A large amount of raw data generated in the sensor network needs to be transmitted to the central node through limited bandwidth for processing,and the high-frequency signals in these data may be vulnerable to noise and interference,leading to the decline of data quality and affecting the classification efficiency and quality. A static node classification algorithm of wireless sensor network is proposed in the paper. Data filtering of wireless sensor network uses FPGA to reduce signal frequency,further reduce the influence of noise and interference on signal,and decrease the amount of data transmission. Supporting feature machine algorithm is introduced to complete the classification of static nodes. Experiments show that the algorithm can complete a large number of data processing tasks in a short time,with good classification effect and good application value.