Duration: 10/2020 – 10/2023
Lead: Böhler Aerospace
The BrAIN research project aims to use the potential of artificial intelligence (AI) to identify the reasons for quality deficiencies and rework in the forging industry of aerospace components. An intelligent AI system should be able to continuously improve manufacturing processes and at the same time save costs and energy. The project is led by the leading supplier to the aerospace industry, Böhler Aerospace. The appropriate AI comes from Know-Center.
Before a passenger aircraft can take off from the ground at a speed of up to 345 km/h, perfect interaction of all technical components must be ensured. Every component has a task and is a result of a complex manufacturing and process chain. Manufacturing in the aircraft industry is one of the most accurate in the world. The safety-critical components, such as drop forged parts made of high-alloy steels, titanium and nickel-based alloys, are subject to very strict safety and quality criteria.
Duration: 10/2020 – 10/2023
Defective components pollute the environment and are costly and time-consuming
If tolerance deviations occur in the complex manufacturing processes, components must either be rejected or reworked. This is not only costly and time-consuming, it also requires an enormous amount of energy and pollutes the environment. That is why simulation models are used in manufacturing. These offer a cost-effective and risk-free way of discovering errors at an early stage, developing new processes or taking optimization measures.
High-tech simulations replace time-consuming “numerical” simulations
Numerical simulation models are typically used to simulate production processes. These are very computationally intensive, and complex process simulations often require up to a week of computing time. In order to save this time and the associated costs, innovative approaches are required. So-called “explainable hybrid simulation models” can shorten the long computation times significantly. The combination of machine learning models and numerical models should be available much faster.
“Using hybrid simulation models, a combination of machine learning and numerical models, we can carry out simulations in a fraction of a second,” explained Ass. Prof. Roman Kern, Head of the Knowledge Discovery Area at Know-Center. “That saves the company quite a bit of development time and costs. In addition, the data science and machine learning methods used are not limited to the calculation of predictions, but can also actively generate decision suggestions. Using the developed models, we will be able not only to analyze individual process steps, but also map the production process in its entirety.”
Explainable AI makes suggestions transparent for domain experts
The system is also intended to support domain experts by making comprehensible suggestions for process design and machine settings. The research method Explainable AI (xAI), also known as “explainable AI”, is used.
Dr. Vedran Sabol, Head of the Knowledge Visualization Area at Know-Center explained: “As experts in this research field, we know from experience how important it is for users to understand the decision-making process of AI algorithms. Within the BrAIn project, we want to make the AI models transparent using xAI in order to promote the acceptance of and trust in AI solutions on the part of technical personnel. A profitable symbiosis should arise from the cooperation between humans and AI. In order to remain competitive as a company in the future, this is inevitable requirement, especially in the area of automation.”
The developed methods can be used in any industry in which sensor data is available and numerical simulations are carried out. Big data and AI are not yet widespread in the forging industry since its manufacturing processes are far more complex than those in other industries. In order to protect the environment, conserve resources and secure technological development, it is necessary to rely on the latest AI technologies such as these.