基于GWO−NSGA−Ⅱ混合算法的露天矿低碳运输调度

文家燕; 闻海潮; 程洋; 罗绍猛; 何伟朝

doi:10.13272/j.issn.1671-251x.2022080008

基于GWO−NSGA−Ⅱ混合算法的露天矿低碳运输调度

doi: 10.13272/j.issn.1671-251x.2022080008

1.
广西科技大学自动化学院, 广西柳州　545616
2.
柳州铁道职业技术学院通信信号学院, 广西柳州　545616
3.
广西柳工机械股份有限公司, 广西柳州　545007

基金项目: 国家自然科学基金项目（61963006）。

详细信息

作者简介:
文家燕（1981—）,男，广西全州人，教授，博士，主要研究方向为多挖掘机协同与控制研究，E-mail：wenjiayan2012@126.com

通讯作者:
程洋（1988—）,男，河南汝南人，讲师，硕士，主要研究方向为智能调度，E-mail：747226728@qq.com

中图分类号: TD57
计量
- 文章访问数: 140
- HTML全文浏览量: 33
- PDF下载量: 15
- 被引次数: 0
出版历程
- 收稿日期: 2022-08-02
- 修回日期: 2023-02-04
- 网络出版日期: 2023-02-27

Low-carbon transportation scheduling of open-pit mine based on GWO-NSGA-Ⅱ hybrid algorithm

1.
School of Automation, Guangxi University of Science and Technology, Liuzhou 545616, China
2.
Faculty of Railway Communication and Signaling Technology, Liuzhou Railway Vocational Technical College, Liuzhou 545616, China
3.
Guangxi Liugong Machinery Co., Ltd., Liuzhou 545007, China

摘要

摘要: 为了提高露天矿卡车运输效率、减少碳排放和节约运输成本，以纯电动卡车为研究对象，以运输成本、总排队时间（包含生产过程中的卡车充电时间、运行时间及维修等待时间）、矿石品位偏差为目标函数，并以破碎场破碎量、采矿场开采量、装车数量、矿石品位误差限制、车辆充电桩选择及充电限制为约束条件，建立了露天矿低碳运输调度优化模型。针对灰狼优化算法（GWO）和非支配排序遗传算法（NSGA−Ⅱ）用于求解露天矿纯电动矿用卡车低碳运输调度模型时前者容易陷入局部最优、后者容易获得全局最优但收敛缓慢的问题，提出了一种GWO−NSGA−Ⅱ混合算法。该混合算法在GWO算法中引入NSGA−Ⅱ的选择、交叉、变异3种遗传操作，有效防止算法陷入局部最优；在NSGA−Ⅱ的精英保留策略中引入狩猎和攻击操作，提高算法全局收敛的稳定性。通过5个标准测试函数验证了该混合算法在保证收敛性的情况下提升了稳定性。实例分析表明，与NSGA−Ⅱ，GWO相比，该混合算法在寻优速度上分别提高了48.7%和27.1%，在寻优精度上分别提高了17.1%和9.3%，且减少了卡车使用数量、碳排放量、运输距离和运输费用。
- 露天矿运输 /
- 低碳 /
- 运输调度 /
- 非支配排序遗传算法 /
- 灰狼优化算法
Abstract: In order to improve truck transport efficiency, reduce carbon emissions and save transport costs in open-pit mines, pure electric trucks are taken as the research object. The objective function is transportation cost, total queuing time (including truck charging time, operation time and maintenance waiting time in the production process), and ore grade deviation. The constraints include the crushing capacity of the crushing site, mining capacity of the mining site, loading capacity, ore grade error limit, vehicle charging pile selection and charging limit. The optimization model of low carbon transportation scheduling of open-pit is established. The gray wolf optimization (GWO) and non-dominated sorting genetic algorithm-II (NSGA-II) have been used to solve the low-carbon transportation scheduling model for pure electric mining trucks in open-pit mines. The former is prone to get trapped in local optimum while the latter is likely to achieve a global optimum but converges slowly. In order to solve the above problems, a GWO-NSGA-II hybrid algorithm is proposed. The hybrid algorithm introduces three genetic operations of NSGA-II, selection, crossover and mutation, into the GWO algorithm to effectively prevent the algorithm from falling into local optimum. In order to improve the stability of the global convergence of the algorithm, hunting and attack operations are introduced into the elite retention strategy of NSGA-II. Five standard test functions are used to verify that the hybrid algorithm improves the stability while ensuring the convergence. The example analysis shows that, compared with NSGA-II and GWO, the hybrid algorithm improves the optimization speed by 48.7% and 27.1% respectively. The hybrid algorithm improves the optimization precision by 17.1% and 9.3% respectively. The hybrid algorithm reduces the number of trucks, carbon emissions, transportation distance and transportation costs.
- open-pit mine transportation /
- low-carbon /
- transportation scheduling /
- non-dominated sorting genetic algorithm /
- gray wolf optimization algorithm

