Design Theory of Full Face Rock Tunnel Boring Machine Transition Cutter Edge Angle and Its Application

At present, the inner cutters of a full face rock tunnel boring machine (TBM) and transition cutter edge angles are designed on the basis of indentation test or linear grooving test. The inner and outer edge angles of disc cutters are characterized as symmetric to each other with respect to the cutter edge plane. This design has some practical defects, such as severe eccentric wear and tipping, etc. In this paper, the current design theory of disc cutter edge angle is analyzed, and the characteristics of the rock-breaking movement of disc cutters are studied. The researching results show that the rotational motion of disc cutters with the cutterhead gives rise to the difference between the interactions of inner rock and outer rock with the contact area of disc cutters, with shearing and extrusion on the inner rock and attrition on the outer rock. The wear of disc cutters at the contact area is unbalanced, among which the wear in the largest normal stress area is most apparent. Therefore, a three-dimensional model theory of rock breaking and an edge angle design theory of transition disc cutter are proposed to overcome the flaws of the currently used TBM cutter heads, such as short life span, camber wearing, tipping. And a corresponding equation is established. With reference to a specific construction case, the edge angle of the transition disc cutter has been designed based on the theory. The application of TBM in some practical project proves that the theory has obvious advantages in enhancing disc cutter life, decreasing replacement frequency, and making economic benefits. The proposed research provides a theoretical basis for the design of TBM three-dimensional disc cutters whose rock-breaking operation time can be effectively increased.

Wear Analysis of Disc Cutters of Full Face Rock Tunnel Boring Machine

Wear is a major factor of disc cutters’ failure. No current theory offers a standard for the prediction of disc cutter wear yet. In the field the wear prediction method commonly used is based on the excavation length of tunnel boring machine（TBM） to predict the disc cutter wear and its wear law, considering the location number of each disc cutter on the cutterhead（radius for installation）; in theory, there is a prediction method of using arc wear coefficient. However, the preceding two methods have their own errors, with their accuracy being 40% or so and largely relying on the technicians’ experience. Therefore, radial wear coefficient, axial wear coefficient and trajectory wear coefficient are defined on the basis of the operating characteristics of TBM. With reference to the installation and characteristics of disc cutters, those coefficients are modified according to penetration, which gives rise to the presentation of comprehensive axial wear coefficient, comprehensive radial wear coefficient and comprehensive trajectory wear coefficient. Calculation and determination of wear coefficients are made with consideration of data from a segment of TBM project（excavation length 173 m）. The resulting wear coefficient values, after modification, are adopted to predict the disc cutter wear in the follow-up segment of the TBM project（excavation length of 5621 m）. The prediction results show that the disc cutter wear predicted with comprehensive radial wear coefficient and comprehensive trajectory wear coefficient are not only accurate（accuracy 16.12%） but also highly congruous, whereas there is a larger deviation in the prediction with comprehensive axial wear coefficient（accuracy 41%, which is in agreement with the prediction of disc cutters’ life in the field）. This paper puts forth a new method concerning prediction of life span and wear of TBM disc cutters as well as timing for replacing disc cutters.

Face Recognition Based on Support Vector Machine and Nearest Neighbor Classifier

Support vector machine (SVM), as a novel approach in pattern recognition, has demonstrated a success in face detection and face recognition. In this paper, a face recognition approach based on the SVM classifier with the nearest neighbor classifier (NNC) is proposed. The principal component analysis (PCA) is used to reduce the dimension and extract features. Then one-against-all stratedy is used to train the SVM classifiers. At the testing stage, we propose an al-

Use of Discrete Wavelet Features and Support Vector Machine for Fault Diagnosis of Face Milling Tool

This paper presents the fault diagnosis of face milling tool based on machine learning approach.While machining,spindle vibration signals in feed direction under healthy and faulty conditions of the milling tool are acquired.A set of discrete wavelet features is extracted from the vibration signals using discrete wavelet transform(DWT)technique.The decision tree technique is used to select significant features out of all extracted wavelet features.C-support vector classification(C-SVC)andν-support vector classification(ν-SVC)models with different kernel functions of support vector machine(SVM)are used to study and classify the tool condition based on selected features.From the results obtained,C-SVC is the best model thanν-SVC and it can be able to give 94.5%classification accuracy for face milling of special steel alloy 42CrMo4.

