An online machine learning framework for early detection of product failures in an Industry 4.0 context

ABSTRACT Current paradigms such as the Internet of Things (IoT) and cyber-physical systems are transforming production environments, where related processes are not only faster and with higher standards, but also more flexible and adaptable to changes in the environment. To address the ever-increasing flexibility requirements while keeping current production standards, a new set of technologies is needed. This paper presents an IoT machine learning and orchestration framework, applied to detection of failures of surface mount devices during production. The paper shows how to build a scalable and flexible system for real-time, online machine learning. Furthermore, the approach is evaluated by using a novel and realistic simulation of a production line for electronic devices as a case study. The system evaluation is done in a holistic manner by analyzing various aspects involving the software architecture, computational scalability, model accuracy, production performance, among others.

[1]  Martín Abadi,et al.  TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systems , 2016, ArXiv.

[2]  Yan Baoping,et al.  Efficient Complex Event Processing over RFID Data Stream , 2008, Seventh IEEE/ACIS International Conference on Computer and Information Science (icis 2008).

[3]  Oksana Mont,et al.  Clarifying the Concept of Product-Service System , 2002 .

[4]  Wolfgang Mahnke,et al.  OPC Unified Architecture , 2009, Autom..

[5]  Mohamed Medhat Gaber,et al.  On-board Mining of Data Streams in Sensor Networks , 2005 .

[6]  Grantham K. H. Pang,et al.  Solder paste inspection using region-based defect detection , 2008 .

[7]  Michael B. Jones,et al.  JSON Web Signature (JWS) , 2015, RFC.

[8]  Steffen Kunz,et al.  Managing Complex Event Processes with Business Process Modeling Notation , 2010, BPMN.

[9]  Jesús S. Aguilar-Ruiz,et al.  Knowledge discovery from data streams , 2009, Intell. Data Anal..

[10]  P. A. Hayek,et al.  Production lot sizing with the reworking of imperfect quality items produced , 2001 .

[11]  Ajay Kumar,et al.  Neural network based detection of local textile defects , 2003, Pattern Recognit..

[12]  Marcello Pellicciari,et al.  Engineering method for adaptive manufacturing systems design , 2009 .

[13]  Charu C. Aggarwal,et al.  Data Streams - Models and Algorithms , 2014, Advances in Database Systems.

[14]  Jaume Escofet,et al.  Detection of local defects in textile webs using Gabor filters , 1998 .

[15]  Dario Bonino,et al.  ALMANAC: Internet of Things for Smart Cities , 2015, 2015 3rd International Conference on Future Internet of Things and Cloud.

[16]  Aydin Nassehi,et al.  STEP-NC compliant process planning as an enabler for adaptive global manufacturing , 2006 .

[17]  Shonali Krishnaswamy,et al.  Mining data streams: a review , 2005, SGMD.

[18]  Da-Wen Sun,et al.  Inspection and grading of agricultural and food products by computer vision systems—a review , 2002 .

[19]  Gaël Varoquaux,et al.  The NumPy Array: A Structure for Efficient Numerical Computation , 2011, Computing in Science & Engineering.

[20]  Jürgen Schmidhuber,et al.  Transfer learning for Latin and Chinese characters with Deep Neural Networks , 2012, The 2012 International Joint Conference on Neural Networks (IJCNN).

[21]  D. Luckham.  Event Processing for Business: Organizing the Real-Time Enterprise , 2011 .

[22]  Peter Muchiri,et al.  Performance measurement using overall equipment effectiveness (OEE): literature review and practical application discussion , 2008 .

[23]  Roger A. Light.  Mosquitto: server and client implementation of the MQTT protocol , 2017, J. Open Source Softw..

[24]  Oliver Niggemann,et al.  Anomaly Detection in Production Plants using Timed Automata - Automated Learning of Models from Observations , 2011, ICINCO.

[25]  Fei-Long Chen,et al.  A neural-network approach to recognize defect spatial pattern in semiconductor fabrication , 2000 .

[26]  Opher Etzion,et al.  Complex event processing , 2004, Proceedings. IEEE International Conference on Web Services, 2004..

[27]  Til Aach,et al.  Improved minimum distance classification with Gaussian outlier detection for industrial inspection , 2001, Proceedings 11th International Conference on Image Analysis and Processing.

[28]  A. J. De Ron,et al.  OEE and equipment effectiveness: an evaluation , 2006 .

[29]  S. Barnes,et al.  Adaptive manufacturing scheduling: a flexible and configurable agent-based prototype , 2005 .

[30]  Davy Preuveneers,et al.  CEML: Mixing and moving complex event processing and machine learning to the edge of the network for IoT applications , 2016, IOT.

[31]  M.-H.C. Li,et al.  DMAIC Approach to Improve the Capability of SMT Solder Printing Process , 2008, IEEE Transactions on Electronics Packaging Manufacturing.

[32]  Andreas Meyer,et al.  Model-Driven Event Query Generation for Business Process Monitoring , 2013, ICSOC Workshops.

[33]  Singa Wang Chiu,et al.  Determining the optimal run time for EPQ model with scrap, rework, and stochastic breakdowns , 2007, Eur. J. Oper. Res..

[34]  Eric Jones,et al.  SciPy: Open Source Scientific Tools for Python , 2001 .

[35]  Duc Truong Pham,et al.  Machine-learning techniques and their applications in manufacturing , 2005 .

[36]  Tak-Wai Hui,et al.  Solder paste inspection using region-based defect detection , 2009 .

[37]  Leo Breiman,et al.  Random Forests , 2001, Machine Learning.

[38]  Hyung Suck Cho,et al.  A neural network approach to the inspection of ball grid array solder joints on printed circuit boards , 2000, Proceedings of the IEEE-INNS-ENNS International Joint Conference on Neural Networks. IJCNN 2000. Neural Computing: New Challenges and Perspectives for the New Millennium.

