12-axis PCB drilling machine production data acquisition and quality management system

Abstract

The invention relates to the technical field of data management of intelligent manufacturing, and particularly discloses a 12-shaft PCB drilling machine production data acquisition and quality management system, which is characterized in that high-speed sensors are mounted on shafts of a drilling machine to acquire speed and pressure data in a drilling process in real time; a speed change rate characteristic value and a pressure stability characteristic value are extracted by adopting a method of combining differential speed analysis with Haar wavelet transform, zero-sequence pressure processing and principal component analysis, the two types of characteristic values are fused into a drilling quality characteristic vector, the drilling quality characteristic vector is input into a quality analysis model based on gradient boosting tree training, and the drilling quality is obtained. Intelligent evaluation and prediction of the drilling quality are realized, when quality abnormity is detected, the system automatically generates early warning information, and operation parameters of the drilling machine are dynamically adjusted in combination with a PID control algorithm, so that a closed-loop quality control mechanism is formed.

Description

Technical Field

[0001] The present invention relates to the technical field of data management in intelligent manufacturing, and particularly to a production data acquisition and quality management system for a 12-axis PCB drilling machine. Background Art

[0002] With the rapid development of electronic information technology, as the core component of various electronic devices, the manufacturing precision and product quality requirements of printed circuit boards (PCBs) are increasing day by day. In the PCB manufacturing process, the drilling process is a key link determining the line connection precision and subsequent assembly quality. Due to its characteristics of high efficiency and multi-hole synchronous processing, 12-axis PCB drilling machines are widely used in the production process of high-density and high-precision circuit boards. In order to ensure the consistency of drilling quality and the stability of equipment operation, there is an urgent need for a quality management system that can collect key parameters in real time, intelligently analyze the drilling state, and achieve closed-loop control. In recent years, with the development of industrial Internet of Things, big data analysis, and artificial intelligence technologies, intelligent manufacturing systems driven by sensor data have provided new solutions for improving the controllability and intelligent level of the drilling process.

[0003] The existing technologies have the following deficiencies:

[0004] The existing 12-axis PCB drilling machines are still in a relatively primary stage in terms of data acquisition and quality monitoring, mainly relying on simple statistical indicators and manual experience judgment, lacking the ability to deeply extract and fuse analyze the speed and pressure data, and it is difficult to accurately identify key problems such as abnormal drill bit movement and pressure instability. At the same time, the lack of a quality assessment model based on machine learning and a closed-loop feedback control mechanism results in a lag in quality anomaly response and low adjustment efficiency, affecting production stability and product consistency. Therefore, there is an urgent need for an efficient quality management solution that can achieve in-depth data mining, intelligent quality assessment, and automatic parameter optimization to solve the deficiencies of the current system in terms of anomaly recognition accuracy, assessment intelligence level, and adaptive regulation ability. Summary of the Invention

[0005] The purpose of the present invention is to provide a production data acquisition and quality management system for a 12-axis PCB drilling machine to solve the problems in the above background.

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

[0007] A production data acquisition and quality management system for a 12-axis PCB drilling machine, comprising:

[0008] A data acquisition module, which uses high-speed sensors installed on each axis of the drilling machine to collect speed and pressure data during the drilling process in real time;

[0009] The high-speed sensor includes a speed sensor and a pressure sensor;

[0010] A speed data analysis module, which performs differential processing on the speed data, constructs a differential speed sequence, and calculates the eigenvalue of the speed change rate for identifying abnormal fluctuations in the drill bit movement;

[0011] A pressure data analysis module, which performs zero-sequence processing on the pressure data, constructs a zero-sequence pressure sequence, and calculates the eigenvalue of the pressure stability for evaluating the stability of the drilling pressure;

[0012] A quality evaluation module, which fuses the eigenvalue of the speed change rate and the eigenvalue of the pressure stability into a drilling quality feature vector and inputs it into a quality analysis model for evaluating the drilling quality grade;

[0013] A feedback control and optimization module, which generates quality warning information according to the evaluation result and dynamically adjusts the speed and pressure parameters of the drilling machine operation to achieve closed-loop quality control of the drilling process.

