Intelligent production method of corrosion-resistant press nut

Abstract

The application discloses an intelligent production method of a corrosion-resistant press rivet nut in the field of information technology, and comprises the following steps: performing surface treatment on the press rivet nut after heat treatment, selecting a galvanizing or nickel plating process according to the corrosion resistance requirement of the product, obtaining a uniform and dense plating layer by controlling the parameters of plating solution temperature, concentration and plating time, detecting the plating layer quality by using a plating layer thickness instrument and an adhesion tester, optimizing the pre-plating treatment and post-plating treatment processes, and improving the protection performance and appearance quality of the plating layer; integrating the surface defect detection result and other performance indexes as the comprehensive evaluation basis of the product quality, establishing a correlation model of the press rivet nut performance detection data and material properties, heat treatment processes and surface treatment processes, using a correlation rule mining and time series prediction method to mine the influence law of each element on the product performance, and predicting the product performance distribution under different production parameter combinations.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of information technology, in particular to the production technology of rivet nuts, and more particularly to an intelligent production method of corrosion-resistant rivet nuts. BACKGROUND

[0002] In the production of corrosion-resistant rivet nuts, the temperature and time control of the heat treatment process is a key technical problem. Currently, most manufacturers use traditional heat treatment methods, which have low temperature control accuracy and unstable holding time, resulting in uneven hardness and strength of the products, and large differences between batches. This not only affects the corrosion resistance of the rivet nuts, but also brings difficulties to subsequent assembly. Overly high heat treatment temperature or excessively long holding time can cause the material to become coarse-grained, reducing its plasticity and toughness; while too low temperature or insufficient time cannot achieve the desired strength and hardness.

[0003] Therefore, how to ensure product performance while achieving precise control of the heat treatment process is a technical problem that needs to be solved. This requires innovation and optimization in heat treatment equipment, temperature measurement, automatic control, and other aspects to improve production efficiency and the stability of product quality. SUMMARY

[0004] The present application provides an intelligent production method of corrosion-resistant rivet nuts, comprising the following steps:

[0005] Step S1, obtain the grain size, plasticity and toughness attribute parameters of different materials from the rivet nut material performance database, establish a mathematical model of material attributes and heat treatment process parameters through a support vector machine algorithm, determine the best material selection and heat treatment process matching scheme, and measure the material utilization rate by calculating the number of qualified rivet nuts that can be produced per unit of raw material, while ensuring the mechanical properties of the product and improving this indicator;

[0006] Step S2, according to the selected material and heat treatment process, install multiple high-precision temperature sensors in the heat treatment furnace, real-time collect temperature data at different positions in the furnace, and transmit them to the process control system. If the actual temperature deviates from the target temperature by more than a preset threshold, automatically adjust the heating power to ensure uniform temperature field distribution in the furnace, and at the same time, use a thermal imager to monitor the temperature distribution in the furnace, obtain three-dimensional temperature field data, simulate the temperature field through finite element analysis method, and optimize the uniformity of furnace temperature;

[0007] Step S3, the process control system presets the holding time and temperature curve according to the optimal heat treatment process parameters of the product, controls the heating and holding state switching by using a programmable logic controller, ensures the consistency of the heat treatment process of each batch of products, combines the product size tolerance requirements, collects experimental data and performs multiple regression analysis, establishes an association model of the holding time and the size accuracy, dynamically optimizes the holding time by using a neural network algorithm, and specific implementation includes: the input layer receives the current process parameters and product size data, the hidden layer performs feature extraction and nonlinear mapping, the output layer predicts the optimal holding time, the network weight is continuously adjusted through back propagation, the holding time is optimized in real time, and the size deviation of the product is controlled within the tolerance range;

[0008] Step S4, the surface treatment is performed on the heat-treated press-in nut, galvanizing or nickel plating process is selected according to the corrosion resistance requirements of the product, the plating layer is obtained by controlling the parameters of the plating solution temperature, concentration and electroplating time, the plating layer thickness instrument and adhesion tester are used to detect the quality of the plating layer, the pre-plating treatment and post-plating treatment process are optimized, and the protection performance and appearance quality of the plating layer are improved;

[0009] Step S5, the finished product after plating treatment is comprehensively detected, including measuring the key size by using a precision gauge, testing the tensile strength and yield strength by using a universal material testing machine, and evaluating the corrosion resistance by using a salt spray test chamber, at the same time, the machine vision system is used to detect the surface defects of the press-in nut, the defects such as scratches, pits and plating layer falling off are identified, the detection data is associated with the process parameters, the heat treatment and surface treatment process are continuously optimized by using a random forest algorithm, the random forest algorithm constructs multiple decision trees, each tree uses different feature subsets and sample subsets, the prediction results of all trees are combined, the optimal process parameter combination is obtained, and the batch stability of product performance is improved;

[0010] Step S6, the surface defect detection result and other performance indicators are integrated as the comprehensive evaluation basis of the product quality, the correlation model of the performance detection data of the press-in nut and the material properties, the heat treatment process and the surface treatment process is established, the influence law of each element on the product performance is mined by using the association rule mining and time series prediction method, and the product performance distribution under different production parameter combinations is predicted;

[0011] Step S7, if the predicted performance exceeds the allowable range of the technical specification, the system automatically gives an early warning and gives process optimization suggestions, the optimization suggestions are applied to the specific production link through the feedback mechanism: the material selection standard is adjusted, the heat treatment process parameters are updated, and the surface treatment formula is optimized, the process control system automatically adjusts the corresponding parameters according to the suggestions, realizes the closed-loop optimization of the production process, and continuously improves the product quality and production efficiency.

