Air source heat pump heating method and system

Abstract

The application provides an air source heat pump heating method and system, and relates to the technical field of heat pump system thermal control, the method comprises the following steps: collecting the frost layer thickness of the evaporator surface, the environmental temperature and the humidity parameters in real time, inputting the parameters into the neural network algorithm model which is trained in advance, identifying the frosting rate by analyzing the nonlinear relationship of multiple factors, predicting the future frosting development trend, and outputting the frost layer thickness growth prediction and the severity result; according to the frost layer thickness growth prediction and the severity result, starting the reverse cycle defrosting in advance when the frost layer does not reach the critical thickness, realizing the optimization control of the defrosting process by adjusting the four-way valve opening degree and the fan rotating speed, and obtaining the system state after defrosting. The application realizes the system energy efficiency improvement and the heating comfort optimization.

Description

Technical Field

[0001] This invention relates to the field of thermal control technology for heat pump systems, and in particular to an air source heat pump heating method and system. Background Technology

[0002] Air source heat pump heating systems have become a core technology solution for winter heating of self-built houses in rural areas of my country's frigid regions due to their advantages of not requiring the combustion of fossil fuels and high operating efficiency. In such scenarios, rural self-built houses generally lack coverage by municipal centralized heating networks, and users are highly sensitive to heating costs and need to consider unattended operation requirements. The decentralized heating characteristics and energy-saving advantages of air source heat pumps can effectively meet these needs.

[0003] However, traditional control technologies have some limitations. Defrosting control based on fixed thresholds is sometimes unable to adapt to dynamically changing temperature and humidity conditions, and is prone to defrosting timing deviations. Parameter adjustment methods relying on mechanistic models are difficult to characterize the complex nonlinear coupling relationship between ambient temperature and humidity, frost rate, heating capacity, and grid voltage in a heat pump system, and cannot achieve precise control. Single-parameter feedback control cannot take into account the interaction of multiple variables, resulting in insufficient control precision. However, when applying neural network algorithms to rural air source heat pump heating scenarios in frigid regions, some challenges still exist. For example, a single neural network model often focuses on solving local problems and fails to form a synergistic optimization overall control framework with other key aspects such as voltage compensation, load matching, and room-by-room control. Summary of the Invention

[0004] The technical problem to be solved by the present invention is to provide an air source heat pump heating method and system to improve system energy efficiency and optimize heating comfort.

[0005] To solve the above-mentioned technical problems, the technical solution of the present invention is as follows:

[0006] In a first aspect, an air-source heat pump heating method, the method comprising:

[0007] Step 1: Real-time acquisition of frost thickness, ambient temperature, and humidity parameters on the evaporator surface, input into a pre-trained neural network algorithm model, analyze multi-factor nonlinear relationships to identify frost rate, predict future frost development trends, and output frost thickness growth prediction and severity results.

[0008] Step 2: Based on the predicted increase in frost thickness and the severity of the frost, reverse circulation defrosting is initiated in advance before the frost layer reaches the critical thickness. The defrosting process is optimized by adjusting the opening of the four-way valve and the fan speed to obtain the system status after defrosting.

[0009] Step 3, based on the system state after defrosting, real-time monitoring of power grid voltage fluctuation, starting voltage compensation before voltage is lower than the normal working range of compressor, and dynamically adjusting the frequency of compressor to maintain stable operation of the system;

[0010] Step 4, according to the stable operation of the system, collecting the ground heating system supply and return water temperature data, combining the historical data and real-time heat load demand, establishing the thermal dynamic response relationship, adjusting the circulating pump speed of buffer water tank and the opening degree of water mixing valve, and obtaining the matching result between heat pump output and heating demand;

[0011] Step 5, based on the matching result of heat pump output and heating demand, obtaining multi-position temperature data through distributed temperature monitoring device, establishing the thermal field characteristic distribution of heating area; generating system control parameters according to the thermodynamic characteristic parameters of each area, formulating regional timing temperature control strategy based on system control parameters, and controlling each heating loop through Internet of Things communication to realize energy efficiency optimization and comfortable heating.

[0012] Further, the thickness of the frost layer on the evaporator surface, the environmental temperature and humidity parameters are collected in real time, input into the pre-trained neural network algorithm model, the frosting rate is identified through analyzing the multi-factor nonlinear relationship, the future frosting development trend is predicted, the frost thickness growth prediction and severity results are output, including:

[0013] Step 1.1, real-time collection of the thickness of the frost layer on the evaporator surface, the environmental temperature and humidity parameters, preprocessing of the collected original data parameters to obtain preprocessed data;

[0014] Step 1.2, according to the preprocessed data, organizing the standardized input vector containing environmental temperature, humidity and frost layer thickness in time sequence, inputting the standardized input vector into a pre-trained neural network model, performing high-dimensional nonlinear mapping and feature extraction on the complex nonlinear interaction between each parameter in the input vector through the internal hidden layer nodes, calculating the hidden state features reflecting the current instantaneous frosting condition, based on the hidden state features, through the linear transformation and activation function processing of the output layer of the neural network model, obtaining the accurate frosting rate under the current working condition;

[0015] Step 1.3, based on the real-time frosting rate, combining the time series data of current environmental temperature and humidity, the neural network model performs multi-step forward deduction calculation in the internal state space, predicts the frost layer thickness increment at each time within the preset time window in the future through iterative method, adds to the current thickness to generate a frost layer thickness growth prediction curve with time as the independent variable, and obtains the grade evaluation result of the frosting severity in the future period.

[0016] Further, according to the frost thickness growth prediction and severity results, the reverse cycle defrosting is started in advance when the frost layer does not reach the critical thickness, and the defrosting process is optimized by adjusting the four-way valve opening and the fan speed to obtain the system state after defrosting, including:

[0017] Step 2.1, based on the prediction and severity results, the frost layer growth trend is judged and the expected time to reach the critical thickness is calculated, and the reverse cycle defrosting start instruction is generated in advance according to the prediction results before the actual thickness of the frost layer reaches the critical thickness;

[0018] Step 2.2, the defrosting start instruction is sent to the air source heat pump unit control system to control the four-way valve to switch the refrigerant flow direction and start the reverse cycle defrosting process;

[0019] Step 2.3, during the defrosting process, the opening change rate of the four-way valve and the speed of the outdoor fan are dynamically adjusted according to the frost severity results to match the defrosting heat demand under different frost degrees, and the optimization control of the defrosting process is realized;

[0020] Step 2.4, the evaporator surface temperature and system pressure parameters are monitored in real time to judge the defrosting completion degree, and when it is confirmed that the evaporator surface frost layer is completely removed and the system parameters return to the normal operation range, the defrosting end instruction is generated to control the four-way valve and the fan to return to the heating operation state, and the system state after defrosting is obtained.

[0021] Further, based on the system state after defrosting, the power grid voltage fluctuation is monitored in real time, the voltage compensation is started before the voltage is lower than the normal working range of the compressor, and the frequency of the compressor is dynamically adjusted to maintain the stable operation of the system, including:

[0022] Step 3.1, based on the system state after defrosting, the power grid voltage monitoring function is activated, the power grid voltage data is collected in real time by the voltage sensor, and the voltage data is filtered and trend analyzed to predict the voltage change trend;

[0023] Step 3.2, the pre-compensation instruction is generated before the power grid voltage is predicted to drop to the minimum voltage threshold required for the normal operation of the compressor;

[0024] Step 3.3, the pre-compensation instruction is sent to the voltage compensation device to control it to run in advance to improve the power supply voltage and ensure that the voltage at the end of the compressor is maintained within the normal working range;

[0025] Step 3.4, while the voltage compensation is being performed, the compressor frequency adjustment instruction is dynamically calculated and generated according to the amplitude and trend of the voltage fluctuation, and the system load and power supply capacity are balanced by fine-tuning the operating frequency of the compressor to maintain the stable operation of the system as a whole.

[0026] Further, according to the stable operation of the system, the supply and return water temperature data of the floor heating system are collected, the historical data and real-time heat load demand are combined, the thermal dynamic response relationship is established, the matching result between the heat pump output and the heating demand is obtained by adjusting the circulating pump speed of the buffer water tank and the opening degree of the water mixing valve, including:

[0027] Step 4.1, based on the maintained stable operation state of the system, starting the floor heating system monitoring sequence, collecting the supply and return water temperature data of the heating system in real time through the temperature sensor;

[0028] Step 4.2, calling the stored historical heating data, the historical data including the supply and return water temperature difference, heat load and system adjustment parameter under different outdoor working conditions, and integrating the historical data with the real-time collected supply and return water temperature data to obtain the integrated data;

[0029] Step 4.3, based on the integrated data, calculating the corresponding relationship between the supply and return water temperature difference and the flow change per unit time, establishing the real-time thermal dynamic response relationship of the system to obtain the analysis result of the thermal dynamic response relationship;

[0030] Step 4.4, comparing the real-time heat load demand with the analysis result of the thermal dynamic response relationship, calculating the target circulating pump speed of the buffer water tank and the target opening degree of the water mixing valve required to achieve the balance between supply and demand, and obtaining the calculation result;

[0031] Step 4.5, generating control instructions according to the calculation result, dynamically adjusting the speed of the circulating pump of the buffer water tank to change the circulating flow of the system, and adjusting the opening degree of the water mixing valve to control the mixed water temperature, so that the heat output of the heat pump is coordinated with the real-time heating demand of the building, and the final matching result is obtained.

