AutoInspect improves the quality of industrial inspection processes

Quality controls are an integral part of industrial manufacturing. Sensors at various inspection stations measure the properties and quality characteristics of the test object. In automotive construction, for example, it can be the dimensions of clearances, the quality of paint or the strength of certain parts, to name just a few examples. During the numerous inspections, some of which are sensor-based and some manual, a large amount of data and measured values ​​are generated, providing precise information about the characteristic being measured in each case. But there is a problem: all this data is usually stored separately from each other, writes the Fraunhofer Institute in a press release.

Recently, a team of researchers from the Fraunhofer Institute for Optronics, System Technologies and Image Exploitation IOSB developed AutoInspect, a solution that combines a wide variety of inspection modalities in a single system and connects all results. Researchers brought together a wide range of sensors, interfaces and software to create an easily adaptable all-in-one solution. AutoInspect Project Manager Henning Schulte says, “The wealth of data generated at sensor-based inspection points is a valuable treasure trove of hidden information. By linking them, we are able to unearth this treasure. AutoInspect provides a consolidated overview and enables intelligent evaluation of all relevant inspection data and measured values. In this way, previously unrecognized interrelationships in the manufacturing process suddenly become visible. This makes it easier to identify the causes of defects, which makes the whole production process more efficient. Ultimately, it also improves the quality of the products.

Sensor data and location information

One of the strengths of AutoInspect is the possibility to combine the inspection results with the respective location information: the first step is to create a 3D mesh of the test object based on existing CAD models of the product. However, this representation in the software goes much further than a classic 3D computer graphics of an object. Indeed, each measured value is stored with reference to this 3D mesh, that is to say with the precise location of the measurement position on the object to be tested. This creates a digital twin that contains all relevant sensor data, including associated location information, as well as meta-information such as the batch number of the material used or the time of the inspection.

Consolidated inspection overview

In this way, a consolidated overview of all inspection data is created, which, assuming the appropriate inspection stations are in place, can cover the entire production process. From the clamping of the first sheet, the shaping of the sheets and the various bonding and welding processes to the application of the paint. By linking the measured values ​​in the AutoInspect software, it is now possible to identify, for example, that a deviation dimension is still too large at a certain point if a certain temperature limit value is exceeded during a step previous machining. The workshop inspection team can then act on this advice, analyze the cause and ultimately solve the problem. This in turn is reflected in the changed data and measured values ​​in the 3D mesh. By adopting this approach, inspection and production merge seamlessly into an optimized and highly efficient overall process.

“We thus help our industrial customers to better understand often complex production quality issues and to understand them more quickly by allowing them to intelligently analyze all the inspection data linked throughout the process”, Schulte summarizes. The requirement here is that the Autoinspect software, which collects all sensor data and enables evaluation with graphical tools, is configured correctly.

Standard interfaces for sensors

The Fraunhofer IOSB team developed and tested the technology with sensors for 3D scanning as well as deflectometry and ellipsometry. Ellipsometry, for example, is able to determine the thickness of a surface coating by recording the polarization state of reflected light. Deflectometry measures and inspects the shape of specular or high gloss surfaces such as painted sheet metal. These measurement techniques and their further development have been a separate research topic at the Fraunhofer IOSB for years.

However, the Fraunhofer solution is not tied to specific sensors, instead relying on the open OPC UA (OPC Unified Architecture) interface. “Any OPC UA-compatible sensor or measuring device can be easily integrated into AutoInspect via plug and play,” says Schulte. In addition, it is possible for a worker to perform manual inspections assisted by augmented reality.

Ideal for machine and vehicle inspections

The evaluation of measurement results is not limited to the current or just completed production process. The history of inspection results in AutoInspect can be analyzed beyond the current batch or manufacturing process. This makes it possible to observe the product life cycle of machines or vehicles through maintenance and inspection intervals. For example, measurement data from previous inspections could be taken into account when inspecting the frame and wheel tires of an ICE train to better understand the latest measured values.

Especially when inspecting safety-relevant components, the ability to consider all maintenance cycles, including all AutoInspect data, means that the causes of faults can be identified more quickly. Ideally, problems can even be detected in advance using AI-based data analysis and the security of the affected machine or plant can be quickly restored.

Fraunhofer IOSB will present a demonstrator at the joint Fraunhofer stand at Hannover Messe 2022 from May 30 to June 2 (Hall 5, Stand A06).