A remote intelligent monitoring method for a production workshop

Abstract

This invention discloses a remote intelligent monitoring method for production workshops, relating to the field of printed circuit board (PCB) technology. It obtains a positioning deviation information sequence by recognizing acquired images. Based on a temperature sensor, it collects temperature data, identifies the temperature distribution, and obtains a temperature-based welding deviation information sequence. It also acquires a sequence of completed welding images, identifying image welding deviation information sequences and welding quality information sequences. Based on the positioning deviation information sequence, it obtains positioning deviation fault trend information. Combining the temperature-based welding and image welding deviation information sequences, it obtains welding deviation fault trend information. Finally, based on the welding quality information sequence, and combining the positioning deviation fault trend information and the welding deviation fault trend information, it obtains the positioning quality impact level and the welding quality impact level. This invention solves the technical problems of existing PCB quality monitoring methods, which suffer from low comprehensiveness, resulting in poor detection accuracy and low detection efficiency.

Description

Technical Field

[0001] This application relates to the field of printed circuit technology, specifically to a remote intelligent monitoring method for production workshops. Background Technology

[0002] In modern manufacturing, the quality of PCB (Printed Circuit Board) circuit boards is crucial to the performance and reliability of electronic products. During PCB production, soldering quality directly affects the stability and functionality of the product. Therefore, real-time monitoring and quality control of the PCB soldering process are of paramount importance. Traditional soldering quality monitoring methods rely on manual inspection, which suffers from low efficiency, insufficient accuracy, and slow response times, failing to meet the demands of efficient and precise modern production.

[0003] Therefore, existing PCB printed circuit board quality monitoring methods suffer from low comprehensiveness of monitoring, resulting in poor detection accuracy and low detection efficiency. Summary of the Invention

[0004] This application provides a remote intelligent monitoring method for production workshops, solving the technical problems of low comprehensiveness, poor detection accuracy, and low detection efficiency in existing PCB printed circuit board quality monitoring methods. It achieves real-time monitoring of the PCB soldering process and comprehensively analyzes and evaluates the impact of positioning and soldering processes on product quality, thus improving the efficiency and accuracy of soldering quality monitoring.

[0005] This application provides a remote intelligent monitoring method for a production workshop. The method includes: continuously acquiring images of PCBs after automatic positioning in a PCB soldering production workshop, obtaining a positioning image sequence, identifying the positioning images to obtain a positioning deviation information sequence, and remotely transmitting it. During the soldering process, based on temperature sensors, monitoring and acquiring temperature distribution data during soldering, obtaining a temperature distribution sequence, identifying the temperature distribution, obtaining a temperature soldering deviation information sequence, and remotely transmitting it. After soldering is completed, acquiring images of the completed soldering process, obtaining a soldering image sequence, identifying the soldering images to obtain an image soldering deviation information sequence and a soldering quality information sequence, and remotely transmitting them. Based on the positioning deviation information sequence, performing a positioning deviation fault trend analysis to obtain positioning deviation fault trend information. Based on the temperature soldering deviation information sequence and the image soldering deviation information sequence, combined with the positioning deviation information sequence, performing a soldering deviation fault trend analysis to obtain soldering deviation fault trend information. Based on the soldering quality information sequence, combined with the positioning deviation fault trend information and the soldering deviation fault trend information, performing a differentiation analysis of the impact of positioning quality and soldering quality to obtain the positioning quality impact level and the soldering quality impact level, which are used as remote monitoring results for control.

[0006] In the implementation method, images of the PCB after automatic positioning are continuously acquired in the PCB soldering production workshop to obtain a positioning image sequence, and the positioning images are identified. This includes: within the PCB soldering production workshop, after the PCB is automatically positioned, images of the automatic positioning are acquired sequentially to obtain a positioning image sequence. A sample positioning image set is collected, and the deviation of the PCB from the standard positioning area in each positioning image is marked to obtain a sample positioning deviation information set. The sample positioning image set and the sample positioning deviation information set are used to train a positioning deviation recognizer. The positioning deviation recognizer is used to identify multiple positioning images within the positioning image sequence to obtain a positioning deviation information sequence, which is then remotely transmitted.

[0007] In the implementation, during the welding process, temperature distribution data is monitored and collected based on temperature sensors to obtain a temperature distribution sequence, and the temperature distribution is identified. This includes: during the welding process, temperature distribution data of the PCB is sequentially monitored and collected based on temperature sensors to obtain a temperature distribution sequence. A sample temperature distribution set is collected, and the deviations of high-temperature points within the sample temperature distribution from the standard welding temperature are marked to obtain a sample temperature welding deviation information set. The sample temperature distribution set and the sample temperature welding deviation information set are used to train a temperature welding deviation analyzer. The temperature welding deviation analyzer is used to identify welding deviations in multiple temperature distributions within the temperature distribution sequence, obtain a temperature welding deviation information sequence, and transmit it remotely.

