Review on the application of machine vision perception theory and technology in coal industry
-
摘要: 机器视觉技术对改善煤矿安全监测手段、提高装备自动化水平具有积极意义。详细阐述了当前煤矿智能化建设过程中基于机器视觉的不同场景和系统下的设备信息状态感知原理，综述了机器视觉感知技术在煤矿安全监测、拣选识别、煤岩识别、定位导航、运输检测、位姿检测和信息测量等方面的实践应用；分析指出未来煤矿机器视觉感知技术应深入挖掘采掘工作面机器视觉场景理解需求，构建生产全视场监视检测体系，提升多时空多维度多变量集成监测效果，改善视频自主监视告警能力，增强视觉引导能力，并形成地面生产管理运行系统的视觉资料统一化管理方式等，重点研究综采装备（群）姿态同时空测量、采掘环境动态变化感知、生产全视场监测与自主告警、煤矿机器人视觉引导控制等技术；指出煤矿机器视觉感知技术在防爆或本安型智能视觉传感器研发、高效视觉测量与分析、检测识别测量精度提升、图像高质量标注方面仍存在挑战，通过开发具有边缘计算能力的视觉传感器，构建井上下视觉分布式测量方案，实现各类复杂环境下开采信息准确识别与测量，可有效提高机器视觉感知技术在煤炭行业的更深层次融合和应用。Abstract: Machine vision technology has positively improved coal mine safety monitoring methods and enhanced equipment automation levels. This article elaborates in detail on the principles of equipment information state perception based on machine vision in different scenarios and systems during the current intelligent construction process of coal mines. It summarizes the practical applications of machine vision perception technology in coal mine safety monitoring, picking recognition, coal rock recognition, positioning navigation, transportation detection, pose detection, and information measurement. The analysis points out that in the future, coal mine machine vision perception technology should deeply explore the understanding needs of mining face machine vision scenes. It is suggested to build a production full field of view monitoring and detection system, and improve the integrated monitoring effect of multiple spatiotemporal, multi-dimensional, and multivariate. It is suggested to improve the video autonomous monitoring and alarm capability, enhance visual guidance capability, and form a unified visual data management method for ground production management and operation systems. The key research should focus on technologies such as simultaneous spatiotemporal measurement of the pose of fully mechanized mining equipment (groups), perception of dynamic changes in the mining environment, full field of view monitoring and autonomous warning for production, and visual guidance and control of coal mining robots. It is pointed out that the coal mine machine vision perception technology still has challenges in explosion-proof or intrinsically safe intelligent vision sensors, efficient methods of visual measurement and analysis, the measurement precision of detection and recognition, and high-quality image annotation. Through the development of visual sensors with edge computing capabilities, a distributed vision measurement scheme is constructed to achieve accurate recognition and measurement of mining information in various complex environments. It can effectively improve the deeper integration and application of machine vision perception technology in the coal industry.
-
0. 引言
综采工作面推进时，液压支架（以下称支架）的高度决定采煤机在运行过程中能否安全通过，为避免采煤机与支架干涉，需及时测量支架高度，为采煤机割煤提供高度调控参考，也为支架按照高度进行自动移架降柱过程提供依据[1-7]。
现有支架高度测量方法包括标尺人工记录法、激光或超声波测距法、多倾角传感器测量加融合算法、计算机视觉方法等。标尺人工记录法无法实现自动化操作。激光测距法虽然精度高，但激光受粉尘影响不易维护，稳定性差。超声波测距法测量结果易受散射角度影响[8]。多倾角传感器测量加融合算法应用较为广泛[9-16]，但需安装4个倾角传感器，配套设备较多，测量系统复杂，且倾角传感器易受井下设备振动、噪声等因素影响，稳定性、可靠性不足。近年来，计算机视觉方法在支架高度测量中被研究应用，文献[17-20]采用单目视觉或深度视觉技术进行包括支架高度在内的姿态检测，但视觉测量技术受限于井下粉尘、光照对图像质量的影响，并且其后端处理复杂，目前技术成熟度不足。鉴此，本文设计了一种基于帕斯卡定律的支架高度测量传感器（以下称测高传感器），利用密闭液管的两端压力差测量支架高度差，并通过结构设计和软件算法补偿环境温度变化带来的影响，从而实现支架高度的准确测量。
1. 测高传感器设计
1.1 测高传感器原理
测高传感器应用流体静力学中的帕斯卡定律，即在密闭的不可压缩流体内部，任意一点受到的压力变化会通过流体均匀地传递到流体的各个部分，如图1所示。
测高传感器主体采用密封的结构方案，在密闭的液管内注入甲基硅油，两端采用压力传感器分别测量压力。当压力传感器两端位于不同的高度位置时，由于重力作用，密闭液管内的液体会对处于更低位置的压力传感器产生力的作用，使两端的压力传感器测得的压力存在差值。测高传感器两端的压力差与高度方向上的距离成正比，则支架高度为
