Quality evaluation method for SMT surface assembly component welding spots based on edge side model processing

Abstract

The invention discloses a quality evaluation method for SMT surface assembly component welding spots based on edge side model processing, and the method comprises the steps: collecting data resources,and constructing a welding spot knowledge base; preprocessing the data; constructing a BP neural network model; extracting a data sample, and performing coding analysis on the key influence factor data influencing the welding spot quality through a BP neural network model; evaluating and correcting the BP neural network model; collecting key influence factors of the welding spot quality online inreal time, performing real-time judgment through the BP neural network model, and obtaining a feedback result; and according to the feedback result, optimizing the BP neural network model and outputting a final defect category. According to the invention, the neural network model can be trained by means of the edge device, an intelligent service platform for quickly feeding back a result is provided for a user, the process parameters are corrected according to the adjustment value, the operation of a predetermined design scheme of the machine device is guided, and the formation of welding spots is accurately controlled.

Description

technical field [0001] The invention relates to the technical field of intelligent manufacturing, in particular to a method for evaluating the quality of solder joints of SMT surface assembly components based on edge-side model processing. Background technique [0002] Surface mount technology (Surface Mounted Technology, SMT) is currently the most popular technology and process in the electronic assembly industry. It is a circuit assembly technology that is mounted on the surface of a printed circuit board (PCB) or other substrates, and soldered and assembled by reflow soldering or dip soldering. [0003] At present, the quality assessment of solder joints usually adopts inspection methods: one is the visual inspection method, with the aid of a magnifying glass with or without illumination and a magnification of 2-5 times, the quality of solder joints is inspected with the naked eye, such as In case of disputes, a magnifying glass with a magnification of 10 times or more c...

AI Technical Summary

Problems solved by technology

The disadvantage of these two methods is that they need to rely on the experience of the operator, and due to the limitation of manual experience, these two methods often produce large errors

Although this method has good advantages, it also has deficiencies to a certain extent, mainly in that there are many factors affecting the welding quality of spot welding, such as process parameters (welding current, voltage between electrodes, preloading time, electrode pressure, Welding time, maintenance time, electrode size, etc.) factors and some non-process parameters (welding contact surface state, base metal composition, spot welding machine power supply performance, etc.)

These factors have the characteristics of high nonlinearity and mutual coupling, which make the welding process very complicated, especially the welding nugget of spot welding is in a closed space state, no matter during or after welding. The size of the weld nugget can be directly observed, which increases the difficulty of obtaining the quality information of the weld joint

[0005] In addition, using the traditional neural network to complete the model training process is very time-consuming and will take up a lot of resources, reducing the efficiency of data processing

Images