Control method and device of heat pump unit, computer equipment and storage medium

Abstract

The invention relates to a control method and device of a heat pump unit, computer equipment and a storage medium. The control method comprises the steps that a first parameter of the heat pump unit is obtained, the first parameter is historical data of the heat pump unit, and the historical data at least comprises historical heat load parameters of the heat pump unit before the current moment; according to the first parameter, predicting a reference heat load parameter of the heat pump unit; and according to the reference heat load parameters, the heat output by the heat pump unit is adjusted. According to the historical data of the heat pump unit, the reference heat load parameter of the heat pump unit is predicted, the accuracy of the reference heat load parameter is improved, the heat output by the heat pump unit is adjusted according to the reference heat load parameter, the heat output by the heat pump unit can be matched with the actual heat load, the heat supply effect of the user side is guaranteed, and meanwhile the user experience is improved. And energy waste is avoided, and the operation cost of the heat pump unit is reduced.

Description

Technical Field

[0001] This application relates to the field of heat pump unit control, and particularly to a control method, device, computer device and storage medium for a heat pump unit. Background Art

[0002] A heat pump unit is an energy-saving device that absorbs heat from a low-temperature heat source (such as air, water, soil, etc.) by inputting a small amount of electric energy (or other driving energy), raises the temperature, and then releases the heat energy to a high-temperature environment. It can realize functions such as heating, cooling, and domestic hot water supply, and is an efficient and environmentally friendly energy conversion device.

[0003] As a complex system with hysteresis and coupling, scientifically and real-time heating on demand is an urgent problem to be solved. During the heating process of the heat pump unit, the heat load is an important basis for adjusting the heat output of the heat pump unit. Accurately predicting the heat load can guide the production and distribution of heat, while ensuring the heating effect on the user side and avoiding energy waste. Currently, it is usually the staff who form a comparison table of outdoor temperature and heat load based on empirical data, or the staff use the method of linear ratio and empirical correction to derive the heat load corresponding to different outdoor temperatures according to the load ratio, and form a comparison table of outdoor temperature and heat load. When predicting the heat load, the staff look up the comparison table and determine the reference heat load parameter for the current day according to the outdoor temperature of the current day.

[0004] However, in addition to the outdoor temperature, other environmental factors such as outdoor wind speed, solar radiation intensity, extreme weather such as rainfall and snowfall, as well as factors such as the supply water temperature, return water temperature and historical heat load inside the heat pump unit will also affect the heat load. The above heat load prediction method ignores these factors, and moreover, the heat load prediction is not a simple linear prediction, and the comparison table derived by the method of linear ratio and empirical correction is not accurate. Therefore, the reference heat load parameter obtained by the above prediction method is not accurate, which will lead to problems such as uneven heating, unqualified indoor temperature and heat waste in the heat pump unit. Summary of the Invention

[0005] To overcome the problems existing in the related art, this application provides a control method, device, computer device and storage medium for a heat pump unit.

[0006] According to the first aspect of the embodiments of this application, a control method for a heat pump unit is provided, including:

[0007] Obtain a first parameter of the heat pump unit, where the first parameter is historical data of the heat pump unit, and the historical data at least includes the historical heat load parameter of the heat pump unit before the current moment;

[0008] Predict the reference heat load parameter of the heat pump unit according to the first parameter;

[0009] Adjust the heat output of the heat pump unit according to the reference heat load parameter.

[0010] In some exemplary embodiments of the present application, the predicting the reference heat load parameter of the heat pump unit according to the first parameter includes:

[0011] Input the first parameter into a preset heat load prediction model;

[0012] Take the output of the heat load prediction model as the reference heat load parameter.

[0013] In some exemplary embodiments of the present application, the heat load prediction model is a neural network model built using a long short-term memory network;

[0014] The heat load prediction model is as follows:

[0015] f t = σ(W f ·[h t-1 , x t +b f );

[0016] i t = σ(W i ·[h t-1 , x t +b i );

[0017]

[0018] o t = σ(W o ·[h t-1 , x t +b o );

[0019] h t = o t ⊙ t(C t );

[0020] y t = W y · h t +b y ;

[0021] where x t is the first parameter at time t, and the time t is the current time, y t is the reference heat load parameter at time t, h t-1is the output of the network structure of the heat load prediction model at time t-1, h t is the output of the network structure of the heat load prediction model at time t, C t-1 is the cell state of the network structure of the heat load prediction model at time t-1, C t is the cell state of the network structure of the heat load prediction model at time t, f t is the activation value of the forget gate of the heat load prediction model at time t, W f is the weight matrix of the forget gate, b f is the bias of the forget gate, i t is the activation value of the input gate of the heat load prediction model at time t, W i is the weight matrix of the input gate, b i is the bias of the input gate, is the candidate memory of the input gate of the heat load prediction model at time t, W c is the weight matrix of the candidate memory, b c is the bias of the candidate memory, o t is the activation value of the output gate of the heat load prediction model at time t, W o is the weight matrix of the output gate, b o is the bias of the output gate, W y is y t 's weight matrix, b y is y t 's bias.

