A Novel Information Fusion Model Based on D-S Evidence Theory for Equipment Diagnosis

2016 ◽  
Author(s):  
Dengji Zhou ◽  
Tingting Wei ◽  
Huisheng Zhang ◽  
Meishan Chen ◽  
Shixi Ma ◽  
...  
Keyword(s):  
Fault Diagnosis ◽  
Diagnostic Accuracy ◽  
Information Fusion ◽  
Diagnostic System ◽  
Sensor Technology ◽  
Mechanical Equipment ◽  
Fusion Model ◽  
Time Data ◽  
First Case ◽  
Data Layer

With the wide-scale use of mechanical equipment, more and more faults occur. At the same time, data deluge about the conditions of machines come into being with the development of sensor technology and information technology. It provides opportunities and challenges to solve the fault problems of mechanical equipment. Information fusion seems to be a useful solution, which is the process of integration of multiple data and knowledge representing the same object into a consistent, accurate, and useful representation. A novel information fusion model, with hybrid-type fusion architecture, is built in this paper. This model consists of data layer, feature layer and decision layer, based on a new Dempster/Shafer (D-S) evidence algorithm. After the data preprocessing based on event reasoning in data layer and feature layer, the information will be fused based on the new algorithm in feature layer and decision layer. Application of this information fusion model in fault diagnosis is beneficial in two aspects, diagnostic applicability and diagnostic accuracy. An effect can be caused by different faults. This information fusion model can solve this problem and increase the number of recognizable faults, to expand the range of fault diagnosis. Additionally, this model can overcome the uncertainty of information and equipment to increase diagnostic accuracy. Two case studies are implemented by this information fusion model to evaluate it. In the first case, fault probabilities calculated by different methods are adopted as inputs to diagnose a fault, which is quite different to be detected based on the information from a single system. The second case is about sensor fault diagnosis. Fault signals are planted into the measured parameters for the diagnostic system, to test the ability to consider the uncertainty of measured parameters. The case study result shows that the model can identify the fault more effectively and accurately. Meanwhile, it has good expansibility, which may be used in more fields.

An Information Fusion Model Based on Dempster–Shafer Evidence Theory for Equipment Diagnosis

2017 ◽  
Vol 4 (2) ◽  
Author(s):  
Dengji Zhou ◽  
Tingting Wei ◽  
Huisheng Zhang ◽  
Shixi Ma ◽  
Fang Wei
Keyword(s):  
Fault Diagnosis ◽  
Diagnostic Accuracy ◽  
Information Fusion ◽  
Evidence Theory ◽  
Diagnostic System ◽  
Fusion Model ◽  
First Case ◽  
Evidence Algorithm ◽  
Data Layer ◽  
Analytical System

An abnormal operating effect can be caused by different faults, and a fault can cause different abnormal effects. An information fusion model, with hybrid-type fusion frame, is built in this paper, so as to solve this problem. This model consists of data layer, feature layer and decision layer, based on an improved Dempster–Shafer (D-S) evidence algorithm. After the data preprocessing based on event reasoning in data layer and feature layer, the information will be fused based on the new algorithm in decision layer. Application of this information fusion model in fault diagnosis is beneficial in two aspects, diagnostic applicability and diagnostic accuracy. Additionally, this model can overcome the uncertainty of information and equipment to increase diagnostic accuracy. Two case studies are implemented by this information fusion model to evaluate it. In the first case, fault probabilities calculated by different methods are adopted as inputs to diagnose a fault, which is quite different to be detected based on the information from a single analytical system. The second case is about sensor fault diagnosis. Fault signals are planted into the measured parameters for the diagnostic system, to test the ability to consider the uncertainty of measured parameters. The case study result shows that the model can identify the fault more effectively and accurately. Meanwhile, it has good expansibility, which may be used in more fields.

scholarly journals Bearing Fault Diagnosis Based on Improved Convolutional Deep Belief Network

