Intelligent regulation and control system for heat supply and power saving of heat pump

Abstract

The invention discloses an intelligent regulation and control system for heat supply and power saving of a heat pump. The system comprises a heat pump body control optimization module, a heat pump kernel regulation optimization module, a heat source dynamic switching module and a heat supply intelligent power saving module. The invention belongs to the technical field of heat pump power-saving intelligent regulation and control, a variable-capacity compression control module accurately regulates the load of a compressor through variable-capacity control of a bimodal slide valve, and more efficient energy utilization is achieved; the heat pump working condition optimization module adopts a multi-target dynamic optimization algorithm, comprehensively considers factors such as system efficiency, service life and noise, and realizes precise adjustment of working conditions; the multi-heat-source dynamic switching module intelligently selects an optimal heat source and realizes non-inductive switching through a game decision algorithm in combination with heat source entropy efficiency, an equipment health index and energy consumption cost, so that pressure fluctuation and system instability in a heat source switching process are reduced; the working efficiency of the heat pump system is effectively improved, the energy consumption is reduced, and the maintenance cost and the failure rate are reduced.

Description

Technical Field

[0001] The present invention belongs to the technical field of heat pump power saving intelligent control, and in particular relates to an intelligent control system for heat pump heating and power saving. Background Art

[0002] The intelligent control system for heat pump heating and electricity conservation is a highly efficient heating control and optimization system based on heat pump technology. This intelligent control system optimizes operating parameters (such as temperature, flow rate, and compressor frequency) to dynamically match user heat load requirements, significantly reducing electricity consumption. Its core function is to extract low-quality thermal energy and convert it into high-quality heat for building use. Simultaneously, through IoT technology, it monitors energy consumption data in real time and automatically adjusts operating modes. This system ensures stable heating while maintaining both environmental and economic performance, meeting the requirements for upgrading building energy systems.

[0003] However, existing intelligent control systems for heat pump heating and electricity saving suffer from the drawback of traditional heat pump systems being overly dependent on a single module under a single control path, making unified coordination and module coupling difficult for energy efficiency optimization. In existing variable-capacity compression control processes, traditional methods suffer from a relatively crude load regulation method for the compressor, lacking dynamic adjustment capabilities and unable to fine-tune the compressor's operating state for different load conditions. This leads to low energy efficiency and can even cause compressor overheating or overcooling due to untimely adjustment, increasing system maintenance costs and failure rates. In existing heat pump operating condition optimization processes, traditional optimization methods have poor optimization effects when addressing multiple objectives (such as efficiency, lifespan, and noise) due to the numerous and variable parameters involved in the complex actual operating conditions of heat pumps, often resulting in an inability to balance conflicts between different objectives. In existing multi-heat source intelligent switching processes, traditional heat source switching is often accompanied by large pressure fluctuations, which can adversely affect the system, such as causing system instability, frequent shutdowns, and increased equipment wear, thereby affecting the operating efficiency and reliability of the entire heat pump system. Summary of the Invention

[0004] In view of the above situation, in order to overcome the defects of the prior art, the present invention provides an intelligent control system for heat pump heating and power saving. In view of the disadvantages of the traditional heat pump system in the existing intelligent control system for heat pump heating and power saving, the traditional heat pump system has the disadvantages of over-reliance on a certain module under a single control path, and the technical problems of energy efficiency optimization being difficult to coordinate and couple with modules, this solution creatively adopts a comprehensive process design and module design that combines variable capacity compression control, heat pump operating condition optimization and multi-heat source intelligent switching, realizes the coordination between the sub-modules in the system, and maximizes the overall energy efficiency of the heat pump; in view of the disadvantages of the traditional heat pump system in the existing variable capacity compression control process ... The load regulation mode of the compressor in the method is relatively rough and lacks dynamic adjustment capability. It is impossible to finely adjust the working state of the compressor under different load conditions, resulting in low energy efficiency and even overheating or overcooling of the compressor due to untimely adjustment, which increases the maintenance cost and failure rate of the system. This solution creatively adopts a dual-mode sliding valve variable capacity compression control method to perform variable capacity compression control, thereby achieving more accurate compressor load regulation. Through the dynamic adjustment of the sliding valve displacement, the compressor can achieve optimal efficiency under high load and low load conditions, thereby improving operational stability. In the existing heat pump working condition optimization process, there are problems. Under the complex actual operating conditions of heat pumps, there are many parameters involved and they are very variable. Traditional optimization methods have poor optimization effects when facing multiple objectives (such as efficiency, life, and noise), which often leads to technical problems such as being unable to balance the contradictions between different objectives. This solution creatively adopts a multi-objective dynamic optimization algorithm combined with digital modeling of heat pumps to optimize the working conditions of heat pumps, achieving comprehensive consideration of multiple objectives such as system performance, life, and noise. Through digital modeling of heat pumps, the influence of various parameters on the performance of heat pumps is accurately simulated; in the existing multi-heat source intelligent switching process, the traditional heat source switching process is often accompanied by large pressure fluctuations. , which may have adverse effects on the system, such as causing system instability, frequent shutdowns or increased equipment wear, thereby affecting the operating efficiency and reliability of the entire heat pump system. This solution creatively adopts a multi-heat source game decision algorithm combined with a dual-path improvement evaluation of the health and energy consumption of heat pump system components to perform dynamic switching of multiple heat sources, thereby achieving a more efficient heat source selection and switching mechanism. Combined with the entropy efficiency of the heat source, the equipment health index and the energy consumption cost, it can intelligently select the optimal heat source under different operating conditions and realize seamless switching, thereby improving the overall working efficiency of the heat pump and reducing the risk of pressure fluctuations and system instability caused by heat source switching.

[0005] The technical solution adopted by the present invention is as follows: the present invention provides an intelligent control system for heat pump heating and power saving, including a heat pump body control optimization module, a heat pump core regulation optimization module, a heat source dynamic switching module and a heating intelligent power saving module;

[0006] The heat pump body control optimization module is used for variable capacity compression control, obtains compressor displacement control optimization reference data through variable capacity compression control, and sends the compressor displacement control optimization reference data to the heating intelligent power saving module;

[0007] The heat pump core regulation optimization module is used for heat pump operating condition optimization, obtains multi-objective optimal operating condition reference data through heat pump operating condition optimization, and sends the multi-objective optimal operating condition reference data to the heating intelligent power saving module;

[0008] The heat source dynamic switching module is used for dynamic switching of multiple heat sources, obtains heat source decision reference instruction data through dynamic switching of multiple heat sources, and sends the heat source decision reference instruction data to the heating intelligent power saving module;

[0009] The heating intelligent power-saving module is used for intelligent power saving of heat pumps, and obtains comprehensive reference data of power-saving efficiency through intelligent power saving of heat pumps.

