AdditiveLLM: Large Language Models Predict Defects in Additive Manufacturing

TL;DR

This paper demonstrates that large language models, when fine-tuned on additive manufacturing data, can accurately predict defect regimes from process parameters, aiding process optimization.

Contribution

It introduces AdditiveLLM, a fine-tuned LLM that predicts additive manufacturing defects with high accuracy and explores input formatting methods for improved performance.

Findings

Achieved 93% accuracy in defect prediction.

Natural language prompts simplify process parameter selection.

Models perform robustly on sparse and natural language datasets.

Abstract

In this work we investigate the ability of large language models to predict additive manufacturing defect regimes given a set of process parameter inputs. For this task we utilize a process parameter defect dataset to fine-tune a collection of models, titled AdditiveLLM, for the purpose of predicting potential defect regimes including Keyholing, Lack of Fusion, and Balling. We compare different methods of input formatting in order to gauge the model's performance to correctly predict defect regimes on our sparse Baseline dataset and our natural language Prompt dataset. The model displays robust predictive capability, achieving an accuracy of 93\% when asked to provide the defect regimes associated with a set of process parameters. The incorporation of natural language input further simplifies the task of process parameters selection, enabling users to identify optimal settings specific to their build.