Temperature control monitoring system for the production process of fascia balls

Abstract

The present invention relates to the field of temperature monitoring technology, specifically to a temperature control monitoring system for the production process of a fascia ball, the system comprising a real-time temperature monitoring module, a temperature anomaly analysis module, a temperature control strategy module, a production scheduling optimization module, a temperature prediction model module, an equipment status diagnosis module, a parameter adjustment module, and a product quality inspection module. The present invention, by introducing a long short-term memory network and a simulated annealing algorithm, realizes intelligent dynamic adjustment of the temperature control strategy, allowing the system to intelligently judge the severity of the abnormal state according to the real-time data of temperature changes, and adjust the temperature control strategy accordingly. For high-frequency fluctuations, the system can quickly adopt short-term high-power regulation, and for low-frequency fluctuations, implement long-term low-power regulation. Through such a dynamic adjustment strategy, the accuracy of temperature control and the efficiency of energy use are significantly improved, ensuring product quality and production efficiency.

Description

Technical Field

[0001] The present invention relates to the technical field of temperature monitoring, and in particular to a temperature control monitoring system for a fascia ball production process. Background Art

[0002] The field of temperature monitoring technology focuses on real-time monitoring and regulation of temperature in an environment or device to ensure the quality and performance of a process or product. This technology is widely used in various industrial manufacturing processes, food processing, pharmaceutical production and other fields, where precise control of temperature directly affects the safety, effectiveness and consistency of the product. It usually involves the use of sensors to collect temperature data, and then adjusting the heating or cooling equipment through a control system to maintain the desired temperature conditions.

[0003] Among them, the fascia ball production process temperature control monitoring system is a system specially designed to monitor and adjust the temperature during the fascia ball manufacturing process. Its main purpose is to ensure that the temperature during the production process is controlled within the optimal range, thereby achieving the effect of improving the quality of the fascia ball, ensuring production efficiency and reducing the defective rate. By maintaining a constant temperature during the production process, it helps to ensure that the physical and chemical properties of the fascia ball meet the predetermined standards, thereby meeting consumers' expectations for product performance.

[0004] Traditional systems are deficient in dynamically responding to actual production conditions. Fixed control parameters lack the ability to respond to immediate changes in temperature fluctuations during the production process, resulting in inaccurate temperature control. When faced with fluctuations in equipment performance or changes in external conditions, traditional systems require manual parameter adjustments, which increases the complexity of operations and affects the stability of the production process and product quality due to untimely or inaccurate adjustments. Summary of the invention

[0005] The purpose of the present invention is to solve the shortcomings existing in the prior art and to propose a temperature control monitoring system for the fascia ball production process.

[0006] In order to achieve the above-mentioned purpose, the present invention adopts the following technical scheme: a temperature control monitoring system for the production process of fascia balls, the system comprising a temperature real-time monitoring module, a temperature anomaly analysis module, a temperature control strategy module, a production scheduling optimization module, a temperature prediction model module, an equipment status diagnosis module, a parameter adjustment module, and a product quality inspection module;

[0007] The real-time temperature monitoring module records the temperature of the working area and the equipment surface every minute based on the data collected by the temperature sensor, analyzes the temperature change trend over time, and obtains the temperature monitoring record;

[0008] The temperature anomaly analysis module calculates the temperature change rate at consecutive time points based on the temperature monitoring records, identifies the key time period with abnormal change rate, and marks the time period as temperature anomaly to obtain abnormal temperature marking information;

[0009] The temperature control strategy module uses a long short-term memory network based on abnormal temperature tag information to analyze temperature fluctuations during an abnormal time period, adjust temperature control parameter settings, including adjusting cooling or heating power, and generate a temperature control strategy;

[0010] The production scheduling optimization module re-evaluates the time arrangement and resource allocation of multiple links in the production process based on the temperature control strategy, adjusts the operation sequence and equipment load of the production line, matches the temperature control requirements, optimizes production efficiency, and obtains a scheduling optimization plan;

[0011] The temperature prediction model module is based on the scheduling optimization plan and combines historical temperature data to evaluate the potential temperature changes in future production links, predict the temperature trends of key production links, provide a basis for temperature control, and establish future temperature prediction data;

[0012] The equipment status diagnosis module checks whether the operating status of the production equipment causes the predicted temperature anomaly based on the future temperature prediction data, analyzes the equipment performance data, identifies the equipment that needs maintenance or adjustment, and generates an equipment maintenance list;

[0013] The parameter adjustment module uses a deep Q network based on the equipment maintenance list to automatically adjust the operating parameters of the associated equipment, including the temperature control threshold and response time, based on the identified equipment problems, to ensure that the equipment is operating in the optimal state and obtain parameter adjustment records;

[0014] The product quality inspection module performs quality inspection on the fascia balls after production based on the parameter adjustment records, including size, elasticity and durability index tests, and evaluates the effectiveness of production process control to generate a quality certificate.

[0015] The present invention has improvements in that the temperature monitoring record includes an ambient temperature sequence, an equipment surface temperature sequence and a timestamp thereof, the abnormal temperature marking information includes an identified high temperature point time period, a low temperature point time period, and a corresponding temperature change rate value, the temperature control strategy includes a cooling power adjustment instruction, a heating power adjustment instruction, and a temperature setting value adjustment instruction, the scheduling optimization plan includes production line operation sequence adjustment, equipment load reallocation, and temperature control demand matching measures, the future temperature prediction data includes predicted temperature values ​​of key production links, predicted time periods, and potential temperature fluctuation ranges, the equipment maintenance list includes the identification of equipment to be maintained, the estimated maintenance time, and a summary of maintenance measures, the parameter adjustment record includes an equipment temperature control threshold adjustment record, a response time adjustment record, and operating parameter update information, and the quality certificate includes a fascia ball size certificate, elasticity test results, and durability test data.

[0016] The present invention is improved in that the temperature real-time monitoring module includes a data collection submodule, a data recording submodule, and a trend analysis submodule;

[0017] The data collection submodule monitors the temperature of the working area and the equipment surface based on the data collected by the temperature sensor, and covers multiple key monitoring points to obtain a temperature monitoring data set;

[0018] The data recording submodule timestamps the temperature monitoring data set, records it once every minute, including the ambient and device surface temperatures, and verifies the timing of the data to generate a time series temperature record;

[0019] The trend analysis submodule analyzes the data in the time series temperature records, identifies the trend of temperature rising or falling over time, determines the pattern of temperature change by comparing consecutive record points, and obtains temperature monitoring records.

