An expert system for the diagnosis of faults in rotating machinery using adaptive order-tracking algorithm

Wu, Jian-Da; Bai, Mingsian R.; Su, Fu-Cheng; Huang, Chin-Wei

doi:10.1016/j.eswa.2008.06.059

Cited by 34 publications

(24 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…To obtain the best tracking characteristics possible, it is generally suggested that δ should be a small positive value [Haykin (2002)], while we found here that, for OT problems treatment, δ > 1 should be used. In the study of Bai et al [2002] and Wu et al [2009], the implemented values of parameter δ are unfortunately omitted. The tracking results obtained by using the recursive VK schemes with one and two pole structural equations (denoted as the VK-1 and VK-2 methods here) demonstrate that, with appropriate parameter choosing, both VK OT filters can be tuned to have very good and similar tracking characteristics, allowing the decoupling of close and/or crossing orders arising in a complex vibration system.…”

Section: Discussionmentioning

confidence: 99%

“…Bai et al [2002] proposed a model-based real-time linear adaptive filtering, based on the exponentially weighted recursive least-squares (RLS) algorithm [Haykin (2002)], for tracking single or multiple orders of the sound emission or vibration signal of rotating machinery. Wu et al [2009] implemented this method as an alternative for the recursive Kalman OT filters in an expert system for the diagnosis of faults in practical applications. An effective recursive Kalman filtering algorithm [Haykin (2002); Brown and Hwang (1997)] with a two pole structural equation, labelled as the recursive VK OT filter, was proposed in Wu et al [2004].…”

Section: Introductionmentioning

confidence: 99%

“…From the studies reported in the literature, it is known that the very simple least mean-square (LMS) recursive filtering method can exhibit a better tracking behavior than the RLS method [Haykin et al (1997)] because the LMS algorithm is model independent, while the RLS algorithm is model dependent [Sayed and Kailath (1994); Haykin (2002)]. According to this fact, an adaptive OT algorithm, based on the recursive LMS method, which, so far, is not being used as OT tools, is implemented here, together with the RLS OT filter [Bai et al (2002); Wu et al (2009)]. Furthermore, the recursive VK OT filter with a one pole structural equation is taken into consideration, together with the recursive VK OT filter with a two pole structural equation introduced in Wu et al [2004] and Pan and Wu [2007].…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

A Comparative Study of Adaptive Order Tracking Techniques for Rotating Machinery Analysis: Computer Experiments and Practical Implementations

Veljkovic

Todorovič

2016

Adv. Data Sci. Adapt. Data Anal.

View full text Add to dashboard Cite

This paper presents and investigates recursive order tracking (OT) techniques based on the least mean-square (LMS) method and the Vold-Kalman (VK) algorithm with a one pole structural equation, both of which could be realized as real-time applications. Additionally, for comparisons, two common adaptive OT filters are considered: the recursive least-squares (RLS) method and the VK algorithm with a two pole structural equation. The numerical implementations of the considered methods, through simulations on a representative noisy synthetic signal, including both close and crossing orders spectral components, are performed. The results indicate a possible degradation in the tracking performance of the RLS algorithm and the effectiveness of the simple LMS method, as well as both considered VK algorithms, for OT and distinguishing. The influence of the sampling frequency on the choosing of a weighting factor for the VK recursive OT filters is further investigated to extend the guidelines from the literature for using these methods. Two examples of practical implementations of the considered recursive OT methods are given: (i) the separation of the crossing orders arising in the laboratory test bench of the two unbalanced rotors rotating at independent frequencies and (ii) the one engineering application of fault diagnosis in the massive reduction gear on an excavator with a cable crowd, based on the distinguishing and separation of close orders. The experimental results justify the implementation of the proposed techniques as OT tools in industrial applications.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

A Comparative Study of Adaptive Order Tracking Techniques for Rotating Machinery Analysis: Computer Experiments and Practical Implementations

Veljkovic

Todorovič

2016

Adv. Data Sci. Adapt. Data Anal.