[0010] Furthermore, the variable capacity compression control is used to optimize the efficiency of the compressor under load. Specifically, a dual-mode slide valve variable capacity compression control method is used to perform variable capacity compression control, and through real-time calculation of the internal volume ratio, the slide valve displacement is dynamically adjusted to obtain reference data for compressor displacement control optimization. The method includes the following steps: heat pump operating parameter collection, dynamic improvement calculation of the target internal volume ratio, slide valve displacement target calculation, dual-mode compression control, variable capacity and frequency conversion coordinated improvement, and variable capacity compression control;

[0011] The heat pump operating parameter collection is specifically performed at a sampling period of once per second, and the raw data noise is processed by low-pass filtering to obtain optimized heat pump operating parameter data;

[0012] The optimized heat pump operating parameter data includes evaporation pressure parameters, condensation pressure parameters, ambient temperature parameters, slide valve displacement parameters and operating frequency parameters;

[0013] The target volume ratio dynamic improvement calculation is specifically to dynamically calculate the optimal volume ratio of the compressor based on the optimized heat pump operating parameter data to obtain dynamic reference data of the volume ratio;

[0014] The target spool valve displacement calculation is specifically performed by numerically inversely calculating the required spool valve displacement based on the dynamic reference data of the internal volume ratio, and calculating the target spool valve displacement by constructing a relationship model between the spool valve displacement and the internal volume ratio to obtain the target spool valve displacement reference data;

[0015] The dual-mode compression control is specifically performed by constructing a load dual-mode control judgment equation to perform dual-mode compression control, and by constructing a high-load mode and a low-load mode to perform compression control to obtain compression control logic reference data;

[0016] The high load mode specifically refers to an operating mode in which the current compressor load is greater than 60% of the rated load, the slide valve displacement control capacity is set to 70% to 100%, and the dual rotor parallel operation is started;

[0017] The low-load mode specifically refers to an operating mode in which the current compressor load is less than or equal to 60% of the rated load, the slide valve displacement control capacity is set to 30% to 70%, and single rotor operation is started;

[0018] The calculation formula of the load dual-mode control judgment equation is:

[0019] ;

[0020] Where, is the current compressor load factor parameter, Q load is the current load parameter of the compressor, which is predicted and calculated by the standard long short-term memory neural network. rated It is the rated heating capacity of the compressor;

[0021] The variable capacity and frequency conversion coordinated improvement is specifically to perform variable capacity and frequency conversion coordinated slide valve adjustment improvement based on the target slide valve displacement reference data by synchronously fine-tuning the motor frequency to obtain the target motor frequency parameter;

[0022] The variable capacity compression control specifically detects and controls compressor outlet temperature and pressure fluctuations based on the target motor frequency parameter, the compression control logic reference data, and the content volume ratio dynamic reference data, and avoids compressor instability through fault protection rules to obtain compressor displacement control optimization reference data;

[0023] The compressor displacement control optimization reference data specifically includes a target internal volume ratio, a target slide valve displacement, a load factor parameter, a target motor frequency parameter, and a fault protection rule execution parameter;

[0024] The fault protection rule specifically reduces the opening of the slide valve and forcibly reduces the load by setting the exhaust temperature threshold and the condensing pressure threshold.

[0025] Furthermore, the heat pump operating condition optimization is used to dynamically match the optimal heat pump operating parameters. Specifically, a multi-objective dynamic optimization algorithm combined with heat pump digital modeling is used to optimize the heat pump operating conditions and obtain multi-objective optimal operating condition reference data. The algorithm includes the following steps: heat pump digital modeling, multi-objective optimization target construction, dynamic optimization framework construction, real-time operating condition decision adjustment, dynamic adjustment of refrigerant components, and heat pump operating condition optimization.

[0026] The heat pump digital modeling specifically includes defining the input and output spaces of the heat pump digital model required for the heat pump operating condition optimization, and performing heat pump digital modeling by calculating the relationship between heat pump performance indicators to obtain a heat pump digital basic model;

[0027] The input and output space definitions include input space definitions and output space definitions. The input variables of the input space specifically include heat pump evaporation temperature, condensing temperature, suction superheat, subcooling, refrigerant component ratio parameters, air volume parameters, and water flow parameters;

[0028] The output variables of the output space specifically include heating parameters, compressor power parameters, system noise interference parameters and heat pump life depreciation rate parameters;

[0029] The multi-objective optimization target construction is specifically to obtain a multi-objective optimization function of the heat pump operating condition by constructing a four-dimensional optimization objective function, and to perform preliminary optimization of the heat pump operating condition and calculate preliminary optimized operating parameters of the heat pump based on the multi-objective optimization function of the heat pump operating condition, wherein the four-dimensional optimization objective function includes a function for maximizing a heat pump performance index, a function for minimizing a heat pump life depreciation rate parameter function, a function for minimizing a system noise interference parameter function, and a function for minimizing an electricity cost expenditure;

[0030] The dynamic optimization framework is constructed by combining the multi-objective optimization function of the heat pump operating condition with a standard reinforcement learning method combined with a multi-objective proximal strategy optimization algorithm, and constructing a dynamic optimization framework for the heat pump operating condition based on the digital basic model of the heat pump to obtain a digital simulation reinforcement learning training framework for the heat pump. Based on the digital simulation reinforcement learning training framework for the heat pump, reinforcement learning dynamic optimization is performed to obtain dynamic optimization operating parameter data of the heat pump;

[0031] The heat pump digital simulation reinforcement learning training framework includes a state space, an action space, and a four-dimensional reward function;

[0032] The four-dimensional reward function is specifically defined by weighting according to the multi-objective optimization function of the heat pump operating condition;

[0033] The real-time working condition decision adjustment is specifically to collect real-time working condition state parameters, call the heat pump digital simulation reinforcement learning training framework to perform reinforcement learning training, obtain a working condition strategy optimization network, and obtain optimal working condition adjustment action reference data by inputting the working condition state parameters obtained by the real-time working condition state parameter collection as the state space;

