention are mainly reflected in the following aspects:

[0039] The present invention forms an efficient and dynamically responsive control system through multi-layer progressive algorithm design. In the key links of load rate calculation and refrigerant flow control, the algorithm proposed by the present invention not only solves the problems of response lag and insufficient optimization ability in traditional methods, but also achieves a more efficient system control effect through the complementarity and superposition of various algorithm steps.

[0040] 1. Balance between dynamic response and smoothness: Piecewise polynomial fitting and Laplace transform form a synergistic effect in load factor calculation. Polynomial fitting provides sensitive capture of dynamic changes in load factor, while Laplace transform eliminates short-term fluctuations through frequency domain smoothing. The combination of the two effectively solves the contradiction between dynamic response and calculation stability.

[0041] 2. Precise control of the optimization path: The variational method further optimizes the load rate path, and through global optimal path planning, the load rate achieves the best balance between smoothness and accuracy. This method effectively reduces the problems of frequent start and stop of the compressor and drastic fluctuations in refrigerant flow.

[0042] 3. Multivariable collaborative optimization: The multidimensional coupling matrix quantifies the complex relationship between multiple key variables and optimizes the overall performance of the system by dynamically adjusting the coupling factors. For example, when the ambient temperature rises, the system can adaptively adjust the refrigerant flow and compressor operating frequency to maintain efficient operation of the system.

[0043] 4. Accurate prediction and control: The Gaussian process regression model plays a core role in refrigerant flow control. Through dynamic learning of historical data and real-time parameters, the model can accurately predict the optimal refrigerant flow under different load conditions and dynamically adjust the opening of the electronic expansion valve, thereby significantly improving the heat exchange efficiency.

[0044] The present invention not only proposes innovative algorithms in the core links of load rate calculation and refrigerant flow control, but also achieves a comprehensive improvement in the performance of the air-cooled heat pump system through the synergy of multiple algorithms. This optimization method solves the problems of response lag, insufficient control accuracy and multi-variable coupling in the prior art, and provides strong support for the efficient operation of the air-cooled heat pump system under complex working conditions. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] Figure 1 It is a flow chart of data collection and preliminary calculation of the present invention.

[0046] Figure 2 This is a flow chart of load rate smoothing and optimized path calculation of the present invention.

[0047] Figure 3 This is a flow chart of the load rate and multivariable collaborative optimization of the present invention.

[0048] Figure 4 This is a flow chart of negative refrigerant flow optimization and electronic expansion valve control of the present invention.

[0049] Figure 5 This is a flow chart of dynamic path switching of the indoor and outdoor heat exchangers of the present invention. DETAILED DESCRIPTION

[0050] In order to further explain the technical means and effects adopted by the present invention to achieve the predetermined invention purpose, the specific implementation methods, structures, features and effects thereof are described in detail below in conjunction with the accompanying drawings and preferred embodiments. In the following description, different "one embodiment" or "another embodiment" does not necessarily refer to the same embodiment. In addition, specific features, structures or characteristics in one or more embodiments may be combined in any suitable form.

[0051] Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.

[0052] The technical solution of the present invention is clearly and completely described below in conjunction with specific implementation methods.

[0053] Please refer to Figure 1-5 The present invention relates to a control method for an air-cooled heat pump, comprising the following steps: collecting parameters such as ambient temperature, compressor suction pressure, exhaust pressure and refrigerant flow; calculating the dynamic load rate by piecewise polynomial fitting; smoothing the load rate by Laplace transform; optimizing the load rate change path by variational method; optimizing the load rate based on a multidimensional coupling matrix; and regulating the refrigerant flow by Gaussian process regression.

[0054] First, when implementing the method of the present invention, the system needs to collect key parameters such as ambient temperature, compressor suction pressure, exhaust pressure and refrigerant flow through multiple sensors. Preferably, the ambient temperature can be obtained through the ambient temperature sensor 1, and its accuracy is preferably within the range of ±0.1°C; the suction pressure and exhaust pressure are collected by the suction pressure sensor 2 and the exhaust pressure sensor 3 respectively, and the specific range can be selected from 0 to 20MPa, and the sensor error is preferably less than 0.5%; the refrigerant flow is obtained by the flow sensor 4, and its measurement range can be 0 to 500L / min, and the error is less than 1%.

