Dimension reduction and 2D-visualization for early change of state detection in a machining process with a variational a
- PDF / 6,507,972 Bytes
- 15 Pages / 595.276 x 790.866 pts Page_size
- 104 Downloads / 222 Views
ORIGINAL ARTICLE
Dimension reduction and 2D-visualization for early change of state detection in a machining process with a variational autoencoder approach Antoine Proteau 1 & Ryad Zemouri 1,2 & Antoine Tahan 1 & Marc Thomas 1 Received: 23 July 2020 / Accepted: 30 October 2020 / Published online: 14 November 2020 # Springer-Verlag London Ltd., part of Springer Nature 2020
Abstract In this paper, we applied a variational autoencoder approach to an industrial machining problematic. We proposed a model based on a two-steps training process and a two-dimensional latent space. This two-dimensional latent space has better dimension reduction capability compared to a principal component analysis, which would require 24 components to express 90.0% of the variation. Moreover, the proposed model is shown capable of classifying a cutting operation based solely on data obtained from sensors mounted on a CNC machine, with an accuracy of 99.24%. The suggested model is also shown capable to be an efficient visual process monitoring tool capable of detecting early changes of state in a machining process. We show that this approach can visually identify defect caused by an increase of less than 1% of the energy in the signal, which is earlier than conventional monitoring methods. Additionally, our work is based on an industrial dataset acquired during regular production. This increases the opportunity for technological transfer when it comes to better understanding and better monitoring early changes in a machining process. Keywords Variational autoencoder . Dimension reduction . 2D-visualization . Process monitoring . Early detection . Machining process
1 Introduction The manufacturing industry continues to face constant pressure to decrease costs, improve quality, and increase production rates. Over the past few years, the industry has been leveraging new concepts, such as Industry 4.0 or smart manufacturing, to introduce new affordable technologies and models promising new ways to improve production [1–3]. In the specific context of machining, it is widely known that the kinds of technologies (connectivity, augmented reality, artificial intelligence, etc.) brought forward by Industry 4.0 can have highly positive impacts on a company [4, 5].
* Antoine Proteau [email protected] 1
Department of Mechanical Engineering, École de technologie supérieure, Montreal, QC H3C 1K3, Canada
2
CEDRIC Laboratory of the Conservatoire National des Arts et Métiers (CNAM), HESAM Université, 750141 Paris Cedex 03, France
Nonetheless, even in this new environment, production throughput and quality levels continue to be affected by unpredictable machine maintenance schedules and faster cutting tool wear, which results in cutting tool breakage, and which ultimately drives up costs and lowers financial performance [6, 7]. The ability to monitor and predict the remaining useful life of a cutting tool or of a CNC machine, or to predict the quality level of a workpiece in real time, could thus lend a real competitive advantage to a mach
Data Loading...
