Neural Network Emulation of a Magnetically Suspended Rotor

2004 ◽  
Vol 126 (2) ◽  
pp. 373-384 ◽  
Author(s):  
A. Escalante ◽  
V. Guzma´n ◽  
M. Parada ◽  
L. Medina ◽  
S. E. Diaz
Keyword(s):  
Neural Network ◽  
Virtual Instrument ◽  
High Speed ◽  
Magnetic Bearing ◽  
Magnetic Bearings ◽  
System Response ◽  
The Neural Network ◽  
Artificial Neurons ◽  
Position Data ◽  
System 2

The use of magnetic bearings in high speed/low friction applications is increasing in industry. Magnetic bearings are sophisticated electromechanical systems, and modeling magnetic bearings using standard techniques is complex and time consuming. In this work a neural network is designed and trained to emulate the operation of a complete system (magnetic bearing, PID controller, and power amplifiers). The neural network is simulated and integrated into a virtual instrument that will be used in the laboratory both as a teaching and a research tool. The main aims in this work are: (1) determining the minimum amount of artificial neurons required in the neural network to emulate the magnetic bearing system, (2) determining the more appropriate ANN training method for this application, and (3) determining the errors produced when a neural network trained to emulate system operation with a balanced rotor is used to predict system response when operating with an unbalanced rotor. The neural network is trained using as input the position data from the proximity sensors; neural network outputs are the control signals to the coil amplifiers.

Neural Network Emulation of a Magnetically Suspended Rotor

2002 ◽  
Author(s):  
A. Escalante ◽  
V. Guzma´n ◽  
M. Parada ◽  
L. Medina ◽  
S. E. Diaz
Keyword(s):  
Neural Network ◽  
Virtual Instrument ◽  
High Speed ◽  
Magnetic Bearing ◽  
Magnetic Bearings ◽  
System Response ◽  
The Neural Network ◽  
Artificial Neurons ◽  
Position Data ◽  
System 2

The use of magnetic bearings in high speed/low friction applications is increasing in industry. Magnetic bearings are sophisticated electromechanical systems, and modeling magnetic bearings using standard techniques is complex and time consuming. In this work a Neural network is designed and trained to emulate the operation of a complete system (magnetic bearing, PID controller and power amplifiers). The neural network is simulated and integrated into a virtual instrument that will be used in the laboratory both as a teaching and a research tool. The main aims in this work are: 1-Determining the minimum amount of artificial neurons required in the neural network to emulate the magnetic bearing system. 2-Determining the more appropriate ANN training method for this application. 3-Determining the errors produced when a neural network trained to emulate system operation with a balanced rotor is used to predict system response when operating with an unbalanced rotor. The neural network is trained using as input the position data from the proximity sensors; neural network outputs are the control signals to the coil amplifiers.

scholarly journals Tip Clearance Actuation With Magnetic Bearings for High-Speed Compressor Stall Control

2000 ◽  
Vol 123 (3) ◽  
pp. 464-472 ◽  
Author(s):  
Z. S. Spakovszky ◽  
J. D. Paduano ◽  
R. Larsonneur ◽  
A. Traxler ◽  
M. M. Bright
Keyword(s):  
High Speed ◽  
Design Procedure ◽  
Magnetic Bearing ◽  
Rotating Stall ◽  
Tip Clearance ◽  
Magnetic Bearings ◽  
Test Facility ◽  
Control Analysis ◽  
Servo Actuator ◽  
Stall Control

Magnetic bearings are widely used as active suspension devices in rotating machinery, mainly for active vibration control purposes. The concept of active tip-clearance control suggests a new application of magnetic bearings as servo-actuators to stabilize rotating stall in axial compressors. This paper presents a first-of-a-kind feasibility study of an active stall control experiment with a magnetic bearing servo-actuator in the NASA Glenn high-speed single-stage compressor test facility. Together with CFD and experimental data a two-dimensional, incompressible compressor stability model was used in a stochastic estimation and control analysis to determine the required magnetic bearing performance for compressor stall control. The resulting requirements introduced new challenges to the magnetic bearing actuator design. A magnetic bearing servo-actuator was designed that fulfilled the performance specifications. Control laws were then developed to stabilize the compressor shaft. In a second control loop, a constant gain controller was implemented to stabilize rotating stall. A detailed closed loop simulation at 100 percent corrected design speed resulted in a 2.3 percent reduction of stalling mass flow, which is comparable to results obtained in the same compressor by Weigl et al. (1998. ASME J. Turbomach. 120, 625–636) using unsteady air injection. The design and simulation results presented here establish the viability of magnetic bearings for stall control in aero-engine high-speed compressors. Furthermore, the paper outlines a general design procedure to develop magnetic bearing servo-actuators for high-speed turbomachinery.