$$ H = {{\left( {{P_2} - {P_1}} \right)} /( {\rho g}}) $$ (1) 式中：$ {P_2} $为下端压力；$ {P_1} $为上端压力；ρ为甲基硅油密度；$ g $为重力加速度。
1.2 硬件设计
测高传感器的硬件主要包括压力传感器、电源、微控制单元（Microcontroller Unit，MCU）、通信接口电路、看门狗，其结构如图2所示。
目前综采工作面的液压支架最高为10 m，若测高传感器液管中充满的介质为水，10 m水柱换算为压力约为100 kPa。压力传感器在正常包装运输过程中，环境温度升高，即使在机械部件波纹管补偿下仍会出现内部压力增加。为保证压力传感器正常工作，需留出足够的安全余量，因此压力传感器的最大量程需在200 kPa以上。量程增加会导致精度下降，综合考虑内部实际压力、精度及通信接口、供电电压等因素，最终选择250 kPa量程的压力传感器（精度为±0.25%），其内部集成温度传感器。
所选压力传感器接口为I2C，压力传感器分布在测高传感器两端，导致LPC11E68距其中一端压力传感器的距离可能超过10 m。为增强I2C的驱动能力，使其适应于远距离通信，在Master端采用MOS管先将信号高电平3.3 V拉至12 V，再进行远距离信号传输，当需要接入Slave端时，再采用MOS管将电平转换到3.3 V，如图3所示。
1.3 测高传感器结构设计
测高传感器壳体采用304不锈钢材料，液管从测高传感器上端贯穿到下端，波纹管连接在液管下端，测高传感器两端的中间部分采用钢丝编织护套进行防护，如图4所示。
测高传感器内部结构设计要点主要包括以下2个方面。
1） 液体介质及充液结构选型。甲基硅油具有良好的化学稳定性、绝缘性、耐热性、疏水性，此外还具有较低的粘温系数，使其在宽温范围内粘度变化很小，综合以上优良特性，选择甲基硅油为测高传感器的液体介质。将气密芯阀安装在测高传感器的充液端作为充液开关机构，气密芯阀特有的单向阀门结构方便充液，且可确保内部液体不外泄。
2） 压力传感器安装及密封结构。测高传感器内部两端分别布置了2个安装压力传感器的金属结构体，压力传感器分别安装在两端的金属结构体上，两端的金属结构体之间采用铁氟龙材质的液管相连接，安装在金属结构体上的压力传感器敏感元件通过金属结构体内部的孔与铁氟龙液管内部的液体介质接触。根据压力传感器的外形尺寸及结构特点，选用适配的O形密封圈安装在压力传感器与金属结构体之间，确保内部液体的密封性，同时在压力传感器和金属结构体的安装面采用胶粘工艺，防止压力传感器脱落；气密芯阀安装在金属体的延长端，提高充液操作的便利性，安装结构如图5所示。
![]()
图 5 压力传感器及气密芯阀安装结构Figure 5. Installation diagram of pressure sensor and airtight core valve1.4 温度补偿方法
甲基硅油在环境温度变化时具有明显的热胀冷缩特性，由此引起密闭空间内的压力急剧变化，可能超出压力传感器的量程且影响测量精度。因此，本文重点研究了测高传感器在环境温度变化时的补偿方法：采用波纹管存储一部分甲基硅油，利用波纹管自身的弹性补偿甲基硅油热胀冷缩造成的体积变化；并在软件中通过算法校准甲基硅油体积变化带来的密度变化，从而确保测高传感器的测量精度。
1.4.1 波纹管选型设计
波纹管主要是用来补偿测高传感器中液体（甲基硅油）热胀冷缩造成的体积变化。温度降低，甲基硅油体积收缩时，波纹管在空气压力作用下收缩，保证压力传感器内部密封的空间不会出现真空；温度升高，甲基硅油体积膨胀时，波纹管在液体作用下伸展，且内压不超过压力传感器设置的最大量程，以保证压力传感器正常工作。
波纹管选型时涉及的关键指标有波纹管的刚度、波纹管的直径（内外径）、压力传感器的量程及甲基硅油的膨胀系数等。
在测高传感器中，液管选用内径为2 mm的铁氟龙管，10 m量程的测高传感器按照最长12 m计算，则液管内可贮存的甲基硅油体积为
$$ V = {\text{π}}( d/2)^2 L $$ (2) 式中：$ d $为液管内部直径；$ L $为液管长度。
将上述参数代入式（2），得到甲基硅油体积为37.68 mL。
假设温度升高，则波纹管要对温度升高导致的甲基硅油体积变化进行补偿。为满足补偿的需要，需对波纹管进行选型设计。首先根据结构设计的需求确定波纹管的部分机械参数，确定外径为18 mm，内径不小于12 mm，壁厚要求尽量薄（按照较高的加工能力要求可做到0.08 mm）。设波纹管长度为$ l $，则其内部容积为
$$ {V_1} = {\text{π}} {[({d_1} + {d_2})/4]^2}l $$ (3) 式中：$ {d_1} $为波纹管内径；$ {d_2} $为波纹管外径。
将上述参数代入式（3），可得波纹管内部容积为1.766l mL。
甲基硅油的热膨胀系数$ i $为0.001 04 cm3/cm3/℃，测高传感器的正常工作温度范围为0～40 ℃，装配生产车间内的环境温度为20 ℃，假设液管内与波纹管内的硅油体积变化为$ \Delta V $。
$$ \Delta V=(V+V_1)i\Delta t\ $$ (4) 式中$ \Delta t $为环境温度变化值。
波纹管需要通过形变补偿硅油的体积变化，波纹管的形变可以近似等于截面积乘以形变量，将参数值代入式（3）和式（4），可得到以下公式。
$$ 1.766\Delta l=0.784+0.036\ 732\ 8l $$ (5) 式中$ \Delta l $为波纹管形变量。
通过式（5）可知波纹管长度$ l $越大，则波纹管形变量$ \Delta l $越大，假设$ l $=5 cm，则$ \Delta l $=0.548 cm。
波纹管的机械加工参数壁厚、内径、外径等决定了其刚度，按照设计指标制作的波纹管刚度$ f $为1.4 N/mm，则波纹管形变量为0.548 cm时，由于波纹管形变所产生的弹性力为
$$ F=f\Delta l=\text{7}\text{.672 } $$ (6) 弹性力$ F $作用在甲基硅油上，根据帕斯卡定律，在密闭的不可压缩流体内部，任意一点受到的压力变化会通过流体均匀地传递到流体的各个部分。因此，在液管内的甲基硅油内压会明显增加，增加的压强为
$$\Delta P =F/ S $$ (7) 式中$ S $为波纹管截面积， $ S = {\text{π}} \left[{\left({{{d_2}}}/{2}\right)^2} - {\left({{{d_1}}}/{2}\right)^2}\right] $ 。
在波纹管截面积与弹性力已知的情况下，可根据式（7）计算出增加的压强$ \Delta P $为43.95 kPa。压力传感器的最大量程为250 kPa，满足应用要求。
综合计算结果和结构设计要求，选用U形电化学波纹管，材质为抗腐蚀性较强的316 L不锈钢；波纹管外径为18 mm、内径为12 mm、壁厚为0.08 mm；波纹管的波距为1.5mm，有效长度为50 mm。
1.4.2 甲基硅油密度校准
由甲基硅油的热膨胀分析和质量守恒定律可知，甲基硅油的密度必然随着甲基硅油的体积膨胀或收缩产生变化，从式（1）可知，密度变化将会导致支架高度计算结果产生误差。为消除密度变化带来的误差，需在软件中进行补偿。为得到甲基硅油的密度与温度变化的规律，使用高精度密度计测试了本文所使用的甲基硅油在不同温度时的密度，测试结果见表1。
表 1 甲基硅油密度与温度关系对应Table 1. Correspondence between density and temperature of methyl silicone oil理想测试温度/℃ 密度/（g·cm−3） 实测温度/℃ 密度平均值/（g·cm−3） 10 0.953 09 10.04 0.953 10 0.953 11 10.01 15 0.948 50 14.99 0.948 50 0.948 49 15.01 18 0.945 73 17.99 0.945 72 0.945 71 18.01 21 0.942 96 21.01 0.942 96 0.942 96 21.01 24 0.940 22 23.99 0.940 21 0.940 19 24.01 27 0.937 45 26.99 0.937 45 0.937 44 27.01 30 0.934 70 30.01 0.934 70 0.934 70 29.99 35 0.930 10 34.99 0.930 11 0.930 12 34.99 40 0.925 55 39.99 0.925 56 0.925 56 39.99 根据密度测试结果，采用最小二乘法拟合出密度随温度变化的经验公式：
