Conference Papers

Permanent URI for this collectionhttps://idr.nitk.ac.in/handle/123456789/28506

Browse

Author: search.filters.author.Bhat, R.

Search Results

Now showing 1 - 3 of 3
  • No Thumbnail Available
    Item
    Microstructure and wear behavior of austempered high carbon high silicon steel
    (EDP Sciences edps@edpsciences.com, 2018) Acharya, P.; Kumar, A.; Bhat, R.
    In the present investigation, the influence of austempering temperature and time on the microstructure and dry sliding wear behavior of high silicon steel was studied. The test specimens were initially austenitised at 900°C for 30 minutes, thereafter austempered at various temperatures 280°C, 360°C and 400°C, for varying duration from 30 to 120 minutes. These samples after austempering heat treatment were subsequently air cooled to room temperature, to generate typical ausferritic microstructures and then correlated with the wear property. The test outcomes demonstrate the slight increase in specific wear rate with increase in both austempering temperature and time. Specific wear rate was found to be minimum at an austempering temperature of 280°C, that exhibits lower bainite microstructure with high hardness, on the other hand specific wear rate was found to be slightly high at increased austempering temperatures at 360°C and 400°C, due to the upper bainite structure that offered lower hardness to the matrix. The sample austempered at 280°C for 30 minutes offered superior wear resistance when compared to other austempering conditions, mainly due to the presence of fine acicular bainitic ferrite along with stabilized retained austenite and also some martensite in the microstructure. © The Authors, published by EDP Sciences, 2018.
  • No Thumbnail Available
    Item
    Multiple response optimisation of process parameters during drilling of GFRP composite with a solid carbide twist drill
    (Elsevier Ltd, 2020) Bhat, R.; Mohan, N.; Sharma, S.; Dayananda Pai, D.; Kulkarni, S.M.
    The article focuses on investigating the effect of operational parameters like feed and speed along with the composite material thickness on the damages caused in the glass fibre reinforced polymer (GFRP) composites during the drilling process. The GFRP composite studied in the presented work comprises E-glass fibre as the reinforcing material and the marine-grade isophthalic polyester as the binding matrix. Multiple responses considered in work comprises Peel-up delamination, push-down delamination and surface roughness. The technique for order of preference by similarity to ideal solution (TOPSIS) is used to develop the performance index and optimise the multiple response problem. Stepwise analysis of variance (S-ANOVA) is used to investigate the significance of each input parameter. The interaction effects of the variables are investigated using the response surface plots. The results indicate that the composite thickness contributes maximum towards the variance in the overall performance index (21.30%) and the optimum combination obtained using TOPSIS approach within the experimental limits for the selected GFRP is N3f1t1 with the maximum value of Pi (0.888). The regression model developed proves to have high goodness of fit with just 6.01% average error between predicted and experimental values. © 2019 Elsevier Ltd.
  • No Thumbnail Available
    Item
    Semantic Segmentation for Autonomous Driving
    (Springer Science and Business Media Deutschland GmbH, 2023) Divakarla, U.; Bhat, R.; Madagaonkar, S.B.; Pranav, D.V.; Shyam, C.; Chandrashekar, K.
    Recently, autonomous vehicles (namely self-driving cars) are becoming increasingly common in developed urban areas. It is of utmost importance for real-time systems such as robots and automatic vehicles (AVs) to understand visual data, make inferences and predict events in the near future. The ability to perceive RGB values (and other visual data such as thermal, LiDAR), and segment each pixel into objects is called semantic segmentation. It is the first step toward any sort of automated machinery. Some existing models use deep learning methods for 3D object detection in RGB images but are not completely efficient when they are fused with thermal imagery as well. In this paper, we summarize many of these architectures starting from those that are applicable to general segmentation and then those that are specifically designed for autonomous vehicles. We also cover open challenges and questions for further research. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.