scholarly journals Axle Temperature Monitoring and Neural Network Prediction Analysis for High-Speed Train under Operation

Symmetry ◽  
2020 ◽  
Vol 12 (10) ◽  
pp. 1662
Author(s):  
Wei Hao ◽  
Feng Liu
Keyword(s):  
Neural Network ◽  
Network Model ◽  
Neural Network Model ◽  
High Speed ◽  
Prediction Method ◽  
High Speed Train ◽  
The Neural Network ◽  
Neural Network Prediction ◽  
Network Prediction ◽  
Trained Neural Network

Predicting the axle temperature states of the high-speed train under operation in advance and evaluating working states of axle bearings is important for improving the safety of train operation and reducing accident risks. The method of monitoring the axle temperature of a train under operation, combined with the neural network prediction method, was applied. A total of 36 sensors were arranged at key positions such as the axle bearings of the train gearbox and the driving end of the traction motor. The positions of the sensors were symmetrical. Axle temperature measurements over 11 days with more than 38,000 km were obtained. The law of the change of the axle temperature in each section was obtained in different environments. The resultant data from the previous 10 days were used to train the neural network model, and a total of 800 samples were randomly selected from eight typical locations for the prediction of axle temperature over the following 3 min. In addition, the results predicted by the neural network method and the GM (1,1) method were compared. The results show that the predicted temperature of the trained neural network model is in good agreement with the experimental temperature, with higher precision than that of the GM (1,1) method, indicating that the proposed method is sufficiently accurate and can be a reliable tool for predicting axle temperature.

Study on Decreasing Vibration of High-Speed Train Semi-Active Suspension System

2011 ◽  
Vol 230-232 ◽  
pp. 1104-1109
Author(s):  
Zhen Ping Fan ◽  
Heng Zeng ◽  
Jian Wei Yang ◽  
Jie Li
Keyword(s):  
Neural Network ◽  
Control Strategy ◽  
High Speed ◽  
Driving Safety ◽  
High Speed Train ◽  
Proportional Valve ◽  
Joint Simulation ◽  
The Neural Network ◽  
Adaptive Control Strategy ◽  
Active Damper

Lateral semi-active damper is designed by author based on the electro-hydraulic proportional valve, from the perspective angle of improving vehicle comfort; its purpose is to ensure vehicle driving safety. At the same time, the neural network adaptive control strategy is used for joint simulation of semi-active damper. The results show that lateral semi-active damper with the train body has significantly improved compared to the traditional passive lateral damper acceleration.

High-Speed Rotor Losses in a Radial Eight-Pole Magnetic Bearing: Part 1—Experimental Measurement

1998 ◽  
Vol 120 (1) ◽  
pp. 105-109 ◽  
Author(s):  
M. E. F. Kasarda ◽  
P. E. Allaire ◽  
E. H. Maslen ◽  
G. R. Brown ◽  
G. T. Gillies
Keyword(s):  
Power Loss ◽  
High Speed ◽  
Large Scale ◽  
Eddy Currents ◽  
Magnetic Bearing ◽  
Rate Of Change ◽  
Magnetic Bearings ◽  
Power Losses ◽  
Loss Mechanism ◽  
Pole Configuration

The continual increase in the use of magnetic bearings in various capacities, including high-speed aerospace applications such as jet engine prototypes, dictates the need to quantify power losses in this type of bearing. The goal of this study is to present experimentally measured power losses during the high-speed operation of a pair of magnetic bearings. A large-scale test rotor has been designed and built to obtain unambiguous power loss measurements while varying a variety of test parameters. The test apparatus consists of a shaft supported in two radial magnetic bearings and driven by two electric motors also mounted on the shaft. The power losses of the spinning rotor are determined from the time rate of change of the kinetic energy of the rotor as its angular speed decays during free rotation. Measured results for the first set of magnetic bearings, a pair of eight-pole planar radial bearings, are presented here. Data from three different parameter studies including the effect of the bias flux density, the effect of the bearing pole configuration, and the effect of the motor stator on the power loss are presented. Rundown plots of the test with the bearings in the paired pole (NNSS) versus the alternating (NSNS) pole configuration show only small differences, with losses only slightly higher when the poles are in the alternating pole (NSNS) configuration. Loss data were also taken with the motor stators axially removed from the motor rotors for comparison with the case where the motor stators are kept in place. No measurable difference was observed between the two cases, indicating negligible windage and residual magnetic effects. Throughout most of the speed range, the dominant loss mechanism appears to be eddy currents.

