An automatic control system and method for top PIN of SMT circuit board

Abstract

The present invention relates to the field of data processing technology, and specifically to an automatic control system and method for the top PIN of an SMT circuit board; the method comprises: clustering the historical pressure data of the top PIN to obtain multiple cluster clusters, the cluster clusters include large clusters and small clusters, and using the CBLOF algorithm to obtain the abnormal score value of each data point in the cluster cluster; clustering the pressure data of multiple top PINs obtained in real time to obtain the cluster clusters to which they belong; in response to the cluster cluster to which the pressure data belongs being a large cluster, calculating the degree of disorder of the large cluster to which the pressure data belongs, in response to the degree of disorder being greater than a threshold, updating the abnormal score values ​​of all data points in the large cluster, and in response to the abnormal score value of any data point being greater than a preset abnormal threshold, issuing an early warning signal. That is, the scheme of the present invention can improve the accuracy of abnormality detection.

Description

Technical Field

[0001] The present invention generally relates to the field of data processing technology. More specifically, the present invention relates to an automatic control system and method for top PIN of an SMT circuit board. Background Art

[0002] SMT (Surface Mounted Technology) is a surface assembly technology. In this process, electronic components are placed on the surface of a printed circuit board (PCB) and fixed by soldering. The role of the top PIN is to support and stabilize the PCB to prevent bending or deformation during the mounting and soldering process, and to ensure that the components are accurately placed and soldered. Usually, multiple dynamically adjustable support PINs are used, and the PINs can be adjusted in position and height according to the layout and needs of the PCB. The SMT production line requires extremely high precision and repeatability to ensure that the components are placed correctly. In this process, it is necessary to monitor the pressure applied to the top PIN to detect and solve problems in time to ensure that the circuit board is not damaged. The CBLOF (Cluster-Based Local Outlier Factor) algorithm is an algorithm for anomaly detection. Its core idea is to use cluster-based local anomaly factor scoring to divide the data points in the data set into small clusters and large clusters, and then calculate the anomaly score value of the data point in different clusters in different calculation methods.

[0003] Pan Songsong, Medical Fraud Detection Based on Hybrid Methods, Journal of East China Normal University, Issue 5, September 2017. The article points out that when using the CBLOF algorithm for anomaly detection, when new data enters, it is necessary to observe whether the new data is marked as a small cluster or a large cluster. If it is a large cluster, a counter needs to be started. The function of the counter is to update the anomaly score value corresponding to each data point when the ratio of the counter value to the cluster size exceeds a preset threshold.

[0004] During the top PIN monitoring process, the pressure data changes greatly and frequently. Using a counter to update the abnormal score value of the data point causes a delay in the abnormal monitoring results, which cannot adapt to the frequent changes in pressure data in top PIN monitoring, resulting in low accuracy of the monitoring results. Summary of the invention

[0005] The present invention proposes an automatic control system and method for the top PIN of an SMT circuit board, which is used to solve the problem of low accuracy when using the CBLOF algorithm to monitor abnormal data in the prior art. To this end, the present invention provides solutions in the following two aspects.

[0006] In a first aspect, the present invention provides an automatic control method for top PIN of an SMT circuit board, comprising the following steps:

[0007] The historical pressure data of the top PIN is clustered to obtain multiple clusters, including large clusters and small clusters. The CBLOF algorithm is used to obtain the abnormal score value of each data point in the cluster.

[0008] Clustering the pressure data of multiple top PINs obtained in real time to obtain the corresponding clusters;

[0009] In response to the cluster to which the pressure data belongs being a large cluster, calculating the degree of disorder of the large cluster to which the pressure data belongs, in response to the degree of disorder being greater than a threshold, updating the abnormal score values ​​of all data points in the large cluster, and in response to the abnormal score value of any data point being greater than a preset abnormal threshold, issuing a warning signal;

[0010] Among them, the calculation method of the degree of disorder of the cluster to which the pressure data belongs is:

[0011] The pressure series is constructed by using the pressure data of the data points in the cluster and the pressure data of the adjacent historical moments, and the first-order difference series is constructed by using the difference between two adjacent data points in the pressure series;

[0012] The degree of abnormal performance of the data point is obtained according to the cumulative sum of the difference between the last data and other data in the first-order difference sequence. The degree of abnormal performance of the data point is positively correlated with the cumulative sum.

