Open Access. Powered by Scholars. Published by Universities.®
Physical Sciences and Mathematics Commons™
Open Access. Powered by Scholars. Published by Universities.®
- Keyword
-
- Simulation (131)
- Virtual reality (41)
- Genetic algorithm (40)
- Numerical simulation (40)
- Path planning (39)
-
- Modeling and simulation (35)
- Particle swarm optimization (34)
- Deep learning (33)
- Modeling (33)
- Multi-objective optimization (29)
- Digital twin (27)
- Fault diagnosis (27)
- Simulation model (23)
- Reinforcement learning (22)
- System simulation (22)
- Neural network (21)
- Visualization (21)
- Optimization (19)
- System dynamics (19)
- Virtual simulation (19)
- Complex network (17)
- Traffic simulation (17)
- UAV (17)
- Permanent magnet synchronous motor (16)
- Unity3D (16)
- Energy consumption (15)
- Support vector machine (15)
- Collision detection (14)
- Deep reinforcement learning (14)
- Parameter identification (14)
- Publication Year
Articles 2221 - 2250 of 3382
Full-Text Articles in Physical Sciences and Mathematics
System-Of-Systems Combat Ooda Loop Robustness Modeling And Experiment, Mingzhi Zhang, Ma Li
System-Of-Systems Combat Ooda Loop Robustness Modeling And Experiment, Mingzhi Zhang, Ma Li
Journal of System Simulation
Abstract: It is a difficult issue to design metrics of measure of the OSOS capabilities, which are emergent properties of OSOS. The concept of the OODA loop robustness was proposed and it was closely related to the overall capabilities of OSOS. A new method to measure the OODA loop robustness was discussed. The OSOS combat network mode was established l. Based on the weighted network, the Perron-Frobenius Eigenvalue (PFE) of the adjacency matrix of the network was used to measure the OODA loop robustness. Simulations show that there is a strong correlation between the PFE and the metric …
Research On Dynamic Authorization Allocation Of Collaborative Virtual Maintenance Based On Cpn Tools, Yunrong Zhang, Zhili Zhang, Shixin Ma
Research On Dynamic Authorization Allocation Of Collaborative Virtual Maintenance Based On Cpn Tools, Yunrong Zhang, Zhili Zhang, Shixin Ma
Journal of System Simulation
Abstract: In order to effectively deal with the concurrent behavior of cooperative virtual maintenance for the same object, a dynamic allocation scheme was proposed to complete the maintenance operation. Before the maintenance task was started, the maintenance steps were planned, and the operation rights were allocated dynamically according to the characteristics of each maintenance step. The idea of allocation and recovery of dynamic operation rights were proposed in multi person cooperative maintenance, discussing the method of ensuring the state uniqueness of maintenance personnel in the process of simulation maintenance. The process of dynamic rights allocation was simulated by colored …
Novel Automatic Pavement Crack Detection Algorithm, Shangbing Gao, Xie Zheng, Zhigeng Pan, Fangzhe Qin, Li Rui
Novel Automatic Pavement Crack Detection Algorithm, Shangbing Gao, Xie Zheng, Zhigeng Pan, Fangzhe Qin, Li Rui
Journal of System Simulation
Abstract: The complexity of noises covers a wide area of actual road images which causes that it is difficult to detect cracks. An automatic pavement crack detection algorithm was proposed in view of the characteristics of crack image in pavement disease. Gray-scale correction and filtering was used to preprocess the crack image. The maximum interclass variance method and Canny operator were used to detect the edge of the disease image, and then the localization and accurate segmentation algorithm was proposed for the crack image based on the maximum connectivity of the crack in the fracture image. The convolution neural network …
Low-Thrust Trajectory In Interplanetary Flight Solved By Pseudospectral Method, Ruiye Jiang, Chao Tao, Songyan Wang, Yang Ming
Low-Thrust Trajectory In Interplanetary Flight Solved By Pseudospectral Method, Ruiye Jiang, Chao Tao, Songyan Wang, Yang Ming
Journal of System Simulation
