Freezer equipment data simulation and instruction interactive simulation system

Abstract

The invention discloses a refrigerator equipment data simulation and instruction interactive simulation system which comprises the following steps: S1, monitoring the working state of refrigerator equipment in real time, and generating equipment working state data; s2, transmitting the working state data of the equipment to a data processing center through a network; s3, receiving and storing the working state data of the equipment, and generating a working data report; s4, performing deep analysis on the working data report, and outputting an optimized optimization control instruction; s5, generating a control instruction according to the optimization control instruction, and transmitting the control instruction to the refrigerator equipment through a data transmission module; s6, virtual simulation of the working state of the refrigerator equipment is carried out through the working data report of the data processing center; and S7, the operation state of the refrigerator equipment is monitored in real time, potential faults are recognized, and early warning information is generated according to the recognition result. The method has the advantages of intelligent prediction, efficient optimization, real-time feedback, simulation verification and the like.

Description

Technical Field

[0001] The present invention relates to the field of simulation and emulation technology, and in particular to a data simulation and instruction interaction simulation system for refrigerator equipment. Background Art

[0002] With the rapid development of cold chain logistics and food storage industries, refrigerator equipment plays an increasingly important role in temperature and humidity control and energy management. In order to ensure that refrigerator equipment can maintain constant temperature and humidity during operation and optimize energy consumption, many modern refrigerator equipment have begun to rely on intelligent control systems to improve efficiency. However, the existing refrigerator equipment control methods still have some technical bottlenecks, especially in the operation status prediction, optimization control and feedback adjustment of refrigerator equipment, which still rely on traditional experience and rule-making methods, lacking flexibility and efficiency.

[0003] In the prior art, traditional refrigerator equipment control systems usually adopt rule-based control methods, relying on manual setting of temperature and humidity control ranges and energy consumption optimization strategies. These methods have the following obvious shortcomings: 1. Lack of intelligent prediction capabilities: Traditional methods are usually unable to accurately predict the operating status of equipment based on historical data and real-time changing environmental factors, making it difficult to make intelligent adjustments based on future needs.

[0004] 2. Single optimization control method: Most of the existing refrigerator equipment control systems are adjusted based on experience, and the optimization scheme is relatively static, making it difficult to make dynamic adjustments based on the actual operating status of the equipment and changes in the external environment.

[0005] 3. Lack of real-time feedback and update mechanism: Traditional control systems fail to receive and process the actual operating data of refrigerator equipment in a timely manner, and cannot effectively update the control strategy based on the execution effect. This results in the system being unable to quickly respond to changes in equipment status and failing to effectively improve control accuracy.

[0006] 4. Insufficient virtual simulation support: The existing technology lacks effective virtual simulation tools, and it is impossible to conduct comprehensive verification before control. Whether the control instruction is effective can only be concluded after actual testing, which wastes a lot of time and resources.

[0007] Therefore, how to provide a refrigerator equipment data simulation and command interaction simulation system is a problem that technical personnel in this field urgently need to solve. Summary of the invention

[0008] One object of the present invention is to propose a refrigerator equipment data simulation and instruction interaction simulation system. The present invention makes full use of deep learning algorithms, particle swarm optimization algorithms and virtual simulation technology, and describes in detail the process of refrigerator equipment status prediction, optimized control instruction generation and real-time feedback update based on historical data and real-time data, and verifies the execution effect of the control instruction through a virtual simulation module. It has the advantages of intelligent prediction, efficient optimization, real-time feedback and simulation verification.

[0009] A data simulation and instruction interaction simulation system for refrigerator equipment according to an embodiment of the present invention includes: S1, IoT sensor module, used to monitor the working status of refrigerator equipment in real time and generate equipment working status data; S2, data transmission module, used to transmit the equipment working status data to the data processing center through the network; S3, a data processing center, for receiving and storing equipment working status data, and performing preliminary processing on the equipment working status data through a data analysis module, and generating a working data report including historical equipment working status data and real-time equipment working status data of the equipment working status; S4, artificial intelligence algorithm module, used to conduct in-depth analysis of work data reports and output optimized optimization control instructions; S5, an instruction generation module, generating a control instruction according to the optimized control instruction, and transmitting the control instruction to the refrigerator device through the data transmission module; S6, virtual simulation module, through the working data report of the data processing center, performs virtual simulation of the working status of the refrigerator equipment, verifies the execution effect of the control instructions in the actual equipment, and provides the user with an operation simulation interface; S7, intelligent early warning and fault diagnosis module, is used to monitor the operating status of the refrigerator equipment in real time, identify potential faults, and generate early warning information based on the identification results.

