Quality Control and Reliability Engineering – Webinar archive
Recent Advances of Causal Inference and Causal Discovery in Manufacturing
Presented by IISE Quality Control & Reliability Engineering (QCRE) Division
Speaker: Dr. Xubo Yue
December 5, 2024
The manufacturing industry is increasingly data-driven, leveraging advanced analytics to optimize processes, enhance product quality, and reduce costs. In this talk, I will present several of my recent work in causal inference and causal discovery techniques applied to manufacturing contexts. We explore methods for inferring causality from observational data,
highlighting approaches such as structural equation modeling, Bayesian networks, and machine learning-based causal discovery algorithms.
Download Video
Sparse Regression Analysis of Mixed Multi-Responses
Presented by the DAIS and QCRE divisions
Speaker: Dr. Xiaoyu Chen, University of Buffalo
April 8, 2024
In this talk, Dr. Chen will present studies on (1) a multivariate regression of mixed responses (MRMR) model with application to a visualization evaluation problem; and (2) a Bayesian MRMR model that considers both individual and group variable selection with application to a runtime performance metrics prediction problem in Fog computing network.
In addition, future research opportunities will be discussed.
Download Video
Data Science Enabled Decision-making in Advanced Manufacturing and Personalized Safety
Presented by the QCRE and DAIS divisions
Speaker: Dr. Hongyue Sun, University of Georgia
March 26, 2024
Dr. Sun presented data science enabled decision-making to address the above challenge, with applications in advanced manufacturing and personalized safety. He will introduce the consideration of high dimensional and streaming data for inkjet printing additive manufacturing process modeling, monitoring, and control. He will also speak about the work on occupational
worker fatigue assessment based on wearable sensors, to model the personalized, dynamic, and heterogeneous information of workers and inform the optimal system management. Finally, the future plans will be discussed.
Download Video
Advancing and Accelerating Qualification and Characterization through Stochastic Inverse ModelingMy Webinar
Presented jointly by the IISE Data Analytics and Quality Control and Reliability Divisions
November 28, 2023
Presenter: Dr. Ashif Iquebal
This webinar explores the existing research on inverse problems and how they are limited in accurately estimating the QoIs and their variabilities.
Download Video
Assessing the Calibration and Performance of Attention-based Spatiotemporal Neural Networks for Lightning Prediction
Presented jointly by the IISE Data Analytics and Quality Control and Reliability Divisions
November 14, 2023
Presenter: Dr. Nathan Gaw
This webinar will discussed the recent neural networks developed to produce accurate lightning nowcasts, using various types of satellite imagery, past lightning data, and other weather parameters as inputs to their model.
View Presentation
Digital Twin for Quality Innovations: Manufacturing and Health Applications
Presented jointly by the IISE Data Analytics and Quality Control and Reliability Divisions
October 31, 2023
Presenter: Dr. Hui Yang
This webinar discusses our continuous research efforts on the “sensing-modeling-optimization” framework to build new cyber-physical digital twins in disparate disciplines of manufacturing and healthcare.
Download Video
Do Reliability and Machine Learning Models With Time Delays and Model Selection Matter?
Presented by the IISE QCRE and DAIS Divisions
1 p.m. ET March 2
Presenter: Dr. Hoang Phan
With the development of various machine learning models, both model-driven and data-driven approaches in recent years, the task of determining an appropriate model which satisfies certain criteria from a set of candidate models given a set of data has become more challenging for engineers and analysts. In this talk, I will discuss various model selection criteria and some recent modeling studies
of systems such as system degradation and body's immune system with time delays.
Machine Learning for Digital Transformation of Clinical Trials and Legal Review
Presented jointly by the IISE Data Analytics and Quality Control and Reliability Divisions
10 a.m. PT/1 p.m. ET Feb. 27
Presenter: Cao (Danica) Xiao
The digital transformation of healthcare and legal data presents remarkable opportunities for machine learning (and deep learning) technologies to revolutionize the healthcare and legal industries. To ensure research will be useful and thus have real world impact, it is desirable to study the industry expert workflow and identify meaningful tasks that machine learning can help automate or augment.
This talk will cover examples of research works and products to show some initial success of machine learning in improving the success and efficiency of patient recruitment in clinical research and privilege and privacy redaction in legal review.