[0014] As a further solution of the present invention: The identification of abnormal fluctuations in the drill bit movement specifically includes:

[0015] The speed data during the drilling process is collected in real time according to the time series by the speed sensors installed on each axis of the drilling machine, the speed data is subjected to differential processing, a differential speed sequence is constructed, the eigenvalue of the speed change rate is calculated, and it is judged whether the eigenvalue of the speed change rate is greater than or equal to a preset threshold. If so, the drill bit movement has abnormal fluctuations; if not, the drill bit movement has normal fluctuations.

[0016] As a further solution of the present invention: The eigenvalue of the speed change rate specifically includes:

[0017] The speed data collected in real time is obtained and integrated into a speed time series, and the speed time series is subjected to first-order differential processing, specifically, each speed value in the speed time series is subtracted from its previous time point speed value, that is, for the speed difference between any two adjacent time points, all speed differences are integrated to obtain a differential speed sequence;

[0018] The Haar wavelet transform is used to analyze the differential speed sequence, the Haar wavelet is selected as the wavelet basis function, and the differential speed sequence is decomposed at multiple scales to generate a set of wavelet coefficients at different scales;

[0019] According to the wavelet coefficients obtained by the Haar wavelet transform, the sum of the squares of all wavelet coefficients at all scales is calculated to obtain the eigenvalue of the speed change rate.

[0020] As a further solution of the present invention: The evaluation of the stability of the drilling pressure specifically includes:

[0021] By means of pressure sensors installed on each axis of the drilling machine, pressure data during the drilling process are collected in real time according to the time series, the zero-sequence processing is performed on the pressure data, a zero-sequence pressure sequence is constructed, the pressure stability characteristic value is calculated, and it is judged whether the pressure stability characteristic value is greater than or equal to a preset threshold. If so, the drilling pressure is unstable; if not, the drilling pressure is stable.

[0022] As a further solution of the present invention: the process for obtaining the pressure stability characteristic value is as follows:

[0023] Obtain the pressure data collected in real time and integrate them into a pressure time series. Perform zero-sequence processing on the pressure data, that is, remove the mean value, and construct a zero-sequence pressure sequence;

[0024] Based on the zero-sequence pressure sequence, calculate its covariance matrix; perform eigenvalue decomposition on the covariance matrix to obtain an eigenvalue set, select the first several largest eigenvalues as the principal components, calculate the ratio of the eigenvalue of each principal component to the sum of the eigenvalue set to obtain the variance contribution rate of each principal component, and calculate the standard deviation of the variance contribution rates of all principal components to obtain the pressure stability characteristic value.

[0025] As a further solution of the present invention: fusing the speed change rate characteristic value and the pressure stability characteristic value into a drilling quality characteristic vector and inputting it into the quality analysis model specifically includes:

[0026] Obtain the speed change rate characteristic value and the pressure stability characteristic value of the drilling operation during the production of the drilling machine, construct the speed change rate characteristic value and the pressure stability characteristic value into a drilling quality characteristic vector as the input of the quality analysis model, take minimizing the error between the predicted drilling quality score and the actual drilling quality score as the training objective of the quality analysis model, train the quality analysis model, and output the drilling quality score according to the trained quality analysis model. The quality analysis model is a gradient boosting tree model.

[0027] As a further solution of the present invention: the training process of the quality analysis model is as follows:

[0028] Obtain the characteristic values of the rate of change of speed and the characteristic values of pressure stability during the production process of multiple groups of historical drill holes, and construct them into a drill hole quality characteristic vector; each drill hole quality characteristic vector corresponds to an actual drill hole quality score. Construct the historical multiple groups of drill hole quality characteristic vectors and drill hole quality scores into a training data set, and input the training data set into the gradient boosting tree model for training. During the training process, use an iterative method to construct decision trees round by round. Each newly generated tree in each round is used to fit the residual between the current model prediction value and the true label. By continuously reducing the mean square error between the prediction value and the actual value, optimize the model parameters. Finally, after the training is completed, obtain a trained quality analysis model, and automatically predict the drill hole quality score of the current drill hole operation according to the real-time collected characteristic values of the rate of change of speed and the characteristic values of pressure stability.

[0029] As a further solution of the present invention: The evaluation of the drill hole quality grade specifically includes:

[0030] Judge whether the drill hole quality score of the drill hole operation during the production of the drill machine is greater than or equal to a preset threshold. If so, the drill hole quality during the production of the drill machine is qualified; if not, the drill hole quality during the production of the drill machine is unqualified.

