Deviation correction control system of automatic coating machine

Abstract

The invention relates to an automatic correction control system for a coating machine. Position parameters and working parameters of a plurality of position sensors of the coating machine are monitored and collected in real time; acquiring position characteristic values of the plurality of position parameters, and judging whether the current position has deviation or not; when the position deviation exists, calculating a hash value of the working parameter through a hash function, and searching a corresponding preset fault mode in a hash table; and training a time mapping relation among the position characteristic value, the working parameter and the fault mode by adopting a machine learning model, and predicting the position deviation and the fault mode in the next time period according to the current working parameter and the position characteristic value and performing deviation correction control. According to the method, the problems of detection position deviation and low fault response speed in the prior art are solved, and the accuracy and efficiency of fault detection are improved by using the time sequence model and the random forest model.

Description

Technical Field

[0001] The invention belongs to the technical field of coating machine control and relates to an automatic coating machine deviation correction control system. Background Art

[0002] In the context of the vigorous development of modern industry, the market competition in various industries is fierce, consumers' expectations for product quality are constantly rising, and industry standards are becoming increasingly stringent. For example, industries such as food packaging and electronics have extremely high requirements for the accuracy and performance of coated products. In addition, under the trend of large-scale production, coating machines need to meet the needs of high-speed continuous production, and high-speed operation can easily cause the substrate to deviate. In addition, the market changes rapidly and customers require a shorter delivery cycle. Therefore, the deviation control of the coating machine needs to meet the dual needs of high quality and high efficiency.

[0003] Patent CN118419663A discloses a real-time tension control and correction system for a coating machine. It includes a data acquisition unit, a simulation model building unit, a parameter adjustment unit, a work correction unit, and a data replacement unit; the data acquisition unit is used to collect the working parameters of the coating machine and obtain the position data of the material on the surface of the coating machine; by detecting the matching of the real-time working parameters and position data with the fault simulation data, the work is stopped in time and a signal is sent for correction, which reduces the possibility of faults and improves the reliability and safety of the system. The new tension correction parameters can be applied to the coating tension simulation model, and all data can be updated and replaced to ensure that the simulation results are consistent with the actual situation. At the same time, the correction parameters are simulated according to the coating tension simulation model according to the real-time working parameters, so as to prepare correction measures in time before the fault occurs.

[0004] However, although the system can detect the match between real-time parameters and fault simulation data, faults occur quickly in actual production. There may be a certain delay from detecting deviations to stopping work and sending correction signals. For high-speed coating machines, this short delay may result in a large number of defective products. Summary of the invention

[0005] The present invention provides an automated coating machine deviation correction control system, which simplifies the logical judgment of position deviation, merges multiple position parameters into a single comprehensive characteristic value, and reduces complex multiple threshold judgments. A hash table is used for fast matching, and the working parameter combination under normal working conditions is stored through hash function calculation. The real-time deviation data is calculated by the hash function and then searched in the table, avoiding the time-consuming traditional linear search. The time mapping relationship between the coating machine position characteristic value, working parameters and fault mode is learned through a machine learning model, so as to achieve early fault prediction and solve the problem of slow fault response in the prior art.

[0006] The purpose of the present invention can be achieved through the following technical solutions:

[0007] The present application provides an automatic coating machine deviation correction control system, including a data acquisition module, a deviation judgment module, a fault identification module and a fault prediction module; the data acquisition module, the deviation judgment module, the fault identification module and the fault prediction module are communicatively connected, wherein:

[0008] The data acquisition module is used to monitor and collect position parameters and working parameters of multiple position sensors of the coating machine in real time;

[0009] The deviation judgment module is used to obtain position characteristic values ​​of multiple position parameters and judge whether there is a deviation in the current position;

[0010] The fault identification module is used to calculate the hash value of the working parameter through a hash function when there is a position deviation, and search the corresponding preset fault mode in the hash table;

[0011] The fault prediction module uses a machine learning model to train the time mapping relationship between position feature values, working parameters and fault modes, and is used to predict the position deviation and fault mode of the next time period based on the current working parameters and position feature values ​​and perform correction control.

[0012] Furthermore, the working parameters include coating speed, coating tension, coating pressure, coating flow rate and coating viscosity.

[0013] Furthermore, the acquisition of position characteristic values ​​of multiple position parameters and the determination of whether there is a deviation in the current position are specifically implemented by a principal component analysis method, including the following steps:

[0014] S1. Collect location parameter data samples of multiple location sensors in historical periods;

[0015] S2. Reduce the dimensions of different position parameters through principal component analysis to obtain several principal components;

[0016] S3, selecting a calculation formula for the first principal component to calculate positional eigenvalues ​​of multiple positional parameters;

[0017] S4. When the current position feature value exceeds a preset position feature value threshold, it is determined that there is a deviation in the current position.

