Artificial Intelligence and Robotics Commons^™

Boiler Combustion Optimization Based On Bayesian Neural Network And Genetic Algorithm, Haiquan Fang, Huifeng Xue, Li Ning, Fei Xi

Journal of System Simulation

Abstract: Neural network and genetic algorithm have been extensively used in boiler combustion optimization problems. But the traditional Back Propagation neural network's generalization ability is poor. The Bayesian regularization can improve the neural network's generalization ability. A boiler combustion multi-objective optimization method combining Bayesian regularization BP neural network and genetic algorithm （Bayes NN-GA）was researched. A number of field test data from a boiler was used to simulate the Bayesian neural network model. The results show that the thermal efficiency and NOx emissions predicted by the Bayesian neural network model show good agreement with the measured, and the optimal results show …

Optimization Model Of Cis Network Architecture Based On Information Flow, Jianhua Li, Junwei Zhao

Journal of System Simulation

Abstract: In order to explore the internal relationship between Command Information System (CIS) network and combat system, a layered combat system model was built, including organizational relationship layer, information interaction layer and communication link layer. Conception of the system coupling intensity was defined, which reflected the influence of network architecture to combat system. An optimization model of CIS network architecture aimed at maximizing the ratio of system coupling intensity to cost coefficient was built. A route programming genetic algorithm was designed and applied into simulation of Air Offensive Campaign (AOC) system network. The results show that the model and algorithm …

Cell Voltage Optimization Of Aluminum Electrolysis Based On Neural Network-Genetic Algorithm, Chenhua Xu, Li Zhi

Journal of System Simulation

Abstract: In order to reduce the production cost of electrolytic aluminum, an optimization extreme method was proposed based on neural network and genetic algorithm, to find the optimal production cell voltage and the corresponding production conditions. Using kernel principal component analysis method to determine the key parameters affecting of aluminum electrolysis production, a neural network model of electrolytic aluminum was established. Using the genetic algorithm, the global optimal value of the cell voltage of the electrolytic aluminum and the corresponding production conditions were found. The simulation results show that the neural network and genetic algorithm can predict the cell …

Study On Aircraft Scheduling Optimization Based On Improved Genetic Algorithm, Yaohua Li, Wang Lei

Journal of System Simulation

Abstract: Aircraft scheduling was studied, and an optimization model of aircraft assignment based on the objective function of maximize total profit was suggested. It considered its cost and benefits by combining fleet and aircraft. In the view of the feature of this model, the innovation of genetic algorithm chromosome was carried on, and these chromosomes formatted chromosome groups. The groups interior could cross over and mutate, and the probability of crossover and mutation could dynamically adjust in accordance with adaptive values to accelerate the convergence speed, the model was resolved fast in this way. In the process of simulation with …

Integrated Dynamic Equivalent Model Of Super Capacitor Energy Storage System, Xinran Li, Tingting Xu, Shaojie Tan, Xingting Cheng, Xiaojun Zeng

Journal of System Simulation

Abstract: As a high-power energy storage device, super capacitor (SC) is applied in micro-grid energy storage, secondary frequency regulation and peak load shifting in power system, and the research of which has become a hotspot. A second-order model of SC monomer suitable for the grid simulation was established, and the parameter identification using the charge and discharge experiment data under constant current and constant power modes was conducted based on genetic algorithm. A SC energy storage system has been set up in Simulink/Matlab based on the established second-order model of SC. The integrated dynamic equivalent model of SC energy storage …

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 …

Modeling And Simulation Of Mooring Force Prediction Based On Improved Ga-Bp Network, Shifeng Li, Zhanzhi Qiu

Journal of System Simulation

Abstract: According to the mooring security and early warning control requirement of the large open sea terminal, a ship mooring force prediction model based on genetic algorithm and BP network was studied. Environmental dynamic factors were considered and a model structure was determined by a weight statistics method; the learning method was improved by individual parent information and contemporary individual local gradient information; according to the improved model, a ship mooring force prediction method of the open sea terminal was proposed. The simulation results show that the performance of the prediction model has improved in the iteration number, …