[0055] In one embodiment of the present invention, the calculation of the dynamic load rate is based on a piecewise polynomial fitting model, specifically:

[0056]

[0057] Among them, L1(t) is the dynamic load rate at time t, a i is the fitting coefficient, t i For segmented time nodes, the fitting coefficients are dynamically updated by the least square method to ensure the accuracy of load rate calculation.

[0058] Through these data, the piecewise polynomial fitting algorithm begins to perform preliminary calculations of the dynamic load rate. This step ensures that the preliminary load rate can reflect the current load situation of the system in real time, laying the foundation for subsequent optimization. Preferably, the present invention uses at least three segments of polynomial fitting, and the duration of each segment is preferably set to 5 minutes to capture the load changes of the system in different time periods.

[0059] Furthermore, in order to eliminate transient fluctuations in the initial calculation of the load factor, the present invention uses Laplace transform to smooth it. Specifically, the calculation formula of the smoothed load factor is as follows:

[0060] L2(s)=∫0 ∞ L1(t)e -st dt

[0061] Wherein, L2(s) is the smoothed load rate in the Laplace domain, and s is a complex variable used for frequency characteristic analysis. Preferably, in an embodiment of the present invention, the parameter range of the Laplace transform is selected to achieve the best smoothing effect, and the |s| value is controlled between 0.1 and 1.0. Through this step, the system can effectively filter short-term fluctuations in the load rate caused by sensor noise or sudden changes in the environment, ensuring that subsequent calculation results are more stable and reliable.

[0062] In one embodiment of the present invention, based on Laplace smoothing, in order to further optimize the load rate change path, the present invention uses a variational method to calculate the optimal load rate change path, and the calculation formula for the optimized load rate is as follows:

[0063]

[0064] Among them, L3(t) is the optimized load rate, λ is the penalty factor, preferably 0.5-2.0; L is the first-order derivative of the load rate, which is used to measure the smoothness of the load rate change. The core of this step is to balance the dynamic smoothness and accuracy of the load rate.

[0065] Preferably, the present invention can dynamically adapt to different environmental conditions by adjusting the value of the penalty factor λ. For example, when the ambient temperature fluctuates greatly, the penalty factor λ can be appropriately increased to improve the stability of the load rate change.

[0066] In one embodiment of the present invention, based on the optimized load rate, the present invention further optimizes the coupling relationship between the load rate, environmental parameters and refrigerant flow rate through a multi-dimensional coupling matrix. The specific calculation formula is as follows:

[0067]

[0068] Where M is the coupling matrix, which is defined as follows:

[0069]

[0070] μ ij is the coupling factor, which indicates the influence of the i-th parameter on the j-th parameter, and M is the coupling matrix, which is used to quantify the correlation between the parameters. e is the ambient temperature, P s is the inspiratory pressure, P d is the exhaust pressure, Q is the refrigerant flow rate. Preferably, the coupling factor μ in the matrix ij The value is dynamically adjusted according to the actual operating conditions, and the initial setting range is 0.01 to 0.1.

[0071] This step has significant advantages in achieving coordinated optimization among parameters. e For example, when it fluctuates within the range of 20 to 35°C, μ 12 The value of will be automatically adjusted to keep the load rate stable. Through matrix coupling, global optimization among load rate, environmental parameters and flow rate is achieved.

[0072] In one embodiment of the present invention, finally, the refrigerant flow rate is dynamically regulated by a Gaussian process regression model (GPR), and the calculation formula for optimizing the refrigerant flow rate is as follows:

[0073] Q adjusted =G(L4,T e ,P s ,P d )

[0074] Among them, Q adjustedis the optimized refrigerant flow rate, g is the Gaussian process regression kernel function. Preferably, the present invention uses a radial basis kernel function (RBF) for fitting, and the value range of its parameter σ is 0.1 to 1.0.

[0075] This step can dynamically predict and optimize the refrigerant flow rate by combining historical operating data with real-time environmental parameters, thereby achieving the best heat exchange efficiency under different load conditions. s When the pressure fluctuates within the range of 0.8-1.2 MPa, the control error of the refrigerant flow can be controlled within 2%. GPR ensures high-precision regulation of the refrigerant flow under complex nonlinear conditions, solving the problem of difficulty in fitting nonlinear models in existing technologies.