[0012] The technical scheme provided by the embodiment of the application can include the following beneficial effects:

[0013] The application discloses an intelligent production method of corrosion-resistant press-in nuts. The system determines the optimal material and heat treatment scheme by establishing a mathematical model of material properties and heat treatment process parameters, thereby improving material utilization. In the heat treatment process, a multi-sensor is used to monitor the temperature distribution in the furnace in real time, and the temperature field uniformity is optimized in combination with finite element analysis. At the same time, the heat preservation time is dynamically optimized using a neural network algorithm to control the dimensional accuracy of the product. After comprehensive detection of the finished product, the correlation between the detection data and the process parameters is analyzed using a random forest algorithm, and the heat treatment and surface treatment processes are continuously optimized. The application realizes intelligent closed-loop optimization of the production process of press-in nuts, significantly improving the product quality stability and production efficiency. DETAILED DESCRIPTION

[0014] In order to make the purpose, technical scheme and advantages of the application clearer, the application will be described in detail below with specific examples.

[0015] The application discloses an intelligent production method of corrosion-resistant press-in nuts, which specifically includes the following steps:

[0016] Step S1: Obtain the grain size, plasticity and toughness attribute parameters of different materials from a press-in nut material performance database. A mathematical model of material properties and heat treatment process parameters is established by a support vector machine algorithm to determine the optimal material selection and heat treatment process matching scheme. Material utilization is measured by calculating the number of qualified press-in nuts that can be produced per unit of raw material, thereby improving this indicator while ensuring the mechanical properties of the product.

[0017] Step S1 includes: obtaining the grain size, plasticity, toughness key attribute parameters of different materials in the press-in nut material performance database, preprocessing the material attribute parameters, removing outliers, and performing standardization processing; using a support vector machine algorithm, taking the material attribute parameters as input and the heat treatment process parameters as output, training to establish a mathematical model of the material properties and the heat treatment process parameters; according to the mathematical model, input the attribute parameters of the target material, and predict the matching heat treatment process parameter combination; according to the predicted heat treatment process parameter combination, perform a heat treatment test on the target material, and test the mechanical properties of the material after heat treatment; if the mechanical properties of the material after heat treatment meet the requirements, calculate the number of qualified press-in nuts that can be produced per unit of raw material to obtain the material utilization index; comprehensively evaluate the material utilization index and the mechanical property test results to determine whether the target material and the heat treatment process parameter combination are the optimal matching scheme; if so, apply the optimal matching scheme to the production of press-in nuts; if not, adjust the attribute parameters of the target material, return to the matching scheme prediction step, and re-predict the matching scheme.

[0018] Specifically, the press-in nut material performance database is the key foundation, containing various material grain size, plasticity, toughness and other attribute parameters. For example, the grain size of a certain carbon steel is 10 μm, the plastic elongation is 20%, and the impact toughness is 80 J / cm2. After obtaining these data, preprocessing is needed to eliminate outliers and standardize them. For example, standardize the plastic elongation to the range of 0-1 to facilitate subsequent modeling. The support vector machine algorithm is used to establish a mathematical model of material attributes and heat treatment process parameters. The input may include standardized attribute values such as grain size, plasticity, toughness, and the output is quenching temperature, holding time and other heat treatment process parameters. This model can learn complex nonlinear relationships and is beneficial to accurately predict the best process parameters. According to the established model, input the attribute parameters of the target material, and the best heat treatment process parameter combination can be predicted. For example, for a new type of alloy steel, input its standardized grain size 0.8, plasticity 0.6, toughness 0.7, the model may output the best quenching temperature 850°C, holding time 30 minutes and other parameters. According to the predicted parameters, heat treatment test is carried out to test whether the mechanical properties of the material meet the requirements. Possible test items include tensile strength, yield strength, elongation, etc. If the tensile strength of the material after heat treatment reaches 800 mPa and the elongation is 15%, it meets the design requirements, and then the next step of evaluation is entered. Material utilization rate is an important indicator to evaluate the pros and cons of the scheme. For example, 1 ton of raw materials can produce 100,000 qualified press-in nuts, and the material utilization rate is 95%. This indicator reflects the economy and environmental protection of the process, and has an important influence on production cost and resource utilization efficiency. By comprehensively evaluating the material utilization rate and the test results of mechanical properties, the best matching scheme is determined. If a scheme can ensure the strength and toughness of the press-in nut and achieve a material utilization rate of more than 95%, it can be considered as the best scheme and applied to production. If the expected goal is not reached, the material attribute parameters need to be adjusted and the matching scheme is predicted again. This iterative optimization process reflects the close combination of materials science and process technology. Through data-driven methods, the optimal material-process matching scheme can be quickly found to improve product quality, reduce production cost, and continuously improve the press-in nut manufacturing process. At the same time, this method also provides a reference for the optimization of manufacturing processes of other metal parts.

[0019] Step S2, according to the selected material and heat treatment process, a plurality of high-precision temperature sensors are installed in the heat treatment furnace to collect real-time temperature data at different positions in the furnace and transmit them to the process control system. If the actual temperature deviates from the target temperature by more than the preset threshold, the heating power is automatically adjusted to ensure uniform temperature field distribution in the furnace. At the same time, a thermal imager is used to monitor the temperature distribution in the furnace to obtain three-dimensional temperature field data, and a finite element analysis method is used to simulate the temperature field to optimize the uniformity of the furnace temperature.

[0020] The step S2 comprises: acquiring real-time temperature data of each position in the heat treatment furnace, the real-time temperature data being collected by a plurality of high-precision temperature sensors arranged at different positions in the heat treatment furnace; transmitting the real-time temperature data to a process control system; after the process control system receives the real-time temperature data, comparing the real-time temperature data with a preset target temperature, calculating a deviation value between the real-time temperature data and the target temperature; if the deviation value exceeds a preset threshold value, the process control system automatically adjusts a heating power of the heat treatment furnace according to the size and positive and negative of the deviation value; acquiring three-dimensional temperature field data in the heat treatment furnace, the three-dimensional temperature field data being collected by a thermal imager for real-time monitoring of the heat treatment furnace; fusing the three-dimensional temperature field data with the real-time temperature data, and generating a high-precision three-dimensional temperature field model in the heat treatment furnace through a data fusion algorithm; simulating the high-precision three-dimensional temperature field model by using a finite element analysis method to obtain a simulation result of furnace temperature uniformity; and optimizing control parameters of the heat treatment furnace according to the simulation result.

