Search results
1 – 3 of 3Armindo Lobo, Paulo Sampaio and Paulo Novais
This study proposes a machine learning framework to predict customer complaints from production line tests in an automotive company's lot-release process, enhancing Quality 4.0…
Abstract
Purpose
This study proposes a machine learning framework to predict customer complaints from production line tests in an automotive company's lot-release process, enhancing Quality 4.0. It aims to design and implement the framework, compare different machine learning (ML) models and evaluate a non-sampling threshold-moving approach for adjusting prediction capabilities based on product requirements.
Design/methodology/approach
This study applies the Cross-Industry Standard Process for Data Mining (CRISP-DM) and four ML models to predict customer complaints from automotive production tests. It employs cost-sensitive and threshold-moving techniques to address data imbalance, with the F1-Score and Matthews correlation coefficient assessing model performance.
Findings
The framework effectively predicts customer complaint-related tests. XGBoost outperformed the other models with an F1-Score of 72.4% and a Matthews correlation coefficient of 75%. It improves the lot-release process and cost efficiency over heuristic methods.
Practical implications
The framework has been tested on real-world data and shows promising results in improving lot-release decisions and reducing complaints and costs. It enables companies to adjust predictive models by changing only the threshold, eliminating the need for retraining.
Originality/value
To the best of our knowledge, there is limited literature on using ML to predict customer complaints for the lot-release process in an automotive company. Our proposed framework integrates ML with a non-sampling approach, demonstrating its effectiveness in predicting complaints and reducing costs, fostering Quality 4.0.
Details
Keywords
Athina Karatzogianni, Korinna Patelis, Fenia Ferra and Ioanna Ferra
Indrajeet Katti, Alistair Jones, Matthias Weiss, Dong Qiu, Joy H. Forsmark and Mark Easton
Powder bed fusion-laser beam (PBF-LB) is a rapidly growing manufacturing technology for producing Al-Si alloys. This technology can be used to produce high-pressure die-casting…
Abstract
Purpose
Powder bed fusion-laser beam (PBF-LB) is a rapidly growing manufacturing technology for producing Al-Si alloys. This technology can be used to produce high-pressure die-casting (HPDC) prototypes. The purpose of this paper is to understand the similarities and differences in the microstructures and properties of PBF-LB and HPDC alloys.
Design/methodology/approach
PBF-LB AlSi10Mg and HPDC AlSi10Mn plates with different thicknesses were manufactured. Iso-thermal heat treatment was conducted on PBF-LB bending plates. A detailed meso-micro-nanostructure analysis was performed. Tensile, bending and microhardness tests were conducted on both alloys.
Findings
The PBF-LB skin was highly textured and softer than its core, opposite to what is observed in the HPDC alloy. Increasing sample thickness increased the bulk strength for the PBF-LB alloy, contrasting with the decrease for the HPDC alloy. In addition, the tolerance to fracture initiation during bending deformation is greater for the HPDC material, probably due to its stronger skin region.
Practical implications
This knowledge is crucial to understand how geometry of parts may affect the properties of PBF-LB components. In particular, understanding the role of geometry is important when using PBF-LB as a HPDC prototype.
Originality/value
This is the first comprehensive meso-micro-nanostructure comparison of both PBF-LB and HPDC alloys from the millimetre to nanometre scale reported to date that also considers variations in the skin versus core microstructure and mechanical properties.
Details