[0076] The present invention forms a highly intelligent air-cooled heat pump control method through the optimization of the above steps and algorithms, from data collection to dynamic adjustment of load rate, and then to precise control of refrigerant flow. By introducing innovative algorithms and detailed parameter optimization, the present invention can effectively improve the overall energy efficiency of the system and ensure operational stability under complex and changeable working conditions.

[0077] In one embodiment of the present invention, the present invention uses a Gaussian process regression model to further dynamically control the refrigerant flow rate based on the load rate after coupling optimization. The Gaussian process regression model optimizes the refrigerant flow rate in real time by constructing a nonlinear relationship between the refrigerant flow rate and the system operating parameters. The optimized refrigerant flow rate calculation formula is:

[0078] Q adjusted =G(L4,T e ,P s ,P d )

[0079] Among them, Q adjusted is the optimized refrigerant flow rate, G is the Gaussian process regression kernel function, which is used to construct a nonlinear mapping relationship; L4 is the load rate after coupling optimization; T e is the ambient temperature; P s is the compressor suction pressure; P d is the compressor exhaust pressure. In a preferred embodiment of the present invention, Gaussian process regression uses a radial basis kernel function (RBF), which is defined as follows:

[0080]

[0081] Among them, x i and x j is the input parameter vector, for example (L4,T e ,P s ,P d ) different values; σ is the kernel function parameter, which controls the smoothness of the model, and the preferred range is 0.1~1.0.

[0082] The Gaussian process regression model can effectively predict the changing trend of the refrigerant flow rate, ensuring that the refrigerant flow rate can be regulated with high accuracy and adaptability when the environmental parameters fluctuate greatly. For example, when the ambient temperature changes from 30°C to 40°C, Q adjusted Able to dynamically adjust to maintain the heat transfer efficiency of the system.

[0083] In one embodiment of the present invention, the Gaussian process regression model in the present invention dynamically updates kernel function parameters using historical operating data and real-time environmental parameters, thereby achieving precise control of refrigerant flow.

[0084] Specifically, the present invention uses sample points (L4, T e ,P s ,P d ,Q) Continuously expand the training data set so that the Gaussian process model can cover more operating conditions. For example, when seasonal changes cause large fluctuations in ambient temperature, the model can automatically adjust the kernel function parameters based on new data to further improve the accuracy of refrigerant flow prediction.

[0085] Preferably, the update cycle of the model can be set to once every 10 minutes to ensure that the model has high real-time performance when the working conditions change. Through dynamic updates, the model can cope with complex and changing working conditions, further improving the intelligence level of the system.

[0086] In one embodiment of the present invention, the present invention uses the optimized refrigerant flow rate to control the opening of the electronic expansion valve, thereby achieving accurate circulation of the refrigerant between the indoor and outdoor heat exchangers.

[0087] The electronic expansion valve is a key actuator in the present invention, and its opening is dynamically adjusted by the refrigerant flow control module 5. Specifically, the expansion valve opening calculation formula is as follows:

[0088] θ=f(Q adjusted )

[0089] Where, θ is the opening of the electronic expansion valve, f(Q adjusted ) is the functional relationship between the opening and the optimized refrigerant flow, preferably a linear function or a piecewise linear function. By adjusting the expansion valve opening, the refrigerant can efficiently flow between the indoor heat exchanger 6 and the outdoor heat exchanger 7, thereby maintaining the target load rate. In a preferred embodiment of the present invention, when Q adjusted When the flow rate is around 300L / min, the expansion valve opening can be set to 45% to 55% to ensure optimal heat exchange efficiency.

[0090] In one embodiment of the present invention, the refrigerant circulation path between the indoor heat exchanger and the outdoor heat exchanger is dynamically adjusted by further optimizing the compressor load rate and the refrigerant flow rate.

[0091] The control module 5 calculates the inlet and outlet temperature difference of the indoor and outdoor heat exchangers in real time to determine the current heat exchange state of the system. When the temperature difference is less than the set threshold (such as 5°C), the refrigerant circulation path is switched to ensure the heat exchange efficiency of the system. The specific switching logic is:

[0092] ΔT indoor =T in -T out <5℃

[0093] Where, ΔT indoor is the inlet and outlet temperature difference of the indoor heat exchanger, T in and T out are the inlet and outlet temperatures of the heat exchanger, respectively. Through this control logic, the present invention can achieve dynamic optimization of the heat exchange performance of the system under different load conditions, avoiding the efficiency loss caused by improper path selection in the traditional system.

