Reliability Analysis of Production System of Fully-Mechanized Face Based on Output Statistic

Production system of fully-mechanized face is a complicated system composed of human, machine and environment, meantime influenced by various random factors. Analyzing the reliability of system needs plentiful data by means of system faults statistic. Based on the viewpoint that shift output of fully-mechanized face is the result of various random factors’ synthetical influence, the process of how to analyze its reliability was deduced by using probability theory, symbolic statistics theory and systematic reliability theory combined with the concrete case study in this paper. And it has been proved that this method is feasible and valuable.

基于SSD与FaceNet的人脸识别系统设计

人脸识别技术广泛应用于考勤管理、移动支付等智慧建设中。伴随着常态化的口罩干扰,传统人脸识别算法已无法满足实际应用需求,为此,本文利用深度学习模型SSD以及FaceNet模型对人脸识别系统展开设计。首先,为消除现有数据集中亚洲人脸占比小造成的类内间距变化差距不明显的问题,在CAS-IA Web Face公开数据集的基础上对亚洲人脸数据进行扩充;其次,为解决不同口罩样式对特征提取的干扰,使用SSD人脸检测模型与DLIB人脸关键点检测模型提取人脸关键点,并利用人脸关键点与口罩的空间位置关系,额外随机生成不同的口罩人脸,组成混合数据集;最后,在混合数据集上进行模型训练并将训练好的模型移植到人脸识别系统中,进行检测速度与识别精度验证。实验结果表明,系统的实时识别速度达20 fps以上,人脸识别模型准确率在构建的混合数据集中达到97.1%,在随机抽取的部分LFW数据集验证的准确率达99.7%,故而该系统可满足实际应用需求,在一定程度上提高人脸识别的鲁棒性与准确性。

基于YOLO5Face重分布的小尺度人脸检测方法

针对复杂场景下小尺度人脸检测精度较低的问题,提出了一种基于YOLO5Face重分布的小尺度人脸检测方法。方法以YOLO5Face为基础,在网络浅层引入改进的CBAM注意力并对模型计算重分布,提升复杂场景下小尺度人脸检测精度的同时降低模型参数量;采用融合mixup的数据增强方法,充分训练模型小尺度人脸检测分支;依据人脸检测特性,将softmax损失作为分类损失以最大化类间特征的差异。在WiderFace各个子集上的实验结果表明,与主流人脸检测方法相比,改进后的模型满足实时性的同时,小尺度人脸检测精度较高,其中Hard子集检测精度比YOLO5Face提升2个百分点。

Numerical simulation for determining three zones in the goaf at a fully-mechanized coal face

According to the theory of ventilation network, a model for a filtration flow field in goaf was built and simulation soft- ware for determining the three zones in goaf has been developed. This software uses no-gap-connection between Visual Basic (VB) and Excel to exchange data, uses Component Object Model (COM) component of MATLAB to plot charts of the three zones and to export the corresponding coordinates of the isolines. An example shows that this software is convenient and simple. By using it, the three zones can be easily determined. The software is convenient in studies and analyses of the three zones in goaf.

Characteristics of Gas Emission at Super-Length Fully-Mechanized Top Coal Caving Face

Characteristics of gas emission at the K8206 working face in the Third mine of the Yangquan Coal Group were investigated. The effects of strata movement,advancing velocity of working face,production capacity of working face and gas extraction capability of strike high-level entry on gas emission at K8206 working face were analyzed. A regression equation,reflecting the relationship between relative gas emission rate and the production capacity of work-ing faces,was established. Another regression equation showing the relationship between the gas emission rate from adjacent layers when the working face was advancing for one metre and advancing velocity was derived. It can be con-cluded that,1) the amount of gas emitted at the K8206 working face is far greater than that of ordinary top coal caving faces with a dip length of 180-190 m; 2) the dynamic process of gas emission from adjacent layers during the initial mining stage is controlled by the movement of key strata; 3) the amount of gas emitted that needs to be forced out by air is greatly affected by the capability of gas extraction; 4) when the advancing velocity is between 3.5-5.5 m/d or when the output is up to 8-12 kt/d,the gas emission from adjacent layers is almost constant.