[0021] Specifically, the temperature field monitoring of the heat treatment furnace is crucial to ensure the quality of the rivet nuts. To achieve accurate monitoring, multiple high-precision thermocouples, such as K-type thermocouples, can be placed inside the furnace to measure a range of -200°C to 1300°C with an accuracy of ±0.75%. These sensors can be installed at different heights and locations inside the furnace, such as the top, bottom, and walls, forming a three-dimensional monitoring network. The temperature data collected by the sensors are transmitted in real-time to the central control system through RS-485 bus or wireless ZigBee network. After receiving the actual temperature data, the control system compares it with the preset target temperature. For example, if the target temperature is 850°C and the actual temperature measured at a certain point is 830°C, the deviation is 20°C. If the system's preset allowable deviation threshold is ±10°C, the deviation is out of range and needs to be adjusted. The control system will automatically increase the heating power according to the size and direction of the deviation. Specifically, a PID control algorithm can be used to calculate the output power based on the deviation value, integral value, and differential value, achieving rapid and stable temperature adjustment. The introduction of thermal imagers further improves the accuracy and comprehensiveness of temperature field monitoring. High-end thermal imagers can achieve a temperature measurement range of -40°C to 2000°C with a thermal sensitivity of 0.03°C. By scanning the entire furnace cavity, the thermal imager can generate a high-resolution temperature distribution map with a resolution of 640x480 pixels. These data are fused with sensor data using algorithms such as Kalman filtering to generate a more accurate three-dimensional temperature field model. Finite element analysis software, such as ANSYS, is used to simulate and analyze the generated three-dimensional temperature field model. By setting appropriate mesh division, boundary conditions, and material properties, the heat transfer process inside the furnace can be simulated. The simulation results can visually display the temperature distribution cloud map, revealing the temperature gradient and hot spot areas. For example, the simulation may find a 20°C temperature drop at the corners of the furnace, which can be used to optimize the layout of heating elements or adjust the thickness of the insulation layer. Based on the simulation results, the heat treatment process parameters can be further optimized. For example, if the rapid heating rate leads to uneven temperature, the heating rate can be reduced from 10°C / min to 5°C / min. If the holding time is not sufficient to eliminate the temperature gradient, the holding time can be extended from 30min to 45min. Through these optimizations, the temperature field inside the furnace can be more uniform, with a temperature deviation controlled within ±5°C, significantly improving the consistency and reliability of the heat treatment quality. This closed-loop feedback control and optimization mechanism not only ensures the quality of single batch heat treatment, but also continuously improves the heat treatment process parameter library through long-term data accumulation. For example, the best heat treatment curves for different materials and sizes of rivet nuts can be established to achieve intelligent recommendation and automatic adjustment of process parameters, further improving production efficiency and product quality.

[0022] Step S3, the process control system presets the holding time and temperature curve according to the optimal heat treatment process parameters of the product, uses a programmable logic controller to control the switching of heating and holding states, and ensures that the heat treatment process of each batch of products is consistent. In combination with the product size tolerance requirements, an association model of holding time and size accuracy is established through experimental data collection and multiple regression analysis. The neural network algorithm is used to dynamically optimize the holding time, which specifically includes: the input layer receives the current process parameters and product size data, the hidden layer performs feature extraction and nonlinear mapping, the output layer predicts the optimal holding time, the network weights are continuously adjusted through back propagation, the real-time optimization of the holding time is realized, and the size deviation of the product is controlled within the tolerance range.

[0023] Step S3 includes: obtaining the preset temperature curve and holding time data as the control basis of the PLC; establishing a mathematical association model between the holding time and the product size to obtain the regression model coefficients; inputting the real-time collected process parameters and product size data into the neural network with the coefficients as the initial weights of the neural network; outputting the optimized holding time through the neural network; and returning the holding time to the PLC to dynamically adjust the holding time of the current batch of products, and through iterative optimization, the product size deviation is controlled within the preset tolerance range.

[0024] Specifically, the acquisition and application of heat treatment process parameters are critical to ensure product quality. Taking the heat treatment of an automobile engine crankshaft as an example, based on material properties and usage requirements, the preset temperature curve can be: heating at a rate of 10°C / min to 850°C, holding for 2 hours, and then cooling at a rate of 5°C / min to 200°C. These parameters will serve as the basis for PLC control. The process of PLC controlling the heating equipment can be compared to the automobile cruise control system. Assuming the target temperature is 850°C and the current temperature is 830°C, the PLC will determine a temperature deviation of 20°C and increase the heating power accordingly. As the temperature gradually approaches the target value, the PLC will dynamically reduce the heating power to avoid overshooting the temperature, and eventually stabilize at the target temperature. The control during the holding phase is similar to the keep-warm function of an electric rice cooker. When the temperature reaches 850°C, the PLC switches to the holding state and starts the timer for 2 hours of timing. During this period, the PLC will fine-tune the heating power to maintain a constant temperature, ensuring that the crankshaft receives uniform heat treatment. The collection of product size data can use a laser measurement system. For example, for the main journal diameter of the crankshaft, multiple points can be measured before and after heat treatment, and the average value is calculated and recorded. These data, together with process parameters such as temperature curve and holding time, are stored in the database to provide a basis for subsequent analysis. The multiple regression analysis method is used to establish a correlation model between holding time and product size. Assuming that a linear relationship is found between holding time (x) and crankshaft main journal diameter change (y): y = 0.02x + 0.05. This means that for every additional hour of holding time, the main journal diameter increases by an average of 0.02mm, with a base expansion of 0.05mm. Using the coefficients of the regression model as the initial weights of the neural network is similar to the application of transfer learning in image recognition. For example, in the optimization of crankshaft heat treatment, the input layer can include material composition, initial size, target size, and other parameters; the hidden layer performs feature extraction and nonlinear transformation, which can contain implicit information such as material properties and thermal expansion coefficient; the output layer gives the optimized holding time. The holding time output by the neural network is fed back to the PLC for dynamic adjustment, which is similar to the adaptive cruise control system. For example, if the neural network predicts that the current batch of crankshafts needs 2.2 hours of holding time to reach the target size, the PLC will extend the holding time accordingly. In this way, the system can adapt to the slight differences in raw materials of different batches, ensuring the consistency of the final product size.

