Current status and development trend of intelligent transportation technology in China's open-pit mines
-
摘要: 运输环节作为露天矿生产工艺的最重要因素之一,其智能化是矿山整体智能化技术的重要研究内容。介绍了露天矿运输系统的构成及分类;明确了露天矿智能运输系统是以露天矿煤岩高效运输为应用场景,以智能化运输装备为核心载体,将物联网、云计算、大数据、人工智能、移动互联等数字技术与露天矿运输系统运行原理和工艺要求深度融合,建立运输系统内设备、环境、物料的自主协同高效运行体系,进而建立起大范围内发挥作用的实时、准确、高效的运输综合管理系统,其构成要素主要包括基础设施、运输工具和运算技术。指出露天矿传统运输系统与智能运输系统的区别在于智能运输系统以提高现场生产作业安全和效率为目标,服务对象由原来的生产管理人员转变为生产作业人员。从基础设施智能化、装备智能化、管控智能化、维保智能化和设计智能化5个方面,综述了我国露天矿智能运输系统的研究和产品应用现状。分析了露天矿卡车运输系统和带式输送机运输系统实现智能化亟待突破的关键技术:卡车智能运输关键技术包括矿山复杂路况的环境感知技术、无人驾驶卡车线控改造技术、多目标智能调度技术、有人−无人混编设备群智能协同技术;带式输送机智能运输关键技术包括工作面带式输送机自主横移技术、自移式大倾角带式输送机运输技术、带式输送机运行控制技术、带式输送机状态在线检测技术、带式输送机智能巡检技术、带式输送机无人化维护技术、带式输送机运输系统智能管控平台。指出露天矿智能运输发展的趋势为连续化、无人化、低碳化、高效协同和本质安全。Abstract: As one of the most important factors in the production process of open-pit mine, the intelligence of transportation is an important research content of the whole intelligence technology of mine. This paper introduces the composition and classification of the transportation system in open-pit mine. It is clarified that the intelligent transportation system in open-pit mine takes the efficient transportation of coal and rock in open-pit mine as the application scenario and the intelligent transportation equipment as the core carrier. The digital technologies such as the Internet of things, cloud computing, big data, artificial intelligence, and mobile Internet are integrated with the operating principles and technological requirements of the open-pit mine transportation system. The autonomous collaborative and efficient operation system of equipment, environment and materials in the transportation system is established. And the real-time, accurate and efficient transportation integrated management system that plays a role in a wide range is further established. The components of the intelligent transportation system in open-pit mine mainly include infrastructure, transportation tools and computing technology. It is pointed out that the difference between the traditional transportation system and the intelligent transportation system in open-pit mine lies in that the intelligent transportation system takes improving the safety and efficiency of field production operation as the goal. The service object is changed from the original production management personnel to the production operating personnel. The research and application status of intelligent transportation system in open-pit mine in China are summarized from five aspects, including intelligent infrastructure, intelligent equipment, intelligent management and control, intelligent maintenance and intelligent design. The key technologies of the truck transportation system and the belt conveyor transportation system in the open-pit mine to realize the intelligence are analyzed in this paper. The key technologies of intelligent truck transportation include environment perception technology for complex road conditions in mines, line control transformation technology for unmanned driving truck, multi-objective intelligent scheduling technology, and intelligent collaboration technology for manned-unmanned mixed equipment group. The key technologies of intelligent belt conveyor transportation include autonomous traverse technology of belt conveyor in working face, transportation technology of self-moving large-angle belt conveyor, operation control technology of belt conveyor, on-line status detection technology of belt conveyor, intelligent inspection technology of belt conveyor, unmanned maintenance technology of belt conveyor, intelligent management and control platform of belt conveyor transportation system. It is pointed out that the development trend of intelligent transportation in open-pit mine is continuous, unmanned, low-carbon, efficient coordination and intrinsic safety.
