Predictive modeling approaches in laser-based material processing

Velli, Maria Christina; Tsibidis, George D.; Mimidis, Alexandros; Skoulas, Evangelos; Pantazis, Yannis; Stratakis, Emmanuel

doi:10.1063/5.0018235

Cited by 12 publications

(5 citation statements)

References 64 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Thus, although the control of coherent scattering effects is always the key to obtaining LIPSS of high regularity, the implementation of a general algorithm for controlling the regularity of LIPSS is still missing. Here, artificial intelligence and machine learning approaches [51] could contribute to improving LIPSS regularity in the future.…”

Section: Question 4 How Can the Regularity Of Lipss Be Controlled?mentioning

confidence: 99%

Ten Open Questions about Laser-Induced Periodic Surface Structures

Bonse

Gräf

2021

Nanomaterials

View full text Add to dashboard Cite

Laser-induced periodic surface structures (LIPSS) are a simple and robust route for the nanostructuring of solids that can create various surface functionalities featuring applications in optics, medicine, tribology, energy technologies, etc. While the current laser technologies already allow surface processing rates at the level of m2/min, industrial applications of LIPSS are sometimes hampered by the complex interplay between the nanoscale surface topography and the specific surface chemistry, as well as by limitations in controlling the processing of LIPSS and in the long-term stability of the created surface functions. This Perspective article aims to identify some open questions about LIPSS, discusses the pending technological limitations, and sketches the current state of theoretical modelling. Hereby, we intend to stimulate further research and developments in the field of LIPSS for overcoming these limitations and for supporting the transfer of the LIPSS technology into industry.

show abstract

Section: Question 4 How Can the Regularity Of Lipss Be Controlled?mentioning

confidence: 99%

Ten Open Questions about Laser-Induced Periodic Surface Structures

Bonse

Gräf

2021

Nanomaterials

View full text Add to dashboard Cite

show abstract

“…Sohrabpoor et al [146] applied an ANN and adaptive inference model to predict the surface quality of laser-processed 316L stainless steel cylindrical pins when machined with a CO 2 laser. Velli et al [147] showed that the laser-induced periodic surface structures [148][149][150] produced via a Yb:KBW femtosecond source on stainless steel (and titanium alloy and crystalline silicon) could be predicted via a range of machine-learning models.…”

Section: Steelmentioning

confidence: 99%

“…Velli et al. [147] showed that the laser‐induced periodic surface structures [148–150] produced via a Yb:KBW femtosecond source on stainless steel (and titanium alloy and crystalline silicon) could be predicted via a range of machine‐learning models.…”

Section: Machine Learning and Laser Machiningmentioning

confidence: 99%

Lasers that learn: The interface of laser machining and machine learning

Mills

Grant-Jacob

2021

IET Optoelectronics

View full text Add to dashboard Cite

Laser machining is a highly flexible non-contact fabrication method used extensively across academia and industry. Whilst simulations based on fundamental understanding offer some insight into the processes, both the highly non-linear interactions between laser light and matter and the variety of materials involved mean that theoretical modelling is not particularly applicable to practical experimentation. However, recent breakthroughs in machine learning have resulted in neural networks that are capable of accurate and rapid modelling of laser machining at a scale, speed, and precision well beyond those of existing theoretical approaches with applications including 3-D surface visualisation and real-time error correction. A perspective at the intersection of laser machining and machine learning is presented, followed by a discussion of future milestones and challenges for this field.10 steps each, that corresponds to a total of 10^5 experimental trials. Because of the often highly non-linear relationships amongst parameters, the standard practice is generally the systematic collection of laser-machining data for all parameter combinations to identify the optimal combination. However, this process is both time-consuming and unfocussed and can take days or weeks, hence costing unnecessary effort, time, and money. Even when the optimal parameters have been determined, small changes during manufacturing, for example in laser power or beam shape, can result in final product quality that is below the required standard, again with associated costs in time and money. What is needed, therefore, is a set of modelling methodologies for identifying optimal parameters and providing real-time monitoring and error correction during manufacturing.However, the processes that describe laser machining, such as the light-matter interaction, heat conduction, phase change of material, and material removal, are particularly complex and hence challenging to model precisely and directly from a theoretical standpoint. The exact details of these processes depend on many factors, including laser parameters (e.g. wavelength, fluence, and pulse length), associated diffraction effects, and sample properties (e.g. absorption, reflectivity, melting temperature, and ablation threshold). In addition, different interaction effects become dominant as the temporal interaction length varies from continuous wave to ultrafast (i.e. femtosecondThis is an open access article under the terms of the Creative Commons Attribution License, which permits use, distribution and reproduction in any medium, provided the original work is properly cited.

show abstract

“…As mentioned above, the photosensitive performance of natural pigments has a wide distribution. Recently, machine learning methods in deep learning are widely utilized for training models of multicellular complexity, tissue specificity, biomedical design, protein structure, and chemical reaction. − Recently, predictive modeling demonstrated a bright prospect in rapid clarification of the physical mechanisms of developing materials . Since the combination of parameters and the hidden mechanism and reactions affects the performance of our devices, an efficient numerical statistical and predictive analytical algorithm is necessary for the development of novel functional devices.…”

Section: Introductionmentioning

confidence: 99%

“…26−28 Recently, predictive modeling demonstrated a bright prospect in rapid clarification of the physical mechanisms of developing materials. 29 Since the combination of parameters and the hidden mechanism and reactions affects the performance of our devices, an efficient numerical statistical and predictive analytical algorithm is necessary for the development of novel functional devices. Thus, in this manuscript, we provide machine learning methods in deep learning which are worthy of mining natural pigments to investigate photosensitive performance.…”

Section: ■ Introductionmentioning

confidence: 99%

Over 9% Water Splitting Nature Dyes Solar Cells via Artificial Intelligent Selected Combination

Lai

2022

ACS Agric. Sci. Technol.

View full text Add to dashboard Cite

In this work, artificial intelligence is achieved using a genetic algorithm integrated with an artificial neuron network (GANN) to find the optimal combination of natural leaves on ZrO2 architecture anodes for water splitting devices and hydrogen evolution. Around 180 kinds of Aglaonema and 100 kinds of Codiaeum variegatum are evaluated from nine kinds of original Aglaonema and five kinds of Codiaeum variegatum over 10 generations of hybridization, respectively. The types and content of natural chlorophyll and anthocyanin are estimated and recorded by CMOS devices and an absorption spectrum for pixel recording and featured parameter mining for GANN. Optical extinction ZrO2 architecture anodes constructed on ITO substrates, which correspond with a leaf’s pigments, demonstrated ultrahigh water splitting performance for hydrogen evolution up to 9.42%. Furthermore, from promising experimental results, the natural pigments extracted from different color parts of Codiaeum variegatum and Aglaonema demonstrated over 85% incident photon to electron conversion efficiency while the pigments correspond with the lowest optical extinction ZrO2 architecture anodes. Ultrahigh current density (157.1 A/m2) and hydrogen evolution quality (around 18 mol after 6 h) are obtained when the lowest optical extinction ZrO2 architecture anodes correspond with green parts of Aglaonema under one sun irradiation.

show abstract

Predictive modeling approaches in laser-based material processing

Cited by 12 publications

References 64 publications

Ten Open Questions about Laser-Induced Periodic Surface Structures

Ten Open Questions about Laser-Induced Periodic Surface Structures

Lasers that learn: The interface of laser machining and machine learning

Over 9% Water Splitting Nature Dyes Solar Cells via Artificial Intelligent Selected Combination

Contact Info

Product

Resources

About