Hybrid Machine Learning Model for Face Recognition Using SVM

Face recognition systems have enhanced human-computer interactions in the last ten years.However,the literature reveals that current techniques used for identifying or verifying faces are not immune to limitations.Principal Component Analysis-Support Vector Machine(PCA-SVM)and Principal Component Analysis-Artificial Neural Network(PCA-ANN)are among the relatively recent and powerful face analysis techniques.Compared to PCA-ANN,PCA-SVM has demonstrated generalization capabilities in many tasks,including the ability to recognize objects with small or large data samples.Apart from requiring a minimal number of parameters in face detection,PCA-SVM minimizes generalization errors and avoids overfitting problems better than PCA-ANN.PCA-SVM,however,is ineffective and inefficient in detecting human faces in cases in which there is poor lighting,long hair,or items covering the subject’s face.This study proposes a novel PCASVM-based model to overcome the recognition problem of PCA-ANN and enhance face detection.The experimental results indicate that the proposed model provides a better face recognition outcome than PCA-SVM.

Machine learning-based classification of rock discontinuity trace:SMOTE oversampling integrated with GBT ensemble learning

This paper presents a hybrid ensemble classifier combined synthetic minority oversampling technique(SMOTE),random search(RS)hyper-parameters optimization algorithm and gradient boosting tree(GBT)to achieve efficient and accurate rock trace identification.A thirteen-dimensional database consisting of basic,vector,and discontinuity features is established from image samples.All data points are classified as either‘‘trace”or‘‘non-trace”to divide the ultimate results into candidate trace samples.It is found that the SMOTE technology can effectively improve classification performance by recommending an optimized imbalance ratio of 1:5 to 1:4.Then,sixteen classifiers generated from four basic machine learning(ML)models are applied for performance comparison.The results reveal that the proposed RS-SMOTE-GBT classifier outperforms the other fifteen hybrid ML algorithms for both trace and nontrace classifications.Finally,discussions on feature importance,generalization ability and classification error are conducted for the proposed classifier.The experimental results indicate that more critical features affecting the trace classification are primarily from the discontinuity features.Besides,cleaning up the sedimentary pumice and reducing the area of fractured rock contribute to improving the overall classification performance.The proposed method provides a new alternative approach for the identification of 3D rock trace.

Theoretical prediction of wear of disc cutters in tunnel boring machine and its application

Predicting the cutter consumption and the exact time to replace the worn-out cutters in tunneling projects constructed with tunnel boring machine(TBM) is always a challenging issue. In this paper, we focus on the analyses of cutter motion in the rock breaking process and trajectory of rock breaking point on the cutter edge in rocks. The analytical expressions of the length of face along which the breaking point moves and the length of spiral trajectory of the maximum penetration point are derived. Through observation of rock breaking process of disc cutters as well as analysis of disc rock interaction, the following concepts are proposed: the arc length theory of predicting wear extent of inner and center cutters, and the spiral theory of predicting wear extent of gage and transition cutters. Data obtained from5621 m-long Qinling tunnel reveal that among 39 disc cutters, the relative errors between cumulatively predicted and measured wear values for nine cutters are larger than 20%, while approximately 76.9% of total cutters have the relative errors less than 20%. The proposed method could offer a new attempt to predict the disc cutter's wear extent and changing time.

Development and Analysis of a Machine Learning Based Software for Assisting Online Classes during COVID-19

Amid the Covid-19 widespread, it has been challenging for educational institutions to conduct online classes, facing multiples challenges. This paper provides an insight into different approaches in facing those challenges which includes conducting a fair online class for students. It is tough for an instructor to keep track of their students at the same time because it is difficult to screen if any of the understudies within the class are not present, mindful, or drowsing. This paper discusses a possible solution, something new that can offer support to instructors seeing things from a more significant point of view. The solution is a facial analysis computer program that can let instructors know which students are attentive and who is not. There’s a green and red square box for face detection, for which Instructors can watch by seeing a green box on those mindful students conjointly, a red box on those who are not mindful at all. This paper finds that the program can automatically give attendance by analyzing data from face detection. It has other features for which the teacher can also know if any student leaves the class early. In this paper, model design, performance analysis, and online class assistant aspects of the program have been discussed.