-
0. 引言
煤炭是我国的主体能源[1],在保障能源需求和推动经济增长方面发挥着关键作用。2020年2月25日,国家八部委联合印发《关于加快煤矿智能化发展的指导意见》,对煤矿运输设备无人驾驶、智能感知等提出了更高要求[2-3]。煤矿电机车作为主要的运输装备,承担着煤炭、物料、人员与相关设备的辅助运输任务[4]。由于矿井电机车运输作业场景多样,常运行于高噪声、窄巷道、低光照等恶劣环境[5]中,容易引起驾驶员疲劳驾驶,从而造成电机车脱轨、追尾等事故。因此,研究煤矿无人驾驶电机车的智能化感知技术具有重要意义。
环境感知是无人驾驶技术的重要组成部分,准确的目标检测对提高无人驾驶电机车的安全性和效率至关重要。传统的目标检测方法难以适应煤矿井下的复杂环境,随着深度学习的快速发展,基于深度学习的目标检测算法得到广泛应用[6]。目前以R−CNN[7]、Mask R−CNN[8]、YOLO系列[9]、SSD[10]等为代表的深度学习算法在目标检测中已取得优异表现。李伟山等[11]在Faster R−CNN上构建了一种区域候选网络(Region Proposals Network,RPN)结构,解决了煤矿井下行人检测的多尺度问题。He Deqiang等[12]在Mask R−CNN模型中引入了ResNet[13]骨干特征提取网络,提高了模型的检测精度。郝帅等[14]在YOLOv5网络模型中引入注意力机制,有效解决了复杂环境条件下输送带中非煤异物难以检测的问题。郑玉珩等[15]基于YOLOv5单阶段检测算法,采用BiFPN特征融合结构,解决了遮挡目标的检测问题。杨艺等[16]提出了一种LiYOLO模型,该模型在面对综采工作面动态变化、煤尘干扰等复杂情况下,表现出了良好的鲁棒性。葛淑伟等[17]通过改进SSD算法,提升了模型对锚孔的检测性能。尽管研究者们在目标检测领域取得了一定成就,但针对运行于光照不均、高噪声等复杂环境中的矿井电机车多目标检测精度低的问题有待深入研究。
为解决上述问题,本文提出了一种基于SD−YOLOv5s−4L的煤矿井下无人驾驶电机车多目标检测模型。在数据预处理阶段,采用高斯噪声、运动模糊和随机光照等方式对数据集进行增强处理,以提升数据集多样性和算法鲁棒性。在损失函数方面,用SIoU[18]替换了原有的CIoU[19],使网络可以更好地学习目标的位置信息。在YOLOv5s检测头部引入解耦头[20],缓解分类任务和回归任务之间的冲突,使模型可以快速捕捉目标的多尺度特征;引入小目标检测层,以增强网络对小目标的特征提取能力和检测精度。
1. YOLOv5s模型及其改进策略
1.1 YOLOv5s网络结构
YOLOv5s网络结构主要由骨干网络(Backbone)、颈部段(Neck)及头部端(Head)3个部分组成,如图1所示。Backbone由CBL模块、C3模块和SPPF模块组合而成,负责提取多尺度特征信息。CBL是由1个卷积层(Conv)、1个批标准化层(Batch Normalization,BN)和1个SiLu激活函数组成的卷积块;C3模块包含3个卷积层和多个Bottleneck模块;SPPF模块在空间金字塔池化(Spatial Pyramid Pooling,SPP)基础上,将原结构中3路并行的Maxpool改为串行,使网络模型能够在不影响性能的同时提升计算速率。Neck采用特征金字塔网络(Feature Pyramid Network, FPN)与路径聚合网络(Path Aggregation Network,PAN)结构来融合不同尺寸的特征图,从而获取丰富的特征信息。其中FPN[21]是自顶向下,将高层的语义信息传递到底层;PAN[22]是自底向上,将底层的位置信息传递到高层。Head根据前向传递的特征信息,在图像上生成带有特征的边界框,且边界框上显示有类别名称及检测概率。
1.2 YOLOv5s改进策略
1.2.1 损失函数改进
损失函数用来估量模型的预测值与真实值之间的不一致程度,目标检测的准确性在很大程度上依赖于所使用的损失函数,因此选用适当的损失函数有利于模型检测精度的提升。
在YOLO系列目标检测模型中,损失函数主要由分类损失、置信度损失和定位损失[23]组成。其中,定位损失对于目标检测算法具有重要意义。通过优化定位损失,算法可更准确地确定目标位置和边界框,并且能够在复杂场景中更好地区分目标和背景,从而提高模型的检测精度和抗干扰能力。
目前YOLOv5网络模型采用CIoU作为定位损失函数,CIoU综合考虑了真实框与预测框之间的重叠面积、中心点距离和长宽比,克服了GIoU的退化问题,同时解决了DIoU无法区分中心点重合时交并比一样的情况,但忽略了真实框与预测框之间角度不匹配的问题。当检测目标尺度差异较大时,模型的收敛速度会变慢,从而影响模型的检测精度。因此,本文引入SIoU作为YOLOv5网络的定位损失函数。SIoU计算公式为
$$ S_{\mathrm{IoU}} = 1 - I_{\mathrm{oU}} + \frac{{\varDelta + \varOmega }}{2} $$ (1) $$ \varDelta = \sum_{t = {\mathrm{x,y}}} {(1 - {\exp( - (2 - \varLambda ){\rho _t}}))} $$ (2) $$ \varLambda = 1 - 2 {\sin ^2}\left(\arcsin \left(\frac{{{c_{\mathrm{h}}}}}{\sigma }\right) - \frac{{\text{π}} }{4}\right) $$ (3) $$ \varOmega = {\sum\limits_{r = {\mathrm{w,h}}} {(1 - {\exp({ - {\omega _r}}}))} ^\theta } $$ (4) 式中:IoU为预测框和真实框的交并比;$ \varDelta $为距离损失;$ \varOmega $为形状损失;$ \varLambda $为角度损失;ρt为衡量预测框中心点与真实框中心点之间坐标偏差的归一化指标,t=x表示横坐标,t=y表示纵坐标;$ {c_{\mathrm{h}}} $为真实框与预测框中心点的高度差;$ \sigma $为真实框与预测框中心点的距离;ωr为预测框和真实框之间的偏差,r=w表示宽度偏差,r=h表示高度偏差;$ \theta $为权重系数。
