Modified self-organising map for automated novelty detection applied to vibration signal monitoring
Citations
1,173 citations
527 citations
Cites methods from "Modified self-organising map for au..."
...The SOM is trained using the architecture of 10 10 neurons....
[...]
...As also indicated by the diagnosis results in this case study, the SOM algorithm generally performs less accurately compared to all other algorithms, mainly due to its inefficiency in learning the non-linearly separable health conditions based on the complex sensory signals [53]....
[...]
...Significant advances have been achieved in applying classification techniques based on machine learning [27–34] or statistical inferences [35–37], which resulted in a number of state-of-the-art health state classification methods, such as back-propagation neural network (BNN) [27–30], self-organizing maps (SOM) [31], support vector machine (SVM) [28,32–34], and Mahalanobis distance (MD) [32,35]....
[...]
...Health diagnosis using DBN based health state classification technique is compared with four existing diagnosis techniques: SVM, BNN, SOM, and MD classifier....
[...]
...The 10 10 architecture of neurons is used to develop SOM models for all datasets....
[...]
406 citations
Cites methods from "Modified self-organising map for au..."
...One of the principal tools for diagnosing rotating machinery problems is the vibration analysis [1–4]....
[...]
...Therefore, there is a demand for techniques that can make decision on the running health of the machine automatically and reliably [4–6]....
[...]
350 citations
269 citations
References
[...]
12,920 citations
836 citations
363 citations
178 citations
157 citations