$$ \rho = - 0.000\;916t + 0.962\;221 $$ (8) 式中$ t $为环境温度。
1.5 软件设计
计算支架高度时，预先通过压力传感器集成的温度传感器测得甲基硅油温度，并通过式（8）计算甲基硅油的实际密度，再将得到的密度代入式（1）中，实现高度测量功能。测高传感器软件流程如图6所示。
2. 试验验证
2.1 高低温试验
将测高传感器放置在可变温度（0～40 ℃）环境下，固定测高传感器位置，测量从高温到低温、从低温到高温1个工作循环。从压力传感器集成的温度传感器读取测高传感器的工作温度，同时读取两端压力传感器的压力。试验数据见表2和表3。
表 2 高温到低温变化过程中的传感器数据Table 2. Sensor data during high temperature to low temperature changes温度/℃ 高度/cm 下端压力/kPa 上端压力/kPa 40.08 154.16 140.24 126.26 35.00 153.04 130.32 116.36 30.02 152.81 123.43 109.41 25.04 153.61 115.09 100.95 20.05 153.21 108.73 94.56 15.03 152.93 103.68 89.46 9.98 153.85 99.74 85.37 5.01 152.67 95.84 81.51 0.04 153.20 92.48 78.03 表 3 低温到高温变化过程中的传感器数据Table 3. Sensor data during low temperature to high temperature changes温度/℃ 高度/cm 下端压力/kPa 上端压力/kPa 0.02 153.51 91.87 77.40 5.03 153.17 95.64 81.23 10.05 152.80 100.28 86.01 14.97 153.85 105.84 91.54 20.01 152.94 111.38 97.23 25.03 153.14 118.28 104.18 29.96 153.59 124.93 110.87 34.98 154.11 133.28 119.24 40.02 153.88 143.39 128.44 从表2可看出，环境温度从高到低变化时，上下两端压力传感器检测到压力降低，但压力差值基本稳定，换算成支架高度后，得到标准差为0.55 cm。
从表3可看出，环境温度从低到高变化时，上下两端压力传感器检测到压力升高，但压力差值基本稳定，换算成支架高度后，得到标准差为0.55 cm。
2.2 检测精度试验
在常温环境下，测高传感器两端高度差在0～1 000 cm范围内变化，对其检测精度进行试验，试验结果见表4。
表 4 常温下检测精度试验结果Table 4. Test results of detection precision at normal temperature实际高度/cm 检测高度/cm 环境温度/℃ 0 0.773 220 24.484 61 100 98.620 932 24.484 61 200 201.481 950 24.093 79 300 302.477 290 24.289 20 400 399.922 510 24.289 20 500 500.598 310 24.386 90 600 598.760 030 24.386 90 700 701.423 10 24.386 90 800 800.505 50 24.483 90 900 898.608 90 24.483 90 1 000 999.288 90 24.483 90 从表4可看出，在高度变化时，测高传感器检测值与实际值基本一致，高度测量值的标准差为1.26 cm，按照三西格玛原则，测量误差为−3.84～3.84 cm，即误差不超过4 cm。
3. 现场应用
目前，测高传感器已在全国多处煤矿进行应用[21]。本文选取国家能源集团神东煤炭乌兰木伦煤矿的中厚煤层工作面与中国神华能源股份有限公司神东煤炭分公司榆家梁煤矿的薄煤层工作面2种典型场景，进行测高传感器井下应用验证。测高传感器的上端固定在支架顶梁，护套管体沿顶梁、连杆的线缆槽走线布置，测高传感器的下端直接连接在支架控制器的对应接口。测高传感器安装后不需要进行标定，在使用过程中也不需要进行校准或清洁维护。
实际应用时需在测量数据的基础上，加上上端安装位置距离支架顶的高度、下端安装位置距离支架底的高度，最终支架高度测量值在支架控制器上显示。
在应用期间，分别将测高传感器检测值与人工测量值做对比，对初次安装和使用一段时间后的数据进行记录，结果见表5和表6。可看出测高传感器能够在井下稳定应用，支架高度检测结果与人工测量结果相比较，误差在5 cm以内，考虑到人工测量引入的偶然误差，该测量结果基本与试验结果一致。
表 5 中厚煤层支架测高传感器数据对比Table 5. Data comparison of support height sensor for medium-thick coal seamcm 支架号 初次安装 3个月后 检测值 人工测量值 检测值 人工测量值 20 376 373 369 372 29 348 343 365 367 39 366 363 359 357 49 363 360 364 368 60 348 348 363 361 表 6 较薄煤层支架测高传感器数据对比Table 6. Data comparison of support height sensor for thin coal seamcm 支架号 初次安装 3个月后 检测值 人工测量值 检测值 人工测量值 15 149 151 151 149 20 158 156 154 155 25 147 147 159 161 30 142 142 155 159 35 132 128 161 159 4. 结论
1） 基于帕斯卡定律的测高传感器通过波纹管和软件补偿相结合的方式有效补偿了环境温度变化带来的影响，测高传感器可稳定应用在0～40 ℃环境下，测量误差小于4 cm。
2） 开展了为期3个月的现场应用，使用该测高传感器测量的液压支架高度与人工测量结果相比，误差在5 cm以内，证明其具有较高的可靠性。
3） 后续需进一步提升测高传感器的测量精度，一方面需提升压力传感器的精度和一致性，另一方面需完善测高传感器的标定算法，在测高传感器生产时加入标定环节。
-
![]()
图 4 机器视觉感知技术在煤炭工业领域应用场景
Figure 4. Application scenes of machine vision perception technology in coal industry field
![]()
![]()
图 6 基于机器视觉的煤岩分界识别效果
Figure 6. Recognition effect of coal-rock boundary based on machine vision
![]()
图 7 基于机器视觉的带式输送机故障识别
Figure 7. Belt conveyor fault recognition based on machine vision
-
[1] 王国法,刘峰,孟祥军,等. 煤矿智能化(初级阶段)研究与实践[J]. 煤炭科学技术,2019,47(8):1-36. WANG Guofa,LIU Feng,MENG Xiangjun,et al. Research and practice on intelligent coal mine construction(primary stage)[J]. Coal Science and Technology,2019,47(8):1-36.