$$ {\rho _{\mathrm{x}}} = {\left[ {\left( {b_{{C_{\mathrm{x}}}}^{{\mathrm{gt}}} - {b_{{C_{\mathrm{x}}}}}} \right)/{C_{\mathrm{w}}}} \right]^2} $$ (5) $$ {\rho _{\mathrm{y}}} = {\left[ {\left( {b_{{C_{\mathrm{y}}}}^{{\mathrm{gt}}} - {b_{{C_{\mathrm{y}}}}}} \right)/{C_{\mathrm{h}}}} \right]^2} $$ (6) $$ {\omega _{\mathrm{w}}} = \left| {w - {w^{{\mathrm{gt}}}}} \right|/\max \left( {w,{w^{{\mathrm{gt}}}}} \right) $$ (7) $$ {\omega _{\mathrm{h}}} = \left| {h - {h^{{\mathrm{gt}}}}} \right|/\max (h,{h^{{\mathrm{gt}}}}) $$ (8) 式中:$ b_{C_{\mathrm{x}}}^{{\mathrm{gt}}},b_{C_{\mathrm{y}}}^{{\mathrm{gt}}} $为真实框中心坐标;$ {b_{C_{\mathrm{x}}}},{b_{C_{\mathrm{y}}}} $为预测框中心坐标;$ {C_{\mathrm{w}}} $为真实框和预测框最小外接矩形的宽;$ {C_{\mathrm{h}}} $为真实框和预测框最小外接矩形的高;$ \left( {w,h} \right) $和$ \left( {{w^{{\mathrm{gt}}}},{h^{{\mathrm{gt}}}}} \right) $分别为真实框和预测框的宽和高。
SIoU在CIoU的基础上引入了角度损失,降低了损失的总自由度,使预测的边界框更加准确地适应目标的形状和方向。
1.2.2 解耦头
在目标检测中,分类任务与回归任务所关注的特征信息不同。分类任务需要确定图像中目标的类别,因此专注于特征图中的突出区域;回归任务则专注于目标的边缘信息,以此来准确预测目标在图像中的位置和尺度。
在YOLOv5网络模型中,分类任务和回归任务通过共享的卷积层完成。由于参数共享,分类任务和回归任务无法专注于各自的目标区域,使得2个任务之间相互干扰,导致模型性能降低。为解决上述问题,本文在YOLOv5s头部引入解耦头替换原耦合头,解耦头结构如图2所示,H,W,C分别为图像的高度、宽度和通道数。首先,采用1个1×1卷积对输入的FPN特征进行降维,将特征维数减少到256;然后,经过2个平行的分支,一个用于分类任务,一个用于回归任务,每个分支后面均接有2个3×3卷积;最后,分类分支再经过1个1×1卷积进行分类操作,回归分支中2个平行的定位与置信度分支里各经过1个1×1卷积进行定位和置信度操作。
解耦头通过2个分支分别处理分类任务和回归任务,使得2个任务之间相互独立、互不干扰。这种结构有利于模型快速准确地捕捉目标的多尺度特征,并在不同层级上进行特征融合与重定位,以提升目标检测的定位准确性与适应性。
1.2.3 小目标检测层
YOLOv5s网络模型通过多个下采样层来增强感受野,这导致图像分辨率降低,使得小目标的细节特征在较大感受野的特征图中变得模糊。此外,由于小目标与背景之间的尺度差异较大,模型更易聚焦于特征明显的区域,从而忽略小目标的微弱特征,导致网络模型对小目标的检测效果不佳。
为了提高网络模型对小目标的检测性能,本文在YOLOv5s网络中增加了1层小目标检测层。将原三尺度检测层增至4层,增强了网络模型对小目标的关注度,使得更底层的特征信息得到进一步融合,对小目标检测精度的提升有着积极作用。结合前述改进方式,将改进后的网络模型命名为SD−YOLOv5s−4L,其网络结构如图3所示。
2. 实验与分析
2.1 数据集创建
本文所采用的电机车图像数据采集于淮南矿业(集团)有限责任公司顾桥煤矿、淮北矿业股份有限公司袁店一矿及中煤新集能源股份有限公司新集二矿3个不同矿井中电机车运行的多段运输巷。为进一步提高数据集多样性与检测算法鲁棒性,除YOLOv5s网络模型本身的数据增强方法外,本文还采用高斯噪声、运动模糊及随机光照等方式对数据集进行增强处理。经整理后共得到4 500张图像,包含辅助运输作业过程中低照度、高噪声、人机多目标混杂及运动模糊4种生产环境。部分数据集图像如图4所示。采用标注工具LabelImg对数据集进行标注,标注类别有“person”“stone”“signal light”,分别表示行人、石块和信号灯。最后将标注好的图像按照8∶1∶1比例随机划分为训练集、测试集和验证集。
2.2 实验环境及评价指标
2.2.1 实验环境
本文实验环境为Ubuntu 18.04操作系统下搭建的PyTorch 1.9.0 深度学习框架Python 3.8及CUDA11.1编程软件,具体配置见表1。
