Proceedings of the 2018 International Conference on Advanced Control, Automation and Artificial Intelligence (ACAAI 2018)
Selection and Optimization of Structures of Double Screw Conveyors
Enliang Dai, Hui Wan, Bin Jian, Guoming Hu
The screw conveyor with no overlap between two screw blades and the screw conveyor with large overlap between two screw blades were simulated by discrete element method and the distribution of particle axial velocity, angular velocity, forces around the shell and forces around screw blades was carried...
Motion Control Realization for an Intelligent Car with Integrity Constraints
In order to realize the obstacle avoidance and tracking movement function of the 3-wheeled intelligent car with integrity constraints, the kinematics model of the car is derived first, and the control of the speed of the car-driven DC motor, i.e. the wheel speed, is realized by using the PWM control...
Bionic Spider Robot Control Based on Image Processing Algorithm
Qingsheng Shi, Cheng Wei, Ke Lu
Compared to wheeled and tracked robots, bionic robots are playing an increasingly important role in search, rescue, anti-terrorism and scientific investigation. The vision processing system is the vital part of the bionic robot system, and its algorithm determines the overall control performance of the...
Research on Recovery Strategy and Motion Control for Autonomous Underwater Vehicle
Yushan Sun, Lifeng Wang, Xiangrui Ran, Guocheng Zhang
During the recovery of AUV, the hydrodynamic power of the hull becomes intricate due to the presence of the submarine. It's unable to accurately obtain the forces and moments in all degrees of freedom. In this paper, we put forward the plan of traversing, depth control and path planning for complex hydrodynamic...
ESN-based Combination Method for Turbine Condition Prediction
Yanyan Liu, Yangming Guo, Aihua Wang
As a nonlinear time series prediction method, echo state network (ESN) attracts more attention because of its good approximation capability for the nonlinear system. Aiming at the characters of nonlinear time series in the Turbine's condition prediction analysis, such as including noise and presenting...
Design and Numerical Simulation of the Ejector of Pneumatic Conveying System
Zhenhui Luan, Xu Zhang, Meng Zheng
Ejector is an important component of pneumatic conveying system and has important influence on the performance of pneumatic conveying system. For the design of the ejector, the system back pressure is generally calculated according to the layout of the pipeline, thus the ejector structure is pushed....
Wind Turbine Tower Mode Analysis Considering Blade and Centrifugal Stiffening Effect
Wenxing Xiao, Tao Yang
In order to study the influence of wind turbine blade and the blade centrifugal stiffening effect on natural vibration characteristics of wind turbine tower, the finite element model of wind turbine tower was established. By calculating the axial force under the rotating state of the blade, the additional...
Flow Stress Calculation of IN718 Alloy for Hot Continuous Rolling Process
Wentao Wang, Han Li, Ke Zhang, Fengli Sui
A flow stress calculation model considering the interval softening was established based on the the single- and double-hit true stress-strain curves of IN718 alloy for multiple-pass hot continuous rolling process. The data calculated by the single-hit flow stress model and the double-hit softening fraction...
Research on Train Wheel Diameter Correction Based on Multi - sensor Fusion and Gray - Scale Prediction
Teng Zhong, Shenghua Dai
Multi-sensor fusion is an effective way to realize low-cost and high-precision positioning on train. And Kalman filter algorithm is easy to be applied in the computer, so it is one of the important research directions of information fusion. This paper studies on the odometer in multi-sensor fusion system...
Research on Structural Order Degree of Armored Vehicle PHM System Based on the Structural Entropy
Yuanhong Liu, Qian Yan, Dongli Duan
The PHM (Prognostic and Health Management) system structure of armored vehicle has a very important influence on the reliability, security, mission success and life cycle cost of armored vehicle system. In view of the lack of scientific evaluation method for armored vehicle PHM system structure, a structural...
