An intelligent cooling supply control method for a cold storage based on phase change cold accumulation

Abstract

The present application relates to the technical field of intelligent control, in particular to a cold storage intelligent cooling control method based on phase change cold storage. A plurality of sensors collect equipment operation data in real time and store the data in a terminal equipment control unit. Through an equipment interface unit, the terminal equipment control unit and a central control unit establish a data transmission channel and synchronously operate data. After receiving the data, the central control unit executes a program module to analyze the data: first, a multi-dimensional information prediction module is used to predict load, phase change state and energy consumption; then, the program uses a multi-objective rolling time domain dynamic optimization strategy to generate optimal control instructions according to the prediction results, and integrates a fuzzy logic-based adaptive controller to adjust instruction parameters in real time; finally, the adjusted control instructions are transmitted to the terminal equipment control unit via the equipment interface unit to realize program control of the equipment operation state or operation parameters.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of intelligent control, in particular to a cold storage intelligent cooling control method based on phase change cold storage. BACKGROUND

[0002] The current industrial control system has limitations in modeling the nonlinearity of cold storage cooling control. The existing technology cannot handle the non-linear thermal property changes using the preset PID algorithm. Secondly, the existing program control architecture is not suitable for complex production scenarios, especially when dealing with different mode switching. It lacks a self-learning optimization algorithm based on real-time data, making it difficult to achieve dynamic parameter correction and intelligent matching of device operation modes. In addition, the existing PLC program control architecture lacks a feedforward compensation mechanism, which cannot adjust the control strategy in advance based on external disturbance prediction information, resulting in system response lag and reduced temperature control accuracy. SUMMARY

[0003] The present application aims to provide a cold storage intelligent cooling control method based on phase change cold storage. Multiple sensors collect real-time device operation data and store it in the terminal device control unit. Through the device interface unit, the terminal device control unit establishes a data transmission channel with the central control unit and synchronizes the operation data. After receiving the data, the central control unit executes the program module for data analysis. First, the multi-dimensional information prediction module predicts the load, phase change state, and energy consumption. Then, the program uses a multi-objective rolling time domain dynamic optimization strategy to generate optimal control instructions based on the prediction results and integrates an adaptive controller based on fuzzy logic to adjust the instruction parameters in real time. Finally, the adjusted control instructions are transmitted to the terminal device control unit via the device interface unit to achieve program control of the device operation state or operation parameters.

[0004] To achieve the above-mentioned purpose, the present application provides the following technical solutions:

[0005] A cold storage intelligent cooling control method based on phase change cold storage, comprising:

[0006] Real-time collection of device operation data by multiple sensors and storage of the data in the corresponding memory of the terminal device control unit;

[0007] Establishing a data transmission channel between the terminal device control unit and the central control unit using the device interface unit, communicating the relevant device operation data stored in the terminal device control unit memory with the central control unit in real time, and transmitting the device operation data and output control instruction signals through the device interface unit;

[0008] The central control unit receives the equipment operation data for processing and control optimization, and outputs control instruction signals to the terminal equipment control unit through the equipment interface unit. The process of the central control unit processing the equipment operation data includes: using a multi-dimensional information prediction module to process the equipment operation data to obtain load prediction, phase change state prediction information and energy consumption prediction information; based on the prediction information, a multi-objective rolling time domain dynamic optimization strategy is used to generate optimal control instructions; a fuzzy logic-based adaptive controller is introduced to adjust the optimal control instructions in real time.

[0009] The terminal equipment control unit controls the operating state or adjusts the operating parameters of the terminal equipment according to the control instruction signals of the central control unit.

[0010] Further, the equipment operation data includes: equipment operation environment data, equipment operation state data, energy consumption data and equipment operation data.

[0011] Further, the process of the central control unit using the multi-dimensional information prediction module to process the equipment operation data to obtain the load prediction, the phase change state prediction information and the energy consumption prediction information includes:

[0012] The central control unit obtains the equipment operation data through the data transmission channel established by the equipment interface unit;

[0013] The equipment operation data is preprocessed to obtain prediction demand data information;

[0014] The multi-dimensional information prediction module is processed using historical equipment operation data to obtain a pre-training module;

[0015] The first prediction demand information, the second prediction demand information and the third prediction demand information in the prediction demand data information are input to the pre-training module in parallel to obtain the load prediction, the phase change state prediction information and the energy consumption prediction information, respectively;

[0016] The memory of the central control unit is used to store the numerical prediction information, so as to execute the optimization control strategy based on the prediction information subsequently.

