scholarly journals Application of Extension Neural Network Type-1 to Fault Diagnosis of Electronic Circuits

2012 ◽  
Vol 2012 ◽  
pp. 1-12 ◽  
Author(s):  
Meng-Hui Wang
Keyword(s):  
Neural Network ◽  
Fault Diagnosis ◽  
Analog Circuits ◽  
Fault Tolerant ◽  
Electronic Components ◽  
High Diagnostic Accuracy ◽  
Fault Type ◽  
Correlation Degree ◽  
Network Type

The values of electronic components are always deviated, but the functions of the modern circuits are more and more precise, which makes the automatic fault diagnosis of analog circuits very complex and difficult. This paper presents an extension-neural-network-type-1-(ENN-1-) based method for fault diagnosis of analog circuits. This proposed method combines the extension theory and neural networks to create a novel neural network. Using the matter-element models of fault types and a correlation function, can be calculated the correlation degree between the tested pattern and every fault type; then, the cause of the circuit malfunction can be directly diagnosed by the analysis of the correlation degree. The experimental results show that the proposed method has a high diagnostic accuracy and is more fault tolerant than the multilayer neural network (MNN) and thek-means based methods.

Combined Optimization of Neural Network Fault Diagnosis Methods for Analog Circuits on Ships

2020 ◽  
Vol 99 (sp1) ◽  
pp. 158
Author(s):  
Sumin Guo ◽  
Hongyu Li ◽  
Bo Wu ◽  
Jingyu Zhou ◽  
Chunjian Su ◽  
...  
Keyword(s):  
Neural Network ◽  
Fault Diagnosis ◽  
Analog Circuits ◽  
Network Fault

Research of Hard Fault Diagnosis Simulation Platform of Aero-Engine's Key Sensors Based on Neural Network

2013 ◽  
Vol 391 ◽  
pp. 150-154 ◽  
Author(s):  
Zhao Rong Sun ◽  
Yi Gang Sun ◽  
Chun Lin Sun Sun
Keyword(s):  
Neural Network ◽  
Fault Diagnosis ◽  
Simulation Platform ◽  
Bp Network ◽  
Fault Type ◽  
Diagnosis Model ◽  
Simulation Results ◽  
Engine Failure ◽  
Aero Engines ◽  
Hard Failure

The purpose of the research is to establish a fault diagnosis model of the aero-engines key sensors using the artificial neural networks to replace the engines mathematical model, so as to establish a hard fault diagnosis simulation platform to monitor the performances of the engine sensors on real-time, to judge the engine failure mode timely, and to locate the fault type of sensors accurately. By analyzing the correlations of the parameters that affect the conditions of the engine, a three-layer BP network model is established. The related QAR (Quick Access Recorder) data are used to simulate and analyze the models using the MATLAB. Combined with the characteristics of the hard failure of the critical engine sensors and the correlation of the parameters, the fault diagnosis simulation platform is established. Then, the parameters of the normal engine and the failure engine are used respectively to evaluate and validate the platform. The simulation results show that the platform can judge the critical sensors faults of the engine accurately, and can locate the type of sensors reliably.

scholarly journals Research on Intelligent Diagnosis Method for Large-Scale Ship Engine Fault in Non-Deterministic Environment

2017 ◽  
Vol 24 (s3) ◽  
pp. 200-206 ◽  
Author(s):  
Donghua Feng ◽  
Yahong Li
Keyword(s):  
Neural Network ◽  
Fault Diagnosis ◽  
Large Scale ◽  
Use Value ◽  
Intelligent Diagnosis ◽  
High Diagnostic Accuracy ◽  
Diagnosis Method ◽  
Main Fault ◽  
Diagnosis Model ◽  
Fault Mode

Abstract Aiming at the problem of inaccurate and time-consuming of the fault diagnosis method for large-scale ship engine, an intelligent diagnosis method for large-scale ship engine fault in non-deterministic environment based on neural network is proposed. First, the possible fault of the engine was analyzed, and the downtime fault of large-scale ship engine and the main fault mode were identified. On this basis, the fault diagnosis model for large-scale ship engine based on neural network is established, and the intelligent diagnosis of engine fault is completed. The experiment proved that the proposed method has high diagnostic accuracy, engine fault diagnosis takes only about 3s, with a higher use value.

Fault Diagnosis of Analog Circuits Based on Evidence Theory

2014 ◽  
Vol 556-562 ◽  
pp. 2149-2152
Author(s):  
Cheng Cheng
Keyword(s):  
Neural Network ◽  
Fault Diagnosis ◽  
Data Fusion ◽  
Analog Circuits ◽  
Bp Neural Network ◽  
Analog Circuit ◽  
Evidence Theory ◽  
Fusion Technology ◽  
Diagnosis Method ◽  
Simulation Results

BP neural network and evidence theory data fusion technology can be used in troubleshooting electronic equipment, from the simulation results show that the fault diagnosis method based on evidence theory and BP neural network can effectively diagnose faults in analog circuit, and it has automated intelligent characteristics.

Sign in / Sign up

Export Citation Format

Share Document