[0008] In the implementation method, after welding is completed, images of the completed welding are acquired to obtain a welding image sequence. The welding images are then identified, including: acquiring images of the welded PCB sequentially after welding to obtain a welding image sequence; acquiring a sample welding image set; labeling the deviation of each solder joint from the standard welding position in each sample welding image to obtain a sample image welding deviation information set; labeling the deviation of each solder joint quality from the standard solder joint quality in each sample welding image to obtain a sample welding quality information set; training an image welding deviation analysis branch using the sample welding image set and the sample welding quality information set; training a welding quality analysis branch using the sample welding image set and the sample welding quality information set; and combining the image welding deviation analysis branch to obtain a welding image recognizer; and using the welding image recognizer to identify multiple welding images within the welding image sequence to obtain an image welding deviation information sequence and a welding quality information sequence, which are then remotely transmitted.

[0009] In the implementation, positioning deviation fault trend analysis is performed based on the positioning deviation information sequence to obtain positioning deviation fault trend information. This includes: collecting a set of sample positioning deviation information sequences based on the automatic positioning monitoring data of the PCB, and setting a set of sample positioning deviation fault trend information based on the change amplitude of the positioning deviation information in each sample positioning deviation information sequence. A positioning deviation trend classifier is constructed using the set of sample positioning deviation information sequences and the set of sample positioning deviation fault trend information. The positioning deviation information sequences are input into the positioning deviation trend classifier for classification to obtain positioning deviation fault trend information.

[0010] In the implementation, welding deviation fault trend analysis is performed based on the temperature welding deviation information sequence and the image welding deviation information sequence, combined with the positioning deviation information sequence, to obtain welding deviation fault trend information. This includes: collecting a set of sample temperature welding deviation information sequences and a set of sample image welding deviation information sequences with zero positioning deviation information based on PCB welding position monitoring data; and setting a sample welding deviation fault trend information set based on the change amplitude of welding deviation within each sample temperature welding deviation information sequence and sample image welding deviation information sequence. A temperature welding deviation trend classifier and an image welding deviation trend classifier are constructed using the sample temperature welding deviation information sequence set and the sample image welding deviation information sequence set, respectively, combined with the sample welding deviation fault trend information set. Deviations in the positioning deviation information sequence are deleted from the temperature welding deviation information sequence and the image welding deviation information sequence to obtain individual temperature welding deviation information sequences and individual image welding deviation information sequences. The change amplitudes of the individual temperature welding deviation information sequences and individual image welding deviation information sequences are input into the temperature welding deviation trend classifier and the image welding deviation trend classifier, respectively, to obtain temperature welding deviation fault trend information and image welding deviation fault trend information. Welding deviation fault trend information is obtained by weighting the temperature welding deviation fault trend information and the image welding deviation fault trend information.

[0011] In the implementation method, based on the welding quality information sequence and combined with the positioning deviation fault trend information and welding deviation fault trend information, a differentiation analysis of the impact of positioning quality and welding quality is performed to obtain the positioning quality impact level and welding quality impact level, which are used as remote monitoring results. This includes: analyzing and obtaining welding quality change trend information based on the welding quality information sequence; obtaining the current transmission delay for remote transmission and, combined with the welding quality change trend information, classifying and obtaining welding quality fault levels; differentiating and allocating the welding quality fault levels according to the magnitude of the positioning deviation fault trend information and welding deviation fault trend information to obtain the positioning quality impact level and welding quality impact level, wherein the sum of the positioning quality impact level and welding quality impact level is the welding quality fault level, and the ratio of the positioning quality impact level to the welding quality impact level is the same as the ratio of the positioning deviation fault trend information and the welding deviation fault trend information; and using the positioning quality impact level and welding quality impact level as the remote monitoring results.

[0012] In the implementation, the current transmission delay during remote transmission is obtained. Combined with the welding quality change trend information, welding quality fault levels are classified. This includes: collecting a set of sample transmission delays and a set of sample welding quality change trend information; and setting a set of sample welding quality fault levels based on the magnitude of each sample transmission delay and welding quality change trend information, wherein the magnitude of the welding quality fault level is positively correlated with the magnitude of the transmission delay and welding quality change trend information. Using the sample transmission delay set and the sample welding quality change trend information set as decision inputs, and the sample welding quality fault level set as the decision output, a welding quality classifier is constructed based on a decision tree. The welding quality classifier is then used to classify the transmission delay and welding quality change trend information to obtain the welding quality fault levels.

