Artificial Intelligence and Robotics Commons^™

Study On Optimization Of Loading Plan In Car Carrier Of Vehicle Logistics Transportation, Qin Liang, Zhicheng Wang, Meng Lei, Deru Deng, Zhiyun Zou, Xijie Gai, Yuqing Guo, Wenqiang Feng

Journal of System Simulation

Abstract: The car carrier load transportation allocation problem is a typical problem in vehicle logistics. In order to improve the efficiency of transport and reduce the cost, this problem was studied by adopted hypothetical data and requirements. All the load combinations whose utilization factor of the length of sweeping board is more than 95% established a matrix. Then the dynamic programming obtained the number of car carrier to the corresponding loading plan. By using the exhaustion method, through computer simulation, loading plan of each layer of car carrier was randomly produced, strictly meeting the loading requirements of each car at …

Simulation And Application Of Dkipso-Svc Combined Model For Credit Risk Assessment, Zhenhai Wan, Tieying Liu, Zhang Yang, Jishuang Li

Journal of System Simulation

Abstract: In order to improve the problem of inefficient parameter selection of the GDS-SVC model and DIPSO-SVC model, and utilize the generalization ability and robustness of support vector classification (SVC), the reduction factor of location updating was introduced based on the dynamic improvement Particle Swarm Optimization (DIPSO), and then the DKIPSO-SVC of parameters selecting in SVC was established based on DKIPSO. The method was applied to credit scoring of commercial banks. The simulation results demonstrate that the robustness of the DKIPSO-SVC model is better than DIPSO-SVC. But beyond that, the accuracy of DKIPSO-SVC model achieves 96.6049%, higher than that of …

Application Of Ansys To Reliability Analysis Of Prefabricated Steel Bridge, Yinlong Zhang, Li Bo, Shichuan Bian

Journal of System Simulation

Abstract: Prefabricated steel bridge is a temporary or semi-permanent bridge structure. When the vehicles pass through the bridge, large internal force and deformation of the bridge structure will occur, and higher requirements of the bridge structure reliability are put forward. Probabilistic analysis design is an analysis technique for assessing the effect of uncertain random input parameters and assumptions on a finite element calculation model. Making use of the Probabilistic Design System, which is offered by the large universal finite element analysis program ANSYS, the reliability analysis of deflection, bend stress and compression member stability of a main truss structure of …

New 2d Flow Visualization Method Based On Mutual Information And Image Fusion, Weihua Shen, Shengbo Wang, Zhigeng Pan

Journal of System Simulation

Abstract: A overview of flow visualization method based on information theory was made. After a comparative analysis of several classic two-dimensional flow visualization techniques, the concept of mutual information from information theory and image fusion technique was used to deal with the existing classical two-dimensional flow visualization techniques. A new two-dimensional flow visualization technique was obtained. The visualization results of the new method is very well.

Technical Reference Framework For Semantic Interoperation Between Combat Simulation Systems And Command & Control Systems, Xiangzhong Xu, Zaijiang Tang, Yaxin Tan

Journal of System Simulation

Abstract: Military training, equipment demonstration, war-fighting test and other applications pose great requirements on the semantic interoperation between combat simulation systems and command & control (C2) systems. The heterogeneity between combat simulation and C2 systems was analyzed from the following aspects, such as architecture, information interaction models, communication protocols and databases. Then a layered technical reference framework was proposed to solve this thorny issue in a comprehensive way, which consists of accession layer, resource layer, semantic interaction layer, service layer and application layer. Its effectiveness was demonstrated against an application use-case. Research results are helpful to make out an engineering …

Design & Implement On Virtual Scheduling System Of Great Square Art Performance, Lv Desheng, Guo Yan

Journal of System Simulation

Abstract: The work of great art performance in square has a great deal of dynamic visual effects scenes, which combines with formation variation, beautiful music, unique clothing and colorful light. According to the requirements of improving efficiency for scheduling section in handwork performance such as inefficient manual drawing, time-consumed and costly rehearsal, it is an effective way to use technology of computer simulation so as to implement real-time and dynamic intermediary platform among performer, director and audience. To meet various demands in practice, a vision-based formation generation was proposed that the path construction was studied based on linear fitting, …

