User:Jalayer masoud/sandbox1: Difference between revisions
No edit summary |
No edit summary |
||
| Line 2: | Line 2: | ||
====Machine learning techniques for signal processing based FDI==== |
====Machine learning techniques for signal processing based FDI==== |
||
{{See also|Machine learning}} |
{{See also|Machine learning}} |
||
In signal processing based FDI, [[Statistical classification|mathematical classification models]] which in fact belong to [[supervised learning]] methods are trained on the [[training set]] of a labeled [[dataset]] to accurately identify the redundancies, faults and anomalous samples. There are numerous different [[Statistical classification|classification]] and [[Data pre-processing|preprocessing]] models developed and proposed in this research area. [[k-nearest neighbors algorithm|''k''-nearest-neighbors algorithm]] is one of the oldest techniques which have been used to solve FDI problems. Despite the simple logic it has, there are some problems with large [[dimensionality]] and processing time in large [[dataset]]s. Since [[k-nearest neighbors algorithm|''k'' |
In signal processing based FDI, [[Statistical classification|mathematical classification models]] which in fact belong to [[supervised learning]] methods are trained on the [[training set]] of a labeled [[dataset]] to accurately identify the redundancies, faults and anomalous samples. There are numerous different [[Statistical classification|classification]] and [[Data pre-processing|preprocessing]] models developed and proposed in this research area. [[k-nearest neighbors algorithm|''k''-nearest-neighbors algorithm]](''k''NN) is one of the oldest techniques which have been used to solve FDI problems. Despite the simple logic it has, there are some problems with large [[dimensionality]] and processing time in large [[dataset]]s. Since [[k-nearest neighbors algorithm|''k''NN]] is not able to automatically extract the features to overcome [[curse of dimensionality]], so often some [[Data pre-processing|data preprocessing]] techniques like [[Principal component analysis]](PCA), [[Linear discriminant analysis]](LDA) or [[Canonical correlation|Canonical correlation analysis]](CCA) accompany it to reach a better performance. In many industrial cases it is shown that [[k-nearest neighbors algorithm|''k''NN]] is outperformed by more complex classification models such as [[Support Vector Machine]]s(SVMs), which is widely used in this field. However [[Svm|SVM]]s do not have automatic feature extraction themselves and just like [[k-nearest neighbors algorithm|''k''NN]], are often coupled with a [[data pre-processing]] technique. Another drawback of [[Svm|SVM]]s is that their performance is highly sensitive to the initial parameters, particularly to the [[kernel method]]s, so in each signal [[dataset]] a parameter tuning process is required to be conducted firstly. |
||
[[Artificial Neural Networks]](ANNs) are among the most mature and widely used [[Statistical classification|mathematical classification algorithms]] in signal processing based FDI. ANNs are well-known for their efficient self-learning capabilities of the complex relations (which generally exists inherently in signal processing based FDI problems) and are easy to operate. Another advantage of ANNs is that they perform automatic feature extraction by allocating negligible weights to the irrelevant features, helping the system to avoid dealing with another feature extractor. However, ANNs tend to [[overfitting|over-fits]] the training set, which will have consequences of having poor validation accuracy on validation set. Hence, often, some regularization terms and prior knowledge are added to the ANN model to avoid [[overfitting|over-fiting]] and achieve higher performance. |
[[Artificial Neural Networks]](ANNs) are among the most mature and widely used [[Statistical classification|mathematical classification algorithms]] in signal processing based FDI. ANNs are well-known for their efficient self-learning capabilities of the complex relations (which generally exists inherently in signal processing based FDI problems) and are easy to operate. Another advantage of ANNs is that they perform automatic feature extraction by allocating negligible weights to the irrelevant features, helping the system to avoid dealing with another feature extractor. However, ANNs tend to [[overfitting|over-fits]] the training set, which will have consequences of having poor validation accuracy on validation set. Hence, often, some regularization terms and prior knowledge are added to the ANN model to avoid [[overfitting|over-fiting]] and achieve higher performance. |
||
In general, ANNs and |
In general, different [[Svm|SVM]]s and ANNs models (i.e. [[Backpropagation|Back-Propagation Neural Networks]] and [[Multilayer perceptron|Multi-Layer Perceptron]]) have shown successful performances in the signal processing based FDI in industries such as [[gearbox]], [[machinery]] parts (i.e. [[mechanical bearing]]s) and [[steam turbine]]s fault detection. |
||
====Deep learning techniques for signal processing based FDI==== |
====Deep learning techniques for signal processing based FDI==== |
||
Revision as of 11:23, 14 June 2018
Signal processing based FDI
Machine learning techniques for signal processing based FDI
In signal processing based FDI, mathematical classification models which in fact belong to supervised learning methods are trained on the training set of a labeled dataset to accurately identify the redundancies, faults and anomalous samples. There are numerous different classification and preprocessing models developed and proposed in this research area. k-nearest-neighbors algorithm(kNN) is one of the oldest techniques which have been used to solve FDI problems. Despite the simple logic it has, there are some problems with large dimensionality and processing time in large datasets. Since kNN is not able to automatically extract the features to overcome curse of dimensionality, so often some data preprocessing techniques like Principal component analysis(PCA), Linear discriminant analysis(LDA) or Canonical correlation analysis(CCA) accompany it to reach a better performance. In many industrial cases it is shown that kNN is outperformed by more complex classification models such as Support Vector Machines(SVMs), which is widely used in this field. However SVMs do not have automatic feature extraction themselves and just like kNN, are often coupled with a data pre-processing technique. Another drawback of SVMs is that their performance is highly sensitive to the initial parameters, particularly to the kernel methods, so in each signal dataset a parameter tuning process is required to be conducted firstly.
Artificial Neural Networks(ANNs) are among the most mature and widely used mathematical classification algorithms in signal processing based FDI. ANNs are well-known for their efficient self-learning capabilities of the complex relations (which generally exists inherently in signal processing based FDI problems) and are easy to operate. Another advantage of ANNs is that they perform automatic feature extraction by allocating negligible weights to the irrelevant features, helping the system to avoid dealing with another feature extractor. However, ANNs tend to over-fits the training set, which will have consequences of having poor validation accuracy on validation set. Hence, often, some regularization terms and prior knowledge are added to the ANN model to avoid over-fiting and achieve higher performance. In general, different SVMs and ANNs models (i.e. Back-Propagation Neural Networks and Multi-Layer Perceptron) have shown successful performances in the signal processing based FDI in industries such as gearbox, machinery parts (i.e. mechanical bearings) and steam turbines fault detection.
Deep learning techniques for signal processing based FDI
Recently, by research advances in ANNs and advent of deep and complex layers (deep learning algorithms), novel classification models are developed to cope with signal processing problems in FDI.