[0013] According to the abnormal performance degree and abnormal score value of the data point, the abnormal performance degree sequence and the abnormal score value sequence are constructed respectively. According to the Pearson correlation coefficient of the abnormal performance degree sequence and the abnormal score value sequence, the disorder degree of the cluster cluster is obtained. The disorder degree is negatively correlated with the Pearson correlation coefficient.

[0014] The effect is that the degree of abnormal performance of data points is calculated through the change characteristics of top PIN pressure data and the relationship between top PINs, and the degree of abnormal performance is calculated from the two aspects of time series dimension and space dimension, which improves the accuracy of the degree of abnormal performance. The abnormal score value of the data point is updated by the degree of chaos of the cluster. Compared with the traditional CBLOF algorithm that uses the ratio of counter value to cluster size as the update condition, the adaptability of the algorithm is improved, and it can change according to the change of the data set, and can effectively detect abnormal points, further improve the accuracy of top PIN pressure data abnormality detection, and improve the efficiency of PIN automation control.

[0015] Preferably, the expression of the abnormal performance degree of a data point is:

[0016]

[0017] In the formula, Indicates Top PIN The degree of abnormal performance of each pressure data point, Indicates the number of differences between the last data and other data in the first-order difference sequence; Indicates The last data of the first-order difference sequence of pressure data points, Indicates The first order difference sequence of pressure data points data.

[0018] The effect is that the above formula can be used to calculate the degree of abnormal performance of the data point, which provides a basis for calculating the degree of chaos of the clustering clusters.

[0019] Preferably, the expression of the abnormal performance degree of a data point is:

[0020]

[0021] In the formula, Indicates Top PIN The degree of abnormal performance of each pressure data point, Indicates the number of differences between the last data and other data in the first-order difference sequence; Indicates The last data of the first-order difference sequence of pressure data points, Indicates The first order difference sequence of pressure data points data.

[0022] Preferably, the expression of the abnormal performance degree of a data point is:

[0023]

[0024] In the formula, Indicates Top PIN The degree of abnormal performance of each pressure data point ， Indicates the number of differences between the last data and other data in the first-order difference sequence; Indicates The last data of the first-order difference sequence of pressure data points, Indicates The first order difference sequence of pressure data points data, It represents the variance of all top PIN pressure data at the same time as the pressure data point. It represents the variance after removing the z-th top PIN pressure data at the same time as the pressure data point.

[0025] The effect is that the degree of confusion is corrected by simultaneously engraving the pressure data of all top PINs, thereby improving the accuracy of the degree of abnormal performance.

[0026] Preferably, the expression of the degree of disorder is:

[0027]

[0028] In the formula, Indicates the degree of chaos of the current clustering. , They represent the abnormal performance degree sequence and abnormal score value sequence of the current cluster respectively. () represents the Pearson correlation coefficient function, () indicates An exponential function with base .

[0029] The effect is that the degree of disorder of the cluster can be calculated by the above formula, and the data points in the cluster are updated according to the degree of disorder, thereby improving the monitoring accuracy of abnormal data points.

[0030] Preferably, the clustering cluster also includes a small cluster. In response to the clustering cluster to which the pressure data belongs being a small cluster, the abnormal score value of each data point is immediately updated and a warning signal is issued.

[0031] Preferably, the calculation formula for the abnormal score value of a data point is:

[0032]

[0033] In the formula, represents the anomaly score of a data point, represents a data point, Indicates the cluster to which the data point belongs. represents the number of data points in the cluster. represents the clusters, Indicates the minimum distance between the data point and the center of the large cluster, Represents a large cluster, Represents a small cluster.

[0034] The effect is that the abnormal score value of the data point can be calculated through the formula, which is convenient for monitoring abnormal data and has a better monitoring effect.

[0035] In a second aspect, the present invention also provides an SMT circuit board top PIN automatic control system, comprising: a processor;

[0036] A memory stores computer instructions for safety warning of photovoltaic power stations based on artificial intelligence. When the computer instructions are executed by the processor, the system executes the above-mentioned SMT circuit board top PIN automatic control method.