Abstract: The local low-thrust trajectory optimization problem in interplanetary flight was obtained with pseudo spectral method. The dynamic equations of the low-thrust orbit and the design ideas of the indirect method to solve the low-thrust trajectory were introduced. How to use the pseudospectral method to solve the trajectory optimization problem was given. The GPOPS solver (General Pseudospectral Optimal Control Software) was used to design the optimal low-thrust orbit, and the performance indexes of designing the low-thrust orbit are chosen as time-optimal, fuel-optimal and energy-optimal condition. The GPOPS solver was used to obtain the initial values of the costate variables which …
Intelligent Acp Based Experimental Approach, Bin Chen, Xiaogang Qiu, Yiping Wang
Intelligent Acp Based Experimental Approach, Bin Chen, Xiaogang Qiu, Yiping Wang
Journal of System Simulation
Abstract: As an approach to solve the problems in complex system research, ACP (Artificial Society, Computational Experiments, Parallel Execution) has played an important role in research fields such as public safety. With the development of information technologies such as big data, intelligent learning, game play theory, an intelligent ACP based experimental approach was proposed to solve the kernel problems in current complex system research. The possibility analysis of the approach in public safety, biological threats and joint combat experiments was illustrated. The applications including evacuation, network opinion and chemical industrial park security of the approach in safety science …
Novel Hierarchical Level Of Detail Combinatorial Optimization Method For Large-Scale 3d Scene, Che Li, Fengju Kang, Xueli Hou
Novel Hierarchical Level Of Detail Combinatorial Optimization Method For Large-Scale 3d Scene, Che Li, Fengju Kang, Xueli Hou
Journal of System Simulation
Abstract: The traditional design process of large-scale 3D scene is cumbersome and lengthy and fail to provide ideal scene rendering effect. Aiming at this problem, a feedback mechanism based combinatorial optimization of level of detail (LOD) model for large-scale 3D scene was proposed. Through analyzing the influence of observation distance, moving speed and other factors on visual perception, the mathematical model of visual sensitivity was established. By the frame rate and visualization effect feedback, invoking the model level selection criterion to adjust the model's LOD level, and eventually an optimal scene model combination solution could be obtained. Experimental results demonstrate …
Modeling And Simulation Of Superheated Steam Temperature Based On Multi-Objective Genetic Algorithm, Zhenlong Wu, Ting He, Lingmei Wang, Fengsheng Jia, Yunkai Yang, Haishu Wu, Donghai Li, Han Lei
Modeling And Simulation Of Superheated Steam Temperature Based On Multi-Objective Genetic Algorithm, Zhenlong Wu, Ting He, Lingmei Wang, Fengsheng Jia, Yunkai Yang, Haishu Wu, Donghai Li, Han Lei
Journal of System Simulation
Abstract: The high order inertial transfer functions were used to approximate the distribution parameter model. In order to compare the influence of the order of the leading region and the inertia object model on the accuracy and get the dynamic parameters, the multi-objective genetic algorithm was used to optimize the model parameters according to the actual operation data of the power plant. The higher the order, the Pareto front moves forward and recognizes the higher accuracy by the simulation when the orders are in a reasonable range. The reasonable superheated steam temperature system model was established considering the engineering …
Data Driven Simulation Of Polluted Gas Dispersion Using Source Estimation And Particle Filter, Rongxiao Wang, Bin Chen, Sihang Qiu, Zhengqiu Zhu, Xiaogang Qiu
Data Driven Simulation Of Polluted Gas Dispersion Using Source Estimation And Particle Filter, Rongxiao Wang, Bin Chen, Sihang Qiu, Zhengqiu Zhu, Xiaogang Qiu
Journal of System Simulation
Abstract: The real-time prediction of the air contaminant dispersion in chemical industry park is important to the emergency management of air pollution accident. Due to the unknown source terms and the error of input parameters in the atmospheric dispersion model, the accuracy of traditional simulation is limited. A data driven atmospheric dispersion simulation based on source estimation and particle filter was proposed. Based on the results of the source estimation, particle filter was applied to assimilate the UAV observation into the dispersion model in real time to calibrate the system state and obtain more accurate prediction results. Experiments show that …
