process optimization

This study aims to investigate the role of digital twins in enhancing the efficiency, quality, and competitiveness of small manufacturers, identifying key motivations, impacts, challenges, and future benefits. This qualitative study employed semi-structured interviews to gather in-depth insights from 28 key stakeholders in small manufacturing businesses that have implemented digital twin technology. Participants included business owners, operations managers, and IT specialists. The data were transcribed and analyzed using NVivo software, following a thematic analysis approach to identify and categorize recurring themes and concepts. The analysis revealed four main themes: Adoption of Digital Twins, Impact on Manufacturing Efficiency, Challenges and Barriers, and Future Outlook and Benefits. Key motivations for adoption included cost reduction, efficiency improvement, and competitive advantage. Digital twins significantly enhanced manufacturing efficiency through process optimization, quality control, and cost management. Major challenges encompassed technical barriers, financial constraints, organizational resistance, and regulatory issues. The future outlook for digital twins was positive, with potential long-term benefits and advancements in AI and IoT expected to further enhance their capabilities. Digital twins offer substantial benefits for small manufacturing businesses, including improved efficiency, quality control, and cost management. However, successful implementation requires addressing technical, financial, and organizational challenges. With continued technological advancements and strategic support, digital twins are likely to become integral to small manufacturers, driving innovation and competitiveness in the industry.

This study compares three machine learning algorithms (Multilayer Perceptron Neural Network (MLP), Random Forest (RF), and Decision Tree (DT)) for modeling biodiesel production. For this purpose the synthesis methods (UIMS, MS, FPUI, PUI), the methanol to oil ratio (3:1 to 15:1) and reaction times (5–50 minutes), were considered as input parameters and the percentage of biodiesel production was considered as the output of the model. According to the results, the MLP model demonstrated superior predictive performance, with an R² score of 0.9800, RMSE of 3.28, and MAE of 2.35, significantly outperforming RF (R² = 0.8892) and DT (R² = 0.8500). Also, the neural network model represents that all parameters (reaction time, methanol to oil ratio, and synthesis method) hold nearly equal importance. Based on the neural network model, the optimal synthesis conditions are: the UIMS method, a reaction time of 47 minutes, and a methanol-to-oil ratio of 5.8:1, yielding a predicted conversion of 98%.