To enhance the accuracy and efficiency of bridge damage identification,a novel data-driven damage identification method was proposed.First,convolutional autoencoder(CAE)was used to extract key features from the accele...To enhance the accuracy and efficiency of bridge damage identification,a novel data-driven damage identification method was proposed.First,convolutional autoencoder(CAE)was used to extract key features from the acceleration signal of the bridge structure through data reconstruction.The extreme gradient boosting tree(XGBoost)was then used to perform analysis on the feature data to achieve damage detection with high accuracy and high performance.The proposed method was applied in a numerical simulation study on a three-span continuous girder and further validated experimentally on a scaled model of a cable-stayed bridge.The numerical simulation results show that the identification errors remain within 2.9%for six single-damage cases and within 3.1%for four double-damage cases.The experimental validation results demonstrate that when the tension in a single cable of the cable-stayed bridge decreases by 20%,the method accurately identifies damage at different cable locations using only sensors installed on the main girder,achieving identification accuracies above 95.8%in all cases.The proposed method shows high identification accuracy and generalization ability across various damage scenarios.展开更多
A design strategy for a research platform of a telepresence telerobot system based on virtual reality technology is put forward. The design frame of the system is described, and its important core techniques are descr...A design strategy for a research platform of a telepresence telerobot system based on virtual reality technology is put forward. The design frame of the system is described, and its important core techniques are described. An octrees data structure is utilized to build kinematic and dynamic modeling of the virtual simulation environment, Delphi+OpenGL+3DS MAX are adopted to carry through the virtual modeling and visible simulation exploitation of the slave-robot and its environment. Photo-correction is adopted to correct positioning deviation of the virtual geometric model and modeling errors. The cost of software and hardware equipment for the research platform realized is low. The master/slave robot (manipulator) system and all software in the system were designed and manufactured by our research group. The performance of the system has reached the level required for research. An indispensable experiment base is provided for the research of a telepresence telerobot system based on virtual reality technology.展开更多
The inherent complexity and uncertainty of multi-operator multi-robot （MOMR） tele-operation system make its safeguard an essential problem. Hazardous factors in the system are analyzed using fault tree analysis（FTA...The inherent complexity and uncertainty of multi-operator multi-robot （MOMR） tele-operation system make its safeguard an essential problem. Hazardous factors in the system are analyzed using fault tree analysis（FTA） technology, and three-layer interactive safety architecture with information flow is designed in modules to control the factors according to the holistic control mode. After that, distributed virtual environment （DVE） including the characteristics of virtual guide （VG） technology is discussed to help the operators achieve some tasks through the visibility of control commands, time-delay, movement collision and operators＇ intentions. Finally an experiment is implemented to test the efficiency of safety control architecture by using two robots to place some building blocks in the same workspace.展开更多
We introduce a novel Sermntic-Category- Tree （SCT） model to present the sen-antic structure of a sentence for Chinese-English Machine Translation （MT）. We use the SCT model to handle the reordering in a hierarchic...We introduce a novel Sermntic-Category- Tree （SCT） model to present the sen-antic structure of a sentence for Chinese-English Machine Translation （MT）. We use the SCT model to handle the reordering in a hierarchical structure in which one reordering is dependent on the others. Different from other reordering approaches, we handle the reordering at three levels： sentence level, chunk level, and word level. The chunk-level reordering is dependent on the sentence-level reordering, and the word-level reordering is dependent on the chunk-level reordering. In this paper, we formally describe the SCT model and discuss the translation strategy based on the SCT model. Further, we present an algorithm for analyzing the source language in SCT and transforming the source SCT into the target SCT. We apply the SCT model to a role-based patent text MT to evaluate the ability of the SCT model. The experimental results show that SCT is efficient in handling the hierarehical reordering operation in MT.展开更多
Finding the optimum solution for dispatching in concrete delivery is computationally intractable because it is a NP-hard （non-deterministic polynomial-time hard） problem. Heuristic methods are required to obtain sat...Finding the optimum solution for dispatching in concrete delivery is computationally intractable because it is a NP-hard （non-deterministic polynomial-time hard） problem. Heuristic methods are required to obtain satisfactory solutions. Inefficiencies in mathematical modeling still make concrete dispatching difficult to solve. In reality, complex dispatching systems are mostly handled by human experts, who are able to manage the assigned tasks well. However, the high dependency on human expertise is a considerable challenge for RMC （ready mixed concrete） companies. In this paper, a logical reconstruction of an expert＇s decision making is achieved by two machine learning techniques： decision tree and rule induction. This paper focuses on the expert dispatcher＇s prioritization of customer orders. The proposed method has been tested on a simulation model consisting of a batch plant and three customers per day. The scenarios generated by the simulation model were given to a dispatch manager who was asked to prioritize the customers in each day. The scenarios and the decisions were then input to the machine learning programs, which created generalizations of the expert＇s decisions. Both decision trees and rules approach 80% accuracy in reproducing the human performance.展开更多
文摘针对环境复杂的区域,高大树木、复杂地形等问题容易造成用电危险,而传统的人工清理树障的方法易造成安全事故,我国现有研发的机器人具有空中姿态控制不稳定以及数据传输不稳定等问题,对树障清理空中机器人进行了设计和实现.该机器人的结构组成主要包括多旋翼无人机、控制系统、远程监控系统、通信系统和刀具装置.通过确定地面坐标系和无人机坐标系的关系,建立空中机器人的动力学模型.充分考虑环境等因素对空中机器人传感器采集数据的影响,建立了传感器的数据融合算法,对传感器采集数据进行处理.采用PID(Proportion Integral Differential)控制方法对空中机器人的姿态控制器进行设计.为了验证该树障清理空中机器人的性能,对其进行了姿态控制试验和树障清理试验.试验结果表明机器人的姿态控制响应时间较短,最短可达1.2 s.在进行树障清理时,最大可清理树障直径约为4 cm,切割最长时间为3 s.
