Car tire building drum error analysis method and system

Abstract

The invention discloses a car tire building drum error analysis method and system, and relates to the technical field of data processing, and the method comprises the steps: collecting technological parameter data in a tire building process in real time through a plurality of sensor combinations, and carrying out the preprocessing of the collected data; based on the preprocessed data, characteristic parameters corresponding to the tire building drum error are extracted through a signal processing technology; based on the extracted characteristic parameters, using a data mining technology and a machine learning algorithm to analyze a relationship between each process parameter and a geometric error of the forming drum, constructing an error analysis model, using the error analysis model to carry out error prediction, feeding back a prediction result to production equipment in real time, and adjusting the corresponding process parameters; the car tire building drum error analysis system comprises a data acquisition module, a data transmission module and an algorithm module. An efficient, intelligent and accurate solution is provided for tire building drum error analysis, and intelligent and lean production development of the tire manufacturing industry is promoted.

Description

Technical Field

[0001] The invention relates to the technical field of data processing, and in particular to a method and system for analyzing errors in a passenger car tire building drum. Background Art

[0002] The passenger car tire building drum is a key equipment in the process of producing passenger car tires. Its main function is to press the rubber material into the basic shape of the tire through a high temperature and high pressure molding process. The geometric error of the building drum directly affects the shape accuracy, appearance quality and performance of the tire, which in turn has an important impact on the service life, safety and comfort of the tire. The existing tire building drum geometric error detection method mainly relies on manual measurement and empirical judgment, and usually requires multiple manual inspections and corrections after each production. Such methods are not only cumbersome and inefficient, but also the measurement accuracy is easily affected by human factors, making it difficult to achieve high-precision and high-efficiency building drum error analysis. As the manufacturing industry has higher and higher requirements for production accuracy and efficiency, traditional detection methods can no longer meet modern production needs. Therefore, there is an urgent need for a new, more accurate and intelligent tire building drum error analysis method. Summary of the invention

[0003] In view of the above existing problems, the present invention is proposed.

[0004] Therefore, the present invention provides a method for analyzing the error of a car tire building drum, the purpose of which is to solve several key problems existing in the existing methods for analyzing the error of a car tire building drum. First, the existing methods rely on manual measurement, which is inefficient and has limited accuracy, and manual intervention is easily affected by the skill level of the operator; secondly, the traditional method is difficult to analyze and predict the geometric error of the building drum in real time and systematically during the production process, and the production parameters cannot be adjusted in time, resulting in fluctuations in production quality; furthermore, the error of the building drum is affected by multiple process parameters (such as pressure, temperature, vibration, etc.) and environmental factors, and the existing technology often cannot fully consider the complex interaction of these factors. Therefore, the present invention proposes a data-driven error analysis method, which adopts a variety of advanced signal processing technologies, data mining technologies and machine learning algorithms, can comprehensively and accurately analyze and predict the geometric error of the building drum, identify the key process parameters that affect the error, and realize real-time monitoring and dynamic optimization through intelligent means.

[0005] In order to solve the above technical problems, the present invention provides the following technical solutions, a method for analyzing the error of a car tire building drum, comprising: The process parameter data of the tire forming process is collected in real time through a combination of multiple sensors, and the collected data is preprocessed, including removing abnormal data caused by equipment failure or environmental interference, time series alignment and standardization processing; Based on the preprocessed data, the characteristic parameters corresponding to the tire building drum error are extracted through signal processing technology; Based on the extracted characteristic parameters, data mining technology and machine learning algorithms are used to analyze the relationship between each process parameter and the geometric error of the forming drum, and an error analysis model is constructed. At the same time, the error analysis model is used to predict the error, and the prediction results are fed back to the production equipment in real time to adjust the corresponding process parameters.

[0006] As a preferred solution of the passenger car tire building drum error analysis method described in the present invention, the sensors include a temperature sensor, a pressure sensor, a displacement sensor, an acceleration sensor and a vibration sensor.

[0007] As a preferred solution of the passenger car tire building drum error analysis method described in the present invention, the preprocessing includes using low-pass filtering and Kalman filtering to remove noise data caused by environmental changes or equipment fluctuations, and performing time-series alignment on the collected data, and finally performing data standardization processing.

