A method and system for self-adapting cold storage temperature regulation

Abstract

The present invention provides a method and system for self-adapting the temperature of a cold storage, and relates to the technical field of temperature control. The method comprises: constructing a dynamic coupling model of a cold storage system; obtaining a current cold storage state vector; obtaining cold storage temperature sequence data; predicting the cold storage temperature through a gated circulation unit according to the cold storage temperature sequence data; replacing the cold storage temperature value in the cold storage state vector with the cold storage temperature prediction value, and updating the cold storage state vector; based on the updated cold storage state vector, based on the dynamic coupling model of the cold storage system, with the goal of eliminating the coupling effect and reaching the target cold storage temperature, the cold storage system is self-adaptedly adjusted through a fuzzy control neural network. In the present invention, the fuzzy control neural network can estimate and compensate the dynamic coupling effect between components in the cold storage system in real time, can reduce the error caused by the mutual influence between components, improve the response speed, and improve the control accuracy.

Description

Technical Field

[0001] The present invention relates to the technical field of temperature control, and in particular to a method and system for self-adapting temperature regulation in a cold storage. Background Art

[0002] Cold storage systems play a central role in cold chain transportation. They ensure that fresh food, medicines and other perishable products are kept at an appropriate low temperature during transportation to prevent spoilage and decay. By controlling the temperature, cold storage systems can extend the shelf life of products, keeping them fresh and safe when they reach their final destination.

[0003] The cold storage system is a complex nonlinear model, which makes it very difficult to model the cold storage system. Therefore, when controlling the cold storage system, some control methods that do not require precise modeling of the cold storage system are often used, such as PID control, fuzzy control, etc.

[0004] However, the current control method is still affected by the dynamic coupling between structural components such as the compressor, condenser, evaporator, and expansion valve. When adjusting a parameter, the system may need to go through multiple time steps to stabilize, and the response speed is poor, resulting in limited control accuracy. Summary of the invention

[0005] In order to solve the technical problems in the prior art that the system may be affected by dynamic coupling, may require multiple time steps to stabilize when adjusting a parameter, and perform poorly in response speed, resulting in limited control accuracy, the present invention provides a cold storage temperature adaptive adjustment method and system.

[0006] The technical solution provided by the embodiment of the present invention is as follows:

[0007] First aspect:

[0008] An embodiment of the present invention provides a method for adaptively adjusting the temperature of a cold storage, comprising:

[0009] S1: Construct a dynamic coupling model of the cold storage system;

[0010] S2: Get the current cold storage state vector;

[0011] S3: Get cold storage temperature series data;

[0012] S4: predicting the cold storage temperature through a gated circulation unit according to the cold storage temperature sequence data;

[0013] S5: Use the predicted value of the cold storage temperature to replace the cold storage temperature value in the cold storage state vector, and update the cold storage state vector;

[0014] S6: According to the updated cold storage state vector, based on the dynamic coupling model of the cold storage system, the cold storage system is adaptively adjusted through the fuzzy control neural network with the goal of eliminating the coupling effect and achieving the target cold storage temperature.

[0015] Second aspect:

[0016] An embodiment of the present invention provides a cold storage temperature adaptive adjustment system, comprising:

[0017] processor;

[0018] A memory having computer-readable instructions stored thereon, wherein when the computer-readable instructions are executed by the processor, the method for adaptively adjusting the temperature of a cold storage as described in the first aspect is implemented.

[0019] The third aspect:

[0020] An embodiment of the present invention provides a computer-readable storage medium, on which a computer program is stored. When the program is executed by a processor, the method for adaptively adjusting the temperature of a cold storage as described in the first aspect is implemented.

[0021] The beneficial effects brought about by the technical solution provided by the embodiment of the present invention include at least:

[0022] In the present invention, the fuzzy control neural network can estimate and compensate for the dynamic coupling effects between the components in the cold storage system in real time, reduce the errors caused by the mutual influence between the components, improve the response speed, and improve the control accuracy. At the same time, the neural network has adaptive learning capabilities and can automatically adjust the control parameters according to the real-time status of the system and environmental changes, ensuring that the system can accurately control the temperature under various working conditions. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0024] Figure 1 A schematic diagram of a flow chart of a method for adaptively adjusting the temperature of a cold storage provided by an embodiment of the present invention;

[0025] Figure 2 A schematic diagram of the structure of a cold storage temperature adaptive adjustment system provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0026] The technical solution of the present invention is described below in conjunction with the accompanying drawings.

[0027] In the embodiments of the present invention, words such as "exemplarily" and "for example" are used to indicate examples, illustrations or explanations. Any embodiment or design described as "example" in the present invention should not be interpreted as being more preferred or more advantageous than other embodiments or designs. Specifically, the use of the word "example" is intended to present the concept in a specific way. In addition, in the embodiments of the present invention, the meaning expressed by "and / or" can be both, or it can be either of the two.

