The application relates to a distributed fusion
estimation method with sensor saturation and
multiplicative noise, and relates to the technical field of sensor network
information fusion estimation. A dynamic model of a multi-sensor linear random
system with sensor saturation and
multiplicative noise is established; state
estimation is performed on the dynamic model; a prediction intermediate matrix of a local estimator of each node at a time t is calculated; correction parameters of each node in a sensor network at the time t are calculated; a local estimator of the node at the time t is obtained; whether a total time length is reached is judged; if yes, the process is ended; otherwise, the next step is executed; an estimation error
constraint matrix of each node at the time t is calculated; and fusion estimation and fusion estimation error
covariance of the sensor network at the time t are calculated. The influence of the sensor saturation and the
multiplicative noise on the fusion estimation performance is considered simultaneously, the method is easy to realize on line, and the fusion estimation precision is high.