Condition monitoring and diagnosis of a bearing are very important for any rotating machine as it governs the safety while the machine is in operating condition. To construct a feature vector selection of suitable signal processing techniques is a challenge for vibration-based condition monitoring techniques. In the methodology proposed, Short Time Fourier Transform (STFT), Walsh Hadamard Transform (WHT) and Variable Mode Decomposition (VMD) are used to generate 2-D time-frequency spectrograms from the various fault conditions of bearing. When Deep learning techniques apply for fault diagnosis, a large amount of dataset is required for training of machine learning model. To overcome this issue single image Generative Adversarial Network (SinGAN) as a data augmentation technique, utilized for generating additional 2-D time-frequency spectrograms from various fault conditions of ball bearing. To detect fault severity, four deep learning algorithms, ResNet 34, ResNet50, VGG16, and MobileNetV2 are used as a classifier. Experiments are conducted on a rolling bearing dataset provided by the bearing data center of Case Western Reserve University (CWRU) for validating the utility of methodology proposed. Results show that the proposed methodology enables to detect fault severity level with high classification accuracy.

No abstract

No abstract

Prediction and validation of Compound factors for prioritization of watersheds is an essential application using Machine Learning (ML) Techniques in water resources engineering. In the current paper, a method is proposed to derive 14 morphometric and 3 Topo-hydrological parameters using Remote Sensing (RS) and Geographical Information System (GIS), whereas prediction and validation of compound factor using ML techniques. Compound factor (CF) values are calculated using Weighted Sum Analysis (WSA), ReliefF, correlation coefficient techniques.A ten-fold cross-validation technique is applied to two machine learning models Multi-Layer Perceptron (MLP) and Support Vector Machine (SVM). Predication accuracy of models has been further achieved by feature ranking. The accuracy of ML models is evaluated with three parameters, Mean Absolute Error (MEA), Correlation Coefficient (CC), and Root Mean Square Error (RMSE). With the ranked features and Ten-fold cross-validation, prediction results were found to be better. The methodology will be useful for the accurate prediction of CF values and to reduce the uncertainty in watershed prioritization for conservation techniques for soil and water.

No abstract