[0025] ±0.01mm. The advantage of this intelligent heat treatment control system lies in its adaptive ability. It can cope with factors such as raw material batch differences and environmental temperature changes, continuously optimize process parameters, and improve product quality stability. At the same time, through data accumulation and analysis, the system can also provide valuable insights for process improvement, such as discovering potential correlations between certain material compositions and heat treatment effects, providing a basis for material optimization.

[0026] Step S4, surface treatment of the heat-treated press-in nuts, according to the corrosion resistance requirements of the product, select zinc plating or nickel plating process. By controlling the parameters of plating solution temperature, concentration and electroplating time, a uniform and dense coating is obtained. Use coating thickness meter and adhesion tester to detect the quality of the coating, optimize the pre-plating treatment and post-plating treatment process, and improve the protective performance and appearance quality of the coating.

[0027] Step S4 includes: obtaining the corrosion resistance requirements of the press-in nuts, determining to use zinc plating process or nickel plating process for surface treatment according to the corrosion resistance requirements; for the zinc plating process or nickel plating process, establish a correlation model between plating solution temperature, plating solution concentration and electroplating time process parameters and coating quality; use support vector machine or decision tree algorithm to train the correlation model, get the optimized correlation model; in the electroplating process, get the plating solution temperature and concentration parameters, input the parameters into the optimized correlation model, get the predicted coating uniformity and density; according to the predicted coating uniformity and density, dynamically adjust the process parameters until the coating quality meets the preset requirements; use coating thickness meter to measure the coating thickness distribution, compare the measurement data with the target thickness, judge whether the coating thickness is uniform; if the coating thickness is not uniform, input the measurement data into the correlation model, retrain and optimize the correlation model; use adhesion tester to detect the bonding force between the coating and the substrate, get the adhesion data; according to the preset threshold, judge whether the adhesion is qualified; if the adhesion is not qualified, input the adhesion data into the pre-plating treatment process optimization model, use neural network algorithm to establish the correlation between pre-plating treatment and post-plating treatment process parameters and defects, optimize the pre-plating treatment process and post-plating treatment process; comprehensively evaluate the coating thickness uniformity, the adhesion and the appearance quality detection results, output the comprehensive quality score of the surface treatment process; according to the comprehensive quality score, continuously optimize the process parameters, improve the corrosion resistance and appearance quality of the press-in nut products, meet the use requirements of downstream customers.

[0028] Specifically, the corrosion resistance of the rivet nut is one of the key indicators of product quality. Depending on the application environment requirements, galvanizing or nickel plating process can be selected for surface treatment. For example, for outdoor use of the rivet nut, hot dip galvanizing process is usually adopted, which can provide 15-20 years of corrosion protection; while for indoor use of precision electronic equipment, electroplating nickel process can be selected, which can not only provide good corrosion resistance, but also ensure dimensional accuracy. Establishing a correlation model between process parameters and coating quality is the key to optimizing the surface treatment process. Taking the galvanizing process as an example, a large amount of historical production data can be collected, including bath temperature (usually in the range of 45-55℃), bath concentration (zinc ion concentration about 10-15g / L), current density (2-3A / dm 2parameters, and corresponding plating layer thickness, uniformity, and other quality indicators. By utilizing support vector machine algorithms, a non-linear classification boundary in the multi-dimensional parameter space can be established to predict the plating layer quality grade under different parameter combinations. In the electroplating process, real-time monitoring and adjustment of process parameters are crucial. For example, by monitoring the plating solution concentration with an online conductivity meter, when the concentration is detected to be lower than 10 g / L, the automatic replenishment system is started; by monitoring the plating solution temperature in real time with an infrared thermometer, combined with a PID control algorithm, the heating power is accurately controlled to make the temperature fluctuation within ±1°C. These real-time adjustment measures can effectively improve the stability of the plating layer quality. The uniformity of the plating layer thickness distribution directly affects the corrosion resistance of the product. By using an X-ray fluorescence plating thickness meter, the plating thickness can be quickly measured at multiple measurement points. For example, for M6 specification press-in nuts, 3 measurement points can be selected on the nut top surface, side surface, and internal thread, respectively, to measure the plating thickness. If the standard deviation of the thickness of the 9 points is less than 0.5 μm, and the average thickness is within the range of 8-12 μm, it is determined to be qualified. The adhesion between the plating layer and the substrate is another important quality indicator. By using grid or tensile test method for adhesion test, the bonding strength can be quantitatively evaluated. For example, using an automatic grid instrument, a 10x10 grid is drawn on the surface of the plating layer, then the grid is quickly peeled off after being pasted with adhesive tape, and the number of peeled grids is observed. If the peeled area is less than 5%, it is determined to be qualified. This test method is simple and fast, suitable for quality control in batch production. For cases where plating layer quality problems occur, the production process can be optimized by analyzing the pre-plating treatment and post-plating treatment processes. For example, if the plating layer adhesion is found to be insufficient, it may be due to insufficient pickling before plating. By establishing a neural network model, inputting parameters such as pickling time and acid concentration, and outputting adhesion prediction value, the optimal pickling process parameter combination can be found. Similarly, for post-plating passivation treatment, by adjusting the passivation solution concentration and soaking time, the corrosion resistance of the plating layer can be improved. In the comprehensive evaluation of plating layer quality, a weighted scoring method can be used. For example, the thickness uniformity, adhesion, and appearance quality are respectively given weights of 40%, 40%, and 20%, and the comprehensive score is calculated according to the measured values of each indicator. By continuously collecting scoring data and feeding back to the process optimization model, the surface treatment quality of the press-in nut can be continuously improved, ultimately meeting the strict requirements of downstream customers, such as the 1000-hour neutral salt spray test standard required by the automotive industry.

