We found a match
Your institution may have access to this item. Find your institution then sign in to continue.
- Title
RESIDUAL LIFE PREDICTION OF ROTATING MACHINERY GUIDED BY QUANTUM DEEP NEURAL NETWORK.
- Authors
GANGHONG YE; NINGXUAN SHI
- Abstract
In order to avoid the low prediction rate and high evaluation rate in estimating the service balance life of rotating machinery, this paper presents a quantum gene chain encoded bidirectional neural network (QGCCBNN) for estimating the service balance life of rotating machinery. In QGCCBNN, quantum bidirectional transmission mechanism has been developed. In order to improve the global optimization ability and convergence speed, we have developed a quantum gene chain encoding method to transform the gradient descent into the data transmission and updating. Because of the advantages of QGCCBNN in nonlinear estimation ability and convergence speed, the proposed QGCCBNN for predicting the remaining service life of rotating machinery can achieve higher prediction precision and optimization. The predicted value of the proposed method for the remaining service life of double row roller bearings is 6.33h (actual value is 7.17h), with a prediction error of only 0.84h and a relative prediction error of only 11.72%. The experimental results demonstrate the effectiveness of the proposed method.
- Subjects
ARTIFICIAL neural networks; ROTATING machinery; SERVICE life; NONLINEAR estimation; ROLLER bearings; GLOBAL optimization
- Publication
Scalable Computing: Practice & Experience, 2024, Vol 25, Issue 4, p2183
- ISSN
1895-1767
- Publication type
Article
- DOI
10.12694/scpe.v25i4.2808