Department of Mechanical engineering

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

Browse

Subject: search.filters.subject.Additive manufacturing

Search Results

Now showing 1 - 10 of 12
  • 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
    Integration of design for manufacturing methods with topology optimization in additive manufacturing
    (ASME, 2017) Ranjan, Rajit
    Additive manufacturing (AM) processes are used to fabricate complex geometries using a layer-by-layer material deposition technique. These processes are recognized for creating complex shapes which are difficult to manufacture otherwise and enable designers to be more creative with their designs. However, as AM is still in its developing stages, relevant literature with respect to design guidelines for AM is not readily available. This paper proposes a novel design methodology which can assist designers in creating parts that are friendly to additive manufacturing. The research includes formulation of design guidelines by studying the relationship between input part geometry and AM process parameters. Two cases are considered for application of the developed design guidelines. The first case presents a feature graph-based design improvement method in which a producibility index (PI) concept is introduced to compare AM friendly designs. This method is useful for performing manufacturing validation of pre-existing designs and modifying it for better manufacturability through AM processes. The second approach presents a topology optimization-based design methodology which can help designers in creating entirely new lightweight designs which can be manufactured using AM processes with ease. Application of both these methods is presented in the form of case studies depicting design evolution for increasing manufac
  • No Thumbnail Available
    Item
    Octree data structure for support accessibility and removal analysis in additive manufacturing
    (Elsevier, 2018-08) Ranjan, Rajit
    Metal Additive Manufacturing (AM) processes have made it possible to build parts with complex geometric features by adopting a layer-by-layer approach. However, additional support structures are needed to support overhanging surfaces and reduce distortion that may occur in these parts. This increases the overall build time of the part and leads to additional post processing efforts for removal of support structures. Often, removal of these supports becomes difficult due to complex part features that may interfere with support removal. Further, support structures have a detrimental effect on the surface finish on the areas of the part that come in contact with the supports. Thus, minimizing the need for support structures and ensuring its maximum removal is essential for an efficient part build in AM. Part build orientation is the main parameter that influences the need for support structures to build a part. This paper presents an approach to identify the best build orientation for a part such that the overall part build time is minimized while ensuring maximum removal of supports and minimizing the contact area between the part surface and supports. A hierarchical octree data structure has been used to analyze support accessibility and the area of support in contact with part. In addition, this paper also focuses on identification of optimal number/direction of part set-ups required to remove the maximum possible support structures from a part. A 2D setup map highlighting the feasible directions of setups for support removal has also been presented. The results of these analyses have been presented with the help of four sample parts.
  • No Thumbnail Available
    Item
    Improving the manufacturability of metal AM parts
    (Mikroniek, 2019) Ranjan, Rajit
    Numerous challenges of additive manufacturing (AM) are tackled in the European Horizon 2020 project PAM^2 by studying and linking every step of the AM process cycle. For example, PAM^2 researchers from the design, processing and application side have collaborated in this work to optimise the manufacturability of metal AM parts using an improved Topology Optimisation (TO) approach, including a thermal constraint. Additionally, the project is focusing on modelling, post-processing, in- and post-process quality control and industrial assessment of AM parts, with the aim of moving beyond the state-of-the-art of precision metal AM.
  • No Thumbnail Available
    Item
    Topology optimisation techniques
    (CRC Press, 2020) Ranjan, Rajit
    This chapter presents topology optimisation techniques suitable for designing parts that will be produced by additive manufacturing, with special attention to precision aspects. First, challenges associated with ‘design for additive manufacturing’ are briefly discussed. Next, an introduction to density-based topology optimisation is given. Specific additive manufacturing limitations relevant for high-technology precision parts are summarised and topology optimisation methods which address these limitations are described. Specifically, critical overhang elimination, overheating prevention and distortion reduction are considered. The industrial relevance of these additive manufacturing–friendly topology optimisation methods are demonstrated through case studies. Finally, an outlook on the current research trends is given and challenges ahead are highlighted.
  • No Thumbnail Available
    Item
    Fast detection of heat accumulation in powder bed fusion using computationally efficient thermal models
    (MDPI, 2020) Ranjan, Rajit
    The powder bed fusion (PBF) process is a type of Additive Manufacturing (AM) technique which enables fabrication of highly complex geometries with unprecedented design freedom. However, PBF still suffers from manufacturing constraints which, if overlooked, can cause various types of defects in the final part. One such constraint is the local accumulation of heat which leads to surface defects such as melt ball and dross formation. Moreover, slow cooling rates due to local heat accumulation can adversely affect resulting microstructures. In this paper, first a layer-by-layer PBF thermal process model, well established in the literature, is used to predict zones of local heat accumulation in a given part geometry. However, due to the transient nature of the analysis and the continuously growing domain size, the associated computational cost is high which prohibits part-scale applications. Therefore, to reduce the overall computational burden, various simplifications and their associated effects on the accuracy of detecting overheating are analyzed. In this context, three novel physics-based simplifications are introduced motivated by the analytical solution of the one-dimensional heat equation. It is shown that these novel simplifications provide unprecedented computational benefits while still allowing correct prediction of the zones of heat accumulation. The most far-reaching simplification uses the steady-state thermal response of the part for predicting its heat accumulation behavior with a speedup of 600 times as compared to a conventional analysis. The proposed simplified thermal models are capable of fast detection of problematic part features. This allows for quick design evaluations and opens up the possibility of integrating simplified models with design optimization algorithms.
  • No Thumbnail Available
    Item
    Overheating control in additive manufacturing using a 3D topology optimization method and experimental validation