Fault detection and tolerance in synchronous vibration control of rotor—magnetic bearing systems

2001 ◽  
Vol 215 (12) ◽  
pp. 1401-1416 ◽  
Author(s):  
M N Sahinkaya ◽  
M O T Cole ◽  
C R Burrows
Keyword(s):  
Vibration Control ◽  
Magnetic Bearing ◽  
Open Loop ◽  
Magnetic Bearings ◽  
Control Technique ◽  
Effective Control ◽  
System Response ◽  
Rotor Support ◽  
Measured System ◽  
Control Forces

The use of magnetic bearings in rotating machinery provides contact-free rotor support, and allows vibration control using both closed-loop and open-loop strategies. One of the simplest and most effective methods to reduce synchronous lateral vibration when using magnetic bearings is through an open-loop adaptive control technique, in which the amplitude and phase of synchronous magnetic control forces are adjusted automatically to minimize the measured vibrations along the rotor. However, transducer malfunction, or faults in the signal-processing channels, may cause the controller to adapt incorrectly, with unwanted and possibly catastrophic effects. It is shown that an extension to the control strategy, which utilizes the variances of the measured system response and identified parameters, enables the faults to be detected and accounted for so that a modified control action can achieve continued and effective control of the synchronous vibration. The approach is extended further to identify changes in external factors, such as unbalance and rotor dynamics. Various faults and perturbations are examined experimentally, and the ability of the controller to detect and compensate for these changes is demonstrated.

Dynamic Analysis and Control of High Speed and High Precision Active Magnetic Bearings

1992 ◽  
Vol 114 (4) ◽  
pp. 623-633 ◽  
Author(s):  
K. Youcef-Toumi ◽  
S. Reddy
Keyword(s):  
Time Delay ◽  
High Speed ◽  
Dynamic Stiffness ◽  
Magnetic Bearing ◽  
Magnetic Bearings ◽  
Successful Operation ◽  
Highly Nonlinear ◽  
Wide Range ◽  
And Control ◽  
Digital Time

The successful operation of actively controlled magnetic bearings depends greatly on the electromechanical design and control system design. The function of the controller is to maintain bearing performance in the face of system dynamic variations and unpredictable disturbances. The plant considered here is the rotor and magnetic bearing assembly of a test apparatus. The plant dynamics consisting of actuator dynamics, rigid rotor dynamics and flexibility effects are described. Various components of the system are identified and their corresponding linearized theoretical models are validated experimentally. Tests are also run to identify the coupling effects and flexibility modes. The highly nonlinear behavior of the magnetic bearings in addition to the inherent instability of such a system makes the controller design complex. A digital Time Delay Controller is designed and its effectiveness evaluated using several simulations based on linear and nonlinear models for the bearing including bending mode effects. This controller is implemented as an alternative to an existing linear analog compensator. Several experiments are conducted with each controller for spinning and nonspinning conditions. These include time responses, closed loop frequency responses and disturbance rejection responses. The experimental results and comparisons between those of a digital Time Delay Controller and an analog compensator indicate that the Time Delay Controller has impressive static and dynamic stiffness characteristics for the prototype considered. The Time Delay Controller also maintains almost the same dynamic behavior over a significantly wide range of rotor speeds.