[0010] Optionally, the S3 specifically includes: S31, a data receiving module receives device working status data transmitted from the Internet of Things sensor module, wherein the device working status data includes temperature ,humidity ,pressure and current ,in Indicates the timestamp, the equipment working status data is transmitted to the data processing center through the network; S32, a data storage module stores the received device working status data, and classifies and archives the device working status data in chronological order using distributed storage. The stored device working status data is ; S33, a data preprocessing module, preprocessing the stored equipment working status data, including denoising, outlier detection and missing value filling; Wavelet transform is used to denoise the equipment working status data, and soft threshold denoising is performed by selecting an appropriate threshold function: ; in, is the wavelet transform, represents the soft threshold function, is the inverse wavelet transform, is the threshold value, It is the equipment working status data after denoising; Detect abnormal values ​​of equipment working status data through statistical methods based on standard deviation, and set abnormal value thresholds for equipment working status data for: ; in, is the mean value of the equipment working status data, is the standard deviation of the equipment working status data, is the abnormal value coefficient. If the working status data of a certain device meets or , the device working status data is considered to be an abnormal value and is removed or replaced; For equipment working status data For each data point in time If there are missing values, the linear interpolation method based on time series is used to fill the missing values: ; in, To fill in the equipment working status data, and are the known data values ​​before and after the missing value, and is the corresponding time point; S34, a data analysis module, analyzing the pre-processed equipment working status data, including trend analysis of historical equipment working status data, comparative analysis of real-time equipment working status data and historical equipment working status data, and pattern recognition of equipment status; S35, a working data report generating module, generating a working data report including historical equipment working status data and real-time equipment working status data of the equipment working status according to the analysis result of the data analyzing module; S36. A report storage module is used to store the generated work data report in a distributed database within the data processing center.

[0011] Optionally, the S4 specifically includes: S41, a data preprocessing module, used for performing preliminary processing on the work data report; S42, a deep learning prediction module, which uses a deep neural network model to train the historical data and real-time data of the equipment working status, wherein the input is the historical data and real-time data of the equipment working status, and the output is the predicted future operating status of the equipment; S43, an optimization control generation module, based on the prediction results output by the deep learning prediction module and combined with a multi-objective optimization function, generates an optimization control instruction for the refrigerator equipment; S44, an instruction output module, used to convert the optimization control instruction into a specific control instruction executable by the refrigerator device, and send the control instruction to the refrigerator device through the data transmission module to perform the adjustment operation; S45, a feedback update module, is used to receive the operation data of the refrigerator equipment after execution in real time, and update the deep neural network model by comparing the operation data with the predicted future operation status of the equipment.

[0012] Optionally, the S42 specifically includes: S421, input data processing module, convert the historical data and real-time data of the equipment working status into a format suitable for deep neural network model processing, the historical data includes temperature ,humidity ,pressure and current The real-time data is the equipment working status data collected in real time. The historical data and real-time data are timestamped. Sorting is performed to generate an input data sequence with time series characteristics; S422, a deep neural network model construction module, used to construct a deep neural network model, the deep neural network model includes multiple fully connected layers, each fully connected layer is composed of multiple neurons, the input layer is processed historical data and real-time data, and the output layer is the predicted future operating state of the device, including temperature ,humidity ,pressure and current ; S423, model training module, used to train the deep neural network model through the back propagation algorithm. During the training process, historical data and real-time data are used as training samples. The training goal is to minimize the prediction error. The error function is the mean square error function: ; in, is the mean square error, The actual working status of the equipment. The working status of the equipment predicted by the deep neural network model, is the sample size, To predict the time point; S424, an optimization algorithm module, is used to update the weights of the deep neural network model using the Adam optimization algorithm during the training process. The update rule of the Adam optimization algorithm is: ; ; ; ; in, and are the first and second moment estimates, and are the exponential decay rates of the first and second order moments, is the learning rate, is a small constant to prevent division by zero errors, is the gradient of the loss function, are neural network parameters, is the current iteration number, and Represents the first-order moment estimate and the second moment estimate The deviation correction of and is the exponential decay rate and exponential decay of S425, a model verification module, used to verify the deep neural network model using a verification set during the training process, wherein the verification set is an independent data set separated from historical data and real-time data, and the model parameters are adjusted according to the verification error during the verification process; S426, a prediction module, used to use the trained deep neural network model to predict the real-time data and output the predicted future operating status of the equipment.

[0013] Optionally, the S43 specifically includes: S431, multi-objective optimization function construction module, constructs a multi-objective optimization function according to the operation requirements of the refrigerator equipment : ; in, is the objective function, and are the temperature and humidity of the equipment, and are the target temperature and target humidity, For energy consumption, is the weighting coefficient, is a time period, wherein the optimization control instructions include temperature adjustment, humidity adjustment and energy consumption optimization instructions; S432, a constraint setting module, sets the constraints that need to be met during the optimization process according to the hardware and environmental limitations of the refrigerator equipment: ; ; ; in, and are the minimum and maximum permissible values ​​of temperature, and are the minimum and maximum permissible values ​​of humidity, is the maximum energy consumption allowed; S433, particle swarm optimization algorithm module, generates optimized control instructions through particle swarm optimization algorithm, the specific process is as follows: Initialize the particle swarm and set the number of particles and the maximum number of iterations , the initial position of the particle and speed Generated by random distribution; Calculate the fitness value of each particle at its current position , the fitness value is calculated as a multi-objective optimization function ; Update the speed and position of each particle. The speed update formula is: ; in, For the first The particle in The speed at the iteration, For particles In the The speed at the iteration, For particles The best location in history, is the global best position among all particles, is the learning factor, for A random number between is the inertia weight; The particle position update formula is: ; in, Indicates that the particle The current position at the iteration, Indicates that the particle Update position at iteration 1; It is used to judge whether the termination condition is met. If it is met, the optimal solution is output as the control instruction. If it is not met, the optimization continues. S434, an optimization control instruction generation module outputs an optimization control instruction according to the calculation result of the particle swarm optimization algorithm, wherein the control instruction includes a temperature adjustment instruction. , humidity adjustment instructions and energy optimization instructions , so that the operating state of the refrigerator equipment is close to the target state and satisfies the set constraints; S435, optimization result verification module, is used to verify the generated optimization control instructions, and evaluate the execution effect of the control instructions by comparing with historical data. If the execution effect meets the expected goal, the control instructions will be transmitted to the refrigerator equipment, otherwise the optimization strategy will be adjusted and the control instructions will be regenerated.

