Enhanced Cyber-Attack Detection in Intelligent Motor Drives: A Transfer Learning Approach With Convolutional Neural Networks
- 25 December 2023
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Emerging and Selected Topics in Industrial Electronics
- Vol. 5 (2) , 710-719
Abstract
As networked digital control units become increasingly prevalent in intelligent motor drive systems, cybersecurity concerns have risen, leading to the development of various cyber-attack detection methods to improve system reliability. Although data-driven methods offer advantages over physicsbased approaches, the requirement for extensive experimental data presents a significant challenge. This paper proposes a novel cyber-attack detection approach for motor drives using Transfer Learning based on Convolutional Neural Networks (CNN). The method initially pre-trains a CNN model with substantial simulation data and fine-tunes it using transfer learning with limited experimental data, achieving outstanding detection performance with 99.5% accuracy while reducing development costs, risks, and time. Additionally, the proposed model Maintains satisfactory detection accuracy of over 96% even when experimental training data is limited to 10% of original available data. The findings indicate that transfer-learned models exhibit faster convergence and better performance when limited experimental data is available compared to newly-trained models. The proposed approach substantially reduces the reliance on large quantities of experimental data during the development process, lowers costs and risks associated with cyber-attack detector development, strengthens the connections between simulations and experiments, and significantly shortens the development period by leveraging powerful simulation modelsKeywords
Funding Information
- National Science Foundation (ECCS-EPCN-2102032 (PI Ye), NSF-SATC-2019311 (PI Song), NSF-SATC-2019340 (PI Liu), NSF-SATC-2019378 (PI Shi))
This publication has 27 references indexed in Scilit:
- Data-Driven Approach for Detection of Physical Faults and Cyber Attacks in Manufacturing Motor Drives2022
- Divergence-Based Transferability Analysis for Self-Adaptive Smart Grid Intrusion Detection With Transfer LearningIEEE Access, 2022
- Data-Driven Detection of Physical Faults and Cyber Attacks in Dual-Motor EV Powertrains2022
- Data-driven cyber-attack detection for photovoltaic systems: A transfer learning approach2022
- Model-based Cyber-attack Detection for Voltage Source Converters in Island Microgrids2021
- A Review of Cyber–Physical Security for Photovoltaic SystemsIEEE Journal of Emerging and Selected Topics in Power Electronics, 2021
- Physics-Based Attack Detection for Traction Motor Drives in Electric Vehicles Using Random Forest2021
- Cyber-Physical Anomaly Detection in Microgrids Using Time-Frequency Logic FormalismIEEE Access, 2021
- Cyber–Physical Security of Powertrain Systems in Modern Electric Vehicles: Vulnerabilities, Challenges, and Future VisionsIEEE Journal of Emerging and Selected Topics in Power Electronics, 2020
- Detection of False Data Injection Cyber-Attacks in DC Microgrids Based on Recurrent Neural NetworksIEEE Journal of Emerging and Selected Topics in Power Electronics, 2020