Search

Reconfigurable Manufacturing Systems (RMS) have gained attention in the aerospace industry in the past years, as post-pandemic context shows drastic production capacity changes and new environmental regulations to which it must adapt quicker than before to maintain competitiveness. Nevertheless, current RMS design methods have not thoroughly considered this industry specificities, nor industrial resources requirements in the current concurrent design practice. These limitations have been identified in several recent research works. Ontology-based Engineering (OBE) systems can stand overly complex collaborative design processes involving multidisciplinary stakeholders and various digital tools, integrating different levels of decision. Models for Manufacturing (MfM) is an OBE methodology aiming to enable industrial design and decision-making in manufacturing by preserving the company knowledge in ontology models, usable as knowledge base to generate and integrate the aircraft and manufacturing systems design. This paper presents an MfM application for RMS design in aerospace, introducing innovative design concepts that allow implementing RMS in a collaborative engineering process of an aerospace product. An implementation is shown designing the RMS of a model aircraft family to illustrate the concepts introduced and considerations are given to transfer this knowledge base into an OBE system to support complex real-life applications. [ABSTRACT FROM AUTHOR]

Cost engineering capabilities are becoming increasingly important for the competitiveness of industrial firms, especially for engineer to order products (ETOPs). Despite this relevance, the literature on the use of advanced data-driven methodologies, such as machine learning (ML), for early cost estimation (CE) of ETOPs is quite sparse. Furthermore, ML has still seen little use in real industrial applications due to several challenges. Accordingly, the objective of this paper is threefold: (a) to develop a solid early CE approach for ETOPs, including feature selection; (b) to investigate the benefits of adopting ML for ETOPs' CE; (c) to identify how ML can be introduced into real industrial context with little knowledge on ML. Long action research has been carried out with a large industrial company that produces Oil & Gas ETOPs. We observed how ML facilitates the exploration of the relationships between the choices of early design stages and the CE. ML algorithms also allowed to both capture the high variability of the data and test different combinations of cost drivers in very effective ways. The project resulted in an accurate CE framework with an iterative feature selection process and an approach for introducing ML into a real industrial context. [ABSTRACT FROM AUTHOR]

Robotic manufacturing systems have proven to be an effective solution for modern manufacturing enterprises to deal with increasing in customer demands and market competition. However, these systems may be unable to completely satisfy user requirements because of the difference between user and design perspectives. Thus, designing robotic manufacturing systems requires iterative processes that significantly increase development costs and lead time. A user-customised design approach is needed that enables users to customise robotic manufacturing systems as well as alleviate the burden on designers of eliciting user requirements. However, most users may not be able to customise their systems because of a lack of engineering knowledge. The authors propose a knowledge-based engineering approach to aid users in customising the architectures of robotic manufacturing systems. Two models — an ontological knowledge model and a multi-attribute decision-making model — are defined and integrated in the proposed KBE architecture definition method. A rule-based reasoning process is proposed in the ontological knowledge model based on explicit semantic descriptions of users' unstructured or semi-structured requirements and the components of robotic manufacturing systems, which infers the possible architecture of the required system. The MADM model is adopted to evaluate the architecture alternatives to determine the optimal solution. [ABSTRACT FROM AUTHOR]