[0037] The beneficial effects of the present invention are:

[0038] The solution of the present invention can calculate the abnormal performance degree of the data point through the change characteristics of the top PIN pressure data and the relationship between the top PINs, and calculate the chaos degree of the cluster cluster through the abnormal performance degree and the abnormal score value. The abnormal score value of the data point is updated according to the degree of chaos, which improves the adaptability of the algorithm, can effectively detect abnormal points, further improve the accuracy of top PIN pressure data abnormality detection, and improve the efficiency of PIN automation control. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] By reading the following detailed description with reference to the accompanying drawings, the above and other objects, features and advantages of the exemplary embodiments of the present invention will become readily understood. In the accompanying drawings, several embodiments of the present invention are shown in an exemplary and non-limiting manner, and the same or corresponding reference numerals represent the same or corresponding parts, wherein:

[0040] Figure 1 A flowchart schematically shows a step flow of an automatic control method for top PIN of an SMT circuit board in this embodiment;

[0041] Figure 2 The structural block diagram of an SMT circuit board top PIN automatic control system in this embodiment is schematically shown. DETAILED DESCRIPTION

[0042] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present invention. The specific implementation methods of the present invention are described in detail in combination with the drawings.

[0043] The present invention aims at the problem that when performing abnormal warning of current data of photovoltaic power station, the collected current data may have noise and interference, and there is inaccuracy in the subsequent abnormal warning detection process, thereby proposing an SMT circuit board top PIN automatic control system and method, that is, the collected current data is denoised in advance, and the abnormal data can be more accurately identified in the subsequent abnormal detection, so as to realize the safety warning of photovoltaic power station.

[0044] Figure 1 A flowchart schematically shows a step flow of an automatic control method for top PIN of an SMT circuit board in this embodiment.

[0045] Specifically, Figure 1As shown, a method for automatically controlling the top PIN of an SMT circuit board in this embodiment includes the following steps:

[0046] S1. Obtain pressure data.

[0047] A miniature force sensor is installed on the top PIN to monitor the supporting force of each top PIN on the PCB in real time. The acquisition frequency is 5HZ to collect the pressure data of each top PIN.

[0048] S2. Cluster the historical pressure data of the top PIN to obtain multiple clusters, including large clusters and small clusters, and use the CBLOF algorithm to obtain the abnormal score value of each data point in the cluster.

[0049] In this embodiment, the historical pressure data of the top PIN is clustered using the K-means algorithm to obtain multiple clusters, and the clusters are divided into large clusters and small clusters. The clusters are divided in the following way: the clusters are sorted from large to small, and the sorted clusters are , , , …, ,when hour, , , , …, For large clusters, the remaining , , …, is a small cluster, among which Indicates The size of the cluster, that is, the number of data points in the cluster, Represents the total number of data points, represents the correlation coefficient, exemplarily, is 0.9.

[0050] It should be noted that the data points in the large cluster are normal data points, and the data points in the small cluster are abnormal data points.

[0051] In other embodiments, the acquired historical pressure data of the top PIN is clustered using a DBSCAN algorithm to obtain a plurality of clusters.

[0052] In this embodiment, the CBLOF algorithm is used to obtain the abnormal score value of each data point in the cluster. The calculation formula of the abnormal score value of the data point is:

[0053]

[0054] In the formula, represents the anomaly score of a data point, represents a data point, Indicates the cluster to which the data point belongs. represents the number of data points in the cluster. represents the clusters, Represents the distance from the data point to the center of the cluster. Indicates the minimum distance between the data point and the center of the large cluster, Represents a large cluster, It can be understood that the anomaly score of a data point in a large cluster is the ratio of the distance from the data point to the center of the cluster to which it belongs and the size of the cluster; the anomaly score of a data point in a small cluster is the ratio of the distance from the data point to the nearest large cluster and the size of the small cluster to which it belongs; the above formula can be used to calculate the anomaly score of a data point in a cluster.

[0055] S3. Cluster the pressure data of multiple top PINs obtained in real time to obtain the corresponding clusters.

[0056] In the actual production process, the pressure data of multiple top PINs are acquired in real time, and the acquired pressure data of the top PINs are clustered to determine the category of the cluster to which the pressure data of each top PIN belongs.