Machining Parameters Optimization of Multi-Pass Face Milling Using a Chaotic Imperialist Competitive Algorithm with an Efficient Constraint-Handling Mechanism

The selection of machining parameters directly affects the production time,quality,cost,and other process performance measures for multi-pass milling.Optimization of machining parameters is of great significance.However,it is a nonlinear constrained optimization problem,which is very difficult to obtain satisfactory solutions by traditional optimization methods.A new optimization technique combined chaotic operator and imperialist competitive algorithm(ICA)is proposed to solve this problem.The ICA simulates the competition between the empires.It is a population-based meta-heuristic algorithm for unconstrained optimization problems.Imperialist development operator based on chaotic sequence is introduced to improve the local search of ICA,while constraints handling mechanism is introduced and an imperialist-colony transformation policy is established.The improved ICA is called chaotic imperialist competitive algorithm(CICA).A case study of optimizing machining parameters for multi-pass face milling operations is presented to verify the effectiveness of the proposed method.The case is to optimize parameters such as speed,feed,and depth of cut in each pass have yielded a minimum total product ion cost.The depth of cut of optimal strategy obtained by CICA are 4 mm,3 mm,1 mm for rough cutting pass 1,rough cutting pass 1 and finish cutting pass,respectively.The cost for each pass are$0.5366 US,$0.4473 US and$0.3738 US.The optimal solution of CICA for various strategies with at=8 mm is$1.3576 US.The results obtained with the proposed schemes are better than those of previous work.This shows the superior performance of CICA in solving such problems.Finally,optimization of cutting strategy when the width of workpiece no smaller than the diameter of cutter is discussed.Conclusion can be drawn that larger tool diameter and row spacing should be chosen to increase cutting efficiency.

Research on Application of Support Vector Machine in Machine Learning

In recent years,support vector machine learning methods have gradually become the main research direction of machine learning.The support vector machine has a small structural risk compared with the traditional learning method,which can make the training error and the classifier capacity reach a relatively balanced state.Secondly,it also has the advantages of strong adaptability and strong promotion ability and has been widely praised by the industry.The following discussion focuses on the application of support vector machine in machine learning.

MATHEMATICAL MODEL OF NC MACHINING NONCONVENTIONAL MILLING CUTTERS-FORMING METHOD OF RAKE FACES

How to generate rake faces of nonconventional milling cutters (NCMC) with constant spiral angled and normal rake angled edges on NC machine tools is presented by use of a blunt cup grinder or a cup milling cutter. Motion functions of the NC machining system are mathematically deduced and exam- ed by a experiment. The research will provide theoretical and practical guidance for machining noncon- ventional tools on NC machine tools.

格里森CONIFACE面齿轮磨齿加工原理与误差分析

研究并给出格里森最新的CONIFACE面齿轮磨齿加工原理。推导砂轮刀具的形状和齿面方程,基于齿轮啮合原理获得磨削后的面齿轮的齿面方程;研究分析该方法加工的面齿轮齿面与理论齿面的齿面误差及误差的影响规律;结果表明,采用该方法加工获得的面齿轮齿厚较NASA报告中提供的阿帕奇直升机面齿轮齿厚要薄,加工误差在齿宽中点处最小,并逐渐向两端增大,类似于圆柱齿轮鼓形修形后的效果,通过改变砂轮刀具的锥角和砂轮半径的值可调控鼓形量误差的大小。

