Department of Mechanical engineering

Permanent URI for this collectionhttp://localhost:4000/handle/123456789/1921

Browse

Filters

Settings

Search Results

Now showing 1 - 10 of 1564
  • No Thumbnail Available
    Item
    Vision-driven robotic grasping order generation using segmentation and relative positioning in a cluttered environment
    (Elsevier, 2025) Sangwan, Kuldip Singh
    In this paper, a multichannel vision-based approach for intelligent robotic grasping in cluttered environments is proposed. The experiments are conducted with an open-source synthetic dataset consisting of color and depth images to address this general problem. The proposed approach involves the use of a modified Cascade Mask R-CNN-based semantic segmentation model to detect and classify objects in the scene. The results show a high mAP@0.5-0.95 score of 93.85% for the customized Meta-Grasp dataset using this model. The captured depth data is processed based on the segmented mask regions to approximate their position in a 3D coordinate system. The affinity between the edge profiles is calculated to estimate the relation between the segmented objects in 3D space. This information is used to generate a priority order for object pickup such that only the objects in the top layer are picked first, followed by the underlying layers. The methodology was evaluated for various placement options for a 6-class subset of the dataset with a varying number of objects. The actual object classes and their mask positions were obtained successfully, and the priority order was calculated so that no lower-layered object was picked before the upper-lying object. Overall, the proposed two-stage decision pipeline has demonstrated its effectiveness in generating the pickup priority and sorting order for a multi-object scene and has potential applications in fully automated factories or smart manufacturing.
  • No Thumbnail Available
    Item
    Machine learning-based predictive life cycle assessment approach during product design
    (Elsevier, 2025) Sangwan, Kuldip Singh
    Most of the past efforts for the environmental impact assessment has been carried out based on the manufactured product. Environmental improvement strategies intertwined with the product design will be more effective as 70-80% of the environmental impacts are fixed during the design phase. However, the major challenge to carry out the life cycle assessment (LCA) during design phase – predictive LCA – is the data scarcity during the design phase. Therefore, this paper proposes data augmentation using deep learning techniques to overcome this challenge for predictive LCA. This paper proposes a four-phase predictive LCA methodology consisting of (i) identification of design requirements and environmental aspects, (ii) database building based upon product descriptors & environmental performance data, (iii) deep learning assisted data preprocessing, and (iv) machine learning based predictive LCA models – random forest, support vector machine, and neural network. It was found that random forest gives the better prediction based on model evaluation metrics of mean absolute error (MAE), mean square error (MSE), root mean squared error (RMSE), and R-square (R2). This research equips environmentalists, companies, researchers, and businesses with a predictive environmental conscious approach to their decision-making processes early in the design phase, thereby, fostering a sustainable approach right from the inception of a product’s design.
  • No Thumbnail Available
    Item
    A cognitive digital twin for process chain anomaly detection and bottleneck analysis
    (Taylor & Francis, 2024-07) Sangwan, Kuldip Singh
    Bottleneck detection and management plays a significant role in the context of Industry 4.0, wherein process chains have become more intricate. The dynamic nature of process chains shifts the bottleneck location, which requires an integrated methodology capable of identifying current as well as predicting future bottlenecks. The paper proposes a cognitive digital twin (CDT) with a novel explainable artificial intelligence (XAI) model. The proposed CDT is capable of (i) detecting existing bottlenecks, (ii) detecting data anomalies and process chain anomalies (iii) estimating shifting bottlenecks due to anomalies, (iv) predicting near future bottlenecks, and (v) the XAI model supports operational and strategic decision making. The usefulness of proposed CDT is demonstrated and validated experimentally on an industry 4.0 compliant learning factory. The proposed novel CDT effectively addresses the process chain bottlenecks (existing, shifting, and future) while the XAI model enhances transparency and trustworthiness for practical implementation.
  • No Thumbnail Available
    Item
    Uncertainty analysis of workpiece orientation: a mathematical decision support system for circular geometry measurements
    (Elsevier, 2025-06) Sangwan, Kuldip Singh