Review On Interoperability Of Command Information System And Combat Simulation System, Zaijiang Tang, Xiangzhong Xu, Xue Qing, Haohua Xu

Journal of System Simulation

Abstract: The interoperability of command information system and combat simulation system is an important and difficult problem of building practical training environment. The four aspects of interoperability connotation were summarized. The demands of interoperability were analyzed. The status and development of interoperability, especially for C⁴ISR/Sim Technical Reference Model (TRM), Battle Management Language (MBL), Levels of Conceptual Interoperability Model (LCIM) were studied. The existing problems were summarized, and four kinds of solutions were proposed. The general technical framework of interoperability based on service oriented architecture was designed, and the interoperability solving method based on Ontology was given.

Total Least-Squares Algorithm For Wiener Errors-In-Variables System Modeling, Ziyun Wang, Zhicheng Ji

Journal of System Simulation

Abstract: The modeling problem of Wiener errors-in-variables systems was investigated where measurements of the system input and output were corrupted by the additive white Gauss noise. After the provided reformulation of the errors-in-variables system, a two-stage algorithm was developed to estimate the unknown parameters with the first stage employing the total least-squares algorithm, followed by a singular value decomposition in the second stage. The asymptotic maximum likelihood estimation property under the PE condition was strictly proven that with data length tends to infinite, and the proposed total least-squares solution provided an asymptotic maximum likelihood estimate for the nonlinear system parameter …

Molecular Dynamics Of Fluid Properties By Normal Oscillations Of Solid Wall, Haijun Dong, Xiaoqing Lu, Haopeng Zhang, Mingming Shan

Journal of System Simulation

Abstract: The fluid properties under the condition of the solid wall normal oscillations were studied using the molecular dynamics method. The two dimensional Couette flow model made up of copper wall and argon fluid was built. The fluid state of the near wall was simulated under the different oscillation parameters of solid wall and the corresponding fluid velocity field, the density distribution, the potential energy curves and the friction force were obtained. Then the influence mechanism of the wall oscillations on the frictional drag at liquid-solid interface was investigated. The results indicate that the frictional drag between wall and fluid …

Novel Method To Identify Pmsm Parameters Based On Multiple Linear Regressive Models, Zhenwei Shi, Zhicheng Ji

Journal of System Simulation

Abstract: A New Coupled Recursive Least Squares (C-FF-RLS) Algorithm with a forgetting factor was proposed for the Parameters Identification of Permanent Magnet Synchronous Motors (PMSMs). The deduced multiple linear regressive models of PMSM were proposed that were simple and appropriate for parameter identification. The C-FF-RLS identification algorithm had a high computational efficiency and a fast convergence speed because which Avoided the Matrix Inversion Operation in the Gain Matrix Compared with the Traditional Multivariable Recursive Least Squares (M-FF-RLS) Algorithm with a Forgetting Factor. The Proposed Identification Algorithm was applied on a simulation system of PMSM. The identification results achieved by …

Guidance Simulation Credibility Evaluation Based On Clustering With Grey Cloud And Entropy Weight, Wang Fei, Xiaogeng Liang, Guo Chao, Peipei Li

Journal of System Simulation

Abstract: Considering the problems of randomness and fuzziness in evaluating indexes from guidance simulation system, a novel grey clustering comprehensive evaluation model combined with center normal grey cloud whitening function and combination weighting function was presented. The comprehensive credibility evaluation index system for guidance simulation was built. The subjective weight vector of indexes was established by weighting cloud model based on analytic hierarchy process, the objective weight vector of indexes was obtained by entropy weighting method based on the entropy and classified distinction of the normal grey cloud whitening function, then the comprehensive weight vector was acquired by fusing the …

Modeling And Analysis Of Command Control System Based On Devs, Xinlong Li, Xiang Mao

Journal of System Simulation

Abstract: A comprehensive discussion was made on the application of DEVS theory in the modeling of command control (C2) system, which introduced the mathematical model of DEVS, gave the principle of using DEVS to model the C2's behavior and analyze how capability-requirement-measurements effected the simulation. The process and approach of DEVS-Modeling battalion's C2 system were introduced.