Face Image Recognition Based on Convolutional Neural Network

With the continuous progress of The Times and the development of technology,the rise of network social media has also brought the“explosive”growth of image data.As one of the main ways of People’s Daily communication,image is widely used as a carrier of communication because of its rich content,intuitive and other advantages.Image recognition based on convolution neural network is the first application in the field of image recognition.A series of algorithm operations such as image eigenvalue extraction,recognition and convolution are used to identify and analyze different images.The rapid development of artificial intelligence makes machine learning more and more important in its research field.Use algorithms to learn each piece of data and predict the outcome.This has become an important key to open the door of artificial intelligence.In machine vision,image recognition is the foundation,but how to associate the low-level information in the image with the high-level image semantics becomes the key problem of image recognition.Predecessors have provided many model algorithms,which have laid a solid foundation for the development of artificial intelligence and image recognition.The multi-level information fusion model based on the VGG16 model is an improvement on the fully connected neural network.Different from full connection network,convolutional neural network does not use full connection method in each layer of neurons of neural network,but USES some nodes for connection.Although this method reduces the computation time,due to the fact that the convolutional neural network model will lose some useful feature information in the process of propagation and calculation,this paper improves the model to be a multi-level information fusion of the convolution calculation method,and further recovers the discarded feature information,so as to improve the recognition rate of the image.VGG divides the network into five groups(mimicking the five layers of AlexNet),yet it USES 3*3 filters and combines them as a convolution sequence.Network deeper DCNN,channel number is bigger.The recognition rate of the model was verified by 0RL Face Database,BioID Face Database and CASIA Face Image Database.

Pre-detection and dual-dictionary sparse representation based face recognition algorithm in non-sufficient training samples

Face recognition based on few training samples is a challenging task. In daily applications, sufficient training samples may not be obtained and most of the gained training samples are in various illuminations and poses. Non-sufficient training samples could not effectively express various facial conditions, so the improvement of the face recognition rate under the non-sufficient training samples condition becomes a laborious mission. In our work, the facial pose pre-recognition(FPPR) model and the dualdictionary sparse representation classification(DD-SRC) are proposed for face recognition. The FPPR model is based on the facial geometric characteristic and machine learning, dividing a testing sample into full-face and profile. Different poses in a single dictionary are influenced by each other, which leads to a low face recognition rate. The DD-SRC contains two dictionaries, full-face dictionary and profile dictionary, and is able to reduce the interference. After FPPR, the sample is processed by the DD-SRC to find the most similar one in training samples. The experimental results show the performance of the proposed algorithm on olivetti research laboratory(ORL) and face recognition technology(FERET) databases, and also reflect comparisons with SRC, linear regression classification(LRC), and two-phase test sample sparse representation(TPTSSR).

A precision generating hobbing method for face gear with assembly spherical hob

In order to improve the processing precision and shorten the hob manufacturing cycle of the face gear,a precision generating hobbing method for face gear with the assembly spherical hob is proposed.Firstly,the evolution of the cylindrical gear to spherical hob basic worm is analyzed,then the spherical hob basic worm is designed,thus the basic worm and spiral angle equation of spherical hob are obtained.Secondly,based on the design method of the existing hob,the development method of the assembly spherical hob is analyzed,the cutter tooth and the cutter substrate of the assembly hob are designed,and the whole assembly is finished.Thirdly,based on the need of face gear hobbing,a numerical control machine for gear hobbing is developed,and the equation of the face gear is obtained.Fourth,for reducing the face gear processing errors induced by equivalent installation errors,the error analysis model is established and the impacts of each error on the gear tooth surface are analyzed.Finally,the assembly spherical hob is manufactured and the gear hobbing test is completed.According to the measurement results,the processing parameters of face gear hobbing are modified,and the deviation of tooth surface is significantly reduced.

基于FaceNet的无人值守变电站智能监控终端

为了解决无人值守变电站由于点位众多所导致的难以对进站人员实时监控的问题,本文提出了一种针对进站人员实时监测的智能分类算法,首先采用级联Haar分类器实现对监控画面中人脸图像的捕获与分离,然后基于Face Net深度人脸识别模型完成对人脸图像的特征提取。在此基础上使用支持向量机算法完成对进站人员的智能分类:对于已知人员记录姓名以及进站时间,对于陌生人执行报警功能以及其他规定动作。在实际应用中的实验结果表明,调节算法超参数将获得不同的灵敏度与识别率,经过对超参数的微调,该算法的准确率达到90%左右。基于该算法开发的监控平台已部署到智能终端上,依靠边缘计算技术实现对无人值守变电站进站人员的自动识别,并在生产实践中取得了预期的效果。

