Guideline for Deployment of Machine Learning Models for Predictive Quality in Production

CC BY-NC-ND 4.0Heymann, HenrikHenrikHeymannKies, Alexander D.Alexander D.KiesFrye, MaikMaikFryeSchmitt, Robert H.Robert H.SchmittBoza, AndrésAndrésBoza2022-09-202024-03-262022-09-202022-05-26https://publica.fraunhofer.de/handle/publica/425840https://doi.org/10.24406/h-42584010.1016/j.procir.2022.05.06810.24406/h-4258402-s2.0-85132306456Predicting product quality represents a common area of application of machine learning (ML) in manufacturing. However, manifold challenges occur during the integration of ML models into production processes. Therefore, this paper aims to provide a guideline for the deployment of ML models in production environments. Relevant decisions and steps for deploying models in predictive quality use cases are demonstrated. The results for each component of the proposed guideline - deployment design, productionizing & testing, monitoring, and retraining - have been validated with industry experts including exemplary implementations.enArtificial IntelligenceDeploymentMachine LearningManufacturingPredictive QualityProductionDDC::600 Technik, Medizin, angewandte Wissenschaften::620 IngenieurwissenschaftenGuideline for Deployment of Machine Learning Models for Predictive Quality in Productionjournal article