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 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.

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.

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%.

A sparse denoising deep neural network for improving fault diagnosis performance

2021 ◽  
Author(s):  
Funa Zhou ◽  
Tong Sun ◽  
Xiong Hu ◽  
Tianzhen Wang ◽  
Chenglin Wen
Keyword(s):  
Neural Network ◽  
Fault Diagnosis ◽  
Deep Neural Network

Research on Roller Bearing with Fault Diagnosis Method Based on EMD and BP Neural Network

2014 ◽  
Vol 1014 ◽  
pp. 501-504 ◽  
Author(s):  
Shu Guo ◽  
You Cai Xu ◽  
Xin Shi Li ◽  
Ran Tao ◽  
Kun Li ◽  
...  
Keyword(s):  
Neural Network ◽  
Fault Diagnosis ◽  
Bp Neural Network ◽  
Roller Bearing ◽  
Vibration Signal ◽  
Classification Performance ◽  
Outer Race ◽  
Mode Decomposition ◽  
Diagnosis Method ◽  
Main Fault

In order to discover the fault with roller bearing in time, a new fault diagnosis method based on Empirical mode decomposition (EMD) and BP neural network is put forward in the paper. First, we get the fault signal through experiments. Then we use EMD to decompose the vibration signal into a series of single signals. We can extract main fault information from the single signals. The kurtosis coefficient of the single signals forms a feature vector which is used as the input data of the BP neural network. The trained BP neural network can be used for fault identification. Through analyzing, BP neural network can distinguish the fault into normal state, inner race fault, outer race fault. The results show that this method can gain very stable classification performance and good computational efficiency.

Sign in / Sign up

Export Citation Format

Share Document