scholarly journals Fault Diagnosis of Rotation Vector Reducer for Industrial Robot Based on a Convolutional Neural Network

2021 ◽  
Vol 67 (10) ◽  
pp. 489-500
Author(s):  
Shuai Yang ◽  
◽  
Xing Luo ◽  
Chuan Li
Keyword(s):  
Neural Network ◽  
Fault Diagnosis ◽  
Convolutional Neural Network ◽  
Classification Accuracy ◽  
Industrial Robot ◽  
Rotation Vector ◽  
Fault Classification ◽  
Economic Losses ◽  
Network Training ◽  
Rv Reducer

As a key component of a mechanical drive system, the failure of the reducer will usually cause huge economic losses and even lead to serious casualties in extreme cases. To solve this problem, a two-dimensional convolutional neural network (2D-CNN) is proposed for the fault diagnosis of the rotation vector (RV) reducer installed on the industrial robot (IR). The proposed method can automatically extract the features from the data and reduce the connections between neurons and the parameters that need to be trained with its local receptive field, weight sharing, and subsampling features. Due to the aforementioned characteristics, the efficiency of network training is significantly improved, and verified by the experimental simulations. Comparative experiments with other mainstream methods are carried out to further validate the fault classification accuracy of the proposed method. The results indicate that the proposed method out-performs all the selected methods.

scholarly journals Exploiting graph neural network with one-shot learning for fault diagnosis of mechanical equipment

2021 ◽  
Vol 1207 (1) ◽  
pp. 012022
Author(s):  
Shuai Yang ◽  
Xu Chen ◽  
Yun Bai
Keyword(s):  
Neural Network ◽  
Fault Diagnosis ◽  
Industrial Robot ◽  
Industrial Robots ◽  
Fault Classification ◽  
Mechanical Equipment ◽  
Data Set ◽  
Feature Vectors ◽  
Public Data ◽  
Rv Reducer

Abstract For the classification of mechanical fault diagnosis, a graph neural network (GNN) method with one-shot learning is proposed. Convolutional Neural Network (CNN) is used to extract the feature vectors and One-Hot coding from images of Fault diagnosis of mechanical equipment. Inputting feature vectors and One-Hot coding into GNN, according to the Adjacency Matrix between vertices in the Graph, and is used for classification and inference. The method with one-shot learning is used for fault diagnosis classification. Through the fault classification for the industrial robot RV reducer and public data set CWRU pictures, the effectiveness of the method is verified. Five categories are used for fault diagnosis and classification in RV Reducer of the industrial robots. 80 categories are used in the public data set CWRU, and 55 categories are used as the training set. GNN is employed to spread the label information from the supervised sample of the unlabeled query data. The large-scale dataset can then be used as baseline classes to learn transferable knowledge for classifying novelties with one-shot samples. The one-shot learning with graph neural network GNN significantly improves the classification accuracy. The results show that the proposed method is superior to other similar methods and has a substantial potential for improvement in Fault diagnosis of mechanical equipment.

scholarly journals Intelligent Fault Diagnosis of Rotary Machinery by Convolutional Neural Network with Automatic Hyper-Parameters Tuning Using Bayesian Optimization

Sensors ◽  
2021 ◽  
Vol 21 (7) ◽  
pp. 2411
Author(s):  
Davor Kolar ◽  
Dragutin Lisjak ◽  
Michał Pająk ◽  
Mihael Gudlin
Keyword(s):  
Neural Network ◽  
Machine Learning ◽  
Fault Diagnosis ◽  
Convolutional Neural Network ◽  
Classification Accuracy ◽  
Bayesian Optimization ◽  
Intelligent Fault Diagnosis ◽  
Accelerometer Signal ◽  
Rotary Machinery