[0032] Further, based on the matching result of the heat pump output and the heating demand, the multi-position temperature data are obtained through the distributed temperature monitoring device, and the thermal field characteristic distribution of the heating area is established, including:

[0033] Step 5.1, based on the matching result of the heat pump output and the heating demand, starting the operation of the distributed temperature monitoring network, collecting real-time temperature data through temperature sensors arranged at multiple positions in the heating area;

[0034] Step 5.2, cleaning and formatting the collected multi-position temperature data, eliminating abnormal data points, and associating the temperature data of each monitoring point with its corresponding spatial position information to obtain a standardized temperature distribution data set;

[0035] Step 5.3, based on the obtained standardized temperature distribution data set, dividing the heating area into several independent sub-areas according to the spatial structure, calculating the representative temperature value of each sub-area by using the weighted average algorithm, and generating sub-area temperature distribution data;

[0036] Step 5.4, based on the generated sub-region temperature distribution data, combined with the spatial structure characteristics and thermal characteristic parameters of the building, analyze the spatial correlation and variation law of each sub-region temperature data, and establish the thermal field characteristic distribution of the heating area.

[0037] Further, generate system control parameters according to the thermodynamic characteristic parameters of each region, formulate a regional timing temperature control strategy based on the system control parameters, and control each heating circuit through Internet of Things communication to realize energy efficiency optimization and comfortable heating, including:

[0038] Step 5.5, based on the thermal field characteristic distribution, extract the thermodynamic characteristic parameters of each sub-region, including temperature stability, thermal inertia coefficient and thermal response time constant;

[0039] Step 5.6, according to the extracted thermodynamic characteristic parameters, combined with the use function characteristics and comfort requirements of each sub-region, generate system control parameters for each sub-region;

[0040] Step 5.7, based on the generated system control parameters, combined with historical heating data and use habits, formulate a regional timing temperature control strategy;

[0041] Step 5.8, the formulated regional timing temperature control strategy is issued to the intelligent control equipment of each heating circuit through Internet of Things communication, realizing independent and accurate control of each heating circuit;

[0042] Step 5.9, real-time monitoring of temperature change and energy consumption data of each sub-region, dynamic optimization of control parameters and control strategy according to actual operation effect, realizing the balance of energy efficiency optimization and comfortable heating.

[0043] Secondly, an air source heat pump heating system, comprising:

[0044] The acquisition module is used to collect the frost layer thickness of the evaporator surface, the environmental temperature and humidity parameters in real time, input into the pre-trained neural network algorithm model, identify the frosting rate through analyzing the nonlinear relationship of multiple factors, predict the future frosting trend, output the frost thickness growth prediction and severity result; according to the frost thickness growth prediction and severity result, start reverse cycle defrosting in advance when the frost layer does not reach the critical thickness, realize the optimization control of defrosting process through adjusting the opening degree of four-way valve and fan speed, so as to obtain the system state after defrosting;

[0045] The computing module is used for monitoring the voltage fluctuation of the power grid in real time based on the system state after defrosting, starting voltage compensation before the voltage is lower than the normal working range of the compressor, and dynamically adjusting the frequency of the compressor to maintain stable operation of the system; according to the stable operation of the system, the ground heating system supply and return water temperature data are collected, the historical data and real-time heat load demand are combined, the thermal dynamic response relationship is established, the matching result between the heat pump output and the heating demand is obtained by adjusting the circulating pump speed of the buffer water tank and the opening degree of the water mixing valve, and the matching result between the heat pump output and the heating demand is obtained.

[0046] The processing module is used for obtaining multi-position temperature data through a distributed temperature monitoring device based on the matching result of the heat pump output and the heating demand, establishing the thermal field characteristic distribution of the heating area, generating system control parameters according to the thermodynamic characteristic parameters of each area, formulating a regional timing temperature control strategy based on the system control parameters, and controlling each heating loop through Internet of Things communication to realize energy efficiency optimization and comfortable heating.

[0047] In a third aspect, a computing device includes:

[0048] one or more processors;

[0049] a storage device storing one or more programs, when the one or more programs are executed by the one or more processors, the one or more processors implement the air source heat pump heating method.

[0050] In a fourth aspect, a computer readable storage medium stores a program, when the program is executed by a processor, the air source heat pump heating method is implemented.

[0051] The above-mentioned scheme of the present application at least has the following beneficial effects:

[0052] By innovatively fusing the neural network algorithm and the whole-process collaborative control logic, the technical bottlenecks of the traditional system are broken through, on the one hand, by means of the deep mining ability of the neural network to the nonlinear relationship of multiple parameters, the evaporator frosting trend prediction and the early defrosting control are accurately realized, the problems of efficiency reduction caused by too late defrosting or energy consumption caused by too early defrosting are avoided, and at the same time, through voltage fluctuation pre-compensation and compressor frequency dynamic adjustment, the unstable power grid scene is coped with, and the equipment downtime loss and the heating interruption risk are reduced; on the other hand, by establishing the thermal dynamic response relationship to optimize the matching degree of the heat pump output and the ground heating demand, the thermal field characteristic distribution is constructed by combining the distributed temperature monitoring, and the regional timing temperature control strategy is formulated, the indoor temperature fluctuation amplitude is reduced, the heating comfort is improved, the differentiated temperature control is realized according to the different regional use requirements, and the energy waste is reduced. Overall, the whole-link intelligent collaboration from the frosting prediction, the voltage adaptation to the thermal load matching and the regional temperature control is realized, and the operation stability of the system in the complex working conditions such as rural severe cold regions is improved. BRIEF DESCRIPTION OF DRAWINGS

[0053] Figure 1 is a flowchart of an air source heat pump heating method provided by an embodiment of the present application.

[0054] Figure 2 is a schematic diagram of an air source heat pump heating system provided by an embodiment of the present application. DETAILED DESCRIPTION

[0055] Exemplary embodiments of the present disclosure will be described in greater detail below with reference to the accompanying drawings. Although exemplary embodiments of the present disclosure are shown in the drawings, it is understood that the present disclosure can be implemented in various forms and should not be limited by the embodiments set forth herein. Rather, these embodiments are provided so that the present disclosure can be more thoroughly understood and the scope of the present disclosure can be accurately conveyed to those skilled in the art.

[0056] As shown in Figure 1 , an air source heat pump heating method is provided by an embodiment of the present application, which comprises the following steps:

[0057] Step 1, real-time collection of the frost layer thickness on the surface of the evaporator, the ambient temperature and humidity parameters, input into a pre-trained neural network algorithm model, identification of the frosting rate through analysis of the multi-factor nonlinear relationship, prediction of the future frosting development trend, output of the frost thickness growth prediction and severity result;

[0058] Step 2, based on the frost thickness growth prediction and severity result, early start of reverse cycle defrosting when the frost layer does not reach the critical thickness, optimization control of the defrosting process through adjustment of the four-way valve opening degree and the fan speed to obtain the system state after defrosting;

[0059] Step 3, based on the system state after defrosting, real-time monitoring of the power grid voltage fluctuation, start of voltage compensation before the voltage is lower than the normal working range of the compressor, and dynamic adjustment of the compressor frequency to maintain stable operation of the system;

[0060] Step 4, based on the stable operation of the system, collection of the ground heating system supply and return water temperature data, establishment of the thermal dynamic response relationship in combination with the historical data and real-time heat load demand, adjustment of the buffer water tank circulating pump speed and the water mixing valve opening degree to obtain the matching result between the heat pump output and the heating demand;

[0061] Step 5, based on the matching result between the heat pump output and the heating demand, acquisition of the multi-position temperature data through the distributed temperature monitoring device, establishment of the thermal field characteristic distribution of the heating area; generation of the system control parameters according to the thermodynamic characteristic parameters of each area, formulation of the regional timing temperature control strategy based on the system control parameters, and control of each heating loop through the Internet of Things communication to realize energy efficiency optimization and comfortable heating.