Genetic Algorithm For Solving Multi-Objective Dynamic Flexible Job Shop Scheduling, Wang Chun, Zhang Ming, Zhicheng Ji, Wang Yan

Journal of System Simulation

Abstract: To solve the scheduling problem of mold workshop in a toy factory with dynamic and flexible features, a mathematical model was established by introducing virtual operation and virtual working hours. Based on the strategies of periodic scheduling combined with dynamic event scheduling as well as the rolling window scheduling operation technology, dynamic scheduling was transformed into several continuous static scheduling windows, under which multi-objective genetic algorithm was used to solve the model. The priority of operation scheduling was given in different dynamic events. In addition, the encoding and anti-encoding of chromosome's operation sequence were made based on the proposed …

Satellite Constellation Deployment And Management, Joseph Ryan Kopacz

Electronic Theses and Dissertations

This paper will review results and discuss a new method to address the deployment and management of a satellite constellation. The first two chapters will explorer the use of small satellites, and some of the advances in technology that have enabled small spacecraft to maintain modern performance requirements in incredibly small packages.

The third chapter will address the multiple-objective optimization problem for a global persistent coverage constellation of communications spacecraft in Low Earth Orbit. A genetic algorithm was implemented in MATLAB to explore the design space – 288 trillion possibilities – utilizing the Satellite Tool Kit (STK) software developers kit. …

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 …

Path Planning For Mobile Sink Based On Enhanced Ant Colony Optimization Algorithm In Wireless Sensor Networks, Shanshan Ji

Journal of System Simulation

Abstract: To reduce the energy consumption and sink mobile distance of mobile sink wireless sensor networks simultaneously, a path planning algorithm for mobile sink based on enhanced ant colony optimization algorithm in wireless sensor networks is proposed. Genetic operators are introduced to ant colony optimization algorithm in order to prevent ant colony optimization premature. The non-uniform of data distribution is considered as the constraint condition, the network lifetime and sink mobile distance are considered as a multi-objective problem, and the enhanced ant colony optimization is adopted to search the Pareto sub-optimal sets of rendezvous points. The simulation results show that …

Size Optimization Method Of 6r Manipulator Based On Global Maneuverability, Xianhua Li, Xuesong Shi, Lü Lei, Leigang Zhang, Song Tao

Journal of System Simulation

Abstract: Aiming at the six-DOF manipulator of service robot, the structure size parameters are optimized and analyzed. The global manipulability index of the manipulator workspace is defined, the coordinate system of the position and attitude is established, and the reachability of the position and attitude is calculated with the inverse solution of the manipulator, and the global manipulability index of the manipulator is proposed. Taking the maximum value of this index as the optimization target, the size parameters of the connecting rod of the manipulator are optimized by genetic algorithm, the size of the optimized connecting rod and the global …

Ads-B In Based Conflict Prediction And Conflict-Free Trajectory Planning For Multi-Aircraft, Siyuan Zhang, Xianying Li, Xiaoyun Shen

Journal of System Simulation

Abstract: For free flight of future, it is necessary to continuously detect conflicts and plan safe flight paths. Through in-depth analysis of detection principle of TCAS, combined with the characteristics of ADS-B data, the target within the scope of ADS-B IN surveillance is classified and given a risk factor, and the TCAS function is implemented in the ADS-B IN simulation software. For complex conflict scenarios with multi-aircraft, by meshing the conflict region and discretizing the flight procedure, the genetic algorithm is then used to calculate the optimal conflict-free trajectory based on risk factors. Two common multi-aircraft conflict scenarios are …

Multi-Channel Transmission Optimization Of Campus Internet Of Things Based On Pheromone Genetic Algorithm, Zhiyong Chen, Liu Hao