Face mask detection algorithm based on HSV+HOG features and SVM

To automatically detecting whether a person is wearing mask properly,we propose a face mask detection algorithm based on hue-saturation-value(HSV)+histogram of oriented gradient(HOG)features and support vector machines(SVM).Firstly,human face and five feature points are detected with RetinaFace face detection algorithm.The feature points are used to locate to mouth and nose region,and HSV+HOG features of this region are extracted and input to SVM for training to realize detection of wearing masks or not.Secondly,RetinaFace is used to locate to nasal tip area of face,and YCrCb elliptical skin tone model is used to detect the exposure of skin in the nasal tip area,and the optimal classification threshold can be found to determine whether the wear is properly according to experimental results.Experiments show that the accuracy of detecting whether mask is worn can reach 97.9%,and the accuracy of detecting whether mask is worn correctly can reach 87.55%,which verifies the feasibility of the algorithm.

Masked Face Recognition Using MobileNet V2 with Transfer Learning

Corona virus(COVID-19)is once in a life time calamity that has resulted in thousands of deaths and security concerns.People are using face masks on a regular basis to protect themselves and to help reduce corona virus transmission.During the on-going coronavirus outbreak,one of the major priorities for researchers is to discover effective solution.As important parts of the face are obscured,face identification and verification becomes exceedingly difficult.The suggested method is a transfer learning using MobileNet V2 based technology that uses deep feature such as feature extraction and deep learning model,to identify the problem of face masked identification.In the first stage,we are applying face mask detector to identify the face mask.Then,the proposed approach is applying to the datasets from Canadian Institute for Advanced Research10(CIFAR10),Modified National Institute of Standards and Technology Database(MNIST),Real World Masked Face Recognition Database(RMFRD),and Stimulated Masked Face Recognition Database(SMFRD).The proposed model is achieving recognition accuracy 99.82%with proposed dataset.This article employs the four pre-programmed models VGG16,VGG19,ResNet50 and ResNet101.To extract the deep features of faces with VGG16 is achieving 99.30%accuracy,VGG19 is achieving 99.54%accuracy,ResNet50 is achieving 78.70%accuracy and ResNet101 is achieving 98.64%accuracy with own dataset.The comparative analysis shows,that our proposed model performs better result in all four previous existing models.The fundamental contribution of this study is to monitor with face mask and without face mask to decreases the pace of corona virus and to detect persons using wearing face masks.

Region Pair Grey Difference Classifier for Face Detection

A new kind of region pair grey difference classifier was proposed. The regions in pairs associated to form a feature were not necessarily directly-connected, but were selected dedicatedly to the grey transition between regions coinciding with the face pattern structure. Fifteen brighter and darker region pairs were chosen to form the region pair grey difference features with high discriminant capabilities. Instead of using both false acceptance rate and false rejection rate, the mutual information was used as a unified metric for evaluating the classifying performance. The parameters of specified positions, areas and grey difference bias for each single region pair feature were selected by an optimization processing aiming at maximizing the mutual information between the region pair feature and classifying distribution, respectively. An additional region-based feature depicting the correlation between global region grey intensity patterns was also proposed. Compared with the result of Viola-like approach using over 2 000 features, the proposed approach can achieve similar error rates with only 16 features and 1/6 implementation time on controlled illumination images.

Face Orientation Normalization Using Eye Positions

Despite the fact that progress in face recognition algorithms over the last decades has been made, changing lighting conditions and different face orientation still remain as a challenging problem. A standard face recognition system identifies the person by comparing the input picture against pictures of all faces in a database and finding the best match. Usually face matching is carried out in two steps： during the first step detection of a face is done by finding exact position of it in a complex background （various lightning condition）, and in the second step face identification is performed using gathered databases. In reality detected faces can appear in different position and they can be rotated, so these disturbances reduce quality of the recognition algorithms dramatically. In this paper to increase the identification accuracy we propose original geometric normalization of the face, based on extracted facial feature position such as eyes. For the eyes localization lbllowing methods has been used： color based method, mean eye template and SVM （Support Vector Machine） technique. Experimental investigation has shown that the best results for eye center detection can be achieved using SVM technique. The recognition rate increases statistically by 28% using face orientation normalization based on the eyes position.