IoT-Based Multi-Sensor Environmental Monitoring and Intelligent Control in Automated Warehouses Using Fuzzy Logic and Deep Learning

Abstract

Logistics companies are automating facilities, increasing demand for advanced environmental monitoring and control solutions. Manual inspections and static criteria cannot manage modern warehouses' dynamic environments. This study proposes an automated warehouse environmental monitoring and intelligent control approach using IoT technology to improve warehouse environmental management efficiency, energy consumption, and cargo storage quality. A multi-sensor network-based system measures temperature, humidity, and gas concentration in real time. Strategic sensor placement and strong data preparation methods like filtering, outlier detection, and dimensionality reduction improve data quality and reliability. Fuzzy logic control with deep learning algorithms can forecast environmental changes and automatically alter control parameters, making environmental regulation more effective and adaptive. Experimental results reveal that the system can dynamically modify warehouse temperature, humidity, and gas concentration to reduce energy consumption and operating expenses and increase environmental monitoring real-time and accuracy. The system monitors temperature, humidity, carbon dioxide content, and light intensity with 50 multipurpose environmental sensors. The system was compared to a baseline rule-based control strategy without adaptive environmental feedback. Comparing our method to the baseline, environmental regulatory accuracy improved by 12.4%, and energy consumption decreased by 18.7%. The training and evaluation dataset had 36,000 hourly records from 30 days. Predefined environmental parameters (20-25°C, 40-60% humidity, <1000 ppm CO₂) were used to annotate data for supervised learning and performance evaluation. By comparing it with traditional methods, the intelligent control system based on the Internet of Things performs well in optimizing energy management, can effectively reduce operating costs, and ensures the stability of the cargo storage environment. The results of this study provide technical support for the intelligent environmental management of automated warehouses, which can not only improve the efficiency and economic benefits of warehouse management, but also have broad application prospects and can be extended to other fields with high environmental requirements, such as smart factories, cold chain logistics and medical storage.