Trumpf: Faster setup AI simplifies punching and laser cutting

Related Vendors

TRUMPF Schweiz AG

Trumpf Grüsch AG Elektrowerkzeuge

FAULHABER Drive Systems

Taiwan Machine Tool & Accessory Builders' Association (TMBA)

Wuxi InfiMotion Technology Co., Ltd.

The software "Runability Guide" supports sheet metal workers with artificial intelligence (AI) to program and set up orders for punching and laser cutting on Trumatic 5000 systems more simply and in the shortest possible time.

At its in-house trade show Intech, the manufacturer Trumpf showed with the software "Runability Guide" a first version of a new, AI-based software, with which users can more quickly and easily start up the highly productive punch-laser machine Trumatic 5000 from Trumpf. So far, the production staff has to individually test the NC program at the machine each time it wants to produce an order with as yet unknown geometries or materials. Especially with fully automated machines, which produce many different sheet metal parts, this results in unproductive idle times. The AI-supported software "Runability Guide" shortens the processes when setting up the punch-laser system by up to 20 minutes.

Stored expertise

The software shows professionals using different evaluation models for each order whether the Trumatic 5000 punch-laser machine can directly produce the components or whether manual interventions are expected. "Our 'Runability Guide' gives companies productivity and competitive advantages. They not only save time, but can also use the expertise of their staff for value-adding tasks or train new staff," says Jonathan Eberle, project manager in development at Trumpf.

Software assesses complexity

When a machine manufactures in an automated way, mistakes can occur. For example, it can happen that the automation cannot correctly remove a sheet metal part from the residual grid due to jamming. This leads to a standstill. A production worker has to manually remove the sheet metal from the machine room and restart the machine. Whether the component can be removed reliably depends, among other things, on its geometry and the position of the grippers on the workpiece. The "Runability Guide" software now checks, for example, how much the component bends due to gravity when removed and could thus cause jamming. If a predetermined limit value is exceeded, the software marks the corresponding point in red. In this way, the staff immediately recognises which components of an order need to be readjusted. In addition to details about possible errors, the software also gives a recommendation on which orders are suitable for the night shift. "Normally, an experienced expert would have to assess the geometry of the component, the material, the sheet thickness and other factors. Our solution makes this decision AI-supported and learns more in the future," says Jonathan Eberle.

Quickly and reliably evaluated

The software uses different models to determine the complexity of a component. For this purpose, the experts of the machine manufacturer continuously provide extensive knowledge from production in the cloud. In addition, the software carries out the evaluation using physical simulations and AI to identify possible challenges in the process steps. It also works with the real machine data of users of the punch-laser machine. This allows conclusions to be drawn about error sources in the processing. "Once all models have checked the order, the tool delivers its forecast. Traditional physical simulation models would need up to one hour for the forecast, depending on the component. Thanks to AI, we can significantly speed up this process and make it practically real-time for our customers," says Jonathan Eberle.

Optimize with machine data from users

Companies that invest in a Trumatic 5000 punch-laser machine now additionally receive the "Runability Guide" software as part of the system. However, they will need to provide data from their production in the future, which the manufacturer can use for its AI in the cloud. "Unlike traditional software, users start with a small range of functions. With their data from production, they then help us to continuously improve the software. This in turn benefits the users. Such new development approaches are needed to create added value with data and AI in production," says Jonathan Eberle.

(kmu)