[0013] This application proposes a remote intelligent monitoring method for production workshops. In a PCB soldering workshop, images of automatically positioned PCBs are continuously acquired to obtain a positioning image sequence. These images are then identified to obtain a positioning deviation information sequence, which is transmitted remotely. During soldering, temperature distribution data is monitored and acquired using temperature sensors. A temperature distribution sequence is obtained, and this sequence is identified to obtain a temperature soldering deviation information sequence, which is also transmitted remotely. After soldering, images of the completed soldering process are acquired to obtain a soldering image sequence. These images are then identified to obtain an image soldering deviation information sequence and a soldering quality information sequence, which are transmitted remotely. Based on the positioning deviation information sequence, a positioning deviation fault trend analysis is performed to obtain positioning deviation fault trend information. Based on the temperature soldering deviation information sequence and the image soldering deviation information sequence, combined with the positioning deviation information sequence, a soldering deviation fault trend analysis is performed to obtain soldering deviation fault trend information. Based on the soldering quality information sequence, combined with the positioning deviation fault trend information and the soldering deviation fault trend information, a differentiation analysis of the impact on positioning quality and soldering quality is performed to obtain the positioning quality impact level and the soldering quality impact level. These results are used as remote monitoring outcomes for control. This invention addresses the technical problems of low comprehensiveness, poor accuracy, and low efficiency in existing PCB (Printed Circuit Board) quality monitoring methods. It achieves real-time monitoring of the PCB soldering process and comprehensively analyzes and evaluates the impact of positioning and soldering processes on product quality, thus improving the efficiency and accuracy of soldering quality monitoring. Attached Figure Description

[0014] To more clearly illustrate the technical solutions of the embodiments of this disclosure, the accompanying drawings of the embodiments of this disclosure will be briefly described below. Flowcharts are used in this application to illustrate the operations performed by the system according to the embodiments of this application. It should be understood that the preceding or following operations are not necessarily performed precisely in sequence. Instead, various steps can be processed in reverse order or simultaneously as needed. Furthermore, other operations can be added to these processes, or one or more steps can be removed from these processes.

[0015] Figure 1 A schematic diagram of a remote intelligent monitoring method for a production workshop provided in an embodiment of this application;

[0016] Figure 2 This is a flowchart illustrating a remote intelligent monitoring method for a production workshop to obtain a positioning deviation information sequence, as provided in an embodiment of this application. Detailed Implementation

[0017] The above description is only an overview of the technical solution of this application. In order to better understand the technical means of this application and to implement it in accordance with the contents of the specification, and to make the above and other objects, features and advantages of this application more obvious and understandable, the following are specific embodiments of this application.

[0018] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description of this application will be provided in conjunction with the accompanying drawings. The described embodiments should not be considered as limitations on this application. All other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0019] In the following description, references to "some embodiments" describe a subset of all possible embodiments. However, it is understood that "some embodiments" may be the same or different subsets of all possible embodiments and may be combined with each other without conflict. The terms "first" and "second" are used merely to distinguish similar objects and do not represent a specific ordering of objects. The terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or server that includes a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or modules not explicitly listed or inherent to these processes, methods, products, or devices. Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. The terminology used herein is for the purpose of describing embodiments of this application only.

[0020] This application provides a remote intelligent monitoring method for production workshops, such as... Figure 1 As shown, the method includes:

[0021] In the PCB soldering production workshop, images of the PCB after automatic positioning are continuously acquired to obtain a positioning image sequence. These images are then identified to obtain a positioning deviation information sequence, which is transmitted remotely. During the soldering process, temperature sensors monitor and collect temperature distribution data, acquiring a temperature distribution sequence. This sequence is then identified to obtain a temperature soldering deviation information sequence, which is transmitted remotely. After soldering is completed, images of the finished soldering process are acquired to obtain a soldering image sequence. These images are then identified to obtain a soldering deviation information sequence and a soldering quality information sequence, which are also transmitted remotely.

[0022] In PCB soldering production workshops, to ensure soldering accuracy, PCBs need to be automatically positioned. Images of the PCB after automatic positioning are captured using camera equipment, resulting in an image sequence. Positioning deviation information is obtained from this image sequence and transmitted remotely. Subsequently, during the soldering process, temperature distribution data is monitored and collected in real time using temperature sensors, resulting in a temperature distribution sequence. This temperature distribution is then identified, and a temperature soldering deviation information sequence is obtained and transmitted remotely. Further, after soldering is completed, images of the finished soldering process are captured, resulting in a soldering image sequence containing images of each solder joint on the PCB. These images are then identified to obtain image soldering deviation information and soldering quality information sequences, which are transmitted remotely. The image soldering deviation information represents positional deviation, and the soldering quality information represents evaluation parameters for solder joint quality.

[0023] like Figure 2 As shown in the embodiments of this application, the method further includes: in the PCB soldering production workshop, after the PCB is automatically positioned, sequentially acquiring images of the automatic positioning to obtain a positioning image sequence. A sample positioning image set is acquired, and the magnitude of the PCB's deviation from the standard positioning area in each positioning image is marked to obtain a sample positioning deviation information set. A positioning deviation recognizer is trained using the sample positioning image set and the sample positioning deviation information set. The positioning deviation recognizer is used to recognize multiple positioning images within the positioning image sequence to obtain a positioning deviation information sequence and transmit it remotely.