HTML全文

图 1 GWO−NSGA−Ⅱ混合算法流程

Figure 1. GWO−NSGA−Ⅱ hybrid algorithm flow

下载: 全尺寸图片幻灯片

图 2 GWO−NSGA−Ⅱ混合算法对标准测试函数的测试结果

Figure 2. Test results of GWO-NSGA-Ⅱ hybrid algorithm on standard test functions

下载: 全尺寸图片幻灯片

图 3 不同算法的进化曲线

Figure 3. Evolution curves of different algorithms

下载: 全尺寸图片幻灯片

表 1 不同算法的标准测试函数测试结果对比

Table 1. Comparison of standard test function test results of different algorithms

测试函数	性能指标	NSGA−Ⅱ	GWO−NSGA−Ⅱ	提升百分比/%
ZDT1	$\gamma $	0.005 8	0.005 6	—
ZDT1	$\varDelta $	0.442 0	0.398 5	9.84
ZDT2	$\gamma $	0.004 6	0.004 2	—
ZDT2	$\varDelta $	0.654 7	0.509 7	22.14
ZDT3	$\gamma $	0.006 3	0.006 5	—
ZDT3	$\varDelta $	0.649 0	0.625 9	3.56
ZDT4	$\gamma $	0.877 5	2.983 0	70.58
ZDT4	$\varDelta $	0.556 7	0.411 8	26.03
ZDT6	$\gamma $	0.003 2	0.003 1	—
ZDT6	$\varDelta $	0.758 5	0.647 8	14.5

下载: 导出CSV

表 2 采矿场至破碎场距离

Table 2. Distance between mining site and crushing site

破碎场	采矿场至破碎场距离/km
破碎场	A₁	A₂	A₃	A₄	A₅	A₆	A₇	A₈
B₁	3.1	3.6	2.4	3.9	3.1	2.2	4.2	1.0
B₂	3.6	5.3	1.9	3.7	3.9	3.7	3.7	4.3
B₃	3.0	3.6	2.9	1.1	1.3	3.8	4.2	3.5
B₄	3.8	2.1	4.7	2.0	3.2	2.9	1.3	3.1

下载: 导出CSV

表 3 不同算法下露天矿低碳运输调度结果对比

Table 3. Comparison of low-carbon transportation scheduling results in open-pit mine under different algorithms

算法	运输距离/km	卡车数量/辆	用电费用/元	碳排放费用/元	运输费用/元
NSGA−Ⅱ	379.629	38	819.998	265.740	1 085.738
GWO	347.222	34	749.996	243.055	993.051
GWO−NSGA−Ⅱ	314.814	30	679.998	220.369	900.367

下载: 导出CSV

表 4 不同类型卡车露天矿运输调度结果对比

Table 4. Comparison of transportation scheduling results in open-pit mine under different types of truck

卡车类型	运输距离/km	卡车数量/辆	用电费用/元	碳排放量/g	运输费用/元
燃油卡车	314.814	30	1 227.78	44 609.144	1 548.049
电动卡车	314.814	30	679.998	30 694.365	900.367

下载: 导出CSV

参考文献(23)

