Review
Computer Science, Artificial Intelligence
Abderrachid Hamrani, Arvind Agarwal, Amine Allouhi, Dwayne McDaniel
Summary: Additive manufacturing, particularly wire arc additive manufacturing (WAAM), is gaining increasing attention due to its unique benefits and advantages over traditional subtractive manufacturing. WAAM utilizes arc welding tools and wire to build metallic components by deposition of weld material, offering advantages such as low cost, rapid deposition rate, and suitability for large complex components. However, challenges including welding deformation, porosity, and residual stress need to be addressed. Multidisciplinary research involving manufacturing, material science, automation control, and machine learning is being conducted to overcome these challenges and improve the WAAM process.
JOURNAL OF INTELLIGENT MANUFACTURING
(2023)
Article
Engineering, Manufacturing
Mojtaba Mozaffar, Shuheng Liao, Hui Lin, Kornel Ehmann, Jian Cao
Summary: An approach using neural networks and graph-based representation was proposed to capture spatiotemporal dependencies of thermal responses in additive manufacturing processes. Results show that the deep learning architecture accurately predicts long thermal histories for unseen geometries in the training process.
ADDITIVE MANUFACTURING
(2021)
Review
Automation & Control Systems
Chenxi Tian, Tianjiao Li, Jenniffer Bustillos, Shonak Bhattacharya, Talia Turnham, Jingjie Yeo, Atieh Moridi
Summary: The latest industrial revolution, Industry 4.0, is driven by digital manufacturing and additive manufacturing technologies, which have expanded the design space for materials and structures. The increasing use of data-driven tools accelerates the exploration and optimization of this design space.
ADVANCED INTELLIGENT SYSTEMS
(2021)
Review
Engineering, Industrial
Shenghan Guo, Mohit Agarwal, Clayton Cooper, Qi Tian, Robert X. Gao, Weihong Guo Grace, Y. B. Guo
Summary: Machine learning has proven to be an effective alternative to physical models in quality prediction and process optimization of metal additive manufacturing. However, the interpretability of machine learning outcomes within the complex thermodynamics of additive manufacturing has been a challenge. Physics-informed machine learning (PIML) addresses this challenge by integrating data-driven methods with physical domain knowledge.
JOURNAL OF MANUFACTURING SYSTEMS
(2022)
Article
Engineering, Industrial
Vidita Gawade, Vani Singh, Weihong Grace Gu
Summary: This study contributes to digital-twin manufacturing in laser-based additive manufacturing by combining finite element analysis (FEA) and pyrometry-based sensors to study the thermal behavior of melt pools and predict the porosity of parts. A hybrid model is proposed to capture the strengths of simulated data and real-world empirical data and accurately predict melt pool porosity.
JOURNAL OF MANUFACTURING SYSTEMS
(2022)
Article
Engineering, Industrial
Markus Bambach, Iason Sideris, Maicol Fabbri, Konrad Wegener
Summary: This paper proposes a new data-driven finite volume model that can predict the transient temperature fields in wire-arc additive manufacturing. The model is able to compute temperature profiles at multiple positions efficiently, ensuring energy conservation.
CIRP ANNALS-MANUFACTURING TECHNOLOGY
(2022)
Article
Engineering, Manufacturing
Phuong Dong Nguyen, Thanh Q. Nguyen, Q. B. Tao, Frank Vogel, H. Nguyen-Xuan
Summary: In this paper, a new data-driven machine learning platform is proposed to predict optimized parameters of the 3D printing process and simplify the printing process.
VIRTUAL AND PHYSICAL PROTOTYPING
(2022)
Article
Engineering, Mechanical
A. Ciampaglia, A. Tridello, D. S. Paolino, F. Berto
Summary: In this paper, machine learning algorithms are utilized to predict the fatigue response of Additive Manufacturing (AM) components. It is found that manufacturing defects and microstructures, which are influenced by process parameters and heat treatments, play significant roles in determining the fatigue response.
INTERNATIONAL JOURNAL OF FATIGUE
(2023)
Article
Engineering, Multidisciplinary
Zhenyang Gao, Hongze Wang, Nikita Letov, Yaoyao Fiona Zhao, Xiaolin Zhang, Yi Wu, Chu Lun Alex Leung, Haowei Wang
Summary: In this study, digital design algorithms were developed to generate the next-generation metamaterials with composite bio-inspired twisting fibrotic structs that are rubber-like recoverable without significant scarification of their mechanical performances. A machine learning predictive model is trained based on experimental data to reveal the resulted specific energy absorption (SEA) and SEA recoveries for such metamaterials with complicated fiber-composition mechanisms.