[0024] In the PCB soldering production workshop, after the PCB completes automatic positioning, images of the automatic positioning are sequentially acquired to obtain a positioning image sequence. A sample positioning image set is collected, which consists of automatic positioning images acquired during historical positioning processes. The deviation of the PCB from the standard positioning area in each positioning image is labeled to obtain a sample positioning deviation information set. That is, the deviation of the PCB from the standard positioning area in each positioning image in the sample positioning image set is labeled, where the standard positioning area is a fixed reference target positioning position, and the sample positioning deviation information set is obtained. The sample positioning deviation information set contains deviation parameters of each sample image from the standard positioning area in different directions. When constructing the positioning deviation recognizer, a convolutional neural network (CNN) is used to construct the positioning deviation recognizer based on the sample positioning image set and the sample positioning deviation information set. CNN is good at processing image data and can effectively identify patterns and features in images. The sample positioning image set and the sample positioning deviation information set are input into the convolutional neural network for supervised training of the model until the output accuracy of the model meets the predetermined requirements. The trained model is then obtained, and the positioning deviation recognizer is obtained. Finally, the positioning deviation recognizer is used to recognize multiple positioning images in the positioning image sequence, obtain the positioning deviation information sequence output by the positioning deviation recognizer, and then transmit the positioning deviation information sequence remotely.

[0025] The method provided in this application embodiment further includes: during the welding process, based on a temperature sensor, sequentially monitoring and collecting temperature distribution data of the PCB during welding to obtain a temperature distribution sequence. A sample temperature distribution set is collected, and the deviations of high-temperature points within the sample temperature distribution from the standard welding temperature are marked to obtain a sample temperature welding deviation information set. Using the sample temperature distribution set and the sample temperature welding deviation information set, a temperature welding deviation analyzer is trained. Using the temperature welding deviation analyzer, welding deviations are identified in multiple temperature distributions within the temperature distribution sequence to obtain a temperature welding deviation information sequence and transmit it remotely.

[0026] During the welding process, temperature sensors, such as infrared thermal imagers or thermocouples, are used to sequentially monitor and collect temperature distribution data of the PCB during welding, obtaining a temperature distribution sequence. This sequence records the temperature data at various locations on the PCB during the welding process. A sample temperature distribution set is then collected, consisting of temperature distribution data collected during historical welding processes. Subsequently, the deviations of high-temperature points within the sample temperature distributions from the standard welding temperature are labeled, i.e., the deviation values ​​between the high-temperature points and the standard welding temperature are labeled, thus obtaining a sample temperature welding deviation information set. This sample temperature distribution set and sample temperature welding deviation information set are used as training data to supervise the training of a neural network model until the model's output meets an accuracy threshold, completing the training and obtaining a temperature welding deviation analyzer. Using this temperature welding deviation analyzer, welding deviations are identified across multiple temperature distributions within the temperature distribution sequence, obtaining a temperature welding deviation information sequence, which is then remotely transmitted.

[0027] The method provided in this application embodiment further includes: after welding is completed, sequentially acquiring images of the welded PCB to obtain a welding image sequence. A sample welding image set is acquired, and each sample welding image is labeled according to the deviation of the solder joint from the standard welding position, to obtain a sample image welding deviation information set. The quality of each sample welding image is labeled according to the deviation of the solder joint quality from the standard solder joint quality, to obtain a sample welding quality information set. Using the sample welding image set and the sample image welding deviation information set, an image welding deviation analysis branch is trained. Using the sample welding image set and the sample welding quality information set, a welding quality analysis branch is trained, and combined with the image welding deviation analysis branch, a welding image recognizer is obtained. Using the welding image recognizer, multiple welding images within the welding image sequence are recognized to obtain an image welding deviation information sequence and a welding quality information sequence, which are then remotely transmitted.

[0028] After welding is completed, images of the welded PCB are sequentially acquired to obtain a welding image sequence. A sample welding image set is collected, which consists of PCB welding images acquired during historical welding processes. Each sample welding image is labeled with the deviation of the solder joint from the standard welding position, i.e., the deviation parameter between the solder joint and the standard welding position is labeled, thus obtaining a sample image welding deviation information set. Subsequently, the deviation of the solder joint quality from the standard solder joint quality in each sample welding image is labeled. The quality deviation parameters corresponding to the image labels of the standard solder joint quality (weld bonding degree, size, shape, etc.) of each sample welding image are manually compared to obtain a sample welding quality information set. Using the sample welding image set and the sample image welding deviation information set, an image welding deviation analysis branch is trained. Using the sample welding image set and the sample welding quality information set, a welding quality analysis branch is trained. Combined with the image welding deviation analysis branch, a welding image recognizer is obtained. The construction method of the welding quality analysis branch and the welding deviation analysis branch is consistent with the construction method of the positioning deviation recognizer. The constructed welding quality analysis branch and the welding deviation analysis branch are obtained and combined to obtain the welding image recognizer. The welding image recognizer is used to output corresponding welding deviation data and welding quality deviation data based on the welding images. Using the welding image recognizer, multiple welding images within the welding image sequence are identified to obtain an image welding deviation information sequence and a welding quality information sequence, which are then transmitted remotely.