文摘树障清理空中机器人的刀具系统在进行切割作业时存在负载扰动,且刀具电机的电机参数会有摄动情况的发生,若使用常规的双闭环 PI控制,会存在动态性能欠佳、超调大、适应性差等不足,而且在给定转速突变的情况下可能会导致 Windup现象。针对以上问题,为防止给定突变时产生 Windup现象,电流环控制器采用了一种在反计算 Anti Windup方法基础上改进的变结构 Anti Windup PI控制方法。为提高系统的自适应能力,将模糊控制思想与PID控制思想相结合,设计了转速环的模糊 PID自适应控制器。最后通过仿真与实物实验对提出的控制器的可行性进行验证。结果表明,控制器对系统参数变化有很强的自适应能力,且对负载的扰动有很强的抑制能力,给定转速突变时系统有较快的动态响应且超调较小。
基金The National Natural Science Foundation of China(No.52361165658,52378318,52078459).
文摘To enhance the accuracy and efficiency of bridge damage identification,a novel data-driven damage identification method was proposed.First,convolutional autoencoder(CAE)was used to extract key features from the acceleration signal of the bridge structure through data reconstruction.The extreme gradient boosting tree(XGBoost)was then used to perform analysis on the feature data to achieve damage detection with high accuracy and high performance.The proposed method was applied in a numerical simulation study on a three-span continuous girder and further validated experimentally on a scaled model of a cable-stayed bridge.The numerical simulation results show that the identification errors remain within 2.9%for six single-damage cases and within 3.1%for four double-damage cases.The experimental validation results demonstrate that when the tension in a single cable of the cable-stayed bridge decreases by 20%,the method accurately identifies damage at different cable locations using only sensors installed on the main girder,achieving identification accuracies above 95.8%in all cases.The proposed method shows high identification accuracy and generalization ability across various damage scenarios.
文摘A design strategy for a research platform of a telepresence telerobot system based on virtual reality technology is put forward. The design frame of the system is described, and its important core techniques are described. An octrees data structure is utilized to build kinematic and dynamic modeling of the virtual simulation environment, Delphi+OpenGL+3DS MAX are adopted to carry through the virtual modeling and visible simulation exploitation of the slave-robot and its environment. Photo-correction is adopted to correct positioning deviation of the virtual geometric model and modeling errors. The cost of software and hardware equipment for the research platform realized is low. The master/slave robot (manipulator) system and all software in the system were designed and manufactured by our research group. The performance of the system has reached the level required for research. An indispensable experiment base is provided for the research of a telepresence telerobot system based on virtual reality technology.
文摘The inherent complexity and uncertainty of multi-operator multi-robot （MOMR） tele-operation system make its safeguard an essential problem. Hazardous factors in the system are analyzed using fault tree analysis（FTA） technology, and three-layer interactive safety architecture with information flow is designed in modules to control the factors according to the holistic control mode. After that, distributed virtual environment （DVE） including the characteristics of virtual guide （VG） technology is discussed to help the operators achieve some tasks through the visibility of control commands, time-delay, movement collision and operators＇ intentions. Finally an experiment is implemented to test the efficiency of safety control architecture by using two robots to place some building blocks in the same workspace.
基金supported by the National High Technology Research and Development Program of China under Grant No.2012AA011104the Fundamental Research Funds for the Center Universities
文摘We introduce a novel Sermntic-Category- Tree （SCT） model to present the sen-antic structure of a sentence for Chinese-English Machine Translation （MT）. We use the SCT model to handle the reordering in a hierarchical structure in which one reordering is dependent on the others. Different from other reordering approaches, we handle the reordering at three levels： sentence level, chunk level, and word level. The chunk-level reordering is dependent on the sentence-level reordering, and the word-level reordering is dependent on the chunk-level reordering. In this paper, we formally describe the SCT model and discuss the translation strategy based on the SCT model. Further, we present an algorithm for analyzing the source language in SCT and transforming the source SCT into the target SCT. We apply the SCT model to a role-based patent text MT to evaluate the ability of the SCT model. The experimental results show that SCT is efficient in handling the hierarehical reordering operation in MT.
文摘Finding the optimum solution for dispatching in concrete delivery is computationally intractable because it is a NP-hard （non-deterministic polynomial-time hard） problem. Heuristic methods are required to obtain satisfactory solutions. Inefficiencies in mathematical modeling still make concrete dispatching difficult to solve. In reality, complex dispatching systems are mostly handled by human experts, who are able to manage the assigned tasks well. However, the high dependency on human expertise is a considerable challenge for RMC （ready mixed concrete） companies. In this paper, a logical reconstruction of an expert＇s decision making is achieved by two machine learning techniques： decision tree and rule induction. This paper focuses on the expert dispatcher＇s prioritization of customer orders. The proposed method has been tested on a simulation model consisting of a batch plant and three customers per day. The scenarios generated by the simulation model were given to a dispatch manager who was asked to prioritize the customers in each day. The scenarios and the decisions were then input to the machine learning programs, which created generalizations of the expert＇s decisions. Both decision trees and rules approach 80% accuracy in reproducing the human performance.