[0020] The present invention is improved in that the temperature anomaly analysis module includes a change rate calculation submodule, an anomaly identification submodule, and a mark generation submodule;

[0021] The change rate calculation submodule calculates the temperature change rate between time points based on the temperature monitoring record, identifies the key time points of temperature change by setting a threshold comparison, and generates temperature change rate data;

[0022] The abnormality identification submodule screens the change rate that exceeds the normal operating range according to the temperature change rate data, identifies the time point as abnormal, and identifies the abnormal time period in combination with the continuity of the time point to obtain the time period identification result;

[0023] The tag generation submodule assigns a corresponding identifier to each abnormal time period based on the time period identification result, performs tracking analysis and processing, so that the abnormal time can be recorded and tracked, and abnormal temperature tag information is obtained.

[0024] The present invention is improved in that the temperature control strategy module includes a fluctuation analysis submodule, a strategy adjustment submodule, and a strategy generation submodule;

[0025] The fluctuation analysis submodule uses a long short-term memory network based on abnormal temperature marking information to count the number of temperature changes in each abnormal time period, calculate the temperature change frequency, and determine the severity of the abnormality. If the frequency exceeds a preset range, it is marked as a high-frequency fluctuation, otherwise it is a low-frequency fluctuation, and a fluctuation frequency analysis record is generated;

[0026] The strategy adjustment submodule uses a simulated annealing algorithm based on the fluctuation frequency analysis record to formulate a matching temperature adjustment strategy for high-frequency fluctuations, including short-term high-power adjustment, and a mild adjustment strategy for low-frequency fluctuations, including long-term low-power adjustment, to generate a preliminary temperature adjustment plan;

[0027] The simulated annealing algorithm is based on the formula:

[0028]

[0029] Calculate new temperature value and generate preliminary temperature adjustment plan;

[0030] in, For the new temperature, is the initialization temperature, is the cooling rate, is the number of iterations, is the weight coefficient, is the normalized value of the fluctuation frequency;

[0031] The strategy generation submodule generates a temperature control strategy based on the preliminary temperature control plan, optimizing the parameters in the control plan according to the current working status of the production line and the energy consumption limit of the equipment, including adjusting the power setting and the action time.

[0032] The present invention is improved in that the production scheduling optimization module includes a job analysis submodule, a job rearrangement submodule, and a resource reconfiguration submodule;

[0033] The operation analysis submodule evaluates the time arrangement and resource allocation of the current production process based on the temperature control strategy, determines the key links that affect production efficiency based on the temperature control requirements and production line conditions, and generates an operation process analysis record;

[0034] The job rescheduling submodule identifies potential job sequences that can be optimized based on job flow analysis records, and reduces waiting time and interruptions caused by temperature control by adjusting the execution order of production tasks to form an optimized production sequence;

[0035] The resource reconfiguration submodule reallocates production resources, including equipment load and personnel arrangement, based on the optimized production sequence, adjusts the equipment load distribution to match the operation sequence, optimizes production efficiency, and obtains a scheduling optimization plan.

[0036] The present invention is improved in that the temperature prediction model module includes a data fusion submodule, a trend identification submodule, and a prediction integration submodule;

[0037] The data fusion submodule collects production scheduling data and historical temperature records based on the scheduling optimization scheme, including the scheduled production time and temperature data of multiple links, and analyzes the correlation between temperature changes and production activities to construct a fusion data set;

[0038] The trend identification submodule identifies the regularity and periodicity of temperature changes based on the fused data set, predicts the temperature change trend under different production conditions for key production links, and generates temperature trend prediction records;

[0039] The prediction integration submodule evaluates the potential impact of predicted temperature changes on production scheduling based on temperature trend prediction records, adjusts strategies and matches predicted temperature conditions, and establishes future temperature prediction data.

[0040] The present invention is improved in that the equipment status diagnosis module includes a temperature impact analysis submodule, a performance data evaluation submodule, and a maintenance demand identification submodule;

[0041] The temperature impact analysis submodule analyzes the performance fluctuation or failure risk of production equipment under the predicted temperature conditions based on the future temperature prediction data, identifies equipment that is sensitive to temperature changes, and generates equipment sensitivity analysis data;

[0042] The performance data evaluation submodule collects the operation data of the device identified in the device sensitive analysis data, including power consumption, operation time and fault history, and evaluates the current performance status and maintenance record of the device to obtain the device performance evaluation result;

[0043] The maintenance requirement identification submodule compares the equipment maintenance measures and the equipment operating conditions based on the equipment performance evaluation results, and formulates a maintenance plan and schedule according to the potential impact of the predicted temperature change on the equipment, and generates an equipment maintenance list.

[0044] The present invention is improved in that the parameter adjustment module includes a problem device identification submodule, a parameter analysis submodule, and an automatic adjustment execution submodule;

[0045] The problem equipment identification submodule uses the isolation forest algorithm based on the equipment maintenance list to screen the equipment that needs maintenance or adjustment due to temperature fluctuation or performance degradation, and combines the equipment temperature sensitivity and historical maintenance records to determine the equipment that cannot maintain optimal performance and generate a list of problem equipment;

[0046] The parameter analysis submodule analyzes the operating parameters of the equipment, including the temperature control threshold and the response time, according to the list of problematic equipment, and compares them with the parameters of the equipment's optimal operating state to obtain parameter adjustment requirements;

[0047] The automatic adjustment execution submodule uses a deep Q network to automatically adjust the operating parameters of the associated equipment according to the parameter adjustment requirements, including adjusting the temperature control threshold and optimizing the response time, and obtaining a parameter adjustment record;

[0048] The deep Q network, according to the formula:

[0049]

[0050] Calculate the Q value of each operation and obtain the parameter adjustment record;

[0051] in, Indicates in status Next Action The Q value, is the symbol of the learning rate, represents the adaptive learning adjustment factor, represents the immediate reward received from the environment, is the sign of the reward decay rate, represents the environmental stability index, Indicates that in the next state Next, for action The Q value takes the maximum value, is the sign of the rate at which the operating parameter is adjusted, Represents the device response sensitivity.

