An air source heat pump integrated system and method based on multi-stage heat exchange

Abstract

The present invention relates to the field of control, and in particular to an integrated air source heat pump system and method based on multi-stage heat exchange. It includes: collecting and integrating environmental and load information data to generate a time series data set; based on the time series data set, making a preliminary forecast of future loads; correcting the load forecast results, and optimizing the load distribution to obtain the preliminary optimal load distribution of the energy conversion equipment; dynamically adjusting the load weight of the energy conversion equipment through feedback optimization to obtain the updated load weight of the energy conversion equipment; based on the updated load weight of the energy conversion equipment, performing energy feedback correction to obtain the total energy consumption of the system; after the energy feedback correction, making a comprehensive judgment on the load distribution. It solves the problem that the prior art lacks accurate allocation and regulation of heat sources and cold sources in different temperature ranges, lacks intelligent optimization means in load distribution, and the recovered waste heat is usually wasted.

Description

Technical Field

[0001] The present invention relates to the field of control, and in particular to an air source heat pump integrated system and method based on multi-stage heat exchange. Background Art

[0002] As global energy shortages and environmental pollution become increasingly serious, energy conservation and emission reduction have become a focus of widespread concern around the world. Building energy consumption accounts for a considerable proportion of global energy consumption, especially in the demand for heating, cooling and domestic hot water. In order to improve energy efficiency and reduce carbon emissions, an integrated system that can solve the above problems is urgently needed.

[0003] The above-mentioned integrated system exists in the prior art, but it has the following technical problems: lack of precise allocation and regulation of heat sources and cold sources in different temperature ranges, lack of intelligent optimization means in load distribution, and inability to dynamically adjust the load distribution of energy conversion equipment at all levels according to the actual efficiency of the energy conversion equipment, further increasing energy consumption; the recovered waste heat is usually wasted and cannot be used for hot water heating or other energy utilization, resulting in low energy utilization of the system. Summary of the invention

[0004] The present invention provides an air source heat pump integrated system and method based on multi-stage heat exchange to solve the problems that the prior art lacks accurate allocation and regulation of heat sources and cold sources in different temperature ranges, lacks intelligent optimization means in load distribution, and cannot dynamically adjust the load distribution of energy conversion equipment at each level according to the actual efficiency of the energy conversion equipment, further increasing energy consumption; and the recovered waste heat is usually wasted and cannot be used for hot water heating or other energy utilization, resulting in low energy utilization of the system.

[0005] The present invention provides an air source heat pump integrated system and method based on multi-stage heat exchange, which specifically includes the following technical solutions:

[0006] An air source heat pump integration method based on multi-stage heat exchange comprises the following steps:

[0007] S1. Collect and integrate environmental and load information data to generate a time series data set; based on the time series data set, make a preliminary forecast of future loads to obtain load forecast results; modify the load forecast results and introduce Multiplier , construct auxiliary functions, and optimize load distribution by deriving the auxiliary functions, so that the load and efficiency of the energy conversion equipment are matched, and the preliminary optimal load distribution of the energy conversion equipment is obtained; the specific optimization formula is as follows:

[0008] ,

[0009] in, It is Energy conversion equipment in The load of the moment; It is Efficiency of energy conversion equipment at the primary level; is the number of stages of energy conversion equipment; It is used to constrain the load distribution of energy conversion equipment. Multiplier; is a revised view of the future moment Load forecasting results:

[0010] S2. Dynamically adjust the load weight of the energy conversion equipment through feedback optimization to obtain an updated load weight of the energy conversion equipment; the specific adjustment formula is as follows:

[0011] ,

[0012] in, It is the updated Load weight of energy conversion equipment; It is the first Load weight of energy conversion equipment; is the learning rate; For auxiliary functions The second derivative of is the load distribution balance factor; It is Load weight of energy conversion equipment; It is Load weight of energy conversion equipment;

[0013] Based on the updated load weight of the energy conversion equipment, energy feedback correction is performed to obtain the total energy consumption of the system; after the energy feedback correction, a comprehensive judgment is made on the load distribution; the formula for energy feedback correction is:

[0014] ,

[0015] in, is the total energy consumption of the system; is the energy recovery amount; is the historical energy consumption smoothing coefficient; is the energy change rate correction factor; It is a differential term, which represents the rate of change of instantaneous energy consumption.

