A thermal energy intelligent adaptation method and system for energy storage cabinet production process

Abstract

The present invention discloses a thermal energy intelligent adaptation method and system for an energy storage cabinet production process, belonging to the technical field of energy storage equipment production, and specifically comprises: installing sensors in different areas during the production process of the energy storage cabinet to monitor the production process in real time and collect state parameter data; combining real-time and historical state parameter data, using a hybrid machine learning model to predict thermal energy demand under different production stages and conditions; formulating an adaptive thermal energy supply control strategy according to the prediction results, and establishing a multi-level safety monitoring system; after implementing the control strategy and safety measures, conducting a multi-dimensional evaluation, and optimizing the strategy based on the evaluation results and real-time data; recording changes and reasons during the development process, and building a knowledge base to support subsequent improvements; the present invention improves the flexibility and safety of thermal energy supply and realizes intelligent control.

Description

Technical Field

[0001] The present invention belongs to the technical field of energy storage equipment production, and specifically relates to a thermal energy intelligent adaptation method and system for an energy storage cabinet production process. Background Art

[0002] As a key component in the new energy system, the thermal energy management of the energy storage cabinet in the production process directly affects the production efficiency, energy consumption and product quality. In traditional processes, thermal energy management often relies on manual experience and fixed parameter settings, which is difficult to adapt to the dynamic changes in the production process, resulting in thermal energy waste, low production efficiency and unstable product quality. Therefore, it is particularly important to develop a method that can intelligently adapt to the thermal energy demand in the energy storage cabinet production process.

[0003] For example, a Chinese patent with authorization publication number CN113348423B discloses a thermal energy distribution system and a control method thereof, comprising: determining prediction data related to the following items: an estimated total heat and / or cooling absorption from a distribution network by a local distribution system connected to the distribution network over time, and an estimated heat and / or cooling production capacity in one or more production equipment, determining a time-resolved control signal at a control server, the control signal being based on the prediction data and associated with at least one local control unit, sending the control signal from the control server to the associated local control unit, receiving the control signal at the associated local control unit, and adjusting the heat and / or cooling absorption from the distribution network by the local distribution system over time in response to the control signal.

[0004] The above existing technologies have the following problems: limited flexibility; lack of knowledge management and improvement mechanism; lack of detailed prediction and monitoring steps. Summary of the invention

[0005] In view of the shortcomings of the prior art, the present invention proposes a thermal energy intelligent adaptation method and system for the production process of an energy storage cabinet, including: installing sensors in different areas of the energy storage cabinet production process to monitor the production process in real time and collect state parameter data; combining real-time and historical state parameter data, and using a hybrid machine learning model to predict the thermal energy demand under different production stages and conditions; formulating an adaptive thermal energy supply control strategy based on the prediction results, and establishing a multi-level safety monitoring system; after implementing the control strategy and safety measures, conducting a multi-dimensional evaluation, and optimizing the strategy based on the evaluation results and real-time data; recording changes and reasons during the development process, and building a knowledge base to support subsequent improvements. The present invention improves the flexibility and safety of thermal energy supply and realizes intelligent control.

[0006] To achieve the above object, the present invention provides the following technical solutions:

[0007] A thermal energy intelligent adaptation method for an energy storage cabinet production process, comprising:

[0008] Step S1: installing sensors in different areas of the energy storage cabinet production process to monitor the production process in real time, and collecting state parameter data in real time during the monitoring process;

[0009] Step S2: Based on the real-time state parameter data and the historical state parameter data extracted from the database, a hybrid machine learning model is used to predict the heat energy demand under different conditions in different production stages;

[0010] Step S3: formulating an adaptive heat supply control strategy based on the heat demand forecast results and establishing multi-level safety measures;

[0011] Step S4: after implementing the adaptive heat supply control strategy and the multi-level safety measures, a multi-dimensional evaluation is performed on the effect after the implementation, and based on the multi-dimensional evaluation results and the state parameter data collected in real time, a data-driven method is used to improve and optimize the adaptive heat supply control strategy and the multi-level safety measures;

[0012] Step S5: Record the changes made during the development process and their reasons to build a knowledge base;

[0013] The specific steps of step S3 include:

[0014] S3.1: Obtain the forecast results of heat demand, analyze the heat demand trend in the current time period, and set the upper threshold of heat supply and lower threshold ,like ,or When the temperature is high, the heat supply is automatically adjusted. The heat supply adjustment formula is:

