Data monitoring and optimizing method based on actual quenching process

Abstract

The invention discloses a data monitoring and optimizing method based on an actual quenching process. The method comprises the following steps: arranging a plurality of temperature sensors in quenching equipment; collecting temperature data of the temperature sensor through a data acquisition module; processing and analyzing the temperature data in a data processing system to generate a temperature distribution diagram; carrying out performance test on the quenched part; according to comparison between the actual performance data and a preset performance standard, the influence of temperature distribution on the performance of the part is analyzed, and a correlation model between the temperature and the performance of the part is established; and based on the correlation model, quenching process parameters are adjusted, and the quenching process is optimized. According to the data monitoring and optimizing method based on the actual quenching process, the complete temperature change data of each part during quenching is recorded, the influence of temperature change on the performance of the parts is analyzed in combination with the performance sampling inspection result of the parts, the model is built, and the quenching process is optimized based on the model.

Description

Technical Field

[0001] The present invention belongs to the technical field of metal heat treatment, and in particular relates to a data monitoring and optimization method based on an actual quenching process. Background Art

[0002] Quenching is a key step in the metal heat treatment process, playing an important role in improving the hardness, strength, and wear resistance of metal parts. However, temperature control during the quenching process is crucial, as even small temperature changes can significantly affect part performance. Traditional quenching processes typically rely on preset temperature parameters and empirical adjustments. However, due to differences in equipment precision, environmental factors, and material properties, precise temperature control is often difficult in actual production, resulting in unstable and inconsistent part performance.

[0003] In recent years, advances in sensor technology, data acquisition techniques, and machine learning algorithms have made it possible to monitor and optimize the quenching process in real time. By deploying multiple temperature sensors within the quenching equipment, the temperature distribution within the equipment can be monitored in real time. This data is then transmitted to a data processing system via a data acquisition module. Using machine learning methods such as neural networks and support vector machines, it is possible to model the relationship between temperature and part performance, enabling dynamic optimization of quenching process parameters.

[0004] The present invention aims to provide a quenching monitoring and optimization method, which accurately monitors the temperature changes during the quenching process, combines the actual performance test results of the parts, establishes a prediction model, and dynamically adjusts the quenching process parameters based on the model to improve the quality and production efficiency of the parts. Summary of the Invention

[0005] The present invention provides a data monitoring and optimization method based on actual quenching process to solve the above-mentioned technical problems, specifically adopting the following technical solutions:

[0006] A data monitoring and optimization method based on an actual quenching process comprises the following steps:

[0007] Arrange multiple temperature sensors in the quenching equipment, and the temperature sensors are distributed in different positions of the quenching equipment to monitor the temperature distribution in the equipment in real time during the quenching process;

[0008] Collecting temperature data from the temperature sensor through a data acquisition module and transmitting the temperature data to a data processing system;

[0009] Processing and analyzing the temperature data in a data processing system to generate a temperature distribution graph, and determining whether the quenching process meets the preset temperature requirements based on the temperature distribution graph;

[0010] Perform performance tests on the quenched parts, including hardness test, strength test and toughness test, to obtain the actual performance data of the parts;

[0011] Analyze the impact of temperature distribution on component performance based on a comparison of the actual performance data with a preset performance standard, and establish a correlation model between temperature and component performance;

[0012] Based on the correlation model, adjusting the quenching process parameters and optimizing the quenching process so that the performance of the part after quenching reaches the preset performance standard;

[0013] The association model is established by using a machine learning method, including a neural network and a support vector machine. The machine learning method learns the influence of temperature changes on part performance by training a large amount of temperature data and performance data, and establishes a prediction model.

[0014] Furthermore, the temperature sensors are arranged as follows:

[0015] Arrange at least three temperature sensors in the heating area of the quenching equipment, located at the center, middle and edge of the heating element;

[0016] Arrange at least two temperature sensors in the part placement area, one at the center and one at the edge of the part;

[0017] Arrange at least two temperature sensors in the cooling area, one at the inlet and one at the outlet of the cooling medium;

[0018] The temperature sensor has a measurement accuracy of ±0.1°C and a response time of less than 1 second;

[0019] The arrangement and number of temperature sensors are optimized according to the size and shape of the quenching equipment to ensure that the temperature distribution inside the equipment can be fully monitored.

