Identification of braking condition for heavy truck on long downhill

doi:10.3969/j.issn.1674-8484.2023.03.005

Abstract

Abstract:

The traditional continuous braking system excessively relies on the subjective judgment of the driver to open and close, which is prone to the problem of thermal decline of the whole vehicle’s braking performance caused by improper operation. Therefore, this paper proposed a method to construct and identify the braking condition of heavy truck on long downhill, which provided a basis for the continuous braking system to intervene or withdraw from active control. Based on the long downhill test data of heavy trucks, including brake pedal action, vehicle speed and GPS data, the long downhill braking conditions was constructed using short stroke division, K-clustering, coding techniques and the Markov-Monte Carlo method, where the total time was 1 194 s and the total distance was 21.18 km. Based on the principle of rolling time window, the Back Propagation(BP) neural network working condition identification model was established, and offline training and identification verification was carried out. The results show that the recognition accuracy of general braking and forced braking working conditions is 89.30%, proving that the proposed method can effectively identify the braking status of heavy trucks on long downhill.

Key words: automotive engineering, heavy truck, braking condition, Markov-Monte Carlo method, condition identification, rolling time window

CLC Number:

U463.5

SHI Peilong, GAO Yipeng, ZHANG Zihao, ZHAO Xuan, YU Qiang. Identification of braking condition for heavy truck on long downhill[J]. Journal of Automotive Safety and Energy, 2023, 14(3): 299-309.

Figures/Tables 29

制动踏板模式	特征
无动作模式	制动踏板位移为0的连续过程；
动作模式	制动踏板位移非0且制动踏板变化率 > 0.05 mm/s;
保持模式	制动踏板位移非0且制动踏板变化率的绝对值 < 阈值(0.05 mm/s);
松开模式	制动踏板位移非0且制动踏板变化率 > -0.05 mm/s

制动踏板平均位移	$D m = 1 n ∑ 1 n D i$
制动踏板位移标准差	$D s t d = 1 n ∑ 1 n (D i - D m) 2$
制动踏板最大位移	$D m a x = m a x D 1 ≤ i ≤ n i$
制动踏板最小位移	$D m i n = m i n 1 ≤ i ≤ n D i$
制动踏板平均位移变化率	$G m = 1 n ∑ 1 n G i$
制动踏板位移变化率标准差	$G s t d = 1 n ∑ 1 n (G i - G m) 2$
制动踏板最大位移变化率	$G m a x = m a x ? G 1 ≤ i ≤ n i$
制动踏板最小位移变化率	$G m i n = m i n 1 ≤ i ≤ n G i$
平均坡度	$i m = 1 n ∑ 1 n i i$
平均速度	$v m = 1 n ∑ 1 n v i$
速度标准差	$v s t d = 1 n ∑ 1 n (v i - v m) 2$
最大速度	$v m a x = m a x 1 ≤ i ≤ n v i$
最小速度	$v m i n = m i n 1 ≤ i ≤ n v i$
平均加速度	$a m = 1 n ∑ 1 n a i$
加速度标准差	$a s t d = 1 n ∑ 1 n (a i - a m) 2$
最大加速度	$a m a x = m a x a 1 ≤ i ≤ n i$
最小加速度	$a m i n = m i n a 1 ≤ i ≤ n i$

制动踏板平均位移	$D m = 1 n ∑ 1 n D i$
制动踏板位移标准差	$D s t d = 1 n ∑ 1 n (D i - D m) 2$
制动踏板最大位移	$D m a x = m a x D 1 ≤ i ≤ n i$
制动踏板最小位移	$D m i n = m i n 1 ≤ i ≤ n D i$
制动踏板平均位移变化率	$G m = 1 n ∑ 1 n G i$
制动踏板位移变化率标准差	$G s t d = 1 n ∑ 1 n (G i - G m) 2$
制动踏板最大位移变化率	$G m a x = m a x ? G 1 ≤ i ≤ n i$
制动踏板最小位移变化率	$G m i n = m i n 1 ≤ i ≤ n G i$
平均坡度	$i m = 1 n ∑ 1 n i i$
平均速度	$v m = 1 n ∑ 1 n v i$
速度标准差	$v s t d = 1 n ∑ 1 n (v i - v m) 2$
最大速度	$v m a x = m a x 1 ≤ i ≤ n v i$
最小速度	$v m i n = m i n 1 ≤ i ≤ n v i$
平均加速度	$a m = 1 n ∑ 1 n a i$
加速度标准差	$a s t d = 1 n ∑ 1 n (a i - a m) 2$
最大加速度	$a m a x = m a x a 1 ≤ i ≤ n i$
最小加速度	$a m i n = m i n a 1 ≤ i ≤ n i$

