Applied AI research Making effective use of AI in machine tool manufacturing

Where can artificial intelligence deliver practical benefits for machine tool manufacturers? The KI4WZM research project identifies opportunities in knowledge management, fault diagnosis and process optimisation – including applications that can run locally without cloud access.

Artificial intelligence is on everyone’s lips, but where exactly does its potential lie for machine tool manufacturers? Eike Rodenbäck of the German Research Center for Artificial Intelligence (DFKI) explored this question in the “Artificial Intelligence for Machine Tools” project. On 17 September 2026, his work received the VDW Research Institute’s Research Project of the Year award at the AMB trade fair in Stuttgart.

“Eike Rodenbäck is taking the machine tool industry a significant step forward on its path towards digital transformation,” says Dr Alexander Broos, Managing Director of the VDW Research Institute. “His findings help our small and medium-sized member companies in particular to answer the question of where and how they can apply AI in a targeted way – in use cases that deliver benefits and with AI models suited to these tasks. Eike Rodenbäck was selected for the award because of his outstanding work in identifying these opportunities.”

VDW members themselves provided initial indications of potential challenges. Building on this input, Rodenbäck identified areas in which AI could support companies in the industry in an economically viable way. These ideas will be developed into specific pre-competitive projects at a later stage.

Automated knowledge management and fault diagnosis

One such area is knowledge management. Particularly at a time when many employees are approaching retirement, the automated documentation of process knowledge is important to minimise the loss of expertise.

“Companies across a wide range of industries still simply collect data in manually maintained Excel spreadsheets,” Eike Rodenbäck points out. “These are copied and passed back and forth. Of course, this opens the door to errors and data loss.”

One project idea developed within KI4WZM involves the automated documentation of software code. AI-assisted analysis of existing codebases and comparison with available documentation could help preserve existing knowledge, even when experienced employees leave the company.

Artificial intelligence can also support fault diagnosis. In his work, Rodenbäck focused on cases in which a problem has already occurred. “A fault is often reported without its cause being identified straight away,” explains the 28-year-old engineering informatics specialist. Multimodal diagnostic support links controller alarms with log files, runtime data and machine documentation to identify causes more quickly and provide recommended actions at the same time. “This could shorten downtime and reduce the effort required for servicing.”

Process optimisation without the cloud

Processes can also be optimised automatically – another area in which machine tool manufacturers can use AI to improve production efficiency. Large, energy-intensive AI models are not always needed to generate data-driven recommendations for parameters such as spindle speed, feed rate or depth of cut, taking account of the material, tool, process data and quality targets. Simpler models, or those that can run locally without connecting to external cloud servers, save both money and energy.

“AI offers considerable potential in the machine tool industry – but not every challenge requires a highly complex model,” Rodenbäck summarises. “The key is to start where companies have a specific need and suitable data is available. This connection between technological possibilities and practical requirements was particularly important to us in the project.”

A focus on knowledge transfer

Rodenbäck summarised the project findings in a detailed report. A workshop also made the findings available to a wider audience within the network of machine tool manufacturers represented by the VDW (German Machine Tool Builders’ Association). Alongside the aim of maximising knowledge transfer, the 60 participants gathered, developed and prioritised further project ideas.

The industry’s digital transformation is a work in progress, explains Broos. Rodenbäck adds: “Another key aim was to raise companies’ awareness of the importance of data quality, reliability, traceability and local data processing. These are areas where shortcomings often hold back further activities.”

(ID:50983815)