Research on Cable-driven Robots
Yupeng Deng, Long Bai, Zhang Long, Jian Guan, Xiaohong Chen, Junzhan Hou, Wenbo Duan
Cable-driven mode has the advantages of low inertia, low noise, high accuracy and some other unique advantages in some occasions. Therefore, the application of cable-driving technology in robots is more and more extensive. Many researchers have also carried out in-depth researches and discussions on...
NUCLEI: A New Unmanned Aerial Vehicle Early Warning Method for the No-fly Zone
Jiaming Wang, Bailong Yu, Zhifang Ma, Shenglan Yang, Li Lu, Wei Yang
In order to monitor the unmanned aerial vehicle(UAV) around the no-fly zone, we proposed a new unmanned aerial vehicle Early warning method for the no-fly zone (NUCLEI) which gives an alarm to the UAV around the no-fly zone in real time. We utilize the least square method to match with the flight trajectory...
Research on Servo System of Permanent Magnet Synchronous Motor Based on Model Design
Xin Jin, Tao Zhang, Hualiang Zhang, Peng Zeng, Anna Wang
The increasing demands of modern industry for motor control make the software more and more complex. The simulation platform and the hardware test platform in traditional control system of permanent magnet synchronous motor (PMSM) are often independent of each other. This paper aims to simplify the PMSM...
Real-time Positioning Measurement using Intelligent Shoes
Yahong Li, Wanyan Guo, Jingzhe Fang, Shujie Sun
The elderly travel safety has attracted more and more attention, this paper studies a real-time positioning measurement using intelligent shoes system that can locate the position information of the elderly in real time. The project is a positioning system integrated in the bottom of the heel part of...
Guidance System Based on Image Processing
Dahai Yu, Manman Shen
To solve the problem of blind travel, a guide system based on image processing is designed. The visual information collected by a CCD camera. The voice information is used to communicate with the user. The overall design of this system is given. Recognize the zebra line by the bipolar system value. Recognize...
Foggy Day Image Sharpening Algorithm Based on Depth of Field Estimation
Changli Li, Qian Jia
Traditional dehazing methods always use the dark channel a priori method to recover the original image, which leads to the calculation of the transmission is large and takes too much time. Therefore, in this paper, we present a fog-day-based image sharpening algorithm based on depth of field estimation....
A Study on Arc Image Acquisition and Spectrum Inspection for Welding Process Surveillance
Yirong Zou, Jiajun Liu, Zheming Wu
This paper proposes a method for welding process surveillance, using the CCD camera and the spectrograph for the acquisition of the welding arc image and the spectral information. The spectral information inferred the temperature distribution and the metallic vapor density in the welding arc space. The...
Context-aware Pedestrian Detection with Salient Region Self-growing in Far-infrared Images
Hao Sheng, Meiyuan Liu, Yanwei Zheng, Yang Liu
In this paper, we present a new framework to detect pedestrians in infrared images. The framework consists of a candidate generation module and a classification module, both of which are implemented based on convolution neural network. Specifically, we learned effective segmentation threshold by deep...
Disease Edge Detection of Medical CT Image Using Digital Wavelet Filter
Woon Cho, Daewon Chung, Yuhan Wu, Joonhyeon Jeon
The aim of this study is detecting disease edge of the medical CT (Computed Tomography) image. This paper describes the method by using 3-Tap bandpass filter signal and two high frequency sub-band CT images in wavelet domain for detecting part of disease. Simulation result show that the proposed method...
Classification Analysis of the Auditory Cognitive States for Sighted and Blind People Based on a Whole-brain "Searchlight" SVM
Jianlong Zheng, Junhai Xu
When talking about auditory perception, it remains unclear how people could achieve sound identification and localization efficiently even in the middle of chaos. Though the dual-pathway model is widely held, there are still controversies in specific brain regions. Moreover, some machine learning methods...