[0057] S4. In response to the cluster to which the pressure data belongs being a large cluster, calculating the degree of disorder of the large cluster to which the pressure data belongs.

[0058] The calculation method of the degree of disorder of the cluster to which the pressure data belongs is:

[0059] S41. A pressure sequence is constructed using the pressure data of the data points in the cluster and the pressure data at adjacent historical moments, and a first-order difference sequence is constructed using the difference between two adjacent data points in the pressure sequence.

[0060] For example, is the first one in the top PIN pressure data sequence pressure data points, and the pressure data at adjacent historical moments is , then the pressure series is ; The first-order difference sequence of the pressure series is ,in Represents pressure data points The first first-order difference of Represents pressure data points The second first-order difference of is the pressure data point The first-order difference of Represents pressure data points The instantaneous pressure change. The mean of the difference between the first-order difference of the current pressure data point and the first-order difference of the historical pressure data can represent the consistency of the data point change. The larger the mean of the difference, the worse the consistency.

[0061] S42. Obtain the abnormal performance degree of the pressure data point according to the cumulative sum of the difference between the last data and other data in the first-order difference sequence. The abnormal performance degree of the data point is positively correlated with the cumulative sum.

[0062] In this embodiment, the pressure data points The calculation formula for the degree of abnormal performance is:

[0063] In the formula, Indicates Top PIN The degree of abnormal performance of each pressure data point, Indicates the number of differences between the last data and other data in the first-order difference sequence; Indicates The last data of the first-order difference sequence of pressure data points, Indicates The first order difference sequence of pressure data points data. Characterizing Pressure Data Points The consistency of the data change and the historical data point change, the larger the value, the greater the pressure data point The worse the consistency with historical pressure data points, Characterizing Pressure Data Points The consistency of the overall change, the larger the value, the higher the pressure data point The worse the consistency of the change compared with the historical pressure data, the more likely it is that the pressure data point The value of the pressure data point has a large change. The probability of abnormality is greater.

[0064] There may be noise when the force sensor collects the pressure data of the top PIN, and the noise will also cause the collected pressure data to change. In the SMT production line, the pressure of multiple top PINs of the same SMT circuit board is basically consistent, so the consistency of the pressure values ​​of multiple top PINs at the same time can be used to correct the degree of abnormal performance.

[0065] Therefore, in other embodiments, the calculation method of the abnormal performance degree of the data point is:

[0066] set up The zth top PIN pressure data points, then The pressure data set at the corresponding time of the pressure data point is: , the pressure data set represents the top PIN pressure values ​​at all positions at the same time, and N represents the number of top PINs. Pressure data point The degree of abnormal performance is:

[0067]

[0068] In the formula, Indicates Top PIN The degree of abnormal performance of each pressure data point, Indicates the number of differences between the last data and other data in the first-order difference sequence; Indicates The last data of the first-order difference sequence of pressure data points, Indicates The first order difference sequence of pressure data points data, represents the variance of all top PIN pressure data at the same time as the pressure data point. In other words, it is the variance of the pressure data set. It represents the variance after removing the z-th top PIN pressure data at the same time as the pressure data point.

[0069] Indicates removal The change of variance before and after is negatively correlated with the consistency of pressure data of multiple top PINs at the same time. The change of variance reflects the change of the variance of the abnormal degree of data. The larger the value, the greater the change of the current pressure data point, which means the greater the abnormal probability of the pressure data point. Correcting the abnormality degree of the pressure data point can obtain a more accurate abnormality degree.

[0070] In another embodiment, the calculation method of the abnormal performance degree of the pressure data point can also be:

[0071] In the formula, Indicates Top PIN The degree of abnormal performance of each pressure data point, Indicates the number of differences between the last data and other data in the first-order difference sequence; Indicates The last data of the first-order difference sequence of pressure data points, Indicates The first order difference sequence of pressure data points data.

[0072] S43. According to the abnormal performance degree and abnormal score value of the data point, an abnormal performance degree sequence and an abnormal score value sequence are respectively constructed. According to the Pearson correlation coefficient of the abnormal performance degree sequence and the abnormal score value sequence, the disorder degree of the cluster cluster is obtained. The disorder degree is negatively correlated with the Pearson correlation coefficient.

