Improving the accuracy of machine-learning models with data from machine test repetitions
- PDF / 2,502,519 Bytes
- 19 Pages / 595.276 x 790.866 pts Page_size
- 24 Downloads / 203 Views
Improving the accuracy of machine-learning models with data from machine test repetitions Andres Bustillo1
· Roberto Reis2 · Alisson R. Machado2,3
· Danil Yu. Pimenov4
Received: 4 July 2020 / Accepted: 24 August 2020 © Springer Science+Business Media, LLC, part of Springer Nature 2020
Abstract The modelling of machining processes by means of machine-learning algorithms is still based on principles that are especially adapted to mechanical approaches, in which very few inputs are varied with little repetition of experimental conditions. These principles might not be ideal to achieve accurate machine-learning models and they are certainly not aligned with the practicalities of industrial machining in factories. In this research the effect of a new strategy to improve machine-learning model accuracy is studied: experimental repetition. Tool-life prediction in the face-turning operations of AISI 1045 steel discs, depending on different cooling systems and tool geometries, is selected as a case study. Both the side rake and the relief angles of HSS tools are optimized using the Brandsma facing test under dry, MQL, and flooding conditions. Different machinelearning algorithms, such as regression trees, kNNs, artificial neural networks, and ensembles (bagging and Random Forest) are tested. On the one hand, the results of the study showed that artificial neural networks of Radial Basis Functions presented the highest model accuracy (11.4 mm RMSE), but required a very sensitive and complex tuning process. On the other hand, they demonstrated that ensembles, especially Random Forest, provided models with accuracy in the same range, but with no tuning procedure (12.8 mm RMSE). Secondly, the effect of an increased dataset size, by means of experimental repetition, is evaluated and compared with traditional experimental modelling that used average values. The results showed that some machine-learning techniques, including both ensemble types, significantly improved their accuracy with this strategy, by up to 23%. The results therefore suggested that the use of raw experimental data, rather than their averaged values, can achieve machine-learning models of higher accuracy for tool-wear processes. Keywords Machine learning · Artificial intelligence · Ensembles · Brandsma facing tests · Tool geometry · Turning
Introduction Electronic supplementary material The online version of this article (https://doi.org/10.1007/s10845-020-01661-3) contains supplementary material, which is available to authorized users.
B
Danil Yu. Pimenov [email protected] Andres Bustillo [email protected] Roberto Reis [email protected] Alisson R. Machado [email protected]; [email protected]
1
Department of Civil Engineering, Universidad de Burgos, Avda Cantabria s/n, 09006 Burgos, Spain
2
School of Mechanical Engineering, Federal University of Uberlandia, Av. João Naves de Ávila, 2121, Bloco 1M, Uberlândia, MG 38400-902, Brazil
Metal-alloy machining processes are of well-known industrial interest. These processes are basic in the ma
Data Loading...
