Driving Quality Prediction of Highway Asphalt Pavement Based on PCA-GA-LSSVMR

doi:10.3969/j.issn.1674-0696.2023.05.05

Abstract

Abstract: To realize accurate prediction of highway driving quality and save maintenance cost, in the context of machine learning theory, a PCA-GA-LSSVMR-based prediction model for driving quality of highway was proposed based on historical pavement performance data. Firstly, the box plot analysis method and min-max standardization method were used to pre-process the road performance data, screen out abnormal data and normalize the data to ensure the reliability of data quality. Then the PCA-GA-LSSVMR model was used in Rstudio software to predict the driving quality and compared with the SVMR model and PCA-LSSSVMR model. The study shows that the linear regression determination coefficient of the proposed model is 0.835, and the model has the best stability. The root mean square error is 2.394, indicating that the model has the smallest prediction error. The average prediction accuracy of the model is 86%, which can effectively evaluate the driving quality of asphalt pavement.

Key words: highway engineering; prediction of driving quality of asphalt pavement; machine learning

摘要： 为实现对高速公路路面行驶质量的准确预测，节约养护成本，在机器学习理论背景下，以历史路面性能数据为基础，提出一种基于PCA-GA-LSSVMR的高速公路沥青路面行驶质量预测模型。首先采用箱型图分析法和min-max标准化方法对路面性能数据进行预处理，筛选剔除异常数据，并对数据进行归一化处理，保证数据质量的可靠性，然后在Rstudio软件中利用PCA-GA-LSSVMR模型对行驶质量进行预测，并与SVMR模型、PCA-LSSVMR模型进行对比。研究表明：PCA-GA-LSSVMR模型线性回归确定系数为0.835，模型稳定性最好，均方根误差为2.394，预测误差最小，模型平均预测准确率为86%，预测精度较高，能够对沥青路面行驶质量进行有效评估。

关键词: 道路工程；沥青路面行驶质量预测；机器学习

CLC Number:

U418.6

CAO Xuejuan1, LI Xiaoyu1, WU Bowen2, HAO Zengheng3. Driving Quality Prediction of Highway Asphalt Pavement Based on PCA-GA-LSSVMR[J]. Journal of Chongqing Jiaotong University(Natural Science), 2023, 42(5): 35-43.

曹雪娟1，李小宇1，吴博文2，郝增恒3. 基于PCA-GA-LSSVMR的高速公路沥青路面行驶质量预测[J]. 重庆交通大学学报（自然科学版）, 2023, 42(5): 35-43.