[0029] Step S5, the finished product after plating treatment is comprehensively detected, including measuring key dimensions with precision gauges, testing tensile strength and yield strength with a universal material testing machine, and evaluating corrosion resistance with a salt spray test chamber. At the same time, a machine vision system is used to detect defects on the surface of the rivet nut, identify scratches, pits and defects of plating falling off. The detection data is correlated with the process parameters for correlation analysis, and the heat treatment and surface treatment process is continuously optimized through the random forest algorithm. The random forest algorithm builds multiple decision trees, each tree uses different feature subsets and sample subsets, and combines the prediction results of all trees to obtain the optimal process parameter combination, thereby improving the batch stability of product performance.

[0030] Step S5 includes: obtaining the technical requirements of the rivet nut, determining the target values and tolerance ranges of the key dimensions, tensile strength, yield strength and corrosion resistance, and establishing product quality evaluation standards; obtaining the detection data of the rivet nut and the heat treatment and surface treatment process parameters of the corresponding batch, and constructing a data set; using a random forest algorithm, based on the data set, a prediction model between process parameters and product performance is established; the key process parameters are determined through feature importance evaluation; according to the prediction model, the heat treatment and surface treatment process parameters are optimized, the process setting values are adjusted, and the batch stability of product performance is improved.

[0031] Specifically, the quality evaluation criteria of the press-in nuts are the basis for product performance control. For example, the key dimension, the thread inner diameter, is an important parameter that determines the precision of the nut and bolt cooperation. Assuming that the target value of the thread inner diameter of a certain type of press-in nut is 6.0 mm, and the tolerance range is ±0.05 mm. Using a precision thread micrometer to measure the thread inner diameter, if the measured value is 6.03 mm, it is judged to be qualified; if the measured value is 6.07 mm, it exceeds the upper limit of the tolerance and needs to be marked as a size defect. Tensile strength and yield strength reflect the load-carrying capacity of the press-in nut. For example, the tensile strength target value of a certain type of press-in nut is 800 MPa, and the yield strength target value is 640 MPa. Through the tensile test of the universal material testing machine, if the measured tensile strength is 785 MPa and the yield strength is 630 MPa, although it is slightly lower than the target value, it is within the allowable range, and it can be judged to be qualified. If the tensile strength is only 750 MPa, it needs to be marked as a mechanical property defect, and whether there is a problem with the heat treatment process needs to be analyzed. The corrosion resistance test simulates the performance of the press-in nut in the actual use environment. For example, for zinc-plated press-in nuts, a salt spray test can be conducted in a 5% sodium chloride solution, and the test time is 96 hours. If there is no obvious red rust on the coating after 96 hours, only a small amount of white rust appears, the corrosion resistance is judged to be qualified. If there is a large area of red rust, it needs to be marked as a corrosion resistance defect, and whether the electroplating process parameters are abnormal needs to be checked. The machine vision system can quickly detect the surface defects of the press-in nut. For example, in the case of nut surface scratch detection, a line scan camera can be used to obtain high-resolution images, and edge features can be extracted through image processing algorithms to identify scratches. If a scratch longer than 0.5 mm is detected, it is judged to be a surface defect. This automated detection method can improve detection efficiency and accuracy, and reduce human error. The random forest algorithm is used to establish a prediction model of process parameters and product performance. For example, in the case of heat treatment process, the quenching temperature, holding time, cooling speed, etc. can be used as input features, and the tensile strength and yield strength can be used as output targets. Through training the random forest model, the influence of each process parameter on the strength can be obtained. Assuming that the model shows that the quenching temperature has the highest feature importance, the quenching temperature can be adjusted first to improve the strength. Process parameter optimization is a dynamic process. For example, in the case of surface treatment process, if the corrosion resistance of a certain batch of products is not good, the electroplating time or current density can be adjusted according to the prediction of the random forest model. In subsequent production, the optimized parameters are applied, and the corrosion resistance test data is continuously collected. By continuously updating the model and optimizing the parameters, the stability of the product performance can be gradually improved, and the batch-to-batch fluctuations can be reduced. This data-driven quality control and process optimization method can effectively improve the overall quality level of the press-in nut. By establishing a complete detection system and prediction model, problems in the production process can be found and solved in a timely manner, and the products can continuously meet the needs of customers.

[0032] Step S6, integrate the surface defect detection result with other performance indicators as the basis for comprehensive evaluation of product quality. Establish the correlation model of the performance detection data of the press-in nut and the material properties, heat treatment process and surface treatment process, use correlation rule mining and time series prediction method to mine the influence law of each factor on product performance, and predict the product performance distribution under different production parameter combinations.

[0033] Step S6 includes: obtaining the surface defect detection result data and other performance indicator data of the press-in nut, performing data fusion processing on the surface defect detection result data and other performance indicator data to obtain comprehensive evaluation data of the product quality of the press-in nut. Obtain the performance detection data of the press-in nut, material attribute data, heat treatment process parameters and surface treatment process parameters, and establish a correlation model of the performance of the press-in nut and production factors based on the performance detection data of the press-in nut, material attribute data, heat treatment process parameters and surface treatment process parameters. Based on the correlation model, use the association rule mining algorithm to mine the association rules between the production factors of material properties, heat treatment process parameters and surface treatment process parameters and the performance of the press-in nut, and obtain the influence law of each production factor on the performance of the press-in nut. Obtain a set of to-be-predicted production parameter combination data, input the production parameter combination data into the correlation model, and combine the influence law to use the time series prediction algorithm to predict the performance distribution of the press-in nut product under the production parameter combination. According to the predicted performance distribution result, it is judged whether the production parameter combination meets the preset performance requirement, if it meets, the production parameter combination is determined as a feasible production parameter, and it is applied to the production and manufacturing process of the press-in nut. In the production and manufacturing process of the press-in nut, the parameter data of each production link is collected in real time, and the real-time collected parameter data is input into the correlation model to dynamically predict the performance distribution of the press-in nut product, and realize real-time monitoring of the product performance. If the predicted performance distribution result does not meet the preset performance requirement, the production parameters are adjusted in time, and the above steps are executed again until the predicted performance distribution result meets the preset performance requirement, so as to ensure the quality stability of the press-in nut product.

