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

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 datadriven 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. INDEX TERMS Data-driven, data mining, process improvement, association rule mining, decision tree, thin-film filter (TFF).

Artificial intelligence and internet of things in manufacturing decision processes

“…We have summarized 41 articles that do not specify specific industries in the discussion. While the rest of the articles defined specific industries, and this review categorized them into 14 types of industries, such as aero-engine [43], automotive [32], [33], electronics [23], [39], [77], fast-moving consumer goods [69], garment [30], machining [62], [67], [68], [76], [80], [82], metallurgies [78], [79], [63], milling [26], [59] and gas [50], semiconductor [49], water treatment plant [73], tobacco [86], transportation [54], small-medium enterprises [52]. The correlation between IoT and AI technologies with the categorized industries type is shown in Figure 5.…”

Ranking routes in semiconductor wafer fabs

“…Lyu et al 11 propose using the chi-square test of independence, the Apriori algorithm, and the decision tree method identify the sub-process causing defective products and extract rules to identify the lot identification of product defects and their associated manufacturing process parameters. For the analysis they use Internet of Things (IoT) technology to collect manufacturing data.…”

Fault Location of Strip Steel Surface Quality Defects on Hot-Rolling Production Line Based on Information Fusion of Historical Cases and Process Data

“…Sun et al [13] proposed a production line fault diagnosis and maintenance decision system based on human-machine multiinformation fusion, and used multi-source data to conduct the final fault location. Lyu et al [14] proposed a six-step datadriven solution with decision tree and associate rules to determine the causes of product defects and the product defect rate decreased from 20% to 5%. And Pei et al [15] contributed to the fault discovery by proposing an integrated approach combining the Taguchi quality loss function (QLF), the signalnoise ratio (SNR), and the relief method.…”