VR/AR-AdaptFace:面向虚拟现实与增强现实的自适应多模态面部替换模型

随着VR/AR技术的迅猛发展,用户对于沉浸式体验的需求日益增长。同时,虚拟人脸技术亦趋成熟。基于此,本文探索将高度拟真的虚拟人脸融入VR/AR,以增强用户体验的自然度与沉浸感。然而,在虚拟数字人领域,图像生成及换脸技术在VR/AR环境下仍遇诸多挑战,尤其是唇形合成模型在动态场景及多语言环境下的性能需进一步优化。为解决上述问题,本文提出VR/AR-AdaptFace模型,一个面向虚拟现实与增强现实的自适应多模态面部替换方案。该模型由两大模块构成:“文颜绘真”模块,采用先进的文本至图像转换技术和特定类别先验保存策略,优化虚拟人脸生成,并通过注意力机制大幅提升图像质量;“语唇映生”模块,依托强大的生成器、唇形同步判别器及视觉质量判别器,实现语音与唇形的精准同步,为VR/AR场景中的动态交互带来更加逼真的体验。

Patterns governing distribution of surrounding-rock stress and strata behaviors of fully-mechanized caving faces

By employing numerical modeling, similar material simulation and comprehen-sive field observation, investigations were made and patterns were obtained governing surrounding-rock stress distribution and strata behaviors. It shows that patterns governing displacement of FMC roadway surrounding rocks and those governing deformation of supports are basically the same along the strike, but the displacements vary greatly. The front stresses affect greater areas than the lateral stresses and their limit widths of equilib-rium zones and K are almost similar. The stress transmits very deep. Our findings offer scientific basis on which to determine parameters for coal pillar retaining and for roadway out-laying, thus increasing the recovery ratio and improving the maintenance of roadway.

Mechanical analysis on deformation of surrounding rock with road-in packing of gob-side entry retaining in fully-mechanized sub-level caving face

Based on the movement regularity of surrounding rock with road-in packing of gob-side entry retaining in fully-mechanized sub-level caving face(RPGERFCF),the me- chanical model of its surrounding rock was established and the calculating formulas of the deformation of the roof,coal wall and filling body were attained.By the mechanical analy- sis to the deformation of the surrounding rock of RPGERFCF,the major factors influencing the deformation of the surrounding rock were found out and the technologic approaches reduced the deformation and enhanced the stability of the surrounding rock were put for- ward.Consequently,the scientific bases were provided for the stability control of the sur- rounding rock of RPGERFCF.

Support-surrounding rock relationship and top-coal movement laws in large dip angle fully-mechanized caving face

When mining the fully-mechanized longwall caving face along strike, the unstable equipment, the low top-coal recovery ratio and the difficulty in controlling surrounding rock may occur due to large dip angle. Considering the effects of strike angle on support stability, the ‘‘support-surrounding rock"mechanical models of support topple and support slip were established in this paper. On the basis, the influencing factors of support stability were analyzed and the technical measures of controlling support and surrounding rock stability were put forward. Then the loose particles simulation experiment was conducted to analyze the impacts of caving directions and methods on the top-coal recovery in large dip angle fully-mechanized caving face. Finally, the ‘‘upward sequence and double-openings doublerounds" caving technology was determined. The research results are of great scientific significance and practical values to improve large dip thick seam mining technology.

Analysis of Noise at Coal Face by Fully-Mechanized Coal Winning Technology

The noise level of coal face by full-mechanized coal winning technology was measured in a coal mine. And then it was analyzed and evaluated using environment science, ergonomics and fussy mathematics analysis. Basis of the statistics and analysis of the measured noise level some measures, such as applying the new materials and improving the construction of the equipment, were carried out. The resuts show that they can reduce the noise level, improve the working environment and enhance the work efficiency.

Probabilistic analysis of tunnel face seismic stability in layered rock masses using Polynomial Chaos Kriging metamodel

Face stability is an essential issue in tunnel design and construction.Layered rock masses are typical and ubiquitous;uncertainties in rock properties always exist.In view of this,a comprehensive method,which combines the Upper bound Limit analysis of Tunnel face stability,the Polynomial Chaos Kriging,the Monte-Carlo Simulation and Analysis of Covariance method(ULT-PCK-MA),is proposed to investigate the seismic stability of tunnel faces.A two-dimensional analytical model of ULT is developed to evaluate the virtual support force based on the upper bound limit analysis.An efficient probabilistic analysis method PCK-MA based on the adaptive Polynomial Chaos Kriging metamodel is then implemented to investigate the parameter uncertainty effects.Ten input parameters,including geological strength indices,uniaxial compressive strengths and constants for three rock formations,and the horizontal seismic coefficients,are treated as random variables.The effects of these parameter uncertainties on the failure probability and sensitivity indices are discussed.In addition,the effects of weak layer position,the middle layer thickness and quality,the tunnel diameter,the parameters correlation,and the seismic loadings are investigated,respectively.The results show that the layer distributions significantly influence the tunnel face probabilistic stability,particularly when the weak rock is present in the bottom layer.The efficiency of the proposed ULT-PCK-MA is validated,which is expected to facilitate the engineering design and construction.