[0020] Furthermore, the processing of the temperature data by the data acquisition module includes:

[0021] Amplify the weak signal output by the temperature sensor to a range suitable for analog-to-digital conversion;

[0022] Use a low-pass filter to filter out noise signals with frequencies higher than 10Hz;

[0023] Convert the amplified analog signal into a digital signal with a sampling rate of 20 times per second;

[0024] Perform linear correction on the collected temperature data to ensure the accuracy of the data. The correction formula is:

[0025]

[0026] Among them, T 校正 is the corrected temperature value, T 采集 is the collected temperature value, T 标准 is the standard temperature value, T 参考 is the reference temperature value.

[0027] Furthermore, the data processing system analyzes the temperature data including:

[0028] The discrete temperature data points are expanded into a continuous temperature distribution graph through interpolation algorithm;

[0029] For each temperature sensor, calculate the deviation between its actual temperature and the preset temperature. The deviation formula is:

[0030] ΔT=T 实际 -T 预设

[0031] Where ΔT is the temperature deviation, T 实际 is the actual measured temperature value, T 预设 is the preset temperature value;

[0032] Calculate the standard deviation of the temperature distribution to evaluate the temperature uniformity within the equipment. The standard deviation formula is:

[0033]

[0034] Among them, σ T is the temperature standard deviation, N is the number of temperature sensors, T i is the temperature value of the i-th sensor, is the average temperature value of all sensors.

[0035] Furthermore, the process of establishing the association model includes:

[0036] Normalize temperature data and performance data to eliminate the effects of different dimensions and orders of magnitude;

[0037] Extract key features from temperature data, such as maximum temperature, minimum temperature, and temperature change rate, to reduce data dimensions and highlight important information;

[0038] Use neural networks and support vector machines to train the extracted features and performance data to learn how temperature changes affect part performance;

[0039] The cross-validation method was used to evaluate the predictive performance of the model and ensure the generalization ability of the model.

[0040] Furthermore, the optimization process of the quenching process parameters includes:

[0041] Define the optimization objective function, such as minimizing part performance deviation or maximizing part performance index;

[0042] Set constraints on process parameters, such as heating temperature range, holding time range, etc., to ensure the feasibility and safety of the process;

[0043] Use genetic algorithm or particle swarm optimization algorithm to optimize process parameters to find the optimal combination of process parameters;

[0044] The effectiveness of the optimized process parameters is verified through part performance tests in actual production to ensure that the optimized process parameters can be actually applied and improve part performance.

[0045] Furthermore, the process of optimizing the process parameters also includes:

[0046] Based on the prediction results of the correlation model, dynamically adjust the heating temperature and holding time to ensure that the quenching process meets the preset performance requirements;

[0047] Adjust cooling rates in real time based on real-time monitored temperature data and output from predictive models to optimize part performance after quenching;

[0048] The correlation model is used to predict the performance of parts under different process parameter combinations, and the optimal process parameter combination is selected to improve production efficiency and part quality.

[0049] Furthermore, the process of optimizing the process parameters also includes:

[0050] During the production process, the parameters of the correlation model are dynamically adjusted according to the actual performance test results of the parts to improve the prediction accuracy of the model;

[0051] Predict potential performance issues through the correlation model and adjust process parameters in advance to avoid quality defects in production;

[0052] The correlation model is continuously optimized by combining historical production data and real-time monitoring data to adapt to the performance differences of different batches of materials.

[0053] Furthermore, the method also includes risk identification and early warning, the specific steps are:

[0054] Based on the correlation model, identify potential risk factors that may cause part performance to fail to meet standards, such as temperature deviation exceeding the allowable range, poor temperature uniformity, etc.