[2] 王国法,任怀伟,庞义辉,等. 煤矿智能化(初级阶段)技术体系研究与工程进展[J]. 煤炭科学技术,2020,48(7):1-27. WANG Guofa,REN Huaiwei,PANG Yihui,et al. Research and engineering progress of intelligent coal mine technical system in early stages[J]. Coal Science and Technology,2020,48(7):1-27.
[3] 王国法,任怀伟,赵国瑞,等. 智能化煤矿数据模型及复杂巨系统耦合技术体系[J]. 煤炭学报,2022,47(1):61-74. WANG Guofa,REN Huaiwei,ZHAO Guorui,et al. Digital model and giant system coupling technology system of smart coal mine[J]. Journal of China Coal Society,2022,47(1):61-74.
[4] HASHMI A W,MALI H S,MEENA A,et al. Machine vision for the measurement of machining parameters:a review[J]. Materials Proceedings,2022,56(4):1939-1946.
[5] WANG Tianhai,CHEN Bin,ZHANG Zhenqian,et al. Applications of machine vision in agricultural robot navigation:a review[J]. Computers and Electronics in Agriculture,2022,198:107085. DOI: 10.1016/j.compag.2022.107085
[6] BAROUD S,CHOKRI S,BELHAOUS S,et al. A brief review of graph convolutional neural network based learning for classifying remote sensing images[J]. Procedia Computer Science,2021,191(1):349-354.
[7] TULBURE A-A,TULBURE A-A,DULF E-H. A review on modern defect detection models using DCNNs-Deep convolutional neural networks[J]. Journal of Advanced Research,2022,35:33-48. DOI: 10.1016/j.jare.2021.03.015
[8] SABZI S,ABBASPOUR-GILANDEH Y,JAVADIKIA H. Machine vision system for the automatic segmentation of plants under different lighting conditions[J]. Biosystems Engineering,2017,161:157-173. DOI: 10.1016/j.biosystemseng.2017.06.021
[9] ELHASSAN M,KONSTANTINOS S,GARETH H. A review of visualisation-as-explanation techniques for convolutional neural networks and their evaluation[J]. Displays,2022,73:102239. DOI: 10.1016/j.displa.2022.102239
[10] VALIZADEH M,WOLFF S J. Convolutional neural network applications in additive manufacturing:a review[J]. Advances in Industrial and Manufacturing Engineering,2022,4:100072. DOI: 10.1016/j.aime.2022.100072
[11] JIAO Jinyang,ZHAO Ming,LIN Jing,et al. A comprehensive review on convolutional neural network in machine fault diagnosis[J]. Neurocomputing,2020,417:36-63. DOI: 10.1016/j.neucom.2020.07.088
[12] 王伯君. 袁大滩煤矿视频监控的组成与功能实现[J]. 信息通信,2020(8):115-117. WANG Bojun. Composition and function realization of video surveillance in Yuandatan Coal Mine[J]. Information & Communications,2020(8):115-117.
[13] 王宇,吴智恒,刘泓滨,等. 机器视觉的煤自燃智能预警系统设计[J]. 煤矿机械,2016,37(8):16-17. WANG Yu,WU Zhiheng,LIU Hongbin,et al. Design of coal spontaneous combustion intelligent warning and monitoring system based on machine vision[J]. Coal Mine Machinery,2016,37(8):16-17.
[14] 曹玉超,范伟强. 基于不同深度识别算法的矿井水位标尺刻度识别性能分析与研究[J]. 煤炭学报,2019,44(11):3529-3538. CAO Yuchao,FAN Weiqiang. Performance analysis and research of mine water level scale recognition based on different depth recognition algorithms[J]. Journal of China Coal Society,2019,44(11):3529-3538.
[15] CHEN Wei,SUN Tongfeng,LI Ming,et al. A new image co-segmentation method using saliency detection for surveillance image of coal miners[J]. Computers & Electrical Engineering,2014,40(8):227-235.
[16] 刘春梅,李辉. 煤矿开采用掘进机人员识别系统设计与研究[J]. 内蒙古农业大学学报(自然科学版),2020,41(4):76-79. LIU Chunmei,LI Hui. Design of the roadheaders used in the personnel identification system[J]. Journal of Inner Mongolia Agricultural University (Natural Science Edition),2020,41(4):76-79.
[17] 王成军,严晨. 机器视觉技术在分拣系统中的应用研究综述[J]. 制造技术与机床,2020(5):32-37. WANG Chengjun,YAN Chen. Summary of application research of machine vision technology in sorting system[J]. Manufacturing Technology & Machine Tool,2020(5):32-37.
[18] IGATHINATHANE C,ULUSOY U. Machine vision methods based particle size distribution of ball- and gyro-milled lignite and hard coal[J]. Powder Technology,2016,297:71-80. DOI: 10.1016/j.powtec.2016.03.032
[19] DOU Dongyang,WU Wenze,YANG Jianguo,et al. Classification of coal and gangue under multiple surface conditions via machine vision and relief-SVM[J]. Powder Technology,2019,356:1024-1028. DOI: 10.1016/j.powtec.2019.09.007
[20] 饶中钰,吴景涛,李明. 煤矸石图像分类方法[J]. 工矿自动化,2020,46(3):69-73. RAO Zhongyu,WU Jingtao,LI Ming. Coal-gangue image classification method[J]. Industry and Mine Automation,2020,46(3):69-73.