[0018] Furthermore, the failure modes include guide roller wear or improper installation, loose or faulty transmission parts, coating head blockage or uneven discharge, excessive or unstable coating speed, abnormal coating tension, inappropriate coating viscosity and unstable coating flow.

[0019] Furthermore, the machine learning model includes the following construction steps:

[0020] T1. Collect the time series coating machine working data set with each complete coating process as the cycle in the historical period;

[0021] T2. Establish a time series model for synchronizing working parameters and position characteristic values ​​during each complete coating process.

[0022] Furthermore, the time series model includes the following construction steps:

[0023] T21. Data preprocessing: Remove noise and outliers from the collected time series coating machine working data, and standardize the data using the Z-score standardization method;

[0024] T22. Feature Engineering: Mining the time characteristics in time series data, combining working parameters with position feature values, and mining potential nonlinear relationships between features;

[0025] T23, ARMA model training and tuning: The preprocessed and feature-engineered data is divided into training sets and test sets in a specific ratio in chronological order, and the ARMA model is trained using the training set. The loss function is minimized by continuously adjusting the autoregressive order p and the moving average order q, so that the model can accurately learn the time series relationship between the working parameters and the position eigenvalues; the cross-validation method is used to optimize the autoregressive order p and the moving average order q;

[0026] T24. Model evaluation and verification: Use the test set data to evaluate the trained ARMA model, use the mean square error and mean absolute error to measure the deviation between the predicted value and the actual value, and judge the model performance; if it does not meet expectations, return to adjust the feature engineering, autoregressive order p and moving average order q.

[0027] Furthermore, predicting the position deviation and failure mode of the next time period according to the current working parameters and position characteristic values ​​and performing correction control includes the following steps:

[0028] E1. Obtain the working parameters and position characteristic values ​​of the current time series, input them into the time series model, and predict the working parameters and position characteristic values ​​of the next time period;

[0029] E2. Based on the position feature value of the next time period, predict whether there will be position deviation in the next time period;

[0030] E3. When it is predicted that there will be a position deviation in the next time period, the hash value of the working parameters of the next time period is calculated, and the failure mode of the next time period is predicted by searching the hash table;

[0031] E4. According to the predicted failure mode in the next time period, the working parameters and the position of the coating machine are adjusted and corrected.

[0032] Furthermore, in step E3, the failure mode of the next time period is predicted, and the working parameters and position characteristic values ​​are used as explanatory variables, and the correction plan corresponding to the failure mode is used as the response variable. A random forest model is trained to output the correction plan for the next time period based on the working parameters and position characteristic values ​​of the next time period.

[0033] Furthermore, the random forest model includes the following construction steps:

[0034] P1. Feature selection and processing: Select the working parameters and position characteristic values ​​related to the correction scheme labels in the historical period as features;

[0035] P2, Random Forest Model Training: Establish multiple decision trees between working parameters and position feature values ​​and correction schemes. Each decision tree randomly extracts samples and features from the training data for training;

[0036] P3, Hyperparameter adjustment: adjust the number of decision trees, maximum depth, minimum number of samples required for node splitting, and optimize the random forest model through cross-validation;

[0037] P4. Model evaluation and application: Use an independent test set to evaluate the trained model, using accuracy, recall, and F1 score as evaluation indicators.

[0038] Beneficial effects of the present invention:

[0039] By real-time monitoring and collecting the position parameters and working parameters of multiple position sensors of the coating machine; obtaining the position characteristic values ​​of multiple position parameters to determine whether there is a deviation in the current position; when there is a position deviation, the hash value of the working parameter is calculated by a hash function, and the corresponding preset fault mode is searched in the hash table; a machine learning model is used to train the time mapping relationship between the position characteristic value, the working parameter and the fault mode, which is used to predict the position deviation and fault mode of the next time period according to the current working parameters and position characteristic values ​​and perform correction control. The present invention solves the problem of slow response speed of detecting position deviation and fault in the prior art, and at the same time improves the accuracy and efficiency of fault detection by using a time series model and a random forest model. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] In order to facilitate understanding by those skilled in the art, the present invention is further described below with reference to the accompanying drawings.

[0041] Figure 1 The present invention is a structural diagram of an automatic coating machine deviation correction control system.

[0042] Figure 2 This is a flow chart of determining whether there is a deviation in the current position through position feature values ​​in one embodiment of the present invention.

[0043] Figure 3 This is a flow chart of predicting the position deviation and failure mode of the next time period and performing correction control based on the current working parameters and position characteristic values ​​in one embodiment of the present invention. DETAILED DESCRIPTION

[0044] In order to further explain the technical means and effects adopted by the present invention to achieve the predetermined invention purpose, the specific implementation mode, structure, characteristics and effects of the present invention are described in detail below in combination with the accompanying drawings and preferred embodiments.