Intelligent fault diagnosis can be related to applications of machine learning theories to machine fault diagnosis. Although there is a large number of successful examples, there is a gap in the optimization of the hyper-parameters of the machine learning model, which ultimately has a major impact on the performance of the model. Machine learning experts are required to configure a set of hyper-parameter values manually. This work presents a convolutional neural network based data-driven intelligent fault diagnosis technique for rotary machinery which uses model with optimized hyper-parameters and network structure. The proposed technique input raw three axes accelerometer signal as high definition 1-D data into deep learning layers with optimized hyper-parameters. Input is consisted of wide 12,800 × 1 × 3 vibration signal matrix. Model learning phase includes Bayesian optimization that optimizes hyper-parameters of the convolutional neural network. Finally, by using a Convolutional Neural Network (CNN) model with optimized hyper-parameters, classification in one of the 8 different machine states and 2 rotational speeds can be performed. This study accomplished the effective classification of different rotary machinery states in different rotational speeds using optimized convolutional artificial neural network for classification of raw three axis accelerometer signal input. Overall classification accuracy of 99.94% on evaluation set is obtained with the CNN model based on 19 layers. Additionally, more data are collected on the same machine with altered bearings to test the model for overfitting. Result of classification accuracy of 100% on second evaluation set has been achieved, proving the potential of using the proposed technique.

scholarly journals A Deep Autoencoder-Based Convolution Neural Network Framework for Bearing Fault Classification in Induction Motors

Sensors ◽  
2021 ◽  
Vol 21 (24) ◽  
pp. 8453
Author(s):  
Rafia Nishat Toma ◽  
Farzin Piltan ◽  
Jong-Myon Kim
Keyword(s):  
Neural Network ◽  
Fault Diagnosis ◽  
Classification Accuracy ◽  
Classification Model ◽  
Data Driven ◽  
Fault Classification ◽  
Current Signal ◽  
Bearing Fault ◽  
Motor Current ◽  
Diagnosis And Classification

Fault diagnosis and classification for machines are integral to condition monitoring in the industrial sector. However, in recent times, as sensor technology and artificial intelligence have developed, data-driven fault diagnosis and classification have been more widely investigated. The data-driven approach requires good-quality features to attain good fault classification accuracy, yet domain expertise and a fair amount of labeled data are important for better features. This paper proposes a deep auto-encoder (DAE) and convolutional neural network (CNN)-based bearing fault classification model using motor current signals of an induction motor (IM). Motor current signals can be easily and non-invasively collected from the motor. However, the current signal collected from industrial sources is highly contaminated with noise; feature calculation thus becomes very challenging. The DAE is utilized for estimating the nonlinear function of the system with the normal state data, and later, the residual signal is obtained. The subsequent CNN model then successfully classified the types of faults from the residual signals. Our proposed semi-supervised approach achieved very high classification accuracy (more than 99%). The inclusion of DAE was found to not only improve the accuracy significantly but also to be potentially useful when the amount of labeled data is small. The experimental outcomes are compared with some existing works on the same dataset, and the performance of this proposed combined approach is found to be comparable with them. In terms of the classification accuracy and other evaluation parameters, the overall method can be considered as an effective approach for bearing fault classification using the motor current signal.

Gas pipeline event classification based on one-dimensional convolutional neural network

2021 ◽  
pp. 147592172110102
Author(s):  
Yang An ◽  
Xueyan Ma ◽  
Xiaocen Wang ◽  
Zhigang Qu ◽  
Xixin Zhu ◽  
...  
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
Classification Accuracy ◽  
Short Term Memory ◽  
Gas Pipeline ◽  
Economic Losses ◽  
Short Term ◽  
Term Memory ◽  
One Dimensional ◽  
Memory Network

Pipeline block and pipeline leak may lead to serious accidents and cause huge economic losses, which have been urgent problems for gas transportation. In this work, active acoustic pulse-compression technology is first introduced to detect and locate these two anomalous events. The matched filtered signals are then normalized and input into one-dimensional convolutional neural network to achieve classification of not only pipeline block and pipeline leak but also normal event such as pipeline elbow which causes acoustic wave reflection as well. Neural network parameter optimization has also been carried out as well as the comparison with long- and short-term memory network. Experimental results demonstrate that compared with long- and short-term memory network, one-dimensional convolutional neural network has an improvement in efficiency due to the great reduction of running time. For non-aliasing pipeline events, both of the models can reach 100% classification accuracy. For aliasing pipeline events, despite the shorter time series and fewer features, the classification accuracy of one-dimensional convolutional neural network still reaches 100.00%, but that of long- and short-term memory network is only 93.89%. Furthermore, the smoothing and slight fluctuation of receiver operating characteristic curve and the high value of area under curve also verify the stability and good classification performance of the proposed trained model. Therefore, the one-dimensional convolutional neural network shows significant performance for pipeline events classification and has considerable potential and application prospect in gas pipeline safety monitoring.

