Conference Programs

Program Overview 

Plenary Talks

1. Physics-informed learning and uncertainty quantification (July 1, 9:00 am)

Speaker: C. F. Jeff Wu, Chinese University of Hong Kong

Abstract: Suppose a system or product can be described by its underlying physical knowledge, usually via a set of partial differential equations (pde’s). Then the corresponding AI tools must be informed by this knowledge. In this talk I will focus on using physical knowledge to “inform” the development of statistical/machine learning. I will use two recent work to illustrate how this can be done. In developing the injector design for rocket propulsion, the mixing of oxygen and fuel was critical for the stability of propulsion. Navier-Stokes equations were used to describe the mixing behavior. However, the solution of the equations could take six weeks on clustered machine. Thus only a small number of numerical solutions could be performed. A surrogate model was instead developed by using tools in uncertainty quantification (UQ) and machine learning (ML). It could be computed within one hour and can mimic the mixing behavior. The success lies in using UQ-ML tools to incorporate known physical phenomena about mixing. The second work addresses the issue of incorporating knowledge of the pde’s such as its boundary conditions. In building an efficient surrogate model, it must also satisfy the same boundary conditions. We have constructed a new class of Gaussian process models that incorporate the same boundary information. We develop a framework of GP models based on stochastic partial differential equations (SPDEs) with Dirichlet or Robin boundary conditions. For fast computation, we use a kernel regression approximation to accurately approximate the SPDE covariances. Real examples are used for illustration.

2. Data Analytics and Optimization for Smart Industry (July 1, 10:20 am)

Speaker: Lixin Tang, Northeastern University

Abstract: Data analytics is the frontier basic research direction of industrial intelligence and one of the driving forces to promote scientific development. Systems optimization is the core basic theory of decision-making in smart industry, as well as the heart and engine of data analytics. This talk will discuss the fusion theory of data analytics and optimization (abbreviated as DAO) inspired by the structure of human brain, as well as the DAO-based octopus-topology solutions that we have been working on. Being related to industrial intelligence, the optimization part of DAO-based octopus-topology solutions include integer optimization, intelligent optimization, convex and sparse optimization, as well as topology and dynamic optimization; while the data analytics part consists of reinforcement learning, evolutionary learning, statistical physics-based learning and information theory-based learning. This talk will also introduce the applications of DAO theory in frontier systems technology, quality science, quality analytics and optimization, as well as production management. First, a frontier systems technology framework is constructed in a hierarchical structure, which consists of four levels, including perception, discovery, decision-making and execution from bottom to top, abbreviated as PDDE. Second, shifting the research perspective from macro production process to micro material, we discuss the material-based quality science on material discovery and synthesis, for quality analytics in manufacturing industries. Third, focusing on full lifecycle quality management of RDMS (Raw Material-Device - Machine - Systems), we consider the supply chain quality analytics and dynamic optimization, which covers the whole process of upstream steel production and downstream equipment manufacturing. Then, to facilitate the comprehensive quality improvement, a full-dimension organic management system is constructed as “Triple Transfer and One Feedback” framework. Based on that, production, logistics and energy across different manufacturing departments within an industrial enterprise are investigated. Finally, the ongoing research is generalized, which focuses on the systematic optimization and mechanism design of environment management, aiming to achieve overall carbon emission reduction for industrial ecosystem.

3. Deep Learning Enabled Modeling and Condition-Based Maintenance of Smart and Connected Systems (July 2, 9:00 am)

Speaker: Shiyu Zhou, University of Wisconsin Madison 

Abstract: Due to the fast development of sensing and information technology, many modern engineering systems, such as manufacturing and logistics systems, have become data-rich. The unprecedented data availability, combined with ever-growing computational power, creates unprecedented opportunities for system modeling and decision-making. In this presentation, new deep learning enabled modeling approaches for system degradation will be introduced. The approach features an integration of deep neural networks and the classical hidden Markov structure. As a result, the proposed modeling approach has excellent interpretability, scalability, and flexibility. In addition, a condition-based maintenance strategy for a large-scale multiple-component system is presented. The advantageous features of the developed methods are demonstrated through numerical studies and real-world case studies. Thoughts on potential research opportunities exploiting the ever-growing data-rich engineering environment will be shared as well.