[0045] See also Figure 1-Figure 3 The present application provides an automatic coating machine deviation correction control system, including a data acquisition module, a deviation judgment module, a fault identification module and a fault prediction module; the data acquisition module, the deviation judgment module, the fault identification module and the fault prediction module are communicatively connected, wherein:

[0046] The data acquisition module is used to monitor and collect position parameters and working parameters of multiple position sensors of the coating machine in real time, and the working parameters include coating speed, coating tension, coating pressure, coating flow rate and coating viscosity;

[0047] In this embodiment, the core function of the data acquisition module is to monitor and collect various key data in the process of coating machine operation in real time, including position parameters fed back by multiple position sensors and a series of working parameters. In terms of position parameter collection, multiple position sensors are arranged at various key nodes of the coating machine, such as the discharge end, the starting and ending positions of the coating area, and specific positions where the risk of material deviation may occur. These sensors can accurately sense the position information of the coating material at each moment through photoelectric sensing, laser ranging or ultrasonic detection, and provide the system with intuitive data on whether the material deviates from the preset path. The working parameters include coating speed, coating tension, coating pressure, coating flow rate and coating viscosity, which reflect the operating status of the coating machine and the key elements of the coating process from different dimensions. Among them, the coating speed directly affects the distance the coating material moves per unit time. If the speed is too fast, the coating material is affected by inertia and is likely to deviate from the established position when turning or passing through complex structures, resulting in inaccurate coating position and uneven coating. If the speed is too slow, it will not only affect production efficiency, but may also cause the material to shift in position under the action of tension due to the long-term force in a single direction.

[0048] Coating tension is a key factor in maintaining the stable operation of coating materials. If the tension is too large, the material will be over-stretched, and when passing through the guide roller or coating head, it is easy to produce position deviation due to local uneven force; if the tension is too small, the material will be loose, and wrinkles and snake-like swings will easily occur during operation, causing the coating position to be out of control.

[0049] The coating pressure mainly affects the transfer and distribution of the coating on the substrate. When the coating pressure is uneven, the distribution of the coating on the substrate surface will be different, with more coating on one side and less on the other side. This uneven coating will cause different forces on both sides of the material, which will cause the coating material to shift in position during subsequent operation.

[0050] The coating flow determines the amount of coating applied to the substrate per unit time. If the coating flow is unstable, the coating thickness will vary at different locations in the coating area. The thicker coating area may cause local deformation of the material due to factors such as gravity and drying shrinkage, affecting the accuracy of the coating position.

[0051] The viscosity of the coating reflects the flow characteristics of the coating. If the viscosity is too high, the coating has poor fluidity and is difficult to spread evenly on the substrate. It is easy to accumulate locally, causing the coating material to change position due to uneven force during operation; if the viscosity is too low, the coating flows too fast on the substrate, making it difficult to control the coating range, which will also affect the accuracy of the coating position.

[0052] The deviation judgment module is used to obtain position characteristic values ​​of multiple position parameters and judge whether there is a deviation in the current position;

[0053] In traditional fault judgment algorithms, there may be a large number of complex conditional judgments and logical nesting. For example, when judging whether the material of a coating machine has deviated, it may be necessary to check the data of multiple sensors at different positions in turn, and the data of each sensor must be judged by multiple thresholds. There are complex logical relationships between these judgments, such as "and" and "or" relationships, which makes the entire judgment process cumbersome and time-consuming. These complex logics are sorted out and simplified, and multiple related conditional judgments are merged into a comprehensive judgment condition. For example, by analyzing historical data, the correlation between sensor data at different positions is found, and mathematical models are used to integrate multiple sensor data into a characteristic value. Only a single threshold judgment is required for this characteristic value to quickly determine whether the material has deviated, thereby reducing a large number of multiple threshold judgment steps and improving the judgment speed.

[0054] Furthermore, the acquisition of position characteristic values ​​of multiple position parameters and the determination of whether there is a deviation in the current position are specifically implemented by a principal component analysis method, including the following steps:

[0055] S1. Collect location parameter data samples of multiple location sensors in historical periods:

[0056] During the operation of the coating machine, sensors at different positions will continuously generate position parameter data. These data contain information about the coating machine at different times and positions, reflecting the position status of the material in the coating machine. The purpose of collecting data samples from historical periods is to fully understand the performance of the coating machine under various working conditions, including position information under normal operation, different coating speeds, different material types, different environmental conditions, etc. The number and diversity of these data samples are crucial for subsequent analysis because they constitute the basic data set for our understanding and analysis of the position status of the coating machine. For example, data from the past few months or even years can be collected, covering data from different shifts, different seasons, and different material batches. These data may be stored in a database, in the form of a time series, recording the position parameters of various position sensors (such as feed port, discharge port, near the coating head, sensors on the material conveying track, etc.) at different times. By analyzing these historical data, some potential rules and characteristics can be discovered, providing sufficient data support for subsequent principal component analysis.

