A Multi-horizon, Multi-objective Training Planner: Building the Skills for Manufacturing

Fast technological progress and the dynamics generated by economic, ecological and societal mega-trends are putting manufacturing companies under strong pressure to radically change the way in which they operate and innovate. Consequently, human work in manufacturing is also visibly changing and the need to up-skill and re-skill workers is rapidly increasing in order to sustain industry competitiveness and innovativeness as well as employability. Life-long training is therefore crucial to achieve the vision of a successful and socially sustainable manufacturing ecosystem in which industry, society and individuals can thrive together. In this paper we present a novel training planner, which provides worker-specific training recommendations based on workers’ knowledge, skills and preferences, job content and allocation statistics, and factory demands. Multiple objectives, related to economic and social performances are taken into account.

[1]  Maurizio Fiasché,et al.  A Quantum-Inspired Evolutionary Algorithm for Optimization Numerical Problems , 2012, ICONIP.

[2]  Vicente Roca-Puig,et al.  Combined effect of human capital, temporary employment and organizational size on firm performance , 2011 .

[3]  Jong-Hwan Kim,et al.  Quantum-inspired evolutionary algorithm for a class of combinatorial optimization , 2002, IEEE Trans. Evol. Comput..

[4]  Yong Yin,et al.  Training and assignment of multi-skilled workers for implementing seru production systems , 2013 .

[5]  Marco Guerrazzi,et al.  Workforce ageing and the training propensity of Italian firms: cross-sectional evidence from the INDACO survey , 2014 .

[6]  Kim Hua Tan,et al.  Managing lean capabilities through flexible workforce development: a process and framework , 2013 .

[7]  David A. Nembhard,et al.  Cross training efficiency and flexibility with process change , 2014 .

[8]  Jun Gong,et al.  Multi-objective optimal cross-training configuration models for an assembly cell using non-dominated sorting genetic algorithm-II , 2012, Int. J. Comput. Integr. Manuf..

[9]  Eric Molleman,et al.  Cross-training in a cellular manufacturing environment , 2005, Comput. Ind. Eng..

[10]  George Chryssolouris,et al.  On industrial learning and training for the factories of the future: a conceptual, cognitive and technology framework , 2013, J. Intell. Manuf..

[11]  Marzio Sorlini,et al.  Anthropocentric Workplaces of the Future Approached through a New Holistic Vision , 2014, APMS.

[12]  Sureswaran Ramadass,et al.  A glimpse of cross training models and workforce scheduling optimization , 2013, 2013 IEEE Symposium on Computers & Informatics (ISCI).

[13]  D. B. Webster,et al.  Mathematical models for developing a flexible workforce , 1994 .

[14]  Ming Liang,et al.  An integrated approach to worker assignment, workforce flexibility acquisition, and task rotation , 2013, J. Oper. Res. Soc..

[15]  Miao Yu,et al.  A Multi-objective Cross-training Plan Based on NSGA-II , 2013, J. Networks.

[16]  Andrea Bettoni,et al.  Toward Human-Centric Factories: Requirements and Design Aspects of a Worker-Centric Job Allocator , 2014, APMS.

[17]  Alan W. Johnson,et al.  A measure of cross-training benefit versus job skill specialization , 2009, Comput. Ind. Eng..

[18]  Lin Lin,et al.  Multiobjective evolutionary algorithm for manufacturing scheduling problems: state-of-the-art survey , 2014, J. Intell. Manuf..

[19]  Emma O'Brien,et al.  Educational programmes for future employability of graduates in SMEs , 2013, J. Intell. Manuf..

[20]  Erik Demeulemeester,et al.  Workforce Planning Incorporating Skills: State of the Art , 2014, Eur. J. Oper. Res..

[21]  Andrea Bettoni,et al.  A New Human-centric Factory Model , 2015 .