Regarding application with smooth variation of detection, spatial correlation of sensors’ data within a small field was applied to sensor nodes’ fault diagnosis. The data were sorted into several continuous sequences by sink node. Sequence with minimum variance was regarded as normal data to determine normal nodes. For undetermined nodes, it can be determined via calculation on deviation to normal nodes’ data of vicinity area. If deviation does not exceed the threshold, the node is normal; otherwise, it is regarded as a fault node. The research on WSN in a greenhouse shows that fault node can be effectively detected in time by this method.

This paper proposed a greenhouse control system utilizing wireless sensor network (WSN) to overcome the wiring difficulties and poor mobility in the application of traditional cable-used control systems. Each wireless sensor node in the WSN collects the environmental data of temperature, humidity and CO2 concentration, and transmits the data to the control center via the sink nodes. A fuzzy neural network with three inputs and six outputs was designed to improve the control accuracy. By analyzing the relationship between the mentioned environmental factors above and the actuators of the system, a fuzzy rule was made and combined with the neural network. The simulation results showed that the proposed method could respond in a short time with high accuracy, and had small overshoot as well as good stability.

In view of characteristics of large time delay, multi-interference and strong coupling in temperature and humidity control system, an adaptive decoupling strategy based on generalized predictive control (GPC) and multi-model control is proposed in this paper. The proposed strategy mainly contains muti-model control, GPC decoupling control and adaptive algorithm. In multi-model control, multi-model sets are established to prevent the model mismatch in different working conditions. Meanwhile, this paper designs adaptive dynamic decoupling algorithms based on the principle of GPC. In actual experiments, temperature and humidity achieve precision of ±0.2°C and ±0.5% respectively.

Real-time monitoring of soil moisture is essential for agricultural production. In this paper, an improved system is designed based on GPRS technology for real-time detecting soil moisture, a salinity calibration model is established based on Least Squares Support Vector Machines on MatLAB (LS-SVMlab) for improving detection precision. The transmission of soil moisture information is the key technology of the system, by software and hardware design we have solved the problems of data congestion, off-line, and moving the monitoring terminal at any time, which still restrict the application of GPRS in soil moisture detection. Field tests show that the system can realize seamless connection between the collection nodes and remote host, and acquire soil moisture accurately. Simultaneously, the time of re-networking has been shortened greatly.

Based on the node low energy consumption wireless sensor network for greenhouse, which takes mobile gathering node as center to self-organize subnets, this article mainly studies the relationship among network parameters and strike a balance between energy saving and system stability to establish the model of network parameter. Examples are illustrated to show how to determine network parameters and why the model is effective.