The dynamic parameters of Straddle-type monorail vehicles with single-axle bogies are optimised by utilising the multi-body dynamic method. The dynamic parameter optimisation is conducted aiming at the curve negotiation properties, comfort and tire eccentric wear of monorail vehicles. The optimisation model is established with software ADAMS and modeFRONTIER and the Sobol is adopted for sensitivity analysis to acquire the optimised parameters. Finally, the multiobjective collaborative optimisation algorithm is utilised for optimised analysis. According to the results, the proposed method can conduct multi-objective optimisation to the monorail vehicles in a successful way. The curve negotiation properties and comfort are improved, and the tire wear is reduced with dynamic parameters after optimisation. Especially, a conversion strategy of the consistent objective function is proposed aiming at multiobjective nonlinear convergence.

A common phenomenon of rail corrugation and its spatial distribution are observed in high-speed rail according to the overall and local field investigations, in which the rail corrugation with a wavelength of 100–300 mm and a depth of 0.01–0.05 mm normally occurs on both the rails in the sharp gradient sections of the high-speed rail. Then, a relevant simulation model of the wheelset–track system supported by the ballast-less track support structure and a wear model of track irregularity are built. Then, the typical phenomenon of rail corrugation on the high-speed rail is investigated from the aspect of the friction-induced vibration and the feedback vibration of wheelset–track, respectively. The obtained conclusions find that the friction-induced vibration caused by the saturated wheel–rail creep force is closely related to the appearance of rail corrugation in the sharp gradient of high-speed rail. Additionally, the feedback oscillation of corrugated wear with a shallow depth does not aggravate the rail corrugation, but may lead to a little difference in corrugation wavelengths in the same interval.

It is difficult for a single model to simultaneously capture the nonlinear, correlation, and periodicity of data series in the passenger flow prediction of urban rail transit (URT). To better predict the short-term passenger flow of URT, based on the long short-term memory network (LSTM) model, a deep learning model prediction method combining the time convolution network (TCN) and the long short-term memory network (LSTM) based on machine learning is proposed. The model couples the external factors such as date attributes, weather conditions, and air quality, to improve the overall prediction performance and solve the difficulty of accurate prediction due to the large fluctuation and randomness of short-term passenger flow in rail transit. Using the swiping data and related weather information of some stations of Chongqing Rail Transit Line 3, the TCN-LSTM model is verified by an example, and the prediction results of the single LSTM model are given for comparison. The results show that the TCN-LSTM model can better predict the passenger flow characteristics of different stations at different times. Compared with the single LSTM model, the TCN-LSTM model has better prediction accuracy and data generalization ability.

The finite element model of the running tyre and the pre-stressed concrete (PC) track beam are created in the study. The wheel-rail contact status under the conditions such as acceleration or braking, lateral deviation, and roll is...

Under the trend of promoting economy, environmental protection and high efficiency in the urban rail transit industry, this paper proposes a new type of straddle-type rapid transit system. Compared with most straddle-type monorail systems, it has the advantages of low construction cost and low operating cost, which makes it more suitable for urban rail transit system in small and medium-sized cities. In the process of vehicle development and design, in order to achieve the coordination and matching of tire systems and reduce the wear of tire systems, this work uses a multi-objective optimisation method to reduce the guiding torque of each tire system when the vehicle passes through the curve. Based on the vehicle dynamics model, the multi-body dynamics simulation model of the vehicle is established. The guiding torque of each tire system is taken as the optimisation objective, and the position and dynamic parameters of each tire system are taken as the optimisation parameter. Based on the NSGA-II algorithm, the ISIGHT and SIMPACK software are used for co-simulation. Finally, the guiding torque of each tire system is effectively reduced, and the coordination and matching of tire system is realised.

To address multiobjective, multi constraint and time-consuming structural optimization problems in a vehicle axle system, a multiobjective cooperative optimization model of a vehicle axle structure is established. In light of the difficulty in the nondominated sorting of the NSGA-II algorithm caused by inconsistent effects of the uniformity objective function and physical objective function, this paper combines a multiobjective genetic algorithm with cooperative optimization and presents a strategy for handling the optimization of a vehicle axle structure. The uniformity objective function of the sub discipline is transformed to its self-constraint. Taking the multiobjective optimization of a vehicle axle system as an example, a multiobjective cooperative optimization design for the system is carried out in ISIGHT. The results show that the multiobjective cooperative optimization strategy can simplify the complexity of optimization problems and that the multiobjective cooperative optimization method based on an approximate model is favorable for accuracy and efficiency, thereby providing a theoretical basis for the optimization of similar complex structures in practical engineering.