Person Re-Identification Based on Data Prior Distribution
Yancheng Wu, Hongchang Chen, Shaomei Li, Chao Gao, Hongxin Zhi, Yuchao Jiang, Yanchuan Wang
In order to solve the problem of insufficient accuracy of the existing person re-identification methods. We propose a neural network model for identifying pedestrian properties and pedestrian ID. Compared with the existing methods, the model mainly has the following three advantages. First, our network...
An Efficient Method of Face and Keypoint Detection Based on Shared Network
Xiaogang Tian, Xiaoye Fan, Feixue Tang, Xixin Cao
We propose a method to perform face detection and facial keypoint detection in parallel. On the basis of the traditional object detection framework Faster R-CNN for face detection, we have designed a facial keypoint detection network with the same base network. And the two networks share the weights...
An Ensemble Method of Global and Local Representation for Face Recognition
To aim at the challenge of face recognition to uncontrolled situations, an ensemble method of global and local representation for face recognition is presented in this paper. shearlets transform is firstly employed to decompose a image into subimages. Then directional information is utilized along with...
Single Image Super-Resolution Based on Improved WGAN
Lei Yu, Xiang Long, Chao Tong
SRGAN has successfully applied the Generative Adversarial Network to the single image super-resolution reconstruction, which has achieved good results. But the loss function based on feature space in SRGAN objectively sacrifices the pursuit of high peak signal-to-noise-ratio (PSNR), which is the result...
Multi-Spectral Stereo Image Matching Based On Adaptive Window
Bin Yan, Xiangshan Kong, Fuyou Jiang, Peng Xu, Hui Yuan
In the multi-spectral image registration, because of the different imaging mechanism, the distribution of image's pixel gray value is non-linear. So the traditional matching algorithm based on gray correlation and image feature cannot be used simply. Since the mutual information measure does not need...
A Neural Dynamics and Oscillator Interference Mixed Model of the Grid Cells for Spatial Recognition
Naigong Yu, Ziwei Luo, Yujia Zhai
Grid cells in the MEC (media entorhinal cortex) of rats show repetitive hexagon firing pattern while moving through the environment. In the deeper layer of the MEC, a kind of interneurons have both the head-directing (HD) and grid-like firing properties. The predecessors' observations indicate the grid...
A Fast Method for Measuring Kinematic Parameters of Experimental Vehicle Based on Machine Vision
Zi Liang, Tao Wang
The vehicle kinematic parameter is important evaluation index of vehicle performance. But the measurement technique for vehicle kinematics parameters is still immature. Practical and efficient measuring system is now in badly demand. With the development of machine vision technique, more and more measurement...
EEG-based Emotion Word Recognition
Weiwei Dong, Panpan Wang, Yazhou Zhang, Tianshu Wang, Jiabin Niu, Shengnan Zhang
Emotion recognition rapidly gains interest from research community, which gives computer the ability to recognize, understand, express, and adapt to human emotions to help computer more intelligent. Traditional emotion recognition modalities (e.g. face and voice) always could not identify the totally...
Chinese Named Entity Recognition with Inception Architecture and Weight Loss
Jun Zhao, Wei Fang
Named Entity Recognition(NER) is a very important part of many Natural Language Processing(NLP) tasks, but the accuracy rate of NER has not reached our expectation, especially in Chinese. Therefore, we studied NER task in Chinese social media. Compared to the previous papers on this dataset, we propose...
Heuristic Maximum Clique Based Identity Switches Awareness for Tracking
Chao Li, Di Cui, Hao Sheng, Jiahui Chen, Yang Zhang
Multi-target tracking is a popular research topic in the field of computer vision. Most recent works based on tracking-by-detection paradigm have trouble when dealing with tracking errors (i.e. identity switches) that are caused by overlapping of different pedestrians. In this work, we propose a novel...
High-Frequency Electronic Modeling Using Neural Networks
We present an overview of neural network approaches for efficient modeling, simulation and optimization of high-frequency electronic and microwave circuits. Neural networks trained from electronic/microwave data are subsequently used for circuit simulation and optimization. A brief introduction of the...