[0055] Set warning thresholds. When the monitored risk factors exceed the warning thresholds, the system automatically issues warning signals.

[0056] According to the early warning signals, timely adjust the quenching process parameters or take other measures to prevent the performance of parts from failing to meet the standards.

[0057] Furthermore, the method also includes further measures for risk warning, the specific steps are:

[0058] Classify and prioritize early warning signals and take different response measures based on the severity of the risk;

[0059] During the production process, the frequency of risk events and the results of their handling are recorded in real time for subsequent risk assessment and process improvement;

[0060] Regularly evaluate and optimize the risk early warning system, and adjust the warning thresholds and response strategies based on actual production conditions.

[0061] The present invention is beneficial in that it provides a data monitoring and optimization method based on actual quenching processes. By recording the complete temperature change data for each part during quenching and combining it with the results of random performance inspections of the parts, the impact of temperature changes on part performance is analyzed. A model is then built to optimize the quenching process based on this data. By accurately monitoring temperature changes during the quenching process and combining it with actual part performance test results, it is possible to identify which small temperature differences have a positive impact on part performance. Based on this data, quenching process parameters can be optimized, thereby improving part performance and quality. BRIEF DESCRIPTION OF THE DRAWINGS

[0062] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0063] Figure 1 It is a schematic diagram of a data monitoring and optimization method based on an actual quenching process of the present invention. DETAILED DESCRIPTION

[0064] The following describes in detail embodiments of the present application. Examples of the embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are intended to be used to explain the present application, and should not be construed as limiting the present application.

[0065] In the actual quenching production process, the temperature control of the quenching equipment is very important. In order to accurately monitor the temperature distribution in the quenching equipment, the present invention arranges multiple high-precision temperature sensors in the quenching equipment. These temperature sensors are distributed in different positions of the quenching equipment, including the heating area, the parts placement area and the cooling area, to ensure that the temperature changes in the equipment can be fully monitored. Figure 1 The present invention shows a data monitoring and optimization method based on an actual quenching process, which includes the following steps:

[0066] S1: Arrange multiple temperature sensors in the quenching equipment. The temperature sensors are distributed in different positions of the quenching equipment to monitor the temperature distribution in the equipment in real time during the quenching process.

[0067] The temperature sensors are arranged as follows:

[0068] Heating zone: Place at least three temperature sensors in the heating zone of the quenching equipment, one at the center, one in the middle, and one at the edge of the heating element. These sensors monitor the temperature distribution during the heating process to ensure heating uniformity.

[0069] Part placement area: Place at least two temperature sensors in the part placement area, one at the center and one at the edge of the part. These sensors monitor the actual temperature changes of the part during the quenching process to ensure that the part temperature meets the process requirements.

[0070] Cooling area: Place at least two temperature sensors in the cooling area, one at the inlet and one at the outlet of the cooling medium. These sensors monitor temperature changes during the cooling process to ensure that the cooling rate and temperature distribution meet process requirements.

[0071] Temperature sensors use high-precision thermocouples or thermistors with a measurement accuracy of ±0.1°C and a response time of less than 1 second. The placement and number of temperature sensors are optimized based on the size and shape of the quenching equipment to ensure comprehensive monitoring of the temperature distribution within the equipment.

[0072] S2: The data acquisition module collects the temperature data of the temperature sensor and transmits the temperature data to the data processing system.

[0073] To transmit the temperature data collected by the temperature sensor to the data processing system, the present invention uses a data acquisition module. This module includes a signal amplifier, a filter, and an analog-to-digital converter, which can amplify, filter, and convert the temperature signal to ensure the accuracy and reliability of the data.

[0074] The specific steps for the data acquisition module to process temperature data are as follows:

[0075] Signal amplification: Amplify the weak signal output by the temperature sensor to a range suitable for analog-to-digital conversion.

[0076] Filtering: Use a low-pass filter to filter out noise signals with a frequency higher than 10 Hz to reduce measurement errors.

[0077] Analog-to-digital conversion: Convert the amplified analog signal into a digital signal with a sampling rate of 20 times per second.

