Degradation prediction method based on quantum attention cycle encoding and decoding neural network

Abstract

The invention discloses a degradation prediction method based on a quantum attention cycle coding and decoding neural network (QAREDNN). The QAREDNN is used in the method, a quantum attention mechanism is introduced to reconstruct an encoder and a decoder at the same time, so that the QAREDNN can fully mine and pay attention to important information, interference of redundant information is inhibited, and better nonlinear approximation capability is obtained. A quantum threshold cycle unit (QGRU) of which the active value and the weight are replaced by a quantum rotation matrix is constructedby adopting quantum neurons to replace traditional cycle units in an encoder and a decoder, so that the generalization ability and the response speed of the QAREDNN can be improved; in the training process of QAREDNN, an LM algorithm is introduced to achieve rapid updating of the rotation angle and attention parameters of a quantum rotation matrix. Due to the advantages of the QAREDNN in the aspects of nonlinear approximation capability, generalization capability, response, training speed and the like, the degradation prediction method based on the quantum attention cycle coding and decoding neural network can obtain higher prediction precision and calculation efficiency.

Description

technical field [0001] The invention belongs to the technical field of mechanical state monitoring, and in particular relates to a degradation prediction method based on a quantum attention loop encoding and decoding neural network. Background technique [0002] Rotating machinery is widely used in various critical equipment such as gas turbines, aero engines and wind turbines. Its state directly determines whether the equipment can operate safely and reliably for a long time. During the entire service process, rotating machinery components will undergo a series of different state degradation stages, and rotating machinery components will experience a series of different state degradation stages. The research on the method of predicting the state degradation trend of rotating machinery components will help to avoid key equipment failures The catastrophic accidents brought about reduce the maintenance cost of equipment and improve the efficiency of equipment. With the devel...

AI Technical Summary

Problems solved by technology

Therefore, the nonlinear approximation ability and generalization ability of the neural network are not ideal, and the prediction accuracy is not high.

Images