[21] SUN Jiping,CHEN Wei,MA Fengying,et al. Classification of infrared monitor images of coal using a feature texture statistics and improved BP network[J]. Journal of China University of Mining & Technology,2007,17(4):489-493.
[22] LYU Ziqi,WANG Weidong,XU Zhiqiang,et al. Cascade network for detection of coal and gangue in the production context[J]. Powder Technology,2021,377:361-371. DOI: 10.1016/j.powtec.2020.08.088
[23] ZHANG Kanghui,WANG Weidong,LYU Ziqi,et al. Computer vision detection of foreign objects in coal processing using attention CNN[J]. Engineering Applications of Artificial Intelligence,2021,102:104242. DOI: 10.1016/j.engappai.2021.104242
[24] WANG Xinquan,WANG Shuang,GUO Yongcun,et al. Dielectric and geometric feature extraction and recognition method of coal and gangue based on VMD-SVM[J]. Powder Technology,2021,392:241-250. DOI: 10.1016/j.powtec.2021.06.057
[25] 郭永存,王希,何磊,等. 基于TW−RN优化CNN的煤矸识别方法研究[J]. 煤炭科学技术,2022,50(1):228-236. DOI: 10.3969/j.issn.0253-2336.2022.1.mtkxjs202201023 GUO Yongcun,WANG Xi,HE Lei,et al. Research on coal and gangue recognition method based on TW-RN optimized CNN[J]. Coal Science and Technology,2022,50(1):228-236. DOI: 10.3969/j.issn.0253-2336.2022.1.mtkxjs202201023
[26] JEMWA G T,ALDRICH C. Estimating size fraction categories of coal particles on conveyor belts using image texture modeling methods[J]. Expert Systems with Applications,2012,39:7947-7960. DOI: 10.1016/j.eswa.2012.01.104
[27] 王鹏,曹现刚,夏晶,等. 基于机器视觉的多机械臂煤矸石分拣机器人系统研究[J]. 工矿自动化,2019,45(9):47-53. WANG Peng,CAO Xiangang,XIA Jing,et al. Research on multi-manipulator coal and gangue sorting robot system based on machine vision[J]. Industry and Mine Automation,2019,45(9):47-53.
[28] 孙磊. 煤矿自动选矸机器人系统设计与应用[J]. 自动化应用,2021(5):39-43. SUN Lei. Design and application of coal mine automatic waste selection robot system[J]. Automation Application,2021(5):39-43.
[29] 马宏伟,孙那新,张烨,等. 煤矸石分拣机器人动态目标稳定抓取轨迹规划[J]. 工矿自动化,2022,48(4):20-30. MA Hongwei,SUN Naxin,ZHANG Ye,et al. Track planning of coal gangue sorting robot for dynamic target stable grasping[J]. Journal of Mine Automation,2022,48(4):20-30.
[30] 司垒,王忠宾,熊祥祥,等. 基于改进U−net网络模型的综采工作面煤岩识别方法[J]. 煤炭学报,2021,46(增刊1):578-589. SI Lei,WANG Zhongbin,XIONG Xiangxiang,et al. Coal-rock recognition method of fully-mechanized coal mining face based on improved U-net network model[J]. Journal of China Coal Society,2021,46(S1):578-589.
[31] 刘俊利,赵豪杰,李长有. 基于采煤机滚筒截割振动特性的煤岩识别方法[J]. 煤炭科学技术,2013,41(10):93-95,116. LIU Junli,ZHAO Haojie,LI Changyou. Coal-rock recognition method based on cutting vibration features of coal shearer drums[J]. Coal Science and Technology,2013,41(10):93-95,116.
[32] 王元军,王明松,田山军,等. 基于卡尔曼滤波与随机森林的煤岩识别研究[J]. 煤炭技术,2021,40(12):208-211. WANG Yuanjun,WANG Mingsong,TIAN Shanjun,et al. Study on recognition of coal and rock based on Kalman filter and random forest[J]. Coal Technology,2021,40(12):208-211.
[33] 张强,张润鑫,刘峻铭,等. 煤矿智能化开采煤岩识别技术综述[J]. 煤炭科学技术,2022,50(2):1-26. ZHANG Qiang,ZHANG Runxin,LIU Junming,et al. Review on coal and rock identification technology for intelligent mining in coal mines[J]. Coal Science and Technology,2022,50(2):1-26.
[34] 孙继平,佘杰. 基于小波的煤岩图像特征抽取与识别[J]. 煤炭学报,2013,38(10):1900-1904. SUN Jiping,SHE Jie. Wavelet-based coal-rock image feature extraction and recognition[J]. Journal of China Coal Society,2013,38(10):1900-1904.
[35] 孙继平,陈浜. 基于双树复小波域统计建模的煤岩识别方法[J]. 煤炭学报,2016,41(7):1847-1858. SUN Jiping,CHEN Bang. An approach to coal-rock recognition via statistical modeling in dual-tree complex wavelet domain[J]. Journal of China Coal Society,2016,41(7):1847-1858.
[36] 孙继平,陈浜. 基于小波域非对称广义高斯模型的煤岩识别算法[J]. 煤炭学报,2015,40(增刊2):568-575. SUN Jiping,CHEN Bang. A coal-rock recognition algorithm using wavelet-domain asymmetric generalized Gaussian models[J]. Journal of China Coal Society,2015,40(S2):568-575.
[37] 孙继平,佘杰. 基于支持向量机的煤岩图像特征抽取与分类识别[J]. 煤炭学报,2013,38(增刊2):508-512. SUN Jiping,SHE Jie. Coal-rock imagefeature extraction and recognition based on support vector machine[J]. Journal of China Coal Society,2013,38(S2):508-512.
[38] 吕红杰. 卷积神经网络在煤岩图像识别中的应用研究[J]. 科技创新导报,2019,16(9):137-139. LYU Hongjie. Application of convolutional neural networks in coal and rock image recognition[J]. Science and Technology Innovation Herald,2019,16(9):137-139.
[39] 伍云霞,田一民. 基于字典学习的煤岩图像特征提取与识别方法[J]. 煤炭学报,2016,41(12):3190-3196. WU Yunxia,TIAN Yimin. Method of coal-rock image feature extraction and recognition based on dictionary learning[J]. Journal of China Coal Society,2016,41(12):3190-3196.
