Operations Research, Systems Engineering and Industrial Engineering Commons^™

Simulation Of Rocket Exhaust Plumes Recognition Based On Dynamic Time Warping, Liu Hao, Hongxia Mao, Zhihe Xiao, Liu Zheng

Journal of System Simulation

Abstract: By analyzing the infrared radiation characteristics of the rocket exhaust plumes and summarizing the changing law of the radiant intensity sequence, an improved recognition algorithm based on Dynamic Time Warping algorithm is proposed. In order to improve the effect of sequence shape similarity measurement, the distance matrix and matching path are calculated by the derivative sequence, and the distance is recalculated according to the matching path and radiant intensity value. The problem of path matching affected by the non-uniformity of observation sequence length is solved to a certain extent by using the prefix and suffix relaxation factors. The simulation …

Engine Wear Fault Diagnosis Based On Supervised Kernel Entropy Component Analysis, Zhichao Zhu, Dinghui Wu, Yuanchang Yue

Journal of System Simulation

Abstract: Focus on the influence of environment on engine operation, which leads to a large amount of redundant information and nonlinear structure in oil spectral data that affects the engine fault diagnosis results, the feature extraction method of SKECA (supervised kernel entropy component analysis) is proposed. A supervised learning algorithm is adopted on the basis of Kernel Entropy Component Analysis, which extracts the inherent geometric features of oil spectrum data to make the extracted fault features include the discriminative information. GA (genetic algorithm) is used to find parameters to optimize the results of feature extraction, and SVM (support vector machine) …

Visual Analysis Of Cross-Domain Association Of Time-Series Data, Beibei Han, Yingmei Wei, Yujie Fang, Shanshan Wan

Journal of System Simulation

Abstract: Time series data is the important research object of data mining. The current visual analysis technology of time series data rarely conducts the cross-domain correlation. The development and evolution of statistical time series data in the spatio-temporal domain and the text theme data in the cognitive domain cannot be simulitaneously supervised in a unified view. The user's visual analysis process based on cross-domain time series data is abstracted and a visual analysis process model is proposed. A multi-view collaborative cross-domain correlation visual analysis tool is designed on the basis of the model. The case study of epidemic time …

Uncertainty Simulation Method Based On Deep Bayesian Networks Learning, Nie Kai, Kejun Zeng, Qinghai Meng

Journal of System Simulation

Abstract: There are lots of uncertain elements in battlefields situation assessment and the uncertainty simulation would enhance the ability of situation assessment. A deep variational autoencoder bayesian networks (BN) model with memory module is proposed aiming at the problem of being unable to represent the uncertainties exactly caused by the various combat objects and more uncertain elements. Based on the deep BN learning, the situation assessment model is designed from the deep generative model. The principle of deep generative model mixing with the memory module is discussed and the leaning and reasoning process of the model is explained. The proposed …

Optimization And Prediction For Multi-Robot Combination Maximum Coverage Area, Yutong Wang, Shiwei Ma, Yuanrui Yang, Chaoyu Chen

Journal of System Simulation

Abstract: Aiming at the optimal control of the multi-robot combination maximum coverage area, based on the intensity radial attenuation disc model and following the superposition principle, a method for estimating, optimizing and predicting the effective coverage area of the multi-robot combination is proposed. The Monte Carlo method is used to estimate the effective coverage area of the robot combination, and the multiple population genetic algorithm is used to obtain the maximum effective coverage area of the combination, and the support vector machine regression is used to predict the relationship between the number of robots and the maximum effective coverage area. …

Research And Implementation Of On-Board Human Factors Collaborative Simulation System, Changqing Yin, Tianran Tan, Jianmin Wang

Journal of System Simulation

Abstract: In order to improve the multi-vehicle evaluation and follow the trend of the Internet of Vehicles in modern vehicle-road collaborative system, an on-board human factors collaborative simulation system is built. Distributed theory is used to establish a joint platform for vehicle simulation, and an on-board human factors co-simulation system is built and MQTT network is used to optimize the data distribution mechanism and data collection mechanism. The simulation experiment shows that the built on-board human factor co-simulation platform reduces the coupling between the participating experimental subsystems and the main system, and has good robustness and flexibility. The distributed data …

Research On Optimal Allocation Method Of Aircraft Towing Rules Based On Multi-Agent, Zhao Zheng, Hu Li, Yuanyuan Qian, Jin Hui, Aiping Jia

Journal of System Simulation

Abstract: In order to study and optimize the effect of aircraft towing rules on aircraft on bridge rate and flight normality, a towing rule configuration method based on surface capacity and demand balance is proposed. By constructing a multi-agent discrete simulation model based on surface operation, the collaborative optimization effect of aircraft on bridge rate and flight regularity is achieved, and which is verified by the example of Beijing Daxing International Airport. The results show that the towing rule configuration method based on airfield capacity and demand balance can obviously improve the aircraft on bridge rate and flight normality, …

Inpatient Discharge-By-Noon: Are Fewer Better Than All?, Nicholas Ballester, Pratik J. Parikh, Kara Combs, Jordan S. Peck

Journal of Maine Medical Center

Introduction: To address boarding in hospital emergency departments, discharge-by-noon could free up inpatient beds earlier in the day. However, discharging all patients by noon can heavily burden inpatient units and may not be feasible. In this study, we determine the number of discharges after which the benefits of an additional discharge-by-noon diminish.