[0052] The present invention is improved in that the product quality inspection module includes a size test submodule, an elasticity test submodule, and a durability test submodule;

[0053] The size test submodule measures the size of the produced fascia ball based on the parameter adjustment record, verifies the diameter and roundness of the fascia ball, compares the measurement result with the standard size, verifies whether the fascia ball size meets the tolerance range, and generates a size qualification record;

[0054] The elasticity test submodule performs elastic compression and recovery tests on the fascia balls that meet the size requirements based on the size qualification records, records the force required for compression and the recovery time, and compares the preset elasticity standards to obtain elasticity test data;

[0055] The durability test submodule performs durability testing based on the elasticity test data, including continuous compression recovery times and service life testing under target load, verifies whether the durability meets the use standards, and generates a quality certificate.

[0056] Compared with the prior art, the advantages and positive effects of the present invention are:

[0057] In the present invention, by introducing long short-term memory network and simulated annealing algorithm, intelligent dynamic adjustment of temperature control strategy is realized. The system is allowed to intelligently judge the severity of abnormal state according to the real-time data of temperature change, and adjust the temperature control strategy accordingly. For high-frequency fluctuations, the system can quickly adopt short-term high-power regulation, and for low-frequency fluctuations, long-term low-power regulation is implemented. Through such a dynamic adjustment strategy, the accuracy of temperature control and the efficiency of energy use are significantly improved, ensuring product quality and production efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0058] Figure 1 The module diagram of the temperature control monitoring system of the fascia ball production process proposed by the present invention;

[0059] Figure 2 The system framework diagram of the temperature control monitoring system for the fascia ball production process proposed by the present invention;

[0060] Figure 3 The present invention proposes a flow chart of a real-time temperature monitoring module in a temperature control monitoring system during the production process of a fascia ball;

[0061] Figure 4 The present invention proposes a flow chart of a temperature anomaly analysis module in a temperature control monitoring system during the production process of a fascia ball;

[0062] Figure 5 The present invention proposes a flow chart of the temperature control strategy module in the temperature control monitoring system of the fascia ball production process;

[0063] Figure 6 The present invention proposes a production scheduling optimization module flow chart in the temperature control monitoring system of the fascia ball production process;

[0064] Figure 7 The present invention proposes a flow chart of a temperature prediction model module in a temperature control monitoring system during the production process of a fascia ball;

[0065] Figure 8 The present invention proposes a flow chart of the equipment status diagnosis module in the temperature control monitoring system of the fascia ball production process;

[0066] Fig. 9 The present invention proposes a parameter adjustment module flow chart in the temperature control monitoring system of the fascia ball production process;

[0067] Fig.10 The present invention proposes a flow chart of a product quality inspection module in a temperature control monitoring system during the production process of a fascia ball. DETAILED DESCRIPTION

[0068] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0069] In the description of the present invention, it should be understood that the terms "length", "width", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside", etc., indicating positions or positional relationships, are based on the positions or positional relationships shown in the accompanying drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as limiting the present invention. In addition, in the description of the present invention, the meaning of "multiple" is two or more, unless otherwise clearly and specifically defined. Example

[0070] See also Figure 1 , the present invention provides a technical solution: the temperature control monitoring system of the fascia ball production process includes a temperature real-time monitoring module, a temperature anomaly analysis module, a temperature control strategy module, a production scheduling optimization module, a temperature prediction model module, an equipment status diagnosis module, a parameter adjustment module, and a product quality inspection module;

[0071] The real-time temperature monitoring module records the temperature of the working area and the equipment surface every minute based on the data collected by the temperature sensor, analyzes the temperature change trend over time, and obtains the temperature monitoring record;

[0072] The temperature anomaly analysis module is based on temperature monitoring records. It calculates the temperature change rate at consecutive time points, identifies the key time period with abnormal change rate, and marks the time period as temperature anomaly to obtain abnormal temperature marking information;

[0073] The temperature control strategy module uses a long short-term memory network based on abnormal temperature tag information to analyze temperature fluctuations during abnormal time periods, adjust temperature control parameter settings, including adjusting cooling or heating power, and generate temperature control strategies;

[0074] The production scheduling optimization module re-evaluates the time arrangement and resource allocation of multiple links in the production process based on the temperature control strategy, adjusts the operation sequence and equipment load of the production line, matches the temperature control requirements, optimizes production efficiency, and obtains scheduling optimization solutions;

[0075] The temperature prediction model module is based on the scheduling optimization plan and combines historical temperature data to evaluate the potential temperature changes in future production links, predict the temperature trends in key production links, provide a basis for temperature control, and establish future temperature prediction data;

[0076] The equipment status diagnosis module checks whether the operating status of production equipment causes the predicted temperature anomaly based on future temperature prediction data, analyzes equipment performance data, identifies equipment that needs maintenance or adjustment, and generates an equipment maintenance list;

[0077] The parameter adjustment module uses a deep Q network based on the equipment maintenance list to automatically adjust the operating parameters of the associated equipment, including temperature control thresholds and response times, based on the identified equipment problems, to ensure that the equipment is operating in the optimal state and obtain parameter adjustment records;

[0078] The product quality inspection module conducts quality inspection on the fascia balls after production based on the parameter adjustment records, including size, elasticity and durability index tests, and evaluates the effectiveness of production process control to generate a quality certificate.

[0079] Temperature monitoring records include ambient temperature sequences, equipment surface temperature sequences and their timestamps. Abnormal temperature marking information includes identified high temperature time periods, low temperature time periods, and corresponding temperature change rate values. Temperature control strategies include cooling power adjustment instructions, heating power adjustment instructions, and temperature set point adjustment instructions. Scheduling optimization plans include production line operation sequence adjustment, equipment load redistribution, and temperature control demand matching measures. Future temperature forecast data include forecasted temperature values, forecasted time periods, and potential temperature fluctuation ranges for key production links. The equipment maintenance list includes the identification of equipment to be maintained, estimated maintenance time, and a summary of maintenance measures. Parameter adjustment records include equipment temperature control threshold adjustment records, response time adjustment records, and operating parameter update information. Quality certification includes fascia ball size certification, elasticity test results, and durability test data.