[0014] Optionally, the S45 specifically includes: S451, an operation data receiving module is used to receive the operation data of the refrigerator equipment in real time, and the operation data includes temperature ,humidity ,pressure and current ; S452, an execution status comparison module is used to compare the received actual data with the predicted data output by the deep learning prediction module, wherein the predicted data includes the predicted temperature ,humidity ,pressure and current , calculate the error value , , and ; S453, error calculation module, using mean square error comparison result to perform error calculation: ; ; in, and are the mean square errors of temperature and humidity respectively, is the sample size, is the time period; S454, a deep neural network model updating module, updates the deep neural network model based on the calculated error value, and adjusts the weight parameters of the deep neural network model through a back propagation algorithm: ; in, are the updated deep neural network model parameters, is the parameter of the previous round of deep neural network model, is the learning rate, is the gradient of the loss function with respect to the parameters of the deep neural network model; S455, a real-time feedback module, generates new prediction results based on the updated deep neural network model.

[0015] Optionally, the S6 specifically includes: S61, a data processing center module receives and processes equipment working status data from the refrigerator equipment, including historical equipment working status data, real-time equipment working status data and optimization control instructions, and forms a data format suitable for virtual simulation processing after preprocessing; S62, a virtual simulation model building module, used to build a virtual simulation model of the refrigerator equipment, based on the working principle and operating characteristics of the refrigerator equipment, simulating the working state of the equipment under different environments and control conditions; S63, a simulation execution module, performing simulation execution according to the virtual simulation model and the real-time equipment working status data input, wherein the simulation execution result includes the predicted values ​​of various equipment operating parameters in the future time period and the response of the equipment under various control instructions; S64, a control instruction verification module, used to verify the execution effect of the control instruction generated by the optimization control generation module in the virtual simulation environment, and to judge whether the control instruction meets the expected goal by comparing the error between the simulation result and the target state; S65, a user operation simulation module is used to provide an interactive operation interface for the user, through which the user inputs control commands, modifies equipment operating parameters or monitors simulation results.

[0016] The beneficial effects of the present invention are: (1) By combining deep learning algorithms, particle swarm optimization algorithms and virtual simulation technology, the present invention can accurately predict the working status of refrigerator equipment and generate optimized control instructions based on the prediction results, thereby effectively improving the energy efficiency and performance of refrigerator equipment. By optimizing the particle swarm optimization algorithm of the control instruction generation module, it is possible to accurately adjust equipment parameters such as temperature and humidity while meeting equipment operation constraints, thereby achieving more efficient energy consumption management.

[0017] (2) The present invention dynamically updates the deep learning model through a real-time feedback update module, which can continuously optimize the equipment prediction model, adapt to changes in equipment status and the needs of different operating environments, and further improve the prediction accuracy and control effect. This not only enhances the system's adaptability to the operating status of the refrigerator equipment, but also effectively reduces the deviation caused by fluctuations in equipment status, ensuring the stable operation of the equipment.

[0018] (3) The present invention provides simulation and prediction of the operating status of refrigerator equipment through a virtual simulation module combined with the execution verification of optimized control instructions, and can verify the execution effect of control instructions in actual equipment in advance. This function greatly reduces the cost and time of experiments, and at the same time provides users with an interactive operation interface, which facilitates users to conduct real-time monitoring and adjustment, and improves the intelligence and flexibility of equipment operation. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] The accompanying drawings are used to provide a further understanding of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation of the present invention. In the accompanying drawings: Figure 1 This is a general framework diagram of a refrigerator equipment data simulation and instruction interaction simulation system proposed by the present invention. DETAILED DESCRIPTION

[0020] The present invention will now be described in further detail with reference to the accompanying drawings. These drawings are simplified schematic diagrams, which only illustrate the basic structure of the present invention in a schematic manner, and therefore only show the components related to the present invention.

[0021] refer to Figure 1 , a refrigerator equipment data simulation and instruction interaction simulation system, the system comprising: S1, IoT sensor module, used to monitor the working status of refrigerator equipment in real time and generate equipment working status data; This embodiment uses the IoT sensor module to monitor the working status of the refrigerator equipment in real time and generate equipment working status data. The module can continuously collect key parameters such as temperature, humidity, pressure, and current of the equipment, providing real-time data support during the operation of the equipment. By accurately monitoring these data, abnormal operation of the equipment can be discovered in time, thereby providing a strong basis for subsequent control instruction optimization and equipment failure warning.

[0022] S2, data transmission module, used to transmit the equipment working status data to the data processing center through the network; This implementation method transmits the device working status data to the data processing center in real time through the data transmission module, thereby ensuring efficient data exchange between the device and the data processing center.

