Proceedings Article10.1109/ICECE.2010.253
Fault Prediction Based on Data-Driven Technique
Lin Luhui,Ma Jie +1 more
- 25 Jun 2010
- pp 997-1001
3
TL;DR: PCA does not depend on the accurate mathematical model, is able to implement the feature extraction of the complex process data, and establishes a principal component model of the corresponding process, and there is the existence of a good applications prospect in thecomplex process of fault diagnosis and prediction maintain.
read more
Abstract: This paper presents principal component analysis (PCA), some improvement of PCA and the development of PCA. PCA does not depend on the accurate mathematical model, is able to implement the feature extraction of the complex process data, and establishes a principal component model of the corresponding process. It can achieve the extraction of the system information and eliminate the interference the system. So there is the existence of a good applications prospect in the complex process of fault diagnosis and prediction maintain.
read more
Chat with Paper
AI Agents for this Paper
Find similar papers on Google Scholar, PubMed and Arxiv
Write a critical review of this paper
Analyze citations of this paper to find unaddressed research gaps
Citations
Training data selection criteria for detecting failures in industrial robots
TL;DR: It is shown that coefficient of variation of the Q-residual from a PCA model built using absolute difference between measurements serves as a robust descriptor for predicting and detecting failure in robots in the one-to-many training scenario.
15
Event Based Robot Prognostics Using Principal Component Analysis
V Sathish,Sithu D. Sudarsan,Srini Ramaswamy +2 more
- 03 Nov 2014
TL;DR: This paper provides a Principal component Analysis (PCA) based approach of failure prediction in industrial robots using event log information and is able to detect abnormal behavior of event pattern within 30 days before failure.
5
•Journal Article
Research on Dynamic Principal ComponentAnalysis and Application
TL;DR: The paper verifies the effectiveness of DPCA for monitoring dynamic multivariate process.
2
References
LIII. On lines and planes of closest fit to systems of points in space
TL;DR: This paper is concerned with the construction of planes of closest fit to systems of points in space and the relationships between these planes and the planes themselves.
Nonlinear principal component analysis using autoassociative neural networks
TL;DR: The NLPCA method is demonstrated using time-dependent, simulated batch reaction data and shows that it successfully reduces dimensionality and produces a feature space map resembling the actual distribution of the underlying system parameters.
3.2K
Statistical process monitoring: basics and beyond
TL;DR: It is demonstrated that the reconstruction-based framework provides a convenient way for fault analysis, including fault detectability, reconstructability and identifiability conditions, resolving many theoretical issues in process monitoring.
1.6K
The process chemometrics approach to process monitoring and fault detection
Barry M. Wise,Neal B. Gallagher +1 more
TL;DR: The state-of-the-art of process chemometrics and current trends in research and applications are reviewed.
896