[0034] The optimal working condition adjustment action reference data includes suction superheat adjustment action, subcooling adjustment action, refrigerant component ratio parameter adjustment action, air volume parameter adjustment action and water flow parameter adjustment action;

[0035] The dynamic adjustment of the refrigerant composition is specifically to construct a refrigerant ratio optimization improvement sub-block. When the ambient temperature is lower than -10 degrees Celsius, the refrigerant composition is dynamically adjusted according to the improved adjustment equation, and the optimal operating condition adjustment action reference data is used to assist in the comprehensive adjustment of the heat pump operating condition to obtain the dynamic adjustment data of the refrigerant composition ratio parameters;

[0036] The calculation formula of the improved adjustment equation is:

[0037] ;

[0038] Where, It is the dynamic adjustment data of the refrigerant component ratio parameters. is the refrigerant component ratio parameter adjustment action parameter in the optimal working condition adjustment action reference data, r 290 is the volume ratio of propane, a low-temperature heating refrigerant, in the heat pump;

[0039] The heat pump operating condition optimization is specifically to perform comprehensive optimization of the heat pump operating condition through the heat pump digital modeling, the multi-objective optimization target construction, the dynamic optimization framework construction and real-time operating condition decision adjustment, combined with the dynamic adjustment of the refrigerant components, to obtain multi-objective optimal operating condition reference data;

[0040] The multi-objective optimal operating condition reference data specifically includes optimal heat pump performance index parameters, optimal life depreciation rate parameters, optimal noise interference parameters, optimal electricity expenditure parameters and optimal refrigerant component dynamic optimization parameters.

[0041] Furthermore, the dynamic switching of multiple heat sources is used for heat source selection optimization, specifically using a multi-heat source game decision algorithm combined with a dual-path improvement evaluation of the health energy consumption of heat pump system components to perform dynamic switching of multiple heat sources and obtain heat source decision reference instruction data, including the following steps: heat source entropy efficiency evaluation, equipment evaluation, heat source benefit matrix construction, game decision solution and dynamic switching of multiple heat sources;

[0042] The heat source entropy efficiency assessment is specifically to perform a thermodynamic grade assessment on each available heat source of the heat pump through heat source entropy efficiency calculation to obtain heat source entropy efficiency assessment data;

[0043] The equipment evaluation is specifically to perform an equipment health evaluation on the heat pump system components based on the optimal life depreciation rate parameter in the multi-objective optimal operating condition reference data and the load rate parameter in the compressor displacement control optimization reference data, for the life depreciation rate of the heat pump corresponding to each available heat source, to obtain an equipment health index parameter, and to obtain an equipment energy consumption index parameter by calculating the unit heating source energy consumption cost;

[0044] The heat source benefit matrix is ​​constructed by constructing a comprehensive heat source benefit matrix, calculating the heat source instant score value, and obtaining the heat source instant score reference data;

[0045] The game decision solution specifically adopts a standard Nash equilibrium game decision algorithm to maximize the comprehensive heat source instant score benefit calculation based on the heat source instant score reference data and the heat source benefit comprehensive matrix to obtain the optimal heat source switching decision reference data;

[0046] The dynamic switching of multiple heat sources is specifically performed by constructing a non-perceptible transition heat source switching method, dynamically switching the heat pump heat source according to the optimal heat source switching decision reference data, and obtaining heat source decision reference instruction data.

[0047] Furthermore, the heat pump intelligent power saving is used to perform comprehensive heat pump intelligent power saving management based on the results of comprehensive compression control, operating condition optimization and heat source switching. Specifically, it receives the compressor displacement control optimization reference data, dynamically matches the compressor displacement and operating frequency, and performs adaptive optimization of the compressor load, receives the multi-objective optimal operating condition reference data, adjusts the heat pump operating parameters in real time, and receives heat source decision reference instruction data, intelligently selects the optimal heat source and realizes seamless switching, and obtains comprehensive reference data on power saving efficiency.

[0048] The beneficial effects achieved by the present invention using the above scheme are as follows:

[0049] (1) In view of the drawbacks of the existing intelligent control system for heat pump heating and electricity saving, the traditional heat pump system has the disadvantage of over-reliance on a certain module under a single control path, and the technical problems of difficulty in unified coordination and module coupling in energy efficiency optimization. This solution creatively adopts a comprehensive process design and module design that combines variable capacity compression control, heat pump operating condition optimization and multi-heat source intelligent switching, realizing the coordination between the sub-modules in the system and maximizing the overall energy efficiency of the heat pump;

[0050] (2) In view of the technical problems in the existing variable capacity compression control process, the load regulation method of the compressor in the traditional method is relatively rough and lacks dynamic adjustment capability. It is impossible to finely adjust the working state of the compressor under different load conditions, resulting in low energy efficiency and even causing the compressor to overheat or overcool due to untimely adjustment, which increases the maintenance cost and failure rate of the system. This solution creatively adopts a dual-mode sliding valve variable capacity compression control method to perform variable capacity compression control, achieving more accurate compressor load regulation. Through the dynamic adjustment of the sliding valve displacement, the compressor can achieve optimal efficiency under high load and low load conditions, thereby improving operational stability.

[0051] (3) In the existing heat pump operating condition optimization process, there are many parameters involved in the complex actual operating conditions of the heat pump, and they are very variable. The traditional optimization method has a poor optimization effect when facing multiple objectives (such as efficiency, life, and noise), which often leads to the technical problem of being unable to balance the contradictions between different objectives. This solution creatively adopts a multi-objective dynamic optimization algorithm combined with heat pump digital modeling to optimize the heat pump operating conditions, achieving comprehensive consideration of multiple objectives such as system performance, life, and noise. Through heat pump digital modeling, the influence of various parameters on heat pump performance is accurately simulated;

[0052] (4) In view of the technical problem that in the existing multi-heat source intelligent switching process, the traditional heat source switching process is often accompanied by large pressure fluctuations, which may have adverse effects on the system, such as causing system instability, frequent shutdowns or increased equipment wear, thereby affecting the operating efficiency and reliability of the entire heat pump system, this solution creatively adopts a multi-heat source game decision algorithm combined with a dual-path improvement evaluation of the health and energy consumption of heat pump system components to perform dynamic switching of multiple heat sources, thereby achieving a more efficient heat source selection and switching mechanism. Combined with the entropy efficiency of the heat source, the equipment health index and the energy consumption cost, it can intelligently select the optimal heat source under different operating conditions and realize seamless switching, thereby improving the overall working efficiency of the heat pump and reducing the risk of pressure fluctuations and system instability caused by heat source switching. BRIEF DESCRIPTION OF THE DRAWINGS

[0053] Figure 1 A schematic diagram of the structure of an intelligent control system for heat pump heating and electricity saving provided by the present invention;

[0054] Figure 2 A flow chart showing the steps executed by the heat pump control optimization module;

[0055] Figure 3 A flow chart illustrating the steps performed by the heat pump core regulation optimization module;

[0056] Figure 4 A flow chart showing the steps executed by the heat source dynamic switching module.

