Date of Award
May 2020
Degree Type
Dissertation
Degree Name
Doctor of Philosophy
Department
Engineering
First Advisor
Wilkistar Otieno
Committee Members
Hamid Seifoddini, Matthew Petering, Rohit J Kate, Xiaohang Yue
Keywords
Machine learning, Manufacturing, Quality control, Reinforcement learning, sequential Acceptance sampling
Abstract
In the 21st century, globalization coupled with technological advancement and free trade has created competition among various businesses enterprises. This competition has led many businesses to adopt various management techniques such as acceptance sampling aimed at transforming their processes in order to remain competitive in the global market and adapt to new market demands. The successful implementation of acceptance sampling is highly dependent on what the academic literature refers to as acceptance sampling optimization. A literature review on the optimization of acceptance sampling has not shown any work that studied whether acceptance sampling and machine learning (ML) plans can be considered as an optimal acceptance sampling technique (sequential sampling being one improved acceptance sampling technique). ML algorithms can be divided into four categories: supervised learning, unsupervised learning, semi-supervised learning, and reinforcement learning. Reinforcement learning is different from the other types of machine learning since it is a method of self-learning and acting based on observed data.
The aim of this dissertation is to develop a model based on coupling reinforcement learning methodology (RL) and sequential acceptance sampling in manufacturing to improve and achieve optimality in process and product monitoring. This model will serve as a continuous improvement strategy towards a better acceptance sampling implementation in the manufacturing industry. Simulation has been used as the model for proof of concept. The simulation model is designed to simulate any manufacturing process. However, this dissertation focuses on simulating the inspection process in a production line. In order to determine if an RL-based sequential sampling model is able to reduce the sample size and time of inspection, this dissertation compares the proposed model with the sequential acceptance sampling plan and the MIL-STD 1916
The result of the research will show the integration of sequential sampling and RL as a key to reduce the sample size and the sampling time interval during the inspection process in a manufacturing industry.
Recommended Citation
Khalil, Hani A., "A Reinforcement Learning Approach to Sequential Acceptance Sampling as a Critical Success Factor for Lean Six Sigma" (2020). Theses and Dissertations. 2391.
https://dc.uwm.edu/etd/2391