System and method for predicting residual life of part of engineering machine

The invention relates to a system and a method for predicting residual life of a part of an engineering machine. The system comprises a reliability analysis module, a data pre-processing module and a residual life prediction module. The reliability analysis module comprises a residual life range acquisition module and a current evaluation object determining module which are respectively used for acquiring the residual life range of the part and determining whether the part serves as the current evaluation object. The data pre-processing module is used for receiving real-time acquired characteristic parameter information of the part serving as the current evaluation object, extracting characteristic parameter values in the characteristic parameter information and pre-processing the extracted characteristic parameter values to construct a sample data set. The residual life prediction module is used for acquiring predicted characteristic parameter values according to the sample data set by using a neural network prediction model and acquiring the residual life of the part by using the predicted characteristic parameter values and consulting the characteristic parameter values of the part in a fault state. By using the system and the method, the residual life of the part can be accurately predicted, and basis is provided for maintenance of the engineering machine.