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

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.

[1]  Chen-Fu Chien,et al.  Analysing semiconductor manufacturing big data for root cause detection of excursion for yield enhancement , 2017, Int. J. Prod. Res..

[2]  Ying-Jen Chen,et al.  Manufacturing intelligence for reducing false alarm of defect classification by integrating similarity matching approach in CMOS image sensor manufacturing , 2016, Comput. Ind. Eng..

[3]  Anders Skoogh,et al.  A data-driven algorithm to predict throughput bottlenecks in a production system based on active periods of the machines , 2018, Comput. Ind. Eng..

[4]  Chen-Fu Chien,et al.  Feature extraction for defect classification and yield enhancement in color filter and micro-lens manufacturing: An empirical study , 2013 .

[5]  Ray Y. Zhong,et al.  Big Data for supply chain management in the service and manufacturing sectors: Challenges, opportunities, and future perspectives , 2016, Comput. Ind. Eng..

[6]  Tomasz Imielinski,et al.  Mining association rules between sets of items in large databases , 1993, SIGMOD Conference.

[7]  Armin Shmilovici,et al.  Data mining for improving a cleaning process in the semiconductor industry , 2002 .

[8]  A. Casali,et al.  Discovering Correlated Parameters in Semiconductor Manufacturing Processes: A Data Mining Approach , 2012, IEEE Transactions on Semiconductor Manufacturing.

[9]  K.K.-W. Tu,et al.  A Novel Statistical Method for Automatically Partitioning Tools According to Engineers' Tolerance Control in Process Improvement , 2009, IEEE Transactions on Semiconductor Manufacturing.

[10]  Jiafu Wan,et al.  Cloud-Assisted Cyber-Physical Systems for the Implementation of Industry 4.0 , 2017, Mob. Networks Appl..

[11]  Ashraf A. Afify,et al.  A fuzzy rule induction algorithm for discovering classification rules , 2016, J. Intell. Fuzzy Syst..

[12]  Alun D. Preece,et al.  Dynamically reconfigurable workflows for time-critical applications , 2015, WORKS@SC.

[13]  Jieping Ye,et al.  Multifeature, Sparse-Based Approach for Defects Detection and Classification in Semiconductor Units , 2018, IEEE Transactions on Automation Science and Engineering.

[14]  Lei Ren,et al.  Real-Time Scheduling of Cloud Manufacturing Services Based on Dynamic Data-Driven Simulation , 2019, IEEE Transactions on Industrial Informatics.

[15]  J. Ross Quinlan,et al.  Induction of Decision Trees , 1986, Machine Learning.

[16]  Petri T. Helo,et al.  Big data applications in operations/supply-chain management: A literature review , 2016, Comput. Ind. Eng..

[17]  Chen-Fu Chien,et al.  建構模糊決策樹及其在有交互作用之半導體資料之資料挖礦以提昇良率之研究; Construct Fuzzy Decision Tree for Mining Interrelated Semiconductor Manufacturing Data for Yield Enhancement , 2008 .

[18]  Flávia Maria Santoro,et al.  A method to infer the need to update situations in business process adaptation , 2015, Comput. Ind..

[19]  M. Y. Huang,et al.  Constructing credit auditing and control & management model with data mining technique , 2011, Expert Syst. Appl..

[20]  Sérgio Moro,et al.  Unfolding the relations between companies and technologies under the Big Data umbrella , 2018, Comput. Ind..

[21]  Chen-Fu Chien,et al.  ANALYZING TFT-LCD ARRAY BIG DATA FOR YIELD ENHANCEMENT AND AN EMPIRICAL STUDY OF TFT-LCD MANUFACTURING IN TAIWAN , 2017 .

[22]  Christoph M. Flath,et al.  Towards a data science toolbox for industrial analytics applications , 2018, Comput. Ind..

[23]  Lihui Wang,et al.  Scheduling in cloud manufacturing: state-of-the-art and research challenges , 2019, Int. J. Prod. Res..

[24]  Ryohei Orihara,et al.  A Comprehensive Big-Data-Based Monitoring System for Yield Enhancement in Semiconductor Manufacturing , 2017, IEEE Transactions on Semiconductor Manufacturing.

[25]  In-Jeong Chung,et al.  A real time process management system using RFID data mining , 2014, Comput. Ind..

[26]  Lina Zhou,et al.  RubE: Rule-based methods for extracting product features from online consumer reviews , 2017, Inf. Manag..