Driver Modeling Based on Vehicular Sensing Data
Zhuowen Wang, Fuqiang Liu, Xinhong Wang, Yuyan Du
In the past few years, the automotive electronics and sensing technologies have developed rapidly. Today, the status of most of the sub-systems in a running vehicle can be accurately monitored. This process produces a huge amount of data. Extracting the potential value of such data, to for instance support...
Simulation Tools and Methods of Physical Phenomena for Smart City
Eloi B. Keita, Valery Monthe, Pierre-Yves Lucas, Bernard Pottier
Many physical phenomena can be modeled as the propagation of sound or radio waves, the fluids flow, the dis-tribution of gas, the dispersion produced in a river, etc. With the help of the AC we can deduce very realistic situations. In previous work, we simulated the propagation of sound in the city using...
Software for Modeling Oilfield Surface Equipment Mode
S. Iakov Korovin, Maxim G. Tkachenko
In the paper we describe a software developed to simulate the complexes of the surface infrastructure of oil and gas fields. The created software is based on methods and algorithms proposed by the team of authors for constructing models of surface equipment for hydrocarbon deposits. The proposed approaches...
Kinematics Simulation of Planar 3-DOF Parallel Mechanism
Chao Jia, Allam Maalla, Fanshu Kong, Xijuan Guo
First, this paper establishes a three-dimension simulation model of the planar 3-dof parallel mechanism, and realized its kinematics simulation;Second, the velocity and acceleration curves of the mechanism are simulated by differential method and influence coefficient method, and the Singular configuration...
Use Spreading Activation to Model E2 Level in Representation Redescription
Xixu Fu, Xizhang Gong
Representational redescription is an important theory which describes conceptualization as an implicit to explicit process. This paper analyzed stages in the description in two dimensions on structural formation and generalization respectively. Focus on the structural formation dimension, this paper...
Digital model of surface equipment within the Digital Oilfield Framework
S. Iakov Korovin, Maxim G. Tkachenko
In the paper we describe a new approach to the construction of a model, applied for a complex for the extraction and processing of hydrocarbon raw materials. The basis of the model is a group of independently functioning components, organized on the basis of modern Arificial Intelligence methods, including...
Teaching Process Control Using the CSTH Model
Xiangshun Li, Xu Jiang
This paper discusses a case-based approach to teaching process control involving modeling, measuring, PID and cascade control methods. In the traditional process control teaching, there are some problems such as knowledge points are taught without any example or taught by different examples. which make...
Research on Database Fragmentation Technology Based on Hibernate Shards Framework for SaaS Development
Fei Zhou, Yurong Guan
As a child frame of Hibernate framework, Hibernate shards provides an effective implementation scheme for the database slicing technology developed by SaaS, expands the shared database and sharing mode, and the program development, deployment and implementation are similar to Hibernate, At present also...
Quantifying the Influences of Data Prefetching Using Artificial Neural Networks
Kecheng Ji, Li Liu
Data prefetching has been widely used in modern cache subsystems. Actually, an aggressive prefetching may bring negative yields unexpectedly, in which a new proposed prefetching strategy normally needs to be evaluated before being applied in the real design. In the last decade, prior researchers prefer...
The Application Study of HHT for the Dynamic EEG Data under +Gz Acceleration
Yifeng Li, Lihui Zhang, Quan Wang, Xiaoyang Wei, Hong Wang, Sanyuan Wu, Baohui Li, Rong Lin
The basic law and method of Hilbert-Huang Transformation (HHT) is introduced, and HHT is induced into the application study of dynamic EEG data under +Gz acceleration. The dynamic EEG data at static state that is when 1G and under +Gz acceleration is made time frequency analysis by using HHT method,...
Analysis of Scientific and Technical Literature in the Big Data
Wen Zeng, Hui Li, Na Qi
Compared with the others data, scientific and technical literature is multi-source and multiple types. Its content is more emphasis on technical and correlation. In order to analyze and evaluate it, the paper got the value of correlation based on VSM. And it introduced the value of correlation into evaluation...