[0016] Preferably, the S1 specifically includes:

[0017] Based on the time series data set, a preliminary forecast of future load is made using a nonlinear autoregressive model.

[0018] Preferably, the S1 specifically includes:

[0019] The specific formula of the nonlinear autoregressive model is:

[0020] ,

[0021] in, It is for the future moment Load forecasting results: for Activation function; yes The outside air temperature at the time; yes The indoor temperature at the moment; yes The user's demand for domestic hot water at all times; yes The outside air humidity at the moment; It is Energy conversion equipment at the time Working status at the time; , , , , is the weight coefficient of the nonlinear autoregressive model.

[0022] Preferably, the S1 specifically includes:

[0023] The load forecasting results are corrected by introducing differential and integral terms. The specific formula is:

[0024] ,

[0025] in, is a revised view of the future moment Load forecasting results: and is the correction factor; the differential term Indicates the instantaneous rate of load change; integral term Used to introduce the cumulative effect of historical loads; is the time-integrated variable.

[0026] Preferably, the S2 specifically includes:

[0027] After energy feedback correction, the working status of the energy conversion equipment is regulated in real time, the load demand of the heating system is calculated, and heat is dynamically allocated among the energy conversion equipment.

[0028] An air source heat pump integrated system based on multi-stage heat exchange includes the following parts:

[0029] Environmental sensor network module, nonlinear load prediction module, load distribution module, control module, feedback optimization module, energy feedback correction module;

[0030] The environmental sensor network module collects the environmental data outside the integrated system and the temperature status inside the building, the user's hot water demand, and the operating status of the energy conversion equipment in real time, and integrates the collected data into a time series data set, which is connected to the nonlinear load prediction module;

[0031] The nonlinear load forecasting module uses a nonlinear autoregressive model to make a preliminary forecast of future loads based on the time series data set, and corrects the load forecast results, and outputs the corrected load forecast results to the load distribution module;

[0032] The load distribution module optimizes the load distribution of each level of energy conversion equipment according to the corrected load forecast result, obtains the preliminary optimal load distribution of each energy conversion equipment, and transmits the preliminary optimal load distribution to the control module;

[0033] The control module executes the preliminary optimal load distribution calculated by the load distribution module, dynamically adjusts the operating status and load ratio of each level of energy conversion equipment, and feeds back the actual operating data of each energy conversion equipment to the feedback optimization module;

[0034] The feedback optimization module receives the operation data of the energy conversion equipment in real time, dynamically adjusts the load weight of the integrated system, and transmits the updated load weight to the energy feedback correction module;

[0035] Energy feedback correction module calculates the total energy consumption of the integrated system.

[0036] The beneficial effects of the technical solution of the present invention are:

[0037] 1. The present invention uses the design of multi-stage energy conversion equipment to perform multi-level heat exchange between heat sources and cold sources of different temperatures in the external environment, ensuring that the load distribution of each stage of energy conversion equipment matches its efficiency; through load prediction, correction and Lagrange multiplier method optimization, the integrated system can dynamically allocate the load of energy conversion equipment at each stage, thereby maximizing the efficiency of each energy conversion equipment. High-efficiency energy conversion equipment bears more load, while inefficient energy conversion equipment bears less load, reducing energy waste.

[0038] 2. During operation, the integrated system can dynamically and adaptively adjust the load weight of the energy conversion equipment by real-time monitoring of external environmental data, indoor temperature and hot water demand, combined with feedback optimization; after each load distribution, the integrated system makes adjustments based on real-time operating data and the actual performance of each energy conversion equipment to cope with changes in environmental conditions, ensuring that energy conversion equipment at all levels is always in the optimal load distribution state, so that the integrated system can adapt to different working conditions, especially in an environment with extreme temperature changes, and can still maintain efficient operation.

[0039] 3. The integrated system is designed with multi-mode operation, which can intelligently switch the supply mode according to seasonal changes and user needs; the integrated system can not only automatically adjust the load of energy conversion equipment at all levels according to changes in ambient temperature, but also heat domestic hot water through waste heat recovery technology in cooling mode, realizing the coordinated work of cooling and hot water supply. This flexible multi-mode switching design enables the integrated system to operate effectively in different seasons and environments, improving the versatility and practicality of the integrated system.

