Comparison of Conventional Method of Fault Determination with Data-Driven Approach for Ball Bearings in a Wind Turbine Gearbox

Expert Systems with Applications

Saurabh

et al. 2021

This paper proposes a wavelet and artificial intelligence-enabled rapid and efficient testing procedure for patients with Severe Acute Respiratory Coronavirus Syndrome (SARS-nCoV) through a deep learning approach from thoracic X-ray images. Presently, the virus infection is diagnosed primarily by a process called the real-time Reverse Transcriptase- Polymerase Chain Reaction (rRT-PCR) based on its genetic prints. This whole procedure takes a substantial amount of time to identify and diagnose the patients infected by the virus. The proposed research uses a wavelet-based convolution neural network architectures to detect SARS-nCoV. CNN is pre-trained on the ImageNet and trained end-to-end using thoracic X-ray images. To execute Discrete Wavelet Transforms (DWT), the available mother wavelet functions from different families, namely Haar, Daubechies, Symlet, Biorthogonal, Coiflet, and Discrete Meyer, were considered. Two-level decomposition via DWT is adopted to extract prominent features peripheral and subpleural ground-glass opacities, often in the lower lobes explicitly from thoracic X-ray images to suppress noise effect, further enhancing the signal to noise ratio. The proposed wavelet-based deep learning models of both, two-class instances (COVID vs. Normal) and four-class instances (COVID-19 vs. PNA bacterial vs. PNA viral vs. Normal) were validated from publicly available databases using k-Fold Cross Validation (k-Fold CV) technique. In addition to these X-ray images, images of recent COVID-19 patients were further used to examine the model’s practicality and real-time feasibility in combating the current pandemic situation. It was observed that the Symlet 7 approximation component with two-level manifested the highest test accuracy of 98.87%, followed by Biorthogonal 2.6 with an efficiency of 98.73%. While the test accuracy for Symlet 7 and Biorthogonal 2.6 is high, Haar and Daubechies with two levels have demonstrated excellent validation accuracy on unseen data. It was also observed that the precision, the recall rate, and the dice similarity coefficient for four-class instances were 98%, 98%, and 99%, respectively, using the proposed algorithm.

Section: Methodsmentioning

confidence: 99%

Wavelet and deep learning-based detection of SARS-nCoV from thoracic X-ray images for rapid and efficient testing

Verma

Expert Systems with Applications

Saurabh

et al. 2021

“…Owing to its better generalization property and the ability to deal with multi-labeled data, SVM found many applications in the field of fault detection and health state identification of various industrial machinery. 18,41,42 The above-prepared feature vector datasets (I, II, and III) are channeled as input to SVM for discriminating the various health states of the multi-stage gearbox. The classification accuracies are displayed in Figure 12.…”

Section: Support Vector Machinementioning

confidence: 99%

An integrated condition monitoring scheme for health state identification of a multi-stage gearbox through Hurst exponent estimates

Structural Health Monitoring

Balaji

Gyanam

et al. 2022

The vibration and acoustic signals collected from rotating machinery are often non-stationary and aperiodic, and it is a challenge to post-process and extract the defect sensitive health indicators. In this paper, we demonstrate how the estimated Hurst exponent of such measured data can be advantageous for analyzing non-stationary and aperiodic data due to its self-similarity and scale-invariance properties. To illustrate this, the paper demonstrates detection of fault diagnostics of a multi-stage gearbox operating under fluctuating speeds through estimated Hurst exponent of the raw vibration and acoustic signals as a health indicator. Thirteen health states of the gearbox are considered, and the raw vibration and acoustic signals are collected. The Hurst exponents are calculated using three different approaches: generalized Hurst exponent (q = 1, 2, 3, and 4), rescale range statistical (R/S) analysis, and dispersion analysis from the vibration and acoustic signals. Three different health indicator datasets are formulated and subjected to feature learning through conventional machine-learning (decision tree and support vector machine) and advanced machine-learning (deep-learning) classifiers. The effectiveness of these datasets while discriminating between the health states of the gearbox is investigated, yielding classification accuracies of 96.4% when compared with the individual health indicator datasets. The ability of the fault diagnosis and defect severity analysis with reduced reliance on the signal post-processing algorithms is demonstrated.

“…Kankar et al., 2011a) reported that, SVM has registered the highest classification accuracies while classifying the bearing fault conditions compared to ANN. PCA is being used not only to classify the data but also to reduce the dimensionality of the data with minimal loss of the original data (Nembhard et al., 2014; Balavignesh et al., 2018). PCA is an orthogonal linear transformation such that the original data are transformed into a new spatial coordinate system.…”

Section: Introductionmentioning

confidence: 99%

Integrated condition monitoring scheme for bearing fault diagnosis of a wind turbine gearbox

Journal of Vibration and Control

Sabareesh

Supradeepan

et al. 2019

Rolling element bearing faults of a laboratory scale wind turbine gearbox operating under nonstationary loads have been diagnosed using condition monitoring (CM) techniques such as vibration analysis, acoustic analysis, and lubrication oil analysis. Two local bearing faults, namely, bearing inner race fault and bearing outer fault are seeded in the gearbox. The raw data from these techniques are decomposed and wavelet approximation coefficients of level four (a4) are extracted using discrete wavelet transform (DWT). A plethora of statistical features is computed from the wavelet approximation coefficients and the most significant features are being identified by implementing the decision tree algorithm. The classification efficiencies of each of these CM techniques are compared by using the support-vector machine algorithm. Furthermore, an integrated CM scheme is developed by combining the individual CM techniques and the fault diagnosing ability of the integrated CM scheme is compared with the individual CM techniques. A principal component analysis-based approach is used as a feature classification algorithm and an input feature matrix is formed by combining the significant features extracted from vibration, acoustic, and lubrication oil analysis. It has been observed that the integrated CM scheme has provided better classification interpretations than the single CM techniques and it can be extended for real time fault diagnosis of a wind turbine gearbox.