[0017] Further, the process of the central control unit generating the optimal control instructions based on the prediction information using the multi-objective rolling time domain dynamic optimization strategy includes:

[0018] The prediction information is extracted from the memory of the central control unit;

[0019] The cooling control problem based on phase change cold storage is modeled as a multi-objective constrained optimization problem, and the objective function, constraint condition and optimization scheme for solving are determined;

[0020] determining a prediction horizon, a control horizon and a control period of the rolling horizon optimization;

[0021] at the start of each control period, based on the prediction information and the equipment operation data, the central control unit solves the objective function in combination with the optimization scheme, thereby generating an optimal control instruction sequence; only the optimal control instruction corresponding to the current control period in the sequence is executed, then the equipment operation data is updated, the next control period is entered, and the optimization solving process is repeated based on the updated equipment operation data and updated prediction information, to realize rolling update and execution of the control instruction.

[0022] Further, the process of real-time adjustment of the optimal control instruction by the fuzzy logic-based adaptive controller comprises:

[0023] fuzzy processing of the real-time collected sensor data, and converting the sensor data into a fuzzy set group;

[0024] fuzzy inference according to the fuzzy set group and a fuzzy rule base, to obtain a fuzzy output;

[0025] de-fuzzy processing of the fuzzy output, to obtain a control instruction adjustment amount;

[0026] adjusting the optimal control instruction obtained by the multi-objective rolling horizon dynamic optimization strategy by using the control instruction adjustment amount, to obtain a final control instruction, and sending the final control instruction to the terminal equipment control unit by the central control unit.

[0027] Further, the operation state comprises an equipment start-stop state and an equipment working mode state; and the operation parameter comprises an equipment operation temperature, an equipment operation frequency, an equipment operation rate, an equipment operation speed, an equipment operation flow and an equipment operation power.

[0028] Compared with the prior art, the present application has the following beneficial effects:

[0029] 1. The present application proposes a multi-dimensional information prediction module, which obtains equipment operation data from a terminal equipment control unit for predicting information in different dimensions; not only relying on a training process of historical data, but also through fusion of multi-dimensional equipment data, for predicting future cold load state, PCM state and energy consumption state; the module provides accurate state prediction results for subsequent dynamic control optimization, and is the basis and premise for realizing forward-looking and fine program control decision.

[0030] 2. The application proposes a multi-objective rolling time domain dynamic optimization strategy user-generated optimal control instruction; the optimization strategy models the phase change cold storage control problem as a multi-objective constrained optimization problem, combines the multi-objective function model and the prediction results of the multi-dimensional information prediction module, can consider both the regular factors of the equipment and the factors affecting the nonlinear characteristics of the phase change cold storage into the control optimization process, thereby ensuring the feasibility and safety of the program control strategy.

[0031] 3. The application proposes an adaptive control adjustment method for adaptive adjustment of control instructions; the method uses a fuzzy logic controller to adjust online by real-time monitoring of operation data and combining a rule base, effectively compensates for prediction errors and suppresses external disturbances, and ensures stable operation of the control strategy; the method can respond more quickly and more finely to small changes in actual parameters through real-time fine tuning of fuzzy logic, further reduces the parameter fluctuation amplitude, and realizes high-precision program control. BRIEF DESCRIPTION OF DRAWINGS

[0032] Fig. 1 is a flowchart of the intelligent cold storage control method based on phase change cold storage of the application;

[0033] Fig. 2 is a structural diagram of the multi-dimensional information prediction module of the application;

[0034] Fig. 3 is a flowchart of the optimal control instruction generation of the application. DETAILED DESCRIPTION

[0035] The technical solutions in the embodiments of the application will be described clearly and completely below with reference to the drawings in the embodiments of the application. Obviously, the described embodiments are only part of the embodiments of the application, not all. Based on the embodiments in the application, all other embodiments obtained by those skilled in the art without creative labor are within the scope of protection of the application.