表 1 实验环境Table 1. Experimental environment实验环境 参数 操作系统 Ubuntu 18.04 CPU Intel(R) Xeon(R) Platinum 8350C CPU@2.6 GHz GPU RTX 3090(24 GiB) 深度学习框架 PyTorch 1.9.0 编程语言 Python 3.8 CUDA 11.1 为获得最优训练模型,在网络模型训练前,需对模型配置文件中的超参数进行设置,具体见表2。batch-size为一批训练样本的数量,该值根据实验设备性能而定;momentum为动量,表示网络每次迭代更新的变化程度,调整梯度下降达到最优值的速度;decay为权重衰减系数,用来防止模型过拟合;learning rate为初始学习率,用以控制参数的更新速度;epochs为迭代次数。网络模型的优化器为SGD。
表 2 超参数设置Table 2. Hyper-parameter setting参数名称 数值 batch-size 32 momentum 0.937 decay 0.0005 learning rate 0.01 epochs 301 2.2.2 评价指标
在目标检测领域中,常用的评价指标包括准确率P、召回率R、平均精度(Average Precision,AP)、平均精度均值(mean Average Precision,mAP)及调和均值F1。有关评价指标的计算公式为
$$ P = \frac{{T_{\mathrm{P}}}}{{T_{\mathrm{P}} + F_{\mathrm{P}}}} $$ (9) $$ R = \frac{{T_{\mathrm{P}}}}{{T_{\mathrm{P}} + F_{\mathrm{N}}}} $$ (10) $$ m_{\mathrm{AP}} = \frac{{\displaystyle\sum {P} }}{N} $$ (11) $$ {F_1} = 2 \frac{{P R}}{{P + R}} $$ (12) 式中:$ T_{\mathrm{P}} $为正样本被正确识别为正样本的数量;$ F_{\mathrm{P}} $为负样本被错误识别为正样本的数量;$ F_{\mathrm{N}} $为正样本被错误识别为负样本的数量;mAP为mAP的值;$ N $为类别总数。
2.3 实验结果分析
2.3.1 不同网络模型检测效果对比
为了直观说明SD−YOLOv5s−4L网络模型的检测效果,将其与YOLOv5n、YOLOv5m和YOLOv5s网络模型进行对比,检测结果如图5所示。
由图5可看出,在对信号灯和行人的检测中,YOLOv5n、YOLOv5m和YOLOv5s网络模型出现了目标置信度得分低的问题,而SD−YOLOv5s−4L网络模型的目标置信度得分较高;在对小目标(石块)的检测中,YOLOv5n网络模型出现了错检情况,YOLOv5m和YOLOv5s存在漏检现象,而SD−YOLOv5s网络模型能够实现精准检测且检测精度较高。因此,SD−YOLOv5s−4L网络模型更能满足煤矿井下电机车的多目标检测需求。
2.3.2 消融实验
为了验证不同的改进策略对YOLOv5s网络模型的优化作用,设计了5组消融实验,实验结果见表3。
表 3 消融实验结果Table 3. Ablation experiment results实验 网络模型 AP mAP person signal light stone 1 YOLOv5s 0.945 0.945 0.891 0.927 2 YOLOv5s+ SIoU 0.946 0.942 0.931 0.940 3 YOLOv5s+解耦头 0.956 0.950 0.923 0.943 4 YOLOv5s+小目标检测层 0.972 0.959 0.971 0.968 5 YOLOv5s+SIoU+
小目标检测层+解耦头0.980 0.967 0.989 0.979 表3中每组消融实验mAP值的对比如图6所示。实验结果表明:引入SIoU损失函数,mAP为0.940,较YOLOv5s提升了1.3%,说明角度损失的加入降低了损失的总自由度,对模型检测精度的提升有着积极作用;引入解耦头后,mAP提升了1.6%,其中对行人、信号灯和石块分别提升了1.1%、0.5%及3.2%,说明解耦头的引入有利于增强网络模型的检测性能;添加小目标检测层后,mAP提高了4.1%,其中对石块的检测精度为97.1%,提高了8%,有效提升了网络模型对小目标的检测能力;将解耦头、SIoU及小目标检测层全部加入原YOLOv5s网络模型中,mAP为0.979,提升了5.2%,其中行人检测的平均精度提高了3.5%,信号灯检测的平均精度提升了2.2%,石块检测的平均精度提升高达9.8%。实验结果验证了各个改进策略对YOLOv5s网络模型均起到了较好的优化作用,有效解决了多目标检测精度低、小目标检测困难的问题。
2.3.3 对比实验
为了进一步验证SD−YOLOv5s−4L网络模型的检测性能,将其与YOLO系列的主流网络模型YOLOv5n,YOLOv5m,YOLOv5s,YOLOv7及YOLOv8进行对比,实验结果见表4。
表 4 对比实验结果Table 4. Comparative experimental results实验 网络模型 AP F1 mAP person signal light stone 1 YOLOv5n 0.900 0.913 0.923 0.89 0.912 2 YOLOv5m 0.965 0.960 0.935 0.93 0.954 3 YOLOv5s 0.945 0.945 0.891 0.91 0.927 4 YOLOv7 0.967 0.950 0.921 0.94 0.946 5 YOLOv8 0.948 0.926 0.985 0.92 0.953 6 SD−YOLOv5s−4L 0.980 0.967 0.989 0.96 0.979 表4中不同网络模型的mAP值对比如图7所示。实验结果表明:SD−YOLOv5s−4L网络模型对多种目标都有较高的检测精度,mAP较YOLOv5n,YOLOv5m,YOLOv5s,YOLOv7,YOLOv8分别提高了6.7%,2.5%,5.2%,3.3%和2.6%。调和均值F1为0.96,较YOLOv5n,YOLOv5m,YOLOv5s,YOLOv7,YOLOv8分别提高了7%,3%,5%,2%和4%,表明SD−YOLOv5s−4L网络模型具有更优异的性能。