[0022] In some exemplary embodiments of the present application, the obtaining of the first parameter of the heat pump unit includes:

[0023] Obtain the historical heat load parameter, time stamp parameter, environmental parameter and the operation parameter of the heat pump unit, wherein the reference heat load parameter is updated every preset time period, the historical heat load parameter includes the reference heat load parameter in the N update cycles before the current moment, N is a positive integer greater than or equal to 1, the time stamp parameter, the environmental parameter and the operation parameter of the heat pump unit are collected simultaneously with the historical heat load parameter, the time stamp parameter includes the time information corresponding to the reference heat load parameter in the N update cycles before the current moment, the environmental parameter includes the environmental factors of the operation environment of the heat pump unit in the N update cycles before the current moment, and the operation parameter of the heat pump unit includes the operation data of the heat pump unit in the N update cycles before the current moment;

[0024] Take the historical heat load parameter, the timestamp parameter, the environmental parameter, and the operating parameter of the heat pump unit as the first parameter.

[0025] In some exemplary embodiments of the present application, adjusting the heat output of the heat pump unit according to the reference heat load parameter includes:

[0026] Calculate the set value of the outlet water temperature of the condenser of the heat pump unit according to the reference heat load parameter;

[0027] Control the opening degree of the electronic expansion valve of the heat pump unit according to the set value of the outlet water temperature to adjust the heat output of the heat pump unit.

[0028] In some exemplary embodiments of the present application, calculating the set value of the outlet water temperature of the condenser of the heat pump unit according to the reference heat load parameter includes:

[0029] Obtain the condensate flow parameter of the heat pump unit;

[0030] Calculate the set value of the outlet water temperature according to the reference heat load parameter and the condensate flow parameter.

[0031] In some exemplary embodiments of the present application, controlling the opening degree of the electronic expansion valve of the heat pump unit according to the set value of the outlet water temperature includes:

[0032] Use a fractional order proportional-integral-derivative controller to control the opening degree of the electronic expansion valve according to the set value of the outlet water temperature.

[0033] According to the second aspect of the embodiments of the present application, there is provided a control device for a heat pump unit, including:

[0034] A parameter acquisition module configured to acquire the first parameter of the heat pump unit, where the first parameter is historical data of the heat pump unit, and the historical data at least includes the historical heat load parameter of the heat pump unit before the current moment;

[0035] A parameter prediction module configured to predict the reference heat load parameter of the heat pump unit according to the first parameter;

[0036] A heat adjustment module configured to adjust the heat output of the heat pump unit according to the reference heat load parameter.

[0037] According to the third aspect of the embodiments of the present application, there is provided a computer device including a memory and a processor, where the memory stores a computer program, and when the processor executes the computer program, the steps of the control method of the heat pump unit as described in the first aspect are implemented.

[0038] According to a fourth aspect of the embodiments of the present application, there is provided a non-transitory computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps of the control method of the heat pump unit as described in the first aspect are implemented.

[0039] The technical solutions provided by the embodiments of the present application may include the following beneficial effects: According to the historical data of the heat pump unit, the reference heat load parameter of the heat pump unit is predicted, which improves the accuracy of the reference heat load parameter. Adjusting the heat output of the heat pump unit according to the reference heat load parameter can make the heat output of the heat pump unit match the actual heat load, avoiding energy waste while ensuring the heating effect on the user side and reducing the operating cost of the heat pump unit.

[0040] It should be understood that the above general description and the following detailed description are only exemplary and explanatory, and cannot limit the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] The drawings herein are incorporated into the specification and constitute a part of the specification, showing embodiments consistent with the present invention and used together with the specification to explain the principles of the present invention.

[0042] Figure 1 is a flowchart of a control method of a heat pump unit shown according to an exemplary embodiment of the present application.

[0043] Figure 2 is shown according to an exemplary embodiment of the present application Figure 1 in the flowchart of step S101.

[0044] Figure 3 is shown according to an exemplary embodiment of the present application Figure 1 in the flowchart of step S102.

[0045] Figure 4 is shown according to an exemplary embodiment of the present application Figure 1 in the flowchart of step S103.

[0046] Figure 5 is shown according to an exemplary embodiment of the present application Figure 4 in the flowchart of step S103-1.

[0047] Figure 6 is a schematic diagram of using a fractional order proportional-integral-derivative controller to control the opening of an electronic expansion valve according to a set value of the outlet water temperature shown according to an exemplary embodiment of the present application.

[0048] Figure 7 is a flowchart of a control method of a heat pump unit shown according to an exemplary embodiment of the present application.

[0049] Figure 8 It is a block diagram of a control device for a heat pump unit shown according to an exemplary embodiment of the present application.

[0050] Figure 9 It is a block diagram of a computer device shown according to an exemplary embodiment of the present application. Specific embodiments

[0051] Here, the exemplary embodiments will be described in detail, and the examples are shown in the drawings. When the following description refers to the drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present invention. On the contrary, they are merely examples of devices and methods consistent with some aspects of the present invention as detailed in the appended claims.

[0052] During the heating process of the heat pump unit, the heat load is an important basis for adjusting the heat output of the heat pump unit. Currently, it is usually the staff who form a comparison table of outdoor temperature and heat load based on empirical data, or the staff adopt a method of linear ratio and empirical correction to deduce the heat load corresponding to different outdoor temperatures according to the load ratio, and form a comparison table of outdoor temperature and heat load. When predicting the heat load, the staff look up the comparison table and determine the reference heat load parameter for the current day according to the outdoor temperature of the current day. However, in addition to the outdoor temperature, other environmental factors such as outdoor wind speed, solar radiation intensity, and extreme weather such as rainfall and snowfall, as well as factors such as the supply water temperature, return water temperature, and historical heat load inside the heat pump unit will also affect the heat load. The above heat load prediction method ignores these factors, and moreover, the heat load prediction is not a simple linear prediction, and the comparison table deduced by the method of linear ratio and empirical correction is not accurate. Therefore, the reference heat load parameter obtained by the above prediction method is not accurate, which will cause problems such as uneven heat supply, unqualified indoor temperature, and heat waste in the heat pump unit.