[0078] Data correction: Perform linear correction on the collected temperature data to ensure the accuracy of the data. The correction formula is:

[0079]

[0080] Among them, T 校正 is the corrected temperature value, T 采集 is the collected temperature value, T 标准 is the standard temperature value, T 参考 is the reference temperature value.

[0081] The purpose of data correction is to ensure the accuracy of temperature data collected from temperature sensors. In actual use, temperature sensors may be affected by environmental factors, device aging, and installation position deviations, resulting in deviations between measured and actual temperatures. Therefore, correction of collected temperature data is necessary to improve its reliability and accuracy. Data correction effectively reduces temperature sensor measurement errors and improves temperature monitoring accuracy, providing reliable data support for subsequent quenching process optimization.

[0082] S3: Processing and analyzing the temperature data in a data processing system to generate a temperature distribution diagram, and judging whether the quenching process meets the preset temperature requirements based on the temperature distribution diagram.

[0083] The data processing system processes and analyzes the received temperature data. The specific steps are as follows:

[0084] Generation of temperature distribution graph: The discrete temperature data points are expanded into a continuous temperature distribution graph through interpolation algorithm, so that the temperature distribution inside the equipment can be observed intuitively.

[0085] Calculation of temperature deviation: For each temperature sensor, calculate the deviation between its actual temperature and the preset temperature. The deviation formula is:

[0086] ΔT=T 实际 -T 预设

[0087] Where ΔT is the temperature deviation, T 实际 is the actual measured temperature value, T 预设 is the preset temperature value.

[0088] By calculating the deviation between the actual temperature of each temperature sensor and the preset temperature, temperature fluctuations during the quenching process can be monitored in real time. If the temperature deviation exceeds the allowable range, process parameters such as heating power and cooling rate can be adjusted promptly to ensure that the quenching process meets the preset temperature requirements. The magnitude of the temperature deviation directly affects the performance of the part after quenching. By monitoring and controlling temperature deviation, the quality and performance consistency of the part can be improved.

[0089] Temperature uniformity assessment calculates the standard deviation of the temperature distribution to evaluate the temperature uniformity within the equipment. The standard deviation formula is:

[0090]

[0091] Among them, σ T is the temperature standard deviation, N is the number of temperature sensors, T i is the temperature value of the i-th sensor, is the average temperature value of all sensors.

[0092] By calculating the standard deviation of the temperature distribution, the temperature uniformity within the quenching equipment can be assessed. A smaller standard deviation indicates a more uniform temperature distribution. If the temperature distribution is uneven, the sensor layout can be optimized by adjusting the location and number of temperature sensors to more comprehensively monitor the temperature distribution within the equipment. The results of the temperature uniformity assessment can serve as a basis for improving quenching equipment design and adjusting process parameters. For example, by adjusting the distribution of heating elements and optimizing the flow of the cooling medium, the temperature uniformity of the quenching equipment can be improved, thereby enhancing the quality and performance consistency of the quenched parts.

[0093] S4: Perform performance tests on the quenched parts, including hardness test, strength test and toughness test, to obtain the actual performance data of the parts.

[0094] After quenching, part performance testing is crucial for verifying the quenching effect. This method performs multiple performance tests on quenched parts, including hardness, strength, and toughness. Hardness testing is performed using a Rockwell or Brinell hardness tester, strength testing is performed using a universal testing machine through tensile or bending tests, and toughness testing is performed using an impact testing machine.

[0095] In addition, to further understand the impact of the quenching process on the internal structure and stress state of the parts, the present invention also conducts microstructure analysis and residual stress testing. Microstructure analysis is performed by metallographic analysis, and residual stress testing is performed by X-ray diffraction.

[0096] S5: Based on the comparison between actual performance data and preset performance standards, analyze the impact of temperature distribution on part performance and establish a correlation model between temperature and part performance.

