Intelligent monitoring method and system for cold and hot impact box

Abstract

The invention relates to the technical field of cold and hot impact box monitoring, in particular to an intelligent monitoring method and system for a cold and hot impact box. The method comprises the following steps: carrying out real-time operation state monitoring on a cold and hot impact box, carrying out time point transient state feature mining one by one, and generating a transient state feature of each time node; performing transient abrupt change analysis on the transient state characteristic of each time node, and performing cold and hot alternating temperature fluctuation analysis so as to generate a cold state temperature fluctuation parameter and a hot state temperature fluctuation parameter; state alternating transition analysis is conducted on the cold state temperature fluctuation parameters and the hot state temperature fluctuation parameters, dynamic transition trend evolution is conducted, and therefore a cooling and heating alternating state trend evolution graph is generated; and obtaining a hot and cold impact box operation log. According to the invention, efficient and accurate fault analysis and prediction of the cold and hot impact box are realized.

Description

Technical Field

[0001] The present invention relates to the technical field of thermal shock chamber monitoring, and in particular to an intelligent monitoring method and system for thermal shock chambers. Background Art

[0002] In today's highly automated manufacturing environment, hot and cold shock chambers, as a key environmental simulation test equipment, play an important role in product reliability verification. This equipment effectively evaluates the product's ability to resist temperature shock by applying rigorous temperature cycles to the product to simulate the harsh environmental conditions that the product may encounter during actual use. However, due to the special operating properties of the hot and cold shock chambers and long-term hot and cold alternating experiments, the probability of failure of the shock chamber is relatively high. Traditional hot and cold shock chamber monitoring methods usually rely on manual observation and manual recording, and there are problems such as low monitoring efficiency and inaccurate prediction of failure probability. With the in-depth development of industrial automation, higher requirements are placed on the intelligent monitoring of hot and cold shock chambers. Therefore, there is an urgent need for a more intelligent intelligent monitoring method for hot and cold shock chambers. Summary of the invention

[0003] In order to solve the above technical problems, the present invention proposes an intelligent monitoring method and system for a cold and hot shock box to solve at least one of the above technical problems.

[0004] To achieve the above object, the present invention provides an intelligent monitoring method for a cold and hot shock chamber, comprising the following steps: Step S1: monitor the operation status of the hot and cold shock box in real time, and mine the transient state characteristics at each time point to generate the transient state characteristics of each time node; Step S2: performing transient mutation analysis on the transient state characteristics of each time node, and performing cold and hot alternating temperature fluctuation analysis, thereby generating cold state temperature fluctuation parameters and hot state temperature fluctuation parameters; Step S3: performing state alternation transition analysis on the cold state temperature fluctuation parameters and the hot state temperature fluctuation parameters, and performing dynamic transition trend evolution, thereby generating a cold-hot alternation state trend evolution map; Step S4: obtaining the operation log of the hot and cold shock box; performing hot and cold alternating shock simulation on the hot and cold alternating state trend evolution map according to the hot and cold shock box operation log, and performing time series state response recognition to construct hot and cold alternating response maps for multiple time periods; Step S5: Calculate the temperature rise amplitude of the hot and cold alternating response diagrams of multiple time periods, locate the abnormal state, and mark the abnormal time period; Step S6: predict the probability of abnormal failures in the abnormal time period, make abnormal fault diagnosis decisions, and build a shock box failure decision strategy to perform real-time status monitoring of the hot and cold shock boxes.

[0005] The present invention helps to instantly understand the working conditions of the equipment by real-time monitoring of the operating status of the hot and cold shock box, timely discover problems and take measures, and mining transient state characteristics at each time point can capture the instantaneous changes in the equipment state, providing detailed data support for subsequent analysis. Transient mutation analysis helps to identify mutations in temperature changes and warn of possible abnormal conditions in advance. The generation of hot and cold alternating temperature fluctuation parameters can evaluate temperature fluctuations and provide data support for subsequent state analysis and control. The evolution trend of the hot and cold alternating state is analyzed through the state trend evolution map, which helps to understand the transition rules between different states and provide a basis for state prediction and regulation. The dynamic transition trend evolution helps to grasp the state change rules of the hot and cold shock box. It provides a reference for equipment management and maintenance. Through the hot and cold alternating shock simulation, it can simulate the hot and cold changes in the real working environment, evaluate the responsiveness and stability of the equipment, and construct the hot and cold alternating response diagram to help analyze the response in different time periods, find abnormal responses and problems, and make timely adjustments. Calculating the temperature rise amplitude can quantify the temperature changes of the equipment during the hot and cold alternation process, and help evaluate the stability and performance of the equipment. Abnormal state positioning can accurately locate the time period when the abnormality occurs, provide guidance for fault diagnosis and repair, and predict the probability of abnormal failures to help early warning of possible problems and reduce losses caused by failures. Constructing an impact box fault decision-making strategy can guide fault diagnosis decisions, speed up fault location and repair, and ensure stable equipment operation.

[0006] Preferably, step S1 comprises the following steps: Step S11: monitor the operation status of the hot and cold shock chamber in real time and collect operation status monitoring parameters; Step S12: performing abnormal missing value filling processing on the operating status monitoring parameters to obtain missing value filled status monitoring parameters; Step S13: performing multi-time point parameter sampling on the missing value filling state monitoring parameters to obtain state monitoring parameters at multiple time nodes; Step S14: mining transient state features of the state monitoring parameters of multiple time nodes one by one, and generating transient state features of each time node.

[0007] The present invention helps to timely capture the operation status of the equipment and discover potential problems in advance by real-time monitoring of the operation status of the cold and hot shock box.

[0008] Collecting operating status monitoring parameters can provide comprehensive data support and provide a basis for subsequent analysis and decision-making. Processing abnormal missing values ​​helps to ensure the integrity and accuracy of the data and avoid analysis errors caused by missing data.

[0009] The parameters after filling in the missing values ​​can provide more complete and reliable condition monitoring data, providing a more accurate basis for subsequent analysis. Multi-point parameter sampling can capture the diversity and change trends of equipment status, providing support for a comprehensive understanding of equipment status.

[0010] Generating condition monitoring parameters at multiple time nodes helps build a comprehensive condition monitoring database and provide a data basis for subsequent analysis and comparison. Mining transient state characteristics at each time point can provide an in-depth understanding of the state characteristics at each time node and discover temporary changes and patterns in the state.

[0011] Generating transient state features helps to identify key features and trends of state changes, providing important clues for condition monitoring and problem diagnosis.

[0012] Preferably, the specific steps of step S12 are: Perform abnormal state parameter detection on the operating state monitoring parameters and extract abnormal state parameters; Perform outlier elimination processing based on abnormal state parameters to obtain abnormal elimination state monitoring parameters; Define the sliding window length value; According to the sliding window length value, the abnormal elimination state monitoring parameter is divided into time series windows to obtain a state monitoring parameter sequence of multiple time windows; Identify missing values ​​of condition monitoring parameter sequences in multiple time windows and extract missing values ​​of parameters in each time window; The abnormal elimination status monitoring parameters are averaged dimension by dimension to obtain the average parameter value of each dimension; Based on the average value of the parameters in each dimension, linear interpolation is performed to fill the missing values ​​of the parameters in each time window to obtain the missing value filling state monitoring parameters.