[0057] S2. Reduce the dimensions of different position parameters through principal component analysis to obtain several principal components:

[0058] Principal component analysis (PCA) is a commonly used statistical method that can transform multiple related variables (here multiple position parameters) into a set of new unrelated variables, namely principal components. In the context of a coating machine, since there may be complex correlations between multiple position parameters, for example, changes in the feed port position may affect the discharge port position, the position parameters at different positions are not completely independent. The dimensionality reduction process of PCA linearly combines these position parameters and converts the original high-dimensional position parameter space into a low-dimensional principal component space. In this process, each principal component is a linear combination of the original position parameters and is sorted according to the size of the explained variance. The first principal component explains the largest variance and contains the most information in the original data, and the variance explained by subsequent principal components gradually decreases. In this way, the original multiple position parameters can be simplified to a few principal components while retaining most of the data information. For example, if there are 10 position parameters originally, after PCA processing, 3 principal components may be obtained. These 3 principal components can cover most of the information of the original 10 position parameters with fewer dimensions, making subsequent analysis and processing more concise and efficient. Such dimensionality reduction processing helps to remove redundant information in the data, highlight the main features of the data, and reduce the amount of calculation and complexity of analysis.

[0059] S3. Select the calculation formula of the first principal component to calculate the position eigenvalues ​​of multiple position parameters:

[0060] Among the several principal components obtained, the first principal component has a special status. Because it explains the largest proportion of variance in the original data, it is the most comprehensive variable that can represent the overall trend of changes in the original position parameters. It is a reasonable choice to select the first principal component as the position eigenvalue because it integrates the most important information in the original position parameters. It can be regarded as an indicator that can represent the overall position status of the coater. For example, if the value of the first principal component is large, it may mean that the position of the material in the coater has shifted significantly as a whole; if the value of the first principal component is close to zero, it may mean that the position of the material is relatively stable and close to the normal position. This position eigenvalue summarizes the information reflected by multiple position parameters in a concise way, providing a single quantitative indicator for subsequent deviation judgment.

[0061] S4. When the current position feature value exceeds the preset position feature value threshold, it is determined that the current position has a deviation:

[0062] In order to determine whether there is a deviation in the current position, a reference standard is required, which is the preset position characteristic value threshold. This threshold is set based on the analysis of historical data and the experience and understanding of the normal operation status of the coater. In normal operation, the first principal component as the position characteristic value should fluctuate within a relatively stable range, and the boundary of this range is the threshold. When the first principal component (i.e., the position characteristic value) calculated based on the current position parameters exceeds this threshold, it means that the current position state deviates from the normal range, and thus it is determined that there is a deviation. For example, if it is found based on historical data that the position characteristic value of the first principal component usually fluctuates between -2 and 2 under normal circumstances, then we can set the threshold to ±2.5. When the position characteristic value calculated at the current moment is 3, it can be determined that there is a deviation in the current position. This deviation may be caused by a variety of factors, such as wear of mechanical parts, unevenness of materials, sudden changes in coating speed, etc. Once it is determined that there is a deviation, the system can trigger subsequent deviation correction operations, such as adjusting the position of the guide roller, adjusting the tension, etc., to ensure the normal operation and coating quality of the coater.

[0063] The fault identification module is used to calculate the hash value of the working parameter through a hash function when there is a position deviation, and search the corresponding preset fault mode in the hash table;

[0064] In this embodiment, the fault identification module plays a key role in the automatic coating machine deviation correction control system, and is activated when the deviation judgment module determines that there is a position deviation. It takes the working parameters of the coating machine (such as coating speed, tension, pressure, coating flow and viscosity, etc.) and the position deviation characteristics when the deviation occurs as input, and calculates a hash value that can highly concentrate the current working state through a hash function, and the hash value is unique. When designing the system, engineers combine the working parameters corresponding to various possible fault modes based on a large amount of historical fault data and experience, and after the hash value is calculated by the hash function, it is stored in the hash table together with the corresponding fault mode information. After the fault identification module calculates the current hash value, it immediately searches for matching items in the hash table. Once found, it can quickly obtain the specific description of the preset fault mode, cause analysis and solution suggestions, etc., so as to quickly locate the fault and provide support for the subsequent effective corrective measures. This not only improves the efficiency of fault diagnosis, but also guarantees accuracy with the help of historical data and experience. With the accumulation of new fault data, the fault identification capability can be further improved.

[0065] Furthermore, during the operation of the automatic coating machine, when position deviation occurs, the fault modes found by the fault identification module include multiple types, and the following are the fault modes covered in this embodiment:

[0066] Guide rollers are worn or improperly installed: Guide rollers are responsible for guiding the direction of the coating material. After long-term use, the surface of the guide rollers may be worn, resulting in uneven friction between the guide rollers and the material, causing the material to deviate from the normal position during operation. In addition, if the guide rollers are not installed in the correct position, such as not being parallel to the center line of the coating machine, the material may also deviate. At this time, the fault is manifested as the material gradually deviating from the predetermined track after passing through the guide rollers, and the hash value calculated by the hash function will match the preset fault mode hash value of the position deviation caused by the guide roller problem.

