EAS-PHD Proposal Defense by Yabo Han
When: Wednesday,
August 21, 2019
10:00 AM
-
12:00 PM
Where: Textiles Building 105
Description: TITLE : Statistical Quality Control: Construction of Multivariate Control Chart and
Statistical GD&T Verification
DATE: Wednesday, August 21, 2019
TIME: 10 AM
LOCATION: TXT-105
Abstract:
Quality monitoring and control in design and manufacturing pose humongous challenges in case when multivariate non-normal processes involved. For quality monitoring in manufacturing, a model-free method for multivariate process control (MSPC) is initially proposed and developed. Adaptive Kernel Density Estimation directly learns the density distribution from data and Metropolis-Hastings algorithm generates large samples for control chart construction. The MSPC method is designed for both monitoring and diagnosis when the out-of-control signal is trigged. In design, GD&T tolerance verification involves complex geometric variation propagation analysis of assembly composed of components and their mating of toleranced surfaces that are characterized by multivariate statistical rough surface models. A two step method is developed to initially predict assembly's variation with rigid random contact algorithm and then a GD&T tolerance verification method based on predictive confidence region concept is proposed. The effectiveness of both methods are verified through case study and simulations.
The proposed MSPC method avoids inevitable difficulties in generic parametric model estimation with an automatic and adaptive model learning algorithm and in small initial sample case. The GD&T assembly model and verification method creates a platform for analyzing variation propagation among random surfaces in assembly and verification of GD&T tolerances with statistical inferences that are impossible with conventional deterministic models.
Advisor: Dr. Wenzhen Huang, Department of Mechanical Engineering
Committee members: Dr. Jianyi Jay Wang, Department of Physics; Dr. Jun Li, Department of Mechanical Engineering and Dr. Bharatendra K. Rai, Department of Decision & Information Sciences
All EAS students are encouraged to attend and all interested parties invited.
For further information, please contact Dr. Wenzhen Huang or by email whuang@umassd.edu
Statistical GD&T Verification
DATE: Wednesday, August 21, 2019
TIME: 10 AM
LOCATION: TXT-105
Abstract:
Quality monitoring and control in design and manufacturing pose humongous challenges in case when multivariate non-normal processes involved. For quality monitoring in manufacturing, a model-free method for multivariate process control (MSPC) is initially proposed and developed. Adaptive Kernel Density Estimation directly learns the density distribution from data and Metropolis-Hastings algorithm generates large samples for control chart construction. The MSPC method is designed for both monitoring and diagnosis when the out-of-control signal is trigged. In design, GD&T tolerance verification involves complex geometric variation propagation analysis of assembly composed of components and their mating of toleranced surfaces that are characterized by multivariate statistical rough surface models. A two step method is developed to initially predict assembly's variation with rigid random contact algorithm and then a GD&T tolerance verification method based on predictive confidence region concept is proposed. The effectiveness of both methods are verified through case study and simulations.
The proposed MSPC method avoids inevitable difficulties in generic parametric model estimation with an automatic and adaptive model learning algorithm and in small initial sample case. The GD&T assembly model and verification method creates a platform for analyzing variation propagation among random surfaces in assembly and verification of GD&T tolerances with statistical inferences that are impossible with conventional deterministic models.
Advisor: Dr. Wenzhen Huang, Department of Mechanical Engineering
Committee members: Dr. Jianyi Jay Wang, Department of Physics; Dr. Jun Li, Department of Mechanical Engineering and Dr. Bharatendra K. Rai, Department of Decision & Information Sciences
All EAS students are encouraged to attend and all interested parties invited.
For further information, please contact Dr. Wenzhen Huang or by email whuang@umassd.edu
Contact: EAS Seminar Series
Topical Areas: University Community, College of Engineering, Mechanical Engineering