Project AutoOPP 2.0: Increasing efficiency in the procurement and manufacturing of components
Automatic recognition of the work plan based on design data (AutoOPP 2.0)
Major industries such as mechanical engineering, automotive engineering, and vehicle manufacturing make up the manufacturing sector, one of Germany's largest industrial sectors. The companies operating in this sector either manufacture technical components themselves or have them manufactured by suppliers based on design data. The most cost-effective manufacturing method depends largely on the design, possible manufacturing processes, and the number of units to be produced. The market knowledge of the players involved, i.e., which company can manufacture which component using which process at what price, is usually incomplete. Determining how and, therefore, which company can manufacture a component most cost-effectively on the market is still very time-consuming.
Goals and approach
The goal of the AutoOPP 2.0 joint project is to develop an AI methodology that can be used to automatically derive the appropriate manufacturing processes and the cost-optimized work plan from 2D and 3D design data of components. The individual manufacturing steps, the classification and interaction of manufacturing parts in assemblies, and other factors such as the respective quantities are to be taken into account. Active learning methods are being incorporated to improve model quality.
Innovations and perspectives
AutoOPP 2.0 aims to automate knowledge-intensive processes in key industrial sectors using AI methods and to lay the foundations for intelligent solutions that support manufacturing technologists and technical purchasing. The project results are to be integrated into a B2B platform and accompanied by broad scientific dissemination. For example, the effort involved in make-or-buy decisions can be significantly reduced and the compatibility of incoming order requests for manufacturing companies can be increased. In important but small-scale industries, the results contribute to greater market transparency, which has a positive effect on the overall economy in terms of higher efficiency.
Funding information: The project AutoOPP 2.0, which will run from March 2023 to April 2025, is funded by the German Federal Ministry of Education and Research.
Project coordination: PartSpace (Easy2Parts GmbH)
Project partner: Deggendorf Institute of Technology
Bring Clarity to Your Manufacturing Decisions
Bring Clarity to Your Manufacturing Decisions
Related Articles
Agentic AI: Why most AI agents in technical procurement will fail
Agentic AI promises to transform technical procurement—but most implementations are set up to fail. The issue isn’t the capability of AI models like ChatGPT, but the absence of structured, integrated industrial data. Without a solid data foundation linking CAD, ERP, PLM, and supplier insights, AI agents remain impressive demos rather than reliable tools. This article explores why data—not algorithms—is the true bottleneck, and what companies must fix to unlock real value.
Value Analysis is changing and what to expect at the VDI conference 2026
At VDI 2026, one thing is becoming clear: cost optimization is shifting from negotiation to data-driven decision-making. As companies like Siemens demonstrate measurable savings through large-scale cost transparency, value analysis is entering a new phase. This article explores how leading industrial organizations are redefining cost strategy—and why scalable cost intelligence is becoming a critical competitive advantage.
How is AI disrupting the world of cost engineering?
Artificial intelligence is transforming cost engineering from a manual, experience-driven discipline into a data-driven strategic capability. By analyzing CAD data, manufacturing processes, and supplier information, AI enables earlier cost transparency and smarter procurement decisions. Industrial companies that integrate AI into engineering and sourcing workflows gain a decisive competitive advantage.