Engineering Commons^™

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 …

Low Power Visual Odometry Technology Based On Monocular Depth Estimation, Ma Rong, Qiurui Chen, Zhang Han, Mei Zheng, Wang Rui, Wei Wei

Journal of System Simulation

Abstract: With the development of artificial intelligence, precision machinery and computing technology, micro-unmanned system will play an important role in the future battlefield. To solve the lack of monocular visual odometry scale, micro robot power consumption and load limits, the monocular depth estimation technology is introduced and a low view dataset is collected. A convolutional neural network to predict depth information from a single image is built, and the structure of neural network model is optimized. The depth estimation with monocular visual odometry are combined and deployed on JetsonNano. Experiments show that the combined monocular visual odometry can recover scale …

Brief Review On Applying Reinforcement Learning To Job Shop Scheduling Problems, Xiaohan Wang, Zhang Lin, Ren Lei, Kunyu Xie, Kunyu Wang, Ye Fei, Chen Zhen

Journal of System Simulation

Abstract: Reinforcement Learning (RL) achieves lower time response and better model generalization in Job Shop Scheduling Problem (JSSP). To explain the current overall research status of JSSP based on RL, summarize the current scheduling framework based on RL, and lay the foundation for follow-up research, the backgrounds of JSSP and RL are introduced. Two simulation techniques commonly used in JSSP are analyzed and two commonly used frameworks for RL to solve JSSP are given. In addition, some existing challenges are pointed out, and related research progress is introduced from three aspects: direct scheduling, feature representation-based scheduling, and parameter search-based scheduling.

Survey Of Ship Detection In Video Surveillance Based On Shallow Machine Learning, Zhenbo Bi, Shiyou Zhang, Yang Hua, Yuanhong Wu

Journal of System Simulation

Abstract: At present, detection of ship targets in video surveillance based on shallow machine learning methods is still attracting attention in the fields of underwater cultural heritage protection, marine aquaculture, maritime traffic, and port management. This paper provides a review and discussion for this kind of ship detection methods. The ship target detection based on video surveillance is divided into five parts according to the key technologies involved: preprocessing, region of interest extraction, target segmentation, ship feature extraction and ship type recognition. According to different functional modules, the core problems involved in them are pointed out, and the core ideas, …

Real-Time Simulation Technology Of Fluid-Thermo-Solid Coupling Of Hypersonic Vehicle, Yunqin Liu, Li Ni, Luming Zhao, Jinpeng Bai, Tingjun Li, Chenguang Wang

Journal of System Simulation

Abstract: The solution of the coupling characteristics of fluid-thermo-solid physics in the modeling of hypersonic vehicle is an unavoidable difficulty, and the real-time simulation of fluid-thermo-solid coupling is particularly challenging. Aiming at the conflicting problem of solution accuracy and solution efficiency in fluid-thermo-solid coupling real-time simulation, a CFD (Computational Fluid Dynamics)/ CSD (Computational Structural Dynamics)-based fluid-thermo-solid coupling characteristic solution method is established, which realizes the high-precision solution of the fluid, temperature, and structural deformation field coupling. According to the multi-condition offline solution set modeling method, by accumulating a large number of offline solutions as effective support for online …

A Data-Driven Modeling Method For Game Adversity Agent, Zeng Bi, Fang Xiao, Deshuai Kong, Xiangxiang Song, Zhengxuan Jia, Tingyu Lin

Journal of System Simulation

Abstract: Aiming at the problems of collaborative modeling of formation behavior and intelligent generation of decision-making in complex confrontation scenarios, based on the serious game to simulate the confrontation scenarios of complex maritime equipment against the air, this paper proposes a data-driven modeling method for game agent and uses a distributed modeling technology of parallel adversarial scenarios and opportunistic decision making technology of smart targets to achieve agent modeling. It provides support for the further exploration of multi-objective collaborative modeling in complex confrontation scenarios. The simulation results show that deep reinforcement learning algorithms can provide a basis for the modeling …

Research On Usv Navigation Simulation Key Technologies, Jianhai Jin, Zexing Zhou, Zhang Bo, Yihong Chen, Xizhong Wei

Journal of System Simulation

Abstract: In order to solve the problems of long test time, high cost and high risk, a general framework of simulation system for autonomous navigation test and verification of USV(Unmanned Surface Vessel) has been developed, and some key simulation technologies such as complex scenario simulation, intelligent perception, navigation simulation and environmental effect modeling are researched. the dynamic equation, kinematics equation, wind load modeling, wave surface modeling, wave drift force modeling and ocean current modeling are designed and realized. The simulation system is proved to have high accuracy and fidelity by the real ship test on the lake, which can greatly …

