In situ process quality monitoring and defect detection for direct metal laser melting

TL;DR

This paper presents two in-process fault detection methods for Direct Metal Laser Melting that utilize sensor data and machine signals to predict defects early, reducing costs associated with post-process inspections.

Contribution

It introduces novel sensor-based features and Bayesian and regression models for real-time quality monitoring in DMLM with minimal hardware changes.

Findings

Effective defect detection using sensor data

Accurate severity prediction of material defects

Methods deployable on existing DMLM systems

Abstract

Quality control and quality assurance are challenges in Direct Metal Laser Melting (DMLM). Intermittent machine diagnostics and downstream part inspections catch problems after undue cost has been incurred processing defective parts. In this paper we demonstrate two methodologies for in-process fault detection and part quality prediction that can be readily deployed on existing commercial DMLM systems with minimal hardware modification. Novel features were derived from the time series of common photodiode sensors along with standard machine control signals. A Bayesian approach attributes measurements to one of multiple process states and a least squares regression model predicts severity of certain material defects.