Research On Live Migration Scheduling Method For Communication Network Simulation System Based On Vmotion, Yanfang Fu, Gao Xiang, Cheng Bing, Xueyao Feng

Journal of System Simulation

Abstract: In order to make the quality of the simulation service not being affected by load dynamic changes, heuristic scheduling algorithm was proposed. Using the VMotion technology, the virtualization simulation platform was created by calling the SDK. Through the research of the simulation platform application overhead and virtual resource scheduling technology, the single communication network simulation model was modified, implementing the distributed network collaborative simulation which adapted to multiple virtual machines, providing new ideas for the mass communication network simulation system.

Design Of Navigation Electronic Interference System For Flight Simulator, Zengbo Zhou, Chen Xi, Zhenyu Sun, Li Xiang

Journal of System Simulation

Abstract: Modern military combat pays more attention to the electronic interference and anti interference, as the important component, the aircraft navigation system is one of the main objects attacked by enemy electronic jamming. In order to simulate the electronic jamming influence on navigation performance of the system, the establishment of an electronic jamming system in aircraft engineering simulator, was designed for the flight simulator interference model and statistical model frame work, and according to the integrity of the system testing and calculation results, the interference was divided into five levels, which not only specified the electrical interference, but also …

Self Formation Development Mode With Vopes, Changming Fu, Chunsheng Long, Tang Hong

Journal of System Simulation

Abstract: To solve the growing conflict between requirements and applications in simulation/visualization, self-formation development mode was proposed: domain experts DIY by WYSWYG in a self-adapting process. VOPES (Visual Open platform for Engineering System) was briefly introduced: integrated architecture, system modeling tools, visualization tools, automatic generation, debugging, deploying, and runtime infrastructure. VOPES enables domain expert to produce distributed simulation/visualization application, no need of coding, complex program skill, hard rules like UML, HLA, DDS, etc. VOPES can be widely used in applications like mission simulation, equipment demonstration, virtual range, training, ITEM. It is especially suitable to the fast, agile, complex simulation/visualization application, …

Design Of Drilling Jumbo Simulation Training System Based On Vega Prime, Youcai Wang, Zilong Guo, Xinhai Xiang, Honghai Luan

Journal of System Simulation

Abstract: A drilling jumbo simulation training system was developed based on the Vega Prime in the MFC framework. The interactive communication control platform was built based on PCI bus, and then multithreading technology was adopted to achieving the Synchronous data communication between acquisition card and computer. A variety of modeling software was studied to aid Creator modeling method, and then the motion simulation of the drilling jumbo double-arm realization method based on DOF nodes was studied, which realized the real-time dynamic interaction of the system. By using the active 3d stereo imaging principle, the realization method of 3d stereo display …

Boiler Combustion Optimization Based On Bayesian Neural Network And Genetic Algorithm, Haiquan Fang, Huifeng Xue, Li Ning, Fei Xi

Journal of System Simulation

Abstract: Neural network and genetic algorithm have been extensively used in boiler combustion optimization problems. But the traditional Back Propagation neural network's generalization ability is poor. The Bayesian regularization can improve the neural network's generalization ability. A boiler combustion multi-objective optimization method combining Bayesian regularization BP neural network and genetic algorithm （Bayes NN-GA）was researched. A number of field test data from a boiler was used to simulate the Bayesian neural network model. The results show that the thermal efficiency and NOx emissions predicted by the Bayesian neural network model show good agreement with the measured, and the optimal results show …

Attitude Control Of Three-Axis Flexible Satellite Based On Active-Disturbance-Rejection Sliding Mode Method, Yunjie Wu, Li Chen, Ma Zheng

Journal of System Simulation

Abstract: By using Kane method, a mathematical model with CMGs as actuators was built for the three-axis satellite with flexible appendages. An active-disturbance-rejection sliding mode controller was designed for the demand about quickness and stability in attitude control. This controller observed the disturbance by expanded state observer, and compensated the output. The slide mode method in the controller made the system quick and stable. The simulation experiments show that the controller could control the attitude of three-axis satellite efficiently and weaken the vibration of flexible solar panel. The active-disturbance-rejection sliding mode controller shows the merits of both active-disturbance-rejection method …