Research Of State Vector In Short-Term Passengers Flow Forecasting Based On Nonparametric Regression, Guo Han, Pengpeng Jiao
Research Of State Vector In Short-Term Passengers Flow Forecasting Based On Nonparametric Regression, Guo Han, Pengpeng Jiao
Journal of System Simulation
Abstract: KNNR (K Nearest Neighbor Based Nonparametric Regression) Method was used for short-term traffic forecast and the choice of state vector was studied. The result shows that taking the data of some historical periods as the state vector has a good prediction. Although the correlation of the historical passenger flow between different Rail transit sites is significant, it neglects the fact that the passengers enter each station is independent. So taking the historical passenger flow of adjacent sites as the state vector is not appropriate.
Energy Efficiency Optimization For Discrete Workshop Based On Parametric Knowledge Pigeon Swarm Algorithm, Shan Xin, Wang Yan, Zhicheng Ji
Energy Efficiency Optimization For Discrete Workshop Based On Parametric Knowledge Pigeon Swarm Algorithm, Shan Xin, Wang Yan, Zhicheng Ji
Journal of System Simulation
Abstract: Aiming at the characteristics of complexity, constraint in discrete manufacturing workshop, in order to minimize the total energy consumption of the workshop as the target, discrete knowledge pigeons algorithm was proposed to solve discrete workshop energy efficiency optimization. In this algorithm, parameter knowledge was introduced into the optimization process to balance local search and global search, and the convergence and optimization ability of the algorithm were improved. The discrete process was added to the pigeons algorithm, which not only preserved the convergence and optimization ability of the algorithm, but also made the algorithm capable of dealing with discrete problems. …
Quick Diagnosis Of Ucav Control Surface Failure And Its Hardware-In-The-Loop Simulation, Guanhua Lu, Xia Jie
Quick Diagnosis Of Ucav Control Surface Failure And Its Hardware-In-The-Loop Simulation, Guanhua Lu, Xia Jie
Journal of System Simulation
Abstract: There are many problems in current detection methods such as conditional limitations and complexity of calculation which make them not easy to be put into practical application. The relationship between the servo motor information and the failure of the control surface was analyzed, and a method of detecting the failure rate of the control surface by using the servo current information in combination with the aerodynamic model was proposed. The result of its hardware-in-the-loop simulation shows that the detection system can quickly and accurately output the failure rate within 1 second which is a conservative estimate. That makes the …
Research On Dynamic Flexible Job Shop Scheduling Problem For Energy Consumption, Chen Chao, Wang Yan, Dahu Yan, Zhicheng Ji
Research On Dynamic Flexible Job Shop Scheduling Problem For Energy Consumption, Chen Chao, Wang Yan, Dahu Yan, Zhicheng Ji
Journal of System Simulation
Abstract: In order to solve the problem of uneven load and energy consumption under disturbance, a flexible job shop scheduling model with average flow time and energy consumption was constructed. Aiming at the above model, a genetic and simulated annealing algorithm (GASA) was designed, which is based on the genetic algorithm and the simulated annealing algorithm. A new group of individuals were generated by genetic algorithm. And then the individual simulated the annealing process, in order to avoid falling into the local optimal. Aiming at the dynamic flexible job shop scheduling problem, the rolling window technique and GASA algorithm were …
Non-Singular Terminal Sliding Mode Control For Bank-To-Turn Missile Based On Active Disturbance Rejection Decoupling Controller, Ma Fei, Yunjie Wu, Mingzhi Cheng
Non-Singular Terminal Sliding Mode Control For Bank-To-Turn Missile Based On Active Disturbance Rejection Decoupling Controller, Ma Fei, Yunjie Wu, Mingzhi Cheng
