Aiming at estimating the road surface condition with improvement of the accuracy in spatial, this paper proposes a new method to classify road surface condition by considering identification interval based on vehicle system responses. First, the response signals in different vehicle speeds are decomposed by using both Wavelet Transform (WT) and Empirical Mode Decomposition (EMD) techniques. Then characteristics of the signals in both the time and decomposed frequency domain are subsequently extracted. An Improved Distance Evaluation Technique (IDET) is used to select superior features from the characteristics. Finally, a Support Vector Machine (SVM) classifier is applied to determine the road classification. The influences of identification intervals in spatial accuracy are discussed, and an adaptive classification interval was proposed to improve accuracy. The algorithm is validated by using both simulation and experimental results.

Abstract. Upper-equipment mounting system is playing more and more important role in the field of transportation vibration isolation. This study summarizes configuration categories, development and research status of the mounting system. Research direction future need of the mounting system is also proposed.

Applying the multi-dynamic theory, a dynamic model of the upper-equipment mounting system of some vehicle is established. An optimization model for the upper-equipment mounting system is constructed, in which the driver's vertical acceleration RMS value and upper equipment vertical acceleration, pitch angle acceleration and roll angle acceleration of the RMS value are selected as objective function, and the mounted stiffness and damping as design variables of optimization.

To address the problems of 5G network planning and optimization, a 5G user time delay prediction model based on the BiLSTM neural network optimized by APSO-SD is proposed. First, a channel generative model based on the ray-tracing model and the statistical channel model is constructed to obtain a large amount of time delay data, and a 5G user ray data feature model based on three-dimensional stereo mapping is proposed for input feature extraction. Then, an adaptive particle swarm optimization algorithm based on a search perturbation mechanism and differential enhancement strategy (APSO-SD) is proposed for the parameters’ optimization of BiLSTM neural networks. Finally, the APSO-SD-BiLSTM model is proposed to predict the time delay of 5G users. The experimental results show that the APSO-SD has a better convergence performance and optimization performance in benchmark function optimization compared with the other PSO algorithms, and the APSO-SD-BiLSTM model has better user time delay prediction accuracy in different scenarios.