scholarly journals A Novel Analog Circuit Soft Fault Diagnosis Method Based on Convolutional Neural Network and Backward Difference

Symmetry ◽  
2021 ◽  
Vol 13 (6) ◽  
pp. 1096
Author(s):  
Chenggong Zhang ◽  
Daren Zha ◽  
Lei Wang ◽  
Nan Mu
Keyword(s):  
Neural Network ◽  
Fault Diagnosis ◽  
Convolutional Neural Network ◽  
Second Order ◽  
Fault Classification ◽  
Global Average ◽  
First Order ◽  
Difference Sequences ◽  
Soft Fault ◽  
Soft Fault Diagnosis

This paper develops a novel soft fault diagnosis approach for analog circuits. The proposed method employs the backward difference strategy to process the data, and a novel variant of convolutional neural network, i.e., convolutional neural network with global average pooling (CNN-GAP) is taken for feature extraction and fault classification. Specifically, the measured raw domain response signals are firstly processed by the backward difference strategy and the first-order and the second-order backward difference sequences are generated, which contain the signal variation and the rate of variation characteristics. Then, based on the one-dimensional convolutional neural network, the CNN-GAP is developed by introducing the global average pooling technical. Since global average pooling calculates each input vector’s mean value, the designed CNN-GAP could deal with different lengths of input signals and be applied to diagnose different circuits. Additionally, the first-order and the second-order backward difference sequences along with the raw domain response signals are directly fed into the CNN-GAP, in which the convolutional layers automatically extract and fuse multi-scale features. Finally, fault classification is performed by the fully connected layer of the CNN-GAP. The effectiveness of our proposal is verified by two benchmark circuits under symmetric and asymmetric fault conditions. Experimental results prove that the proposed method outperforms the existing methods in terms of diagnosis accuracy and reliability.

scholarly journals Research on Fault Diagnosis Model of Generative Adss Based on Improved Semisupervised Diagnosis Algorithm

2021 ◽  
Vol 2021 ◽  
pp. 1-11
Author(s):  
Yi Qian
Keyword(s):  
Neural Network ◽  
Fault Diagnosis ◽  
Convolutional Neural Network ◽  
Rapid Development ◽  
Network Models ◽  
Fault Classification ◽  
Neural Network Models ◽  
Diagnosis Algorithm ◽  
Diagnosis Model ◽  
Network Fault

With the advent of the era of big data and the rapid development of deep learning and other technologies, people can use complex neural network models to mine and extract key information in massive data with the support of powerful computing power. However, it also increases the complexity of heterogeneous network and greatly increases the difficulty of network maintenance and management. In order to solve the problem of network fault diagnosis, this paper first proposes an improved semisupervised inverse network fault diagnosis algorithm; the proposed algorithm effectively guarantees the convergence of generated against network model, makes full use of a large amount of trouble-free tag data, and obtains a good accuracy of fault diagnosis. Then, the diagnosis model is further optimized and the fault classification task is completed by the convolutional neural network, the discriminant function of the network is simplified, and the generation pair network is only responsible for generating fault samples. The simulation results also show that the fault diagnosis algorithm based on network generation and convolutional neural network achieves good fault diagnosis accuracy and saves the overhead of manually labeling a large number of data samples.

scholarly journals Rolling Bearing Fault Diagnosis Based on Wavelet Packet Transform and Convolutional Neural Network

2020 ◽  
Vol 10 (3) ◽  
pp. 770 ◽  
Author(s):  
Guoqiang Li ◽  
Chao Deng ◽  
Jun Wu ◽  
Zuoyi Chen ◽  
Xuebing Xu
Keyword(s):  
Neural Network ◽  
Machine Learning ◽  
Fault Diagnosis ◽  
Convolutional Neural Network ◽  
Wavelet Packet ◽  
Rolling Bearing ◽  
Wavelet Packet Transform ◽  
Fault Classification ◽  
Bearing Fault ◽  
Bearing Fault Diagnosis

