Condition Monitoring of Chain Sprocket Drive System Based on IoT Device and Convolutional Neural Network. (25th July 2020)

• Record Type: Journal Article
• Authors: Lee, Sang Kwon; Back, Jiseon; An, Kanghyun; Kim, Sunwon; Lee, Changho; Kim, Pungil
• Other Names: Beltran-Carbajal Francisco Academic Editor.
• Is Part Of: Shock and vibration. Volume 2020(2020)
• Publication Date: 2020-07-25
• Subjects: Shock (Mechanics) -- Periodicals; Vibration -- Periodicals; 534.5
• DOI: 10.1155/2020/8826507
• Languages: English
• ISSNs: 1070-9622

Abstract

Abstract : This paper proposes a condition monitoring method for the early defect detection in a chain sprocket drive (CSD) system and classification of fault types before a catastrophic failure occurs. In the operation of a CSD system, early defect detection is very useful in preventing system failure. In this work, eight fault types associated with the CSD system components, such as the gear tooth, bearings, and drive motor shaft, were arbitrarily damaged and incorporated into the CSD system. To detect the fault signals during the CSD system operation, the vibration was measured using an Internet of Things (IoT) device, which features a wireless MEMS accelerometer, Bluetooth function, Wi-Fi function, and battery. The IoT device was mounted on the gearbox housing. The measured one-dimensional vibration time-series was transformed into time-scale images using continuous wavelet transform (CWT). A convolution neural network (CNN) was employed to extract deep features embedded in the images, which are closely related to fault types. To update the learning parameters of the CNN, the RMSprop learning algorithm was applied, and the CNN was trained using 500 image samples. Multiple-classification performance of the trained network was tested using 100 image samples. Feature maps for different fault types were obtained from the final CNN convolution layer. For the visualization of fault types, t -stochastic neighbor embedding was employed and applied to the feature maps to convert high-dimensional data into two-dimensional data. Two-dimensional features enabled excellent classification of the eight fault types and one normal type.