Search | Engineering

订阅投稿

首页工程期刊工程焦点工程成就工程前沿关于我们 English

资源类型

期刊论文 98

年份

2023 8

2022 6

2021 6

2020 9

2019 10

2018 8

2017 9

2016 2

2015 8

2014 1

2013 4

2012 7

2011 2

2010 1

2009 1

2008 1

2007 4

2006 3

2005 2

2003 2

展开︾

关键词

分类 5

政策建议 2

深度学习 2

COVID-19 1

NURBS技术 1

SARS危机 1

k-最近邻分类 1

三台阶七步开挖法 1

三维模型 1

三维路径规划 1

不规则三角网 1

中国 1

主成分分析 1

亚分级 1

产品设计；知识推送系统；增强训练集；多分类神经网络；知识匹配 1

人的可靠性 1

仿人机器人 1

位置敏感机制深度学习网络 1

展开︾

检索范围：

排序：展示方式：

Terrain classification and adaptive locomotion for a hexapod robot Qingzhui

Yue ZHAO, Feng GAO, Qiao SUN, Yunpeng YIN

《机械工程前沿（英文）》 2021年第16卷第2期页码 271-284 doi: 10.1007/s11465-020-0623-1

摘要： Legged robots have potential advantages in mobility compared with wheeled robots in outdoor environments. The knowledge of various ground properties and adaptive locomotion based on different surface materials plays an important role in improving the stability of legged robots. A terrain classification and adaptive locomotion method for a hexapod robot named Qingzhui is proposed in this paper. First, a force-based terrain classification method is suggested. Ground contact force is calculated by collecting joint torques and inertial measurement unit information. Ground substrates are classified with the feature vector extracted from the collected data using the support vector machine algorithm. Then, an adaptive locomotion on different ground properties is proposed. The dynamic alternating tripod trotting gait is developed to control the robot, and the parameters of active compliance control change with the terrain. Finally, the method is integrated on a hexapod robot and tested by real experiments. Our method is shown effective for the hexapod robot to walk on concrete, wood, grass, and foam. The strategies and experimental results can be a valuable reference for other legged robots applied in outdoor environments.

关键词： terrain classification hexapod robot legged robot adaptive locomotion gait control

HTML PDF 收藏

Enhancing the terrain adaptability of a multirobot cooperative transportation system via novel connectors

《机械工程前沿（英文）》 2023年第18卷第3期 doi: 10.1007/s11465-023-0754-2

摘要： Given limited terrain adaptability, most existing multirobot cooperative transportation systems (MRCTSs) mainly work on flat pavements, restricting their outdoor applications. The connectors’ finite deformation capability and the control strategies’ limitations are primarily responsible for this phenomenon. This study proposes a novel MRCTS based on tracked mobile robots (TMRs) to improve terrain adaptability and expand the application scenarios of MRCTSs. In structure design, we develop a novel 6-degree-of-freedom passive adaptive connector to link multiple TMRs and the transported object (the communal payload). In addition, the connector is set with sensors to measure the position and orientation of the robot with respect to the object for feedback control. In the control strategy, we present a virtual leader–physical follower collaborative paradigm. The leader robot is imaginary to describe the movement of the entire system and manage the follower robots. All the TMRs in the system act as follower robots to transport the object cooperatively. Having divided the whole control structure into the leader robot level and the follower robot level, we convert the motion control of the two kinds of robots to trajectory tracking control problems and propose a novel double closed-loop kinematics control framework. Furthermore, a control law satisfying saturation constraints is derived to ensure transportation stability. An adaptive control algorithm processes the wheelbase uncertainty of the TMR. Finally, we develop a prototype of the TMR-based MRCTS for experiments. In the trajectory tracking experiment, the developed MRCTS with the proposed control scheme can converge to the reference trajectory in the presence of initial tracking errors in a finite time. In the outdoor experiment, the proposed MRCTS consisting of four TMRs can successfully transport a payload weighing 60 kg on an uneven road with the single TMR’s maximum load limited to 15 kg. The experimental results demonstrate the effectiveness of the structural design and control strategies of the TMR-based MRCTS.