[0034] Specifically, the quality assessment of the press-in nuts involves the fusion of data from multiple dimensions. For example, surface defect detection may include indicators such as scratch depth, area percentage, etc., while performance indicators include tensile strength, yield strength, corrosion resistance, etc. By standardizing these heterogeneous data and assigning weights, a comprehensive score can be obtained. Assuming that a batch of press-in nuts has a surface defect area of 2%, a tensile strength of 500 MPa, and a corrosion resistance of 96 hours, the comprehensive score obtained after data fusion processing is 92 points, higher than the 90-point pass line. Establishing a correlation model between press-in nut performance and production factors is key to optimizing the production process. This model needs to consider factors such as material composition, heat treatment temperature, time, cooling rate, surface treatment process, etc. For example, by analyzing historical data, it may be found that when the carbon content is within the range of 0.45%-0.50%, the heat treatment temperature is between 850°C-870°C, and the holding time is 30-35 minutes, the tensile strength of the product is most stable. This correlation model can be constructed using machine learning algorithms such as random forests or neural networks. Correlation rule mining algorithms can discover hidden patterns from massive production data. For example, it may be found that when the heat treatment temperature increases by 10°C, the product hardness increases by 2HRC, but the toughness decreases slightly. For another example, for every 5μm increase in zinc plating layer thickness, the corrosion resistance increases by about 20 hours. These rules provide quantitative basis for process optimization. Based on the established correlation model and the discovered influence rules, the performance of new production parameter combinations can be predicted. Assuming a new set of parameters: carbon content 0.48%, heat treatment temperature 860°C, holding time 32 minutes, zinc plating layer thickness 15μm. Input these parameters into the model, combined with time series prediction algorithms, the following prediction results may be obtained: tensile strength mean 520MPa, standard deviation 10MPa; hardness mean 52HRC, standard deviation 1HRC; corrosion resistance mean 110 hours, standard deviation 5 hours. If these prediction results meet the pre-set performance requirements, the parameter combination can be applied to actual production. In the production process, real-time monitoring and dynamic adjustment are crucial. By installing sensors at key processes, parameters such as heat treatment furnace temperature curve, cooling rate, and surface treatment tank liquid concentration can be collected in real time. Inputting these real-time data into the correlation model can dynamically predict product performance. For example, if the heat treatment furnace temperature fluctuation exceeds ±5°C, the model may predict that the product hardness distribution will be abnormal. At this time, the system will alarm in time, and the operator can adjust the heating power or extend the holding time to compensate for this deviation. This data-driven intelligent manufacturing method has significant advantages. First, it can fully utilize historical production data and convert the implicit experience wisdom in the data into quantifiable decision-making basis. Second, by establishing complex correlations between multiple factors, the influence of process parameters on product performance can be more comprehensively understood, avoiding negative effects that may be caused by single-factor optimization.Furthermore, real-time monitoring and predictive capabilities make the production process more agile, allowing for timely intervention before problems escalate. Finally, this approach can continuously improve itself as data accumulates, with the accuracy of the model improving over time, leading to continuous optimization of the production process. However, implementing this approach also faces some challenges. Data quality is the primary issue, requiring ensuring that the collected data is accurate and reliable. Second, model interpretability is also important, especially when applying machine learning algorithms, requiring the ability to explain the reasons for the prediction results to engineers. In addition, how to balance the complexity and practicality of the model also needs careful consideration, as overly complex models may increase computational burden and affect real-time performance. Finally, attention needs to be paid to data security and privacy protection, especially when it comes to core process parameters.

[0035] Step S7, if the predicted performance exceeds the allowable range of technical specifications, the system automatically warns and gives process optimization suggestions. These optimization suggestions are applied to specific production links through a feedback mechanism: adjusting material selection criteria, updating heat treatment process parameters, and optimizing surface treatment formulations. The process control system automatically adjusts the corresponding parameters based on these suggestions to achieve closed-loop optimization of the production process, continuously improving product quality and production efficiency.

[0036] Step S7 includes: obtaining equipment operation data, the equipment operation data including temperature, pressure and vibration frequency; preprocessing the equipment operation data to obtain a standardized equipment operation data set; constructing a prediction model using a support vector machine regression algorithm based on the standardized equipment operation data set to obtain a device performance prediction value; if the device performance prediction value exceeds a preset threshold range, triggering a warning signal; obtaining preliminary process optimization rules through a decision tree algorithm based on the warning signal; combining expert knowledge base and Bayesian network reasoning to generate process optimization suggestions based on the preliminary process optimization rules, the process optimization suggestions including material selection, heat treatment temperature and time, and surface treatment solution concentration.