Design of Exponential Distributed Median Chart with Unknown Parameters
Chengming Cao, Yizhong Ma
It is recommended to monitor the time between events(TBE) when the defect rate is very low. An unbiased median chart is proposed to monitor exponential distributed TBE data and some design parameters are provided for ease of application. For the parameter is usually unknown, the effects of estimation...
Website Intelligent Recommendation Based on K-means and Apriori Algorithms
Shaohua Zhang, Changhua Liu, Qiaodan Li
The recommended algorithm is one of the most popular applications of today. Firstly, the original data is cleaned and processed, and then the association rules model and user value analysis model are established in this paper. Secondly, a Apriori algorithm is used to analyze the relationship between...
Workload Partitioning Algorithm Based on Performance Curve of GPU in Heterogeneous Platforms
Hongyu Yang, Hui Chen, Chengming Li, Qingshan Jiang, Xueyuan Cai
With the development of GPU's general computing power, hybrid systems composed of multi-core CPU and GPU are becoming more and more popular in data parallel applications. Because the performance of GPU is related to the magnitude of the load received, effective load allocation methods are very important...
Research on Attitude Algorithm of Aircraft Based on Quaternion
In this paper, the quaternion method is used to get the accurate aircraft attitude. It is introduced coordinate system and attitude angle establishment, attitude angle acquisition and data fusion algorithm in detail. Experiments show that the algorithm effectively suppresses the gyroscope deviation and...
The Flight Navigation Planning Based on Potential Field Ant Colony Algorithm
Zhao Jin, Bin Yan, Run Ye
Path planning in complex environment is the main foundation of flights automation navigation. Therefore, this paper aims to propose an algorithm combined ant colony optimal algorithm with potential field heuristic information. The main implement method of this algorithm is to use the information between...
A Hybrid Algorithm Combining Kriging Model and Importance Sampling for Structural Reliability Analysis
Juan Wang, Yizhong Ma
One primary goal of structural reliability analysis aims at computing the probability of failure of a component or system with respect to some prescribed performance functions. In modern engineering, most performance functions usually resort to running an expensive-to-evaluate computational model, which...
An Approach of Sleep Stage Classification Based on Time-frequency Analysis and Random Forest on a Single Channel
Siyuan Bi, Qingmin Liao, Zongqing Lu
An approach of sleep stage classification based on Time-Frequency analysis and Random Forest (TFRF) on a single channel is presented in the paper. Before classifying sleep stages, representative features are extracted by feature extraction method, such as FFT in the frequency domain of EEG signal and...
Construct an Intelligent Evacuation Guidance System with Open System Architecture
Kun-Ming Yu, Huan-Po Hsu, Nien-En Chung, Cheng-Chang Lien, Shao-Tsai Cheng, Ming-Yuan Lei, Nancy Tsai
Intelligent building and environment sensing technology are becoming more and more popular. Many office buildings use IoT to set up environment collection sensors to collect environmental information, however the way of evacuation inside still using traditional evacuation guidance equipment. Therefore,...
A Medical Device Interaction System based on IEEE 11073
Zhiwei Wen, Jinzhong Cui, Leiting Chen
One of the most significant achievements in modern healthcare systems is the release of the IEEE 11073 family of standards, which formalize the compatibility and interoperability of medical devices and external computer systems. However, IEEE 11073 does not define standards and modes of communication...
Equipment Support Grid Architectures Based on WSRF
Wenjun Li, Xueqiang Yang
Grid technology as a new information technology enables resource sharing and the "two fog" eliminating in the field of equipment support. Firstly, the demands of equipment support grid design were analyzed. Besides, the three popular grid architectures were outlined. Finally, the equipment support grid...
