Performance for rotor system of hybrid electromagnetic bearing and elastic foil gas bearing with dynamic characteristics analysis under deep learning

The bearing-rotor system is prone to faults during operation, so it is necessary to analyze the dynamic characteristics of the bearing-rotor system to discuss the optimal structure of the convolutional neural network (CNN) in system fault detection and classification. The turbo expander is undertaken as the research object. Firstly, the hybrid magnetic bearing-rotor system is modeled into the form of four stiffness coefficients and four damping coefficients, so as to analyze and explain the dynamic characteristics of the system. Secondly, the ambient pressure is introduced to analyze the dynamic characteristics of the elastic foil gas bearing-rotor system based on the changes in the dynamic stiffness and dynamic damping of the gas bearing. Finally, the CNN is introduced to be applied in the detection of faults of bearing-rotor system through determining the parameters of the constructed CNN. The results show that the displacement of the rotor increases and the stiffness decreases with the acceleration of the speed of the electromagnetic bearing. The maximum displacement of the rotor can reach 135μm, and the maximum stiffness can be reduced to 35×105N/m. Increase of ambient pressure causes enhancement of main stiffness of the gas bearing, and the main damping decreases accordingly. Analysis of the classification accuracy and loss function based on the CNN model shows that the convolution kernel size of 7*1 and the batch size of 128 can realize the best performance of CNN in fault classification. This provides a data support and reference for studying the dynamic characteristics of the bearing-rotor system and for the optimization of CNN structure in fault classification and detection.

Performance and Cost Reduction of Permanent Magnet Biased Magnetic Bearings

Active magnetic bearings (AMBs) have the well-documented advantage of reduced operational power losses when compared to conventional fluid-film bearings; however, they have yet to be widely adopted in industry due to the high initial costs of manufacturing and supporting power electronics. As AMBs look to become more cost competitive in more widely based applications, permanent magnet biased designs seek to reduce both the operating electrical power losses and the power electronic hardware costs while maintaining normal load and maximum load capacities. In these new designs, permanent magnet components are used to provide the necessary bias magnetic flux in the bearing usually provided by an electrical bias current in traditional all electromagnetic AMB designs. By eliminating electrical bias currents, operating electrical power losses can be significantly reduced while allowing for smaller, cheaper electronic components. This paper provides a comparison of the performance of permanent magnet biased thrust and radial bearing designs with conventional, all electromagnetic bearing designs. The thrust bearings are designed with nominal and maximum load capacities of 1,333 N and 4,000 N, while the radial bearings are designed with nominal and maximum load capacities of 1,000 N and 3,000 N. The shaft diameter is considered to be 70 mm for all bearings. Finite element modeling is used to calculate load capacities and operating electrical power requirements. Power requirements for a number of loads ranging from nominal to maximum capacity are presented for the permanent magnet biased and all electromagnetic bearing designs. A significant reduction in electrical power requirements under maximum load conditions is shown in the permanent magnet biased designs. This reduction is further magnified under nominal load conditions. Additionally, the number of pole wire turns and maximum wire currents are adjusted to realize even greater electrical power losses. The required bias magnetic flux can be generated with reduced wire currents by increasing the number of wire turns. While reducing wire currents also reduces electrical power requirements, the increase in wire turns increases the circuit induction. This increase in induction decreases the bearing slew rate and, in turn, the bandwidth. This study looks at a number of wire turns and current combinations. Tradeoffs between reduced electrical power losses and bearing bandwidth are presented and discussed. The permanent magnet biased AMB designs are shown to significantly reduce electrical power losses having the potential to improve overall machine efficiency. Implications of adopting this technology to both operating and manufacturing costs are discussed. The use of permanent magnets in AMBs is shown to make the costs of these systems more competitive with oil lubricated bearings when compared to conventional AMB designs.