Publicação
Towards a functional architecture for integrating ai techniques to enhance kpi management and production performance: a mechatronics industry perspective
| Resumo: | In the rapidly evolving mechatronics industry, optimizing manufacturing productivity is essential for maintaining competitiveness and sustainability. This research aims to develop a functional architecture that integrates AI technologies, such as machine learning and predictive analytics, to improve KPI management. The framework seeks to enhance KPI management by optimizing individual performance metrics and promoting collaboration among companies to share experiences and results. The study will validate three key hypotheses about the impact of AI-driven KPI management on production performance, decision-making, and sustainability. The first hypothesis (H1) explores whether AI-driven KPI management frameworks lead to improvements in operational efficiency, quality, and productivity, using regression analysis of data from IoT sensors that monitor machine performance. The second hypothesis (H2) examines how predictive analytics and machine learning models in KPI systems enhance real-time decision-making. Time-series analysis and neural networks will be applied to data from ERP and MES systems to assess decision-making improvements. The third hypothesis (H3) investigates the integration of ecological KPIs using Life Cycle Assessment (LCA) tools. Econometric models, such as the Cobb-Douglas production function, will be used to quantify the impact of green manufacturing practices on production efficiency and sustainability. The results provide actionable insights for stakeholders, demonstrating how integrating AI technologies into a KPI framework can significantly improve productivity and sustainability in the mechatronics sector. |
|---|---|
| Autores principais: | Khelia, Amani |
| Assunto: | Técnicas de IA Gestão de KPI Análises preditivas Aprendizado de máquina Sustentabilidade |
| Ano: | 2025 |
| País: | Portugal |
| Tipo de documento: | dissertação de mestrado |
| Tipo de acesso: | acesso aberto |
| Instituição associada: | Instituto Politécnico de Bragança |
| Idioma: | inglês |
| Origem: | Biblioteca Digital do IPB |
| Resumo: | In the rapidly evolving mechatronics industry, optimizing manufacturing productivity is essential for maintaining competitiveness and sustainability. This research aims to develop a functional architecture that integrates AI technologies, such as machine learning and predictive analytics, to improve KPI management. The framework seeks to enhance KPI management by optimizing individual performance metrics and promoting collaboration among companies to share experiences and results. The study will validate three key hypotheses about the impact of AI-driven KPI management on production performance, decision-making, and sustainability. The first hypothesis (H1) explores whether AI-driven KPI management frameworks lead to improvements in operational efficiency, quality, and productivity, using regression analysis of data from IoT sensors that monitor machine performance. The second hypothesis (H2) examines how predictive analytics and machine learning models in KPI systems enhance real-time decision-making. Time-series analysis and neural networks will be applied to data from ERP and MES systems to assess decision-making improvements. The third hypothesis (H3) investigates the integration of ecological KPIs using Life Cycle Assessment (LCA) tools. Econometric models, such as the Cobb-Douglas production function, will be used to quantify the impact of green manufacturing practices on production efficiency and sustainability. The results provide actionable insights for stakeholders, demonstrating how integrating AI technologies into a KPI framework can significantly improve productivity and sustainability in the mechatronics sector. |
|---|