[0062] In the embodiment of the present application, through the whole-process intelligent design of prediction, regulation, matching and optimization, the core pain points of traditional heating systems are solved, and multi-dimensional advantages are possessed. Taking the neural network algorithm as the core, the frost rate is accurately identified by fusing the frost layer thickness of the evaporator, the environmental temperature and humidity and other parameters, and the development trend is predicted, the reverse defrosting before the frost layer reaches the critical thickness is realized, the problem of sudden drop of heat exchange efficiency caused by too late defrosting or energy waste caused by too early defrosting in the traditional defrosting mode is avoided, the defrosting process is optimized by dynamically adjusting the opening degree of the four-way valve and the rotating speed of the fan; after defrosting, relying on the real-time monitoring and pre-compensation mechanism of the voltage fluctuation of the power grid, combined with the dynamic adjustment of the frequency of the compressor, the system shutdown or damage caused by voltage abnormalities is avoided, and the operation continuity in the unstable scene of the power grid in the rural areas of severe cold regions is ensured; at the same time, by collecting the heating supply and return water temperature and combining the historical data to establish the thermal dynamic response relationship, the circulating pump of the buffer tank and the water mixing valve are adjusted to realize the accurate matching of the heat pump output and the heating demand, and based on the distributed temperature monitoring, the heating area heat field characteristic distribution is constructed, the regional timing temperature control strategy is formulated, and each loop is controlled through the Internet of Things, the indoor temperature fluctuation is reduced, the heating comfort is improved, the temperature is controlled differently according to the demand difference of different areas to reduce energy consumption, and finally the collaborative optimization of system energy efficiency, operation stability and user comfort is realized.

[0063] In a preferred embodiment of the present application, step 1 can include:

[0064] Step 1.1, real-time acquisition of the frost layer thickness of the evaporator surface, environmental temperature and humidity parameters, preprocessing of the collected original data parameters to obtain preprocessed data, specifically including: relying on the preset sensor monitoring component to complete the parameter acquisition operation, wherein for the frost layer thickness of the evaporator surface, an infrared distance measuring sensor or a capacitive thickness detection device can be used to obtain real-time thickness data at a collection frequency of not less than 1 time / minute; for the environmental temperature and humidity parameters, a temperature and humidity integrated sensor arranged within 1 meter around the evaporator is used for synchronous acquisition, and the collection frequency is consistent with the frost layer thickness collection frequency, ensuring the correspondence of the parameter time dimension.

[0065] Further, considering that the original collected data may have noise data or abnormal values caused by sensor fluctuation and external electromagnetic interference, the above original data parameters need to be preprocessed: first, the temperature, humidity and frost layer thickness data collected continuously are smoothed by using the moving average filtering method to filter out high-frequency noise; second, abnormal data points outside the normal fluctuation range are identified and removed by the 3 sigma rule to avoid interference of abnormal values on subsequent analysis; finally, the data after filtering and abnormal value removal are normalized to map each parameter value to the [0, 1] interval, so as to obtain the standardized preprocessed data.

[0066] Step 1.2, according to the pre-processed data, the standardized input vector containing the ambient temperature, humidity and frost thickness is organized in time sequence, and the standardized input vector is input into a pre-trained neural network model, the complex nonlinear interaction between each parameter in the input vector is mapped and characterized by high-dimensional nonlinear mapping through the internal hidden layer nodes, and the hidden state characteristics reflecting the current instantaneous frosting condition are calculated, based on the hidden state characteristics, the accurate frosting rate under the current working condition is obtained through the linear transformation and activation function processing of the output layer of the neural network model, specifically including: according to the obtained pre-processed data, the ambient temperature, humidity and frost thickness data at the same collection time are associated and integrated in time sequence, and a standardized input vector is formed, and the time interval is fixed, such as 5 minutes as a data unit, 5 groups of pre-processed data collected continuously in the time unit are arranged in the order of temperature, humidity and frost thickness dimension corresponding to 5 collection times, forming a matrix input vector with a dimension of 3x5, ensuring that the vector contains multi-parameter information at a single time and covers the parameter variation trend in a short time sequence.

[0067] Then, the standardized input vector is input into a pre-trained neural network model, the construction process of the neural network model is as follows, first, a multi-layer perceptron MLP is selected as the basic network structure, which includes an input layer, 2-3 hidden layers and an output layer; wherein the number of input layer neurons matches the dimension of the standardized input vector, i.e. 15 neurons corresponding to a 3x5 matrix input, the number of neurons in each hidden layer is set to 32-64 according to the complexity of parameter coupling, and the output layer is set to 1 neuron to output the frosting rate, secondly, the historical frosting working condition data is collected as training samples, the sample data covers the measured frosting rate under different environmental temperature and humidity intervals and different frost thickness, and the same pre-processing operation as step 1.1 is performed on the sample data, and then the training set and the validation set are divided according to the ratio of 7:3, then the mean square error is used as the loss function, the model is trained by Adam optimization algorithm, the second moment estimation of parameter gradient is calculated, the adaptive learning rate term is used to dynamically adjust the update step of each parameter, for parameters with flat gradient changes, the update step is appropriately increased to speed up the convergence; for parameters with large gradient fluctuations, the update step is reduced to ensure stability, so as to realize efficient optimization of model parameters, for example, the initial learning rate is set to 0.001, the learning rate is attenuated once every 100 iterations, and the early stopping method is used, when the validation set loss does not decrease for 20 consecutive rounds, the training is terminated to avoid overfitting, until the prediction error of the model on the validation set is less than a preset threshold, such as less than 5%, that is, the training and construction of the model are completed.

[0068] In the model operation process, firstly, the complex nonlinear interaction among temperature, humidity and frost thickness in the input vector is processed by the internal implicit layer nodes, each implicit layer node weights the input parameters through the weight coefficient obtained by training, and combines with the activation function to perform nonlinear transformation, wherein, is the input value of the implicit state feature received by the output layer node of the neural network after linear transformation, is the lower limit value of the frost rate, is the upper limit value of the frost rate, is the parameter of the adjustment function slope, realizing high-dimensional nonlinear mapping and extraction of the coupling characteristics of multiple parameters, and finally obtaining the implicit state feature reflecting the current instantaneous frosting condition, such as the slow growth feature in the initial frosting stage and the accelerated growth feature in the middle frosting stage. Based on the implicit state feature, it is further transmitted to the output layer of the neural network model, the output layer performs dimension compression on the implicit state feature through linear transformation, and maps the output result to a reasonable frost rate value range by means of the activation function, so as to obtain the accurate frost rate under the current working condition.

[0069] Step 1.3, based on the real-time frosting rate, combined with the time series data of the current ambient temperature and humidity, the neural network model performs multi-step forward inference calculation in the internal state space, predicts the frost thickness increment at each time in the future preset time window by iterative method, adds to the current thickness to generate a frost thickness growth prediction curve with time as the independent variable, and obtains the grade evaluation result of the frosting severity in the future period, including: based on the obtained real-time frosting rate, combined with the time series data of the current ambient temperature and humidity, first, the real-time frosting rate and the time series data of the temperature and humidity are input into the neural network model, and the model starts multi-step forward inference calculation in its internal state space. Specifically, a future preset time window is set, such as 1 hour in the future, which can be adjusted according to the frosting sensitivity of the actual heating system, and the time window is divided into several equal time interval sub-periods, such as 10 minutes for each sub-period. Then, the model takes the current frosting rate as the initial value, combines the change trend of the time series data of temperature and humidity, such as whether the temperature continues to decrease and the humidity continues to increase, and predicts the frost thickness increment in each sub-period by iterative calculation. In the first sub-period, based on the current temperature and humidity conditions and the real-time frosting rate, the thickness increment in this period is calculated. When entering the next sub-period, the predicted thickness of the previous sub-period is taken as the current thickness, combined with the temperature and humidity prediction value of the sub-period, which is derived from the change trend of the time series data of temperature and humidity, and the new thickness increment is recalculated. In this way, the thickness increment prediction of all sub-periods in the future time window is completed. Then, the predicted thickness increments of each sub-period are added to the collected current frost thickness in turn, and a frost thickness growth prediction curve with time as the horizontal coordinate and frost thickness as the vertical coordinate is generated. Finally, according to the preset frosting severity grade division standard, such as mild frosting for 0-1 mm of frost thickness, moderate frosting for 1-2 mm, and severe frosting for more than 2 mm, the frost thickness values at each time in the future are matched with the grades, and the grade evaluation result of the frosting severity in the future period is obtained.

[0070] In the embodiment of the present application, by real-time collection and preprocessing of the frost layer thickness on the evaporator surface, environmental temperature and humidity parameters, noise interference and abnormal fluctuations in the original data are filtered out; then the standardized input vector is introduced into the pre-trained neural network model, with the help of deep mining and high-dimensional mapping of the complex nonlinear relationship between multiple parameters by the hidden layer nodes, the key features reflecting the instantaneous frosting condition are accurately extracted, and then the accurate frosting rate is obtained through the output layer processing, which breaks through the limitation of traditional single parameter model that is difficult to capture the influence of multiple factor coupling, greatly improves the accuracy of the frosting rate calculation; finally, based on the real-time frosting rate and environmental time series data, multi-step forward deduction is carried out, the frost layer thickness growth prediction curve is generated in an iterative manner, and the severity grade evaluation is completed, so as to accurately predict the future frosting trend in advance, and enhance the active prevention and control ability and adaptability of the system to the frosting problem.

