An improved online denoising algorithm based on Kalman filter and adaptive current statistics model

In practical process, it's necessary to obtain the real-time data without noise. The Kalman filter is a classical recursive method of the state estimation, thus, it can be used in the online denoising. In order to acquire the preferable denoising effect, the appropriate model would be required to capture the features of the signals. In this paper, adaptive current statistics model (ACSM) was applied to the state estimation of Kalman filter. However, the measurement variance `R' in this method was unknown, meanwhile, it could have a huge impact on the denoising effect. Therefore, this paper proposed a self-adaptive adjustment algorithm of measurement variance, by means of introducing forgetting factor to estimate `R'. In this way, `R' would be convergent to the real value. The effectiveness of the method was verified by the simulation experiment. The results show that the proposed method not only can make `R' to be convergence to real value, but also can achieve the favorable denoising effect.