Asphalt Mixture Fatigue Life Prediction Model Based on Neural Network

doi:10.3969/j.issn.1674-0696.2018.02.06

Abstract

Abstract: A neural network fatigue life prediction model with single hidden layer was established on MATLAB platform. The model took 3 indexes as the input term，such as the asphalt content，the void fraction and the strain level，and took the fatigue life as the output item.Four point bending fatigue test was carried out under different conditions，and a total of 27 sets of test data after normalization were obtained for training.After training，the goodness of fitness of the neural network fatigue life prediction model (R2) could reach 0.91.To make a comparsion，the same data was used to fit the traditional fatigue life regression equation.All the statistical indexes show that the prediction results of the neural network model are obviously superior to that of the fatigue equation model.Meanwhile，the neural network also has the function of the index weight analysis that the fatigue equation does not possess.

Key words: highway engineering, fatigue life prediction, neural network, four point bending fatigue test

摘要： 以MATLAB为平台，搭建了一种单隐层结构的BP神经网络沥青混合料疲劳寿命预测模型。模型以沥青含量、空隙率和应变水平3个指标作为输入项，疲劳寿命作为输出项。进行了不同试验条件下的四点弯曲疲劳试验，将试验数据归一化处理后得到27组数据用于训练。训练后的神经网络疲劳寿命预测模型拟合优度R2可达到0.91。采用同一组数据对传统的疲劳方程模型进行拟合，并对比两者的预测效果，各项统计指标均显示神经网络模型预测结果明显优于疲劳方程模型，且神经网络还具有疲劳方程所不具备的指标权重分析的功能。

关键词: 道路工程, 疲劳寿命预测, 神经网络, 四点弯曲小梁疲劳试验

CLC Number:

U414

XIE Chunlei1，3，ZHANG Yong1，3，GENG Hongbin2，3，WANG Xueying1 ，2，3. Asphalt Mixture Fatigue Life Prediction Model Based on Neural Network[J]. Journal of Chongqing Jiaotong University(Natural Science), 2018, 37(02): 35-40.

谢春磊1，3，张勇1，3，耿红斌2，3，王学营1，2，3. 基于BP神经网络的沥青混合料疲劳性能预测模型[J]. 重庆交通大学学报（自然科学版）, 2018, 37(02): 35-40.

