Đang chuẩn bị liên kết để tải về tài liệu:
Chẩn đoán thời gian thực không xâm lấn lỗi động cơ điện ba pha

Bài viết Chẩn đoán thời gian thực không xâm lấn lỗi động cơ điện ba pha được nghiên cứu với mục tiêu là ứng dụng mạng học sâu chạy trên nền tảng hệ thống nhúng để chẩn đoán thời gian thực lỗi động cơ điện ba pha bằng phương pháp không tiếp xúc dựa trên tiếng ồn phát ra. | JOURNAL OF TECHNOLOGY EDUCATION SCIENCE Ho Chi Minh City University of Technology and Education Website https jte.hcmute.edu.vn index.php jte index ISSN 1859-1272 Email jte@hcmute.edu.vn Realtime Non-invasive Fault Diagnosis of Three-phase Induction Motor Nguyen Van Khanh1 Tran Vy Khang2 Nguyen Minh Khai2 Thach Van To Em2 Pham Tran Lam Hai1 Nguyen Chi Ngon1 1Can Tho University Vietnam 2Automation and Control Engineering Can Tho University Vietnam Corresponding author. Email vankhanh@ctu.edu.vn ARTICLE INFO ABSTRACT Received 20 06 2022 The objective of this paper is to apply deep learning network running on an embedded system platform to diagnose faults of a three-phase electric motor Revised 14 08 2022 by a non-contact method based on operating motor noise. To accomplish Accepted 06 10 2022 this at first deep learning network should be designed and trained on a computer and then converted to an equivalent network to run on the Published 28 10 2022 embedded system. The network input data is a two-dimension spectrogram image of the noise emitted by the motor in four main cases including normal KEYWORDS operation phase shift phase loss and bearing failure. The execution time and accuracy of these deep learning network structures will be deployed on three Non-invasive fault diagnosis microcontrollers including ESP32 ESP32-C3 and nRF52840 to determine Spectrogram the suitable embedded platform and network structure for real-time running. esp32 Experimental results show that the proposed deep learning network models deep learning network could diagnose the faults well on both computer and embedded platform embedded system. with the highest accuracies are 99 7 and 99 3 respectively. In particular the preliminary results are remarkable with the recognition time and accuracy at 1 7 seconds and 72 respectively associated with the proposed deep learning network on realtime embedded system performance. Chẩn Đoán Thời Gian Thực Không Xâm Lấn Lỗi Động Cơ Điện Ba Pha Nguyễn Văn