Journal of System Simulation
Abstract: An overload tracking model was established, based on the traditional model of BTT (Bank-to-Turn) missile, and an ADRDC (active disturbance rejection decoupling controller) was designed because of the strong coupling problem in this model. For the coupled channel, the decoupling was performed by the ADRDC, and then the NTSMC (non-singular terminal sliding mode controller) was added. For the non-coupled channel, only the NTSMC was designed. The experimental results show that the new control strategy can combine the strong robustness of ADRDC with the finite time convergence ability of NTSMC. Besides, it shows good dynamic performances and steady-state …
Off-Line Calibration Of Dynamic Traffic Assignment System Based On Flowsim, Yuhan Jia, Jianping Wu, Xu Ming, Mingyu Liu, He Lei
Off-Line Calibration Of Dynamic Traffic Assignment System Based On Flowsim, Yuhan Jia, Jianping Wu, Xu Ming, Mingyu Liu, He Lei
Journal of System Simulation
Abstract: Advanced dynamic traffic assignment (DTA) system can be utilized to mitigate traffic congestion. Therefore, the calibration of DTA parameters is becoming increasingly significant in traffic research area. Based on extended Kalman Filter (EKF) and unscented Kalman Filter (UKF) algorithms, a case study for the off-line calibration of DTA was proposed using the microscopic traffic simulation system of FlowSIM. Experiments with a synthetic network validate the effectiveness of the two solutions, and the UKF shows better accuracy than the EKF algorithm. Furthermore, the performance of FlowSIM is promising to conduct the calibration of traffic system in future …
Agent Modeling Of Web Users Orientating Simulation Of Internet Public Opinion, Chuan Ai, Bin Chen, Liu Liang, Xiaogang Qiu
Agent Modeling Of Web Users Orientating Simulation Of Internet Public Opinion, Chuan Ai, Bin Chen, Liu Liang, Xiaogang Qiu
Journal of System Simulation
Abstract: People are individuals with independent behavior in society, and have important influence on the occurrence and development of public opinion emergencies. At the same time, the group composed of individuals is the disaster-bearing body of public opinion events. Therefore, the use of simulation modeling means to explore the occurrence and development of public opinion Mechanism, for the public opinion emergency response measures to provide decision support, the individual behavior of the modeling simulation is particularly important. Based on the analysis of the psychological behavior process of individual information processing, a complete mechanism model was put forward which could reflect …
Research Of Air Mission Recognition Method Based On Deep Learning, Qingkai Yao, Shaojun Liu, Xiaoyuan He, Ou Wei
Research Of Air Mission Recognition Method Based On Deep Learning, Qingkai Yao, Shaojun Liu, Xiaoyuan He, Ou Wei
Journal of System Simulation
Abstract: In the large-scale simulation of war game, the air mission is the focus of the commander's attention. The rapid, accurate and automatic recognition of air missions is the prerequisite and basis for intelligent decision making. The rapid development of deep learning technology provided a practical and feasible solution for the extraction of complex battlefield posture features, and provided technical support for studying air mission recognition. The research progress of the traditional mission recognition research method and the mission recognition method based on the deep learning was summarized. The three methods of deep learning of Convolution Neural Network (CNN), Long-short …
Skeleton Extraction From Three-Dimensional Maize Based On Kinect, Zhili Fang, Weiliang Wen, Xinyu Guo, Jianwei Wu
Skeleton Extraction From Three-Dimensional Maize Based On Kinect, Zhili Fang, Weiliang Wen, Xinyu Guo, Jianwei Wu
Journal of System Simulation
Abstract: Aiming at acquiring three-dimensional skeleton of maize plant efficiently, an automatic three-dimensional maize plant skeleton extraction method based on Kinect data was proposed. Kinect data was transformed into point cloud data. Backgroundpoint cloud was deleted by threshold segmentation and the point cloud was stratified according to the height of the 3D model. Each layer was clustered by two circle iteration and the center points of each cluster could be obtained. The set of center points could be considered as the skeleton points of maize. The quadratic B-spline interpolation curve was used to obtain relatively accurate and smooth linear …
