Electromechanical System Integration Lab
Research Field
Dr. Meng-Kun Liu is an Associate Professor in the Department of Mechanical Engineering at National Taiwan University of Science and Technology (NTUST/Taiwan Tech) . His research primarily focuses on signal analysis, machine learning, and deep learning methods applied to vibration, electrical, and physiological signals . Over the past five years, Dr. Liu has published 10 SCI/SCIE journal papers in top-tier venues (such as Expert Systems with Applications, Engineering Applications of Artificial Intelligence, and Measurement) and holds 1 US patent and 2 Taiwan patents, with his research receiving 1,480 citations (as of January 1, 2026) .
In addition to his academic publications, Dr. Liu is highly active in leadership and professional services . He serves as the Co-Editor-in-Chief of the International Journal of Automation and Smart Technology (AUSMT), Deputy Secretary-General of the Chinese Automatic Technology Association, and Student Affairs Director of the NTUST Paraguay Project Office . He also holds prestigious professional certifications, including the Certified Measurement and Verification Professional (CMVP) credential and advanced NI LabVIEW qualifications . For his dedicated contributions, he has been honored with multiple Institutional Awards for Excellence in Teaching, Research, and Service at NTUST.
The Electromechanical System Integration Lab (ESILab), directed by Dr. Meng-Kun Liu, is a highly research-oriented laboratory at NTUST . ESILab is dedicated to fostering students' core engineering competencies by providing rigorous and systematic training in English literature review, data collection, logical thinking, theoretical analysis, and technical paper writing. Outstanding students are consistently given opportunities to present their research at major international conferences .
The lab maintains an excellent track record of industrial collaboration and student placement. Over 50% of the lab's graduates over the past three years have secured positions at ASML (Netherlands) and in leading semiconductor companies. Furthermore, undergraduate students under Dr. Liu’s mentorship routinely win top prizes in national and regional engineering design competitions (such as the prestigious Hiwin Mechanical Thesis Award and the TDK Cup National Creative Thinking Competition) , with exceptional members successfully advancing to world-class graduate schools, such as UC Berkeley .
ESILab specializes in blending advanced data science with electromechanical engineering across four primary research domains:
Deep Learning Architectures for Induction Motor Fault Diagnosis: Developing non-invasive, cost-effective induction motor monitoring systems based on three-phase current and voltage signals . By replacing expensive traditional vibration sensors, the lab builds custom deep learning models featuring multi-head attention mechanisms to automatically capture spatial, temporal, long-term, and short-term characteristics from raw current data, advancing towards explainable AI models .
MMG-based Wearable Human-Machine Interfaces & Gesture Recognition: Developing wearable gesture recognition devices using Mechanomyogram (MMG/muscle vibration) signals . Unlike traditional Electromyography (EMG), which is heavily affected by sweat or environmental dryness, ESILab's robust MMG feature-extraction method achieves precise gesture tracking. This technology has been successfully patented and transferred to CoolSo Technology, attracting venture capital from the top-tier US startup accelerator, Alchemist Accelerator .
Acoustic Signal-Based Tool Wear Prediction in CNC Milling: Creating commercialized tool wear prediction models by mounting accessible microphones on CNC milling machines . By applying wavelet packet decomposition, collinearity diagnostics, and stepwise regression, the system filters out robust acoustic features . These features are used in statistical regression and artificial neural networks to accurately predict tool wear without bias from varying cutting parameters.
Milling Chatter and Stability Analysis: Analyzing the nonlinear, "route-to-chaos" behavior of workpiece-tool vibrations in machining processes . Moving beyond subjective feature selection and traditional Fourier spectrum analysis, the lab leverages the continuous wavelet transform (CWT) to construct scalograms and applies deep learning models to automatically and accurately classify cutting states and detect chatter anomalies.
- Zhan-Shuo Liao, Meng-Kun Liu, and Zhen-Yang Lan, "Integration of Physics-Based Modeling and Deep Learning Framework for General-Purpose Delta Robot Fault Diagnosis," The 21st Hiwin Mechanical Thesis Award - Technological University Special Award. (2024/12/26)
- Chung-Lin Hsieh, Thanh-Tung Vo, and Meng-Kun Liu (2023, Aug 30th-Sep 1st), "Residual Current-based Deep Learning Architecture for the Induction Motor Fault Diagnosis," 2023 International Conference on Advanced Robotics and Intelligent Systems (ARIS 2023), Taipei, Taiwan. Honorable Mention Award.