SAFETY PROBLEMS IN FULLY-MECHANIZED TOP-COAL CAVING LONGWALL FACES

The thick-san top-ctal catrig technology has been in use in China for over a decade,and has given rise to siguscant economic efficiendes. Eftorts in reeent years to extend its applica tion to more complex mining conditions, mostly high-gas seams , with or without proneness ofspontaneous combustion. have brought about new safety problems This paper will highlight thefcatures and problems retared with thick-seam top-coal caving systems, compared with conventionai, fully-mecbanized longwall systems , particularly issues retated to methane, spontaneous combustion and dust,and disam the methods and measures to ded with them.

Rock mass quality prediction on tunnel faces with incomplete multi-source dataset via tree-augmented naive Bayesian network

Rock mass quality serves as a vital index for predicting the stability and safety status of rock tunnel faces.In tunneling practice,the rock mass quality is often assessed via a combination of qualitative and quantitative parameters.However,due to the harsh on-site construction conditions,it is rather difficult to obtain some of the evaluation parameters which are essential for the rock mass quality prediction.In this study,a novel improved Swin Transformer is proposed to detect,segment,and quantify rock mass characteristic parameters such as water leakage,fractures,weak interlayers.The site experiment results demonstrate that the improved Swin Transformer achieves optimal segmentation results and achieving accuracies of 92%,81%,and 86%for water leakage,fractures,and weak interlayers,respectively.A multisource rock tunnel face characteristic(RTFC)dataset includes 11 parameters for predicting rock mass quality is established.Considering the limitations in predictive performance of incomplete evaluation parameters exist in this dataset,a novel tree-augmented naive Bayesian network(BN)is proposed to address the challenge of the incomplete dataset and achieved a prediction accuracy of 88%.In comparison with other commonly used Machine Learning models the proposed BN-based approach proved an improved performance on predicting the rock mass quality with the incomplete dataset.By utilizing the established BN,a further sensitivity analysis is conducted to quantitatively evaluate the importance of the various parameters,results indicate that the rock strength and fractures parameter exert the most significant influence on rock mass quality.

VanillaFaceNet:一种高精度快速推理的牛脸识别方法

快速精准确定牛只身份对于牛只活体贷款,改善牛只骗保等问题具有重要意义。针对不同牛只面部差异小,FaceNet网络层数深,推理速度较慢,模型分类精度不足等问题,该研究提出了基于FaceNet的牛脸识别方法-VanillaFaceNet。该方法首先将FaceNet的主干特征提取网络替换为极简网络VanillaNet-13并提出动态激活和增强型线性变换的激活函数两种方法提高网络的非线性;然后,提出一种新的DBCA(dual-branch coordinate attention)注意力模块,能够更好地反映不同牛只面部特征之间的差异,从而提高网络的识别精度;最后,针对triplet loss仅能减小牛只类间差异的问题,采用center-triplet loss联合监督来减少牛只类内差异,从而提高了相同牛只身份比对的准确性。基于自建的牛脸数据集对该模型进行训练和测试,试验结果表明,VanillaFaceNet对牛只识别的准确率达到88.21%,每秒传输帧数为26.23帧。与FaceNet、MobileFaceNet、CenterFace、CosFace和ArcFace算法相比,本文算法的识别准确率分别提高了2.99、9.58、6.26、3.85和4.49个百分点,推理速度分别提升了2.67、0.77、0.10、1.28和0.94帧/s。该模型对牛只有较为优秀的识别效果,适于在嵌入式设备上部署,实现了牛只面部识别精度和推理速度之间的平衡。

Analysis and control of hydraulic support stability in fully-mechanized longwall face to the dip with great mining height

The working condition of the hydraulic support in working face can be divided into three kinds of situations in the following： roof fall and col,lapse with cavity, advancing support and supporting. Took single support with four-pole in Iongwall face to the dip as research object, control method was studied to avoid support instability in three situations mentioned above. Based on these researches, the major factors of influencing on support stability and its controlling measures were put forward. According to specific conditions of working face 1215（3）, which is fully-mechanized and Iongwall face to the dip with great mining height in Zhangji Coal Mine, Huainan Mining Group, the effective measures was taken to control supports stability..