Vulcanization Shop Scheduling Based On Distribution Estimation Algorithm, Shougang Zhang, Longcheng Wu, Wang Yan, Zhicheng Ji
Vulcanization Shop Scheduling Based On Distribution Estimation Algorithm, Shougang Zhang, Longcheng Wu, Wang Yan, Zhicheng Ji
Journal of System Simulation
Abstract: Due to the characteristics of long time-consuming, energy consumption and high concentration in rubber tire vulcanization process, which is the tire production process bottlenecks process, a discrete distribution estimation algorithm (EDA) was proposed to solve the problem of vulcanization shop scheduling optimization with minimum maximum completion time as the optimization target. The algorithm was tested by different examples, and it was compared with the genetic algorithm and the harmony search algorithm. The experimental results show that the EDA algorithm is superior to the genetic algorithm and the harmony search algorithm in the quality of the solution and convergence speed, …
Visual Simulation Of Eroded Rill Evolution Process On Graphics Processing Unit, Mansheng Long
Visual Simulation Of Eroded Rill Evolution Process On Graphics Processing Unit, Mansheng Long
Journal of System Simulation
Abstract: A slope erosion model based on CA (Cellular Automata) and a corresponding simulation algorithm based on GPU (Graphics Processing Unit) were proposed to visualize rapidly the dynamic process of water erosion and microrelief development on hillslope under rainfall events. The model is composed of processes such as rainfall, infiltration, runoff, erosion, deposition, and sediment transport. At each time step, water and sediment were exchanged among adjacent cells observing sediment mass conservation law and flow continuity equation. All cells update their runoff and sediment simultaneously complying with the above simple rules so as to realize the evolution of hillslope microrelief. …
Research Of The Construction Of Gis-T Traffic Simulation Road Network, Huang Min, Zhongming Niu, Xiaolan Zhang, Jiajie Pan, Xueqiang Zhang
Research Of The Construction Of Gis-T Traffic Simulation Road Network, Huang Min, Zhongming Niu, Xiaolan Zhang, Jiajie Pan, Xueqiang Zhang
Journal of System Simulation
Abstract: In order to provide road network data for traffic simulation platform on the base of GIS-T, a GIS-T road network data model was created. The model put the emphasis on the description of traffic rules and road markings. On the basis of data model, a quantified cut method for linear referencing was proposed and the method was adopted to create road network element, such as lane boundary and road surface. Furthermore, the carriageway was regarded as the unit to keep the shape of road segment, and flow of building a road network was put forward. An intersection …
Soc-Based Bi-Directional Active Equalization Control For Lithium-Ion Power Battery, Shaojian Song, Zhihao Wang, Xiaofeng Lin
Soc-Based Bi-Directional Active Equalization Control For Lithium-Ion Power Battery, Shaojian Song, Zhihao Wang, Xiaofeng Lin
Journal of System Simulation
Abstract: The inconsistency of cell in the electric vehicles' lithium-ion power battery pack leads to decrease the battery pack's capacity and lifetime, and even seriously affect the electric vehicles' performance. An active equalization system was designed based on the bi-directional Buck-Boost topology. A novel active equalization control strategy was proposed to balance the lithium-ion battery pack in the process of charging and static state, which extreme learning machine (ELM) was used to predict the state of charge(SOC), and SOC was employed as the main balance criterion. The simulation results show that the proposed bi-directional active equalization method can realize the …
Work Mode Identification Of Phased Array Radar With Denoising Auto-Encoder, Haodong Liu, Weidong Jin, Chunli Chen, Cai Jian
