Big Data Analysis of Manufacturing Processes

The high complexity of manufacturing processes and the continuously growing amount of data lead to excessive demands on the users with respect to process monitoring, data analysis and fault detection. For these reasons, problems and faults are often detected too late, maintenance intervals are chosen too short and optimization potential for higher output and increased energy efficiency is not sufficiently used. A possibility to cope with these challenges is the development of self-learning assistance systems, which identify relevant relationships by observation of complex manufacturing processes so that failures, anomalies and need for optimization are automatically detected. The assistance system developed in the present work accomplishes data acquisition, process monitoring and anomaly detection in industrial and agricultural processes. The assistance system is evaluated in three application cases: Large distillation columns, agricultural harvesting processes and large-scale sorting plants. In this paper, the developed infrastructures for data acquisition in these application cases are described as well as the developed algorithms and initial evaluation results.

[1]  M. Amer,et al.  Nearest-Neighbor and Clustering based Anomaly Detection Algorithms for RapidMiner , 2012 .

[2]  Miriam Schleipen,et al.  The CAEX tool suite - User assistance for the use of standardized plant engineering data exchange , 2010, 2010 IEEE 15th Conference on Emerging Technologies & Factory Automation (ETFA 2010).

[3]  Oliver Niggemann,et al.  MapReduce algorithms for efficient generation of CPS models from large historical data sets , 2015, 2015 IEEE 20th Conference on Emerging Technologies & Factory Automation (ETFA).

[4]  Hans-Peter Kriegel,et al.  LOF: identifying density-based local outliers , 2000, SIGMOD 2000.

[5]  Oliver Niggemann,et al.  A generic synchronized data acquisition solution for distributed automation systems , 2012, Proceedings of 2012 IEEE 17th International Conference on Emerging Technologies & Factory Automation (ETFA 2012).

[6]  Charu C. Aggarwal,et al.  Outlier Analysis , 2013, Springer New York.

[7]  Oliver Niggemann,et al.  A stochastic method for the detection of anomalous energy consumption in hybrid industrial systems , 2013, 2013 11th IEEE International Conference on Industrial Informatics (INDIN).

[8]  Paulo Leitão,et al.  Agent-based distributed manufacturing control: A state-of-the-art survey , 2009, Eng. Appl. Artif. Intell..

[9]  Benno Stein,et al.  Learning Behavior Models for Hybrid Timed Systems , 2012, AAAI.

[10]  Oliver Niggemann,et al.  Detecting anomalous energy consumptions in distributed manufacturing systems , 2012, IEEE 10th International Conference on Industrial Informatics.

[11]  Peng Li,et al.  Data Driven Modeling for System-Level Condition Monitoring on Wind Power Plants , 2015, DX.

[12]  Sang-Min Park,et al.  Chameleon: a resource scheduler in a data grid environment , 2003, CCGrid 2003. 3rd IEEE/ACM International Symposium on Cluster Computing and the Grid, 2003. Proceedings..

[13]  Clara Pizzuti,et al.  Fast Outlier Detection in High Dimensional Spaces , 2002, PKDD.

[14]  Mathias Uslar,et al.  OPC UA and CIM: Semantics for the smart grid , 2010, IEEE PES T&D 2010.

[15]  Okyay Kaynak,et al.  An LWPR-Based Data-Driven Fault Detection Approach for Nonlinear Process Monitoring , 2014, IEEE Transactions on Industrial Informatics.

[16]  Ashish B. Shah,et al.  Common Object Request Broker Architecture (CORBA) , 2015 .

[17]  Damminda Alahakoon,et al.  Minority report in fraud detection: classification of skewed data , 2004, SKDD.

[18]  C. W. Frey.  Monitoring of complex industrial processes based on self-organizing maps and watershed transformations , 2012, 2012 IEEE International Conference on Industrial Technology.

[19]  Melvin Michael Henry,et al.  Model-based Estimation of Probabilistic Hybrid Automata , 2002 .

[20]  R. Dearden,et al.  Detecting and Learning Unknown Fault States in Hybrid Diagnosis , 2009 .

[21]  Sicco Verwer.  Efficient Identification of Timed Automata: Theory and practice , 2010 .

[22]  Jörg Neidig,et al.  Improved diagnosis by combining structural and process knowledge , 2011, ETFA2011.

[23]  Hans-Peter Kriegel,et al.  LOF: identifying density-based local outliers , 2000, SIGMOD '00.

[24]  Weimin Chen,et al.  Review of fault diagnosis in control systems , 2009, 2009 Chinese Control and Decision Conference.

[25]  Ping Zhang,et al.  A comparison study of basic data-driven fault diagnosis and process monitoring methods on the benchmark Tennessee Eastman process , 2012 .

[26]  Wolfgang Emmerich,et al.  The impact of research on the development of middleware technology , 2008, TSEM.

[27]  Feng Zhao,et al.  Monitoring and fault diagnosis of hybrid systems , 2005, IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics).

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

[29]  Simon Haykin,et al.  Neural Networks and Learning Machines , 2010 .

[30]  Hai Jin,et al.  An adaptive meta-scheduler for data-intensive applications , 2005, Int. J. Grid Util. Comput..

[31]  Alexander Maier,et al.  Online passive learning of timed automata for cyber-physical production systems , 2014, 2014 12th IEEE International Conference on Industrial Informatics (INDIN).

[32]  Hans Kleine Büning,et al.  Identifying behavior models for process plants , 2011, ETFA2011.

[33]  Uwe Brinkschulte,et al.  OSA+ real-time middleware, results and perspectives , 2004, Seventh IEEE International Symposium onObject-Oriented Real-Time Distributed Computing, 2004. Proceedings..

[34]  David G. Stork,et al.  Pattern classification, 2nd Edition , 2000 .

[35]  Christos Faloutsos,et al.  LOCI: fast outlier detection using the local correlation integral , 2003, Proceedings 19th International Conference on Data Engineering (Cat. No.03CH37405).