4. Singapore and Micron: At the Heart of Future Intelligence (Jul 2, 10:10 am)

Speaker: Joshua Lee, Micron Technology 

Abstract: This keynote presentation explores the transformative impact of artificial intelligence (AI) on the semiconductor industry and advanced manufacturing. The address outlines how AI is reshaping global industries—from autonomous vehicles to smart factories—and highlights Micron’s strategic role in enabling this transformation through cutting-edge memory and storage technologies. The presentation details Micron’s global leadership in DRAM and NAND innovation, its AI Centers of Excellence, and its contributions to AI infrastructure across cloud and edge computing. It also showcases real-world AI applications within Micron, including smart warehousing, image analytics for defect detection, and generative AI for manufacturing optimization. Emphasis is placed on the exponential growth in memory and storage demand driven by AI workloads, and the company’s roadmap to meet these needs through advanced process nodes and high-performance products. Key enablers such as ecosystem collaboration, digital infrastructure, and talent development are discussed as critical to unlocking AI’s full potential. The keynote concludes with a call for cross-sector partnership to accelerate innovation and responsibly harness AI for global impact.

Featured Sessions

Panel Discussion: Impact of AI and Human-AI collaboration in Economics and Industries 

Leader Forum – Leveraging AI for the Next Generation QSR Education and Innovation 

Best Paper Competition

Chair: Zhisheng Ye

1. Ruixian Li, The University of Hong Kong

A Periodic Fractional Wiener Process for Remaining Useful Life Prediction of Photovoltaic Systems with Long-Range Dependence

2. Peiyao Liu, Tsinghua University

Spatial In-Profile Monitoring via Latent Tensor Gaussian Process with Mixed Effects

3. Kangan Chen, University of Wisconsin-Madison

Exact Multistage Bayesian Optimization

4. Qiuzhuang Sun, Singapore Management University

Optimal Maintenance Policy for Multi-Station Manufacturing Systems with Quality-Reliability Chain

Session Details

• Tu_C1: AI for Smart Manufacturing in Quality Design and Control

Co-Chairs: Yongxiang Li and Jianguo Wu            

1.      Enhancing Sensitivity Analysis of Building Energy Performance through Batch-Sequential Maximum One-Factor-At-A-Time Designs

Qian Xiao     Shanghai Jiao Tong University   

2.      Data-centric Paradigm in Advanced In-Process Monitoring for Smart Manufacturing

Feng Zhu     The Hong Kong Polytechnic University

3.      Adaptive sampling for detecting defects in multi-stream functional data from manufacturing systems

Chao Wang The University of Iowa         

4.      A Physical-Statistical Framework on Complex Mechanical System Fault Isolation

Bingxin Yan National University of Singapore

• Tu_D1: Contributed Session

Chair: Ran Jin            

1.      Privacy-Preserving Data Trade in Manufacturing Industrial Internet

Ran Jin          Virginia Tech

2.      Nexios: Network EXperimentation under Interference-an Online Strategy

Zhu Hongtao  National University of Singapore

3.      A Generative AI Framework for Digital Scam Prevention Targeting Older Adults

Shing Chang   Kansas State University

• Wd_C1: Data analytics for quality improvement in manufacturing systems

Co-Chairs: Rui Wang and Kaibo Wang             

1.      Recognition and classfication of mixed-type defect patterns in wafer bin maps

Rui Wang     Harbin Institute of Technolody (Shenzhen)    

2.      Federated Multi-task Bayesian Network  Learning in the Presence of Overlapping  and Distinct Variables

Xing Yang     Shenzhen University

3.      Advancing 4D Printing: New Frontiers in Modelling and Control

Michael Biehler       University of Wisconsin-Madison

4.     IoT Event Data Monitoring and Prediction Considering Within- and Between-Event Correlations

Zihan Yu       Tsinghua University

• Wd_D1: Contributed Session

Chair: Marco Grasso         

1.      Data and Knowledge dual-driven artificial intelligence for Equipment Health monitoring and Its Applications in Electromechanical Systems

Diyin Tang    Beihang University

2.      In-line monitoring of complex sensor data for zero-defect additive manufacturing in the electromobility industry

Marco Grasso           Politecnico di Milano,

3.      Quality Analytics Based on Digital Twin for Steel Production Process

Chang Liu    Northeastern University

4.      Model-based Prior for Model-free Reinforcement Learning in Process Control: An Offline Methodology for Semiconductor Manufacturing

