An efficient remaining useful life（RUL）can provide key information for manager to make preventive maintenance strategy and prevent equipment unexpected downtime.Aim to nonlinear state process of equipment and real-time demand of life prediction in engineering

a remaining useful life prediction method based on unscented Kalman filter is proposed.The state space model（SSM）is constructed by this method to describe degradation evolution process

by using unscented Kalman filter method

the state distribution in SSM is estimated and the Expectation-Maximization（EM）algorithm is taken to estimate model parameter.Then

the equipment remaining useful life is solved by using the model state and model parameter under current moment.A practical case study of Helicopter main gearbox is present in the last

the results show the remaining useful life of Helicopter gearbox can be accurately estimated by this method.