[0029] The method provided in this application embodiment further includes: performing positioning deviation fault trend analysis based on the positioning deviation information sequence to obtain positioning deviation fault trend information; performing welding deviation fault trend analysis based on the temperature welding deviation information sequence and the image welding deviation information sequence, combined with the positioning deviation information sequence, to obtain welding deviation fault trend information; and performing differentiation analysis of positioning quality impact and welding quality impact based on the welding quality information sequence, combined with the positioning deviation fault trend information and the welding deviation fault trend information, to obtain the positioning quality impact level and the welding quality impact level, which are then used as remote monitoring results for control.

[0030] Based on the positioning deviation information sequence, a positioning deviation fault trend analysis is performed to obtain positioning deviation fault trend information, which is the deviation trend information generated by automatic positioning. Based on the temperature welding deviation information sequence and the image welding deviation information sequence, combined with the positioning deviation information sequence, a welding deviation fault trend analysis is performed to obtain welding deviation fault trend information, which is the welding deviation trend generated by welding temperature and welding deviation. Finally, based on the welding quality information sequence, combined with the positioning deviation fault trend information and the welding deviation fault trend information, a differentiation analysis of the impact of positioning quality and welding quality is performed to obtain the impact levels of positioning quality and welding quality. As a result of remote monitoring, optimization guidance is provided to technicians based on the magnitude of the impact levels of positioning quality and welding quality, thereby facilitating equipment management. If the positioning deviation is assessed as a high-level impact and the welding deviation as a low-level impact, the positioning problem is addressed first. This solves the technical problems of existing PCB printed circuit board quality monitoring methods, which suffer from low monitoring comprehensiveness, resulting in poor detection accuracy and low detection efficiency. It achieves real-time monitoring of the PCB soldering process and comprehensively analyzes and evaluates the impact of positioning and soldering processes on product quality, thereby improving the efficiency and accuracy of soldering quality monitoring.

[0031] The method provided in this application embodiment further includes: collecting a set of sample positioning deviation information sequences based on the automatic positioning monitoring data of the PCB, and setting a set of sample positioning deviation fault trend information based on the change amplitude of the positioning deviation information within each sample positioning deviation information sequence. A positioning deviation trend classifier is constructed using the set of sample positioning deviation information sequences and the set of sample positioning deviation fault trend information. The change amplitude of the positioning deviation information sequences is input into the positioning deviation trend classifier to classify and obtain positioning deviation fault trend information.

[0032] Based on the automatic positioning monitoring data of the PCB, which is historical automatic positioning monitoring data, a set of sample positioning deviation information sequences is collected. This set consists of multiple sample positioning deviation information sequences generated by historical automatic positioning. The amplitude of the change in positioning deviation information in each sample positioning deviation information sequence is used. This amplitude is the average deviation amplitude between parameters in each sample positioning deviation information sequence. For example, if the amplitude of the gradual increase in positioning deviation of a sample PCB from the first to the third is 2mm, then the amplitude is 1mm per sequence. Based on the amplitude of the change, a set of sample positioning deviation fault trend information is obtained. Subsequently, using the set of sample positioning deviation information sequences and the set of sample positioning deviation fault trend information, a positioning deviation trend classifier is constructed. This classifier is based on a decision tree model. The set of sample positioning deviation information sequences and the set of sample positioning deviation fault trend information are used as training data to train the decision tree model, resulting in the positioning deviation trend classifier. The positioning deviation trend classifier is used to output corresponding positioning deviation fault trend information based on the positioning deviation information sequences. The positioning deviation information sequence is input into the positioning deviation trend classifier to obtain positioning deviation fault trend information.

[0033] The method provided in the application embodiment further includes: collecting a set of sample temperature welding deviation information sequences and a set of sample image welding deviation information sequences with zero positioning deviation information based on PCB welding position monitoring data; and setting a set of sample welding deviation fault trend information based on the change amplitude of welding deviation within each sample temperature welding deviation information sequence and sample image welding deviation information sequence. A temperature welding deviation trend classifier and an image welding deviation trend classifier are constructed by combining the sample temperature welding deviation information sequence set and the sample image welding deviation information sequence set with the sample welding deviation fault trend information set. Deviations in the positioning deviation information sequences are deleted from the temperature welding deviation information sequences and image welding deviation information sequences to obtain individual temperature welding deviation information sequences and individual image welding deviation information sequences. The change amplitudes of the individual temperature welding deviation information sequences and individual image welding deviation information sequences are input into the temperature welding deviation trend classifier and the image welding deviation trend classifier, respectively, to obtain temperature welding deviation fault trend information and image welding deviation fault trend information. The temperature welding deviation fault trend information and image welding deviation fault trend information are weighted and calculated to obtain welding deviation fault trend information.

