Fine Tuning Machine Fault Diagnosis System Towards Mission Critical Applications

Gopinath, R.; Kumar, C. Santhosh; Vaijeyanthi, V.; Ramachandran, K. I.

doi:10.1007/978-3-319-23036-8_19

Cited by 3 publications

(2 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The better performance of LLC is obtained for 1024 codebooks in improving the overall accuracy and no-alarm (no-fault) accuracy at the expense of alarm accuracy. But a better alarm accuracy is desired for mission critical applications (aerospace) even at the expense of no-alarm accuracy (Gopinath et al, 2016b). The system-dependent features degrade the performance of the classifier in identifying the fault conditions of the 5 kVA synchronous generator.…”

Section: Llc For Scalable Fault Modelsmentioning

confidence: 99%

See 1 more Smart Citation

Scalable fault models for diagnosis of synchronous generators

Gopinath

Kumar

Ramachandran

2016

IJISTA

Self Cite

View full text Add to dashboard Cite

In this paper, we experiment with a small working model (SWM), where we can inject faults and learn the intelligence about the system, then scale up this fault models to monitor the condition of an actual/complex system, without injecting faults in the actual system. We refer to this approach as scalable fault models. We check the effectiveness of our approach using 3 kVA and 5 kVA synchronous generators to emulate the behaviour of SWM and actual system, respectively. We linearise the features from the SWM and actual system in a higher-dimensional space using locality constrained linear coding (LLC) to make them linearly separable. Subsequently, the systemindependent features are selected using principal component analysis (PCA) to make the fault models robust across the systems. Support vector machine (SVM) is used as a back-end classifier. Experiments and results show that proposed LLC-PCA system outperforms the baseline system.

show abstract

Section: Llc For Scalable Fault Modelsmentioning

confidence: 99%

“…We improved the alarm accuracy for the scalable fault models at the expense of no-fault accuracy. It may be noted that a better alarm accuracy is desired in mission critical applications even at the expense of a lower no-alarm detection accuracy (Gopinath et al, 2016b).…”

Section: Llc-pca For Scalable Fault Modelsmentioning

confidence: 99%