• Smart Structures and Systems
• /
• v.29 no.4
• /
• pp.625-640
• /
• 2022

Maglev rail joints are vital components serving as connections between the adjacent F-type rail sections in maglev guideway. Damage to maglev rail joints such as bolt looseness may result in rough suspension gap fluctuation, failure of suspension control, and even sudden clash between the electromagnets and F-type rail. The condition monitoring of maglev rail joints is therefore highly desirable to maintain safe operation of maglev. In this connection, an online damage detection approach based on three-dimensional (3D) convolutional neural network (CNN) and time-frequency characterization is developed for simultaneous detection of multiple damage of maglev rail joints in this paper. The training and testing data used for condition evaluation of maglev rail joints consist of two months of acceleration recordings, which were acquired in-situ from different rail joints by an integrated online monitoring system during a maglev train running on a test line. Short-time Fourier transform (STFT) method is applied to transform the raw monitoring data into time-frequency spectrograms (TFS). Three CNN architectures, i.e., small-sized CNN (S-CNN), middle-sized CNN (M-CNN), and large-sized CNN (L-CNN), are configured for trial calculation and the M-CNN model with excellent prediction accuracy and high computational efficiency is finally optioned for multiple damage detection of maglev rail joints. Results show that the rail joints in three different conditions (bolt-looseness-caused rail step, misalignment-caused lateral dislocation, and normal condition) are successfully identified by the proposed approach, even when using data collected from rail joints from which no data were used in the CNN training. The capability of the proposed method is further examined by using the data collected after the loosed bolts have been replaced. In addition, by comparison with the results of CNN using frequency spectrum and traditional neural network using TFS, the proposed TFS-CNN framework is proven more accurate and robust for multiple damage detection of maglev rail joints.

• Proceedings of the KSR Conference
• /
• 2006.11a
• /
• pp.189-197
• /
• 2006

Maglev using EMS becomes unstable by unexpected big air-gap disturbance. The main causes of the unexpected air-gap disturbance are step-wise rail joint and large distance between rail splices. For the stable operation of the Maglev, the conventional system uses the threshold method, which selects one gap sensor among two gap sensors installed on the magnet to read the gap between magnet and guide rail. But the threshold method with a wide bandwidth makes the discontinuous air-gap signal at the rail joints because of the offset in air gap sensors and/or the step-wise rail joins. Further more, in the case of the one with a narrow bend-width, it makes Maglev system unstable because of frequent alternation. In this paper, a new method using fuzzy rule to reduce air-gap disturbances proposed to improve the stability of Maglev system. It treats the air-gap signal from dual gap sensors effectively to make continuous signal without air gap disturbance. Simulation and experiment results proved that the proposed scheme was effective to reduce air-gap disturbance from dual gap sensors in rail joints.

• Proceedings of the KIEE Conference
• /
• 2006.07b
• /
• pp.1071-1072
• /
• 2006

Maglev using EMS becomes unstable by unexpected big air-gap disturbance. The main causes of the unexpected air-gap disturbance are step-wise rail joint and large distance between rail splices. For the stable operation of the Maglev, the conventional system uses the threshold method, which selects one gap sensor among two gap sensors installed on the magnet to read the gap between magnet and guide rail. But the threshold method with a wide bandwidth makes the discontinuous air-gap signal at the rail joints because of the offset in air gap sensors and/or the step-wise rail joins. Further more, in the case of the one with a narrow bend-width, it makes Maglev system unstable because of frequent alternation. In this paper, a new method using fuzzy rule to reduce air-gap disturbances proposed to improve the stability of Maglev system. It treats the air-gap signal from dual gap sensors effectively to make continuous signal without air gap disturbance. Simulation and experiment results proved that the proposed scheme was effective to reduce air-gap disturbance from dual gap sensors in rail joints.

• Proceedings of the Korean Society for Noise and Vibration Engineering Conference
• /
• 2014.10a
• /
• pp.622-624
• /
• 2014

A maglev train records a host of physical variables such as gaps, voltages and currents for suspension control and monitoring purposes. These data available from a maglev contains wealth of information that can be explored for various uses. One possible of such application is to use the gap data to estimate the shape of the rail, especially at the joints where rails are connected. The eddy current sensors that measure the gap between the rail and the car body produce large peaks around the joints. The suspension controller discards these peaks. Since the shape of the peaks is related to the joint, however, these peaks can be utilized to estimate the shape of the joints. In this paper, we present preliminary results on estimating the joint shape using the peak data. The results show that the approach is promising, albeit several technical difficulties to overcome.

• Proceedings of the KIEE Conference
• /
• 2006.04b
• /
• pp.310-312
• /
• 2006

Maglev using EMS becomes unstable by unexpected big air-gap disturbance. The main causes of the unexpected air-gap disturbance are step-wise rail joint and large distance between rail splices. For the stable operation of the Maglev, the conventional system uses the threshold method, which selects one gap sensor among two gap sensors installed on the magnet to read the gap between magnet and guide rail. But the threshold method with a wide bandwidth makes the discontinuous air-gap signal at the rail joints because of the offset in air gap sensors and/or the step-wise rail joins. Further more, in the case of the one with a narrow bend-width, it makes Maglev system unstable because of frequent alternation. In this paper, a new method using fuzzy rule to reduce air-gap disturbances proposed to improve the stability of Maglev system. It treats the air-gap signal from dual gap sensors effectively to make continuous signal without air gap disturbance. Simulation and experiment results proved that the proposed scheme was effective to reduce air-gap disturbance from dual gap sensors in rail joints.

• Proceedings of the KSR Conference
• /
• 2011.05a
• /
• pp.1189-1194
• /
• 2011

The Maglev train is operated by levitating from a power of a large number of magnets and moving without direct contact to railway track so that reduces noise and vibration due to mechanical friction. Also, the Maglev passes sharp curves and steep hill without any difficulties. The Maglev has a potential to be an alternative transport system urban areas. For successful commercializing of Maglev, the organization of interface for safety and reliability of third rail system are one of the key considerations. Especially, the components of the third rail system, such as power rail, expansion joints, FRP section insulator, and supporter with epoxy insulator, should be durable, convenient for construction, and easy to maintenance. This paper analyzes the characteristics of the third rail system components and proposes organization of interface for system engineering. The operating tests of KIMM for the proposed third rail system verify the safety. Also, this paper analyzes the life cycle of the system components to improve the system reliability and evaluation.