Feature Selection Scheme Based on Pareto Method for Gearbox Fault Diagnosis

Ziani, Ridha; Mahgoun, Hafida; Fedala, Semcheddine; Ahmed, Faraz

doi:10.1007/978-3-319-96181-1_1

Cited by 4 publications

(6 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The features’ pre-selection is based on the scheme presented in [ 17 ], with the evaluation carried out by means of the Fisher score. The idea behind the method is that the distance between points of different classes is the maximum possible, while the distance between points of the same class is the minimum possible.…”

Section: Materials and Methodsmentioning

confidence: 99%

“…This is a technique for decision-making based on the Pareto principle, also known as the 80/20 rule [ 22 ]. The analysis is based on the idea that 80% of the benefit can be achieved by doing 20% of the work [ 17 ]. The objective of this paper was to create a subset of features to be provided as the input to the PCA in order to obtain the classification of the analysed signals.…”

Section: Materials and Methodsmentioning

confidence: 99%

“…The aim of the paper was to achieve high classification accuracy by reducing the computational power required. Another approach was presented by Ziani et al [ 17 ], who proposed an approach of fault detection based on three steps: feature extraction, selection of sensitive features, and classification. Feature extraction took place after the signal was decomposed through Wavelet Packet Decomposition (WPD).…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Screening of Discrete Wavelet Transform Parameters for the Denoising of Rolling Bearing Signals in Presence of Localised Defects

Brusa

Delprete

Gargiuli

et al. 2022

Sensors

View full text Add to dashboard Cite

Maintenance scheduling is a fundamental element in industry, where excessive downtime can lead to considerable economic losses. Active monitoring systems of various components are ever more used, and rolling bearings can be identified as one of the primary causes of failure on production lines. Vibration signals extracted from bearings are affected by noise, which can make their nature unclear and the extraction and classification of features difficult. In recent years, the use of the discrete wavelet transform for denoising has been increasing, but studies in the literature that optimise all the parameters used in this process are lacking. In the current article, the authors present an algorithm to optimise the parameters required for denoising based on the discrete wavelet transform and thresholding. One-hundred sixty different configurations of the mother wavelet, threshold evaluation method, and threshold function are compared on the Case Western Reserve University database to obtain the best combination for bearing damage identification with an iterative method and are evaluated with tradeoff and kurtosis. The analysis results show that the best combination of parameters for denoising is dmey, rigrSURE, and the hard threshold. The signals were then distributed in a 2D plane for classification through an algorithm based on principal component analysis, which uses a preselection of features extracted in the time domain.

show abstract

Section: Materials and Methodsmentioning

confidence: 99%

Section: Materials and Methodsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Screening of Discrete Wavelet Transform Parameters for the Denoising of Rolling Bearing Signals in Presence of Localised Defects

Brusa

Delprete

Gargiuli

et al. 2022

Sensors

View full text Add to dashboard Cite

show abstract

“…The data are presented based on the results of the observations in the period from 04.2018 to 11.2020. For a visual representation of the frequency of occurrence of the causes of the failures, a Pareto diagram was built [14][15] (figure 4). The diagram shows that seventy percent of the failures are due to the causes 1a (Defective thermostat), 3b (Mechanical damage (cracks) in the evaporator tubes) and 2c (Clogged (dirty) condenser).…”

Section: Research Status and Work Relevancementioning

confidence: 99%

Investigation of the reasons for the failures of the tractor microclimate system

et al. 2021

View full text Add to dashboard Cite

In the process of performing technological operations, any agricultural machinery is exposed to a large number of changing factors. The result of performing technological operations, i.e. the assessment of performance indicators, in most cases, is performed by the organoleptic method, which is characterized by a significant error (up to 40%) and labour intensity. The use of automatic means of control gives an undoubted advantage in convenience of use and in speed of obtaining results. Given the complexity and labour intensity of assessing the quality indicators of agricultural machinery, even partial automation of this process in practice gives a significant (tens of percent) economic effect and becomes the basis for the formation of digital agriculture. We have analyzed the existing methods for controlling the quality indicators of technological operations using the example of the grain harvesting process. In particular, the possibilities of improving the methods of monitoring the quality indicators of the work of the combine harvester are considered.

show abstract

“…Therefore, many studies have recently been conducted to optimize the combination of features with the highest classification accuracy in feature selection. An optimal combination of features has been derived using filter methods such as relief, chi-square, and information gain [ 13 ], or by using Pareto optimization [ 14 ] or a binary particle swarm optimization method [ 15 ] after using a filter method. A wrapper-based embedded method, using a support vector machine (SVM) [ 16 ], and a method of deriving optimal features using the sensitivity of features [ 17 ] or a genetic algorithm [ 18 ] have been proposed.…”

Section: Introductionmentioning

confidence: 99%

Multi-Filter Clustering Fusion for Feature Selection in Rotating Machinery Fault Classification

Solichin

Noh

Kang

et al. 2022

Sensors

View full text Add to dashboard Cite

In the fault classification process, filter methods that sequentially remove unnecessary features have long been studied. However, the existing filter methods do not have guidelines on which, and how many, features are needed. This study developed a multi-filter clustering fusion (MFCF) technique, to effectively and efficiently select features. In the MFCF process, a multi-filter method combining existing filter methods is first applied for feature clustering; then, key features are automatically selected. The union of key features is utilized to find all potentially important features, and an exhaustive search is used to obtain the best combination of selected features to maximize the accuracy of the classification model. In the rotating machinery examples, fault classification models using MFCF were generated to classify normal and abnormal conditions of rotational machinery. The obtained results demonstrated that classification models using MFCF provide good accuracy, efficiency, and robustness in the fault classification of rotational machinery.

show abstract

Feature Selection Scheme Based on Pareto Method for Gearbox Fault Diagnosis

Cited by 4 publications

References 20 publications

Screening of Discrete Wavelet Transform Parameters for the Denoising of Rolling Bearing Signals in Presence of Localised Defects

Screening of Discrete Wavelet Transform Parameters for the Denoising of Rolling Bearing Signals in Presence of Localised Defects

Investigation of the reasons for the failures of the tractor microclimate system

Multi-Filter Clustering Fusion for Feature Selection in Rotating Machinery Fault Classification

Contact Info

Product

Resources

About