Download Video |
View Presentation
Doing More with Less: Cost-Effective Machine Learning for Manufacturing Quality Control
Presented jointly by the IISE Manufacturing and Design and Quality Control and Reliability Divisions
3 p.m. ET/2 p.m. CT Feb. 21
Presenter: Dr. Chenhui Shao
In the era of smart manufacturing, the “cost of data” accounts for an ever-increasing proportion of the “cost of quality.” Decision-making in smart manufacturing, especially quality control, calls for learning efficiency, responsiveness, and intelligent data collection. This webinar will present some recent advances in transfer learning, domain generalization, federated learning, and sampling design (aka active learning) that have promoted
cost-effective decision-making for manufacturing quality control.
Watch Video
Dynamic Characterization and Optimal Self-Management of the Emergence Trajectories of Multiple Chronic Conditions
Presented jointly by the IISE Quality Control and Reliability Engineering (QCRE) Division and Data Analytics and Information Systems (DAIS) Division
1 p.m. ET Dec. 6
Presenter: Dr. Adel Alaeddini
More than a quarter of all Americans and two out of three older Americans are estimated to have at least two chronic health problems. Treatment for people living with multiple chronic conditions (MCC) consume an estimated 66 percent of U.S. healthcare costs, and as the population ages, the number of MCC patients will increase. However, fundamental knowledge gaps remain in our understanding of how MCC evolves at the individual and population levels.
his presentation introduces functional and deep continuous time Bayesian networks to model the relationship among MCC and non/modifiable risk factors to characterize major patterns of MCC emergence in individuals based on a dataset from the US Department of Veteran Affairs.
Download Video
Online Monitoring of Big Data Streams -- Roadmap and Recent Advances
A Webinar presented by the Online Monitoring of Big Data Streams -- Roadmap and Recent Advances
Nov. 17, 2022
Presenter: Dr. Kaibo Liu, Associate Professor, University of Wisconsin-Madison
The rapid advancements of internet of things (IoT) technology and cyber-physical infrastructure have resulted in a temporally and spatially dense data-rich environment, which provides unprecedented opportunities for performance improvement in various complex systems. Meanwhile, it also raises new research challenges on process monitoring,
such as heterogeneous data formats, high-dimensional and big data structures, inherent complexity of the target systems, and potential lack of complete a priori knowledge.
Download Video
The Importance of Industrial Predictive Analytics in Self-Awareness and Self-sufficiency of the Deep Space Habitats
A Webinar presented by the Quality Control and Reliability Engineering (QCRE) Division and the Manufacturing and Design (M&D) Division
Apr. 26, 2022
Presenter: Dr. Nagi Gebraeel, Georgia Power Early Career Professor and Professor, School of Industrial and Systems Engineering, Georgia Institute of Technology
Since humans first set foot on the moon half a century ago, most of the focus has been on low-Earth orbit missions with few unmanned scientific explorations. The accelerated growth of Space industry has created a new focus towards Deep Space applications, especially ones related to habitation. Deep space mission requires new concepts and paradigms that are different from what is currently adopted by the International Space Station (ISS). The ISS is constantly
occupied by astronaut crew members, maintains an extensive supply of spare parts, and is supported by a large mission-control staff. Future deep space habitats will have none of these attributes. This talk will highlight ongoing research at the HOME Institute. HOME, Habitats Optimized for Missions of Exploration, is a NASA Space Technology Space Institute charged with helping NASA design future deep space SmarHabs. In this talk, I focus on novel Industrial Engineering
research applications and the profound impact of “Earth Independence” when developing modeling frameworks and algorithms for self-awareness and self-sufficiency for deep space SmartHabs.
Download Video
Some Practical Procedures for Quality and Reliability Monitoring of Industrial Processes
A Webinar presented jointly by the Quality Control and Reliability Division and the Manufacturing and Design Division
March 30, 2022
Presenter: Dr. Min Xie
Covid-19 has shown us the drawbacks of our supply chains and exposed our vulnerabilities. "self-sufficiency," can only be realized by making SMMs an integral part of the larger manufacturing ecosystem. Local Manufacturing, a paradigm that relates the local skills, resources, and SMMs is needed for making our country self-sufficient. We show how IIoT, AI&ML, and Networks will become the backbone of such a futuristic manufacturing ecosystem and bring four different areas of research together to pave the foundation for the next generation manufacturing.
