Automatic control method and system for constant-temperature test room

Abstract

The invention relates to the field of temperature control, in particular to an automatic control method and system for a constant-temperature test room. The method comprises the following steps: acquiring real-time indoor operation monitoring parameters and external environment multi-dimensional data of a constant-temperature test room; performing indoor operation state analysis on the real-time indoor operation monitoring parameters, and constructing a laboratory dynamic state space model; carrying out multi-time-point environment temperature fluctuation calculation on the external environment multi-dimensional data, and carrying out nonlinear correlation learning to generate indoor state-environment nonlinear correlation characteristics; carrying out dynamic temperature evolution simulation on the laboratory dynamic state space model based on the indoor state-environment nonlinear correlation characteristics, and carrying out dynamic temperature evolution prediction to obtain temperature prediction values of a plurality of regions; constant-temperature deviation compensation calculation is carried out on the temperature prediction values of the multiple areas, then intelligent temperature control compensation is carried out, and an intelligent temperature control strategy is constructed; according to the invention, efficient and accurate constant-temperature automatic control is realized.

Description

Technical Field

[0001] The invention relates to the field of temperature control, and in particular to an automatic control method and system for a constant temperature test chamber. Background Art

[0002] As an important experimental equipment in various scientific research, production and quality inspection fields, the constant temperature laboratory is widely used in temperature control experiments in materials, electronics, chemistry and other industries. The main function of the constant temperature laboratory is to provide a temperature-stable and precisely controlled environment to ensure that the temperature factors in the experiment do not interfere with the test results. During the long-term continuous operation of the constant temperature laboratory, the temperature control system will be unstable due to environmental changes, equipment aging and other factors. For example, the temperature control equipment is not adjusted in time, the temperature fluctuates greatly, or the temperature field is unevenly distributed, which will directly affect the accuracy and repeatability of the experiment. Traditional control methods are often difficult to accurately monitor and adjust the temperature changes in the laboratory in real time, especially under a variety of complex conditions, manual adjustment operations cannot be responded to in time. Therefore, in response to the automation control needs of the constant temperature laboratory, a more intelligent, efficient and precise automation control method is urgently needed to improve the accuracy, stability and experimental efficiency of temperature control, and ensure that the test environment can be continuously and stably maintained within the set temperature range, thereby improving the reliability and consistency of the test data. Summary of the invention

[0003] In order to solve the above technical problems, the present invention proposes an automatic control method and system for a constant temperature test chamber to solve at least one of the above technical problems.

[0004] To achieve the above object, the present invention provides an automatic control method for a constant temperature test chamber, comprising the following steps: Step S1: obtaining real-time indoor operation monitoring parameters of the constant temperature test room and multi-dimensional data of the external environment; performing indoor operation state analysis on the real-time indoor operation monitoring parameters, and constructing a dynamic state space model of the test room; Step S2: Calculate the ambient temperature fluctuations at multiple time points on the multi-dimensional data of the external environment, and perform nonlinear association learning to generate indoor state-environment nonlinear association features; Step S3: based on the indoor state-environment nonlinear correlation characteristics, the dynamic temperature evolution simulation is performed on the dynamic state space model of the test room, and the dynamic temperature evolution prediction is performed to obtain the temperature prediction values ​​of multiple areas; Step S4: performing constant temperature deviation compensation calculation on the temperature prediction values ​​of multiple regions, and then performing intelligent temperature control compensation to construct an intelligent temperature control strategy; Step S5: Based on the intelligent temperature control strategy, the real-time operation power of multiple devices is calculated, and energy consumption optimization decisions are made to build a dynamic energy consumption optimization strategy; Step S6: Perform intelligent collaborative control optimization according to the intelligent temperature control strategy and the dynamic energy consumption optimization strategy, and build a constant temperature collaborative control model to perform constant temperature automatic control operations.

[0005] The present invention can understand the real-time operation status of the laboratory through real-time monitoring parameter analysis, provide data support for subsequent control, construct a dynamic state space model to help describe the evolution law of the internal state of the laboratory, and provide a basis for the design of control strategies. The calculation of multi-time point ambient temperature fluctuations can reveal the changing law of the external environment and provide a reference for temperature prediction. The complex relationship between the indoor state and the external environment can be discovered through nonlinear association learning, providing a basis for subsequent temperature control. The temperature evolution simulation based on nonlinear association characteristics can simulate the temperature change of the laboratory and provide a reference for prediction. The dynamic temperature evolution prediction can predict the temperature change trend in advance and help to formulate an effective temperature control strategy. The constant temperature deviation compensation and the construction of the intelligent temperature control strategy can effectively adjust the temperature deviation and improve the constant temperature performance. The construction of the intelligent temperature control strategy helps to achieve precise temperature control and improve the stability and accuracy of the laboratory. The real-time operation power calculation of multiple devices can monitor the energy consumption of the equipment and provide data support for energy consumption optimization. The formulation of the dynamic energy consumption optimization strategy can adjust the energy consumption according to the real-time demand and improve the energy utilization efficiency. The intelligent collaborative control optimization can realize the collaborative work between the devices and improve the overall control efficiency. The construction of the constant temperature collaborative control model helps to realize the constant temperature automatic control operation, improve the work efficiency and reduce human intervention.

[0006] Preferably, step S1 comprises the following steps: Step S11: obtaining real-time indoor operation monitoring parameters of the constant temperature test room and multi-dimensional data of the external environment; Step S12: performing indoor operation status analysis on the real-time indoor operation monitoring parameters to generate multi-dimensional indoor state features; Step S13: Analyze the indoor space structure of the constant temperature test room and extract the indoor space structure characteristics; Step S14: dividing the indoor space structure features into space structure regions, thereby obtaining a plurality of indoor space regions; Step S15: performing regional state feature mapping on multiple indoor space regions based on the multi-dimensional indoor state feature to obtain a state feature mapping space region; Step S16: Perform dynamic state modeling on the state feature mapping space area to construct a dynamic state space model of the laboratory.

[0007] The present invention can realize comprehensive monitoring and understanding of the current state of the constant temperature test room by acquiring the real-time indoor operation monitoring parameters and multi-dimensional data of the external environment of the constant temperature test room. Regularly acquiring these data is helpful to establish historical data records, providing a basis for subsequent analysis and control decisions. By analyzing the real-time indoor operation monitoring parameters, multi-dimensional indoor state characteristics can be generated, including temperature, humidity, air quality, etc., so as to comprehensively describe the internal state of the test room. These characteristics can reveal the changing trend of the internal state of the test room, and provide data support for subsequent control strategies and optimization. By analyzing the indoor space structure of the constant temperature test room, the layout, ventilation conditions, heat transfer and other characteristics of different areas in the test room can be understood. These analysis results are helpful to determine the correlation between various areas, and provide a basis for subsequent area division and state mapping. The internal spatial structure characteristics can be analyzed and divided in detail, and the laboratory can be divided into multiple independent areas, such as experimental area, control area, ventilation area, etc. The regional division helps to better understand and manage the characteristics and needs of different areas, and provide a basis for subsequent state feature mapping and model construction. By mapping the multi-dimensional indoor state characteristics to each spatial area, the correlation between the indoor state and the spatial structure can be established. Through mapping, the changes in the internal state of different areas can be better understood, which provides a basis for subsequent dynamic state modeling and control strategy formulation. Constructing the dynamic state space model of the laboratory can comprehensively describe the state evolution law of each area of ​​the laboratory, including temperature changes, air flow, etc., which provides an important basis for the automated control of the constant temperature laboratory, enabling the control system to respond to state changes more intelligently and achieve accuracy and stability of temperature control.

[0008] Preferably, the specific steps of step S12 are: The real-time indoor operation monitoring parameters include temperature parameters, humidity parameters, air pressure parameters and indoor lighting parameters; Identify the indoor temperature distribution of temperature parameters and extract indoor temperature distribution data; Perform time series temperature change analysis on indoor temperature distribution data to generate indoor temperature distribution change data; The humidity parameters are used to calculate the average space humidity, thereby obtaining the average space humidity; Conduct air pressure fluidity analysis on air pressure parameters to generate indoor air pressure fluidity characteristics; Calculate the light intensity of indoor light parameters to generate indoor light intensity values; Perform spatial distribution analysis on indoor light intensity values ​​to generate spatial distribution data of light intensity; Multi-dimensional state feature mining is performed on indoor temperature distribution change data, spatial average humidity, indoor air pressure fluidity characteristics and light intensity spatial distribution data to generate multi-dimensional indoor state features.

[0009] The present invention helps to comprehensively monitor the environmental conditions of the laboratory by acquiring real-time data of parameters such as temperature, humidity, air pressure and light. These parameters can provide detailed information about the internal environment of the laboratory and provide basic data for subsequent analysis and control. Identifying and extracting indoor temperature distribution data helps to understand the heat distribution in different areas and provide a reference for temperature control and regulation. Analysis of temperature changes in different time periods can reveal the periodic or trend changes in the temperature inside the laboratory and provide support for the formulation of temperature control strategies. Calculating the average humidity of the space and analyzing the air pressure fluidity can help understand the humidity and air pressure conditions inside the laboratory and provide a reference for the maintenance of comfort and experimental conditions. Combining temperature distribution changes, average humidity of the space, air pressure fluidity and light intensity data to perform multi-dimensional state feature mining can comprehensively describe the environmental state of the laboratory. The generation of these features helps to establish a state model of the laboratory and provide a more accurate state monitoring and control basis for the automated control system.

