NLP for Maintenance Report Analysis in Machine Tools

Experiment description:

The decision support system developed in this experiment aims to facilitate the identification of faults in a machine. Maintenance, repair and troubleshooting normally demand the presence of an expert. However, the growing complexity of machines and the difficulty in finding skilled operators raises serious concerns in this regard. Currently, troubleshooting tools are developed as context-specific solutions and are often based on rigid and inefficient logic, hindering their adoption and use.
FASSI S.p.A., a hydraulic crane manufacturer and partner of Intellimech, currently uses a basic troubleshooting tool. It provided the maintenance reports’ initial dataset and its knowledge to validate the proposed solution in a relevant environment.

Experiment results:

The tool developed in AI REGIO consists of a probabilistic decision support system. The tool identifies machine faults based on the analysis of visible symptoms.
To this end, the knowledge concerning the machine/process is organised as an association between each fault and the probability of questions related to specific symptoms being answered positively. Thus, expert knowledge is represented as the likelihood of showing specific symptoms for each fault. At the beginning of the troubleshooting, the tools use Natural Language Processing to select the most appropriate question to ask based on a user description of the issue. The input can be provided orally through a speech-to-text interface, making the system intuitive and easy to interact with.
Then, by using an algorithm to minimize the number of questions necessary and speed up the identification process, the system selects and asks a series of questions regarding the symptoms. Based on the operator’s responses, which can be “Yes”, “Don’t Know”, or “No”, the system identifies the most probable fault.

This project has received funding from the European Union’s Horizon 2020 research and innovation programme under grant agreement N. 952003

I nostri contatti