Methods: We conducted a simulation analysis to quantify how occupancy rate, mean daily number of discharges, and peak discharge time impact upstream boarding time in an inpatient neurology unit at Maine Medical Center. Using a day-of-discharge simulation model with one year of retrospective data, we assessed configurations approximating …

Simulation Research On U-Automated Container Terminal, Ding Yi, Tiantian Li

Journal of System Simulation

Abstract: To analyze the new U-layout effect on the handling operation efficiency in automated container terminal, the U-automated container terminal simulation model is established by FlexTerm software to visualize the handling operation process. The traditional automated terminal simulation model is established to compare the working efficiency under different working modes. The working ability of terminal handling equipment such as AGV（Automated Guided Vehicle）, yard cranes and rail-mounted gantry cranes are compared by simulation tests. Simulation results show that due to the creation of yard layout and handling technology, the superiority of U-layout is proved when the working efficiency of each handling …

Intelligent Control Of Wastewater Treatment Processes Based On Adaptive Immune Optimization, Li Fei, Su Zhong

Journal of System Simulation

Abstract: In order to solve the problems of excessive energy consumption and excessive effluent quality in wastewater treatment process control, an intelligent control system based on adaptive immune optimization (AIOIC) is proposed. A hierarchical control strategy is designed, and a fast online self-organizing fuzzy neural network based on singular value decomposition (SVDFNN) is used to construct the mathematical model of wastewater treatment energy consumption and effluent quality. In order to obtain the optimal set values of dissolved oxygen and nitrate nitrogen, an adaptive hybrid evolutionary immune optimization algorithm is designed. The self-organizing recursive fuzzy neural network controller is used …

Track Deception Modeling Method Based On Multi-Jammer Cooperation, Wang Rui, Xiangyang Li, Zhili Zhang, Hongguang Ma

Journal of System Simulation

Abstract: The false track generated by the jammer formation is an effective interference measure against networked radars. This paper starts from the basic principle of false track generation and presents the model of the measurement error of the radar for the false track and the control error of the jammer formation. It also presents an analysis of the effects of these errors on the false track. The effectiveness of the false track is further analyzed through the confrontation scenario between the rectangular front formation of a certain type of equipment and networked radars. The simulation results show that the false …

Research On Supply Chain Recovery Strategy Under Disruption Risks, Yang Yi, Peng Chen, Yujiu Yang, Yulong Wang

Journal of System Simulation

Abstract: Aiming at supply chain disruptions, two effective supply chain recovery strategies are proposed, namely, a supplier’s preset emergency inventory strategy and a manufacturer’s product change strategy, meanwhile, emergency inventory storage cost and products return rate after change are also taken into consideration. In order to maximize the manufacturer’s profit and customer satisfaction, a single-objective model and a bi-objective model are established, respectively. The optimization problems in the two models are transformed into mixed integer programming problems, moreover, corresponding solution algorithms are presented based on ILOG CPLEX. The simulation results show that the disruption recovery strategies proposed can not only …

Radar Emitter Signal Identification Via Distance Features, Yingkun Huang, Weidong Jin, Yan Kang, Jiehao Zhu

Journal of System Simulation

Abstract: Aiming at the problem that traditional recognition methods of radar emitter signal have low accuracy in low signal to noise ratio (SNR) environment, and are usually suitable for only several specific radar signals, an identification approach of radar signal based on distance features is proposed. Several cluster centers are extracted via the k-means algorithm, and the Dynamic Time Warping (DTW) values between the radar signal and the cluster center are calculated respectively, which are combined as the input features of k-Nearest Neighbor (k-NN) algorithm. The simulation results show that when the SNR is 3 dB, the identification rate …

An Evolutionary Multi-Objective Simulation Optimization Algorithm For Supply Chain With Uncertain Demands, Hongfeng Wang, Yitian Zhang, Jingze Chen