Yanrong Li   National University of Singapore

• Wd_C2:  Recent Advances in Maintenance Decision Making

Co-Chairs: Xiao-Lin Wang and Qiuzhuang Sun

1.      Classical Periodic Replacement Policy Revisited: An Operational Statistics Perspective

Xiao-Lin Wang         Sichuan University

2.      Joint Optimization of Maintenance and Repositioning for Dockless Bike-Sharing Systems

Qiuzhuang Sun       University of Sydney        

3.      Optimal Predictive Inspection and Maintenance Policies: Forms, Properties, and Algorithms

Yao Cheng  The University of Hong Kong

4.      Condition-based maintenance for multi-component system using FMDP

Ziyu Wang   Tianjin University

• Wd_D2: Contributed Session

Chair: Xiaochen Xian                      

1.      Reinforcement Learning Based Adaptive Data-Driven Decision-Making for Resource Scarce Scenarios

Hongyue Sun University of Georgia

2.      Capacity Degradation Assessment of Lithium-Ion Battery Considering Coupling Effects of Calendar and Cycling Aging

Xingchen Liu  The Hong Kong Polytechnic University

3.      Integrating Quality and Maintenance: Benefits and challenges in the AI era

Hendry Raharjo       Chalmers University of Technology

4.      A Bayesian Jump Model-based Pathwise Sampling Approach for Online Anomaly Detection

Xiaochen Xian         Georgia Institute of Technology

• Wd_C3: Quality Management in the New Technology Environment (Flash Talk)

Co-Chairs: Huchen Liu and Jianxin You           

1.      Human reliability analysis of bunkering operation using consensus-based success likelihood index model and ROCOSD method

Jing-Hui Wang         Tongji University

2.      New model for occupational hazards risk assessment and classification based on three-way decision in the healthcare industry

Qi Zhen Zhang         Tongji University

3.      New approach for quality function development based on social network analysis and DANP method

Yi-Fan Song Tongji University

4.      Quality Design Based on Product Specification Limit Constraints in Uncertain Production Environment

Yunxia Han  Yangzhou University

5.      Towards Second-Life Battery SOH Estimation: A Physics-Feature Enhanced Deep Learning framework

Rong Zhu     City University of Hong Kong

6.      The Development and Application of Intelligent Quality Control System Based on Industrial Big Data

Di Zhao        Zhengzhou University

7.      Joint Optimization of Product Family Quality and Prices Under Multinomial Logit Choices with Self-Cannibalization

Mengyuan Han        Tianjin University

• Wd_D3: Contributed Session (Flash Talk)

Chair: Jun Zhu                     

1.      Confidence-Bounded Satellite Temperature Prediction Synergizing Empirical Mode Decomposition with Monte Carlo-Augmented LSTM Framework

Yingchun Xu   National University of Defense Technology

2.      Condition-based maintenance for redundant systems considering spare inventory with stochastic lead time

Jun Wang     Beijing Foreign Studies University

3.      Prospect-Theoretic Pricing Optimization for Remanufactured Equipment Leasing

Xiaoke Cheng           Tianjin University

4.      Resilience of the interdependent network against cascade failure

Changchun Lv         Ximen University of Architecture and Technology

5.      Diffusion-Driven Robust Cooperative Control for Industrial Vehicles under Stochastic Path Tracking Tasks

Lian Geng    Beihang University

6.      Bivariate Degradation Analysis of Products Reliability Based on Exponential Dispersion Process and a Shared Frailty Factor

Chen Siyi     Chinese Academy of Sciences

7.      A New Weighted Mechanism-based Partial Transfer Fault Diagnosis Method for Voltage Source Inverter

Jun Zhu         Northwestern polytechnical university

• Th_C1: High Dimensional Process Monitoring and Diagnosis

Co-Chairs: Lianjie Shu and Yanting Li              

1.      Robust and Sparse PCA for High-dimensional  Data Via Local Linear Approximation

Lianjie Shu  University of Macau

2.      A Robust Control Chart for Monitoring High-Dimensional Data Streams

Dong Ding   Xi'an Polytechnic University

3.      A phase I change-point method for high-dimensional process with sparse mean shifts

Wenpo Huang         Hangzhou Dianzi University

4.      Dynamic Network Modeling for Early Fault Diagnosis in Wind Turbines Using SCADA Data

Yujie Wang  University of Miami

• Th_D1: Advanced Statistical Modeling for Industrial Process Monitoring in Data-rich Environment

