Faculty Publications

Permanent URI for this communityhttps://idr.nitk.ac.in/handle/123456789/18736

Publications by NITK Faculty

Browse

Subject: search.filters.subject.Mine safety

Search Results

Now showing 1 - 7 of 7
  • No Thumbnail Available
    Item
    Evaluation of Whole Body Vibration of Heavy Earth Moving Machinery Operators
    (Springer Nature, 2020) Jeripotula, S.K.; Mangalpady, A.; Raj, G.R.
    Operators of Heavy Earth Moving Machinery (HEMM) performing routine tasks in surface mines are highly vulnerable to whole body vibration (WBV) due to their continuous exposure to vibration. In the present study seventeen types of machinery were considered for the evaluation of the operator’s exposure to WBV. The measurements were made by placing the triaxial seat pad accelerometer on operator’s seat-surface as well as at the seat-back. Among these machinery one shovel, two front-end loaders, three drills, one grader and one water sprinkler were found to have RMS values in the severe zone as per ISO2631-1:1997 standards for seat-surface measurements. Similarly, for the seat-back measurements, one front-end loader, two drills, one grader and one water sprinkler were experienced the highest RMS value. For both seat-surface and seat-back measurements, Z-axis (i.e. vertical direction) was found to be a prominent axis for most of the machinery. © 2020, Springer Nature Switzerland AG.
  • No Thumbnail Available
    Item
    A Systematic Review on Implementation of Internet-of-Things-Based System in Underground Mines to Monitor Environmental Parameters
    (Springer, 2024) Naik, A.S.; Kumar Reddy, S.K.; Raj, G.R.
    The automation in the mining industry by adopting Internet of Things (IoT) technology is great potential to improve safety and efficiency. The mining industry is recognized globally for its valuable resources (gold, coal, iron ore, etc.) which are obtained by mining below the surface. The productivity and safety of mine personnel are impacted by several environmental parameters in underground mines, such as toxic gases, flammable gases, elevated levels of carbon dioxide (CO2), and decreased levels of oxygen (O2) concentrations. The presence of these gases is a significant issue and needs to be dealt with suitably. There are various methods to monitor the percentage of gases and provide a suitable course of action in case of an increase in the threshold limit of gases. Each system has its limitations. Wireless monitoring systems are indispensable in underground mines. This paper presents the methodology to adopt IoT in underground mines to measure environmental parameters in underground mine areas, the structure of installation of sensors in underground mines, threshold limits of gases, and underground mine disasters which were caused by gas explosion accidents. Further, it evaluates wireless sensor networks (WSNs) techniques ZigBee and LoRa for underground mines applications. Subsequently, it proposed a real-time industrial safety system in underground mines with its working, effectiveness, and scope are discussed. © The Institution of Engineers (India) 2023.
  • No Thumbnail Available
    Item
    Evaluation of Whole-Body Vibration (WBV) of Dozer Operators Based on Job Cycle
    (Springer, 2019) Jeripotula, S.K.; Mangalpady, A.; Raj, G.R.
    Dozer operators are frequently exposed to high levels of occupational vibration. So far, no study reported component wise evaluation of dozer cycle of operation. In the present study, WBV data were collected by placing the trial accelerometer at operator’s seat-surface and at seat-back. Frequency-weighted root mean square (RMS), vibration dose value (VDV) and crest factor were collected for each dozer for two phases’ forward motion and return motion. All the dozers under study were found to be in severe zone with respect to measured RMS, during forward motion and return motion, irrespective of type of measurements (i.e., seat-surface and seat-back). As per VDV, out of eight dozers three dozers were found to be in caution zone during forward motion and three in return motion. According to EU Directive 2002 (as per RMS), all the dozers under study have reported exposure action value above 0.5 m/s2. Further, out of eight dozers, four dozers have shown exposure limit value above 1.15 m/s2 for seat-surface measurements and three dozers for seat-back measurements. Vibration mitigation strategies should be adapted not just based on intensity of vibration but also with respect to dominant axis of vibration. Considering the severe health risk due to the translational vibration (i.e., in x-direction), the vibration risk in the forward x-direction can be reduced by using seat belt; similarly in rear x-direction it can be attenuated by placing lumber-assisted back rest. © 2019, The Institution of Engineers (India).