[0067] Loose or faulty transmission parts: If the transmission system of the coating machine, such as belts, chains or gears, becomes loose, worn or damaged, it will lead to unstable power transmission and change the running speed and direction of the coating material. For example, a loose belt may cause slippage between the belt and the transmission wheel, making the running speed of the material at different positions inconsistent, which in turn causes position deviation. This type of fault will be reflected in the fault identification module with specific working parameter changes and position deviation characteristics, and the corresponding fault mode will be matched through hash function calculation.

[0068] Coating head blockage or uneven discharge: The coating head is responsible for applying the coating evenly to the surface of the material. When the coating head outlet is partially blocked, the coating will flow out unevenly, resulting in inconsistent coating thickness on the material, which will generate lateral force and cause the material to shift position. In this fault mode, in addition to position deviation, there will also be abnormal changes in coating flow and coating pressure. The fault identification module will match the corresponding fault mode through the hash function based on these comprehensive features.

[0069] The coating speed is too fast or unstable: When the coating speed is too fast, the inertial force on the material during the coating process increases, and it is easy to deviate from the predetermined path. Moreover, if the coating speed is unstable, it will cause the material to be subjected to different forces at different speed stages, resulting in position deviation. For example, during acceleration or deceleration, the material may deviate briefly. In this fault mode, the abnormal change in coating speed will become a key parameter for fault identification, and the hash function will be used to match it with the preset fault mode of position deviation caused by coating speed problems.

[0070] Abnormal coating tension: Too much or too little coating tension may cause position deviation. If the tension is too high, the material will be overstretched and easily deviate due to local uneven force when passing through certain parts; if the tension is too low, the material will be loose and prone to wrinkles and serpentine swings during operation, resulting in position loss. The fault identification module will use the hash function to determine the fault mode caused by abnormal coating tension based on the abnormal tension data collected by the tension sensor and the position deviation information.

[0071] Inappropriate coating viscosity: If the viscosity is too high, the coating has poor fluidity and is difficult to spread evenly on the substrate. It is easy to accumulate locally, causing the material to change position due to uneven force during operation; if the viscosity is too low, the coating will flow too fast on the substrate, making it difficult to control the coating range, which will also affect the accuracy of the coating position. The fault identification module will match the corresponding fault mode caused by the coating viscosity problem through the hash function based on the measured value of the coating viscosity and the position deviation.

[0072] Unstable paint flow: Unstable paint flow will lead to uneven coating thickness. The thicker coating area may cause local deformation of the material due to factors such as gravity and drying shrinkage, affecting the accuracy of the coating position. The fault identification module will identify the fault mode caused by unstable paint flow through the hash function based on the data of the paint flow sensor and the position deviation characteristics.

[0073] The fault prediction module uses a machine learning model to train the time mapping relationship between position feature values, working parameters and fault modes, and is used to predict the position deviation and fault mode of the next time period based on the current working parameters and position feature values ​​and perform correction control.

[0074] In this embodiment, the fault prediction module uses a machine learning model to explore the time mapping relationship between position characteristic values, working parameters and fault modes, so as to improve the fault prediction and response capabilities of the automatic coating machine. The module first collects a large amount of historical data, covering various working parameters, corresponding position characteristic values ​​and fault modes, and then uses a machine learning model to deeply mine and analyze these data. After repeated training, the model accurately grasps the influence of changes in working parameters on position characteristic values ​​and fault modes. During actual operation, the module predicts position deviations and possible fault modes based on the current working parameters collected in real time, with the help of a trained model, and then implements targeted correction control based on the prediction results, such as adjusting the position of the guide roller, changing the coating speed or adjusting the tension, etc., to avoid faults in advance and ensure stable operation of the coating machine. This not only achieves early warning of faults, but also makes intelligent decisions on correction measures, reduces dependence on manual experience, and significantly improves production efficiency and product quality.

[0075] Furthermore, the machine learning model includes the following construction steps:

[0076] T1. Collect the time series coating machine working data set with each complete coating process as the cycle in the historical period:

[0077] By collecting enough historical data, these data are divided according to each complete coating process. Each complete coating process contains key information of the coating machine from the beginning to the end of coating. The collected data covers the position characteristic values. The comprehensive position information calculated by the previously mentioned deviation judgment module using principal component analysis and other methods reflects the position status of the coating material in the coating machine; the working parameters include coating speed, coating tension, coating pressure, coating flow and coating viscosity, etc., which together describe the working status of the coating machine; the fault mode is a record of whether a fault occurred during the coating process and the specific type of fault, which may be a mechanical fault, process parameter fault, etc.

[0078] T2. Establish a time series model for synchronizing working parameters and position characteristic values ​​during each complete coating process:

[0079] For each complete coating process, the working parameters and position characteristic values ​​are considered as a data series that changes over time. For example, in a coating process, the coating speed may be adjusted over time, and the position characteristic values ​​will also change accordingly. These changes follow a certain time series pattern.

