Space Physical Sensor Protection and Control System Based on Neural Network Prediction: Application in Princess Elizabeth Area of Antarctica

• Main Authors: Yuchen Wang, Yinke Dou, Jingxue Guo, Dehong Huang
• Format: Article
• Language: English
• Published: MDPI AG 2020-08-01
• Series: Sensors
• Subjects: unattended; machine learning; long- and short-term memory; lumped parameter method
• Online Access: https://www.mdpi.com/1424-8220/20/17/4662

In the inland areas of Antarctica, the establishment of an unmanned automatic observation support system is an urgent problem and challenge. This article introduces the development and application of an unmanned control system suitable for inland Antarctica. The system is called RIOD (<b>R</b>emote Control, <b>I</b>mage Acquisition, <b>O</b>peration Maintenance, and <b>D</b>ocument Management System) for short. At the beginning of this research project, a mathematical model of heat conduction in the surface observation chamber was established, and the control strategy was determined through mathematical relationships and field experiments. Based on the analysis of local meteorological data, various neural network models are compared, and the training model with the smallest error is used to predict the future ambient temperature. Moreover, the future temperature is substituted into the mathematical model of thermal conductivity to obtain the input value of the next input power, to formulate the operation strategy for the system. This method maintains the regular operation of the sensor while reducing energy consumption. The RIOD system has been deployed in the Tai-Shan camp in China’s Antarctic inland inspection route. The application results 4.5 months after deployment show that the RIOD system can maintain stable operation at lower temperatures. This technology solves the demand for unmanned high-altitude physical observation or astronomical observation stations in inland areas.