Least-Energy Maneuver Of Five-Link Manipulator Constrained Within Tunnel Space Using Direct Collocation, Xiuqiang Pan, Chengcai Mei, Junjie Chen

Journal of System Simulation

Abstract: Optimal control and designs least-energy maneuver control laws for a five-linked manipulator were applied in order to carry out designated tasks in a confined space. Lagrange-Euler equation described the relationships between the actuators and system dynamics. Euler-Lagrange formulation indicates how optimization can be achieved when optimum occurs. Direct collocation method was introduced in order to solve this highly nonlinear dynamic optimal control problem. Simulations were done to exploit how the manipulator reacted to the constraint. In this study, the diameter of the cylindrical space was shrunken each time by 0.1 meters. The value of the cost function and …

Research Of Multi-Views Based Weapon And Equipment Simulation Model Architecture, Chunguang Peng, Jianhui Deng, Zhang Bo

Journal of System Simulation

Abstract: ：It's an important approach to build reasonable and complete simulation model architecture for promoting the simulation interoperability, establishing simulation model standards and promoting reusability of models and codes. Some problems existed in the research of simulation model architecture were analyzed. The weapon and equipment simulation model architecture describing method based on multi-views was brought out by using the system engineering theory, which emphasized on the complicated relations between modes and its environment. The method could describe simulation model architecture from different views of different users. Therefore, based on DoDAF and the popular software architecture, five-view models of weapon …

Research On Equipment Operation Capabilities Requirements Based On Exploratory Simulation Experiment Methodology, Zongrui Yan, Yinhua Wu, Chen Yong, Jianshu Dong

Journal of System Simulation

Abstract: Analysis on equipment operation requirements is a very difficult problem which has included a lot of uncertain factors, and it can assist peoples to determine whether the equipment item should be started. Exploratory simulation experiment methodology which is synthetized by exploratory analysis and war fighting experimentation can provide a better service for many problems about the equipment demonstration. Through the summary on basic applications exploratory simulation experiments related out comes and its analysis for concrete implementation steps equipment demonstration areas, a tactical level exploratory simulation methodology and its concrete implementation steps were proposed for the operational requirements analysis. An …

Research And Development Of Eicas System Emulator Based On Idata, Baoming Zhao, Hongshu Cheng, Cancan Liu, Jiying Li

Journal of System Simulation

Abstract: Some modeling tools can't design simulation instruments efficiently and conveniently such as OpenGL, etc. A cockpit display development tool of IData was worked in which has graphical user interface and could develop a system easily and rapidly. IData is a method of designing maps and pictures, it can respond variables of application and controlling events in real time and develop graphical interface by clicking on the menu. So IData can reduce the time of graphic development and integration in simulation. In order to render maps in real time, IData used a powerful graphic editor to model for instruments, and …

Diagnosis Of Aircraft Control Surface Fault Based On Semi-Physical Simulation, Yunlong Li, Xia Jie, Zifang Shi

Journal of System Simulation

Abstract: The aircraft control surface defaults of rudders were mainly divided into jam fault and damage fault. On the basis of the relationship between motor toque and hinge moment, a new method of using the motor voltage was proposed to detect the control surface'faults of rudder. And the method could detect the damage degree of the faults. Torque motor was used to play the role of hinge moment. And the new method was simulated by Semi-Physical system which is consisted of dSPACE system, PC and simulated rudder actuator. The results show that, the damage faults and jam faults can be …

Research On Scenario-Driven Component-Based Model Composition Method, Jianchun Zhang, Fengju Kang

Journal of System Simulation

Abstract: To fulfil the requirements for fast, easy and integrated modeling under certain operation conditions, a model composition method of scenario-driven was proposed. Starting with corresponding composition framework, traditional component models were extended through corresponding meta-model and normalization description of scenario was given. Furthermore, a full combat simulation system could be constructed quickly by realizing integrated process including three processes: scenario parse, model search and match. By preliminarily performing underwater weapon system modeling and simulation application, the result shows efficiency of this composition method.

