Air bubble detection in water flow by means of ai-assisted infrared reflection system
This letter introduces an innovative, cost-effective solution for detecting air bubbles in water flow systems using an AI-assisted infrared reflection system. In industries, such as chemical, mechanical, oil, and nuclear, the presence of air bubbles in fluids can compromise both product quality and...
| Autores: | , , , |
|---|---|
| Tipo de recurso: | artículo |
| Estado: | Versión aceptada para publicación |
| Fecha de publicación: | 2024 |
| País: | España |
| Institución: | Universidad Pública de Navarra |
| Repositorio: | Academica-e. Repositorio Institucional de la Universidad Pública de Navarra |
| OAI Identifier: | oai:academica-e.unavarra.es:2454/52573 |
| Acceso en línea: | https://hdl.handle.net/2454/52573 |
| Access Level: | acceso abierto |
| Palabra clave: | Electromagnetic wave sensors Artificial intelligence Bubble detection Machine learning Principal component analysis (PCA) Support vector machine (SVM) |
| Sumario: | This letter introduces an innovative, cost-effective solution for detecting air bubbles in water flow systems using an AI-assisted infrared reflection system. In industries, such as chemical, mechanical, oil, and nuclear, the presence of air bubbles in fluids can compromise both product quality and process efficiency. Our research develops a system that combines infrared optical sensors with machine learning algorithms to detect and quantify bubble presence effectively. The system’s design utilizes infrared emitters and photodetectors arranged around a pipe to capture detailed data on bubble characteristics, which is then analyzed using a support vector machine (SVM) model to predict bubble concentrations. Experimental results demonstrate the system’s ability to accurately identify different levels of bubble presence, offering significant improvements over existing methods. Key performance metrics include a mean squared error of 0.0694, a root mean squared error of 0.2634, and a coefficient of determination of 0.9765, indicating high accuracy and reliability. This approach not only enhances operational reliability and safety but also provides a scalable solution adaptable to various industrial settings. |
|---|