[0053] To solve the above technical problems, the present application provides a control method, device, computer device, and storage medium for a heat pump unit. Obtain the first parameter of the heat pump unit, where the first parameter is the historical data of the heat pump unit, and the historical data at least includes the historical heat load parameter of the heat pump unit before the current moment. According to the first parameter, predict the reference heat load parameter of the heat pump unit. According to the reference heat load parameter, adjust the heat output of the heat pump unit. The accuracy of the reference heat load parameter is improved, which can make the heat output of the heat pump unit match the actual heat load, while ensuring the heating effect on the user side, avoiding waste of energy, and reducing the operating cost of the heat pump unit.

[0054] An exemplary embodiment of the present application provides a control method for a heat pump unit, such asFigure 1 As shown, the control method of the heat pump unit shown in this exemplary embodiment includes:

[0055] S101. Obtain the first parameter of the heat pump unit, where the first parameter is the historical data of the heat pump unit, and the historical data at least includes the historical heat load parameter of the heat pump unit before the current moment.

[0056] A heat pump unit is an energy-saving device that absorbs heat from a low-temperature heat source (such as air, water, soil, etc.) by inputting a small amount of electric energy (or other driving energy), raises the temperature, and then releases the heat energy to a high-temperature environment. It can realize functions such as heating, cooling, and domestic hot water supply, and is an efficient and environmentally friendly energy conversion device.

[0057] The heat load refers to the amount of heat that needs to be supplemented per unit time in a certain space or system to maintain the set temperature requirement.

[0058] The historical heat load parameter of the heat pump unit is the heat load set for the heat pump unit in history.

[0059] In some exemplary embodiments, as Figure 2 shown, step S101 includes:

[0060] S101-1. Obtain the historical heat load parameter, the timestamp parameter, the environmental parameter, and the operating parameter of the heat pump unit.

[0061] The reference heat load parameter is updated every preset time interval. The historical heat load parameter includes the reference heat load parameters in the N update cycles before the current moment, where N is a positive integer greater than or equal to 1. The timestamp parameter, the environmental parameter, and the operating parameter of the heat pump unit are collected simultaneously with the historical heat load parameter. The timestamp parameter includes the time information corresponding to the reference heat load parameters in the N update cycles before the current moment. The environmental parameter includes the environmental factors of the operating environment of the heat pump unit in the N update cycles before the current moment. The operating parameter of the heat pump unit includes the operating data of the heat pump unit in the N update cycles before the current moment.

[0062] The reference heat load parameter is updated every preset time interval, and each reference heat load parameter is the heat load set for the heat pump unit in its corresponding update cycle. Obtain the reference heat load parameters in the N update cycles before the current moment. In some examples, the reference heat load parameter is updated every 1 hour, and N is 240. Obtain the historical heat load parameter, that is, obtain 240 reference heat load parameters in the 240 hours before the current moment. In other examples, the preset time interval for updating the reference heat load parameter can be other durations, and N can be other values.

[0063] The timestamp parameter, environmental parameter, and operating parameters of the heat pump unit are collected simultaneously with the historical heat load parameter. It can be understood that the timestamp parameter, environmental parameter, and operating parameters of the heat pump unit each include N groups of data, and the N groups of data correspond one-to-one in time with the reference heat load parameters in the N update cycles before the current moment.

[0064] The timestamp parameter may include time information such as hour, week, month, and whether it is a holiday corresponding to each reference heat load parameter in the N update cycles before the current moment. In some examples, the value of N is 240. In the timestamp parameter, the time information corresponding to the 10th reference heat load parameter is 20:00, Friday, December, non-holiday, and the time information corresponding to the 15th reference heat load parameter is 1:00, Saturday, December, holiday.

[0065] The environmental parameter may include outdoor temperature, humidity, wind speed, solar radiation intensity, and indoor temperature set value of the operating environment of the heat pump unit in the N update cycles before the current moment.

[0066] The operating parameters of the heat pump unit may include compressor speed, inlet and outlet water temperature and flow rate of the evaporator, inlet and outlet water temperature and flow rate of the condenser, expansion valve opening degree, and suction superheat degree in the N update cycles before the current moment. The expansion valve opening degree refers to the opening degree of the throttling channel inside the expansion valve in the heat pump system. The suction superheat degree is the value of the refrigerant vapor temperature at the suction port of the compressor of the heat pump unit being higher than the saturated evaporation temperature at this pressure.

[0067] S101-2: Take the historical heat load parameter, timestamp parameter, environmental parameter, and operating parameters of the heat pump unit as the first parameter.

[0068] It is possible to record the reference heat load parameter, timestamp parameter, environmental parameter, and operating parameters of the heat pump unit in each update cycle, and use the data corresponding to the N update cycles before the current moment to predict the reference heat load parameter at the current moment.

