Open Access. Powered by Scholars. Published by Universities.®

Computer Engineering

Institution
Keyword
Publication Year
Publication
Publication Type

Articles 3031 - 3060 of 3961

Full-Text Articles in Numerical Analysis and Scientific Computing

Research On The Simulation Technology For Multi-Aerocraft Cooperative Guidance, Li Jing, Han Jian, Zhang Qing Dec 2019

Research On The Simulation Technology For Multi-Aerocraft Cooperative Guidance, Li Jing, Han Jian, Zhang Qing

Journal of System Simulation

Abstract: The formal system of multi- aerocraft cooperative simulation system is identified as the discrete event system & different equation system specifications (DEV&DESS) through the analysis of the composition and running mechanism. The running control problem of cooperative simulation system is transformed into simulation control problem of a specific DEV&DESS system. A dynamic operation control method for cooperative guidance simulation system based on coordinator is proposed, and this method is validated by real-time mathematical simulation experiments.


An Lstm-Based Motion Recognition Method For Power Operation And Maintenance, Peizhen Liu, Yuxiang Jia, Shihong Xia Dec 2019

An Lstm-Based Motion Recognition Method For Power Operation And Maintenance, Peizhen Liu, Yuxiang Jia, Shihong Xia

Journal of System Simulation

Abstract: The security of power operation and maintenance has always been a subject of great social concern. In order to avoid serious consequences caused by the fault of staffs, a motion recognition method for power operation and maintenance jobs based on LSTM (Long Short-Term Memory) is proposed, which covers the whole process from data collection, data processing to motion classification and recognition, then it can recognise and supervise the behavior of staffs who are at work. In addition, a simulation experiment is conducted between the deep learning algorithm LSTM and the traditional machine learning algorithm KNN based on the newly …


Design Of Feedback Linearization Nonlinear Controller For Asynchronous Motor Power Consumption Efficiency, Li Rui, Yingnian Wu Dec 2019

Design Of Feedback Linearization Nonlinear Controller For Asynchronous Motor Power Consumption Efficiency, Li Rui, Yingnian Wu

Journal of System Simulation

Abstract: In order to realize precise feedback linearization and optimal control of motor power consumption for MIMO nonlinear affine system, we build the model of induction motor within which dynamic power loss factor is included. Based on the differential geometry theory, a nonlinear optimization model of the controller is designed for this model to control the asynchronous motor outputs accurately and enhance the power efficiency. This paper presents an optimal control law for multiple inputs multiple outputs affine nonlinear system and the detailed design steps are given combined with examples for multiple outputs tracking problem. The simulation results show that …


Research On Intelligent Clustering Algorithm For Complex Water Wireless Network Surveillance, Hua Xiang, Hongtao Liang, Zhaoxin Dong, Wang Zhao, Hongjuan Yao, Baohua Li, Bingqing Jiang Dec 2019

Research On Intelligent Clustering Algorithm For Complex Water Wireless Network Surveillance, Hua Xiang, Hongtao Liang, Zhaoxin Dong, Wang Zhao, Hongjuan Yao, Baohua Li, Bingqing Jiang

Journal of System Simulation

Abstract: The clustering of irregular networks will cause load imbalance, which results in the phenomenon of “energy hot zone”. Aiming at the unreasonable topology of irregular network clustering, an intelligent clustering algorithm based on genetic strategy is proposed for the wireless network surveillance of complex water system. An irregular complex water topology model and an energy consumption model are built, and a genetic clustering strategy is designed via the principle of minimum energy consumption. The P matrix coding method is given, which avoids the squared increment of data calculation. Simultaneously, an adaptive genetic operator and a fuzzy modified operator are …


Moving Object Detection Based On Deep Convolutional Neural Network, Yuqiu Lu, Jinyu Sun, Shiwei Ma Dec 2019

Moving Object Detection Based On Deep Convolutional Neural Network, Yuqiu Lu, Jinyu Sun, Shiwei Ma

Journal of System Simulation

Abstract: A deep convolution neural network MONet is designed for the intermittent motion problem in moving objects detection. In the absence of training data sets, a synthetic dataset GoChairs is generated by affine transformation, and on this basis the network training and testing are performed. The results show that the trained MONet can effectively detect the moving objects based on the correspondence between the pixels. The traditional datasets CDnet and I2R are also tested to verify the generalization performance of the network. In addition, MONet is compared qualitatively and quantitatively with classical methods for the intermittent motion problem of …