Study on the Characteristics of Information Service Industry in Yangtze River Delta
Shaoli He, Jun Wang, Liang Zhang
The information service industry is regarded as one of the new poles of growth for China's economy with much more effective productivity of factors and it is overall most competitive in the Yangtze River Delta region. In this paper, the quantitative analysis of total factor productivity (TFP) growth...
Unsupervised Clustering Separation in Cross-Layer Approach for UHF RFID Tag Collision Recovery
Yu Zeng, Haifeng Wu, Chuanxi Xing
In passive ultra-high frequency (UHF) radio frequency identification (RFID) system, tag collision is generally resolved on a medium access control (MAC) layer. However, the collided signals are in fact recovered on a cross-physical (PHY)-MAC layer to enhance identification efficiency. This paper adopts...
Deployment Techniques of Nodes in WSN and Survey on their performance Analysis
Farhad Banoori, Muhammad Kashif, Muhammad Arslan, Rocky Chakma, Faizan Khan, Abdullah Al Mamun
Wireless Sensor nodes are small, low power consumption nodes which are basically used for sensing, transmitting and receiving the target values to specify nodes. Basically, we deploy nodes to collect information about specific region and to know about current and future results. Wireless Sensor Networks...
Support System for Operation Status Awareness and Troubleshooting of UHVDC Transmission System
Jinjun Lu, Xin Shan, Yi Wang, Xi Xu
The transmission capacity of ultra-high voltage direct current (UHVDC) transmission system is huge. Once a fault occurs, it will bring tremendous impact on the operation of the power grid, bring about a number of problems such as power flow overload, insufficient reserve, and frequency drop, and induce...
Wideband Signal Based Near-Field Electromagnetic Ranging for Indoor Localizatio
Peng Wang, Zhiyang Liu, Xiaotong Zhang, Liyuan Xu, Jie He, Yadong Wan
The near-field electromagnetic ranging (NFER) technology exploits the near-field phase behavior of low frequency signals to measure the distance and can provide better ranging performance than the high frequency signal based methods in the cluttered environments. However, the currently existing NFER...
A Multi-label Classifier for Human Protein Subcellular Localization Based on LSTM Networks
Zhiying Gao, Lijun Sun, Zhihua Wei
Nowadays, with the increasing number of protein sequences all over the world, more and more people are paying their attention to predicting protein subcellular location. Since wet experiment is costly and time-consuming, the automatic computational methods are urgent. In this paper, we propose a variant...
Example-based Chinese Calligraphy Synthesis
Wei Li, Yumin Chen, Chao Tang, Shaoyong Yu
Chinese calligraphy synthesis is important meaningful to protect non-heritage cultural and augmented reality. In this paper, we proposed an algorithm of Chinese Calligraphy synthesis based on examples. First, we construct a stroke library represented by vector. Second, we obtain the trajectory of character...
Terrain Matching Based on Adaptive Digital Elevation Map
Bin Yan, Yiming Wang, Lun Feng, Hui Zhou, Zefeng Jiang
In order to improve the navigation precision of the classical sandia inertial terrain aided navigation (SITAN), replacing kalman filter (KF) with particle filter (PF) for nonlinear system, this paper modifies and compensates inertial navigation system (INS) by terrain matching. Moreover, this paper proposes...
Analysis of Criminal Case Judgment Documents Based on Deep Learning
Jinbo Han, Dakui Li, Nanhai Yang, Zhu Liu, Qiong Nan
In recent years, along with the improvement of population quality and the advancement of the rule of law society, the market for legal services in the middle and low-end markets has continued to expand, and legal advice has become widespread in daily life. In the process of legal services, the legal...
Classification of Direct Kinematics to 3D3A Generalized Stewart Platform with Equilateral Triangle Platforms
Jiawen Zhang, Guifang Zhang
Generalized Stewart Platform is the extended form of Stewart platform of parallel linkages, which is two rigid bodies connected with six constraints. The classification of direct kinematics to 3D3A generalized Stewart platform with equilateral triangle platforms based on symbolic computation is presented....