Fountain -- an intelligent contextual assistant combining knowledge representation and language models for manufacturing risk identification

TL;DR

Fountain is an intelligent assistant that combines domain-specific language models and knowledge graphs to identify manufacturing risks early, providing explainable and consistent recommendations within deviation management workflows.

Contribution

The paper introduces Fountain, a novel contextual assistant integrating fine-tuned language models and knowledge graphs for risk identification in manufacturing processes.

Findings

Effective risk identification in manufacturing deviations

Model adaptation feasible with moderate infrastructure

Inference can be performed on CPU-only instances

Abstract

Deviations from the approved design or processes during mass production can lead to unforeseen risks. However, these changes are sometimes necessary due to changes in the product design characteristics or an adaptation in the manufacturing process. A major challenge is to identify these risks early in the workflow so that failures leading to warranty claims can be avoided. We developed Fountain as a contextual assistant integrated in the deviation management workflow that helps in identifying the risks based on the description of the existing design and process criteria and the proposed deviation. In the manufacturing context, it is important that the assistant provides recommendations that are explainable and consistent. We achieve this through a combination of the following two components 1) language models finetuned for domain specific semantic similarity and, 2) knowledge representation in the form of a property graph derived from the bill of materials, Failure Modes and Effect Analysis (FMEA) and prior failures reported by customers. Here, we present the nuances of selecting and adapting pretrained language models for an engineering domain, continuous model updates based on user interaction with the contextual assistant and creating the causal chain for explainable recommendations based on the knowledge representation. Additionally, we demonstrate that the model adaptation is feasible using moderate computational infrastructure already available to most engineering teams in manufacturing organizations and inference can be performed on standard CPU only instances for integration with existing applications making these methods easily deployable.