[1]	王忠鑫,辛凤阳,陈洪亮,等. 我国露天矿智能运输技术现状及发展趋势[J]. 工矿自动化,2022,48(6):15-26. WANG Zhongxin,XIN Fengyang,CHEN Hongliang,et al. Current status and development trend of intelligent transportation technology in China's open-pit mines[J]. Journal of Mine Automation,2022,48(6):15-26.
[2]	赵浩,毛开江,曲业明,等. 我国露天煤矿无人驾驶及新能源卡车发展现状与关键技术[J]. 中国煤炭,2021,47(4):45-50. doi: 10.19880/j.cnki.ccm.2021.04.007 ZAHO Hao,MAO Kaijiang,QU Yeming,et al. Development status and key technology of driverless and new energy trucks in open-pit coal mine in China[J]. China Coal,2021,47(4):45-50. doi: 10.19880/j.cnki.ccm.2021.04.007
[3]	苏楷,门飞. 露天矿运输调度问题求解的自适应果蝇优化算法[J]. 金属矿山,2017,46(11):172-176. doi: 10.3969/j.issn.1001-1250.2017.11.034 SU Kai,MEN Fei. Adaptive fruit fly optimization algorithm for solving open-pit hauling dispatching optimization problem[J]. Metal Mine,2017,46(11):172-176. doi: 10.3969/j.issn.1001-1250.2017.11.034
[4]	程平, 李晓光, 顾清华, 等. 露天矿新能源纯电动卡车的智能调度优化及应用[J/OL]. 金属矿山: 1-11[2022-05-04]. http://kns.cnki.net/kcms/detail/34.1055.TD.20211223.1738.002.html. CHENG Ping, LI Xiaoguang, GU Qinghua, et al. Intelligent scheduling optimization and application of new energy electric truck in open-pit mine[J/OL]. Metal Mine: 1-11[2022-05-04]. http://kns.cnki.net/kcms/detail/34.1055.TD.20211223.1738.002.html.
[5]	李勇,胡乃联,李国清. 基于改进粒子群算法的露天矿运输调度优化[J]. 中国矿业,2013,22(4):98-101,105. doi: 10.3969/j.issn.1004-4051.2013.04.027 LI Yong,HU Nailian,LI Guoqing. Open-pit hauling dispatching optimization based on improved PSO algorithm[J]. China Mining Magazine,2013,22(4):98-101,105. doi: 10.3969/j.issn.1004-4051.2013.04.027
[6]	彭程,薛伟宁,黄轶. 露天矿运输问题的模拟退火优化[J]. 中国矿业,2018,27(4):138-141. PENG Cheng,XUE Weining,HUANG Yi. Simulated annealing algorithm for the open-pit mine transportation problem[J]. China Mining Magazine,2018,27(4):138-141.
[7]	彭程,隋晓梅,王辉俊. 用于求解露天矿运输问题的改进差分进化算法[J]. 工矿自动化,2018,44(4):104-108. doi: 10.13272/j.issn.1671-251x.2017100044 PENG Cheng,SUI Xiaomei,WANG Huijun. Improved differential evolution algorithm for solving open-pit mine transportation problem[J]. Industry and Mine Automation,2018,44(4):104-108. doi: 10.13272/j.issn.1671-251x.2017100044
[8]	鞠兴军,李林,刘光伟. 基于遗传算法的神经网络在露天矿卡车调度系统中的应用研究[J]. 露天采矿技术,2009,24(6):31-33. doi: 10.3969/j.issn.1671-9816.2009.06.012 JU Xingjun,LI Lin,LIU Guangwei. Application research on truck dispatching system based on neural network of genetic algorithm in surface mine[J]. Opencast Mining Technology,2009,24(6):31-33. doi: 10.3969/j.issn.1671-9816.2009.06.012
[9]	刘浩洋. 基于改进蚁群算法的露天矿卡车优化调度研究[D]. 西安: 西安建筑科技大学, 2013. LIU Haoyang. Strip mine truck optimization scheduling research based on improved ant colony algorithm[D]. Xi'an: Xi'an University of Architecture and Technology, 2013.
[10]	蒋浩,唐欢容,郑金华. 一种基于快速排序的快速多目标遗传算法[J]. 计算机工程与应用,2005,41(30):46-48. doi: 10.3321/j.issn:1002-8331.2005.30.015 JIANG Hao,TANG Huanrong,ZHENG Jinhua. A fast multi-objective genetic algorithm based on quick sort[J]. Computer Engineering and Applications,2005,41(30):46-48. doi: 10.3321/j.issn:1002-8331.2005.30.015
[11]	门飞,蒋欣. 求解露天矿低碳运输调度问题的改进灰狼优化算法[J]. 工矿自动化,2020,46(12):90-94. doi: 10.13272/j.issn.1671-251x.2020070049 MEN Fei,JIANG Xin. Improved gray wolf optimization algorithm for solving low-carbon transportation scheduling problem in open-pit mines[J]. Industry and Mine Automation,2020,46(12):90-94. doi: 10.13272/j.issn.1671-251x.2020070049