Kinematics Analysis And Simulation Of Automatically Tracking Dental Surgery Lamp, Zerui Jiang, Lijun Yang, Li Jun, Xiaolong Jiao, Zheng Hang

Journal of System Simulation

Abstract: In order to solve the problem that the oral surgical lamp cannot automatically adjust the irradiation posture of the surgical lamp according to the face direction and oral cavity position, a six-degree-of-freedom automatic tracking visual manipulator solution is proposed. Coordinate conversion is achieved through binocular vision to obtain three-dimensional information of oral cavity position and face normal vector. The geometric method is introduced into the kinematics calculation, and the closed solution of the inverse kinematics is obtained. The correctness is verified by the Maltab programming and the introduction of numerical values. Five-degree polynomial motion planning is performed …

Research On Digital Twin-Based Modeling And Monitoring Of Five-Axis Grinder, Xiao Tong, Haifan Jiang, Guofu Ding, Jiang Lei, Shuwen Ma

Journal of System Simulation

Abstract: Aiming at the poor virtual-real interaction ability, single data presentation mode, and hysteretic abnormality handling in CNC machine tool status monitoring, a visual monitoring method for machine tool process based on digital twin is proposed, Which realizes the mapping of three subsystems of machine tool, machinery, control and electrical to the information space from three dimensions of geometry, logic and data. The verification of instructions and CNC programs, real-time status monitoring and abnormality handling during operation are carried out. A digital twin-based machine tool modeling and monitoring system is designed and developed. Taking a five-axis CNC …

Hyperspectral Rx Anomaly Detection Method Based On The Fusion Of Spatial And Spectral Feature, Liu Xuan, Xiangyang Li, He Fang, Jianwei Zhao, Fenggan Zhang

Journal of System Simulation

Abstract: To address the problem that the hyperspectral anomaly detection algorithm does not make full use of the spatial information of the hyperspectral image and the detection accuracy is limited, a FSSRX (Fusing Spatial and Spectral Reed-Xiaol) anomaly detection algorithm that fuses spatial and spectrum information is proposed to improve the accuracy of hyperspectral anomaly detection. In FSSRX algorithm, the spatial feature of hyperspectral images is firstly extracted by the EMAP(Extended Multi-attribute Profile) method and the abnormal score of each pixel in spatial features is then calculated with RX detector. Meanwhile, RX anomaly detection is carried out directly on the …

Research On Model Reuse Technology Based On Semantic Matching And Composition, Xingyu Tian, Guangxun Zeng, Yunbo Gao, Lili Ye, Guanghong Gong, Li Ni

Journal of System Simulation

Abstract: In order to solve the data barriers between the conceptual model and the simulation scenario of the combat system, the intelligent mapping and model reuse technology of the simulation scenario is researched. The conceptual model is analyzed using DOM technology. Based on the ontology theory, the knowledge base of the combat domain is constructed and the web crawler is customized to build the domain thesaurus. Through the SWRL rule library, the reasoning engine is called to realize the relational reasoning at the semantic level. An intelligent matching algorithm is designed to map the semantic relationship to the combination relationship …

Research On Cloud Tool Integration And Management Methods, Tianying Zhang, Ji Hang, Junhua Zhou, Tao Luan

Journal of System Simulation

Abstract: In response to the application needs of using professional tools to develop complex products in the fields of aerospace, aviation, weapons, ships, etc., it is urgent to implement centralized management of cloud tools and cross-professional sharing of tools through tool service-oriented methods, so as to solve issues such as inconsistent tool versions, cross-professional resource barriers, and high thresholds for tool mastery during the traditional model development process. By studying the integration and calling methods of cross-professional and different versions of self-developed tools, as well as methods of tool server operation control, authority management, etc., and taking the local …

Predictive Control Method Of Peak Hour Passenger Flow At Urban Rail Station, Xiaohe Li, Jianping Wu, Depin Peng

Journal of System Simulation

Abstract: With the rapid development of subway in China, the urban rail station, especially the transfer station, is prone to generate passenger congestion in the peak period. After analyzing the types of passenger flow in and out of the platform, a predictive control model of passenger flow is established based on the discrete linear quadratic optimal control theory. Taking Fuxingmen Station as an example, the simulation environment of the station is built by using the simulation software of Anylogic. The historical passenger flow data in peak period and the optimal passenger flow control sequence obtained by solving the passenger flow …

Study And Effect Evaluation On The Setting Of Contraflow Left-Turn At Intersections, Zhao Dan, Xuejun Niu, Shuhao Zhang, Jiaxu Wei

