Deep convolutional neural network with new training method and transfer learning for structural fault classification of
- PDF / 2,649,838 Bytes
- 10 Pages / 595.22 x 842 pts (A4) Page_size
- 82 Downloads / 250 Views
DOI 10.1007/s12206-020-1009-3
Journal of Mechanical Science and Technology 34 (11) 2020 Original Article DOI 10.1007/s12206-020-1009-3 Keywords: · 2D CNN · Structural fault classification · Spatial information of input data · Transfer learning
Deep convolutional neural network with new training method and transfer learning for structural fault classification of vehicle instrument panel structure Sang-Yun Lee and Sang-Kwon Lee
Correspondence to: Sang-Kwon Lee [email protected]
Citation: Lee, S.-Y., Lee, S.-K. (2020). Deep convolutional neural network with new training method and transfer learning for structural fault classification of vehicle instrument panel structure. Journal of Mechanical Science and Technology 34 (11) (2020) 4489~4498. http://doi.org/10.1007/s12206-020-1009-3
Received March 30th, 2020 Revised
July 3rd, 2020
Accepted August 16th, 2020
Mechanical Engineering, Inha University, Incheon, Korea
Abstract Structural defect have been detected by attaching sensors to all possible defect locations. A new method is proposed to enable the identification of structural defect locations with minimal data collection points using a deep convolutional neural network. Transfer learning was used to improve the accuracy of a hard-to-classify task by using a pre-trained model from an easy-to-classify task. To reduce the number of data collection points, it is necessary to learn the spatial information of the structure. To this end, a structure fault classification-deep convolutional neural network (SFC-DCNN) is proposed. It is an end-to-end convolutional neural network. The time-domain input data and convolutional neural network filter have 2 dimensions. With the proposed method, the accuracy of classifying the location of structural defects in a vehicle’s instrument panel structure was verified with a single vibration measurement point where the location is independent of the structural fault location.
† Recommended by Editor No-cheol Park
1. Introduction
© The Korean Society of Mechanical Engineers and Springer-Verlag GmbH Germany, part of Springer Nature 2020
The use of deep neural networks for diagnosing faults in machinery is increasing, and they are being applied to the diagnosis of bearing conditions in rotating machines for machine health monitoring. Unlike bearings in rotating machines, however, structural defect diagnosis has many points to monitor. The position of structural defects is widely diagnosed using the data from all positions where faults are expected to occur [1]. In this study, a method is proposed that enables the identification of structural defect locations with minimal measurement points using a deep convolutional neural network (CNN). Transfer learning for the initial value was used to increase the accuracy of classifying a more complicated structural defect problem by using the extracted features from a less complicated structural defect problem. To reduce the locations of data measurement points, it is necessary to learn the spatial information of the structure. To this end
Data Loading...