[0040] 4. By introducing the energy feedback correction module, the total energy consumption of the system can be calculated in real time and the energy balance correction can be performed; through the energy feedback correction formula, the changing trends of historical energy consumption and instantaneous energy consumption are comprehensively considered, and the energy consumption of the system is further reduced through energy recovery; through the adjustment of integral and differential terms, the stable utilization of energy can be maintained in both the long and short term, ensuring that the energy consumption of the integrated system is always in the optimal state during operation, reducing energy waste and improving the overall energy efficiency of the integrated system. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] Figure 1 This is a structural diagram of an air source heat pump integrated system based on multi-stage heat exchange according to the present invention;

[0042] Figure 2 This is a flow chart of an air source heat pump integration method based on multi-stage heat exchange described in the present invention. DETAILED DESCRIPTION

[0043] In order to further explain the technical means and effects adopted by the present invention to achieve the predetermined invention purpose, the technical scheme in the embodiment of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiment of the present invention. Obviously, the described embodiment is only a part of the embodiment of the present invention, not all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0044] 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.

[0045] The specific scheme of an integrated system and method provided by the present invention is described in detail below with reference to the accompanying drawings.

[0046] An integrated system includes an environmental sensor network module, a nonlinear load prediction module, a load distribution module, a control module, a feedback optimization module, and an energy feedback correction module;

[0047] The environmental sensor network module collects the environmental data outside the integrated system and the temperature status inside the building, the user's hot water demand, and the operating status of the energy conversion equipment in real time, and integrates the collected data into a time series data set through the data acquisition interface, which is connected to the nonlinear load prediction module;

[0048] The nonlinear load forecasting module uses a nonlinear autoregressive model to make a preliminary forecast of future loads based on the time series data set, and corrects the load forecast results, and outputs the corrected load forecast results to the load distribution module;

[0049] The load distribution module optimizes the load distribution of each level of energy conversion equipment according to the corrected load forecast result, obtains the preliminary optimal load distribution of each energy conversion equipment, and transmits the preliminary optimal load distribution to the control module;

[0050] The control module executes the preliminary optimal load distribution calculated by the load distribution module, dynamically adjusts the operating status and load ratio of each level of energy conversion equipment, and feeds back the actual operating data of each energy conversion equipment to the feedback optimization module;

[0051] The feedback optimization module receives the operation data of the energy conversion equipment in real time, dynamically adjusts the load weight of the integrated system, and transmits the updated load weight to the energy feedback correction module;

[0052] The energy feedback correction module calculates the total energy consumption of the integrated system to ensure that the energy utilization efficiency of the integrated system is optimal.

[0053] An integration method comprises the following steps:

[0054] S1. Collect and integrate environmental and load information data to generate a time series data set; based on the time series data set, make a preliminary forecast of future loads to obtain load forecast results; modify the load forecast results, and optimize the load distribution based on the load weight of the energy conversion equipment to match the load and efficiency of the energy conversion equipment, and obtain the preliminary optimal load distribution of the energy conversion equipment;

[0055] The integrated system collects key environmental and load information data in real time through the environmental sensor network module, which includes devices for detecting external air temperature, humidity, indoor temperature, current hot water demand, and the working status of various levels of energy conversion equipment. The environmental sensor network integrates the collected data into a time series data set through the data acquisition interface ,The collected data is the initial input of the integrated system, covering the current ,external environmental conditions, the temperature status inside the building, the user’s ,hot water demand, and the operating status of the energy conversion equipment.

[0056] The time series data set is sent to the nonlinear load forecasting module, and a preliminary forecast of future load is made through the nonlinear autoregressive model. The specific formula is:

[0057] ,

[0058] in, It is for the future moment Load forecasting results: for Activation function; yes The outside air temperature at the time; yes The indoor temperature at the moment; yes The user's demand for domestic hot water at all times; yes The outside air humidity at the moment; It is Energy conversion equipment at the time The working status at that time indicates the current load or power of the energy conversion device; , , , , It is the weight coefficient of the nonlinear autoregressive model, which is used to balance the influence of external temperature, indoor temperature, hot water demand, external air humidity and the working status of energy conversion equipment on the prediction results.