COMPOSITES PART B-ENGINEERING
(2023)
Article
Mechanics
Zhixin Zhan, Weiping Hu, Qingchun Meng
Summary: This paper proposes a machine learning framework based on damage mechanics for data-driven fatigue life prediction of AM titanium alloy. Fatigue life predictions are conducted for AM titanium alloy specimens under different stress levels and stress ratios, compared with experimental data, and parametric studies on prediction performance and fatigue lives are carried out.
ENGINEERING FRACTURE MECHANICS
(2021)
Article
Engineering, Industrial
Gengxiang Chen, Yingguang Li, Xu Liu, Charyar Mehdi-Souzani, Qinglu Meng, Jing Zhou, Xiaozhong Hao
Summary: This paper proposes a physics-guided neural operator to directly predict the high-dimensional temperature history from the given cure cycle. By integrating domain knowledge into a time-resolution independent parameterised neural network, the mapping between cure cycles to temperature histories can be learned using a limited number of labelled data. Detailed experiments show that the proposed model can accurately predict the temperature histories and provide better process optimisation results.
JOURNAL OF MANUFACTURING SYSTEMS
(2023)
Article
Engineering, Mechanical
Meritxell Gomez-Omella, Jon Flores, Basilio Sierra, Susana Ferreiro, Nicolas Hascoet, Francisco Chinesta
Summary: Additive manufacturing is an attractive solution for companies producing complex parts, but a challenge is to avoid defects, especially porosity. This study compares three solutions for the early detection and prediction of porosity failure.
ENGINEERING FAILURE ANALYSIS
(2023)
Article
Computer Science, Interdisciplinary Applications
Firas Zoghlami, Philip Kurrek, Mark Jocas, Giovanni Masala, Vahid Salehi
Summary: The use of flexible and autonomous robotic systems is seen as a viable solution for automation in dynamic and unstructured industrial environments. This work introduces a deep post gripping perception framework, utilizing unsupervised learning methods to enhance robots' abilities in stable and precise item placement while meeting process quality requirements. The modular design of the framework allows for planning, monitoring, and verifying modules, with experimental evaluations showing advantages in process quality and stability for pick and place applications.
JOURNAL OF COMPUTING AND INFORMATION SCIENCE IN ENGINEERING
(2021)
Review
Engineering, Manufacturing
Zhuo Wang, Wenhua Yang, Qingyang Liu, Yingjie Zhao, Pengwei Liu, Dazhong Wu, Mihaela Banu, Lei Chen
Summary: This paper provides a systematic review of existing data-driven additive manufacturing (AM) modeling, focusing on different quantities of interest (QoI) along the process-structure-property chain. It summarizes important information and analyzes the successes achieved so far. The paper also discusses the limitations and suggests promising research directions for advancing data-driven AM modeling.
JOURNAL OF MANUFACTURING PROCESSES
(2022)
Article
Computer Science, Interdisciplinary Applications
Luis Velazquez, Genevieve Palardy, Corina Barbalata
Summary: This paper presents a robotic 3D printer specifically designed for UV-curable thermosets, with selectable printing parameters using a predictive modeling strategy. It integrates a specialized extruder head with a UR5e robotic arm, and includes software packages for communication and control systems for regulating the printing process. A predictive approach utilizing either a feedforward neural network (FNN) or convolutional neural network (CNN) is proposed for estimating future print dimensions based on process parameters, enabling selection of optimal parameters for high-quality prints. Experimental results demonstrate the capabilities of the 3D printer and the accuracy of the predictive approach.
INTERNATIONAL JOURNAL OF COMPUTER INTEGRATED MANUFACTURING
(2023)
Article
Automation & Control Systems
D. S. Srinivasu, N. Venkaiah
INTERNATIONAL JOURNAL OF ADVANCED MANUFACTURING TECHNOLOGY
(2017)
Article
Engineering, Industrial
Ming Chu Kong, Devadula Srinivasu, Dragos Axinte, Wayne Voice, Jamie McGourlay, Bernard Hon
CIRP ANNALS-MANUFACTURING TECHNOLOGY
(2013)
Article
Engineering, Manufacturing
D. S. Srinivasu, D. A. Axinte
JOURNAL OF MANUFACTURING SCIENCE AND ENGINEERING-TRANSACTIONS OF THE ASME
(2014)
Article
Engineering, Manufacturing
V Akhil, N. Arunachalam, G. Raghav, Sivasrinivasu Devadula
Summary: Selective Laser Melting (SLM) based additive manufacturing has wide applications in various industries. Surface texture characterization plays a crucial role in qualifying components for specific tribological applications. This study employs fractal analysis to characterize the surface of Ti-6Al-4V SLM components and demonstrates a strong correlation between computed fractal dimension and measured 3D surface roughness parameters. The study also investigates the anisotropic nature of surface textures under different process parameters and the homogeneity of the surface texture under different roughness conditions. The findings can be used to develop a real-time, low-cost surface monitoring system for additive manufacturing industries.
