From Anomaly Detection to Defect Classification.

This paper proposes a new approach to defect detection system design focused on exact damaged areas demonstrated through visual data containing gear wheel images. The main advantage of the system is the capability to detect a wide range of patterns of defects occurring in datasets. The methodology is built on three processes that combine different approaches from unsupervised and supervised methods. The first step is a search for anomalies, which is performed by defining the correct areas on the controlled object by using the autoencoder approach. As a result, the differences between the original and autoencoder-generated images are obtained. These are divided into clusters using the clustering method (DBSCAN). Based on the clusters, the regions of interest are subsequently defined and classified using the pre-trained Xception network classifier. The main result is a system capable of focusing on exact defect areas using the sequence of unsupervised learning (autoencoder)-unsupervised learning (clustering)-supervised learning (classification) methods (U2S-CNN). The outcome with tested samples was 177 detected regions and 205 occurring damaged areas. There were 108 regions detected correctly, and 69 regions were labeled incorrectly. This paper describes a proof of concept for defect detection by highlighting exact defect areas. It can be thus an alternative to using detectors such as YOLO methods, reconstructors, autoencoders, transformers, etc.

Autoencoders Based on 2D Convolution Implemented for Reconstruction Point Clouds from Line Laser Sensors.

Gradual development is moving from standard visual content in the form of 2D data to the area of 3D data, such as points scanned by laser sensors on various surfaces. An effort in the field of autoencoders is to reconstruct the input data based on a trained neural network. For 3D data, this task is more complicated due to the demands for more accurate point reconstruction than for standard 2D data. The main difference is in shifting from discrete values in the form of pixels to continuous values obtained by highly accurate laser sensors. This work describes the applicability of autoencoders based on 2D convolutions for 3D data reconstruction. The described work demonstrates various autoencoder architectures. The reached training accuracies are in the range from 0.9447 to 0.9807. The obtained values of the mean square error (MSE) are in the range from 0.059413 to 0.015829 mm. They are close to resolution in the Z axis of the laser sensor, which is 0.012 mm. The improvement of reconstruction abilities is reached by extracting values in the Z axis and defining nominal coordinates of points for the X and Y axes, where the structural similarity metric value is improved from 0.907864 to 0.993680 for validation data.

Design of the Automated Calibration Process for an Experimental Laser Inspection Stand.

This paper deals with the concept of the automated calibration design for inspection systems using laser sensors. The conceptual solution is based on using a laser sensor and its ability to scan 3D surfaces of inspected objects in order to create a representative point cloud. Problems of scanning are briefly discussed. The automated calibration procedure for solving problems of errors due to non-precise adjustment of the mechanical arrangement, possible tolerances in assembly, and their following elimination is proposed. The main goal is to develop a system able to measure and quantify the quality of produced objects in the environment of Industry 4.0. Laboratory measurements on the experimental stand, including the principal software solution for automated calibration of laser sensors suitable for gear wheel inspection systems are presented. There is described design of compensation eccentricity by Fourier transform and sinusoidal fitting to identify and suppress the first harmonic component in the data with high precision measuring.

Analysis of the Possibilities of Tire-Defect Inspection Based on Unsupervised Learning and Deep Learning.

At present, inspection systems process visual data captured by cameras, with deep learning approaches applied to detect defects. Defect detection results usually have an accuracy higher than 94%. Real-life applications, however, are not very common. In this paper, we describe the development of a tire inspection system for the tire industry. We provide methods for processing tire sidewall data obtained from a camera and a laser sensor. The captured data comprise visual and geometric data characterizing the tire surface, providing a real representation of the captured tire sidewall. We use an unfolding process, that is, a polar transform, to further process the camera-obtained data. The principles and automation of the designed polar transform, based on polynomial regression (i.e., supervised learning), are presented. Based on the data from the laser sensor, the detection of abnormalities is performed using an unsupervised clustering method, followed by the classification of defects using the VGG-16 neural network. The inspection system aims to detect trained and untrained abnormalities, namely defects, as opposed to using only supervised learning methods.

Analysis of Laser Sensors and Camera Vision in the Shoe Position Inspection System.

Inspection systems are currently an evolving field in the industry. The main goal is to provide a picture of the quality of intermediates and products in the production process. The most widespread sensory system is camera equipment. This article describes the implementation of camera devices for checking the location of the upper on the shoe last. The next part of the article deals with the analysis of the application of laser sensors in this task. The results point to the clear advantages of laser sensors in the inspection task of placing the uppers on the shoe's last. The proposed method defined the resolution of laser scanners according to the type of scanned surface, where the resolution of point cloud ranged from 0.16 to 0.5 mm per point based on equations representing specific points approximated to polynomial regression in specific places, which are defined in this article. Next, two inspection systems were described, where one included further development in the field of automation and Industry 4.0 and with a high perspective of development into the future. The main aim of this work is to conduct analyses of sensory systems for inspection systems and their possibilities for further work mainly based on the resolution and quality of obtained data. For instance, dependency on scanning complex surfaces and the achieved resolution of scanned surfaces.

Design of Smart Steering Wheel for Unobtrusive Health and Drowsiness Monitoring.

This article describes the design of a smart steering wheel intended for use in unobtrusive health and drowsiness monitoring. The aging population, cardiovascular disease, personalized medicine, and driver fatigue were significant motivations for developing a monitoring platform in cars because people spent much time in cars. The purpose was to create a unique, comprehensive monitoring system for the driver. The crucial parameters in health or drowsiness monitoring, such as heart rate, heart rate variability, and blood oxygenation, are measured by an electrocardiograph and oximeter integrated into the steering wheel. In addition, an inertial unit was integrated into the steering wheel to record and analyze the movement patterns performed by the driver while driving. The developed steering wheel was tested under laboratory and real-life conditions. The measured signals were verified by commercial devices to confirm data correctness and accuracy. The resulting signals show the applicability of the developed platform in further detecting specific cardiovascular diseases (especially atrial fibrillation) and drowsiness.