Analysis on distribution law of the abutment pressure of the integrated coal beside the road-in packing for gob-side entry retaining in fully-mechanized caving face

The three-dimensional damage constitutive relationship of coal is established and distribution law of the abutment pressure of the integrated coal beside the road-in packing for gob-side entry retaining in fully-mechanized caving face under the effect of given deformation of the main roof is analyzed by the damage mechanics theory. And the relationship between distribution of the abutment pressure and thickness of coal seam is explored. The presented result is of great theoretical significance and practical value to the study on stability control of the surrounding rock of road-in packing for gob-side entry retaining in fully-mechanized caving face.

基于改进YOLOv5s-face的Face5系列人脸检测算法

针对人脸检测中小尺度人脸和遮挡人脸的漏检问题,提出了一种基于改进YOLOv5s-face(you only look once version 5 small-face)的Face5系列人脸检测算法Face5S(face5 small)和Face5M(face5 medium)。使用马赛克(mosaic)和图像混合(mixup)数据增强方法,提升算法在复杂场景下检测人脸的泛化性和稳定性;通过改进C3的网络结构和引入可变形卷积(DCNv2)降低算法的参数量,提高算法提取特征的灵活性;通过引入特征的内容感知重组上采样算子(CARAFE),提高多尺度人脸的检测性能;引入损失函数WIoUV3(wise intersection over union version 3),提升算法的小尺度人脸检测性能。实验结果表明,在WIDER FACE验证集上,相较于YOLOv5s-face算法,Face5S算法的平均mAP@0.5提升了1.03%;相较于先进的人脸检测算法ASFD-D3(automatic and scalable face detector-D3)和TinaFace,Face5M算法的平均mAP@0.5分别提升了1.07%和2.11%,提出的Face5系列算法能够有效提升算法对小尺度和部分遮挡人脸的检测性能,同时具有实时性。

Stability analysis of tunnel face reinforced with face bolts

Face bolting has been widely utilized to enhance the stability of tunnel face,particularly in soft soil tunnels.However,the influence of bolt reinforcement and its layout on tunnel face stability has not been systematically studied.Based on the theory of linear elastic mechanics,this study delved into the specific mechanisms of bolt reinforcement on the tunnel face in both horizontal and vertical dimensions.It also identified the primary failure types of bolts.Additionally,a design approach for tunnel face bolts that incorporates spatial layout was established using the limit equilibrium method to enhance the conventional wedge-prism model.The proposed model was subsequently validated through various means,and the specific influence of relevant bolt design parameters on tunnel face stability was analyzed.Furthermore,design principles for tunnel face bolts under different geological conditions were presented.The findings indicate that bolt failure can be categorized into three stages:tensile failure,pullout failure,and comprehensive failure.Increasing cohesion,internal friction angle,bolt density,and overlap length can effectively enhance tunnel face stability.Due to significant variations in stratum conditions,tailored design approaches based on specific failure stages are necessary for bolt design.

Study on Filling Cross-Roadway in Fully-Mechanized Coal Faces with High Water-Content Material

A new method using high water content material to mechanically fill cross roadways to form artificial bottom for coal faces was introduced. The reasonable determination of filling range, the optimization of the compounding ratio of high water content material, and the filling technique were discussed in detail. This new method has been spread after industrial testing in Baodian Colliery. Compared with the traditional method, the manual wooden chock method, the new one decreases about 40% of the filling range and cost in dealing every one set of cross roadway in the testing condition.

Generating animatable 3D cartoon faces from single portraits

Background With the development of virtual reality(VR)technology,there is a growing need for customized 3D avatars.However,traditional methods for 3D avatar modeling are either time-consuming or fail to retain the similarity to the person being modeled.This study presents a novel framework for generating animatable 3D cartoon faces from a single portrait image.Methods First,we transferred an input real-world portrait to a stylized cartoon image using StyleGAN.We then proposed a two-stage reconstruction method to recover a 3D cartoon face with detailed texture.Our two-stage strategy initially performs coarse estimation based on template models and subsequently refines the model by nonrigid deformation under landmark supervision.Finally,we proposed a semantic-preserving face-rigging method based on manually created templates and deformation transfer.Conclusions Compared with prior arts,the qualitative and quantitative results show that our method achieves better accuracy,aesthetics,and similarity criteria.Furthermore,we demonstrated the capability of the proposed 3D model for real-time facial animation.