[0097] After obtaining actual performance data from a component through performance testing, the present invention analyzes the impact of temperature distribution on component performance by comparing the actual performance data with pre-set performance standards, and establishes a correlation model between temperature and component performance. This correlation model is established using machine learning methods, including neural networks and support vector machines. By training on a large amount of temperature and performance data, the machine learning method learns the patterns that influence component performance and establishes a predictive model.

[0098] Among them, the establishment of the correlation model adopts machine learning methods, including neural networks and support vector machines. The machine learning method learns the impact of temperature changes on part performance by training a large amount of temperature data and performance data, and establishes a prediction model.

[0099] The process of building the association model includes the following steps:

[0100] Data preprocessing: Normalize the temperature data and performance data to eliminate the effects of different dimensions and orders of magnitude.

[0101] Feature extraction: Extract key features from temperature data, such as maximum temperature, minimum temperature, and temperature change rate, to reduce data dimensions and highlight important information.

[0102] Model training: Use neural networks and support vector machines to train the extracted features and performance data to learn how temperature changes affect part performance.

[0103] Model validation: Use cross-validation methods to evaluate the predictive performance of the model and ensure the generalization ability of the model.

[0104] S6: Based on the correlation model, adjust the quenching process parameters and optimize the quenching process so that the performance of the parts after quenching meets the preset performance standards.

[0105] Based on the established correlation model, the present invention adjusts the quenching process parameters and optimizes the quenching process so that the performance of the part after quenching reaches the preset performance standard. The optimization process of the quenching process parameters includes the following steps:

[0106] Constraint setting: Set the constraints of process parameters, such as heating temperature range, holding time range, etc., to ensure the feasibility and safety of the process.

[0107] Optimization algorithm selection: Use genetic algorithm or particle swarm optimization algorithm to optimize process parameters to find the optimal combination of process parameters.

[0108] Verification of optimization results: Verify the effectiveness of the optimized process parameters through part performance tests in actual production to ensure that the optimized process parameters can be actually applied and improve part performance.

[0109] Specifically, the process of optimizing process parameters also includes:

[0110] Based on the prediction results of the correlation model, the heating temperature and holding time are dynamically adjusted to ensure that the quenching process meets the preset performance requirements. The correlation model predicts the performance of the part under the current process parameters based on the real-time monitored temperature data and historical performance data. If the prediction results show that the part performance may be lower than the preset standard, the system will automatically trigger the adjustment mechanism. Based on the prediction results, the system dynamically adjusts the power of the heating element to ensure that the heating temperature meets the process requirements. For example, if the prediction results show that the hardness of the part may be insufficient, the system will appropriately increase the heating temperature to increase the uniformity of the austenite. The adjustment of the holding time is also based on the prediction results. If the prediction results show that the performance indicators of the part may be unstable, the system will appropriately extend the holding time to ensure that the temperature inside the part is evenly distributed, thereby improving the performance consistency after quenching.

[0111] Based on real-time temperature data and the output of the predictive model, the cooling rate is adjusted in real time to optimize the performance of the part after quenching. Cooling rate is one of the key factors affecting the performance of the part after quenching. Based on real-time temperature data and the output of the predictive model, the system can adjust the cooling rate in real time to optimize the performance of the part after quenching. The system uses temperature sensors placed in the cooling area to monitor temperature changes during the cooling process in real time. This data is transmitted to the data processing system in real time to analyze whether the cooling rate meets process requirements. The correlation model uses real-time temperature data and historical performance data to predict the part performance at the current cooling rate. If the predicted cooling rate indicates that the cooling rate is too fast or too slow, the system automatically adjusts the flow rate or pressure of the coolant. The system adjusts the cooling rate in real time by controlling the flow rate or pressure of the coolant. For example, if the predicted results indicate that the part's toughness may be insufficient, the system will appropriately reduce the cooling rate to reduce quenching stress and improve the part's toughness.

[0112] During production, the correlation model's parameters are dynamically adjusted based on actual part performance test results to improve prediction accuracy. This correlation model predicts potential performance issues and allows process parameters to be adjusted in advance to avoid quality defects during production. The correlation model is continuously optimized using historical production data and real-time monitoring data to adapt to performance differences between different batches of materials.