关键词： multirobot system cooperative transportation terrain adaptability trajectory tracking collaborative paradigm uneven road

HTML PDF 收藏

Footholds optimization for legged robots walking on complex terrain

《机械工程前沿（英文）》 2023年第18卷第2期 doi: 10.1007/s11465-022-0742-y

摘要： This paper proposes a novel continuous footholds optimization method for legged robots to expand their walking ability on complex terrains. The algorithm can efficiently run onboard and online by using terrain perception information to protect the robot against slipping or tripping on the edge of obstacles, and to improve its stability and safety when walking on complex terrain. By relying on the depth camera installed on the robot and obtaining the terrain heightmap, the algorithm converts the discrete grid heightmap into a continuous costmap. Then, it constructs an optimization function combined with the robot’s state information to select the next footholds and generate the motion trajectory to control the robot’s locomotion. Compared with most existing footholds selection algorithms that rely on discrete enumeration search, as far as we know, the proposed algorithm is the first to use a continuous optimization method. We successfully implemented the algorithm on a hexapod robot, and verified its feasibility in a walking experiment on a complex terrain.

关键词： footholds optimization legged robot complex terrain adapting hexapod robot locomotion control

HTML PDF 收藏

Contact detection with multi-information fusion for quadruped robot locomotion under unstructured terrain

《机械工程前沿（英文）》 2023年第18卷第3期 doi: 10.1007/s11465-023-0760-4

摘要： Reliable foot-to-ground contact state detection is crucial for the locomotion control of quadruped robots in unstructured environments. To improve the reliability and accuracy of contact detection for quadruped robots, a detection approach based on the probabilistic contact model with multi-information fusion is presented to detect the actual contact states of robotic feet with the ground. Moreover, a relevant control strategy to address unexpected early and delayed contacts is planned. The approach combines the internal state information of the robot with the measurements from external sensors mounted on the legs and feet of the prototype. The overall contact states are obtained by the classification of the model-based predicted probabilities. The control strategy for unexpected foot-to-ground contacts can correct the control actions of each leg of the robot to traverse cluttered environments by changing the contact state. The probabilistic model parameters are determined by testing on the single-leg experimental platform. The experiments are conducted on the experimental prototype, and results validate the contact detection and control strategy for unexpected contacts in unstructured terrains during walking and trotting. Compared with the body orientation under the time-based control method regardless of terrain, the root mean square errors of roll, pitch, and yaw respectively decreased by 60.07%, 54.73%, and 64.50% during walking and 73.40%, 61.49%, and 61.48% during trotting.

关键词： multi-information fusion contact detection quadruped robot probabilistic contact model unstructured terrain

HTML PDF 收藏

Development of a new method for RMR and Q classification method to optimize support system in tunneling

Asghar RAHMATI,Lohrasb FARAMARZI,Manouchehr SANEI

《结构与土木工程前沿（英文）》 2014年第8卷第4期页码 448-455 doi: 10.1007/s11709-014-0262-x

摘要： Rock mass classification system is very suitable for various engineering design and stability analysis. classification method is confirmed by Japan Highway Public Corporation that this method can figure out either strength or deformability of rock mass, further appropriating the amount of rock bolts, thickness of shotcrete, and size of pitch of steel ribs just after the blasting procedure. Based on these advantages of method, in this study, according to data of five deep and long tunnels in Iran, two equations for estimating the value of method from and classification systems were developed. These equations as a new method were able to optimize the support system for and classification systems. From classification and its application in these case studies, it is pointed out that the method for the design of support systems in underground working is more reliable than the and classification systems.

关键词： JH classification Q and RMR classification new method

HTML PDF 收藏

Molecular classification and precision therapy of cancer: immune checkpoint inhibitors

null

《医学前沿（英文）》 2018年第12卷第2期页码 229-235 doi: 10.1007/s11684-017-0581-0

摘要：

On May 23, 2017, the US Food and Drug Administration (FDA) approved a treatment for cancer patients with positive microsatellite instability-high (MSI-H) markers or mismatch repair deficient (dMMR) markers. This approach is the first approved tumor treatment using a common biomarker rather than specified tumor locations in the body. FDA previously approved Keytruda for treatment of several types of malignancies, such as metastatic melanoma, metastatic non-small-cell lung cancer, recurrent or metastatic head and neck cancer, refractory Hodgkin lymphoma, and urothelial carcinoma, all of which carry positive programmed death-1/programmed death-ligand 1 biomarkers. Therefore, indications of Keytruda significantly expanded. Several types of malignancies are disclosed by MSI-H status due to dMMR and characterized by increased neoantigen load, which elicits intense host immune response in tumor microenvironment, including portions of colorectal and gastric carcinomas. Currently, biomarker-based patient selection remains a challenge. Pathologists play important roles in evaluating histology and biomarker results and establishing detection methods. Taking gastric cancer as an example, its molecular classification is built on genome abnormalities, but it lacks acceptable clinical characteristics. Pathologists are expected to act as “genetic interpreters” or “genetic translators” and build a link between molecular subtypes with tumor histological features. Subsequently, by using their findings, oncologists will carry out targeted therapy based on molecular classification.