[0010] Preferably, step S2 specifically comprises the following steps: Step S21: performing multi-time point ambient temperature fluctuation calculation on the multi-dimensional data of the external environment to generate ambient temperature fluctuation data at multiple time points; Step S22: performing time series fluctuation fitting on the ambient temperature fluctuation data at multiple time points to construct an ambient temperature fluctuation curve; Step S23: Evolving the time series state change trend of the multi-dimensional indoor state features to generate indoor state change trend features; Step S24: performing nonlinear association learning on the indoor state change trend characteristics according to the ambient temperature fluctuation curve to generate indoor state-environment nonlinear association characteristics.

[0011] The present invention calculates the temperature fluctuation of the multi-dimensional data of the external environment, so as to understand the fluctuation of the ambient temperature at different time points, provide a reference for the responsiveness of the temperature control of the laboratory, and generate the ambient temperature fluctuation data at multiple time points, which is helpful to reveal the changing law of the ambient temperature and provide a basis for the formulation of the control strategy. By performing time series fluctuation fitting on the ambient temperature fluctuation data at multiple time points, a curve of the ambient temperature fluctuation can be constructed to show the trend and periodicity of the temperature change. This curve is helpful to predict the changing trend of the ambient temperature and provide more information for the response of the laboratory temperature control system. By performing time series state change trend evolution analysis on the multi-dimensional indoor state characteristics, the trend characteristics of the indoor state change can be generated to reveal the regularity of the state change. These characteristics are helpful to understand the changing trend of the internal state of the laboratory and provide a basis for the adjustment and optimization of the control system. By performing nonlinear correlation learning on the indoor state change trend characteristics according to the ambient temperature fluctuation curve, the complex relationship between the indoor state and the external environment can be revealed. Generating indoor state-environment nonlinear correlation characteristics is helpful to establish a more accurate state model and improve the responsiveness and control accuracy of the automatic control system to environmental changes.

[0012] Preferably, step S3 specifically comprises the following steps: Step S31: based on the indoor state-environment nonlinear correlation characteristics, the dynamic temperature evolution simulation is performed on the dynamic state space model of the test room to construct a dynamic evolution twin model; Step S32: performing regional temperature evolution analysis on the dynamic evolution twin model to generate regional temperature evolution response data; Step S33: performing regional temperature distribution identification on the regional temperature evolution response data, and extracting temperature evolution data of different regions; Step S34: performing deep temperature change learning on the temperature evolution data of different regions, thereby generating temperature change laws of different regions; Step S35: According to the temperature variation rules of different regions, the dynamic temperature evolution prediction is performed on the dynamic state space model of the test room to obtain the temperature prediction values ​​of multiple regions.

[0013] The present invention can simulate the dynamic evolution process of the temperature in the test room by constructing a dynamic state space model based on the indoor state-environment nonlinear correlation characteristics, and provide a comprehensive understanding of the temperature change. Constructing a dynamic evolution twin model helps to monitor and predict the temperature change in the test room in real time, and provides a dynamic adjustment basis for the automatic control system. By performing regional temperature evolution analysis on the dynamic evolution twin model, temperature evolution response data of different regions can be generated to reveal the temperature change trend of different regions. The regional temperature evolution response data helps to understand the temperature distribution of each region inside the test room and provide support for regional temperature control. Identifying and extracting temperature evolution data of different regions can help understand the temperature change characteristics of each region and provide a basis for the formulation of regional temperature control strategies. These data help to distinguish the temperature change laws of different regions and provide support for personalized temperature regulation. By learning the temperature evolution data of different regions through deep temperature changes, the temperature change laws of different regions can be generated to reveal the unique characteristics of each region. Learning the temperature change laws of different regions helps to formulate personalized temperature adjustment strategies for each region and improve the accuracy of temperature control inside the test room. By learning the temperature evolution data of different regions through deep temperature changes, the temperature change laws of different regions can be generated to reveal the unique characteristics of each region. Learning the temperature variation patterns in different areas helps to develop personalized temperature regulation strategies for each area and improve the accuracy of temperature control inside the laboratory.

[0014] Preferably, the specific steps of step S4 are: Step S41: extracting a preset laboratory constant temperature value based on the real-time test log; Step S42: Calculating the temperature deviation of each region for the temperature prediction values ​​of the multiple regions based on the preset laboratory constant temperature value to obtain a constant temperature deviation value for each region; Step S43: performing constant temperature deviation compensation calculation on the constant temperature deviation value of each area to generate a constant temperature deviation compensation parameter for each area; Step S44: finely adjusting the constant temperature deviation compensation parameters of each area to obtain the deviation compensation optimization value of each area; Step S45: Perform intelligent temperature control compensation on the dynamic state space model of the laboratory according to the deviation compensation optimization value of each area, and construct an intelligent temperature control strategy.

[0015] The present invention extracts the preset laboratory constant temperature value through the real-time test log, realizes the accurate acquisition of the set temperature of the laboratory, provides basic data for the subsequent control strategy, calculates the deviation between the temperature prediction value and the actual value of multiple regions based on the preset laboratory constant temperature value, obtains the constant temperature deviation value of each region, and reveals the temperature control accuracy of each region. The regional temperature deviation calculation is helpful to understand the temperature control status of different regions, and provides a basis for the subsequent compensation calculation and adjustment. The constant temperature deviation value of each region is compensated and calculated to generate a constant temperature deviation compensation parameter for adjusting the temperature control deviation of each region and improving the accuracy of temperature control. The constant temperature deviation compensation calculation is effective. It helps to optimize the temperature control of each area in the laboratory, improve the stability of the overall ambient temperature, make fine error adjustments to the constant temperature deviation compensation parameters, obtain the deviation compensation optimization value for each area, and improve the accuracy and stability of temperature control. By optimizing the deviation compensation parameters, fine adjustment of the temperature control system is achieved, and the efficiency and accuracy of temperature control are improved. According to the deviation compensation optimization value for each area, intelligent temperature control compensation is performed on the dynamic state space model of the laboratory, and an intelligent temperature control strategy is constructed to achieve precise control of the laboratory temperature. Intelligent temperature control compensation helps to optimize the response speed and stability of the temperature control system and improve the constant temperature performance and control accuracy of the laboratory environment.

[0016] Preferably, the specific steps of step S5 are: Step S51: performing real-time temperature control on the constant temperature test room based on the intelligent temperature control strategy, and extracting the multi-modal energy consumption parameters of the current test room; Step S52: performing real-time operation power calculation of multiple devices on the multi-modal energy consumption parameters of the current laboratory, and extracting operation power parameters of multiple devices; Step S53: performing a time-series power situation analysis on the operating power parameters of the multiple devices to generate a time-series power situation of the multiple devices; Step S54: Make energy consumption optimization decisions on the sequential power status of multiple devices and build a dynamic energy consumption optimization strategy.

[0017] The present invention realizes real-time temperature control of a constant temperature test room based on an intelligent temperature control strategy, ensures the temperature stability in the test room, extracts multimodal energy consumption parameters of the current test room, provides basic data for subsequent energy consumption optimization, performs real-time operating power calculation of multiple devices on the multimodal energy consumption parameters, extracts the operating power parameters of multiple devices, and understands the energy consumption of each device. The operating power calculation of multiple devices helps to monitor the real-time energy consumption status of the devices and provides data support for energy consumption optimization decisions. The operating power parameters of multiple devices are subjected to time-series power situation analysis, and the time-series power situation of multiple devices is generated to reveal the changing trend of the energy consumption of the devices. The time-series power situation analysis helps to discover the changing law of the energy consumption of the devices and provides time-series data support for the energy consumption optimization decision. Energy consumption optimization decisions are made based on the time-series power situation of multiple devices, and a dynamic energy consumption optimization strategy is constructed to realize effective management and optimization of the energy consumption of the test room. The energy consumption optimization decision can help improve the energy utilization efficiency of the test room, reduce operating costs, and reduce energy waste, thereby achieving the goal of environmental protection and energy saving.

[0018] Preferably, the specific steps of step S6 are: Step S61: performing multi-scheme collaborative strategy simulation according to the intelligent temperature control strategy and the dynamic energy consumption optimization strategy, and extracting multiple collaborative simulation schemes; Step S62: performing dynamic control simulation on the constant temperature test chamber based on multiple collaborative simulation schemes to generate multiple test chamber control simulation data; Step S63: Comprehensively evaluate the control simulation data of multiple laboratories one by one to obtain a comprehensive evaluation of each solution; Step S64: extracting the optimal collaborative simulation scheme based on the comprehensive evaluation of each scheme; Step S65: Perform intelligent collaborative control optimization on the optimal collaborative simulation solution and build a constant temperature collaborative control model to perform constant temperature automation control operations.

[0019] The present invention performs multi-scheme collaborative strategy simulation according to the intelligent temperature control strategy and the dynamic energy consumption optimization strategy, extracts multiple collaborative simulation schemes, and explores the influence of different strategy combinations on laboratory control. Multi-scheme collaborative strategy simulation helps to find the best control strategy combination to achieve the optimal performance of laboratory control. Based on multiple collaborative simulation schemes, a dynamic control simulation is performed on the constant temperature laboratory, and multiple laboratory control simulation data are generated to simulate the laboratory behavior under different control strategies. Dynamic control simulation helps to evaluate the effects of various control schemes and provide data support for selecting the best scheme. A comprehensive evaluation of multiple laboratory control simulation data is performed scheme by scheme, and a comprehensive evaluation of each scheme is obtained to evaluate the pros and cons of each scheme. The comprehensive evaluation of the scheme helps to compare the comprehensive effects of different control schemes and provide an objective basis for selecting the best scheme. The optimal collaborative simulation scheme is extracted based on the comprehensive evaluation of each scheme, and the optimal control scheme is determined for laboratory control. Extracting the optimal scheme can improve the efficiency of laboratory control, optimize energy consumption management, and improve the overall performance of the system. The optimal collaborative simulation scheme is optimized for intelligent collaborative control, a constant temperature collaborative control model is constructed, and intelligent constant temperature automatic control operation is realized. Intelligent collaborative control optimization can improve the intelligence level of laboratory control, optimize resource utilization, and improve the stability and efficiency of the control system.