3d Shape Deformation Simulation Algorithm Based On Haptics, Binbin Qi, Xuefang Zhu, Lipeng Fan Dec 2019

3d Shape Deformation Simulation Algorithm Based On Haptics, Binbin Qi, Xuefang Zhu, Lipeng Fan

Journal of System Simulation

Abstract: Shape deformation is widely used in virtual reality, system simulation, computer animation and other graphics applications. Few people pay attention to introducing haptic interaction into 3D model deformation. We provide a haptic interactive framework by introducing haptic interaction into shape editing field. Based on the above haptic interactive framework, we propose a 3D model deformation simulation algorithm based on haptics. In order to realize the shape deformation, this algorithm needs to involve three parts: grid hierarchical structure, local mass-spring model and the dynamic shape deformation. Experimental results show that this algorithm has good stability and strong robustness, and the …


Intelligent Manufacturing Plan Management Based On Digital Twins, Yingying Xiao, Wang Mei, Liqin Guo, Xing Chi, Changhui Zhuang Dec 2019

Intelligent Manufacturing Plan Management Based On Digital Twins, Yingying Xiao, Wang Mei, Liqin Guo, Xing Chi, Changhui Zhuang

Journal of System Simulation

Abstract: For the multi-variety and small-batch manufacturing mode, the planning management system cannot be timely automatically adjusted according to uncertain factors. This paper proposes an intelligent manufacturing plan management system based on factory digital twins. The plan management PDCA business process model is established. In addition, the processing logic model and constraints of the periodic static scheduling model and the dynamic emergency scheduling model are proposed. Based on the planning management case of hybrid assembly of two types of aerospace complex products, it is verified that the management model proposed in this paper can support the intelligent dynamic adjustment of …


A Cloud Service Composition Optimization Based On Hnn, Huili Zhang, Zhihe Li Dec 2019

A Cloud Service Composition Optimization Based On Hnn, Huili Zhang, Zhihe Li

Journal of System Simulation

Abstract: With the rapid development of Cloud service application, how to effectively optimize the composition of Cloud services on cloud platform and improve the overall performance of cloud platform system have become an urgent research issue. In order to improve the efficiency of Cloud services, a combined optimization model based on Hopfield neural network is proposed. The problem of Cloud services is modeled. The problem is expressed as Hopfield Neural Network energy model for optimization, and a PSO group algorithm with Cauchy disturbance is designed to improve the Hopfield model. The experimental comparison shows that the method can improve …


Modeling And Simulation Of Complex Equipment Health Management System Based On Cloud Computing, Tianrui Zhang, Chuansheng Qu, Baoku Wu, Jianan Xu Dec 2019

Modeling And Simulation Of Complex Equipment Health Management System Based On Cloud Computing, Tianrui Zhang, Chuansheng Qu, Baoku Wu, Jianan Xu

Journal of System Simulation

Abstract: For complex equipment operation safely, the health management problems of complex equipment life cycle is analyzed. In order to realize remote service, complex equipment health management mode based on cloud computing is proposed. Aiming at the accuracy problem in the process of extracting and recognizing complex equipment characteristic data, the feature knowledge acquisition method based on ontology is researched, and the expression and acquisition algorithm of state characteristic knowledge is proposed. A task sequencing algorithm faults based on fuzzy comprehensive evaluation method is proposed, an appropriate task assignment model is selected for scheduling health management technicians. …


Agent Based Modeling And Simulation Analysis Of Low-Orbit Early-Warning Satellites, Liu Wen, Xiaolu Wang, Hongsheng Wang, Zhang Heng, Changqing Wang Dec 2019

Agent Based Modeling And Simulation Analysis Of Low-Orbit Early-Warning Satellites, Liu Wen, Xiaolu Wang, Hongsheng Wang, Zhang Heng, Changqing Wang

Journal of System Simulation

Abstract: Low-Orbit Early-Warning Satellite has accurate midcourse ballistic missile tracking and surveillance capability. The paper takes Space Tracking and Surveillance System’s function and construction as the research subject. System model is constructed based on Agent method. The possible constellation configurations of STSS are analyzed considering the coverage performance,and the detection capability of ballistic missile target is simulated and analyzed. Simulation analysis of target detection is carried out. The result shows that STSS can effectively detect a certain number of targets, but detecting capability is affected severely by solar illumination.