关键词： molecular classification precision medicine pembrolizumab PD-1/PD-L1 MSI-H

HTML PDF 收藏

深海钴结壳采集微地形探测技术实验研究

罗柏文,夏毅敏,王韬,白宏峰,王克智

《中国工程科学》 2010年第12卷第9期页码 78-83

摘要：

通过地表高程信息计算最佳采集深度是解决钴结壳开采贫化问题的关键技术之一。根据钴结壳的赋存环境和开采方法，提出了一种摆动式超声单波束微地形探测方法。为了检验该方法的可行性，成功搭建了实验台，并验证了该实验台的垂直探测精度可达到厘米级；提出了一种改进型数据加窗算法，进一步提高了高程异常值被剔除的准确性；提出了采用线性相关系数法解决支持向量线性与非线性回归的选择问题；提出并证明了高斯径向基参数σ可根据测线上的坡度、坡长信息来确定。

关键词：钴结壳超声微地形加窗支持向量

HTML PDF 收藏

An approach for mechanical fault classification based on generalized discriminant analysis

LI Wei-hua, SHI Tie-lin, YANG Shu-zi

《机械工程前沿（英文）》 2006年第1卷第3期页码 292-298 doi: 10.1007/s11465-006-0022-2

摘要： To deal with pattern classification of complicated mechanical faults, an approach to multi-faults classification based on generalized discriminant analysis is presented. Compared with linear discriminant analysis (LDA), generalized discriminant analysis (GDA), one of nonlinear discriminant analysis methods, is more suitable for classifying the linear non-separable problem. The connection and difference between KPCA (Kernel Principal Component Analysis) and GDA is discussed. KPCA is good at detection of machine abnormality while GDA performs well in multi-faults classification based on the collection of historical faults symptoms. When the proposed method is applied to air compressor condition classification and gear fault classification, an excellent performance in complicated multi-faults classification is presented.

关键词： generalized discriminant non-separable abnormality classification multi-faults classification

HTML PDF 收藏

EAI-oriented information classification code system in manufacturing enterprises

WANG Junbiao, DENG Hu, JIANG Jianjun, YANG Binghong, WANG Bailing

《机械工程前沿（英文）》 2008年第3卷第1期页码 81-85 doi: 10.1007/s11465-008-0011-8

摘要： Although the traditional information classification coding system in manufacturing enterprises (MEs) emphasizes the construction of code standards, it lacks the management of the code creation, code data transmission and so on. According to the demands of enterprise application integration (EAI) in manufacturing enterprises, an enterprise application integration oriented information classification code system (EAIO-ICCS) is proposed. EAIO-ICCS expands the connotation of the information classification code system and assures the identity of the codes in manufacturing enterprises with unified management of codes at the view of its lifecycle.

关键词： EAI EAIO-ICCS management classification connotation

HTML PDF 收藏

Fault classification and reconfiguration of distribution systems using equivalent capacity margin method

K. Sathish KUMAR, T. JAYABARATHI

《能源前沿（英文）》 2012年第6卷第4期页码 394-402 doi: 10.1007/s11708-012-0211-0

摘要： This paper investigates the capability of support vector machines (SVM) for prediction of fault classification and the use of the concept of equivalent capacity margin (ECM) for restoration of the power system. The SVM, as a novel type of machine learning based on statistical learning theory, achieves good generalization ability by adopting a structural risk minimization (SRM) induction principle aimed at minimizing a bound on the generalization error of a model rather than the minimization of the error on the training data only. Here, the SVM has been used as a classification. The inputs of the SVM model are power and voltage values. An equation has been developed for the prediction of the fault in the power system based on the developed SVM model. The next steps of this paper are the restoration and reconfiguration by using the ECM concept, the development of a code, and the testing of the results with various load outages, which have been executed for a 12 load system.

