• Proceedings of the Korean Society for Noise and Vibration Engineering Conference
• /
• 2002.11a
• /
• pp.399.2-399
• /
• 2002

This paper concerns on a non-rotating single-DOF beam-active magnetic bearing(AMB) system subject to arbitrary shaped base motion. In such a system, it is desirable to retain the beam within the predetermined air-gap under foundation excitation. Motivated form this, an adaptive acceleration feedforward control is proposed to reduce the base motion response without deteriorating other feedback control performances. Experimental results demonstrate the effectiveness of the acceleration feedforward control.

• Transactions of the Korean Society for Noise and Vibration Engineering
• /
• v.15 no.3 s.96
• /
• pp.364-370
• /
• 2005

The active magnetic bearing (AMB) systems mounted in moving vehicles are exposed to the disturbances due to the base motion, often leading to malfunction or damage as well as inaccurate positioning of the systems. Thus, in the controller design of such AMB systems, robustness to base disturbances becomes an essential requirement. In this study, effective control schemes are proposed for the homo-polar AMB system, which uses permanent magnets for generation of bias magnetic flux, when it is subject to base motion, and its control performance is experimentally evaluated. The base motion of AMB system is modeled as the dynamic disturbances in the gravity and base excitation forces. To effectively compensate for the disturbances, the angle feed-forward controller based on the inverse dynamic model and the acceleration feed-forward controller based on the normalized filtered-X LMS algorithm are proposed. The performance test of the prototype AMB system is carried out, when the system is mounted on rate table. The experimental results show that the performance of the proposed controllers for the AMB system is satisfactory in compensating for the disturbances due to the base motion.

• Proceedings of the Korean Society for Noise and Vibration Engineering Conference
• /
• 2004.11a
• /
• pp.486-489
• /
• 2004

The active magnetic bearing (AMB) systems mounted in moving vehicles are exposed to the disturbances due to the base motion, often leading to malfunction or damage as well as inaccurate positioning of the systems. Thus, in the controller design of such AMB systems, robustness to base disturbances becomes an essential requirement. In this study, effective control schemes are proposed for the homo-polar AMB system, which uses permanent magnets for generation of bias magnetic flux, when it is subject to base motion, and its control performance is experimentally evaluated. The base motion of AMB system is modeled as the dynamic disturbances in the gravity and base excitation forces. To effectively compensate for the disturbances, the angle feed-forward controller based on the inverse dynamic model and the acceleration feed-forward controller based on the normalized filtered-X LMS algorithm are proposed. The performance test of the prototype AMB system is carried out, when the system is mounted on rate table. The experimental results show that the performance of the proposed controllers for the AMB system is satisfactory in compensating for the disturbances due to the base motion.

• Journal of Intelligence and Information Systems
• /
• v.29 no.1
• /
• pp.107-119
• /
• 2023

The technology that recognizes a soldier's motion and movement status has recently attracted large attention as a combination of wearable technology and artificial intelligence, which is expected to upend the paradigm of troop management. The accuracy of state determination should be maintained at a high-end level to make sure of the expected vital functions both in a training situation; an evaluation and solution provision for each individual's motion, and in a combat situation; overall enhancement in managing troops. However, when input data is given as a timer series or sequence, existing feedforward networks would show overt limitations in maximizing classification performance. Since human behavior data (3-axis accelerations and 3-axis angular velocities) handled for military motion recognition requires the process of analyzing its time-dependent characteristics, this study proposes a high-performance data-driven classifier which utilizes the long-short term memory to identify the order dependence of acquired data, learning to classify eight representative military operations (Sitting, Standing, Walking, Running, Ascending, Descending, Low Crawl, and High Crawl). Since the accuracy is highly dependent on a network's learning conditions and variables, manual adjustment may neither be cost-effective nor guarantee optimal results during learning. Therefore, in this study, we optimized hyperparameters using Bayesian optimization for maximized generalization performance. As a result, the final architecture could reduce the error rate by 62.56% compared to the existing network with a similar number of learnable parameters, with the final accuracy of 98.39% for various military operations.