[0080] See also Figure 2 and Figure 3 ,The temperature real-time monitoring module includes a data collection submodule, a data recording submodule, and a trend analysis submodule;

[0081] The data collection submodule monitors the temperature of the working area and equipment surface based on the data collected by the temperature sensor, and covers multiple key monitoring points to obtain the temperature monitoring data set;

[0082] The data logging submodule timestamps the temperature monitoring data set, records it once every minute, including the ambient and device surface temperatures, and verifies the timing of the data to generate a time series temperature record;

[0083] The trend analysis submodule analyzes the data in the time series temperature records, identifies the trend of temperature rising or falling over time, and determines the pattern of temperature change by comparing consecutive record points to obtain temperature monitoring records.

[0084] In the data collection submodule, based on the data collected by the temperature sensor, digital signal processing technology is used to collect the temperature of the working area and the surface of the equipment using high-precision temperature sensors, covering multiple key monitoring points. The analog signal is converted into a digital signal through an analog-to-digital converter (ADC), the sampling frequency is set to 1kHz, and a filtering algorithm is used, specifically a Butterworth low-pass filter, with the cutoff frequency set to 100Hz, to reduce high-frequency noise and generate a temperature monitoring data set.

[0085] In the data recording submodule, the temperature monitoring data set is timestamped and recorded once every minute, including the ambient and device surface temperatures. Time series database technology, specifically InfluxDB, is used. The data retention policy is set to 30 days, and the HTTP protocol is used for data transmission. The data block size is set to 512 bytes to reduce network latency, verify the timing of the data, and generate time series temperature records.

[0086] In the trend analysis submodule, the data in the time series temperature records are analyzed. The statistical analysis method is adopted, specifically the moving average algorithm. The time window is set to 5 minutes, and the average temperature in the window is calculated. The pattern of temperature change is determined by comparing consecutive recording points. The slope detection algorithm is used and the threshold is set to 0.5°C / min to identify rapid temperature change events and generate temperature monitoring records.

[0087] See also Figure 2 and Figure 4 ,The temperature anomaly analysis module includes a change rate calculation submodule, anomaly identification submodule, and mark generation submodule;

[0088] The change rate calculation submodule calculates the temperature change rate between time points based on the temperature monitoring records, identifies the key time points of temperature change by setting threshold comparison, and generates temperature change rate data;

[0089] The abnormal identification submodule screens the change rate that exceeds the normal operating range based on the temperature change rate data, identifies the time point as abnormal, and identifies the abnormal time period in combination with the continuity of the time point to obtain the time period identification result;

[0090] The tag generation submodule assigns a corresponding tag to each abnormal time period based on the time period recognition result, performs tracking analysis and processing, so that the abnormal time can be recorded and tracked, and the abnormal temperature tag information is obtained.

[0091] In the change rate calculation submodule, based on the temperature monitoring records, a differential algorithm is used to calculate the temperature change rate between time points. The temperature values ​​at two consecutive time points are subtracted and divided by the time interval to obtain the temperature change rate per minute. The threshold is set to 0.1°C / minute. By comparing the actual calculated change rate with the threshold, the key time points of temperature change are identified and the temperature change rate data is generated.

[0092] In the abnormality identification submodule, based on the temperature change rate data, the threshold method is used to screen the change rate that exceeds the normal operating range. The normal operating range is set as a temperature change rate not exceeding 0.2°C / minute, and the time points outside this range are marked as abnormal. Furthermore, continuity analysis is used to identify the time periods of continuous abnormalities. If three or more consecutive time points are marked as abnormal, it is determined to be an abnormal time period, and the time period identification result is obtained.

[0093] In the tag generation submodule, a unique identifier is assigned to each abnormal time period based on the time period identification result, and a unique identifier is generated using a UUID generation algorithm to ensure that each abnormal time period can be uniquely tracked. Preparations for tracking, analyzing and processing the abnormal time period are performed, and abnormal temperature tag information is generated so that the abnormal time can be recorded and tracked.

[0094] See also Figure 2 and Figure 5 ,The temperature control strategy module includes a fluctuation analysis submodule, a strategy adjustment submodule, and a strategy generation submodule;

[0095] The fluctuation analysis submodule uses a long short-term memory network based on abnormal temperature marking information to count the number of temperature changes in each abnormal time period, calculate the temperature change frequency, and determine the severity of the abnormality. If the frequency exceeds the preset range, it is marked as a high-frequency fluctuation, otherwise it is a low-frequency fluctuation, and a fluctuation frequency analysis record is generated;

[0096] The strategy adjustment submodule uses simulated annealing algorithm based on fluctuation frequency analysis records to formulate matching temperature adjustment strategies for high-frequency fluctuations, including short-term high-power adjustment, and for low-frequency fluctuations, formulates mild adjustment strategies, including long-term low-power adjustment, and generates preliminary temperature adjustment plans;

[0097] The strategy generation submodule is based on the preliminary temperature control plan. According to the current working status of the production line and the energy consumption limit of the equipment, it optimizes the parameters in the control plan, including adjusting the power setting and the length of action time, and generates a temperature control strategy.

[0098] In the fluctuation analysis submodule, based on the abnormal temperature marking information, the long short-term memory network (LSTM) algorithm is adopted, and the model is built using the Python programming language and the TensorFlow library. The input layer receives the temperature data of the abnormal temperature time period, passes through two LSTM layers, each with 128 neurons, and uses tanh as the activation function to avoid the gradient disappearance problem. The temperature change frequency is calculated, and the number of temperature changes in each abnormal time period is counted. If the set frequency exceeds the preset range, specifically, the number of changes per minute exceeds 5 times, it is marked as high-frequency fluctuation, otherwise it is low-frequency fluctuation, and a fluctuation frequency analysis record is generated.

[0099] In the strategy adjustment submodule, based on the fluctuation frequency analysis records, the simulated annealing algorithm is adopted and implemented in Python programming language. The initialization temperature is 1000, the cooling rate is 0.95, and the number of iterations is 1000. A matching temperature adjustment strategy is formulated for high-frequency fluctuations, including short-term high-power adjustment. Specifically, the power is set to 1500W and the action time is 5 minutes. For low-frequency fluctuations, a mild adjustment strategy is formulated, including long-term low-power adjustment. The power is set to 500W and the action time is 30 minutes. A preliminary temperature adjustment plan is generated.