3. 结论
1) 为解决真实框与预测框方向不匹配问题,引入损失函数SIoU,以降低损失的总自由度,使网络可以更好地学习目标的位置信息;为了缓解模型回归任务与分类任务之间的冲突,引入解耦头,使模型可以快速捕捉目标的多尺度特征;为解决小目标识别困难的问题,在YOLOv5的基础上增加小目标检测层,提升网络模型对小目标的检测性能。改进后的网络模型SD−YOLOv5s−4L的mAP较原YOLOv5s网络模型提升了5.2%,达97.9%。
2) SD−YOLOv5s−4L网络模型对小目标的检测精度高达98.9%,较YOLOv5s网络模型提升了9.8%,改进后的网络模型大幅提高了对小目标的检测能力,有效解决了小目标识别困难的问题。
3) 将SD−YOLOv5s−4L网络模型与YOLOv5n, YOLOv5m, YOLOv5s,YOLOv7,YOLOv8进行对比,实验结果表明:SD−YOLOv5s−4L网络模型对多种目标的检测精度均为最高且调和均值F1更逼近于1,为实现煤矿井下电机车的无人驾驶提供了技术支撑。
-
-
[1] 李杰, 王富, 何雅琴. 交通工程学[M]. 北京: 北京大学出版社, 2010. LI Jie, WANG Fu, HE Yaqin. Traffic engineering[M]. Beijing: Peking University Press, 2010.
[2] 张瑞新,赵红泽. 中国露天矿山信息化现状及发展趋势[J]. 露天采矿技术,2014(9):1-4. ZHANG Ruixin,ZHAO Hongze. Current situation and development trend of open-pit mines informatization in China[J]. Opencast Mining Technology,2014(9):1-4.
[3] 王国法. “双碳”目标下, 煤炭工业如何应对新挑战[N]. 中国煤炭报, 2021-09-23(3). WANG Guofa. How can the coal industry cope with new challenges under the goal of 'double carbon'[N]. China Coal News, 2021-09-23(3).
[4] 杨兆升, 于德新. 智能运输系统概论[M]. 3版. 北京: 人民交通出版社, 2015. YANG Zhaosheng, YU Dexin. Introduction to intelligent transportation system[M]. 3rd ed. Beijing: China Communication Press, 2015.
[5] 王青, 任凤玉, 顾晓薇, 等. 采矿学[M]. 北京: 冶金工业出版社, 2011. WANG Qing, REN Fengyu, GU Xiaowei, et al. Coal mining science[M]. Beijing: Metallurgical Industry Press, 2011.
[6] 王国法,庞义辉,任怀伟. 智慧矿山技术体系研究与发展路径[J]. 金属矿山,2022,51(5):1-9. DOI: 10.19614/j.cnki.jsks.202205001 WANG Guofa,PANG Yihui,REN Huaiwei. Research and development path of smart mine technology system[J]. Metal Mine,2022,51(5):1-9. DOI: 10.19614/j.cnki.jsks.202205001
[7] 王忠鑫,辛凤阳,宋波,等. 论露天煤矿智能化建设总体设计[J]. 煤炭科学技术,2022,50(2):37-46. DOI: 10.13199/j.cnki.cst.2021-1053 WANG Zhongxin,XIN Fengyang,SONG Bo,et al. Overall design of intelligent construction in open pit coal mines[J]. Coal Science and Technology,2022,50(2):37-46. DOI: 10.13199/j.cnki.cst.2021-1053
[8] 邓红星,巴兴强. 浅谈智能运输系统的发展[J]. 黑龙江交通科技,2008(1):117. DOI: 10.3969/j.issn.1008-3383.2008.01.060 DENG Hongxing,BA Xingqiang. On the development of intelligent transportation system[J]. Communications Science and Technology Heilongjiang,2008(1):117. DOI: 10.3969/j.issn.1008-3383.2008.01.060
[9] 王爽,余涵. 智能运输系统的发展与应用[J]. 交通世界,2019(7):8-9. WANG Shuang,YU Han. Development and application of intelligent transportation system[J]. Transpo World,2019(7):8-9.