[0037] Specifically, device operation data collection is the foundation of predictive maintenance. Taking a rivet nut production line as an example, key parameters such as heat treatment furnace temperature, press pressure, and vibration sensor frequency can be collected. Data preprocessing cleans and standardizes the original data, such as removing outliers, filling missing values, and normalizing, to ensure data quality. Support vector machine regression algorithm is suitable for small sample and nonlinear problems, and can be used to predict device performance indicators. For example, based on historical data, a model is trained to predict the maximum pressure value of the press within the next 24 hours. Comparing the performance prediction value with the threshold value can timely discover potential problems. For example, if the predicted pressure value exceeds the set threshold value of 800 kN, the system will generate a warning signal, recording the time and specific value of the exceedance. Decision tree algorithm can quickly locate the key parameter combination that causes performance anomalies by analyzing historical data. For example, it is found that when the heat treatment temperature exceeds 550 ℃ and the holding time is less than 30 minutes, it is easy to cause pressure to exceed. The generation of process optimization suggestions integrates data analysis results and expert experience. Bayesian network can simulate the complex relationship between parameters and infer the optimal parameter combination. For example, according to the analysis results, it is recommended to adjust the heat treatment temperature to 530 ℃, extend the holding time to 40 minutes, and increase the surface treatment solution concentration by 5%. These optimization suggestions are sent to the control system through the communication interface to realize the automatic adjustment of production parameters. After receiving the optimization suggestions, the control system converts them into specific execution instructions. For example, adjust the temperature curve of the heat treatment furnace, modify the pressure set value of the press, and update the solution ratio of the surface treatment tank, etc. This closed-loop optimization process can continuously improve product quality and production efficiency. By continuously collecting new operation data, the system can learn and optimize itself, adapting to the dynamic changes of the production environment. The core advantage of this method is to combine data-driven prediction analysis with expert knowledge, realizing intelligent and adaptive optimization of the production process. It not only can timely discover potential problems, but also can give targeted solutions, greatly improving production efficiency and product quality stability. At the same time, through continuous data accumulation and model optimization, the prediction accuracy and optimization effect of the system will continuously improve, providing strong support for the long-term development of enterprises.

[0038] Based on the above examples according to the present application, through the above description, relevant personnel can make various changes and modifications without deviating from the technical idea of the present application. The technical scope of the present application is not limited to the content of the specification, and must be determined by the scope of the claims.

Claims

1. An intelligent production method of corrosion-resistant press nut, characterized in that, The method comprises the following steps: Step S1, obtain the grain size, plasticity and toughness attribute parameters of different materials from the rivet nut material performance database, establish a mathematical model of material attributes and heat treatment process parameters through a support vector machine algorithm, determine the optimal material selection and heat treatment process matching scheme, and measure the material utilization rate by calculating the number of qualified rivet nuts that can be produced per unit of raw material, while ensuring the mechanical properties of the product and improving this indicator; Step S2, according to the selected material and heat treatment process, install multiple high-precision temperature sensors in the heat treatment furnace, real-time collect temperature data at different positions in the furnace, and transmit them to the process control system. If the actual temperature deviates from the target temperature by more than the preset threshold, the heating power is automatically adjusted to ensure uniform temperature field distribution in the furnace. At the same time, a thermal imager is used to monitor the temperature distribution in the furnace to obtain three-dimensional temperature field data. Through finite element analysis method, temperature field simulation is carried out to optimize the uniformity of furnace temperature; Step S3, the process control system presets the holding time and temperature curve according to the optimal heat treatment process parameters of the product, uses a programmable logic controller to control the switching of heating and holding state, ensures the consistency of the heat treatment process of each batch of products, combines the product size tolerance requirements, collects experimental data and carries out multiple regression analysis to establish a correlation model between holding time and size accuracy, and uses a neural network algorithm to dynamically optimize the holding time. The specific implementation includes: the input layer receives the current process parameters and product size data, the hidden layer performs feature extraction and nonlinear mapping, and the output layer predicts the optimal holding time. Through back propagation, the network weight is continuously adjusted to realize real-time optimization of holding time and control the size deviation of the product within the tolerance range; Step S4, surface treatment is performed on the heat treated rivet nut. According to the corrosion resistance requirements of the product, galvanizing or nickel plating process is selected. By controlling the parameters of plating solution temperature, concentration and plating time, uniform and dense plating layer is obtained. Plating thickness meter and adhesion tester are used to detect the quality of the plating layer, and the pre-plating treatment and post-plating treatment process is optimized to improve the protective performance and appearance quality of the plating layer; Step S5, the finished product after plating treatment is comprehensively detected, including measuring the key dimensions with precision gauges, testing the tensile strength and yield strength with a universal material testing machine, and evaluating the corrosion resistance in a salt spray test chamber. At the same time, a machine vision system is used to detect defects on the surface of the rivet nut, such as scratches, pits and plating layer shedding. The detection data is correlated with the process parameters, and the heat treatment and surface treatment processes are continuously optimized through a random forest algorithm. The random forest algorithm constructs multiple decision trees, each tree uses different feature subsets and sample subsets, and combines the prediction results of all trees to obtain the optimal process parameter combination, thereby improving the batch stability of product performance. Step S6, integrate the surface defect detection results with other performance indicators as the basis for comprehensive evaluation of product quality, establish the correlation model of pressure nut performance detection data and material properties, heat treatment process and surface treatment process, use correlation rule mining and time series prediction method to mine the influence law of each factor on product performance and predict the product performance distribution under different production parameter combinations; Step S7, if the predicted performance exceeds the allowable range of technical specifications, the system automatically warns and gives process optimization suggestions, which are applied to specific production links through feedback mechanism: adjust material selection criteria, update heat treatment process parameters, optimize surface treatment formula, the process control system automatically adjusts the corresponding parameters according to these suggestions to realize closed-loop optimization of production process and continuously improve product quality and production efficiency.

2. The intelligent production method of the corrosion-resistant press nut according to claim 1, characterized in that, The step S1 comprises: Obtaining the grain size, plasticity and toughness key attribute parameters of different materials in the pressure nut material performance database, preprocessing the material attribute parameters, removing outliers and standardizing the processing; Using support vector machine algorithm, taking the material attribute parameters as input and heat treatment process parameters as output, training to establish the mathematical model of material attributes and heat treatment process parameters; According to the mathematical model, input the attribute parameters of the target material to predict the matched heat treatment process parameter combination; According to the predicted heat treatment process parameter combination, the target material is subjected to heat treatment test, and the mechanical properties of the material after heat treatment are tested; If the mechanical properties of the material after heat treatment meet the requirements, calculate the number of qualified pressure nuts that can be produced per unit of raw material to obtain the material utilization rate index; Comprehensive evaluation of the material utilization rate index and the mechanical property test results to determine whether the target material and the heat treatment process parameter combination are the best matching scheme; If yes, the best matching scheme is applied to the production of pressure nuts; If not, adjust the attribute parameters of the target material and return to the matching scheme prediction step to predict the matching scheme again.

