ANN Based Fault Classification of High Speed Ball Bearings

2009 ◽  
Author(s):  
Aashish Bhatnagar ◽  
P. K. Kankar ◽  
Satish C. Sharma ◽  
S. P. Harsha
Keyword(s):  
High Speed ◽  
Fault Analysis ◽  
Fault Classification ◽  
Wavelet Filter ◽  
Vibration Signals ◽  
Training Time ◽  
Outer Race ◽  
Key Issues ◽  
The Time Domain ◽  
Vibration Signatures

In the rotating machines, maintenance of the high speed operated bearings is the major problem and is one of the key issues due to excessive vibrations. Hence, the vibration signatures can be used as a feature for the fault diagnosis. This paper presents the Artificial Neural Networks (ANN) based fault analysis, which is used to classify various known faults using the features extracted from the vibration signals. The vibration signals from the piezoelectric accelerometers are being measured for the following conditions — No defect (NOD), Outer race defect (ORD), Inner race defect (IRD), Ball fault (BF) and Combination of above (COMB). The features are extracted from the time domain using the statistical method. These features are filtered using wavelet filter & kernel filter and compiled as the input vectors. The multilayer neural network is trained by these input vectors. The training and testing results show that wavelet and kernel filter can be effective tool in the diagnosis of ball bearing faults using ANN. Results obtained from the ANN predict that the wavelet filter provides good accuracy with reduction in the training time.

scholarly journals Confirmation of Thermal Images and Vibration Signals for Intelligent Machine Fault Diagnostics

2012 ◽  
Vol 2012 ◽  
pp. 1-10 ◽  
Author(s):  
Achmad Widodo ◽  
Djoeli Satrijo ◽  
Toni Prahasto ◽  
Gang-Min Lim ◽  
Byeong-Keun Choi
Keyword(s):  
Vibration Signal ◽  
Rolling Element Bearing ◽  
Self Organizing Map ◽  
Fault Diagnostics ◽  
Vibration Signals ◽  
Thermal Images ◽  
Outer Race ◽  
Intelligent Machine ◽  
Machine Fault ◽  
The Time Domain

This paper deals with the maintenance technique for industrial machinery using the artificial neural network so-called self-organizing map (SOM). The aim of this work is to develop intelligent maintenance system for machinery based on an alternative way, namely, thermal images instead of vibration signals. SOM is selected due to its simplicity and is categorized as an unsupervised algorithm. Following the SOM training, machine fault diagnostics is performed by using the pattern recognition technique of machine conditions. The data used in this work are thermal images and vibration signals, which were acquired from machine fault simulator (MFS). It is a reliable tool and is able to simulate several conditions of faulty machine such as unbalance, misalignment, looseness, and rolling element bearing faults (outer race, inner race, ball, and cage defects). Data acquisition were conducted simultaneously by infrared thermography camera and vibration sensors installed in the MFS. The experimental data are presented as thermal image and vibration signal in the time domain. Feature extraction was carried out to obtain salient features sensitive to machine conditions from thermal images and vibration signals. These features are then used to train the SOM for intelligent machine diagnostics process. The results show that SOM can perform intelligent fault diagnostics with plausible accuracies.

scholarly journals A Fault Diagnosis and Visualization Method for High-Speed Train Based on Edge and Cloud Collaboration

2021 ◽  
Vol 11 (3) ◽  
pp. 1251
Author(s):  
Kunlin Zhang ◽  
Wei Huang ◽  
Xiaoyu Hou ◽  
Jihui Xu ◽  
Ruidan Su ◽  
...  
Keyword(s):  
Fault Diagnosis ◽  
Real Time ◽  
Transfer Learning ◽  
High Speed ◽  
Visual Analysis ◽  
Monitoring Data ◽  
Fault Classification ◽  
Training Time ◽  
Diagnosis Model ◽  
Sensor Monitoring