[0036] The current automated stereoscopic warehouse intelligent control system has limitations in accurate modeling and control of nonlinear characteristics. The existing technology cannot handle nonlinear thermal property changes using the preset PID algorithm. Secondly, the existing program control architecture lacks adaptability to complex production scenarios, especially when switching between different modes. It lacks a self-learning optimization algorithm based on real-time data, making it difficult to achieve dynamic parameter correction and intelligent matching of device operation modes. In addition, the existing PLC program control architecture lacks a feedforward compensation mechanism, which cannot adjust the control strategy in advance based on external disturbance prediction information, resulting in system response lag and reduced temperature control accuracy.

[0037] Please refer to Figs. 1 to 3The application provides a cold storage intelligent cooling control method based on phase change cold storage, and the technical scheme is as follows:

[0038] Embodiment one:

[0039] In order to improve the effectiveness and reliability of the cooling control strategy, an enterprise uses a cold storage intelligent cooling control method based on phase change cold storage provided by the application, which combines a terminal device control unit, a device interface unit, a central control unit and the terminal device control unit in the control system, and the process is as shown in Fig. 1 The specific steps are as follows:

[0040] Real-time equipment operation data is collected by multiple sensors and stored in the corresponding memory of the terminal device control unit;

[0041] Further, the equipment operation data includes equipment operation environment data, equipment operation state data, energy consumption data and equipment operation data.

[0042] Further, the equipment operation environment data includes indoor and outdoor environment data, and the environment data includes temperature and humidity.

[0043] Further, the equipment operation state data includes phase change material (PCM) parameter data and refrigeration equipment parameter data; the PCM parameter data includes thermal physical parameters (phase change temperature, phase change latent heat, specific heat capacity, density, etc.), cold storage capacity and state of charge (SoC) of the PCM; and the refrigeration equipment parameter data includes condensing temperature, refrigeration capacity, refrigerant flow, fan speed, heat exchange rate, charging / discharging rate, etc.

[0044] Further, the energy consumption data includes equipment power data and electricity price data.

[0045] Further, the equipment operation data includes in-out warehouse cargo data, warehouse door opening frequency, equipment maintenance log, etc.

[0046] Using multi-dimensional equipment operation data can provide reliable data sources for subsequent multi-task prediction, multi-target optimization and adaptive adjustment operations, thereby ensuring the effectiveness of intelligent cooling program control.

[0047] The device interface unit is used to establish a data transmission channel between the terminal device control unit and the central control unit, to communicate the relevant equipment operation data stored in the terminal device control unit memory with the central control unit in real time, and to transmit the equipment operation data and output control instruction signals through the device interface unit.

[0048] The central control unit receives the equipment operation data for processing and control optimization, and outputs control instruction signals to the terminal equipment control unit through the equipment interface unit; the process of the central control unit processing the equipment operation data includes: using a multi-dimensional information prediction module to process the equipment operation data to obtain load prediction, phase change state prediction information and energy consumption prediction information; based on the prediction information, a multi-objective rolling time domain dynamic optimization strategy is used to generate optimal control instructions; a fuzzy logic-based adaptive controller is introduced to adjust the optimal control instructions in real time;

[0049] Further, the process of the central control unit using a multi-dimensional information prediction module to process the equipment operation data to obtain load prediction, phase change state prediction information and energy consumption prediction information includes:

[0050] The central control unit obtains the equipment operation data through the data transmission channel established by the equipment interface unit;

[0051] The equipment operation data is preprocessed to obtain prediction demand data information;

[0052] The multi-dimensional information prediction module is processed using historical equipment operation data to obtain a pre-training module;

[0053] The first prediction demand information, the second prediction demand information and the third prediction demand information in the prediction demand data information are input in parallel to the pre-training module to obtain load prediction, phase change state prediction information and energy consumption prediction information, respectively;

[0054] The memory of the central control unit is used to store the numerical prediction information, so that the subsequent optimization control strategy can be executed based on the prediction information;

[0055] Further, the preprocessing of the equipment operation data includes data alignment, data cleaning, data normalization and data classification;