[0057] The accompanying drawings are used to provide further understanding of the present invention and constitute a part of the specification. They are used to explain the present invention together with the embodiments of the present invention and do not constitute a limitation of the present invention. DETAILED DESCRIPTION

[0058] The technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all the embodiments; based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.

[0059] Example 1, see Figure 1 , the technical solution adopted by the present invention is as follows: the present invention provides an intelligent control system for heat pump heating and power saving, including a heat pump body control optimization module, a heat pump core regulation optimization module, a heat source dynamic switching module and a heating intelligent power saving module;

[0060] The heat pump body control optimization module is used for variable capacity compression control, obtains compressor displacement control optimization reference data through variable capacity compression control, and sends the compressor displacement control optimization reference data to the heating intelligent power saving module;

[0061] The heat pump core regulation optimization module is used for heat pump operating condition optimization, obtains multi-objective optimal operating condition reference data through heat pump operating condition optimization, and sends the multi-objective optimal operating condition reference data to the heating intelligent power saving module;

[0062] The heat source dynamic switching module is used for dynamic switching of multiple heat sources, obtains heat source decision reference instruction data through dynamic switching of multiple heat sources, and sends the heat source decision reference instruction data to the heating intelligent power saving module;

[0063] The heating intelligent power-saving module is used for intelligent power saving of heat pumps, and obtains comprehensive reference data of power-saving efficiency through intelligent power saving of heat pumps.

[0064] By performing the above operations, in the existing intelligent control system for heat pump heating and electricity saving, there are disadvantages of traditional heat pump systems that are overly dependent on a certain module under a single control path, and the technical problems of energy efficiency optimization being difficult to coordinate and couple modules. This solution creatively adopts a comprehensive process design and module design that combines variable capacity compression control, heat pump operating condition optimization and multi-heat source intelligent switching, realizes the coordination between the sub-modules in the system, and maximizes the overall energy efficiency of the heat pump.

[0065] Example 2: This example is based on the above example. Figure 1 、 Figure 2The variable capacity compression control is used to optimize the efficiency of the compressor under load. Specifically, a dual-mode slide valve variable capacity compression control method is used to perform variable capacity compression control, and the slide valve displacement is dynamically adjusted by real-time calculation of the internal volume ratio to obtain reference data for compressor displacement control optimization. The method includes the following steps: heat pump operating parameter collection, dynamic improvement calculation of the target internal volume ratio, slide valve displacement target calculation, dual-mode compression control, variable capacity and frequency conversion coordinated improvement, and variable capacity compression control;

[0066] The heat pump operating parameter collection is specifically performed at a sampling period of once per second, and the raw data noise is processed by low-pass filtering to obtain optimized heat pump operating parameter data;

[0067] The optimized heat pump operating parameter data includes evaporation pressure parameters, condensation pressure parameters, ambient temperature parameters, slide valve displacement parameters and operating frequency parameters;

[0068] The target volume ratio dynamic improvement calculation is specifically to dynamically calculate the optimal volume ratio of the compressor based on the optimized heat pump operating parameter data to obtain dynamic reference data of the volume ratio;

[0069] The calculation formula of the optimal internal volume ratio is:

[0070] ;

[0071] Where, is the optimal content volume ratio, used to represent the dynamic reference data of the content volume ratio, P c is the condensation pressure parameter, P e is the evaporation pressure parameter, k1 is the pressure ratio fitting parameter, k2 is the temperature fitting parameter, T amb is the ambient temperature parameter, T0 is the reference temperature parameter;

[0072] Preferably, the specific value of the pressure ratio fitting parameter k1 is 0.5, the specific value of the temperature fitting parameter k2 is -0.01, and the specific value of the reference temperature parameter T0 is 20 degrees Celsius;

[0073] The target spool valve displacement calculation is specifically performed by numerically inversely calculating the required spool valve displacement based on the dynamic reference data of the internal volume ratio, and calculating the target spool valve displacement by constructing a relationship model between the spool valve displacement and the internal volume ratio to obtain the target spool valve displacement reference data;

[0074] The calculation formula of the relationship model between the displacement of the slide valve and the internal volume ratio is:

[0075] ;

[0076] Where, is the required slide valve displacement corresponding to the internal volume ratio, which is used to represent the reference data of the target slide valve displacement. max is the maximum sliding stroke of the slide valve, V min is the minimum content volume ratio, is the optimal content volume ratio;

[0077] Preferably, the minimum internal volume ratio V min The specific value of is 2.5. When the value of the optimal internal volume ratio is less than 2.5, the required slide valve displacement corresponding to the internal volume ratio is Set to 0 to protect the compressor from low pressure overload;

[0078] The dual-mode compression control is specifically performed by constructing a load dual-mode control judgment equation to perform dual-mode compression control, and by constructing a high-load mode and a low-load mode to perform compression control to obtain compression control logic reference data;

[0079] The high load mode specifically refers to an operating mode in which the current compressor load is greater than 60% of the rated load, the slide valve displacement control capacity is set to 70% to 100%, and the dual rotor parallel operation is started;

[0080] The low-load mode specifically refers to an operating mode in which the current compressor load is less than or equal to 60% of the rated load, the slide valve displacement control capacity is set to 30% to 70%, and single rotor operation is started;

[0081] The calculation formula of the load dual-mode control judgment equation is:

[0082] ;

[0083] Where, is the current compressor load factor parameter, Q load is the current load parameter of the compressor, which is predicted and calculated by the standard long short-term memory neural network. rated It is the rated heating capacity of the compressor;

