Validation of a physics-based model of a rotating machine for synthetic data generation in hybrid diagnosis

Leturiondo, Urko; Salgado, Óscar; Galar, Diego

doi:10.1177/1475921716676053

Cited by 12 publications

(8 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…x jk 2 (7) where x jk (j = 1:7,k = 1:n) is the amplitude of discrete point of reconstructed signal S j .…”

Section: Feature Extractionmentioning

confidence: 99%

“…In general, methods of prognostic and diagnostics can be categorized into physics-based, data-driven, and hybrid approaches [3,4]. The physics-based method uses a specific physical model to represent the normal machine state and detects the potential failure types based on the deviations between the actual system and the physical model [5][6][7][8][9][10][11]. Hashemnia et al [5,6] used frequency response analysis diagnostics to improve the fault detection of power transformer winding.…”

Section: Introductionmentioning

confidence: 99%

“…Hashemnia et al [5,6] used frequency response analysis diagnostics to improve the fault detection of power transformer winding. Leturiondo et al [7] presented an electromechanical model of a rotating machine for its diagnosis. Lu et al [8] proposed a physics-based prognostic model for the rolling element bearings using the realized volatility and wavelet neural network to predict their remaining life.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Failure Type Prediction Using Physical Indices and Data Features for Solenoid Valve

et al. 2020

View full text Add to dashboard Cite

A high-speed solenoid valve is a key component of the braking system. Accurately predicting the failure type of the solenoid valve is an important guarantee for safe operation of the braking system. However, electrical, magnetic, and mechanical coupling aging mechanism; individual differences; and uncertainty of aging processes have remained major challenges. To address this problem, a method combining physical indices and data features is proposed to predict the failure type of solenoid valve. Firstly, the mechanism model of the solenoid valve is established and five physical indices are extracted from the driven current curve. Then, the frequency band energy characteristics are obtained from the current change rate curve of the solenoid valve by wavelet packet decomposition. Combining physical indices and frequency band energy characteristics into a comprehensive feature vector, we applied random forest to both predict and classify the failure type. We generate a data set consisting of 60 high-speed solenoid valves periodically switched under accelerated aging test conditions, including driven current, final failure type, and switching cycles. The prediction result shows that the proposed method achieves 95.95% and 94.68% precision for the two failures using the driven current data of the 3000th cycle and has better prediction performance than other algorithms.

show abstract

“…x jk 2 (7) where x jk (j = 1:7,k = 1:n) is the amplitude of discrete point of reconstructed signal S j .…”

Section: Feature Extractionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Failure Type Prediction Using Physical Indices and Data Features for Solenoid Valve

et al. 2020

View full text Add to dashboard Cite

show abstract

“…Urko et al [13] propose an architecture to implement hybrid modelling based on the fusion of real data and synthetic data. The proposed hybrid modelling architecture is validated in the field of rotating machinery, where the goal is to improve diagnosis and prognosis and, consequently, to optimize maintenance.…”

Section: Integrating Model-based and Data Drivenmentioning

confidence: 99%

Probability-Based Algorithm for Bearing Diagnosis with Untrained Spall Sizes

Tam

Kalech

Rokach

et al. 2020

Sensors

View full text Add to dashboard Cite

Bearing spall detection and predicting its size are great challenges. Model-based simulation is a well-known traditional approach to physically model the influence of the spall on the bearing. Building a physical model is challenging due to the bearing complexity and the expert knowledge required to build such a model. Obviously, building a partial physical model for some of the spall sizes is easier. In this paper, we propose a machine-learning algorithm, called Probability-Based Forest, that uses a partial physical model. First, the behavior of some of the spall sizes is physically modeled and a simulator based on this model generates scenarios for these spall sizes in different conditions. Then, the machine-learning algorithm trains these scenarios to generate a prediction model of spall sizes even for those that have not been modeled by the physical model. Feature extraction is a key factor in the success of this approach. We extract features using two traditional approaches: statistical and physical, and an additional new approach: Time Series FeatuRe Extraction based on Scalable Hypothesis tests (TSFRESH). Experimental evaluation with well-known physical model shows that our approach achieves high accuracy, even in cases that have not been modeled by the physical model. Also, we show that the TSFRESH feature-extraction approach achieves the highest accuracy.

show abstract

“…Bonnardot et al [7] tracked the rotation behavior of a gearbox based on resampling the acceleration signals. Leturiondo et al [8] evaluated the condition of the gearbox based on the physics-based model. In their model, not only the dynamics of the rolling element bearings have been considered, but also the influence of the electrical process is included.…”

Section: Introductionmentioning

confidence: 99%

Acoustic Emission Signatures of Fatigue Damage in Idealized Bevel Gear Spline for Localized Sensing

Zhang

Ozevin

Hardman

et al. 2017

Metals

View full text Add to dashboard Cite

In many rotating machinery applications, such as helicopters, the splines of an externally-splined steel shaft that emerges from the gearbox engage with the reverse geometry of an internally splined driven shaft for the delivery of power. The splined section of the shaft is a critical and non-redundant element which is prone to cracking due to complex loading conditions. Thus, early detection of flaws is required to prevent catastrophic failures. The acoustic emission (AE) method is a direct way of detecting such active flaws, but its application to detect flaws in a splined shaft in a gearbox is difficult due to the interference of background noise and uncertainty about the effects of the wave propagation path on the received AE signature. Here, to model how AE may detect fault propagation in a hollow cylindrical splined shaft, the splined section is essentially unrolled into a metal plate of the same thickness as the cylinder wall. Spline ridges are cut into this plate, a through-notch is cut perpendicular to the spline to model fatigue crack initiation, and tensile cyclic loading is applied parallel to the spline to propagate the crack. In this paper, the new piezoelectric sensor array is introduced with the purpose of placing them within the gearbox to minimize the wave propagation path. The fatigue crack growth of a notched and flattened gearbox spline component is monitored using a new piezoelectric sensor array and conventional sensors in a laboratory environment with the purpose of developing source models and testing the new sensor performance. The AE data is continuously collected together with strain gauges strategically positioned on the structure. A significant amount of continuous emission due to the plastic deformation accompanied with the crack growth is observed. The frequency spectra of continuous emissions and burst emissions are compared to understand the differences of plastic deformation and sudden crack jump. The correlation of the cumulative AE events at the notch tip and the strain data is used to predict crack growth. The performance of the new sensor array is compared with the conventional AE sensors in terms of signal to noise ratio and the ability to detect fatigue cracking.

show abstract

Validation of a physics-based model of a rotating machine for synthetic data generation in hybrid diagnosis

Cited by 12 publications

References 26 publications

Failure Type Prediction Using Physical Indices and Data Features for Solenoid Valve

Failure Type Prediction Using Physical Indices and Data Features for Solenoid Valve

Probability-Based Algorithm for Bearing Diagnosis with Untrained Spall Sizes

Acoustic Emission Signatures of Fatigue Damage in Idealized Bevel Gear Spline for Localized Sensing

Contact Info

Product

Resources

About