A City Shared Bike Dispatch Approach Based on Temporal Graph Convolutional Network and Genetic Algorithm.

Public transportation scheduling aims to optimize the allocation of resources, enhance efficiency, and increase passenger satisfaction, all of which are crucial for building a sustainable urban transportation system. As a complement to public transportation, bike-sharing systems provide users with a solution for the last mile of travel, compensating for the lack of flexibility in public transportation and helping to improve its utilization rate. Due to the characteristics of shared bikes, including peak usage periods in the morning and evening and significant demand fluctuations across different areas, optimizing shared bike dispatch can better meet user needs, reduce vehicle vacancy rates, and increase operating revenue. To address this issue, this article proposes a comprehensive decision-making approach for spatiotemporal demand prediction and bike dispatch optimization. For demand prediction, we design a T-GCN (Temporal Graph Convolutional Network)-based bike demand prediction model. In terms of dispatch optimization, we consider factors such as dispatch capacity, distance restrictions, and dispatch costs, and design an optimization solution based on genetic algorithms. Finally, we validate the approach using shared bike operating data and show that the T-GCN can effectively predict the short-term demand for shared bikes. Meanwhile, the optimization model based on genetic algorithms provides a complete dispatch solution, verifying the model's effectiveness. The shared bike dispatch approach proposed in this paper combines demand prediction with resource scheduling. This scheme can also be extended to other transportation scheduling problems with uncertain demand, such as store replenishment delivery and intercity inventory dispatch.

Bidirectional robust and fault-tolerant H∞ non-sensitive compensation filter controller based on amorphous flattened air-to-ground wireless self-assembly system.

With the cross-fertilization development of automatic control technology, electronic science and technology, and wireless communication technology, a single filter is no longer able to solve the fault problem of the control system and communication system simultaneously and in a balanced manner. In this paper, we design a bidirectional robust fault-tolerant H∞ non-sensitive compensation filter controller based on the robust adaptive fault-tolerant control algorithm, and further optimize the fault-tolerance correction factor and robust adaptive factor by the LMI (Linear-Matrix-Inequation) method under the regulation of the feedback matrix K, so that the system estimation error can converge to zero asymptotically. It can simultaneously solve the optimization problems of unknown faults (including external disturbances, partial failure of internal actuators, and random interruptions) of the self-assembling node and the acquisition of SNR (Signal-Noise-Ratio) by wireless self-assembling nodes. The simulation results show that the system eventually tends to be asymptotically stable in all performance metrics with feedback adjustment under the designed filter controller, and the estimation error asymptotically tends to zero. The robustness and fault tolerance performance indicators are good against external disturbances and internal actuator failure of the wireless self-assembling network node. The control rate of the network system all increases significantly as the total feedback constraint rate of the system increases, allowing the system to eventually obtain the optimal SNR. The experimental results show that the network nodes of the amorphous flat wireless air-to-ground self-organizing network system can change flexibly and adaptively with the change of scenes, and the wireless communication distance between the network nodes is relatively improved by 86.36%, 110%, and 79.91%, and the loop success rate appears to be stable fluctuation interval, which can greatly improve the survival rate of the self-organizing network nodes. This paper is of great research significance for further realizing the long-spacing transmission of self-organizing nodes and laying the foundation for future low-altitude fly-by-wire research.

All-PM wavelength-tunable and harmonically mode-locking Yb-doped fiber laser.

We report a wavelength-tunable harmonically mode-locking dissipative soliton fiber laser based on a high-speed intensity modulator with a simple all-polarization-maintaining (all-PM) cavity. The center wavelength can be precisely tuned from 1029.35 to 1079.25 nm by tuning only the frequency of the pulse pattern generator (PPG), and the linear tuning accuracy of the wavelength can reach 0.0093 nm/kHz. The degree of polarization can reach 98.969%. The FWHM of the pulse is measured to be 30.1 ps, and the intracavity pulse energy after the gain fiber can reach 5.41 nJ. All orders of the harmonic mode-locking repetition rate are tuned from ∼33.346 to ∼366.806 MHz through adjustment of the data length and frequency of PPG.