Simulation Of Vehicle Startup Delay At Green Light And Its Direct And Chain-Reaction Impact On Traffic Flow, Longxi Luo, Lijun Xie, Jianping Wu, Xu Ming Dec 2019

Simulation Of Vehicle Startup Delay At Green Light And Its Direct And Chain-Reaction Impact On Traffic Flow, Longxi Luo, Lijun Xie, Jianping Wu, Xu Ming

Journal of System Simulation

Abstract: In current traffic simulations, it is implicitly assumed vehicles are driven by ideal drivers. Therefore, simulated vehicles make the most reasonable decisions such as moving out immediately when traffic lights turn green, resulting in a gap between simulations and real traffics. Research shows that drivers, including those who follow the rules, show a delay in starting-up their vehicles at the green light. The vehicle startup delay (SUD) is even more significant for drivers by things such as cell phones during waiting. However, the SUD has rarely been considered in simulations. The SUD is simulated to study its impacts on …


Fault Prediction Of Satellite Attitude Control System Based On Neural Network, Xiaofan Meng, Song Hua Dec 2019

Fault Prediction Of Satellite Attitude Control System Based On Neural Network, Xiaofan Meng, Song Hua

Journal of System Simulation

Abstract: A new method based on BP neural network(BPNN), wavelet neural network(WNN) and wavelet decomposition-LSTM(wLSTM) network is proposed for predicting faults in the satellite attitude control system. Normal satellite attitude data is used to train BPNN which is used as the standard model of satellite attitude control system. The real-time attitude residuals is obtained by subtracting the BPNN output attitude angle from the real-time data of satellite attitude. The time series of the residuals are used to build WNN and wLSTM models to predict the faults of satellite attitude control system. A conclusion is given according to comparing the …


Design Of Combat Simulation And Visualization System Of Hypersonic Vehicle, Yu Ying, Weidong Liang, Xiujuan Zhu, Jianlin Wang, Wang Ling Dec 2019

Design Of Combat Simulation And Visualization System Of Hypersonic Vehicle, Yu Ying, Weidong Liang, Xiujuan Zhu, Jianlin Wang, Wang Ling

Journal of System Simulation

Abstract: Based on the thought of combat simulation, the system of combat simulation and visualization is designed to show the typical combat mode and the characteristics of near space vehicles. Taking the aircraft attacking a fixed target as an example, the formulation of combat plan, the deployment of forces and the design of combat process of both sides are realized. On the one hand, a combat simulation platform which covers various combat modes of attack and defense is established. On the other hand, the whole process of combat confrontation of hypersonic vehicles is presented, driven by the real-time simulation data. …


Multi-Sensor Data Fusion With Network Delays And Correlated Noises, Shankai Zhang, Zhu Cui, Su Zhong, Dai Juan Dec 2019

Multi-Sensor Data Fusion With Network Delays And Correlated Noises, Shankai Zhang, Zhu Cui, Su Zhong, Dai Juan

Journal of System Simulation

Abstract: This paper focuses on the state estimation for multi-sensor system with network delays and correlated noises. An orthogonal transformation method is applied to remove the correlations between different noises. For the problem of packet delays due to the unreliable network, a buffer with certain length is introduced to store the measurements, and the measurements are reordered using a timestamp in the buffer. Based on that, a novel sequential data fusion algorithm is proposed, by which the influence of the noise correlation and packet delays can be weakened effectively. Compared with the traditional sequential fusion method, the proposed algorithm has …


Pedestrian Navigation Method Based On Uwb And Sins, Yang Yang, Li Qing Dec 2019

Pedestrian Navigation Method Based On Uwb And Sins, Yang Yang, Li Qing

Journal of System Simulation

Abstract: In view of the problem that the inertial navigation error is accumulating with time and UWB indoor is hard to continue tracking problems in complex environment, an extended Kalman filter (EKF) fusing UWB and sins pedestrian navigation is proposed.The zero speed correction algorithm is used to trigger EKF at zero speed. The sins is corrected by the velocity error measurement provided by sins and the position error measurement provided by UWB restraining error accumulation.When UWB signal is interrupted, the position of UWB output without interruption is taken as the starting position. The experiment results of SINS autonomous navigation …


Research On Uncertainty Measurement Method Of Aircraft Hwil System, Huapin Geng, Jiahui Tong, Hongtao Ma Dec 2019

Research On Uncertainty Measurement Method Of Aircraft Hwil System, Huapin Geng, Jiahui Tong, Hongtao Ma

Journal of System Simulation

Abstract: Uncertainty is the inherent attribute of simulation system, causing the expected results inconformity with the real results, even influencing the robustness and reliability of system. Based on the analysis of the system uncertainty characteristics, the analysis framework of HWIL system uncertainty measurement is proposed. Three kinds of the uncertainty measurement methods based on the uncertainty type and the compound and weighting are researched on aircraft HWIL System. The typical uncertainty measurement methods are applied based on some aircraft HWIL system and the result proves that the method is efficient.