[0113] The correlation model predicts part performance under different process parameter combinations and selects the optimal combination to improve production efficiency and part quality. The correlation model uses historical data and real-time monitoring data to predict part performance under different process parameter combinations. These parameters include heating temperature, holding time, cooling rate, and so on. The system evaluates the predicted performance of each parameter combination and selects the one with the best performance. Evaluation metrics include key performance indicators such as hardness, strength, and toughness. Based on the evaluation results, the system selects the optimal process parameter combination and applies it to actual production. This process not only improves part performance but also optimizes production efficiency, reducing production time and energy consumption.

[0114] By dynamically adjusting heating temperature and holding time, the system ensures that each part reaches optimal temperature conditions during the quenching process, thereby improving the consistency of part performance. Real-time adjustment of cooling rate effectively reduces quenching stresses, preventing cracks and other defects in parts, thereby reducing the defective rate. Selecting the optimal combination of process parameters not only improves part performance but also optimizes production efficiency, reducing production time and energy consumption.

[0115] During the quenching process, potential risks may arise due to the influence of equipment precision, material properties, and environmental factors. These risks may lead to substandard part performance or quality problems during the production process. In order to improve the reliability and stability of production, this invention introduces a risk identification and early warning mechanism, which specifically includes the following steps:

[0116] Risk identification: Based on the association model, potential risk factors that may cause part performance to fail to meet standards are identified, such as temperature deviations exceeding the allowable range, poor temperature uniformity, etc. During the quenching process, precise temperature control is key to ensuring part performance. Through the established association model, the system can analyze temperature data and performance data in real time to identify potential risk factors that may cause part performance to fail to meet standards. For example, if the readings of a temperature sensor continuously deviate from the preset range, or the uniformity index of the temperature distribution exceeds the allowable deviation range, these may indicate potential quality problems. Therefore, the system will set early warning thresholds based on these risk factors. When the monitored risk factors exceed the early warning threshold, the system will automatically issue an early warning signal to remind the operator to take appropriate measures.

[0117] Alert threshold settings: Set alert thresholds. When monitored risk factors exceed the threshold, the system automatically issues an alert. Setting alert thresholds is a crucial component of risk identification and early warning mechanisms. These thresholds are set based on historical data and experience to determine whether current production conditions are within normal ranges. For example, if temperature deviations exceed a set threshold, the system identifies a potential risk and triggers an alert. Alert signals can take the form of audible and visual alarms, text message notifications, or system prompts, ensuring operators receive timely alerts and take action.

[0118] Risk Response: Based on early warning signals, timely adjustments to quenching process parameters or other measures are implemented to prevent substandard part performance. Once the system issues an early warning signal, operators must quickly take action to address potential risks. These measures may include adjusting heating temperatures, extending or shortening holding times, or varying cooling rates. Timely adjustments to process parameters can effectively prevent substandard part performance. Furthermore, the system offers an automatic adjustment function that automatically optimizes process parameters based on early warning signals, reducing the need for manual intervention.

[0119] Further measures for risk warning include:

[0120] Early warning signals are classified and prioritized, and different response measures are implemented based on the severity of the risk. This classification and prioritization of early warning signals helps operators quickly identify and address the most pressing issues. For example, the system can categorize early warning signals into three levels: low, medium, and high, based on the severity of the risk. For high-risk early warning signals, the system can automatically take emergency measures, such as suspending production and notifying maintenance personnel. For low-risk early warning signals, the system can provide recommended adjustment plans for operators' reference. This classification and prioritization mechanism not only improves the responsiveness of the production process but also optimizes resource allocation.

[0121] During the production process, the frequency and handling outcomes of risk events are recorded in real time for subsequent risk assessment and process improvement. Recording the frequency and handling outcomes of risk events is a crucial component of continuous production process improvement. By collecting this data, companies can analyze patterns and trends in risk events to optimize early warning thresholds and response strategies. For example, if a certain type of risk event occurs frequently, companies can consider upgrading related equipment or improving process parameters. Furthermore, these records can serve as training materials to help new employees better understand and address risks in the production process.