3. The intelligent production method of the corrosion-resistant press nut according to claim 1, characterized in that, The step S2 comprises: Obtaining real-time temperature data at each position in the heat treatment furnace, the real-time temperature data is collected by a plurality of high-precision temperature sensors arranged at different positions in the heat treatment furnace; The real-time temperature data is transmitted to the process control system; After receiving the real-time temperature data, the process control system compares the real-time temperature data with the preset target temperature, calculates the deviation value between the real-time temperature data and the target temperature; If the deviation value exceeds the preset threshold, the process control system automatically adjusts the heating power of the heat treatment furnace according to the size and positive and negative of the deviation value; Obtaining three-dimensional temperature field data in the heat treatment furnace, the three-dimensional temperature field data is collected by a thermal imager for real-time monitoring of the heat treatment furnace; Fuse the three-dimensional temperature field data with the real-time temperature data to generate a high-precision three-dimensional temperature field model of the heat treatment furnace through a data fusion algorithm; Using finite element analysis method to simulate the high-precision three-dimensional temperature field model to obtain the simulation result of furnace temperature uniformity; According to the simulation result, the control parameters of the heat treatment furnace are optimized.

4. The intelligent production method of the corrosion-resistant press nut according to claim 1, characterized in that, The step S4 comprises: Obtaining the corrosion resistance requirement of the press-in nut, and determining the galvanizing process or the nickel plating process according to the corrosion resistance requirement; For the galvanizing process or the nickel plating process, a correlation model between the plating solution temperature, the plating solution concentration, the electroplating time process parameter and the plating layer quality is established; The correlation model is trained by using a support vector machine or a decision tree algorithm to obtain an optimized correlation model; In the electroplating process, the plating solution temperature and the concentration parameters are obtained, and the parameters are input into the optimized correlation model to obtain the predicted plating layer uniformity and compactness; According to the predicted plating layer uniformity and compactness, the process parameters are dynamically adjusted until the plating layer quality meets the preset requirement; The plating layer thickness distribution is measured by using a plating layer thickness instrument, and the measured data is compared with the target thickness to determine whether the plating layer thickness is uniform; If the plating layer thickness is not uniform, the measured data is input into the correlation model for retraining and optimization; The adhesion between the plating layer and the base material is detected by using an adhesion tester to obtain adhesion data; According to a preset threshold, it is judged whether the adhesion is qualified; If the adhesion is not qualified, the adhesion data is input into a pre-plating treatment process optimization model, and a neural network algorithm is used to establish a correlation between the pre-plating treatment and post-plating treatment process parameters and defects, so as to optimize the pre-plating treatment process and post-plating treatment process; The plating layer thickness uniformity, the adhesion and the appearance quality detection result are comprehensively evaluated to output a comprehensive quality score of the surface treatment process; According to the comprehensive quality score, the process parameters are continuously optimized to improve the corrosion resistance and appearance quality of the press-in nut product, and to meet the use requirements of downstream customers.

5. The intelligent production method of the corrosion-resistant press nut according to any one of claims 1-4, characterized in that, The step S6 comprises: Obtaining press-in nut surface defect detection result data and other performance index data, and performing data fusion processing on the surface defect detection result data and other performance index data to obtain comprehensive evaluation data of the quality of the press-in nut product; Obtaining press-in nut performance detection data, material attribute data, heat treatment process parameters and surface treatment process parameters, and establishing a correlation model between the press-in nut performance and production factors based on the press-in nut performance detection data, material attribute data, heat treatment process parameters and surface treatment process parameters; Based on the correlation model, a correlation rule between the production factors of the material attribute, the heat treatment process parameter and the surface treatment process parameter and the performance of the press-in nut is mined by using a correlation rule mining algorithm to obtain the influence law of each production factor on the performance of the press-in nut; A group of to-be-predicted production parameter combination data is obtained, the production parameter combination data is input into the correlation model, and the performance distribution of the press-in nut product under the production parameter combination is predicted by using a time series prediction algorithm in combination with the influence law; According to the predicted performance distribution result, it is judged whether the production parameter combination meets the preset performance requirement, and if so, the production parameter combination is determined as a feasible production parameter and is applied to the production and manufacturing process of the press-in nut. In the production process of the press-in nut, parameter data of each production link is collected in real time, and the real-time collected parameter data is input into the correlation model to dynamically predict the performance distribution of the press-in nut product, so as to realize real-time monitoring of the product performance. If the predicted performance distribution result does not meet the preset performance requirement, the production parameters are adjusted in time, and the above steps are re-executed until the predicted performance distribution result meets the preset performance requirement, so as to ensure the quality stability of the press-in nut product.

6. The intelligent production method of the corrosion-resistant press nut according to any one of claims 1-4, characterized in that, The step S7 comprises: obtaining equipment operation data, the equipment operation data including temperature, pressure and vibration frequency; preprocessing the equipment operation data to obtain a standardized equipment operation data set; constructing a prediction model according to the standardized equipment operation data set by using a support vector machine regression algorithm to obtain an equipment performance prediction value; if the equipment performance prediction value exceeds a preset threshold range, triggering an early warning signal; obtaining preliminary process optimization rules through a decision tree algorithm according to the early warning signal; generating process optimization suggestions based on the preliminary process optimization rules in combination with an expert knowledge base and Bayesian network reasoning, the process optimization suggestions including material selection, heat treatment temperature and time, and surface treatment solution concentration.