[0059] Due to the dynamic changes in the external environment and equipment status, the forecast results may be biased, so further feedback correction is required. The correction process dynamically adjusts the load forecast by introducing differential and integral terms. The specific formula is:

[0060] ,

[0061] in, is a revised view of the future moment Load forecasting results: and are correction coefficients, which respectively control the response of the prediction results to the current load change rate and the historical cumulative load. Indicates the instantaneous rate of load change; integral term It is used to introduce the cumulative effect of historical loads; is the time-integrated variable.

[0062] After obtaining the corrected load forecast results, the load distribution is optimized to ensure that the load of each energy conversion device matches its efficiency, ultimately maximizing the energy efficiency of the integrated system. The load distribution of energy conversion equipment is performed using the following optimization formula:

[0063] ,

[0064] in, It is Energy conversion equipment in The load of the moment; It is Efficiency of energy conversion equipment at the primary level; is the number of stages of energy conversion equipment; It is used to constrain the load distribution of energy conversion equipment. Multiplier; is a revised view of the future moment The goal of the optimization formula is to make the load of each energy conversion device With its efficiency Proportionally, this ensures that efficient energy conversion equipment takes on more of the load, thereby optimizing the overall energy efficiency of the integrated system.

[0065] In order to solve this load dispatch optimization problem, we first need to apply Multiplier method. Specifically, the optimization objective function consists of two parts: the first part It is to optimize the energy efficiency of each energy conversion device. The goal is to make the load of each energy conversion device and its efficiency Proportional; Part II It is used to constrain the moment The total load and the revised load forecast results To optimize both parts at the same time, use Multiplier Constructor Helper Function :

[0066] ,

[0067] Through Derivation, get The optimal solution of .

[0068] No. Load of energy conversion equipment The load weight Multiply by the total system load Determined, that is:

[0069] ,

[0070] Will optimize the auxiliary function Rewritten as:

[0071] ,

[0072] calculate Optimize auxiliary functions for load weight The first-order partial derivative of and set it to 0:

[0073] ,

[0074] The partial derivative represents the sensitivity of system energy consumption to load weight.

[0075] Use load balance constraint solution, the load balance constraint conditions are:

[0076] ,

[0077] Substitute the load balance condition into the partial derivative of the optimization auxiliary function:

[0078] ,

[0079] Therefore, the optimization of load is distributed around the efficiency of energy conversion equipment at each level, and the load weight of each energy conversion equipment should be proportional to its efficiency.

[0080] By deducing, the relationship between load weight and efficiency is obtained, and the optimal load distribution of each energy conversion device is solved. Load of energy conversion equipment With total load The specific load distribution formula is:

[0081] ,

[0082] The results show that the load of each energy conversion device The total system load According to the efficiency of each energy conversion device By weighted allocation, energy conversion equipment with higher efficiency will bear more load.

[0083] S2. Dynamically adjust the load weight of the energy conversion equipment through feedback optimization to obtain an updated load weight of the energy conversion equipment; perform energy feedback correction based on the updated load weight of the energy conversion equipment to obtain the total energy consumption of the system; after the energy feedback correction, make a comprehensive judgment on the load distribution.

[0084] Although the initial optimal load distribution of each energy conversion device is obtained, the initial load weight may show a non-optimal state in the subsequent working conditions due to the continuous change of working conditions in actual operation. Therefore, it is necessary to further dynamically adjust the load distribution weight to adapt to the changing working conditions.

[0085] According to the real-time operation data and the actual performance of each energy conversion equipment, the load weights initially allocated are adjusted. It indicates the proportion of the total load borne by each energy conversion device, which directly affects the power consumption calculation and energy feedback of subsequent energy conversion devices. The specific load weight feedback optimization formula is:

[0086] ,

[0087] in, It is the updated Load weight of energy conversion equipment; It is the first Load weight of energy conversion equipment; is the learning rate, which controls the step size of the update; For auxiliary functions The second derivative of reflects the acceleration of load weight update; This item is used to prevent the load weight of a certain energy conversion device from being too high or too low, ensuring the balance of the load distribution of the integrated system. is the load distribution balance coefficient, It is By continuously adjusting the weights, the integrated system can adaptively adjust the loads of energy conversion equipment at each level according to real-time operating data, so that the integrated system is always in the best working state.