[0056] Further, the data classification is divided according to three different prediction input demands in the multi-dimensional information prediction module to obtain the first prediction demand information, the second prediction demand information and the third prediction demand information; for example: the second prediction demand information is mainly used for predicting the phase change material state, so the second prediction demand information contains PCM parameter data and environmental data;

[0057] Further, there may be a preprocessed data for multiple prediction tasks, i.e. the first prediction demand information, the second prediction demand information and the third prediction demand information have the same data; for example: the environmental data will be used as the input of load prediction, phase change state prediction and energy consumption prediction, i.e. the first prediction demand information, the second prediction demand information and the third prediction demand information all contain environmental data;

[0058] Further, the historical equipment operation data is obtained by calling the equipment management platform;

[0059] Further, the structure of the multi-dimensional information prediction module is as shown in Fig. 2 , and includes an input layer, a multi-dimensional feature extraction layer, a parallel multi-task prediction layer, and an output layer.

[0060] The input layer and the multi-dimensional feature extraction layer are used to receive multi-dimensional prediction demand information and convert it into feature representations, which are first prediction demand feature representations, second prediction demand feature representations, and third prediction demand feature representations, respectively.

[0061] The multi-dimensional feature extraction layer is used to input the first prediction demand feature representations, the second prediction demand feature representations, and the third prediction demand feature representations into a load prediction unit, a phase change state prediction unit, and an energy consumption prediction unit, respectively, to obtain load prediction features, phase change state prediction features, and energy consumption prediction features.

[0062] Further, the prediction output of each unit is used as the input of the subsequent unit, for example, the prediction result of the load prediction unit is used as the input of the phase change state prediction unit and the energy consumption prediction unit, i.e., the load prediction features obtained by the load prediction unit need to be combined with the second prediction demand feature representations and input into the phase change state prediction unit together to obtain the phase change state prediction result.

[0063] The prediction scheme adopted in this embodiment is because the load is a key influencing factor of the PCM state and the energy consumption state, and the cold load and the PCM state can jointly affect the prediction of energy consumption. The prediction scheme proposed in the present application can improve the prediction accuracy.

[0064] The output layer uses a fully connected layer and an activation function to convert the load prediction features, the phase change state prediction features, and the energy consumption prediction features into load prediction, phase change state prediction information, and energy consumption prediction information, respectively.

[0065] Further, the load prediction unit, the phase change state prediction unit, and the energy consumption prediction unit use LSTM, CNN, and Transformer structures for prediction, respectively.

[0066] By using historical equipment operation data for training and combining multi-dimensional equipment data, the future cold load state, PCM state, and energy consumption state can be predicted. This can provide accurate state prediction results for subsequent dynamic program control optimization and is the basis and premise for realizing forward-looking and fine program control decisions.

[0067] Further, the central control unit generates optimal control instructions based on the prediction information using a multi-objective rolling time domain dynamic optimization strategy, and the process is as shown in Fig. 3 , and is as follows:

[0068] extracting prediction information from the memory of the central control unit;

[0069] modeling the cold supply control problem based on phase change cold storage as a multi-objective constrained optimization problem, determining the objective function, the constraint condition and the optimization scheme for solving;

[0070] determining the prediction horizon, the control horizon and the control period of the rolling horizon optimization;

[0071] In the embodiment, the prediction horizon, the control horizon and the control period are set to 24 hours, 6 hours and 1 hour respectively.

[0072] At the start of each control period, based on the prediction information and the equipment operation data, the central control unit combines the optimization scheme to solve the objective function, thereby generating the optimal control instruction sequence; only the optimal control instruction corresponding to the current control period in the sequence is executed, and then the equipment operation data is updated, entering the next control period, and based on the updated equipment operation data and the updated prediction information, the optimization solving process is repeatedly executed to realize the rolling update and execution of the control instruction;

[0073] Further, the objective function can be expressed as:

[0074]

[0075] wherein J represents the objective function; H c represents the control horizon; ω1 represents the cost weight factor; P ele (t+k) represents the electricity price at t+k moment; t and k represent the current time step and the future time step index respectively; P ch (t+k) represents the refrigeration equipment power at t+k moment; Δt represents the control period; ω2 represents the temperature weight factor; T in (t+k+1) represents the indoor temperature at t+k+1 moment; T set represents the indoor temperature set value;