[40] 黄韶杰,刘建功. 基于高斯混合聚类的煤岩识别技术研究[J]. 煤炭学报,2015,40(增刊2):576-582. HUANG Shaojie,LIU Jiangong. Research of coal-rock recognition technology based on GMM clustering analysis[J]. Journal of China Coal Society,2015,40(S2):576-582.
[41] 王超,张强. 基于LBP和GLCM的煤岩图像特征提取与识别方法[J]. 煤矿安全,2020,51(4):129-132. WANG Chao,ZHANG Qiang. Coal rock image feature extraction and recognition method based on LBP and GLCM[J]. Safety in Coal Mines,2020,51(4):129-132.
[42] 王燕平. 基于改进YOLOv3的煤岩界线识别及采高仿人智能控制研究[D]. 太原: 中北大学, 2021. WANG Yanping. Coal-rock boundary identification based on improved YOLOv3 and research on human-simulating intelligent control of mining height[D]. Taiyuan: Central North University, 2021.
[43] 黄韶杰. 基于聚类的煤岩分界图像识别技术研究[D]. 北京: 中国矿业大学（北京）, 2016. HUANG Shaojie. Research on coal rock boundary image recognition technology based on clustering[D]. Beijing: China University of Mining and Technology-Beijing, 2016.
[44] 张羽飞,马宏伟,毛清华,等. 视觉与惯导融合的煤矿移动机器人定位方法[J]. 工矿自动化,2021,47(3):46-52. ZHANG Yufei,MA Hongwei,MAO Qinghua,et al. Coal mine mobile robot positioning method based on fusion of vision and inertial navigation[J]. Industry and Mine Automation,2021,47(3):46-52.
[45] 薛旭升,张旭辉,毛清华,等. 基于双目视觉的掘进机器人定位定向方法研究[J]. 西安科技大学学报,2020,40(5):781-789. XUE Xusheng,ZHANG Xuhui,MAO Qinghua,et al. Localization and orientation method of roadheader robot based on binocular vision[J]. Journal of Xi'an University of Science and Technology,2020,40(5):781-789.
[46] 马宏伟,王岩,杨林. 煤矿井下移动机器人深度视觉自主导航研究[J]. 煤炭学报,2020,45(6):2193-2206. MA Hongwei,WANG Yan,YANG Lin. Research on depth vision based mobile robot autonomous navigation in underground coal mine[J]. Journal of China Coal Society,2020,45(6):2193-2206.
[47] 程健. 煤矿巷道机器人管线视觉辅助定位与导航方法研究[J]. 煤炭科学技术,2020,48(7):226-232. CHENG Jian. Study on pipeline vision-aided positioning and navigation method for coal mine tunnel robot[J]. Coal Science and Technology,2020,48(7):226-232.
[48] 张旭辉, 沈奇峰, 杨文娟, 等. 基于三激光点标靶的掘进机机身视觉定位技术研究[J/OL]. 电子测量与仪器学报: 1-9. [2022-08-27]. https://kns.cnki.net/kcms/detail/11. 2488.TN.20220612.1403.024.html. ZHANG Xuhui, SHEN Qifeng, YANG Wenjuan, et al. Research on visual positioning technology of roadheader body based on three laser point target[J/OL]. Journal of Electronic Measurement and Instrumentation: 1-9. [2022-08-27]. https://kns.cnki.net/kcms/detail/ 11.2488.TN. 20220612.1403.024.html.
[49] 张旭辉,赵建勋,杨文娟,等. 悬臂式掘进机视觉导航与定向掘进控制技术[J]. 煤炭学报,2021,46(7):2186-2196. ZHANG Xuhui,ZHAO Jianxun,YANG Wenjuan,et al. Vision-based navigation and directional heading control technologies of boom-type roadheader[J]. Journal of China Coal Society,2021,46(7):2186-2196.
[50] 韩江洪,卫星,陆阳,等. 煤矿井下机车无人驾驶系统关键技术[J]. 煤炭学报,2020,45(6):2104-2115. HAN Jianghong,WEI Xing,LU Yang,et al. Driverless technology of underground locomotive in coal mine[J]. Journal of China Coal Society,2020,45(6):2104-2115.
[51] 王星. 基于视觉的煤矿井下带式输送机异常状态监测方法研究[D]. 太原: 太原科技大学, 2017. WANG Xing. Research on abnormal state monitoring method of coal mine underground belt conveyor based on vision[D]. Taiyuan: Taiyuan University of Science and Technology, 2017.
[52] 王涛. 机器视觉技术在煤矿胶带运输系统中的应用[J]. 能源科技,2021,19(2):34-40. WANG Tao. Application of the machine vision technology in the belt conveyor system for coal mines[J]. Energy Science and Technology,2021,19(2):34-40.
[53] 顼熙亮. 基于机器视觉的矿用皮带运输机故障智能检测系统[J]. 煤矿现代化,2020(5):212-215. XU Xiliang. Intelligent fault detection system of mine belt conveyor based on machine vision[J]. Coal Mine Modernization,2020(5):212-215.
[54] 董征,张旭辉,王泰华,等. 基于机器视觉的矿用带式输送机跑偏故障检测系统[J]. 智能矿山,2022,3(2):60-65. DONG Zheng,ZHANG Xuhui,WANG Taihua,et al. Mine belt conveyor deviation detection system based on machine visio[J]. Journal of Intelligent Mine,2022,3(2):60-65.
[55] ZHANG Mengchao,JIANG Kai,CAO Yueshuai,et al. A deep learning-based method for deviation status detection in intelligent conveyor belt system[J]. Journal of Cleaner Production,2022,363:132575. DOI: 10.1016/j.jclepro.2022.132575
[56] 刘尹霞,李斯,王东,等. 煤炭传输带边缘磨损机器视觉无损在线检测[J]. 露天采矿技术,2015(5):39-41. LIU Yinxia,LI Si,WANG Dong,et al. Coal conveying belt edge wear machine vision non-destructive on-line detection[J]. Opencast Mining Technology,2015(5):39-41.
[57] 胡明明,乔铁柱,郑补祥. 基于NI机器视觉的胶带纵向撕裂检测系统[J]. 仪表技术与传感器,2013(11):41-43. HU Mingming,QIAO Tiezhu,ZHENG Buxiang. Inspection system of belt longitudinal tear based on NI machine vision[J]. Instrument Technique and Sensor,2013(11):41-43.