[0020] In this specification, an automatic control system of a constant temperature test chamber is provided, which is used to execute the automatic control method of the constant temperature test chamber as described above, including: The operation status module is used to obtain the real-time indoor operation monitoring parameters of the constant temperature test room and the multi-dimensional data of the external environment; perform indoor operation status analysis on the real-time indoor operation monitoring parameters and construct a dynamic state space model of the test room; The nonlinear association module is used to calculate the ambient temperature fluctuations at multiple time points based on the multi-dimensional data of the external environment, and to perform nonlinear association learning to generate indoor state-environment nonlinear association features; The temperature evolution prediction module is used to simulate the dynamic temperature evolution of the dynamic state space model of the test room based on the indoor state-environment nonlinear correlation characteristics, and to predict the dynamic temperature evolution to obtain the temperature prediction values ​​of multiple areas; Intelligent temperature control module, which is used to calculate the constant temperature deviation compensation for the temperature prediction values ​​of multiple areas, and then perform intelligent temperature control compensation to build an intelligent temperature control strategy; Energy consumption optimization module, which is used to calculate the real-time operating power of multiple devices based on intelligent temperature control strategies, make energy consumption optimization decisions, and build dynamic energy consumption optimization strategies; The collaborative control module is used to perform intelligent collaborative control optimization according to the intelligent temperature control strategy and dynamic energy consumption optimization strategy, build a constant temperature collaborative control model, and execute constant temperature automatic control operations.

[0021] The present invention realizes comprehensive monitoring and analysis of the laboratory operation status by acquiring real-time indoor operation monitoring parameters and multi-dimensional data of the external environment, constructs a dynamic state space model of the laboratory, helps to understand the changing law of the internal state of the laboratory, and provides a basis for subsequent intelligent control. The multi-dimensional data of the external environment are used to perform multi-time point ambient temperature fluctuation calculation and nonlinear correlation learning, and extract the nonlinear correlation characteristics of the indoor state-environment. The generated nonlinear correlation characteristics help to more accurately understand the complex relationship between indoor temperature changes and the external environment. Based on the nonlinear correlation characteristics, the dynamic temperature evolution simulation and prediction are performed on the dynamic state space model of the laboratory to obtain temperature prediction values ​​of multiple areas. The temperature evolution prediction helps to predict the temperature change trend of each area in advance, provides a basis for the formulation of intelligent temperature control strategies, and can be used for multiple The temperature prediction values ​​of each area are used to perform constant temperature deviation compensation calculation and intelligent temperature control compensation, and an intelligent temperature control strategy is constructed to achieve precise control of the laboratory temperature. The intelligent temperature control strategy can effectively reduce temperature fluctuations and improve the stability and energy efficiency of the constant temperature laboratory. Based on the intelligent temperature control strategy, the real-time operating power of multiple devices is calculated, energy consumption optimization decisions are implemented, and a dynamic energy consumption optimization strategy is constructed to reduce the energy consumption cost of the laboratory. The energy consumption optimization module can effectively manage equipment energy consumption, improve energy utilization efficiency, and reduce operating costs. According to the intelligent temperature control strategy and the dynamic energy consumption optimization strategy, intelligent collaborative control optimization is performed, a constant temperature collaborative control model is constructed, and constant temperature automation control operations are realized. The collaborative control module can coordinate the work between various subsystems, optimize the overall control effect, and improve the overall performance of the laboratory automation control system. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] Figure 1 A schematic flow chart of the steps of an automated control method for a constant temperature test chamber of the present invention; Figure 2 Detailed implementation flow chart of step S1; Figure 3 Detailed implementation flow chart of step S2; Figure 4 Detailed implementation flow chart of step S3. DETAILED DESCRIPTION

[0023] It should be understood that the specific embodiments described herein are only used to explain the present invention, and are not used to limit the present invention.

[0024] The present application example provides an automated control method and system for a constant temperature test room. The execution subject of the automated control method and system for the constant temperature test room includes but is not limited to: mechanical equipment, data processing platform, cloud server node, network upload device, etc. equipped with the system can be regarded as the general computing node of the present application, and the data processing platform includes but is not limited to: at least one of an audio and image management system, an information management system, and a cloud data management system.

[0025] See also Figures 1 to 4 The present invention provides an automatic control method for a constant temperature test chamber, and the automatic control method for the constant temperature test chamber comprises the following steps: Step S1: obtaining real-time indoor operation monitoring parameters of the constant temperature test room and multi-dimensional data of the external environment; performing indoor operation state analysis on the real-time indoor operation monitoring parameters, and constructing a dynamic state space model of the test room; Step S2: Calculate the ambient temperature fluctuations at multiple time points on the multi-dimensional data of the external environment, and perform nonlinear association learning to generate indoor state-environment nonlinear association features; Step S3: based on the indoor state-environment nonlinear correlation characteristics, the dynamic temperature evolution simulation is performed on the dynamic state space model of the test room, and the dynamic temperature evolution prediction is performed to obtain the temperature prediction values ​​of multiple areas; Step S4: performing constant temperature deviation compensation calculation on the temperature prediction values ​​of multiple regions, and then performing intelligent temperature control compensation to construct an intelligent temperature control strategy; Step S5: Based on the intelligent temperature control strategy, the real-time operation power of multiple devices is calculated, and energy consumption optimization decisions are made to build a dynamic energy consumption optimization strategy; Step S6: Perform intelligent collaborative control optimization according to the intelligent temperature control strategy and the dynamic energy consumption optimization strategy, and build a constant temperature collaborative control model to perform constant temperature automatic control operations.

[0026] The present invention can understand the real-time operation status of the laboratory through real-time monitoring parameter analysis, provide data support for subsequent control, construct a dynamic state space model to help describe the evolution law of the internal state of the laboratory, and provide a basis for the design of control strategies. The calculation of multi-time point ambient temperature fluctuations can reveal the changing law of the external environment and provide a reference for temperature prediction. The complex relationship between the indoor state and the external environment can be discovered through nonlinear association learning, providing a basis for subsequent temperature control. The temperature evolution simulation based on nonlinear association characteristics can simulate the temperature change of the laboratory and provide a reference for prediction. The dynamic temperature evolution prediction can predict the temperature change trend in advance and help to formulate an effective temperature control strategy. The constant temperature deviation compensation and the construction of the intelligent temperature control strategy can effectively adjust the temperature deviation and improve the constant temperature performance. The construction of the intelligent temperature control strategy helps to achieve precise temperature control and improve the stability and accuracy of the laboratory. The real-time operation power calculation of multiple devices can monitor the energy consumption of the equipment and provide data support for energy consumption optimization. The formulation of the dynamic energy consumption optimization strategy can adjust the energy consumption according to the real-time demand and improve the energy utilization efficiency. The intelligent collaborative control optimization can realize the collaborative work between the devices and improve the overall control efficiency. The construction of the constant temperature collaborative control model helps to realize the constant temperature automatic control operation, improve the work efficiency and reduce human intervention.

[0027] In the embodiment of the present invention, refer to Figure 1 , is a schematic flow chart of the steps of an automatic control method for a constant temperature test chamber of the present invention. In this example, the steps of the automatic control method for the constant temperature test chamber include: Step S1: obtaining real-time indoor operation monitoring parameters of the constant temperature test room and multi-dimensional data of the external environment; performing indoor operation state analysis on the real-time indoor operation monitoring parameters, and constructing a dynamic state space model of the test room; In this embodiment, suitable sensors and monitoring equipment are selected, such as temperature sensors (PT100, DHT22), humidity sensors (such as SHT3x series), light sensors, air pressure sensors, etc. These sensors should have high precision and stability. Sensors are arranged at different locations in the laboratory to ensure coverage of the entire space, especially in key areas (such as near experimental equipment, vents, etc.). Microcontrollers (such as Arduino, RaspberryPi) or dedicated data acquisition equipment are used to read sensor data regularly, and real-time data is transmitted to a central server or cloud platform through a wireless network (such as Wi-Fi, LoRa) or a wired connection. Environmental monitoring equipment, such as a weather station, is installed outside the laboratory to monitor external parameters such as temperature, humidity, wind speed, and radiation intensity. These devices should have a communication interface compatible with the indoor data acquisition system. The data of the external environmental sensors are integrated into the indoor monitoring system to ensure that the real-time data is stored in the same database. Data fusion technology can be used to synchronize the timestamps of indoor and outdoor data, and the acquired real-time monitoring data is preprocessed, including removing outliers, filling missing values, and standardizing. , use statistical methods (such as mean and standard deviation) and machine learning techniques (such as anomaly detection algorithms) to identify and deal with data problems. According to the laboratory's operating requirements and monitoring data, select appropriate state variables for analysis. For example, select indoor temperature, humidity, air flow velocity, etc. as state variables to reflect the operating status of the indoor environment. Use data analysis tools (such as Pandas and NumPy in Python) to perform statistical analysis on real-time data, identify the relationship between parameters such as temperature and humidity, and analyze the changing trend of indoor operating status. Select the appropriate type of dynamic model according to the characteristics of the indoor environment. Commonly used models include linear state space models, nonlinear dynamic models, or models based on physical principles (such as heat conduction models). Use system identification methods (such as subspace methods and least squares methods) to estimate model parameters. Perform regression analysis on historical data or use optimization algorithms to adjust model parameters so that it can accurately predict indoor environmental changes. Use the reserved test data set to verify the constructed model, compare the model output with the actual monitoring data, and evaluate the prediction ability of the model. Indicators such as root mean square error (RMSE) can be used to quantify model performance.

