No abstract

The quality of teaching in mechanical engineering greatly depends on the practical application of the fundamental theory taught. During COVID-19, limited access to in-class lectures, practical courses with demonstrator plants, and active student participation forced us, an institute of a mechanical engineering faculty in the German higher education system, to transform the teaching strategy in a limited time of one month. For class sizes of between ~25 and ~700 participants, mainly addressing mechanical, electrical and software engineering students, we share challenges and successes in our transformation strategy during April-October 2020. Furthermore, we present a collection of suitable tools, their functions, advantages, disadvantages, and feedback from three sources to provide profound assessment and adaptation criteria in digital teaching. Using quantitative evaluations of four lectures in automation and information systems over the past five years, we highlight the experience from the students’ perspective and evaluate our digital teaching methods compared to well-established in-class formats. This compilation of causes and consequences clarifies the effort involved in achieving the result and discusses the potential of digital teaching or hybrid teaching in engineering.

No abstract

The distributed blocking flowshop scheduling problem (DBFSP) with new job insertions is studied. Rescheduling all remaining jobs after a dynamic event like a new job insertion is unreasonable to an actual distributed blocking flowshop production process. A deep reinforcement learning (DRL) algorithm is proposed to optimise the job selection model, and local modifications are made on the basis of the original scheduling plan when new jobs arrive. The objective is to minimise the total completion time deviation of all products so that all jobs can be finished on time to reduce the cost of storage. First, according to the definitions of the dynamic DBFSP problem, a DRL framework based on multi-agent deep deterministic policy gradient (MADDPG) is proposed. In this framework, a full schedule is generated by the variable neighbourhood descent algorithm before a dynamic event occurs. Meanwhile, all newly added jobs are reordered before the agents make decisions to select the one that needs to be scheduled most urgently. This study defines the observations, actions and reward calculation methods and applies centralised training and distributed execution in MADDPG. Finally, a comprehensive computational experiment is carried out to compare the proposed method with the closely related and well-performing methods. The results indicate that the proposed method can solve the dynamic DBFSP effectively and efficiently. K E Y W O R D S deep reinforcement learning, distributed blocking flowshop scheduling problem, dynamic scheduling, job insertions, multi-agent deep deterministic policy gradientThis is an open access article under the terms of the Creative Commons Attribution-NonCommercial-NoDerivs License, which permits use and distribution in any medium, provided the original work is properly cited, the use is non-commercial and no modifications or adaptations are made.