RESUMEN
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.
RESUMEN
The purpose of this study was to fabricate a force sensor. A novel three-dimensional carbon-based material called a carbon nano-flake ball (CNFB) was used because it exhibits a large surface-area and high electrical conductivity. Moreover, CNFB can be easily fabricated using a one-step process via microwave plasma chemical vapor deposition. In the present study, two different methods, chemical and mechanical exfoliation, were used to fabricate the CNFB thin films. CNFEs were successfully synthesized on the silicon-based composite substrate. The substrate was constructed by the Si, SiO2, and Al2O3, where Al2O3played the role of the substrate for the force sensor while SiO2was the interface layer and was removed in the process by hydrogen fluoride (HF) solution to separate Al2O3from Silicon. The experiments showed that using sol-gel catalyst coating as pretreatment precursor, results in a larger ball-size but lower deposition density of CNFB on Al2O3substrate. By using mechanical exfoliation by polyimide (PI) tape, the CNFB grown on silicon substrate can be easily exfoliated from the substrate. PI/CNFB was successfully exfoliated from the substrate with a silver-grey color at the bottom of the CNFB which is likely to be silicon carbide (SiC) from the energy dispersive spectrometer analysis. The sheet resistance of PI/CNFB was 18.3 ± 1.0 Ω sq.-1PI/CNFB exhibits a good force sensing performance with good stability after 10 times of loading-unloading cycles and a good sensitivity of 11.6 Ω g-1.
RESUMEN
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.
RESUMEN
Force measurement is a science discipline that experiences significant progress with the introduction of new materials and evaluation methods. Many different sensor types, working on different principles, have been developed and reviewed and have found use in medicine as well as many other industries. New trends and demands require a size reduction and simple applicability, with the use of, for example, micro electromechanical systems (MEMS). For purposes of this study, the initial MEMS body is supplemented by its scaled version. Force measurement in this study works on the force to time-delay conversion principle. A compact compliant mechanical body (CCMB) with an embedded parallel resonant circuit (PRC) acting as a transducer realizes the conversion. Depending on the resonant frequency of the transducer (CCMB or MEMS), we have measured the applied force based on the reverse influence of the transducer on the surrounding EM field. The analysis shows that the transducer's resonant frequency has a detectable reverse influence on the voltage-controlled oscillator (VCO) DC supply current. The force influencing the transducer is determined by the DC supply current ripple position during the VCO frequency sweep. The study presents the method proposal and mathematical analysis, as well as its function verification by simulation and prototype measurements. The proposed principle was validated on a CCMB prototype capable of measuring forces up to â¼2.5 N at a sampling frequency of â¼23 kHz, while the measured time-delay ranges from 14.5 µs to 27.4 µs.
RESUMEN
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.