Corrigendum to “A Novel MILP Model for the Production, Lot Sizing, and Scheduling of Automotive Plastic Components on Parallel Flexible Injection Machines with Setup Common Operators”

Enhancing manufacturing operations with synthetic data: a systematic framework for data generation, accuracy, and utility

“…Studies have showcased synthetic data generation's efficacy in enhancing machine learning models' performance by balancing data sets and enriching training data (Han et al, 2019;Kim et al, 2020). Synthetic data sets have also been used to evaluate algorithm and model performance (Laxman et al, 2007;Andres et al, 2021). To complement limited real-world data for model training, a Generative Adversarial Network (GAN) is utilized for synthetic data generation, improving defect detection in models (da Silva et al, 2021).…”

“…Recognizing this remarkable opportunity and necessity, various industries have integrated data-driven applications, propelling foundational research towards synthetic data. Many studies, for instance, utilize synthetic data to enhance manufacturing processes, including process monitoring (Fecker et al, 2013), quality inspection (Nguyen et al, 2022), production scheduling (Andres et al, 2021), and process optimization (Apornak et al, 2021). Despite considerable progress in enhancing production efficiency, reducing waste, and improving product quality, notable challenges remain in generating synthetic data for the development and validation of innovative assembly models and algorithms, particularly with real-world production data (Tao et al, 2018).…”