ILAS 2019: DEEP LEARNING IN LASER PROCESSING


THINKING LASERS


Dr Ben Mills, an EPSRC early career fellow and senior research fellow for the ORC in Southampton, UK, explains how deep learning could be used to enhance laser processing


A


dvances in lasers now allow the laser-based processing of almost any material, and consequently innovation in this field is becoming heavily focused


on making existing processing techniques more precise and efficient. Deep learning, a computing paradigm


inspired by biological neurons that learns directly from real-world data, has seen a dramatic rise in interest over recent years, due to its capability in solving extremely complex problems. Te question is: how can these two fields be combined? Our team at the Optoelectronics


Research Centre (ORC) at the University of Southampton is addressing this by exploring whether the power of deep learning can be harnessed in order to improve the repeatability, precision, and control of high-precision femtosecond laser machining of objects on the micro- and even nanoscale. Te objective of the


research at the ORC is two-fold: Firstly, to explore the application of deep learning for recognising, in real-time, unexpected events – e.g. laser power fluctuations or unexpected debris – whilst also providing process control – e.g. stopping a manufacturing process at exactly the optimal time, even though the process time may be unknown. Secondly, to investigate the application of deep learning for predictive capabilities for laser machining, in order to be able to accurately predict what a sample would look like aſter machining with any combination of laser machining parameters. Te intention is that these two approaches


Figure 1: Schematic describing a setup for monitoring and controlling a process via a neural network


24 LASER SYSTEMS EUROPE ISSUE 42 • SPRING 2019


will be combined, as unexpected events must first be observed before a predictive capability can determine which parameters will need to be changed, in order to compensate for the earlier manufacturing error. Te critical point is that this combined capability needs to operate in real-time. Deep learning, which generally refers to the application of neural networks (NNs), is based


whether the power of deep learning can be harnessed in order to improve the repeatability, precision, and control of high- precision femtosecond laser machining


Our team is exploring


on the premise of computers learning how to solve a problem by themselves. Tis means that equations describing, for example, the interaction of light and matter, or the probabilistic nature of debris production, are not needed, providing a significant advantage – the interaction of laser light with materials, particularly for femtosecond pulses, is extremely complex. Instead, the deep learning approach simply involves the collection of experimental data, e.g. images of laser machined samples for a wide variety of different experimental parameters. Te NN is then trained directly and automatically from this experimental data. Once trained, the NN can process input data and provide useful information on a timescale of tens of milliseconds, and hence is applicable for real-time data processing. An NN can, therefore, be


considered as a transfer function, which converts input data to output data. In the case of laser machining, the input data could be, for example, spectral data, camera images and temperature measurements,


while the output data could be anything from beam power corrections to 3D predictions of the sample surface aſter machining. While NNs have been studied and


understood for many decades, the rate of adoption across academia has only been extremely rapid since 2017, due to the available computing power and data – both which are increasing exponentially – having reached a critical level. As such, most previous work in this area, while being academically interesting, has offered limited potential for industrial application. However, the computing power available now is such that accurate and real-time capability can be offered during processing, which is attracting significant industrial interest. Te schematic describing our setup for the


@lasersystemsmag | www.lasersystemseurope.com


Page 1  |  Page 2  |  Page 3  |  Page 4  |  Page 5  |  Page 6  |  Page 7  |  Page 8  |  Page 9  |  Page 10  |  Page 11  |  Page 12  |  Page 13  |  Page 14  |  Page 15  |  Page 16  |  Page 17  |  Page 18  |  Page 19  |  Page 20  |  Page 21  |  Page 22  |  Page 23  |  Page 24  |  Page 25  |  Page 26  |  Page 27  |  Page 28  |  Page 29  |  Page 30  |  Page 31  |  Page 32  |  Page 33  |  Page 34  |  Page 35  |  Page 36