References

［1］管子豪.高速公路沥青路面使用性能预测及预防养护决策研究［D］. 西安：长安大学,2019.
GUAN Zihao. Research on Performance Prediction and Prevention and Maintenance Decision of Highway Asphalt Pavement ［D］. Xian: Changan University, 2019.
［2］ BUTT A A, SHAHIN M Y, CARPENTER S H, et al. Application of Markov process to pavement management systems at network level ［C］ // The Third International Conference on Managing Pavement, Washington D.C., 1994.
［3］ JOHNSON K D, CATION K A.Performance Prediction Development Using Three Indexes for North Dakota Pavement Management Systems ［R］. Washington D.C.: Transportation Research Board, 1992.
［4］ ABAZA K A. Empirical Markovian-based models for rehabilitated pavement performance used in a life cycle analysis approach ［J］. Structure and Infrastructure Engineering, 2017, 13(5): 625-636.
［5］ HOSSAIN M I, GOPISETTI L S P, MIAH M S. Internationalroughness index prediction of flexible pavements using neural networks ［J］. Journal of Transportation Engineering, Part B: Pavements, 2019, 145(1): 04018058.
［6］ BIANCHINI A, BANDINI P. Prediction ofpavement performance through neuro-fuzzy reasoning ［J］. Computer-Aided Civil and Infrastructure Engineering, 2010, 25(1): 39-54.
［7］于晓贺,邱怀中,罗蓉,等.基于修正灰色预测模型的沥青路面使用性能预测［J］.武汉理工大学学报(交通科学与工程版),2021,45(1):59-63.
YU Xiaohe, QIU Huaizhong, LUO Rong, et al. Prediction of asphalt pavement performance based on modified grey prediction model ［J］. Journal of Wuhan University of Technology (Transportation Science and Engineering), 2021, 45(1): 59-63.
［8］赵静,吴旺杰,王选仓,等.基于等维灰数递补模型的路面性能预测方法［J］.深圳大学学报(理工版),2019,36(6):628-634.
ZHAO Jing, WU Wangjie, WANG Xuancang, et al. Prediction method of pavement performance based on same dimension gray recurrence dynamic model ［J］. Journal of Shenzhen University (Science and Technology), 2019, 36(6): 628-634.
［9］李海莲,林梦凯,王起才.基于IFA-SVM的高速公路沥青路面使用性能预测［J］.公路交通科技,2019,36(12):8-14,78.
LI Hailian, LIN Mengkai, WANG Qicai. Prediction of performance of expressway asphalt pavement based on IFA-SVM ［J］. Journal of Highway and Transportation Research and Development, 2019, 36(12): 8-14,78.
［10］王笑风,毛海臻,杨博,等.基于深度学习LSTM网络的沥青路面性能预测研究［J］.公路交通科技(应用技术版),2020,16(8):4-7.
WANG Xiaofeng, MAO Haizhen, YANG Bo, et al. Research on asphalt pavement performance prediction based on deep learning LSTM network ［J］. Journal of Highway and Transportation Research and Development (Applied Technology Edition), 2020, 16(8): 4-7.
［11］赵静,王选仓,丁龙亭,等.基于灰色关联度分析和支持向量机回归的沥青路面使用性能预测［J］.重庆大学学报,2019,42(4):72-81.
ZHAO Jing, WANG Xuancang, DING Longting, et al. Performance prediction of asphalt pavement based on grey relational analysis and support vector machine regression ［J］. Journal of Chongqing University, 2019, 42(4): 72-81.
［12］陈仕周,李山,熊峰,等.基于GA-灰色神经网络的沥青路面使用性能预测［J］.重庆交通大学学报(自然科学版),2019,38(2):44-50.
CHEN Shizhou, LI Shan, XIONG Feng, et al. Forecasting of asphalt pavement performance based on GA-grey neural network ［J］. Journal of Chongqing Jiaotong University (Natural Science), 2019, 38(2): 44-50.
［13］杨国峰,王浩仰,潘玉利.基于混合效应模型的沥青路面使用性能预测［J］.公路交通科技,2018,35(8):19-27.
YANG Guofeng, WANG Haoyang, PAN Yuli. Prediction of asphalt pavement performance based on mixed effect model ［J］. Journal of Highway and Transportation Research and Development, 2018, 35(8):19-27.
［14］孔令云,尹果果,林雄伟,等.基于集料力学指标的沥青路面抗滑性能衰减模型［J］.长沙理工大学学报(自然科学版),2017,14(3):13-20.
KONG Lingyun, YIN Guoguo, LIN Xiongwei, et al. Anti-sliding performance attenuation model of asphalt pavement based on aggregate mechanical index ［J］. Journal of Changsha University of Science and Technology (Natural Science), 2017, 14(3):13-20.
［15］陈勇,李鹏,张忠军,等.基于PCA-GA-LSSVM的输电线路覆冰负荷在线预测模型［J］.电力系统保护与控制,2019,47(10):110-119.
CHEN Yong, LI Peng, ZHANG Zhongjun, et al. Online prediction model for power transmission line icing load based on PCA-GA-LSSVM［J］. Power System Protection and Control, 2019, 47(10): 110-119.
［16］王彦彬.基于PCA-PSO-ELM的瓦斯涌出量预测［J］.湖南科技大学学报(自然科学版),2020,35(4):1-9.
WANG Yanbin. Prediction of gas emission based on PCA-PSO-ELM ［J］. Journal of Hunan University of Science and Technology (Natural Science Edition), 2020, 35(4):1-9.
［17］ HOFFMANN A, STANKO M E. Real-time production optimization of a production network with ESP-boosted wells: A case study ［C］ // SPE Middle East Artificial Lift Conference and Exhibition, Manama, Kingdom of Bahrain,2016.
［18］ ABDELAZIZ M, LASTRA R, XIAO JJ. ESP data analytics: Predicting failures for improved production performance ［C］ // Abu Dhabi International Petroleum Exhibition & Conference, Abu Dhabi, 2017.
［19］ DRUCKER H, BURGES C J C, KAUFMAN L, et al. Support vector regression machines ［C］ // Advances in Neural Information Processing Systems. Cambridge, MA: MIT Press, 1997, 9: 155-161.
［20］ LI Zhi, YE Lin, ZHAO Yongning, et al. Short-term wind power prediction based on extreme learning machine with error correction ［J］. Protection and Control of Modern Power Systems, 2016, 1:1.
［21］王帅伟,于少将,李绍康,等.基于RS-PCA-GA-SVM的砂土液化预测方法研究［J］.地震工程学报,2019,41(2):445-453.
WANG Shuaiwei, YU Shaojiang, LI Shaokang, et al. A method of predicting sand liquefaction based on RS-PCA-GA-SVM ［J］. China Earthquake Engineering Journal, 2019, 41(2): 445-453.
［22］袁颖,李绍康,周爱红.基于PCA-GA-SVM的火成岩分类方法研究［J］.数学的实践与认识,2017,47(12):121-128.
YUAN Ying, LI Shaokang, ZHOU Aihong. Study on the classification method of igneous rocks based on PCA-GA-SVM ［J］. Mathematics in Practice and Theory, 2017, 47(12): 121-128.

