Machine Learning Use Cases for Smart Manufacturing KPIs

In this paper, we present methods for prediction of key performance indicators relating to a manufacturing environment. This work represents a current snapshot of machine learning methods that are being used to provide actionable insight into events that may affect the following three indicators: number of units produced, number of defects per unit, and amount of rework time per defect.

[1]  Jürgen Schmidhuber,et al.  Long Short-Term Memory , 1997, Neural Computation.

[2]  Luca Antiga,et al.  Automatic differentiation in PyTorch , 2017 .

[3]  László Monostori,et al.  Machine Learning Approaches to Manufacturing , 1996 .

[4]  Yang Wang,et al.  Cost-sensitive boosting for classification of imbalanced data , 2007, Pattern Recognit..

[5]  Ken Kennedy,et al.  Automotive big data , 2013, 2013 IEEE International Conference on Cluster Computing (CLUSTER).

[6]  Chris Hakes.  The EFQM Excellence Model to Assess Organizational Performance - A Management Guide , 2007 .

[7]  Ken Kennedy,et al.  Artificial Intelligence and Deep Learning Applications for Automotive Manufacturing , 2018, 2018 IEEE International Conference on Big Data (Big Data).

[8]  William Ian Miller.  Statistical Process Control , 2013 .

[9]  Ken Kennedy,et al.  Data Infrastructure for Intelligent Transportation Systems , 2017 .

[10]  Jiafu Wan,et al.  Implementing Smart Factory of Industrie 4.0: An Outlook , 2016, Int. J. Distributed Sens. Networks.

[11]  Fred Spiring,et al.  Introduction to Statistical Quality Control , 2007, Technometrics.

[12]  László Monostori,et al.  AI and machine learning techniques for managing complexity, changes and uncertainties in manufacturing , 2003 .

[13]  Tianqi Chen,et al.  XGBoost: A Scalable Tree Boosting System , 2016, KDD.

[14]  Guigang Zhang,et al.  Deep Learning , 2016, Int. J. Semantic Comput..

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

[16]  N. Japkowicz.  Learning from Imbalanced Data Sets: A Comparison of Various Strategies * , 2000 .

[17]  Ken Kennedy,et al.  Automotive big data: Applications, workloads and infrastructures , 2015, 2015 IEEE International Conference on Big Data (Big Data).

[18]  Ehsan Sadrfaridpour,et al.  Algebraic multigrid support vector machines , 2016, ESANN.