[10] 何林,李克民. 无线Mesh网络技术在露天矿通信系统中的应用前景[J]. 金属矿山,2012,41(4):118-120,167. DOI: 10.3969/j.issn.1001-1250.2012.04.030 HE Lin,LI Kemin. Application outlook of wireless mesh networks in open-pit communication system[J]. Metal Mine,2012,41(4):118-120,167. DOI: 10.3969/j.issn.1001-1250.2012.04.030
[11] 郭文馨. 4G无线通信系统在露天矿山中的应用[J]. 电脑编程技巧与维护,2017(8):76-79. DOI: 10.3969/j.issn.1006-4052.2017.08.031 GUO Wenxin. Application of 4G wireless communication system in open pit mine[J]. Computer Programming Skills & Maintenance,2017(8):76-79. DOI: 10.3969/j.issn.1006-4052.2017.08.031
[12] 孙继平,陈晖升. 智慧矿山与5G和WiFi6[J]. 工矿自动化,2019,45(10):1-4. SUN Jiping,CHEN Huisheng. Smart mine with 5G and WiFi6[J]. Industry and Mine Automation,2019,45(10):1-4.
[13] 王国法,赵国瑞,胡亚辉. 5G技术在煤矿智能化中的应用展望[J]. 煤炭学报,2020,45(1):16-23. WANG Guofa,ZHAO Guorui,HU Yahui. Application prospect of 5G technology in coal mine intelligence[J]. Journal of China Coal Society,2020,45(1):16-23.
[14] 孙效玉,田凤亮,张航,等. 基于GPS数据的露天矿道路网自动提取[J]. 煤炭学报,2017,42(11):3059-3064. DOI: 10.13225/j.cnki.jccs.2017.0308 SUN Xiaoyu,TIAN Fengliang,ZHANG Hang,et al. Automatic extraction of road network in open-pit mine based on GPS data[J]. Journal of China Coal Society,2017,42(11):3059-3064. DOI: 10.13225/j.cnki.jccs.2017.0308
[15] TIAN Fengliang,SUN Xiaoyu,GU Xiaowei,et al. Updating road information in open-pit mines using truck trajectories[J]. Mathematical Problems in Engineering,2019,2019:1-8.
[16] SUN Xiaoyu,ZHANG Hang,TIAN Fengliang,et al. The use of a machine learning method to predict the real-time link travel time of open-pit trucks[J]. Mathematical Problems in Engineering,2018(7):1-14.
[17] 顾清华,薛步青,卢才武,等. 基于D−LinkNet网络的露天矿道路智能识别与路网建模[J]. 煤炭学报,2020,45(增刊2):1100-1108. GU Qinghua,XUE Buqing,LU Caiwu,et al. Road intelligent recognition and road network modeling of open pit based on D-LinkNet network[J]. Journal of China Coal Society,2020,45(S2):1100-1108.
[18] 李庆玲,张慧祥,赵旭阳,等. 露天矿无人驾驶自卸卡车发展综述[J]. 煤炭工程,2021,53(2):29-34. LI Qingling,ZHANG Huixiang,ZHAO Xuyang,et al. Overview of unmanned mining trucks in open-pit mine[J]. Coal Engineering,2021,53(2):29-34.
[19] 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: 10.3969/j.issn.1006-530X.2021.04.007 ZHAO 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: 10.3969/j.issn.1006-530X.2021.04.007
[20] 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[2022-04-15]. 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[2022-04-15]. http://kns.cnki.net/kcms/detail/34.1055.TD.20211223.1738.002.html.
[21] 葛世荣,郝尚清,张世洪,等. 我国智能化采煤技术现状及待突破关键技术[J]. 煤炭科学技术,2020,48(7):28-46. GE Shirong,HAO Shangqing,ZHANG Shihong,et al. Status of intelligent coal mining technology and potential key technologies in China[J]. Coal Science and Technology,2020,48(7):28-46.
[22] 蒋卫良,郗存根,宋兴元,等. 煤矿带式输送机关键技术发展现状与展望[J]. 智能矿山,2020,1(1):98-104. JIANG Weiliang,XI Cungen,SONG Xingyuan,et al. Development status and prospect of key technology of coal mine belt conveyor[J]. Journal of Intelligent Mine,2020,1(1):98-104.
