Fraunhofer Institute for Production Technology IPTResearch project "KI4ToolPath"
Artificial intelligence and machine learning for tool path optimization
Additive manufacturing is becoming increasingly attractive for the production of a wide variety of components, especially for single and small batch production of individualized and geometrically complex products. In many cases, not only are additive manufacturing processes significantly more efficient, but they save more resources than conventional, subtractive processes. In addition, they are more flexible from a production planning perspective and offer much greater scope for designing components, for example with hollow or lightweight structures.
The advantages of additive manufacturing are offset by the fact that the processes often do not run stably: Fluctuations occur in the process, which impair product quality. Another disadvantage is that, since they lack digital tools, machine operators have to carry out process and path planning manually, which is time-consuming.
Thus, for additive manufacturing to become a real alternative to conventional processes, shorter process planning phases and consistently high product quality are required. By using extensive process data through machine learning, research could create digital path planning for additive manufacturing processes that automatically compensates for process variations.
New path planning concept shortens manufacturing process by around 20 percent
The aim of the research project "KI4ToolPath – Geometry-supported classification of process states for path planning support using the WAAM process" is fully digital process planning for wire arc additive manufacturing (WAAM). With it, process errors will be detected and compensated during web planning using data-based machine learning. The focus of the development is on implementing interfaces between the software and hardware components for data acquisition, forwarding and processing.
Automated process planning will significantly improve the reliability and quality of the WAAM process. For example, the lead time of the manufacturing process can be reduced by around 20 percent. In addition, the reject rate drops, as does the number of geometry deviations and, thus, the associated effort for inspection and reworking.
Sensor data for artificial intelligence training
In the first stage of the project, the project partners are integrating various sensors into the WAAM system. During production, the sensors record selected process data, such as the geometry of the weld beads or a temperature profile. This data is then fed to artificial intelligence (AI), which uses the data for machine learning.
To generate sufficient data volume for training the AI system, the partners build geometries defined at the beginning of the project many times in the WAAM plant; here, the maximum limits of the process are identified. Process instabilities and aborts are also recorded and help the AI system learn further. Tests of various process and control strategies are used to generate the widest possible data field.
New interface for transfer between sensors and AI
The process data is forwarded to an AI platform for further processing. For the transfer between sensor technology and AI, the researchers are designing a suitable interface with an appropriate data structure. To make the data usable, the project partners are also developing a so-called auto-encoder, which is used to reduce the dimension of and further process the various data formats. In the next step, this uniformly "translated" data will be used to train an artificial intelligence system.
Data-based development of manufacturing strategies
The AI algorithms are then integrated into the path planning process: By training the AI with large amounts of data from the WAAM process, the partners are generating a path planning strategy, one whose portfolio of possibilities also includes compensating unwanted process fluctuations. Path planning for the WAAM process is particularly challenging because the component temperature – which has a direct influence on the result – varies significantly during the machining process.
Such important factors as component temperature can be taken into account for the first time before production with the new digital path planning system. The new strategies also ensure that the temperature level remains constant since the path sequence can be automatically adjusted.
Project partners
- Collective mind AG, Leonberg (Coordination)
- Fraunhofer Institute for Production Technology IPT, Aachen
- ModuleWorks GmbH, Aachen
Funding
The research project "KI4ToolPath – Geometry-supported classification of process states for path planning support using the WAAM process" is funded by the German Federal Ministry of Education and Research (BMBF) as part of the research project "KI4ToolPath." Funding code: 01IS22021C
Project Management Agency
DLR Project Management Agency – German Aerospace Center e.V.