[0028] Step S2: Calculate the ambient temperature fluctuations at multiple time points on the multi-dimensional data of the external environment, and perform nonlinear association learning to generate indoor state-environment nonlinear association features; In this embodiment, the external environment temperature data is extracted from the database, including multi-dimensional data such as the ambient temperature, humidity, wind speed, etc. at multiple time points (such as hours, days, and weeks). These data should include historical records of at least several weeks to several months to facilitate the analysis of fluctuations and trends. The uniform format of the data is ensured, including the standardization of timestamps and the consistency of numerical units (such as the temperature unit is unified as degrees Celsius). The data is organized into a table format to facilitate subsequent analysis. The sliding window technology is used to calculate the temperature fluctuations in different time periods. For example, a 7-day sliding window is set to calculate the weekly temperature fluctuations. The following steps can be taken: the average temperature, maximum temperature, minimum temperature and standard deviation in each window are calculated, and the temperature change rate of each window is recorded. This can be achieved by comparing the average temperature of the current window with the average temperature of the previous window. Fluctuation features such as the standard deviation, change rate and periodicity of the temperature are extracted. These features will be used to describe the temperature fluctuations of the external environment. The features to be used for nonlinear association learning are determined, including the extracted temperature fluctuation features and other external environment data (humidity , wind speed, etc.), combine the extracted features with indoor monitoring parameters (such as indoor temperature, humidity, etc.) to form a data set containing multiple features, ensure that each row of the data set corresponds to the same timestamp, select a machine learning algorithm suitable for processing nonlinear relationships, such as random forest, support vector machine (SVM) or neural network, select a suitable model according to the complexity of the data and the number of features, use the prepared data set to train the selected nonlinear model, use the cross-validation method to evaluate the performance of the model and prevent overfitting, optimize the model's hyperparameters through grid search (GridSearch) or random search (RandomSearch) to improve the model's prediction accuracy and generalization ability, after the model training is completed, use the trained model to predict new external environment data to generate indoor state-environment nonlinear correlation features, which reflect the complex relationship between indoor temperature and external environmental factors, and store the generated indoor state-environment nonlinear correlation features in the database for subsequent dynamic state space model construction and control strategy optimization.

[0029] Step S3: based on the indoor state-environment nonlinear correlation characteristics, the dynamic temperature evolution simulation is performed on the dynamic state space model of the test room, and the dynamic temperature evolution prediction is performed to obtain the temperature prediction values ​​of multiple areas; In this embodiment, features for model training are extracted from previously generated indoor state-environment nonlinear correlation features. These features should include external environmental factors (such as temperature, humidity, wind speed) and their corresponding indoor monitoring data (such as indoor temperature and humidity). The timestamps of the data are ensured to be consistent to form a time series data set for subsequent dynamic temperature evolution simulation. The feature data are standardized or normalized to make the numerical ranges of different features consistent to improve the stability and accuracy of model training. A suitable dynamic state space model is selected, such as a Kalman filter model or a nonlinear state space model (such as an extended Kalman filter EKF) to describe the dynamic evolution process of indoor temperature. The model parameters are initialized according to historical data, including a state transfer matrix, an observation matrix, and a covariance matrix of process noise and measurement noise. A state transfer equation is defined to describe how the indoor temperature changes over time. The model is used for dynamic simulation from the initial state to the ambient temperature. Starting from the state, the temperature values ​​of multiple time points in the future are obtained through iterative calculation, the state at each moment is recorded, and a temperature prediction model is constructed based on the dynamic state space model. The input is the current state and external environmental characteristics, and the output is the temperature prediction values ​​of multiple time points in the future. The model is used to predict the temperature of future time periods (such as the next few hours or days). The following steps can be taken: input the current indoor state and external environmental characteristics, run the prediction algorithm, obtain the temperature prediction value of the next moment, gradually iterate and predict the temperature of subsequent moments to form a prediction sequence, save the temperature prediction value of each area, and make sure to record the timestamp and the corresponding area identifier for subsequent analysis and decision-making. By comparing with the actual monitoring data, the prediction accuracy of the model is evaluated, and performance is evaluated using indicators such as root mean square error (RMSE) and mean absolute error (MAE). According to the evaluation results, the model parameters or structure are adjusted to optimize the prediction performance to improve the robustness and accuracy of the model.

[0030] Step S4: performing constant temperature deviation compensation calculation on the temperature prediction values ​​of multiple regions, and then performing intelligent temperature control compensation to construct an intelligent temperature control strategy; In this embodiment, the temperature prediction values ​​of multiple regions are extracted from the previous dynamic temperature evolution prediction, ensuring that the prediction value of each region is compared with the actually set constant temperature target value to prepare for the subsequent deviation calculation. For each region, the temperature deviation is calculated, and the deviation value of each region is recorded in the database, including the timestamp and region identifier, for subsequent analysis and compensation calculation. According to the calculated temperature deviation, an intelligent temperature control strategy is designed. The following methods can be used: PID controller: implements proportional (P), integral (I), and differential (D) control, and adjusts the output of the device to compensate for the deviation. Fuzzy control: For nonlinear and complex systems, a fuzzy logic controller is used to generate control rules based on the deviation value and the rate of change. For each region, the required compensation amount is calculated based on the deviation value. According to the compensation calculation results, set the operating status and target value of each device, for example, set the operating frequency, start and stop status of the heater and cooler, etc., implement the intelligent temperature control strategy into the actual control system, and adjust the operating status of the equipment in real time through the controller to achieve temperature compensation. Feedback mechanism: establish a real-time monitoring system to continuously track the indoor temperature and equipment status to ensure that the strategy can be adjusted dynamically. After implementation, continuously monitor the actual temperature changes in each area to evaluate the effect of the intelligent temperature control strategy, record the temperature data before and after implementation for comparison, and use indicators such as temperature deviation mean and response time to evaluate the control effect and judge the effectiveness of the intelligent temperature control strategy. According to the evaluation results, adjust the control parameters (such as PID gain) or optimize the control algorithm to improve the stability and response speed of the system.

[0031] Step S5: Based on the intelligent temperature control strategy, the real-time operation power of multiple devices is calculated, and energy consumption optimization decisions are made to build a dynamic energy consumption optimization strategy; In this embodiment, a smart meter or power monitor is installed on each device in the laboratory. These devices can record parameters such as voltage, current and power factor in real time. The real-time power data is transmitted to the central monitoring system through the Internet of Things platform (such as MQTT or HTTP) to ensure the real-time nature of the data. The power calculation results of all devices are integrated into a data set, and the timestamp is recorded for subsequent analysis. The energy consumption data of each device is counted by time periods such as hours, days, and weeks, and the total energy consumption and average power per unit time are calculated. Energy consumption reports are generated regularly to record the energy consumption trends and changes of each device to facilitate analysis and decision-making, and determine the goals of energy consumption optimization, such as reducing overall energy consumption, reducing energy consumption during peak hours, and improving equipment utilization. According to the real-time power data, a dynamic scheduling strategy is designed to adjust the operating time and load of the equipment. For example, high-efficiency equipment is given priority during peak energy consumption periods, or the operating status of the equipment is dynamically adjusted according to demand. A suitable optimization algorithm is selected, such as linear programming, genetic algorithm, or dynamic programming, to construct Energy consumption optimization model, set optimization constraints, such as equipment operating time, minimum and maximum load limits, temperature control requirements, etc., establish a dynamic energy consumption optimization model, input is real-time power data, equipment status and external environment data, output is optimized equipment operation strategy and load distribution, train and verify the optimization model to ensure that the model can effectively process actual data and give reasonable optimization suggestions, implement the optimized equipment operation strategy into the actual control system, adjust the start and stop status and load distribution of the equipment in real time to achieve dynamic management of energy consumption, set up a feedback monitoring system, track energy consumption data and equipment status in real time, ensure that the optimization strategy can be dynamically adjusted according to real-time data, after implementation, continuously monitor changes in energy consumption data, evaluate the effectiveness of the optimization strategy, record energy consumption comparison data before and after implementation, calculate the percentage of energy consumption reduction and cost savings, adjust the optimization strategy and model parameters according to the evaluation results, continuously improve the efficiency and effectiveness of energy consumption management, set up a regular review mechanism, and continuously monitor and optimize energy consumption management strategies.

[0032] Step S6: Perform intelligent collaborative control optimization according to the intelligent temperature control strategy and the dynamic energy consumption optimization strategy, and build a constant temperature collaborative control model to perform constant temperature automatic control operations.