[0008] As a preferred solution of the passenger car tire building drum error analysis method described in the present invention, the corresponding characteristic parameters include mold deviation, pressure fluctuation, building speed, mold surface temperature distribution, and building machine vibration frequency.

[0009] As a preferred solution of the error analysis method for a passenger car tire building drum of the present invention, the extracting characteristic parameters corresponding to the error of the tire building drum includes: performing frequency domain analysis on the signal by fast Fourier transform FFT and wavelet transform, extracting the frequency characteristics corresponding to the process change and the error, and identifying them, and using variable scale wavelet transform VSWT to replace the traditional wavelet transform; The different frequency components in the signal are extracted through multi-level wavelet transform, and the wavelet transform results of each scale are used for weighted fusion to obtain multi-level features: ; in, Represents the feature extraction results after multi-level wavelet transform, different scale factors and translation factor Capture the characteristics of different frequency bands of signals; Represents the weight coefficient, which controls the contribution of each scale's wavelet transform to the final result; represents the original input signal; Indicates the number of decomposition layers, indicating that the signal is analyzed at multiple levels at different scales. Indicates The scale factor of the layer small table transformation, Indicates The translation factor of the layer small table transformation; Calculate the comprehensive influence of each process parameter on the error of the building drum: ; in, Represents the final error value, that is, the error predicted by the process parameters; Represents the first Process parameters Frequency domain characteristics of Indicates The characteristics of the process parameters in the frequency domain; The weighting coefficients associated with each frequency component; Represents the first The frequency content of each process parameter; represents the total number of process parameters, and They represent weighting coefficients respectively; Combine the training data and covariance matrix for optimization and output the error prediction value: ; in, Represents the error value predicted by the Gaussian process regression model; Represents the input feature matrix and The covariance matrix between ; Represents the variance of the noise, which is used to represent the random errors in the observed data; Represents the identity matrix, which is used to balance the relationship between noise and features; Represents the target value in the training data, that is, the known error data.

[0010] As a preferred solution of the error analysis method for a passenger car tire building drum of the present invention, the error analysis model is constructed by clustering feature parameters using a K-means algorithm to identify the potential relationship between different features and the geometric error of the building drum, and obtaining the best cluster division by minimizing the sum of the squares of the distances from each data point to the cluster center, as follows: ; in, express Cluster centers; Indicates The feature data vector of samples; Indicates The center of the cluster; Represents the indicator function. If the sample Assigned to cluster ,but , otherwise 0; Representation sample With cluster center The squared Euclidean distance between .

[0011] As a preferred embodiment of the error analysis method for a passenger car tire building drum of the present invention, the error analysis model further comprises: using cross validation to evaluate the training process, dividing the data set into Subsets are trained and validated multiple times, as follows: ; in, Represents the result of cross-validation, which is the average loss of model performance. In each validation process, select The subset is used as the training set, and the remaining subset is used as the validation set. Indicated in A compromise loss function.

[0012] As a preferred solution of the passenger car tire building drum error analysis system described in the present invention, it includes: a data acquisition module, a data transmission module and an algorithm module; the data acquisition module is used to collect data information; the data transmission module is used to transmit data information; the algorithm module is used to carry the required algorithm.

[0013] Beneficial effects of the present invention: The present invention uses a data-driven analysis method, wavelet transform, fast Fourier transform and other advanced signal processing technologies, can extract characteristic parameters related to the geometric error of the building drum from the multi-dimensional data collected during the production process, and build an error prediction model based on a machine learning algorithm, thereby realizing accurate analysis and prediction of the geometric error of the building drum. At the same time, through the joint analysis of multi-dimensional process parameters, the present invention can effectively identify and quantify the source and law of the error, reduce the interference of human errors, and improve the accuracy of the prediction. In addition, the present invention is combined with a cloud computing platform to support real-time data acquisition, storage and analysis, can monitor the geometric error of the building drum in real time during the production process, and provide optimization suggestions through an intelligent analysis system to help the production line adjust the process parameters, significantly improve production efficiency, reduce scrap rate, and ensure the stability and consistency of tire quality. Overall, the present invention provides an efficient, intelligent and accurate solution for tire building drum error analysis, which promotes the development of intelligent and lean production in the tire manufacturing industry. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative work.