Safety is the most important aspect of railway transportation. To ensure the safety of high-speed trains, various train components are equipped with sensor devices for real-time monitoring. Sensor monitoring data can be used for fast intelligent diagnosis and accurate positioning of train faults. However, existing train fault diagnosis technology based on cloud computing has disadvantages of long processing times and high consumption of computing resources, which conflict with the real-time response requirements of fault diagnosis. Aiming at the problems of train fault diagnosis in the cloud environment, this paper proposes a train fault diagnosis model based on edge and cloud collaboration. The model first utilizes a SAES-DNN (stacked auto-encoders deep neural network) fault recognition method, which can integrate automatic feature extraction and type recognition and complete fault classification over deep hidden features in high-dimensional data, so as to quickly locate faults. Next, to adapt to the characteristics of edge computing, the model applies a SAES-DNN model trained in the cloud and deployed in the edge via the transfer learning strategy and carries out real-time fault diagnosis on the vehicle sensor monitoring data. Using a motor fault as an example, when compared with a similar intelligent learning model, the proposed intelligent fault diagnosis model can greatly improve diagnosis accuracy and significantly reduce training time. Through the transfer learning approach, adaptability of the fault diagnosis algorithm for personalized applications and real-time performance of the fault diagnosis is enhanced. This paper also proposes a visual analysis method of train fault data based on knowledge graphs, which can effectively analyze fault causes and fault correlation.

Fault analysis on continuous variable transmission using DB-06 wavelet decomposition and fault classification using ANN

2021 ◽  
pp. 1-11
Author(s):  
T. Narendiranath Babu ◽  
N. Senthilnathan ◽  
Shailesh Pancholi ◽  
S.P. Nikhil Kumar ◽  
D. Rama Prabha ◽  
...  
Keyword(s):  
Large Scale ◽  
Continuous Variable ◽  
Fault Analysis ◽  
Fault Classification ◽  
Classification Rate ◽  
Vibration Data ◽  
Continuous Variable Transmission ◽  
Variable Transmission ◽  
Data Points ◽  
The Time Domain

This study aims at developing a novel method for condition monitoring technique for detection and classification of developing faults and increase the working life of continuous variable transmission (CVT) using Daubechies Wavelet 06 (DB-06). The vibration data is collected for 4 different types of faults and healthy condition. Using a magnetic accelerometer and signal analyser, vibration data is collected from the system in the time-domain which is then used as input for a MATLAB code producing the plot of the frequency-domain signal. Maximum frequency is determined to diagnose the faults which are induced over three different belts. Collected data for large scale automotive system (CVT) is used to train the network and then it is tested based on random data points. Faults were classified using ANN with a classification rate of 90.8 %.

scholarly journals Multiview deep learning based on tensor decomposition and its application in fault detection of overhead contact systems

2021 ◽  
Author(s):  
Xuewu Zhang ◽  
Yansheng Gong ◽  
Chen Qiao ◽  
Wenfeng Jing
Keyword(s):  
High Speed ◽  
Tensor Decomposition ◽  
Detection Methods ◽  
Detection Accuracy ◽  
Feature Maps ◽  
Training Time ◽  
Detection Model ◽  
Railway Line ◽  
Result Show ◽  
Deep Layers

AbstractThis article mainly focuses on the most common types of high-speed railways malfunctions in overhead contact systems, namely, unstressed droppers, foreign-body invasions, and pole number-plate malfunctions, to establish a deep-network detection model. By fusing the feature maps of the shallow and deep layers in the pretraining network, global and local features of the malfunction area are combined to enhance the network's ability of identifying small objects. Further, in order to share the fully connected layers of the pretraining network and reduce the complexity of the model, Tucker tensor decomposition is used to extract features from the fused-feature map. The operation greatly reduces training time. Through the detection of images collected on the Lanxin railway line, experiments result show that the proposed multiview Faster R-CNN based on tensor decomposition had lower miss probability and higher detection accuracy for the three types faults. Compared with object-detection methods YOLOv3, SSD, and the original Faster R-CNN, the average miss probability of the improved Faster R-CNN model in this paper is decreased by 37.83%, 51.27%, and 43.79%, respectively, and average detection accuracy is increased by 3.6%, 9.75%, and 5.9%, respectively.