[0088] After feedback optimization, the integrated system will pass the final updated load weight to the energy feedback correction module to accurately calculate the total energy consumption of the system and correct the energy balance, ensuring that the integrated system takes energy recovery into account in actual operation, further reducing energy consumption and optimizing the performance of the integrated system. The formula for energy feedback correction is:

[0089] ,

[0090] in, is the total energy consumption of the system; is the energy recovery amount; is the historical energy consumption smoothing coefficient; Is the energy change rate correction factor. Integral term and the differential term The cumulative effect of historical energy consumption and the rate of change of instantaneous energy consumption are considered separately to ensure that the energy balance of the integrated system can be accurately corrected in the long and short term. Through energy feedback correction, the integrated system can further optimize the actual energy consumption and maximize the energy efficiency of the integrated system.

[0091] After energy feedback correction, the integrated system needs to make a comprehensive judgment on the load distribution and perform secondary optimization based on the current energy consumption and energy demand.

[0092] As a specific embodiment, the above integrated system is applied to an air source heat pump integrated system based on multi-stage heat exchange; Figure 1 , which shows a structural diagram of an air source heat pump integrated system based on multi-stage heat exchange provided by an embodiment of the present invention, the system includes the following parts:

[0093] Environmental sensor network module, nonlinear load prediction module, load distribution module, control module, feedback optimization module, energy feedback correction module;

[0094] The environmental sensor network module collects the external environmental data of the air source heat pump integrated system, the temperature status inside the building, the user's hot water demand, and the operating status of the heat exchanger in real time, and integrates the collected data into a time series data set through the data acquisition interface, which is connected to the nonlinear load prediction module;

[0095] The nonlinear load forecasting module uses a nonlinear autoregressive model to make a preliminary forecast of future loads based on the time series data set, and corrects the load forecast results, and outputs the corrected load forecast results to the load distribution module;

[0096] The load distribution module optimizes the load distribution of each level of heat exchangers according to the corrected load prediction results, obtains the preliminary optimal load distribution of each heat exchanger, and transmits the preliminary optimal load distribution to the control module;

[0097] The control module executes the preliminary optimal load distribution calculated by the heat exchanger load distribution module, dynamically adjusts the operating status and load ratio of each level of heat exchangers, and feeds back the actual operating data of each heat exchanger to the feedback optimization module;

[0098] The feedback optimization module receives the operating data of the heat exchanger in real time, dynamically adjusts the load weight of the air source heat pump integrated system, and transmits the updated load weight to the energy feedback correction module;

[0099] The energy feedback correction module calculates the total energy consumption of the air source heat pump integrated system to ensure that the energy utilization efficiency of the air source heat pump integrated system is optimized.

[0100] As a specific embodiment, the above integration method is applied to an air source heat pump integration method based on multi-stage heat exchange; Figure 2 , which shows a flow chart of an air source heat pump integration method based on multi-stage heat exchange provided by an embodiment of the present invention, the method comprising the following steps:

[0101] S1. Collect and integrate environmental and load information data to generate a time series data set; based on the time series data set, make a preliminary forecast of future loads to obtain load forecast results; modify the load forecast results, and optimize the load distribution based on the load weight of the heat exchanger to match the load and efficiency of the heat exchanger, and obtain the preliminary optimal load distribution of the heat exchanger;

[0102] The air source heat pump integrated system collects key environmental and load information data in real time through the environmental sensor network module. The sensors include devices for detecting external air temperature, humidity, indoor temperature, current hot water demand, and the working status of each level of heat exchanger. The environmental sensor network integrates the collected data into a time series data set through the data acquisition interface ,The collected data is the initial input of the air source heat pump ,integrated system, covering the current external environmental conditions, the temperature status inside the building, the user’s ,hot water demand, and the operating status of the heat exchanger.

