A Data-Driven Approach for Identifying Possible Manufacturing Processes and Production Parameters That Cause Product Defects: A Thin-Film Filter Company Case Study

Jrjung Lyu,Chia Wen Liang,Ping-Shun Chen

doi:10.1109/access.2020.2974535

Abstract

A semiconductor or photoelectric manufacturer faces a more competitive market with small quantities of many products. These products require hundreds of processes for production, thereby generating huge manufacturing data. With the help of the Internet of Things (IoT) technology, the manufacturer can collect manufacturing process data in a timely manner. Due to the massive quantities of manufacturing process data, it has become difficult for manufacturers to determine the causes of product defects, by which machine, and by what manufacturing process (or recipe) parameters. This research proposes a six-step data-driven solution to this problem. The chi-square test of independence, the Apriori algorithm, and the decision tree method identify the process that is generating the defective products and extract rules to identify the lot identification of product defects and their associated manufacturing process parameters. An empirical study was conducted at an optical thin-film filter (TFF) company in Taiwan. Based on the data of the optical TFF production lines, the coating process was identified as the source of the defective products, and the extracted rules were validated and implemented. The product defect rate decreased from 20% to 5%. Hence, the proposed data-driven solution was found to be capable of helping manufacturers enhance their product yield.

Highlights

Global production of thin-film-transistor liquidcrystal displays (TFT-LCD) was mainly carried out in Taiwan, Korea, and Japan
Crucial to the future development of TFT-LCD manufacturers is the integration of automation technology and the Internet of Things (IoT) with historical information, experience, and intelligence serving as the basis for integrating smart factories into an automated production system [2]–[8]
The factory produced thin-film filters (TFFs) that were used in fiber-optic communication devices and precision optics

Summary

Introduction

Global production of thin-film-transistor liquidcrystal displays (TFT-LCD) was mainly carried out in Taiwan, Korea, and Japan. TFT-LCD manufacturers tended to be conservative in production expansion due to the lack of market demand and difficult to earn good profits. Crucial to the future development of TFT-LCD manufacturers is the integration of automation technology and the Internet of Things (IoT) with historical information, experience, and intelligence serving as the basis for integrating smart factories into an automated production system [2]–[8]. The objective is to allow equipment to communicate, collaborate, and make decisions. Equipment can quickly assess a machine’s status through parameter values collected from sensors and using algorithmic rules. Warnings can be sent to process engineers that preventive maintenance should be performed before problems occur, reducing the percentage of defective products Manyika et al [9]

Methods

Results

Conclusion