Journal of System Simulation

Abstract: Aiming at the difficulty in selecting and optimizing the multi-path transmission of campus Internet of Things information, an optimization algorithm of network multi-path transmission based on intelligent optimization algorithm is proposed. Based on the standard genetic algorithm and the concept of pheromone concentration in ant colony algorithm, this algorithm improves the global optimization ability and convergence efficiency by controlling the evolution direction of individuals, and designs and constructs an evaluation index mathematical model which conforms to the characteristics of multi-channel information transmission optimization in the Internet of Things. The mathematical model of the evaluation index realizes the multi-channel comprehensive …

Multi-Objective Operation Scheduling Optimization Of Shipborne-Equipment Based On Genetic Algorithm, Jinsong Bao, Zhiqiang Li, Yaqin Zhou

Journal of System Simulation

Abstract: Multi-objective operation scheduling of shipborne equipment is a complex combinational optimization problem under multi-task system. Existing research focuses mainly on single-objective optimization while several other objectives need to be considered during real operation such as path, duration, resource, etc. Considering the operation scheduling before exporting of an amphibious landing ship as the research object, both scheduling duration and resource requirement under the precedence constraint are optimized. The mathematical model of this multi-objective operation scheduling is established and solved using genetic algorithm. A fitness function which can be self-adaptively adjusted is designed; an adapting encoding strategy, a crossover operator, and …

Route Planning For A Fleet Of Electric Vehicles With Waiting Times At Charging Stations, Baoxiang Li, Shashi Shekhar Jha, Hoong Chuin Lau

Research Collection School Of Computing and Information Systems

Electric Vehicles (EVs) are the next wave of technology in the transportation industry. EVs are increasingly becoming common for personal transport and pushing the boundaries to become the mainstream mode of transportation. Use of such EVs in logistic fleets for delivering customer goods is not far from becoming reality. However, managing such fleet of EVs bring new challenges in terms of battery capacities and charging infrastructure for efficient route planning. Researchers have addressed such issues considering different aspects of the EVs such as linear battery charging/discharging rate, fixed travel times, etc. In this paper, we address the issue of waiting …

Current Sensor Fault Diagnosis For Induction Motor In Vector Control System, Sun Kai, Baina He, Sarah Odofin, Gu Yu

Journal of System Simulation

Abstract: A current sensor fault diagnosis method of induction motor in vector control system is proposed. A state-space form including sensor faults and environmental disturbances/noises of induction machine is described. An augmented observer is designed to simultaneously estimate system states, and current sensor faults. To attenuate the effects from the environmental disturbances/noises, a genetic algorithm is employed to design observer gain by minimizing the estimation error against environmental disturbances and noises. A simulation model based on Matlab and real-data of the induction motor collected by experiment is utilized to validate the proposed methods, which show the efficiency of the proposed …

Image Classification Based On Sparse Autoencoder And Support Vector Machine, Liu Fang, Lixia Lu, Hongjuan Wang, Wang Xin

Journal of System Simulation

Abstract: A new algorithm of image classification based on the sparse autoencoder and the support vector machine was proposed in view of the drawbacks that the single layer sparse autoencoder for feature learning is easy to lose the deep abstract feature and the features lack the robustness. The deep sparse autoencoder is constructed to learn each image layer and the feature of each layer is automatically extracted. The each feature weights and the reorganized set of feature are obtained according to the feature weighting method. By combining the strong global search ability of genetic algorithm and the excellent performance of …

Modeling And Simulation Of Pid Networked Control Systems Based On Neural Network, Zhanzhi Qiu, Shifeng Li

Journal of System Simulation

Abstract: According to the problems of the delay compensation and PID parameters tuning of networked control systems, a class of rapid PID networked control systems based on improved BP network was proposed. Considering the problems of obtaining hidden layer nodes number and local optimum of the BP network delay prediction model, a calculation method was proposed to obtain hidden layer nodes number, and an improved genetic algorithm was proposed to train the BP network. Considering the problems of integral saturation, parameters tuning and model mismatch of the PID network control systems, a PID parameter adjuster was designed based on …

Simulation Of Wind Power Prediction Based On Improved Elm, Wang Hao, Wang Yan, Zhicheng Ji