    The article aims at quantifying and controlling the measurement uncertainties contributed by the workpiece orientation during the automated inspection of a circular geometry by using Coordinate Measuring Machines. The paper proposes a mathematical model to compute angular error and circular variance to quantify and minimize the measurement uncertainty associated with the workpiece orientation. The proposed methodology involves part programming, acquisition of the raw coordinate data points through experiments, identification of the potential factors influencing measurement results, development of the mathematical model to estimate and correct measurement uncertainties, and finally supports the user to minimize the variations in the measurement results. It was found that diameter, circularity and centroid measurements are affected by the workpiece orientation and probe start position has a significant effect on the measurement results. The proposed model reduced uncertainties as the data tends to spread uniformly along the geometric feature. The overall measurement results improved by 12 %.
  • No Thumbnail Available
    Item
    Comparative life cycle assessment of flooring options for sustainable buildings
    (Emerald, 2023-12) Sangwan, Kuldip Singh
    This study aims to quantify and compare the environmental impacts of Marble-stone and Kota-stone flooring options widely used for buildings in India. The study discusses the possibility of carbon sequestration through Bamboo cultivation in India.
  • No Thumbnail Available
    Item
    Cyber physical production system for smart manufacturing analytics and management: a systematic literature review, framework and roadmap
    (Taylor & Francis, 2025-09) Sangwan, Kuldip Singh
    Cyber physical production system (CPPS) is a key enabling technology of Industry 4.0 that plays an important role in improving the efficiency, quality, productivity, and sustainability of production systems, resulting in smarter and more responsive manufacturing processes. An in-depth understanding of the multidisciplinary concepts of CPPS is required for quick adoption of CPPS by the industries. This paper presents a systematic literature review on CPPS, analysing 209 identified literatures from 2010 to December 2024 using the PRISMA technique. It proposes a generic CPPS framework to facilitate a comprehensive understanding of multidisciplinary concepts and serve as a roadmap for its effective implementation. Recommendations for future research developments, including innovative concepts, methodologies (tools and techniques), and practices, are explored to bridge the gap between previous studies and emerging research directions. This study serves as a reference in providing researchers and practitioners with valuable insights, knowledge updates, and decision support in selecting CPPS elements and sub-elements according to their impacts and required efforts. Future research recommendations indicate that CPPS should prioritize the deeper integration of digital technologies and artificial intelligence, with a focus on developing sustainable, flexible, and human-centric designs to address evolving industrial needs.
  • No Thumbnail Available
    Item
    Detecting additive manufacturing anomalies with shallow convolutional neural networks
    (Springer, 2025-10) Sangwan, Kuldip Singh
    Additive manufacturing often known as 3D printing, has been significant in the manufacturing industry in recent decades. However, the method encounters significant challenges in the form of printing errors, adversely impacting end-user product experience and obstacles to widespread adoption. The current manual and sensor-based continuous monitoring techniques lack a clear distinction between anomalies and healthy data points, making them ineffective for implementation in industrial environments. This research introduces a computer vision-based methodology for detecting anomalies in real-time. Two Convolutional Neural Networks versions are created, Model V1 using residual connection with decreased parameters and computational complexity and Model V2 to facilitate effortless deployment on constraint devices without compromising performance. The proposed CNN networks are evaluated against state-of-the-art classification models, namely ResNet18, ResNet34, and Deep LSTM classifier, to assess their performance. Model V1 and Model V2 achieved comparable performances with 86.7% and 11.86% reduced parameters compared to ResNet18. Afterward, quantization is applied to produce a compact model representation for edge-device deployment. The quantization model proposed has no loss in performance. Lastly, an inference study is conducted on multiple edge devices where the TI AM68A board proved fast, with 0.246 and 0.04 s inference time for models V1 and V2 respectively.
  • No Thumbnail Available
    Item
    Stochastic robot failure management in an assembly line under industry 4.0 environment
    (Taylor & Francis, 2025-01) Sangwan, Kuldip Singh
