Reliability Analysis of Stator Shielding Sleeve Based on Hybrid Data-Mechanism Driven Approach

The shielding sleeve of main pump motor is prone to failure under various stresses. Due to the structural impact, it is impossible to install corresponding sensors to observe the state of the shielding sleeve. Due to the lack of performance degradation model of the shielding sleeve, it is difficult to accurately evaluate the reliability. This paper presents a data-mechanism driven reliability modeling and evaluation method. Firstly, the Wiener process theory is combined with the random filtering method to construct the degradation model of non-stationary random process. Secondly, the creep damage constitutive equation of the shielding sleeve is established through the analysis of material properties and microstructure research. The performance degradation rate under the stress temperature coupling condition is quantitatively described. The maximum likelihood estimation method is used to determine the degradation model parameters, and the degradation model of the main pump motor shielding sleeve is established. Finally, taking the bulge fault of the stator shielding sleeve of the main pump motor as an example, the eddy current loss is selected as the performance degradation index, and the accuracy of the proposed reliability modeling and evaluation method is verified by simulation. The results show that the fitting effect of performance degradation characteristics is good, with root mean square error of 0.1523 kW and <tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">$R^{2}$</tex> of 0.9231. And the reliability of the motor is high at the initial stage of operation, and the survival probability of the shield sleeve in the actual operation and maintenance cycle of 15 years is 85.8%.