[0015] ;

[0016] in, Indicates the current time period The heat demand within Indicates the heat supply adjustment, It represents the proportionality coefficient between the heat demand forecast and the actual heat supply, represents the coefficient of change rate of heat energy demand and actual heat energy supply, represents the difference coefficient, represents the current forecast value of heat energy demand, Indicates the actual heat supply. Indicates the current time period The predicted value of heat energy demand within Indicates the current time period The actual heat supply in the

[0017] S3.2: Use temperature sensors on the production line to monitor the temperature during the production process in real time and set warning thresholds for abnormally high temperatures ,like When an emergency occurs, the emergency response mechanism is automatically triggered and multi-level security measures are taken, including: Indicates the temperature in the current production process;

[0018] S3.3: For welding and laser cutting operation areas, set up intelligent safety barriers and one-touch emergency stop buttons, and conduct regular safety inspections and maintenance.

[0019] Specifically, the sensor installation positions in step S1 include cold plates, welding areas of stainless steel plates, laser welding areas of aluminum plates, cabinet surface treatment areas, plastic spraying and painting areas, and electrical component installation areas in the electric control cabinet; the status parameter data include equipment working status parameters, material type parameters, surface treatment type parameters, plastic spraying and painting parameters, and environmental parameters in the electric control cabinet.

[0020] Specifically, the specific steps of step S4 include:

[0021] S4.1: Acquire the real-time status parameter data and historical status parameter data in step S2, and form a storage cabinet status parameter data set through data integration ,in, represents the nth energy storage cabinet state parameter data, and n represents the number of energy storage cabinet state parameter data;

[0022] S4.2: Define multiple evaluation indicators based on the energy storage cabinet state parameter dataset , perform multi-dimensional evaluation based on multiple evaluation indicators and generate a multi-dimensional evaluation result report. The multi-dimensional evaluation formula is:

[0023] ;

[0024] in, Indicates the average deviation between the actual temperature and the set temperature. represents the actual temperature at the i-th time point, m represents the length of the time period for temperature measurement, represents the set temperature at the i-th time point, It represents the energy consumption per unit time. represents the power of the energy storage cabinet at time t, Indicates the fluctuation degree of the energy storage cabinet status parameter value, Indicates the state parameter data of the kth energy storage cabinet, Represents the mean value of the energy storage cabinet status parameter data, It indicates the average response time for the system to take measures after detecting an abnormal situation. represents the time of the jth response, and M represents the number of responses in which the system detects an abnormal situation and takes measures.

[0025] Specifically, the specific steps of step S4 also include:

[0026] S4.3: According to the multi-dimensional evaluation results, label each energy storage cabinet state parameter data with a heat supply control strategy label and a safety measure label to obtain a labeled energy storage cabinet state parameter data set;

[0027] S4.4: Load the pre-trained gradient boosting tree model, and use the labeled energy storage cabinet state parameter data set as the input of the gradient boosting tree model to perform dual-task learning, and output the optimized adaptive heat supply control strategy and optimized multi-level safety measures through training;

[0028] S4.5: Apply the optimized adaptive heat supply control strategy and the optimized multi-level safety measures to the actual system, and perform multi-dimensional evaluation again to generate an optimized multi-dimensional evaluation result report;

[0029] S4.6: Compare the evaluation results before and after optimization to verify whether the effect after optimization reaches the expected goal. If not, repeat S4.2 to S4.5 for iterative training.

[0030] Specifically, the specific steps of S4.4 include:

[0031] S4.41: Load the pre-trained gradient boosting tree model and obtain the labeled energy storage cabinet state parameter data set;

[0032] S4.42: Define the mean square error objective function for dual-task learning, and combine the loss functions of the dual tasks to form the total loss function ,in, represents the loss function of the heat supply control strategy task, represents the safety measure task loss function, represents the weight coefficient;

[0033] S4.43: Input the labeled energy storage cabinet state parameter data set into the gradient boosting tree model, perform dual-task learning training, and obtain a trained gradient boosting tree model;

[0034] S4.44: Use the trained gradient boosting tree model to predict the labeled energy storage cabinet state parameter data set obtained in real time, and generate an optimized adaptive heat supply control strategy and optimized multi-level safety measures.