[0028] In the embodiments of the present invention, "image" and "picture" can sometimes be used interchangeably. It should be noted that when the difference between them is not emphasized, the meanings they intend to express are the same. "of", "corresponding, relevant" and "corresponding" can sometimes be used interchangeably. It should be noted that when the difference between them is not emphasized, the meanings they intend to express are the same.

[0029] In the embodiments of the present invention, sometimes a subscript such as W1 may be written as a non-subscript such as W1. When the difference is not emphasized, the meanings to be expressed are the same.

[0030] In order to make the technical problems, technical solutions and advantages to be solved by the present invention more clear, a detailed description will be given below with reference to the accompanying drawings and specific embodiments.

[0031] Reference Manual Attached Figure 1 , showing a schematic flow chart of a cold storage temperature adaptive adjustment method provided by an embodiment of the present invention.

[0032] The embodiment of the present invention provides a method for self-adapting the temperature of a cold storage, which can be implemented by a device for self-adapting the temperature of a cold storage, and the device for self-adapting the temperature of a cold storage can be a terminal or a server. The processing flow of the method for self-adapting the temperature of a cold storage can include the following steps:

[0033] S1: Construct a dynamic coupling model of the cold storage system.

[0034] In a possible implementation, the dynamic coupling model of the cold storage system is specifically:

[0035]

[0036] y=h(x)

[0037] x=[h L ,T L ,h z ,T z ,T ri ] T

[0038] u=[f y ,AE ] T

[0039] Among them, x represents the cold storage state vector, h L Indicates the enthalpy of the refrigerant in the condenser tube, T L Indicates the temperature inside the condenser tube, h z Indicates the enthalpy of the refrigerant in the evaporator tube, T z Indicates the temperature inside the evaporator tube, T ri Indicates the cold storage temperature, [] T represents the matrix transpose, represents the rate of change of the cold storage state vector, f(x) represents the dynamic coupling nonlinear function, g(x) represents the input matrix function, u represents the control variable, and f y Indicates the compressor frequency, A E represents the opening of the electronic expansion valve, y represents the output variable, and h(x) represents the output matrix function.

[0040] Optionally, the dynamic coupling nonlinear function is specifically:

[0041]

[0042] Among them, α Li represents the heat transfer coefficient in the condenser tube, A Li Indicates the heat transfer area in the condenser tube, m L Indicates the mass of the refrigerant in the condenser tube, T L Indicates the temperature inside the condenser tube, T z represents the temperature inside the evaporator tube, α Lo A represents the heat transfer coefficient on the air side outside the condenser tube. Lo Represents the heat transfer area on the air side outside the condenser tube, C L Indicates the heat capacity per unit length of the condenser tube wall, L L Indicates the length of the condenser tube, T ro represents the outdoor ambient temperature, α zi represents the heat transfer coefficient in the evaporator tube, A zi Indicates the heat transfer area in the evaporator tube, m z Indicates the mass of refrigerant in the evaporator tube, T zB Indicates the temperature at the evaporator tube inlet, T zL represents the temperature at the outlet of the evaporator tube, α zo represents the heat transfer coefficient outside the evaporator tube, A zo Represents the heat transfer area outside the evaporator tube, C z Indicates the heat capacity per unit length of the evaporator tube wall, L z Indicates the evaporator tube length, T ri represents the cold storage temperature, α rIndicates the heat transfer coefficient of the cold storage, A r Represents the heat transfer area of ​​the cold storage, C r represents the constant pressure specific heat of air, ρ k Indicates the density of the refrigerant at the inlet of the electronic expansion valve, C k Indicates the heat capacity of the electronic expansion valve, V r Indicates the volume of cold storage, C r represents the constant pressure specific heat of air, Q r Indicates the heat load of objects in the cold storage.

[0043] Optionally, the input matrix function is specifically:

[0044]

[0045] Among them, f λ Indicates the throttling coefficient of the electronic expansion valve, V y represents the compressor air volume, s represents the motor speed difference, h z Indicates the enthalpy of the refrigerant in the evaporator tube, V c Indicates the compressor scavenging volume, f Nth represents the isentropic efficiency coefficient, h L represents the enthalpy value of the refrigerant in the condenser tube, p represents the number of motor poles, m L Indicates the mass of the refrigerant in the condenser tube, f mv Denotes the mass flow coefficient, h L Indicates the enthalpy of the refrigerant in the condenser tube, h z Indicates the enthalpy of the refrigerant in the evaporator tube, m z Indicates the mass of refrigerant in the evaporator tubes.