Work Mode Identification Of Phased Array Radar With Denoising Auto-Encoder, Haodong Liu, Weidong Jin, Chunli Chen, Cai Jian
Journal of System Simulation
Abstract: A new method to recognize phased array radar in different work modes was proposed based on multi-level modeling combined with Marginalized Stacked Denoising Auto-encoder. In order to analyze the change law of pulses intercepted by surveillance radar, multi-level modeling was proposed to model the pulses at pulse level, pulse group level and work mode level. Marginalized stacked denoising auto-encoder was trained to extract amplitude characteristics at the work mode level. SVM (Support Vector Machine) was added to the top of deep network to realize work mode identification of phased array radar. Qualitative experiments show that the new method is …
Threat Assessment Of Aircraft Carrier Formation Based On Hierarchical Bayesian Network, Chen Long, Yaping Ma
Threat Assessment Of Aircraft Carrier Formation Based On Hierarchical Bayesian Network, Chen Long, Yaping Ma
Journal of System Simulation
Abstract: The use of bayesian network model for threat assessment is a relatively new quantitative analysis method. The hierarchical bayesian network model was applied to aircraft carrier formation to assess submarine formation threat for the first time, which also assessed the threat level of the submarine formation, to achieve the purpose of assisting decision-making for aircraft carrier formation commanders in anti-submarine warfare. The hierarchical bayesian network model was described. The causes and the mechanism of the aircraft carrier formation from the underwater target threat, integrated force data, institutional experts and information were analyzed. A reliable aircraft carrier formation hierarchical …
Fast Tree Modeling Method Based On Simple Freehand Sketch, Ma Ling, Xiaoping Liu, Xiaoping Liu
Fast Tree Modeling Method Based On Simple Freehand Sketch, Ma Ling, Xiaoping Liu, Xiaoping Liu
Journal of System Simulation
Abstract: Aiming at problems such as complicated process and professional knowledge requirements in tree modeling, a quick tree modeling method for non-experts was proposed, combining branch library with simple sketch to make non-experts create tree model quickly. The method preprocessed the sketch to eliminate noise and error points and identify the strokes, the trunk and branch were reconstructed, child three-dimensional profile was built through the two-dimensional canopy profile, under the constraint of the child profile, suitable branches from library and insert were extracted into the branches, consequently the whole tree model was completed. Experimental results show that this method …
Research On Online Lssvm Prediction Based On Hermite Matrix Inversion, Hong Bei, Xuepeng Jiang, Yudong Qi, Qinghua Chen
Research On Online Lssvm Prediction Based On Hermite Matrix Inversion, Hong Bei, Xuepeng Jiang, Yudong Qi, Qinghua Chen
Journal of System Simulation
Abstract: For forecasting the gyro drift tendency of a missile, a prediction model based on LSSVM was established taking the time series of gyro's drift as study object, and an online algorithm for nonlinear system based on hermite matrix inversion was proposed. The mathematical model of regression LSSVM, and online learning algorithm were introduced. Based on the characteristic that the reproducing kernel matrix is Hermite and positive definite, a new online learning algorithm was proposed by matrix block-inversion. The algorithm was applied to prediction research on real gyro drift data of certain missile. The experiment results show that the …
Extended Target Tracking In Presence Of Target Crossing, Jinguang Chen, Mengxi Jiang, Lili Ma
Extended Target Tracking In Presence Of Target Crossing, Jinguang Chen, Mengxi Jiang, Lili Ma
Journal of System Simulation
Abstract: In the process of extended target tracking, if there are some crossing targets, target missing problem in target estimation will appear when the extended target Gaussian mixture probability hypothesis density filter is used directly. Aiming at this problem, an improved algorithm was proposed. Euclidean distances among targets estimated were calculated at each time, and then these targets were distinguished if they were in an adjacent region or not. In the next time step, Gaussian components weights of the targets in the same adjacent region were compensated if the target number estimated became small; otherwise, there was nothing to do. …