Journal of System Simulation

Abstract: Contraflow left-turn is one of the traffic organization ways at intersections. By analyzing the setting parameters of the contraflow left-turn, the length and the range of the contraflow left-turn lane, the constrained conditions of the contraflow left-turn are determined, and the applicable conditions are determined from the road, traffic and signal control. VISSIM software is used to analyze a road intersection, simulate and evaluate the indicators related to the intersection entrance, optimize the timing plan of contraflow left-turn lane, and validate the feasibility and advantages of contraflow left-turn lane. The results show that the intersection delays are reduced by …

Variety Recognition Based On Deep Learning And Double-Sided Characteristics Of Maize Kernel, Feng Xiao, Zhang Hui, Zhou Rui, Qiao Lu, Wei Dong, Dandan Li, Yuyao Zhang, Guoqing Zheng

Journal of System Simulation

Abstract: In order to construct a maize kernel variety recognition model with high recognition accuracy and suitable for mobile phone application, a mobile phone is used to obtain maize kernel double-sided (embryonic and non-embryonic) images. Based on the lightweight convolutional neural network MobileNetV2 and transfer learning, a maize kernel image variety recognition model is constructed. In view of the existing research methods are mainly for single-sided recognition of maize kernel variety, the performance of single-sided and double-sided characteristics modeling and recognition is compared. The results show that the double-sided recognition accuracy of maize kernel double-sided characteristics modeling is 99.83%, which …

Single Event Transient Sensitivity Measurement And Worst-Case Test Vector Exploration For Asic Devices Exposed To Space Single Event Environment, Mohamed Wael

Theses and Dissertations

Space radiation and nuclear reactors produce single event effects (SEE) in electronic circuits and impact their performance. The SEE phenomena cause circuits and electronic devices to fail by producing faulty results. Therefore, today’s circuit’s reliability is a significant concern for all circuit designers.

This thesis suggests a new automated flow to measure the single-event-transient (SET) effects in combinational circuits in application-specific integrated circuits (ASIC) while reaching full fault coverage. The developed flow characterizes the whole circuit nodes by identifying the most sensitive paths to the propagated SET pulses from the node under test to an observable primary output, causing single …

Q&Ai: Provost Margaret Mcfadden Discusses The New Davis Institute For Artificial Intelligence And How The Liberal Arts Can Shape The Future Of Ai, Laura Meader

Colby Magazine

Following the announcement in January of a $30-million gift from the Davis family and trustee of its charitable foundation Andrew Davis ’85, LL.D. ’15 to establish the Davis Institute for Artificial Intelligence, the first of its kind at a liberal arts college, Provost and Dean of Faculty Margaret McFadden sat down with Colby Magazine’s Laura Meader to better explain the institute and its developing academic program.

Self-Relabeling For Noise-Tolerant Retina Vessel Segmentation Through Label Reliability Estimation, Jiacheng Li, Ruirui Li, Ruize Han, Song Wang

Faculty Publications

Background Retinal vessel segmentation benefits significantly from deep learning. Its performance relies on sufficient training images with accurate ground-truth segmentation, which are usually manually annotated in the form of binary pixel-wise label maps. Manually annotated ground-truth label maps, more or less, contain errors for part of the pixels. Due to the thin structure of retina vessels, such errors are more frequent and serious in manual annotations, which negatively affect deep learning performance.

Methods In this paper, we develop a new method to automatically and iteratively identify and correct such noisy segmentation labels in the process of network training. We consider …

Graphene Oxide Functionalized Biosensor For Detection Of Stress-Related Biomarkers, Erican Santiago, Shailu Shree Poudyal, Sung Y. Shin, Hyeun Joong Yoon

Michigan Tech Publications, Part 1

A graphene oxide (GO)-based cortisol biosensor was developed to accurately detect corti-sol concentrations from sweat samples at point-of-care (POC) sites. A reference electrode, counter electrode, and working electrode make up the biosensor, and the working electrode was functional-ized using multiple layers consisting of GO and antibodies, including Protein A, IgG, and anti-Cab. Sweat samples contact the anti-Cab antibodies to transport electrons to the electrode, resulting in an electrochemical current response. The sensor was tested at each additional functionalization layer and at cortisol concentrations between 0.1 and 150 ng/mL to determine how the current response differed. A potentiostat galvanostat device was …

Physiological Signal Analysis For Emotion Estimation Of Children With Autism Spectrum Disorder, Janet Pulgares Soriano, Karla Conn Welch Phd

Posters-at-the-Capitol

The diagnosis of Autism Spectrum Disorder (ASD) in children is based on human observations by a clinician. The medical evaluation assesses deficits in social communication, social interaction, and restricted, repetitive behaviors. Robotic technology can assist in quantitatively measuring the observations to be used as a future tool for autism diagnosis and intervention. The project explores this technology to produce robotic partners that can adapt to the needs of the ASD population. This way, such robots could serve as instructors or learning peers. A friendly, partner robot, specifically designed for children with ASD could be used to investigate the effect of …