[0046] Optionally, the output matrix function is specifically:

[0047]

[0048] Among them, T ri Indicates the cold storage temperature, T y Indicates the compressor outlet temperature, T zL Indicates the temperature at the evaporator tube outlet.

[0049] In the present invention, the complex coupling relationship between the various parts of the system is accurately described by dynamically coupling nonlinear functions and input matrix functions, so that the cold storage temperature can be predicted and adjusted more accurately and the control accuracy can be improved. The dynamic coupling model can quickly respond to changes in the system state, adjust the control strategy in real time, reduce the response time and adjustment time of the system, and ensure that the cold storage temperature remains within the target range. By accurately controlling the temperature and dynamically adjusting the compressor frequency and the opening of the electronic expansion valve, the operating efficiency of the system can be optimized, energy consumption can be reduced, and operating costs can be reduced.

[0050] It should be noted that in the dynamic coupling control system, the cold storage temperature is not only a member of the input state vector, but also an output. This is because in the control system, the output variable is often fed back to the controller to adjust and optimize the system performance. For example, the cold storage temperature is measured and fed back to the controller so that the controller can adjust the control measures (such as compressor frequency and electronic expansion valve opening) based on the deviation between the actual temperature and the desired temperature. The design of cold storage temperature as input and output reflects the core idea of ​​feedback control in the control system, which realizes precise control and optimization of the system through real-time feedback and adjustment. This is especially important in complex dynamic coupling systems because they require precise control strategies to deal with the nonlinearity, time-varying characteristics and multivariable coupling relationships of the system.

[0051] S2: Get the current cold storage state vector.

[0052] Optionally, the cold storage state vector includes: the enthalpy value of the refrigerant in the condenser tube, the temperature in the condenser tube, the enthalpy value of the refrigerant in the evaporator tube, the temperature in the evaporator tube, and the cold storage temperature.

[0053] S3: Get the cold storage temperature series data.

[0054] Optionally, the temperature series data of the cold storage within 24 hours may be selected.

[0055] S4: According to the cold storage temperature sequence data, the cold storage temperature is predicted through the gated cycle unit.

[0056] Among them, the gated recurrent unit (GRU) is an improved recurrent neural network (RNN) designed specifically for processing sequence data. It can more effectively capture long-term dependencies in time series while avoiding the gradient vanishing and gradient exploding problems in traditional RNNs. GRU controls the flow of information by introducing update gates and reset gates.

[0057] Among them, the attention mechanism enables the model to better focus on important information by assigning different weights to different parts of the input sequence.

[0058] In a possible implementation, S4 specifically includes:

[0059] S401: In the input layer of the gated recurrent unit, the cold storage temperature sequence data is input.

[0060] S402: According to the cold storage temperature sequence data, based on the gated recurrent unit, the hidden state in the cold storage temperature sequence data is extracted:

[0061] z t =σ(W uz T ri,t +W hz ht-1 +b z )

[0062] r t =σ(W ur T ri,t +W hr h t-1 +b r )

[0063] c t =σ(W uc T ri,t +W hc (r t ⊙h t-1 )+b c )

[0064] h t =(1-z t )⊙h t-1 +z t ⊙c t

[0065] Among them, z t represents the output vector of the update gate at time t, σ() represents the activation function, and W uz represents the weight matrix between the input layer and the update gate, T ri,t represents the cold storage temperature at time t, W hz represents the self-connection weight matrix of the update gate between time t and time t-1, h t-1 represents the hidden state vector at time t-1, b z represents the bias term of the update gate, r t represents the output vector of the reset gate at time t, W ur represents the weight matrix between the input layer and the reset gate, W hr represents the self-connection weight matrix between the reset gate at time t and time t-1, b r represents the bias term of the reset gate, c t represents the output vector of the candidate layer at time t, W uc Represents the weight matrix between the input layer and the candidate layer, W hc represents the self-connection weight matrix between the candidate layer at time t and time t-1, b c represents the bias term of the candidate layer, ⊙ represents the element-wise product operation, and h t Represents the hidden state vector at time t.

[0066] It should be noted that GRU can capture long-term dependencies in time series data and extract important patterns implicit in the data, which is very critical for temperature prediction because the temperature of cold storage is affected by many factors and has strong time dependence.

[0067] Furthermore, when predicting the temperature of a cold storage, temperature changes during certain specific time periods (opening and closing the door, putting in new goods, etc.) may have a greater impact on future temperatures. The attention mechanism can automatically adjust the weights so that the model pays more attention to these critical moments.