[0023] S3, a data processing center, for receiving and storing equipment working status data, and performing preliminary processing on the equipment working status data through a data analysis module, and generating a working data report including historical equipment working status data and real-time equipment working status data of the equipment working status; In this implementation, S3 specifically includes: S31, a data receiving module receives device working status data transmitted from the Internet of Things sensor module, wherein the device working status data includes temperature ,humidity ,pressure and current ,in Indicates the timestamp, the equipment working status data is transmitted to the data processing center through the network; S32, a data storage module stores the received device working status data, and classifies and archives the device working status data in chronological order using distributed storage. The stored device working status data is ; S33, a data preprocessing module, preprocessing the stored equipment working status data, including denoising, outlier detection and missing value filling; Wavelet transform is used to denoise the equipment working status data, and soft threshold denoising is performed by selecting an appropriate threshold function: ; in, is the wavelet transform, represents the soft threshold function, is the inverse wavelet transform, is the threshold value, It is the equipment working status data after denoising; Detect abnormal values ​​of equipment working status data through statistical methods based on standard deviation, and set abnormal value thresholds for equipment working status data for: ; in, is the mean value of the equipment working status data, is the standard deviation of the equipment working status data, is the abnormal value coefficient. If the working status data of a certain device meets or , the device working status data is considered to be an abnormal value and is removed or replaced; For equipment working status data For each data point in time If there are missing values, the linear interpolation method based on time series is used to fill the missing values: ; in, To fill in the equipment working status data, and are the known data values ​​before and after the missing value, and is the corresponding time point; S34, a data analysis module, analyzing the pre-processed equipment working status data, including trend analysis of historical equipment working status data, comparative analysis of real-time equipment working status data and historical equipment working status data, and pattern recognition of equipment status; S35, a working data report generating module, generating a working data report including historical equipment working status data and real-time equipment working status data of the equipment working status according to the analysis result of the data analyzing module; S36. A report storage module is used to store the generated work data report in a distributed database within the data processing center.

[0024] This implementation method receives and stores the equipment working status data through the data processing center, and performs preliminary processing on these data in combination with the data analysis module to generate a working data report containing historical data and real-time data of the equipment working status. This method provides a comprehensive and detailed analysis of the equipment operating status, which can not only monitor the current status of the equipment in real time, but also predict trends through historical data.

[0025] S4, artificial intelligence algorithm module, used to conduct in-depth analysis of work data reports and output optimized optimization control instructions; In this implementation, S4 specifically includes: S41, a data preprocessing module, used for performing preliminary processing on the work data report; S42, a deep learning prediction module, which uses a deep neural network model to train the historical data and real-time data of the equipment working status, wherein the input is the historical data and real-time data of the equipment working status, and the output is the predicted future operating status of the equipment; S43, an optimization control generation module, based on the prediction results output by the deep learning prediction module and combined with a multi-objective optimization function, generates an optimization control instruction for the refrigerator equipment; S44, an instruction output module, used to convert the optimization control instruction into a specific control instruction executable by the refrigerator device, and send the control instruction to the refrigerator device through the data transmission module to perform the adjustment operation; S45, a feedback update module, is used to receive the operation data of the refrigerator equipment after execution in real time, and update the deep neural network model by comparing the operation data with the predicted future operation status of the equipment.

[0026] The S42 specifically includes: S421, input data processing module, convert the historical data and real-time data of the equipment working status into a format suitable for deep neural network model processing, the historical data includes temperature ,humidity ,pressure and current The real-time data is the equipment working status data collected in real time. The historical data and real-time data are timestamped. Sorting is performed to generate an input data sequence with time series characteristics; S422, a deep neural network model construction module, used to construct a deep neural network model, the deep neural network model includes multiple fully connected layers, each fully connected layer is composed of multiple neurons, the input layer is processed historical data and real-time data, and the output layer is the predicted future operating state of the device, including temperature ,humidity ,pressure and current ; S423, model training module, used to train the deep neural network model through the back propagation algorithm. During the training process, historical data and real-time data are used as training samples. The training goal is to minimize the prediction error. The error function is the mean square error function: ; in, is the mean square error, The actual working status of the equipment. The working status of the equipment predicted by the deep neural network model, is the sample size, To predict the time point; S424, an optimization algorithm module, is used to update the weights of the deep neural network model using the Adam optimization algorithm during the training process. The update rule of the Adam optimization algorithm is: ; ; ; ; in, and are the first and second moment estimates, and are the exponential decay rates of the first and second order moments, is the learning rate, is a small constant to prevent division by zero errors, is the gradient of the loss function, are neural network parameters, is the current iteration number, and Represents the first-order moment estimate and the second moment estimate The deviation correction of and is the exponential decay rate and exponential decay of S425, a model verification module, used to verify the deep neural network model using a verification set during the training process, wherein the verification set is an independent data set separated from historical data and real-time data, and the model parameters are adjusted according to the verification error during the verification process; S426, a prediction module, used to use the trained deep neural network model to predict the real-time data and output the predicted future operating status of the equipment.

