Entropy Measures in Machine Fault Diagnosis: Insights and Applications

Huo, Zhiqiang; Martínez-García, Miguel; Zhang, Yu; Yan, Ruqiang; Shu, Lei

doi:10.1109/tim.2020.2981220

Cited by 136 publications

(48 citation statements)

References 116 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Further, where this project identified singular model thresholds and hyperparameters deemed suitable to the wind farm as a whole (for simplicity's sake), it is entirely possible that a purely data-driven tuning of models on an individual wind turbine basis could provide even stronger NBM's than those chosen as best in this study. Finally, to provide a level of oversight and reliability, monitoring the model's wind turbine performance metric using a complexity indicator such as entropy could be implemented as in [21].…”

Section: Discussionmentioning

confidence: 99%

Applied Machine Learning Techniques for Performance Analysis in Large Wind Farms

Lyons

Göçmen

2021

Energies

View full text Add to dashboard Cite

As the amount of information collected by wind turbines continues to grow, so too does the potential of its leveraging. The application of machine learning techniques as an advanced analytic tool has proven effective in solving tasks whose inherent complexity can outreach expert-based ability. Such is the case presented by this study, in which the dataset to be leveraged is high-dimensional (79 turbines × 7 SCADA channels) and high-frequency (1 Hz). In this paper, a series of machine learning techniques is applied to the retrospective power performance analysis of a withheld test set containing SCADA data collectively representing 2 full days worth of operation at the Horns Rev I offshore wind farm. A sequential machine-learning based methodology is thoroughly explored, refined, then applied to the power performance analysis task of identifying instances of abnormal behaviour; namely instances of wind turbine under and over-performance. The results of the final analysis suggest that a normal behaviour model (NBM), consisting of a uniquely constructed artificial neural network (ANN) variant trained on abnormality filtered dataset, indeed proves effective in accomplishing the power performance analysis objective. Instances of over and under performance captured by the developed NBM network are presented and discussed, including the operation status of the turbines and the uncertainty embedded in the prediction results.

show abstract

Section: Discussionmentioning

confidence: 99%

Applied Machine Learning Techniques for Performance Analysis in Large Wind Farms

Lyons

Göçmen

2021

Energies

View full text Add to dashboard Cite

show abstract

“…These often lead to significant implementation difficulties. The vibration signals contain the complete structural state information [41]; thus, it is of great potential to use the vibration signals as structural damage indicators. The information of a single sensor has a certain ability to detect the structural damage state [42]; however, the influence of the sensor location on damage detection results is not clear, and the complementarity of multiple sensors is also a topic worthy of further study.…”

Section: Introductionmentioning

confidence: 99%

Multi-Sensor and Decision-Level Fusion-Based Structural Damage Detection Using a One-Dimensional Convolutional Neural Network

Chen

Liu

et al. 2021

Sensors

View full text Add to dashboard Cite

This paper presents a novel approach to substantially improve the detection accuracy of structural damage via a one-dimensional convolutional neural network (1-D CNN) and a decision-level fusion strategy. As structural damage usually induces changes in the dynamic responses of a structure, a CNN can effectively extract structural damage information from the vibration signals and classify them into the corresponding damage categories. However, it is difficult to build a large-scale sensor system in practical engineering; the collected vibration signals are usually non-synchronous and contain incomplete structure information, resulting in some evident errors in the decision stage of the CNN. In this study, the acceleration signals of multiple acquisition points were obtained, and the signals of each acquisition point were used to train a 1-D CNN, and their performances were evaluated by using the corresponding testing samples. Subsequently, the prediction results of all CNNs were fused (decision-level fusion) to obtain the integrated detection results. This method was validated using both numerical and experimental models and compared with a control experiment (data-level fusion) in which all the acceleration signals were used to train a CNN. The results confirmed that: by fusing the prediction results of multiple CNN models, the detection accuracy was significantly improved; for the numerical and experimental models, the detection accuracy was 10% and 16–30%, respectively, higher than that of the control experiment. It was demonstrated that: training a CNN using the acceleration signals of each acquisition point and making its own decision (the CNN output) and then fusing these decisions could effectively improve the accuracy of damage detection of the CNN.

show abstract

“…Entropy is used as an analytical method to estimate the complexity of time series. It is widely used in the fault diagnosis of bearings [26][27][28][29][30]. At present, research on entropy is ongoing.…”

Section: Introductionmentioning

confidence: 99%

A New Method Based on Time-Varying Filtering Intrinsic Time-Scale Decomposition and General Refined Composite Multiscale Sample Entropy for Rolling-Bearing Feature Extraction

Han

et al. 2021

Entropy

View full text Add to dashboard Cite

The early fault diagnosis of rolling bearings has always been a difficult problem due to the interference of strong noise. This paper proposes a new method of early fault diagnosis for rolling bearings with entropy participation. First, a new signal decomposition method is proposed in this paper: intrinsic time-scale decomposition based on time-varying filtering. It is introduced into the framework of complete ensemble intrinsic time-scale decomposition with adaptive noise (CEITDAN). Compared with traditional intrinsic time-scale decomposition, intrinsic time-scale decomposition based on time-varying filtering can improve frequency-separation performance. It has strong robustness in the presence of noise interference. However, decomposition parameters (the bandwidth threshold and B-spline order) have significant impacts on the decomposition results of this method, and they need to be artificially set. Aiming to address this problem, this paper proposes rolling-bearing fault diagnosis optimization based on an improved coyote optimization algorithm (COA). First, the minimal generalized refined composite multiscale sample entropy parameter was used as the objective function. Through the improved COA algorithm, optimal intrinsic time-scale decomposition parameters based on time-varying filtering that match the input signal are obtained. By analyzing generalized refined composite multiscale sample entropy (GRCMSE), whether the mode component is dominated by the fault signal is determined. The signal is reconstructed and decomposed again. Finally, the mode component with the highest energy in the central frequency band is selected for envelope spectrum variation for fault diagnosis. Lastly, simulated and experimental signals were used to verify the effectiveness of the proposed method.

show abstract

Entropy Measures in Machine Fault Diagnosis: Insights and Applications

Cited by 136 publications

References 116 publications

Applied Machine Learning Techniques for Performance Analysis in Large Wind Farms

Applied Machine Learning Techniques for Performance Analysis in Large Wind Farms

Multi-Sensor and Decision-Level Fusion-Based Structural Damage Detection Using a One-Dimensional Convolutional Neural Network

A New Method Based on Time-Varying Filtering Intrinsic Time-Scale Decomposition and General Refined Composite Multiscale Sample Entropy for Rolling-Bearing Feature Extraction

Contact Info

Product

Resources

About