[0068] S403: Add attention weights to the hidden states at each moment:

[0069] s t =σ(W h h t +b h )

[0070]

[0071] h t '=α t h t

[0072] Among them, s t represents the attention score at time t, σ() represents the activation function, and W h represents the attention weight matrix, h t represents the hidden state vector at time t, b h represents the bias term of the attention layer, α t represents the attention weight at time t, exp() represents an exponential function with a natural constant as the base, T represents the total length of the data, and h t ' represents the hidden state vector after adding the attention weight.

[0073] It should be noted that the attention mechanism can dynamically assign different weights to the hidden state of each time step, so that the model can focus on the most important information for prediction at the current moment and improve the accuracy of the prediction.

[0074] S404: According to the hidden state vector after adding the attention weight, predict the cold storage temperature prediction value at the next moment:

[0075]

[0076] in, represents the predicted value of the cold storage temperature at time t+1, σ() represents the activation function, and W x represents the prediction weight matrix, h t ' represents the hidden state vector after adding the attention weight, b x Represents the bias term of the prediction layer.

[0077] In the present invention, GRU and attention mechanism are used to predict the cold storage temperature, which can not only capture and process the complex dynamic characteristics of the cold storage temperature changes, but also improve the prediction accuracy and the generalization ability of the model, providing strong support for achieving efficient and accurate cold storage temperature control.

[0078] S5: Use the predicted value of the cold storage temperature to replace the cold storage temperature value in the cold storage state vector, and update the cold storage state vector.

[0079] In the present invention, by replacing the cold storage temperature in the state vector with the latest predicted value, the control system can obtain the latest state information in real time, reduce the impact of information lag, and thus respond to temperature changes more quickly and adjust the control strategy in time. Furthermore, using the predicted value for updating can make the controller more adaptive and able to adjust the control parameters in time to cope with the changing operating environment.

[0080] S6: According to the updated cold storage state vector, based on the dynamic coupling model of the cold storage system, the cold storage system is adaptively adjusted through the fuzzy control neural network with the goal of eliminating the coupling effect and achieving the target cold storage temperature.

[0081] In a possible implementation, S6 specifically includes:

[0082] S601: Calculate the deviation between the predicted cold storage temperature value and the target cold storage temperature value and the deviation change:

[0083]

[0084] e c,t =e t -e t-1

[0085] Among them, e t It represents the deviation between the predicted cold storage temperature at time t and the target cold storage temperature. ri,s Indicates the target cold storage temperature value, represents the predicted value of the cold storage temperature at time t, e c,t It represents the deviation between the predicted cold storage temperature value and the target cold storage temperature value at time t, e t-1 It represents the deviation between the predicted cold storage temperature at time t-1 and the target cold storage temperature.

[0086] S602: In the input layer of the fuzzy control neural network, the deviation between the predicted cold storage temperature value and the target cold storage temperature value and the deviation change are input.

[0087] S603: In the fusion layer of the fuzzy control neural network, the deviation between the cold storage temperature prediction value and the target cold storage temperature value and the deviation change are fused:

[0088] E(t)=K e e t +K ec e c,t

[0089] Among them, E(t) represents the fusion deviation at time t, K e represents the bias fusion weight, K ec Represents the deviation change fusion weight.

[0090] It should be noted that by weighted fusion of the deviation and the deviation change through the fusion layer, the current error and the error change trend can be comprehensively considered to make the control more accurate.

[0091] S604: In the hidden layer of the fuzzy control neural network, with the goal of eliminating the coupling effect, the proportional gain coefficient and the integral gain coefficient are adjusted in real time through the proportional neurons and the integral neurons.

[0092] The output of the proportional neuron is specifically:

[0093] y1(t)=K p (t)E(t)

[0094] Among them, y1(t) represents the proportional control output of the proportional neuron at time t, K p (t) represents the proportional gain coefficient at time t, and E(t) represents the fusion deviation at time t.

[0095] The output of the integrating neuron is:

[0096] y2(t)=K i (t)E(t)+y2(t-1)

[0097] Among them, y2(t) represents the integral control output of the integral neuron at time t, K i (t) represents the integral gain coefficient at time t, y2(t-1) represents the output of the integral neuron at time t-1, and E(t) represents the fusion deviation at time t.

[0098] It should be noted that by adjusting the proportional gain coefficient and the integral gain coefficient in real time through the proportional neurons and the integral neurons, it is possible to dynamically respond to changes in the system state, adaptively adjust the control strategy, and avoid control errors caused by fixed parameters.

[0099] S605: In the output layer of the fuzzy control neural network, the proportional control output and the integral control output are integrated to output the total control output:

[0100] Y(t)=w1y1(t)+w2y2(t)

[0101] Among them, Y(t) represents the total control output at time t, w1 represents the weight coefficient between the proportional neuron and the output layer, and w2 represents the weight coefficient between the integral neuron and the output layer.