[0027] The S43 specifically includes: S431, multi-objective optimization function construction module, constructs a multi-objective optimization function according to the operation requirements of the refrigerator equipment : ; in, is the objective function, and are the temperature and humidity of the equipment, and are the target temperature and target humidity, For energy consumption, is the weighting coefficient, is a time period, wherein the optimization control instructions include temperature adjustment, humidity adjustment and energy consumption optimization instructions; S432, a constraint setting module, sets the constraints that need to be met during the optimization process according to the hardware and environmental limitations of the refrigerator equipment: ; ; ; in, and are the minimum and maximum permissible values ​​of temperature, and are the minimum and maximum permissible values ​​of humidity, is the maximum energy consumption allowed; S433, particle swarm optimization algorithm module, generates optimized control instructions through particle swarm optimization algorithm, the specific process is as follows: Initialize the particle swarm and set the number of particles and the maximum number of iterations , the initial position of the particle and speed Generated by random distribution; Calculate the fitness value of each particle at its current position , the fitness value is calculated as a multi-objective optimization function ; Update the speed and position of each particle. The speed update formula is: ; in, For the first The particle in The speed at the iteration, For particles In the The speed at the iteration, For particles The best location in history, is the global best position among all particles, is the learning factor, for A random number between is the inertia weight; The particle position update formula is: ; in, Indicates that the particle The current position at the iteration, Indicates that the particle Update position at iteration 1; It is used to judge whether the termination condition is met. If it is met, the optimal solution is output as the control instruction. If it is not met, the optimization continues. S434, an optimization control instruction generation module outputs an optimization control instruction according to the calculation result of the particle swarm optimization algorithm, wherein the control instruction includes a temperature adjustment instruction. , humidity adjustment instructions and energy optimization instructions , so that the operating state of the refrigerator equipment is close to the target state and satisfies the set constraints; S435, optimization result verification module, is used to verify the generated optimization control instructions, and evaluate the execution effect of the control instructions by comparing with historical data. If the execution effect meets the expected goal, the control instructions will be transmitted to the refrigerator equipment, otherwise the optimization strategy will be adjusted and the control instructions will be regenerated.

[0028] The S45 specifically includes: S451, an operation data receiving module is used to receive the operation data of the refrigerator equipment in real time, and the operation data includes temperature ,humidity ,pressure and current ; S452, an execution status comparison module is used to compare the received actual data with the predicted data output by the deep learning prediction module, wherein the predicted data includes the predicted temperature ,humidity ,pressure and current , calculate the error value , , and ; S453, error calculation module, using mean square error comparison result to perform error calculation: ; ; in, and are the mean square errors of temperature and humidity respectively, is the sample size, is the time period; S454, a deep neural network model updating module, updates the deep neural network model based on the calculated error value, and adjusts the weight parameters of the deep neural network model through a back propagation algorithm: ; in, are the updated deep neural network model parameters, is the parameter of the previous round of deep neural network model, is the learning rate, is the gradient of the loss function with respect to the parameters of the deep neural network model; S455, a real-time feedback module, generates new prediction results based on the updated deep neural network model.

[0029] This implementation uses an artificial intelligence algorithm module to conduct an in-depth analysis of the work data report, and combines deep learning and optimization algorithms to comprehensively analyze the operating status of the refrigerator equipment, and can generate optimized control instructions for the current status of the equipment. This module can not only analyze historical operating data, but also identify potential operating problems and optimization space, thereby generating more accurate and efficient control instructions.

[0030] S5, an instruction generation module, generating a control instruction according to the optimized control instruction, and transmitting the control instruction to the refrigerator device through the data transmission module; In this embodiment, the instruction generation module generates control instructions according to the optimized control instructions, and transmits the control instructions to the refrigerator equipment through the data transmission module. This method makes full use of the optimization control technology, combines the interactive mechanism of the deep learning model and the real-time feedback data, and can accurately generate the optimal control instructions for the operating status of the refrigerator equipment.

[0031] S6, virtual simulation module, through the working data report of the data processing center, performs virtual simulation of the working status of the refrigerator equipment, verifies the execution effect of the control instructions in the actual equipment, and provides the user with an operation simulation interface; In this implementation, S6 specifically includes: S61, a data processing center module receives and processes equipment working status data from the refrigerator equipment, including historical equipment working status data, real-time equipment working status data and optimization control instructions, and forms a data format suitable for virtual simulation processing after preprocessing; S62, a virtual simulation model building module, used to build a virtual simulation model of the refrigerator equipment, based on the working principle and operating characteristics of the refrigerator equipment, simulating the working state of the equipment under different environments and control conditions; S63, a simulation execution module, performing simulation execution according to the virtual simulation model and the real-time equipment working status data input, wherein the simulation execution result includes the predicted values ​​of various equipment operating parameters in the future time period and the response of the equipment under various control instructions; S64, a control instruction verification module, used to verify the execution effect of the control instruction generated by the optimization control generation module in the virtual simulation environment, and to judge whether the control instruction meets the expected goal by comparing the error between the simulation result and the target state; S65, a user operation simulation module is used to provide an interactive operation interface for the user, through which the user inputs control commands, modifies equipment operating parameters or monitors simulation results.