[0084] The variable capacity and frequency conversion coordinated improvement is specifically to perform variable capacity and frequency conversion coordinated slide valve adjustment improvement based on the target slide valve displacement reference data by synchronously fine-tuning the motor frequency to obtain the target motor frequency parameter;

[0085] The calculation formula of the target motor frequency parameter is:

[0086] ;

[0087] Where, f * is the target motor frequency parameter, f base is the reference frequency parameter, P c is the condensation pressure parameter, Pe is the evaporation pressure parameter;

[0088] The variable capacity compression control specifically detects and controls compressor outlet temperature and pressure fluctuations based on the target motor frequency parameter, the compression control logic reference data, and the content volume ratio dynamic reference data, and avoids compressor instability through fault protection rules to obtain compressor displacement control optimization reference data;

[0089] The compressor displacement control optimization reference data specifically includes a target internal volume ratio, a target slide valve displacement, a load factor parameter, a target motor frequency parameter, and a fault protection rule execution parameter;

[0090] The fault protection rule specifically reduces the opening of the slide valve and forcibly reduces the load by setting the exhaust temperature threshold and the condensing pressure threshold.

[0091] By performing the above operations, in the existing variable capacity compression control process, there is a technical problem that the load regulation method of the compressor in the traditional method is relatively rough, lacks dynamic adjustment capability, and cannot finely adjust the working state of the compressor under different load conditions, resulting in low energy efficiency, and even causing the compressor to overheat or overcool due to untimely adjustment, thereby increasing the maintenance cost and failure rate of the system. This solution creatively adopts a dual-mode slide valve variable capacity compression control method to perform variable capacity compression control, thereby achieving more accurate compressor load regulation. Through the dynamic adjustment of the slide valve displacement, the compressor can achieve optimal efficiency under high load and low load conditions, thereby improving operational stability.

[0092] Example 3: This example is based on the above example. Figure 1 、 Figure 3 The heat pump operating condition optimization is used to dynamically match the optimal heat pump operating parameters. Specifically, a multi-objective dynamic optimization algorithm combined with heat pump digital modeling is used to optimize the heat pump operating condition and obtain multi-objective optimal operating condition reference data, including the following steps: heat pump digital modeling, multi-objective optimization target construction, dynamic optimization framework construction, real-time operating condition decision adjustment, dynamic adjustment of refrigerant components and heat pump operating condition optimization;

[0093] The heat pump digital modeling specifically includes defining the input and output spaces of the heat pump digital model required for the heat pump operating condition optimization, and performing heat pump digital modeling by calculating the relationship between heat pump performance indicators to obtain a heat pump digital basic model;

[0094] The input and output space definitions include input space definitions and output space definitions. The input variables of the input space specifically include heat pump evaporation temperature, condensing temperature, suction superheat, subcooling, refrigerant component ratio parameters, air volume parameters, and water flow parameters;

[0095] The output variables of the output space specifically include heating parameters, compressor power parameters, system noise interference parameters and heat pump life depreciation rate parameters;

[0096] The calculation formula of the heat pump performance index relationship is:

[0097] ;

[0098] Where COP is the heat pump performance index, which is used to represent the heat pump performance evaluation index of the heat pump digital basic model, Q heat is the heating capacity parameter, W comp is the compressor power parameter;

[0099] The multi-objective optimization target construction is specifically to obtain a multi-objective optimization function of the heat pump operating condition by constructing a four-dimensional optimization objective function, and to perform preliminary optimization of the heat pump operating condition and calculate preliminary optimized operating parameters of the heat pump based on the multi-objective optimization function of the heat pump operating condition, wherein the four-dimensional optimization objective function includes a function for maximizing a heat pump performance index, a function for minimizing a heat pump life depreciation rate parameter function, a function for minimizing a system noise interference parameter function, and a function for minimizing an electricity cost expenditure;

[0100] The calculation formula of the multi-objective optimization function of the heat pump operating condition is:

[0101] ;

[0102] Where, F target is the multi-objective optimization function of the heat pump working condition, maxmize is the maximization function, minimize is the minimization function, COP is the heat pump performance index, D life is the heat pump life depreciation rate parameter, W comp is the compressor power parameter, N is the system noise interference parameter, C elec is the electricity expenditure function, and p(t) is the electricity price calculation function;

[0103] The dynamic optimization framework is constructed by combining the multi-objective optimization function of the heat pump operating condition with a standard reinforcement learning method combined with a multi-objective proximal strategy optimization algorithm, and constructing a dynamic optimization framework for the heat pump operating condition based on the digital basic model of the heat pump to obtain a digital simulation reinforcement learning training framework for the heat pump. Based on the digital simulation reinforcement learning training framework for the heat pump, reinforcement learning dynamic optimization is performed to obtain dynamic optimization operating parameter data of the heat pump;

[0104] The heat pump digital simulation reinforcement learning training framework includes a state space, an action space, and a four-dimensional reward function;

[0105] The state space includes ambient temperature parameters, compressor current load parameters, heat pump evaporation temperature, condensation temperature, refrigerant component ratio parameters, air volume parameters and water flow parameters;

[0106] The dynamic space includes suction superheat adjustment action, subcooling adjustment action, refrigerant component ratio parameter adjustment action, air volume parameter adjustment action and water flow parameter adjustment action;

[0107] The four-dimensional reward function is specifically defined by weighting based on the multi-objective optimization function of the heat pump operating condition, and the calculation formula is:

[0108] ;

[0109] Where R is the four-dimensional reward function, w1 is the performance index weight, COP is the heat pump performance index, specifically used to represent the heat pump performance index maximization reward item, w2 is the heat pump life depreciation rate weight, D life is the heat pump life depreciation rate parameter, specifically used to represent the heat pump life depreciation rate parameter minimization reward item, w3 is the system noise interference weight, N is the system noise interference parameter, specifically used to represent the system noise interference parameter minimization reward item, w4 is the electricity expenditure weight, C elec is the electricity expenditure function, specifically used to represent the reward item for minimizing the electricity expenditure function;

[0110] Preferably, the specific value of the performance index weight w1 is 0.4, the specific value of the heat pump life depreciation rate weight w2 is 0.3, the specific value of the system noise interference weight w3 is 0.2, and the specific value of the electricity expenditure weight w4 is 0.1;