[0013] The present invention helps to identify parameters that may have problems by detecting and extracting abnormal state parameters, providing an important basis for subsequent processing. Extracting abnormal state parameters can help focus attention on parameters that may be abnormal and improve problem diagnosis efficiency. Eliminating abnormal values ​​can improve data quality and accuracy and ensure the reliability of subsequent analysis. Obtaining abnormal elimination state monitoring parameters helps to perform subsequent analysis and decision-making based on more reliable data. Dividing time series windows can segment data by time to better capture trends and laws of state changes. Generating state monitoring parameter sequences for multiple time windows helps to analyze and compare states in different time periods. Identifying missing parameter values ​​for each time window helps to discover missing data and avoid the impact of incomplete data on analysis. Filling missing values ​​can improve data integrity and ensure the accuracy and reliability of subsequent analysis. Calculating the average parameter value of each dimension helps to understand the trend and change of parameters as a whole and provide a reference for subsequent analysis. Filling missing values ​​with linear interpolation can effectively restore missing data and ensure data integrity, providing more reliable data support for subsequent analysis.

[0014] Preferably, the specific steps of step S2 are: Step S21: performing time series change analysis on the transient state characteristics of each time node to generate transient state change characteristic data; Step S22: performing transient change time series fitting on the transient state change characteristic data to construct a transient change curve of the impact box; Step S23: Perform transient mutation analysis on the transient change curve of the impact box and mark the hot and cold alternating change timestamp; Step S24: performing a cold-hot alternating temperature fluctuation analysis on the transient state characteristics of each time node based on the cold-hot alternating change timestamp, thereby generating a cold state temperature fluctuation parameter and a hot state temperature fluctuation parameter.

[0015] The present invention helps to explore the changing trend of transient state characteristics over time through time series change analysis, reveals the regularity of state changes, generates transient state change characteristic data, can provide a detailed description of state changes, and provides a data basis for subsequent analysis. By fitting the transient change time series, the data can be integrated into a continuous curve to better display the trend and characteristics of state changes. Constructing the transient change curve of the impact box helps to intuitively display the state change process, and provides support for subsequent analysis and visualization. Transient mutation analysis can help identify mutation points in state changes, marking key timestamps helps to record key moments of state changes, marking hot and cold alternating change timestamps helps to identify the periodicity of temperature changes, and provides a basis for subsequent temperature fluctuation analysis. Temperature fluctuation analysis can reveal the temperature change law under hot and cold alternating states, and help understand the operating status of the equipment. Generating temperature fluctuation parameters for cold and hot states helps to evaluate the stability and performance of the equipment, and provides a reference for equipment maintenance and optimization.

[0016] Preferably, step S3 specifically comprises the following steps: Step S31: Calculate the peak-to-valley interval of the transient change curve of the impact box to obtain the cold-hot alternating cycle period; Step S32: Calculate the mutation frequency of the transient change curve of the impact box to obtain the frequency of hot and cold alternation within the cycle; Step S33: mining the alternating logic of the hot and cold alternating cycle based on the hot and cold alternating frequency within the cycle, thereby generating a hot and cold alternating law; Step S34: performing state alternating transition analysis on the cold state temperature fluctuation parameter and the hot state temperature fluctuation parameter, thereby generating an alternating process parameter transition feature; Step S35: dynamically evolve the transition trend of the parameter transition characteristics of the alternating process according to the cold-hot alternating transformation rule, thereby generating a cold-hot alternating state trend evolution map.

[0017] The present invention can reveal the periodicity of the transient change curve of the impact box by calculating the peak-to-valley interval, help understand the period of the hot-cold alternating cycle, and obtain the hot-cold alternating cycle period to help determine the frequency and regularity of state changes, providing a basis for subsequent analysis. Calculating the mutation frequency can quantify the change frequency in the transient change curve of the impact box, help understand the speed and frequency of state changes, and obtain the hot-cold alternating frequency within the period to help evaluate the speed of state changes, providing important data support for subsequent analysis. Logically mining the hot-cold alternating transformation law can help understand the mechanism and regularity of state conversion, provide in-depth understanding for state monitoring, generate the hot-cold alternating transformation law to help predict future state changes, and provide guidance for equipment maintenance and management. State alternating transition analysis can reveal the change characteristics of parameters under the hot-cold alternating state, help understand the process of state conversion, generate the transition characteristics of the alternating process parameters to help quantify the process of state change, and provide a detailed description for state monitoring and analysis. Dynamic trend evolution analysis of transition characteristics according to the hot-cold alternating transformation law can help understand the evolution process of the state, and generate the hot-cold alternating state trend evolution map to help intuitively display the trend and law of state change, providing visualization support for decision-making.

[0018] Preferably, the specific steps of step S4 are: Step S41: obtaining the operation log of the hot and cold shock chamber; Step S42: Calculate the remaining number of hot and cold alternations in the hot and cold shock box operation log to obtain the remaining number of operation alternations; Step S43: performing a cold-hot alternation impact simulation on the cold-hot alternation state trend evolution map according to the remaining number of alternating operations, and collecting parameters in multiple time periods to generate cold-hot alternation simulation data in multiple time periods; Step S44: performing time series state response identification on the hot-cold alternation simulation data of multiple time periods, and constructing hot-cold alternation response diagrams of multiple time periods.

[0019] The present invention can record the operating status and historical data of the equipment by obtaining the operating log of the hot and cold shock box, providing a basis for subsequent analysis. The information contained in the operating log can be used to understand the operating conditions, fault conditions, etc. of the equipment, which is helpful for equipment management and maintenance. Calculating the remaining number of hot and cold alternations can help predict the life of the equipment and the remaining operating cycle, providing a reference for equipment maintenance and planning. Obtaining the remaining number of operating alternations is helpful to evaluate the health status of the equipment and take corresponding maintenance measures in time. Performing hot and cold alternating shock simulation can simulate the response of the equipment under different working conditions and help understand the performance of the equipment. Multi-time period parameter acquisition can obtain hot and cold alternating simulation data in different time periods to provide support for diversified analysis. Performing time series state response identification on hot and cold alternating simulation data can help understand the response of the equipment under different conditions and the regularity of state changes. Constructing hot and cold alternating response diagrams for multiple time periods is helpful to compare the response of the equipment in different time periods, providing more detailed data support for state monitoring and analysis.

[0020] Preferably, the specific steps of step S5 are: Step S51: mining the temperature state of each time period on the hot-cold alternating response diagrams of multiple time periods, and extracting the temperature state characteristics of each time period; Step S52: Calculate the temperature rise amplitude for the temperature state characteristics of each time period to generate the temperature rise amplitude for each time period; Step S53: analyzing the abnormal temperature change of the temperature rise amplitude in each time period to obtain abnormal temperature change data; Step S54: locate the abnormal state based on the abnormal temperature change data and mark the abnormal time period.

[0021] The present invention can help understand the temperature variation law in each time period by mining the temperature status characteristics time period by time period, and provide data support for anomaly detection. Extracting the temperature status characteristics of each time period is helpful to identify the mode and trend of temperature variation, and provide a basis for subsequent analysis. Calculating the temperature rise amplitude in each time period can quantify the temperature variation amplitude, and help evaluate the working status and stability of the equipment. Generating the temperature rise amplitude data for each time period is helpful to compare the temperature variation in different time periods, and provide a reference for anomaly detection. Analyzing the abnormal temperature variation of the temperature rise amplitude can help detect abnormal conditions and promptly discover problems in the operation of the equipment. Obtaining the abnormal temperature variation data is helpful to identify the characteristics of the abnormal state of the equipment, and provide a basis for fault diagnosis and maintenance. Abnormal state positioning based on abnormal temperature variation data can help accurately locate the abnormal problems of the equipment and guide subsequent processing and maintenance. Marking the abnormal time period is helpful to monitor the changes in the equipment state in real time, and take timely measures to avoid potential risks.

