data-driven SPI defect type intelligent identification method on an SMT production line

Abstract

The invention discloses a data-driven SPI defect type intelligent identification method on an SMT production line. The method comprises the following steps of in a first stage, carrying out clusteringprocessing on SPI historical quality detection data sets, independently sampling the obtained K types of training data sets for 20 times by adopting a Bagging algorithm, and respectively training independent defect classifiers for K types of K * 20 groups of training sets by utilizing a BP neural network model to obtain K * 20 independent defect classifiers to form a classifier set; in A second stage, detecting 6 solder paste printing quality parameters online; comparing with a historical training data set to classify the detection records T; determining which category of the real-time detection point belongs to the K categories of training data sets, and when T is just located on the boundary of two or more categories of training data sets, simultaneously selecting twenty independent defect classifiers from the multiple categories of K categories of training data sets according to approximately equal quantity to carry out category judgment of detection records T; And inputting T intoeach independent defect classifier, carrying out integrated prediction on an output result according to an integration rule, and judging a defect type. According to the invention, the effect of people in automatic detection is reduced, and the online real-time detection efficiency and accuracy are improved.

Description

technical field [0001] The invention relates to the field of online detection and prediction of production and processing quality, and specifically relates to a data-driven intelligent identification method for SPI defect categories on an SMT production line. Background technique [0002] In intelligent manufacturing, online quality detection and prediction technology is one of the key technologies to improve quality management capabilities and build intelligent production lines. The application of online quality automatic detection and prediction reduces manual detection operations, improves the consistency and stability of quality detection results, detection speed and accuracy of detection results, and avoids the time and cost caused by false positives and missed quality problems to a certain extent. cost loss. With the continuous innovation of science and technology and the rapid development of miniaturization of electronic products, higher requirements are placed on th...

AI Technical Summary

Problems solved by technology

With the continuous innovation of science and technology and the rapid development of miniaturization of electronic products, higher requirements are placed on the automation and intelligence of Surface Mount Technology (SMT, Surface Mount Technology). Among them, the quality inspection SPI (Solder Paste Inspection) technology of solder paste printing has passed The 3D-SPI automatic detection technology detects the volume, area, height, offset and sharpening of the solder paste on the pad, and identifies the quality results according to the upper and lower limits of each detection parameter set by the quality process control. However, in the actual production process, the The upper and lower control limits of detection parameters such as volume, height, area, and position offset are set by operators based on experience. Therefore, the false alarm rate and false negative rate in actual production are very high. Traditional process quality control methods poor optimization

[0003] With the rise of data mining technology, machine learning and other methods, more intelligent data-based intelligent quality prediction and control schemes have been designed, and these methods can effectively use quality The historical data of online inspection, fully learn and mine the correlation between inspection data and quality results, and record and display them in the form of learning models. Currently, the application of this technology in the field of online inspection and quality prediction is mostly concentrated on equipment. For SMT There are few applications in the production line, and the quality identification of the SPI inspection link is still in the current situation where the upper and lower limits of the inspection parameters are set by manual experience.

Images