Uncertainties Induced By Processing Parameter Variation In Selective Laser Melting Of Ti6al4v Revealed By In-Situ X-Ray Imaging, Zachary A. Young, Meelap M. Coday, Qilin Guo, Minglei Qu, S. Mohammad H. Hojjatzadeh, Luis I. Escano, Kamel Fezzaa, Tao Sun, Lianyi Chen

Mechanical and Aerospace Engineering Faculty Research & Creative Works

Selective laser melting (SLM) additive manufacturing (AM) exhibits uncertainties, where variations in build quality are present despite utilizing the same optimized processing parameters. In this work, we identify the sources of uncertainty in SLM process by in-situ characterization of SLM dynamics induced by small variations in processing parameters. We show that variations in the laser beam size, laser power, laser scan speed, and powder layer thickness result in significant variations in the depression zone, melt pool, and spatter behavior. On average, a small deviation of only ~5% from the optimized/reference laser processing parameter resulted in a ~10% or greater change …

Lava Volume From Remote Sensing Data: Comparisons With Reverse Petrological Approaches For Two Types Of Effusive Eruption, Pauline Verdurme, Simon Carn, Andrew J.L. Harris, Diego Coppola, Andrea Di Muro, Santiago Arellano, Lucia Gurioli

Michigan Tech Publications, Part 1

Five effusive eruptions of Piton de la Fournaise (La Réunion) are analyzed to investigate temporal trends of erupted mass and sulfur dioxide (SO2) emissions. Daily SO2 emissions are acquired from three ultraviolet (UV) satellite instruments (the Ozone Monitoring Instrument (OMI), the Ozone Mapping and Profiler Suite (OMPS), and the Tropospheric Monitoring Instrument (TROPOMI)) and an array of ground-based UV spectrometers (Network for Observation of Volcanic and Atmospheric Change (NOVAC)). Time-averaged lava discharge rates (TADRs) are obtained from two automatic satellite-based hot spot detection systems: MIROVA and MODVOLC. Assuming that the lava volumes measured in the field are accurate, the MIROVA …

Spatters And Spills: Spreading Dynamics For Partially Wetting Droplets, Sylvia C. L. Durian, Sam Dillavou, Kwame Markin, Adrian Portales, Bryan O. Torres Maldonado, William T. M. Irvine, Paulo E. Arratia, Douglas J. Durian

Mechanical Engineering Faculty Publications

We present a solvable model inspired by dimensional analysis for the time-dependent spreading of droplets that partially wet a substrate, where the spreading eventually stops and the contact angle reaches a nonzero equilibrium value. We separately consider small droplets driven by capillarity and large droplets driven by gravity. To explore both regimes, we first measure the equilibrium radius vs a comprehensive range of droplet volumes for four household fluids, and we compare the results with predictions based on minimizing the sum of gravitational and interfacial energies. The agreement is good and gives a reliable measurement of an equilibrium contact angle …

Fabrication And Characterization Of A Ph-Sensitive Intelligent Film Incorporating Dragon Fruit Skin Extract, Nurnabila Afiqah Azlim, Abdorreza Mohammadi Nafchi, Nazila Oladzadabbasabadi, Fazilah Ariffin, Pantea Ghalambor, Shima Jafarzadeh, A. A. Al-Hassan

Research outputs 2022 to 2026

A novel intelligent pH-sensing indicator based on gelatin film and anthocyanin extracted from dragon fruit skin (Hylocereus polyrhizus) (DFSE) as a natural dye was developed to monitor food freshness by the casting method. Anthocyanin content of DFSE was 15.66 ± 1.59 mg/L. Dragon fruit bovine gelatin films were characterized by Fourier transform infrared spectroscopy (FTIR) and observed by a scanning electron microscope (SEM). Moisture content, mechanical properties, water solubility, water vapor permeability (WVP), light transmittance, color, and pH-sensing evaluations were evaluated for potential application. FTIR spectroscopy revealed that the extracted anthocyanin could interact with the other film components through hydrogen …

C2c Stem Collaboration, Mary Andrea Parish, Angela Renee Rowe, Annette Hines, Hannah Elizabeth Brewer

Posters-at-the-Capitol

Campus to Classroom is a STEM collaboration effort brought about by the brainstorming and continued efforts of Ms. Angela Rowe (MSUTeach), Ms. Annette Hines (Talent Search), MSUTeach STEM Ambassadors, and MSUExplore (MSUTeach student group).

The goal is an educational, collaborative partnership with cross-campus departments and both pre-service and in-service teachers, with a main focus on students from underserved population and communities.

Continued steps will be planned to develop a multi-level partnership with the end goals of increased usage of project-based instruction, incorporate research that increases STEM knowledge/skill, and encourage career exploration while building bridges from “campus and classroom”.