[0035] Specifically, a thermal energy intelligent adaptation system for the production process of an energy storage cabinet includes: a monitoring module, an intelligent analysis module, a control strategy module, and an effect evaluation module;

[0036] The monitoring module is used to collect state parameter data during the production process in real time;

[0037] The intelligent analysis module is used to perform intelligent analysis based on real-time state parameter data in combination with historical state parameter data using a machine learning model to predict thermal energy demand;

[0038] The control strategy module is used to formulate an adaptive heat supply control strategy according to the heat demand prediction result, and automatically adjust the working state of the heat supply equipment;

[0039] The effect evaluation module is used to perform a multi-dimensional evaluation on the effects after the implementation of the adaptive heat supply control strategy and the multi-level safety measures.

[0040] Specifically, the control strategy module includes: a control strategy formulation unit and a temperature monitoring unit;

[0041] The control strategy formulation unit is used to formulate an adaptive heat supply control strategy according to the heat demand prediction result;

[0042] The temperature monitoring unit is used to monitor the temperature during the production process in real time, and trigger an early warning mechanism when an abnormally high temperature is detected.

[0043] Specifically, the effect evaluation module includes: a multi-dimensional evaluation unit, a data-driven optimization unit, and a recording and feedback unit;

[0044] The multi-dimensional evaluation unit is used to perform a multi-dimensional evaluation on the effect of implementing the adaptive heat supply control strategy and the multi-level safety measures;

[0045] The data-driven optimization unit improves and optimizes the adaptive heat supply control strategy and multi-level safety measures using a data-driven approach based on the multi-dimensional evaluation results and the state parameter data collected in real time;

[0046] The recording and feedback unit is used to record the changes made during the development process and the reasons therefor.

[0047] An electronic device comprises a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, steps of a thermal energy intelligent adaptation method for an energy storage cabinet production process are implemented.

[0048] Compared with the prior art, the present invention has the following beneficial effects:

[0049] 1. The present invention proposes a thermal energy intelligent adaptation system for the production process of an energy storage cabinet, and optimizes and improves the architecture, operation steps and processes. The system has the advantages of simple process, low investment and operation costs, and low production work costs.

[0050] 2. The present invention proposes a thermal energy intelligent adaptation method for the energy storage cabinet production process. By real-time monitoring of the production process and collecting status parameter data, the thermal energy demand is predicted by combining historical data and a hybrid machine learning model, thereby achieving precise control and adaptive adjustment of the thermal energy supply. This can not only improve the efficiency and stability of the thermal energy supply, but also effectively avoid energy waste and reduce production costs.

[0051] 3. The present invention proposes a thermal energy intelligent adaptation method for the production process of energy storage cabinets, establishes a multi-level safety monitoring system, and conducts a multi-dimensional evaluation of the effect after implementation. The data-driven method is used to improve and optimize the strategy, which can not only ensure the safety and reliability of the thermal energy supply process, but also continuously improve the performance and intelligence level of the system. At the same time, recording the changes and reasons in the development process and building a knowledge base also provides an important reference for subsequent system maintenance and upgrades. BRIEF DESCRIPTION OF THE DRAWINGS

[0052] Figure 1 A schematic diagram of a thermal energy intelligent adaptation method for an energy storage cabinet production process of the present invention;

[0053] Figure 2 This is a principle flow chart of a thermal energy intelligent adaptation method for an energy storage cabinet production process of the present invention;

[0054] Figure 3 This is a thermal energy intelligent adaptation system architecture diagram for an energy storage cabinet production process of the present invention. DETAILED DESCRIPTION

[0055] Example 1

[0056] See also Figure 1 and Figure 2 , an embodiment provided by the present invention: a thermal energy intelligent adaptation method for an energy storage cabinet production process, comprising the following steps:

[0057] Step S1: installing sensors in different areas of the energy storage cabinet production process to monitor the production process in real time, and collecting state parameter data in real time during the monitoring process;

[0058] In step S1, the sensor installation positions include the cold plate, the welding area of ​​the stainless steel plate, the laser welding area of ​​the aluminum plate, the cabinet surface treatment area, the plastic spraying and painting area, and the electrical component installation area in the electric control cabinet; the state parameter data includes equipment working state parameters, material type parameters, surface treatment type parameters, plastic spraying and painting parameters, and environmental parameters in the electric control cabinet.