[0076] Further, the indoor temperature at t+k+1 moment can be obtained by the following state transition equation, and the state transition equation is expressed as:

[0077]

[0078] wherein T in (t+k) represents the indoor temperature at t+k moment; mc p represents the heat capacity coefficient; Q ch (t+k) represents the refrigeration capacity at t+k moment; Q pc (t+k) represents the exchange heat rate at t+k moment; Q load(t+k+1) represents the load prediction information at t+k+1; T out (t+k) represents the outdoor temperature at t+k;

[0079] Further, the constraints include: the indoor temperature control range, the PCM state of charge range, the refrigeration equipment power range and the heat exchange rate range; the definition of these parameter ranges can be flexibly adjusted according to actual needs.

[0080] By modeling the phase change cold storage control problem as a multi-objective constrained optimization problem, combining the multi-objective function model and the prediction results of the multi-dimensional information prediction module, both the conventional factors of the equipment and the factors affecting the nonlinear characteristics of the phase change cold storage are considered in the program control optimization process, thereby ensuring the feasibility and safety of the program control strategy.

[0081] Further, the process of real-time adjustment of the optimal control instruction by the fuzzy logic-based adaptive controller includes:

[0082] The real-time collected sensor data is fuzzified and converted into a fuzzy set group;

[0083] Further, the sensor data includes environmental sensor data, PCM state sensor data and equipment state sensor data, etc.

[0084] Further, the fuzzification process includes: determining the input variables of the fuzzy controller and preprocessing; defining a set of fuzzy sets for each input variable, each fuzzy set representing a different degree of description of the variable; substituting the preprocessed input value into the membership function of each fuzzy set, calculating the membership degree of the value to each fuzzy set, and constructing a complete fuzzy set group from the fuzzy sets containing the corresponding membership degrees.

[0085] According to the fuzzy set group and the fuzzy rule base, fuzzy reasoning is performed to obtain a fuzzy output;

[0086] Further, the fuzzy reasoning adopts the Mamdani method, which calculates the fuzzy output by combining the fuzzy rule and the fuzzy set group.

[0087] The fuzzy output is de-fuzzified to obtain a control instruction adjustment amount;

[0088] Further, the de-fuzzification method can adopt the barycenter method or the maximum mean method.

[0089] The optimal control instruction obtained by the multi-objective rolling horizon dynamic optimization strategy is adjusted by the control instruction adjustment amount to obtain a final control instruction, which is sent to the terminal equipment control unit by the central control unit.

[0090] By using the fuzzy logic controller, the running data are monitored in real time, and the online adjustment is combined with the rule base, so that the prediction error is effectively compensated and the external disturbance is inhibited, and the stable operation of the control strategy is ensured; through the real-time fine adjustment of the fuzzy logic, the small changes of the actual parameters can be responded faster and more finely, the parameter fluctuation range is further reduced, and high-precision program control is realized.

[0091] The terminal equipment control unit controls the running state or the running parameter of the terminal equipment according to the control instruction signal of the central control unit.

[0092] Further, the running state includes the start-stop state and the working mode state of the equipment, and the running parameter includes the running temperature, the running frequency, the running speed, the running speed, the running flow and the running power of the equipment.

[0093] The embodiment proposes an intelligent cold supply control method for a cold storage based on phase change cold storage; the running data of the equipment are collected in real time by a plurality of sensors and stored in a terminal equipment control unit. The terminal equipment control unit and the central control unit establish a data transmission channel through a device interface unit, and the running data are synchronized. After receiving the data, the central control unit executes a program module to analyze the data: first, the load, the phase change state and the energy consumption are predicted through a multi-dimensional information prediction module; then, the program generates optimal control instructions according to the prediction results by using a multi-objective rolling time domain dynamic optimization strategy, and integrates an adaptive controller based on fuzzy logic to adjust the instruction parameters in real time; finally, the adjusted control instructions are transmitted to the terminal equipment control unit through the device interface unit, so that the program control of the running state or the running parameter of the equipment is realized. The method can effectively improve the precision and reliability of the control strategy.