[0111] The real-time working condition decision adjustment is specifically to collect real-time working condition state parameters, call the heat pump digital simulation reinforcement learning training framework to perform reinforcement learning training, obtain a working condition strategy optimization network, and obtain optimal working condition adjustment action reference data by inputting the working condition state parameters obtained by the real-time working condition state parameter collection as the state space;

[0112] The optimal working condition adjustment action reference data includes suction superheat adjustment action, subcooling adjustment action, refrigerant component ratio parameter adjustment action, air volume parameter adjustment action and water flow parameter adjustment action;

[0113] The dynamic adjustment of the refrigerant composition is specifically to construct a refrigerant ratio optimization improvement sub-block. When the ambient temperature is lower than -10 degrees Celsius, the refrigerant composition is dynamically adjusted according to the improved adjustment equation, and the optimal operating condition adjustment action reference data is used to assist in the comprehensive adjustment of the heat pump operating condition to obtain the dynamic adjustment data of the refrigerant composition ratio parameters;

[0114] The calculation formula of the improved adjustment equation is:

[0115] ;

[0116] Where, It is the dynamic adjustment data of the refrigerant component ratio parameters. is the refrigerant component ratio parameter adjustment action parameter in the optimal working condition adjustment action reference data, r 290 is the volume ratio of propane, a low-temperature heating refrigerant, in the heat pump;

[0117] The heat pump operating condition optimization is specifically to perform comprehensive optimization of the heat pump operating condition through the heat pump digital modeling, the multi-objective optimization target construction, the dynamic optimization framework construction and real-time operating condition decision adjustment, combined with the dynamic adjustment of the refrigerant components, to obtain multi-objective optimal operating condition reference data;

[0118] The multi-objective optimal operating condition reference data specifically includes optimal heat pump performance index parameters, optimal life depreciation rate parameters, optimal noise interference parameters, optimal electricity expenditure parameters and optimal refrigerant component dynamic optimization parameters.

[0119] By performing the above operations, in the existing heat pump operating condition optimization process, there is a problem that the heat pump involves many parameters and changes under complex actual operating conditions. The traditional optimization method has poor optimization effect when facing multiple objectives (such as efficiency, life, noise), which often leads to the technical problem of being unable to balance the contradictions between different objectives. This solution creatively adopts a multi-objective dynamic optimization algorithm combined with heat pump digital modeling to optimize the heat pump operating conditions, realizing comprehensive consideration of multiple objectives such as system performance, life, noise, etc. Through heat pump digital modeling, it accurately simulates the influence of various parameters on the heat pump performance.

[0120] Example 4: This example is based on the above example. Figure 1 、 Figure 4 The multi-heat source dynamic switching is used for heat source selection optimization, specifically adopting a multi-heat source game decision algorithm combined with a dual-path improvement evaluation of heat pump system components to perform multi-heat source dynamic switching and obtain heat source decision reference instruction data, including the following steps: heat source entropy efficiency evaluation, equipment evaluation, heat source benefit matrix construction, game decision solution and multi-heat source dynamic switching;

[0121] The heat source entropy efficiency assessment is specifically to perform a thermodynamic grade assessment on each available heat source of the heat pump through heat source entropy efficiency calculation to obtain heat source entropy efficiency assessment data;

[0122] The equipment evaluation is specifically to perform an equipment health evaluation on the heat pump system components based on the optimal life depreciation rate parameter in the multi-objective optimal operating condition reference data and the load rate parameter in the compressor displacement control optimization reference data, for the life depreciation rate of the heat pump corresponding to each available heat source, to obtain an equipment health index parameter, and to obtain an equipment energy consumption index parameter by calculating the unit heating source energy consumption cost;

[0123] The equipment health index parameter is calculated using the following formula:

[0124] ;

[0125] Where H i is the equipment health index parameter, W1 is the life loss rate weight, D life is the heat pump life depreciation rate parameter, W2 is the compressor load rate weight, is the current compressor load factor parameter;

[0126] Preferably, the specific value of the life loss rate weight W1 is 0.6, and the specific value of the compressor load rate weight W2 is 0.4;

[0127] The calculation formula for the unit heating source energy consumption cost is:

[0128] ;

[0129] Where C i is the equipment energy consumption index parameter, i is the equipment index of the heat pump system, W input,i is the total power consumed by the heat source, p(t) is the electricity price calculation function, Q output,i is the output caloric value;

[0130] The heat source benefit matrix is ​​constructed by constructing a comprehensive heat source benefit matrix, calculating the heat source instant score value, and obtaining the heat source instant score reference data;

[0131] The calculation formula of the heat source benefit comprehensive matrix is:

[0132] ;

[0133] Where, It is the reference data of heat source instant score. is the heat source entropy efficiency evaluation weight, is the heat source entropy efficiency evaluation data, is the equipment health index parameter weight, H i is the device health index parameter, is the equipment energy consumption index parameter weight, C i is the equipment energy consumption index parameter;

[0134] Preferably, the heat source entropy efficiency evaluation weight The specific value of is 0.4, and the equipment health index parameter weight H i The specific value is 0.4, and the equipment energy consumption index parameter weight The specific value of is 0.2;

[0135] The game decision solution specifically adopts a standard Nash equilibrium game decision algorithm to maximize the comprehensive heat source instant score benefit calculation based on the heat source instant score reference data and the heat source benefit comprehensive matrix to obtain the optimal heat source switching decision reference data;

[0136] The dynamic switching of multiple heat sources is specifically performed by constructing a non-perceptual transition heat source switching method, dynamically switching the heat pump heat source according to the optimal heat source switching decision reference data, and obtaining heat source decision reference instruction data;

[0137] The heat source decision reference instruction data specifically refers to the control instruction for executing heat pump switching;

[0138] Preferably, the imperceptible transition heat source switching method realizes seamless switching of flow within 3 seconds by controlling the magnetic levitation three-way valve, and avoids excessive pressure fluctuations by dynamically synchronizing the working conditions of the heat pump compressor. Pressure difference detection is performed during the heat source switching process. If the pressure difference change exceeds 5% during the switching process, the refrigerant circulation flow rate is automatically reduced for buffering.