[0059] Step S2: Based on the real-time state parameter data and the historical state parameter data extracted from the database, a hybrid machine learning model is used to predict the heat energy demand under different conditions in different production stages;

[0060] Furthermore, the specific steps of step S2 include:

[0061] (1) Collect state parameter data in the production process in real time and extract historical state parameter data from the database, including thermal energy demand and related state parameters under different production stages and conditions in the past;

[0062] (2) Clean the real-time state parameter data and historical state parameter data, remove noise, outliers and duplicate data, and normalize or standardize the data to improve the training efficiency and prediction accuracy of the machine learning model;

[0063] (3) According to the production stage and conditions, the historical state parameter data is feature extracted using the principal component analysis method to obtain the historical state characteristic parameter data, and the historical state characteristic parameter data is divided into a training set, a validation set and a test set for the training, validation and testing of the hybrid machine learning model. The principal component analysis method is a prior art in the art and is not an inventive solution of the present application, and is not described in detail here.

[0064] (4) Load the pre-built deep neural network and support vector machine models, and combine the deep neural network and support vector machine models to form a hybrid machine learning model through an integration method;

[0065] (5) Use the training set data to train the hybrid machine learning model and adjust the parameters of the hybrid machine learning model to minimize the prediction error;

[0066] (6) Use the validation set data to validate the hybrid machine learning model, evaluate the predictive performance of the hybrid machine learning model, and optimize the hybrid machine learning model based on the validation results, such as adjusting features, algorithm parameters, or selecting a more appropriate algorithm;

[0067] (7) Using the test set data to test the hybrid machine learning model to ensure the stability and reliability of the hybrid machine learning model. The training, verification and testing process of the machine learning model is the prior art content in this field and is not the inventive solution of the present application, and is not described in detail here;

[0068] (8) Apply the hybrid machine learning model to the actual production environment to predict the thermal energy demand under different production stages and conditions based on real-time state parameter data.

[0069] Step S3: formulating an adaptive heat supply control strategy based on the heat demand forecast results and establishing multi-level safety measures;

[0070] It should be noted that the adaptive heat supply control strategy mainly includes:

[0071] (1) Dynamic heat energy regulation: According to the heat energy demand forecast results, the output of the heat energy supply system is adjusted in real time to ensure that the heat energy supply matches the demand, including adjusting the temperature, flow rate and other parameters of the heat source to meet the heat energy demand under different production stages and conditions;

[0072] (2) Intelligent control algorithm: Use intelligent control algorithms, such as fuzzy control, to optimize the control of the heat supply system. Intelligent control algorithms can automatically adjust control strategies based on real-time data and learning experience to improve the response speed and stability of the system.

[0073] (3) Fault warning and diagnosis: Establish a fault warning and diagnosis system to monitor the operating status of the heat supply system in real time, detect and handle potential faults in a timely manner, and help reduce heat supply interruptions and energy waste caused by system failures;

[0074] (4) Energy management optimization: Combined with the energy management system, global optimization of thermal energy supply is carried out to achieve efficient energy utilization and cost savings through data analysis, prediction and scheduling.

[0075] The specific steps of formulating the adaptive heat supply control strategy include:

[0076] (1) Demand analysis: First, it is necessary to conduct an in-depth analysis of thermal energy demand to understand the characteristics of thermal energy demand under different production stages and conditions. This can be done through historical data analysis and on-site investigations;

[0077] (2) System modeling: Based on the demand analysis results, a mathematical model of the heat supply system is established. The model should be able to accurately reflect the dynamic characteristics of the system and the heat transfer process.

[0078] (3) Control strategy design: Design an adaptive heat supply control strategy based on the system model and heat demand characteristics;

[0079] (4) Simulation verification: Verify the control strategy in a simulation environment and evaluate its performance and stability. This helps to identify potential problems and make optimizations.

[0080] (5) On-site implementation: Apply the verified control strategy to the actual thermal energy supply system and conduct on-site debugging and optimization.