[0102] S606: Determine the final control variable according to the total control output:

[0103] f y (t) = F y [Y(t)]

[0104] A E (t) = F A [Y(t)]

[0105] Among them, f y (t) represents the compressor frequency at time t, F y [] represents the compressor frequency mapping function, A E (t) represents the opening degree of the electronic expansion valve at time t, F A [] represents the electronic expansion valve opening mapping function.

[0106] In the present invention, the fuzzy control neural network can effectively handle the dynamic coupling effects between the components inside the cold storage system by fusing deviation information, adjusting the gain coefficient and outputting the total control signal, reduce the influence of coupling on the control accuracy, and enable the cold storage system to operate efficiently and stably in a complex and changeable environment, ensuring that the temperature inside the cold storage is always maintained at the optimal state, thereby improving the overall performance and reliability of the system.

[0107] In a possible implementation, the training method of the fuzzy control neural network specifically includes:

[0108] Construct the loss function of the fuzzy control neural network:

[0109]

[0110] Where J represents the loss function, θ represents the network parameters of the fuzzy control neural network, and the network parameters include the deviation fusion weight, the deviation variation fusion weight, the weight coefficient between the proportional neuron and the output layer, the weight coefficient between the integral neuron and the output layer, the compressor frequency mapping function parameters, and the electronic expansion valve opening mapping function parameters, e t It represents the deviation between the predicted cold storage temperature at time t and the target cold storage temperature, t represents time, d t represents the differentiation of time, ‖θ‖ represents the modulo operation of the network parameter θ, and β represents the regularization term coefficient.

[0111] It should be noted that the integral term in the loss function can accurately measure the deviation between the predicted value and the target value of the cold storage temperature. Minimizing this term can directly improve the prediction accuracy of the model, making the actual temperature closer to the target temperature. The regularization term in the loss function can prevent the model from overfitting. By constraining the network parameters, the regularization term can reduce the model's excessive dependence on training data and improve the model's generalization ability and robustness on new data.

[0112] With the goal of minimizing the loss function of the fuzzy control neural network, the optimal network parameters are determined by the gradient descent method:

[0113]

[0114] Among them, θ k+1 represents the network parameters at the k+1th iteration, θ k represents the network parameters at the kth iteration, η represents the learning rate, and ▽ represents the gradient operation.

[0115] In the present invention, by constructing the loss function of the fuzzy control neural network and taking minimizing the loss function as the goal, the optimal network parameters are determined by the gradient descent method, which can significantly improve the prediction accuracy of the model and the control performance of the system, enhance the robustness and stability of the system, simplify the control strategy design process, and provide a more reliable and efficient cold storage temperature control solution. The introduction of the regularization term can also prevent overfitting and improve the generalization ability of the model under different environments. In general, this method enables the cold storage system to operate stably and efficiently under complex and changeable conditions.

[0116] The beneficial effects brought about by the technical solution provided by the embodiment of the present invention include at least:

[0117] In the present invention, the fuzzy control neural network can estimate and compensate for the dynamic coupling effects between the components in the cold storage system in real time, reduce the errors caused by the mutual influence between the components, improve the response speed, and improve the control accuracy. At the same time, the neural network has adaptive learning capabilities and can automatically adjust the control parameters according to the real-time status of the system and environmental changes, ensuring that the system can accurately control the temperature under various working conditions.

[0118] Reference Manual Attached Figure 2 , showing a schematic structural diagram of a cold storage temperature adaptive adjustment system provided by the present invention.

[0119] The present invention also provides a cold storage temperature adaptive adjustment system 20, which is applied to the cold storage temperature adaptive adjustment method described above, and comprises:

[0120] Processor 201;

[0121] The memory 202 stores computer-readable instructions, and when the computer-readable instructions are executed by the processor 201, the method for adaptively adjusting the temperature of a cold storage as described in the method embodiment is implemented.

[0122] The cold storage temperature adaptive adjustment system 20 provided by the present invention can execute the above-mentioned cold storage temperature adaptive adjustment method and achieve the same or similar technical effects. To avoid repetition, the present invention will not go into details.

[0123] The beneficial effects brought about by the technical solution provided by the embodiment of the present invention include at least:

[0124] In the present invention, the fuzzy control neural network can estimate and compensate for the dynamic coupling effects between the components in the cold storage system in real time, reduce the errors caused by the mutual influence between the components, improve the response speed, and improve the control accuracy. At the same time, the neural network has adaptive learning capabilities and can automatically adjust the control parameters according to the real-time status of the system and environmental changes, ensuring that the system can accurately control the temperature under various working conditions.

[0125] It should be understood that the processor in the embodiment of the present invention may be a central processing unit (CPU), and the processor may also be other general-purpose processors, digital signal processors (DSP), application specific integrated circuits (ASIC), field programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.

