scholarly journals Deep Sparse Autoencoder for Feature Extraction and Diagnosis of Locomotive Adhesion Status

2018 ◽  
Vol 2018 ◽  
pp. 1-9 ◽  
Author(s):  
Changfan Zhang ◽  
Xiang Cheng ◽  
Jianhua Liu ◽  
Jing He ◽  
Guangwei Liu
Keyword(s):  
Neural Network ◽  
Fault Diagnosis ◽  
Deep Neural Network ◽  
Single Layer ◽  
Diagnosis Method ◽  
Diagnosis Accuracy ◽  
Sparse Autoencoder ◽  
Single Layer Network ◽  
Network Studies ◽  
Fine Tune

The model is difficult to establish because the principle of the locomotive adhesion process is complex. This paper presents a data-driven adhesion status fault diagnosis method based on deep learning theory. The adhesion coefficient and creep speed of a locomotive constitute the characteristic vector. The sparse autoencoder unsupervised learning network studies the input vector, and the single-layer network is superimposed to form a deep neural network. Finally, a small amount of labeled data is used to fine-tune training the entire deep neural network, and the locomotive adhesion state fault diagnosis model is established. Experimental results show that the proposed method can achieve a 99.3% locomotive adhesion state diagnosis accuracy and satisfy actual engineering monitoring requirements.

Open-circuit fault diagnosis of power rectifier using sparse autoencoder based deep neural network

2018 ◽  
Vol 311 ◽  
pp. 1-10 ◽  
Author(s):  
Lin Xu ◽  
Maoyong Cao ◽  
Baoye Song ◽  
Jiansheng Zhang ◽  
Yurong Liu ◽  
...  
Keyword(s):  
Neural Network ◽  
Fault Diagnosis ◽  
Deep Neural Network ◽  
Open Circuit ◽  
Sparse Autoencoder ◽  
Circuit Fault Diagnosis ◽  
Power Rectifier

scholarly journals Deep Forest-Based Fault Diagnosis Method for Chemical Process

2020 ◽  
Vol 2020 ◽  
pp. 1-15
Author(s):  
Jiaman Ding ◽  
Qingbo Luo ◽  
Lianyin Jia ◽  
Jinguo You
Keyword(s):  
Neural Network ◽  
Fault Diagnosis ◽  
Chemical Industry ◽  
Deep Neural Network ◽  
Representation Learning ◽  
Data Representation ◽  
Training Cost ◽  
Deep Forest ◽  
Cascade Structure ◽  
Diagnosis Method

With the rapid expanding of big data in all domains, data-driven and deep learning-based fault diagnosis methods in chemical industry have become a major research topic in recent years. In addition to a deep neural network, deep forest also provides a new idea for deep representation learning and overcomes the shortcomings of a deep neural network such as strong parameter dependence and large training cost. However, the ability of each base classifier is not taken into account in the standard cascade forest, which may lead to its indistinct discrimination. In this paper, a multigrained scanning-based weighted cascade forest (WCForest) is proposed and has been applied to fault diagnosis in chemical processes. In view of the high-dimensional nonlinear data in the process of chemical industry, WCForest first designs a set of relatively suitable windows for the multigrained scan strategy to learn its data representation. Next, considering the fitting quality of each forest classifier, a weighting strategy is proposed to calculate the weight of each forest in the cascade structure without additional calculation cost, so as to improve the overall performance of the model. In order to prove the effectiveness of WCForest, its application has been carried out in the benchmark Tennessee Eastman (TE) process. Experiments demonstrate that WCForest achieves better results than other related approaches across various evaluation metrics.

scholarly journals A Bearing Fault Diagnosis Method Using Multi-Branch Deep Neural Network

Machines ◽  
2021 ◽  
Vol 9 (12) ◽  
pp. 345
Author(s):  
Van-Cuong Nguyen ◽  
Duy-Tang Hoang ◽  
Xuan-Toa Tran ◽  
Mien Van ◽  
Hee-Jun Kang
Keyword(s):  
Neural Network ◽  
Feature Extraction ◽  
Fault Diagnosis ◽  
Deep Neural Network ◽  
Image Representation ◽  
Vibration Signal ◽  
Bearing Fault ◽  
Bearing Fault Diagnosis ◽  
Diagnosis Method ◽  
Multiple Domain

Feature extraction from a signal is the most important step in signal-based fault diagnosis. Deep learning or deep neural network (DNN) is an effective method to extract features from signals. In this paper, a novel vibration signal-based bearing fault diagnosis method using DNN is proposed. First, the measured vibration signals are transformed into a new data form called multiple-domain image-representation. By this transformation, the task of signal-based fault diagnosis is transferred into the task of image classification. After that, a DNN with a multi-branch structure is proposed to handle the multiple-domain image representation data. The multi-branch structure of the proposed DNN helps to extract features in multiple domains simultaneously, and to lead to better feature extraction. Better feature extraction leads to a better performance of fault diagnosis. The effectiveness of the proposed method was verified via the experiments conducted with actual bearing fault signals and its comparisons with well-established published methods.