位置号	D_s(t)	i_s(t)	v_s(t)	状态表示	c_t(t)
1	1	2	2	（1，2，2）	17
2	1	2	2	（1，2，2）	17
3	1	2	2	（1，2，2）	17
4	1	2	2	（1，2，2）	17
5	1	1	2	（1，1，2）	13
…	…	…	…	…	…
15	1	2	1	（1，2，1）	5
16	1	2	2	（1，2，2）	17
17	1	2	4	（1，2，4）	41
…	…	…	…	…	…
660	2	2	3	（2，2，3）	30
661	4	2	3	（4，2，3）	32
662	4	2	3	（4，2，3）	32
663	3	2	3	（3，2，3）	31
664	1	2	2	（1，2，2）	17
…	…	…	…	…	…
864	1	2	1	（1，2，1）	5
865	1	1	1	（1，1，1）	1
866	1	1	1	（1，1，1）	1

片段间隔	相关系数
1	0.747 7
2	0.565 2
5	0.330 7
10	0.222 4

特征参数	符号	特征参数	符号
平均制动踏板位移	D_m	制动踏板位移标准差	D_std
制动踏板无动作时间比	P_D1	平均制动踏板位移变化率	G_m
制动踏板踩踏时间比	P_D2	平均制动踏板踩踏变化率	G_sm
制动踏板动作保持时间比	P_D3	平均制动踏板松放变化率	G_1m
制动踏板松放时间比	P_D4	制动踏板位移变化率标准差	G_std
平均坡度	i_m	坡度标准差	i_std
平均速度	V_m	速度标准差	V_std
怠速时间比	P_V1	平均加速度	A_m
加速时间比	P_V2	平均正加速度	A₁
匀速时间比	P_V3	平均负加速度	A₂
减速时间比	P_V4	加速度标准差	A_std

特征参数	总体数据	典型工况	偏差 / %
D_m	5.532 1	5.939 1	7.36
P_D1	0.043 9	0.035 5	19.19
P_D2	0.377 6	0.397 2	5.18
P_D3	0.329 1	0.321 5	2.31
P_D4	0.249 4	0.245 9	1.43
D_std	0.698 9	0.632 1	9.56
G_s	0.035 9	0.033 0	8.13
G_sm	0.359 8	0.362 4	0.71
G_1m	-0.317 9	-0.322 8	1.51
G_std	0.447 9	0.437 7	2.27
i_m	0.035	0.035	0.00
i_std	0.002 5	0.002 2	11.48
v_m	64.980 7	65.339 9	0.55
P_V1	0.00	0.00	0.00
P_V2	0.564 2	0.582 5	3.23
P_V3	0.00	0.00	0.00
P_V4	0.435 8	0.417 5	4.18
v_std	0.218 9	0.202 1	7.67
a_m	-0.002 5	-0.001 4	42.58
a	0.039 0	0.038 9	0.27
a₂	-0.042 7	-0.042 0	1.63
a_std	0.017 9	0.018 0	0.63

	D_m	D_om	…	D_std	G_m	…	G_std
D_m	1.000 0	0.924 5	…	0.751 0	0.216 3	…	0.764 3
D_om	0.924 5	1.000 0	…	0.533 6	0.167 6	…	0.799 9
…	…	…	…	…	…	…	…
D_std	0.751 0	0.533 6	…	1.000 0	0.183 9	…	0.533 2
G_m	0.216 3	0.167 6		0.183 9	1.000 0	…	0.109 1
…	…	…	…	…	…	…	…
G_std	0.764 3	0.799 9		0.533 2	0.109 1	…	1.000 0

工况类别	1	2	3
短行程数量	19	10	22
D_m	0.263 7	3.281 2	5.190 6
D_om	0.479 7	3.794 2	7.510 5
D_max	0.914 6	9.651 7	12.038 4
G_sm	0.633 4	0.774 5	1.434 7
G_lm	-0.636 2	-0.836 0	-1.187 2
Δv₁	-1.609 5	-0.017 0	3.290 7
Δv₂	0.229 5	3.296 0	5.552 5