[0015] Figure 1 A schematic flow chart of a method for analyzing a passenger car tire building drum error is provided as an embodiment of the present invention. DETAILED DESCRIPTION

[0016] In order to make the above-mentioned purposes, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the drawings of the specification. Obviously, the described embodiments are part of the embodiments of the present invention, but not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary persons in the art without creative work should fall within the scope of protection of the present invention.

[0017] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention may also be implemented in other ways different from those described herein, and those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0018] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The term "in one embodiment" that appears in different places in this specification does not necessarily refer to the same embodiment, nor does it refer to a separate or selective embodiment that is mutually exclusive with other embodiments.

[0019] The present invention is described in detail with reference to schematic diagrams. When describing the embodiments of the present invention, for the sake of convenience, the cross-sectional diagrams showing the device structure will not be partially enlarged according to the general scale, and the schematic diagrams are only examples, which should not limit the scope of protection of the present invention. In addition, in actual production, the three-dimensional dimensions of length, width and depth should be included.

[0020] At the same time, in the description of the present invention, it should be noted that the directions or positional relationships indicated by the terms "upper, lower, inner and outer" are based on the directions or positional relationships shown in the drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific direction, be constructed and operated in a specific direction, and therefore cannot be understood as limiting the present invention. In addition, the terms "first, second or third" are only used for descriptive purposes and cannot be understood as indicating or implying relative importance.

[0021] In the present invention, unless otherwise clearly specified and limited, the terms "install, connect, connect" should be understood in a broad sense, for example: it can be a fixed connection, a detachable connection or an integral connection; it can also be a mechanical connection, an electrical connection or a direct connection, or it can be indirectly connected through an intermediate medium, or it can be the internal communication of two components. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0022] Example 1, reference Figure 1 , which is the first embodiment of the present invention, provides a method for analyzing errors of a passenger car tire building drum, comprising: S1: Real-time collection of process parameter data during tire forming by a combination of multiple sensors, and pre-processing of the collected data, including removal of abnormal data caused by equipment failure or environmental interference, time series alignment and standardization; S2: Based on the preprocessed data, the characteristic parameters corresponding to the tire building drum error are extracted through signal processing technology; S3: Based on the extracted characteristic parameters, data mining technology and machine learning algorithms are used to analyze the relationship between each process parameter and the geometric error of the forming drum, and an error analysis model is constructed. At the same time, the error analysis model is used to predict the error, and the prediction results are fed back to the production equipment in real time to adjust the corresponding process parameters.

[0023] The process parameter data collected during the tire molding process include mold temperature, pressure, molding machine speed, tire material properties, and ambient temperature; the sensors include temperature sensors, pressure sensors, displacement sensors, acceleration sensors, and vibration sensors.

[0024] The preprocessing includes using low-pass filtering and Kalman filtering to remove noise data caused by environmental changes or equipment fluctuations, wherein the low-pass filter is used to remove high-frequency noise and retain low-frequency signals, and is suitable for parameters such as temperature and pressure; the Kalman filter is used to deal with situations with large noise and complex signals, such as vibration sensor data, and optimizes data quality by recursively estimating multi-dimensional noise signals; secondly, the data collected under different time periods or process conditions are time-series aligned to ensure the consistency of time series from different data sources. This operation includes unifying timestamps and filling in missing data through interpolation methods when necessary to ensure the alignment of time series data; finally, data standardization is performed to convert data of different dimensions into unified standard units to avoid the impact of dimensional differences on subsequent analysis and ensure the comparability of various types of data.

[0025] The corresponding characteristic parameters include mold deviation, pressure fluctuation, molding speed, mold surface temperature distribution, and molding machine vibration frequency.