Analysis of faults in rotor-bearing system using three-level full factorial design and response surface methodology

2021 ◽  
pp. 095745652110307
Author(s):  
Hara P Mishra ◽  
Arun Jalan
Keyword(s):  
Response Surface Methodology ◽  
Response Surface ◽  
Fault Analysis ◽  
Vibration Response ◽  
Effect Analysis ◽  
Outer Race ◽  
Surface Plot ◽  
Rotor Bearing ◽  
Full Factorial ◽  
Bearing System

This article presents the experimental and statistical methodology for localized fault analysis in the rotor-bearing system. These defects on outer race, on inner race, and on a combination of ball and outer race are considered. In this study speed, load and defects were considered as the essential process variables to understand their significance and effects on vibration response for the rotor-bearing system. Three factors at three levels were considered for experimentation, and the experiment was designed for L27 based on design of experiments (DOE) methodology. From the experiments, the vibration response results are recorded in terms of root mean square value for the analysis. Response surface methodology (RSM) is used for identifying the interaction effect of varying process parameters upon the response of vibrations by response surface plot. The rotor-bearing test setup is used for experimentation and is analyzed by using DOE. This study establishes the prediction of fault in the rotor-bearing system in combined parametric effect analysis and its influence with DOE and RSM.

An improved model for investigating the vibration characteristics of ball bearing owing to outer race waviness under high speed

2021 ◽  
Vol 69 (2) ◽  
pp. 89-101
Author(s):  
Pingping Hou ◽  
Liqin Wang ◽  
Zhijie Xie ◽  
Qiuyang Peng
Keyword(s):  
High Speed ◽  
Ball Bearing ◽  
Vibration Measurement ◽  
Vibration Frequencies ◽  
Outer Race ◽  
Response Characteristics ◽  
Lagrange’S Equation ◽  
Rolling Elements ◽  
Initial Clearance ◽  
Improved Model

In this study, an improved model for a ball bearing is established to investigate the vibration response characteristics owing to outer race waviness under an axial load and high speed. The mathematical ball bearing model involves the motions of the inner ring, outer ring, and rolling elements in the radial XY plane and axial z direction. The 2Nb + 5 nonlinear differential governing equations of the ball bearing are derived from Lagrange's equation. The influence of rotational speed and outer race waviness is considered. The outer race waviness is modeled as a superposition of sinusoidal function and affects both the contact deformation between the outer raceway and rolling elements and initial clearance. The MATLAB stiff solver ODE is utilized to solve the differential equations. The simulated results show that the axial vibration frequency occurred at l fc and the radial vibration frequencies appeared at l fc fc when the outer race waviness of the order (l) was the multiple of the number of rolling elements (k Nb) and that the principal vibration frequencies were observed at l fc fc in the radial x direction when the outer race waviness of the order (l) was one higher or one lower than the multiple of the number of rolling elements (k Nb 1). At last, the validity of the proposed ball bearing model was verified by the high-speed vibration measurement tests of ball bearings.

Application of PLC Pulse Command in the Step Motor Position Control

2011 ◽  
Vol 130-134 ◽  
pp. 3954-3957
Author(s):  
Liu Wei
Keyword(s):  
Motor Control ◽  
High Speed ◽  
Position Control ◽  
Step Motor ◽  
Stepper Motor ◽  
Equipment Selection ◽  
Stepper Motor Control ◽  
Key Issues ◽  
Pulse Output

Mitsubishi FX2n series PLC's CPU module comes with high-speed pulse output channels. Using these channels, you can achieve position control of stepper motor. This article describes the use of high-speed pulse output instruction on the stepper motor control to achieve the design points. Contents include: key issues of PLC equipment selection, use of pulse command, and the stepper motor selection and setting.

Sign in / Sign up

Export Citation Format

Share Document