[23] 李臻,操虹,贾洪钢,等. 煤矿带式输送机轴承监测诊断系统及其应用[J]. 工矿自动化,2011,37(12):15-18. LI Zhen,CAO Hong,JIA Honggang,et al. Bearing monitoring and diagnosis system of belt conveyor of coal mine and its application[J]. Industry and Mine Automation,2011,37(12):15-18.
[24] 曹艳军,柳骁. 原煤运输系统智能化关键技术研究[J]. 工矿自动化,2021,47(增刊2):56-59. CAO Yanjun,LIU Xiao. Research on the key technologies of intelligent coal transport system[J]. Industry and Mine Automation,2021,47(S2):56-59.
[25] 毛君, 陈迪, 白杨溪, 等. 一种带式输送机工作状态下的托辊更换车: CN112975830A[P]. 2021-06-18. MAO Jun, CHEN Di, BAI Yangxi, et al. An idler replacement vehicle under the working state of belt conveyor: CN112975830A[P]. 2021-06-18.
[26] 陈洪月, 毕文钦, 王鑫, 等. 一种运行中带式输送机托辊更换车: CN112975831A[P]. 2021-06-18. CHEN Hongyue, BI Wenqin, WANG Xin, et al. A roller replacement vehicle for belt conveyor in operation: CN112975831A[P]. 2021-06-18.
[27] 聂永朝,冯宝忠,杨洋. 带式输送机智能运维管理平台研究与设计[J]. 中国煤炭,2021,47(4):37-44. DOI: 10.3969/j.issn.1006-530X.2021.04.006 NIE Yongchao,FENG Baozhong,YANG Yang. Research and design of intelligent operation and maintenance management platform for belt conveyor[J]. China Coal,2021,47(4):37-44. DOI: 10.3969/j.issn.1006-530X.2021.04.006
[28] 付恩三,刘光伟,邸帅,等. 露天矿山无人驾驶技术及系统架构研究[J]. 煤炭工程,2022,54(1):34-39. FU Ensan,LIU Guangwei,DI Shuai,et al. Unmanned driving technology and system architecture in open-pit mines[J]. Coal Engineering,2022,54(1):34-39.
[29] 辛凤阳,王忠鑫,田凤亮,等. 基于BS架构的露天矿连续工艺一体化管控平台设计与实现[J]. 金属矿山,2021,50(12):177-182. XIN Fengyang,WANG Zhongxin,TIAN Fengliang,et al. Design and implementation of integrated management and control platform for open pit continuous process based on BS architecture[J]. Metal Mine,2021,50(12):177-182.
[30] 田凤亮,孙效玉,张航. 一种露天矿卡车故障的NLP技术挖掘与分析方法[J]. 金属矿山,2017,46(7):138-142. DOI: 10.3969/j.issn.1001-1250.2017.07.028 TIAN Fengliang,SUN Xiaoyu,ZHANG Hang. A mining and analyzing method of truck fault in open-pit mine based on NLP technology[J]. Metal Mine,2017,46(7):138-142. DOI: 10.3969/j.issn.1001-1250.2017.07.028
[31] 白润才,柴森霖,刘光伟,等. 基于Mallat算法与ARMA模型的露天矿卡车故障率预测[J]. 中国安全科学学报,2018,28(10):31-37. DOI: 10.16265/j.cnki.issn1003-3033.2018.10.006 BAI Runcai,CHAI Senlin,LIU Guangwei,et al. Method for predicting truck's failure rate in open-pit mine based on Mallat algorithm and ARMA model[J]. China Safety Science Journal,2018,28(10):31-37. DOI: 10.16265/j.cnki.issn1003-3033.2018.10.006
[32] 刘威,郭直清,黄敏,等. 基于MCMC算法的露天矿典型设备故障预测方法研究[J]. 煤炭科学技术,2019,47(10):51-57. LIU Wei,GUO Zhiqing,HUANG Min,et al. Research on fault prediction method of typical equipment in open-pit mine based on MCMC algorithm[J]. Coal Science and Technology,2019,47(10):51-57.
[33] 毛清华,毛金根,马宏伟,等. 矿用带式输送机智能监测系统研究[J]. 工矿自动化,2020,46(6):48-52,58. MAO Qinghua,MAO Jingen,MA Hongwei,et al. Research on intelligent monitoring system of mine-used belt conveyor[J]. Industry and Mine Automation,2020,46(6):48-52,58.
[34] 刘光伟,柴森霖,白润才,等. 露天矿山开拓运输系统道路选线算法[J]. 煤炭学报,2019,44(12):3931-3940. LIU Guangwei,CHAI Senlin,BAI Runcai,et al. Route selection algorithm of open-pit mine transportation system[J]. Journal of China Coal Society,2019,44(12):3931-3940.
