Statistical Spectral Analysis for Fault Diagnosis of Rotating Machines

Ciabattoni, Lucio; Ferracuti, Francesco; Freddi, Alessandro; Monteriù, Andrea

doi:10.1109/tie.2017.2762623

Cited by 127 publications

(57 citation statements)

References 34 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In each iteration, the same procedure was repeated by incrementing the value of k by one until the whole feature set was evaluated. Then, the feature subset with the maximum consistency metric (11) was selected as the best-correlated feature subset. The calculated consistency parameters are given in Fig.…”

Section: B Results and Discussionmentioning

confidence: 99%

“…. , k), where k = max(Con) (11) and N is the number of observations. Then, the mean distance vector d i (12) between the given feature values x t i at time t, (x i t , i = 1, .…”

Section: B Adaptive Feature Fusionmentioning

confidence: 99%

“…After the extraction of time-based, frequency-based, and time-frequency-based [11] features from the measurements, the feature evaluation and selection are a key step in HI construction. The feature evaluation and selection metrics can be classified as follows.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Railway Point Machine Prognostics Based on Feature Fusion and Health State Assessment

Atamuradov

Medjaher

Camci

et al. 2019

IEEE Trans. Instrum. Meas.

View full text Add to dashboard Cite

This paper presents a condition monitoring approach for point machine prognostics to increase the reliability, availability, and safety in railway transportation industry. The proposed approach is composed of three steps: 1) health indicator (HI) construction by data fusion, 2) health state assessment, and 3) failure prognostics. In Step 1, the time-domain features are extracted and evaluated by hybrid and consistency feature evaluation metrics to select the best class of prognostics features. Then, the selected feature class is combined with the adaptive feature fusion algorithm to build a generic point machine HI. In Step 2, health state division is accomplished by time-series segmentation algorithm using the fused HI. Then, fault detection is performed by using a support vector machine classifier. Once the faulty state has been classified (i.e., incipient/starting fault), the single spectral analysis recurrent forecasting is triggered to estimate the component remaining useful life. The proposed methodology is validated on in-field point machine sliding-chair degradation data. The results show that the approach can be effectively used in railway point machine monitoring.

show abstract

Section: B Results and Discussionmentioning

confidence: 99%

“…. , k), where k = max(Con) (11) and N is the number of observations. Then, the mean distance vector d i (12) between the given feature values x t i at time t, (x i t , i = 1, .…”

Section: B Adaptive Feature Fusionmentioning

confidence: 99%

See 1 more Smart Citation

Railway Point Machine Prognostics Based on Feature Fusion and Health State Assessment

Atamuradov

Medjaher

Camci

et al. 2019

IEEE Trans. Instrum. Meas.

View full text Add to dashboard Cite

show abstract

“…Because mechanical big data is typically characterized as large-volume, diverse, and of high-velocity [8], methods of extracting features rapidly and accurately from mechanical big data has become an urgent subject of research [9,10]. Existing fault diagnosis methods can be divided into two major categories [11]: physics-based models and data-driven ones [12,13]. Physics-based models overly rely on high-quality domain knowledge and necessitate massive computation costs, which reduces the overall efficiency of fault diagnosis.…”

Section: Introductionmentioning

confidence: 99%

An Intelligent Fault Diagnosis Approach Considering the Elimination of the Weight Matrix Multi-Correlation

Wang

et al. 2018

Applied Sciences

View full text Add to dashboard Cite

Faults in bearings and gearboxes, which are widely used in rotating machines, can lead to heavy investment and productivity loss. Accordingly, a fault diagnosis system is necessary to ensure a high-performance transmission. However, as mechanical fault diagnosis enters the era of big data, it can be difficult to apply traditional fault diagnosis methods because of the massive computation cost and excessive reliance on human labor. Meanwhile, unsupervised learning has been shown to have excellent performance in processing machanical big data. In this paper, an unsupervised learning method known as sparse filtering is applied, the multi-correlation of a weight matrix is investigated, and a method that is more suitable for the feature extraction of signals is proposed. The main contribution of our work is the modification of original method. First, to understand the non-monotonicity testing accuracies of the original method, the physical interpretation of input dimensions is studied. Second, using the physical interpretation, an overfitting phenomenon is discovered and examined. Third, to reduce the overfitting phenomenon, a method which eliminates the multi-correlation of the weight matrix is proposed. Finally, bearing and gear datasets are employed to verify the effectiveness of the proposed method; experimental results show that the proposed method can achieve a superior performance in comparison to the original sparse filtering model.

show abstract

“…In the past few decades, the ocean boilers system has become increasingly complex, the probability of the failure of the system is increasing, and the occurrence of the fault is also more complex [1]. If the failure of the system fails to be detected in time and correctly, it may cause a major failure in the whole system and even the catastrophic consequences of the system.…”

Section: Introductionmentioning

confidence: 99%

Research on SDG Fault Diagnosis of Ocean Shipping Boiler System Based on Fuzzy Granular Computing Under Data Fusion

Zhu

Geng

2018

Polish Maritime Research

View full text Add to dashboard Cite

The research work in this paper belongs to the application of granular computing, graph theory and its application in fault detection and diagnosis. It is a cross cutting and frontier research field in computer science, information science and graph theory. The results of this paper are of great significance to the application of the fault detection and diagnosis of the ocean boilers system. This research combines granular computing theory and signed directed graph, and proposes a new method of fault diagnosis, and applies it to the fault diagnosis of ocean ship boiler system.

show abstract

Statistical Spectral Analysis for Fault Diagnosis of Rotating Machines

Cited by 127 publications

References 34 publications

Railway Point Machine Prognostics Based on Feature Fusion and Health State Assessment

Railway Point Machine Prognostics Based on Feature Fusion and Health State Assessment

An Intelligent Fault Diagnosis Approach Considering the Elimination of the Weight Matrix Multi-Correlation

Research on SDG Fault Diagnosis of Ocean Shipping Boiler System Based on Fuzzy Granular Computing Under Data Fusion

Contact Info

Product

Resources

About