Faculty Publications
Permanent URI for this communityhttps://idr.nitk.ac.in/handle/123456789/18736
Publications by NITK Faculty
Browse
10 results
Search Results
Item Artificial Intelligence in Damage Detection of Concrete Structures: Techniques, Integration and Future Directions(Springer Science and Business Media Deutschland GmbH, 2025) Barbhuiya, S.; Das, B.B.The chapter thoroughly explores the pivotal role played by Artificial Intelligence (AI) in the identification of damages in concrete structures. It delves into conventional methods, their limitations, and how AI can effectively complement these approaches. The basics of AI, encompassing machine learning and deep learning, are elucidated within the specific context of damage detection. Additionally, the chapter examines data acquisition and pre-processing techniques tailored for AI models. It sheds light on AI-driven damage detection methodologies, such as the utilization of convolutional neural networks for image analysis, vibration analysis, and AI-enhanced non-destructive testing methods, highlighting their precision in identifying structural issues. Moreover, the chapter investigates the integration of AI into structural health monitoring systems, providing in-depth discussions on data fusion and real-time monitoring. Emphasis is placed on the significance of performance assessment and model validation to ensure the reliability of AI algorithms. The chapter also addresses future trends, including the integration of AI with the Internet of Things (IoT), and delves into ethical considerations in the sphere of infrastructure development. In summary, the chapter underscores AI's transformative potential in revolutionizing damage detection and structural health assessment, contributing to the creation of more resilient and sustainable concrete structures. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.Item Fault Detection and Health Condition Analysis of Single Stage Gear Box System(Springer Science and Business Media Deutschland GmbH info@springer-sbm.com, 2021) Mohiuddin, B.; Kivade, S.B.; Rajole, S.Every machine with the relative motion of parts produces sound and vibration. All the gear boxes usually generate vibrations and respective vibration signatures may be taken as referable characteristics if the condition of the gear is good. During working condition, whenever fault occurs, it may result in serious damage of the gear box. The change in the gear pair meshing could result in changes in vibration signals. The accelerometer mounting on the gear box system is the accurate task for assessment of pair of gear. So the technique of monitoring the condition is very essential to prevent and diagnose the vibration of gear box. Nowadays damage identification and condition monitoring of gear boxes in the industrial machinery have received more attention from the researchers. To analyze the various fault and problems related with gear box failure in a working environment efficiently and accurately, few technologies like material technology, information technology, and processing of signals, etc. bring latest solutions. For the assessment of industrial gear boxes, many investigations are carried out for monitoring the condition of machinery. Signal processing and vibration analysis techniques are well known and much suitable for industrial practices. Since, the signals of vibrations from the gear box are transient and non-stationary in nature. Every technique has some disadvantages and may not be used in all condition, i.e., few failure detection is not possible by simple vibration method. At an early stage, simple analysis by spectral is not very successful to find the injury of gear. © 2021, Springer Nature Singapore Pte Ltd.Item A note on the occurrence of landslides in Araku valley and its environs, Visakhapatnam district, Andhra Pradesh, India(2010) Balaji, P.; Pavanaguru, R.; Venkat Reddy, D.The occurrence of landslides in Araku valley and its environs of Visakhapatnam district of Andhra Pradesh have been studied. The slides occurred in a rugged hilly terrain which is a part of Eastern Ghats Mobile Belt. The slides are predominantly debris slides of varying dimensions and occurred in khondalitic country having slopes of the order of 30°. The debris are composed mostly of scree, soil, boulders and weathered rock. The significant causative factor of triggering slides was manifested through heavy rainfall associated with cyclonic storm. The causes of the slope failure include toe erosion, debris accumulation that resulted in blockade, overtopping and changes in the stream courses. The present paper is aimed to identify damage assessment, magnitude of slides and causes of slides with an attempt to suggest some long term corrective and control measures in the area. © 2010 Cafet-Innova Technical Society.Item Studies on concrete cylinders subjected to elevated temperatures(2010) Babu Narayan, K.S.; Anil Kumar, G.; Chandrakala, C.; Shashikumar, H.M.; Venkataramana, K.; Yaragal, S.C.; Chinnagiri Gowda, H.C.; Reddy, G.R.; Sharma, A.Concrete is a poor conductor of heat, but can suffer considerable damage when exposed