[0126] It should also be understood that the memory in the embodiments of the present invention may be a volatile memory or a non-volatile memory, or may include both volatile and non-volatile memories. Among them, the non-volatile memory may be a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), or a flash memory. The volatile memory may be a random access memory (RAM), which is used as an external cache. By way of example and not limitation, many forms of random access memory (RAM) are available, such as static RAM (SRAM), dynamic random access memory (DRAM), synchronous DRAM (SDRAM), double data rate synchronous dynamic random access memory (DDR SDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchronous link DRAM (SLDRAM), and direct rambus RAM (DR RAM).

[0127] The above embodiments can be implemented in whole or in part by software, hardware (such as circuits), firmware or any other combination. When implemented by software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the process or function described in the embodiment of the present invention is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from one website, computer, server or data center to another website, computer, server or data center by wired (such as infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server or data center that contains one or more available media sets. The available medium can be a magnetic medium (for example, a floppy disk, a hard disk, a tape), an optical medium (for example, a DVD), or a semiconductor medium. The semiconductor medium can be a solid-state hard disk.

[0128] It should be understood that the term "and / or" in this article is only a description of the association relationship of associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. A and B can be singular or plural. In addition, the character " / " in this article generally indicates that the associated objects before and after are in an "or" relationship, but it may also indicate an "and / or" relationship. Please refer to the context for specific understanding.

[0129] In the present invention, "at least one" means one or more, and "more than one" means two or more. "At least one of the following" or similar expressions refers to any combination of these items, including any combination of single or plural items. For example, at least one of a, b, or c can be represented by: a, b, c, ab, ac, bc, or abc, where a, b, c can be single or multiple.

[0130] It should be understood that in various embodiments of the present invention, the size of the serial numbers of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present invention.

[0131] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.

[0132] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the above-described equipment, devices and units can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0133] In the several embodiments provided by the present invention, it should be understood that the disclosed devices, apparatuses and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another device, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0134] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0135] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0136] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention can be essentially or partly embodied in the form of a software product that contributes to the prior art. The computer software product is stored in a storage medium and includes several instructions for enabling a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods described in various embodiments of the present invention. The aforementioned storage medium includes: various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

[0137] An embodiment of the present invention provides a computer-readable storage medium having a computer program stored thereon, wherein when the program is executed by a processor, the method for adaptively adjusting the temperature of a cold storage as described in the method embodiment is implemented.

[0138] A computer-readable storage medium provided by the present invention can implement the steps and effects of the cold storage temperature adaptive adjustment method of the above method embodiment. To avoid repetition, the present invention will not go into details.

[0139] The beneficial effects brought about by the technical solution provided by the embodiment of the present invention include at least:

[0140] In the present invention, the fuzzy control neural network can estimate and compensate for the dynamic coupling effects between the components in the cold storage system in real time, reduce the errors caused by the mutual influence between the components, improve the response speed, and improve the control accuracy. At the same time, the neural network has adaptive learning capabilities and can automatically adjust the control parameters according to the real-time status of the system and environmental changes, ensuring that the system can accurately control the temperature under various working conditions.

[0141] The above is only a specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art can easily think of changes or substitutions within the technical scope disclosed by the present invention, which should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention should be based on the protection scope of the claims.

[0142] There are a few points to note:

[0143] (1) The drawings of the embodiments of the present invention only relate to the structures related to the embodiments of the present invention, and other structures may refer to the general design.

[0144] (2) For the sake of clarity, in the drawings used to describe the embodiments of the present invention, the thickness of the layers or regions is exaggerated or reduced, that is, these drawings are not drawn according to the actual scale. It is understood that when an element such as a layer, film, region or substrate is referred to as being "on" or "under" another element, the element may be "directly" "on" or "under" the other element or there may be intermediate elements.

[0145] (3) In the absence of conflict, the embodiments of the present invention and the features therein may be combined with each other to obtain new embodiments.

[0146] The above are only specific embodiments of the present invention, but the protection scope of the present invention is not limited thereto. The protection scope of the present invention shall be based on the protection scope of the claims.