A Study Of Information Bots And Knowledge Bots, Amartya Hatua

Dissertations

In this dissertation, a study of different aspects of information bots and knowledge bots is done. The research contributes to a better understanding of the various characteristics of information bots as well as the different patterns and factors responsible for the information diffusion in a social network. This research also shows how these factors can be used to predict information diffusion for a particular topic in a social network. The second part of the research is focused on strategies for improving the knowledge base of knowledge bots, where two different approaches are studied. In the first approach, knowledge is transferred …

Empirical Studies Of Deep Learning On Information Diffusion On Social Networks And Collective Task Learning For Swarm Robotics, Trung T. Nguyen

Dissertations

Researchers in multiple disciplines have recently adopted deep learning because of its ability of high accuracy representation learning from big and complex data. My research goal in this thesis is developing deep learning models for information diffusion analysis on social networks and collective tasks learning in swarm robotics. Firstly, the information diffusion on social networks is modeled as a multivariate time series in three dimensions with ten features. Then, we applied time-series clustering algorithms with Dynamic Time Warping to discover different patterns of our models. Then, we build a prediction model based on LSTM, which outperforms traditional time-series prediction methods. …

A 3d Image-Guided System To Improve Myocardial Revascularization Decision-Making For Patients With Coronary Artery Disease, Haipeng Tang

Dissertations

OBJECTIVES. Coronary artery disease (CAD) is the most common type of heart disease and kills over 360,000 people a year in the United States. Myocardial revascularization (MR) is a standard interventional treatment for patients with stable CAD. Fluoroscopy angiography is real-time anatomical imaging and routinely used to guide MR by visually estimating the percent stenosis of coronary arteries. However, a lot of patients do not benefit from the anatomical information-guided MR without functional testing. Single-photon emission computed tomography (SPECT) myocardial perfusion imaging (MPI) is a widely used functional testing for CAD evaluation but limits to the absence of anatomical information. …

Applications Of Artificial Intelligence And Graphy Theory To Cyberbullying, Jesse D. Simpson

Graduate Theses/Dissertations

Cyberbullying is an ongoing and devastating issue in today's online social media. Abusive users engage in cyber-harassment by utilizing social media to send posts, private messages, tweets, or pictures to innocent social media users. Detecting and preventing cases of cyberbullying is crucial. In this work, I analyze multiple machine learning, deep learning, and graph analysis algorithms and explore their applicability and performance in pursuit of a robust system for detecting cyberbullying. First, I evaluate the performance of the machine learning algorithms Support Vector Machine, Naïve Bayes, Random Forest, Decision Tree, and Logistic Regression. This yielded positive results and obtained upwards …

Secure Mobile Computing By Using Convolutional And Capsule Deep Neural Networks, Rui Ning

Electrical & Computer Engineering Theses & Dissertations

Mobile devices are becoming smarter to satisfy modern user's increasing needs better, which is achieved by equipping divers of sensors and integrating the most cutting-edge Deep Learning (DL) techniques. As a sophisticated system, it is often vulnerable to multiple attacks (side-channel attacks, neural backdoor, etc.). This dissertation proposes solutions to maintain the cyber-hygiene of the DL-Based smartphone system by exploring possible vulnerabilities and developing countermeasures.

First, I actively explore possible vulnerabilities on the DL-Based smartphone system to develop proactive defense mechanisms. I discover a new side-channel attack on smartphones using the unrestricted magnetic sensor data. I demonstrate that attackers can …

Deep Learning For Remote Sensing Image Processing, Yan Lu

Computational Modeling & Simulation Engineering Theses & Dissertations

Remote sensing images have many applications such as ground object detection, environmental change monitoring, urban growth monitoring and natural disaster damage assessment. As of 2019, there were roughly 700 satellites listing “earth observation” as their primary application. Both spatial and temporal resolutions of satellite images have improved consistently in recent years and provided opportunities in resolving fine details on the Earth's surface. In the past decade, deep learning techniques have revolutionized many applications in the field of computer vision but have not fully been explored in remote sensing image processing. In this dissertation, several state-of-the-art deep learning models have been …