Δv₂	工况类别
Δv₂∈[0, 0.7]	加速弱制动工况
Δv₂∈[0.7, 4]	匀速一般制动工况
Δv₂∈[4, +∞]	减速强制动工况

References 15

[1]	Brady J, O’Mahony M. Development of a driving cycle to evaluate the energy economy of electric vehicles in urban areas[J]. Appl Energ, 2016, 177: 165-178. doi: 10.1016/j.apenergy.2016.05.094 URL
[2]	Balau A, Kooijman D, Vazquez R I, et al. Stochastic real-world drive cycle generation based on a two stage Markov chain approach[J]. SAE Int J Mate Manfact, 2015, 8(2): 390-397.
[3]	ZHAO Xuan, ZHAO Xiangmo, YU Qiang, et al. Development of a representative urban driving cycle construction methodology for electric vehicles: A case study in Xi'an - ScienceDirect[J]. Transport Res Part D: Transport Environ, 2020, 81(4):102278. doi: 10.1016/j.trd.2020.102278 URL
[4]	张宏, 姚延钢, 杨晓勤. 城市道路轻型汽车行驶工况构建[J]. 西南交通大学学报, 2019, 54(6): 1139-1146+1154.
	ZHANG Hong, YAO Yangang, YANG Xiaoqin. Light-duty vehicles driving cycle construction based on urban roads[J]. J Southwest Jiaotong Univ, 2019, 54(6): 1139-1146, 1154. (in Chinese)
[5]	曹骞, 李君, 曲大为. 大连市乘用车典型行驶工况的构建[J]. 上海交通大学学报, 2018, 52(11): 1537-1542.
	CAO Qian, LI Jun, QU Dawei. Construction of typical driving cycle for passenger cars in the city of dalian[J]. J Shanghai Jiaotong Univ, 2018, 52(11): 1537-1542. (in Chinese)
[6]	孙强, 白书战, 韩尔樑, 等. 基于试验测量的瞬时行驶工况构建[J]. 吉林大学学报(工学版), 2015, 45(2): 364-370.
	SUN Qiang, BAI Shuzhan, HAN Erliang, et al. Instantaneous driving cycle construction based on experimental measurement[J]. J Jilin Univ (Engi Tech Edit), 2015, 45(2): 364-370. (in Chinese)
[7]	胡正云. 乘用车城市行驶工况构建方法研究[J]. 公路交通科技, 2019, 36(11): 142-150. doi: 10.3969/j.issn.1002-0268.2019.11.019
	HU Zhengyun. Study on construction method of urban driving cycle of passenger vehicles[J]. J Highway Transport Res Develop, 2019, 36(11): 142-150. (in Chinese)
[8]	Emilia S, Kobus H, HUEI P, et al. Synthesis of realistic driving cycles with high accuracy and computational speed, including slope information[J]. IEEE Trans Contr Syst Vehi Tech, 2015, 65(6): 4118-4128.
[9]	高建平, 高小杰. 改进模糊C均值聚类法的车辆实际行驶工况构建[J]. 河南科技大学学报(自然科学版), 2017, 38(6): 21-27+4-5.
	GAO Jianping, GAO Xiaojie. Vehicle real driving cycle construction based on improved fuzzy C-means clustering algorithm[J]. J Henan Univ Sci Tech (Natu Sci). 2017, 38(6): 21-27+4-5. (in Chinese)
[10]	Förster D, Inderka R, Gauterin F. Data-driven identification of characteristic real-driving cycles based on k-means clustering and mixed-integer optimization[J]. IEEE Trans Vehi Tech, 2020, 69(3): 2398-2410.
[11]	高建平, 赵金宝, 孙中博, 等. 基于工况识别的插电式混合动力公交车控制策略[J]. 科学技术与工程, 2016, 16(21): 99-105+111.
	GAO Jianping, ZHAO Jinbao, SUN Zhongbo, et al. Control strategy of plug-in hybrid electric bus base on drive-cycle recognition[J]. Sci Tech Engi, 2016, 16(21): 99-105+111. (in Chinese)
[12]	石琴, 仇多洋, 吴冰, 等. 基于粒子群优化支持向量机算法的行驶工况识别及应用[J]. 中国机械工程, 2018, 29(15): 1875-1883.
	SHI Qin, QIU Duoyang, WU Bing, et al. DCR and applications based on PSO-SVM algorithm[J]. China Mech Engi, 2018, 29(15): 1875-1883. (in Chinese)
[13]	余强, 陈萌三, 马建, 等. 发动机制动、排气制动与缓行器联合作用的模糊控制系统研究[J]. 汽车工程, 2004, 26(4): 476-480.
	YU Qiang, CHEN Yingsan, MA Jian, et al. A research on fuzzy control system with combination of engine brake, exhaust brake and retarder[J]. Autom Engi, 2004, 26(4): 476-480. (in Chinese)
[14]	韩云武, 罗禹贡, 李克强. 基于驾驶员意图和行车安全的下坡辅助制动退出方法[J]. 汽车工程, 2015, 37(10): 1144-1149 +1143.
	HAN Yunwu, LUO Yugong, LI Keqiang. A retreat scheme for downhill assist braking based on driver's intent and driving safety[J]. Autom Engi, 2015, 37(10): 1144- 1149 +1143. (in Chinese)
[15]	韩云武, 罗禹贡, 赵峰, 等. 混合动力汽车发动机辅助制动控制方法[J]. 汽车工程, 2014, 36(12): 1433-1438.
	HAN Yunwu, LUO Yugong, ZHAO Feng, et al. Control method of engine auxiliary braking for hybrid electric vehicles[J]. Autom Engi, 2014, 36(12): 1433-1438. (in Chinese)