[0081] Step S4: after implementing the adaptive heat supply control strategy and the multi-level safety measures, a multi-dimensional evaluation is performed on the effect after the implementation, and based on the multi-dimensional evaluation results and the state parameter data collected in real time, a data-driven method is used to improve and optimize the adaptive heat supply control strategy and the multi-level safety measures;

[0082] Step S5: Record the changes made during the entire development process and their reasons to build a knowledge base;

[0083] Furthermore, the specific steps of building a knowledge base include:

[0084] (1) Select an online knowledge base system based on the needs and characteristics of the knowledge base;

[0085] (2) Enter the classified and organized knowledge into the online knowledge base system. During the entry process, pay attention to maintaining the accuracy and completeness of the content, and appropriately add auxiliary information such as labels and pictures to improve the readability and ease of use of the content;

[0086] (3) Regularly update the knowledge base to ensure that its content is consistent with the latest research results and practical experience;

[0087] (4) In order to improve the user's search experience, it is necessary to optimize the search function of the knowledge base. The search function can be optimized by setting a keyword index or a classification label method so that users can quickly and accurately find the required knowledge. Among them, the keyword index or classification label method is the existing technical content in this field and is not the inventive solution of this application, and will not be elaborated here.

[0088] The specific steps of step S3 include:

[0089] S3.1: Obtain the forecast results of heat demand, analyze the heat demand trend in the current time period, and set the upper threshold of heat supply and lower threshold ,like ,or When the temperature is high, the heat supply is automatically adjusted. The heat supply adjustment formula is:

[0090] ;

[0091] in, Indicates the current time period The heat demand within Indicates the heat supply adjustment, It represents the proportionality coefficient between the heat demand forecast and the actual heat supply, represents the coefficient of change rate of heat energy demand and actual heat energy supply, It represents the difference coefficient, which is used to take into account the long-term accumulated difference between the heat demand and the actual heat supply to eliminate static errors. represents the current forecast value of heat energy demand, Indicates the actual heat supply. Indicates the current time period The predicted value of heat energy demand within Indicates the current time period The actual heat supply in Indicates the rate of change of the predicted value of heat energy demand, indicating the changing trend of heat energy demand in the future. Indicates the rate of change of the actual heat supply, indicating the current response speed of the heat supply system;

[0092] It should be noted that the formula in the present invention can more comprehensively reflect the dynamic characteristics and control requirements of the thermal energy supply system, and achieve more accurate, stable and rapid thermal energy supply adjustment, thereby improving energy utilization efficiency and the overall performance of the system.

[0093] S3.2: Use temperature sensors on the production line to monitor the temperature during the production process in real time and set warning thresholds for abnormally high temperatures ,like When an emergency occurs, the emergency response mechanism is automatically triggered and multi-level security measures are taken, including: Indicates the temperature in the current production process;

[0094] S3.3: For high-risk operation areas such as welding and laser cutting, set up intelligent safety barriers and one-touch emergency stop buttons, and conduct safety inspections and maintenance on high-risk operation areas regularly.

[0095] The specific steps of step S4 include:

[0096] S4.1: Acquire the real-time status parameter data and historical status parameter data in step S2, and form a storage cabinet status parameter data set through data integration ,in, represents the nth energy storage cabinet state parameter data, and n represents the number of energy storage cabinet state parameter data;

[0097] S4.2: Define multiple evaluation indicators based on the energy storage cabinet state parameter dataset , perform multi-dimensional evaluation based on multiple evaluation indicators and generate a multi-dimensional evaluation result report. The multi-dimensional evaluation formula is:

[0098] ;

[0099] in, Indicates the average deviation between the actual temperature and the set temperature. represents the actual temperature at the i-th time point, m represents the length of the time period for temperature measurement, represents the set temperature at the i-th time point, It represents the energy consumption per unit time. represents the power of the energy storage cabinet at time t, Indicates the fluctuation degree of the energy storage cabinet status parameter value, Indicates the state parameter data of the kth energy storage cabinet, Represents the mean value of the energy storage cabinet status parameter data, It indicates the average response time for the system to take measures after detecting an abnormal situation. represents the time of the jth response, and M represents the number of responses in which the system detects an abnormal situation and takes measures;

[0100] Among them, multiple evaluation indicators include average deviation, energy consumption per unit time, fluctuation degree of energy storage cabinet status parameter value and average response time.

