scispace - formally typeset
Search or ask a question
Topic

Condition monitoring

About: Condition monitoring is a research topic. Over the lifetime, 13911 publications have been published within this topic receiving 201649 citations.


Papers
More filters
Journal ArticleDOI
TL;DR: A novel semi-supervised Support Vector Data Description with negative samples (NSVDD) fault detection approach is proposed and shows superior characteristics in anomaly detection compared to three classification methodologies, i.e. the Back-Propagation Neural Network, the Random Forest and the K-Nearest Neighbour.

70 citations

Journal ArticleDOI
TL;DR: The High Flux Isotope Reactor (HFIR) at the Oak Ridge National Laboratory (ORNL) tested the potential of predictive or condition-based maintenance techniques to reduce maintenance costs, minimize the risk of catastrophic failures, and maximize system availability by attaching wireless-based sensors to selected rotating equipment at HFIR as discussed by the authors.

70 citations

Journal ArticleDOI
TL;DR: In this paper, the results from three years of continuous condition monitoring of highvoltage circuit breakers using vibration analysis are reported, and the reproducibility of the vibration patterns is high for a faultless CB and this makes it possible to separate faulty conditions from natural variations.
Abstract: This paper reports the results from three years of continuous condition monitoring of high-voltage circuit breakers (CBs) using vibration analysis. More than 1000 vibration patterns from the operating mechanism of three different spring-operated SF/sub 6/ breakers in normal service are analyzed. The patterns are recorded during each opening/closing operation and compared with references to identify timing and frequency deviations. Two of the three investigated CBs were operating well, while the third suffered from several severe problems. A developing failure that caused this breaker to not open on command was identified in advance. The reproducibility of the vibration patterns is high for a faultless CB and this makes it possible to separate faulty conditions from natural variations. The vibration analysis method is, however, dependent on a well-conditioned vibration pattern without noise and with distinct events. If the instrumentation is made sufficiently robust to withstand both the electrical disturbances in a substation environment and the mechanical shocks during CB operation, vibration analysis seems to be a promising technique that can be used on a continuous basis to detect malfunctions in the operating mechanism.

70 citations

Journal ArticleDOI
TL;DR: A comprehensive algorithm for fault diagnosis in solar modules using infrared thermography, a reliable, non-destructive, fast and cost effective technique which is widely used to identify where and how faults occurred in an electrical installation is provided.

70 citations

Journal ArticleDOI
TL;DR: In this article, wide-band spectrum analysis is used to detect potential faults long before an inservice failure occurs, and the salient results of numerous tests conducted during 1980 and 1981 are presented.
Abstract: Electromagnetic interference, or EMI, monitoring at an operating machine's neutral can detect many types of stator deterioration, as well as various design defects Accurate, wide-band spectrum analysis may indicate a problem's location, its severity and its rate of change This method can be sensitive enough to detect potential faults long before an inservice failure occurs The salient results of numerous tests conducted during 1980 and 1981 are presented

70 citations


Network Information
Related Topics (5)
Control theory
299.6K papers, 3.1M citations
84% related
Electric power system
133K papers, 1.7M citations
84% related
Voltage
296.3K papers, 1.7M citations
83% related
Wireless sensor network
142K papers, 2.4M citations
79% related
Support vector machine
73.6K papers, 1.7M citations
78% related
Performance
Metrics
No. of papers in the topic in previous years
YearPapers
2023164
2022413
2021798
2020927
2019936
2018906