[58] 郝志伟. 基于机器视觉识别技术的煤矿带式输送自适应控制系统设计[J]. 煤炭工程,2019,51(9):37-41. HAO Zhiwei. Coal mine belt conveyor adaptive control system based on machine vision recognition technology[J]. Coal Engineering,2019,51(9):37-41.
[59] QIAO Tiezhu,CHEN Lulu,PANG Yusong,et al. Integrative binocular vision detection method based on infrared and visible light fusion for conveyor belts longitudinal tear[J]. Measurement,2017,110:192-201. DOI: 10.1016/j.measurement.2017.06.032
[60] YANG Yanli,MIAO Changyun,LI Xianguo,et al. On-line conveyor belts inspection based on machine vision[J]. Optik,2014,125(19):5803-5807. DOI: 10.1016/j.ijleo.2014.07.070
[61] LI Xianguo,SHEN Lifang,MING Zixu,et al. Laser-based on-line machine vision detection for longitudinal rip of conveyor belt[J]. Optik,2018,168:360-369. DOI: 10.1016/j.ijleo.2018.04.053
[62] CHE Jian,QIAO Tiezhu,YANG Yi,et al. Longitudinal tear detection method of conveyor belt based on audio-visual fusion[J]. Measurement,2021,176:109152. DOI: 10.1016/j.measurement.2021.109152
[63] 张和平. 基于机器视觉的矿用带式输送机堆煤故障监控系统研究[J]. 煤炭科技,2020,41(1):89-92. DOI: 10.3969/j.issn.1008-3731.2020.01.029 ZHANG Heping. Research on fault monitoring system of mine belt conveyor based on machine vision[J]. Coal Science & Technology Magazine,2020,41(1):89-92. DOI: 10.3969/j.issn.1008-3731.2020.01.029
[64] BAO Nengsheng,KUANG Huiling,SIMEONE A,et al. A machine vision-based automatic inspection system for power station coal bunkers maintenance[J]. Procedia CIRP,2021,103:250-255. DOI: 10.1016/j.procir.2021.10.040
[65] 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.
[66] 马宏伟,杨文娟,张旭辉. 带式输送机托辊红外图像分割与定位算法[J]. 西安科技大学学报,2017,37(6):892-898. MA Hongwei,YANG Wenjuan,ZHANG Xuhui. Segmentation and location algorithm for infrared image of roller on conveyor belt[J]. Journal of Xi'an University of Science and Technology,2017,37(6):892-898.
[67] 李帅帅,任怀伟. 综采工作面“三机”设备位姿测量技术研究现状与展望[J]. 煤炭科学技术,2020,48(9):218-226. LI Shuaishuai,REN Huaiwei. Research status and development trend of position and posture measurement technology on hydraulic support,scraper conveyor,shearer in fully-mechanized mining face[J]. Coal Science and Technology,2020,48(9):218-226.
[68] 许金星. 机器视觉的液压支架姿态角度测量系统设计[J]. 煤矿机械,2019,40(9):11-13. XU Jinxing. Design of attitude angle measurement system for hydraulic support based on machine vision[J]. Coal Mine Machinery,2019,40(9):11-13.
[69] 张旭辉,王冬曼,杨文娟. 基于视觉测量的液压支架位姿检测方法[J]. 工矿自动化,2019,45(3):56-60. ZHANG Xuhui,WANG Dongman,YANG Wenjuan. Position detection method of hydraulic support based on vision measurement[J]. Industry and Mine Automation,2019,45(3):56-60.
[70] 任怀伟,李帅帅,赵国瑞,等. 基于深度视觉原理的工作面液压支架支撑高度与顶梁姿态角测量方法研究[J]. 采矿与安全工程学报,2022,39(1):72-81,93. REN Huaiwei,LI Shuaishuai,ZHAO Guorui,et al. Measurement method of support height and roof beam posture angles for working face hydraulic support based on depth vision[J]. Journal of Mining & Safety Engineering,2022,39(1):72-81,93.
[71] 王渊,李红卫,郭卫,等. 基于图像识别的液压支架护帮板收回状态监测方法[J]. 工矿自动化,2019,45(2):47-53. WANG Yuan,LI Hongwei,GUO Wei,et al. Monitoring method of recovery state of hydraulic support guard plate based on image recognition[J]. Industry and Mine Automation,2019,45(2):47-53.
[72] 刘鹏坤,王聪. 基于机器视觉的长壁工作面直线度测量算法研究[J]. 矿业科学学报,2017,2(3):267-273. LIU Pengkun,WANG Cong. Straightness measurement algorithm based on machine vision for coal longwall face[J]. Journal of Mining Science and Technology,2017,2(3):267-273.
[73] 康红普,姜鹏飞,高富强,等. 掘进工作面围岩稳定性分析及快速成巷技术途径[J]. 煤炭学报,2021,46(7):2023-2045. KANG Hongpu,JIANG Pengfei,GAO Fuqiang,et al. Analysis on stability of rock surrounding heading faces and technical approaches for rapid heading[J]. Journal of China Coal Society,2021,46(7):2023-2045.
[74] 雷孟宇,张旭辉,杨文娟,等. 煤矿掘进装备视觉位姿检测与控制研究现状与趋势[J]. 煤炭学报,2021,46(增刊2):1135-1148. LEI Mengyu,ZHANG Xuhui,YANG Wenjuan,et al. Current status and trend of research on visual pose detection and control of heading equipment in coal mines[J]. Journal of China Coal Society,2021,46(S2):1135-1148.
[75] 杨文娟,马宏伟,张旭辉. 悬臂式掘进机截割头姿态视觉检测系统[J]. 煤炭学报,2018,43(增刊2):581-590. YANG Wenjuan,MA Hongwei,ZHANG Xuhui. Attitude measurement system of cutting head for boom-type roadheader based on vision measurement[J]. Journal of China Coal Society,2018,43(S2):581-590.
[76] 张旭辉,刘永伟,杨文娟,等. 矿用悬臂式掘进机截割头姿态视觉测量系统[J]. 工矿自动化,2018,44(8):63-67. ZHANG Xuhui,LIU Yongwei,YANG Wenjuan,et al. Vision measurement system for cutting head attitude of mine-used boom-type roadheader[J]. Industry and Mine Automation,2018,44(8):63-67.