[35] 刘光伟,李晋,柴森霖,等. 基于时空演化的露天矿运输线路存留状态判别算法[J]. 煤炭学报,2020,45(6):2147-2154. DOI: 10.13225/j.cnki.jccs.zn20.0236 LIU Guangwei,LI Jin,CHAI Senlin,et al. Spatio-temporal state discrimination and prediction of road transportation system in open-pit mine[J]. Journal of China Coal Society,2020,45(6):2147-2154. DOI: 10.13225/j.cnki.jccs.zn20.0236
[36] 赵明,王忠鑫,曾祥玉,等. 基于3DMine软件的露天矿境界优化研究[J]. 露天采矿技术,2021,36(3):30-33. DOI: 10.13235/j.cnki.ltcm.2021.03.008 ZHAO Ming,WANG Zhongxin,ZENG Xiangyu,et al. Study on boundary optimization of open-pit mine based on 3DMine software[J]. Opencast Mining Technology,2021,36(3):30-33. DOI: 10.13235/j.cnki.ltcm.2021.03.008
[37] 徐文轩,李伟. 无人驾驶汽车环境感知与定位技术[J]. 汽车科技,2021(6):53-60. XU Wenxuan,LI Wei. Environment perception and location technology of driverless vehicles[J]. Auto Sci-Tech,2021(6):53-60.
[38] 张伦. 矿用自卸卡车无人驾驶线控改装[J]. 工矿自动化,2021,47(增刊1):88-90. ZHANG Lun. Linear control refit of mine-used self-unloading truck for driverless[J]. Industry and Mine Automation,2021,47(S1):88-90.
[39] 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. 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.
[40] 孙效玉,田凤亮,张航,等. 兼顾固定配车需要的露天矿车流规划模型[J]. 煤炭学报,2016,41(增刊2):583-588. SUN Xiaoyu,TIAN Fengliang,ZHANG Hang,et al. Traffic flow model in open pit mine for needs of fixed assignment of truck[J]. Journal of China Coal Society,2016,41(S2):583-588.
[41] 孙效玉,赵松松,刘恒,等. 露天矿车流路网均衡分配模型[J]. 煤炭学报,2017,42(6):1607-1613. SUN Xiaoyu,ZHAO Songsong,LIU Heng,et al. Equilibrium distribution model of traffic flow on road network for traffic flow of open pit[J]. Journal of China Coal Society,2017,42(6):1607-1613.
[42] 武讲,郑群飞. 哈尔乌素露天矿无人驾驶方案研究[J]. 金属矿山,2021,50(2):167-172. WU Jiang,ZHENG Qunfei. Feasibility study of driverless system in Harwusu Open-pit Coal Mine[J]. Metal Mine,2021,50(2):167-172.
[43] 陈洪亮,李申岩,刘玲,等. 露天矿端帮自移式大倾角输送设备结构形式的研究[J]. 煤矿机械,2019,40(6):149-151. DOI: 10.13436/j.mkjx.201906048 CHEN Hongliang,LI Shenyan,LIU Ling,et al. Research on structural forms of self-moving high angle conveying equipment for open pit mine slope[J]. Coal Mine Machinery,2019,40(6):149-151. DOI: 10.13436/j.mkjx.201906048
[44] 周保卫. 多级串联带式输送机智能协调控制系统[J]. 煤矿机械,2020,41(12):180-182. ZHOU Baowei. Intelligent coordinated control system of multi-stage series belt conveyor[J]. Coal Mine Machinery,2020,41(12):180-182.
[45] 谢进,任文清. 煤矿钢丝绳芯输送带检测系统[J]. 工矿自动化,2021,47(增刊1):69-71. XIE Jin,REN Wenqing. Coal mine steel cord conveyor belt detection system[J]. Industry and Mine Automation,2021,47(S1):69-71.
[46] 刘澎,任文清. 煤矿无人值守带式输送机智能化系统设计[J]. 工矿自动化,2021,47(增刊2):75-77,96. LIU Peng,REN Wenqing. Design of intelligent system of unattended belt conveyor in coal mine[J]. Industry and Mine Automation,2021,47(S2):75-77,96.
[47] 林东玲. 基于多信息融合技术的矿用带式输送机故障诊断系统研究[J]. 煤矿机械,2020,41(6):169-171. DOI: 10.13436/j.mkjx.202006056 LIN Dongling. Research on fault diagnosis system of mine belt conveyor based on multi information fusion technology[J]. Coal Mine Machinery,2020,41(6):169-171. DOI: 10.13436/j.mkjx.202006056
[48] 蒋卫良,王兴茹,刘冰,等. 煤矿智能化连续运输系统关键技术研究[J]. 煤炭科学技术,2020,48(7):134-142. DOI: 10.13199/j.cnki.cst.2020.07.013 JIANG Weiliang,WANG Xingru,LIU Bing,et al. Study on key technology of coal mine intelligent continuous transportation[J]. Coal Science and Technology,2020,48(7):134-142. DOI: 10.13199/j.cnki.cst.2020.07.013