[0069] In some examples, the reference heat load parameter is updated every 1 hour, the value of N is 240, and the set of reference heat load parameters in the 240 update cycles before the current moment, the time information such as hour, week, month, and whether it is a holiday corresponding to each reference heat load parameter, the outdoor temperature, humidity, wind speed, solar radiation intensity, and indoor temperature set value of the operating environment of the heat pump unit in the 240 update cycles before the current moment, and the compressor speed, inlet and outlet water temperature and flow rate of the evaporator, inlet and outlet water temperature and flow rate of the condenser, expansion valve opening degree, and suction superheat degree of the heat pump unit in the 240 update cycles before the current moment are used as the first parameter.

[0070] S102. Predict the reference heat load parameter of the heat pump unit according to the first parameter.

[0071] In some examples, the first parameter includes the reference heat load parameters in the N update cycles before the current moment, the time information such as the hour, week, month, and whether it is a holiday corresponding to each reference heat load parameter, the outdoor temperature, humidity, wind speed, solar radiation intensity of the operating environment of the heat pump unit in the N update cycles before the current moment, the indoor temperature setting value, and the compressor speed, evaporator inlet and outlet water temperature and flow rate, condenser inlet and outlet water temperature and flow rate, expansion valve opening, and suction superheat degree of the heat pump unit in the N update cycles before the current moment. Using the first parameter to predict the reference heat load parameter of the heat pump unit comprehensively considers the influence of external and internal factors of the heat pump unit on the heat load. The predicted reference heat load parameter has high accuracy, can make the heat output by the heat pump unit match the actual heat load, while ensuring the heating effect on the user side, avoiding waste of energy, and reducing the operating cost of the heat pump unit.

[0072] In some exemplary embodiments, such as Figure 3 shown, step S102 includes:

[0073] S102-1. Input the first parameter into a preset heat load prediction model.

[0074] The heat load prediction model is a neural network model built using a long short-term memory network.

[0075] The long short-term memory network (LSTM) is a special recurrent neural network designed to solve the long-term dependence problem (i.e., long-distance information loss) of traditional recurrent neural networks. The LSTM network can selectively remember or forget information by introducing a gating mechanism and a cell state, thus effectively capturing long-term dependence relationships. The cell state of the LSTM network is a memory channel that runs through the entire network, transmitting information like a conveyor belt. Information can be added or deleted through the gating mechanism, making some data valid for a long time. The LSTM network includes three gating structures, namely the forget gate, the input gate, and the output gate. The inflow and outflow of information can be controlled by the three gating structures of the LSTM. The forget gate is used to determine which information to discard from the cell state. The input gate is used to determine which new information to store in the cell state. The output gate is used to control which information of the current cell state is used as the output of the LSTM network structure.

[0076] The heat load prediction model is as follows:

[0077] f t =σ(W f ·[h t-1 ,x t +bf )

[0078] i t = σ(W i · [h t-1 , x t + b i )

[0079]

[0080] o t = σ(W o · [h t-1 , x t + b o )

[0081] h t = o t ⊙ tanh(C t )

[0082] y t = W y · h t + b y ;

[0083] x t is the first parameter at time t, where t is the current time, y t is the reference heat load parameter at time t, h t-1 is the output of the network structure of the heat load prediction model at time t - 1, h t is the output of the network structure of the heat load prediction model at time t, C t-1 is the cell state of the network structure of the heat load prediction model at time t - 1, C t is the cell state of the network structure of the heat load prediction model at time t, f t is the activation value of the forget gate of the heat load prediction model at time t, W f is the weight matrix of the forget gate, b f is the bias of the forget gate, i t is the activation value of the input gate of the heat load prediction model at time t, W i is the weight matrix of the input gate, b i is the bias of the input gate, is the candidate memory of the input gate of the heat load prediction model at time t, W c is the weight matrix of the candidate memory, b c is the bias of the candidate memory, o t is the activation value of the output gate of the heat load prediction model at time t, W o is the weight matrix of the output gate, b o is the bias of the output gate, W yis y t is the weight matrix of, b y is y t is the bias of.

[0084] Use the sigmoid function as the parameter of the activation function, and the value is between 0 and 1. Use the tanh function as the parameter of the activation function, and the value is between -1 and 1.

[0085] Before using the heat load prediction model, a training set composed of multiple samples can be used to train the heat load prediction model, so that the trained heat load prediction model can predict accurate reference heat load parameters according to the first parameter. The reference heat load parameters within an update period can be used as output samples, and the reference heat load parameters in the N update periods before this update period, the time information such as the hour, week, month, and whether it is a holiday corresponding to each reference heat load parameter, the outdoor temperature, humidity, wind speed, solar radiation intensity of the operating environment of the heat pump unit in the N update periods before this update period, the indoor temperature setting value, and the compressor speed, evaporator inlet and outlet water temperature and flow rate, condenser inlet and outlet water temperature and flow rate, expansion valve opening degree, and suction superheat degree of the heat pump unit in the N update periods before this update period can be used as input samples to form a sample pair. In some examples, an update period is one hour and N is 240. In other examples, an update period can be other durations and N can be other values.