[0022] Preferably, the specific steps of step S6 are: Step S61: performing abnormal attribution inference on the abnormal time period to obtain abnormal state factors; Step S62: predicting the probability of abnormal failure for the abnormal state factors to obtain the predicted probability of alternating hot and cold failures; Step S63: performing a fault risk analysis based on the cold-hot alternating fault prediction probability, thereby generating alternating fault risk data; Step S64: making abnormal fault diagnosis decisions on the alternating fault risk data and constructing a shock box fault decision strategy; Step S65: Based on the impact box fault decision strategy, intelligent monitoring and protection are performed on the cold and hot impact box to perform real-time status monitoring operations of the cold and hot impact box.

[0023] The present invention can help determine the cause and root cause of the abnormality by performing abnormal attribution inference on the abnormal time period, guide subsequent processing measures, obtain abnormal state factors, help understand possible problems and risk sources in equipment operation, predict abnormal failure probabilities for abnormal state factors, help evaluate the possibility of equipment failure and make preparations in advance, obtain the predicted probability of alternating hot and cold failures, help conduct risk assessment and formulate preventive measures, perform fault risk analysis based on the predicted probability of alternating hot and cold failures, help identify risks and problems that the equipment may face, generate alternating failure risk data, help formulate targeted fault prevention and processing strategies, perform abnormal fault diagnosis decisions on alternating failure risk data, help quickly and accurately handle equipment abnormalities and avoid fault expansion, construct impact box fault decision strategies, help improve equipment stability and reliability, reduce downtime and maintenance costs, perform intelligent monitoring and protection of hot and cold shock boxes based on the impact box fault decision strategies, and achieve real-time monitoring and protection of equipment status, and perform real-time status monitoring operations of hot and cold shock boxes, which help to promptly detect abnormal situations and take corresponding measures to ensure safe operation and work efficiency of equipment.

[0024] In this specification, an intelligent monitoring system for a cold and hot shock box is provided, which is used to execute the intelligent monitoring method for the cold and hot shock box as described above, comprising: The transient feature mining module monitors the real-time operation status of the hot and cold shock chamber, and mines the transient state features at each time point to generate the transient state features of each time node; The transient mutation module performs transient mutation analysis on the transient state characteristics of each time node, and performs cold and hot alternating temperature fluctuation analysis, thereby generating cold state temperature fluctuation parameters and hot state temperature fluctuation parameters; The dynamic transition trend module performs state alternation transition analysis on the temperature fluctuation parameters of the cold state and the temperature fluctuation parameters of the hot state, and performs dynamic transition trend evolution, thereby generating a cold-hot alternation state trend evolution map; The hot-cold alternation simulation module obtains the hot-cold alternation shock box operation log; performs hot-cold alternation shock simulation on the hot-cold alternation state trend evolution map according to the hot-cold alternation shock box operation log, and performs time series state response recognition to construct hot-cold alternation response maps for multiple time periods; The abnormal state positioning module calculates the temperature rise amplitude of the hot and cold alternating response diagrams in multiple time periods, locates the abnormal state, and marks the abnormal time period; The fault diagnosis module predicts the probability of abnormal faults in abnormal time periods, makes abnormal fault diagnosis decisions, and builds a shock box fault decision strategy to perform real-time status monitoring operations for hot and cold shock boxes.

[0025] The present invention helps to immediately discover potential problems by real-time monitoring of the status of the hot and cold shock box, improves the response speed and equipment stability, and mining transient state characteristics at each time point can help understand the changes in the equipment operation status and provide data support for subsequent analysis. Transient mutation analysis can capture the mutation of temperature fluctuations, which helps to timely discover abnormal fluctuations and conduct further research. The hot and cold alternating temperature fluctuation analysis can reveal the temperature fluctuation characteristics under different states and provide a reference for state transition. The state alternation transition analysis helps to understand the temperature change trend between different states and provide an in-depth understanding of the state transition mechanism. Generating a hot and cold alternating state trend evolution map can help monitor the state evolution in real time and provide support for prediction and The simulation of alternating hot and cold shocks based on the operation log can help simulate the real working environment and evaluate the performance of the equipment under different working conditions. The recognition of time-series state response can help identify abnormal conditions and provide support for fault diagnosis and prevention. The calculation of temperature rise and the positioning of abnormal conditions can help accurately locate abnormal conditions and improve the accuracy of fault location. Marking abnormal time periods can help monitor the occurrence of abnormal conditions and provide clues for further processing. The prediction of abnormal fault probability and diagnosis decision-making can help to deal with abnormal conditions in a timely and accurate manner and reduce the impact of equipment failure on production. The construction of an impact box fault decision-making strategy can improve equipment maintenance efficiency and production stability and ensure the safe operation of equipment. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] Figure 1 A schematic flow chart of the steps of an intelligent monitoring method for a cold and hot shock box according to 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

[0027] 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.

[0028] The present application example provides an intelligent monitoring method and system for a hot and cold shock box. The execution subject of the intelligent monitoring method and system for a hot and cold shock box 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 a 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.

[0029] See also Figures 1 to 4The present invention provides an intelligent monitoring method for a cold and hot shock box, and the intelligent monitoring method for a cold and hot shock box comprises the following steps: Step S1: monitor the operation status of the hot and cold shock box in real time, and mine the transient state characteristics at each time point to generate the transient state characteristics of each time node; Step S2: performing transient mutation analysis on the transient state characteristics of each time node, and performing cold and hot alternating temperature fluctuation analysis, thereby generating cold state temperature fluctuation parameters and hot state temperature fluctuation parameters; Step S3: performing state alternation transition analysis on the cold state temperature fluctuation parameters and the hot state temperature fluctuation parameters, and performing dynamic transition trend evolution, thereby generating a cold-hot alternation state trend evolution map; Step S4: obtaining the operation log of the hot and cold shock box; performing hot and cold alternating shock simulation on the hot and cold alternating state trend evolution map according to the hot and cold shock box operation log, and performing time series state response recognition to construct hot and cold alternating response maps for multiple time periods; Step S5: Calculate the temperature rise amplitude of the hot and cold alternating response diagrams of multiple time periods, locate the abnormal state, and mark the abnormal time period; Step S6: predict the probability of abnormal failures in the abnormal time period, make abnormal fault diagnosis decisions, and build a shock box failure decision strategy to perform real-time status monitoring of the hot and cold shock boxes.

[0030] The present invention helps to instantly understand the working conditions of the equipment by real-time monitoring of the operating status of the hot and cold shock box, timely discover problems and take measures, and mining transient state characteristics at each time point can capture the instantaneous changes in the equipment state, providing detailed data support for subsequent analysis. Transient mutation analysis helps to identify mutations in temperature changes and warn of possible abnormal conditions in advance. The generation of hot and cold alternating temperature fluctuation parameters can evaluate temperature fluctuations and provide data support for subsequent state analysis and control. The evolution trend of the hot and cold alternating state is analyzed through the state trend evolution map, which helps to understand the transition rules between different states and provide a basis for state prediction and regulation. The dynamic transition trend evolution helps to grasp the state change rules of the hot and cold shock box. It provides a reference for equipment management and maintenance. Through the hot and cold alternating shock simulation, it can simulate the hot and cold changes in the real working environment, evaluate the responsiveness and stability of the equipment, and construct the hot and cold alternating response diagram to help analyze the response in different time periods, find abnormal responses and problems, and make timely adjustments. Calculating the temperature rise amplitude can quantify the temperature changes of the equipment during the hot and cold alternation process, and help evaluate the stability and performance of the equipment. Abnormal state positioning can accurately locate the time period when the abnormality occurs, provide guidance for fault diagnosis and repair, and predict the probability of abnormal failures to help early warning of possible problems and reduce losses caused by failures. Constructing an impact box fault decision-making strategy can guide fault diagnosis decisions, speed up fault location and repair, and ensure stable equipment operation.

