The invention discloses a road passing time prediction method based on PSO and neural network series optimization. Firstly, based on the defects of a traditional impedance function, a road impedance function considering vehicle model influence is provided, a PSO algorithm is utilized to calibrate undetermined parameters in the optimized road impedance function, then a BP neural network is utilizedto further correct the calibrated road impedance function, and the impedance function is optimized through series combination of the two algorithms. Compared with a traditional prediction method, theaccuracy of road passing time prediction can be greatly improved.
本发明公开了一种基于PSO与神经网络串联优化的道路通行时间预测方法,首先依据传统阻抗函数的不足,提出了考虑车型影响的道路阻抗函数,利用PSO算法标定优化的道路阻抗函数中的待定参数,其次利用BP神经网络对标定后的道路阻抗函数进行进一步的修正,通过两种算法的串联组合对阻抗函数进行优化。本发明相较于传统预测方法,可以大大提高道路通行时间预测的准确度。
Road passing time prediction method based on PSO and neural network series optimization
基于PSO与神经网络串联优化的道路通行时间预测方法
2020-08-18
Patent
Electronic Resource
Chinese
IPC: | G06Q Datenverarbeitungssysteme oder -verfahren, besonders angepasst an verwaltungstechnische, geschäftliche, finanzielle oder betriebswirtschaftliche Zwecke, sowie an geschäftsbezogene Überwachungs- oder Voraussagezwecke , DATA PROCESSING SYSTEMS OR METHODS, SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORY OR FORECASTING PURPOSES / G06N COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS , Rechnersysteme, basierend auf spezifischen Rechenmodellen / G08G Anlagen zur Steuerung, Regelung oder Überwachung des Verkehrs , TRAFFIC CONTROL SYSTEMS |
European Patent Office | 2024
|Road passing method, road passing device, electronic device, vehicle and medium
European Patent Office | 2024
|Robust Time Series Prediction of Neural Network
British Library Online Contents | 2001
|