[0086] When training the heat load prediction model, network structures and training parameters such as the number of nodes in the input layer, hidden layer, fully connected layer, output layer, initial learning rate, learning rate decay factor, number of iteration rounds, and L2 regularization coefficient can be set. The input layer refers to the number of variables in each input sample. The number of hidden layer nodes refers to the number of neurons in the hidden layer. The number of fully connected layer nodes refers to the number of neurons in the fully connected layer. The number of output layer nodes refers to the number of neurons in the last layer of the neural network. The initial learning rate refers to the step size of the optimizer at the beginning of training. The learning rate decay factor refers to the ratio at which the learning rate decays according to a certain rule during training. The number of iteration times refers to the number of times the entire training set is completely traversed by the model. The L2 regularization coefficient refers to the intensity coefficient of L2 regularization. In some examples, set the input layer to 15, the number of hidden layer nodes to 64, the number of fully connected layer nodes to 1, the number of output layer nodes to 1, the initial learning rate to 0.01, the learning rate decay factor to 0.5, the number of iteration rounds to 500, and the L2 regularization coefficient to 0.001. In other examples, these parameters can also be other values.

[0087] After setting the above network structure and training parameters and training the heat load prediction model using the above training set, the trained heat load prediction model can accurately predict the heat load according to the first parameter.

[0088] When predicting the reference heat load parameter at the current moment, the first parameter is input into the trained heat load prediction model.

[0089] S102-2. Use the output of the heat load prediction model as the reference heat load parameter.

[0090] After inputting the first parameter into the heat load prediction model, use the output of the heat load prediction model as the reference heat load parameter.

[0091] Since the heat load prediction model is built using an LSTM network, introducing a unique gating mechanism and cell state, it can effectively capture long-term dependencies when processing time series data, has good performance in non-linear prediction, and the heat load prediction model has been trained before use and is suitable for predicting heat load. Therefore, the reference heat load parameter predicted by using the heat load prediction model has high accuracy.

[0092] S103. Adjust the heat output of the heat pump unit according to the reference heat load parameter.

[0093] The reference heat load parameter is the predicted heat that needs to be supplemented per unit time in a certain space or system to maintain the set temperature requirement, providing a basis for adjusting the heat output of the heat pump unit. Adjusting the heat output of the heat pump unit according to the reference heat load parameter can match the heat output of the heat pump unit with the actual heat load in real time, achieve supply-demand balance, reduce energy waste while ensuring the heating effect.

[0094] In some exemplary embodiments, as Figure 4 shown, step S103 includes:

[0095] S103-1. Calculate the set value of the outlet water temperature of the condenser of the heat pump unit according to the reference heat load parameter.

[0096] During the operation of the heat pump unit, different heat loads are matched by adjusting the outlet water temperature of its condenser. Therefore, when adjusting the heat output of the heat pump unit according to the reference heat load parameter, first calculate the set value of the outlet water temperature of the condenser of the heat pump unit according to the reference heat load parameter.

[0097] In some exemplary embodiments, as Figure 5 shown, step S103-1 includes:

[0098] S103-1-1. Obtain the condensate flow parameter of the heat pump unit.

[0099] The condensate flow can be measured by a flow meter set on the condensate pipeline. The condensate flow within an update period before the current moment can be obtained as the condensate flow parameter.

[0100] S103-1-2. Calculate the set value of the outlet water temperature based on the reference heat load parameter and the condensate water flow parameter.

[0101] The reference heat load parameter can be divided by the condensate water flow parameter to obtain a first value, and the set value of the outlet water temperature of the condenser of the heat pump unit can be obtained by subtracting the first value from the return water temperature of the condenser of the heat pump unit.

[0102] The return water temperature of the condenser of the heat pump unit can be measured using a temperature sensor installed at the condenser return water pipe. The temperature sensor can be a temperature sensor such as a platinum resistance, a thermocouple, or a digital temperature sensor, and is not limited herein.

[0103] S103-2. Control the opening degree of the electronic expansion valve of the heat pump unit according to the set value of the outlet water temperature to adjust the heat output by the heat pump unit.

[0104] When the opening degree of the electronic expansion valve of the heat pump unit changes, the outlet water temperature of the condenser of the heat pump unit will change. When the opening degree of the electronic expansion valve increases, the flow rate of the condensate water increases accordingly, the condensation pressure rises, and the outlet water temperature of the condenser rises. Conversely, when the opening degree of the electronic expansion valve decreases, the flow rate of the condensate water decreases accordingly, the condensation pressure decreases, and the outlet water temperature of the condenser decreases.

[0105] After calculating the set value of the outlet water temperature of the condenser, control the opening degree of the electronic expansion valve so that the actual outlet water temperature of the condenser meets the set value of the outlet water temperature, so as to adjust the heat output by the heat pump unit and make the heat output by the heat pump unit match the reference heat load parameter.

[0106] In some exemplary embodiments, controlling the opening degree of the electronic expansion valve of the heat pump unit according to the set value of the outlet water temperature includes: using a fractional-order proportional-integral-derivative (PID) controller to control the opening degree of the electronic expansion valve according to the set value of the outlet water temperature.

[0107] Compared with the traditional PID controller, the fractional-order PID controller introduces additional order parameters λ and μ, provides finer dynamic regulation, faster response speed, smaller overshoot, and higher robustness, and is suitable for systems with non-integer order characteristics (such as long memory, hysteresis).