[0026] The extraction of characteristic parameters corresponding to the tire building drum error includes performing frequency domain analysis on the signal through fast Fourier transform FFT and wavelet transform, extracting the frequency characteristics corresponding to the process change and the error, and identifying them. At the same time, in order to better process nonlinear and non-stationary signals, variable scale wavelet transform VSWT is used to replace the traditional wavelet transform, as follows: ; in, represents the output of the scaled wavelet transform, is the scale factor, is the translation factor; represents the input signal; represents the variable scale wavelet function; The different frequency components in the signal are extracted through multi-level wavelet transform, and the wavelet transform results of each scale are used for weighted fusion to obtain multi-level features: ; in, Represents the feature extraction results after multi-level wavelet transform, different scale factors and translation factor Capture the characteristics of different frequency bands of signals; Represents the weight coefficient, which controls the contribution of each scale's wavelet transform to the final result; represents the original input signal; Indicates the number of decomposition layers, indicating that the signal is analyzed at multiple levels at different scales. Indicates The scale factor of the layer small table transformation, Indicates The translation factor of the layer small table transformation; Calculate the comprehensive influence of each process parameter on the error of the building drum: ; in, Represents the final error value, that is, the error predicted by the process parameters; Represents the first Process parameters Frequency domain characteristics of Indicates The characteristics of the process parameters in the frequency domain; The weighting coefficients associated with each frequency component; Represents the first The frequency content of each process parameter; represents the total number of process parameters, and They represent weighting coefficients respectively; Combine the training data and covariance matrix for optimization and output the error prediction value: ; in, Represents the error value predicted by the Gaussian process regression model; Represents the input feature matrix and The covariance matrix between ; Represents the variance of the noise, which is used to represent the random errors in the observed data; Represents the identity matrix, which is used to balance the relationship between noise and features; Represents the target value in the training data, that is, the known error data.

[0027] The error analysis model is constructed by clustering feature parameters using the K-means algorithm, identifying the potential relationship between different features and the geometric error of the forming drum, and obtaining the best cluster division by minimizing the sum of the squares of the distances from each data point to the cluster center, as follows: ; in, express Cluster centers; Indicates The feature data vector of samples; Indicates The center of the cluster; Represents the indicator function. If the sample Assigned to cluster ,but , otherwise 0; Representation sample With cluster center The squared Euclidean distance between The Apriori algorithm is used to find frequently occurring item sets and generate association rules for predicting the geometric error of the building drum: ; in, Represents association rules The confidence level, that is, given In case of occurrence Probability of occurrence; Indicates an event and events Probability of simultaneous occurrence; Indicates an event Probability of occurrence; Use support vector machine SVM to establish error analysis model: ; in, Represents the prediction result, that is, based on the input features The predicted value of the geometric error of the building drum is obtained; Represents the feature vector With the weight vector The inner product of represents the bias term; If the random forest algorithm is used to further optimize the error prediction, then: ; in, represents the output of random forest, i.e., the final prediction value of the geometric error of the building drum; Represents the number of decision trees in the random forest; Indicates The prediction results of decision trees, each tree based on the input features Output a predicted value; Represents the average of all decision tree prediction results; If a deep neural network DNN is used to automatically learn features through a multi-layer neural network to further optimize error prediction, then: ; in, represents the output of the deep neural network, i.e., the final prediction value of the geometric error of the building drum; Represents the weight matrix of each layer of the neural network, controlling the input features of different layers transformation; Represents the bias term of each layer of the neural network; represents the activation function; Represents the number of layers of the neural network.

[0028] The error analysis model also includes using cross validation to evaluate the training process and dividing the data set into Subsets are trained and validated multiple times, as follows: ; in, Represents the result of cross-validation, usually the average loss of model performance. In each validation process, select The subset is used as the training set, and the remaining subset is used as the validation set. Indicated in A compromise loss function.

[0029] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

[0030] Embodiment 2 is another embodiment of the present invention, which provides a passenger car tire forming drum error analysis system, including: a data acquisition module, a data transmission module and an algorithm module; the data acquisition module is used to collect data information; the data transmission module is used to transmit data information; the algorithm module is used to carry the required algorithm.

[0031] Embodiment 3, the third embodiment of the present invention, is different from the first two embodiments in that: If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions to enable a computer device (which can be a personal computer, server, or network device, etc.) to perform all or part of the steps of the methods described in various embodiments of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc., which can store program codes.

[0032] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0033] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0034] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0035] Although the preferred embodiments of the present application have been described, those skilled in the art may make other changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications falling within the scope of the present application.

[0036] Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the spirit and scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the claims of the present application and their equivalents, the present application is also intended to include these modifications and variations.