- Yu-Sing Wu and Meng-Kun Liu (2023, May 29-31th), "MMG-based Hand Gesture Recognition Device," 11th International Senior Project Conference, King Mongkut’s University of Technology Thonburi (KMUTT), Bangkok, Thailand. Excellent Presentation Award.
- An-Hua Huang, Meng-Kun Liu, and Jun-Liang Guo, "Validation of a Lubricating Oil Quality Detection System Based on RC Discharge Signal Analysis," The 19th Hiwin Mechanical Thesis Award - Technological University Special Award. (2022/12/26)
- Advised undergraduate students (Hong-Jia Chen, Jing Luo, Zi-You Liu, and Zheng-Xu Lai) in participating in "The 26th TDK Cup National Colleges and Universities Creative Thinking Design and Manufacturing Competition," winning Second Place in the Automated Group. (2022/10/21)
- Advised undergraduate senior project students (Wei-Hao Chen, Jia-Hui Li, Yu-Xin Wu, and Zong-Qi Yang), winning the Honorable Mention Award (Smart Wristband) at the 6th Northern Region Three-University Mechanical (Mechatronic) Engineering Department Senior Project Competition. (2022/1/14)
- Minh-Quang Tran* and Meng-Kun Liu (2021, Aug), "Machine Learning-based Milling Stability Diagnosis using Vibration Signal," International Conference on Precision Engineering and Sustainable Manufacturing (PRESM 2021). Outstanding Presentation Award.
- Advised students (Hong-Jun Liu, Yu-Cheng Zhao, Qing-Xuan He, and Pin-Zhang Qiu), winning the Honorable Mention Award in the Remote Control Group (Team: NTUST Quack Quack) at the 25th TDK Cup National Colleges and Universities Creative Thinking Design and Manufacturing Competition. (2021/12/17)
Meng-Kun Liu received his B.S. degree from National Yang Ming Chiao Tung University and his M.S. degree from National Taiwan University, both in Mechanical Engineering. He earned his Ph.D. in Mechanical Engineering from Texas A&M University in 2012. Since 2014, he has been serving as an assistant professor in the Department of Mechanical Engineering at the National Taiwan University of Science and Technology (NTUST). His research interests encompass time-frequency analysis of manufacturing processes, fault diagnosis of induction motors, robot force control, and chaos control
Job Description
- Industry-Academia Collaboration: Act as a key coordinator and researcher for dedicated industry-academia collaboration projects; facilitate communication, track milestones, and align project goals between the company and university partners.
- Automation Research: Conduct research on advanced factory automation technologies, assembly methods, and robotic integration.
- Process Optimization: Analyze existing manufacturing workflows, collect data, and propose data-driven solutions to optimize cycle time and efficiency.
- Programming & Scripting: Develop, test, and debug automation control scripts and software for machinery or robotic systems.
- Simulation & Testing: Create virtual simulations of assembly lines or mechanical setups to test feasibility before physical deployment.
- Documentation & Reporting: Maintain clear documentation of research findings and coding structures, and prepare project reports for both internal stakeholders and academic partners.
Preferred Intern Educational Level
- Current Student: Pursuing a Bachelor’s, Master’s, or Ph.D. degree.
- Major: Mechanical Engineering, Electrical Engineering, Automation Engineering, Mechatronics, or a closely related technical field.
Skill sets or Qualities
Skill Set (Technical Skills)
Automation Programming: Proficiency in automation-related programming languages (e.g., Python, C/C++, PLC programming like Ladder Logic, or structured text).
Hardware Knowledge: Basic understanding of sensors, actuators, motor controllers, and microcontrollers (e.g., Arduino, Raspberry Pi) or industrial PLCs.
CAD & Simulation Software: Familiarity with 3D modeling software (e.g., SolidWorks, Autodesk Inventor) or process simulation tools is a strong plus.
Data Analysis: Ability to use tools like Excel, MATLAB, or Python libraries to analyze process data and manufacturing metrics.
Qualities (Soft Skills & Attributes)
Project Management & Coordination: Ability to organize tasks, manage timelines, and coordinate between external academic entities and internal teams.
Analytical Mindset: A strong problem-solving orientation with a passion for finding root causes and optimizing complex systems.
Curiosity & Adaptability: Eager to learn new manufacturing technologies and quickly adapt to industrial hardware/software ecosystems.
Communication & Teamwork: Excellent interpersonal skills to effectively collaborate with cross-functional teams and present research findings clearly.
Attention to Detail: Precision-oriented, especially when dealing with equipment calibration, coding, and safety protocols.