Unimetrik is a Metrological Service company, oriented to offer solutions for the industry related to Calibration, Measurement and Metrological engineering. UNIMETRIK is accredited by ENAC and acknowledged by the principal aeronautic groups in Spain. It is exporting its technology to countries such as USA, Germany, Brazil and the Czech Republic.

Unimetrik is part of Innovalia Metrology, with the strategy of create and develop projects in a flexible way. For this reason, multi-disciplinary teams are formed, joining efforts from the different companies in order to achieving the particular objectives of each project. The team at the company holds great relations established with the biggest Technological Centers of the world. All the team meets the technical and administrative requirements, what together with its wide knowledge of this sector in the Basque Country, Spain and the rest of the world, facilitates the growing penetration in the global market by Unimetrik.

Problem description

The technology that is currently being imposed for the realization of dimensional quality controls is optical technology, since it allows the acquisition of a large amount of information in a much shorter time than probing technology. As a consequence, the number of pieces controlled is much higher. On the other hand, the amount of information that is handled is much greater, a point cloud of a car door can have 15 million points; therefore, the management and calculation algorithms have to be optimized to the maximum.

Currently, the optical measurement system has its own information processing software parameterizable associated with it and depending on the operator, one result or another will be obtained, which the developers design as a “black box” making it difficult to verify the how they process this information. Therefore, due to the large number of data processing SWs and the existence of discrepancies between the results obtained by each of them, it is necessary to optimize the parametrization of the algorithms, which allows us to obtain optimal results and validate what is developed in the project.

In practice, XMANAI AI models will be able to help critically (in the case of an inexperienced metrologist, for example) in approaching the measurement process. To do this, XMANAI will increase the speed of metrological analysis (more productive) and guide engineers to plan strategy (efficiency) sometimes finding new innovative methods. Explanations of why certain decisions / recommendations are made will keep engineers on a dynamic cycle and speed up the analysis in an informed manner. For the above reasons, the demonstration app to be developed is characterized by being semi-autonomous, since the XMANAI AI models will help with recommendations and strategies, but in the end, it is the engineer who decides how to approach the metrological study. Through the changes to be introduced during the demonstration, XMANAI will make UNIMETRIK metrological software an intelligent and training environment that improves quality control prior to measurement planning definition and indirectly contributes to generative design.

The XMANAI program will affect, above all, two crucial points in the UNIMETRIK measurement process: on the one hand, in the generation of an optimal point cloud (XMANAI 1), in which its density will be analyzed; and, on the other hand, based on that optimal point cloud, the program will recommend optimal measurement plan parameters (XMANAI 2) along with the level of precision with which the measurement will be achieved.

Expected Results

The expected benefits are:

  • Intelligent measurement software that warns that the point sets defined for the measurement strategy are adequate, that is, that warns us if the measurement is correct.
  • That the system is able to suggest other point sets so that the measurement is more accurate and correct.
  • An intelligent software that is capable of proposing point sets when the geometries to be measured are not standard.