[0073] After obtaining the abnormal performance degree of the pressure data point in the cluster, the abnormal performance degree sequence is constructed. The abnormal score value of the data point is calculated using the calculation formula of the abnormal score value of the data point, and the abnormal score value sequence is constructed. The chaos degree of the cluster is calculated based on the abnormal performance degree sequence and the abnormal score value sequence. The expression of the chaos degree is:

[0074]

[0075] In the formula, Indicates the degree of chaos of the current clustering. , They represent the abnormal performance degree sequence and abnormal score value sequence of the current cluster respectively. () represents the Pearson correlation coefficient function, () indicates An exponential function with as the base. When the abnormal performance degree sequence and the abnormal score value sequence are positively correlated, the larger the Pearson correlation coefficient, the smaller the value of the chaos degree of the current cluster; when the abnormal performance degree sequence and the abnormal score value sequence are negatively correlated, the smaller the Pearson correlation coefficient, the greater the value of the chaos degree of the current cluster.

[0076] S5. In response to the disorder degree being greater than a threshold, the abnormal score values ​​of all data points in the large cluster are updated, and in response to the abnormal score value of any data point being greater than a preset abnormal threshold, an early warning signal is issued.

[0077] When the degree of chaos is greater than the threshold, it means that with the addition of new data, the density of pressure data points in the cluster and the relative position between data points have changed significantly, and the abnormal score value of the data point has also changed. The properties of the large cluster that was originally in a normal state have changed. Therefore, it is necessary to update the abnormal score value of all data points in the large cluster in time. When the abnormal score value is greater than the abnormal threshold, it indicates that the cluster to which the currently acquired data belongs is in an abnormal state as a whole. Then, an early warning signal is issued in time to readjust the support position of the top PIN to the SMT circuit board so that the SMT circuit board is in a normal working state. The abnormal threshold is set manually according to the actual situation. For example, the abnormal threshold is 0.8.

[0078] In this embodiment, in response to the fact that the cluster to which the pressure data belongs is a small cluster, it indicates that the data acquired in real time is in an abnormal state, the abnormal score value of each data point is immediately updated, and an early warning signal is issued, and the supporting position of the top PIN on the SMT circuit board is readjusted to put the SMT circuit board in normal working condition.

[0079] The solution of the present invention can calculate the abnormal performance degree of the data point through the change characteristics of the top PIN pressure data and the relationship between the top PINs, and calculate the chaos degree of the cluster cluster through the abnormal performance degree and the abnormal score value. The abnormal score value of the data point is updated according to the degree of chaos, which improves the adaptability of the algorithm, can effectively detect abnormal points, further improve the accuracy of top PIN pressure data abnormality detection, and improve the efficiency of PIN automation control.

[0080] Figure 2 The structural block diagram of an SMT circuit board top PIN automatic control system in this embodiment is schematically shown.

[0081] The present invention also provides an automatic control system for the top PIN of an SMT circuit board. Figure 2 As shown, the safety warning system includes a processor and a memory, wherein the memory stores computer program instructions, and when the computer program instructions are executed by the processor, an automatic control method for the top PIN of an SMT circuit board according to the present invention is implemented.

[0082] The safety warning system also includes other components familiar to those skilled in the art, such as a communication bus and a communication interface, whose settings and functions are known in the art and will not be described in detail here.

[0083] In the present invention, the aforementioned memory may be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, apparatus or device. For example, a computer-readable storage medium may be any appropriate magnetic storage medium or magneto-optical storage medium, such as a resistive random access memory RRAM (Resistive Random Access Memory), a dynamic random access memory DRAM (Dynamic Random Access Memory), a static random access memory SRAM (Static Random-Access Memory), an enhanced dynamic random access memory EDRAM (Enhanced Dynamic Random Access Memory), a high-bandwidth memory HBM (High-Bandwidth Memory), a hybrid memory cube HMC (Hybrid Memory Cube), etc., or any other medium that can be used to store the required information and can be accessed by an application, a module, or both. Any such computer storage medium may be part of a device or accessible or connectable to a device. Any application or module described in the present invention may be implemented using computer-readable / executable instructions that may be stored or otherwise maintained by such a computer-readable medium.