[0103] The time series data set is sent to the nonlinear load forecasting module, and a preliminary forecast of future load is made through the nonlinear autoregressive model. The specific formula is:

[0104] ,

[0105] in, It is for the future moment Load forecasting results: for Activation function; yes The outside air temperature at the time; yes The indoor temperature at the moment; yes The user's demand for domestic hot water at all times; yes The outside air humidity at the moment; It is Stage heat exchanger at time The working status at the time indicates the current load or power of the heat exchanger; , , , , is the weight coefficient of the nonlinear autoregressive model, which is used to balance the impact of external temperature, indoor temperature, hot water demand, external air humidity and heat exchanger working status on the prediction results.

[0106] Due to the dynamic changes in the external environment and equipment status, the forecast results may be biased, so further feedback correction is required. The correction process dynamically adjusts the load forecast by introducing differential and integral terms. The specific formula is:

[0107] ,

[0108] in, is a revised view of the future moment Load forecasting results: and are correction coefficients, which respectively control the response of the prediction results to the current load change rate and the historical cumulative load. Indicates the instantaneous rate of load change, ensuring that the prediction results can be adjusted in real time with the dynamic changes of the load; integral term It is used to introduce the cumulative effect of historical load to smooth out short-term fluctuations; is the time-integrated variable.

[0109] After obtaining the corrected load forecast results, the load distribution is optimized to ensure that the load of each heat exchanger matches its efficiency, ultimately maximizing the energy efficiency of the air source heat pump integrated system. The load distribution of the heat exchanger is performed using the following optimization formula:

[0110] ,

[0111] in, It is Heat exchanger in The load of the moment; It is The efficiency of the heat exchanger indicates the ability of the heat exchanger to convert input heat or cold into effective energy; is the number of heat exchanger stages; It is used to constrain the load distribution of the heat exchanger. Multiplier; is a revised view of the future moment The goal of the optimization formula is to make the load of each heat exchanger With its efficiency Proportionally, this ensures that the more efficient heat exchanger takes on more of the load, thus optimizing the overall energy efficiency of the system.

[0112] In order to solve this load dispatch optimization problem, we first need to apply Multiplier method. Specifically, the optimization objective function consists of two parts: the first part It is to optimize the energy efficiency of each heat exchanger. The goal is to make the load of each heat exchanger and its efficiency Proportional; Part II It is used to constrain the moment The total load and the revised load forecast results To optimize both parts simultaneously, the Lagrange multiplier is used. Constructor Helper Function :

[0113] ,

[0114] Through Derivation, get The optimal solution of .

[0115] No. Heat exchanger load The load weight Multiply by the total system load Determined, that is:

[0116] ,

[0117] Will optimize the auxiliary function Rewritten as:

[0118] ,

[0119] calculate Optimize auxiliary functions for load weight The first-order partial derivative of and set it to 0:

[0120] ,

[0121] The partial derivative represents the sensitivity of system energy consumption to load weight.

[0122] Use load balance constraint solution, the load balance constraint conditions are:

[0123] ,

[0124] Substitute the load balance condition into the partial derivative of the optimization auxiliary function:

[0125] ,

[0126] Therefore, the optimization of load is distributed around the efficiency of each stage of heat exchanger, and the load weight of each heat exchanger should be proportional to its efficiency.

[0127] By deducing, the relationship between load weight and efficiency is obtained, and the optimal load distribution of each heat exchanger is solved. Heat exchanger load With total load The specific load distribution formula is:

[0128] ,

[0129] The results show that the load of each heat exchanger The total system load According to the efficiency of each heat exchanger A weighted distribution is performed, and the heat exchanger with higher efficiency will bear more load.

[0130] S2. Dynamically adjust the load weight of the heat exchanger through feedback optimization to obtain an updated load weight of the heat exchanger; perform energy feedback correction based on the updated load weight of the heat exchanger to obtain the total energy consumption of the system; after the energy feedback correction, make a comprehensive judgment on the load distribution.

[0131] Although the initial optimal load distribution for each heat exchanger is obtained, the operating conditions will continue to change in actual operation, and the initial load weights may show non-optimal status in subsequent operating conditions. Therefore, it is necessary to further dynamically adjust the load distribution weights to adapt to the changing operating conditions.