[0100] Simulated annealing algorithm, according to the formula:

[0101]

[0102] Calculate new temperature value and generate preliminary temperature adjustment plan;

[0103] in, is the new temperature, reflecting the temperature status after the strategy adjustment. Initialization temperature, set the starting temperature value, is the cooling rate, which controls the rate at which the temperature drops. is the number of iterations, indicating the number of steps of temperature adjustment during simulated annealing. is the weight coefficient, which is used to adjust the impact of fluctuation frequency on the temperature regulation strategy. is the normalized value of the fluctuation frequency, which quantifies the frequency characteristics of the fluctuation.

[0104] Execution process:

[0105] S1: Setting =1000 (initial temperature), = 0.95 (cooling rate), N = 1000 (number of iterations);

[0106] S2: Calculate based on the fluctuation frequency data Normalized values ​​to quantify the frequency characteristics of fluctuations;

[0107] S3: By analyzing the relationship between fluctuation frequency and temperature regulation effect, the weight coefficient is determined using statistical methods such as linear regression The optimal value of

[0108] S4: Calculate the new temperature at each step using the formula , in order to gradually approach the optimal temperature regulation strategy;

[0109] S5: According to The value of is used to generate a temperature adjustment plan by adopting short-term high-power adjustment (1500W, 5 minutes) for high-frequency fluctuations and long-term low-power adjustment (500W, 30 minutes) for low-frequency fluctuations.

[0110] In the strategy generation submodule, based on the preliminary temperature control plan, the genetic algorithm is used to optimize the parameters in the control plan. It is implemented using the Python programming language and the DEAP library. The population size is set to 50, the crossover probability is 0.7, the mutation probability is 0.2, and the iteration generation is 100 generations. According to the current working status of the production line and the energy consumption limit of the equipment, the optimization parameters include adjusting the power setting and the action time length. The power range is set to 200W to 2000W, and the action time range is set to 1 minute to 60 minutes to generate a temperature control strategy.

[0111] See also Figure 2 and Figure 6 ,The production scheduling optimization module includes the job analysis submodule, the job rescheduling submodule, and the resource reconfiguration submodule;

[0112] The operation analysis submodule evaluates the time arrangement and resource allocation of the current production process based on the temperature control strategy, determines the key links that affect production efficiency based on the temperature control requirements and production line conditions, and generates operation process analysis records;

[0113] The job rescheduling submodule identifies potential job sequences that can be optimized based on job process analysis records. By adjusting the execution order of production tasks, it reduces waiting time and interruptions caused by temperature control and forms an optimized production sequence.

[0114] The resource reconfiguration submodule reallocates production resources, including equipment load and personnel arrangements, based on the optimized production sequence, adjusts the equipment load distribution to match the operation sequence, optimizes production efficiency, and obtains scheduling optimization solutions.

[0115] In the job analysis submodule, based on the temperature control strategy, data analysis technology is used, and the Python programming language and Pandas library are used to evaluate the timing and resource allocation of the current production process. Combining the temperature control requirements with the production line conditions, scatter plots and time series analysis methods are used to determine the key links that affect production efficiency, including equipment hot start time and cooling cycle, and generate job process analysis records.

[0116] In the job rescheduling submodule, a heuristic algorithm is adopted based on the job process analysis records, specifically a genetic algorithm, which is implemented using the Python programming language and the DEAP library. The population size is initialized to 50, the crossover probability is 0.7, and the mutation probability is 0.2. By adjusting the execution order of production tasks, the waiting time and interruptions caused by temperature control are reduced. The optimization parameters include the order of task execution and resource allocation strategy to form an optimized production sequence.

[0117] In the resource reconfiguration submodule, according to the optimized production sequence, the linear programming method is adopted, and the Python programming language and PuLP library are used to reallocate production resources. The objective function is set to maximize production efficiency. The constraints include equipment load and personnel arrangement restrictions. The equipment load distribution is adjusted to match the operation sequence. The CPLEX solver is selected to optimize production efficiency and obtain the scheduling optimization plan.

[0118] See also Figure 2 and Figure 7 ,The temperature prediction model module includes a data fusion submodule, a trend identification submodule, and a prediction integration submodule;

[0119] The data fusion submodule collects production scheduling data and historical temperature records based on the scheduling optimization scheme, including the scheduled production time and temperature data of multiple links, and analyzes the correlation between temperature changes and production activities to construct a fused data set;

[0120] The trend recognition submodule identifies the regularity and periodicity of temperature changes based on the fused data set, predicts the temperature change trend under different production conditions for key production links, and generates temperature trend prediction records;

[0121] The forecast integration submodule evaluates the potential impact of predicted temperature changes on production scheduling based on temperature trend forecast records, adjusts strategies and matches predicted temperature conditions, and establishes future temperature forecast data.

[0122] In the data fusion submodule, based on the scheduling optimization scheme, data fusion technology is adopted. Specifically, Python programming language and Pandas library are used to process data, and production scheduling data and historical temperature records are collected, including scheduled production time and temperature data of multiple links. The association rule learning method is used, specifically Apriori algorithm, with support threshold set to 0.5 and confidence threshold set to 0.7. The correlation between temperature change and production activities is analyzed, and the correlation between production links and temperature change is identified by generating association rules to construct a fused data set.

[0123] In the trend identification submodule, based on the fused data set, time series analysis technology is adopted, specifically implemented using the Python programming language and the Statsmodels library, to identify the regularity and periodicity of temperature changes. The trend component and seasonal component of the temperature data are analyzed through the time series analysis method of seasonal decomposition (STL decomposition). For key production links, the temperature change trend under different production conditions is predicted, and temperature trend prediction records are generated.

[0124] In the prediction integration submodule, based on the temperature trend prediction records, decision support system technology is adopted, specifically using Python programming language and SciPy library for optimization, to evaluate the potential impact of predicted temperature changes on production scheduling. Through linear programming methods, the production line scheduling strategy is adjusted to match the predicted temperature conditions. The objective function is set to minimize production delays and energy costs. Constraints include equipment energy consumption limits and production time windows. Future temperature prediction data is established to ensure the combination of production efficiency and energy optimization.