Claims

1. A method for adaptively adjusting the temperature of a cold storage, characterized in that: include: S1: Construct a dynamic coupling model of the cold storage system; S2: Get the current cold storage state vector; S3: Get cold storage temperature series data; S4: predicting the cold storage temperature through a gated circulation unit according to the cold storage temperature sequence data; S5: Use the predicted value of the cold storage temperature to replace the cold storage temperature value in the cold storage state vector, and update the cold storage state vector; S6: According to the updated cold storage state vector, based on the dynamic coupling model of the cold storage system, the cold storage system is adaptively adjusted through the fuzzy control neural network with the goal of eliminating the coupling effect and achieving the target cold storage temperature; Among them, the dynamic coupling model of the cold storage system is specifically: y=h(x) x=[h L ,T L ,h z ,T z ,T ri ] T u=[f y ,A E ] T Among them, x represents the cold storage state vector, h L Indicates the enthalpy of the refrigerant in the condenser tube, T L Indicates the temperature inside the condenser tube, h z Indicates the enthalpy of the refrigerant in the evaporator tube, T z Indicates the temperature inside the evaporator tube, T ri Indicates the cold storage temperature, [] T represents the matrix transpose, represents the rate of change of the cold storage state vector, f(x) represents the dynamic coupling nonlinear function, g(x) represents the input matrix function, u represents the control variable, and f y Indicates the compressor frequency, A E represents the opening of the electronic expansion valve, y represents the output variable, and h(x) represents the output matrix function; Among them, S4 specifically includes: S401: In the input layer of the gated cycle unit, the cold storage temperature sequence data is input; S402: According to the cold storage temperature sequence data, based on the gated recurrent unit, extract the hidden state in the cold storage temperature sequence data: z t =σ(W uz T ri,t +W hz h t-1 +b z ) r t =σ(W ur T ri,t +W hr h t-1 +b r ) c t =σ(W uc T ri,t +W hc (r t ⊙h t-1 )+b c ) h t =(1-z t )⊙h t-1 +z t ⊙c t Among them, z t represents the output vector of the update gate at time t, σ() represents the activation function, and W uz represents the weight matrix between the input layer and the update gate, T ri,t represents the cold storage temperature at time t, W hz represents the self-connection weight matrix of the update gate between time t and time t-1, h t-1 represents the hidden state vector at time t-1, b z represents the bias term of the update gate, r t represents the output vector of the reset gate at time t, W ur represents the weight matrix between the input layer and the reset gate, W hr represents the self-connection weight matrix between the reset gate at time t and time t-1, b r represents the bias term of the reset gate, c t represents the output vector of the candidate layer at time t, W uc Represents the weight matrix between the input layer and the candidate layer, W hc represents the self-connection weight matrix between the candidate layer at time t and time t-1, b c represents the bias term of the candidate layer, ⊙ represents the element-wise product operation, and h t Represents the hidden state vector at time t; S403: Add attention weights to the hidden states at each moment: s t =σ(W h h t +b h ) h t '=a t h t Among them, s t represents the attention score at time t, σ() represents the activation function, and W h represents the attention weight matrix, h t represents the hidden state vector at time t, b h represents the bias term of the attention layer, α t represents the attention weight at time t, exp() represents an exponential function with a natural constant as the base, T represents the total length of the data, and h t ' represents the hidden state vector after adding the attention weight; S404: According to the hidden state vector after adding the attention weight, predict the cold storage temperature prediction value at the next moment: in, represents the predicted value of the cold storage temperature at time t+1, σ() represents the activation function, and W x represents the prediction weight matrix, h t ' represents the hidden state vector after adding the attention weight, b x Represents the bias term of the prediction layer.

2. The method for self-adapting cold storage temperature according to claim 1, characterized in that: The dynamic coupling nonlinear function is specifically: Among them, α Li represents the heat transfer coefficient in the condenser tube, A Li Indicates the heat transfer area in the condenser tube, m L Indicates the mass of the refrigerant in the condenser tube, T L Indicates the temperature inside the condenser tube, T z represents the temperature inside the evaporator tube, α Lo A represents the heat transfer coefficient on the air side outside the condenser tube. Lo Represents the heat transfer area on the air side outside the condenser tube, C L Indicates the heat capacity per unit length of the condenser tube wall, L L Indicates the length of the condenser tube, T ro represents the outdoor ambient temperature, α zi represents the heat transfer coefficient in the evaporator tube, A zi Indicates the heat transfer area in the evaporator tube, m z Indicates the mass of refrigerant in the evaporator tube, T zB Indicates the temperature at the evaporator tube inlet, T zL represents the temperature at the outlet of the evaporator tube, α zo represents the heat transfer coefficient outside the evaporator tube, A zo Represents the heat transfer area outside the evaporator tube, C z Indicates the heat capacity per unit length of the evaporator tube wall, L z Indicates the evaporator tube length, T ri represents the cold storage temperature, α r Indicates the heat transfer coefficient of the cold storage, A r Represents the heat transfer area of ​​the cold storage, C r represents the constant pressure specific heat of air, ρ k Indicates the density of the refrigerant at the inlet of the electronic expansion valve, C k Indicates the heat capacity of the electronic expansion valve, V r Indicates the volume of cold storage, C r represents the constant pressure specific heat of air, Q r Indicates the heat load of objects in the cold storage.

