Weigh-in-motion is an efficient way to manage overload vehicles, and usually utilizes multi-sensor to measure vehicle weight at present. To increase generalization and accuracy of support vector regression (SVR) applied in multi-sensor weigh-in-motion data fusion, three improved algorithms are presented in this paper. The first improved algorithm divides train samples into two sets to construct SVR1 and SVR2, respectively, and then test samples are distributed to SVR1 or SVR2 based on the nearest distance principle. The second improved algorithm calculates the theoretical biases of two training samples closeted to one test sample, and then obtains the bias of the test sample by linear interpolation method. The third improved algorithm utilizes the second improved algorithm to realize adaptive adjustment of biases for SVR1 and SVR2. Five vehicles were selected to conduct multi-sensor weigh-in-motion experiments on the built test platform. According to the obtained experiment data, fusion tests of SVR and three improved algorithms are performed, respectively. The results show that three improved algorithms gradually increase accuracy of SVR with fast operation speed, and the third improved algorithm exhibits the best application prospect in multi-sensor weigh-in-motion data fusion.
WangTWangSZhangL, et al. A major infrastructure risk-assessment framework: application to a cross-sea route project in China. Int J Project Manage2016; 34: 1403–1415.
2.
ZhouYSunL. Effects of high winds on a long-span sea-crossing bridge based on structural health monitoring. J Wind Eng Ind Aerodyn2018; 174: 260–268.
3.
ChenBYeZChenZ, et al. Bridge vehicle load model on different grades of roads in China based on Weigh-in-Motion (WIM) data. Measurement2018; 122: 670–678.
XuXWangJWeiJ, et al. A forensic investigation of the Taihe arch bridge collapse. Eng Struc2018; 176: 881–891.
9.
BurnosPRysD. The effect of flexible pavement mechanics on the accuracy of axle load sensors in vehicle weigh-in-motion systems. Sensors2017; 17: 2053–2069.
10.
HaugenTLevyJAakreE, et al. Weigh-in-motion equipment-experiences and challenges. Transp Res Proc2016; 14: 1423–1432.
11.
CollopAHakimBThomN. Effects of weigh-in-motion errors on pavement thickness design. Proc IMechE Part D: J Automobile Engineering2002; 216: 141–151.
12.
QinTLinMCaoM, et al. Effects of sensor location on dynamic load estimation in weigh-in-motion system. Sensors2018; 18: 3044–3060.
13.
GajdaJBurnosPSrokaR. Accuracy assessment of weigh-in-motion systems for vehicle’s direct enforcement. IEEE Intel Transp Sy2018; 10: 88–94.
14.
ChenNLiQLiF, et al. A data processing algorithm based on vehicle weigh-in-motion systems. In: Proceedings of the 2013 ninth international conference on natural computation, Shenyang, China, 23–25 July 2013, pp.227–231. New York: IEEE.
15.
BurnosPGajdaJPiwowarP, et al. Accurate weighing of moving vehicles. Metrol Meas Syst2007; 14: 507–516.
16.
ZhangWSuoCWangQ. A novel sensor system for measuring wheel loads of vehicles on highways. Sensors2008; 8: 7671–7689.
17.
LiBLiYWangH, et al. Compensation of automatic weighing error of belt weigher based on BP neural network. Measurement2018; 129: 625–632.
18.
KimSLeeJParkM-S, et al. Vehicle signal analysis using artificial neural networks for a bridge weigh-in-motion system. Sensors2009; 9: 7943–7956.
19.
MangeasMGlaserSDolcemascoloV. Neural networks estimation of truck static weights by fusing weight-in-motion data. In: Proceedings of the fifth international conference on information fusion, Annapolis, MD, 8–11 July 2002, pp.456–462. New York: IEEE.
20.
ShamseldinABlackBJO’BrienE. Multiple-sensor weigh-in-motion of road vehicles using a neural network algorithm. In: Topping BHV (ed.) Computational engineering using metaphors from nature. Edinburgh: Civil-Comp Press, 2000, pp.53–58.
21.
GonzálezAPapagiannakisATO’BrienE. Evaluation of an artificial neural network technique applied to multiple-sensor weigh-in-motion systems. Transport Res Rec2003; 1855: 151–159.
22.
ZhouYCaoR. The artificial neural network prediction algorithm research of rail-gun current and armature speed based on B-dot probes array. Measurement2019; 133: 47–55.
23.
VapnikVGolowichSSmolaA. Support vector method for function approximation, regression estimation, and signal processing. Adv Neur In 1996; 9: 281–287.
24.
WuCLChauKWLiYS. River stage prediction based on a distributed support vector regression. J Hydrol2008; 35: 96–111.
25.
KarimipourABagherzadehSATaghipourA, et al. A novel nonlinear regression model of SVR as a substitute for ANN to predict conductivity of MWCNT-CuO/water hybrid nanofluid based on empirical data. Physica A2019; 521: 89–97.
26.
TokanNTGuneşF. Knowledge-based support vector synthesis of the microstrip lines. Prog Electromagn Res2009; 92: 65–77.
27.
GaoDZhangYCaoJ. Urban road status perception information fusion using support vector regression. In: Proceedings of the 2013 4th IEEE international conference on software engineering and service science, Beijing, China, 23–25 May 2013, pp.870–873. New York: IEEE.
28.
ShamshirbandSPetkovićDJavidniaH, et al. Sensor data fusion by support vector regression methodology—a comparative study. IEEE Sens J2015; 15: 850–854.
29.
SantosJDABarretoGA. Novel sparse LSSVR models in primal weight space for robust system identification with outliers. J Process Contr2018; 67: 129–140.
30.
ChenK. Forecasting systems reliability based on support vector regression with genetic algorithms. Reliab Eng Syst Saf2007; 92: 423–432.
31.
QinTZengSGuoJ. Robust prognostics for state of health estimation of lithium-ion batteries based on an improved PSO-SVR model. Microelectron Reliab2015; 55: 1280–1284.
32.
GajdaJSrokaRZeglenT, et al. The influence of temperature on errors of WIM systems employing piezoelectric sensors. Metrol Meas Syst2013; 20: 171–182.
33.
LiuXFengZHuH. Fusion design method of weigh-in-motion sensor based on piezoelectric material. Chin J Sci Inst2019; 40: 115–122.
34.
SmolaAJSchoelkopfB. A tutorial on support vector regression. Stat Comput2004; 14: 199–222.
35.
RoushangarKKooshehA. Evaluation of GA-SVR method for modeling bed load transport in gravel-bed rivers. J Hydrol2015; 527: 1142–1152.
36.
ZhangWZhangLYangJ, et al. An experimental modeling of cyclone separator efficiency with PCA-PSO-SVR algorithm. Powder Technol2019; 347: 114–124.
37.
ChenJChingRKLinY. An extended study of the K-means algorithm for data clustering and its applications. J Oper Res Soc2004; 55: 976–987.