[0032] This implementation achieves real-time virtual simulation of the working status of the refrigerator equipment and verification of control instructions through the virtual simulation module combined with the working data report of the data processing center. This module can not only accurately simulate the performance of the equipment under different working conditions, but also verify the effect of executing control instructions in the actual equipment, and provide users with an interactive operation simulation interface.

[0033] S7, intelligent early warning and fault diagnosis module, is used to monitor the operating status of the refrigerator equipment in real time, identify potential faults, and generate early warning information based on the analysis results.

[0034] This implementation introduces an intelligent early warning and fault diagnosis module to monitor the operating status of the refrigerator equipment in real time, and combines deep learning and data analysis technology to promptly identify potential equipment failures or abnormal operating modes. This module continuously monitors and analyzes various operating data of the equipment, combines historical data and real-time feedback, accurately predicts possible equipment failures, and generates corresponding early warning information.

[0035] Example: In order to verify the effectiveness of the present invention, the present invention is applied to a medium-sized refrigerator equipment operating company (hereinafter referred to as Company B), which owns multiple distributed refrigerator equipment around the world and is widely used in the retail, logistics and warehousing industries. Since the operating status of refrigerator equipment is crucial to product quality, Company B has been looking for a more efficient and accurate equipment control and optimization solution to ensure that the refrigerator equipment can meet the preset temperature and humidity requirements during operation and save energy consumption to the greatest extent.

[0036] In the operation of Company B, the temperature and humidity control of refrigerator equipment are the main performance indicators. With the increase in the number of refrigerator equipment, traditional manual adjustment and monitoring methods seem to be unable to cope with the situation, especially in the face of complex environmental changes. How to achieve accurate control command generation and real-time feedback adjustment has become a technical problem. Company B hopes to improve the accuracy of equipment control, optimize energy use, and further reduce the need for manual intervention by implementing the refrigerator equipment data simulation and command interaction simulation system in the present invention.

[0037] In the implementation process of the present invention, first, Company B connects the data of all its refrigerator equipment to the data processing center module. This module is responsible for receiving real-time operating data from each device, such as temperature, humidity, pressure, current, etc., and processing historical operating data and optimization control instructions generated by the system. The data processing center pre-processes these data and converts them into a format suitable for input into the virtual simulation model. Through this processing process, Company B can achieve real-time monitoring and prediction of the equipment status.

[0038] In the virtual simulation model construction module, the present invention constructs a virtual simulation model for each refrigerator device based on the working principle of the refrigerator device and its environmental characteristics. The model can simulate the behavior of the device under different environmental conditions and control instructions, especially in terms of changes in parameters such as temperature and humidity, to help Company B understand the state performance of the device under different operating conditions. This virtual simulation model is compared with the actual data in real time during operation, providing a highly dynamic simulation environment, thereby enhancing the predictability of the execution effect of the control instructions.

[0039] In order to further optimize the operation of the refrigerator equipment, the present invention also adopts a control instruction generation module based on the particle swarm optimization algorithm. This module generates optimized temperature and humidity adjustment instructions by analyzing the prediction results of the deep learning model and combining the operation data of the equipment. The particle swarm optimization algorithm can efficiently explore the optimal solution of each control variable, ensure the stable operation of the equipment in a complex environment, and reduce energy consumption.

[0040] In the feedback update module of the present invention, the system receives the operation data from the refrigerator equipment after execution in real time, and compares it with the output of the deep learning prediction module, and dynamically updates the weight of the deep learning model by calculating the error. Through this closed-loop optimization mechanism, the system can continuously improve the prediction accuracy and adjust the control strategy according to the real-time data to ensure the continuous efficiency of the refrigerator equipment during long-term operation.

[0041] In order to verify the effectiveness of the present invention, Company B applied the refrigerator equipment data simulation and instruction interaction simulation system of the present invention in an actual operating environment and conducted a three-month test. During the test, Company B selected 10 of its distributed refrigerator equipment and applied the system to optimize the temperature and humidity control of the equipment. The specific data is shown in Table 1 below: Table 1: Report on the optimization and control effect of refrigerator equipment of Company B

[0042] According to the data in Table 1, we can see that after implementing the system of the present invention, Company B has achieved significant improvements in equipment failure rate and energy consumption. Specifically, before the implementation of the system, the number of equipment failures due to unstable temperature and humidity was 12 times per month, which was reduced to only 2 times after implementation. By optimizing the control instructions, the energy consumption of the refrigerator equipment dropped from 50,000 kWh to 42,000 kWh, showing an improvement in energy saving. In addition, the matching accuracy of the control instructions generated by the system with the target temperature and humidity increased from 85.3% to 98.5%, greatly improving the control accuracy.

[0043] For error correction of control instructions, the error correction time was 20 minutes before implementation, and it was shortened to 5 minutes after implementation, showing the efficiency improvement of the system in real-time feedback and adjustment. In terms of equipment operation stability, the equipment can maintain stable operation under set temperature and humidity conditions for a period of time from 14 hours to 24 hours after implementation, further proving the accuracy of control instructions and the stability of equipment.

[0044] From these data, it can be seen that the freezer equipment data simulation and instruction interactive simulation system of the present invention has significant advantages in improving equipment control accuracy, reducing energy consumption, and improving equipment operation stability. This not only meets Company B's demand for precise equipment control, but also provides technical support for energy saving and intelligent management of freezer equipment.