[0132] According to the real-time operating data and the actual performance of each heat exchanger, the initially allocated load weight is adjusted. It indicates the total load proportion borne by each heat exchanger, which directly affects the power consumption calculation and energy feedback of subsequent heat exchangers. The specific load weight feedback optimization formula is:

[0133] ,

[0134] in, It is the updated Load weight of the heat exchanger; It is the first Load weight of the heat exchanger; is the learning rate, which controls the step size of the update; For auxiliary functions The second-order derivative of reflects the acceleration of load weight update, ensuring a smoother adjustment process; This item is used to prevent the load weight of a heat exchanger from being too high or too low, ensuring the balance of load distribution in the air source heat pump integrated system. is the load distribution balance coefficient, It is By continuously adjusting the weights, the air source heat pump integrated system can adaptively adjust the loads of each level of heat exchangers according to real-time operating data, so that the air source heat pump integrated system is always in the best working state.

[0135] After feedback optimization, the air source heat pump integrated system will pass the final updated load weight to the energy feedback correction module to accurately calculate the total energy consumption of the system and correct the energy balance, ensuring that the air source heat pump integrated system takes energy recovery into account in actual operation, further reducing energy consumption and optimizing the performance of the air source heat pump integrated system. The formula for energy feedback correction is:

[0136] ,

[0137] in, is the total energy consumption of the system; is the energy recovery amount, which represents the energy saved by the air source heat pump integrated system through waste heat recovery during the heat exchange process; is the historical energy consumption smoothing coefficient; It is the energy change rate correction factor, which is used to respond to the instantaneous change of energy consumption of the air source heat pump integrated system. and the differential term The cumulative effect of historical energy consumption and the rate of change of instantaneous energy consumption are considered separately to ensure that the energy balance of the air source heat pump integrated system can be accurately corrected in the long and short term. Through energy feedback correction, the air source heat pump integrated system can further optimize the actual energy consumption and maximize the energy efficiency of the air source heat pump integrated system.

[0138] After the energy feedback correction, the air source heat pump integrated system needs to make a comprehensive judgment on the load distribution. At this time, the heating, cooling and hot water demands of the air source heat pump may change dynamically, rather than simply completing the operation through simple load optimization and energy correction. For example, in summer cooling, the air source heat pump integrated system can use the waste heat generated by the condenser to provide users with domestic hot water, while in winter heating mode, the heat demand of the air source heat pump integrated system is higher than the cooling demand. The air source heat pump integrated system will give priority to the heating function and dynamically allocate the heat exchanger load according to the actual hot water demand. Therefore, after the load distribution, the air source heat pump integrated system needs to be optimized twice according to the current energy consumption and heating demand.

[0139] Specifically, the working status of the heat exchanger needs to be regulated in real time to maximize the use of heat in the air in heating mode. By real-time monitoring of factors such as ambient temperature changes, indoor temperature changes, and humidity, the load demand of the heating system can be calculated, and heat can be dynamically allocated between heat exchangers to ensure that indoor heating remains stable.

[0140] The air source heat pump integrated system dynamically adjusts the load distribution ratio of the high-temperature heat exchanger and the low-temperature heat exchanger according to the changes in the actual outdoor temperature, ensuring that when the outside temperature drops sharply, the air source heat pump integrated system can give priority to the use of high-efficiency heat exchangers for heat supply, while the low-temperature heat exchanger reduces energy consumption while ensuring hot water demand.

[0141] In summary, an air source heat pump integrated system and method based on multi-stage heat exchange has been completed.

[0142] The order of the embodiments of the invention is for description only and does not represent the advantages and disadvantages of the embodiments. The processes depicted in the drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0143] The various embodiments in this specification are described in a progressive manner, and the same or similar parts between the various embodiments can be referenced to each other, and each embodiment focuses on the differences from other embodiments.

[0144] The above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the above embodiments, those skilled in the art should understand that the technical solutions described in the above embodiments may still be modified, or some of the technical features may be replaced by equivalents. Such modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention, and should be included in the protection scope of the present invention.