  • No Thumbnail Available
    Item
    Assessment of Exposure to Whole-Body Vibration of Dozer Operators Based on Postural Variability
    (Springer, 2020) Jeripotula, S.K.; Mangalpady, A.; Raj, G.R.
    The main aim of this work is to evaluate whole-body vibration (WBV) of dozer operators based on three sitting postures (i.e., with 15° lean forward inclination posture, vertically erect posture with no inclination, and with 15° lean backward inclination posture) in Indian surface coal mines. A seat pad tri-axial accelerometer was used to collect WBV data from six dozer operators for three different sitting postures. Results showed that except for Dozer-1, 2, 4, and 5 operators during lean forward sitting posture and Dozer-4 operator during vertical erected posture, no other dozer operators have exceeded an exposure limit value (ELV) of 1.15 m/s2 in any of the considered sitting postures. Similarly, the vibration dose value (VDV) based on exposure action value (EAV) of 9.1 m/s1.75 has surpassed for all the dozers. But no dozer operator has exceeded an exposure limit value of 21 m/s1.75. The outcome of the study infers that based on “above health guidance caution zone (HGCZ)” for daily vibration exposure, i.e., A(8) measurements, for the operator sitting in lean backward postures the vibration amplification was reduced by 32.89% less compared with lean forward posture and 16.23% less when compared with vertically erected posture. Similarly, based on VDV(8), the exposure to vibration for the lean backward posture was reduced by 33.34% when compared with lean forward posture and 17.11% less when compared with vertically erected posture. Based on the above observation, it is concluded that lean back inclination with a trunk flexion of 15° is a favorable sitting posture, as it exposes the dozer operators to minimum vibration. © 2020, Society for Mining, Metallurgy & Exploration Inc.
  • No Thumbnail Available
    Item
    Human-in-the-Loop Data Analytics for Classifying Fatal Mining Accident Causes Using Natural Language Processing and Machine Learning Techniques
    (Springer Science and Business Media Deutschland GmbH, 2025) Sharma, A.; Kumar, A.; Vardhan, H.; Mangalpady, A.; Mandal, B.B.; Senapati, A.; Akhil, A.; Saini, S.
    Mining remains one of the most hazardous industries globally, marked by frequent fatalities resulting from complex operational risks. While accident investigation reports hold valuable insights for improving safety practices, the manual coding of fatality narratives remains labor-intensive, inconsistent, and impractical for large datasets. Although natural language processing (NLP) and machine learning (ML) techniques have gained traction for automating the analysis of safety narratives in other high-risk industries, their application to mining accident data, particularly within the Indian context, remains limited. Addressing this gap, the present study proposes a ML framework for the semi-automated classification of fatal accident causes from unstructured text narratives reported by the Directorate General of Mines Safety (DGMS) between 2016 and 2022. A total of 401 fatal accident descriptions were pre-processed and vectorized using Bag-of-Words, TF-IDF, and Word2Vec techniques, followed by model evaluation across multiple algorithms. A semi-automated classification scheme was developed to balance efficiency with expert oversight, where high-confidence predictions were assigned automatically and uncertain cases were flagged for manual review. Logistic regression combined with TF-IDF unigram features achieved the highest performance, with an F1 score of 0.78 and an accuracy of 0.81. Overall, the developed framework successfully auto-coded 68.75% of cases with 94% accuracy, 0.93 recall, and 0.91 precision. Word cloud visualizations were also employed to capture dominant words associated with different cause categories. The proposed framework offers a practical and operationally feasible solution for assigning fatality causes in the mining sector, contributing to active safety management, surveillance, and policy formulation. © Society for Mining, Metallurgy & Exploration Inc. 2025.
  • No Thumbnail Available
    Item