[0139] By performing the above operations, in order to address the technical problem that in the existing multi-heat source intelligent switching process, the traditional heat source switching process is often accompanied by large pressure fluctuations, which may have adverse effects on the system, such as causing system instability, frequent shutdowns or increased equipment wear, thereby affecting the operating efficiency and reliability of the entire heat pump system, this solution creatively adopts a multi-heat source game decision algorithm combined with a dual-path improvement evaluation of the health and energy consumption of heat pump system components to perform dynamic switching of multiple heat sources, thereby realizing a more efficient heat source selection and switching mechanism. Combined with the entropy efficiency of the heat source, the equipment health index and the energy consumption cost, it can intelligently select the optimal heat source under different operating conditions and realize seamless switching, thereby improving the overall working efficiency of the heat pump and reducing the risk of pressure fluctuations and system instability caused by heat source switching.

[0140] Example 5: This example is based on the above example. Figure 1The heat pump intelligent power saving is used to perform comprehensive heat pump intelligent power saving management based on the results of compression control, operating condition optimization and heat source switching. Specifically, it receives the compressor displacement control optimization reference data, dynamically matches the compressor displacement and operating frequency, and performs adaptive optimization of the compressor load. It receives the multi-objective optimal operating condition reference data, adjusts the heat pump operating parameters in real time, and receives the heat source decision reference instruction data, intelligently selects the optimal heat source and realizes seamless switching, and obtains comprehensive reference data on power saving efficiency.

[0141] It should be noted that, in this document, relational terms such as first and second, etc., are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the terms "include," "comprise," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process or method comprising a set of elements includes not only those elements, but also other elements not explicitly listed, or elements inherent to such process or method.

[0142] While the embodiments of the present invention have been shown and described, it will be apparent to those skilled in the art that various changes, modifications, substitutions, and alterations can be made to the embodiments without departing from the principles and spirit of the invention.

[0143] The present invention and its embodiments are described above. This description is not restrictive. The drawings show only one embodiment of the present invention, and the actual structure is not limited thereto. In short, if a person skilled in the art is inspired by this and, without departing from the purpose of the present invention, designs structures and embodiments similar to this technical solution without inventiveness, they shall fall within the scope of protection of the present invention.

Claims

1. An intelligent control system for heat pump heating and power saving, characterized by: It includes heat pump body control optimization module, heat pump core regulation optimization module, heat source dynamic switching module and heating intelligent power saving module; The heat pump body control optimization module adopts a dual-mode slide valve variable capacity compression control method to perform variable capacity compression control, and dynamically adjusts the slide valve displacement by calculating the internal volume ratio in real time to obtain compressor displacement control optimization reference data, and sends the compressor displacement control optimization reference data to the heating intelligent power saving module; The heat pump core regulation optimization module uses a multi-objective dynamic optimization algorithm combined with heat pump digital modeling to optimize the heat pump operating conditions, obtain multi-objective optimal operating condition reference data, and send the multi-objective optimal operating condition reference data to the heating intelligent power saving module; The heat source dynamic switching module adopts a multi-heat source game decision algorithm combined with a dual-path improvement evaluation of the healthy energy consumption of heat pump system components to perform dynamic switching of multiple heat sources, obtain heat source decision reference instruction data, and send the heat source decision reference instruction data to the heating intelligent power saving module; The heating intelligent power-saving module is used for intelligent power saving of heat pumps, and obtains comprehensive reference data of power-saving efficiency through intelligent power saving of heat pumps.

2. The intelligent control system for heat pump heating and electricity saving according to claim 1, characterized in that: The variable capacity compression control is used to optimize the efficiency of the compressor under load. Specifically, a dual-mode slide valve variable capacity compression control method is used to perform variable capacity compression control, and the slide valve displacement is dynamically adjusted by real-time calculation of the internal volume ratio to obtain reference data for compressor displacement control optimization. The method includes the following steps: heat pump operating parameter collection, dynamic improvement calculation of the target internal volume ratio, slide valve displacement target calculation, dual-mode compression control, variable capacity and frequency coordinated improvement, and variable capacity compression control.

3. The intelligent control system for heat pump heating and electricity saving according to claim 2 is characterized by: The heat pump operating parameter collection is specifically performed at a sampling period of once per second, and the raw data noise is processed by low-pass filtering to obtain optimized heat pump operating parameter data; The optimized heat pump operating parameter data includes evaporation pressure parameters, condensation pressure parameters, ambient temperature parameters, slide valve displacement parameters and operating frequency parameters; The target volume ratio dynamic improvement calculation is specifically to dynamically calculate the optimal volume ratio of the compressor based on the optimized heat pump operating parameter data to obtain dynamic reference data of the volume ratio; The target spool valve displacement calculation is specifically performed by numerically inversely calculating the required spool valve displacement based on the dynamic reference data of the internal volume ratio, and calculating the target spool valve displacement by constructing a relationship model between the spool valve displacement and the internal volume ratio to obtain the target spool valve displacement reference data; The dual-mode compression control is specifically performed by constructing a load dual-mode control judgment equation to perform dual-mode compression control, and by constructing a high-load mode and a low-load mode to perform compression control to obtain compression control logic reference data; The high load mode specifically refers to an operating mode in which the current compressor load is greater than 60% of the rated load, the slide valve displacement control capacity is set to 70% to 100%, and the dual rotor parallel operation is started; The low-load mode specifically refers to an operating mode in which the current compressor load is less than or equal to 60% of the rated load, the slide valve displacement control capacity is set to 30% to 70%, and single rotor operation is started; The calculation formula of the load dual-mode control judgment equation is: ； Where, is the current compressor load factor parameter, Q load is the current load parameter of the compressor, which is predicted and calculated by the standard long short-term memory neural network. rated It is the rated heating capacity of the compressor; The variable capacity and frequency conversion coordinated improvement is specifically to perform variable capacity and frequency conversion coordinated slide valve adjustment improvement based on the target slide valve displacement reference data by synchronously fine-tuning the motor frequency to obtain the target motor frequency parameter; The variable capacity compression control specifically detects and controls compressor outlet temperature and pressure fluctuations based on the target motor frequency parameter, the compression control logic reference data, and the content volume ratio dynamic reference data, and avoids compressor instability through fault protection rules to obtain compressor displacement control optimization reference data; The compressor displacement control optimization reference data specifically includes a target internal volume ratio, a target slide valve displacement, a load rate parameter, a target motor frequency parameter, and a fault protection rule execution parameter.