[0033] In this embodiment, the control objectives are clearly defined, including keeping the indoor temperature within a set range, optimizing energy consumption, improving equipment efficiency, etc., and specific performance indicators are set, such as the allowable temperature fluctuation range, energy consumption target, and equipment response time, etc. All relevant data are collected, including real-time indoor temperature, external environmental data, equipment operating status, and energy consumption data, to ensure the integrity and consistency of the data for subsequent analysis. The collected data are cleaned, missing values ​​and outliers are processed, and the quality of the data is ensured. Standardization or normalization is performed to eliminate the impact of different data scales on the analysis results. A suitable control model is selected, such as a fuzzy control model, a PID control model, or a method based on model predictive control (MPC), and the input (such as temperature deviation, equipment status, external environmental data) and output (such as equipment start and stop, power regulation) of the model are determined. The model parameters are set according to historical data and expert experience. For example, in PID control, the proportional, integral, and differential gains are set, and a suitable optimization algorithm is selected. Methods (such as genetic algorithms, particle swarm optimization or reinforcement learning) are used to optimize control strategies. The objective function to be optimized is determined, such as minimizing energy consumption or temperature fluctuations. Algorithm codes are written to implement optimized control strategies. It is ensured that the algorithm can calculate and adjust the control strategy in real time to adapt to the changing environment and equipment status. A real-time monitoring system is implemented to continuously track the indoor temperature, external environment and equipment status, and to ensure that the monitoring data can be quickly fed back to the control model. According to the output of the intelligent collaborative control model, the operating status of the equipment is automatically adjusted, such as starting and stopping the heater or cooler, adjusting the operating speed of the fan, etc. The implementation effect is continuously monitored, and the control effect is evaluated by comparing the deviation between the actual indoor temperature and the set temperature. Energy consumption data is recorded, and the changes in energy consumption before and after implementation are calculated to evaluate the optimization effect. According to the evaluation results, the parameters of the control model and the optimization algorithm are regularly adjusted to improve the control performance and energy efficiency. A regular review mechanism is established to ensure that the intelligent collaborative control strategy can continuously adapt to environmental changes and changes in equipment status.

[0034] In this embodiment, refer to Figure 2 , is a flowchart of detailed implementation steps of step S1. In this embodiment, the detailed implementation steps of step S1 include: Step S11: obtaining real-time indoor operation monitoring parameters of the constant temperature test room and multi-dimensional data of the external environment; Step S12: performing indoor operation status analysis on the real-time indoor operation monitoring parameters to generate multi-dimensional indoor state features; Step S13: Analyze the indoor space structure of the constant temperature test room and extract the indoor space structure characteristics; Step S14: dividing the indoor space structure features into space structure regions, thereby obtaining a plurality of indoor space regions; Step S15: performing regional state feature mapping on multiple indoor space regions based on the multi-dimensional indoor state feature to obtain a state feature mapping space region; Step S16: Perform dynamic state modeling on the state feature mapping space area to construct a dynamic state space model of the laboratory.

[0035] In this embodiment, the indoor parameters that need to be monitored in real time are determined, including temperature, humidity, air pressure, light intensity, air flow rate, etc. It is also necessary to obtain external environmental data, such as outdoor temperature, humidity, wind speed, etc., and install appropriate sensors inside and outside the test room to ensure that the required multi-dimensional data can be collected in real time. For example, a DHT22 sensor is used to monitor temperature and humidity, and a light sensor is used to monitor light intensity. A data acquisition system (such as Arduino, RaspberryPi or a dedicated data acquisition device) is used to transmit the sensor data to the central processing system. The data should be collected at a certain time interval (such as every minute) and stored in the database. The real-time monitoring data is cleared. Clean the data, remove outliers and missing values, ensure the accuracy and completeness of the data, extract key features from the cleaned data, such as the average value and fluctuation range of temperature and humidity, and the change trend of air flow rate, use statistical analysis methods (such as mean and standard deviation) to extract and describe indoor state characteristics, apply multivariate analysis methods (such as principal component analysis PCA) to analyze the extracted state characteristics to identify the main factors affecting the indoor environment, collect the floor plan, elevation and 3D model data of the test room to ensure a clear understanding of the indoor space structure, use computer vision and image processing technology (such as OpenCV) to analyze indoor images, extract spatial features (such as room The indoor space is divided into multiple areas according to the defined standards, and the boundaries and characteristics of each area are recorded. Clustering algorithms (such as K-means) can be used to assist in dividing areas with similar characteristics. The multi-dimensional indoor state characteristics obtained from the indoor operation state analysis are mapped to each divided space area, and interpolation methods (such as Kriging or linear interpolation) are used to calculate the indoor climate. The state characteristics are spatially interpolated to generate a regional state characteristic map, and a state characteristic mapping model is established to ensure that the real-time monitoring data can be associated with the regional characteristics to facilitate subsequent analysis. According to the changes in spatial characteristics and state characteristics, an appropriate dynamic modeling method is selected, such as a state space model (StateSpaceModel) or a recursive neural network (RNN). The dynamic state space model is trained using historical data and real-time monitoring data to ensure that the model can capture the dynamic changes of indoor environmental characteristics. The accuracy of the model is evaluated using a test data set, and the performance of the model under different environmental conditions is analyzed. The model is regularly updated and optimized to adapt to environmental changes and new monitoring data.

[0036] In this embodiment, the specific steps of step S12 are: The real-time indoor operation monitoring parameters include temperature parameters, humidity parameters, air pressure parameters and indoor lighting parameters; Identify the indoor temperature distribution of temperature parameters and extract indoor temperature distribution data; Perform time series temperature change analysis on indoor temperature distribution data to generate indoor temperature distribution change data; The humidity parameters are used to calculate the average space humidity, thereby obtaining the average space humidity; Conduct air pressure fluidity analysis on air pressure parameters to generate indoor air pressure fluidity characteristics; Calculate the light intensity of indoor light parameters to generate indoor light intensity values; Perform spatial distribution analysis on indoor light intensity values ​​to generate spatial distribution data of light intensity; Multi-dimensional state feature mining is performed on indoor temperature distribution change data, spatial average humidity, indoor air pressure fluidity characteristics and light intensity spatial distribution data to generate multi-dimensional indoor state features.

[0037] In this embodiment, temperature data of various indoor locations are obtained from the real-time monitoring system. These data can be obtained by deploying temperature sensors. The collected temperature data are processed using an interpolation method (such as Kriging interpolation or bilinear interpolation) to generate an indoor temperature distribution map. A heat map visualization tool is used to display the temperature distribution of different locations to provide intuitive data for subsequent analysis. Key data, such as the highest temperature, lowest temperature, and mean value of each area, are extracted from the generated temperature distribution map to form a temperature distribution data set. The temperature data are sorted according to timestamps to form a time series data set to ensure that the data is arranged in chronological order. The rate of change of temperature over time is calculated. A simple difference method (current temperature minus temperature at the previous moment) can be used to analyze the change trend. Time series temperature change data is generated to record the temperature change at each time point for subsequent analysis and modeling. Humidity data of different locations are obtained from humidity sensors to ensure the accuracy and coverage of the data. The readings of all humidity sensors are collected to calculate the average humidity of the space. Real-time air pressure is obtained from the air pressure sensor. The pressure data can be collected to ensure that the air pressure information at different locations is recorded. The pressure change rate can be calculated using the differential method, and the trend of pressure change can be identified. The pressure fluidity characteristics, such as rising, falling, and stable states, can be recorded. The light intensity data at different locations in the room can be obtained from the light sensor. The light intensity value output by the sensor can be directly recorded to form a light intensity data set. The light intensity distribution diagram can be drawn using visualization tools (such as Matplotlib or Seaborn) to display the light intensity in different areas. The statistical characteristics such as the mean and standard deviation of the light intensity can be calculated to evaluate the uniformity and change of the light. The indoor temperature distribution change data, the average humidity of the space, the indoor air pressure fluidity characteristics, and the light intensity spatial distribution data can be integrated into a comprehensive data set. Clustering algorithms (such as K-means) or principal component analysis (PCA) can be used to mine multi-dimensional data, identify potential state feature patterns, and output multi-dimensional indoor state features, including the comprehensive characteristics of temperature, humidity, air pressure, and light, to facilitate subsequent decision-making and optimization.

[0038] In this embodiment, refer to Figure 3 , is a flowchart of detailed implementation steps of step S2. In this embodiment, the detailed implementation steps of step S2 include: Step S21: performing multi-time point ambient temperature fluctuation calculation on the multi-dimensional data of the external environment to generate ambient temperature fluctuation data at multiple time points; Step S22: performing time series fluctuation fitting on the ambient temperature fluctuation data at multiple time points to construct an ambient temperature fluctuation curve; Step S23: Evolving the time series state change trend of the multi-dimensional indoor state features to generate indoor state change trend features; Step S24: performing nonlinear association learning on the indoor state change trend characteristics according to the ambient temperature fluctuation curve to generate indoor state-environment nonlinear association characteristics.

