Assisted diagnostics methodology

Together with one of our industrial partners, we have developed an end-to-end model-based methodology to assist the diagnostics of existing problems and to predict upcoming issues within complex production chains. The purpose is to resolve such problems by either an intervention (service action, repairs) or compensative actions via adaptive control. The assisted aspect of the diagnostics methodology implies automated data analysis and the timely detection of issues, as well as guiding experts through a structured and consistent flow of complex diagnostics steps.

The result of this assistance is gains in the diagnostics efficiency and operational optimization of the high-tech process chains.

The diagnostics flow usually encompasses a monitoring step (in which equipment and products-in-progress are measured regularly during processing to identify anomalies from normal operation or specification), a root-cause analysis step to identify the root causes of anomalies and an intervention step in which service actions or repairs are used to resolve the issues. The basis for conducting the diagnostics is operational data, which often come from various (unstructured) sources such as interface logging, machine log files, calibration and test results and job reports. These need to be continuously combined and analyzed.

Our methodology builds on models from two main knowledge sources – experts and data – including techniques such as domain-specific languages to enable domain modeling, data analysis to discover knowledge and probabilistic analysis models for assisted root cause analysis.

The generic nature of the methodology allows for its application in other technical areas such as large-scale distributed Internet of Things platforms (e.g. intelligent lighting systems), as well as for other purposes such as the prognostics of end-product performance.

The developed methodology was demonstrated in our partner use-case. The demonstrator follows the diagnostics flow presented above and is driven by a probabilistic engine built in a systematic manner on the basis of data and experts.

Please contact us for further details and a showcase of the demonstrator.