Periodic Monitoring and Filtering Suppression of Signal Interference in Mine 5G Communication

Abstract

Diverse IoT applications, such as unmanned driving, intelligent video, unmanned working face, industrial control, and intelligent robot inspection, are the key technologies in the field of intelligent mines. In order to fully meet the requirements of underground IoT systems of high bandwidth, low latency, and massive connections, it is necessary to study 5G technologies suitable for underground environments to achieve effective deployment in mines. In key areas, such as main transport roadways, fully mechanized mining faces, and underground substations, both spurs and crosstalk in the frequency domain are the dominant factors affecting the stability and reliability of 5G signals. For the purpose of improving the performance of mine 5G, a fusion anti-interference scheme is designed here. Based on a deep complex network and blind source separation, periodic monitoring and filtering suppression of signal interference can be achieved. The test results show that the frequency domain spurs’ suppression capability of the proposed method is 20% higher than that of the traditional equalization method. For frequency domain crosstalk, 90% interference elimination could be achieved by the proposed method without additional delays when compared with the conventional blind source separation. The high-bandwidth and low-latency characteristics of 5G communication can be guaranteed by this method.

Keywords

• mine 5G communication
• interference suppression
• blind source separation
• neural network