[0122] Regularly evaluate and optimize the risk warning system, adjusting warning thresholds and response strategies based on actual production conditions. The evaluation and optimization of the risk warning system is an ongoing process. As production conditions change, equipment ages, and new processes are introduced, existing warning thresholds and response strategies may no longer be applicable. Therefore, the system requires regular evaluation and optimization to ensure it accurately identifies and addresses potential risks. For example, companies can regularly analyze the system's false alarm and missed alarm rates and use this data to adjust warning thresholds and optimize algorithms. Through this continuous optimization mechanism, companies can continuously improve production reliability and stability, reducing the occurrence of quality defects and production accidents.

[0123] Through the aforementioned risk identification and early warning mechanism, the present invention can effectively improve the reliability and stability of the quenching process and reduce quality defects and defective product rates during the production process. This not only improves the production efficiency of the enterprise, but also reduces production costs and enhances the enterprise's market competitiveness.

[0124] This invention provides a quenching monitoring and optimization method. By precisely monitoring temperature changes during the quenching process and combining it with actual part performance test results, a predictive model is established. Based on this model, quenching process parameters are dynamically adjusted to improve part quality and production efficiency. Furthermore, the invention incorporates a risk identification and early warning mechanism, further enhancing production reliability and stability. Practical application testing has demonstrated significant results in improving part performance and production efficiency, demonstrating its broad potential for application.

[0125] The above shows and describes the basic principles, main features and advantages of the present invention. Those skilled in the art should understand that the above embodiments do not limit the present invention in any form, and any technical solutions obtained by equivalent replacement or equivalent transformation fall within the scope of protection of the present invention.

Claims

1. A data monitoring and optimization method based on actual quenching process, characterized in that: The following steps are involved: Arrange multiple temperature sensors in the quenching equipment, and the temperature sensors are distributed in different positions of the quenching equipment to monitor the temperature distribution in the equipment in real time during the quenching process; Collecting temperature data from the temperature sensor through a data acquisition module and transmitting the temperature data to a data processing system; Processing and analyzing the temperature data in a data processing system to generate a temperature distribution graph, and determining whether the quenching process meets the preset temperature requirements based on the temperature distribution graph; Perform performance tests on the quenched parts, including hardness test, strength test and toughness test, to obtain the actual performance data of the parts; Analyze the impact of temperature distribution on component performance based on a comparison of the actual performance data with a preset performance standard, and establish a correlation model between temperature and component performance; Based on the correlation model, adjusting the quenching process parameters and optimizing the quenching process so that the performance of the part after quenching reaches the preset performance standard; The association model is established by using a machine learning method, including a neural network and a support vector machine. The machine learning method learns the influence of temperature changes on part performance by training a large amount of temperature data and performance data, and establishes a prediction model.

2. The data monitoring and optimization method based on actual quenching process according to claim 1 is characterized in that: The arrangement of the temperature sensors is as follows: Arrange at least three temperature sensors in the heating area of the quenching equipment, located at the center, middle and edge of the heating element; Arrange at least two temperature sensors in the part placement area, one at the center and one at the edge of the part; Arrange at least two temperature sensors in the cooling area, one at the inlet and one at the outlet of the cooling medium; The temperature sensor has a measurement accuracy of ±0.1°C and a response time of less than 1 second; The arrangement and number of temperature sensors are optimized according to the size and shape of the quenching equipment to ensure that the temperature distribution inside the equipment can be fully monitored.

3. The data monitoring and optimization method based on actual quenching process according to claim 2, characterized in that: The data acquisition module processes the temperature data including: Amplify the weak signal output by the temperature sensor to a range suitable for analog-to-digital conversion; Use a low-pass filter to filter out noise signals with frequencies higher than 10Hz; Convert the amplified analog signal into a digital signal with a sampling rate of 20 times per second; Perform linear correction on the collected temperature data to ensure the accuracy of the data. The correction formula is: Among them, T 校正 is the corrected temperature value, T 采集 is the collected temperature value, T 标准 is the standard temperature value, T 参考 is the reference temperature value.