[0084] Although this specification has shown and described a number of embodiments of the present invention, it will be apparent to those skilled in the art that such embodiments are provided by way of example only. Those skilled in the art will conceive of many modifications, changes and alternatives without departing from the ideas and spirit of the present invention. It should be understood that in the practice of the present invention, various alternatives to the embodiments of the present invention described herein may be employed.

Claims

1. A method for automatically controlling the top PIN of an SMT circuit board, characterized in that: Includes steps: The historical pressure data of the top PIN is clustered to obtain multiple clusters, including large clusters and small clusters. The CBLOF algorithm is used to obtain the abnormal score value of each data point in the cluster. The calculation formula of the abnormal score value of the data point is: In the formula, represents the anomaly score of a data point, represents a data point, Indicates the cluster to which the data point belongs. represents the number of data points in the cluster. represents the clusters, Indicates the minimum distance between the data point and the center of the large cluster, Represents a large cluster, represents a small cluster; Clustering the pressure data of multiple top PINs obtained in real time to obtain the corresponding clusters; In response to the cluster to which the pressure data belongs being a large cluster, calculating the degree of disorder of the large cluster to which the pressure data belongs, in response to the degree of disorder being greater than a threshold, updating the abnormal score values ​​of all data points in the large cluster, and in response to the abnormal score value of any data point being greater than a preset abnormal threshold, issuing a warning signal; Among them, the calculation method of the degree of disorder of the cluster to which the pressure data belongs is: The pressure series is constructed by using the pressure data of the data points in the cluster and the pressure data of the adjacent historical moments, and the first-order difference series is constructed by using the difference between two adjacent data points in the pressure series; The abnormal performance degree of the pressure data point is obtained according to the cumulative sum of the difference between the last data and other data in the first-order difference sequence. The abnormal performance degree of the data point is positively correlated with the cumulative sum. According to the abnormal performance degree and abnormal score value of the data point, the abnormal performance degree sequence and the abnormal score value sequence are constructed respectively. According to the Pearson correlation coefficient of the abnormal performance degree sequence and the abnormal score value sequence, the disorder degree of the cluster cluster is obtained. The disorder degree is negatively correlated with the Pearson correlation coefficient.

2. The SMT circuit board top PIN automatic control method according to claim 1, characterized in that: The expression of the abnormal performance degree of a data point is: In the formula, Indicates Top PIN The degree of abnormal performance of each pressure data point, Indicates the number of differences between the last data and other data in the first-order difference sequence; Indicates The last data of the first-order difference sequence of pressure data points, Indicates The first order difference sequence of pressure data points data.

3. The SMT circuit board top PIN automatic control method according to claim 1, characterized in that: The expression of the abnormal performance degree of a data point is: In the formula, Indicates Top PIN The degree of abnormal performance of each pressure data point, Indicates the number of differences between the last data and other data in the first-order difference sequence; Indicates The last data of the first-order difference sequence of pressure data points, Indicates The first order difference sequence of pressure data points data.

4. The SMT circuit board top PIN automatic control method according to claim 1, characterized in that: The expression of the abnormal performance degree of a data point is: In the formula, Indicates Top PIN The degree of abnormal performance of each pressure data point, Indicates the number of differences between the last data and other data in the first-order difference sequence; Indicates The last data of the first-order difference sequence of pressure data points, Indicates The first order difference sequence of pressure data points data, It represents the variance of all top PIN pressure data at the same time as the pressure data point. It represents the variance after removing the z-th top PIN pressure data at the same time as the pressure data point.

5. The SMT circuit board top PIN automatic control method according to claim 1, characterized in that: The expression of the degree of chaos is: In the formula, Indicates the degree of chaos of the current clustering. , They represent the abnormal performance degree sequence and abnormal score value sequence of the current cluster respectively. () represents the Pearson correlation coefficient function, () indicates An exponential function with base .

6. The SMT circuit board top PIN automatic control method according to claim 1, characterized in that: In response to the cluster to which the pressure data belongs being a small cluster, the abnormal score value of each data point is immediately updated and a warning signal is issued.

7. An automatic control system for top PIN of SMT circuit board, characterized in that: include: processor; A memory storing computer instructions for safety warning of photovoltaic power stations based on artificial intelligence. When the computer instructions are executed by the processor, the system executes an automatic control method for top PIN of an SMT circuit board according to any one of claims 1 to 6.

Images