[0108] As Figure 6 shown, in this embodiment, a fractional-order PID controller is used to control the opening degree of the electronic expansion valve according to the set value of the outlet water temperature. K p in the fractional-order PID controller is the proportional gain, K i is the integral gain, K d is the derivative gain, λ is the integral order, μ is the derivative order, and Kp , K i , K d , λ, μ and other parameter settings need to be determined according to the actual situation of the heat pump unit. The input of the fractional-order PID controller is determined according to the set value of the outlet water temperature and the feedback value of the outlet water temperature of the condenser of the heat pump unit. The feedback value of the outlet water temperature can be measured by a temperature sensor installed at the outlet pipe of the condenser. The temperature sensor can be a platinum resistance, a thermocouple, a digital temperature sensor or other temperature sensors, which are not limited here. In some examples, the set value of the outlet water temperature minus the feedback value of the outlet water temperature is used as the input of the fractional-order PID controller. In other examples, other operations can also be performed on the set value of the outlet water temperature and the feedback value of the outlet water temperature as the input of the fractional-order PID controller. The output of the fractional-order PID controller is used to control the opening degree of the electronic expansion valve.

[0109] In this embodiment, the fractional-order PID controller is used to control the opening degree of the electronic expansion valve according to the set value of the outlet water temperature, and it shows superiority in terms of adjustment time and stability.

[0110] In some exemplary embodiments, traditional PID control can also be used to adjust the opening degree of the electronic expansion valve according to the set value of the outlet water temperature.

[0111] In this embodiment, an LSTM network is used to build a heat load prediction model, which is suitable for predicting the heat load. The external factors and internal factors of the heat pump unit that affect the heat load are used as the input of the trained heat load prediction model, comprehensively considering the influence of the external factors and internal factors of the heat pump unit on the heat load, and the accuracy of the predicted reference heat load parameters is high. The fractional-order PID is used to control the heat output of the heat pump unit according to the reference heat load parameters, and it shows superiority in terms of adjustment time and stability, which can make the heat output of the heat pump unit match the actual heat load, while ensuring the heating effect on the user side, avoiding waste of energy, and reducing the operating cost of the heat pump unit.

[0112] An exemplary embodiment of the present application provides a control method for a heat pump unit. As Figure 7 shown, the control method of the heat pump unit shown in this exemplary embodiment includes:

[0113] S701. Obtain historical heat load parameters, timestamp parameters, environmental parameters and operating parameters of the heat pump unit.

[0114] S702. Take the historical heat load parameters, timestamp parameters, environmental parameters and operating parameters of the heat pump unit as the first parameters.

[0115] S703. Input the first parameters into a preset heat load prediction model.

[0116] S704. Use the output of the heat load prediction model as the reference heat load parameter.

[0117] S705. Obtain the condensate water flow parameter of the heat pump unit.

[0118] S706. Calculate the set value of the outlet water temperature according to the reference heat load parameter and the condensate water flow parameter.

[0119] S707. Use a fractional order proportional-integral-derivative controller to control the opening degree of the electronic expansion valve according to the set value of the outlet water temperature, so as to adjust the heat output of the heat pump unit.

[0120] In this embodiment, both the external factors and internal factors of the heat pump unit affecting the heat load are comprehensively considered. The heat load prediction model applicable to heat load prediction is used, and the accuracy of the predicted reference heat load parameter is high. Using the fractional order PID to control the heat output of the heat pump unit based on the reference heat load parameter shows superiority in terms of adjustment time and stability. It can make the heat output of the heat pump unit match the actual heat load, ensuring the heating effect on the user side while avoiding energy waste and reducing the operating cost of the heat pump unit.

[0121] An exemplary embodiment of the present application provides a control device for a heat pump unit, as Figure 8 shown. The control device of the heat pump unit includes a parameter acquisition module 801, a parameter prediction module 802, and a heat adjustment module 803.

[0122] The parameter acquisition module 801 is configured to acquire the first parameter of the heat pump unit. The first parameter is the historical data of the heat pump unit, and the historical data at least includes the historical heat load parameter of the heat pump unit before the current moment.

[0123] The parameter prediction module 802 is configured to predict the reference heat load parameter of the heat pump unit according to the first parameter.

[0124] The heat adjustment module 803 is configured to adjust the heat output of the heat pump unit according to the reference heat load parameter.

[0125] The control device of the heat pump unit in this embodiment improves the accuracy of the reference heat load parameter, can make the heat output of the heat pump unit match the actual heat load, ensuring the heating effect on the user side while avoiding energy waste and reducing the operating cost of the heat pump unit.

[0126] In some exemplary embodiments, the parameter prediction module 802 is further configured to:

[0127] Input the first parameter into a preset heat load prediction model;

[0128] Use the output of the heat load prediction model as the reference heat load parameter.

[0129] In some exemplary embodiments, the heat load prediction model is a neural network model built using a long short-term memory network.

[0130] The heat load prediction model is as follows:

[0131] f t = σ(W f · [h t-1 , x t + b f );

[0132] i t = σ(W i · [h t-1 , x t + b i );

[0133]

[0134] o t = σ(W o · [h t-1 , x t + b o );

[0135] h t = o t ⊙ tanh(C t );

[0136] y t = W y · h t + b y ;

[0137] x t is the first parameter at time t, where time t is the current time, y t is the reference heat load parameter at time t, h t-1 is the output of the network structure of the heat load prediction model at time t - 1, h t is the output of the network structure of the heat load prediction model at time t, C t-1 is the cell state of the network structure of the heat load prediction model at time t - 1, C t is the cell state of the network structure of the heat load prediction model at time t, f t is the activation value of the forget gate of the heat load prediction model at time t, W f is the weight matrix of the forget gate, b f is the bias of the forget gate, i t is the activation value of the input gate of the heat load prediction model at time t, W i is the weight matrix of the input gate, bi is the bias of the input gate, is the candidate memory of the input gate of the heat load prediction model at time t, W c is the weight matrix of the candidate memory, b c is the bias of the candidate memory, o t is the activation value of the output gate of the heat load prediction model at time t, W o is the weight matrix of the output gate, b o is the bias of the output gate, W y is y t 's weight matrix, b y is y t 's bias.