[0039] In this embodiment, multiple temperature sensors (such as DS18B20 or DHT22) are installed in the external environment to ensure that the sensors can cover different climatic conditions and regions. Each sensor should be placed at different heights and positions to record temperature differences. Select a suitable microcontroller (such as Arduino or RaspberryPi) to read temperature data regularly. Set the sampling frequency, for example, once an hour, to ensure the timeliness of the data. The collected data can be sent to a cloud database (such as InfluxDB or MySQL) via the MQTT protocol or HTTP request for real-time storage and management. For each recorded time point t, calculate the temperature fluctuation, ΔT(t)=T(t)−mean(T), where T(t) is the temperature value at time point, t, and mean(T) is the average of all temperature values ​​in the time period. For each recorded time point, calculate the temperature fluctuation at that time point. In order to obtain the temperature fluctuation, the temperature value at each time point can be compared with the average temperature in the time period to determine the amplitude of the fluctuation. Ensure that all temperature fluctuation data are arranged in chronological order to form a complete time series data set. This step is the basis for accurate analysis. According to the data characteristics and analysis objectives, select a suitable fitting model. Commonly used models include polynomial fitting, spline interpolation, and other linear or nonlinear regression models. Use statistical analysis tools to fit the fluctuation data. Through fitting, a mathematical function can be found to describe the relationship between temperature fluctuation and time. Compare the fitting results with the actual fluctuation data, and use a chart to show the relationship between the fitting curve and the original data. This helps to intuitively understand the fluctuation pattern and evaluate the effectiveness of the model. Extract multi-dimensional indoor state feature data from the database, including indicators such as temperature, humidity, air pressure, and light, and ensure that these data have timestamps for time series analysis. Use moving average, exponential smoothing, or other time series analysis methods to smooth the data and identify long-term trends. These methods can effectively eliminate the impact of short-term fluctuations and make trends more obvious. Calculate the rate of change for each feature to identify the key points and trends of state changes. For example, if the indoor temperature continues to rise over a period of time, it means changes in external conditions or the influence of internal heat sources. Integrate the ambient temperature fluctuation data and indoor state change features into a comprehensive data set. This step is the basis for nonlinear association analysis and ensures the comprehensiveness and consistency of the data. Select a suitable nonlinear learning model based on data characteristics and analysis requirements. Common choices include random forests, support vector machines (SVMs), and neural networks. These models are able to capture complex nonlinear relationships. The selected model is trained using the integrated data. By taking ambient temperature fluctuations as input and indoor state features as output, the model is able to learn the complex relationship between the two. After training, the model output is used to generate nonlinear correlation features between indoor state and ambient temperature.These features can reveal the changing patterns of indoor conditions under different environmental conditions and provide support for subsequent optimization and decision-making.

[0040] In this embodiment, refer to Figure 4 , is a flowchart of detailed implementation steps of step S3. In this embodiment, the detailed implementation steps of step S3 include: Step S31: based on the indoor state-environment nonlinear correlation characteristics, the dynamic temperature evolution simulation is performed on the dynamic state space model of the test room to construct a dynamic evolution twin model; Step S32: performing regional temperature evolution analysis on the dynamic evolution twin model to generate regional temperature evolution response data; Step S33: performing regional temperature distribution identification on the regional temperature evolution response data, and extracting temperature evolution data of different regions; Step S34: performing deep temperature change learning on the temperature evolution data of different regions, thereby generating temperature change laws of different regions; Step S35: According to the temperature variation rules of different regions, the dynamic temperature evolution prediction is performed on the dynamic state space model of the test room to obtain the temperature prediction values ​​of multiple regions.

[0041] In this embodiment, a suitable dynamic state space model (such as a Kalman filter model or a nonlinear state space model) is selected to describe the dynamic changes of the indoor environment. The previously generated indoor state-environment nonlinear correlation characteristics are used as the input of the model to ensure that the model can capture the mutual influence between the indoor state and the external environment. The model parameters are estimated through historical data, and the least squares method or maximum likelihood estimation method is used to ensure that the model fits well. The model is verified by cross-validation to ensure the stability and accuracy of the model on different data sets. The constructed dynamic evolution twin model is used to dynamically simulate the regional temperature of the test room, considering the input conditions at different time points (such as external temperature, humidity, etc.), and the temperature change data during the simulation process are recorded, with special attention paid to the temperature change response of each area. These data may include temperature values ​​at different time points, change trends, etc. The test room is divided into multiple areas, and each area should have similar environmental characteristics to facilitate subsequent analysis. The generated regional temperature evolution response data is analyzed to identify the temperature change pattern of each area, which can This is achieved by calculating the average temperature, maximum value, minimum value and rate of change of each area, using heat maps or other visualization tools to display the temperature distribution of different areas, so as to intuitively understand the temperature evolution of each area, selecting a deep learning model suitable for time series analysis, such as long short-term memory network (LSTM) or convolutional neural network (CNN), to capture the deep-level characteristics of temperature changes, and organizing the extracted temperature evolution data of different regions into a format suitable for deep learning model input, including windowing of time series data, using the organized data to train the selected deep learning model, optimizing the model parameters to improve the prediction accuracy, and evaluating the performance of the model by calculating the mean square error (MSE) or other indicators of the model on the validation set to ensure that it can effectively capture the law of temperature changes. Using the trained deep learning model, the temperature of different areas is dynamically predicted, and the corresponding environmental parameters and historical temperature data are input to obtain future temperature prediction values. The prediction results are organized and output, including the temperature prediction value and change trend of each area. These results can be used for indoor environment monitoring and control decisions.

[0042] In this embodiment, step S4 includes the following steps: Step S41: extracting a preset laboratory constant temperature value based on the real-time test log; Step S42: Calculating the temperature deviation of each region for the temperature prediction values ​​of the multiple regions based on the preset laboratory constant temperature value to obtain a constant temperature deviation value for each region; Step S43: performing constant temperature deviation compensation calculation on the constant temperature deviation value of each area to generate a constant temperature deviation compensation parameter for each area; Step S44: finely adjusting the constant temperature deviation compensation parameters of each area to obtain the deviation compensation optimization value of each area; Step S45: Perform intelligent temperature control compensation on the dynamic state space model of the laboratory according to the deviation compensation optimization value of each area, and construct an intelligent temperature control strategy.

[0043] In this embodiment, according to the specific needs and standards of the laboratory, an ideal constant temperature value (for example, 21°C) is set. This value is usually determined in the laboratory design stage and used as a benchmark for subsequent temperature control. The current temperature setting value of the laboratory is extracted from the real-time test log. The log record comes from the environmental monitoring system or the laboratory management system. The extracted constant temperature value is stored in the database to ensure the accuracy of subsequent analysis and calculation. The temperature prediction value of each area is obtained from the temperature prediction model. These prediction values ​​are based on the output of the previous dynamic evolution model. The temperature prediction value of each area is compared with the preset constant temperature value to calculate the temperature deviation. Deviation = predicted temperature − constant temperature. The calculated constant temperature deviation value of each area is stored in the database for subsequent compensation calculation. A suitable compensation strategy is selected, which is usually linear compensation or nonlinear compensation. According to the size of the deviation value and the system response characteristics, the corresponding constant temperature deviation compensation parameters are generated based on the constant temperature deviation value of each area. The compensation algorithm is set, such as using proportional control (P control) or proportional-integral-differential control (PID control) to calculate the compensation parameters. For simple proportional control, the compensation parameters can be expressed as: ,in is the compensation parameter of the 𝑖th area, k is the compensation coefficient, which is usually determined by experimental data or historical data. The difference between the compensation parameters of each area and the actual temperature response is analyzed to identify the existing system errors. The compensation parameters of each area are finely adjusted. The following methods can be used: Feedback control: According to the real-time temperature data, adjust the compensation parameters to reduce the deviation. Iterative optimization: Use an optimization algorithm (such as gradient descent method) to gradually adjust the compensation parameters until the preset accuracy is achieved. The adjusted deviation compensation optimization value is stored in the database for use in the intelligent temperature control strategy. Design an intelligent temperature control system that can monitor the indoor temperature in real time and adjust it according to the deviation compensation optimization value. The system should have an automatic adjustment function to respond to real-time data. According to the deviation compensation optimization value of each area, a temperature control strategy is formulated. Commonly used control algorithms are: PID control: Use the proportional-integral-differential control algorithm to adjust according to the deviation between the real-time temperature and the set temperature. Fuzzy control: If the system is complex and has many variables, fuzzy logic control can be used for intelligent adjustment based on the rule base.

[0044] In this embodiment, the specific steps of step S5 are: Step S51: performing real-time temperature control on the constant temperature test room based on the intelligent temperature control strategy, and extracting the multi-modal energy consumption parameters of the current test room; Step S52: performing real-time operation power calculation of multiple devices on the multi-modal energy consumption parameters of the current laboratory, and extracting operation power parameters of multiple devices; Step S53: performing a time-series power situation analysis on the operating power parameters of the multiple devices to generate a time-series power situation of the multiple devices; Step S54: Make energy consumption optimization decisions on the sequential power status of multiple devices and build a dynamic energy consumption optimization strategy.