Study of the Fault Diagnosis Based on Wavelet and Neural Network for the Motor

2013 ◽  
Vol 433-435 ◽  
pp. 483-488
Author(s):  
Ke Yong Shao ◽  
Li Juan Han ◽  
Xin Min Wang ◽  
Feng Wu Zhang ◽  
Kun Qian
Keyword(s):  
Neural Network ◽  
Fault Diagnosis ◽  
Wavelet Packet ◽  
Vibration Signals ◽  
Operation Conditions ◽  
Neural Network System ◽  
Diagnosis Method ◽  
Diagnosis Accuracy ◽  
Hidden Layer ◽  
Motor Operation

In the motor fault diagnosis technology, vibration signals can fully reflect the motor operation conditions. In this paper, a linear motor fault diagnosis method based on wavelet packet and neural network was presented. The improved neural network system was designed with variable hidden layer neurons. The network chosen different numerical values depending on different situations to reach the requirements that improving diagnostic accuracy and shortening the diagnosis time. The linear motor’s normal and two common faults vibration signals were analyzed and the vibration signals energy characteristics were extracted through wavelet packet, then identified fault through neural network. The experimental results show that this method can effectively improve the motor fault diagnosis accuracy.

scholarly journals Construction of a Sensitive and Speed Invariant Gearbox Fault Diagnosis Model Using an Incorporated Utilizing Adaptive Noise Control and a Stacked Sparse Autoencoder-Based Deep Neural Network

Sensors ◽  
2020 ◽  
Vol 21 (1) ◽  
pp. 18
Author(s):  
Cong Dai Nguyen ◽  
Alexander E. Prosvirin ◽  
Cheol Hong Kim ◽  
Jong-Myon Kim
Keyword(s):  
Neural Network ◽  
Fault Diagnosis ◽  
Deep Neural Network ◽  
Noise Control ◽  
Vibration Characteristics ◽  
Vibration Signals ◽  
Sparse Autoencoder ◽  
Stacked Sparse Autoencoder ◽  
Diagnosis Model ◽  
Adaptive Noise

Gearbox fault diagnosis based on the analysis of vibration signals has been a major research topic for a few decades due to the advantages of vibration characteristics. Such characteristics are used for early fault detection to guarantee the enhanced safety of complex systems and their cost-effective operation. There exist many fault diagnosis models that have been developed for classifying various fault types in gearboxes. However, the classification results of the conventional fault classification models degrade when they are applied to gearbox systems with multi-level tooth cut gear (MTCG) faults operating under variable shaft speeds. These conditions cause difficulty in discriminating the gear fault types. Due to the improved computational capabilities of modern systems, the application of deep neural networks (DNNs) is getting popular in a variety of research fields, such as image and natural language processing. DNNs are capable of improving the classification results even when addressing complex problems such as diagnosing gearbox MTCG faults. In this research, an adaptive noise control (ANC) and a stacked sparse autoencoder–based deep neural network (SSA-DNN) are used to construct a sensitive fault diagnosis model that can diagnose a gearbox system with MTCG fault types under varying shaft rotation speeds, despite its complicatedness. An ANC is applied to gear vibration characteristics to remove a significant level of noise along the frequency spectrum of vibration signals to fix the most fault-informative components of each fault case. Next, the autoencoder learns the gear faults characteristic features from these fault-informative components to separate the fault types considered in this study. Furthermore, the implementation of the SSA-DNN is substituted for feature extraction, feature selection, and the classification processes in traditional fault diagnosis schemes by high-performance unity. The experimental results show that the proposed model outperforms conventional methodologies with higher classification accuracy.

Fault diagnosis method of peak-load-regulation steam turbine based on improved PCA-HKNN artificial neural network

2021 ◽  
pp. 1748006X2110105
Author(s):  
Yifan Wu ◽  
Wei Li ◽  
Deren Sheng ◽  
Jianhong Chen ◽  
Zitao Yu
Keyword(s):  
Neural Network ◽  
Fault Diagnosis ◽  
Steam Turbine ◽  
Power Plants ◽  
Peak Load ◽  
Clean Energy ◽  
Steam Turbines ◽  
Peak Shaving ◽  
Diagnosis Method ◽  
Load Regulation

Clean energy is now developing rapidly, especially in the United States, China, the Britain and the European Union. To ensure the stability of power production and consumption, and to give higher priority to clean energy, it is essential for large power plants to implement peak shaving operation, which means that even the 1000 MW steam turbines in large plants will undertake peak shaving tasks for a long period of time. However, with the peak load regulation, the steam turbines operating in low capacity may be much more likely to cause faults. In this paper, aiming at peak load shaving, a fault diagnosis method of steam turbine vibration has been presented. The major models, namely hierarchy-KNN model on the basis of improved principal component analysis (Improved PCA-HKNN) has been discussed in detail. Additionally, a new fault diagnosis method has been proposed. By applying the PCA improved by information entropy, the vibration and thermal original data are decomposed and classified into a finite number of characteristic parameters and factor matrices. For the peak shaving power plants, the peak load shaving state involving their methods of operation and results of vibration would be elaborated further. Combined with the data and the operation state, the HKNN model is established to carry out the fault diagnosis. Finally, the efficiency and reliability of the improved PCA-HKNN model is discussed. It’s indicated that compared with the traditional method, especially handling the large data, this model enhances the convergence speed and the anti-interference ability of the neural network, reduces the training time and diagnosis time by more than 50%, improving the reliability of the diagnosis from 76% to 97%.

Sign in / Sign up

Export Citation Format

Share Document