[0138] In some exemplary embodiments, the parameter acquisition module 801 is further configured to:

[0139] Obtain historical heat load parameters, timestamp parameters, environmental parameters, and operating parameters of the heat pump unit. Among them, the reference heat load parameters are updated every preset time interval. The historical heat load parameters include the reference heat load parameters in the N update cycles before the current moment, N is a positive integer greater than or equal to 1. The timestamp parameters, environmental parameters, and operating parameters of the heat pump unit are collected simultaneously with the historical heat load parameters. The timestamp parameters include the time information corresponding to the reference heat load parameters in the N update cycles before the current moment. The environmental parameters include the environmental factors of the operating environment of the heat pump unit in the N update cycles before the current moment. The operating parameters of the heat pump unit include the operating data of the heat pump unit in the N update cycles before the current moment;

[0140] Use the historical heat load parameters, timestamp parameters, environmental parameters, and operating parameters of the heat pump unit as the first parameters.

[0141] In some exemplary embodiments, the heat adjustment module 803 is further configured to:

[0142] Calculate the set value of the outlet water temperature of the condenser of the heat pump unit according to the reference heat load parameter;

[0143] Control the opening degree of the electronic expansion valve of the heat pump unit according to the set value of the outlet water temperature to adjust the heat output by the heat pump unit.

[0144] In some exemplary embodiments, the heat adjustment module 803 is further configured to:

[0145] Obtain the condensate flow rate parameter of the heat pump unit;

[0146] Calculate the set value of the outlet water temperature according to the reference heat load parameter and the condensate flow rate parameter.

[0147] In some exemplary embodiments, the heat adjustment module 803 is further configured to:

[0148] Use a fractional order proportional-integral-derivative controller to control the opening degree of the electronic expansion valve according to the set value of the outlet water temperature.

[0149] Each module in the control device of the above heat pump unit can be implemented in whole or in part by software, hardware, and their combination. Each of the above modules can be embedded in the processor in the computer device in the form of hardware or independent of it, or stored in the memory in the computer device in the form of software, so that the processor can call and execute the operations corresponding to each of the above modules.

[0150] An exemplary embodiment of the present application provides a computer device, including a processor and a memory. The memory stores a computer program, and when the processor executes the computer program, the steps of any of the above control methods of the heat pump unit are implemented.

[0151] An exemplary embodiment of the present application provides a non-transitory computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps of any of the above control methods of the heat pump unit are implemented. The computer-readable storage medium may be ROM, random access memory (RAM), CD-ROM, magnetic tape, floppy disk, and optical data storage device, etc.

[0152] An exemplary embodiment of the present application provides a computer program product, including a computer program. When the computer program is executed by a processor, the steps of any of the above control methods of the heat pump unit are implemented.

[0153] Refer to Figure 9 , and now the structural block diagram of the computer device that can be the computer device of the present application will be described. The computer device includes a computing unit 901, which can execute various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 902 or the computer program loaded from the storage unit 908 into the random access memory (RAM) 903. In the RAM 903, various programs and data required for the operation of the computer device 900 can also be stored. The computing unit 901, ROM 902, and RAM 903 are connected to each other through a bus 904. The input / output (I / O) interface 905 is also connected to the bus 904.

[0154] Multiple components in the computer device 900 are connected to the I / O interface 905, including: an input unit 906, an output unit 907, a storage unit 908, and a communication unit 909. The input unit 906 can be any type of device capable of inputting information into the computer device 900. The input unit 906 can receive input digital or character information, and generate key signal inputs related to the user settings and / or function controls of the computer device 900, and can include, but is not limited to, a mouse, a keyboard, a touch screen, a track pad, a track ball, a joystick, a microphone, and / or a remote control. The output unit 907 can be any type of device capable of presenting information, and can include, but is not limited to, a display, a speaker, a video / audio output terminal, a vibrator, and / or a printer. The storage unit 908 can include, but is not limited to, magnetic disks and optical discs. The communication unit 909 allows the computer device 900 to exchange information / data with other devices via a computer network such as the Internet and / or various telecommunication networks, and can include, but is not limited to, a modem, a network card, an infrared communication device, a wireless communication transceiver, and / or a chipset, such as a BluetoothTM device, a WiFi device, a WiMax device, a cellular communication device, and / or the like.

[0155] The computing unit 901 can be various general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of the computing unit 901 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. The computing unit 901 executes the various methods and processes described above, such as the control method of the heat pump unit. For example, in some embodiments, the control method of the heat pump unit can be implemented as a computer software program, which is tangibly contained in a machine-readable medium, such as the storage unit 908. In some embodiments, part or all of the computer program can be loaded and / or installed onto the computer device 900 via the ROM 902 and / or the communication unit 909. When the computer program is loaded into the RAM 903 and executed by the computing unit 901, one or more steps of the control method of the heat pump unit described above can be executed. Alternatively, in other embodiments, the computing unit 901 can be configured to execute the control method of the heat pump unit by any other suitable means (such as, by means of firmware).

