Study on Machine Learning Based Intelligent Defect Detection System

Abstract

In the paper, it is proposed to develop a machine learning based intelligent defect detection system for metal products. The common machine vision system has the surface (stain, shallow pit, shallow tumor, scratches, Edge defects, pattern defects) detection, or for the processing of the size, diameter, diameter, eccentricity, height, thickness and other parts of the non-contact numerical parameters of detection. Considering the quality of the work piece and the defects of the standard, so for the quality of customized testing requirements, the study is the development of machine vision and machine learning metal products defect detection system, mainly composed of three procedures: Image preprocessing, training procedures and testing procedures. The system architecture consists of three parts: (1) Image preprocessing: we first use the machine vision. OPENCV to carry out the image pre-processing part of the product before the detection. (2) Training procedures: The algorithm of the machine learning includes the convolution neural network (CNN), chunk-max pooling is used to train the program, and the generative adversarial network (GAN) based architecture is used to solve the problem of small datasets for surface defects. (3) Testing procedures：The Python language is used to write the program and implement the testing procedures with the GPU-Based embedded hardware In industries, collecting training dataset is usually costly and related methods are highly dataset-dependent. So most companies cannot provide Big-data to be analyzed or applied. By the experimental results, the recognition accuracy can be obviously improved as increasing data augmentation by GAN-Based samples maker. Manual inspection is labor intensive, costly and less in efficiency. Therefore, this study will contribute to technological innovation, industry, national development and other applications. (1) The use of intelligent machine learning technology will make the industry 4.0 technology more sophisticated. (2) It will make the development of equipment industry be better by the machine learning applications. (3) It will increase the economics and productivity of countries for the aging of the population by machine learning.

A more reliable defect detection and performance improvement method for panel inspection based on artificial intelligence

“…Equation ( 1) is the loss function of the segmentation and classification network. Our proposed network learns to minimize the total cost of Equation (2). Weights α and β in Equation ( 2) are user-defined values for segmentation and classification performance control.…”

“…They also posed a challenge in setting numerical criteria for distinguishing real defects from fake or allowable defects. To overcome the limitations of conventional inspection algorithms, deep learning (DL) methods [1,2] have recently been widely explored. For a DL-based inspection algorithm to be a successful alternative to conventional algorithms, two key requirements must be satisfied.…”

Deep Learning aplicado a inspeção visual da presença de um componente de conjunto de eixo

“…As redes neurais que se enquadram no conceito de DL são chamadas de deep neural networks (DNNs) [9]. O reconhecimento de imagens com essas redes tem a vantagem de não distinguir a segmentação, extração de características, e classificação, aprendendo das imagens as características, diferente da abordagem clássica de reconhecimento de padrões, onde há uma engenharia de características projetada por humanos [17] [48] [10]. Além disso, é possível que o DL produza um melhor desempenho de classificação, pois muitas vezes as técnicas clássicas de limiar são insuficientes para segmentar defeitos de fundo se não houver um ambiente controlado e com iluminação estável [49].…”

“…Alguns exemplos desse tipo de aplicação são: um método proposto para detecção automática da presença de componentes em placas de circuito impresso e bombas de injeção utilizando a rede neural Multi-Layer Perceptron (MLP) [14]; método para detecção de componentes (o'ring) utilizando o classificador Gaussian Mixture Models (GMM) [3]; detecção de grampos de fixação em uma peça estampada utilizando um classificador neuro-fuzzy e um classificador baseado em limites [15]; e detecção de componentes de transformadores elétricos utilizando um modelo baseado em Faster Regionbased Convolutional Neural Network [16]. O uso dessas tecnologias está em rápida expansão, muitas vezes criando novas formulações de problemas impulsionados por aplicações práticas [8], e devem fazer a Indústria 4.0 mais sofisticada [17].…”

A Low Cost Solution for Automatic Plastic Segregation

“…Audio signals from different materials are transformed to data sets that represents the material explicitly using feature engineering. [4][5][6][7] There are many feature extraction techniques for audio signal [19] and these feature extraction methods use both spectral, and joint time-frequency signal representation. Artificial Neural Network is the classifier used to classify the feature database.…”