Claims

1. An air source heat pump integration method based on multi-stage heat exchange, characterized in that: The following steps are involved: S1. Collect and integrate environmental and load information data to generate a time series data set; based on the time series data set, make a preliminary forecast of future loads to obtain load forecast results; The load forecast results are corrected and based on the load weight of the energy conversion equipment, the Multiplier , construct auxiliary functions, and optimize load distribution by deriving the auxiliary functions, so that the load and efficiency of the energy conversion equipment are matched, and the preliminary optimal load distribution of the energy conversion equipment is obtained; the specific optimization formula is as follows: ， in, It is Energy conversion equipment in The load of the moment; It is Efficiency of energy conversion equipment; is the number of stages of energy conversion equipment; It is used to constrain the load distribution of energy conversion equipment. Multiplier; is a revised view of the future moment Load forecasting results: S2. Dynamically adjust the load weight of the energy conversion equipment through feedback optimization to obtain an updated load weight of the energy conversion equipment; the specific adjustment formula is as follows: ， in, It is the updated Load weight of energy conversion equipment; It is the first Load weight of energy conversion equipment; is the learning rate; For auxiliary functions The second derivative of is the load distribution balance factor; It is Load weight of energy conversion equipment; It is Load weight of energy conversion equipment; Based on the updated load weight of the energy conversion equipment, energy feedback correction is performed to obtain the total energy consumption of the system; after the energy feedback correction, a comprehensive judgment is made on the load distribution; the formula for energy feedback correction is: ， in, is the total energy consumption of the system; is the energy recovery amount; is the historical energy consumption smoothing coefficient; is the energy change rate correction factor; It is a differential term, which represents the rate of change of instantaneous energy consumption.

2. The air source heat pump integration method based on multi-stage heat exchange according to claim 1, characterized in that: The S1 specifically includes: Based on the time series data set, a preliminary forecast of future load is made using a nonlinear autoregressive model.

3. The air source heat pump integration method based on multi-stage heat exchange according to claim 2 is characterized in that: The S1 specifically includes: The specific formula of the nonlinear autoregressive model is: ， in, It is for the future moment Load forecasting results: for Activation function; yes The outside air temperature at the time; yes The indoor temperature at the moment; yes The user's demand for domestic hot water at all times; yes The outside air humidity at the moment; It is Energy conversion equipment at the time Working status at the time; , , , , is the weight coefficient of the nonlinear autoregressive model.

4. The air source heat pump integration method based on multi-stage heat exchange according to claim 3 is characterized in that: The S1 specifically includes: The load forecasting results are corrected by introducing differential and integral terms. The specific formula is: ， in, is a revised view of the future moment Load forecasting results: and is the correction factor; the differential term Indicates the instantaneous rate of load change; integral term Used to introduce the cumulative effect of historical loads; is the time-integrated variable.

5. The air source heat pump integration method based on multi-stage heat exchange according to claim 1, characterized in that: The S2 specifically includes: After energy feedback correction, the working status of the energy conversion equipment is regulated in real time, the load demand of the heating system is calculated, and heat is dynamically allocated among the energy conversion equipment.

6. An air source heat pump integrated system based on multi-stage heat exchange, applied to the air source heat pump integrated method based on multi-stage heat exchange according to claim 1, characterized in that: Includes the following parts: Environmental sensor network module, nonlinear load prediction module, load distribution module, control module, feedback optimization module, energy feedback correction module; The environmental sensor network module collects the environmental data outside the integrated system and the temperature status inside the building, the user's hot water demand, and the operating status of the energy conversion equipment in real time, and integrates the collected data into a time series data set, which is connected to the nonlinear load prediction module; The nonlinear load forecasting module uses a nonlinear autoregressive model to make a preliminary forecast of future loads based on the time series data set, and corrects the load forecast results, and outputs the corrected load forecast results to the load distribution module; The load distribution module optimizes the load distribution of each level of energy conversion equipment according to the corrected load forecast result, obtains the preliminary optimal load distribution of each energy conversion equipment, and transmits the preliminary optimal load distribution to the control module; The control module executes the preliminary optimal load distribution calculated by the load distribution module, dynamically adjusts the operating status and load ratio of each level of energy conversion equipment, and feeds back the actual operating data of each energy conversion equipment to the feedback optimization module; The feedback optimization module receives the operation data of the energy conversion equipment in real time, dynamically adjusts the load weight of the integrated system, and transmits the updated load weight to the energy feedback correction module; Energy feedback correction module calculates the total energy consumption of the integrated system.

Images