[0156] The computer device 900 can be implemented by one or more application-specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field-programmable gate arrays (FPGAs), controllers, microcontrollers, microprocessors, or other electronic components for executing the above-described control method of the heat pump unit.

[0157] Other embodiments of the present invention will be readily apparent to those skilled in the art upon consideration of the specification and practice of the invention disclosed herein. This application is intended to cover any variations, uses, or adaptations of the invention, which follow the general principles of the invention and include known common knowledge or conventional technical means in the technical field not disclosed in this application. The specification and examples are only to be considered exemplary, and the true scope and spirit of the invention are pointed out by the following claims.

[0158] It should be understood that the present invention is not limited to the exact structures described above and shown in the drawings, and various modifications and changes can be made without departing from its scope. The scope of the present invention is only limited by the appended claims.

Claims

1. A control method for a heat pump unit, characterized in that: include: Acquire a first parameter of the heat pump unit, where the first parameter is historical data of the heat pump unit, and the historical data at least includes a historical heat load parameter of the heat pump unit before a current moment; Predicting a reference heat load parameter of the heat pump unit according to the first parameter; The heat output of the heat pump unit is adjusted according to the reference heat load parameter.

2. The control method of the heat pump unit according to claim 1, characterized in that: The step of predicting a reference heat load parameter of the heat pump unit according to the first parameter includes: inputting the first parameter into a preset heat load prediction model; The output of the heat load prediction model is used as the reference heat load parameter.

3. The control method of the heat pump unit according to claim 2, characterized in that: The heat load prediction model is a neural network model built using a long short-term memory network; The heat load prediction model is as follows: f t =σ(W f ·[h t-1 ,x t ]+b f ); i t =σ(W i ·[h t-1 ,x t ]+b i ); the t =σ(W o ·[h t-1 ,x t ]+b o ); h t =o t ⊙tanh(C t ); y t =W y ·h t +b y ; Among them, x t is the first parameter at time t, where time t is the current time, and y t is the reference heat load parameter at time t, h t-1 is the output of the network structure of the heat load prediction model at time t-1, h t is the output of the network structure of the heat load prediction model at time t, C t-1 is the cell state of the network structure of the heat load prediction model at the time t-1, C t is the cell state of the network structure of the heat load prediction model at time t, f t is the activation value of the forget gate of the heat load prediction model at time t, W f is the weight matrix of the forget gate, b f is the bias of the forget gate, i t is the activation value of the input gate of the heat load prediction model at time t, W i is the weight matrix of the input gate, b i is the bias of the input gate, is the candidate memory of the input gate of the heat load prediction model at time t, W c is the weight matrix of the candidate memory, b c is the bias of the candidate memory, o t is the activation value of the output gate of the heat load prediction model at time t, W o is the weight matrix of the output gate, b o is the bias of the output gate, W y Yes t The weight matrix, b y Yes t The bias.

4. The control method of the heat pump unit according to claim 1, characterized in that: The obtaining of the first parameter of the heat pump unit comprises: Acquire the historical heat load parameters, timestamp parameters, environmental parameters and operating parameters of the heat pump unit, wherein the reference heat load parameters are updated once at intervals of a preset time length, the historical heat load parameters include the reference heat load parameters in N update cycles before the current moment, N is a positive integer greater than or equal to 1, the timestamp parameters, the environmental parameters and the operating parameters of the heat pump unit are collected simultaneously with the historical heat load parameters, the timestamp parameters include the time information corresponding to the reference heat load parameters in the N update cycles before the current moment, the environmental parameters include the environmental factors of the operating environment of the heat pump unit in the N update cycles before the current moment, and the operating parameters of the heat pump unit include the operating data of the heat pump unit in the N update cycles before the current moment; The historical heat load parameter, the timestamp parameter, the environmental parameter and the operating parameter of the heat pump unit are used as the first parameter.

5. The control method of the heat pump unit according to claim 1, characterized in that: The step of adjusting the heat output by the heat pump unit according to the reference heat load parameter comprises: Calculating a water outlet temperature setting value of a condenser of the heat pump unit according to the reference heat load parameter; According to the outlet water temperature setting value, the opening of the electronic expansion valve of the heat pump unit is controlled to adjust the heat output by the heat pump unit.

6. The control method of the heat pump unit according to claim 5, characterized in that: The step of calculating the outlet water temperature setting value of the condenser of the heat pump unit according to the reference heat load parameter comprises: Obtaining a condensing water flow parameter of the heat pump unit; The outlet water temperature setting value is calculated according to the reference heat load parameter and the condensed water flow parameter.

7. The control method of the heat pump unit according to claim 5, characterized in that: The step of controlling the opening of the electronic expansion valve of the heat pump unit according to the outlet water temperature setting value comprises: A fractional-order proportional-integral-differential controller is used to control the opening of the electronic expansion valve according to the outlet water temperature setting value.

8. A control device for a heat pump unit, characterized in that: include: A parameter acquisition module is configured to acquire a first parameter of the heat pump unit, wherein the first parameter is historical data of the heat pump unit, and the historical data at least includes a historical heat load parameter of the heat pump unit before a current moment; a parameter prediction module, configured to predict a reference heat load parameter of the heat pump unit according to the first parameter; The heat adjustment module is configured to adjust the heat output by the heat pump unit according to the reference heat load parameter.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the control method of the heat pump unit according to any one of claims 1 to 7 are implemented.

10. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the control method of the heat pump unit according to any one of claims 1 to 7 are implemented.

Images