[0125] See also Figure 2 and Figure 8 ,The equipment status diagnosis module includes a temperature impact analysis submodule, a performance data evaluation submodule, and a maintenance requirement identification submodule;

[0126] The temperature impact analysis submodule analyzes the performance fluctuation or failure risk of production equipment under predicted temperature conditions based on future temperature prediction data, identifies equipment that is sensitive to temperature changes, and generates equipment sensitivity analysis data;

[0127] The performance data evaluation submodule collects the operating data of the equipment identified in the equipment sensitive analysis data, including power consumption, operating time and fault history, and evaluates the current performance status and maintenance records of the equipment to obtain the equipment performance evaluation results;

[0128] The maintenance requirement identification submodule compares the equipment maintenance measures and the equipment operating conditions based on the equipment performance evaluation results, and formulates a maintenance plan and schedule based on the potential impact of predicted temperature changes on the equipment, and generates an equipment maintenance list.

[0129] In the temperature impact analysis submodule, based on future temperature prediction data, the random forest algorithm is adopted, implemented using the Python programming language and the Scikit-learn library. The input includes historical temperature data and production equipment operation data. The number of trees is set to 100 and the maximum depth is 10. The performance fluctuations or failure risks of production equipment under predicted temperature conditions are analyzed through training models, and equipment that is sensitive to temperature changes is identified. The feature importance score is used to identify which equipment parameters are most sensitive to temperature changes, and generate equipment sensitivity analysis data.

[0130] In the performance data evaluation submodule, the operating data of the equipment identified in the equipment sensitivity analysis data are collected, including power consumption, operating time and fault history. A data clustering algorithm is used, specifically the K-means algorithm, which is implemented using the Python programming language and the Scikit-learn library. The number of clusters is set to 3, representing equipment in high, medium and low performance states, respectively. The equipment is classified through operating data, and the current performance status and maintenance records of the equipment are evaluated. Based on the clustering results, the equipment performance evaluation results are obtained.

[0131] In the maintenance demand identification submodule, based on the equipment performance evaluation results, the decision tree algorithm is adopted, implemented using the Python programming language and the Scikit-learn library. The input includes the equipment performance evaluation results and the predicted temperature change data. The maximum depth of the tree is set to 5. The algorithm compares the equipment maintenance measures and the equipment operating conditions. According to the potential impact of the predicted temperature changes on the equipment, a maintenance plan and schedule are formulated, taking into account the maintenance cycle, equipment failure rate and the severity of the temperature impact, and generating an equipment maintenance list.

[0132] See also Figure 2 and Fig. 9 ,The parameter adjustment module includes a problem device identification submodule, a parameter analysis submodule, and an automatic adjustment execution submodule;

[0133] The problem equipment identification submodule uses the isolation forest algorithm based on the equipment maintenance list to screen the equipment that needs maintenance or adjustment due to temperature fluctuations or performance degradation. It also combines the equipment temperature sensitivity and historical maintenance records to identify the equipment that cannot maintain optimal performance and generate a list of problem equipment.

[0134] The parameter analysis submodule analyzes the operating parameters of the equipment, including temperature control threshold and response time, based on the list of problematic equipment, and compares them with the parameters of the equipment's optimal operating state to obtain parameter adjustment requirements;

[0135] The automatic adjustment execution submodule uses a deep Q network to automatically adjust the operating parameters of the associated equipment according to the parameter adjustment requirements, including adjusting the temperature control threshold and optimizing the response time, and obtains the parameter adjustment record.

[0136] In the problem equipment identification submodule, the isolation forest algorithm is used based on the equipment maintenance list, implemented using the Python programming language and the Scikit-learn library. The input includes the temperature sensitivity data and historical maintenance records of the equipment. The number of trees is set to 100 and the depth of the isolation tree is set to 8. Equipment that requires maintenance or adjustment due to temperature fluctuations or performance degradation is screened. The equipment temperature sensitivity and historical maintenance records are combined to determine the equipment that cannot maintain optimal performance and generate a list of problem equipment.

[0137] In the parameter analysis submodule, based on the list of problematic devices, a linear regression analysis method is used, Python programming language and Pandas library are used for data processing, and Scikit-learn library is used to implement linear regression. The input includes the operating parameters of the equipment, such as temperature control threshold and response time, which are compared with the parameters of the optimal operating state of the equipment. The relationship between the parameters and the performance status of the equipment is analyzed, the parameters that deviate from the optimal operating state are determined, and the parameter adjustment requirements are obtained.

[0138] In the automatic adjustment execution submodule, according to the parameter adjustment requirements, the deep Q network (DQN) algorithm is adopted, and the model is built using the Python programming language and the TensorFlow library. The network structure is defined to include an input layer, two hidden layers with 128 neurons in each layer, and an output layer. The learning rate is set to 0.001 and the reward decay rate is set to 0.9. The operating parameters of the associated equipment are automatically adjusted, including adjusting the temperature control threshold and optimizing the response time. The Q value table is continuously optimized during the training process to find the best parameter adjustment strategy and obtain the parameter adjustment record.

[0139] Deep Q network, according to the formula:

[0140]

[0141] Calculate the Q value of each operation and generate parameter adjustment records;

[0142] in, Indicates in status Next Action The Q value, is the symbol of the learning rate, which indicates the speed at which the weights are updated during the learning process. Represents the adaptive learning adjustment factor, which is used to dynamically adjust the learning rate according to the model performance. represents the immediate reward received from the environment, is the symbol of the reward decay rate, which represents the present value of future rewards, Represents the environmental stability index, which is used to quantify the impact of external environmental changes on model predictions. Indicates that in the next state Next, for all possible actions The Q value of takes the maximum value, that is, the predicted optimal future reward, is the sign of the operating parameter adjustment rate, reflecting the sensitivity of the model to adjusting the equipment operating parameters. It stands for device response sensitivity, which indicates how quickly the device responds to parameter adjustments.

[0143] Execution process:

[0144] S1: Before training begins, initialize the weights and biases of the deep Q network. This step includes setting the initial weights for the input layer, hidden layer (128 neurons per layer), and output layer.

[0145] S2: The model obtains state information by interacting with the environment and immediate rewards ,The status information includes the current operating parameter settings, such as temperature control thresholds;

[0146] S3: Update actions using collected state information and rewards Q value;

[0147] S4: Through repeated interactions and Q-value updates, the model learns to identify which actions maximize long-term rewards, including adjusting the device’s operating parameters, such as temperature control thresholds and response times, to achieve optimal performance.

[0148] S5: Regularly evaluate model performance during training and adjust To optimize the learning process, if the model performance does not meet expectations, further adjustments can be made and .