Fault-Tolerant Method And Simulation Of Heterogeneous Multi-Core Processor Based On Speculative Mechanism, Shigan Yu, Zhimin Tang, Xiaochun Ye, Dongrui Fan Dec 2019

Fault-Tolerant Method And Simulation Of Heterogeneous Multi-Core Processor Based On Speculative Mechanism, Shigan Yu, Zhimin Tang, Xiaochun Ye, Dongrui Fan

Journal of System Simulation

Abstract: Heterogeneous multicore is one of the important branches of processors,but they are still faced with frequent transient failures. TMR(Triple mode redundancy) is the main method to solve transient faults, which has the characteristics of low efficiency and high power consumption, a high-performance Fault-Tolerant Scheduling Algorithm with Speculative mechanism(FTSAS) is proposed. Each heterogeneous core can execute tasks independently, the state values of the first completed core are recorded, and the first completed core continues to perform the next task with forward speculative method. The results are compared by backward core, the majority consensus principle is adopted to ensure the reliability …


Lstm Model For Trajectory Design Of Missile-Borne Bfsar Imaging Guidance, Bohao Li, Yunjie Wu Dec 2019

Lstm Model For Trajectory Design Of Missile-Borne Bfsar Imaging Guidance, Bohao Li, Yunjie Wu

Journal of System Simulation

Abstract: In the multi-platform path planning of multi-missile cooperative guidance algorithm used for missile-borne Bi-static Forward-looking Synthetic Aperture Radar (BFSAR) imaging, it is necessary to plan and adjust the transmitter trajectory according to the space state of the receiver and the path constraints between the receiver and the transmitter.An effective LSTM model is constructed to study and train the trajectory path generated by the existing algorithms, and the direct mapping relationship between the receiver space state, path constraint and the trajectory of the transmitter is obtained. The simulation results not only show that LSTM is feasible in multi-missile path …


Energy Efficiency Data Mining And Scheduling Optimization Of Discrete Workshop, Yugu Lin, Wang Yan Dec 2019

Energy Efficiency Data Mining And Scheduling Optimization Of Discrete Workshop, Yugu Lin, Wang Yan

Journal of System Simulation

Abstract: This paper addresses the optimization of energy consumption in discrete workshops and establishes the energy efficiency optimization model of discrete workshops. The relationship between data mining and knowledge discovery is established. Through scheduling data preprocessing and C4.5 decision tree learning algorithm, the discovery of scheduling knowledge is realized. Energy efficiency optimization calculation is achieved in discrete workshops by the combination of scheduling knowledge and improved differential evolution algorithm (IDE). By comparing with TLBO, GA and PSO, the feasibility of IDE algorithm is verified.


Research On Social Network Inference Method Based On Observation Data, Hailiang Chen, Bin Chen, Yuan Peng, Dong Jian, Chuan Ai Dec 2019

Research On Social Network Inference Method Based On Observation Data, Hailiang Chen, Bin Chen, Yuan Peng, Dong Jian, Chuan Ai

Journal of System Simulation

Abstract: Internet technology and online social networks have developed rapidly, which enables people to randomly express their opinions, ideas, emotional exchanges and economic exchanges. Inferring social networks is made possible through the observation data exchanged by people on the Internet. Through the analysis of ConNIe (Convex Network Inference) algorithm, this paper researches the effects of sparse parameter, propagation time distribution model and its parameters on the inference results of the algorithm. According to the analysis, a social network inference framework based on ConNIe algorithm is proposed. Combining the perceptron and particle swarm optimization algorithm, the ConNIe algorithm inference becomes a …


Exploration Of Soldier Morale Using Multi-Mode Simulation Approach, Yongsheng Zhang, Zhengxiang Xiong Dec 2019