to fire. Concrete in structures is likely to be exposed to high temperatures during fire. The relative properties of concrete after such an exposure are of great importance in terms of the serviceability of buildings. Unraveling the heating history of concrete is important to forensic research or to determine whether a fire exposed concrete structures and its components are still structurally sound or not. Assessment of fire damage concrete structures usually starts with visual observation of color change, cracking and spalling. On heating, a change in color from normal to pink is often observed and this is useful since it coincides with the onset of significant loss of concrete strength. This work reports the characteristics of concrete at elevated temperatures. Popular normal strength grades (M20, M25, M30, M35, M40 and M45) produced by Ready Mix Concrete (RMC) India, Mangalore have been used in production of test specimens (150 mm diameter and 300mm height cylinders) to obtain more meaningful and realistic data. In the preliminary phase 150 mm diameter and 300mm height cylinders were cast, cured and tested by destructive method for gathering data on strength characteristics. Later these test samples were subjected to elevated temperatures ranging from 100°C to 800°C, in steps of 100°C with a retention period of 2 hours. After exposure, weight losses were determined and then again destructive tests were conducted to estimate the residual split tensile strength. Test results indicated that weight and strength significantly reduces with an increase in temperature. © 2010 CAFET-INNOVA TECHNICAL SOCIETY. All rights reserved.Item Structural Health Monitoring techniques in civil engineering: An overview(CAFET INNOVA Technical Society cafetinnova@gmail.com 1-2-18/103, Mohini Mansion, Gagan Mahal Road, Domalguda, Hyderabad 500029, 2014) Bhavana Patel, S.S.; Venkataramana, K.; Babu Narayan, K.S.; Parla, B.; Kimura, Y.Structural Health Monitoring (SHM) is an emerging and promising technology for safety and integrity of structures. Vibration Based Monitoring (VBM) has gained more importance in the field of civil engineering as damage parameters are sensitive to vibration. This paper presents brief introduction on SHM and VBM. Traditional and advanced techniques adopted for damage identification, localization and quantification by various authors have been discussed. However it is still a challenging task for the researchers to develop a technique which gives efficient and reliable solution for a particular Structure. © 2014 CAFET-INNOVA TECHNICAL SOCIETY.Item Structural damage identification of bridge using high dimensional model representation(Bellwether Publishing, Ltd., 2021) Naveen, B.O.; Balu, A.S.Any engineering structure under the action of various internal and external factors like changes in the material properties, inadequate design, faulty construction, deterioration due to malfunctioning are susceptible to damages. In the past, many methods have attempted to identify damage by solving an inverse problem, which inevitably needs an analytical model. However, often the construction of these analytical model requires considerable effort in building a mathematical framework with acceptable level of accuracy and reliability which makes these approaches less attractive. To circumvent this complexity, this work presents a computationally efficient approach in structural damage identification using high dimensional model representation. © 2020 Taylor & Francis Group, LLC.Item Damage Analysis of Tool-Based Micromachining Setup Using Electrical Continuity-Based Contact Detection System(Springer, 2021) Veeresha, R.K.; Rao, M.; Rao, R.; Sushith, S.; Karegoudra, M.K.Initial registration of tool with respect to workpiece is a critical requirement in tool-based micromachining setup. As the tool is in the order of few hundred micrometre diameter and rotating at very high speed, hence, the chance of tool breakage or workpiece surface damage during tool workpiece registration is more during micromachining. Initial tool registration of tool with respect to workpiece circuit was developed and incorporated with developed tool-based micromachining setup. The performance of the developed electrical continuity-based contact detection circuit was done by feeding the workpiece with different offset dimensions. From the experiments, it’s observed that there is more damage in workpiece when tool workpiece offset distance is more in both milling and drilling tools. © 2021, ASM International.Item Internal damage growth in quasi-brittle fibre-reinforced cementitious materials under cyclic compressive loading(Structural Engineering Research Centre, 2023) Vidya Sagar, R.; Basu, D.J.; Suhas Reddy, K.V.; Prathap, Y.; Bhuvaneswari, G.; Sai Keerthi, P.This article reports a comparison between the internal damage growth in cementitious materials without fibres and with fibres subjected to elevated amplitude cyclic compressive loading. The damage progression was assessed using ultrasonic testing method and Acoustic Emission (AE) testing. The intricate fracture mechanism in the test specimens causes rise