References

［1］ JONES D，HARVEY J T，MONISMITH C L.Reflective Cracking Study：Summary Report［R］.UC Berkeley：University of California Pavement
Research Center，2007.
［2］ QI X，SHENOY A，AL-KHATEEB G.Laboratory characterization and fullscale accelerated performance testing of crumb rubber asphalts
and other modified asphalt systems［C］//Asphalt Rubber Conference.Palm Springs，California：［s.n.］，2006：39-66.
［3］ MANGIAFICO S，BENEDETTO H D，SAUZAT C，et al.Statistical analysis of the influence of RAP and mix composition on viscoelastic
and fatigue properties of asphalt mixes［J］.Materials & Structures，2015，48(4)：1187-1205.
［4］ MONISMITH C L，LONG F，HARVEY J T.California’s interstate-710 rehabilitation：Mix and structural section designs，construction
specifications［J］.Asphalt Paving Technology：Association of Asphalt Paving Technologists-Proceedings of the Technical Sessions，2001
，70：762-799.
［5］ DONDI G，PETTINARI M，SANGIORGI C，et al.Traditional and Dissipated Energy approaches to compare the 2PB and 4PB flexural
methodologies on a warm mix asphalt［J］.Construction & Building Materials，2013，47(47)：833-839.
［6］赵复笑，余天庆，金生吉.沥青路面反射裂缝机理及夹层结构应力分析［J］.沈阳建筑大学学报(自然科学版)，2010，26(2)：296-300.
ZHAO Fuxiao，YU Tianqing，JIN Shengji.Experimental study on deformati of multi-level retaining［J］.Journal of Shenyang Jianzhu
University(Natural Science)，2010，26(2)：296-300.
［7］ HAFEEZ I，KAMAL M A，MIRZA M W，et al.Laboratory fatigue performance evaluation of different field laid asphalt mixtures
［J］.Construction & Building Materials，2013，44(7)：792-797.
［8］ LI N，MOLENAAR A A A，PRONK A C，et al.Application of the partial healing model on laboratory fatigue results of asphalt mixture
［J］.Construction & Building Materials，2015，95：842-849.
［9］李友坤.BP神经网络的研究分析及改进应用［D］.合肥：安徽理工大学，2012.
LI Youkun.Analysis and Improvement Applications of Bp Neural Network［D］.Hefei：Anhui University of Science and Technology，2012.
［10］谭忆秋，公维强，徐慧宁.基于BP神经网络沥青混合料低温弯拉应变预测模型［J］.沈阳建筑大学学报(自然科学版)，2009，25(2)：224-229.
TAN Yiqiu，GONG Weiqiang，XU Huining.Research on the application of neural network in the model for limiting flexural strain of
asphalt mixture at low temperature［J］.Journal of Shenyang Jianzhu University (Natural Science)，2009，25(2)：224-229.
［11］王震宇.基于BP神经网络的沥青老化预测系统研究［D］.重庆：重庆交通大学，2014.
WANG Zhenyu.Research on Asphalt Aging Prediction System Based on BP Neural Network［D］.Chongqing：Chongqing Jiaotong University，
2014.
［12］ XIAO F P.Development of Fatigue Predictive Models of Rubberized Asphalt Concrete (RAC) Containing Reclaimed Asphalt Pavement
(RAP) Mixtures［D］.South Carolina ：Clemson University，2006
［13］吴宏宇，熊卫士，张庆明.基于沥青混合料疲劳性能预测的混沌神经网络模型研究［J］.公路交通技术，2011(5)：45-47，53.
WU Hongyu，XIONG Weishi，ZHANG Qingming.Research on chaotic neural network model based on prediction for fatigue performance of
asphalt mixtures［J］.Technology of Highway and Transport，2011(5)：45-47，53.
［14］袁斌，葛折贵，葛折圣.沥青混合料抗疲劳性能的预测模型［J］.市政技术，2006，24(1)：31-33.
YUAN Bin，GE Zhegui，GE Zhesheng.Prediction model of asphalt mixtures fatigue properties［J］.Municipal Engineering Technology，
2006，
24(1)：31-33.
［15］ FAKHRI M，HASSANI K，GHANIZADEH A R.Impact of loading frequency on the fatigue behavior of sbs modified asphalt mixtures［J］.
Procedia-Social and Behavioral Sciences，2013，104(3)：69-78.
［16］张天云，陈奎，魏伟，等.BP神经网络法确定工程材料评价指标的权重［J］.材料导报，2012，26(2)：159-163.
ZHANG Tianyun，CHEN Kui，WEI Wei，et al.The determination of index weights for comprehensive evaluation of engineering materials with
bp neural network［J］.Materials Review，2012，26(2)：159-163.
［17］ WANG Z L，LI Y C，SHEN R F.Correction of soil parameters in calculation of embankment settlement using a BP network back-
analysis model［J］.Engineering Geology，2007，91(2)：168-177.
［18］ HE Y，LI X，DENG X.Discrimination of varieties of tea using near infrared spectroscopy by principal component analysis and BP
model［J］.Journal of Food Engineering，2007，79(4)：1238-1242.
［19］马雁军，李建英，张兆同.基于神经网络的农业机械化水平影响因子权重测算和分析［J］.中国制造业信息化(学术版)，2006，35(5)：74-77.
MA Yanjun，LI Jianying，ZHANG Zhaotong.The factors weight measurement and analysis of agricultural mechanization level affect with bp
neural network［J］.Manufacturing Information Engineering of China，2006，35(5)：74-77.