[0101] S4.3: According to the multi-dimensional evaluation results, label each energy storage cabinet state parameter data with a heat supply control strategy label and a safety measure label to obtain a labeled energy storage cabinet state parameter data set;

[0102] Furthermore, the specific steps of S4.3 include:

[0103] (1) Determine the standards for labeling heat supply control strategies and safety measures based on the multi-dimensional evaluation results;

[0104] (2) Traverse each energy storage cabinet state parameter data point, and label it with the corresponding heat supply control strategy label and safety measure label according to the multi-dimensional evaluation results and labeling standards;

[0105] For example, if , then it is marked as no adjustment is required;

[0106] like , it is marked as adjustment;

[0107] like , it is marked as normal;

[0108] like , it is marked as optimized power management;

[0109] like , it is marked as normal;

[0110] like , it is marked as enhanced alarm mechanism, where °C represents the temperature unit, Wh represents the watt-hour unit, and s represents the second unit.

[0111] (3) Randomly sample and check some data points, manually verify whether the annotated labels are correct, and correct the annotation errors based on the verification results.

[0112] S4.4: Load the pre-trained gradient boosting tree model, and use the labeled energy storage cabinet state parameter data set as the input of the gradient boosting tree model to perform dual-task learning, and output the optimized adaptive heat supply control strategy and optimized multi-level safety measures through training;

[0113] S4.5: Apply the optimized adaptive heat supply control strategy and the optimized multi-level safety measures to the actual system, and perform multi-dimensional evaluation again to generate an optimized multi-dimensional evaluation result report;

[0114] S4.6: Compare the evaluation results before and after optimization to verify whether the effect after optimization reaches the expected goal. If not, repeat S4.2 to S4.5 for iterative training.

[0115] The specific steps of S4.4 include:

[0116] S4.41: Load the pre-trained gradient boosting tree model and obtain the labeled energy storage cabinet state parameter data set, wherein the gradient boosting tree model is the prior art content in this field and is not the inventive solution of the present application, and will not be described in detail here;

[0117] S4.42: Define the mean square error objective function for dual-task learning, and combine the loss functions of the dual tasks to form the total loss function ,in, represents the loss function of the heat supply control strategy task, represents the safety measure task loss function, represents the weight coefficient;

[0118] Further, ;

[0119] in, represents the predicted value of the thermal energy supply control strategy of the i-th labeled energy storage cabinet state parameter data predicted by the gradient boosting tree model, represents the actual heat supply control strategy value of the i-th annotated energy storage cabinet state parameter data, represents the safety measure value of the i-th labeled energy storage cabinet state parameter data predicted by the gradient boosting tree model, Represents the actual safety measure value of the energy storage cabinet status parameter data after the i-th annotation.

[0120] S4.43: Input the labeled energy storage cabinet state parameter data set into the gradient boosting tree model, perform dual-task learning training, and obtain a trained gradient boosting tree model;

[0121] S4.44: Use the trained gradient boosting tree model to predict the annotated energy storage cabinet status parameter data set obtained in real time, and generate an optimized adaptive thermal energy supply control strategy and optimized multi-level safety measures. The training and prediction process of the gradient boosting tree model is the prior art content in this field, and is not the creative solution of this application, and will not be elaborated here.

[0122] Example 2

[0123] See also Figure 3 Another embodiment provided by the present invention is a thermal energy intelligent adaptation system for an energy storage cabinet production process, comprising:

[0124] Monitoring module, intelligent analysis module, control strategy module, effect evaluation module;

[0125] Monitoring module, used to collect status parameter data in the production process in real time;

[0126] Intelligent analysis module, which is used to perform intelligent analysis based on real-time state parameter data and historical state parameter data using machine learning models to predict thermal energy demand;

[0127] The control strategy module is used to formulate an adaptive heat supply control strategy based on the heat demand forecast results, and automatically adjust the working state of the heat supply equipment to meet the heat demand in the production process;

[0128] The effect evaluation module is used to conduct a multi-dimensional evaluation of the effects after the implementation of the adaptive heat supply control strategy and multi-level safety measures.

[0129] The control strategy module includes: control strategy formulation unit, temperature monitoring unit, and emergency shutdown unit;

[0130] A control strategy formulation unit, used to formulate an adaptive heat supply control strategy according to the heat demand prediction results;

[0131] The temperature monitoring unit is used to monitor the temperature during the production process in real time and immediately trigger the early warning mechanism when abnormally high temperatures are detected;

[0132] Emergency stop unit: In high-risk operation areas such as welding and laser cutting, safety isolation measures and emergency stop buttons are set up to ensure production safety.