[0031] In the embodiment of the present invention, refer to Figure 1 , is a schematic flow chart of the steps of an intelligent monitoring method for a cold and hot shock box of the present invention. In this example, the steps of the intelligent monitoring method for a cold and hot shock box include: Step S1: monitor the operation status of the hot and cold shock box in real time, and mine the transient state characteristics at each time point to generate the transient state characteristics of each time node; In this embodiment, multiple sensors are installed in the hot and cold shock box to monitor key parameters in real time, such as temperature, humidity, air pressure, flow rate, etc. These sensors should have high precision and fast response capabilities. Suitable monitoring equipment, such as thermocouples, humidity sensors and pressure sensors, are selected. A data acquisition system is configured to ensure that sensor data can be received and stored in real time. The system should support high-frequency data acquisition to capture transient state changes. A data acquisition card or an embedded system (such as RaspberryPi or Arduino) is used for data acquisition. The hot and cold shock box is started, and the data acquisition system is started at the same time to ensure that each sensor starts to record data in real time. The data recording frequency is set, such as collecting data once per second, so as to capture transient changes. The real-time collected data Clean the data, remove noise and outliers, ensure data accuracy, handle missing values, use interpolation or filling methods to ensure data continuity, analyze the data at each time node, extract transient state features, use time series analysis methods, such as sliding window technology, to capture the rate of change and trend at each time point, organize the extracted transient features into a data set, and form the transient state features of each time node. The data set should include timestamps and corresponding feature values ​​for subsequent analysis. Use statistical analysis software (such as Python's Pandas, NumPy, or R) to analyze the transient feature data, identify the relationship between features and change trends, and apply machine learning or deep learning algorithms (such as cluster analysis, regression analysis) to further explore potential rules.

[0032] Step S2: performing transient mutation analysis on the transient state characteristics of each time node, and performing cold and hot alternating temperature fluctuation analysis, thereby generating cold state temperature fluctuation parameters and hot state temperature fluctuation parameters; In this embodiment, a statistical method (such as Z-score, moving average or CUSUM method) is used to detect the mutation point of the temperature data, and the standard of the mutation point is determined. For example, when the temperature change rate exceeds a preset threshold, it is marked as a mutation state, and the time, mutation amplitude (temperature change amount) and duration of each mutation point are recorded. The mutation characteristics are classified to identify whether it is a cold mutation or a hot mutation for subsequent analysis. According to the mutation point, the temperature data is divided into a cold state segment and a hot state segment. Each segment of data represents a temperature state (cold or hot). The fluctuation amplitude of the temperature data in the cold state and the hot state is calculated respectively. The standard deviation or range is usually used to quantify the degree of fluctuation. The fluctuation amplitude of the cold state segment is recorded as the cold state temperature fluctuation parameter, and the fluctuation amplitude of the hot state segment is recorded as the hot state temperature fluctuation parameter. The cold state temperature fluctuation parameter and the hot state temperature fluctuation parameter are organized into a report, which includes mutation analysis results and fluctuation analysis results, and provides data visualization (such as a line chart, a bar chart) to show the temperature fluctuation characteristics in the cold and hot alternation process for easy understanding and decision-making.

[0033] Step S3: performing state alternation transition analysis on the cold state temperature fluctuation parameters and the hot state temperature fluctuation parameters, and performing dynamic transition trend evolution, thereby generating a cold-hot alternation state trend evolution map; In this embodiment, the fluctuation parameters of the cold state and the hot state are organized into time series data for subsequent analysis, ensuring that the timestamp corresponds to the fluctuation parameters to form a unified data set, and determining the alternation conditions between the cold state and the hot state, usually based on the threshold value or time period of the temperature change. By analyzing the changes in the fluctuation parameters, the time point of transition from the cold state to the hot state and the time point of transition from the hot state back to the cold state are identified, and the time, duration, fluctuation amplitude and change rate of each state alternation are recorded to form a characteristic data set of the alternating state for subsequent dynamic analysis. Statistical methods and time series analysis techniques (such as moving average, exponential smoothing) are used to analyze the dynamic change trend of the fluctuation parameters, and the rise, fall and stability of the fluctuation parameters during the alternation process are identified. Determine the trend, establish a mathematical model (such as linear regression, polynomial regression) to fit the trend of fluctuation parameters changing over time, apply the model to the entire time series data, predict future fluctuation trends, and use data visualization tools (such as Matplotlib, Seaborn or Tableau) to draw a trend evolution map of alternating hot and cold states. The map should show the fluctuation parameter changes, alternating state marks and trend lines in the time series, including the time axis, fluctuation parameters (cold state and hot state), alternating state indicators (such as marked points or shaded areas) and trend lines. Ensure that the map is clear and intuitive, and facilitate understanding of the dynamic changes in the process of alternating hot and cold. Organize the results of alternating transition analysis and dynamic trend evolution into a report, including the map and related data analysis.

[0034] Step S4: obtaining the operation log of the hot and cold shock box; performing hot and cold alternating shock simulation on the hot and cold alternating state trend evolution map according to the hot and cold shock box operation log, and performing time series state response recognition to construct hot and cold alternating response maps for multiple time periods; In this embodiment, the format and content of the operation log of the hot and cold shock box are determined, which usually includes parameters such as operation time, temperature setting, actual temperature, humidity, pressure, and current. The historical operation log is extracted from the control system or data recording system of the hot and cold shock box to ensure the integrity and accuracy of the data. The log data should cover a certain time range for subsequent analysis. The collected operation logs are sorted in chronological order to ensure that the timestamp of each record is consistent. The data is cleaned to remove unnecessary fields and invalid records. The initial conditions of the simulation are set according to the operation log, including the temperature change range, duration, and frequency of hot and cold alternation. The time step of the simulation is determined to capture subtle state changes. The hot and cold alternation state is simulated using computer simulation software (such as MATLAB, Simulink, or a custom simulation tool) to generate shock response data. During the simulation, the state parameters such as temperature and humidity at each time node are recorded to reflect the impact of hot and cold alternation. The time series state response data is extracted from the simulation results, and attention is paid to the temperature, Changes in humidity and other key parameters. Use time series analysis methods to identify the change patterns of various state parameters during the hot and cold alternation process and evaluate their response characteristics. Use statistical methods such as autocorrelation function (ACF) and partial autocorrelation function (PACF) to analyze the time series characteristics of the response data. According to the simulation results and operation logs, reasonably divide multiple time periods, usually based on the duration of the cold state and the hot state. Each time period should represent a complete hot and cold alternation cycle. Use data visualization tools (such as Matplotlib, Seaborn or Excel) to draw hot and cold alternation response diagrams for multiple time periods. The diagram should include changes in state parameters (such as temperature and humidity) for each time period, and mark the start and end time of the alternating state to ensure that the response diagram is clear and intuitive, and can show the hot and cold alternation state and corresponding parameter fluctuations in each time period. The generated diagram should facilitate observation of the relationship between hot and cold alternation and equipment performance and environmental impact. Organize the simulation results and response diagrams to form a complete analysis report, recording the results of the hot and cold alternation shock simulation and the time series state response.

