2025 6th International Conference on Mechanical Engineering, Intelligent Manufacturing, and Automation Technology (MEMAT 2025)

Title: Contribution of Digital Twin Model in Smart Manufacturing and Quality Control.

Abstract: The rapid evolution of smart manufacturing is transforming traditional production systems through the integration of advanced digital technologies. Among these innovations, the Digital Twin (DT) has emerged as a key enabler for intelligent decision-making, real-time monitoring, and advanced quality control. This presentation explores the contribution of Digital Twin models to modern manufacturing environments, emphasizing their role in enhancing operational efficiency, product reliability, and process transparency. A Digital Twin provides a dynamic virtual representation of physical assets, allowing manufacturers to simulate, predict, and optimize performance across the entire product lifecycle. By leveraging data from sensors, IoT devices, and machine-learning algorithms, DT models enable continuous monitoring and early detection of deviations, thereby reducing downtime and improving quality assurance.

The talk highlights how Digital Twins support predictive maintenance, adaptive process control, and scenario-based simulations that guide informed decision-making. Their ability to integrate heterogeneous data sources facilitates better traceability, real-time defect identification, and optimization of production parameters. Case studies are presented to demonstrate measurable improvements in productivity, cost efficiency, and product consistency. Overall, this presentation underscores the transformative potential of Digital Twin technology as a cornerstone of smart manufacturing, offering a robust framework for achieving higher levels of automation, precision, and quality in Industry 4.0 environments.

Experience: David BASSIR is as Professor at the French University of Technology and Senior Researcher at Centre Borelli, (UMR-CNRS), University of Paris-Saclay, ENS-Cachan, France. He holds a Master and a PhD degree in structural optimization from the University of Franche-Comte (France), with the most honorable mention. Previously, he was the Dean of the University of Technology (IUT) at the University of Lorraine (France), Consult for Science and Technology at the French Embassy in China, General Director of Research at the ESTP-ENSAM (Paris) and Space Craft engineer at GECI Technology in different Space Agencies such as Arianespace (France) and Matra Marconi Space (Astrium Group). He joined the French University of Technology as associate professor in 2001 and then was qualified as Full professor in 2009. Prof. Bassir hold Doctor Honoris Causa title and was invited as visiting professor in top universities and institutes such as (TUDelft (NL), Shanghai Jiaotong (Shanghai), Northwestern Polytechnical University (Xian), University of Oviedo (Spain), Chinese Academy of Sciences (Guangzhou), … etc). He has published over 150 papers in journals, books and conference proceedings, including more than 50 Sci. journals. He also supervised over 15 Phd. and 50 Master degrees. Most of his students have won best paper awards at conferences. And all of them are now either full professor in high ranked universities or well-known companies.

Prof. Bassir serves as or chairman or active member of various expert committees in many international organizations and highly estimated scientific societies. He is also acting as editor-in-chief and guest editors in different journals. Since 2012, he is the president of the well-recognized Sino-French Association for Sciences and Technology. In 2021 he was awarded a top 5% scientific award from the French ministry of high education and research.

Abstract: After over five decades of development, intelligent control has evolved from early fuzzy logic and neural networks to contemporary deep learning and reinforcement learning. Its core objective remains emulating human intelligent behavior to address complex system control challenges. This presentation aims to systematically review this evolutionary trajectory and delve into the paradigm shift brought by new-generation artificial intelligence to motion contrl—transitioning from traditional model-driven approaches to new principles based on the synergistic integration of data and knowledge. Practical case studies will be presented, highlighting specific advances in AI-driven motion control within the field of robotics. Finally, the talk will conclude by outlining key future directions for intelligent motion control and discussing the cutting-edge challenges that lie ahead.

Experience: Li Zhifu, Professor, PhD SupervisorMember of the Chinese Association of Automation (CAA),Member of IEEE,Member of the CAA Young Scientists Committee,Member of the CAA Technical Committee on Adaptive Dynamic Programming and Reinforcement Learning. Research Interests: Intelligent Equipment and Systems, Intelligent Robotics, Artificial Intelligence Technologies.He has led over 10 government-funded research projects, including the General Program of the National Natural Science Foundation of China (NSFC). He has published more than 50 research papers and has been granted 15 patents.

Accurate screening for respiratory diseases is essential for effective clinical diagnostics. Two of the most widely used indicators of pulmonary function are Forced Expiratory Volume in 1 second (FEV₁) and Forced Vital Capacity (FVC). Traditional diagnostic methods, such as spirometry, are effective but often limited by device availability, patient compliance, and the complexity of testing procedures.

In this study, we present a novel, non-invasive approach to estimate pulmonary function using the voiced pharyngeal sound of “He”. By analyzing these voice signals, we developed models to predict FEV₁ and FVC values, benchmarked against conventional spirometry. A total of 21 features were extracted from the voiced segments of the pharyngeal sound. Machine learning models—including linear regression, quadratic regression, and neural networks—were applied to estimate pulmonary function parameters.

Data was collected from 18 male participants, aged 33–49 years, between June and August 2022, resulting in 56 recordings. Among the models evaluated, the neural network consistently outperformed the linear and quadratic models. Specifically, a neural network using three features estimated FEV₁ with a mean error of 0.24%, while a two-feature neural network predicted FVC with a mean error of 0.58%.

This study demonstrates that voiced pharyngeal sound analysis, combined with machine learning, can serve as an accurate and non-invasive method for assessing pulmonary function, offering potential for rapid, accessible respiratory health screening.

Experience: Dr. Ata Jahangir Moshayedi is an Associate Professor at Jiangxi University of Science and Technology. He holds a Ph.D. in Electronic Science from Savitribai Phule Pune University (formerly the University of Pune), India. He is a Senior Member of IEEE, a Professional Member of ACM, and a Life Member of the Instrument Society of India.Dr. Moshayedi has published over 100 research papers, authored 4 books, contributed to 4 book chapters, and holds 2 patents and 16 copyrights. He actively serves as a technical program committee member and session chair for numerous international conferences.

His current research focuses on robotics, particularly the development of autonomous guided vehicles (AGVs) for applications such as smart farming, food delivery and elderly care.

Abstract: Multiple-input, multiple-output (MIMO) model is a rather general concept for describing diverse classes of engineering and data processing systems. The underlying mathematical model is a linear or nonlinear differential or difference matrix equation. The most common objectives in analyzing these equations are determining the conditions when the system is stable, and how to efficiently observe and control the system in some well-defined sense. In this talk, I will discuss how to linearize non-linear models, and how to define the optimum observability and controlability for linear MIMO systems. I will also explore the issues and methods that are required for achieving the system stability. I will assume examples from signal processing to illustrate the key concepts.

Experience: Pavel Loskot joined the ZJU-UIUC Institute in January 2021 as an Associate Professor after being 14 years with Swansea University in the UK. He received his PhD degree in Wireless Communications from the University of Alberta in Canada, and the MSc and BSc degrees in Radioelectronics and Biomedical Electronics, respectively, from the Czech Technical University of Prague in the Czech Republic. In the past 25 years, he was involved in numerous collaborative research and development projects, and also held a number of paid consultancy contracts with industry. He is the Senior Member of the IEEE, Fellow of the Higher Education Academy in the UK, and the Recognized Research Supervisor of the UK Council for Graduate Education. His current research interests focus on mathematical and probabilistic modeling, statistical signal processing and classical machine learning for multi-sensor data.