Research on intelligent fault diagnosis based on time series analysis algorithm

Time series analysis is advantageous since it offers insight into the underlying dynamics and forecasts system behavior. The construction of the discriminant function is of vital importance in the time series analysis based fault diagnosis. Aiming at the problem that some of the time series analysis based fault diagnosis methods exist the weakness of higher time complexity, weaker discriminant ability and insufficient online diagnosis power, this paper proposes an approach which makes full use of the characteristics of the model and observation data to construct the discriminant function, and presents an efficient algorithm which can effectively recognize the system state by the proposed discriminant function. As compared to the related work, it has the characteristics of lower time complexity, shorter computation time and stronger distinguished ability, without the requirement of same orders of the reference model and the detected model. The fault diagnosis steps based on the proposed discriminant function and its algorithm are also suggested.

Download Full-text

A Time Series Analysis and Neural Network Based Scheme for Fault Diagnosis of Transformers

Applied Mechanics and Materials ◽

10.4028/www.scientific.net/amm.742.412 ◽

2015 ◽

Vol 742 ◽

pp. 412-418

Author(s):

Jian Jun Zhang ◽

Ye Xin Song ◽

Yong Qu

Keyword(s):

Neural Network ◽

Time Series ◽

Fault Diagnosis ◽

Time Series Analysis ◽

Bp Neural Network ◽

Back Propagation ◽

Characteristic Parameters ◽

Series Analysis ◽

Diagnosis Accuracy ◽

Artificial Neural Network Ann

This research presents a time series analysis and artificial neural network (ANN)-based scheme for fault diagnosis of power transformers, which extracts the characteristic parameters of the faults of the transformer from the results of time series analysis and bases on this basis establishes the corresponding back propagation (BP) neural network to detect the transformer operating faults. The simulation experimental results show that as compared to the related works, the proposed approach effectively integrates the superiority of time series analysis and BP neural network and thus can greatly improve the diagnosis accuracy and reliability.

Download Full-text

Proton exchange membrane fuel cell dynamic model based on time series analysis for fault diagnosis

International Journal of Renewable Energy Technology ◽

10.1504/ijret.2021.118509 ◽

2021 ◽

Vol 12 (4) ◽

pp. 351

Author(s):

Sujit Sopan Barhate ◽

Rohini Mudhalwadkar

Keyword(s):

Time Series ◽

Fuel Cell ◽

Fault Diagnosis ◽

Time Series Analysis ◽

Dynamic Model ◽

Proton Exchange Membrane ◽

Proton Exchange ◽

Series Analysis ◽

Model Based ◽

Exchange Membrane

Download Full-text

The Mechanical Fault Diagnosis Method Based on EMD and Time Series Analysis

Applied Mechanics and Materials ◽

10.4028/www.scientific.net/amm.602-605.2330 ◽

2014 ◽

Vol 602-605 ◽

pp. 2330-2333 ◽

Cited By ~ 1

Author(s):

Jun Ma ◽

Shi Hai Zhang

Keyword(s):

Time Series ◽

Fault Diagnosis ◽

Time Series Analysis ◽

Mechanical Vibration ◽

Vibration Signal ◽

Vibration Monitoring ◽

Analysis Method ◽

Series Analysis ◽

Mode Decomposition ◽

Empirical Mode Decomposition Method

It is the precondition of vibration fault diagnosis technology that appropriate signal analysis method is applied to separate mechanical fault character message from vibration monitoring signal. Based on the characteristics of multi-exciting, multi-model, non-stationary, nonlinear of the complex mechanical vibration signal, the EMD (Empirical Mode Decomposition) method is firstly applied to decompose the most refined IMF (Intrinsic Mode Function) components of vibration monitoring signal, and then the time series analysis method is applied to estimate power spectrums of IMF components and separate the fault character messages. The feasibility and advantage of the associated method are proved by analyzing the diesel engine crankshaft vibration monitoring signal in the paper.

Download Full-text