[1]	GAO Lining, FU Xiaohong, JIA Qinlong, HE Rui, CHEN Huaxin. Effects of Carboxyl Group on Performance of Amphoteric Asphalt Emulsifier and Emulsified Asphalt [J]. Journal of Chongqing Jiaotong University(Natural Science), 2020, 39(11): 81-85.
[2]	CHEN Shizhou1, 2, LI Shan1, XIONG Feng2, LI Guannan1. Forecasting of Asphalt Pavement Performance Based on GA-Gray Neural Network [J]. Journal of Chongqing Jiaotong University(Natural Science), 2019, 38(02): 44-50.
[3]	WEI Lianyu，LI Hao,MA Xinwei. Mechanics Analysis and Disease Prevention of the Pavement Around Inspection Well Using ABAQUS [J]. Journal of Chongqing Jiaotong University(Natural Science), 2016, 35(4): 25-28.
[4]	LI Lin-jian, TANG Bo-ming, WEI Gang, WU Zhi-hui. Computation of Thermal Interface Stress in Two-Layer Concrete Slab Based on Energy Variation Principle [J]. Journal of Chongqing Jiaotong University(Natural Science), 2008, 27(4): 555-557.
[5]	SUN Bo-cheng, QIU Yan-jun. Pavement Cracks Identification Using Image Technology [J]. Journal of Chongqing Jiaotong University(Natural Science), 2008, 27(1): 61-64,168.
[6]	LUO Xiao-hui,DONG Jun,LIU Hai-liang. Mechanics Model Analysis of Joint after Overlaying Asphalt on old Concrete Pavement [J]. Journal of Chongqing Jiaotong University(Natural Science), 2007, 26(6): 82-86.
[7]	BAI Wen-jun ，HE Zhao-yi ，LI Li ，YANG Shao-jing ，JIANG Wen-li. Material Study on Faulting of Slab Ends of Cement Concrete Pavements [J]. Journal of Chongqing Jiaotong University(Natural Science), 2007, 26(4): 69-72.
[8]	ZHAO Li-jie，CHEN Kun-lin，LIU Jun，CHEN Zuo-ming. How to layout the south-north approach of lijiaotuo Changjiang River bridge Chongqing [J]. Journal of Chongqing Jiaotong University(Natural Science), 2006, 25(5): 28-31.
[9]	BIAN Jia-min，HAO Xiu-min. Outline of research in the reason of the rural cement concrete pavement fissure an d the prevent [J]. Journal of Chongqing Jiaotong University(Natural Science), 2006, 25(1): 35-37.
[10]	CHENG Feng. APPlieation of Pressure grouting to rePair strong road bed and eonerete roadin Huizhou Nan sanhuan road [J]. Journal of Chongqing Jiaotong University(Natural Science), 2004, 23(Z1): 34-35.
[11]	YI Zhi-jian. Discussion of the forming mechanism of reflective cracks in pavement from the angle of deformation compatibility [J]. Journal of Chongqing Jiaotong University(Natural Science), 2003, 22(4): 17-19.
[12]	MEI Ying-jun , LI Zhi-yong. Reflective cracks analysis on asphalt over layer [J]. Journal of Chongqing Jiaotong University(Natural Science), 2002, 21(2): 45-48.
[13]	JIANG Ying-jun , DAI Jing-liang , CHEN Zhong-da. Analyzing about cracking mechanism and prevention and cure measures of semi-rigid base course [J]. Journal of Chongqing Jiaotong University(Natural Science), 2002, 21(2): 54-57.
[14]	WANG Yan-li, WANG Bing-gang. Research of maintenance criteria of asphalt pavement for high-graded roadway [J]. Journal of Chongqing Jiaotong University(Natural Science), 2000, 19(4): 26-29.
[15]	MU Chang-chun, HE Zhao-yi. A new method on priority rating of pavement maintenance planning [J]. Journal of Chongqing Jiaotong University(Natural Science), 2000, 19(3): 51-53.