Generalized quantum neural predictive networks
Nan Dongxiang, Yunsheng Zhang · 2008
A nonlinear system such as prediction of coal and methane outbursts, mechanical faults diagnosis and so on, which has the character coupled, randomized and sudden changed to the system variants. It is a difficult problem to predict this kind of nonlinear system with using the accurate and effective approach. We proposed a novel generalized quantum neural predictive networks which can be solved this problem better. To construct the model of a nonlinear system, ANN-PID (artificial neural networks with proportional, integral and derivative) has good nonlinear property, so that it can be constructed the model of the nonlinear system according to the knowledge of history data. And then, according to the projected property, the model can be launched from generalized space to Hilbert space, so that the model with superposition quantum states can be developed. In the quantum mechanicalism, a special state which is so called predictive state can be inverted with more and more hight probability from the superposition stats of sample data, before its predictive results has been produced. We have constructed the model of mapping and a predictive algorithm for the nonlinear system, which can be realized the hidden relations between the system inputs and outputs. The results of calculation shows that generalized quantum neural predictive networks predicts the nonlinear system is effective and accurate.