Application Of Haze Forecasts Based On Combined Multivariable And Probability Stepwise Regression, Yonghua Xie, Le Yang, Mingmin Zhang, Hengde Zhang
Application Of Haze Forecasts Based On Combined Multivariable And Probability Stepwise Regression, Yonghua Xie, Le Yang, Mingmin Zhang, Hengde Zhang
Journal of System Simulation
Abstract: Aiming at the less models available and poor prediction performance of current haze forecasting, combining statistical forecast and numerical prediction, a new haze prediction model was proposed based on hybrid stepwise multivariable and probability regression. Multivariable stepwise regression was used to control physical factors which influenced depending variable and the equation for atmosphere visibility wasgenerated. A haze prediction model based on binary variables was established using probability regression combined with factors like visibility and relative humidity. Experimental results have proved that compared with the existing CUACE, which is one of the main digital haze forecasting system, the accuracy using …
Orthogonal Wavelet Transform Blind Equalization Algorithm Based On Tabu Search And Double-Stranded Dna Computimg, Yecai Guo, Jieru Zhang, Binglong Zhang
Orthogonal Wavelet Transform Blind Equalization Algorithm Based On Tabu Search And Double-Stranded Dna Computimg, Yecai Guo, Jieru Zhang, Binglong Zhang
Journal of System Simulation
Abstract: Aiming at disadvantages of orthogonal wavelet transform constant modulus blind equalization algorithm (WTCMA), such as slower convergence rate, larger mean square error, and immerging in partial minimum easily, an orthogonal wavelet transform blind equalization algorithm based on Tabu search strategy and adaptive double-stranded DNA genetic algorithm (TD-DNAGA-WTCMA) was proposed. DNA populations were initialized by using double-stranded DNA form, to select the single-stranded DNA sequences whose fitness value are largest as the representative strands of the double-stranded individuals. In order to ensure different paths which ccould be searched and escaped from local optimum, Tabu search strategy was introduced into …
Study On Vacuum Dehydration Rate From Oil Based On T_S Fuzzy Identifying Model, Liu Ge, Bin Chen, Xianming Zhang
Study On Vacuum Dehydration Rate From Oil Based On T_S Fuzzy Identifying Model, Liu Ge, Bin Chen, Xianming Zhang
Journal of System Simulation
Abstract: The process of vacuum dehydration from oil is time-varying, nonlinear, and difficult to be specified with mathematical methods. Takagi-Sugeno (T_S) fuzzy model of vacuum dehydration rate of oil purifier is proposed, which a method of applying Fuzzy C-Means (FCM) clustering algorithm and using the least square method identifying the consequent parameters. The nonlinear mapping is set up from four influence factors (the initial water content, the vacuum pressure , the initial temperature and running time) to vacuum dehydration rate using the T_S fuzzy model. The simulation and experimental results show the T_S model reflects the laws of the influences …
Two Grade Learning Goal Neural Network Modeling With Power Activation Function, Jiacun Liu, Qixiang Mei, Donghong Yang
Two Grade Learning Goal Neural Network Modeling With Power Activation Function, Jiacun Liu, Qixiang Mei, Donghong Yang
Journal of System Simulation
Abstract: In order to obtain the very generalized and accurater mathematic model, a regression neural network algorithm with frequency decomposition power function and two grade learning objectives was proposed. The network structure is divided into frequency decomposition, input layer, hidden layer and output layer. The input signal is decomposed into several frequency range and sent to the hidden layer. The transfer function of hidden layer is power function. The hidden layer and output layer have learning objectives respectively, and the neural network has local and globe feedback. The hidden layer adopts the local gradient algorithm based on vector angle and …