Abstract:In this paper we present a publicly-available maintenance ontology (Iof-maint). Iof-maint is a modular ontology aligned with the Industrial Ontology Foundry Core (IOF Core) and contains 20 classes and 2 relations. It provides a set of maintenance-specific terms used in a wide variety of practical data-driven use cases. Iof-maint supports OWL DL reasoning, is documented, and is actively maintained on GitHub. In this paper, we describe the evolution of the Iof-maint reference ontology based on the extraction of common concepts identified in a number of application ontologies working with industry maintenance work order, procedure and failure mode data.
Abstract:In this paper we present the first investigation into the effectiveness of Large Language Models (LLMs) for Failure Mode Classification (FMC). FMC, the task of automatically labelling an observation with a corresponding failure mode code, is a critical task in the maintenance domain as it reduces the need for reliability engineers to spend their time manually analysing work orders. We detail our approach to prompt engineering to enable an LLM to predict the failure mode of a given observation using a restricted code list. We demonstrate that the performance of a GPT-3.5 model (F1=0.80) fine-tuned on annotated data is a significant improvement over a currently available text classification model (F1=0.60) trained on the same annotated data set. The fine-tuned model also outperforms the out-of-the box GPT-3.5 (F1=0.46). This investigation reinforces the need for high quality fine-tuning data sets for domain-specific tasks using LLMs.
Abstract:The recent explosion in low-cost, low-power wireless microcontrollers, coupled with low-power, robust MEMS sensors has opened up the opportunity to create new forms of low-cost Industrial Internet-of-Things (IIoT) devices for condition monitoring. Piezoelectric MEMS microphones constructed with a cantilever diaphragm are a potential solution against failure modes, such as water and dust ingress, that have challenged the use of capacitive MEMS microphones in industrial applications. In this paper, we couple a pair of piezoelectric MEMS microphones to a COTS microcontroller to create a stand-alone microphone array capable of discerning the direction of a noise source. The microphone array is designed to acquire sound data without aliasing at frequencies of 2000 Hz or below. Testing is conducted in an anechoic chamber. We compare the performance of this microphone array to a simple idealized theoretical model. The experimental results obtained in the anechoic chamber compare well with the theoretical model. The work stands as a proof-of-principle. By providing detailed information on how we coupled the sensors to a COTS microcontroller, and the open-source code used to process the data, we hope that others will be able to build upon this work by expanding on both the number and type of sensors used.