[39]  Frank Steiner,et al.  Mass Customization at Adidas: Three Strategic Capabilities to Implement Mass Customization , 2012 .

[40]  Marco Jahn,et al.  Enabling Smart Cities through IoT: The ALMANAC Way , 2017 .

[41]  László Monostori,et al.  ScienceDirect Variety Management in Manufacturing . Proceedings of the 47 th CIRP Conference on Manufacturing Systems Cyber-physical production systems : Roots , expectations and R & D challenges , 2014 .

[42]  Du-Ming Tsai,et al.  An eigenvalue-based similarity measure and its application in defect detection , 2005, Image Vis. Comput..

[43]  Clemens Heinrich,et al.  Transport Layer Security (TLS) , 2011, Encyclopedia of Cryptography and Security.

[44]  Matthias Damm,et al.  OPC Unified Architecture , 2009, Autom..

[45]  约瑟夫·L·比莱利亚.  Electronic assembly video inspection system , 1998 .

[46]  John Salvatier,et al.  Theano: A Python framework for fast computation of mathematical expressions , 2016, ArXiv.

[47]  Paulo Leitão,et al.  ADACOR: A holonic architecture for agile and adaptive manufacturing control , 2006, Comput. Ind..

[48]  Sam Newman,et al.  Building microservices - designing fine-grained systems, 1st Edition , 2015 .

[49]  Young Shik Moon,et al.  Visual inspection system for the classification of solder joints , 1999, Pattern Recognit..

[50]  Margaret Fisher.  Application programming interface , 2006 .

[51]  Gaël Varoquaux,et al.  Scikit-learn: Machine Learning in Python , 2011, J. Mach. Learn. Res..

[52]  Sam Ruby,et al.  RESTful Web Services , 2007 .

[53]  Mohammed Bennamoun,et al.  Optimal Gabor filters for textile flaw detection , 2002, Pattern Recognit..

[54]  Roger Calantone,et al.  Performance and time to market: accelerating cycle time with overlapping stages , 2000, IEEE Trans. Engineering Management.

[55]  Jianbing Wu,et al.  Design and Realization of General Interface Based on Object Linking and Embedding for Process Control , 2014 .

[56]  Hans-Peter Wiendahl,et al.  Changeable and Reconfigurable Assembly Systems , 2009 .

[57]  L. Bottou.  Stochastic Gradient Learning in Neural Networks , 1991 .

[58]  Maurizio A. Spirito,et al.  Towards a Federation of Smart City Services. , 2016 .

[59]  Kagermann Henning.  Recommendations for implementing the strategic initiative INDUSTRIE 4.0 , 2013 .

[60]  CugolaGianpaolo,et al.  Processing flows of information , 2012 .

[61]  Yuan-Shyi Peter Chiu,et al.  Optimal run time for EPQ model with scrap, rework and stochastic breakdowns: A note , 2014 .

[62]  Andreas Meyer,et al.  BPMN extension for business process monitoring , 2014, EMISA.

[63]  Andrei Lobov,et al.  OPC-UA and DPWS interoperability for factory floor monitoring using complex event processing , 2011, 2011 9th IEEE International Conference on Industrial Informatics.

[64]  Zsolt János Viharos,et al.  Vision based, statistical learning system for fault recognition in industrial assembly environment , 2016, 2016 IEEE 21st International Conference on Emerging Technologies and Factory Automation (ETFA).

[65]  Weikang Gu,et al.  Computer vision based system for apple surface defect detection , 2002 .

[66]  Boris Otto,et al.  Design Principles for Industrie 4.0 Scenarios , 2016, 2016 49th Hawaii International Conference on System Sciences (HICSS).

[67]  V. Vyatkin,et al.  Now That's Smart! , 2007, IEEE Industrial Electronics Magazine.

[68]  Jaume Escofet,et al.  Detection of local defects in textile webs using Gabor filters , 1996, Other Conferences.

[69]  Gkh Pang,et al.  Erratum: Solder paste inspection using region-based defect detection (International Journal of Advanced Manufacturing Technology DOI 10.1007/s00170-008-1639-6) , 2009 .

[70]  Giuseppe Acciani,et al.  Application of neural networks in optical inspection and classification of solder joints in surface mount technology , 2006, IEEE Transactions on Industrial Informatics.

[71]  Giovani J.C. da Silveira,et al.  The mass customization decade: An updated review of the literature , 2012 .

[72]  Maged M. Michael,et al.  Scale-up x Scale-out: A Case Study using Nutch/Lucene , 2007, 2007 IEEE International Parallel and Distributed Processing Symposium.

[73]  Samuel H. Huang,et al.  Manufacturing productivity improvement using effectiveness metrics and simulation analysis , 2003 .

[74]  Hui-Ming Wee,et al.  Multi-product production quantity model with repair failure and partial backordering , 2010, Comput. Ind. Eng..

[75]  Jay Lee,et al.  A Cyber-Physical Systems architecture for Industry 4.0-based manufacturing systems , 2015 .

[76]  Eric Rescorla,et al.  The Transport Layer Security (TLS) Protocol Version 1.2 , 2008, RFC.

[77]  Geoff Holmes,et al.  Active Learning With Drifting Streaming Data , 2014, IEEE Transactions on Neural Networks and Learning Systems.

[78]  J. Sola,et al.  Importance of input data normalization for the application of neural networks to complex industrial problems , 1997 .

[79]  Dávid Gyulai,et al.  Industry 4.0: Mining Physical Defects in Production of Surface-Mount Devices , 2017 .

[80]  Alessandro Margara,et al.  Processing flows of information: From data stream to complex event processing , 2012, CSUR.