4. The intelligent control system for heat pump heating and electricity saving according to claim 3 is characterized by: The heat pump operating condition optimization is used to dynamically match the optimal heat pump operating parameters. Specifically, a multi-objective dynamic optimization algorithm combined with heat pump digital modeling is used to optimize the heat pump operating conditions and obtain multi-objective optimal operating condition reference data. The method includes the following steps: heat pump digital modeling, multi-objective optimization target construction, dynamic optimization framework construction, real-time operating condition decision adjustment, dynamic adjustment of refrigerant components and heat pump operating condition optimization.

5. The intelligent control system for heat pump heating and electricity saving according to claim 4 is characterized in that: The heat pump digital modeling specifically includes defining the input and output spaces of the heat pump digital model required for the heat pump operating condition optimization, and performing heat pump digital modeling by calculating the relationship between heat pump performance indicators to obtain a heat pump digital basic model; The multi-objective optimization target construction is specifically to obtain a multi-objective optimization function of the heat pump operating condition by constructing a four-dimensional optimization objective function, and to perform preliminary optimization of the heat pump operating condition and calculate preliminary optimized operating parameters of the heat pump based on the multi-objective optimization function of the heat pump operating condition, wherein the four-dimensional optimization objective function includes a function for maximizing a heat pump performance index, a function for minimizing a heat pump life depreciation rate parameter function, a function for minimizing a system noise interference parameter function, and a function for minimizing an electricity cost expenditure; The dynamic optimization framework is constructed by combining the multi-objective optimization function of the heat pump operating condition with a standard reinforcement learning method combined with a multi-objective proximal strategy optimization algorithm, and constructing a dynamic optimization framework for the heat pump operating condition based on the digital basic model of the heat pump to obtain a digital simulation reinforcement learning training framework for the heat pump. Based on the digital simulation reinforcement learning training framework for the heat pump, reinforcement learning dynamic optimization is performed to obtain dynamic optimization operating parameter data of the heat pump; The heat pump digital simulation reinforcement learning training framework includes a state space, an action space, and a four-dimensional reward function; The four-dimensional reward function is specifically defined by weighting according to the multi-objective optimization function of the heat pump operating condition; The real-time working condition decision adjustment is specifically to collect real-time working condition state parameters, call the heat pump digital simulation reinforcement learning training framework to perform reinforcement learning training, obtain a working condition strategy optimization network, and obtain optimal working condition adjustment action reference data by inputting the working condition state parameters obtained by the real-time working condition state parameter collection as the state space; The dynamic adjustment of the refrigerant composition is specifically to construct a refrigerant ratio optimization improvement sub-block. When the ambient temperature is lower than -10 degrees Celsius, the refrigerant composition is dynamically adjusted according to the improved adjustment equation, and the optimal operating condition adjustment action reference data is used to assist in the comprehensive adjustment of the heat pump operating condition to obtain the dynamic adjustment data of the refrigerant composition ratio parameters; The calculation formula of the improved adjustment equation is: ； Where, It is the dynamic adjustment data of the refrigerant component ratio parameters. is the refrigerant component ratio parameter adjustment action parameter in the optimal working condition adjustment action reference data, r 290 is the volume ratio of propane, a low-temperature heating refrigerant, in the heat pump; The heat pump operating condition optimization is specifically to perform comprehensive optimization of the heat pump operating condition through the heat pump digital modeling, the multi-objective optimization target construction, the dynamic optimization framework construction and real-time operating condition decision adjustment, combined with the dynamic adjustment of the refrigerant components, to obtain multi-objective optimal operating condition reference data; The multi-objective optimal operating condition reference data specifically includes optimal heat pump performance index parameters, optimal life depreciation rate parameters, optimal noise interference parameters, optimal electricity expenditure parameters and optimal refrigerant component dynamic optimization parameters.

6. The intelligent control system for heat pump heating and electricity saving according to claim 5, characterized in that: The dynamic switching of multiple heat sources is used for heat source selection optimization. Specifically, a multi-heat source game decision algorithm combined with a dual-path improvement evaluation of the healthy energy consumption of heat pump system components is used to perform dynamic switching of multiple heat sources and obtain heat source decision reference instruction data. The algorithm includes the following steps: heat source entropy efficiency evaluation, equipment evaluation, heat source benefit matrix construction, game decision solution and dynamic switching of multiple heat sources.

7. The intelligent control system for heat pump heating and electricity saving according to claim 6, characterized in that: The heat source entropy efficiency evaluation is specifically to evaluate the thermodynamic quality of each available heat source of the heat pump through heat source entropy efficiency calculation to obtain heat source entropy efficiency evaluation data; The equipment evaluation is specifically to perform an equipment health evaluation on the heat pump system components based on the optimal life depreciation rate parameter in the multi-objective optimal operating condition reference data and the load rate parameter in the compressor displacement control optimization reference data, for the life depreciation rate of the heat pump corresponding to each available heat source, to obtain an equipment health index parameter, and to obtain an equipment energy consumption index parameter by calculating the unit heating source energy consumption cost; The heat source benefit matrix is ​​constructed by constructing a comprehensive heat source benefit matrix, calculating the heat source instant score value, and obtaining the heat source instant score reference data; The game decision solution specifically adopts a standard Nash equilibrium game decision algorithm to maximize the comprehensive heat source instant score benefit calculation based on the heat source instant score reference data and the heat source benefit comprehensive matrix to obtain the optimal heat source switching decision reference data; The dynamic switching of multiple heat sources is specifically performed by constructing a non-perceptible transition heat source switching method, dynamically switching the heat pump heat source according to the optimal heat source switching decision reference data, and obtaining heat source decision reference instruction data.

8. The intelligent control system for heat pump heating and electricity saving according to claim 7, characterized in that: The heat pump intelligent power saving is used to perform comprehensive heat pump intelligent power saving management based on the results of comprehensive compression control, operating condition optimization and heat source switching. Specifically, it receives the compressor displacement control optimization reference data, dynamically matches the compressor displacement and operating frequency, and performs adaptive optimization of the compressor load. It also receives the multi-objective optimal operating condition reference data, adjusts the heat pump operating parameters in real time, and receives heat source decision reference instruction data, intelligently selects the optimal heat source and realizes seamless switching, thereby obtaining comprehensive reference data on power saving efficiency.

Images