[0080] Common time series models, such as ARIMA and SARIMA, can be used to model the working parameters and position characteristic values. By establishing a time series model, it is possible to capture the dynamic change trend of these parameters within a coating cycle, as well as their mutual relationship and time dependency. The time model can help understand how the adjustment of working parameters affects the position characteristic values, their temporal sequence and the delayed effect of their mutual influence, and provide more detailed information for subsequent fault prediction.

[0081] Furthermore, the time series model includes the following construction steps:

[0082] T21. Data preprocessing: For the time series coating machine working data collected in cycles of each complete coating process, first carefully check and eliminate the noise and outliers caused by sensor failure, data transmission errors, etc., and use appropriate interpolation methods to fill in the missing data to ensure data integrity. In view of the different dimensions and value ranges of working parameters and position feature values, Z-score standardization or minimum-maximum normalization method is used to make the data on the same scale to ensure that the weight of each feature is reasonable in subsequent analysis, laying a good foundation for building the ARMA model.

[0083] T22. Feature Engineering: Deeply explore the time characteristics in time series data, extract periodic information such as seconds, minutes, and hours, as well as trend features such as moving average and difference that can reflect the long-term trend and short-term fluctuations of the data. At the same time, combine the working parameters and position characteristic values, such as generating new features such as products and ratios, or implementing transformations such as squares and square roots, deeply explore the potential nonlinear relationship between features, enrich the data feature dimensions, and help the ARMA model better capture data patterns. In view of the characteristics of the coating machine working data, after comprehensive consideration, the ARMA model is more suitable. It can effectively handle data that has both autocorrelation and interference from random factors. Combined with evaluation indicators such as mean square error and mean absolute error, this model will be used in the future to deeply analyze the dynamic changes and mutual connections between working parameters and position characteristic values ​​in time series.

[0084] T23, ARMA model training and tuning: The preprocessed and feature-engineered data is divided into training and test sets in chronological order with an appropriate ratio (e.g., 80:20). The ARMA model is trained using the training set, and loss functions such as AIC or BIC are minimized by continuously adjusting the autoregressive order p and the moving average order q, so that the model can accurately learn the time series relationship between the working parameters and the positional eigenvalues. At the same time, cross-validation and other strategies are used to fine-tune hyperparameters such as p and q to improve the model's predictive performance and generalization ability.

[0085] T24, Model evaluation and validation: Use the test set data to evaluate the trained ARMA model, measure the deviation between the predicted value and the actual value based on indicators such as mean square error and mean absolute error, and judge the model performance. If it does not meet expectations, it is necessary to return to adjust the model order, feature engineering methods, etc. In addition, cross-validation is used to ensure the stability and reliability of the model, avoid overfitting, and ensure that the model can accurately predict the working status of the coating machine in actual applications.

[0086] Furthermore, predicting the position deviation and failure mode of the next time period according to the current working parameters and position characteristic values ​​and performing correction control includes the following steps:

[0087] E1. Obtain the working parameters and position characteristic values ​​of the current time series, input them into the time series model, and predict the working parameters and position characteristic values ​​of the next time period;

[0088] E2. Based on the position feature value of the next time period, predict whether there will be position deviation in the next time period;

[0089] E3. When it is predicted that there will be a position deviation in the next time period, the hash value of the working parameters of the next time period is calculated, and the failure mode of the next time period is predicted by searching the hash table;

[0090] E4. According to the predicted failure mode in the next time period, the working parameters and the position of the coating machine are adjusted and corrected.

[0091] Furthermore, in step E3, the failure mode of the next time period is predicted, and the working parameters and position characteristic values ​​are used as explanatory variables, and the correction plan corresponding to the failure mode is used as the response variable. A random forest model is trained to output the correction plan for the next time period based on the working parameters and position characteristic values ​​of the next time period.

[0092] The random forest model is trained by taking the working parameters and position characteristic values ​​as explanatory variables and the correction plan corresponding to the fault mode as the response variable, so as to output an accurate correction plan based on the working parameters and position characteristic values ​​of the next time period.

[0093] First, collect a large amount of historical data, which covers the working parameters of the coating machine under various working conditions, such as coating speed, tension, pressure, coating flow and viscosity, as well as position characteristic values. At the same time, record each failure mode and its corresponding correction plan in detail. For example, when the material position is offset and wrinkle failure occurs due to excessive coating speed and abnormal tension, the correction plan is to reduce the coating speed, fine-tune the tension system, and adjust the position of the guide roller. These data are the cornerstone of the training model. Random forest, as a powerful ensemble learning algorithm, consists of many decision trees. During training, each decision tree randomly selects some samples and features for learning, effectively avoiding overfitting, so that each decision tree can mine data rules from different dimensions. In this scenario, the working parameters and position characteristic values ​​are used as input, and the model will learn the complex relationship between them and the corresponding fault mode correction plan. For example, when a specific set of working parameters and position characteristic values ​​are input, the model will judge the possible fault mode based on past learning experience and give the corresponding correction plan. After the training is completed, facing the working parameters and position characteristic values ​​of the next time period, the model can quickly output targeted correction plans, prevent failures in advance, reduce downtime and production losses, help the coating machine operate stably and efficiently, and provide operators with a scientific decision-making basis.