PROCEEDINGS OF THE INSTITUTION OF MECHANICAL ENGINEERS PART B-JOURNAL OF ENGINEERING MANUFACTURE
(2023)
Article
Engineering, Manufacturing
Ng Peter Singh, D. S. Srinivasu, N. Ramesh Babu
JOURNAL OF MANUFACTURING PROCESSES
(2020)
Article
Engineering, Manufacturing
Ng Peter Singh, D. S. Srinivasu, N. Ramesh Babu
Summary: Abrasive waterjets can process multi-layered structures, but difficulties arise in achieving quality cuts due to the heterogeneous/homogenous properties of the layers. The model presented in the paper accurately predicts kerf geometry in a double-layered structure by considering various factors such as jet characteristics, workpiece properties, and the jet-workpiece interaction at the layers' interface. The results show good agreement with experimental data, with low errors in the kerf profile accuracy.
JOURNAL OF MANUFACTURING PROCESSES
(2021)
Article
Materials Science, Multidisciplinary
Rajesh Ranjan Ravi, D. S. Srinivasu, Prafulla Kumar Behera
Summary: This study experimentally investigated the machinability of Al-CF composite material, observing that kerf width and erosion depth increase with waterjet pressure and abrasive mass flow rate, while decreasing with jet traverse rate. By leveraging this understanding, fabrication of a thin-wall (2D) structure with small features in Al-CF composite material was successfully demonstrated using micro-AWJs.
ADVANCES IN MATERIALS AND PROCESSING TECHNOLOGIES
(2022)
Article
Engineering, Mechanical
Ananthakrishna Ayankalath Thekkepat, Sivasrinivasu Devadula, Mohit Law
Summary: This paper characterizes how joint stiffness and damping parameters for a bolted cantilevered beam change with different number of bolts, different tightening torques on each, and with different levels of torsional excitations. The proposed harmonic balance method for joint parameter identification is shown to be robust and less sensitive to signal processing and conditioning, providing a viable alternative to the standard method. The experimental setup and procedures are simple, and the findings can guide other researchers and practitioners interested in the dynamics of assemblies with bolted joints.
JOURNAL OF VIBRATION ENGINEERING & TECHNOLOGIES
(2022)
Article
Engineering, Manufacturing
Ngangkham Peter Singh, D. S. Srinivasu, N. Ramesh Babu
Summary: Abrasive waterjet is an effective tool for manufacturing parts from multi-layered structures. However, the complex interaction between the jet and multiple layers with different material properties poses a challenge in achieving the desired kerf geometry. This study proposes a model that captures the interaction and predicts the kerf geometry in a single layer of multi-layered structures, considering nonlinearities and the effects of process parameters.
CIRP JOURNAL OF MANUFACTURING SCIENCE AND TECHNOLOGY
(2022)
Proceedings Paper
Materials Science, Multidisciplinary
Swatantra Kumar, D. S. Srinivasu
Summary: This study investigates the thermal deformation issue in high-speed machine tool spindles and proposes a method to predict the deformation by selecting an appropriate number of temperature sensors. The results show that using only one temperature sensor is sufficient to predict TCP deflection with an accuracy of 85.99%.
MATERIALS TODAY-PROCEEDINGS
(2022)
Article
Materials Science, Multidisciplinary
Sourabh Adsul, D. S. Srinivasu
Summary: This study proposes a region-wise surface characterisation approach for abrasive waterjet milling and validates it on aluminum alloy material. Qualitative analysis of depth variations at jet start/stop and jet traverse direction change, as well as quantitative analysis of surface roughness and waviness parameters, were conducted. The results suggest that 3D characterisation with surface waviness as a parameter is better suited for AWJ milled surfaces.
ADVANCES IN MATERIALS AND PROCESSING TECHNOLOGIES
(2022)
Proceedings Paper
Engineering, Manufacturing
Deep Singh, N. Arunachalam, D. S. Srinivasu
Summary: Circularity is a crucial feature in the manufacturing industry, posing challenges for the production of micro and nano-sized components. A novel algorithm based on the concept of minimum zone circle is proposed for evaluating roundness error, showing effectiveness compared to existing methods. The algorithm is simple, robust, and flexible, demonstrating good performance on both uniformly and non-uniformly spaced data.
49TH SME NORTH AMERICAN MANUFACTURING RESEARCH CONFERENCE (NAMRC 49, 2021)
(2021)
Proceedings Paper
Engineering, Industrial
D. S. Srinivasu, D. A. Axinte
2ND CIRP CONFERENCE ON SURFACE INTEGRITY (CSI)
(2014)
Article
Engineering, Manufacturing
D. S. Srinivasu, D. Axinte
PROCEEDINGS OF THE INSTITUTION OF MECHANICAL ENGINEERS PART B-JOURNAL OF ENGINEERING MANUFACTURE
(2011)