No abstract

Electrical equipment maintenance is of vital importance to management companies. Efficient maintenance can significantly reduce business costs and avoid safety accidents caused by catastrophic equipment failures. In the current context, predictive maintenance (PdM) is becoming increasingly popular based on machine learning approaches, while its research on electrical equipment such as low-voltage contactors is in its infancy. The failure modes are mainly fusion welding and explosion, and a few are unable to switch on. In this study, a data-driven approach is proposed to predict the remaining useful life (RUL) of the low-voltage contactor. Firstly, the three-phase alternating voltage and current records the life of electrical equipment by tracking the number of times it has been operated. Secondly, the failure-relevant features are extracted by using the time domain, frequency domain, and wavelet methods. Then, a CNN-LSTM network is designed and used to train an electrical equipment RUL prediction model based on the extracted features. An experimental study based on ten datasets collected from low-voltage AC contactors reveals that the proposed method shows merits in comparison with the prevailing deep learning algorithms in terms of MAE and RMSE.

Background: When an unbalanced flexible rotor passes through its critical speed, it is very easy to result in great vibration amplitude, even the destruction of rotor and bearings. Therefore, it is significant for high-speed rotating machines to reduce the vibration amplitude of flexible rotor. Various patents have been discussed in this article. Objective: The purpose of this study is to find out the amplitude reduction method and simulate the feasibility of flexible rotor passing through critical speed. Methods: On the basis of the model of single disk rotor system with eccentric mass, a novel method is presented to reduce the vibration amplitude passing through critical speed by modulating the acceleration and stiffness simultaneously. Firstly, the amplitude characteristic of a flexible rotor with different acceleration and supporting stiffness was investigated. Then, the method of changing the stiffness during variable acceleration was carried out by numerical simulation based on Newmark algorithm. Furthermore, the strain energy of rotor and input power were also analyzed by using the method of simultaneous modulation of acceleration and stiffness. Results: The simulation results revealed that the simultaneous modulation of acceleration and stiffness could reduce the vibration amplitude of rotor effectively, which was reduced by 44% and 13%, comparing with the single variable acceleration and the single variation of stiffness, respectively. Moreover, the variation tendency of total energy was similar to that of the rotor amplitude, which could be controlled at a very small level. The input power was mainly dependent on the acceleration, but had very little to do with the stiffness. Conclusion: The method was suitable for the model of single disk rotor system, and it could also be applied to complex rotor systems, which was very useful for the security of high speed rotating machine.

No abstract