Numerical and experimental studies on unsupervised deep Lagrangian learning based rotor balancing method

Rotor balancing is essential to rotor dynamic analysis.To make the balancing process convenient and costless,a balancing method using unsupervised deep Lagrangian network without weight trail is proposed.In the proposed network,a Lagrangian layer is applied to the network to introduce the physical prior knowledge.Compared to traditional balancing method,trail weight process is not necessary.Meanwhile,parameter sharing mechanics in baseline design or Lagrangian layer are applied to identify the unbalanced force without labeled data.Both numerical case study and corresponding experiment are conducted to validate the method.Both experimental and numerical results find that the proposed rotor balancing approach gives reasonable and comparative results with the considerations of both cost and accuracy.Compared with the baseline,to which no physical prior is applied,the balancing method with Lagrangian mechanism involved could achieve better performance.This proposed rotor dynamic balancing method gives out an alternative approach of rotor balancing methods.

A new vibration mechanism of balancing machine for satellite-borne spinning rotors

The centrifugal force and overturning moment generated by satellite-borne rotating payload have a significant impact on the stability of on-orbit satellite attitude, which must be controlled to the qualified range. For the satellite-borne rotors＇ low working revs and large centroidal deviation and height, and that the horizontal vibration produced by centrifugal force is not of the same magnitude as the torsional vibration by overturning moment, the balancing machine＇s measurement accuracy is low. Analysis shows that the mixture of horizontal vibration and torsional vibration of the vibrational mechanism contribute mainly to the machine＇s performance, as well as the instability of vibration center position. A vibrational mechanism was put forward, in which the horizontal and torsional vibration get separated effectively by way of fixing the vibration center. From experimental results, the separation between the weak centrifugal force signal and the strong moment signal was realized, errors caused by unstable vibration center are avoided, and the balancing machine based on this vibration structure is able to meet the requirements of dynamic balancing for the satellite＇s rotating payloads in terms of accuracy and stability.