An evolving neuro-fuzzy technique for system state forecasting

Wang, Wilson; Li, De Zhi; Vrbanek, J.

doi:10.1016/j.neucom.2012.02.006

Cited by 27 publications

(13 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Ramasso, et al [113], proposed a method combining NFSs and belief function theory to evaluate the RUL of a turbofan engine. Wang, et al [114], proposed an evolutionary neuro-fuzzy (eNF) predictor on time-varying dynamic systems. A newly enhanced least squares estimator was used to train the linear parameters of the eNF predictor.…”

Section: Nfssmentioning

confidence: 99%

Comprehensive Overview on Computational Intelligence Techniques for Machinery Condition Monitoring and Fault Diagnosis

Zhang

Jia

Zhu

et al. 2017

Chin. J. Mech. Eng.

View full text Add to dashboard Cite

Computational intelligence is one of the most powerful data processing tools to solve complex nonlinear problems, and thus plays a significant role in intelligent fault diagnosis and prediction. However, only few comprehensive reviews have summarized the ongoing efforts of computational intelligence in machinery condition monitoring and fault diagnosis. The recent research and development of computational intelligence techniques in fault diagnosis, prediction and optimal sensor placement are reviewed. The advantages and limitations of computational intelligence techniques in practical applications are discussed. The characteristics of different algorithms are compared, and application situations of these methods are summarized. Computational intelligence methods need to be further studied in deep understanding algorithm mechanism, improving algorithm efficiency and enhancing engineering application. This review may be considered as a useful guidance for researchers in selecting a suitable method for a specific situation and pointing out potential research directions.

show abstract

Section: Nfssmentioning

confidence: 99%

Comprehensive Overview on Computational Intelligence Techniques for Machinery Condition Monitoring and Fault Diagnosis

Zhang

Jia

Zhu

et al. 2017

Chin. J. Mech. Eng.

View full text Add to dashboard Cite

show abstract

“…The Mackey-Glass data set (Farmer, 1982;Li and Wang, 2011;Wang et al, 2012) is a commonly used simulation data set in the field of time series forecasting to compare the performance of predictors, due to its specific properties such as chaotic, non-periodic and non-convergence, it is given by:…”

Section: Performance Evaluationmentioning

confidence: 99%

An Evolving Autoregressive Predictor for Time Series Forecasting

Li¹,

Wang²,

Ismail³

2015

American Journal of Engineering and Applied Sciences

Self Cite

View full text Add to dashboard Cite

Autoregressive (AR) model is a common predictor that has been extensively used for time series forecasting. Many training methods can used to update AR model parameters, for instance, least square estimate and maximum likelihood estimate; however, both techniques are sensitive to noisy samples and outliers. To deal with the problems, an evolving AR predictor, EAR, is developed in this study to enhance prediction accuracy and mitigate the effect of noisy samples and outliers. The model parameters of EAR are trained with an Adaptive Least Square Estimate (ALSE) method, which can learn samples characteristics more effectively. In each training epoch, the ALSE weights the samples by their fitting accuracy. The samples with larger fitting errors will be given a larger penalty value in the cost function; however the penalties of difficult-to-predict samples will be adaptively reduced to enhance the prediction accuracy. The effectiveness of the developed EAR predictor is verified by simulation tests. Test results show that the proposed EAR predictor can capture the dynamics of the time series effectively and predict the future trend accurately.

show abstract

“…Their superior performance was further confirmed by the studies of Zhao et al [167] in bearing prognosis and Wang et al [172] in machinery prognosis. Zhao et al [167] pointed out that an NF system performs better than RBFN in terms of accuracy, reliability, and dynamic modelling and tracking.…”