[0031] As a further solution of the present invention: If the drill hole quality during the production of the drill machine is determined to be in an unqualified state, the system automatically triggers an early warning mechanism, generates an early warning signal, and transmits it to the monitoring platform of the factory management layer through a wireless communication method.

[0032] As a further solution of the present invention: Dynamically adjust the speed and pressure parameters of the drill machine operation to achieve closed-loop quality control of the drilling process, specifically including:

[0033] If it is determined that the drill hole quality is unqualified, calculate the corresponding speed and pressure correction amounts based on the deviation degree between the characteristic value of the rate of change of speed and the characteristic value of pressure stability, and send the new operating parameters to the servo control system of each axis of the drill machine through the PLC controller; the correction amounts are generated according to the preset PID control algorithm. After the system completes the parameter adjustment, collect a new round of speed and pressure data and re-evaluate the drill hole quality to form a closed-loop feedback mechanism; the closed-loop feedback mechanism supports multiple rounds of iterative optimization until the drill hole quality returns to the qualified range, so as to realize the online adaptive control of the operating state of the 12-axis PCB drill machine.

[0034] The beneficial effects of the present invention:

[0035] (1) By deploying high-speed sensors on each moving axis of a 12-axis PCB drilling machine, the present invention constructs a high-frequency and multi-dimensional data acquisition system to achieve millisecond-level synchronous acquisition of speed and pressure signals during the drilling process. The system uses a method combining differential speed analysis and Haar wavelet transform to jointly model the speed data in the time-frequency domain, extract the eigenvalue of the speed change rate with localization characteristics, so as to effectively capture the transient fluctuations and abnormal trends in the drill bit movement. At the same time, for the pressure data, zero-sequence processing and principal component analysis techniques are introduced. By decomposing the eigenvalues of the covariance matrix, the standard deviation of the principal component variance contribution rate is calculated, and the pressure stability eigenvalue that can reflect the stability of the multi-axis pressure distribution is obtained. The above two types of eigenvalues not only overcome the problems of insufficient sensitivity and poor robustness of traditional statistics (such as mean and variance) in the analysis of non-stationary signals, but also can reveal potential quality risks during the drilling process from the perspective of dynamic response, significantly improving the system's ability to identify small but significant process deviations, providing high-quality input for the subsequent quality assessment model based on machine learning, and then realizing high-precision, real-time online assessment and early warning of drilling quality.

[0036] (2) The present invention innovatively introduces a drilling quality analysis model based on gradient boosting trees, fully integrating multi-dimensional key parameters such as the eigenvalue of the speed change rate and the pressure stability eigenvalue collected from high-speed sensors and extracted by algorithms, constructing a highly representative drilling quality feature vector as the model input to achieve high-precision prediction of the drilling quality score. The model optimized by training with historical data can accurately identify the quality trends under different combinations of process parameters, and during the real-time operation process, quickly evaluate the drilling quality grade according to the current feature vector. Once it is detected that the predicted quality score is lower than the set threshold, the system determines it as an abnormal quality state, not only automatically generates structured warning information and pushes it to the management terminal through the wireless communication module, but also triggers a feedback control mechanism. Combining the proportional-integral-derivative (PID) control algorithm, the optimal correction amounts of speed and pressure parameters are calculated according to the deviation degree, and the operating parameters of each axis of the drilling machine are dynamically adjusted to form a closed-loop control process. This mechanism effectively improves the adaptive adjustment ability of the equipment under complex working conditions, significantly enhances the stability and robustness of the production process, reduces the dependence on manual experience intervention, realizes the full-process intelligent management from data perception, intelligent decision-making to automatic regulation, and greatly improves the product consistency and manufacturing efficiency of the 12-axis PCB drilling machine. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] The present invention will be further described below with reference to the drawings.

