Skip to main content

PROJECT: AIMO

ABOUT AIMO

AI-assisted Tools for Modular Product Strategy Design and Implementation

AIMO aims to develop AI-assisted tools and techniques that assist small and medium-sized companies in making optimized decisions during the product development process. This is achieved through a combination of AI and modularization approaches, resulting in sustainable and competitive businesses.

The project’s core task is to provide a life cycle overview of the financial implications of various product and process decisions made during the product design phase. This information helps companies make more informed strategic decisions. The project includes a state-of-the-art variant costing model integrated into the IT systems of four case companies, providing valuable knowledge for daily decision-making.

The AIMO project team works closely with the case companies to identify their needs and opportunities, integrating the developed tools and techniques into their IT systems and business processes. Through the project, the four case companies gain insight into their products’ life cycles, IT systems, value chains, and modular potential.

The project’s key findings will be made publicly available to benefit other Danish companies interested in business optimization, sustainability, and modularity.

THE BENEFITS OF COMBINING AI AND MODULARIZATION 

Read the article Danish SMEs can unlock modular potential with AI to learn more about AIMO and how the project uses AI technology to pave the way for modularization in SMEs.

read it here

PROJECT FUNDING

AIMO is co-funded by the Danish Industry Foundation and Thomas B. Thriges Fond.

PROJECT MANAGEMENT AND EXECUTION

AIMO is executed collaboratively by Technical University of Denmark (DTU) and Aarhus University (AU).
Project manager is Carsten Keinicke Fjord Christensen, DTU.

PROJECT DURATION

AIMO was launched in 2022 and is to conclude in 2025.

PROJECT OWNERSHIP

AIMO is owned and supported by NEM.

PROJECT PRIORITIES

To develop methods for estimating variant costs for life cycle costs across the value chain and at different product levels.

To promote sustainability and suggest superior alternatives in the product design phase using AI technology.

To implement and test prototypes of design assistance tools in collaboration with four case companies.

PROJECT PHASES

Phase 1: Developing methods and models that promote the project objectives
  • Design and implementation of product and process architectures and considerations on how to design basic structures of products, which are optimal in relation to processes and recycling.
  • Variant cost estimation principles for life-cycle costs across the value chain and at different product levels – e.g., what is the value-chain and life-cycle cost of a given product if choosing between variant A or variant B in the design process.
  • Variant cost modeling in IT systems.
  • Methods for pattern recognition, classification, and segmentation of parts, modules, and products from digital product drawings.
  • Using deep learning to determine relationships in 2D digital product drawings, generate 3D product drawings from 2D, and provide recommendations to product engineers in the design phase.
Phase 2: Implementing the methods and models in the four case companies
  • Using a framework tool for estimating life cycle costs for one or more product lines in the company.
  • Implementing a model that integrates the above-mentioned cost model into the specific IT systems found in the case companies.
  • Testing methods to summarize life cycle costs of product based on 2D product drawings and the costs of each individual component.
  • Comparing efficiency levels.
  • Testing methods to produce more cost-effective alternatives to products or parts by comparing with similar designs or with the company’s existing portfolio of parts.
Phase 3: Communicating the project findings to broader audiences

The communication efforts in the final phase will, among other topics, consider the following questions:

  • How do the economic and competitiveness results from the project land?
  • What application possibilities are available through the project?
  • How are efficient solutions implemented and what does the investment case look like regarding costs and benefits?