[0034] Based on the PCB soldering position monitoring data, which records the soldering position of each PCB soldering process, a set of sample temperature soldering deviation information sequences and a set of sample image soldering deviation information sequences with a positioning deviation of 0 are collected. These sample sets exclude samples with positioning deviations. Based on the amplitude of the change in soldering deviation within each sample temperature soldering deviation information sequence and sample image soldering deviation information sequence, a set of sample soldering deviation fault trend information is obtained. The amplitude of the change in soldering deviation is the average deviation amplitude of the soldering deviation sequence. For example, if a sample has multiple deviation parameters, such as 1mm, 2mm, and 3mm to the right, the corresponding average deviation amplitude is 1mm / deviation. Based on the amplitude of the change in soldering deviation, a set of sample soldering deviation fault trend information is obtained. Using the sample temperature soldering deviation information sequence set and the sample image soldering deviation information sequence set, combined with the set of sample soldering deviation fault trend information, a temperature soldering deviation trend classifier and an image soldering deviation trend classifier are constructed. The construction methods for the temperature welding deviation trend classifier and the image welding deviation trend classifier are the same as those for the positioning deviation trend classifier, differing only in the training data. The training data for the temperature welding deviation trend classifier consists of a set of sample temperature welding deviation information sequences and a set of sample welding deviation fault trend information. The training data for the image welding deviation trend classifier consists of a set of sample image welding deviation information sequences and a set of sample welding deviation fault trend information. The deviations in the positioning deviation information sequences are removed from the temperature welding deviation information sequences and the image welding deviation information sequences to obtain individual temperature welding deviation information sequences and individual image welding deviation information sequences. The elements in the individual temperature welding deviation information sequences are identical to those in the original temperature welding deviation information sequences. The individual image welding deviation information sequence is the sequence after removing the deviations from the positioning deviation information sequences from the image welding deviation information sequences. In other words, the deviations present in the image welding deviation information are compensated and corrected using the deviations in the positioning deviation information sequences. For example, if the original image welding deviation information has a 3mm rightward deviation, and the corresponding PCB deviation in the positioning deviation information is also 3mm rightward, then the corrected image welding deviation information deviation will be 0. The amplitude values ​​of the individual temperature welding deviation information sequence and the individual image welding deviation information sequence are input into the temperature welding deviation trend classifier and the image welding deviation trend classifier, respectively, to obtain temperature welding deviation fault trend information and image welding deviation fault trend information. Finally, the temperature welding deviation fault trend information and image welding deviation fault trend information are weighted and calculated, where the weights are set based on the actual situation, to obtain welding deviation fault trend information.

[0035] The method provided in this application embodiment further includes: analyzing and obtaining welding quality change trend information based on the welding quality information sequence; obtaining the current transmission delay for remote transmission; and classifying welding quality fault levels based on the welding quality change trend information; differentiating and allocating the welding quality fault levels according to the magnitude of the positioning deviation fault trend information and the welding deviation fault trend information to obtain a positioning quality impact level and a welding quality impact level, wherein the sum of the positioning quality impact level and the welding quality impact level is the welding quality fault level, and the ratio of the positioning quality impact level to the welding quality impact level is the same as the ratio of the positioning deviation fault trend information and the welding deviation fault trend information; and using the positioning quality impact level and the welding quality impact level as remote monitoring results.

[0036] Based on the welding quality information sequence, each welding quality information is extracted and deviation is calculated to obtain the quality deviation of the sequence. A first-order polynomial fitting is performed on the quality deviation of the sequence, and welding quality change trend information is obtained based on the fitting result. The transmission delay of the current remote transmission is obtained, and combined with the welding quality change trend information, welding quality fault levels are classified. Further, the positioning deviation fault trend information and welding deviation fault trend information are standardized. Based on the magnitude of the standardized positioning deviation fault trend information and welding deviation fault trend information, the welding quality fault levels are differentiated and allocated to obtain the positioning quality influence level and the welding quality influence level. The positioning quality influence level is the ratio of the standardized positioning deviation fault trend information to the sum of the standardized positioning deviation fault trend information and welding deviation fault trend information, multiplied by the welding quality fault level. The welding quality influence level is the ratio of the standardized positioning deviation fault trend information to the sum of the standardized positioning deviation fault trend information and welding deviation fault trend information, multiplied by the welding quality fault level. The sum of the positioning quality impact level and the welding quality impact level constitutes the welding quality fault level. The ratio of the positioning quality impact level to the welding quality impact level is the same as the ratio of the positioning deviation fault trend information and the welding deviation fault trend information. The positioning quality impact level and the welding quality impact level are used as remote monitoring results.

[0037] The method provided in this application embodiment further includes: collecting a set of sample transmission delays and a set of sample welding quality change trend information; setting a set of sample welding quality fault levels based on the magnitude of each sample transmission delay and sample welding quality change trend information, wherein the magnitude of the welding quality fault level is positively correlated with the magnitude of the transmission delay and the welding quality change trend information. Using the set of sample transmission delays and the set of sample welding quality change trend information as decision inputs, and using the set of sample welding quality fault levels as decision outputs, a welding quality classifier is constructed based on a decision tree. The welding quality classifier is used to classify the transmission delays and welding quality change trend information to obtain the welding quality fault levels.

