Deep Neural Network based Classification of Rolling Element Bearings and Health Degradation Through Comprehensive Vibration Signal Analysis

Abstract

Rolling element bearings are machine components used to allow circular movement and hence deliver forces between components of machines used in diverse areas of industry. The likelihood of failure has the propensity of increasing under prolonged operation and varying working conditions. Hence, the accurate fault severity categorization of bearings is vital in diagnosing faults that arise in rotating machinery. The variability and complexity of the recorded vibration signals pose a great hurdle to distinguishing unique characteristic fault features. In this paper, the efficacy and the leverage of a pre-trained convolutional neural network (CNN) is harnessed in the implementation of a robust fault classification model. In the absence of sufficient data, this method has a high-performance rate. Initially, a modified VGG16 architecture is used to extract discriminating features from new samples and serves as input to a classifier. The raw vibration data are strategically segmented and transformed into two representations which are trained separately and jointly. The proposed approach is carried out on bearing vibration data and shows high-performance results. In addition to successfully implementing a robust fault classification model, a prognostic framework is developed by constructing a health indicator (HI) under varying operating conditions for a given fault condition.

Phased array antenna diagnosis from amplitude-only data using parallel deep learning models

“…While Biswas et al 20 focused on array correction using artificial NN (ANN), Patnaik et al 21 proposed a method to figure out the location of failed array elements in different failure scenarios using ANNs. With the rapid growth of DL in medical diagnosis 22 and engineering applications, 23 some research have also considered the use of CNNs in array fault diagnosis. 8 3 System Description and Model Under Array Element Failure…”

“…proposed a method to figure out the location of failed array elements in different failure scenarios using ANNs. With the rapid growth of DL in medical diagnosis 22 and engineering applications, 23 some research have also considered the use of CNNs in array fault diagnosis 8 …”

DCEL: Classifier Fusion Model for Android Malware Detection

“…According to the Internet data center survey of International Data Corporation (IDC), as of the third quarter of 2020, the market share of Android operating system is 85.0% of the total mobile operating system [3]. In 2018, Wang et al [4] implemented a largescale analysis of six million Apps in 16 Chinese Android App markets and the Google Play market. Approxi-mately 12.30% of Apps in Chinese Android App markets were reported as malicious Apps based on at least 10 antivirus engines.…”

“…(ii) A new classifier fusion classification mechanism based on deep learning is proposed. This mechanism first performs data preprocessing on the original data, removes some redundant data, converts the one-dimensional data into a two-dimensional gray image, and uses the convolutional neural network (CNN) algorithm [16] to train the gray image to generate model 1. At the same time, different levels of deep neural networks (DNN) [17] are used to train one-dimensional data to generate model 2 and model 3.…”

Rolling Bearing Fault Diagnostics Based on Improved Data Augmentation and ConvNet

“…In recent years, the advancement and implementation of deep learning (DL) in component diagnostics, prognostics [4,5] and image classifications [6−8] has motivated research in the application of such models in bearing fault diagnostics [9,10]. This research aims to leverage the capabilities of a convolutional neural network (CNN), which comprises sequentially composed layers of convolution and pooling operations, in establishing an effective fault classification model.…”