A Wireless Sensor Network-Based Combustible Gas Detection System Using PSO-DBO-Optimized BP Neural Network DOI Creative Commons

Min Zhou,

Sen Wang,

Jianming Li

и другие.

Sensors, Год журнала: 2025, Номер 25(10), С. 3151 - 3151

Опубликована: Май 16, 2025

Combustible gas leakage remains a critical safety concern in industrial and indoor environments, necessitating the development of detection systems that are both accurate practically deployable. This study presents wireless system integrates sensor array, low-power microcontroller with Zigbee-based communication, Back Propagation (BP) neural network optimized via sequential hybrid strategy. Specifically, Particle Swarm Optimization (PSO) is employed for global parameter initialization, followed by Dung Beetle (DBO) local refinement, jointly enhancing network’s convergence speed predictive precision. Experimental results confirm proposed PSO-DBO-BP model achieves high correlation coefficients (above 0.997) low mean relative errors (below 0.25%) all monitored gases, including hydrogen, carbon monoxide, alkanes, smog. The exhibits strong robustness handling nonlinear responses cross-sensitivity effects across multiple sensors, demonstrating its effectiveness complex scenarios under laboratory conditions within embedded networks.

Язык: Английский

A Wireless Sensor Network-Based Combustible Gas Detection System Using PSO-DBO-Optimized BP Neural Network DOI Creative Commons

Min Zhou,

Sen Wang,

Jianming Li

и другие.

Sensors, Год журнала: 2025, Номер 25(10), С. 3151 - 3151

Опубликована: Май 16, 2025

Combustible gas leakage remains a critical safety concern in industrial and indoor environments, necessitating the development of detection systems that are both accurate practically deployable. This study presents wireless system integrates sensor array, low-power microcontroller with Zigbee-based communication, Back Propagation (BP) neural network optimized via sequential hybrid strategy. Specifically, Particle Swarm Optimization (PSO) is employed for global parameter initialization, followed by Dung Beetle (DBO) local refinement, jointly enhancing network’s convergence speed predictive precision. Experimental results confirm proposed PSO-DBO-BP model achieves high correlation coefficients (above 0.997) low mean relative errors (below 0.25%) all monitored gases, including hydrogen, carbon monoxide, alkanes, smog. The exhibits strong robustness handling nonlinear responses cross-sensitivity effects across multiple sensors, demonstrating its effectiveness complex scenarios under laboratory conditions within embedded networks.

Язык: Английский

Процитировано

0