[12]	MIRJALILI S,MIRJALILI S M,LEWIS A. Grey wolf optimizer[J]. Advances in Engineering Software,2014,69:46-61. doi: 10.1016/j.advengsoft.2013.12.007
[13]	SAREMI S,MIRJALILI S Z,MIRJALILI S M. Evolutionary population dynamics and grey wolf optimizer[J]. Neural Computing and Applications,2015,26(5):1257-1263. doi: 10.1007/s00521-014-1806-7
[14]	张明,顾清华,李发本,等. 基于多目标遗传算法的露天矿卡车调度优化研究[J]. 金属矿山,2019,48(6):157-162. doi: 10.19614/j.cnki.jsks.201906028 ZHANG Ming,GU Qinghua,LI Faben,et al. Research of open-pit mine truck dispatching optimization based on multi-objective genetic algorithm[J]. Metal Mine,2019,48(6):157-162. doi: 10.19614/j.cnki.jsks.201906028
[15]	吕新桥,廖天龙. 基于灰狼优化算法的置换流水线车间调度[J]. 武汉理工大学学报,2015,37(5):111-116. LYU Xinqiao,LIAO Tianlong. Permutation flow-shop scheduling based on the grey wolf optimizer[J]. Journal of Wuhan University of Technology,2015,37(5):111-116.
[16]	冯麟皓,方喜峰,李俊. 基于灰狼算法的多目标车间调度优化[J]. 组合机床与自动化加工技术,2023(1):168-172. doi: 10.13462/j.cnki.mmtamt.2023.01.038 FENG Linhao,FANG Xifeng,LI Jun. Multi-objective job shop scheduling optimization based on gray wolf algorithm[J]. Modular Machine Tool & Automatic Manufacturing Technique,2023(1):168-172. doi: 10.13462/j.cnki.mmtamt.2023.01.038
[17]	王敏,唐明珠. 一种新型非线性收敛因子的灰狼优化算法[J]. 计算机应用研究,2016,33(12):3648-3653. doi: 10.3969/j.issn.1001-3695.2016.12.029 WANG Min,TANG Mingzhu. Novel grey wolf optimization algorithm based on nonlinear convergence factor[J]. Application Research of Computers,2016,33(12):3648-3653. doi: 10.3969/j.issn.1001-3695.2016.12.029
[18]	龙文,赵东泉,徐松金. 求解约束优化问题的改进灰狼优化算法[J]. 计算机应用,2015,35(9):2590-2595. doi: 10.11772/j.issn.1001-9081.2015.09.2590 LONG Wen,ZHAO Dongquan,XU Songjin. Improved grey wolf optimization algorithm for constrained optimization problem[J]. Journal of Computer Applications,2015,35(9):2590-2595. doi: 10.11772/j.issn.1001-9081.2015.09.2590
[19]	王琴,杨信丰,李楠,等. 不确定环境下的危险品运输车辆路径优化[J]. 计算机工程与应用,2022,58(15):309-316. doi: 10.3778/j.issn.1002-8331.2201-0137 WANG Qin,YANG Xinfeng,LI Nan,et al. Route optimization of hazardous materials transportation vehicles in uncertain environment[J]. Computer Engineering and Applications,2022,58(15):309-316. doi: 10.3778/j.issn.1002-8331.2201-0137
[20]	EI-GAAFARY A A M,MOHAMED Y S,HEMEIDA A M,et al. Grey wolf optimization for multi input multi output system[J]. Universal Journal of Communications and Network,2015,3(1):1-6. doi: 10.13189/ujcn.2015.030101
[21]	林海. 城市纯电动车配送路径优化研究[D]. 西安: 长安大学, 2018. LIN Hai. Optimization of the urban vehicle routing problem of pure electric vehicles[D]. Xi'an: Chang'an University, 2018.
[22]	SALIM F,JULES T,YASH G. A new algorithm using front prediction and NSGA-II for solving two and three-objective optimization problems[J]. Optimization and Engineering,2015(4):713-736.
[23]	乔俊飞,李霏,杨翠丽. 一种基于均匀分布策略的NSGAⅡ算法[J]. 自动化学报,2019,45(7):1325-1334. doi: 10.16383/j.aas.c180085 QIAO Junfei,LI Fei,YANG Cuili. An NSGA II algorithm based on uniform distribution strategy[J]. Acta Automatica Sinica,2019,45(7):1325-1334. doi: 10.16383/j.aas.c180085