[0038] Figure 1 It is a flow chart of a production data acquisition and quality management system for a 12-axis PCB drilling machine according to the present invention. DETAILED DESCRIPTION OF THE INVENTION

[0039] The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0040] Please refer to Figure 1 As shown, the present invention is a production data acquisition and quality management system for a 12-axis PCB drilling machine, including:

[0041] A data acquisition module, which collects speed and pressure data during the drilling process in real time through high-speed sensors installed on each axis of the drilling machine;

[0042] The high-speed sensors include a speed sensor and a pressure sensor;

[0043] A speed data analysis module, which performs differential processing on the speed data, constructs a differential speed sequence, and calculates the speed change rate eigenvalue for identifying abnormal fluctuations in the drill bit movement;

[0044] A pressure data analysis module, which performs zero-sequence processing on the pressure data, constructs a zero-sequence pressure sequence, and calculates the pressure stability eigenvalue for evaluating the stability of the drilling pressure;

[0045] A quality evaluation module, which fuses the speed change rate eigenvalue and the pressure stability eigenvalue into a drilling quality feature vector and inputs it into the quality analysis model for evaluating the drilling quality grade;

[0046] A feedback control and optimization module, which generates quality warning information according to the evaluation result and dynamically adjusts the speed and pressure parameters of the drilling machine operation to achieve closed-loop quality control of the drilling process.

[0047] In the data acquisition module, the data acquisition module collects speed and pressure data during the drilling process in real time through high-speed sensors installed on each axis of the drilling machine, specifically including:

[0048] The key physical quantities during the drilling process are monitored and data is collected in real time through high-speed sensors respectively installed on each moving axis of the drilling machine. Specifically, the high-speed sensors include a speed sensor and a pressure sensor, where the speed sensor is used to collect the real-time movement speed data of each axis of the drilling machine in the X, Y, and Z directions, and the pressure sensor is used to collect the drilling pressure data applied by the drill bit to the PCB board. The sampling frequency is not less than 1 kHz to ensure obtaining high-precision time series raw data.

[0049] The high-speed sensor converts the collected analog signals into digital signals and transmits them to the local data acquisition unit through the industrial bus interface, forming a structured timestamp data sequence, the format of which includes but is not limited to {timestamp, axis number, speed value} and {timestamp, axis number, pressure value}. The system further caches and preprocesses the original data, removing outliers and noise interference, providing a high-quality data basis for the subsequent calculation of the speed change rate eigenvalue and the pressure stability eigenvalue.

[0050] In the speed data analysis module, differential processing is performed on the speed data to construct a differential speed sequence and calculate the speed change rate eigenvalue for identifying abnormal fluctuations in the drill bit movement, specifically including:

[0051] The speed sensors installed on each axis of the drilling machine are used to collect the speed data during the drilling process in real time according to the time series. Differential processing is performed on the speed data to construct a differential speed sequence, and the speed change rate eigenvalue is calculated. It is judged whether the speed change rate eigenvalue is greater than or equal to the preset threshold. If so, the drill bit movement has abnormal fluctuations; if not, the drill bit movement has normal fluctuations.

[0052] The speed change rate eigenvalue specifically includes:

[0053] Obtain the speed data collected in real time and integrate it into a speed time series. Perform first-order differential processing on the speed time series, specifically by subtracting the speed value at each time point in the speed time series from the speed value at the previous time point, that is, for the speed difference between any two adjacent time points, integrate all the speed differences to obtain a differential speed sequence;

[0054] Use Haar wavelet transform to analyze the differential speed sequence. Select Haar wavelet as the wavelet basis function and perform multi-scale decomposition on the differential speed sequence to generate a set of wavelet coefficients at different scales. Haar wavelet transform is a simple form of discrete wavelet transform, which realizes multi-level signal representation by recursively decomposing the signal into approximation and detail parts;

[0055] According to the wavelet coefficients obtained by the Haar wavelet transform, sum the squares of all wavelet coefficients at all scales to calculate the speed change rate eigenvalue. For example, in the first-level decomposition, calculate the energy sum of the detail coefficients, and perform deeper decomposition and energy calculation on the approximation coefficients until the predetermined decomposition level is reached.

[0056] It should be noted that: In the speed data analysis module of the present invention, a multi-scale analysis method based on Haar wavelet transform is introduced. The speed time series collected during the drilling process is subjected to first-order difference processing, and through wavelet decomposition and energy aggregation calculation of the differential speed sequence, a speed change rate eigenvalue with time-frequency localization characteristics is obtained. The speed change rate eigenvalue not only reflects the instantaneous speed fluctuation intensity during the movement of the drill bit, but also can effectively identify abnormal fluctuation behaviors caused by factors such as mechanical vibration, servo system response delay, or drill bit wear. By setting a reasonable threshold, the system can real-time judge whether the drill bit is in an abnormal motion state, thereby providing accurate data support for subsequent quality assessment and closed-loop control. This solution improves the sensitivity and recognition accuracy for small but critical speed mutation events, has stronger robustness and engineering practicability, and reflects significant technological progress and innovation.