[0094] Embodiment two:

[0095] The application proposes an intelligent cold supply control method for a cold storage based on phase change cold storage. In order to further verify the effectiveness of the method proposed in the application in the multi-dimensional information prediction module and the overall control scheme, the application selects two enterprises A and B to test the effectiveness of the multi-dimensional information prediction module and the overall control scheme.

[0096] The application collects the historical equipment running data of enterprise A in the past year as the test data for the effectiveness test of the multi-dimensional information prediction module, and divides the data into data one, data two and data three, and each group of data is different; the historical data of enterprise A in the past 2-3 years are selected as the training data of the multi-dimensional information prediction module; the sampling of the data set is based on the following rules: 5 days of data are randomly selected every week; 2 groups of data are selected every day in the morning, at noon and in the evening.

[0097] The test data of each group is respectively input into the pre-trained module one and module two to obtain respective module prediction results, which are divided into load, phase change state and energy consumption; then the average proportion of the prediction results of each group within a reasonable range is obtained by manually comparing the difference between the module prediction value and the actual value; wherein the module one is the multi-dimensional information prediction module proposed by the application; the module two is to change the structure of the parallel multi-task prediction layer in the multi-dimensional information prediction module, that is, each unit in the parallel multi-task prediction layer is completely independent, and the input of each unit only has the corresponding prediction demand feature representation.

[0098] The multi-dimensional information prediction module effectiveness test results are shown in Table 1.

[0099] Table 1 Multi-dimensional information prediction module effectiveness test results

[0100]

[0101] From the results in Table 1, it can be seen that the multi-dimensional information prediction module proposed by the application, i.e. module one, is better than module two in the multi-dimensional information prediction module effectiveness test results; thereby it can be illustrated that the module proposed by the application can accurately predict the future state of different types of data, and further improve the reliability of the cooling program control strategy.

[0102] In order to further test the effectiveness of the overall control scheme, the historical equipment operation data of B enterprise in the past two years are selected as test data in this embodiment; three different control schemes are used to process the same test data to obtain control instructions under each group of schemes and perform control operations, and the proportion of the control results of each group of schemes within a reasonable range is obtained by manual investigation; wherein the test scheme one is the overall scheme proposed by the application, i.e. "multi-dimensional information prediction + multi-objective dynamic optimization + adaptive control adjustment"; the test scheme two is to remove the adaptive control adjustment process in the application; the test scheme three is to change the multi-objective dynamic optimization process in the application to output control instructions by combining experience summary and multi-dimensional information prediction results, i.e. "module automation" is converted into "manual operation".

[0103] The overall control scheme effectiveness test results are shown in Table 2.

[0104] Table 2 Overall control scheme effectiveness test results

[0105]

[0106] From the results in Table 2, it can be seen that the effectiveness test results obtained by using the test scheme one, i.e. the overall scheme proposed by the application, are better than those of other schemes, which illustrates that it is necessary to combine "multi-dimensional information prediction + multi-objective dynamic optimization + adaptive control adjustment", which can improve the effectiveness and reliability of the cooling program control strategy.

[0107] While embodiments of the application have been shown and described, it is to be understood that the application is not limited to the details of the embodiments described, since numerous changes, modifications, substitutions and variations can be made thereto without departing from the spirit and scope of the application as defined by the appended claims and their equivalents.

