Multi-Sensor Hierarchical Fusion Estimation Based on Improved Kalman Filter and Weighted Data Fusion in Greenhouse Environment
Xiaoyan Wang, Wenyan Wang, Shanshan Zheng, Liang Pei · 2021 IEEE Asia-Pacific Conference on Image Processing, Electronics and Computers (IPEC) · 2021
Greenhouse environment is complex and large, and sensor nodes are vulnerable to interference. In order to realize the real-time collection and monitoring of greenhouse humidity data and improve the reliability of wireless sensor networks (WSNs) in greenhouse, a multi-sensor hierarchical fusion estimation based on improved Kalman filter (IKF) and weighted data fusion (WDF) is proposed. In order to save energy, the sensors in the space are divided into multiple clusters, and each cluster has a certain number of sensors. The data collected by the sensors are estimated locally by using the IKF algorithm, and then the estimated data is sent to the cluster head (CH) node. The CH node further processes the data, and uses the WDF algorithm to further fuse the local estimated values. The simulation results show that the multi-sensor data fusion method can greatly reduce the amount of network data transmission and energy consumption, and improve the anti-interference ability. In addition, compared with the traditional algorithm, the proposed algorithm has better effect and accurate estimation accuracy.