ABSTRACT
Manufacturing has enabled the mechanized mass production of the same (or similar) products by replacing craftsmen with assembly lines of machines. The quality of each product in an assembly line greatly hinges on continual observation and error compensation during machining using sensors that measure quantities such as position and torque of a cutting tool and vibrations due to possible imperfections in the cutting tool and raw material. Patterns observed in sensor data from a (near-)optimal production cycle should ideally recur in subsequent production cycles with minimal deviation. Manually labeling and comparing such patterns is an insurmountable task due to the massive amount of streaming data that can be generated from a production process. We present UDAVA, an unsupervised machine learning pipeline that automatically discovers process behavior patterns in sensor data for a reference production cycle. UDAVA performs clustering of reduced dimensionality summary statistics of raw sensor data to enable high-speed clustering of dense time-series data. It deploys the model as a service to verify batch data from subsequent production cycles to detect recurring behavior patterns and quantify deviation from the reference behavior. We have evaluated UDAVA from an AI Engineering perspective using two industrial case studies.
- Saeed Aghabozorgi, Ali Seyed Shirkhorshidi, and Teh Ying Wah. 2015. Time-series clustering-a decade review. Information Systems 53 (2015), 16--38.Google ScholarDigital Library
- Ali Alqahtani, Mohammed Ali, Xianghua Xie, and Mark W Jones. 2021. Deep Time-Series Clustering: A Review. Electronics 10, 23 (2021), 3001.Google Scholar
- Saleema Amershi, Andrew Begel, Christian Bird, Robert DeLine, Harald Gall, Ece Kamar, Nachiappan Nagappan, Besmira Nushi, and Thomas Zimmermann. 2019. Software engineering for machine learning: A case study. In 2019 IEEE/ACM 41st International Conference on Software Engineering: Software Engineering in Practice (ICSE-SEIP). IEEE, 291--300.Google ScholarDigital Library
- Nagdev Amruthnath and Tarun Gupta. 2018. A research study on unsupervised machine learning algorithms for early fault detection in predictive maintenance. In 2018 5th International Conference on Industrial Engineering and Applications (ICIEA). IEEE, 355--361.Google ScholarCross Ref
- Angelos Angelopoulos, Emmanouel T Michailidis, Nikolaos Nomikos, Panagiotis Trakadas, Antonis Hatziefremidis, Stamatis Voliotis, and Theodore Zahariadis. 2020. Tackling faults in the industry 4.0 era---a survey of machine-learning solutions and key aspects. Sensors 20, 1 (2020), 109.Google ScholarCross Ref
- Moslem Azamfar, Xiang Li, and Jay Lee. 2020. Deep learning-based domain adaptation method for fault diagnosis in semiconductor manufacturing. IEEE Transactions on Semiconductor Manufacturing 33, 3 (2020), 445--453.Google ScholarCross Ref
- Jan Bosch, Helena Holmström Olsson, and Ivica Crnkovic. 2021. Engineering AI systems: A research agenda. In Artificial Intelligence Paradigms for Smart Cyber-Physical Systems. IGI Global, 1--19.Google Scholar
- YUE Caixu, GAO Haining, LIU Xianli, Steven Y Liang, and WANG Lihui. 2019. A review of chatter vibration research in milling. Chinese Journal of Aeronautics 32, 2 (2019), 215--242.Google ScholarCross Ref
- Chieh-Yu Chen, Shi-Chung Chang, and Da-Yin Liao. 2020. Equipment Anomaly Detection for Semiconductor Manufacturing by Exploiting Unsupervised Learning from Sensory Data. Sensors 20, 19 (2020), 5650.Google ScholarCross Ref
- Yizong Cheng. 1995. Mean shift, mode seeking, and clustering. IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE (1995).Google Scholar
- Chia-Shang James Chu. 1995. Time series segmentation: A sliding window approach. Information Sciences 85, 1-3 (1995), 147--173.Google Scholar
- Code Carbon. [n.d.]. https://codecarbon.io/. Visited in 2022.Google Scholar
- A Del Olmo, G Martínez de Pissón, L Sastoque, A Fernández, A Calleja, and LN López De Lacalle. 2021. Merging complex information in high speed broaching operations in order to obtain a robust machining process. In IOP Conference Series: Materials Science and Engineering, Vol. 1193. IOP Publishing, 012079.Google Scholar
