基于LM-BD-ESN模型的路面抗滑性能預測
首發時間：2023-10-19
摘要：針對路面抗滑性能預測任務中存在的指標單一和預測精度差等問題，在傳統回聲狀態網絡（echo state network, ESN）模型的基礎上，提出了邏輯映射(logistic mapping, LM)和偏差丟失(bias dropout, BD)優化的改進回聲狀態網絡模型(LM-BD-ESN)。其中，LM模塊能夠優化輸入權重矩陣，從而與多變量非平穩序列數據產生更高的契合度；BD模塊能夠自主刪除多余的存儲單元，從而降低模型復雜度。針對路面材料與抗滑性能之間存在的非線性關系描述，基于三維測量儀采集路面的多組三維形貌數據，分別利用支持向量機(support vector machine, SVM)、相關向量機(relevance vector machine, RVM)、極限學習機(extreme learning machine, ELM)、ESN及LM-BD-ESN對路面抗滑數據進行分析驗證。結果表明，所提LM-BD-ESN算法在預測任務中的均方根誤差和平均絕對百分比誤差分別為0.085 8和0.066 4，相較于其他算法具有更高的效率和精度。
關鍵詞： 路面性能 抗滑預測 多變量時間序列分析 LM-BD-ESN模型
For information in English, please click here
Prediction of pavement skid resistance based on LM-BD-ESN model
Abstract：As the main index of highway performance evaluation, pavement skid resistance performance analysis and trend prediction are important items to improve the construction quality and ensure service safety of highway. In order to solve the problem of single index and poor prediction accuracy, an improved Echo State Network (LM-BD-ESN) model optimized by Logical Mapping (LM) and Bias Dropout (BD) was proposed on the basis of the traditional Echo State Network (ESN) model, which was further applied to the prediction task of pavement anti-sliding performance. Compared with traditional ESN model, LM-BD-ESN model has stronger generalization ability and better network model structure. Among them, the logic mapping module of LM can optimize the input weight matrix, thus producing a higher degree of fitting with the multivariate time series data. The deviation loss module of BD can delete redundant storage cells independently, thus reducing the complexity of the model. In view of the nonlinear relationship between pavement materials and anti-sliding performance, multiple sets of three-dimensional topography data of pavement was collected based on three-dimensional measuring instrument. Based on this, the anti-sliding data of pavement using support vector machine (SVM), relevance vector machine (RVM), extreme learning machine (ELM), ESN and LM-BD-ESN were analyzed and verified, respectively. The results show that the root mean square error and average absolute percentage error of the LM-BD-ESN algorithm proposed in this paper are 0.085 8 and 0.066 4, respectively in the prediction task, which has higher efficiency and accuracy compared with other algorithms.
Keywords： pavement performance rediction of anti-sliding performance multivariable time series analysis LM-BD-ESN model
論文圖表：
引用
No.****
同行評議
勘誤表
基于LM-BD-ESN模型的路面抗滑性能預測
中國科技論文在線 版權所有
網站地圖|
在線首頁|
在線簡介|
服務條款|
聯系我們
京公網安備 11040202430024號 京ICP備15006316號-2| 網絡出版服務許可證 （總）網出證（京）字第083號 | 文保網安備案號：1101080066
提示
.txt
.ris
.doc
評論
全部評論