[0071] In a preferred embodiment of the present application, step 2 above can include:

[0072] Step 2.1, based on the prediction and severity results, judge the frost layer growth trend and calculate the expected time to reach the critical thickness, before the actual thickness of the frost layer reaches the critical thickness, generate the reverse cycle defrosting start instruction in advance according to the prediction results, specifically including: according to the output frost layer thickness growth prediction curve and the severity grade evaluation results, the change slope of the frost layer thickness with time is calculated by the trend fitting algorithm, so as to judge whether the growth trend of the frost layer is accelerated, uniform or decelerated, further, combined with the preset critical thickness value of the frost layer, such as 1.5mm, which can be adjusted according to the evaporator model and heat exchange efficiency requirement, the critical thickness is subtracted from the current measured frost layer thickness, and then divided by the current frosting rate, to calculate the expected time for the frost layer to reach the critical thickness, on this basis, set an advance threshold, such as 20% of the expected time, when the difference between the actual thickness of the frost layer and the critical thickness is greater than the thickness value corresponding to the advance, the generation of the reverse cycle defrosting start instruction is triggered, to ensure that the defrosting operation is started before the frost layer really reaches the critical thickness.

[0073] Step 2.2, the defrosting start instruction is issued to the air source heat pump unit control system, and the four-way valve is switched to control the refrigerant flow direction, and the reverse cycle defrosting process is started, specifically including: based on the generated reverse cycle defrosting start instruction, the start instruction is issued to the main control system of the air source heat pump unit in the form of electrical signal through the internal communication bus of the system, such as RS485 bus, the main control system sends a switching signal to the drive module of the four-way valve after receiving the instruction, and the valve core of the four-way valve is moved from the heating working condition position to the defrosting working condition position, so that the circulation direction of the refrigerant in the system is changed, the high temperature and high pressure refrigerant originally flowing to the indoor heat exchanger is preferentially flowed to the outdoor evaporator, and the frost layer on the surface of the evaporator is heated by using the condensation heat release of the refrigerant, so that the reverse cycle defrosting process is started, and the response time of the whole instruction issuing and four-way valve switching is controlled within 5 seconds, so that the rapid start of the defrosting process is ensured.

[0074] Step 2.3, in the defrosting process, the opening change rate of the four-way valve and the rotating speed of the outdoor fan are dynamically adjusted according to the frost severity result, so as to match the defrosting heat demand under different frost degrees, and realize the optimization control of the defrosting process, specifically including: after starting the reverse cycle defrosting process, the system first calls the output frost severity level, such as light, medium and heavy, and adjusts the opening change rate of the four-way valve and the rotating speed of the outdoor fan in real time according to the preset level and parameter correspondence, when the light frost is determined, the opening of the four-way valve is gradually increased at a slow rate, and the outdoor fan is maintained at 60%-70% of the rated rotating speed; when the medium frost is determined, the opening change rate of the four-way valve is accelerated, and the fan rotating speed is reduced to 40%-50% of the rated rotating speed; when the heavy frost is determined, the opening change rate of the four-way valve is further improved, and the fan rotating speed is reduced to less than 20% of the rated rotating speed or even stopped.

[0075] Step 2.4, the evaporator surface temperature and system pressure parameters are monitored in real time, the defrosting completion degree is judged, when it is confirmed that the evaporator surface frost layer is completely removed and the system parameters return to the normal operation range, a defrosting end instruction is generated, the four-way valve and the fan are restored to the heating operation state, the system state after defrosting is obtained, and specifically, the defrosting completion degree judgment and system recovery operation are synchronously performed while the dynamic defrosting control is performed, the temperature sensor arranged on the evaporator surface is used to collect the surface temperature in real time, and the pressure transmitter is used to monitor the pressure parameters of the high-pressure side of the system; when the evaporator surface temperature is monitored to be restored to more than 5 DEG C for 30 seconds, the temperature can ensure that the frost layer is completely melted, and the high-pressure side of the system is stable in the normal operation interval of 1.8-2.2 MPa, it is determined that the frost layer has been completely removed, and the defrosting process reaches the expected effect, at this time, the system generates a defrosting end instruction, the instruction is also issued to the unit control system through the internal communication bus, the valve core of the four-way valve is switched from the defrosting working condition position back to the heating working condition position, and the rotating speed of the outdoor fan is restored to the set value in the heating operation, such as the rotating speed automatically adjusted according to the environment temperature, so that the whole heat pump system reenters the heating operation state, and thus the stable operation state of the system after defrosting is obtained.

[0076] In the embodiment of the present application, the frost layer growth trend is accurately judged through the previous prediction and severity result, the time reaching the critical thickness is calculated in advance, the defrosting instruction is generated before the frost layer actually reaches the critical value, the influence of the frost layer on the evaporator heat exchange is effectively prevented, the heating capacity is ensured to be stable, the instruction is quickly conveyed to the air source heat pump unit control system, the four-way valve is quickly switched to control the flow direction of the refrigerant, the defrosting is started, the response time is greatly shortened, and the risk of continuous thickening of the frost layer is reduced, the four-way valve opening degree change rate and the outdoor fan rotating speed are flexibly adjusted according to the frosting severity, the accurate supply of defrosting heat is realized, and energy waste is avoided, the defrosting completion condition is accurately judged through real-time monitoring of the evaporator surface temperature and the system pressure parameters, the defrosting is ensured to be complete and not excessive, the system can quickly recover to stable heating after defrosting, the indoor temperature fluctuation is reduced, and the heating comfort and system operation efficiency are improved.

[0077] In a preferred embodiment of the present application, the above-mentioned step 3 can include:

[0078] Step 3.1, based on the system state after defrosting, and accordingly activate the grid voltage monitoring function, real-time acquisition of grid voltage data through voltage sensor, and voltage data filtering and trend analysis to predict voltage change trend, specifically including: first, the obtained system state after defrosting as the trigger condition, when the system confirms that the four-way valve and the fan have returned to the heating operation state, and the evaporator surface temperature and system pressure parameters are stable in the normal interval, send an activation signal to the grid voltage monitoring module to switch from standby state to working state; on this basis, through the voltage sensor installed in the compressor power supply circuit, real-time acquisition of instantaneous value data of grid input voltage at a frequency not less than 10 times / sec; then, the original voltage data collected is processed by moving average filtering method to filter out high-frequency noise caused by grid interference to obtain a smooth voltage curve; further, by analyzing the change slope and fluctuation amplitude of the voltage curve in the last 30 seconds, it is judged whether the voltage is currently rising, falling or stable, so as to predict the voltage change trend in the next 5-10 seconds.

[0079] Step 3.2, before analyzing and predicting that the grid voltage will drop to the minimum voltage threshold required for the normal operation of the compressor, generate a pre-compensation instruction, specifically including: based on the obtained voltage change trend prediction result, the system pre-sets the minimum voltage threshold required for the normal operation of the compressor, which is usually 85% of the rated voltage, which can be adjusted according to the compressor model, and compares the predicted future voltage value with the minimum threshold in real time; when it is found through trend analysis that the voltage will drop to the minimum threshold in the next 0.5-1 second, and this falling trend is persistent, such as showing voltage drop in 3 consecutive sampling periods, the central control unit of the system immediately generates a pre-compensation instruction, which contains the voltage amplitude information that needs to be compensated, to ensure that the compensation action is started before the voltage actually drops to the threshold.

[0080] Step 3.3, issue the pre-compensation instruction to the voltage compensation device to control it to run in advance to boost the power supply voltage and ensure that the voltage at the compressor end is maintained within the normal operating range, specifically including: based on the generated pre-compensation instruction, the pre-compensation instruction is issued to the voltage compensation device through the control bus inside the system, such as CAN bus; after receiving the instruction, the voltage compensation device runs according to the compensation amplitude information contained in the instruction, adjusts its output voltage gain, and injects compensation voltage into the compressor power supply circuit; wherein the size of the compensation voltage is determined according to the predicted voltage drop amplitude, so that the actual voltage at the input end of the compressor is always maintained within its normal operating range, i.e. 90%-110% of the rated voltage, to avoid abnormal operation of the compressor due to low voltage.

[0081] Step 3.4, while voltage compensation, according to the amplitude and trend of voltage fluctuation, dynamic calculation and generation of compressor frequency adjustment instruction, by fine-tuning the compressor frequency to balance the system load and power supply capacity, maintain the stable operation of the whole system, including: while performing voltage compensation operation, synchronous compressor frequency adjustment, system real-time record voltage fluctuation amplitude, that is, the deviation value and fluctuation trend of actual voltage and rated voltage, such as rapid drop, slow drop or fluctuation amplitude, and according to the preset voltage fluctuation and frequency adjustment mapping relationship, the relationship is determined based on the operating parameters provided by the compressor manufacturer and the actual debugging experience, the required compressor frequency adjustment amount under the current working condition is calculated; then, the corresponding frequency adjustment instruction is generated and issued to the frequency conversion driving device of the compressor, the output power of the compressor is adjusted by fine-tuning the operating frequency, so as to balance the load demand of the system and the power supply capacity of the power grid; through the cooperative operation of voltage compensation and frequency adjustment, the stable operation of the heat pump system under the fluctuation of power grid voltage is finally ensured, and the situation of shutdown or sudden drop of operation efficiency is avoided.