[0149] See also Figure 2 and Fig.10 ,The product quality inspection module includes a size test submodule, an elasticity test submodule, and a durability test submodule;

[0150] The size test submodule measures the size of the fascia ball after production based on the parameter adjustment record, verifies the diameter and roundness of the fascia ball, and compares the measurement results with the standard size to verify whether the fascia ball size meets the tolerance range and generates a size qualification record;

[0151] The elasticity test submodule performs elastic compression and recovery tests on the fascia balls that meet the size requirements based on the size qualification records, records the force required for compression and the recovery time, and compares the preset elasticity standards to obtain elasticity test data;

[0152] The durability test submodule conducts durability testing based on the elastic test data, including continuous compression recovery times and service life testing under target load, to verify whether the durability meets the use standards and generate a quality certificate.

[0153] In the size test sub-module, based on the parameter adjustment record, an automatic measurement system is adopted, and image processing technology is utilized, which is specifically implemented using the OpenCV library. The input includes the image data of the fascia ball after production. The edge detection algorithm is used to determine the outline of the fascia ball, calculate the diameter and roundness, and compare the measurement results with the standard size to verify whether the fascia ball size is within the tolerance range and generate a size qualification record.

[0154] In the elasticity test submodule, based on the dimensional qualification record, an elasticity testing machine is used, and mechanical sensors and timers are used to measure the compression force and recovery time. The input includes a fascia ball that meets the dimensional requirements, and the compression load is set to 5kg. The force required for compression and the time to recover to 90% of the original diameter are recorded and compared with the preset elasticity standard. The elasticity standard is set to a compression force of no more than 10N and a recovery time of no more than 2 seconds to obtain elasticity test data.

[0155] In the durability test submodule, based on the elasticity test data, the durability test equipment is used to conduct specific tests on the number of continuous compression and recovery times and the service life under the target load. The input includes a fascia ball that has passed the elasticity test, the number of continuous compression and recovery times is set to 1000 times, and the target load is 5kg. It is verified whether the durability meets the use standard. The use standard is set to no performance degradation after 1000 compression and recovery times, and a quality certificate is generated.

[0156] The above are only preferred embodiments of the present invention and are not intended to limit the present invention in other forms. Any technician familiar with the profession may use the technical contents disclosed above to change or modify them into equivalent embodiments with equivalent changes and apply them to other fields. However, any simple modification, equivalent change and modification made to the above embodiments based on the technical essence of the present invention without departing from the technical solution of the present invention still falls within the protection scope of the technical solution of the present invention.

Claims

1. The temperature control monitoring system of the fascia ball production process is characterized by: The system includes a temperature real-time monitoring module, a temperature anomaly analysis module, a temperature control strategy module, a production scheduling optimization module, a temperature prediction model module, an equipment status diagnosis module, a parameter adjustment module, and a product quality inspection module; The real-time temperature monitoring module records the temperature of the working area and the equipment surface every minute based on the data collected by the temperature sensor, analyzes the temperature change trend over time, and obtains the temperature monitoring record; The temperature anomaly analysis module calculates the temperature change rate at consecutive time points based on the temperature monitoring records, identifies the key time period with abnormal change rate, and marks the time period as temperature anomaly to obtain abnormal temperature marking information; The temperature control strategy module uses a long short-term memory network based on abnormal temperature tag information to analyze temperature fluctuations during an abnormal time period, adjust temperature control parameter settings, including adjusting cooling or heating power, and generate a temperature control strategy; The production scheduling optimization module re-evaluates the time arrangement and resource allocation of multiple links in the production process based on the temperature control strategy, adjusts the operation sequence and equipment load of the production line, matches the temperature control requirements, optimizes production efficiency, and obtains a scheduling optimization plan; The temperature prediction model module is based on the scheduling optimization plan and combines historical temperature data to evaluate the potential temperature changes in future production links, predict the temperature trends of key production links, provide a basis for temperature control, and establish future temperature prediction data; The equipment status diagnosis module checks whether the operating status of the production equipment causes the predicted temperature anomaly based on the future temperature prediction data, analyzes the equipment performance data, identifies the equipment that needs maintenance or adjustment, and generates an equipment maintenance list; The parameter adjustment module uses a deep Q network based on the equipment maintenance list to automatically adjust the operating parameters of the associated equipment, including the temperature control threshold and response time, based on the identified equipment problems, to ensure that the equipment is operating in the optimal state and obtain parameter adjustment records; The product quality inspection module performs quality inspection on the fascia balls after production based on the parameter adjustment records, including size, elasticity and durability index tests, and evaluates the effectiveness of production process control to generate a quality certificate; The temperature monitoring record includes an ambient temperature sequence, an equipment surface temperature sequence and its timestamp, the abnormal temperature marking information includes an identified high temperature point time period, a low temperature point time period, and a corresponding temperature change rate value, the temperature control strategy includes a cooling power adjustment instruction, a heating power adjustment instruction, and a temperature setting value adjustment instruction, the scheduling optimization plan includes production line operation sequence adjustment, equipment load redistribution, and temperature control demand matching measures, the future temperature prediction data includes the predicted temperature value of the key production link, the predicted time period, and the potential temperature fluctuation range, the equipment maintenance list includes the identification of the equipment to be maintained, the estimated maintenance time, and the maintenance measure summary, the parameter adjustment record includes the equipment temperature control threshold adjustment record, the response time adjustment record, and the operating parameter update information, the quality certificate includes the fascia ball size certificate, elasticity test results, and durability test data; The temperature real-time monitoring module includes a data collection submodule, a data recording submodule, and a trend analysis submodule; The data collection submodule monitors the temperature of the working area and the equipment surface based on the data collected by the temperature sensor, and covers multiple key monitoring points to obtain a temperature monitoring data set; The data recording submodule timestamps the temperature monitoring data set, records it once every minute, including the ambient and device surface temperatures, and verifies the timing of the data to generate a time series temperature record; The trend analysis submodule analyzes the data in the time series temperature records, identifies the trend of temperature rising or falling over time, determines the pattern of temperature change by comparing consecutive record points, and obtains temperature monitoring records; The temperature anomaly analysis module includes a change rate calculation submodule, an anomaly identification submodule, and a mark generation submodule; The change rate calculation submodule calculates the temperature change rate between time points based on the temperature monitoring records, identifies the key time points of temperature change by setting threshold comparison, and generates temperature change rate data; The abnormality identification submodule screens the change rate that exceeds the normal operating range according to the temperature change rate data, identifies the time point as abnormal, and identifies the abnormal time period in combination with the continuity of the time point to obtain the time period identification result; The tag generation submodule assigns a corresponding tag to each abnormal time period based on the time period identification result, performs tracking analysis and processing, so that the abnormal time can be recorded and tracked, and abnormal temperature tag information is obtained; The temperature control strategy module includes a fluctuation analysis submodule, a strategy adjustment submodule, and a strategy generation submodule; The fluctuation analysis submodule uses a long short-term memory network based on abnormal temperature marking information to count the number of temperature changes in each abnormal time period, calculate the temperature change frequency, and determine the severity of the abnormality. If the frequency exceeds a preset range, it is marked as a high-frequency fluctuation, otherwise it is a low-frequency fluctuation, and a fluctuation frequency analysis record is generated; The strategy adjustment submodule uses a simulated annealing algorithm based on the fluctuation frequency analysis record to formulate a matching temperature adjustment strategy for high-frequency fluctuations, including short-term high-power adjustment, and a mild adjustment strategy for low-frequency fluctuations, including long-term low-power adjustment, to generate a preliminary temperature adjustment plan; The simulated annealing algorithm is based on the formula: ； Calculate new temperature value and generate preliminary temperature adjustment plan; in, For the new temperature, is the initialization temperature, is the cooling rate, is the number of iterations, is the weight coefficient, is the normalized value of the fluctuation frequency; The strategy generation submodule generates a temperature control strategy based on the preliminary temperature control plan, optimizing the parameters in the control plan according to the current working status of the production line and the energy consumption limit of the equipment, including adjusting the power setting and the action time length; The temperature prediction model module includes a data fusion submodule, a trend identification submodule, and a prediction integration submodule; The data fusion submodule collects production scheduling data and historical temperature records based on the scheduling optimization scheme, including the scheduled production time and temperature data of multiple links, and analyzes the correlation between temperature changes and production activities to construct a fusion data set; The trend identification submodule identifies the regularity and periodicity of temperature changes based on the fused data set, predicts the temperature change trend under different production conditions for key production links, and generates temperature trend prediction records; The prediction integration submodule evaluates the potential impact of predicted temperature changes on production scheduling based on temperature trend prediction records, adjusts strategies and matches predicted temperature conditions, and establishes future temperature prediction data.