[77] 张旭辉,张超,杨文娟,等. 悬臂式掘进机可视化辅助截割系统研制[J]. 煤炭科学技术,2018,46(12):21-26. ZHANG Xuhui,ZHANG Chao,YANG Wenjuan,et al. Research and development of visual auxiliary cutting system for cantilever roadheader[J]. Coal Science and Technology,2018,46(12):21-26.
[78] 张旭辉,谢楠,张超,等. 悬臂式掘进机截割头位姿视觉测量系统改进[J]. 工矿自动化,2021,47(7):1-7. ZHANG Xuhui,XIE Nan,ZHANG Chao,et al. Improvement of vision measurement system for cutting head position of boom-type roadheader[J]. Industry and Mine Automation,2021,47(7):1-7.
[79] 张旭辉,张楷鑫,张超,等. 悬臂式掘进机视觉位姿检测系统外参标定方法[J]. 机械科学与技术,2022,41(12):1928-1935. ZHANG Xuhui,ZHANG Kaixin,ZHANG Chao,et al. Calibrating external parameters of visual position detection system of cantilever roadheader[J]. Mechanical Science and Technology for Aerospace Engineering,2022,41(12):1928-1935.
[80] 赵建勋,杨文娟,张旭辉,等. 悬臂式掘进机井下精确定位方法及其视觉测量技术[J]. 煤炭科学技术,2021,49(12):192-201. ZHAO Jianxun,YANG Wenjuan,ZHANG Xuhui,et al. Study on accurate positioning method and its visual measurement technology of cantilever roadheader underground[J]. Coal Science and Technology,2021,49(12):192-201.
[81] 张超,张旭辉,杜昱阳,等. 基于双目视觉的悬臂式掘进机位姿测量技术研究[J]. 煤炭科学技术,2021,49(11):225-235. ZHANG Chao,ZHANG Xuhui,DU Yuyang,et al. Measuring technique of cantilever roadheader position based on binocular stereo vision[J]. Coal Science and Technology,2021,49(11):225-235.
[82] 张旭辉,赵建勋,张超,等. 悬臂式掘进机视觉伺服截割控制系统研究[J]. 煤炭科学技术,2022,50(2):263-270. ZHANG Xuhui,ZHAO Jianxun,ZHANG Chao,et al. Study on visual servo control system for cutting of cantilever roadheader[J]. Coal Science and Technology,2022,50(2):263-270.
[83] 柳学猛,张凯, 马跃. 基于视觉测量的挖掘机工作装置姿态测量系统[J]. 中国矿业,2022,31(9):89-94. LIU Xuemeng,ZHANG Kai,MA Yue. Application status and trend of roadheader pose detection based on machine vision[J]. China Mining Magazine,2022,31(9):89-94.
[84] 张旭辉,周创,张超,等. 基于视觉测量的快速掘进机器人纠偏控制研究[J]. 工矿自动化,2020,46(9):21-26. ZHANG Xuhui,ZHOU Chuang,ZHANG Chao,et al. Research on deviation correction control of rapid tunneling robot based on vision measurement[J]. Industry and Mine Automation,2020,46(9):21-26.
[85] 王昱栋,代伟,马小平. 基于机器视觉的非接触式锚杆异常快速检测方法[J]. 工矿自动化,2021,47(4):13-18. WANG Yudong,DAI Wei,MA Xiaoping. Rapid detection method of bolt abnormality based on machine vision[J]. Industrial and Mining Automation,2021,47(4):13-18.
[86] 李萍,任安祥. 基于机器视觉的带送煤炭体积测量方法研究[J]. 工矿自动化,2018,44(4):24-29. LI Ping,REN Anxiang. Research on volume measurement method of coal on belt conveying based on machine vision[J]. Industry and Mine Automation,2018,44(4):24-29.
[87] 胡而已. 融合激光扫描与机器视觉的煤流量测量研究[J]. 煤炭工程,2021,53(11):146-151. HU Eryi. Coal flow measurement based on laser scanning and machine vision[J]. Coal Engineering,2021,53(11):146-151.
[88] 杨春雨,顾振,张鑫,等. 基于深度学习的带式输送机煤流量双目视觉测量[J]. 仪器仪表学报,2021,41(8):164-174. YANG Chunyu,GU Zhen,ZHANG Xin,et al. Binocular vision measurement of coal flow of belt conveyors based on deep learning[J]. Chinese Journal of Scientific Instrument,2021,41(8):164-174.
[89] QIU Zhaoyu,DOU Dongyang,ZHOU Deyang,et al. On-line prediction of clean coal ash content based on image analysis[J]. Measurement,2021,173:108663. DOI: 10.1016/j.measurement.2020.108663
[90] ZHANG Zelin,YANG Jianguo,WANG Yuling,et al. Ash content prediction of coarse coal by image analysis and GA-SVM[J]. Powder Technology,2014,268:429-435. DOI: 10.1016/j.powtec.2014.08.044
[91] ZHANG Zelin,LIU Yang,HU Qi,et al. Multi-information online detection of coal quality based on machine vision[J]. Powder Technology,2020,374:250-262. DOI: 10.1016/j.powtec.2020.07.040
[92] 吴智峰,柴鑫,王亚波,等. 基于机器视觉非接触测量外螺纹尺寸系统[J]. 煤矿机械,2018,39(8):171-172. WU Zhifeng,CHAI Xin,WANG Yabo,et al. Measurement of external thread size system based on machine vision non-contact[J]. Coal Mine Machinery,2018,39(8):171-172.
[93] GAO Yuan,QIAO Tiezhu,ZHANG Haitao,et al. A contact-less measuring speed system of belt conveyor based on machine vision and machine learning[J]. Measurement,2019,139:127-133. DOI: 10.1016/j.measurement.2019.03.030
[94] 田原. 浅谈机器视觉技术在煤矿中的应用前景[J]. 工矿自动化,2010,36(5):30-32. TIAN Yuan. Brief discussion of application prospect of technology of machine vision in coal mine[J]. Industry and Mine Automation,2010,36(5):30-32.
下载:
计量
- 文章访问数: 1088
- HTML全文浏览量: 332
- PDF下载量: 160
