To achieve efficient personalized production at an affordable cost, a modular manufacturing system (MMS) can be utilized. MMS enables restructuring of its configuration to accommodate product changes and is thus an efficient solution to reduce the costs involved in personalized production. A micro smart factory (MSF) is an MMS with heterogeneous production processes to enable personalized production. Similar to MMS, MSF also enables the restructuring of production configuration; additionally, it comprises cyber-physical production systems (CPPSs) that help achieve resilience. However, MSFs need to overcome performance hurdles with respect to production control. Therefore, this paper proposes a digital twin (DT) and reinforcement learning (RL)-based production control method. This method replaces the existing dispatching rule in the type and instance phases of the MSF. In this method, the RL policy network is learned and evaluated by coordination between DT and RL. The DT provides virtual event logs that include states, actions, and rewards to support learning. These virtual event logs are returned based on vertical integration with the MSF. As a result, the proposed method provides a resilient solution to the CPPS architectural framework and achieves appropriate actions to the dynamic situation of MSF. Additionally, applying DT with RL helps decide what-next/where-next in the production cycle. Moreover, the proposed concept can be extended to various manufacturing domains because the priority rule concept is frequently applied.
Today, megatrends such as individualization, climate change, emissions, energy, and resource scarcity, urbanization, and human well-being, impact almost every aspect of people’s lives. Transformative impacts on many sectors are inevitable, and manufacturing is not an exception. Many studies have investigated solutions that focus on diverse directions, with urban production being the focus of many research efforts and recent studies concentrating on Industry 4.0 and smart manufacturing technologies. This study investigated the integration of smart factory technologies with urban manufacturing as a solution for the aforementioned megatrends. A literature review on related fields, mass personalization, sustainable manufacturing, urban factory, and smart factory was conducted to analyze the benefits, challenges, and correlations. In addition, applications of smart factory technologies in urban production with several case studies are summarized from the literature review. The integration of smart factory technologies and urban manufacturing is proposed as the urban smart factory which has three major characteristics, human-centric, sustainable, and resilient. To the best of the author’s knowledge, no such definition has been proposed before. Practitioners could use the conceptual definition of an urban smart factory presented in this study as a reference model for enhancement of urban production while academics could benefit from the mentioned future research directions.
The manufacturing industry has witnessed rapid changes, including unpredictable product demand, diverse customer requirements, and increased pressure to launch new products. To deal with such changes, the reconfigurable manufacturing system has been proposed as one of the advanced manufacturing systems that is close to the realisation of smart manufacturing since it is able to reconfigure its hardware, software, and system structures in a much quicker manner. Conventional simulation technologies lack convergence with physical manufacturing systems, and reconfigurable manufacturing lines require the manual construction of production line models for each reconfiguration. This study presents a digital twin-based integrated reconfiguration assessment application that synchronises with real-time manufacturing data and provides accurate, automated simulation functionality to build and analyse a manufacturing system. The paper discusses the architectural design and implementation of the application, an information model, and an assessment model that enable quantitatively assessment on reconfigurations of manufacturing systems from various aspects. The effectiveness of the proposed application is verified via application to an automotive parts production line to assess the reconfiguration indicators of the manufacturing system under different scenarios. The results reveal that the proposed application provides faster and more accurate reconfiguration assessments compared to existing methods. The findings of this study are expected to facilitate accurate and consistent decision making for evaluating the various indicators of production line performance.
In the era of the Fourth Industrial Revolution, there is a growing focus on digital twin (DT) in order to advance toward smart manufacturing. Thus, researchers have conducted numerous studies on DT and extensively developed related technologies. There are many studies that apply and analyse DT to actual manufacturing sites for the realization of a smart factory, but it is necessary to clearly consider which part of DT is applied and what function it performs in manufacturing. As such, this study analysed and classified prior literature based on various phases of product lifecycle management, an application field of DT in manufacturing, and the hierarchy level axis of Reference Architecture Model Industry 4.0, the target scope of DT. Accordingly, this study identified research trends in the past and present as well as analysed and identified the major functions of DT (prototyping, pilot testing, monitoring, improvement, and control). Through a gab study on the inadequate aspects of past and present researches, this study proposes directions for future studies on DT and a system architecture that can perform all the functions of DT.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.