Quality Assurance in Engine Production Vision On Line Automates Fan Inspection at US Manufacturer With Customized Image Processing

From Manuel Christa | Translated by AI 2 min Reading Time

Related Vendors

A major American corporation relies on automatic image processing from Vision On Line for the production of fans for diesel engines. The aim: to detect faults early, prevent failures and ensure the quality of engine components.

A major US manufacturer ensures the quality of its motor fans with image processing.(Image: AI-generated)
A major US manufacturer ensures the quality of its motor fans with image processing.
(Image: AI-generated)

When diesel engines overheat, the cause is often an inconspicuous but crucial component: the fan. Without it, the necessary cooling is lacking - in extreme cases, there is a risk of costly engine damage. To prevent this, a globally active US manufacturer has been inspecting its fans with automated image processing systems from Vision On Line since the beginning of 2024. The systems are used in the production of fans for trucks, construction machinery and other commercial vehicles.

The aim was to increase automation and ensure that only flawless fans enter the drive systems. Vision On Line took over the planning, integration and commissioning of the systems, which are now in use at four test stations.

Gallery
Gallery with 5 images

Fans with data matrix and millimeter tolerance

The inspection process starts with the reading of a data matrix code, which is centrally located on a piece of black-painted metal. This contains all relevant information about the fan model. After successful recognition, the stored target values are loaded. The vision system then checks the number, shape and size of the fan blades - and even detects minimal material defects. Tolerances of up to ±1 mm are reliably checked. Deviating components are automatically ejected and sorted out or reworked depending on the type of defect.

The main challenge was the size of the components: Diameters of up to 800 millimeters require a large field of vision. Vision On Line therefore opted for specially developed LED lighting from Büchner Lichtsysteme's TLS series with a 600 x 600 mm illuminated area. 3,500 blue LEDs provide a high light intensity, which is precisely directed onto the test object using an adapted camera mount.

Technology in detail: lighting, camera, controls

At the heart of the system is a 20-megapixel exo183MGE camera from the Bavarian manufacturer SVS-Vistek. It achieves a data rate of up to 120 MB/s and transmits the images via a GigE Vision interface. The Halcon library from MVTec is used for evaluation. The camera's integrated strobe control allows precise control of the LEDs without an additional controller, which saves space and costs.

In addition, image processing was integrated into the manufacturer's existing control system. The results of the inspection are directly transferred, documented and control the further production process. Manual reworking of faulty components is also carried out on the basis of this data.

Expansion of image processing planned

With the four systems installed, the Group was able to increase its productivity and identify quality defects at an early stage. The positive experiences have since triggered further discussions: Other manufacturing processes are also to be automated with image processing solutions from Vision On Line in the future. For Managing Director Andreas Schaarschmidt, this is proof that investments in precise quality control are worthwhile: "Vision On Line has implemented a powerful image processing solution for the quality inspection of motor fans within just a few months." (mc)

Subscribe to the newsletter now

Don't Miss out on Our Best Content

By clicking on „Subscribe to Newsletter“ I agree to the processing and use of my data according to the consent form (please expand for details) and accept the Terms of Use. For more information, please see our Privacy Policy. The consent declaration relates, among other things, to the sending of editorial newsletters by email and to data matching for marketing purposes with selected advertising partners (e.g., LinkedIn, Google, Meta)

Unfold for details of your consent