Explainable AI for Bearing Fault Prognosis Using Deep Learning Techniques

Abstract

Predicting bearing failures is a vital component of machine health monitoring since bearings are essential parts of rotary machines, particularly large motor machines. In addition, determining the degree of bearing degeneration will aid firms in scheduling maintenance. Maintenance engineers may be gradually supplanted by an automated detection technique in identifying motor issues as improvements in the extraction of useful information from vibration signals are made. State-of-the-art deep learning approaches, in particular, have made a considerable contribution to automatic defect identification. Under variable shaft speed, this research presents a novel approach for identifying bearing defects and their amount of degradation. In the proposed approach, vibration signals are represented by spectrograms, and deep learning methods are applied via pre-processing with the short-time Fourier transform (STFT). A convolutional neural network (CNN), VGG16, is then used to extract features and classify health status. After this, RUL prediction is carried out with the use of regression. Explainable AI using LIME was used to identify the part of the image used by the CNN algorithm to give the output. Our proposed method was able to achieve very high accuracy and robustness for bearing faults, according to numerous experiments.

A Two-Stage Screw Detection Framework for Automatic Disassembly Using a Reflection Feature Regression Model

“…It can also be expressed based on Equation (12) as where and denote the weight and bias of the linear regression function, respectively. In the following, Equation (21) is adopted to construct the regression model due to the availability of and , where the optimiser used is the Adam optimiser [ 34 ] and the loss function is defined as where denotes the predicted L value of the screw region and denotes the data length.…”

DCFF-MTAD: A Multivariate Time-Series Anomaly Detection Model Based on Dual-Channel Feature Fusion

“…Haleem et al [35] used short-time Fourier transform to convert ECG beats into 2D images to automatically distinguish normal ECG from cardiac adverse events such as arrhythmia and congestive heart failure. Sanakkayala et al [36] used short-time Fourier transform to convert bearing vibration signals into spectral graphs and then used the convolutional neural network VGG16 to extract features and classify health conditions.…”

Application and Prospect of Artificial Intelligence Methods in Signal Integrity Prediction and Optimization of Microsystems

“…In recent years, AI, as a modern discipline, has been widely used in performance prediction [ 37 , 38 , 39 , 40 ], floor planning [ 22 , 41 , 42 ], collaborative optimization [ 43 , 44 , 45 ], image recognition [ 46 , 47 , 48 , 49 ], defect detection [ 50 , 51 , 52 , 53 ], micromanufacturing processes [ 54 , 55 ] and other aspects of research, and has been successfully applied in microsystem SI design. The application of artificial intelligence methods to microsystem design is commonly divided into four steps [ 56 ]: (1) clarify the problem to be solved, determine the design parameters and performance parameters; (2) obtain data; (3) establish a neural networks model and use the acquired data to train neural networks to achieve performance prediction; and (4) optimize the performance through an intelligent optimization algorithm.…”