[0045] In this embodiment, high-precision temperature sensors (such as PT100 or DHT22) are used to monitor the temperature at various key locations in the laboratory. The sensors should have networking capabilities and be able to transmit data to the monitoring system in real time. A feedback mechanism is set to compare the sensor data with the preset constant temperature in real time. The monitoring system will automatically adjust the working state of the refrigeration or heating equipment according to the temperature deviation to maintain a constant indoor temperature. Smart meters or energy consumption monitoring devices are installed on the main equipment in the laboratory (such as air conditioners, heaters, ventilation equipment, etc.). These devices should be able to record information such as voltage, current, power factor, etc. in real time, and transmit the collected energy consumption data to a central database (such as Influx) through an Internet of Things platform (such as MQTT or HTTP). xDB or MySQL), ensure the real-time and traceability of data, calculate the actual power of each device, the formula is: P = V × I × PF, where P is power (watt), V is voltage (volt), I is current (ampere), PF is power factor (usually provided by the monitoring device), integrate the power calculation results of all devices into a unified data table, ensure that the power data of each device corresponds to the timestamp, this step is the basis for subsequent analysis, ensure that the energy consumption monitoring system can update the data in real time, and transmit the latest power calculation results to the database regularly (such as every minute) for time series analysis, clean the collected power data, handle missing values, outliers and noise, ensure the quality of the data, and use plug-in Use the mean filling method to handle missing values, use time series analysis methods (such as the autoregressive moving average model ARIMA) to model the power data of each device, identify trends, seasonality, and cyclical changes, apply sliding average or exponential smoothing methods to reduce data volatility and make long-term trends more obvious, use data visualization tools (such as Tableau or Python's Matplotlib) to create power situation diagrams to show the power changes of different devices in the time dimension. The generated charts should clearly mark the peak and trough periods for further analysis and decision-making, clarify the goals of energy consumption optimization, such as reducing overall energy consumption, balancing loads, reducing peak energy consumption, etc., and select appropriate optimization methods based on the goals. Optimization model, according to the specific needs of the laboratory and equipment characteristics, select the appropriate optimization algorithm, such as linear programming, dynamic programming or genetic algorithm-based strategy, to ensure that the algorithm can effectively handle multi-objective optimization problems, according to the output of the optimization algorithm, adjust the operation strategy of laboratory equipment, for example, adjust the operation sequence of equipment, change the operation time or reduce the load of certain equipment, to ensure that during the adjustment process, the laboratory's environmental conditions (such as temperature and humidity) still meet the experimental requirements, after implementing the optimization strategy, continuously monitor the changes in energy consumption data, evaluate the optimization effect, record the energy consumption comparison data before and after implementation, for subsequent analysis and optimization, establish a feedback mechanism, obtain energy consumption data in real time and compare it with the optimization target, and continuously adjust the optimization strategy according to the results,Ensure continuous improvement in energy management.

[0046] In this embodiment, the specific steps of step S6 are: Step S61: performing multi-scheme collaborative strategy simulation according to the intelligent temperature control strategy and the dynamic energy consumption optimization strategy, and extracting multiple collaborative simulation schemes; Step S62: performing dynamic control simulation on the constant temperature test chamber based on multiple collaborative simulation schemes to generate multiple test chamber control simulation data; Step S63: Comprehensively evaluate the control simulation data of multiple laboratories one by one to obtain a comprehensive evaluation of each solution; Step S64: extracting the optimal collaborative simulation scheme based on the comprehensive evaluation of each scheme; Step S65: Perform intelligent collaborative control optimization on the optimal collaborative simulation solution and build a constant temperature collaborative control model to perform constant temperature automation control operations.

[0047] In this embodiment, according to the previously formulated intelligent temperature control strategy and dynamic energy consumption optimization strategy, multiple collaborative control schemes are designed. These schemes include different equipment start-stop strategies, temperature set points, operating time and load distribution. Different parameter combinations are set for each scheme, for example: Scheme A: Maintain a constant temperature throughout the entire period, such as maintaining 22°C; Scheme B: Reduce the load during peak hours, such as 22°C, and adjust to 24°C during non-peak hours; Scheme C: Start and stop equipment on demand, such as automatically starting and stopping equipment when the temperature deviates from the set value. Select appropriate simulation tools (such as MATLAB Simulink, Energy Plus or AnyLogic) to simulate different collaborative control schemes. These tools should support dynamic simulation And multivariate analysis, determine the variables that need to be optimized, such as the equipment's on / off time, target temperature setting, power allocation of each device, and operating mode (such as energy-saving mode, fast mode, etc.). Multiple scenarios based on different external temperatures and internal load conditions can be designed, corresponding to different control strategies, and a combination of optimization methods (such as genetic algorithms, particle swarm optimization) can be used to generate multiple collaborative control schemes. These schemes should cover different equipment operation strategies and temperature control parameters. 100 different schemes can be generated by random sampling. Each scheme contains information such as the equipment's on time, set temperature, and operating mode. The generated collaborative simulation schemes are recorded in detail in the database, including the parameter settings, expected goals, and applicable conditions of each scheme. In order to facilitate subsequent execution and analysis, advanced simulation tools (such as MATLAB / Simulink, EnergyPlus, TRNSYS, etc.) are used to perform dynamic control simulation on each collaborative scheme. The input parameters of each scheme (such as set temperature, equipment configuration) are input into the simulation model, and the model performs dynamic simulation of temperature and energy consumption based on physical principles and equipment characteristics. During the simulation process, the temperature changes, energy consumption data, equipment operating status and response time under each scheme are recorded to form multiple laboratory control simulation data sets. The room temperature, equipment power, total energy consumption and other data at each time point are simulated and output to form a complete time series data set. The simulation data generated by each control scheme is stored in a structured form. The data are stored in the database, including timestamp, temperature, power and other fields, for subsequent evaluation and analysis, and comprehensive evaluation indicators are determined, including: temperature stability: temperature fluctuation range, ideally should be close to the set value, energy efficiency: energy consumption per unit time, ideally should be minimized, equipment utilization: the ratio of the actual operating time of the equipment during the simulation to the total time, operating cost: the total cost considering factors such as electricity price and equipment maintenance, set weights for each indicator to reflect its importance in the overall evaluation, ensure that the evaluation can fairly reflect the pros and cons of each solution, analyze the control simulation data of each solution, calculate the score of each evaluation indicator, and use standardized methods to convert the value of each indicator into a score between 0 and 1.The temperature stability score can be calculated by calculating the ratio of the temperature fluctuation range to the set target value. The temperature stability score = 1-(set target value / fluctuation range). The weighted scoring method is used to calculate the comprehensive evaluation. The score and weight of each indicator are combined to record the comprehensive evaluation of each solution to form a set of evaluation results. All solutions are sorted according to the comprehensive evaluation and the highest-rated solution is identified. A threshold can be set to ensure that the selected solution performs well in all indicators. The collaborative simulation solution with the highest comprehensive evaluation is extracted from the evaluation results, and its parameters and characteristics are recorded for subsequent optimization and implementation. If the comprehensive evaluation of Solution A is 0.9 and the evaluations of other solutions are all below 0.85, Solution A is selected as the optimal solution. According to the parameters of the optimal solution, a constant temperature control model is constructed. This can be based on control theory, such as PID control, fuzzy control or model-based control methods. A PID controller is designed and its proportional, integral and differential are adjusted. Parameters to achieve rapid response and stable control of temperature, use machine learning or optimization algorithms (such as reinforcement learning, fuzzy logic, etc.) to train the control model, optimize the control strategy to adapt to dynamic environmental changes and load requirements, during the training process, historical data and simulation results can be used for feedback learning, and the control parameters can be gradually adjusted to make them more suitable for actual operating conditions. The constructed constant temperature collaborative control model is deployed to the actual control system, and the temperature and energy consumption of the laboratory are monitored in real time, and automatic adjustments are made according to the model output. For example, all sensors and actuators are connected through Internet of Things (IoT) devices to form a comprehensive automated control system. After implementation, the system performance is continuously monitored, and the control parameters are adjusted in real time to ensure that the constant temperature test room operates in the best state, and the control strategy is optimized according to the feedback data. Use real-time data analysis tools (such as data visualization software) to monitor temperature and energy consumption changes to ensure that the system can respond to emergencies in a timely manner. ,

[0048] In this embodiment, an automatic control system of a constant temperature test chamber is provided, which is used to execute the automatic control method of the constant temperature test chamber as described above, including: The operation status module is used to obtain the real-time indoor operation monitoring parameters of the constant temperature test room and the multi-dimensional data of the external environment; perform indoor operation status analysis on the real-time indoor operation monitoring parameters and construct a dynamic state space model of the test room; The nonlinear association module is used to calculate the ambient temperature fluctuations at multiple time points based on the multi-dimensional data of the external environment, and to perform nonlinear association learning to generate indoor state-environment nonlinear association features; The temperature evolution prediction module is used to simulate the dynamic temperature evolution of the dynamic state space model of the test room based on the indoor state-environment nonlinear correlation characteristics, and to predict the dynamic temperature evolution to obtain the temperature prediction values ​​of multiple areas; Intelligent temperature control module, used to calculate constant temperature deviation compensation for temperature prediction values ​​of multiple areas, and then perform intelligent temperature control compensation to build an intelligent temperature control strategy; Energy consumption optimization module, which is used to calculate the real-time operating power of multiple devices based on intelligent temperature control strategies, make energy consumption optimization decisions, and build dynamic energy consumption optimization strategies; The collaborative control module is used to perform intelligent collaborative control optimization according to the intelligent temperature control strategy and dynamic energy consumption optimization strategy, build a constant temperature collaborative control model, and execute constant temperature automatic control operations.

[0049] The present invention realizes comprehensive monitoring and analysis of the laboratory operation status by acquiring real-time indoor operation monitoring parameters and multi-dimensional data of the external environment, constructs a dynamic state space model of the laboratory, helps to understand the changing law of the internal state of the laboratory, and provides a basis for subsequent intelligent control. The multi-dimensional data of the external environment are used to perform multi-time point ambient temperature fluctuation calculation and nonlinear correlation learning, and extract the nonlinear correlation characteristics of the indoor state-environment. The generated nonlinear correlation characteristics help to more accurately understand the complex relationship between indoor temperature changes and the external environment. Based on the nonlinear correlation characteristics, the dynamic temperature evolution simulation and prediction are performed on the dynamic state space model of the laboratory to obtain temperature prediction values ​​of multiple areas. The temperature evolution prediction helps to predict the temperature change trend of each area in advance, provides a basis for the formulation of intelligent temperature control strategies, and can be used for multiple The temperature prediction values ​​of each area are used to perform constant temperature deviation compensation calculation and intelligent temperature control compensation, and an intelligent temperature control strategy is constructed to achieve precise control of the laboratory temperature. The intelligent temperature control strategy can effectively reduce temperature fluctuations and improve the stability and energy efficiency of the constant temperature laboratory. Based on the intelligent temperature control strategy, the real-time operating power of multiple devices is calculated, energy consumption optimization decisions are implemented, and a dynamic energy consumption optimization strategy is constructed to reduce the energy consumption cost of the laboratory. The energy consumption optimization module can effectively manage equipment energy consumption, improve energy utilization efficiency, and reduce operating costs. According to the intelligent temperature control strategy and the dynamic energy consumption optimization strategy, intelligent collaborative control optimization is performed, a constant temperature collaborative control model is constructed, and constant temperature automation control operations are realized. The collaborative control module can coordinate the work between various subsystems, optimize the overall control effect, and improve the overall performance of the laboratory automation control system.