[0094] Furthermore, the random forest model includes the following construction steps:

[0095] P1. Feature selection and processing: Taking working parameters and position eigenvalues ​​as explanatory variables, they need to be processed. The first is feature selection. Not all working parameters have the same important impact on failure modes and correction schemes. Some parameters may be redundant or have low correlation. Excluding them can make the model more focused on key information and improve training efficiency. At the same time, since the value ranges of different working parameters and position eigenvalues ​​may vary greatly, normalization or standardization is required. Taking coating speed and paint viscosity as examples, if they are not processed, their different magnitudes will make the model more inclined to focus on features with large values ​​during training, and ignore features with small values, resulting in deviations in model training. By converting them to the same dimensional range, such as normalizing them to [0,1], the model can consider the impact of each feature equally and learn the relationship between them and the correction scheme more accurately.

[0096] P2. Random forest model training: The random forest model is a powerful ensemble learning algorithm, the core of which is that multiple decision trees make decisions together. Each decision tree randomly extracts samples and features from the training data for training, so that different decision trees can learn the characteristics of the data from different perspectives. Each decision tree will find different decision paths according to the different values ​​of the input working parameters and position feature values, and finally form a judgment on the correction scheme. For example, a decision tree may find that when the coating speed is high and the position feature value deviates from a certain range, it means that the material moves too fast and the position deviates. At this time, it is necessary to take correction measures such as reducing the speed and adjusting the position of the guide roller; while another decision tree may find from the combined characteristics of the coating viscosity and coating tension that the material may have position deviation and uneven coating due to high viscosity and low tension, thereby deriving a correction scheme of adding diluent and adjusting tension. The comprehensive decision of many decision trees enables the model to learn very complex mapping relationships, avoids the one-sidedness that may occur in a single decision tree, and improves the robustness and generalization ability of the model.

[0097] P3. Hyperparameter adjustment: Hyperparameters play an important regulatory role in the random forest model, and they determine the structure and performance of the model. Hyperparameters such as the number of decision trees, the maximum depth of each tree, and the minimum number of samples required for node splitting all need to be carefully adjusted. Through cross-validation, we can try different hyperparameter combinations, divide the data into multiple parts, one for training and one for validation, and compare the performance of the model on the validation set under different hyperparameter combinations. For example, the adjustment of the number of decision trees, too few decision trees may lead to insufficient learning ability of the model, and too many decision trees may lead to overfitting, making the model too dependent on training data and lose the ability to generalize to new data. Through continuous attempts, find a suitable hyperparameter combination so that the model has a good learning effect on the training set, while maintaining good performance on the validation set, ensuring that the model can accurately predict the correction plan in practical applications.

[0098] P4. Model evaluation and application: Use an independent test set to evaluate the trained model. For classified correction schemes, use indicators such as accuracy, recall, and F1 score. They can measure whether the correction scheme predicted by the model is accurate and whether it can cover various possible situations. For regression-type correction schemes (if the correction scheme includes continuous numerical adjustments), use indicators such as mean square error and mean absolute error to evaluate the deviation between the correction scheme predicted by the model and the actual situation. When the evaluation results show that the model performs well, it can be applied to actual operations. When the working parameters and position characteristic values ​​of the next time period are input, the model can output a specific correction scheme based on the existing learning results, such as giving detailed operational suggestions such as "increasing coating pressure, adjusting the guide roller angle", etc., to provide timely and effective decision-making support for the stable operation of the coating machine.

[0099] Furthermore, the evaluation index is calculated as follows:

[0100]

[0101] In the formula, ACC represents accuracy; PPV represents precision; TRP represents recall; F1 represents F1 value; TP represents true positive examples; TN represents true negative examples; FP represents false positive examples; and FN represents false negative examples.

[0102] The above description is only a preferred embodiment of the present invention and does not limit the present invention in any form. Although the present invention has been disclosed as a preferred embodiment as above, it is not used to limit the present invention. Any technical personnel in this field can make some changes or modify the technical contents disclosed above into equivalent embodiments without departing from the scope of the technical solution of the present invention. However, any brief modifications, equivalent changes and modifications made to the above embodiments based on the technical essence of the present invention without departing from the content of the technical solution of the present invention are still within the scope of the technical solution of the present invention.