Download Video
Disaster damage assessment in the U.S. is increasingly important as natural hazard-induced disasters (e.g., hurricanes) are breaking records nearly every year, costing the nation hundreds of billions of dollars per year. However, the current practice of disaster damage assessment is largely dependent on humans (e.g., ground surveys) being slow, costly and error prone.
This webcast will focus on the value of developing holistic reliability program with different reliability assessment tools in Refinery Asset Management to identify top bad actors in refinery units and optimize maintenance strategies; and potential challenges to be faced during the
reliability program implementation.
Geometric shape deviation models constitute an important component in quality control for cyber-physical additive manufacturing (AM) systems. However, specified models have a limited scope of application across the vast spectrum of processes in a system that are characterized by different settings of process variables, and the disparate classes of shapes that are of interest for manufacture.
This webcast will cover the presenters recent published and ongoing work in in-process monitoring of defects, as well as fundamental thermal modeling of metal Additive Manufacturing processes, such as laser powder bed fusion and directed energy deposition.
During this webcast, the intension is to extend that discussion by focusing on how to use data with complicated structures to do reliability analysis. Such data types include high-dimensional sensor data, functional curve data and image streams.
This webinar will cover the fundamentals of accelerated life testing (ALT), types of stresses, load applications, design of test plans and reliability prediction and estimation. Design of equivalent test plans will also be presented.
Earlier known as neural networks, deep learning saw a remarkable resurgence in the past decade. neural networks did not find enough adopters in the past century due to its limited accuracy in real world applications (due to various reasons) and difficult interpretation. Many of these limitations got resolved in the recent years, and it was re-branded as deep learning.
This webinar for IISE student members and potential student members will provide an overview of opportunities for student participation and leadership in IISE, Quality Control and Reliability Engineering (QCRE) related research and education areas.
In this webinar, the presenter will discuss analytical data approaches developed successfully, which reportedly lead to revenue increases for IBM in the range of millions of dollars each quarter, enabling the pricing of solutions in a tiny fraction of the time that this task use to take and in a more accurate and efficient manner, as stated by the VP of global solutions.
This webinar provided an overview of next-generation additive manufacturing (AM) technologies, its capabilities, and research challenges, with particular emphasis on research needs and challenges in process monitoring and quality control.
The discovery of lean production methods used at leading Japanese companies is not a new event. Several American companies that were awarded the Deming Application Prize in the early 1980s by the Union of Japanese Scientists and Engineers (JUSE) had spent significant time studying Japanese management practices related to the process of continual improvement and Hewlett-Packard was one of the pioneers in implementing these methods in its U.S.-based manufacturing facilities in the early 1980s. However, the publication of the MIT study The Machine that Changed the World and other books by academics greatly enhanced the reputation of lean methods and this has caused many organizations to seek productivity improvement through the application of such methods.
Managing for quality requires a systems approach that includes all components of a comprehensive product: hardware, software, service and people processes. Such quality systems are designed using technologies that include: applied statistics, process management, reliability engineering, information systems, and data base management. When problems occur, diagnostic analysis is required to contain the issue as well as develop prompt corrective action as well as effective preventive action to eliminate recurrence of the issue.
Estimation of system reliability is generally based on system structures and component reliability estimates. However, the component reliability estimates are often uncertain due to insufficient failure data or limited testing times, and thus, the associated system reliability estimate exhibits uncertainty as well. The variance is often used to quantify the uncertainty of system reliability estimates. This webinar introduces a non-parametric based modeling approach to estimating the system reliability base on the limited component lifetime data.
This is a two-part webinar series that covers the basics and fundamentals of reliability engineering. Part 1 begins with an introduction of reliability - the definition and reliability characteristics and measurements.
This is the second of a two-part webinar series that covers the basics and fundamentals of reliability engineering. Part 2 covers reliability calculation, estimation of failure rates and understanding of the implications of failure rates on system maintenance and replacements. It will also cover the most important and practical failure time distributions and how to obtain the parameters of the distributions and interpretations of these parameters.