A cognitive approach for laser milled PMMA surface characteristics forecasting. (May 2019)

• Record Type: Journal Article
• Authors: Leone, C.; Matarazzo, D.; Genna, S.; D'Addona, D.M.
• Is Part Of: Optics & laser technology. Volume 113(2019)
• Page Start: 225
• Page End: 233
• Publication Date: 2019-05
• Subjects: Artificial intelligence -- Laser Machining -- Polymers -- Tool -- Prototyping -- ANoVA; Optics -- Periodicals; Lasers -- Periodicals; Electronic journals; 621.366
• DOI: 10.1016/j.optlastec.2018.12.025
• Languages: English
• ISSNs: 0030-3992

Abstract

Highlights: Features were machined by Laser milling on PMMA sheets, adopting a 30 W CW-PW CO2 laser. ANNs were developed to estimate the achieved depth and surface roughness of the features. To avoid fitting problems, at the input data matrix randomly noise was added (Rn). Network architecture was defined on the basis of desirability indexes. ANN offers an effective methodology for the estimations of roughness parameters. Abstract: In the present work, different Artificial Neural Networks (ANN) architectures were developed and applied to predict the surface characteristics (roughness and depth) of laser milled pockets, performed on poly-methyl-methacrylate (PMMA) sheets. The experimental data were obtained by adopting a 30 W CO2 laser source, fixing the average power at the maximum value and changing the wave mode (continuous or pulsed mode), the scan speed and the etching distance in large range. The depth and the roughness parameters (Ra and Rt ), of machined surfaces were acquired by a 3D Surface Profiling System and adopted for the ANN training together with the process parameters. In order to allow network convergence, ANN training was executed by applying a random variable noise to the input data (Rn). The Mean Absolute Percentage Error (MAPE) was adopted to evaluate the ability of ANNs in surface characteristics forecasting. The results show a strong influence of the adopted ANN configuration on the forecasting ability. Nevertheless, a careful selection of the network architecture allows forecasting the roughness with a MAPE lower than 7%.