[0057] In the pressure data analysis module, zero-sequence processing is performed on the pressure data to construct a zero-sequence pressure sequence, and the pressure stability eigenvalue is calculated to evaluate the stability of the drilling pressure, specifically including:

[0058] The pressure data during the drilling process is collected in real time according to the time series by the pressure sensors installed on each axis of the drilling machine. Zero-sequence processing is performed on the pressure data to construct a zero-sequence pressure sequence, the pressure stability eigenvalue is calculated, and it is judged whether the pressure stability eigenvalue is greater than or equal to the preset threshold. If so, the drilling pressure is unstable; if not, the drilling pressure is stable.

[0059] The process of obtaining the pressure stability eigenvalue is as follows:

[0060] The pressure data collected in real time is obtained and integrated into a pressure time series. Zero-sequence processing is performed on the original pressure data, that is, the mean value is removed, and a zero-sequence pressure sequence is constructed. The calculation expression is: ; where represents the average pressure value in the pressure time series, represents the pressure data in the zero-sequence pressure sequence after zero-sequence processing, represents the pressure data in the pressure time series, represents the acquisition time point;

[0061] Based on the zero-sequence pressure sequence, its covariance matrix is calculated. The calculation expression is: ;

[0062] where is the vector composed of the zero-sequence pressure sequence, represents the transpose operation of the vector, represents the vector 's transposed vector, represents the total number of data acquisition points, denotes the covariance matrix; perform eigenvalue decomposition on the covariance matrix to obtain the set of eigenvalues , denotes the th data point, denotes the eigenvalue of data points. Select the first largest eigenvalues as the principal components, calculate the ratio of the eigenvalue of each principal component to the sum of the set of eigenvalues, obtain the variance contribution rate of each principal component, and calculate the standard deviation of the variance contribution rates of all principal components to obtain the pressure stability eigenvalue.

[0063] It should be noted that: In the pressure data analysis module of the present invention, a feature extraction method combining zero-sequence processing and principal component analysis is introduced. By performing mean removal on the pressure time series collected in real time during the drilling process, a zero-sequence pressure series is constructed, and its covariance matrix is further calculated. Combining eigenvalue decomposition technology, the principal components and their variance contribution rates are extracted. Finally, the standard deviation of the variance contribution rate of the principal components is used as the pressure stability eigenvalue. The pressure stability eigenvalue can effectively reflect the concentration and volatility of the pressure distribution during the drilling process, and identify potential pressure instability states caused by factors such as abnormal cooling systems, unstable air pressure, or drill bit blockage. By setting a reasonable judgment threshold, the system can achieve online assessment of the drilling pressure stability, thereby improving the refinement level of drilling quality control. Compared with the traditional method of only relying on the average value or range to judge the pressure, this solution has stronger statistical robustness and sensitivity to the multi-dimensional pressure change trend, reflecting significant technological innovation and engineering application value.

[0064] In the quality assessment module, the velocity change rate eigenvalue and the pressure stability eigenvalue are fused into a drilling quality feature vector and input into the quality analysis model for drilling quality grade assessment, specifically including:

[0065] Obtain the velocity change rate eigenvalue and the pressure stability eigenvalue of the drilling operation during the production of the drilling machine, construct the velocity change rate eigenvalue and the pressure stability eigenvalue into a drilling quality feature vector, which is used as the input of the quality analysis model. Taking the minimization of the error between the predicted drilling quality score and the actual drilling quality score as the training objective of the quality analysis model, train the quality analysis model, and according to the trained quality analysis model, output the drilling quality score. The quality analysis model is a gradient boosting tree model.

[0066] The training process of the quality analysis model is as follows:

[0067] Obtain the characteristic values of the rate of change of speed and the characteristic values of pressure stability during the production process of multiple groups of historical drill holes, and construct them into a drill hole quality characteristic vector; each drill hole quality characteristic vector corresponds to an actual drill hole quality score. Construct the historical multiple groups of drill hole quality characteristic vectors and drill hole quality scores into a training data set, and input the training data set into the gradient boosting tree model for training. During the training process, use an iterative method to construct decision trees round by round. Each newly generated tree in each round is used to fit the residual between the current model prediction value and the true label. By continuously reducing the mean square error between the prediction value and the actual value, optimize the model parameters. Finally, after the training is completed, obtain a trained quality analysis model, and automatically predict the drill hole quality score of the current drill hole operation according to the real-time collected characteristic values of the rate of change of speed and the characteristic values of pressure stability.