[0050] Therefore, the embodiments should be regarded as illustrative and non-restrictive from all points, and the scope of the present invention is limited by the appended claims rather than the above description, and it is intended that all changes falling within the meaning and range of equivalent elements of the application documents are included in the present invention.

[0051] The above is only a specific embodiment of the present invention, so that those skilled in the art can understand or implement the present invention. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to the embodiments shown herein, but will conform to the widest scope consistent with the principles and novel features invented herein.

Claims

1. An automatic control method for a constant temperature test chamber, characterized in that: The following steps are involved: Step S1: Obtaining real-time indoor operation monitoring parameters of the constant temperature test room and multi-dimensional data of the external environment; Performing indoor operation status analysis on the real-time indoor operation monitoring parameters and constructing a dynamic state space model of the laboratory; Step S2: Calculate the ambient temperature fluctuations at multiple time points on the multi-dimensional data of the external environment, and perform nonlinear association learning to generate indoor state-environment nonlinear association features; Step S3: based on the indoor state-environment nonlinear correlation characteristics, the dynamic temperature evolution simulation is performed on the dynamic state space model of the test room, and the dynamic temperature evolution prediction is performed to obtain the temperature prediction values ​​of multiple areas; Step S4: performing constant temperature deviation compensation calculation on the temperature prediction values ​​of multiple regions, and then performing intelligent temperature control compensation to construct an intelligent temperature control strategy; Step S5: Based on the intelligent temperature control strategy, the real-time operation power of multiple devices is calculated, and energy consumption optimization decisions are made to build a dynamic energy consumption optimization strategy; Step S6: Perform intelligent collaborative control optimization according to the intelligent temperature control strategy and the dynamic energy consumption optimization strategy, and build a constant temperature collaborative control model to perform constant temperature automatic control operations.

2. The automatic control method of the constant temperature test chamber according to claim 1, characterized in that: The specific steps of step S1 are: Step S11: obtaining real-time indoor operation monitoring parameters of the constant temperature test room and multi-dimensional data of the external environment; Step S12: performing indoor operation status analysis on the real-time indoor operation monitoring parameters to generate multi-dimensional indoor state features; Step S13: Analyze the indoor space structure of the constant temperature test room and extract the indoor space structure characteristics; Step S14: dividing the indoor space structure features into space structure regions, thereby obtaining a plurality of indoor space regions; Step S15: performing regional state feature mapping on multiple indoor space regions based on the multi-dimensional indoor state feature to obtain a state feature mapping space region; Step S16: Perform dynamic state modeling on the state feature mapping space area to construct a dynamic state space model of the laboratory.

3. The automatic control method of the constant temperature test chamber according to claim 2, characterized in that: The specific steps of step S12 are: The real-time indoor operation monitoring parameters include temperature parameters, humidity parameters, air pressure parameters and indoor lighting parameters; Identify the indoor temperature distribution of temperature parameters and extract indoor temperature distribution data; Perform time series temperature change analysis on indoor temperature distribution data to generate indoor temperature distribution change data; The humidity parameters are used to calculate the average space humidity, thereby obtaining the average space humidity; Conduct air pressure fluidity analysis on air pressure parameters to generate indoor air pressure fluidity characteristics; Calculate the light intensity of indoor light parameters to generate indoor light intensity values; Perform spatial distribution analysis on indoor light intensity values ​​to generate spatial distribution data of light intensity; Multi-dimensional state feature mining is performed on indoor temperature distribution change data, spatial average humidity, indoor air pressure fluidity characteristics and light intensity spatial distribution data to generate multi-dimensional indoor state features.

4. The automatic control method of the constant temperature test chamber according to claim 1, characterized in that: The specific steps of step S2 are: Step S21: performing multi-time point ambient temperature fluctuation calculation on the multi-dimensional data of the external environment to generate ambient temperature fluctuation data at multiple time points; Step S22: performing time series fluctuation fitting on the ambient temperature fluctuation data at multiple time points to construct an ambient temperature fluctuation curve; Step S23: Evolving the time series state change trend of the multi-dimensional indoor state features to generate indoor state change trend features; Step S24: performing nonlinear association learning on the indoor state change trend characteristics according to the ambient temperature fluctuation curve to generate indoor state-environment nonlinear association characteristics.

5. The automatic control method of the constant temperature test chamber according to claim 1, characterized in that: The specific steps of step S3 are: Step S31: based on the indoor state-environment nonlinear correlation characteristics, the dynamic temperature evolution simulation is performed on the dynamic state space model of the test room to construct a dynamic evolution twin model; Step S32: performing regional temperature evolution analysis on the dynamic evolution twin model to generate regional temperature evolution response data; Step S33: performing regional temperature distribution identification on the regional temperature evolution response data, and extracting temperature evolution data of different regions; Step S34: performing deep temperature change learning on the temperature evolution data of different regions, thereby generating temperature change laws of different regions; Step S35: According to the temperature variation rules of different regions, the dynamic temperature evolution prediction is performed on the dynamic state space model of the test room to obtain the temperature prediction values ​​of multiple regions.

6. The automatic control method of the constant temperature test chamber according to claim 1, characterized in that: The specific steps of step S4 are: Step S41: extracting a preset laboratory constant temperature value based on the real-time test log; Step S42: Calculating the temperature deviation of each region for the temperature prediction values ​​of the multiple regions based on the preset laboratory constant temperature value to obtain a constant temperature deviation value for each region; Step S43: performing constant temperature deviation compensation calculation on the constant temperature deviation value of each area to generate a constant temperature deviation compensation parameter for each area; Step S44: finely adjusting the constant temperature deviation compensation parameters of each area to obtain the deviation compensation optimization value of each area; Step S45: Perform intelligent temperature control compensation on the dynamic state space model of the laboratory according to the deviation compensation optimization value of each area, and construct an intelligent temperature control strategy.

7. The automatic control method of the constant temperature test chamber according to claim 1, characterized in that: The specific steps of step S5 are: Step S51: performing real-time temperature control on the constant temperature test room based on the intelligent temperature control strategy, and extracting the multi-modal energy consumption parameters of the current test room; Step S52: performing real-time operation power calculation of multiple devices on the multi-modal energy consumption parameters of the current laboratory, and extracting operation power parameters of multiple devices; Step S53: performing a time-series power situation analysis on the operating power parameters of the multiple devices to generate a time-series power situation of the multiple devices; Step S54: Make energy consumption optimization decisions on the sequential power status of multiple devices and build a dynamic energy consumption optimization strategy.

8. The automatic control method of the constant temperature test chamber according to claim 1, characterized in that: The specific steps of step S6 are: Step S61: performing multi-scheme collaborative strategy simulation according to the intelligent temperature control strategy and the dynamic energy consumption optimization strategy, and extracting multiple collaborative simulation schemes; Step S62: performing dynamic control simulation on the constant temperature test chamber based on multiple collaborative simulation schemes to generate multiple test chamber control simulation data; Step S63: Comprehensively evaluate the control simulation data of multiple laboratories one by one to obtain a comprehensive evaluation of each solution; Step S64: extracting the optimal collaborative simulation scheme based on the comprehensive evaluation of each scheme; Step S65: Perform intelligent collaborative control optimization on the optimal collaborative simulation solution and build a constant temperature collaborative control model to perform constant temperature automation control operations.

9. An automatic control system for a constant temperature test chamber, characterized in that: The method for executing the automatic control of the constant temperature test chamber according to claim 1 comprises: The operation status module is used to obtain the real-time indoor operation monitoring parameters of the constant temperature test room and the multi-dimensional data of the external environment; perform indoor operation status analysis on the real-time indoor operation monitoring parameters and construct a dynamic state space model of the test room; The nonlinear association module is used to calculate the ambient temperature fluctuations at multiple time points based on the multi-dimensional data of the external environment, and to perform nonlinear association learning to generate indoor state-environment nonlinear association features; The temperature evolution prediction module is used to simulate the dynamic temperature evolution of the dynamic state space model of the test room based on the indoor state-environment nonlinear correlation characteristics, and to predict the dynamic temperature evolution to obtain the temperature prediction values ​​of multiple areas; Intelligent temperature control module, used to calculate constant temperature deviation compensation for temperature prediction values ​​of multiple areas, and then perform intelligent temperature control compensation to build an intelligent temperature control strategy; Energy consumption optimization module, which is used to calculate the real-time operating power of multiple devices based on intelligent temperature control strategies, make energy consumption optimization decisions, and build dynamic energy consumption optimization strategies; The collaborative control module is used to perform intelligent collaborative control optimization according to the intelligent temperature control strategy and dynamic energy consumption optimization strategy, build a constant temperature collaborative control model, and execute constant temperature automatic control operations.

Images