Machine learning algorithms for manufacturing quality assurance: A systematic review of performance metrics and applications
Алгоритмы машинного обучения для обеспечения качества производства: систематический обзор показателей эффективности и областей применения
2025-03-26
SCID: 54.1/vzubpbgx
Discuss with AI
defect detectionmachine learning algorithmsmanufacturing quality assuranceperformance metricspredictive maintenance
Figures from the paper
Abstract (AI)
Adopting Machine Learning (ML) in manufacturing quality assurance (QA) has accelerated with Industry 4.0, enabling automated defect detection , predictive maintenance , and real-time process optimization. However, selecting the most effective ML model remains challenging due to performance variability, scalability constraints, and inconsistent evaluation metrics across manufacturing sectors. This systematic review analyzes over 300 peer-reviewed studies over the last two decades (mostly analyzing the recent works) to evaluate the effectiveness of widely used ML algorithms—Artificial Neural Networks (ANNs), Support Vector Machines (SVMs), Random Forests (RFs), Decision Trees (DTs), and K-Nearest Neighbors (KNN)—in QA applications. Performance metrics include accuracy, precision, speed, recall, computational efficiency, scalability, and real-time processing capabilities. Findings reveal that ANNs outperform other models in image-based defect detection, while SVMs and RFs excel in predictive maintenance and process parameter optimization. DTs provide better interpretability for process control, and KNN is effective for small-scale QA implementations. In specific case scenarios, RF models showed particular strength in handling high-dimensional sensor data in fault detection in manufacturing quality assurance operations. The study presents a comparative assessment framework, guiding algorithm selection based on industry-specific requirements and operational constraints. This review provides the latest implementation of ML in QA along with quantitative evidence on which algorithm offers the most optimization in specific industrial settings, which would help in algorithm selection in manufacturing quality assurance in future for both researchers and industrial experts. Also, it offers an overview of the major and minor algorithms based on their performance metrics.
Key Findings
1
Artificial Neural Networks outperform other reviewed models for image-based manufacturing defect detection.
2
Decision Trees offer superior interpretability for process control, while K-Nearest Neighbors is effective for small-scale quality assurance implementations.
3
Random Forests are particularly strong for fault detection involving high-dimensional sensor data, motivating algorithm selection based on industrial constraints and requirements.
4
Support Vector Machines and Random Forests excel in predictive maintenance and process parameter optimization applications.
5
The systematic review analyzes over 300 peer-reviewed studies on machine learning algorithms for manufacturing quality assurance across the past two decades.
Research Object
Machine-learning algorithms applied to manufacturing quality assurance
Research Subject
Comparative effectiveness, performance metrics, scalability, computational efficiency, interpretability, and application-specific suitability of ML algorithms for defect detection, predictive maintenance, process control, and process parameter optimization
Publication Details
Publication Date
2025-03-26
Journal
Publisher
ISSN
Cited by
88
Open access PDF
Access Type
Author Information
Download PDF
Subscribe to digest
References available in scid.ai11
ImageNet classification with deep convolutional neural networks2017
XGBoost2016
Convergence of Edge Computing and Deep Learning: A Comprehensive Survey2020
Machine Learning and Deep Learning frameworks and libraries for large-scale data mining: a survey2019
A Survey of Methods for Explaining Black Box Models2018
Machine learning for estimation of building energy consumption and performance: a review2018
Performance Analysis of IoT-Based Sensor, Big Data Processing, and Machine Learning Model for Real-Time Monitoring System in Automotive Manufacturing2018
Machine learning and deep learning based predictive quality in manufacturing: a systematic review2022
Digital Twins Driven Supply Chain Visibility within Logistics: A New Paradigm for Future Logistics2021
Implementation of Cyber-Physical Production Systems for Quality Prediction and Operation Control in Metal Casting2018
Deep Learning and Computer Vision Techniques for Enhanced Quality Control in Manufacturing Processes2024