[0045] The above description is only a preferred specific implementation manner of the present invention, but the protection scope of the present invention is not limited thereto. Any technician familiar with the technical field can make equivalent replacements or changes according to the technical scheme and inventive concept of the present invention within the technical scope disclosed by the present invention, which should be covered by the protection scope of the present invention.

Claims

1. A refrigerator equipment data simulation and instruction interaction simulation system, characterized in that: The system comprises: S1, IoT sensor module, used to monitor the working status of refrigerator equipment in real time and generate equipment working status data; S2, data transmission module, used to transmit the equipment working status data to the data processing center through the network; S3, a data processing center, for receiving and storing equipment working status data, and performing preliminary processing on the equipment working status data through a data analysis module, and generating a working data report including historical equipment working status data and real-time equipment working status data of the equipment working status; S4, artificial intelligence algorithm module, used to conduct in-depth analysis of work data reports and output optimized optimization control instructions; S5, an instruction generation module, generating a control instruction according to the optimized control instruction, and transmitting the control instruction to the refrigerator device through the data transmission module; S6, virtual simulation module, through the working data report of the data processing center, performs virtual simulation of the working status of the refrigerator equipment, verifies the execution effect of the control instructions in the actual equipment, and provides the user with an operation simulation interface; S7, intelligent early warning and fault diagnosis module, is used to monitor the operating status of the refrigerator equipment in real time, identify potential faults, and generate early warning information based on the identification results.

2. A refrigerator equipment data simulation and instruction interactive simulation system according to claim 1, characterized in that: The S3 specifically includes: S31, a data receiving module receives device working status data transmitted from the Internet of Things sensor module, wherein the device working status data includes temperature ,humidity ,pressure and current ,in Indicates the timestamp, the equipment working status data is transmitted to the data processing center through the network; S32, a data storage module stores the received device working status data, and classifies and archives the device working status data in chronological order using distributed storage. The stored device working status data is ; S33, a data preprocessing module, preprocessing the stored equipment working status data, including denoising, outlier detection and missing value filling; Wavelet transform is used to denoise the equipment working status data, and soft threshold denoising is performed by selecting an appropriate threshold function: ； in, is the wavelet transform, represents the soft threshold function, is the inverse wavelet transform, is the threshold value, It is the equipment working status data after denoising; Detect abnormal values ​​of equipment working status data through statistical methods based on standard deviation, and set abnormal value thresholds for equipment working status data for: ； in, is the mean value of the equipment working status data, is the standard deviation of the equipment working status data, is the abnormal value coefficient. If the working status data of a certain device meets or , the device working status data is considered to be an abnormal value and is removed or replaced; For equipment working status data For each data point in time If there are missing values, the linear interpolation method based on time series is used to fill the missing values: ； in, To fill in the equipment working status data, and are the known data values ​​before and after the missing value, and is the corresponding time point; S34, a data analysis module, analyzing the pre-processed equipment working status data, including trend analysis of historical equipment working status data, comparative analysis of real-time equipment working status data and historical equipment working status data, and pattern recognition of equipment status; S35, a working data report generating module, generating a working data report including historical equipment working status data and real-time equipment working status data of the equipment working status according to the analysis result of the data analyzing module; S36. A report storage module is used to store the generated work data report in a distributed database within the data processing center.

3. A refrigerator equipment data simulation and instruction interactive simulation system according to claim 1, characterized in that: The S4 specifically includes: S41, a data preprocessing module, used for performing preliminary processing on the work data report; S42, a deep learning prediction module, which uses a deep neural network model to train the historical data and real-time data of the equipment working status, wherein the input is the historical data and real-time data of the equipment working status, and the output is the predicted future operating status of the equipment; S43, an optimization control generation module, based on the prediction results output by the deep learning prediction module and combined with a multi-objective optimization function, generates an optimization control instruction for the refrigerator equipment; S44, an instruction output module, used to convert the optimization control instruction into a specific control instruction executable by the refrigerator device, and send the control instruction to the refrigerator device through the data transmission module to perform the adjustment operation; S45, a feedback update module, is used to receive the operation data of the refrigerator equipment after execution in real time, and update the deep neural network model by comparing the operation data with the predicted future operation status of the equipment.

4. A refrigerator equipment data simulation and instruction interactive simulation system according to claim 3, characterized in that: The S42 specifically includes: S421, input data processing module, convert the historical data and real-time data of the equipment working status into a format suitable for deep neural network model processing, the historical data includes temperature ,humidity ,pressure and current The real-time data is the equipment working status data collected in real time. The historical data and real-time data are timestamped. Sorting is performed to generate an input data sequence with time series characteristics; S422, a deep neural network model construction module, used to construct a deep neural network model, the deep neural network model includes multiple fully connected layers, each fully connected layer is composed of multiple neurons, the input layer is processed historical data and real-time data, and the output layer is the predicted future operating state of the device, including temperature ,humidity ,pressure and current ; S423, model training module, used to train the deep neural network model through the back propagation algorithm. During the training process, historical data and real-time data are used as training samples. The training goal is to minimize the prediction error. The error function is the mean square error function: ； in, is the mean square error, The actual working status of the equipment. The working status of the equipment predicted by the deep neural network model, is the sample size, To predict the time point; S424, an optimization algorithm module, is used to update the weights of the deep neural network model using the Adam optimization algorithm during the training process. The update rule of the Adam optimization algorithm is: ； ； ； ； in, and are the first and second moment estimates, and are the exponential decay rates of the first and second order moments, is the learning rate, is a small constant to prevent division by zero errors, is the gradient of the loss function, are neural network parameters, is the current iteration number, and Represents the first-order moment estimate and the second moment estimate The deviation correction of and is the exponential decay rate and exponential decay of S425, a model verification module, used to verify the deep neural network model using a verification set during the training process, wherein the verification set is an independent data set separated from historical data and real-time data, and the model parameters are adjusted according to the verification error during the verification process; S426, a prediction module, used to use the trained deep neural network model to predict the real-time data and output the predicted future operating status of the equipment.