[0133] The effect evaluation module includes: multi-dimensional evaluation unit, data-driven optimization unit, and recording and feedback unit;

[0134] Multi-dimensional evaluation unit, used to evaluate the effects of implementing adaptive heat supply control strategies and multi-level safety measures in multiple dimensions, including production efficiency, energy consumption, safety, etc.

[0135] Data-driven optimization unit, based on multi-dimensional evaluation results and real-time collected state parameter data, uses data-driven methods to improve and optimize adaptive heat supply control strategies and multi-level safety measures;

[0136] The recording and feedback unit is used to record the changes made during the entire development process and their reasons, and provide experience and feedback for subsequent continuous optimization.

[0137] Example 3

[0138] An electronic device includes a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, steps of a thermal energy intelligent adaptation method for an energy storage cabinet production process are implemented. For details, please refer to the above method embodiment, which will not be repeated here.

[0139] The embodiments of the present invention are described above in conjunction with the accompanying drawings, but the present invention is not limited to the above-mentioned specific implementation modes, which are merely illustrative rather than restrictive. Under the guidance of the present invention, ordinary technicians in the field may also change, modify, replace and modify the above-mentioned embodiments without departing from the purpose and scope of protection of the present invention, and all of these are within the protection of the present invention.

Claims

1. A thermal energy intelligent adaptation method for an energy storage cabinet production process, characterized in that: include: Step S1: installing sensors in different areas of the energy storage cabinet production process to monitor the production process in real time, and collecting state parameter data in real time during the monitoring process; Step S2: Based on the real-time state parameter data and the historical state parameter data extracted from the database, a hybrid machine learning model is used to predict the heat energy demand under different conditions in different production stages; Step S3: formulating an adaptive heat supply control strategy based on the heat demand forecast results and establishing multi-level safety measures; Step S4: after implementing the adaptive heat supply control strategy and the multi-level safety measures, a multi-dimensional evaluation is performed on the effect after the implementation, and based on the multi-dimensional evaluation results and the state parameter data collected in real time, a data-driven method is used to improve and optimize the adaptive heat supply control strategy and the multi-level safety measures; Step S5: Record the changes made during the development process and their reasons to build a knowledge base; The specific steps of step S3 include: S3.1: Obtain the forecast results of heat demand, analyze the heat demand trend in the current time period, and set the upper threshold of heat supply and lower threshold ,like ,or When the temperature is high, the heat supply is automatically adjusted. The heat supply adjustment formula is: ； in, Indicates the current time period The heat demand within Indicates the heat supply adjustment, It represents the proportionality coefficient between the heat demand forecast and the actual heat supply, represents the coefficient of change rate of heat energy demand and actual heat energy supply, represents the difference coefficient, represents the current forecast value of heat energy demand, Indicates the actual heat supply. Indicates the current time period The predicted value of heat energy demand within Indicates the current time period The actual heat supply in the S3.2: Use temperature sensors on the production line to monitor the temperature during the production process in real time and set warning thresholds for abnormally high temperatures ,like When an emergency occurs, the emergency response mechanism is automatically triggered and multi-level security measures are taken, including: Indicates the temperature in the current production process; S3.3: For welding and laser cutting operation areas, set up intelligent safety barriers and one-touch emergency stop buttons, and conduct regular safety inspections and maintenance.

2. The thermal energy intelligent adaptation method of the energy storage cabinet production process according to claim 1, characterized in that: The sensor installation positions in step S1 include cold plates, welding areas of stainless steel plates, laser welding areas of aluminum plates, cabinet surface treatment areas, plastic spraying and painting areas, and electrical component installation areas in the electric control cabinet; the status parameter data include equipment working status parameters, material type parameters, surface treatment type parameters, plastic spraying and painting parameters, and environmental parameters in the electric control cabinet.

3. The thermal energy intelligent adaptation method of the energy storage cabinet production process according to claim 2, characterized in that: The specific steps of step S4 include: S4.1: Acquire the real-time status parameter data and historical status parameter data in step S2, and form a storage cabinet status parameter data set through data integration ,in, represents the nth energy storage cabinet state parameter data, and n represents the number of energy storage cabinet state parameter data; S4.2: Define multiple evaluation indicators based on the energy storage cabinet state parameter dataset , perform multi-dimensional evaluation based on multiple evaluation indicators and generate a multi-dimensional evaluation result report. The multi-dimensional evaluation formula is: ； in, Indicates the average deviation between the actual temperature and the set temperature. represents the actual temperature at the i-th time point, m represents the length of the time period for temperature measurement, represents the set temperature at the i-th time point, It represents the energy consumption per unit time. represents the power of the energy storage cabinet at time t, Indicates the fluctuation degree of the energy storage cabinet status parameter value, Indicates the state parameter data of the kth energy storage cabinet, Represents the mean value of the energy storage cabinet status parameter data, It indicates the average response time for the system to take measures after detecting an abnormal situation. represents the time of the jth response, and M represents the number of responses in which the system detects an abnormal situation and takes measures.