[0038] When obtaining the welding quality fault level, a set of sample transmission delays and a set of sample welding quality change trend information are collected. Based on the magnitude of the transmission delay and welding quality change trend information for each sample, a set of sample welding quality fault levels is obtained through settings by professional technicians. These samples are historical transmission data samples. The magnitude of the welding quality fault level and the transmission delay are positively correlated with the magnitude of the welding quality change trend information. Subsequently, using the sample transmission delay set and the sample welding quality change trend information set as decision inputs, and the sample welding quality fault level set as the decision output, a welding quality classifier is constructed based on a decision tree. When the output of the trained welding classifier meets a preset accuracy rate, the trained welding quality classifier is obtained. Finally, the welding quality classifier is used to classify the transmission delay and welding quality change trend information to obtain the welding quality fault level.

[0039] The technical solution provided by this invention identifies the acquired positioning images to obtain a positioning deviation information sequence. Based on a temperature sensor, it collects temperature distribution data, identifies the temperature distribution, and obtains a temperature welding deviation information sequence. It also acquires a sequence of completed welding images, identifies them, and obtains an image welding deviation information sequence and a welding quality information sequence. Based on the positioning deviation information sequence, it obtains positioning deviation fault trend information. Combining the temperature welding and image welding deviation information sequences, it obtains welding deviation fault trend information. Based on the welding quality information sequence, and combining the positioning deviation fault trend information and the welding deviation fault trend information, it obtains the positioning quality impact level and the welding quality impact level. This solves the technical problems of low comprehensiveness of monitoring in existing PCB printed circuit board quality monitoring methods, leading to poor detection accuracy and low detection efficiency. It achieves real-time monitoring of the PCB welding process and comprehensive analysis and evaluation of the impact levels of the positioning and welding processes on product quality, improving the efficiency and accuracy of welding quality monitoring.

[0040] Note that the above description is merely a preferred embodiment of the present invention and the technical principles employed. Those skilled in the art will understand that the present invention is not limited to the specific embodiments described herein, and various obvious changes, readjustments, and substitutions can be made without departing from the scope of protection of the present invention. Therefore, although the present invention has been described in detail through the above embodiments, the present invention is not limited to the above embodiments, and may include many other equivalent embodiments without departing from the concept of the present invention, the scope of which is determined by the scope of the appended claims.

Claims

1. A method for remote intelligent monitoring of a production plant, characterized in that, The method includes: In the PCB soldering production workshop, images of the PCB after automatic positioning are continuously collected to obtain a positioning image sequence. The positioning images are then identified to obtain a positioning deviation information sequence, which is then transmitted remotely. During the welding process, temperature distribution data is monitored and collected based on temperature sensors to obtain a temperature distribution sequence. The temperature distribution is then identified to obtain a temperature welding deviation information sequence, which is then transmitted remotely. After welding is completed, images of the completed welding are acquired to obtain a welding image sequence. The welding images are then identified to obtain a sequence of image welding deviation information and a sequence of welding quality information, which are then transmitted remotely. The welding quality information serves as an evaluation parameter for the quality of the weld joint. Based on the positioning deviation information sequence, a positioning deviation fault trend analysis is performed to obtain positioning deviation fault trend information; Based on the temperature welding deviation information sequence and the image welding deviation information sequence, combined with the positioning deviation information sequence, welding deviation fault trend analysis is performed to obtain welding deviation fault trend information. Based on the welding quality information sequence, combined with the positioning deviation fault trend information and the welding deviation fault trend information, a differentiation analysis of the impact of positioning quality and welding quality is performed to obtain the impact level of positioning quality and the impact level of welding quality, which are then used as remote monitoring results for control. Based on the welding quality information sequence, combined with the positioning deviation fault trend information and the welding deviation fault trend information, a differentiation analysis of the impact of positioning quality and welding quality is performed to obtain the impact levels of positioning quality and welding quality, which are used as remote monitoring results, including: Based on the welding quality information sequence, the trend information of welding quality change is obtained through analysis; The transmission delay of the current remote transmission is obtained, and the welding quality change trend information is combined to classify and obtain the welding quality fault level. Based on the magnitude of the positioning deviation fault trend information and the welding deviation fault trend information, the welding quality fault level is differentiated and allocated to obtain the positioning quality influence level and the welding quality influence level. The sum of the positioning quality influence level and the welding quality influence level is the welding quality fault level, and the ratio of the positioning quality influence level and the welding quality influence level is the same as the ratio of the positioning deviation fault trend information and the welding deviation fault trend information. The positioning quality impact level and welding quality impact level are used as remote monitoring results; The transmission delay of the current remote transmission is obtained, and combined with the welding quality change trend information, the welding quality fault levels are classified and obtained, including: Collect a set of sample transmission delays and a set of sample welding quality change trend information. Based on the magnitude of the transmission delay and the sample welding quality change trend information for each sample, set a set of sample welding quality fault levels is obtained. Using the sample transmission delay set and the sample welding quality change trend information set as decision inputs, and the sample welding quality fault level set as decision outputs, a welding quality classifier is constructed based on a decision tree. The welding quality classifier is used to classify the transmission delay and welding quality change trend information to obtain the welding quality fault level.