[0035] Step S5: Calculate the temperature rise amplitude of the hot and cold alternating response diagrams of multiple time periods, locate the abnormal state, and mark the abnormal time period; In this embodiment, key temperature data is extracted from the hot and cold alternating response diagram to ensure that the data is complete and representative, and the temperature changes in each time period are recorded, including the highest temperature, the lowest temperature and the average temperature at each time node. The extracted temperature data is organized into a time series format for subsequent analysis, including a timestamp, a temperature value and an identifier of the time period to which it belongs. The temperature rise amplitude is usually defined as the temperature change amplitude within a specific time period. For each time period, the corresponding temperature rise amplitude is calculated and the results are recorded. The calculation results are organized into a table, including the time period identifier, the highest temperature, the lowest temperature and the temperature rise amplitude. According to industry standards or historical data, Define the abnormal threshold of temperature rise, for example, set the temperature rise exceeding a certain value (such as 10°C) as an abnormal state, traverse the calculated temperature rise data, identify the time period exceeding the abnormal threshold, record the start time and end time of the abnormal state, use logical conditions to filter, mark the detected abnormal time period in the hot and cold alternating response diagram, and use different colors or marking symbols to highlight the abnormal area to ensure that the mark is clearly visible for subsequent analysis and discussion. Organize the temperature rise calculation results and abnormal state positioning results to form a complete analysis report. The report should include the abnormal time period, temperature rise data and corresponding graphical representation.

[0036] Step S6: predict the probability of abnormal failures in the abnormal time period, make abnormal fault diagnosis decisions, and build a shock box failure decision strategy to perform real-time status monitoring of the hot and cold shock boxes.

[0037] In this embodiment, relevant data is extracted from the acquired abnormal time period records, including the abnormal temperature rise amplitude, duration, operation log, etc., and organized into structured data for subsequent analysis. Characteristic variables used for fault probability prediction, such as temperature fluctuation amplitude, ambient humidity, operation time, equipment load, etc., are determined to ensure data integrity and accuracy to improve the effect of the prediction model. A suitable fault prediction model is selected according to data characteristics. The following can be considered: statistical models (such as logistic regression), machine learning models (such as random forests, support vector machines, decision trees), deep learning models (such as neural networks), and the input and output of the model are determined. The output is usually the probability of a fault. The collected historical data is divided into a training set and a test set. The data set usually uses 70% of the data for training and 30% of the data for verification. The selected model is trained using the training set, and the model parameters are adjusted to improve the prediction accuracy. The model performance is evaluated on the test set. Indicators such as accuracy, recall, and F1-score are used to evaluate the prediction ability of the model. According to the results of abnormal fault probability prediction, fault diagnosis decision rules are formulated. For example, if the fault probability exceeds a certain threshold (such as 70%), a fault alarm is triggered. Combined with the operating status and historical fault records of the equipment, the corresponding maintenance measures are determined, and a complete set of fault decision-making strategies are designed, including fault warnings, response measures, and subsequent maintenance plans. Considering the operating environment and frequency of use of the equipment, personalized maintenance strategies are formulated.

[0038] 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: monitor the operation status of the hot and cold shock chamber in real time and collect operation status monitoring parameters; Step S12: performing abnormal missing value filling processing on the operating status monitoring parameters to obtain missing value filled status monitoring parameters; Step S13: performing multi-time point parameter sampling on the missing value filling state monitoring parameters to obtain state monitoring parameters at multiple time nodes; Step S14: mining transient state features of the state monitoring parameters of multiple time nodes one by one, and generating transient state features of each time node.

[0039] In this embodiment, it is ensured that the hot and cold shock box is equipped with necessary sensors, including temperature sensors, humidity sensors, pressure sensors and vibration sensors, to ensure that these parameters can be monitored in real time, configure a data acquisition system (such as a PLC or a data acquisition card) to ensure that real-time data from the sensors can be received and stored, start the operation program of the hot and cold shock box, activate the monitoring system, and start real-time collection of operation status parameters. During operation, the status monitoring parameters are regularly collected and recorded, including timestamps, temperature, humidity, pressure, etc., to ensure that data is collected at a preset frequency (such as every second, every minute), perform a preliminary analysis on the collected operation status monitoring parameters, identify missing values, and use the Pandas library in a programming language (such as Python) to detect missing data using the isnull() function. Combined with statistical methods (such as the Z-score or IQR method) to identify outliers, so as to avoid introducing erroneous data when filling missing values, and select a suitable missing value filling method. Common methods include: mean filling: using the mean of the parameter to fill missing values, interpolation: using linear interpolation or polynomial interpolation and other methods to fill in according to adjacent data points, KNN filling Filling: Use the K nearest neighbor algorithm to fill missing values ​​based on similar samples, use the selected filling method to process missing values, generate missing value filling state monitoring parameters, ensure that the filled data is consistent with the original data format, set a suitable sampling frequency (such as every minute, every hour) according to experimental requirements and data characteristics to ensure that enough samples are obtained for subsequent analysis, determine multiple time nodes for sampling, such as selecting key operating cycles or state change points, extract data at specified time nodes from missing value filling state monitoring parameters, generate state monitoring parameter sets for multiple time nodes, determine the definition of transient state characteristics, such as transient response time, maximum value, minimum value, mean, standard deviation, etc. These characteristics will be used to analyze the trend and pattern of state changes, and select appropriate feature extraction methods, such as: Time series analysis: Use autocorrelation function (ACF) and partial autocorrelation function (PACF) to analyze the time correlation of data, Fourier transform: used for frequency domain analysis, identify periodic characteristics, wavelet transform: suitable for extracting transient signal characteristics, identifying mutations or changes, and mining transient state characteristics for each state monitoring parameter at each time node one by one, and calculate and record relevant characteristic values.

[0040] In this embodiment, the specific steps of step S12 are: Perform abnormal state parameter detection on the operating state monitoring parameters and extract abnormal state parameters; Perform outlier elimination processing based on abnormal state parameters to obtain abnormal elimination state monitoring parameters; Define the sliding window length value; According to the sliding window length value, the abnormal elimination state monitoring parameter is divided into time series windows to obtain a state monitoring parameter sequence of multiple time windows; Identify missing values ​​of condition monitoring parameter sequences in multiple time windows and extract missing values ​​of parameters in each time window; The abnormal elimination status monitoring parameters are averaged dimension by dimension to obtain the average parameter value of each dimension; Based on the average value of the parameters in each dimension, linear interpolation is performed to fill the missing values ​​of the parameters in each time window to obtain the missing value filling state monitoring parameters.

[0041] In this embodiment, a suitable anomaly detection method is selected, for example: a statistical method: using the mean and standard deviation, determining a threshold (such as mean ± 3 × standard deviation) to identify outliers; a machine learning method: using isolation forest (IsolationForest) or support vector machine (SVM) for anomaly detection; applying the selected anomaly detection method, marking and extracting abnormal state parameters, visualizing the data to help identify anomalies; based on the detected abnormal state parameters, removing these outliers, generating abnormal removal state monitoring parameters; using programming tools (such as Python's Pandas library) for data cleaning, using dropna() or conditional filtering to remove outliers; defining the length of the sliding window according to data characteristics and analysis requirements, for example, a fixed length (such as 10 data points) or a time-based window (such as 1 minute) can be selected; and the abnormal removal state monitoring parameters are time-series windowed according to the defined sliding window length value. The data in each window forms a new sequence for subsequent analysis. The missing values ​​of the state monitoring parameter sequence in each time window can be identified by the isnull() function. The position and number of missing values ​​in each time window are recorded for subsequent processing. The state monitoring parameters of each dimension are averaged. In each time window, the mean() function is used to calculate the mean of each parameter. The mean value of each dimension is stored in a new data structure for subsequent filling of missing values. The linear interpolation method is selected to fill the missing values. Linear interpolation predicts missing values ​​through the linear relationship of known data points. The missing values ​​of each time window are filled by linear interpolation using the previously calculated parameter mean value. The interpolate() method of Pandas can be used to ensure that the interpolated data maintains the time order and format of the original sequence.

