Machine learning approach for systematic analysis of energy efficiency potentials in manufacturing processes: A case of battery production

Energy efficiency in manufacturing plays a crucial role in decreasing manufacturing costs and reducing environmental footprint. This is particularly important for producing battery cells with novel processes due to their cost-sensitivity and high potential impact on the environment. Therefore, design and operation of these processes are critical and require a high level of process and machine specific understanding. A methodology based on machine learning is presented, which has the capability of identifying improvement potentials using machine and process specific influencing factors. A battery production case is used to demonstrate the accuracy, transferability and validity of the methodology.

[1]  Chris Yuan,et al.  Manufacturing energy analysis of lithium ion battery pack for electric vehicles , 2017 .

[2]  Junkai Wang,et al.  A Data-Driven Model for Energy Consumption in the Sintering Process , 2016 .

[3]  Wolfgang Haselrieder,et al.  Current status and challenges for automotive battery production technologies , 2018 .

[4]  R. Tibshirani,et al.  Least angle regression , 2004, math/0406456.

[5]  Christoph Herrmann,et al.  Multiscale simulation approach for production systems , 2019, The International Journal of Advanced Manufacturing Technology.

[6]  Carlos Ocampo-Martinez,et al.  Energy efficiency in discrete-manufacturing systems: Insights, trends, and control strategies , 2019, Journal of Manufacturing Systems.

[7]  Karl-Heinz Pettinger,et al.  When Does the Operation of a Battery Become Environmentally Positive , 2017 .

[8]  Shai Ben-David,et al.  Understanding Machine Learning: From Theory to Algorithms , 2014 .

[9]  Sang Do Noh,et al.  Smart manufacturing: Past research, present findings, and future directions , 2016, International Journal of Precision Engineering and Manufacturing-Green Technology.

[10]  Z. Irani,et al.  Critical analysis of Big Data challenges and analytical methods , 2017 .

[11]  Christoph Herrmann,et al.  Data mining in battery production chains towards multi-criterial quality prediction , 2019, CIRP Annals.

[12]  Sami Kara,et al.  Energy characterisation and benchmarking of factories , 2017 .

[13]  Sami Kara,et al.  Unit process energy consumption models for material removal processes , 2011 .

[14]  Moneer Helu,et al.  Towards a generalized energy prediction model for machine tools. , 2017, Journal of manufacturing science and engineering.

[15]  Sebastian Thiede,et al.  Factors influencing the energy intensity of automotive manufacturing plants , 2017 .

[16]  Sangkee Min,et al.  Development of an energy consumption monitoring procedure for machine tools , 2012 .

[17]  Vimal Dhokia,et al.  Energy efficient process planning for CNC machining , 2012 .

[18]  Sebastian Thiede,et al.  Simulation-based assessment of the energy demand in battery cell manufacturing , 2019, Procedia CIRP.

[19]  Sami Kara,et al.  Towards Energy and Resource Efficient Manufacturing: A Processes and Systems Approach , 2012 .

[20]  Jumyung Um,et al.  Deep Learning Approach of Energy Estimation Model of Remote Laser Welding , 2019, Energies.

[21]  Christoph Herrmann,et al.  SME appropriate concept for continuously improving the energy and resource efficiency in manufacturing companies , 2013 .

[22]  Lars Ole Valøen,et al.  Life Cycle Assessment of a Lithium‐Ion Battery Vehicle Pack , 2014 .

[23]  Günther Seliger,et al.  Methodology for planning and operating energy-efficient production systems , 2011 .

[24]  J. Manyika.  Big data: The next frontier for innovation, competition, and productivity , 2011 .