关键词： support vector machines (SVM) structural risk minimization (SRM) equivalent capacity margin (ECM) restoration fault classification

HTML PDF 收藏

Progress on molecular biomarkers and classification of malignant gliomas

null

《医学前沿（英文）》 2013年第7卷第2期页码 150-156 doi: 10.1007/s11684-013-0267-1

摘要：

Gliomas are the most common primary intracranial tumors in adults. Anaplastic gliomas (WHO grade III) and glioblastomas (WHO grade IV) represent the major groups of malignant gliomas in the brain. Several diagnostic, predictive, and prognostic biomarkers for malignant gliomas have been reported over the last few decades, and these markers have made great contributions to the accuracy of diagnosis, therapeutic decision making, and prognosis of patients. However, heterogeneity in patient outcomes may still be observed, which highlights the insufficiency of a classification system based purely on histopathology. Great efforts have been made to incorporate new information about the molecular landscape of gliomas into novel classifications that may potentially guide treatment. In this review, we summarize three distinctive biomarkers, three most commonly altered pathways, and three classifications based on microarray data in malignant gliomas.

关键词： malignant glioma molecular biomarker IDH1 MGMT molecular classification

HTML PDF 收藏

Multiclass classification based on a deep convolutional

Ying CAI,Meng-long YANG,Jun LI

《信息与电子工程前沿（英文）》 2015年第16卷第11期页码 930-939 doi: 10.1631/FITEE.1500125

摘要： Head pose estimation has been considered an important and challenging task in computer vision. In this paper we propose a novel method to estimate head pose based on a deep convolutional neural network (DCNN) for 2D face images. We design an effective and simple method to roughly crop the face from the input image, maintaining the individual-relative facial features ratio. The method can be used in various poses. Then two convolutional neural networks are set up to train the head pose classifier and then compared with each other. The simpler one has six layers. It performs well on seven yaw poses but is somewhat unsatisfactory when mixed in two pitch poses. The other has eight layers and more pixels in input layers. It has better performance on more poses and more training samples. Before training the network, two reasonable strategies including shift and zoom are executed to prepare training samples. Finally, feature extraction filters are optimized together with the weight of the classification component through training, to minimize the classification error. Our method has been evaluated on the CAS-PEAL-R1, CMU PIE, and CUBIC FacePix databases. It has better performance than state-of-the-art methods for head pose estimation.

关键词： Head pose estimation Deep convolutional neural network Multiclass classification

HTML PDF 收藏

Modular design of typical rigid links in parallel kinematic machines: Classification and topology optimization

Xinjun LIU, Xiang CHEN, Zhidong LI

《机械工程前沿（英文）》 2012年第7卷第2期页码 199-209 doi: 10.1007/s11465-012-0315-6

摘要：

Due to the demand of reconfigurable system in parallel kinematic machines (PKMs), modular design technology is significant and necessary. However, in earlier research, the core joint modules have been concerned about rather than the customized link modules. The modular design to the typical customized links from the point of seeking optimal structures with best mechanical performances is analyzed and processed in two steps: classification and optimization. Firstly, a brief introduction to the current research status and the aims of this paper are outlined. And then, how the typical customized links classified is proposed. Next, the technology method and the iterative formula derivation process of topology optimization are described in detail. Finally, calculation models for each group of classified ones are set up and their optimal structures are achieved through topology optimization technique. The results provide useful references for reconfigurable and modular design in engineering cases.

关键词： parallel kinematic machines (PKMs) modular design classification topology optimization and improved Guide-Weight method

HTML PDF 收藏

Arthrogryposis multiplex congenita: classification, diagnosis, perioperative care, and anesthesia

null

《医学前沿（英文）》 2017年第11卷第1期页码 48-52 doi: 10.1007/s11684-017-0500-4

摘要：

Arthrogryposis multiplex congenita (AMC) is a rare disorder characterized by non-progressive, multiple contractures. In addition to affected extremities, patients may also present microstomia, decreased temporomandibular joint mobility. Although the etiology of AMC is unclear, any factor that decreases fetal movement is responsible for AMC. Thus, accurate diagnosis and classification are crucial to the appropriate treatment of AMC. The development of ultrasound technology has enabled prenatal diagnosis. Very early treatment is favorable, and multidisciplinary treatment is necessary to improve the function of AMC patients. Most patients require surgery to release contracture and reconstruct joints. However, perioperative care is challenging, and difficult airway is the first concern of anesthesiologists. Postoperative pulmonary complications are common and regional anesthesia is recommended for postoperative analgesia. This review on AMC is intended for anesthesiologists. Thus, we discuss the treatment and perioperative management of patients undergoing surgery, as well as the diagnosis and classification of AMC.

关键词： arthrogryposis amyoplasia distal arthrogryposis anesthesia