2020 ◽  
Vol 10 (18) ◽  
pp. 6359 ◽  
Author(s):  
Shuangjie Liu ◽  
Jiaqi Xie ◽  
Changqing Shen ◽  
Xiaofeng Shang ◽  
Dong Wang ◽  
...  
Keyword(s):  
Fault Diagnosis ◽  
Diagnostic Accuracy ◽  
Vibration Signal ◽  
Deep Belief Network ◽  
Mechanical Equipment ◽  
Belief Network ◽  
Bearing Faults ◽  
Qualitative And Quantitative ◽  
Proposed Model ◽  
Different Types

Mechanical equipment fault detection is critical in industrial applications. Based on vibration signal processing and analysis, the traditional fault diagnosis method relies on rich professional knowledge and artificial experience. Achieving accurate feature extraction and fault diagnosis is difficult using such an approach. To learn the characteristics of features from data automatically, a deep learning method is used. A qualitative and quantitative method for rolling bearing faults diagnosis based on an improved convolutional deep belief network (CDBN) is proposed in this study. First, the original vibration signal is converted to the frequency signal with the fast Fourier transform to improve shallow inputs. Second, the Adam optimizer is introduced to accelerate model training and convergence speed. Finally, the model structure is optimized. A multi-layer feature fusion learning structure is put forward wherein the characterization capabilities of each layer can be fully used to improve the generalization ability of the model. In the experimental verification, a laboratory self-made bearing vibration signal dataset was used. The dataset included healthy bearings, nine single faults of different types and sizes, and three different types of composite fault signals. The results of load 0 kN and 1 kN both indicate that the proposed model has better diagnostic accuracy, with an average of 98.15% and 96.15%, compared with the traditional stacked autoencoder, artificial neural network, deep belief network, and standard CDBN. With improved diagnostic accuracy, the proposed model realizes reliable and effective qualitative and quantitative diagnosis of bearing faults.

scholarly journals A Novel Fault Diagnosis System on Polymer Insulation of Power Transformers Based on 3-stage GA–SA–SVM OFC Selection and ABC–SVM Classifier

Polymers ◽  
2018 ◽  
Vol 10 (10) ◽  
pp. 1096 ◽  
Author(s):  
Xiaoge Huang ◽  
Yiyi Zhang ◽  
Jiefeng Liu ◽  
Hanbo Zheng ◽  
Ke Wang
Keyword(s):  
Artificial Intelligence ◽  
Fault Diagnosis ◽  
Diagnostic Accuracy ◽  
Diagnostic System ◽  
Gas Analysis ◽  
Diagnostic Methods ◽  
Power Transformers ◽  
Svm Classifier ◽  
Diagnosis System ◽  
Optimal Feature

Dissolved gas analysis (DGA) has been widely used in various scenarios of power transformers’ online monitoring and diagnoses. However, the diagnostic accuracy of traditional DGA methods still leaves much room for improvement. In this context, numerous new DGA diagnostic models that combine artificial intelligence with traditional methods have emerged. In this paper, a new DGA artificial intelligent diagnostic system is proposed. There are two modules that make up the diagnosis system. The two modules are the optimal feature combination (OFC) selection module based on 3-stage GA–SA–SVM and the ABC–SVM fault diagnosis module. The diagnosis system has been completely realized and embodied in its outstanding performances in diagnostic accuracy, reliability, and efficiency. Comparing the result with other artificial intelligence diagnostic methods, the new diagnostic system proposed in this paper performed superiorly.

Fault Diagnosis of Gearbox Based on Information Fusion Technique

2014 ◽  
Vol 543-547 ◽  
pp. 1083-1086
Author(s):  
Hao Tian ◽  
Xiao Yong Kang ◽  
Jun Nuo Zhang ◽  
Li Ping Luo
Keyword(s):  
Fault Diagnosis ◽  
Information Fusion ◽  
Target Identification ◽  
Mechanical Equipment ◽  
Information Quantity ◽  
Fusion Technique ◽  
Diagnosis System ◽  
Military Application ◽  
Fault Diagnosis System ◽  
Information Fusion Technique

At present, some elementary problems need to be solved when apply information fusion technique to gearbox fault diagnosis system. Firstly, it is exceedingly necessary to present the precise definition, model and architecture for gearbox, even for mechanical equipment fault diagnosis application, since current definitions, models and architectures about information fusion all refer to target identification, image processing and automatic command system. Secondly, it is also important that investigate the information pre-processing for gearbox fault diagnosis, viz. how to associate data in fault diagnosis application, which is very different with military application. Based on it, the fusion demands can be brought forward in terms of different information, e.g. through fusion to get feature parameter or enhance the information quantity---to get respective fusion method ultimately. Finally, investigate how to assess properly the performance of gearbox fault diagnosis system based on information fusion, including assessment of performance of the chosen feature parameters. In this paper we investigate and discuss preliminarily these three problems.

