Learning time-series data of industrial design optimization using recurrent neural networks

Saha，Sneha1; Rios，Thiago1; Menzel，Stefan1; Sendhoff，Bernhard1; Back，Thomas2; Yao，Xin3,4; Xu，Zhao5; Wollstadt，Patricia1

10.1109/ICDMW.2019.00116

2019-11-01

2375-9232

2375-9259

978-1-7281-4897-7

IEEE International Conference on Data Mining Workshops, ICDMW

2019-November

785-792

8-11 Nov. 2019

Beijing, China

IEEE Computer Society

In automotive digital development, 3D shape morphing techniques are used to create new designs in order to match design targets, such as aerodynamic or stylistic requirements. Control-point based shape morphing alters existing geometries either through human user interactions or through computational optimization algorithms that optimize for product performance targets. Shape morphing is typically continuous and results in potentially large data sets of time-series recordings of control point movements. In the present paper, we utilize recurrent neural networks to model such time-series recordings in order to predict future design steps based on the history of currently performed design modifications. To build a data set sufficiently large for the training of neural networks, we use target shape matching optimization as digital analogy for a human user interactive shape modification and to build data sets of control point movements in an automated fashion. Experiments show the potential of recurrent neural networks to successfully learn time-series data representing design changes and to perform single-and multi-step prediction of potential next design steps. We thus demonstrate the feasibility of recurrent neural networks for learning successful design sequences in order to predict promising next design steps in future design tasks.

Computer aided engineering Deep learning Optimization Recurrent neural networks

其他

英语

EI

Horizon 2020 Framework Programme[766186]

20200608123343

Computer aided engineering ; Computer aided instruction ; Data mining ; Deep learning ; Deep neural networks ; Forecasting ; Optimization ; Product design ; Shape optimization ; Time series

Data Processing and Image Processing:723.2 ; Computer Applications:723.5 ; Production Engineering:913.1 ; Optimization Techniques:921.5 ; Mathematical Statistics:922.2

2-s2.0-85078738761

Scopus

1.Honda Research Institute Europe GmbH,Offenbach,Carl-Legien-Str. 30,63073,Germany
2.Leiden Institute of Advanced Computer Science (LIACS),CA Leiden,Niels Bohrweg 1,2333,Netherlands
3.CERCIA,School of Computer Science,University of Birmingham,Birmingham,United Kingdom
4.Department of Computer Science and Engineering,Southern University of Science and Technology,Shenzhen,China
5.NEC Laboratories Europe,Heidelberg,Kurfürsten-Anlage 36,69115,Germany

Saha，Sneha,Rios，Thiago,Menzel，Stefan,et al. Learning time-series data of industrial design optimization using recurrent neural networks[C]:IEEE Computer Society,2019:785-792.