Browsing by Author "Mahanta T.K."

Now showing 1 - 2 of 2
  • Thumbnail Image
    Item
    Ensemble Deep Learning for Wear Particle Image Analysis
    (Multidisciplinary Digital Publishing Institute (MDPI), 2023) Shah R.; Sridharan N.V.; Mahanta T.K.; Muniyappa A.; Vaithiyanathan S.; Ramteke, Sangharatna M.; Marian, Max
    This technical note focuses on the application of deep learning techniques in the area of lubrication technology and tribology. This paper introduces a novel approach by employing deep learning methodologies to extract features from scanning electron microscopy (SEM) images, which depict wear particles obtained through the extraction and filtration of lubricating oil from a 4-stroke petrol internal combustion engine following varied travel distances. Specifically, this work postulates that the amalgamation of ensemble deep learning, involving the combination of multiple deep learning models, leads to greater accuracy compared to individually trained techniques. To substantiate this hypothesis, a fusion of deep learning methods is implemented, featuring deep convolutional neural network (CNN) architectures including Xception, Inception V3, and MobileNet V2. Through individualized training of each model, accuracies reached 85.93% for MobileNet V2 and 93.75% for Inception V3 and Xception. The major finding of this study is the hybrid ensemble deep learning model, which displayed a superior accuracy of 98.75%. This outcome not only surpasses the performance of the singularly trained models, but also substantiates the viability of the proposed hypothesis. This technical note highlights the effectiveness of utilizing ensemble deep learning methods for extracting wear particle features from SEM images. The demonstrated achievements of the hybrid model strongly support its adoption to improve predictive analytics and gain insights into intricate wear mechanisms across various engineering applications.
  • No Thumbnail Available
    Item
    Wear particle image analysis: feature extraction, selection and classification by deep and machine learning
    (2024) Vivek J.; Venkatesh S N.; Mahanta T.K.; V S.; Amarnath M.; Ramteke R., Sangharatna Munneshwar; Marian, Max
    Purpose: This study aims to explore the integration of machine learning (ML) in tribology to optimize lubrication interval decisions, aiming to enhance equipment lifespan and operational efficiency through wear image analysis. Design/methodology/approach: Using a data set of scanning electron microscopy images from an internal combustion engine, the authors used AlexNet as the feature extraction algorithm and the J48 decision tree algorithm for feature selection and compared 15 ML classifiers from the lazy-, Bayes and tree-based families. Findings: From the analyzed ML classifiers, instance-based k-nearest neighbor emerged as the optimal algorithm with a 95% classification accuracy against testing data. This surpassed individually trained convolutional neural networks’ (CNNs) and closely approached ensemble deep learning (DL) techniques’ accuracy. Originality/value: The proposed approach simplifies the process, enhances efficiency and improves interpretability compared to more complex CNNs and ensemble DL techniques.