Fault Classification of Hydroelectric Generating Unit Based on Improved Evidence Theory

2014 ◽  
Vol 7 (1) ◽  
pp. 78-83 ◽  
Author(s):  
Jiatang Cheng ◽  
Li Ai ◽  
Zhimei Duan ◽  
Yan Xiong
Keyword(s):  
Fault Diagnosis ◽  
Information Fusion ◽  
Evidence Theory ◽  
Fault Classification ◽  
Fusion Method ◽  
Inconsistent Result ◽  
High Conflict

Aiming at the problem of the conventional vibration fault diagnosis technology with inconsistent result of a hydroelectric generating unit, an information fusion method was proposed based on the improved evidence theory. In this algorithm, the original evidence was amended by the credibility factor, and then the synthesis rule of standard evidence theory was utilized to carry out information fusion. The results show that the proposed method can obtain any definitive conclusion even if there is high conflict evidence in the synthesis evidence process, and may avoid the divergent phenomenon when the consistent evidence is fused, and is suitable for the fault classification of hydroelectric generating unit.

scholarly journals Fault Diagnosis of Bearings Based on Multi-Sensor Information Fusion and 2D Convolutional Neural Network

IEEE Access ◽  
2021 ◽  
Vol 9 ◽  
pp. 23717-23725
Author(s):  
Jiaxing Wang ◽  
Dazhi Wang ◽  
Sihan Wang ◽  
Wenhui Li ◽  
Keling Song
Keyword(s):  
Neural Network ◽  
Fault Diagnosis ◽  
Convolutional Neural Network ◽  
Information Fusion ◽  
Sensor Information

scholarly journals A Novel Domain Adaptation-Based Intelligent Fault Diagnosis Model to Handle Sample Class Imbalanced Problem

Sensors ◽  
2021 ◽  
Vol 21 (10) ◽  
pp. 3382
Author(s):  
Zhongwei Zhang ◽  
Mingyu Shao ◽  
Liping Wang ◽  
Sujuan Shao ◽  
Chicheng Ma
Keyword(s):  
Fault Diagnosis ◽  
Domain Adaptation ◽  
Class Imbalance ◽  
Rolling Bearing ◽  
Industrial Applications ◽  
Mechanical Equipment ◽  
Reliable Operation ◽  
Cross Domain ◽  
Geometric Difference ◽  
Model Generalization

As the key component to transmit power and torque, the fault diagnosis of rotating machinery is crucial to guarantee the reliable operation of mechanical equipment. Regrettably, sample class imbalance is a common phenomenon in industrial applications, which causes large cross-domain distribution discrepancies for domain adaptation (DA) and results in performance degradation for most of the existing mechanical fault diagnosis approaches. To address this issue, a novel DA approach that simultaneously reduces the cross-domain distribution difference and the geometric difference is proposed, which is defined as MRMI. This work contains three parts to improve the sample class imbalance issue: (1) A novel distance metric method (MVD) is proposed and applied to improve the performance of marginal distribution adaptation. (2) Manifold regularization is combined with instance reweighting to simultaneously explore the intrinsic manifold structure and remove irrelevant source-domain samples adaptively. (3) The ℓ2-norm regularization is applied as the data preprocessing tool to improve the model generalization performance. The gear and rolling bearing datasets with class imbalanced samples are applied to validate the reliability of MRMI. According to the fault diagnosis results, MRMI can significantly outperform competitive approaches under the condition of sample class imbalance.

Sign in / Sign up

Export Citation Format

Share Document