Peter Lendermann
Co-Founder and CBDO, D-SIMLAB Technologies Pte Ltd
联合创始人&首席业务发展官，D-SIMLAB Technologies Pte Ltd

讲师简介 / Speaker Bio

Peter Lendermann has been involved in decision-support for logistics and advanced simulation technology for 15 years and is a recognized authority in the field. As the Chief Business Development Officer (CBDO), he is the scientific thought leader and is responsible for strategy and business development at D-SIMLAB.

Peter has been engaged in the simulation community since the early 1990’s when he worked in multinational research collaboration at the European Laboratory for Particle Physics CERN (Geneva, Switzerland) and Nagoya University (Japan). In 1996 he joined a German consulting firm where he was responsible for business process re-engineering projects with numerous process manufacturing, aviation and automotive clients in Europe, Canada and China. Since 2000 he led the simulation-related research activities at the Singapore Institute of Manufacturing Technology until spinning them off into D-SIMLAB Technologies in 2006.

Peter holds a PhD in Applied High-Energy Physics from Humboldt-University in Berlin (Germany) and an MBA in International Economics and Management from SDA Bocconi in Milan (Italy).

摘要 / Abstract

In the AI-Driven Smart Factory, AI techniques and Digital Twins play an essential role for capacity planning and WIP flow optimization. A Digital Twin of a factory in particular, in order to be able to make predictions about the factory’s future evolution, should “represent” the factory and react to key drivers in the same way as the actual factory. To achieve this, such Digital Twins also need to “connect” and “synchronize” with the factory to get a real-time view of its state and detect changes in its underlying behavioral patterns to enhance the enabling simulation model (i.e., the quality of “represent”).

Because a factory can never be modelled to the lowest level of detail, a Digital Twin would always be a simplified representation and therefore always needs to be validated with regard to a specific application purpose before it can be used at multiple levels, depending on which decision variables require how much capital investment, effort and lead time.

The presentation will showcase how the entire business process planning chain for Semiconductor Manufacturing, starting from capacity planning and identification of capacity gaps, identification of tools to invest in, determination of tool phase-in/out schedules and dedications, setting of sales targets (also under consideration of existing sales orders), load mix optimisation, all the way to due-date commitment, can be enabled through one single D-SIMCON Digital Twin framework for static and dynamic planning, thereby automating all processes associated with “represent”, “connect” and “synchronize”, and how this is a critical enabler of the AI-Driven Smart Factory of the Future.