[0082] In the embodiment of the present application, the voltage monitoring is activated based on the system state after defrosting, the data is collected in real time by the voltage sensor and is filtered and trend analyzed to predict the voltage trend, so as to grasp the power grid fluctuation risk in advance and avoid the impact of voltage drop on the equipment; the pre-compensation instruction is generated before the voltage is predicted to drop to the lowest working threshold of the compressor, so that the voltage compensation device intervenes in advance to improve the power supply voltage, ensures that the voltage at the compressor end is always in the normal range, and prevents the compressor from stopping due to under-voltage; at the same time, the amplitude and trend of voltage fluctuation are combined to dynamically adjust the frequency of the compressor to balance the system load and power supply capacity, avoid the unstable operation problem caused by the mismatch between load and power supply. The whole process realizes the early response and cooperative regulation and control of power grid fluctuation, reduces the risk of compressor failure, ensures the continuous and stable operation of the system, avoids the interruption of heating caused by voltage problems, and takes into account the reliability of the equipment and the continuity of heating.

[0083] In a preferred embodiment of the present application, the above-mentioned step 4 can include:

[0084] Step 4.1, based on the maintained system stable running state, start the floor heating system monitoring sequence, real-time collection of heating system water supply temperature and return temperature data through temperature sensor, specifically including: based on the premise of maintaining the system stable running state, confirm that the compressor end voltage is in the normal working range, the compressor frequency is adjusted to the stable value and the system has no abnormal pressure fluctuation, then the start instruction of the floor heating system monitoring sequence can be triggered, after the monitoring sequence is started, the temperature sensor installed at the specific position of the heating system water supply pipeline and return pipeline, usually near the heat pump outlet of the water supply pipeline and near the heat pump inlet of the return pipeline, will be driven into working state, wherein the temperature sensor is preferably a platinum resistance sensor to ensure measurement accuracy, the sensor will acquire the instantaneous value of water supply temperature and return temperature in real time at a collection frequency not less than 1 time / min, and the collected temperature data will be transmitted to the system for storage through wired or wireless communication.

[0085] Step 4.2, call stored historical heating data, historical data including water supply and return temperature difference, heat load and system adjustment parameter under different outdoor working conditions, and integrate historical data with real-time collected water supply and return temperature data to get integrated data, specifically including: on the basis of continuous collection of real-time data of water supply and return temperature, the central control unit of the system will send data calling instruction to the data storage module to call the stored historical heating data, which needs to cover at least one complete heating season under different outdoor working conditions, the actual heat load data of the building under corresponding working conditions, and the system adjustment parameters used at that time to meet the heat load demand, such as buffer tank circulating pump speed, water mixing valve opening degree, etc. Then, the called historical heating data and real-time collected water supply and return temperature data are integrated according to the correlation dimension of outdoor working condition, water supply and return temperature difference, heat load and adjustment parameter, specifically, the real-time water supply and return temperature data are matched and classified with the water supply and return temperature difference data under the same or similar outdoor working condition in the historical data to form the integrated data containing real-time and historical information.

[0086] Step 4.3, based on the integrated data, the relationship between the water supply and return temperature difference and the flow rate change per unit time is calculated, and the real-time thermal dynamic response relationship of the system is established to obtain the analysis result of the thermal dynamic response relationship, which specifically includes: based on the obtained integrated data, first, the supply and return water temperature difference data and the corresponding system circulation flow rate data in a continuous time period such as 1 hour are extracted from the integrated data, and the circulation flow rate data can be calculated by converting the speed of the buffer tank circulating pump and the pump characteristic curve, then the corresponding relationship between the change amount of the supply and return water temperature difference and the change amount of the circulation flow rate per unit time such as 10 minute interval in this time period is calculated, for example, the change amplitude of the supply and return water temperature difference when the circulation flow rate increases by 10% is calculated, through the analysis and fitting of multiple sets of such corresponding relationship data, the real-time thermal dynamic response relationship of the system under the current working condition can be established, which can clearly reflect the influence law of the system circulation flow rate change on the supply and return water temperature difference, and then the analysis result of the thermal dynamic response relationship is formed.

[0087] Step 4.4, compare the real-time heat load demand with the analysis result of the thermal dynamic response relationship, calculate the target speed of the buffer tank circulating pump and the target opening of the water mixing valve required to achieve the supply-demand balance, and obtain the calculation result, which specifically includes: after obtaining the analysis result of the thermal dynamic response relationship, the system needs to obtain the real-time heat load demand of the current building, which can be determined in two ways, one is to combine the real-time outdoor temperature and the indoor set temperature, and the other is to monitor the deviation between the actual indoor temperature and the set temperature through the indoor temperature sensor, and then the required heat load supplement is deduced, then the real-time heat load demand is compared with the obtained analysis result of the thermal dynamic response relationship, to determine whether the current system heat supply can meet the real-time heat load demand, if the heat supply is insufficient, the circulation flow rate adjustment amplitude and the water temperature adjustment amplitude corresponding to the heat supply required to be increased need to be determined, if the heat supply is excessive, the adjustment amplitude corresponding to the heat supply required to be reduced needs to be determined, according to the above judgment result, combined with the speed and flow characteristic curve of the buffer tank circulating pump and the opening and water temperature adjustment characteristics of the water mixing valve, the target speed of the buffer tank circulating pump required to achieve the heat load supply-demand balance such as the current speed needs to be adjusted from 1500 r / min to 1800 r / min and the target opening of the water mixing valve such as the current opening needs to be adjusted from 30% to 45% is calculated, and finally the clear calculation result is obtained.

[0088] Step 4.5, generating control instructions according to the calculation results, dynamically adjusting the rotating speed of the buffer tank circulating pump to change the system circulation flow, and adjusting the opening degree of the mixing valve to control the mixed water temperature, so that the output heat of the heat pump matches the real-time heating demand of the building, and the final matching result is obtained, specifically including: according to the obtained calculation results, generating corresponding control instructions according to the calculation results, wherein the control instructions for the buffer tank circulating pump contain target rotating speed information, and the control instructions for the mixing valve contain target opening degree information, then, the control instructions are respectively sent to the variable frequency drive module of the buffer tank circulating pump and the actuator of the mixing valve, after the variable frequency drive module receives the instructions, the rotating speed of the circulating pump is gradually adjusted to the target rotating speed by adjusting the output frequency, so as to change the circulation flow of the system, and the change of the circulation flow will directly affect the heat delivery amount through the floor heating pipe per unit time; after the mixing valve actuator receives the instructions, the opening degree of the valve core is adjusted through the mechanical transmission structure, so as to control the mixing ratio of high-temperature water supply and low-temperature return water in the floor heating system, and then control the mixed water temperature delivered to the floor heating coil; through the coordinated dynamic adjustment of the rotating speed of the circulating pump and the opening degree of the mixing valve, the heat output by the heat pump can accurately match the real-time heating demand of the building, and finally the matching result of the heat pump output and the heating demand is obtained.

[0089] In the embodiment of the application, the system is started to monitor the floor heating based on stable operation, real-time collection of supply and return water temperature data is ensured to reflect the current heating situation, historical heating data is called and integrated with real-time data to avoid the limitation of single data, the heat dynamic response relationship is established by calculating the relationship between the supply and return water temperature difference and the flow change, the system heat transfer law is accurately mastered, the target rotating speed of the buffer tank circulating pump and the target opening degree of the mixing valve are calculated by comparing the real-time heat load demand and the response relationship analysis result, and clear basis is provided for regulation and control, and finally the pump rotating speed and the valve opening degree are dynamically adjusted to make the heat output of the heat pump match the real-time heating demand of the building, avoid the influence of insufficient heat supply on comfort, and prevent energy waste caused by excessive heat supply.

[0090] In a preferred embodiment of the application, step 5 can include:

[0091] Step 5.1, based on the matching result of heat pump output and heating demand, start the operation of the distributed temperature monitoring network, collect real-time temperature data through temperature sensors arranged at multiple positions in the heating area, specifically including: according to the obtained matching result of heat pump output and heating demand, confirm that the heat output of the heat pump has preliminarily coordinated with the real-time heating demand of the building, and the system heat output is in a stable state, then the system central control unit can issue a start instruction to the distributed temperature monitoring network, so that the network switches from standby mode to data collection mode. The distributed temperature monitoring network is composed of several temperature sensors, and the arrangement of the sensors needs to cover the key positions of the heating area, for example, the central of the living room, the bedside and window of each bedroom, the operating area of the kitchen, the dry area of the bathroom, etc. Different functional areas need to be arranged, and the number of sensors in each independent space is not less than 2, respectively close to the ground and 1.5m away from the ground. The temperature of the human activity area is simulated, and the sensor is preferably a digital temperature sensor to ensure data accuracy. After starting, these sensors will collect temperature data at the corresponding position at a collection frequency of 1 time / 3 minutes.