[0094] Through this control logic, the present invention can achieve dynamic optimization of the system heat exchange performance under different load conditions, avoiding efficiency loss caused by improper path selection in traditional systems.

[0095] In one embodiment of the present invention, the air-cooled heat system of the present invention includes a compression device, an indoor heat exchanger 6, an outdoor heat exchanger 7 and a control module 5, and the control module dynamically optimizes the system operation status based on the above method.

[0096] The compression equipment in the system ensures stable and efficient operation of the system through the load rate and refrigerant flow instructions provided by the control module. The control module 5 interacts with the sensor network in real time and dynamically adjusts the system parameters through the above algorithm, so that the system can always maintain efficient operation under complex environmental conditions.

[0097] In a preferred embodiment of the present invention, by implementing the above-mentioned air-cooled heat pump control method, the system's energy efficiency ratio (COP) can be improved by 15% to 25%, which significantly reduces energy consumption and improves operational stability.

[0098] The present invention provides an air-cooled heat pump control method, which optimizes system performance through algorithms such as piecewise polynomial fitting, Laplace transform, variational method, multidimensional coupling matrix and Gaussian process regression. In the embodiment, the following parameters are specifically used for testing:

[0099] Ambient temperature: 30℃; Suction pressure: 1.2MPa; Exhaust pressure: 2.8MPa; Initial refrigerant flow rate: 350L / min;

[0100] The control system dynamically adjusts the refrigerant flow rate based on real-time parameters using the Gaussian process regression model, and controls the opening of the electronic expansion valve to optimize the heat exchange efficiency.

[0101] The comparative example adopts the traditional constant frequency load rate calculation method and fixed refrigerant flow control strategy. All other operating parameters are consistent with the embodiment, including:

[0102] Ambient temperature: 30°C; Suction pressure: 1.2MPa; Exhaust pressure: 2.8MPa; Refrigerant flow rate: fixed at 350L / min

[0103] In the comparative example, the opening of the electronic expansion valve remains unchanged, and the refrigerant flow in the heat exchanger cannot be dynamically adjusted according to the real-time load rate.

[0104] To verify the superiority of the present invention, the following key indicators were tested:

[0105] 1. Energy efficiency ratio (COP): The ratio of the cooling / heating capacity provided by the system per unit time to the input power is measured by a calorimeter.

[0106] 2. Heat exchange efficiency: Calculate the actual heat exchange efficiency of the heat exchanger by detecting the inlet and outlet temperature difference and refrigerant flow rate of the heat exchanger.

[0107] 3. System stability: It is evaluated by the fluctuation of load factor during operation, and the load factor fluctuation is calculated using the standard deviation (SD).

[0108] The detection method adopts the international standards ASHRAE 37-2009 and GB / T 18430.1-2007, and the test time is 8 hours of continuous operation.

[0109] The test results are shown in the following table:

[0110] index Example Comparative Example Energy efficiency ratio (COP) 4.75 3.95 Heat transfer efficiency (%) 92.3 80.1 Load factor fluctuation (SD) 0.05 0.22

[0111] 1. Energy efficiency ratio (COP) analysis: The energy efficiency ratio of the embodiment is significantly higher than that of the comparative example, which is increased by about 20%. This result shows that through the dynamic optimization control method of the present invention, the system can more efficiently convert the input power into cooling / heating. This is mainly attributed to the Gaussian process regression model dynamically controlling the refrigerant flow rate, so that the system always operates within the optimal load rate range.

[0112] 2. Analysis of heat exchange efficiency: In the embodiment, the heat exchange efficiency reaches 92.3%, which is significantly higher than 80.1% in the comparative example. This shows that the dynamic refrigerant flow and electronic expansion valve control of the present invention can effectively improve the performance of the heat exchanger and reduce heat loss.

[0113] 3. Load rate fluctuation analysis: The load rate fluctuation standard deviation in the embodiment is only 0.05, while that in the comparative example is 0.22. This shows that the present invention can significantly improve the stability of system operation and avoid energy efficiency loss caused by load rate fluctuation. This performance is due to the application of Laplace transform and variational method, which realizes the smoothing and optimization of load rate.