2. The temperature control monitoring system for the fascia ball production process according to claim 1 is characterized in that: The production scheduling optimization module includes a job analysis submodule, a job rescheduling submodule, and a resource reconfiguration submodule; The operation analysis submodule evaluates the time arrangement and resource allocation of the current production process based on the temperature control strategy, determines the key links that affect production efficiency based on the temperature control requirements and production line conditions, and generates an operation process analysis record; The job rescheduling submodule identifies potential job sequences that can be optimized based on job flow analysis records, and reduces waiting time and interruptions caused by temperature control by adjusting the execution order of production tasks to form an optimized production sequence; The resource reconfiguration submodule reallocates production resources, including equipment load and personnel arrangement, based on the optimized production sequence, adjusts the equipment load distribution to match the operation sequence, optimizes production efficiency, and obtains a scheduling optimization plan.

3. The temperature control monitoring system for the fascia ball production process according to claim 1 is characterized in that: The equipment status diagnosis module includes a temperature impact analysis submodule, a performance data evaluation submodule, and a maintenance requirement identification submodule; The temperature impact analysis submodule analyzes the performance fluctuation or failure risk of production equipment under the predicted temperature conditions based on the future temperature prediction data, identifies equipment that is sensitive to temperature changes, and generates equipment sensitivity analysis data; The performance data evaluation submodule collects the operation data of the device identified in the device sensitive analysis data, including power consumption, operation time and fault history, and evaluates the current performance status and maintenance record of the device to obtain the device performance evaluation result; The maintenance requirement identification submodule compares the equipment maintenance measures and the equipment operating conditions based on the equipment performance evaluation results, and formulates a maintenance plan and schedule according to the potential impact of the predicted temperature change on the equipment, and generates an equipment maintenance list.

4. The temperature control monitoring system for the fascia ball production process according to claim 1 is characterized in that: The parameter adjustment module includes a problem device identification submodule, a parameter analysis submodule, and an automatic adjustment execution submodule; The problem equipment identification submodule uses the isolation forest algorithm based on the equipment maintenance list to screen the equipment that needs maintenance or adjustment due to temperature fluctuation or performance degradation, and combines the equipment temperature sensitivity and historical maintenance records to determine the equipment that cannot maintain optimal performance and generate a list of problem equipment; The parameter analysis submodule analyzes the operating parameters of the equipment, including the temperature control threshold and the response time, according to the list of problematic equipment, and compares them with the parameters of the equipment's optimal operating state to obtain parameter adjustment requirements; The automatic adjustment execution submodule uses a deep Q network to automatically adjust the operating parameters of the associated equipment according to the parameter adjustment requirements, including adjusting the temperature control threshold and optimizing the response time, and obtaining a parameter adjustment record; The deep Q network, according to the formula: ； Calculate the Q value of each operation and obtain the parameter adjustment record; in, Indicates in status Next Action The Q value, is the symbol of the learning rate, represents the adaptive learning adjustment factor, represents the immediate reward received from the environment, is the sign of the reward decay rate, represents the environmental stability index, Indicates that in the next state Next, for action The Q value takes the maximum value, is the sign of the rate at which the operating parameter is adjusted, Represents the device response sensitivity.

5. The temperature control monitoring system for the fascia ball production process according to claim 1 is characterized in that: The product quality inspection module includes a size test submodule, an elasticity test submodule, and a durability test submodule; The size test submodule measures the size of the produced fascia ball based on the parameter adjustment record, verifies the diameter and roundness of the fascia ball, compares the measurement result with the standard size, verifies whether the fascia ball size meets the tolerance range, and generates a size qualification record; The elasticity test submodule performs elastic compression and recovery tests on the fascia balls that meet the size requirements based on the size qualification records, records the force required for compression and the recovery time, and compares the preset elasticity standards to obtain elasticity test data; The durability test submodule performs durability testing based on the elasticity test data, including continuous compression recovery times and service life testing under target load, verifies whether the durability meets the use standards, and generates a quality certificate.

Images