Claims

1. A method for analyzing the error of a passenger car tire building drum, characterized in that: include: The process parameter data of the tire forming process is collected in real time through a combination of multiple sensors, and the collected data is preprocessed, including removing abnormal data caused by equipment failure or environmental interference, time series alignment and standardization processing; Based on the preprocessed data, the characteristic parameters corresponding to the tire building drum error are extracted through signal processing technology; Based on the extracted characteristic parameters, data mining technology and machine learning algorithms are used to analyze the relationship between each process parameter and the geometric error of the forming drum, and an error analysis model is constructed. At the same time, the error analysis model is used to predict the error, and the prediction results are fed back to the production equipment in real time to adjust the corresponding process parameters.

2. The passenger car tire building drum error analysis method according to claim 1, characterized in that: The sensors include temperature sensors, pressure sensors, displacement sensors, acceleration sensors and vibration sensors.

3. The passenger car tire building drum error analysis method according to claim 2, characterized in that: The preprocessing includes using low-pass filtering and Kalman filtering to remove noise data caused by environmental changes or equipment fluctuations, performing time-series alignment on the collected data, and finally performing data standardization processing.

4. The passenger car tire building drum error analysis method according to claim 3, characterized in that: The corresponding characteristic parameters include mold deviation, pressure fluctuation, molding speed, mold surface temperature distribution and molding machine vibration frequency.

5. The passenger car tire building drum error analysis method according to claim 4, characterized in that: The extracting of characteristic parameters corresponding to the tire building drum error includes performing frequency domain analysis on the signal through fast Fourier transform FFT and wavelet transform, extracting frequency characteristics corresponding to the process change and the error, identifying them, and using variable scale wavelet transform VSWT to replace the traditional wavelet transform; The different frequency components in the signal are extracted through multi-level wavelet transform, and the wavelet transform results of each scale are used for weighted fusion to obtain multi-level features: ； in, Represents the feature extraction results after multi-level wavelet transform, different scale factors and translation factor Capture the characteristics of different frequency bands of signals; Represents the weight coefficient, which controls the contribution of each scale's wavelet transform to the final result; represents the original input signal; Indicates the number of decomposition layers, indicating that the signal is analyzed at multiple levels at different scales. Indicates The scale factor of the layer small table transformation, Indicates The translation factor of the layer small table transformation; Calculate the comprehensive influence of each process parameter on the error of the building drum: ； in, Represents the final error value, that is, the error predicted by the process parameters; Represents the first Process parameters Frequency domain characteristics of Indicates The characteristics of the process parameters in the frequency domain; The weighting coefficients associated with each frequency component; Represents the first The frequency content of the process parameters; represents the total number of process parameters, and They represent weighting coefficients respectively; Combine the training data and covariance matrix for optimization and output the error prediction value: ； in, Represents the error value predicted by the Gaussian process regression model; Represents the input feature matrix and The covariance matrix between ; Represents the variance of the noise, which is used to represent the random errors in the observed data; Represents the identity matrix, which is used to balance the relationship between noise and features; Represents the target value in the training data, that is, the known error data.

6. The method for analyzing the error of a passenger car tire building drum according to claim 5, characterized in that: The error analysis model is constructed by clustering feature parameters using the K-means algorithm, identifying the potential relationship between different features and the geometric error of the forming drum, and obtaining the best cluster division by minimizing the sum of the squares of the distances from each data point to the cluster center, as follows: ； in, express Cluster centers; Indicates The feature data vector of samples; Indicates The center of the cluster; Represents the indicator function. If the sample Assigned to cluster ,but , otherwise 0; Representation sample With cluster center The squared Euclidean distance between .

7. The passenger car tire building drum error analysis method according to claim 6, characterized in that: The error analysis model also includes using cross validation to evaluate the training process and dividing the data set into Subsets are trained and validated multiple times, as follows: ； in, Represents the result of cross-validation, which is the average loss of model performance. In each validation process, select The subset is used as the training set, and the remaining subset is used as the validation set. Indicated in A compromise loss function.

8. A passenger car tire building drum error analysis system, based on the passenger car tire building drum error analysis method according to any one of claims 1 to 7, characterized in that: Including data acquisition module, data transmission module and algorithm module; The data acquisition module is used to collect data information; The data transmission module is used to transmit data information; The algorithm module is used to carry the required algorithm.

Images