View full text Add to dashboard Cite

show abstract

“…For example, things that are in good condition sound energetic, whereas they sound obviously weak under bad conditions. As a specific example, emission with a choking sound as well as abnormal acoustic/vibration energy of automobiles might indicate some problems [12]. By the same token, different sound features may symbolize corresponding characteristics of an entity.…”

Section: Introductionmentioning

confidence: 99%

Implementation of Artificial Intelligence for Classification of Frogs in Bioacoustics

Chao

Chao³

et al. 2019

Symmetry

View full text Add to dashboard Cite

This research presents the implementation of artificial intelligence (AI) for classification of frogs in symmetry of the bioacoustics spectral by using the feedforward neural network approach (FNNA) and support vector machine (SVM). Recently, the symmetry concept has been applied in physics, and in mathematics to help make mathematical models tractable to achieve the best learning performance. Owing to the symmetry of the bioacoustics spectral, feature extraction can be achieved by integrating the techniques of Mel-scale frequency cepstral coefficient (MFCC) and mentioned machine learning algorithms, such as SVM, neural network, and so on. At the beginning, the raw data information for our experiment is taken from a website which collects many kinds of frog sounds. This in fact saves us collecting the raw data by using a digital signal processing technique. The generally proposed system detects bioacoustic features by using the microphone sensor to record the sounds of different frogs. The data acquisition system uses an embedded controller and a dynamic signal module for making high-accuracy measurements. With regard to bioacoustic features, they are filtered through the MFCC algorithm. As the filtering process is finished, all values from ceptrum signals are collected to form the datasets. For classification and identification of frogs, we adopt the multi-layer FNNA algorithm in machine learning and the results are compared with those obtained by the SVM method at the same time. Additionally, two optimizer functions in neural network include: scaled conjugate gradient (SCG) and gradient descent adaptive learning rate (GDA). Both optimization methods are used to evaluate the classification results from the feature datasets in model training. Also, calculation results from the general central processing unit (CPU) and Nvidia graphics processing unit (GPU) processors are evaluated and discussed. The effectiveness of the experimental system on the filtered feature datasets is classified by using the FNNA and the SVM scheme. The expected experimental results of the identification with respect to different symmetry bioacoustic features of fifteen frogs are obtained and finally distinguished.

show abstract

“…The KNNC and NBC were implemented by utilizing the Matlab Toolbox for Pattern Recognition (PRTools 4.1) [7]. The LS-SVM was implemented by the LS-SVMlab1.5, which can be downloaded from [8]. The parameters of the LS-SVM were optimized by cross-validation method.…”

Section: Characterizing Vibration Signals Using Morphological Patternmentioning

confidence: 99%

Characterizing vibration signals utilizing morphological pattern spectrum for gear fault diagnosis

Li¹,

Gao²,

Qing-chen³

et al. 2015

Advances in Computer Science Research

View full text Add to dashboard Cite

In this investigation, we present an alternative technique to characterize the vibration signals by utilizing the morphological pattern spectrum (MPS) based on the mathematical morphology theory. Different from the conventional morphological pattern spectrum which is based on morphological open operator, we extend the morphological pattern spectrum with other morphological operators. Vibration signals measured from a gearbox with three operating states are employed to evaluate the effectiveness of MPS. Experimental results have demonstrated the extended MPS calculated based on morphological erosion operator to be very effective on characterizing vibration signals for gear fault diagnosis.

show abstract

An expert system for the diagnosis of faults in rotating machinery using adaptive order-tracking algorithm

Cited by 34 publications

References 10 publications

A Comparative Study of Adaptive Order Tracking Techniques for Rotating Machinery Analysis: Computer Experiments and Practical Implementations

A Comparative Study of Adaptive Order Tracking Techniques for Rotating Machinery Analysis: Computer Experiments and Practical Implementations

Implementation of Artificial Intelligence for Classification of Frogs in Bioacoustics

Characterizing vibration signals utilizing morphological pattern spectrum for gear fault diagnosis

Contact Info

Product

Resources

About