    (Elsevier, 2023-01) Ranjan, Rajit
    Overheating is a major issue especially in metal Additive Manufacturing (AM) processes, leading to poor surface quality, lack of dimensional precision, inferior performance and/or build failures. A 3D density-based topology optimization (TO) method is presented which addresses the issue of local overheating during metal AM. This is achieved by integrating a simplified AM thermal model and a thermal constraint within the optimization loop. The simplified model, recently presented in literature, offers significant computational gains while preserving the ability of overheating detection. The novel thermal constraint ensures that the overheating risk of optimized designs is reduced. This is fundamentally different from commonly used geometry-based TO methods which impose a geometric constraint on overhangs. Instead, the proposed approach takes the process physics into account. The proposed method is validated via an experimental comparative study. Optical tomography (OT) is used for in-situ monitoring of process conditions during fabrication and obtained data is used for evaluation of overheating tendencies. The novel TO method is compared with two other methods: standard TO and TO with geometric overhang control. The experimental data reveals that the novel physics-based TO design experienced less overheating during the build as compared to the two classical designs. A study further investigated the correlation between overheating observed by high OT values and the defect of porosity. It shows that overheated regions indeed show higher defect of porosity. This suggests that geometry-based guidelines, although enhance printability, may not be sufficient for eliminating overheating issues and related defects. Instead, the proposed physics-based method is able to deliver efficient designs with reduced risk of overheating.
  • No Thumbnail Available
    Item
    Eco-friendly tool-based electrochemical polishing of additively manufactured metallic components
    (Elsevier, 2023-12) Garg, Girish Kant
    The elevated surface roughness of metal additive manufacturing (MAM) parts detrimentally affects wear resistance, diminishes fatigue strength, and hampers cooling efficiency, which mandates post-processing. Electrochemical polishing is a non-contact and non-thermal post-processing technique but uses non-ecofriendly acidic baths and is ineffective in removing unmolten or partially molten metal particles. To address these challenges, we propose a novel approach using a flat nano-polished cylindrical tool as the cathode and an eco-friendly electrolyte for finishing a MAM component fabricated via atomic diffusion additive manufacturing (ADAM). Our study evaluates the effectiveness of this approach through numerical simulation and optimises the process through experimental analysis. The numerical simulation developed in COMSOL incorporates the surface roughness data of the ADAM part as the anode surface profile in the 2D simulation domain. The current density distribution, viscous layer formation, reduction in surface roughness and mass material removal rate (MRRg) are analysed from the simulation results. The experimental optimisation of parameters, including polishing time, inter-electrode gap (IEG), electrolyte flow, and electrolyte composition, resulted in a substantial decrease in the average surface roughness (Ra) value of the ADAM component by 95.91 %. The polished surface is more levelled, exhibiting a glossy finish with no waviness and fewer surface cracks. The EDS and XRD analysis portrayed the presence of passive films, indicating improved corrosion resistance. Repeating the experiment for rolled and milled surfaces with the same process parameters resulted in a similar reduction in the Ra value by 97.59 % and 94.73 %, respectively. The comparative analysis, of ECP on MAM, rolled, and milled surfaces, indicates the potential to achieve a similar notable improvement in surface finish, irrespective of the process history of the manufactured part for the same ECP parameters. Comparing the anode surface profiles, Ra values, and mass of material dissolved showed a close fit between experimental and simulation results. Our study highlights the feasibility of ECP with the flat tool electrode and eco-friendly electrolytes to reduce the surface roughness of an MAM component significantly.
  • No Thumbnail Available
    Item
    A review of the applications of machine learning for prediction and analysis of mechanical properties and microstructures in additive manufacturing
    (ACM Digital Library, 2024-12) Challa, Jagat Sesh; Singh, Amit Rajnarayan
    This article provides an insightful review of the recent applications of machine learning (ML) techniques in additive manufacturing (AM) for the prediction and amelioration of mechanical properties, as well as the analysis and prediction of microstructures. AM is the modern digital manufacturing technique adopted in various industrial sectors because of its salient features, such as the fabrication of geometrically complex and customized parts, the fabrication of parts with unique properties and microstructures, and the fabrication of hard-to-manufacture materials. The functioning of the AM processes is complicated. Several factors such as process parameters, defects, cooling rates, thermal histories, and machine stability have a prominent impact on AM products’ properties and microstructure. It is difficult to establish the relationship between these AM factors and the AM end product properties and microstructure. Several studies have utilized different ML techniques to optimize AM processes and predict mechanical properties and microstructure. This article discusses the applications of various ML techniques in AM to predict mechanical properties and optimization of AM processes for the amelioration of mechanical properties of end parts. Also, ML applications for segmentation, prediction, and analysis of AM-fabricated material’s microstructures and acceleration of microstructure prediction procedures are discussed in this article.
  • No Thumbnail Available
    Item
    Analysis of Density of Laser Powder Bed Fusion Fabricated Part Using Decision Tree Algorithm
    (Springer, 2023-05) Mishra, Radha Raman
    Additive manufacturing (AM) enabled manufacturing industries to fabricate metallic components with complex shapes. However, the properties of additively manufactured parts need further improvements to compete with the performance of traditionally manufactured parts. Machine learning (ML) models provide an alternative to study the correlation between the process parameters–properties of the fabricated parts. In the present work, the ML approach has been applied to understand the effect of AM process parameters on the density of additively built parts. The decision tree model was developed for the laser powder bed fusion-processed parts based on the input parameters such as laser power, scan speed, hatching space, energy density, and build rate. The model was trained and tested with experimental data obtained from the relevant literature. The process parameters were optimized to achieve the desired density of the part. A good agreement was indicated between the predicted and experimental data. The study revealed the applicability and potential of the model to determine and predict the density of the additively manufactured parts.