[0068] Judge whether the drill hole quality score of the drill hole operation during the production of the drilling machine is greater than or equal to the preset threshold. If so, the drill hole quality during the production of the drilling machine is qualified; if not, the drill hole quality during the production of the drilling machine is unqualified.

[0069] If the drill hole quality during the production of the drilling machine is determined to be in an unqualified state, the system automatically triggers an early warning mechanism, generates an early warning signal, and transmits it to the monitoring platform of the factory management layer through wireless communication.

[0070] In the feedback control and optimization module, according to the evaluation results, generate quality early warning information, and dynamically adjust the speed and pressure parameters of the drilling machine operation to achieve closed-loop quality control of the drilling process, specifically including:

[0071] If it is determined that the drill hole quality is unqualified, calculate the corresponding speed and pressure correction amounts based on the deviation degree of the characteristic values of the rate of change of speed and the characteristic values of pressure stability, and send the new operating parameters to the servo control systems of each axis of the drilling machine through the PLC controller; the correction amounts are generated according to the preset PID control algorithm to ensure a stable, fast-response adjustment process without causing new fluctuations. After the system completes the parameter adjustment, continuously collect a new round of speed and pressure data and re-evaluate the drill hole quality to form a closed-loop feedback mechanism; the closed-loop feedback mechanism supports multiple rounds of iterative optimization until the drill hole quality returns to the qualified range, so as to realize the online adaptive control of the operating state of the 12-axis PCB drilling machine and improve production stability and product consistency;

[0072] Among them, the specific calculation process of the speed and pressure correction amounts is as follows:

[0073] The system takes the difference between the current drilling quality fraction and the set quality qualification threshold as the quality deviation signal. At the same time, it combines the eigenvalue of the speed change rate and the eigenvalue of the pressure stability calculated in real time, and compares them with their respective set normal range thresholds to obtain the speed deviation factor and the pressure deviation factor. The proportional-integral-differential control algorithm is used to calculate the speed adjustment amount and the pressure adjustment amount. The calculation method of the speed adjustment amount is: the speed proportional control coefficient multiplied by the speed deviation factor, plus the speed integral control coefficient multiplied by the time integral term of the speed deviation factor, and then plus the speed differential control coefficient multiplied by the time change rate of the speed deviation factor. The calculation method of the pressure adjustment amount is: the pressure proportional control coefficient multiplied by the pressure deviation factor, plus the pressure integral control coefficient multiplied by the time integral term of the pressure deviation factor, and then plus the pressure differential control coefficient multiplied by the time change rate of the pressure deviation factor.

[0074] The working principle of the present invention: The system of the present invention includes a data acquisition module, a speed data analysis module, a pressure data analysis module, a quality evaluation module, and a feedback control and optimization module. By deploying high-speed sensors on each axis of the drilling machine, the speed and pressure data during the drilling process are collected in real time. The speed data is respectively processed by first-order difference and Haar wavelet transform analysis to extract the eigenvalue of the speed change rate with time-frequency localization characteristics. At the same time, the pressure data is processed by zero-sequence processing and principal component analysis to extract the eigenvalue of the pressure stability based on the standard deviation of the variance contribution rate. The two types of eigenvalues are fused into a drilling quality feature vector and input into a quality analysis model trained based on the gradient boosting tree algorithm to realize the intelligent evaluation of the drilling quality grade. When it is detected that the drilling quality is unqualified, the system automatically generates a quality warning message and triggers a feedback control mechanism, calculates the correction amount of the speed and pressure parameters according to the PID control algorithm, and dynamically adjusts the operating parameters of the drilling machine to form a closed-loop quality control system. The present invention realizes the full-process intelligent management from data acquisition, feature extraction, quality prediction to automatic regulation, significantly improves the stability of the drilling process, the consistency of product quality and the response efficiency of abnormal states, and has good engineering application prospects and promotion value.