Section: The Robustness Of This Technique Is Due To the Combination Omentioning

confidence: 70%

“…• Overcomes the disadvantages of fuzzy system by integrating it with neural network to train the fuzzy structure and parameters [165][166][167] • Very reliable and robust prognostic technique with high forecasting accuracy [166] • Fast and accurately capture and model the system dynamic behaviour so that it can be further utilized to perform prognosis of machine health [166,168] • The most promising flexible-model technique in areas with high uncertainty and complexity [165,166,169] • Model design based on linguistic rules making it easy to comprehend [165,169] • Can apply to deal with non-stationary operating condition [167,170] • Inherent non-linear nature [165,169] • Short prediction horizons [65] • • Unable to update the system states in real time using the updated online new data [168] • With fixed reasoning structures but without sufficient adaptive capability to accommodate timevarying dynamic effects [172] • Parallel processing and fault-tolerance abilities [165,169] …”

Section: Fuzzy(nf) Networkmentioning

confidence: 99%

“…Zhao et al [167] pointed out that an NF system performs better than RBFN in terms of accuracy, reliability, and dynamic modelling and tracking. Wang et al [172] used an NF system for machinery condition prognostics and proved its high accuracy in forecasting. Their technique effectively captured the dynamics of the system and accommodated the system's varying conditions.…”

Section: The Robustness Of This Technique Is Due To the Combination Omentioning

confidence: 99%

See 1 more Smart Citation

Multi-Sensor Condition Monitoring of Bearings Using Support Vector Machines

Kan¹

View full text Add to dashboard Cite

Keywords AbstractBearings are one of the most commonly-used and crucial components in the majority of rotating machines in industrial applications. Failure of this component is common and can lead to machine breakdown. If it is not detected in time, bearing faults can even lead to catastrophic failures. An effective diagnostic system provides early warning and fault identification such that any machine breakdown can be avoided. Condition monitoring can benefit plant operators resulting in shorter downtimes, higher operation reliability, reduced operations and maintenance cost, and more effective maintenance and logistics planning.However, machines and associated systems today are increasingly complex, while diagnostic techniques have been mainly applied to relatively simple rotating machines. Therefore, there is a need for research on condition monitoring techniques that can be applied to complex systems in variable operating conditions. This thesis presents a study on bearing condition monitoring under variable operating condition using Support Vector Machines. Data collected from multiple sensors including accelerometers, acoustic emission sensors and tachometers are used for the studies presented in this thesis. Support Vector Machines are an efficient method for classification and prediction, and shows outstanding performance in modelling and generalization.The study begins with collecting bearing condition monitoring data. Vibration analysis is a well-established technique, while acoustic emission is gaining an increasing amount of attention especially on its capability to detect bearing incipient fault such as subsurface cracks. Existing studies so far have not demonstrated AE's diagnostic capabilities using naturally-damaged bearing, and only a very few studies adopt envelope and cyclostationary analysis on bearing fault diagnosis with this sensor technology. Due to the second-order cyclostationary nature of bearing signals and the success of envelope analysis in analysing bearing signals, the diagnostic and prognostic studies presented in this thesis make use of both envelope analysis and cyclostationary analysis to analyse vibration and acoustic emission bearing signals that will be collected from bearing diagnostics and run-to-failure prognostic experiments through a bearing diagnostic test-rig and a bearing prognostic test-rig.Using the collected data, the effectiveness and diagnostic capability of cyclostationary analysis will first be assessed using feature analysis with support vector machine. A diagnostic study is then conducted, investigating the diagnostic effectiveness of acoustic emission and its superiority to vibration, especially in the detection of bearing subsurface cracks. Through comparison of AE with vibration signals, this study confirms AE's superiority in detecting subsurface cracks in bearings and the absence of vibration symptoms of subsurface cracks.This diagnostic study has also shown the crucial ability of the cyclic logarithmic envelope iii spectrum in separating different cyc...

show abstract

An evolving neuro-fuzzy technique for system state forecasting

Cited by 27 publications

References 21 publications

Comprehensive Overview on Computational Intelligence Techniques for Machinery Condition Monitoring and Fault Diagnosis

Comprehensive Overview on Computational Intelligence Techniques for Machinery Condition Monitoring and Fault Diagnosis

An Evolving Autoregressive Predictor for Time Series Forecasting

Multi-Sensor Condition Monitoring of Bearings Using Support Vector Machines

Contact Info

Product

Resources

About