[1]	Tailings AggregateLI Sheng1, YANG Xi1, ZHONG Ming2, XIAO Han2. Adhesion Performance and Micro-mechanisms of Asphalt-Antimony [J]. Journal of Chongqing Jiaotong University(Natural Science), 2026, 45(4): 29-37.
[2]	WAN Bing1, XIAO Shengcai1, XIONG Sui1, YANG Bo2, TANG Jiale2. Performance of Sandstone Asphalt Stabilized Macadam Mixed with Reclaimed Asphalt Pavement as Road Base Layer [J]. Journal of Chongqing Jiaotong University(Natural Science), 2026, 45(4): 38-44.
[3]	PENG Miaojuan1, CHEN Song1, LI Li1, ZHUANG Kailin2. Improved YOLOv8n Lightweight Highway Asset Detection Model for UAV Inspection [J]. Journal of Chongqing Jiaotong University(Natural Science), 2026, 45(3): 1-10.
[4]	HE Chao1, LAN Jingjie2, LI Maorong2, ZHANG Lu1, REN Xunfu3, HE Zhaoyi2. Rheological Properties and Microscopic Mechanisms of Rubber-Plastic Alloy Modified Asphalt with Activation-Grafting Pretreatment [J]. Journal of Chongqing Jiaotong University(Natural Science), 2026, 45(3): 30-38.
[5]	XIAO Zhiquan, PANG Guoqiang, CAI Zhanwen, WANG Pei. Application of CNN-LSTM in Predicting CG Height of the Whole Vehicle by the Tilt Table Method [J]. Journal of Chongqing Jiaotong University(Natural Science), 2026, 45(3): 120-127.
[6]	LI Longhai, WU Siming. Evaluation of Airport Rigid Pavement Grades and Parameter Sensitivity [J]. Journal of Chongqing Jiaotong University(Natural Science), 2026, 45(2): 14-23.
[7]	LING Tianqing1, WEI Qiao1,2,3, YUAN Ying1. Evaluation of Crack Resistance of Multi-source Oil Rejuvenated Asphalts Based on Optimized Parameters [J]. Journal of Chongqing Jiaotong University(Natural Science), 2026, 45(2): 24-30.
[8]	CHEN Hua，BAI Jiayu，LYU Yuejing. Intelligent Detection of Asphalt Pavement Wear Based on Terrain Prominence [J]. Journal of Chongqing Jiaotong University(Natural Science), 2026, 45(2): 31-38.
[9]	LI Ping1，ZHANG Liubo1，BAI Zhongliang1，LI Wei1, ZHANG Qiang2. Effect of Rejuvenator on the Rheological Properties and Anti-aging Performance of Aged Asphalt [J]. Journal of Chongqing Jiaotong University(Natural Science), 2026, 45(2): 39-46.
[10]	SHAO Changqiao, ZHANG Dongyu. Comparative Study on Calculation Models of the Transition Section Length of Parallel Acceleration Lane on Freeway [J]. Journal of Chongqing Jiaotong University(Natural Science), 2026, 45(1): 1-6.
[11]	YANG Pengpeng1,2, ZENG Shenghao2, XUE Hai2, BAI Yongliang2. Lithium Battery Remaining Life Prediction Based on Dual Strategy Optimization of VMD-HO-LSTM [J]. Journal of Chongqing Jiaotong University(Natural Science), 2026, 45(1): 120-128.
[12]	CHANG Jun, ZHONG Ziting, LIU Chenguang. Channel Missing Data Recovery of Bridge Monitoring System Based on Improved GRU [J]. Journal of Chongqing Jiaotong University(Natural Science), 2025, 44(9): 10-18.
[13]	LIU Yunfei1, LI Shuang1, MA Jianxiao2. Mobile ViT Network Road Defect Detection Model Integrating Multi-task Learning [J]. Journal of Chongqing Jiaotong University(Natural Science), 2025, 44(9): 84-92.
[14]	YANG Xiangfei, CHEN Yu. Prediction of High-Speed Rail Express Transportation Volume Based on Gray-BP Neural Network [J]. Journal of Chongqing Jiaotong University(Natural Science), 2025, 44(8): 66-74.
[15]	WANG Yuanyuan1,2, LI Biyang1, ZHOU Zhe1, YANG Jianhua2, LIU Yanyan3. Binocular Fusion Structured Light Vision Algorithm and Complex Environment Impact Analysis in the Field of Road Applications [J]. Journal of Chongqing Jiaotong University(Natural Science), 2025, 44(7): 67-74.