3. The method for self-adapting the temperature of a cold storage according to claim 2, characterized in that: The input matrix function is specifically: Among them, f λ Indicates the throttling coefficient of the electronic expansion valve, V y represents the compressor air volume, s represents the motor speed difference, h z Indicates the enthalpy of the refrigerant in the evaporator tube, V c Indicates the compressor scavenging volume, f Nth represents the isentropic efficiency coefficient, h L represents the enthalpy value of the refrigerant in the condenser tube, p represents the number of motor poles, m L Indicates the mass of the refrigerant in the condenser tube, f mv Denotes the mass flow coefficient, h L Indicates the enthalpy of the refrigerant in the condenser tube, h z Indicates the enthalpy of the refrigerant in the evaporator tube, m z Indicates the mass of refrigerant in the evaporator tubes.

4. The method for self-adapting cold storage temperature according to claim 3, characterized in that: The output matrix function is specifically: Among them, T ri Indicates the cold storage temperature, T y Indicates the compressor outlet temperature, T zL Indicates the temperature at the evaporator tube outlet.

5. The method for self-adapting cold storage temperature according to claim 1, characterized in that: The S6 specifically includes: S601: Calculate the deviation between the predicted cold storage temperature value and the target cold storage temperature value and the deviation change: And c,t =and t -And t-1 Among them, e t It represents the deviation between the predicted cold storage temperature at time t and the target cold storage temperature. ri,s Indicates the target cold storage temperature value, represents the predicted value of the cold storage temperature at time t, e c,t It represents the deviation between the predicted cold storage temperature value and the target cold storage temperature value at time t, e t-1 It represents the deviation between the predicted cold storage temperature at time t-1 and the target cold storage temperature; S602: In the input layer of the fuzzy control neural network, the deviation between the predicted value of the cold storage temperature and the target cold storage temperature value and the deviation change are input; S603: In the fusion layer of the fuzzy control neural network, the deviation between the cold storage temperature prediction value and the target cold storage temperature value and the deviation change are fused: E(t)=K e e t +K ec e c,t Among them, E(t) represents the fusion deviation at time t, K e represents the bias fusion weight, K ec Indicates the fusion weight of the deviation change; S604: In the hidden layer of the fuzzy control neural network, with the goal of eliminating the coupling effect, the proportional gain coefficient and the integral gain coefficient are adjusted in real time through the proportional neurons and the integral neurons; The output of the proportional neuron is specifically: y1(t)=K p (t)E(t) Among them, y1(t) represents the proportional control output of the proportional neuron at time t, K p (t) represents the proportional gain coefficient at time t, and E(t) represents the fusion deviation at time t; The output of the integrating neuron is specifically: y2(t)=K i (t)E(t)+y2(t-1) Among them, y2(t) represents the integral control output of the integral neuron at time t, K i (t) represents the integral gain coefficient at time t, y2(t-1) represents the output of the integral neuron at time t-1, and E(t) represents the fusion deviation at time t; S605: In the output layer of the fuzzy control neural network, the proportional control output and the integral control output are integrated to output the total control output: Y(t)=w1y1(t)+w2y2(t) Among them, Y(t) represents the total control output at time t, w1 represents the weight coefficient between the proportional neuron and the output layer, and w2 represents the weight coefficient between the integral neuron and the output layer; S606: Determine the final control variable according to the total control output: f y (t)=F y [Y(t)] A E (t)=F A [Y(t)] Among them, f y (t) represents the compressor frequency at time t, F y [] represents the compressor frequency mapping function, A E (t) represents the opening degree of the electronic expansion valve at time t, F A [] represents the electronic expansion valve opening mapping function.

6. The method for self-adapting cold storage temperature according to claim 5, characterized in that: The training method of the fuzzy control neural network specifically includes: Construct the loss function of the fuzzy control neural network: Where J represents the loss function, θ represents the network parameters of the fuzzy control neural network, and the network parameters include the deviation fusion weight, the deviation variation fusion weight, the weight coefficient between the proportional neuron and the output layer, the weight coefficient between the integral neuron and the output layer, the compressor frequency mapping function parameters, and the electronic expansion valve opening mapping function parameters, e t It represents the deviation between the predicted cold storage temperature at time t and the target cold storage temperature, t represents time, d t represents the differentiation of time, ||θ|| represents the modulus operation of the network parameter θ, and β represents the regularization term coefficient; With the goal of minimizing the loss function of the fuzzy control neural network, the optimal network parameters are determined by the gradient descent method.

7. A cold storage temperature adaptive adjustment system, characterized in that: include: processor; A memory having computer-readable instructions stored thereon, wherein when the computer-readable instructions are executed by the processor, the method for adaptively adjusting the temperature of a cold storage as claimed in any one of claims 1 to 6 is implemented.

Images