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.

Weak signal extraction of micro-motor rotor unbalance based on all-phase fast Fourier transform

To improve the dynamic balancing accuracy of the micro-motor rotor,an unbalanced vibration feature extraction based on an all-phase fast Fourier transform(APFFT)method is proposed.The amplitude and phase of the signal are extracted by spectrum analysis after windowing the unbalanced signal.The mathematical model is derived to simulate the weak signal of rotor unbalance.The simulation results show that this method is accurate in extracting the weak signal of the rotor under different noise levels.The micro-motor rotor unbalanced test system is developed for experimental validations.The accuracy and stability of the vibration amplitude and phase extracted by the APFFT are better than the accuracy and stability from the hardware filtering method.The rotor unbalance is reduced by more than 80%.Furthermore,secondary balance of the rotor after the first balance is carried out.The proposed method can still extract the residual unbalance of the rotor.The results demonstrated that the proposed method can achieve a reduction rate of 90%and the accuracy is within 5mg,verifying the effectiveness of the proposed method for high-precision rotor dynamic balance.

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.

Vibration of 1000-MW Ultra-Supercritical Turbine-Generator Unit with Simens Technology

The layout features of unit shafting and their effects on vibration, as well as evaluation criteria, were introduced for a 1000-MW ultra-supercritical turbine-generator unit with Simens technology. Based on vibration diagnosis and treatment for more than 10 units, some typical vibration faults were summarized, such as the vibration fluctuation of the high pressure (HP) rotor, abnormal vibration increases of the No.3 bearing pedestal and large vibration of the exciter rotor during its critical speed range. The vibration characteristics and the causes of faults and countermeasures were analyzed. Three applications for further illustration were given. The vibration fault identification method, control measures, and applications can provide a reference for vibration diagnoses and treatment of same type units.