Online Unbalance Detection and Diagnosis on Large Flexible Rotors by SVR and ANN trained by Dynamic Multibody Simulations

Abstract

Multiple-stage steam turbine generators, like those found in nuclear power plants, pose special challenges with regards to mechanical unbalance diagnosis. Several factors contribute to a complex vibrational response, which can lead to incorrect assessments if traditional condition monitoring strategies are used without considering the mechanical system as a whole. This, in turn, can lead to prolonged machinery downtime. Several machine learning techniques can be used to integrally correlate mechanical unbalance along the shaft with transducer signals from rotor bearings. Unfortunately, this type of machinery has scarce data regarding faulty behavior. However, a variety of fault conditions can be simulated in order to generate these data using computational models to simulate the dynamic response of individual machines. In the present work, a multibody model of a 640 MW steam turbine flexible rotor is employed to simulate mechanical unbalance in several positions along the shaft. Synchronous components of the resulting vibration signals at each bearing are obtained and utilized as training data for two regression models designed for mechanical unbalance diagnosis. The first approach uses an artificial neural network and the second one utilizes a support vector regression algorithm. In order to test their performance, the stiffness of each bearing in the multibody simulation was altered between 50% and 150% of the training model values, random noise was added to the signal and several dynamic unbalance conditions were simulated. Results show that both approaches can reliably diagnose dynamic rotor unbalance even when there is a typical degree of uncertainty in bearing stiffness values.

Multibody dynamics and control using machine learning

“…Topic DL Methods SD MD SM Surrogate models Ardeh et al [37] Submodel of a tire FFNN Azzam et al [38] Virtual sensor for loads on wind turbine gearbox FFNN García Peyrano et al [39] Mechanical unbalance of the flexible rotor of a steam turbine FFNN, SVM Inverse dynamics of robotic manipulators SOUL, RNN Rane et al [46] Internal forces in musculoskeletal models during motion CNN, FFNN Ren and Ben-Tzvi [36] Inverse kinematics and dynamics of robotic manipulators GAN Nasr et al [47] Inverse muscle dynamics in musculoskeletal models…”

“…Multibody simulations often generate synthetic data for training ML-based condition monitoring systems. Monitored systems include bearing fault detection (Sobie et al [43], Kahr et al [41]), wind turbine gearbox (Azzam et al [38]), flexible rotors (García Peyrano et al [39]), and diagnosis of wheel out-of-roundness in high-speed trains (Ye et al [44]). The main reason to use synthetic data instead of measurements for model learning is the difficulty in data acquisition for various failure scenarios.…”

“…García Peyrano et al [39] have analyzed the mechanical imbalance of the flexible rotor of a steam turbine. The multibody model considers various imbalance conditions and bearing stiffness.…”