Claims

1. An automatic coating machine deviation correction control system, characterized in that: It includes a data acquisition module, a deviation judgment module, a fault identification module and a fault prediction module; the data acquisition module, the deviation judgment module, the fault identification module and the fault prediction module are communicatively connected, wherein: The data acquisition module is used to monitor and collect position parameters and working parameters of multiple position sensors of the coating machine in real time; The deviation judgment module is used to obtain position characteristic values ​​of multiple position parameters and judge whether there is a deviation in the current position; The fault identification module is used to calculate the hash value of the working parameter through a hash function when there is a position deviation, and search the corresponding preset fault mode in the hash table; The fault prediction module uses a machine learning model to train the time mapping relationship between position feature values, working parameters and fault modes, and is used to predict the position deviation and fault mode of the next time period based on the current working parameters and position feature values ​​and perform correction control.

2. The automatic coating machine deviation correction control system according to claim 1 is characterized in that: The working parameters include coating speed, coating tension, coating pressure, coating flow rate and coating viscosity.

3. The automatic coating machine deviation correction control system according to claim 1 is characterized in that: The obtaining of position characteristic values ​​of multiple position parameters and judging whether there is a deviation in the current position is specifically implemented by using a principal component analysis method, and includes the following steps: S1. Collect location parameter data samples of multiple location sensors in historical periods; S2. Reduce the dimensions of different position parameters through principal component analysis to obtain several principal components; S3, selecting a calculation formula for the first principal component to calculate positional eigenvalues ​​of multiple positional parameters; S4. When the current position feature value exceeds a preset position feature value threshold, it is determined that there is a deviation in the current position.

4. The automatic coating machine deviation correction control system according to claim 1 is characterized in that: The failure modes include guide roller wear or improper installation, loose or faulty transmission parts, blocked or uneven discharge of coating heads, excessive or unstable coating speed, abnormal coating tension, inappropriate coating viscosity and unstable coating flow.

5. The automatic coating machine deviation correction control system according to claim 1 is characterized in that: The machine learning model includes the following construction steps: T1. Collect the time series coating machine working data set with each complete coating process as the cycle in the historical period; T2. Establish a time series model for synchronizing working parameters and position characteristic values ​​during each complete coating process.

6. The automatic coating machine deviation correction control system according to claim 5, characterized in that: The time series model includes the following construction steps: T21. Data preprocessing: Remove noise and outliers from the collected time series coating machine working data, and standardize the data using the Z-score standardization method; T22. Feature Engineering: Mining the time characteristics in time series data, combining working parameters with position feature values, and mining potential nonlinear relationships between features; T23, ARMA model training and tuning: The preprocessed and feature-engineered data is divided into training sets and test sets in a specific ratio in chronological order, and the ARMA model is trained using the training set. The loss function is minimized by continuously adjusting the autoregressive order p and the moving average order q, so that the model can accurately learn the time series relationship between the working parameters and the position eigenvalues; the cross-validation method is used to optimize the autoregressive order p and the moving average order q; T24. Model evaluation and verification: Use the test set data to evaluate the trained ARMA model, use the mean square error and mean absolute error to measure the deviation between the predicted value and the actual value, and judge the model performance; if it does not meet expectations, return to adjust the feature engineering, autoregressive order p and moving average order q.

7. The automatic coating machine deviation correction control system according to claim 1 is characterized by: The method of predicting the position deviation and failure mode of the next time period and performing correction control according to the current working parameters and position characteristic values ​​includes the following steps: E1. Obtain the working parameters and position characteristic values ​​of the current time series, input them into the time series model, and predict the working parameters and position characteristic values ​​of the next time period; E2. Based on the position feature value of the next time period, predict whether there will be position deviation in the next time period; E3. When it is predicted that there will be a position deviation in the next time period, the hash value of the working parameters of the next time period is calculated, and the failure mode of the next time period is predicted by searching the hash table; E4. According to the predicted failure mode in the next time period, the working parameters and the position of the coating machine are adjusted and corrected.

8. The automatic coating machine deviation correction control system according to claim 7, characterized in that: In step E3, the failure mode of the next time period is predicted, and the working parameters and position characteristic values ​​are used as explanatory variables, and the correction plan corresponding to the failure mode is used as the response variable. A random forest model is trained to output the correction plan for the next time period based on the working parameters and position characteristic values ​​of the next time period.

9. The automatic coating machine deviation correction control system according to claim 8, characterized in that: The random forest model includes the following construction steps: P1. Feature selection and processing: Select the working parameters and position characteristic values ​​related to the correction scheme labels in the historical period as features; P2, Random Forest Model Training: Establish multiple decision trees between working parameters and position feature values ​​and correction schemes. Each decision tree randomly extracts samples and features from the training data for training; P3, Hyperparameter adjustment: adjust the number of decision trees, maximum depth, minimum number of samples required for node splitting, and optimize the random forest model through cross-validation; P4. Model evaluation and application: Use an independent test set to evaluate the trained model, using accuracy, recall, and F1 score as evaluation indicators.

Images