The project aims to integrate a deep learning neural model for the control of tank boosting systems on an embedded system platform. The selected model optimizes the management of the fluid transfer process using a combination of artificial intelligence techniques, specifically deep learning and reinforcement learning. In this context, the study encompasses the development, integration, and subsequent analysis of neural models with embedded devices, particularly the ESP32. The results demonstrate that such devices can be effectively utilized for IoT applications, enabling intelligent and decentralized control with a high degree of precision compared to higher-capacity devices.