[0042] 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 time series change analysis on the transient state characteristics of each time node to generate transient state change characteristic data; Step S22: performing transient change time series fitting on the transient state change characteristic data to construct a transient change curve of the impact box; Step S23: Perform transient mutation analysis on the transient change curve of the impact box and mark the hot and cold alternating change timestamp; Step S24: performing a cold-hot alternating temperature fluctuation analysis on the transient state characteristics of each time node based on the cold-hot alternating change timestamp, thereby generating a cold state temperature fluctuation parameter and a hot state temperature fluctuation parameter.

[0043] In this embodiment, the transient state feature data is organized into a time series format to ensure that the features corresponding to each time node can be listed in order, and a suitable time series change analysis method is selected, such as: trend analysis: use moving average or exponential smoothing method to analyze data trends, change rate calculation: calculate the change rate of each time node (such as relative change percentage), analyze the transient state characteristics of each time node, record the change characteristics (such as rise, fall, fluctuation, etc.), and generate transient state change feature data, according to the characteristics of the transient state change characteristics, select a suitable fitting model, such as: linear regression: suitable for linear change trends, polynomial regression: suitable for complex change curves, smoothing spline fitting: suitable for smooth fitting of nonlinear data, use a fitting algorithm (such as the regression model in Scikit-learn, or the interpolation method in SciPy) to fit the transient state change feature data, generate a transient change curve, and evaluate the accuracy of the fitting results, such as through Use the coefficient of determination R² or root mean square error (RMSE) to judge the effect of fitting, select a suitable mutation detection algorithm, such as: CUSUM (cumulative sum control chart): used to detect changes in the mean, gradient change detection: analyze the rate of change, identify mutation points, input the transient change curve into the selected mutation detection algorithm, identify and mark transient mutation points, which usually correspond to the timestamps of the cold and hot alternation changes, extract the marked cold and hot alternation change timestamps from the previous step, and prepare for subsequent analysis. According to the cold and hot alternation change timestamps, divide the transient state feature data into cold state and hot state data sets, and select a suitable fluctuation analysis method, such as: standard deviation calculation: measure the degree of discreteness of temperature fluctuations, range analysis: calculate the maximum and minimum values ​​in each state, identify the fluctuation range, perform temperature fluctuation analysis on the cold state data set, and calculate the cold state temperature fluctuation parameters (such as mean, standard deviation, maximum and minimum values), perform temperature fluctuation analysis on the hot state data set, and calculate the hot state temperature fluctuation parameters.

[0044] 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: Calculate the peak-to-valley interval of the transient change curve of the impact box to obtain the cold-hot alternating cycle period; Step S32: Calculate the mutation frequency of the transient change curve of the impact box to obtain the frequency of hot and cold alternation within the cycle; Step S33: mining the alternating logic of the hot and cold alternating cycle based on the hot and cold alternating frequency within the cycle, thereby generating a hot and cold alternating law; Step S34: performing state alternating transition analysis on the cold state temperature fluctuation parameter and the hot state temperature fluctuation parameter, thereby generating an alternating process parameter transition feature; Step S35: dynamically evolve the transition trend of the parameter transition characteristics of the alternating process according to the cold-hot alternating transformation rule, thereby generating a cold-hot alternating state trend evolution map.

[0045] In this embodiment, a suitable peak-valley detection algorithm is used, for example: find_peaks in the SciPy library: used to detect the local maximum (peak) and local minimum (valley) of the curve, and the selected peak-valley detection algorithm is applied to mark each peak and valley in the change curve, and the hot and cold alternation cycle period is obtained by calculating the time difference between adjacent peaks. A simple difference calculation (such as time[i+1]-time[i]) can be used to record the duration of each cycle. The mutation frequency represents the frequency of occurrence of mutation events (peaks or valleys) in a specific time period. In the calculated hot and cold alternation cycle, the total number of mutations (peaks and valleys) is counted, and the mutation frequency = cycle duration / number of mutations. The mutation frequency in each cycle is recorded, and data mining technology (such as association rule learning or classification algorithm) is used to identify the alternating transformation law. The selected method is applied to analyze the frequency data to extract the hot and cold alternation. Transformation rules, for example, use the Apriori algorithm to discover frequent item sets, or use the decision tree model for classification, select appropriate analysis methods, such as: Markov model: used to analyze the transition probability between states, time series analysis: analyze the changing trend of fluctuation parameters, analyze the fluctuation parameters of cold and hot states, calculate the transition characteristics between states (such as transition probability, average duration, etc.), generate alternating process parameter transition characteristics, extract alternating process parameter characteristics from the previous steps, prepare for dynamic trend evolution, select appropriate models (such as time series prediction models, neural network models) for dynamic trend evolution analysis, calculate and predict future state changes based on the cold and hot alternation transformation rules and the extracted alternating process characteristics, and draw the cold and hot alternating state trend evolution map, which can be achieved using visualization tools (such as Matplotlib or Tableau).

[0046] In this embodiment, step S4 includes the following steps: Step S41: obtaining the operation log of the hot and cold shock chamber; Step S42: Calculate the remaining number of hot and cold alternations in the hot and cold shock box operation log to obtain the remaining number of operation alternations; Step S43: performing a cold-hot alternation impact simulation on the cold-hot alternation state trend evolution map according to the remaining number of alternating operations, and collecting parameters in multiple time periods to generate cold-hot alternation simulation data in multiple time periods; Step S44: performing time series state response identification on the hot-cold alternation simulation data of multiple time periods, and constructing hot-cold alternation response diagrams of multiple time periods.

[0047] In this embodiment, the operation log storage location of the hot and cold shock box is determined, which is usually the control system, data logger or server of the device. Use appropriate tools (such as SQL query, API interface or file reading) to extract the operation log. The log content should include key information such as timestamp, operation status, temperature, pressure, humidity, etc. Clarify the definition of hot and cold alternation, such as the change between the set cold state and hot state each time the temperature reaches. By analyzing the operation log, the number of hot and cold alternations since the device was started is counted, and the remaining number of alternations is calculated according to the design and use cycle of the device. Use a simple counting algorithm to traverse the log data and accumulate alternating events. According to the remaining number of operation alternations, set the simulation time period and specific parameters of each time period (such as temperature range, time interval, impact frequency). Select a suitable simulation method, such as: Numerical simulation: Use computational fluid dynamics (CFD) software to simulate heat conduction and fluid flow. Discrete event simulation: simulate the process of each alternating event. Perform hot and cold alternating shock simulation according to the set parameters and record the state change data in each time period. Professional simulation software (such as ANSYS, MATLABSimulink) can be used to achieve this. During the simulation process, key parameters (such as temperature, pressure, and humidity) are collected regularly to generate hot and cold alternating simulation data for multiple time periods. The hot and cold alternating simulation data for each time period are organized into a structured time series format to ensure that the data for each time period is clear and available. Select a suitable time series state response identification method, such as: Time series analysis: Use the autoregressive moving average (ARMA) model for analysis. Machine learning method: Use classification algorithms (such as decision trees and random forests) for state identification. Perform state response identification on the simulation data for multiple time periods and extract the hot and cold alternating response characteristics for each time period. Plot the identified response characteristics into a graph to generate hot and cold alternating response graphs for multiple time periods. This can be drawn using visualization tools (such as Matplotlib and Tableau).