Journal of System Simulation

Abstract: During the COVID-19 pandemic, supply chain of manufacturing companies is facing more severe product demand uncertainty, which is manifested in the sharp increase in demand for certain types of products and the increased fluctuations in supply for raw materials. For this supply chain optimization problem with demand uncertainty, a multi-objective stochastic programming model is developed in order to maximize the total profit and product order fulfillment rate simultaneously in this paper. For solving the investigated problem, a new evolutionary multi-objective simulation optimization algorithm is proposed by combining the mechanism of NSGA-II and simulation computing budget allocation adaptively. Experimental …

Research On Detection Data Driven Calibration Method Of Traffic Simulation Parameters, Wenxin Ma, Ruimin Li

Journal of System Simulation

Abstract: To improve the accuracy of traffic simulation model and timely response of traffic demand and driving behavior changes, dynamic calibration method of simulation parameters based on detection data is proposed. Dynamic interaction between detection data and simulation platform is proposed. Intersection of Guanghua Road/Jintong East Road in Beijing and five consecutive intersections on Youyi Street in Baotou are Selected as study cases. Sensitivity analysis is conducted on initial parameter combinations. Based on the analysis results, parameters to be calibrated are selected. Models of cases are developed in VISSIM and driving behavior parameters are calibrated. Simulation results show that …

Weld Bead Size Prediction Of Wire And Arc Additive Manufacturing Based On Acs-Dbn, Dong Hai, Xiuxiu Gao, Mingqi Wei

Journal of System Simulation

Abstract: Welding pass overlap is the essence of wire and arc additive manufacturing (WAAM) technology. Appropriate process parameter selection is of great significance to control the welding pass geometry and improve the dimensional accuracy of the molded parts. A prediction model of deep beilef network (DBN) optimized by adaptive cuckoo search (ACS) algorithm is constructed. The welding width and residual height of the weld pass are predicted based on the four technological parameters of the given nozzle height, welding current, welding speed and wire feeding speed. The optimal number of hidden layers and hidden elements are determined based on the …

Study On Prediction Of Crystal Properties Based On Deep Learning, Buwei Wang, Wang Min, Fan Qian, Ya'nan Wang, Hanwen Zhang, Yunliang Yue

Journal of System Simulation

Abstract: Predicting crystal properties using traditional machine learning methods requires complex feature engineering. In order to bypass time-consuming feature engineering, element network (ElemNet), representation learning from stoichiometry (Roost), compositionally-restricted attention-based network (CrabNet) and crystal graph convolution neural network (CGCNN) based on deep learning technology are used to simulate the formation energy, total energy per atom, band gap, and Fermi energy of crystal. The residual learning is introduced into CGCNN, and a crystal graph convolution residual neural network (CGCRN) is proposed. In the CGCRN, the number of hidden layers and the number of nodes in the hidden layers are increased, …

Improved Ant Colony Optimization Algorithm For Jamming Resource Allocation, Qingyun Wang, Dezhong Jiao, Shi Shuo, Genyan Peng, Junhua Sun, Yuxin Duan

Journal of System Simulation

Abstract: Ant Colony Optimization (ACO) is a new intelligence optimization algorithm. When applied to jamming resource allocation, the velocity of convergence in optimization process is slow and the probability of obtaining the global optimal solution is low. In order to raise the efficiency of jamming resource allocation and the probability of getting global optimal solution, the attenuation factor is improved to a variable that changes according to the exponential function in optimization process. The attenuation factor is taken as a relatively small value in the initial search phase, and increases monotonically and exponentially as the number of iterations increases. Simulation …

Research On Semi-Physical Simulation Model Of Special Vehicle Cockpit With Force Feedback, Liang Feng, Zhili Zhang, Xiangyang Li, Yihao Li, Wang Bei, Long Yong

Journal of System Simulation

Abstract: To improve the interaction and immersion of cockpit simulation training system, a semi-physical model of special vehicle cockpit with force feedback is studied. The important force feedback parts of the semi-physical simulation model are designed to provide more real operation experience for operators. The simulation training method of special vehicle cockpit based on dynamic model is studied to match the action input of operators with scene changes and provide a high fidelity visual experience. The driving simulation operation process of special vehicle is analyzed and verified. Simulation experiments show that the model has the characteristics of high precision, fast …

Special Vehicle Driving Training Simulation System Based On Integration Of Virtuality And Reality, Xiangyang Li, Wang Xiao, Zhili Zhang, Yihao Li, Long Yong

Journal of System Simulation

Abstract: Aiming at the actual demands of special vehicle driving training, special vehicle driving training simulation system is designed and developed based on the integration of virtuality and reality mode. Through building all kinds of mathematical models, functional modules, workflows and control software, and applying the cab that same as actual equipment with manipulating device, central control instrument and driving seat, immersive driving training environment with integration of virtuality and reality is established based on 6-DoF motion platform and its control system as well as multi-channel visual display device. It can provide the integrated support platform with “educating, training and …