The Dynamic Analysis of an Energy Storage Flywheel System With Hybrid Bearing Support

2009 ◽  
Vol 131 (5) ◽  
Author(s):  
Hongchang Wang ◽  
Shuyun Jiang ◽  
Zupei Shen
Keyword(s):  
Control System ◽  
Energy Storage ◽  
Active Control ◽  
High Speed ◽  
Magnetic Bearing ◽  
Magnetic Bearings ◽  
Squeeze Film ◽  
Transmitted Force ◽  
Hybrid Bearing ◽  
Active Control System

Active magnetic bearings and superconducting magnetic bearings were used on a high-speed flywheel energy storage system; however, their wide industrial acceptance is still a challenging task because of the complexity in designing the elaborate active control system and the difficulty in satisfying the cryogenic condition. A hybrid bearing consisting of a permanent magnetic bearing and a pivot jewel bearing is used as the support for the rotor of the energy storage flywheel system. It is simple and has a long working life without requiring maintenance or an active control system. The two squeeze film dampers are employed in the flywheel system to suppress the lateral vibration, to enhance the rotor leaning stability, and to reduce the transmitted forces. The dynamic equation of the flywheel with four degrees of complex freedom is built by means of the Lagrange equation. In order to improve accuracy, the finite element method is utilized to solve the Reynolds equation for the dynamic characteristics of the squeeze film damper. When the calculated unbalance responses are compared with the test responses, they indicate that the dynamics model is correct. Finally, the effect of the squeeze film gap on the transmitted force is analyzed, and the appropriate gap should be selected to cut the energy loss and to control vibration of the flywheel system.

scholarly journals Tip-Clearance Actuation With Magnetic Bearings for High-Speed Compressor Stall Control

2000 ◽  
Author(s):  
Z. S. Spakovszky ◽  
J. D. Paduano ◽  
R. Larsonneur ◽  
A. Traxler ◽  
M. M. Bright
Keyword(s):  
High Speed ◽  
Design Procedure ◽  
Magnetic Bearing ◽  
Rotating Stall ◽  
Tip Clearance ◽  
Magnetic Bearings ◽  
Test Facility ◽  
Control Analysis ◽  
Servo Actuator ◽  
Stall Control

Magnetic bearings are widely used as active suspension devices in rotating machinery, mainly for active vibration control purposes. The concept of active tip clearance control suggests a new application of magnetic bearings as servo-actuators to stabilize rotating stall in axial compressors. This paper presents a first-of-a-kind feasibility study of an active stall control experiment with a magnetic bearing servo-actuator in the NASA Glenn high-speed single-stage compressor test facility. Together with CFD and experimental data a two-dimensional, incompressible compressor stability model was used in a stochastic estimation and control analysis to determine the required magnetic bearing performance for compressor stall control. The resulting requirements introduced new challenges to the magnetic bearing actuator design. A magnetic bearing servo-actuator was designed which fulfilled the performance specifications. Control laws were then developed to stabilize the compressor shaft. In a second control loop, a constant gain controller was implemented to stabilize rotating stall. A detailed closed loop simulation at 100% corrected design speed resulted in a 2.3% reduction of stalling mass flow which is comparable to results obtained in the same compressor by Weigl et al. (1998) using unsteady air injection. The design and simulation results presented here establish the viability of magnetic bearings for stall control in aero-engine high-speed compressors. Furthermore the paper outlines a general design procedure to develop magnetic bearing servo-actuators for high-speed turbomachinery.

scholarly journals Improvement of flexible rotor/active magnetic bearings system performance using pi-d control

2020 ◽  
Vol 40 (2) ◽  
pp. 112-123
Author(s):  
Adis Muminovic ◽  
Sanjin Braut ◽  
Adil Muminovic ◽  
Isad Saric ◽  
Goranka Štimac Rončević
Keyword(s):  
Pid Control ◽  
Real Life ◽  
Magnetic Bearing ◽  
Magnetic Bearings ◽  
Active Magnetic Bearing ◽  
System Response ◽  
Active Magnetic Bearings ◽  
Flexible Rotor ◽  
Notch Filters ◽  
Common Control

Proportional–integral–derivative (PID) control is the most common control approach used to control active magnetic bearings system, especially in the case of supporting rigid rotors. In the case of flexible rotor support, the most common control is again PID control in combination with notch filters. Other control approaches, known as modern control theory, are still in development process and cannot be commonly found in real life industrial application. Right now, they are mostly used in research applications. In comparison to PID control, PI-D control implies that derivate element is in feedback loop instead in main branch of the system. In this paper, performances of flexible rotor/active magnetic bearing system were investigated in the case of PID and PI-D control, both in combination with notch filters. The performances of the system were analysed using an analysis in time domain by observing system response to step input and in frequency domain by observing a frequency response of sensitivity function.

Sign in / Sign up

Export Citation Format

Share Document