Machine learning for multi-dimensional optimisation and predictive visualisation of laser machining

Abstract

Interactions between light and matter during short-pulse laser materials processing are highly nonlinear, and hence acutely sensitive to laser parameters such as the pulse energy, repetition rate, and number of pulses used. Due to this complexity, simulation approaches based on calculation of the underlying physical principles can often only provide a qualitative understanding of the inter-relationships between these parameters. An alternative approach such as parameter optimisation, often requires a systematic and hence time-consuming experimental exploration over the available parameter space. Here, we apply neural networks for parameter optimisation and for predictive visualisation of expected outcomes in laser surface texturing with blind vias for tribology control applications. Critically, this method greatly reduces the amount of experimental laser machining data that is needed and associated development time, without negatively impacting accuracy or performance. The techniques presented here could be applied in a wide range of fields and have the potential to significantly reduce the time, and the costs associated with laser process optimisation.

Artificial neural network tools for predicting the functional response of ultrafast laser textured/structured surfaces

“…GANs were already utilised as a predictive visualisation method in laser machining. Laser-ablated topographies were recreated based on spatial laser intensity profiles [16] or by transforming the key laser parameters into predicted 3D surface profiles [17].…”

Multi-objective optimisation of ultrasonically welded dissimilar joints through machine learning

“…In the USW process the input parameters take integer values, therefore, the parameter space is discrete. Once trained, interrogating the GA–ANN ensemble to retrieve LSS, defect and repeatability predictions for the entire bounded parameter space took less than 180 s. A similar approach was implemented by McDonnell et al ( 2021 ) when optimising a multi-objective laser machining process, where the optimised process was superior to the observed DoE data. In this study, the predictions were formatted to return the input parameters corresponding to the maximum LSS achievable when the model predicts the process to produce zero defects while having class one repeatability.…”

“…The study found ANN modelling provided a more accurate prediction. Similarly, McDonnell et al ( 2021 ) compared the performance of Gaussian process regression (GPR), support vector machines (SVM), and ANN’s for the multi-objective optimisation of a laser machining process identifying ANN as the superior machine learning method. Seyyedian Choobi et al ( 2012 ) used forty-one training samples to train an ANN with fifteen, twenty and twenty-five neurons in the first, second and third hidden layers, respectively.…”

Random Target Localization for an Upper Limb Prosthesis

“…In the forward transmission process, the signal is processed layer by layer from the input layer through the hidden layer to the output layer. If the output layer cannot obtain the desired output, the signal is transmitted to back propagation, and the weight and threshold are adjusted according to the prediction error, so that the output of BPNN continues to be close to the expected output [13][14][15]. It is known that BPNN containing a hidden layer has sufficient accuracy to approximate any continuous function [16].…”

“…After the training, the E i and the average absolute error (AAE) E s of the output values of the MPGA-BPNN relative to the actual measurement value are obtained by (15) and (19). To evaluate the error correction ability of MPGA-BPNN, E s of the ILA, BPNN, and SPGA-BPNN are introduced as follows: Shock and Vibration 7…”