[0048] In this embodiment, step S5 includes the following steps: Step S51: mining the temperature state of each time period on the hot-cold alternating response diagrams of multiple time periods, and extracting the temperature state characteristics of each time period; Step S52: Calculate the temperature rise amplitude for the temperature state characteristics of each time period to generate the temperature rise amplitude for each time period; Step S53: analyzing the abnormal temperature change of the temperature rise amplitude in each time period to obtain abnormal temperature change data; Step S54: locate the abnormal state based on the abnormal temperature change data and mark the abnormal time period.

[0049] In this embodiment, temperature state characteristics are defined, including but not limited to: maximum temperature: the maximum temperature value in each time period, minimum temperature: the minimum temperature value in each time period, average temperature: the temperature mean in the time period, temperature volatility: the standard deviation of the temperature, the above characteristics are calculated for the temperature data of each time period, and the temperature state characteristics of each time period are extracted. This can be achieved through programming tools (such as Python's Pandas library). The temperature rise amplitude refers to the temperature change amount in the time period, which can be defined as: temperature rise amplitude = maximum temperature - minimum temperature, or it can also be calculated based on the average temperature change in the time period. The temperature rise amplitude calculation is performed on the temperature state characteristics of each time period to obtain the temperature rise amplitude data of each time period, and the standard of abnormal temperature change is determined, for example, using statistical methods. Methods (such as Z-score) are used to identify values ​​that are significantly different from the average temperature rise. A common strategy is to set a threshold, for example: abnormal threshold = average temperature rise + k × standard deviation, where k is usually 2 or 3. The temperature rise in each time period is analyzed, the temperature rise that exceeds the abnormal threshold is marked, the abnormal temperature change data is recorded, and the conditional filtering function in Pandas is used to extract the abnormal values. According to the analysis results, the time period corresponding to the identified abnormal temperature change is marked. An identification column can be added to the data set to record whether each time period is abnormal. The marked abnormal time period is recorded in the report, describing the specific circumstances and possible causes of the abnormality. The report should include: the time period when the abnormality occurred, the abnormal temperature rise, the possible cause of the failure or the recommended follow-up measures.

[0050] In this embodiment, step S6 includes the following steps: Step S61: performing abnormal attribution inference on the abnormal time period to obtain abnormal state factors; Step S62: predicting the probability of abnormal failure for the abnormal state factors to obtain the predicted probability of alternating hot and cold failures; Step S63: performing a fault risk analysis based on the cold-hot alternating fault prediction probability, thereby generating alternating fault risk data; Step S64: making abnormal fault diagnosis decisions on the alternating fault risk data and constructing a shock box fault decision strategy; Step S65: Based on the impact box fault decision strategy, intelligent monitoring and protection are performed on the cold and hot impact box to perform real-time status monitoring operations of the cold and hot impact box.

[0051] In this embodiment, a suitable attribution analysis method is adopted, such as: root cause analysis (RCA): identifying the root cause of the abnormality, causal relationship model: using data-driven methods (such as Bayesian networks) to establish causal relationships, using selected analysis methods, analyzing abnormal data, identifying abnormal state factors, which may include equipment failure, external environment changes or improper operation, etc., documenting the identified abnormal state factors, forming an attribution analysis report, and selecting a suitable probability prediction model according to data characteristics and needs, such as: logistic regression: suitable for binary classification problems, random forest: suitable for complex nonlinear relationships, support vector machine (SVM): suitable for classification of high-dimensional data, using the abnormal state factors obtained by attribution analysis, constructing a training data set, including input features and target variables (fault or not labels), using the selected model to train the data, adjusting model parameters to optimize the prediction effect, applying the trained model to the new data set, predicting the failure probability of each state, generating the hot and cold alternating failure prediction probability, and selecting a suitable risk assessment model, such as: fault tree analysis (FT A): Used for system failure analysis, Markov model: analyze the probability of state transition, calculate the risk value of each failure based on the predicted failure probability, generate alternating failure risk data, record the risk assessment results in the database, including the risk level of each failure, possible impact and recommended countermeasures, select appropriate decision support models, such as: decision tree: used to visualize the decision process, fuzzy logic control: deal with uncertainty and ambiguity, formulate fault diagnosis decision strategies based on alternating failure risk data, identify high-risk failures and propose corresponding preventive measures, design the architecture of the intelligent monitoring system, including data acquisition, processing and analysis modules, deploy sensors and data acquisition equipment, monitor the operating status of the hot and cold shock box in real time, collect key parameters (such as temperature, pressure, humidity, etc.), analyze real-time data through the data processing module, and identify abnormal conditions and potential failures in time. According to the fault decision strategy, automatically execute monitoring and protection measures, such as: alarm system: issue an alarm in time when an abnormality is detected, automatic adjustment: when conditions permit, automatically adjust the operating parameters of the equipment to reduce the risk of failure.

[0052] In this embodiment, an intelligent monitoring system for a cold and hot shock box is provided, which is used to execute the intelligent monitoring method for a cold and hot shock box as described above, including: The transient feature mining module monitors the real-time operation status of the hot and cold shock chamber, and mines the transient state features at each time point to generate the transient state features of each time node; The transient mutation module performs transient mutation analysis on the transient state characteristics of each time node, and performs cold and hot alternating temperature fluctuation analysis, thereby generating cold state temperature fluctuation parameters and hot state temperature fluctuation parameters; The dynamic transition trend module performs state alternation transition analysis on the temperature fluctuation parameters of the cold state and the temperature fluctuation parameters of the hot state, and performs dynamic transition trend evolution, thereby generating a cold-hot alternation state trend evolution map; The hot-cold alternation simulation module obtains the hot-cold alternation shock box operation log; performs hot-cold alternation shock simulation on the hot-cold alternation state trend evolution map according to the hot-cold alternation shock box operation log, and performs time series state response recognition to construct hot-cold alternation response maps for multiple time periods; The abnormal state positioning module calculates the temperature rise amplitude of the hot and cold alternating response diagrams in multiple time periods, locates the abnormal state, and marks the abnormal time period; The fault diagnosis module predicts the probability of abnormal faults in abnormal time periods, makes abnormal fault diagnosis decisions, and builds a shock box fault decision strategy to perform real-time status monitoring operations for hot and cold shock boxes.

[0053] The present invention helps to immediately discover potential problems by real-time monitoring of the status of the hot and cold shock box, improves the response speed and equipment stability, and mining transient state characteristics at each time point can help understand the changes in the equipment operation status and provide data support for subsequent analysis. Transient mutation analysis can capture the mutation of temperature fluctuations, which helps to timely discover abnormal fluctuations and conduct further research. The hot and cold alternating temperature fluctuation analysis can reveal the temperature fluctuation characteristics under different states and provide a reference for state transition. The state alternation transition analysis helps to understand the temperature change trend between different states and provide an in-depth understanding of the state transition mechanism. Generating a hot and cold alternating state trend evolution map can help monitor the state evolution in real time and provide support for prediction and The simulation of alternating hot and cold shocks based on the operation log can help simulate the real working environment and evaluate the performance of the equipment under different working conditions. The recognition of time-series state response can help identify abnormal conditions and provide support for fault diagnosis and prevention. The calculation of temperature rise and the positioning of abnormal conditions can help accurately locate abnormal conditions and improve the accuracy of fault location. Marking abnormal time periods can help monitor the occurrence of abnormal conditions and provide clues for further processing. The prediction of abnormal fault probability and diagnosis decision-making can help to deal with abnormal conditions in a timely and accurate manner and reduce the impact of equipment failure on production. The construction of an impact box fault decision-making strategy can improve equipment maintenance efficiency and production stability and ensure the safe operation of equipment.

[0054] 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 therefore intended that all changes falling within the meaning and range of equivalent elements of the application documents are included in the present invention.