Claims

1. A method for intelligent cooling control of cold storage based on phase change cold storage, characterized in that, include: The system collects real-time equipment operation data through sensors and stores it in the corresponding memory in the terminal equipment control unit. The device interface unit is used to transmit device operation data stored in the memory and control command signals generated by the central control unit. Equipment operation data includes: equipment operating environment data, equipment operating status data, energy consumption data, and equipment operation data; equipment operating status data includes phase change material parameter data and refrigeration equipment parameter data; phase change material parameter data includes: thermophysical properties, cold storage capacity, and the state of charge of the phase change material; The central control unit receives equipment operation data, processes and optimizes control, generates control command signals, and transmits them to the terminal equipment control unit via the equipment interface unit. The processing and control optimization process of the central control unit includes: the central control unit uses a pre-trained multi-dimensional information prediction module to process the equipment operation data to obtain load prediction, phase change state prediction information, and energy consumption prediction information; the central control unit uses a multi-objective rolling time-domain dynamic optimization strategy to generate the optimal control command based on the load prediction, phase change state prediction information, and energy consumption prediction information. The prediction time domain, control time domain, and control cycle of the rolling time domain optimization are determined. At the start of each control cycle, based on the prediction information and the equipment operation data, the central control unit solves the objective function in conjunction with the optimization scheme to generate the optimal control command sequence. Only the optimal control command corresponding to the current control cycle is executed in the sequence. Subsequently, the equipment operation data is updated, and the next control cycle begins. Based on the updated equipment operation data and updated prediction information, the optimization solution process is repeated to achieve rolling update and execution of control commands. The central control unit combines sensor data with an adaptive controller based on fuzzy logic to adjust the optimal control command in real time, thereby obtaining a control command signal. The optimal control command is then adjusted using the control command adjustment amount to obtain the final control command. The terminal device control unit responds to the control command signal from the central control unit, executes program control, and controls the operating status of the device or adjusts the operating parameters of the device.

2. The intelligent cooling control method for cold storage based on phase change cold storage according to claim 1, characterized in that, The equipment operation data includes: equipment operating environment data, equipment operating status data, energy consumption data, and equipment operation data.

3. The intelligent cooling control method for cold storage based on phase change cold storage according to claim 1, characterized in that, The process by which the central control unit processes the equipment operation data using the multi-dimensional information prediction module to obtain the load prediction, the phase change state prediction information, and the energy consumption prediction information includes: the central control unit acquiring the equipment operation data through a data transmission channel established by the equipment interface unit; preprocessing the equipment operation data to obtain predicted demand data information; processing the multi-dimensional information prediction module using historical equipment operation data to obtain a pre-training module; and inputting the first, second, and third predicted demand information from the predicted demand data information into the pre-training module in parallel to obtain the load prediction, the phase change state prediction information, and the energy consumption prediction information, respectively; wherein, the memory of the central control unit is used to store numerical prediction information so that subsequent optimization control strategies can be executed based on the prediction information.

4. The intelligent cooling control method for cold storage based on phase change cold storage according to claim 1, characterized in that, The process by which the central control unit generates the optimal control command based on the multi-objective rolling time-domain dynamic optimization strategy using load forecasting, phase change state prediction information, and energy consumption prediction information includes: extracting prediction information from the memory of the central control unit; wherein, the prediction information includes: the load forecasting, the phase change state prediction information, and the energy consumption prediction information; modeling the cooling control problem based on phase change cold storage as a multi-objective constrained optimization problem, and determining the objective function, constraints, and optimization scheme for solving.

5. The intelligent cooling control method for cold storage based on phase change cold storage according to claim 1, characterized in that, The process by which the central control unit combines sensor data with a fuzzy logic-based adaptive controller to adjust the optimal control command in real time includes: fuzzifying the real-time collected sensor data and converting it into a fuzzy set group; performing fuzzy inference based on the fuzzy set group and a fuzzy rule base to obtain a fuzzy output; defuzzifying the fuzzy output to obtain a control command adjustment amount; adjusting the optimal control command obtained by the multi-objective rolling time-domain dynamic optimization strategy using the control command adjustment amount to obtain the final control command, which is then sent by the central control unit to the terminal device control unit.

6. The intelligent cooling control method for cold storage based on phase change cold storage according to claim 5, characterized in that, The fuzzification process includes: determining the input sensor variables of the fuzzy controller and preprocessing them; defining a set of fuzzy sets for each input sensor variable, each fuzzy set representing a different degree of description of the variable; substituting the preprocessed input variable values ​​into the membership function of each fuzzy set, calculating the membership degree of the variable value to each fuzzy set, and forming a complete fuzzy set group by combining the fuzzy sets containing the corresponding membership degrees.

7. The intelligent cooling control method for cold storage based on phase change cold storage according to claim 1, characterized in that, The operating status includes the equipment start / stop status and the equipment working mode status; the operating parameters include: equipment operating temperature, equipment operating frequency, equipment operating speed, equipment operating rotation speed, equipment operating flow rate, and equipment operating power.

Images