[0092] Step 5.2, clean and format the collected multi-position temperature data, eliminate abnormal data points, and associate the temperature data of each monitoring point with its corresponding space position information to obtain a standardized temperature distribution data set, specifically including: based on the continuous collection of multi-position temperature real-time data, the received original temperature data is cleaned, specifically, first set a reasonable temperature data value range, usually 5-30℃, which can be adjusted according to the heating season demand, and values exceeding this range are judged as abnormal data points, such as instantaneous high or low temperature caused by sensor failure; For the abnormal data points, instead of directly eliminating, the average value of the normal data of the adjacent 3 times of collection is used for replacement to ensure the continuity of the data sequence. After cleaning, the data is formatted, and the scattered temperature data is arranged into structured data according to the fixed format of collection time, sensor number, corresponding position and temperature value; further, the temperature data of each sensor is associated with its pre-recorded space position information, which is marked by two ways, one is to record the function name of the area where the sensor is located, and the other is to record the corresponding space coordinates. Through the association operation, a standardized temperature distribution data set containing time, position and temperature three-dimensional information is finally formed.

[0093] Step 5.3, based on the obtained normalized temperature distribution dataset, the heating area is divided into several independent sub-regions according to the spatial structure, and the representative temperature value of each sub-region is calculated by using the weighted average algorithm to generate the sub-region temperature distribution data, which specifically includes: based on the obtained normalized temperature distribution dataset, further sub-region division and representative temperature calculation will be carried out, and in the specific operation, first, according to the actual spatial structure of the heating area, the sub-regions are divided, for example, based on the physical partition of the building such as walls, doors and windows, the whole heating area is divided into living room sub-region, master bedroom sub-region, secondary bedroom sub-region, kitchen sub-region, bathroom sub-region and several independent sub-regions, each of which corresponds to a group of associated temperature data in the normalized dataset. After the division is completed, the representative temperature value of each sub-region is calculated by using the weighted average algorithm, specifically, first, determine the weight according to the layout position of the sensor in each sub-region, for example, the weight of the sensor at a height of 1.5 m from the ground is set to 0.6, and the weight of the sensor close to the ground is set to 0.4; then multiply the temperature data of each sensor in the sub-region by its corresponding weight, and divide the sum by the total weight to obtain the representative temperature value of the sub-region. By executing the above calculation on all sub-regions one by one, the sub-region temperature distribution data containing the names of each sub-region and the corresponding representative temperature is finally generated.

[0094] Step 5.4, based on the generated sub-region temperature distribution data, combined with the spatial structure characteristics and thermal characteristic parameters of the building, the spatial correlation and variation law of the temperature data of each sub-region are analyzed, and the thermal field characteristic distribution of the heating area is established, which specifically includes: according to the generated sub-region temperature distribution data, combined with the characteristics of the building itself, the establishment of the thermal field characteristic distribution of the heating area is completed. First, the system will call the pre-stored spatial structure characteristics and thermal characteristic parameters of the building, wherein the spatial structure characteristics include the wall thickness of each sub-region, the size and orientation of doors and windows, the floor height, etc., and the thermal characteristic parameters include the thermal conductivity of the wall insulation material, the heat transfer coefficient of the window, the thermal resistance of the roof and the ground, etc. Subsequently, based on these parameters, the spatial correlation of the temperature data of each sub-region is analyzed, for example, whether the temperature difference between the south-facing bedroom sub-region and the north-facing bedroom sub-region is caused by the different solar radiation heating caused by the orientation, whether there is mutual influence between the temperature of the living room sub-region and the adjacent kitchen sub-region, such as the heating effect of the kitchen on the living room temperature; at the same time, by continuously monitoring the change of the sub-region temperature with time, such as recording the representative temperature once an hour, the variation law is analyzed, for example, the corresponding drop amplitude of the temperature of each sub-region when the outdoor temperature drops by 2℃, to judge the difference in thermal stability of different sub-regions; through the comprehensive analysis of the spatial correlation and the variation law, the thermal field characteristic distribution that can directly reflect the temperature distribution difference, heat transfer characteristics and stability in the heating area is finally established in the form of temperature gradient chart or partition temperature distribution table.

[0095] In the embodiment of the present application, the distributed temperature monitoring is started based on the matching result of the heat pump and the heating demand, the data is collected by the multi-position sensor, the temperature distribution of the heating area is comprehensively captured, and the limitation of single-point monitoring is avoided; the collected data is cleaned, formatted and associated with the spatial position, the abnormal value interference can be eliminated, and the accuracy and normativity of the temperature distribution data set are ensured; the sub-regions are divided according to the space, and the representative temperature is calculated, so that the temperature data is more suitable for the actual heating partition demand, and the targeted regulation and control is facilitated; the correlation and law of the sub-regional temperature are analyzed in combination with the building structure and the thermal parameter, the thermal field characteristic distribution is established, and the heat transfer characteristics and temperature change trend of each region are clearly mastered.

[0096] In a preferred embodiment of the present application, step 5 can include:

[0097] Step 5.5, based on the thermal field characteristic distribution, extracting the thermodynamic characteristic parameters of each sub-region, the thermodynamic characteristic parameters including temperature stability, thermal inertia coefficient and thermal response time constant, specifically including: based on the established thermal field characteristic distribution of the heating area, first, the representative temperature data of the continuous thermodynamic characteristics of each sub-region in the thermal field characteristic distribution is called, based on which the temperature stability is calculated, by calculating the difference between the maximum value and the minimum value of the temperature of the sub-region in the time period, the smaller the difference, the higher the temperature stability, and the frequency of temperature fluctuation is recorded as an auxiliary evaluation index of temperature stability. For the extraction of the thermal inertia coefficient, the building thermal characteristic parameters such as the wall thickness of the sub-region, the thermal conductivity coefficient of the thermal insulation material and the temperature change data are combined, when the system adjusts the heating output, the time required for the temperature of the sub-region to change from the initial value to the new stable value is recorded, the longer the time, the larger the thermal inertia coefficient, and the thermal response time constant can be determined by comparing the temperature response lag time of different sub-regions under the same heating adjustment amplitude, and the extraction of the thermal response time constant requires monitoring the time required for the temperature of the sub-region to reach the final stable temperature after the heating starts or stops, which is the thermal response time constant, and the average value of the monitoring data of multiple heating start-stop processes is taken to ensure the accuracy of the parameter extraction, and finally a parameter set containing the temperature stability grade of each sub-region, the specific thermal inertia coefficient value and the thermal response time constant is formed.

[0098] Step 5.6, according to the extracted thermodynamic characteristic parameters, combined with the use function characteristics and comfort requirements of each sub-region, generate system control parameters for each sub-region, specifically including: based on the extraction of the thermodynamic characteristic parameters of each sub-region, combined with the use function characteristics and comfort requirements of each sub-region, generate dedicated system control parameters, first, the use function characteristics of each sub-region are determined, for example, the master bedroom and the secondary bedroom are sleep and rest areas, and the use period is concentrated in the thermodynamic characteristics 22:00-7:00; the living room is a daily activity area, and the use period is concentrated in the thermodynamic characteristics 8:00-22:00; the kitchen is a short-time operation area, and the use period is concentrated in the thermodynamic characteristics 1 hour before and after each meal; the bathroom is a washing area, and the use period is scattered and needs to maintain a basic temperature, at the same time, according to different function areas, corresponding comfort requirements are set: the temperature of the sleep area needs to be stable at the thermodynamic characteristics 18-20℃, and the fluctuation amplitude is not more than the thermodynamic characteristics ±0.5℃; the temperature of the activity area needs to be maintained at the thermodynamic characteristics 22-24℃, and the fluctuation amplitude is not more than the thermodynamic characteristics ±1℃; the temperature of the short-time use area can be controlled at the thermodynamic characteristics 16-18℃, and the basic temperature is not lower than the thermodynamic characteristics 15℃, then, combined with the thermodynamic characteristic parameters, the control parameters are generated, for the sub-regions with large thermal inertia coefficient and long thermal response time, such as the master bedroom with thick wall and good heat preservation, the heating start-stop advance is set to the thermodynamic characteristics 30-40 minutes, to avoid the influence of temperature response lag on comfort; for the sub-regions with poor temperature stability and easy to be disturbed by the outside world, such as the secondary bedroom near the window, the temperature fluctuation threshold is set to the thermodynamic characteristics ±0.3℃, and the sensitivity of the triggered control is higher; finally, the dedicated system control parameters of each sub-region are formed, including the thermodynamic characteristics target temperature range, the temperature fluctuation threshold, the heating start-stop advance, and the control sensitivity.