2. The remote intelligent monitoring method for a production plant according to claim 1, characterized in that, In the PCB soldering production workshop, images of the PCB after automatic positioning are continuously acquired to obtain a positioning image sequence, and the positioning images are then identified, including: In the PCB soldering production workshop, after the PCB is automatically positioned, images of the automatic positioning are collected sequentially to obtain a positioning image sequence. Collect a set of sample positioning images, mark the magnitude of the PCB's deviation from the standard positioning area in each positioning image, and obtain a set of sample positioning deviation information. The positioning deviation recognizer is trained using the sample positioning image set and the sample positioning deviation information set. The positioning deviation identifier is used to identify multiple positioning images within the positioning image sequence, obtain a positioning deviation information sequence, and transmit it remotely.

3. The remote intelligent monitoring method for a production plant according to claim 1, characterized in that, During the welding process, temperature distribution data is monitored and collected using temperature sensors to obtain a temperature distribution sequence, and the temperature distribution is identified, including: During the welding process, temperature distribution data of the PCB is monitored and collected sequentially based on temperature sensors to obtain a temperature distribution sequence; Collect a set of sample temperature distributions, and mark the deviations of high-temperature points within the sample temperature distributions from the standard welding temperature to obtain a set of sample temperature welding deviation information. The temperature welding deviation analyzer is trained using the sample temperature distribution set and the sample temperature welding deviation information set. The temperature welding deviation analyzer is used to identify welding deviations in multiple temperature distributions within the temperature distribution sequence, obtain a temperature welding deviation information sequence, and transmit it remotely.

4. The remote intelligent monitoring method for a production plant according to claim 1, characterized in that, After welding is completed, images of the welded section are acquired to obtain a welding image sequence. The welding images are then identified, including: After welding is completed, images of the welded PCB are acquired sequentially to obtain a welding image sequence; Collect a set of sample welding images, and mark the deviation of the weld point from the standard welding position in each sample welding image to obtain a set of sample image welding deviation information; The deviation of the weld quality in each sample welding image from the standard weld quality is marked to obtain a set of sample welding quality information. The image welding deviation analysis branch is trained using the sample welding image set and the sample image welding deviation information set. Using the sample welding image set and sample welding quality information set, a welding quality analysis branch is trained, and combined with the image welding deviation analysis branch, a welding image recognizer is obtained; The welding image recognizer is used to identify multiple welding images within the welding image sequence, obtain a sequence of image welding deviation information and a sequence of welding quality information, and transmit them remotely.

5. The remote intelligent monitoring method for a production plant according to claim 1, characterized in that, Based on the positioning deviation information sequence, a positioning deviation fault trend analysis is performed to obtain positioning deviation fault trend information, including: Based on the automatic positioning monitoring data of the PCB, a set of sample positioning deviation information sequences is collected, and based on the change amplitude of the positioning deviation information in each sample positioning deviation information sequence, a set of sample positioning deviation fault trend information is obtained. A positioning deviation trend classifier is constructed using the sample positioning deviation information sequence set and the sample positioning deviation fault trend information set. The positioning deviation information sequence is input into the positioning deviation trend classifier to obtain positioning deviation fault trend information.

6. The remote intelligent monitoring method for a production plant according to claim 1, characterized in that, Based on the temperature welding deviation information sequence and the image welding deviation information sequence, combined with the positioning deviation information sequence, welding deviation fault trend analysis is performed to obtain welding deviation fault trend information, including: Based on the PCB soldering position monitoring data, a set of sample temperature soldering deviation information sequences and a set of sample image soldering deviation information sequences with a positioning deviation of 0 are collected. Based on the change amplitude of the soldering deviation within each sample temperature soldering deviation information sequence and sample image soldering deviation information sequence, a set of sample soldering deviation fault trend information is obtained. The temperature welding deviation information sequence set and the image welding deviation information sequence set are used respectively, and combined with the sample welding deviation fault trend information set, to construct a temperature welding deviation trend classifier and an image welding deviation trend classifier; The deviation of the positioning deviation information sequence is removed from the temperature welding deviation information sequence and the image welding deviation information sequence to obtain a separate temperature welding deviation information sequence and a separate image welding deviation information sequence. The variation amplitudes of the individual temperature welding deviation information sequence and the individual image welding deviation information sequence are respectively input into the temperature welding deviation trend classifier and the image welding deviation trend classifier to obtain temperature welding deviation fault trend information and image welding deviation fault trend information. Welding deviation fault trend information is obtained by weighting the temperature welding deviation fault trend information and the image welding deviation fault trend information.

Images