Bathroom plastic part defect identification method, device and equipment

Abstract

The invention discloses a bathroom plastic part defect identification method, device and equipment. The method comprises the steps of acquiring a bathroom plastic part and an actual mold cavity pressure curve of the bathroom plastic part in the injection molding process; comparing the actual die cavity pressure curve with a standard die cavity pressure curve to obtain a variation curve section ofthe actual die cavity pressure curve; obtaining a potential defect position corresponding to the variation curve segment; acquiring an image of a predetermined visual angle of the bathroom plastic part corresponding to the potential defect position; and extracting features of the image, and inputting the features into a pre-trained neural network model to judge whether the bathroom plastic part has defects or not and the types of the defects. According to the invention, the defect identification efficiency of the bathroom plastic part can be improved.

Description

technical field [0001] The invention relates to the field of sanitary ware, in particular to a method, device and equipment for predicting defects of plastic parts of sanitary ware. Background technique [0002] In the molding process of plastic products, due to the variety of plastic raw materials, the complex structure of the mold cavity, the different control and operation states of the molding equipment, and the differences in the rheology and mechanical properties of the molding materials, various plastic products will be produced. Various molding defects. Generally, the factors related to the quality (defect) of plastic products are: appearance, dimensional accuracy, and functional content. [0003] The elements of appearance are related to the appearance and practicability of the product, and the poor appearance of the product is closely related to the injection conditions; the dimensional accuracy of the product is an important quality factor when it is used as vari...

AI Technical Summary

Problems solved by technology

(2) Process problems: insufficient filling, excessive flash on the parting surface, mold sticking in the runner, abnormal ejection, etc.

(3) Performance problems: brittleness, warping, stress concentration, overweight and underweight (uneven density), etc.

At present, after the products are produced, it is necessary to conduct defect and performance testing on each product to separate the defective products. This method of separating defective products takes a lot of time and cost, and the efficiency is not high.

[0005] At present, artificial intelligence, such as the method of neural network model, is used to identify the defects of plastic parts. However, because the plastic parts are three-dimensional, and some plastic parts have complex structures (such as internal and external structures), the location of the defect is difficult to identify. Therefore, it may be necessary to input multiple pictures of different perspectives of plastic parts into the neural network model to determine whether there are defects in plastic parts, resulting in low detection efficiency

Images