    Root reinforcement of herbaceous vegetation for stabilization of coal mine overburden dump slopes
    (Springer Science and Business Media Deutschland GmbH, 2025) Kumar, A.; Nainegali, L.; Das, S.K.; Reddy, K.R.
    Slope instability of coal mine overburden dumps poses significant challenges to mining safety and environmental sustainability. This study investigates the potential for root reinforcement offered by herbaceous vegetation (Dendrocalamus strictus and Cymbopogon citratus) for enhanced slope stability. A series of pot experiments were conducted to grow grasses with the coal mine overburden material. The survival and growth of grasses in the nutrient-devoid overburden are critical because they directly impact the effectiveness of root reinforcement. Therefore, the effect of amendment quantity on plant growth was assessed. A direct shear box test was conducted on the bare and rooted samples using a fabricated internal shear test assembly to determine the strength. The higher peak shear stress and dilatancy angle observed for the rooted specimens were due to the high root tensile strength mobilizing the shear stresses. The results of shear tests were subsequently employed in limit equilibrium slope stability analyses where material heterogeneity was considered to account for uncertainties linked to material properties. The deterministic analysis provided insights into the expected improvements in slope stability due to root reinforcement, offering a baseline for comparison. Meanwhile, the probabilistic analysis considered the variability in material properties, thus providing a more comprehensive understanding of the uncertainty associated with the slope stability assessment regarding the reliability index and probability of failure. By combining experimental investigations with rigorous analytical approaches, this study enhances our understanding of how grassroots reinforcement can enhance the stability of coal mine overburden dumps. © The Author(s), under exclusive license to Springer-Verlag GmbH Germany, part of Springer Nature 2025.
  • No Thumbnail Available
    Item
    An uncertainty-aware decision support system: Integrating text narratives and conformal prediction for trustworthy accident code classification
    (Institution of Chemical Engineers, 2025) Kumar, A.; Senapati, A.; Upadhyay, R.; Chatterjee, S.; Bhattacherjee, A.; Samanta, B.
    It is imperative to assign accident classification codes to the Mine Safety and Health Administration (MSHA) accident data for effective data analysis and risk assessment. Although trained personnel are capable of performing this task, the manual process is both time-consuming and resource-intensive. Automating the classification process with machine learning (ML) algorithms promises to expedite code assignment. However, ML predictions typically lack uncertainty metrics. This study proposes an uncertainty-aware hierarchical classification framework that assists human experts in efficiently and accurately assigning accident codes. Several text representation techniques combined with different ML algorithms were employed within a hierarchical architecture to assign classification codes. Low-frequency codes were consolidated into a single category, with a primary classifier distinguishing between these and a secondary classifier further classifying the grouped categories. Regularized Adaptive Prediction Sets (RAPS) was integrated to quantify uncertainty. Highly confident predictions yielding single-class sets were automatically classified, whereas multi-class sets were flagged for manual review. Primary Classifier with XGBoost with word2vec text representation achieved the best performance, with 95.12 % coverage, 37.02 % single-class prediction sets at 96.11 % accuracy, and an average prediction set size of 2.39. Whereas the secondary classifier, a logistic regression model with TF-IDF representation, yielded 96.19 % coverage, an average set size of 1.80, and 53.66 % single-class prediction sets with 98.90 % accuracy. Additionally, sensitivity analysis determined that a 95 % coverage guarantee offers the best trade-off between prediction set size and coverage. The framework effectively integrates conformal prediction to quantify uncertainty and aid human experts in improving the decision-making process in safety management. Although the framework is broadly applicable across different sectors, it needs to be retrained on domain-specific data for effective use. © 2025 The Institution of Chemical Engineers