Feature ranking for multi-fault diagnosis of rotating machinery by using random forest and KNN

Sánchez, René–Vinicio; Lucero, Pablo; Vásquez, Rafael E.; Cerrada, Mariela; Macancela, Jean-Carlo; Cabrera, Diego

doi:10.3233/jifs-169526

Cited by 84 publications

(41 citation statements)

References 47 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Previous studies with traditional features in time domain and frequency domain such as power spectral density (PSD) or kurtosis were done obtaining good results in severe faults and laboratory conditions, 33 but, if incipient faults have been studied, the amplitude of the spectra is too low to discriminate between signal and noise.…”

Section: Vibration Processing Methodologymentioning

confidence: 99%

Wavelet Packets Transform processing and Genetic Neuro-Fuzzy classification to detect faulty bearings

Hernández

Castejón

García-Prada

et al. 2019

Advances in Mechanical Engineering

View full text Add to dashboard Cite

A great investment is made in maintenance of machinery in any industry. A big percentage of this is spent both in workers and in materials in order to prevent potential issues with said devices. In order to avoid unnecessary expenses, this article presents an intelligent method to detect incipient faults. Particularly, this study focuses on bearings due to the fact that they are the mechanical elements that are most likely to break down. In this article, the proposed method is tested with data collected from a quasi-real industrial machine, which allows for the measurement of the behaviour of faulty bearings with incipient defects. In a second phase, the vibrations obtained from healthy and defective pieces are processed with a multiresolution analysis with the purpose of extracting the most interesting characteristics. Particularly, a Wavelet Packets Transform processing is carried out. Finally, these parameters are used as Genetic Neuro-Fuzzy inputs; this way, once it has been trained, it will indicate whether the analyzed mechanical element is faulty or not.

show abstract

Section: Vibration Processing Methodologymentioning

confidence: 99%

Wavelet Packets Transform processing and Genetic Neuro-Fuzzy classification to detect faulty bearings

Hernández

Castejón

García-Prada

et al. 2019

Advances in Mechanical Engineering

View full text Add to dashboard Cite

show abstract

“…Statistical feature dataset is small and simple to extract, and it allows a highly accurate classification of the set of 13 faulty conditions under study. This set of features has been selected and applied to fault classification in gearboxes and roller bearings [39] providing high classification accuracy. The set of features based on SD is also simple to calculate and provides a high classification accuracy.…”

Section: Discussionmentioning

confidence: 99%

“…A set of classical statistical features was considered for comparing to the performance of the proposed CCM and SD features. The set of statistical features has been studied in [39] for detection of multi-fault in roller bearings and gearboxes. The features are the mean value, root mean square value, standard deviation, kurtosis, maximum value, crest factor, rectified mean value, shape factor, impulse factor, variance, minimum value and skewness.…”

Section: Statistical Featuresmentioning

confidence: 99%

Reciprocating Compressor Multi-Fault Classification Using Symbolic Dynamics and Complex Correlation Measure

et al. 2020

Self Cite

View full text Add to dashboard Cite

Prognostics and Health Management technologies are useful for early fault detection and optimization of reliability in mechanical systems. Reciprocating compressors units are commonly used in industry for gas pressurization and transportation, and the valves in compressors are considered vulnerable parts susceptible to failure. Then, early detection of faults is important for avoiding catastrophic accidents. A feasible approach for fault detection consists in measuring the vibration signal for extracting useful features enabling fault detection and classification. In this research, a test-bed composed by two-stage reciprocating compressor was used for simulating a set of 13 different conditions of combined faults in valves and roller bearings. Three accelerometers were used for collecting the vibration signals for extracting three different types of features. These features were analyzed furthermore by using two random forest models to classifying the different faults. The first set of features was obtained by applying the symbolic dynamics algorithm, which provides the histogram of a set of symbols. This set of symbols was obtained by subdividing a 2D Poincaré plot into angular regions and counting the intersection of the phase trajectories on each of regions. The second type of features corresponds to the complex correlation measure which is calculated as the addition of the areas of triangles belonging to a Poincaré plot. Additionally, a small set of classical statistical features was also used for comparing their classification abilities to the new set of proposed features. The three sets of features enable highly accurate classification of the set of faults when used with random forest classification models. Notably, the ensemble subspace k-Nearest Neighbors algorithm provides classification accuracies higher than 99%.

show abstract

“…erefore, in order to achieve a comprehensive fault feature extraction of rolling bearing, a new fault feature extraction method named hierarchical dispersion entropy is proposed. e fault features of vibration signals of rolling bearing are extracted by the hierarchical dispersion entropy and inputted into the KNN classifier [17] to realize fault diagnosis.…”

Section: Introductionmentioning

confidence: 99%

A New Method of Fault Feature Extraction Based on Hierarchical Dispersion Entropy

Peng

Zhao

Jiang

2021

Shock and Vibration

View full text Add to dashboard Cite

In the process of fault feature extraction of rolling bearing, the feature information is difficult to be extracted fully. A novel method of fault feature extraction called hierarchical dispersion entropy is proposed in this paper. In this method, the vibration signals firstly are decomposed hierarchically. Secondly, dispersion entropies of different nodes are calculated. Hierarchical dispersion entropy can realize the comprehensive feature extraction of the high- and low-frequency band information of vibration signals and overcome the problems that dispersion entropy and multiscale dispersion entropy are insufficient to extract the fault feature information of vibration signals. The feasibility of hierarchical dispersion entropy is obtained by analyzing the hierarchical dispersion entropy of Gaussian white noise and compared with the multiscale dispersion entropy of Gaussian white noise. Meanwhile, a fault diagnosis method for rolling bearings based on hierarchical dispersion entropy and k-nearest neighbor (KNN) classifier is developed. Finally, the superiority of the proposed fault diagnosis method is verified in the realization of fault diagnosis of the rolling bearing in different positions and different degrees of damage.

show abstract

Feature ranking for multi-fault diagnosis of rotating machinery by using random forest and KNN

Cited by 84 publications

References 47 publications

Wavelet Packets Transform processing and Genetic Neuro-Fuzzy classification to detect faulty bearings

Wavelet Packets Transform processing and Genetic Neuro-Fuzzy classification to detect faulty bearings

Reciprocating Compressor Multi-Fault Classification Using Symbolic Dynamics and Complex Correlation Measure

A New Method of Fault Feature Extraction Based on Hierarchical Dispersion Entropy

Contact Info

Product

Resources

About