    Robot failures at stations pose a major challenge to the smooth functioning of fully automated assembly lines in an industry 4.0 environment. A probable solution to this problem is a redundant configuration wherein downstream stations automatically take over upstream operations in the event of a failure. This paper proposes an improved integrated model of operation reallocation and robot allocation for stochastic failures of a robotic assembly line. A particle swarm optimization (PSO) algorithm is developed to solve the proposed integrated model. The novelty of the proposed algorithm is that it optimizes the production rate and power consumption simultaneously at the targeted production rate. The paper demonstrates the superiority of the proposed model over the genetic algorithm and differential evolution models. The robustness of the proposed model is evaluated at different production rates. The proposed model is capable of fulfilling organizational needs of production rate at the minimum energy consumption.
  • No Thumbnail Available
    Item
    Geometric nonlinear buckling behaviour of randomly distributed carbon nanotube and fibre reinforced hybrid stiffened composite plates: Effect of CNT agglomeration
    (Elsevier, 2025-10) Patel, Shuvendu Narayan; Kumar, Rajesh; Watts, Gaurav
    This article investigates buckling and geometric nonlinear buckling response of stiffened composite plates reinforced with randomly distributed carbon nanotubes and hybrid composites embedded with carbon nanotubes and carbon fibres, using the finite element method. Carbon nanotubes (CNTs) tend to agglomerate into spherical inclusions within matrix due to weak Van der Waals force of attraction between them, which reduces mechanical properties and affects the structural performance. Eshelby-Mori-Tanaka homogenisation method, which incorporates CNT agglomeration, is employed to determine mechanical properties of randomly distributed carbon nanotube reinforced composite (RD-CNTRC) plates, which are further used in mixture rule to estimate mechanical properties of carbon nanotube and fibre reinforced hybrid composite (CNT-FRHC) plates. The plate and stiffener are modelled by isoparametric formulation based on first-order shear deformation theory (FSDT). The plate is modelled by eight-nodded degenerated shell element, and stiffener is modelled by 3-nodded curved beam element. Buckling analysis is performed by solving eigenvalue equation, and postbuckling behaviour is traced by Crisfield's arc-length method. Accuracy of present finite element formulation is validated with different examples from literature, followed by buckling and postbuckling analysis of RD-CNTRC and CNT-FRHC plates under different non-uniform loads. A distinct behaviour is observed in RD-CNTRC plates, where the transverse displacement reduces at the plate's centre due to increased stresses. A parametric investigation includes the influence of CNT volume fraction, agglomeration types, agglomeration parameters, loads, and stiffener parameters on buckling and postbuckling behaviour of RD-CNTRC and CNT-FRHC plates.
  • No Thumbnail Available
    Item
    Postbuckling behaviour of functionally graded carbon nanotube reinforced stiffened composite plate under non-uniform loadings
    (Elsevier, 2025-11) Patel, Shuvendu Narayan; Watts, Gaurav; Kumar, Rajesh
    Understanding buckling and postbuckling characteristics of composite plates is essential to ensure lightweight, safe and optimized design of aerospace, marine and civil structures under in-plane loads. The main contribution of the study is investigation of buckling and postbuckling behaviour of functionally graded carbon nanotube (FG-CNT) reinforced stiffened composite plates under various non-uniform in-plane loading conditions. Carbon nanotubes (CNTs) are embedded through the plate thickness in both uniform distribution (UD) and functional gradation (FG) patterns including FG-X, FG-O and FG-V. Finite element method based on first order shear deformation theory (FSDT) is employed in isoparametric formulation of the plate and stiffener. The plate is modelled with eight-noded degenerated shell element, while the stiffener is modelled by three-noded degenerated curved beam element. Layer-wise effective mechanical properties of FG-CNTRC plate are estimated by extended rule of mixture. Buckling loads are determined by solving eigenvalue equation, while postbuckling behaviour is studied by solving nonlinear equilibrium equation using arc-length method. Accuracy of the present formulation is verified with existing analytical, experimental, and finite element results. Results show that adopting functional gradation approach can enhance buckling and postbuckling performance for constant CNT volume fraction. The addition of stiffeners further improves structural stability of FG-CNTRC plates. A detailed parametric study examines the influence of CNT volume fraction, CNT configuration, number of stiffeners, and unidirectional and bidirectional non-uniform in-plane loading types on buckling and postbuckling performance of FG-CNTRC plates.