[0075] The above formulas are all dimensionless and take their numerical calculations. The formulas are obtained by collecting a large amount of data for software simulation to get a formula closest to the real situation. The preset parameters in the formulas are set by those skilled in the art according to the actual situation.

[0076] The above embodiments can be implemented in whole or in part by software, hardware, firmware, or any combination thereof. When implemented using software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the processes or functions described in the embodiments of the present application are generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center in a wired or wireless (such as infrared, wireless, microwave, etc.) manner. The computer-readable storage medium can be any available medium that can be accessed by a computer, or a data storage device such as a server or data center that contains one or more sets of available media. The available media can be magnetic media (such as floppy disks, hard disks, magnetic tapes), optical media (such as DVDs), or semiconductor media. The semiconductor media can be a solid-state drive.

[0077] It should be understood that the term "and / or" in this document is merely a description of the association relationship between associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist simultaneously, and B exists alone. Here, A and B can be singular or plural. In addition, the character " / " in this document generally represents an "or" relationship between the associated objects before and after, but it may also represent an "and / or" relationship, which can be specifically understood with reference to the context.

[0078] It should be understood that in various embodiments of the present application, the magnitudes of the sequence numbers of the above processes do not mean the order of execution. The order of execution of each process should be determined by its function and internal logic, and should not constitute any limitation to the implementation process of the embodiments of the present application.

[0079] The above has described in detail one embodiment of the present invention, but the content described is only a preferred embodiment of the present invention and cannot be considered as limiting the scope of implementation of the present invention. Any equivalent changes and improvements made within the scope of the application of the present invention should still fall within the scope covered by the patent of the present invention.

Claims

1. A production data acquisition and quality management system for a 12-axis PCB drilling machine, characterized in that Including: A data acquisition module, which collects speed and pressure data during the drilling process in real time through high-speed sensors installed on each axis of the drilling machine; The high-speed sensors include a speed sensor and a pressure sensor; A speed data analysis module, which performs differential processing on the speed data, constructs a differential speed sequence, and calculates the speed change rate eigenvalue for identifying abnormal fluctuations in the drill bit movement; A pressure data analysis module, which performs zero-sequence processing on the pressure data, constructs a zero-sequence pressure sequence, and calculates the pressure stability eigenvalue for evaluating the stability of the drilling pressure; A quality evaluation module, which fuses the speed change rate eigenvalue and the pressure stability eigenvalue into a drilling quality feature vector and inputs it into a quality analysis model for evaluating the drilling quality grade; A feedback control and optimization module, which generates quality warning information according to the evaluation result and dynamically adjusts the speed and pressure parameters of the drilling machine operation to achieve closed-loop quality control of the drilling process.

2. The production data acquisition and quality management system for a 12-axis PCB drilling machine according to claim 1, characterized in that, The identification of abnormal fluctuations in the drill bit movement specifically includes: Collecting speed data during the drilling process in real time according to the time series through the speed sensors installed on each axis of the drilling machine, performing differential processing on the speed data, constructing a differential speed sequence, calculating the speed change rate eigenvalue, and determining whether the speed change rate eigenvalue is greater than or equal to a preset threshold. If so, the drill bit movement has abnormal fluctuations; if not, the drill bit movement has normal fluctuations.

3. A production data acquisition and quality management system for a 12-axis PCB drilling machine according to claim 2, characterized in that, The speed change rate eigenvalue specifically includes: Obtaining the speed data collected in real time and integrating it into a speed time series, and performing first-order differential processing on the speed time series, specifically subtracting each speed value in the speed time series from its previous time point's speed value, that is, for the speed difference between any two adjacent time points, integrating all the speed differences to obtain a differential speed sequence; Analyzing the differential speed sequence using Haar wavelet transform, selecting Haar wavelet as the wavelet basis function, and performing multi-scale decomposition on the differential speed sequence to generate a set of wavelet coefficients at different scales; According to the wavelet coefficients obtained by the Haar wavelet transform, summing the squares of all wavelet coefficients at all scales to obtain the speed change rate eigenvalue.

4. A production data acquisition and quality management system for a 12-axis PCB drilling machine according to claim 1, characterized in that, The evaluation of the stability of the drilling pressure specifically includes: Collecting pressure data during the drilling process in real time according to the time series through the pressure sensors installed on each axis of the drilling machine, performing zero-sequence processing on the pressure data, constructing a zero-sequence pressure sequence, calculating the pressure stability eigenvalue, and determining whether the pressure stability eigenvalue is greater than or equal to a preset threshold. If so, the drilling pressure is unstable; if not, the drilling pressure is stable.