[0055] 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 intelligent monitoring method for a hot and cold shock chamber, characterized in that: The following steps are involved: Step S1: monitor the operation status of the hot and cold shock box in real time, and mine the transient state characteristics at each time point to generate the transient state characteristics of each time node; Step S2: performing transient mutation analysis on the transient state characteristics of each time node, and performing cold and hot alternating temperature fluctuation analysis, thereby generating cold state temperature fluctuation parameters and hot state temperature fluctuation parameters; Step S3: performing state alternation transition analysis on the cold state temperature fluctuation parameters and the hot state temperature fluctuation parameters, and performing dynamic transition trend evolution, thereby generating a cold-hot alternation state trend evolution map; Step S4: obtaining the operation log of the hot and cold shock box; performing hot and cold alternating shock simulation on the hot and cold alternating state trend evolution map according to the hot and cold shock box operation log, and performing time series state response recognition to construct hot and cold alternating response maps for multiple time periods; Step S5: Calculate the temperature rise amplitude of the hot and cold alternating response diagrams of multiple time periods, locate the abnormal state, and mark the abnormal time period; Step S6: predict the probability of abnormal failures in the abnormal time period, make abnormal fault diagnosis decisions, and build a shock box failure decision strategy to perform real-time status monitoring of the hot and cold shock boxes.

2. The intelligent monitoring method for a cold and hot shock chamber according to claim 1, characterized in that: The specific steps of step S1 are: Step S11: monitor the operation status of the hot and cold shock chamber in real time and collect operation status monitoring parameters; Step S12: performing abnormal missing value filling processing on the operating status monitoring parameters to obtain missing value filled status monitoring parameters; Step S13: performing multi-time point parameter sampling on the missing value filling state monitoring parameters to obtain state monitoring parameters at multiple time nodes; Step S14: mining transient state features of the state monitoring parameters of multiple time nodes one by one, and generating transient state features of each time node.

3. The intelligent monitoring method for a cold and hot shock chamber according to claim 2, characterized in that: The specific steps of step S12 are: Perform abnormal state parameter detection on the operating state monitoring parameters and extract abnormal state parameters; Perform outlier elimination processing based on abnormal state parameters to obtain abnormal elimination state monitoring parameters; Define the sliding window length value; According to the sliding window length value, the abnormal elimination state monitoring parameter is divided into time series windows to obtain a state monitoring parameter sequence of multiple time windows; Identify missing values ​​of condition monitoring parameter sequences in multiple time windows and extract missing values ​​of parameters in each time window; The abnormal elimination status monitoring parameters are averaged dimension by dimension to obtain the average parameter value of each dimension; Based on the average value of the parameters in each dimension, linear interpolation is performed to fill the missing values ​​of the parameters in each time window to obtain the missing value filling state monitoring parameters.

4. The intelligent monitoring method for a cold and hot shock chamber according to claim 1, characterized in that: The specific steps of step S2 are: Step S21: performing time series change analysis on the transient state characteristics of each time node to generate transient state change characteristic data; Step S22: performing transient change time series fitting on the transient state change characteristic data to construct a transient change curve of the impact box; Step S23: Perform transient mutation analysis on the transient change curve of the impact box and mark the hot and cold alternating change timestamp; Step S24: performing a cold-hot alternating temperature fluctuation analysis on the transient state characteristics of each time node based on the cold-hot alternating change timestamp, thereby generating a cold state temperature fluctuation parameter and a hot state temperature fluctuation parameter.

5. The intelligent monitoring method for a cold and hot shock chamber according to claim 1, characterized in that: The specific steps of step S3 are: Step S31: Calculate the peak-to-valley interval of the transient change curve of the impact box to obtain the cold-hot alternating cycle period; Step S32: Calculate the mutation frequency of the transient change curve of the impact box to obtain the frequency of hot and cold alternation within the cycle; Step S33: mining the alternating logic of the hot and cold alternating cycle based on the hot and cold alternating frequency within the cycle, thereby generating a hot and cold alternating law; Step S34: performing state alternating transition analysis on the cold state temperature fluctuation parameter and the hot state temperature fluctuation parameter, thereby generating an alternating process parameter transition feature; Step S35: dynamically evolve the transition trend of the parameter transition characteristics of the alternating process according to the cold-hot alternating transformation rule, thereby generating a cold-hot alternating state trend evolution map.

6. The intelligent monitoring method for a cold and hot shock chamber according to claim 1, characterized in that: The specific steps of step S4 are: Step S41: obtaining the operation log of the hot and cold shock chamber; Step S42: Calculate the remaining number of hot and cold alternations in the hot and cold shock box operation log to obtain the remaining number of operation alternations; Step S43: performing a cold-hot alternation impact simulation on the cold-hot alternation state trend evolution map according to the remaining number of alternating operations, and collecting parameters in multiple time periods to generate cold-hot alternation simulation data in multiple time periods; Step S44: performing time series state response identification on the hot-cold alternation simulation data of multiple time periods, and constructing hot-cold alternation response diagrams of multiple time periods.

7. The method according to claim 1, characterized in that The specific steps of step S5 are: Step S51: mining the temperature state of each time period on the hot-cold alternating response diagrams of multiple time periods, and extracting the temperature state characteristics of each time period; Step S52: Calculate the temperature rise amplitude for the temperature state characteristics of each time period to generate the temperature rise amplitude for each time period; Step S53: analyzing the abnormal temperature change of the temperature rise amplitude in each time period to obtain abnormal temperature change data; Step S54: locate the abnormal state based on the abnormal temperature change data and mark the abnormal time period.

8. The intelligent monitoring method for a cold and hot shock chamber according to claim 1, characterized in that: The specific steps of step S6 are: Step S61: performing abnormal attribution inference on the abnormal time period to obtain abnormal state factors; Step S62: predicting the probability of abnormal failure for the abnormal state factors to obtain the predicted probability of alternating hot and cold failures; Step S63: performing a fault risk analysis based on the cold-hot alternating fault prediction probability, thereby generating alternating fault risk data; Step S64: making abnormal fault diagnosis decisions on the alternating fault risk data and constructing a shock box fault decision strategy; Step S65: Based on the impact box fault decision strategy, intelligent monitoring and protection are performed on the cold and hot impact box to perform real-time status monitoring operations of the cold and hot impact box.

9. An intelligent monitoring system for a hot and cold shock chamber, characterized in that: The intelligent monitoring method for executing the thermal shock chamber according to claim 1 comprises: The transient feature mining module monitors the real-time operation status of the hot and cold shock chamber, and mines the transient state features at each time point to generate the transient state features of each time node; The transient mutation module performs transient mutation analysis on the transient state characteristics of each time node, and performs cold and hot alternating temperature fluctuation analysis, thereby generating cold state temperature fluctuation parameters and hot state temperature fluctuation parameters; The dynamic transition trend module performs state alternation transition analysis on the temperature fluctuation parameters of the cold state and the temperature fluctuation parameters of the hot state, and performs dynamic transition trend evolution, thereby generating a cold-hot alternation state trend evolution map; The hot-cold alternation simulation module obtains the hot-cold alternation shock box operation log; performs hot-cold alternation shock simulation on the hot-cold alternation state trend evolution map according to the hot-cold alternation shock box operation log, and performs time series state response recognition to construct hot-cold alternation response maps for multiple time periods; The abnormal state positioning module calculates the temperature rise amplitude of the hot and cold alternating response diagrams in multiple time periods, locates the abnormal state, and marks the abnormal time period; The fault diagnosis module predicts the probability of abnormal faults in abnormal time periods, makes abnormal fault diagnosis decisions, and builds a shock box fault decision strategy to perform real-time status monitoring operations for hot and cold shock boxes.

Images