to a higher harmonic generation, which was used as an indicator to the internal damage. The decrement in wave peak amplitude with higher harmonic generation may be regarded as a ‘internal damge growth’ in the deformable solid. The complexity in the fracture mechanism in fibrous cementitious matrix influenced the heterogeneity of the specimen, which is reflected by the steep decrement in the slope of the line plotted using normalized higher harmonic ratio and load. It was observed that the ‘magnitude of the total damage’ developed in plain concrete at the last loading phase was relatively lower than brass coated steel fibre reinforced concrete. This was supported by the damage parameter based on generated AE, where final failure of the specimens preceded an AE avalanche. Therefore, the utilization of a combination of nondestructive testing techniques such as AE and nonlinear ultrasonic testing can offer a more comprehensive understanding of the progression of damage in quasi-brittle cementitious materials. © 2023, Structural Engineering Research Centre. All rights reserved.Item Low-velocity impact characterization of polyurethane rubber/nano-clay enriched sustainable sandwich composites: Synergy of experimentation and simulations(John Wiley and Sons Inc, 2024) Gowda, D.; Mahesh, V.; Mahesh, V.; Ravishankar, K.S.This research proposes a novel sustainable composite using basalt (B), hemp (H) and polyurethane rubber (Pu) reinforced in nano clay functionalised epoxy matrix for sacrificial structural applications prone to low-velocity impact (LVI). To this end, symmetric and asymmetric laminates such as HHHH, BBBB, BHHB, BHPuHB, BBPuHH and BPuBPuHPuH are fabricated using compression molding techniques and subjected to LVI at three different impact energies of 19.66, 39.39, and 59.05 J. The hemp fibers were treated with NaOH solution before fabrication. Material characterization such as X-ray diffraction, Raman spectroscopy and morphological studies has been carried out. The impact and post-impact properties of the proposed composites are experimentally evaluated and validated with the finite element (FE) results. The effect on the residual tensile strength degradation of laminates at different interlayers and energy levels is also investigated using the Caprino analytical model. The barely visible impact damages (BVID) are investigated through non-destructive dye-penetration tests, which facilitate easy identification of the prominent LVI damages like “Plateau” and “Cliff-drop” impressions. Based on the impact energy absorption and residual tensile strength, proposed laminates followed BHPuHB > BBBB > BHHB > HHHH. The experimentation suggests that Polyurethane core laminates support maximum impact energy absorption by favoring a structural change in interlayers. Also, the residual tensile strength decreases as impact velocity increases. Highlights: Low-velocity impact behavior of sustainable composites is experimented. Basalt, hemp and polyurethane rubber are reinforced in nano clay epoxy matrix. A FE framework to validate the experimentation is proposed. Dye penetrant NDT is adopted to investigate the damages. Morphological studies are conducted to understand LVI responses. © 2024 Society of Plastics Engineers.Item Improving Vertebral Fracture Detection in C-Spine CT Images Using Bayesian Probability-Based Ensemble Learning(Multidisciplinary Digital Publishing Institute (MDPI), 2025) Pandey, A.K.; Senapati, K.; Argyros, I.K.; Pateel, G.P.Vertebral fracture (VF) may induce spinal cord injury that can lead to serious consequences which eventually may paralyze the entire or some parts of the body depending on the location and severity of the injury. Diagnosis of VFs is crucial at the initial stage, which may be challenging because of the subtle features, noise, and homogeneity present in the computed tomography (CT) images. In this study, Wide ResNet-40, DenseNet-121, and EfficientNet-B7 are chosen, fine-tuned, and used as base models, and a Bayesian-based probabilistic ensemble learning method is proposed for fracture detection in cervical spine CT images. The proposed method considers the prediction’s uncertainty of the base models and combines the predictions obtained from them, to improve the overall performance significantly. This method assigns weights to the base learners, based on their performance and confidence about the prediction. To increase the robustness of the proposed model, custom data augmentation techniques are performed in the preprocessing step. This work utilizes 15,123 CT images from the RSNA-2022 C-spine fracture detection challenge and demonstrates superior performance compared to the individual base learners, and the other existing conventional ensemble methods. The proposed model also outperforms the best state-of-the-art (SOTA) model by 1.62%, 0.51%, and 1.29% in terms of accuracy, specificity, and sensitivity, respectively; furthermore, the AUC score of the best SOTA model is lagging by 5%. The overall accuracy, specificity, sensitivity, and F1-score of the proposed model are 94.62%, 93.51%, 95.29%, and 93.16%, respectively. © 2025 by the authors.