[0114] According to the above test results, the embodiments are superior in energy efficiency ratio, heat exchange efficiency and system stability. Especially under complex working conditions, through the multi-layer optimization algorithm of the present invention, the system can quickly respond to load changes and dynamically adjust the refrigerant flow and heat exchange path, thereby greatly improving the overall performance.

[0115] The present invention significantly improves the energy efficiency and operation stability of the air-cooled heat pump system by improving the traditional control strategy. This not only reduces energy consumption, but also prolongs the service life of the equipment, providing reliable technical support for practical applications.

[0116] In summary, the remarkable superiority of the present invention under complex working conditions fully verifies its wide applicability and technical innovation in practical applications.

[0117] It should be noted that the above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the principles of the present invention should be included in the protection scope of the present invention.

Claims

1. Air-cooled heat pump control method, characterized in that: The steps include: Collect ambient temperature, compressor suction pressure, exhaust pressure and refrigerant flow parameters; Dynamic load rate is calculated by piecewise polynomial fitting; Laplace transform is used to smooth the load factor; Optimize the load rate change path using the variational method; Optimize the load factor based on the multi-dimensional coupling matrix; The refrigerant flow rate is regulated by Gaussian process regression. The refrigerant flow rate regulated by Gaussian process regression is used to dynamically adjust the refrigerant circulation path to optimize system operating parameters.

2. The air-cooled heat pump control method according to claim 1, characterized in that: The calculation of the dynamic load rate is based on a piecewise polynomial fitting model, specifically: Among them, L1(t) is the dynamic load rate at time t, a i is the fitting coefficient, t i For segmented time nodes, the fitting coefficients are dynamically updated by the least square method to ensure the accuracy of load rate calculation.

3. The air-cooled heat pump control method according to claim 2, characterized in that: The dynamic load rate is smoothed by Laplace transform, specifically: Wherein, L2(s) is the load rate in the Laplace domain, s is a complex variable used to characterize the frequency characteristics of the load rate, and the Laplace transform is used to eliminate transient fluctuations in dynamic calculations.

4. The air-cooled heat pump control method according to claim 3, characterized in that: Based on the smoothed load rate, the load rate path is optimized by the variational method. The calculation formula for the optimized load rate is as follows: Among them, L3(t) is the optimized load rate at time t, λ is the penalty factor, and L is the first-order derivative of the load rate, which is used to balance the smoothness and deviation of the load rate change.

5. The air-cooled heat pump control method according to claim 4, characterized in that: The optimized load rate is further optimized by a multi-dimensional coupling matrix, specifically: Where M is the coupling matrix, which is defined as follows: μ ij is the coupling factor, which indicates the influence of the i-th parameter on the j-th parameter and is used to describe the interaction between the parameters. e is the ambient temperature, P s is the inspiratory pressure, P d is the exhaust pressure, Q is the refrigerant flow rate.

6. The air-cooled heat pump control method according to claim 5, characterized in that: The refrigerant flow rate is dynamically regulated by the Gaussian process regression model, and the calculation formula of the model is: Q adjusted =G(L4,T e ,P s ,P d ) Among them, Q adjusted is the optimized refrigerant flow, G is the Gaussian process regression model, and the accurate prediction and optimization of the refrigerant flow can be achieved by updating the kernel function parameters in real time.

7. The air-cooled heat pump control method according to claim 6, characterized in that: The Gaussian process regression model utilizes historical operation data and real-time parameters to dynamically update the kernel function, and the kernel function is used to characterize complex nonlinear relationships to improve the accuracy of refrigerant flow prediction.

8. The air-cooled heat pump control method according to claim 7, characterized in that: The optimized refrigerant flow is used to control the opening of the electronic expansion valve, and the electronic expansion valve adjusts the flow path of the refrigerant in the heat exchanger according to the refrigerant flow.

9. The air-cooled heat pump control method according to claim 8, characterized in that: The optimized compressor load rate and refrigerant flow rate are used to dynamically adjust the refrigerant circulation path between the indoor heat exchanger and the outdoor heat exchanger, and the path switching is achieved by the control module according to the real-time operating parameters of the system.

10. An air-cooled heat pump for executing the method according to any one of claims 1 to 9, characterized in that: The air-cooled heat pump includes a compression device, an indoor heat exchanger, an outdoor heat exchanger and a control module. The control module dynamically optimizes the system operation status based on the method to improve the overall energy efficiency.

Images