4. The data monitoring and optimization method based on actual quenching process according to claim 3 is characterized in that: The data processing system analyzes the temperature data including: The discrete temperature data points are expanded into a continuous temperature distribution graph through interpolation algorithm; For each temperature sensor, calculate the deviation between its actual temperature and the preset temperature. The deviation formula is: △T=T 实际 -T 预设 Where ΔT is the temperature deviation, T 实际 is the actual measured temperature value, T 预设 is the preset temperature value; Calculate the standard deviation of the temperature distribution to evaluate the temperature uniformity within the equipment. The standard deviation formula is: Among them, σ T is the temperature standard deviation, N is the number of temperature sensors, T i is the temperature value of the i-th sensor, is the average temperature value of all sensors.

5. The data monitoring and optimization method based on actual quenching process according to claim 1 is characterized in that: The process of establishing the association model includes: Normalize temperature data and performance data to eliminate the effects of different dimensions and orders of magnitude; Extract key features from temperature data, such as maximum temperature, minimum temperature, and temperature change rate, to reduce data dimensions and highlight important information; Use neural networks and support vector machines to train the extracted features and performance data to learn how temperature changes affect part performance; The cross-validation method was used to evaluate the predictive performance of the model and ensure the generalization ability of the model.

6. The data monitoring and optimization method based on actual quenching process according to claim 5, characterized in that: The optimization process of the quenching process parameters includes: Define the optimization objective function, such as minimizing part performance deviation or maximizing part performance index; Set constraints on process parameters, such as heating temperature range, holding time range, etc., to ensure the feasibility and safety of the process; Use genetic algorithm or particle swarm optimization algorithm to optimize process parameters to find the optimal combination of process parameters; The effectiveness of the optimized process parameters is verified through part performance tests in actual production to ensure that the optimized process parameters can be actually applied and improve part performance.

7. The data monitoring and optimization method based on actual quenching process according to claim 6, characterized in that: The process of optimizing process parameters also includes: Based on the prediction results of the correlation model, dynamically adjust the heating temperature and holding time to ensure that the quenching process meets the preset performance requirements; Adjust cooling rates in real time based on real-time monitored temperature data and output from predictive models to optimize part performance after quenching; The correlation model is used to predict the performance of parts under different process parameter combinations, and the optimal process parameter combination is selected to improve production efficiency and part quality.

8. The data monitoring and optimization method based on actual quenching process according to claim 7, characterized in that: The process of optimizing process parameters also includes: During the production process, the parameters of the correlation model are dynamically adjusted according to the actual performance test results of the parts to improve the prediction accuracy of the model; Predict potential performance issues through the correlation model and adjust process parameters in advance to avoid quality defects in production; The correlation model is continuously optimized by combining historical production data and real-time monitoring data to adapt to the performance differences of different batches of materials.

9. The data monitoring and optimization method based on actual quenching process according to claim 1, characterized in that: The method also includes risk identification and early warning, and the specific steps are: Based on the correlation model, identify potential risk factors that may cause part performance to fail to meet standards, such as temperature deviation exceeding the allowable range, poor temperature uniformity, etc. Set warning thresholds. When the monitored risk factors exceed the warning thresholds, the system automatically issues warning signals. According to the early warning signals, timely adjust the quenching process parameters or take other measures to prevent the performance of parts from failing to meet the standards.

10. The data monitoring and optimization method based on actual quenching process according to claim 9, characterized in that: The method also includes further measures for risk early warning, which include the following steps: Classify and prioritize early warning signals and take different response measures based on the severity of the risk; During the production process, the frequency of risk events and the results of their handling are recorded in real time for subsequent risk assessment and process improvement; Regularly evaluate and optimize the risk early warning system, and adjust the warning thresholds and response strategies based on actual production conditions.

Images