[27]  Pierre Bect,et al.  Identification of abnormal events by data monitoring: Application to complex systems , 2015, Comput. Ind..

[28]  Ian Taylor,et al.  SWITCH workbench: A novel approach for the development and deployment of time-critical microservice-based cloud-native applications , 2019, Future Gener. Comput. Syst..

[29]  Ryohei Orihara,et al.  A comprehensive “big-data-based” monitoring system for yield enhancement in semiconductor man ufacturing , 2016, 2016 International Symposium on Semiconductor Manufacturing (ISSM).

[30]  Martha Mendoza,et al.  CMIN — a CRISP-DM-based case tool for supporting data mining projects , 2010 .

[31]  Wei-Yin Loh,et al.  A Comparison of Prediction Accuracy, Complexity, and Training Time of Thirty-Three Old and New Classification Algorithms , 2000, Machine Learning.

[32]  Lin Li,et al.  Industrial Big Data in an Industry 4.0 Environment: Challenges, Schemes, and Applications for Predictive Maintenance , 2017, IEEE Access.

[33]  Davy Preuveneers,et al.  The intelligent industry of the future: A survey on emerging trends, research challenges and opportunities in Industry 4.0 , 2017, J. Ambient Intell. Smart Environ..

[34]  Argon Chen,et al.  Sample-Efficient Regression Trees (SERT) for Semiconductor Yield Loss Analysis , 2010, IEEE Transactions on Semiconductor Manufacturing.

[35]  Ya Chen,et al.  A hybrid data envelopment analysis approach to analyse college graduation rate at higher education institutions , 2017, INFOR Inf. Syst. Oper. Res..

[36]  A. Afify.  A novel algorithm for fuzzy rule induction in data mining , 2014 .

[37]  J. Ross Quinlan,et al.  Improved Use of Continuous Attributes in C4.5 , 1996, J. Artif. Intell. Res..

[38]  Francis Rousseaux,et al.  BIG DATA and Data-Driven Intelligent Predictive Algorithms to support creativity in Industrial Engineering , 2017, Comput. Ind. Eng..

[39]  Grace T. R. Lin,et al.  Measuring Dynamic Operation Efficiency for Universal Top 10 TFT-LCDs by Improved Data Envelopment Analysis , 2018 .

[40]  Rajkumar Buyya,et al.  Big Data computing and clouds: Trends and future directions , 2013, J. Parallel Distributed Comput..

[41]  Marko Bohanec,et al.  Decision-making framework with double-loop learning through interpretable black-box machine learning models , 2017, Ind. Manag. Data Syst..

[42]  A. R. Crathorne,et al.  Economic Control of Quality of Manufactured Product. , 1933 .

[43]  Chen-Fu Chien,et al.  Data Mining for Optimizing IC Feature Designs to Enhance Overall Wafer Effectiveness , 2014, IEEE Transactions on Semiconductor Manufacturing.

[44]  Padhraic Smyth,et al.  From Data Mining to Knowledge Discovery in Databases , 1996, AI Mag..

[45]  Fernando Alonso,et al.  Cooperation between expert knowledge and data mining discovered knowledge: Lessons learned , 2012, Expert Syst. Appl..

[46]  Armin Shmilovici,et al.  On the use of decision tree induction for discovery of interactions in a photolithographic process , 2003 .

[47]  Wen-Chih Wang,et al.  Data mining for yield enhancement in semiconductor manufacturing and an empirical study , 2007, Expert Syst. Appl..

[48]  Björn Johansson,et al.  A framework for operative and social sustainability functionalities in Human-Centric Cyber-Physical Production Systems , 2020, Comput. Ind. Eng..

[49]  Chen-Fu Chien,et al.  Semiconductor fault detection and classification for yield enhancement and manufacturing intelligence , 2012, Flexible Services and Manufacturing Journal.

[50]  Wen-Chih Wang,et al.  An empirical study of design-of-experiment data mining for yield-loss diagnosis for semiconductor manufacturing , 2013, J. Intell. Manuf..

[51]  Sungzoon Cho,et al.  Mining the relationship between production and customer service data for failure analysis of industrial products , 2017, Comput. Ind. Eng..

[52]  Thomas Reinartz,et al.  CRISP-DM 1.0: Step-by-step data mining guide , 2000 .

[53]  Efendi N. Nasibov,et al.  Performance evaluation of industrial enterprises via fuzzy inference system approach: a case study , 2015, Soft Comput..