A Rule-Based Approach Founded on Description Logics for Industry 4.0 Smart Factories

Abstract

This paper develops a formal framework, founded on description logics, to assist decision making in relation to the manufacturing operation and control in modern enterprises that stand to benefit from the transition to Industry 4.0. The objective is to provide sophisticated support to individuals making decisions in the area of production operations management and in particular production scheduling and material requirements planning. Using this framework, the paper demonstrates an approach to encode the domain knowledge of human experts managing the production as sets of formal rules. These rules can be implemented in an intelligent system that can assist and empower human experts, reducing difficulty when making decisions in complex manufacturing environments.

An Information Theory Inspired Real-Time Self-Adaptive Scheduling for Production-Logistics Resources: Framework, Principle, and Implementation

“…At this time, the processing task O 2 2 is triggered and moved from the waiting pool to the scheduling pool. O 3 2 is moved from the job pool to the waiting pool. Task O 2 2 is released to the set of optional services m t j at the same time.…”

“…(2) The development and application of technologies such as the Internet of Things (IoT) and Cyber-Physical Systems (CPS) have made the manufacturing resources in smart factories (e.g., machines, AGVs, intelligent forklifts, etc.) ever more intelligent [3]. On the one hand, the application of intelligent resources in the factory makes manufacturing intelligent possible.…”

“…On the other hand, intelligent resources will also bring fuzzy operation time, including transportation time caused by the uncertainty of the impact of AGVs obstacle avoidance and human factors on the production operation time during human-machine cooperation [4]. (3) The flexibility of production organization is the basis for enterprises to meet personalized customer needs. This not only requires the factory's production factors to have the ability to dynamically organize to meet production demands, but also raises the dynamic adaptability requirements of production organization for security, flexibility, and agility [5].…”

“…However, most scholars pay attention to the random arrival of orders and ignore the impact of fuzzy working hours on job-shop. (3) In order to realize the real-time reaction scheduling of Production-Logistics Resources in intelligent job shop, it is necessary to study when the Production-Logistics Resources in the system provide services. Moreover, how to provide services according to the current task requirements and their service capabilities is a critical issue to be addressed in a discrete manufacturing system.…”

Ontologies for Industry 4.0

“…For this purpose, in the last decade, ontologies have been developed for one specific industrial domain such as aviation (Keller, 2016), aeropsace (Kossmann et al, 2009), construction (Liao et al, 2009), steel production (Dobrev et al, 2008), chemical engineering (Vinoth & Sankar, 2016;Feng et al, 2018), oil industry (Du et al, 2010;Guo & Wu, 2012), energy (Santos et al, 2018), and electronics (Liu et al, 2005a). Other ontologies have been used for one specific manufacturing process such as packaging (Liu et al, 2005b), process engineering (Wiesner et al, 2010), process compliance (Disi & Zualkernan, 2009), risk management (Atkinson et al, 2006), safety management (Hooi et al, 2012), customer feedback analysis (Kim and Lee, 2013;Daly et al, 2015), organizational management (Grangel-Gonzalez et al, 2016;Izhar and Apduhan, 2017), project management (Cheah et al, 2011), product development (Zhang et al, 2017), maintenance (Haupert et al, 2014), resource reconfiguration (Wan et al, 2018b), and production scheduling (Kourtis et al, 2019). Ontologies have also been focused on one service, for example, ticketing (Vukmirovic et al, 2006), or on one manufacturing concept, for example, information flow (Bildstein and Feng, 2018), information security (Mozzaquatro et al, 2016), and data integration (Yusupova et al).…”