5. The production data acquisition and quality management system for a 12-axis PCB drilling machine according to claim 4, characterized in that, The process of obtaining the pressure stability eigenvalue is: Obtaining the pressure data collected in real time and integrating it into a pressure time series, and performing zero-sequence processing on the pressure data, that is, removing the mean value to construct a zero-sequence pressure sequence; Calculating its covariance matrix based on the zero-sequence pressure sequence; Perform eigenvalue decomposition on the covariance matrix to obtain a set of eigenvalues, select the first largest eigenvalues as the principal components, calculate the ratio of the eigenvalue of each principal component to the sum of the set of eigenvalues, obtain the variance contribution rate of each principal component, calculate the standard deviation of the variance contribution rates of all principal components, and obtain the pressure stability eigenvalue.

6. A production data acquisition and quality management system for a 12-axis PCB drilling machine according to claim 1, characterized in that, The fusion of the speed change rate eigenvalue and the pressure stability eigenvalue into a drilling quality feature vector and inputting it into the quality analysis model specifically includes: Obtain the characteristic values of the drilling speed change rate and the pressure stability during the production of the drilling machine. Construct the characteristic values of the drilling speed change rate and the pressure stability into a drilling quality characteristic vector, which is used as the input of the quality analysis model. With the goal of minimizing the error between the predicted drilling quality score and the actual drilling quality score, train the quality analysis model. According to the trained quality analysis model, output the drilling quality score. The quality analysis model is a gradient boosting tree model.

7. A production data acquisition and quality management system for a 12-axis PCB drilling machine according to claim 6, characterized in that, The training process of the quality analysis model is as follows: Obtain the characteristic values of the drilling speed change rate and the pressure stability during multiple groups of historical drilling production processes, and construct them into a drilling quality characteristic vector; each drilling quality characteristic vector corresponds to an actual drilling quality score. Construct the historical multiple groups of drilling quality characteristic vectors and drilling quality scores into a training dataset, and input the training dataset into the gradient boosting tree model for training. During the training process, use an iterative method to construct decision trees round by round. Each newly generated tree in each round is used to fit the residual between the current model prediction value and the true label. By continuously reducing the mean square error between the prediction value and the actual value, optimize the model parameters. Finally, after the training is completed, obtain the trained quality analysis model, and automatically predict the drilling quality score of the current drilling operation based on the real-time collected characteristic values of the drilling speed change rate and the pressure stability.

8. The production data acquisition and quality management system of a 12-axis PCB drilling machine according to claim 1, characterized in that, The evaluation of the drilling quality grade specifically includes: Judge whether the drilling quality score of the drilling operation during the production of the drilling machine is greater than or equal to the preset threshold. If so, the drilling quality during the production of the drilling machine is qualified; if not, the drilling quality during the production of the drilling machine is unqualified.

9. The production data acquisition and quality management system of a 12-axis PCB drilling machine according to claim 1, characterized in that, Generate a quality warning message according to the evaluation result, specifically including: If the drilling quality during the production of the drilling machine is determined to be in an unqualified state, the system automatically triggers an early warning mechanism, generates a warning signal, and transmits it to the monitoring platform of the factory management layer through wireless communication.

10. The production data acquisition and quality management system of a 12-axis PCB drilling machine according to claim 1, characterized in that, Dynamically adjust the speed and pressure parameters of the drilling machine to achieve closed-loop quality control of the drilling process, specifically including: If it is determined that the drilling quality is unqualified, calculate the corresponding speed and pressure correction amounts based on the deviation degree of the characteristic values of the drilling speed change rate and the pressure stability, and send the new operating parameters to the servo control system of each axis of the drilling machine through the PLC controller; the correction amounts are generated according to the preset PID control algorithm. After the system completes the parameter adjustment, collect a new round of speed and pressure data and re-evaluate the drilling quality to form a closed-loop feedback mechanism; the closed-loop feedback mechanism supports multiple rounds of iterative optimization until the drilling quality returns to the qualified range, so as to realize the online adaptive control of the operating state of the 12-axis PCB drilling machine.

Images