5. The data simulation and instruction interaction simulation system for refrigerator equipment according to claim 3 is characterized in that: The S43 specifically includes: S431, multi-objective optimization function construction module, constructs a multi-objective optimization function according to the operation requirements of the refrigerator equipment : ； in, is the objective function, and are the temperature and humidity of the equipment, and are the target temperature and target humidity, For energy consumption, is the weighting coefficient, is a time period, wherein the optimization control instructions include temperature adjustment, humidity adjustment and energy consumption optimization instructions; S432, a constraint setting module, sets the constraints that need to be met during the optimization process according to the hardware and environmental limitations of the refrigerator equipment: ； ； ； in, and are the minimum and maximum permissible values ​​of temperature, and are the minimum and maximum permissible values ​​of humidity, is the maximum energy consumption allowed; S433, particle swarm optimization algorithm module, generates optimized control instructions through particle swarm optimization algorithm, the specific process is as follows: Initialize the particle swarm and set the number of particles and the maximum number of iterations , the initial position of the particle and speed Generated by random distribution; Calculate the fitness value of each particle at its current position , the fitness value is calculated as a multi-objective optimization function ; Update the speed and position of each particle. The speed update formula is: ； in, For the first The particle in The speed at the iteration, For particles In the The speed at the iteration, For particles The best location in history, is the global best position among all particles, is the learning factor, for A random number between is the inertia weight; The particle position update formula is: ； in, Indicates that the particle The current position at the iteration, Indicates that the particle Update position at iteration 1; It is used to judge whether the termination condition is met. If it is met, the optimal solution is output as the control instruction. If it is not met, the optimization continues. S434, an optimization control instruction generation module outputs an optimization control instruction according to the calculation result of the particle swarm optimization algorithm, wherein the control instruction includes a temperature adjustment instruction. , humidity adjustment instructions and energy optimization instructions , so that the operating state of the refrigerator equipment is close to the target state and satisfies the set constraints; S435, optimization result verification module, is used to verify the generated optimization control instructions, and evaluate the execution effect of the control instructions by comparing with historical data. If the execution effect meets the expected goal, the control instructions will be transmitted to the refrigerator equipment, otherwise the optimization strategy will be adjusted and the control instructions will be regenerated.

6. A refrigerator equipment data simulation and instruction interactive simulation system according to claim 3, characterized in that: The S45 specifically includes: S451, an operation data receiving module is used to receive the operation data of the refrigerator equipment in real time, and the operation data includes temperature ,humidity ,pressure and current ; S452, an execution status comparison module is used to compare the received actual data with the predicted data output by the deep learning prediction module, wherein the predicted data includes the predicted temperature ,humidity ,pressure and current , calculate the error value , , and ; S453, error calculation module, using mean square error comparison result to perform error calculation: ； ； in, and are the mean square errors of temperature and humidity respectively, is the sample size, is the time period; S454, a deep neural network model updating module, updates the deep neural network model based on the calculated error value, and adjusts the weight parameters of the deep neural network model through a back propagation algorithm: ； in, are the updated deep neural network model parameters, is the parameter of the previous round of deep neural network model, is the learning rate, is the gradient of the loss function with respect to the parameters of the deep neural network model; S455, a real-time feedback module, generates new prediction results based on the updated deep neural network model.

7. A refrigerator equipment data simulation and instruction interactive simulation system according to claim 1, characterized in that: The S6 specifically includes: S61, a data processing center module receives and processes equipment working status data from the refrigerator equipment, including historical equipment working status data, real-time equipment working status data and optimization control instructions, and forms a data format suitable for virtual simulation processing after preprocessing; S62, a virtual simulation model building module, used to build a virtual simulation model of the refrigerator equipment, based on the working principle and operating characteristics of the refrigerator equipment, simulating the working state of the equipment under different environments and control conditions; S63, a simulation execution module, performing simulation execution according to the virtual simulation model and the real-time equipment working status data input, wherein the simulation execution result includes the predicted values ​​of various equipment operating parameters in the future time period and the response of the equipment under various control instructions; S64, a control instruction verification module, used to verify the execution effect of the control instruction generated by the optimization control generation module in the virtual simulation environment, and to judge whether the control instruction meets the expected goal by comparing the error between the simulation result and the target state; S65, a user operation simulation module is used to provide an interactive operation interface for the user, through which the user inputs control commands, modifies equipment operating parameters or monitors simulation results.

Images