Surface Defect Detection Methods for Industrial Products: A Review

The comprehensive intelligent development of the manufacturing industry puts forward new requirements for the quality inspection of industrial products. This paper summarizes the current research status of machine learning methods in surface defect detection, a key part in the quality inspection of industrial products. First, according to the use of surface features, the application of traditional machine vision surface defect detection methods in industrial product surface defect detection is summarized from three aspects: texture features, color features, and shape features. Secondly, the research status of industrial product surface defect detection based on deep learning technology in recent years is discussed from three aspects: supervised method, unsupervised method, and weak supervised method. Then, the common key problems and their solutions in industrial surface defect detection are systematically summarized; the key problems include real-time problem, small sample problem, small target problem, unbalanced sample problem. Lastly, the commonly used datasets of industrial surface defects in recent years are more comprehensively summarized, and the latest research methods on the MVTec AD dataset are compared, so as to provide some reference for the further research and development of industrial surface defect detection technology.

Comparison of International Codes for a Fatigue Crack Growth Flaw Tolerance Sample Problem

As part of the development of American Society of Mechanical Engineers Code Case N-809 [1], a series of sample calculations were performed to gain experience in using the Code Case methods and to determine the impact on a typical application. Specifically, the application of N-809 in a fatigue crack growth analysis was evaluated for a large diameter austenitic pipe in a pressurized water reactor coolant system main loop using the current analytical evaluation procedures in Appendix C of Section XI of the ASME Code [2]. The same example problem was previously used to evaluate the reference fatigue crack growth curves during the development of N-809, as well as to compare N-809 methods to similar methods adopted by the Japan Society of Mechanical Engineers. The previous example problem used to evaluate N-809 during its development was embellished and has been used to evaluate additional proposed ASME Code changes. For example, the Electric Power Research Institute investigated possible improvements to ASME Code, Section XI, Nonmandatory Appendix L [3], and the previous N-809 example problem formed the basis for flaw tolerance calculations to evaluate those proposed improvements [4]. In addition, the ASME Code Section XI, Working Group on Flaw Evaluation Reference Curves continues to evaluate additional research data and related improvements to N-809 and other fatigue crack growth rate methods. As a part of these Code investigations, EPRI performed calculations for the Appendix L flaw tolerance sample problem using three international codes and standards to evaluate fatigue crack growth (da/dN) curves for PWR environments: (1) ASME Code Case N-809, (2) JSME Code methods [5], and (3) the French RSE-M method [6]. The results of these comparative calculations are presented and discussed in this paper.

WMW-A: Rank-based two-sample independent test for small sample sizes through an auxiliary sample

Two-sample independent test methods are widely used in case-control studies to identify significant changes or differences, for example, to identify key pathogenic genes by comparing the gene expression levels in normal and disease cells. However, due to the high cost of data collection or labelling, many studies face the small sample problem, for which the traditional two-sample test methods often lose power. We propose a novel rank-based nonparametric test method WMW-A for small sample problem by introducing a three-sample statistic through another auxiliary sample. By combining the case, control and auxiliary samples together, we construct a three-sample WMW-A statistic based on the gap between the average ranks of the case and control samples in the combined samples. By assuming that the auxiliary sample follows a mixed distribution of the case and control populations, we analyze the theoretical properties of the WMW-A statistic and approximate the theoretical power. The extensive simulation experiments and real applications on microarray gene expression data sets show the WMW-A test could significantly improve the test power for two-sample problem with small sample sizes, by either available unlabelled auxiliary data or generated auxiliary data.

Multiscale Information Fusion for Hyperspectral Image Classification Based on Hybrid 2D-3D CNN

Hyperspectral images are widely used for classification due to its rich spectral information along with spatial information. To process the high dimensionality and high nonlinearity of hyperspectral images, deep learning methods based on convolutional neural network (CNN) are widely used in hyperspectral classification applications. However, most CNN structures are stacked vertically in addition to using a onefold size of convolutional kernels or pooling layers, which cannot fully mine the multiscale information on the hyperspectral images. When such networks meet the practical challenge of a limited labeled hyperspectral image dataset—i.e., “small sample problem”—the classification accuracy and generalization ability would be limited. In this paper, to tackle the small sample problem, we apply the semantic segmentation function to the pixel-level hyperspectral classification due to their comparability. A lightweight, multiscale squeeze-and-excitation pyramid pooling network (MSPN) is proposed. It consists of a multiscale 3D CNN module, a squeezing and excitation module, and a pyramid pooling module with 2D CNN. Such a hybrid 2D-3D-CNN MSPN framework can learn and fuse deeper hierarchical spatial–spectral features with fewer training samples. The proposed MSPN was tested on three publicly available hyperspectral classification datasets: Indian Pine, Salinas, and Pavia University. Using 5%, 0.5%, and 0.5% training samples of the three datasets, the classification accuracies of the MSPN were 96.09%, 97%, and 96.56%, respectively. In addition, we also selected the latest dataset with higher spatial resolution, named WHU-Hi-LongKou, as the challenge object. Using only 0.1% of the training samples, we could achieve a 97.31% classification accuracy, which is far superior to the state-of-the-art hyperspectral classification methods.

Kepraktisan Video Pembelajaran Kalkulus untuk Fisika dalam Proses Belajar Daring pada Masa Pandemi Covid-19

Corona virus disease (covid-19) has spread all over the world and became a pandemic in short time. Indonesia is one of the countries that affected by covid-19 pandemic. Covid-19 changed everything in various area including education. Online learning became one of the solutions in universities in order to keep learning process going. Unfortunately, policy to apply online learning is facing many difficulties associated with infra-structure, student economic capability and time management. Learning video is presented to overcome difficulties of online learning during covid-19 pandemic in subject of Calculus for Physics. The video presents material supported by sample problem and solution. Practicality of the learning video was examined by collecting student`s responses in aspect of ease of use, learning time efficiency, attractiveness and benefits. Data was analyzed using percentage formula to determine criteria of practicality. The result of the observation revealed that learning video of calculus for physics has a good practicality that represented by score of each aspects of 81,26% for ease of use, 83,53% for learning time efficiency, 79,87% for attractiveness and 81,08% for benefits. Based on this result we conclude that learning video is very useful to assist student in online learning during covid-19 pandemic. Furthermore, learning video could be one of the best choices in learning media to apply digital and remote learning in facing of Industrial Revolution 4.0.