Deep Neural Networks (DNN) will emerge as a cornerstone in automotive software engineering. However, developing systems with DNNs introduces novel challenges for safety assessments. This paper reviews the state-of-the-art in verification and validation of safety-critical systems that rely on machine learning. Furthermore, we report from a workshop series on DNNs for perception with automotive experts in Sweden, confirming that ISO 26262 largely contravenes the nature of DNNs. We recommend aerospace-to-automotive knowledge transfer and systems-based safety approaches, e.g., safety cage architectures and simulated system test cases.
A platform is commonly used as a basis for generating a number of derivative products, after which it is replaced by a new platform. For some companies, a more viable approach is to adopt a continuous platform that is sustained and expanded over time. This applies to companies that have to provide highly customized products while not in control of interfaces, suppliers in the aerospace industry, for example. For them, the traditional part-based generation of platforms is not sufficient, and more flexibility must be built into the platform. This article proposes an approach for continuous platform development, based on an integrated artifact model and connected development processes. The processes apply set-based concurrent engineering to develop derivative products and to extend the bandwidth of the platform. The artifact model serves as a basis for development and connects products and manufacturing systems to enable informed design decisions that span across the lifecycle. The proposed approach incorporates two modes of platform use. Mode I is applied for configuring products to order within the bandwidth of the platform. This includes automatic concept evaluation using a pallet of computer-aided engineering tools and supporting tools. Mode II is applied when the bandwidth does not suffice to cover the required functionality and therefore needs to be expanded. This article exemplifies the approach through a case from a supplier in the aerospace industry.
Platforms may enable offering a variety of products to the market while keeping the development cost down. Reusing design knowledge is a key concept, whether manifested as reusing parts, ideas, concepts, or technologies. This article describes processes and information technology solutions for holistically working with both technology platforms and product platforms. A platform framework was developed for managing information and to support the processes. The use of the framework is illustrated through a case study performed at a subsupplier in the aerospace industry focusing on technology development, platform-based product development, and platform configuration. A wiki system supports the technology platform, containing electronic guidelines, methods, and information about the technologies. To support the product platform, a product lifecycle management architecture is created. A turbine rear structure from a turbofan engine is used as an example, requiring several different analysis technologies to be used and coordinated when creating a variant. The solution is a product lifecycle management architecture created based on the technology platform. It integrates a product data management system, a computer-aided design tool, two computer-aided engineering tools, and a configurator.
One problem in incremental product development is that geometric models are limited in their ability to explore radical alternative design variants. In this publication, a function modeling approach is suggested to increase the amount and variety of explored alternatives, since function models (FM) provide greater model flexibility. An enhanced function-means (EF-M) model capable of representing the constraints of the design space as well as alternative designs is created through a reverse engineering process. This model is then used as a basis for the development of a new product variant. This work describes the EF-M model's capabilities for representing the design space and integrating novel solutions into the existing product structure and explains how these capabilities support the exploration of alternative design variants. First-order analyses are executed, and the EF-M model is used to capture and represent already existing design information for further analyses. Based on these findings, a design space exploration approach is developed. It positions the FM as a connection between legacy and novel designs and, through this, allows for the exploration of more diverse product concepts. This approach is based on three steps – decomposition, design, and embodiment – and builds on the capabilities of EF-M to model alternative solutions for different requirements. While the embodiment step of creating the novel product's geometry is still a topic for future research, the design space exploration concept can be used to enable wider, more methodological, and potentially automated design space exploration.
Product platforms are used to enable mass customisation to serve a large number of different market segments. The products are configured-to-order, meaning they are compiled using a variety of pre-developed building blocks. However, the building blocks that make up a traditional platform can only serve customer requirements that are known. Engineering-to-order (ETO) development serves companies where customer requirements vary frequently. Here, designs are tailored to fit specific customer requirements upon request, an approach which is time consuming if serving a large number of different customers. This paper presents an approach for ETO configuration design. It comprises a two-stage model that enables design reuse while simultaneously maintaining flexibility to manage changes in customer requirements. The proposed artefact model is configured modularly to progress the design work and to create an architecture to work with, and scalable flexibility is maintained until the customer requirements are considered stable enough to optimise the final design. An illustrative case shows the approach's feasibility to a twostage configuration of a rear frame of a jet engine. While using overall design considerations to select modules, trade-off curves are used for final scalable configuration. A change in customer requirements is accommodated by scalable flexibility, thereby creating an adaptable product platform.
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.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.