4. The thermal energy intelligent adaptation method of the energy storage cabinet production process according to claim 3 is characterized in that: The specific steps of step S4 also include: S4.3: According to the multi-dimensional evaluation results, label each energy storage cabinet state parameter data with a heat supply control strategy label and a safety measure label to obtain a labeled energy storage cabinet state parameter data set; S4.4: Load the pre-trained gradient boosting tree model, and use the labeled energy storage cabinet state parameter data set as the input of the gradient boosting tree model to perform dual-task learning, and output the optimized adaptive heat supply control strategy and optimized multi-level safety measures through training; S4.5: Apply the optimized adaptive heat supply control strategy and the optimized multi-level safety measures to the actual system, and perform multi-dimensional evaluation again to generate an optimized multi-dimensional evaluation result report; S4.6: Compare the evaluation results before and after optimization to verify whether the effect after optimization reaches the expected goal. If not, repeat S4.2 to S4.5 for iterative training.

5. The thermal energy intelligent adaptation method of the energy storage cabinet production process according to claim 4, characterized in that: The specific steps of S4.4 include: S4.41: Load the pre-trained gradient boosting tree model and obtain the labeled energy storage cabinet state parameter data set; S4.42: Define the mean square error objective function for dual-task learning, and combine the loss functions of the dual tasks to form a total loss function ,in, represents the loss function of the heat supply control strategy task, represents the safety measure task loss function, represents the weight coefficient; S4.43: Input the labeled energy storage cabinet state parameter data set into the gradient boosting tree model, perform dual-task learning training, and obtain a trained gradient boosting tree model; S4.44: Use the trained gradient boosting tree model to predict the labeled energy storage cabinet state parameter data set obtained in real time, and generate an optimized adaptive heat supply control strategy and optimized multi-level safety measures.

6. A thermal energy intelligent adaptation system for an energy storage cabinet production process, which is used to implement a thermal energy intelligent adaptation method for an energy storage cabinet production process according to any one of claims 1 to 5, characterized in that: include: Monitoring module, intelligent analysis module, control strategy module, effect evaluation module; The monitoring module is used to collect state parameter data during the production process in real time; The intelligent analysis module is used to perform intelligent analysis based on real-time state parameter data in combination with historical state parameter data using a machine learning model to predict thermal energy demand; The control strategy module is used to formulate an adaptive heat supply control strategy according to the heat demand prediction result, and automatically adjust the working state of the heat supply equipment; The effect evaluation module is used to perform a multi-dimensional evaluation on the effects after the implementation of the adaptive heat supply control strategy and the multi-level safety measures.

7. A thermal energy intelligent adaptation system for energy storage cabinet production process according to claim 6, characterized in that: The control strategy module includes: a control strategy formulation unit and a temperature monitoring unit; The control strategy formulation unit is used to formulate an adaptive heat supply control strategy according to the heat demand prediction result; The temperature monitoring unit is used to monitor the temperature during the production process in real time, and trigger an early warning mechanism when an abnormally high temperature is detected.

8. The thermal energy intelligent adaptation system for the energy storage cabinet production process according to claim 7, characterized in that: The effect evaluation module includes: a multi-dimensional evaluation unit, a data-driven optimization unit, and a recording and feedback unit; The multi-dimensional evaluation unit is used to perform a multi-dimensional evaluation on the effect of implementing the adaptive heat supply control strategy and the multi-level safety measures; The data-driven optimization unit improves and optimizes the adaptive heat supply control strategy and multi-level safety measures using a data-driven approach based on the multi-dimensional evaluation results and the state parameter data collected in real time; The recording and feedback unit is used to record the changes made during the development process and the reasons therefor.

9. An electronic device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the thermal energy intelligent adaptation method for the energy storage cabinet production process described in any one of claims 1-5 are implemented.

Images