Prediction model for determining the optimum operational parameters in laser forming of fiber-reinforced composites

Gisario, Annamaria; Mehrpouya, Mehrshad; Rahimzadeh, Atabak; Bartolomeis, Andrea de; Barletta, Massimiliano

doi:10.1007/s40436-020-00304-3

Cited by 15 publications

(9 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The primary input parameters were the laser power, hatch spacing, and scanning speed. In similar studies [19,20], an ANN model was used to construct a surrogate map between the laser parameters and outputs such as temperature, strains, etc., for an AM build part. Recently, surrogate models have gained popularity for UA in the AM process.…”

Section: Literature Reviewmentioning

confidence: 99%

A Comparative Study of Machine Learning Methods for Computational Modeling of the Selective Laser Melting Additive Manufacturing Process

Chaudhry

Soulaïmani

2022

Applied Sciences

View full text Add to dashboard Cite

Selective laser melting (SLM) is a metal-based additive manufacturing (AM) technique. Many factors contribute to the output quality of SLM, particularly the machine and material parameters. Analysis of the parameters’ effects is critical, but using traditional experimental and numerical simulation can be expensive and time-consuming. This paper provides a framework to analyze the sensitivity and uncertainty in SLM input and output parameters, which can then be used to find the optimum parameters. The proposed data-driven approach combines machine learning algorithms with high-fidelity numerical simulations to study the SLM process more efficiently. We have considered laser speed, hatch spacing, layer thickness, Young modulus, and Poisson ratio as input variables, while the output variables are numerical predicted normal strains in the building part. A surrogate model was constructed with a deep neural network (DNN) or polynomial chaos expansion (PCE) to generate a response surface between the SLM output and the input variables. The surrogate model and the sensitivity analysis found that all five parameters were important in the process. The surrogate model was combined with non-intrusive optimization algorithms such as genetic algorithms (GA), differential evolution (DE), and particle swarm optimization (PSO) to perform an inverse analysis and find the optimal parameters for the SLM process. Of the three algorithms, the PSO performed well, and the DNN model was found to be the most efficient surrogate model compared to the PCE.

show abstract

Section: Literature Reviewmentioning

confidence: 99%

A Comparative Study of Machine Learning Methods for Computational Modeling of the Selective Laser Melting Additive Manufacturing Process

Chaudhry

Soulaïmani

2022

Applied Sciences

View full text Add to dashboard Cite

show abstract

“…Recently, these forming methods were utilised to form steel-based FMLs, but the latest research papers have been focused mainly on aluminium-based composites. Researchers consider the configuration of the material layers [374][375][376][377] or the process parameter setup [86,[378][379][380][381][382][383][384][385][386] to reduce material defects and go beyond the current forming limits caused mainly by breakage and wrinkling. In order to improve the formability of the layers of FRP, many studies are focused on die forming at elevated temperatures [387][388][389].…”

Section: Die Formingmentioning

confidence: 99%

“…For aluminium layers, the occurrence of the tempering phenomenon caused by repeated laser irradiation should be considered in process design. In work by Gisario et al [386], GLARE 1 and GLARE 2 FMLs were used in research and a multi-layer perceptron artificial neural network (ANN) while a Levenberg-Marquardt algorithm was employed to analyse the data. The artificial neural networks that were developed predicted the temperature and bending angle by a power set and velocity laser beam.…”

Section: Laser Formingmentioning

confidence: 99%

New Advances and Future Possibilities in Forming Technology of Hybrid Metal–Polymer Composites Used in Aerospace Applications

et al. 2021

View full text Add to dashboard Cite

Fibre metal laminates, hybrid composite materials built up from interlaced layers of thin metals and fibre reinforced adhesives, are future-proof materials used in the production of passenger aircraft, yachts, sailplanes, racing cars, and sports equipment. The most commercially available fibre–metal laminates are carbon reinforced aluminium laminates, aramid reinforced aluminium laminates, and glass reinforced aluminium laminates. This review emphasises the developing technologies for forming hybrid metal–polymer composites (HMPC). New advances and future possibilities in the forming technology for this group of materials is discussed. A brief classification of the currently available types of FMLs and details of their methods of fabrication are also presented. Particular emphasis was placed on the methods of shaping FMLs using plastic working techniques, i.e., incremental sheet forming, shot peening forming, press brake bending, electro-magnetic forming, hydroforming, and stamping. Current progress and the future directions of research on HMPCs are summarised and presented.

show abstract

“…The complicated deformation mechanisms, interfacial delamination, and thermal alteration of the layers are three main challenges in the laser forming of FMLs. However, using the experimental test and using an artificial neural network tool made it possible to predict the behavior of FMLs during the laser bending process [41,42]. Moreover, the deformation of FMLs can be predicted using Eigen-strain field prediction [43,44].…”

Section: Laser Forming Of Composite Sheetsmentioning

confidence: 99%

Recent Advances in the Laser Forming Process: A Review

Safari

Sousa

Joudaki

2020

Metals

View full text Add to dashboard Cite

Laser forming is an emerging manufacturing process capable of producing either uncomplicated and complicated shapes by employing a concentrated heating source. The heat source movement creates local softening, and a plastic strain will be induced during the rise of temperature and the subsequent cooling. This contactless forming process may be used for the simple bending of sheets and tubes or fabrication of doubly-curved parts. Different studies have been carried out over recent years to understand the mechanism of forming and predicting the bending angle. The analysis of process parameters and search for optimized manufacturing conditions are among the most discussed topics. This review describes the main recent findings in the laser forming of single and multilayer sheets, composite and fiber-metal laminate plates, force assisted laser bending, tube bending by laser beam, the optimization technique implemented for process parameters selection and control, doubly-curved parts, and the analytical solutions in laser bending. The main focus is set to the researches published since 2015.

show abstract

Prediction model for determining the optimum operational parameters in laser forming of fiber-reinforced composites

Cited by 15 publications

References 23 publications

A Comparative Study of Machine Learning Methods for Computational Modeling of the Selective Laser Melting Additive Manufacturing Process

A Comparative Study of Machine Learning Methods for Computational Modeling of the Selective Laser Melting Additive Manufacturing Process

New Advances and Future Possibilities in Forming Technology of Hybrid Metal–Polymer Composites Used in Aerospace Applications

Recent Advances in the Laser Forming Process: A Review

Contact Info

Product

Resources

About