Timely sensing the abnormal condition of the bearings plays a crucial role in ensuring the normal and safe operation of the rotating machine. Most traditional bearing fault diagnosis methods are developed from machine learning, which might rely on the manual design features and prior knowledge of the faults. In this paper, based on the advantages of CNN model, a two-step fault diagnosis method developed from wavelet packet transform (WPT) and convolutional neural network (CNN) is proposed for fault diagnosis of bearings without any manual work. In the first step, the WPT is designed to obtain the wavelet packet coefficients from raw signals, which then are converted into the gray scale images by a designed data-to-image conversion method. In the second step, a CNN model is built to automatically extract the representative features from gray images and implement the fault classification. The performance of the proposed method is evaluated by a real rolling-bearing dataset. From the experimental study, it can be seen the proposed method presents a more superior fault diagnosis capability than other machine-learning-based methods.

scholarly journals A Novel Deep Learning Method for Intelligent Fault Diagnosis of Rotating Machinery Based on Improved CNN-SVM and Multichannel Data Fusion

Sensors ◽  
2019 ◽  
Vol 19 (7) ◽  
pp. 1693 ◽  
Author(s):  
Gong ◽  
Chen ◽  
Zhang ◽  
Zhang ◽  
Wang ◽  
...  
Keyword(s):  
Neural Network ◽  
Deep Learning ◽  
Fault Diagnosis ◽  
Convolutional Neural Network ◽  
Back Propagation ◽  
Rotating Machinery ◽  
Fault Classification ◽  
Support Vector ◽  
Intelligent Fault Diagnosis ◽  
K Nearest Neighbor

Intelligent fault diagnosis methods based on deep learning becomes a research hotspot in the fault diagnosis field. Automatically and accurately identifying the incipient micro-fault of rotating machinery, especially for fault orientations and severity degree, is still a major challenge in the field of intelligent fault diagnosis. The traditional fault diagnosis methods rely on the manual feature extraction of engineers with prior knowledge. To effectively identify an incipient fault in rotating machinery, this paper proposes a novel method, namely improved the convolutional neural network-support vector machine (CNN-SVM) method. This method improves the traditional convolutional neural network (CNN) model structure by introducing the global average pooling technology and SVM. Firstly, the temporal and spatial multichannel raw data from multiple sensors is directly input into the improved CNN-Softmax model for the training of the CNN model. Secondly, the improved CNN are used for extracting representative features from the raw fault data. Finally, the extracted sparse representative feature vectors are input into SVM for fault classification. The proposed method is applied to the diagnosis multichannel vibration signal monitoring data of a rolling bearing. The results confirm that the proposed method is more effective than other existing intelligence diagnosis methods including SVM, K-nearest neighbor, back-propagation neural network, deep BP neural network, and traditional CNN.

scholarly journals Classification of Few Labeled Images Based on Integrated GMM Clustering

2019 ◽  
Vol 37 (3) ◽  
pp. 465-470
Author(s):  
Pengfei Zhang ◽  
Minzhou Dong ◽  
Junhong Duan
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
Classification Accuracy ◽  
Unlabeled Data ◽  
Data Sets ◽  
Neural Network Training ◽  
Model Classification ◽  
Network Training ◽  
Present Algorithm

In order to improve the classifier classification accuracy of by using convolutional neural network training, a large amount of labeled data is often required, but sometimes labeled data is not easily obtained.This paper proposes a solution based on the idea of integrated GMM clustering and label delivery for classifying images with few labeled samples, assigning tags to unlabeled data through certain rules, and converting unlabeled data into labeled data for training of the model.In this paper, experiments are performed on hand-written digital recognition data sets. The results show that the present algorithm has a great improvement in the accuracy of model classification comparing with the method of using only labeled samples in the case of few labeled samples. The effectiveness of the present algorithm is validated.

Sign in / Sign up

Export Citation Format

Share Document