- Hui Ding, Goce Trajcevski, Peter Scheuermann, Xiaoyue Wang, and Eamonn Keogh. 2008. Querying and mining of time series data: experimental comparison of representations and distance measures. Proceedings of the VLDB Endowment 1, 2 (2008), 1542--1552.Google ScholarDigital Library
- Alican Dog6an and Derya Birant. 2021. Machine learning and data mining in manufacturing. Expert Systems with Applications 166 (2021), 114060.Google ScholarCross Ref
- David H Evans. 1975. Statistical Tolerancing: The State of the Art: Part III. Shifts and Drifts. Journal of Quality Technology 7, 2 (1975), 72--76.Google ScholarCross Ref
- Tak-chung Fu. 2011. A review on time series data mining. Engineering Applications of Artificial Intelligence 24, 1 (2011), 164--181.Google ScholarDigital Library
- K. Fukunaga and L. Hostetler. 1975. The estimation of the gradient of a density function, with applications in pattern recognition. IEEE Transactions on Information Theory 21, 1 (1975), 32--40. Google ScholarDigital Library
- Ning Ge, Guanghao Li, Li Zhang, and Yi Liu. 2021. Failure prediction in production line based on federated learning: an empirical study. Journal of Intelligent Manufacturing (2021), 1--18.Google Scholar
- Great Expectations. [n.d.]. https://greatexpectations.io/. Visited in 2022.Google Scholar
- iterative.ai. [n.d.]. Open-source Version Control System for Machine Learning Projects. https://dvc.org/. Visited in 2022.Google Scholar
- ITP Aero. [n.d.]. https://www.itpaero.com/. Visited in 2022.Google Scholar
- Mustafa Kuntoğlu, Emin Salur, Munish Kumar Gupta, Murat Sarıkaya, and Danil Yu Pimenov. 2021. A state-of-the-art review on sensors and signal processing systems in mechanical machining processes. The International Journal of Advanced Manufacturing Technology 116, 9 (2021), 2711--2735.Google ScholarCross Ref
- Ruslan Kuprieiev, Dmitry Petrov, Pawel Redzyński, Saugat Pachhai, Casper da Costa-Luis, Alexander Schepanovski, Peter Rowlands, Ivan Shcheklein, Jorge Orpinel, Fábio Santos, Aman Sharma, Zhanibek, Gao, Batuhan Taskaya, Dani Hodovic, Andrew Grigorev, Earl, Nabanita Dash, nik123, George Vyshnya, maykulkarni, Max Hora, Vera, Sanidhya Mangal, Wojciech Baranowski, Clemens Wolff, Alex Maslakov, Alex Khamutov, Kurian Benoy, and Ophir Yoktan. 2021. DVC: Data Version Control - Git for Data & Models. Google ScholarCross Ref
- Hongbin Liu, Mingzhi Huang, Iman Janghorban, Payam Ghorbannezhad, and ChangKyoo Yoo. 2011. Faulty sensor detection, identification and reconstruction of indoor air quality measurements in a subway station. In 2011 11th International Conference on Control, Automation and Systems. IEEE, 323--328.Google Scholar
- Mika Liukkonen and Yrjö Hiltunen. 2018. Recognition of systematic spatial patterns in silicon wafers based on SOM and K-means. IFAC-PapersOnLine 51, 2 (2018), 439--444.Google ScholarCross Ref
- Jon Loeliger and Matthew McCullough. 2012. Version Control with Git: Powerful tools and techniques for collaborative software development. "O'Reilly Media, Inc.".Google Scholar
- J. Macqueen. 1967. Some methods for classification and analysis of multivariate observations. In In 5-th Berkeley Symposium on Mathematical Statistics and Probability. 281--297.Google Scholar
- AB Martins, JT Farinha, and AM Cardoso. 2020. Calibration and Certification of Industrial Sensors---A Global Review. WSEAS Trans. Syst. Control (2020), 394--416.Google Scholar
- Benjamin Maschler, Hannes Vietz, Nasser Jazdi, and Michael Weyrich. 2020. Continual learning of fault prediction for turbofan engines using deep learning with elastic weight consolidation. In 2020 25th IEEE international conference on emerging technologies and factory automation (ETFA), Vol. 1. IEEE, 959--966.Google ScholarCross Ref
- Meinard Müller. 2007. Dynamic time warping. Information retrieval for music and motion (2007), 69--84.Google ScholarDigital Library
- F. Pedregosa, G. Varoquaux, A. Gramfort, V. Michel, B. Thirion, O. Grisel, M. Blondel, P. Prettenhofer, R. Weiss, V. Dubourg, J. Vanderplas, A. Passos, D. Cournapeau, M. Brucher, M. Perrot, and E. Duchesnay. 2011. Scikit-learn: Machine Learning in Python. Journal of Machine Learning Research 12 (2011), 2825--2830.Google ScholarDigital Library
- Ioannis Prapas, Behrouz Derakhshan, Alireza Rezaei Mahdiraji, and Volker Markl. 2021. Continuous Training and Deployment of Deep Learning Models. Datenbank-Spektrum 21, 3 (2021), 203--212.Google ScholarCross Ref