Co-Chairs: Xi Zhang and Yu An                 

1.      Predicting Spatial Porosity Variation in Batch Metal Binder Jetting via In-Situ Stereovision Data Modeling

Hui Wang    Florida A&M University - Florida State University

2.      Online Anomaly Monitoring for Partial Data Streams: Adaptive Sampling Path Planning via Safe Reinforcement Learning

Yuge Cao     Peking University

3.      Partially-Linked Multi-Matrix Decomposition for Multivariate Profile Data Modeling and Monitoring

Kai Wang     Xi'an Jiaotong University

4.      Quantile-Based Monitoring of Profiles with Generally Distributed Responses

Jian Li  Xi'an Jiaotong University

• Th_C2: Data-Driven Stochastic Models for Resilient Systems

Co-Chairs: Xun Xiao and Piao Chen                 

1.      A Bayesian approach to a value-based preventive maintenance model for multi-component system

Wanqing Cheng      Tianjin University

2.      Estimating Degradation Dynamics in Railway Systems with Random Slopes: A Spatio-Temporal Mixed Model Approach

Zhanzhongyu Gao  University of New South Wales

3.      Statistical inference and maintenance strategy of the lifetime delayed heterogenous degradation process

Zan Li  Nankai University

4.      Learning local cascading failure pattern from massive network failure data

Xun Xiao      University of Otago

• Th_D2:  Statistical Control and Optimal Design for Intelligent Systems

Co-Chair: Chen Zhang and Xiaowei Yue          

1.      Recent Progress in Data-Driven Quality Improvement

Xiaowei Yue Tsinghua University

2.      Multi-fidelity Kriging Structural Reliability Analysis with the Fusion of Non-hierarchical Low-fidelity models

Yan Ma         Nanjing University of Finance and Economics

3.      A novel Bayesian approach for multi-objective stochastic simulation optimization

Mei Han       Nanjing University of Aeronautics and Astronautics

• Th_C3: Advances in Quality Engineering for System Intelligence  

Co-Chairs: Di Wang and Yingdong He            

1.      Risk-adjusted monitoring of online user-generated reviews via user preference learning

Qiao Liang   Southwestern University of Finance and Economics

2.      Enabling Tensor Decomposition for Time-Series Classification via A Simple Pseudo-Laplacian Contrast

Man Li Southwestern University of Finance and Economics

3.      Partially Observable Online Nonparametric Monitoring of Spatiotemporally Correlated  Data Streams

Di Wang       Shanghai Jiao Tong University

4.      Quality Monitoring & Quality Optimization for Complex Systems

Yingdong He   Tianjin University

• Th_D3: Generative, Predictive, and Prescriptive Maintenance Framework

Co-Chairs: Jae Wook Song and Suk Joo Bae                      

1.      Driving-Protocol Fuel Cell Degradation Pattern Modeling Using DeepAR

Na Yosep     Hanyang University

2.      A Zero-Inflated Multivariate Peaks Over Threshold Model for Serial Multi-Stage Process Data

Hwi Jun Jung  Hanyang university

3.      Generation and Validation of Multimodal Data for Bearing Fault Diagnosis via Large Language Models

Misuk Kim   Hanyang University

4.      Enhancing Manufacturing Reliability Through NLP-Based Log Anomaly Detection

Jaewon Cheon        Korea University

• Th_C4: Data Analytics and Machine Learning for Quality Management

Co-Chairs: Mei Han and Linhan Ouyang

1.      Statistical tests assisted Bayesian variable selection for Kriging metamodeling

Baoping Tao Nanjing University of Aeronautics and Astronautics

2.      Proactive Quality Control of Highly Reliable Products' Lifetime via Prediction-Driven Monitoring

Chenglong Li  Northwestern Polytechnical University

3.      A Local Variational Inference Framework for the Orthogonal Gaussian Process Calibration

Yan Wang    Beijing University of Technology

4.      Estimating the all-terminal signatures for networks by using deep neural network

Gaofeng Da Nanjing University of Aeronautics and Astronautics

• Th_D4: Contributed Session

Chair: Yu Sun          

1.      A Demand Forecasting and Inventory Management Method for Supply Chain Networks

Yu Sun           Beihang University

2.      KDE-Hypernetwork Based Client Clustering Federated Learning for Non-IID Anomaly Detection

Jiayi Fan       Beihang University

3.      Mechanistic-Data Fusion Approach with  Small-sample quality Prediction in Hot-rolled Products

Jian Wu        Northeastern University