[0099] Step 5.7, based on the generated system regulation parameters, combined with historical heating data and usage habits, formulate a sub-regional timing temperature control strategy, specifically including: based on the generated system regulation parameters of each sub-region, the thermodynamic characteristics will combine historical heating data and user usage habits to formulate a sub-regional timing temperature control strategy. First, the system calls the historical heating data stored in the data storage module, which needs to cover at least one complete heating season of temperature adjustment records of each sub-region, energy consumption data of corresponding period, and optimal heating parameters under different outdoor conditions. At the same time, through the user interaction interface or historical operation record, the user usage habits are obtained, for example, the user habit is to use the living room from 7:00 to 8:00 and from 18:00 to 22:00 on weekdays, and to use the living room all day on weekends; The habit is to lower the temperature of the master bedroom to 18°C from 23:00 to 6:30, and then divide different control periods for each sub-region with time as the axis, and match the corresponding target temperature and regulation rules: for example, the living room from 7:00 to 8:00 and from 18:00 to 22:00 on weekdays, the target temperature is set to 23°C, and the regulation sensitivity is set to medium; From 22:00 to 7:00, the target temperature is set to 18°C, and the heating start-stop advance is set to 20 minutes; On weekends, the target temperature from 10:00 to 21:00 is set to 23°C, and the rest of the period is the same as weekdays; For the master bedroom, the target temperature from 23:00 to 6:30 is set to 18°C, from 6:30 to 23:00 is set to 20°C, and because of the large thermal inertia, the heating start-stop advance is set to 40 minutes, to ensure that the temperature meets the standard during the user's usage period. Through the above method, the timing temperature control strategy of all sub-regions is completed.

[0100] Step 5.8, the formulated sub-regional timing temperature control strategy is issued to the intelligent control devices of each heating circuit through Internet of Things communication to realize independent and accurate control of each heating circuit, specifically including: after the completion of the sub-regional timing temperature control strategy is formulated, the strategy is issued and executed through Internet of Things communication, and in specific operation, the system central control unit first splits the formulated sub-regional timing strategy according to sub-regions, converts it into an instruction format thermodynamic characteristic recognizable by the intelligent control device, and the instruction content includes sub-region number, corresponding heating circuit identifier, start and end time of each control period, target temperature value, and adjustment instruction when the temperature deviation exceeds the limit, such as increasing the opening degree of the electric regulating valve by 10% when the temperature is 1°C lower than the target value; then, through industrial Internet of Things communication, preferably LoRa or NB-IoT communication protocol, the communication stability in low temperature and long distance environment is ensured, and the split instructions are issued to the intelligent control devices of each heating circuit, wherein each sub-region corresponds to an independent heating circuit, and the intelligent control devices in the circuit include electric regulating valves and intelligent temperature controllers, and the devices have been pre-bound with the identifiers of sub-regions and heating circuits. After receiving the instructions, the intelligent control devices automatically store and load the strategy, and perform control actions according to the time period and temperature requirements in the instructions, for example, automatically adjusting the opening degree of the electric regulating valve to change the heating capacity at the set time period, to realize independent and accurate control of each heating circuit, and avoid mutual interference of different sub-regions due to control.

[0101] Step 5.9, real-time monitoring of temperature changes and energy consumption data of each sub-region, dynamically optimizing the control parameters and control strategy according to the actual operation effect, realizing the balance of energy efficiency optimization and comfortable heating, specifically including: realizing independent and accurate control of each heating loop, and through real-time monitoring and dynamic optimization, ensuring that the system is always in a balanced state of energy efficiency and comfort. Specifically, first, start the double-dimensional monitoring mechanism. On the one hand, through the temperature sensors in each sub-region, the actual temperature data is collected at a frequency of 1 minute, 2 minutes, 3 minutes, or 4 minutes according to the actual temperature and the target temperature set by the strategy, and the temperature deviation time is recorded. On the other hand, through the energy consumption measuring device installed in each heating loop, such as an ultrasonic heat meter, the energy consumption data is collected at a frequency of 1 hour, 2 hours, 3 hours, or 4 hours, and the heat consumption per unit time of each sub-region is calculated. Then, according to the monitoring data, the actual operation effect is evaluated. If the actual temperature of a certain sub-region continuously meets the target requirements and the energy consumption is at a historically low level, it means that the current control parameters and strategy are suitable and do not need to be adjusted. If the temperature deviation frequently occurs in the sub-region, such as the temperature rise lag in the sub-region with large thermal inertia, the heating start-stop advance amount is appropriately increased, such as from 30 minutes to 40 minutes. If the energy consumption is too high but the temperature has reached the standard, the target temperature upper limit or the maximum opening degree of the electric regulating valve is appropriately reduced. Through the cycle optimization mechanism of monitoring, evaluation, and adjustment, the system control parameters and regional timing strategy of each sub-region are dynamically updated, and finally the two-way balance of system energy efficiency optimization and user heating comfort is realized, avoiding energy waste or insufficient comfort caused by fixed strategies.

[0102] In the embodiments of the present application, the thermal parameters such as temperature stability of each sub-region are extracted from the thermal field characteristic distribution, and the differences in thermal characteristics of different regions are accurately grasped. Then, combined with the use function and comfort requirement of the sub-region, the exclusive control parameters are generated to avoid the disadvantages of one-size-fits-all control. Then, combined with historical data and use habits, the regional timing temperature control strategy is formulated to make the control more in line with actual needs. Then, through the Internet of Things, the strategy is issued to the intelligent device to realize independent and accurate control of each heating loop and ensure that the temperature of different regions meets the standard. Finally, real-time monitoring of temperature and energy consumption and dynamic optimization are carried out to avoid the influence of temperature fluctuation on comfort and reduce unnecessary energy consumption.

[0103] As shown in Figure 2 , the embodiments of the present application also provide an air source heat pump heating system, which comprises:

[0104] The acquisition module is used for collecting the frost layer thickness on the surface of the evaporator, the ambient temperature and the humidity parameter in real time, inputting to the neural network algorithm model trained in advance, identifying the frosting rate through analyzing the nonlinear relationship of multiple factors, predicting the future frosting development trend, and outputting the frost layer thickness growth prediction and severity result; according to the frost layer thickness growth prediction and severity result, starting the reverse cycle defrosting in advance when the frost layer does not reach the critical thickness, realizing the optimization control of the defrosting process through adjusting the four-way valve opening degree and the fan rotating speed, so as to obtain the system state after defrosting;

[0105] The calculation module is used for monitoring the power grid voltage fluctuation in real time based on the system state after defrosting, starting the voltage compensation before the voltage is lower than the normal working range of the compressor, and dynamically adjusting the compressor frequency, so as to maintain the stable operation of the system; according to the stable operation of the system, collecting the ground heating system supply and return water temperature data, combining the historical data and the real-time heat load demand, establishing the thermal dynamic response relationship, adjusting the circulating pump rotating speed of the buffer water tank and the water mixing valve opening degree, so as to obtain the matching result between the heat pump output and the heating demand;

[0106] The processing module is used for obtaining the multi-position temperature data through the distributed temperature monitoring device based on the matching result between the heat pump output and the heating demand, establishing the thermal field characteristic distribution of the heating area; generating the system control parameter according to the thermodynamic characteristic parameter of each area, formulating the regional timing temperature control strategy based on the system control parameter, and controlling each heating loop through the Internet of Things communication, so as to realize the energy efficiency optimization and the comfortable heating.

[0107] The above is the preferred embodiment of the present application, it should be noted that for those skilled in the art, without departing from the principles of the present application, can make a number of improvements and refinements, these improvements and refinements should also be considered as the protection scope of the present application.

Claims

1. A method for heating using an air source heat pump, characterized in that, The method includes: Step 1: Real-time acquisition of frost thickness, ambient temperature, and humidity parameters on the evaporator surface, input into a pre-trained neural network algorithm model, analyze multi-factor nonlinear relationships to identify frost rate, predict future frost development trends, and output frost thickness growth prediction and severity results. Step 2: Based on the predicted increase in frost thickness and the severity of the frost, reverse circulation defrosting is initiated in advance before the frost layer reaches the critical thickness. The defrosting process is optimized by adjusting the opening of the four-way valve and the fan speed to obtain the system status after defrosting. Step 3: Based on the system status after defrosting, monitor the grid voltage fluctuations in real time, initiate voltage compensation before the voltage drops below the compressor's normal operating range, and dynamically adjust the compressor frequency to maintain stable system operation; Step 4: Based on the stable operation of the system, collect the supply and return water temperature data of the underfloor heating system, combine historical data with real-time heat load demand, establish a dynamic thermal response relationship, and obtain the matching result between heat pump output and heating demand by adjusting the speed of the buffer tank circulation pump and the opening of the mixing valve. Step 5: Based on the matching results of heat pump output and heating demand, acquire temperature data from multiple locations through distributed temperature monitoring devices to establish the thermal field characteristic distribution of the heating area; generate system control parameters according to the thermodynamic characteristic parameters of each area, formulate a timed temperature control strategy for each area based on the system control parameters, and control each heating circuit through IoT communication to achieve energy efficiency optimization and comfortable heating.