- Predict. [n.d.]. https://www.predict.fr/produits-services/logiciels/. Visited in 2022.Google Scholar
- Renault Assembly Plant. [n.d.]. https://www.renaultgroup.com/en/our-company/locations/valladolid-bodywork-assembly-plant-2/. Visited in 2022.Google Scholar
- SAVVY Data Systems. [n.d.]. https://www.savvydatasystems.com/es/inicio. Visited in 2022.Google Scholar
- D. Sculley. 2010. Web-scale k-means clustering. In Proceedings of the 19th international conference on World wide web - WWW '10. ACM Press. Google ScholarDigital Library
- David Sculley, Gary Holt, Daniel Golovin, Eugene Davydov, Todd Phillips, Dietmar Ebner, Vinay Chaudhary, Michael Young, Jean-Francois Crespo, and Dan Dennison. 2015. Hidden technical debt in machine learning systems. Advances in neural information processing systems 28 (2015), 2503--2511.Google Scholar
- Krishna Kumar Sharma and Ayan Seal. 2021. Outlier-robust multi-view clustering for uncertain data. Knowledge-Based Systems 211 (2021), 106567.Google ScholarCross Ref
- Carla Silva, Marvin F da Silva, Arlete Rodrigues, José Silva, Vítor Santos Costa, Alipio Jorge, and Iněs Dutra. 2021. Predictive Maintenance for Sensor Enhancement in Industry 4.0. In Asian Conference on Intelligent Information and Database Systems. Springer, 403--415.Google ScholarCross Ref
- Ashish Singhal and Dale E Seborg. 2005. Clustering multivariate time-series data. Journal of Chemometrics: A Journal of the Chemometrics Society 19, 8 (2005), 427--438.Google ScholarCross Ref
- Dimla E Dimla Snr. 2000. Sensor signals for tool-wear monitoring in metal cutting operations---a review of methods. International Journal of Machine Tools and Manufacture 40, 8 (2000), 1073--1098.Google ScholarCross Ref
- Hugo Steinhaus et al. 1956. Sur la division des corps materiels en parties. Bull. Acad. Polon. Sci 1, 804 (1956), 801.Google Scholar
- Ye Tian, Zili Wang, and Chen Lu. 2019. Self-adaptive bearing fault diagnosis based on permutation entropy and manifold-based dynamic time warping. Mechanical Systems and Signal Processing 114 (2019), 658--673.Google ScholarCross Ref
- Laurens Van Der Maaten, Eric Postma, Jaap Van den Herik, et al. 2009. Dimensionality reduction: a comparative review. Journal of Machine Learning Research 10, 66--71 (2009), 13.Google Scholar
- Ethan Wescoat, Matthew Krugh, Andrew Henderson, Josh Goodnough, and Laine Mears. 2019. Vibration analysis utilizing unsupervised learning. Procedia Manufacturing 34 (2019), 876--884.Google ScholarCross Ref
- Michael Wocker, Naomi Kimberly Betz, Christian Feuersanger, Alexander Lindworsky, and Jochen Deuse. 2020. Unsupervised learning for opportunistic maintenance optimization in flexible manufacturing systems. Procedia CIRP 93 (2020), 1025--1030.Google ScholarCross Ref
- Zhengzheng Xing, Jian Pei, and Eamonn Keogh. 2010. A brief survey on sequence classification. ACM Sigkdd Explorations Newsletter 12, 1 (2010), 40--48.Google ScholarDigital Library
- Hamdi Yahyaoui and Aisha Al-Mutairi. 2016. A feature-based trust sequence classification algorithm. Information Sciences 328 (2016), 455--484.Google ScholarDigital Library
- Kaichao You, Mingsheng Long, Zhangjie Cao, Jianmin Wang, and Michael I Jordan. 2019. Universal domain adaptation. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. 2720--2729.Google ScholarCross Ref
- Jiaping Zhao and Laurent Itti. 2018. shapedtw: Shape dynamic time warping. Pattern Recognition 74 (2018), 171--184.Google ScholarDigital Library
Recommendations
Effect of Modern Information Industry on Manufacturing Industry
AIAM2021: 2021 3rd International Conference on Artificial Intelligence and Advanced ManufactureThe transformation and upgrading of the manufacturing sector is an important step in implementing the new stage of development. Information technology is having an increasingly profound impact on the development of manufacturing industry, based on this ...
Manufacturing Execution System for a Subsidiary of Aerospace Manufacturing Industry
ICCAE '09: Proceedings of the 2009 International Conference on Computer and Automation EngineeringAbstract—Aerospace manufacturing requires precision tools and control systems. Integrated Manufacturing Execution System (MES) in a subsidiary of aerospace manufacturing industry initiate, guide, respond to and report on manufacturing activities as they ...
Comments