Exploration Of Soldier Morale Using Multi-Mode Simulation Approach, Yongsheng Zhang, Zhengxiang Xiong

Journal of System Simulation

Abstract: Soldier morale is a complex social construction influenced by factors at multiple levels and integrates many research domains. This research seeks to explore, model, and simulate soldier morale at multiple levels of analysis. Microcosmically Agent-Based Modeling method is used to reflect the interaction among fighters and the course of affecting morale,Macrocosmically SD method is used to reflect the influence of the tactical psychology on morale and the whole war in the counter-combat process. The developed sample case scenario pertained to US security efforts against insurgency in Afghanistan in 2007. The scenario includes representation of the patrol base operations serving …


Dynamic Simulation Of Marine Pasture Water Quality Monitoring Network Based On Aug, Wenxia Xue, Bin Lin, Hu Xu, Jingbo Zhang Dec 2019

Dynamic Simulation Of Marine Pasture Water Quality Monitoring Network Based On Aug, Wenxia Xue, Bin Lin, Hu Xu, Jingbo Zhang

Journal of System Simulation

Abstract: The development of marine pastures puts forward higher requirements for water quality monitoring. In order to achieve large-scale and long-term underwater water quality monitoring, AUG-based Underwater Sensor Network (AUSN) is studied. The AUG is introduced as the underwater sink node of the sensor network and the sleep scheduling mechanism is adopted for the sensors, which can effectively reduce the total energy consumption of the network. Based on the analysis of energy consumption characteristics of underwater sensor networks, the energy consumption calculation formula of underwater sensor networks is discussed. Combined with the virtual visualization technology, the underwater sensor network simulation …


Design And Implement Of Semi Physical Simulation System For Underwater Acoustic Imaging, Ruonan Fan, Jijun Jiang, Naiwei Sun Dec 2019

Design And Implement Of Semi Physical Simulation System For Underwater Acoustic Imaging, Ruonan Fan, Jijun Jiang, Naiwei Sun

Journal of System Simulation

Abstract: A semi physical simulation system based on underwater scale target and acoustic imaging is designed. Functional requirements are presented, the echo models of underwater scale target acoustic image are established through the planar element method, the structure, hardware and software are designed, the real-time signal generation techniques of applying the model to the simulation system are researched. The results of underwater experiment show that the simulation system can simulate the acoustic imaging echo signal of Benchmark submarine model, the imaging results are recognizable to some extent, it can be promoted to any underwater scale target and meet the …


Research On Supporting Action Model Of Long-Rang Strike Space Reconnaissance Based On Combination Mode, Changliang Xiao, Jingyu Yang, Wu Xi, Ma Jun, Xiaojing Yin Dec 2019

Research On Supporting Action Model Of Long-Rang Strike Space Reconnaissance Based On Combination Mode, Changliang Xiao, Jingyu Yang, Wu Xi, Ma Jun, Xiaojing Yin

Journal of System Simulation

Abstract: Space reconnaissance support operations mainly undertake the tasks of target detection and identification in the early stage of strike, target guidance during strike and damage effect evaluation after strike. Based on EBI(Entity, Behavior, Interaction)modeling framework, this paper describes the entity models of signal intelligence sensor, radar alarm sensor and imaging sensor, constructs a combined mode of space reconnaissance support operation. It mainly models the combined mode algorithm of three sensors and their respective target detection behavior rules, whick is conductive to improving reconnaissance efficiency and enhancing intelligence quality in combat operations.


Research On Gear Appearance Defect Recognition Based On Improved Faster R-Cnn, Weixi Ji, Du Meng, Peng Wei, Xu Jie Dec 2019

Research On Gear Appearance Defect Recognition Based On Improved Faster R-Cnn, Weixi Ji, Du Meng, Peng Wei, Xu Jie

Journal of System Simulation

Abstract: In order to achieve automatic identification of gear appearance defects and improve the qualification rate of gear products, aiming at the generalization of traditional defect recognition algorithms and the time-consuming of manual features extraction, this paper proposes an improved gear flaw detection algorithm for Faster R-CNN. VGG-2CF network is designed to improve the ability to identify smaller targets. Introducing AM-Softmax loss function is introduced to reduce the intra-class variation and optimize the inter-class difference. Combining with F-measure in machine learning algorithm, an AMF-Softmax loss function is proposed to solve the problem of data imbalance. The experimental results show the …