2. The air source heat pump heating method according to claim 1, characterized in that, The system collects real-time data on frost thickness, ambient temperature, and humidity on the evaporator surface. This data is then input into a pre-trained neural network algorithm model. By analyzing the nonlinear relationships between multiple factors, the system identifies the frost formation rate, predicts future frost development trends, and outputs predictions of frost thickness growth and severity, including: Step 1.1: Real-time collection of frost thickness, ambient temperature, and humidity parameters on the evaporator surface; preprocessing of the collected raw data parameters to obtain preprocessed data. Step 1.2: Based on the preprocessed data, organize it into a standardized input vector containing ambient temperature, humidity, and frost thickness in chronological order. Input the standardized input vector into a pre-trained neural network model. Through the internal hidden layer nodes, perform high-dimensional nonlinear mapping and feature extraction on the complex nonlinear interactions between the parameters in the input vector to calculate the hidden state features reflecting the current instantaneous frost condition. Based on the hidden state features, obtain the accurate frost rate under the current working condition through linear transformation and activation function processing of the output layer of the neural network model. Step 1.3: Based on the real-time frost rate and combined with the time-series data of the current ambient temperature and humidity, the neural network model performs multi-step forward extrapolation calculations in its internal state space. Iteratively, it predicts the frost thickness increment at each moment within the preset time window in the future, accumulates it to the current thickness, and generates a frost thickness growth prediction curve with time as the independent variable, thus obtaining the rating result of the severity of frost in the future period.

3. The air source heat pump heating method according to claim 2, characterized in that, Based on the predicted frost thickness and severity, reverse circulation defrosting is initiated before the frost layer reaches the critical thickness. Optimized control of the defrosting process is achieved by adjusting the opening of the four-way valve and the fan speed to obtain the system state after defrosting, including: Step 2.1: Based on the prediction and severity results, determine the frost growth trend and calculate the expected time to reach the critical thickness. Before the actual thickness of the frost layer reaches the critical thickness, generate a reverse cycle defrosting start command in advance based on the prediction results. Step 2.2: Send the defrost start command to the air source heat pump unit control system, control the four-way valve to switch the refrigerant flow direction, and start the reverse cycle defrost process; Step 2.3: During the defrosting process, the opening rate of the four-way valve and the speed of the outdoor fan are dynamically adjusted according to the severity of frost to match the defrosting heat demand under different frost levels and achieve optimized control of the defrosting process. Step 2.4: Monitor the evaporator surface temperature and system pressure parameters in real time to determine the defrosting completion rate. When it is confirmed that the frost layer on the evaporator surface has been completely removed and the system parameters have returned to the normal operating range, generate a defrosting end command, control the four-way valve and fan to return to the heating operation state, and obtain the system status after defrosting.

4. The air source heat pump heating method according to claim 3, characterized in that, Based on the system status after defrosting, the grid voltage fluctuations are monitored in real time. Voltage compensation is initiated before the voltage drops below the compressor's normal operating range, and the compressor frequency is dynamically adjusted to maintain stable system operation, including: Step 3.1: Based on the system status after defrosting, activate the grid voltage monitoring function accordingly, collect grid voltage data in real time through voltage sensors, and perform filtering and trend analysis on the voltage data to predict voltage change trends. Step 3.2: By analyzing and predicting that the grid voltage is about to drop to the minimum voltage threshold required for the compressor to operate normally, a pre-compensation command is generated; Step 3.3: Send the pre-compensation command to the voltage compensation device to control it to start operation in advance to increase the power supply voltage and ensure that the compressor terminal voltage is maintained within the normal operating range; Step 3.4: While compensating for voltage, dynamically calculate and generate compressor frequency adjustment commands based on the amplitude and trend of voltage fluctuations. By fine-tuning the compressor operating frequency, balance the system load and power supply capacity to maintain the overall stable operation of the system.

5. The air source heat pump heating method according to claim 4, characterized in that, Based on the stable operation of the system, the supply and return water temperature data of the underfloor heating system are collected. Combined with historical data and real-time heat load demand, a dynamic thermal response relationship is established. By adjusting the speed of the buffer tank circulation pump and the opening of the mixing valve, the matching result between the heat pump output and the heating demand is obtained, including: Step 4.1: Based on the maintained stable operation of the system, start the underfloor heating system monitoring sequence and collect the supply and return water temperature data of the heating system in real time through temperature sensors. Step 4.2: Retrieve the stored historical heating data, which includes the supply and return water temperature difference, heat load and system adjustment parameters under different outdoor conditions. Integrate the historical data with the real-time collected supply and return water temperature data to obtain the integrated data. Step 4.3: Based on the integrated data, calculate the correspondence between the supply and return water temperature difference and flow rate change per unit time, establish the real-time thermal dynamic response relationship of the system, and obtain the analysis results of the thermal dynamic response relationship. Step 4.4: Compare the analysis results of the relationship between real-time heat load demand and thermal dynamic response, calculate the target speed of the buffer tank circulating pump and the target opening of the mixing valve required to achieve supply and demand balance, and obtain the calculation results; Step 4.5: Generate control commands based on the calculation results, dynamically adjust the speed of the buffer tank circulation pump to change the system circulation flow rate, and simultaneously adjust the opening of the mixing valve to control the mixed water temperature, so that the heat output of the heat pump is coordinated with the real-time heating demand of the building, and the final matching result is obtained.

6. The air source heat pump heating method according to claim 5, characterized in that, Based on the matching results between heat pump output and heating demand, multi-location temperature data are acquired through distributed temperature monitoring devices to establish the thermal field characteristic distribution of the heating area, including: Step 5.1: Based on the matching results of heat pump output and heating demand, start the operation of the distributed temperature monitoring network and collect real-time temperature data through temperature sensors placed in multiple locations within the heating area. Step 5.2: Clean and format the collected multi-location temperature data, remove abnormal data points, and associate the temperature data of each monitoring point with its corresponding spatial location information to obtain a standardized temperature distribution dataset. Step 5.3: Based on the obtained normalized temperature distribution dataset, the heating area is divided into several independent sub-regions according to the spatial structure. The weighted average algorithm is used to calculate the representative temperature value of each sub-region to generate sub-region temperature distribution data. Step 5.4: Based on the generated sub-region temperature distribution data, combined with the spatial structural characteristics and thermal performance parameters of the building, analyze the spatial correlation and variation law of the temperature data of each sub-region, and establish the thermal field characteristic distribution of the heating area.

7. The air source heat pump heating method according to claim 6, characterized in that, System control parameters are generated based on the thermodynamic characteristics of each region. A regional timed temperature control strategy is then formulated based on these parameters. Furthermore, each heating circuit is controlled via IoT communication to achieve energy efficiency optimization and comfortable heating, including: Step 5.5: Based on the thermal field characteristic distribution, extract the thermodynamic characteristic parameters of each sub-region. The thermodynamic characteristic parameters include temperature stability, thermal inertia coefficient, and thermal response time constant. Step 5.6: Based on the extracted thermodynamic characteristic parameters, and combined with the functional characteristics and comfort requirements of each sub-region, generate system control parameters for each sub-region; Step 5.7: Based on the generated system control parameters, combined with historical heating data and usage habits, formulate a zoned timed temperature control strategy; Step 5.8: The established zoned timed temperature control strategy is sent to the intelligent control equipment of each heating circuit via IoT communication to achieve independent and precise control of each heating circuit. Step 5.9: Monitor the temperature changes and energy consumption data of each sub-region in real time, and dynamically optimize the control parameters and control strategies based on the actual operating results to achieve a balance between energy efficiency optimization and comfortable heating.

8. An air source heat pump heating system, wherein the system implements the air source heat pump heating method as described in any one of claims 1 to 7, characterized in that, include: The acquisition module is used to collect real-time data on the frost thickness, ambient temperature, and humidity parameters on the evaporator surface. This data is then input into a pre-trained neural network algorithm model. By analyzing the nonlinear relationships of multiple factors, the frost rate is identified, the future frost development trend is predicted, and the predicted frost thickness growth and severity results are output. Based on the predicted frost thickness growth and severity results, reverse cycle defrosting is initiated in advance before the frost layer reaches the critical thickness. The defrosting process is optimized by adjusting the opening of the four-way valve and the fan speed to obtain the system status after defrosting. The calculation module is used to monitor grid voltage fluctuations in real time based on the system status after defrosting, initiate voltage compensation before the voltage drops below the compressor's normal operating range, and dynamically adjust the compressor frequency to maintain stable system operation. Based on the stable operation of the system, it collects the supply and return water temperature data of the underfloor heating system, combines historical data with real-time heat load demand, establishes a dynamic thermal response relationship, and obtains the matching result between heat pump output and heating demand by adjusting the speed of the buffer tank circulation pump and the opening of the mixing valve. The processing module is used to acquire temperature data from multiple locations through distributed temperature monitoring devices based on the matching results of heat pump output and heating demand, and establish the thermal field characteristic distribution of the heating area; generate system control parameters according to the thermodynamic characteristic parameters of each area, formulate regional timed temperature control strategies based on the system control parameters, and control each heating circuit through IoT communication to achieve energy efficiency optimization and comfortable heating.

9. A computing device, characterized in that, include: One or more processors; A storage device for storing one or more programs, which, when executed by one or more processors, cause the one or more processors to implement the air source heat pump heating method as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a program that, when executed by a processor, implements the air source heat pump heating method as described in any one of claims 1 to 7.

Images