Survey Of Vision-Based Augmented Reality 3d Registration Technology, Shouming Hou, Han Ji, Yudong Zhang, Ziqiu Zhu Dec 2019

Survey Of Vision-Based Augmented Reality 3d Registration Technology, Shouming Hou, Han Ji, Yudong Zhang, Ziqiu Zhu

Journal of System Simulation

Abstract: Three-dimensional registration technology is one of the core technologies for augmented reality system implementation. In recent years, with the maturity of augmented reality hardware technology and the expansion of application fields, vision-based three-dimensional registration technology has received more attention and development. This paper introduces the basic principles and classification methods of 3D registration technology, focuses on the analysis of the principles and research status of three kinds of visual three-dimensional registration technology based on artificial identification, natural feature points and model.Furthermore, the defects and treatment methods of three visual registration technologies are discussed. The development prospect of visual 3D …


Decision-Making Method For Formulating Spares Reserve Scheme Based On Deep Neural Network, Yunjing Zhang, Guangming Tang, Xiaoyu Xu Dec 2019

Decision-Making Method For Formulating Spares Reserve Scheme Based On Deep Neural Network, Yunjing Zhang, Guangming Tang, Xiaoyu Xu

Journal of System Simulation

Abstract: Spare parts classification is important for spare parts storage and is a key part of spare parts decision-making activities. This paper analyzes the factors affecting the reserve scheme of wartime spares. Then by analyzing the inherent attributes of wartime spares, two methods of spare parts classification are proposed to determine the variety and quantity of wartime spares based on deep neural network: (1) Ranks wartime spares according to their importance. A relatively simple deep neural network is used to analyze every attribute of the wartime spares in turn; (2) Inputs all the attributes of wartime spares into a relatively …


Urban Functional Area Identification Method Based On Mobile Big Data, Xiao Di, Xiaoyong Zhang, Hu Yang Dec 2019

Urban Functional Area Identification Method Based On Mobile Big Data, Xiao Di, Xiaoyong Zhang, Hu Yang

Journal of System Simulation

Abstract: With the rapid development of urbanization, the function of urban land is constantly evolving. It is of great significance to identify urban functional areas in real time and accurately. In recent years, accompanied by the popularity of smart phones and the rapid development of the Internet, mobile phones have become sensors of human activities. In this paper, a method of urban functional area identification based on time series mobile phone data mining and POI semantics analysis is proposed. The time series feature of remaining mobile phone positioning is extracted facing block scale. And a FCM clustering algorithm based …


Intelligent Fire Rescue Based On Internet Of Things And Virtual Reality, Fengting Yan, Zhicai Shi, Qianmin Su, Dong Jing, Jue Chen, Yunyu Shi, Tang Xian Dec 2019

Intelligent Fire Rescue Based On Internet Of Things And Virtual Reality, Fengting Yan, Zhicai Shi, Qianmin Su, Dong Jing, Jue Chen, Yunyu Shi, Tang Xian

Journal of System Simulation

Abstract: The integration of virtual reality, Internet of Things and artificial intelligence can provide intelligent WebVR interaction for fire rescue decision-making. However, it is necessary to solve the problems of data lightweight, real-time data transmission based on the Internet of Things, and visualization of fire scenario data on the web, and to build effective mechanisms and algorithms. This paper proposes an intelligent fire rescue (IVIFR) mechanism based on the integration of Internet of Things and Virtual Reality, gives a virtual intelligent fire rescue (VIFR) algorithm, and constructs a prototype system of intelligent fire rescue. The VIFR algorithm …


Rehabilitation Training System Of Vr-Based Speech Apraxia, Huanhuan Jiao, Zhigeng Pan, Shuchang Xu, Qingshu Yuan Dec 2019

Rehabilitation Training System Of Vr-Based Speech Apraxia, Huanhuan Jiao, Zhigeng Pan, Shuchang Xu, Qingshu Yuan

Journal of System Simulation

Abstract: Aiming at the problem that the enthusiasm of active training in patients with traditional speech apraxia rehabilitation is gradually weakened, a virtual reality-based rehabilitation training system for speech apraxia is designed. The system simulates the 26 monosyllabic pronunciation mouths shapes made by virtual human in Chinese and uses it for the learning module. It is proposed to identify 26 monosyllabic words by using the isolated word speech recognition algorithm, which improves the accuracy of speech recognition. The system includes a training module and a scene module for assisting the patient's pronunciation rehabilitation training. The evaluation results show that …