Journal of System Simulation

Abstract: To predict the range of ultra-short-term wind power fluctuation effectively, a combined forecasting model based on fuzzy information granulation (FIG) and genetic algorithm optimization extreme learning machine (GA-ELM) is proposed. The parameters of wind power are granulated by fuzzy information, and the corresponding valid information including the maximal value, the minimum value, and the general average value in time series window is further extracted. By integrating the effective components of each parameter as training samples, the GA-ELM-based prediction model is established. The range of wind power fluctuation in next time series is forecasted through using the optimized model. The …

Improved Bp Neural Network Of Heat Load Forecasting Based On Temperature And Date Type, Li Qi, Zhao Feng

Journal of System Simulation

Abstract: The heat load forecasting provides data support for urban district heating systems, which is the basis of need-based heating. The change of heat load is greatly influenced by various exterior factors, especially the outdoor temperature. To meet demand of heating system, save energy and balance the comfort of human body, a kind of improved BP neural network method is proposed by temperature and date type. The temperature and date type are quantified and the heat load forecasting model is established by using BP neural network. To guarantee prediction accuracy, the genetic algorithm is used to optimize the weights and …

Simulation Optimization On Multi-Ports Slot Plan Problem Considering Dispatching Sequence Of Containers In Yard, Zhang Yu, Huimin Cheng, Xu Jin, Tian Wei, Junfeng Sun

Journal of System Simulation

Abstract: The multi-ports slot plan problem considering dispatching sequence of containers in yard is solved by an integer linear programming model, which minimizes heeling moment. The influences of different dispatching rules on solving the problem are simulated and analyzed through the programming model. Accordingly, a simulation optimization model based on genetic algorithm is constructed in order to enhance the computational efficiency. The simulation optimization model simulates the process of dispatching containers and loading vessel. The feasible solution is constructed through rules sets and inputted into the optimization model. An efficient encoding and decoding solutions are developed in genetic algorithm, …

Fuzzy Sliding Backstepping Mode Control For Flight Simulator Servo Based On Friction And Disturbance Compensation, Huibo Liu, Shanglei Liu

Journal of System Simulation

Abstract: Considering friction, modeling errors and other uncertainties of flight simulator servo system, a compensation strategy which combines model-based friction compensation with nonlinear disturbance observer compensation was proposed. First, the friction is modeled , whose parameters are identified by using genetic algorithm, and using the identified model to compensate. Second, using a nonlinear disturbance observer to estimate the modeling errors, friction less-compensation or over-compensation and other uncertainties, and using this observed value to compensate. The system adopted sliding backstepping controller to ensure the stabilization of the system. Finally, the fuzzy algorithm is adopted to adjust the switching gain of sliding …

Modeling And Simulation Of Networked Control Systems Based On Improved Bp Network, Shifeng Li, Zhanzhi Qiu, Liping Fan, Lina Zhao

Journal of System Simulation

Abstract: In the circumstance where both the delay model and the controlled object model were unknown in networked control systems, a class of networked predictive control systems based on improved BP network were studied. For the problem of obtaining the hidden layer nodes number of BP network, a rapid calculation method was proposed. For the problem of avoiding local optimum of BP network, a hybrid learning method was proposed. A off-line BP network model was proposed for coping with the problem of the delay prediction based on the above algorithms. For the problem of the linear …

Leveraging The Trade-Off Between Accuracy And Interpretability In A Hybrid Intelligent System, Di Wang, Chai Quek, Ah-Hwee Tan, Chunyan Miao, Geok See Ng, You Zhou

Research Collection School Of Computing and Information Systems

Neural Fuzzy Inference System (NFIS) is a widely adopted paradigm to develop a data-driven learning system. This hybrid system has been widely adopted due to its accurate reasoning procedure and comprehensible inference rules. Although most NFISs primarily focus on accuracy, we have observed an ever increasing demand on improving the interpretability of NFISs and other types of machine learning systems. In this paper, we illustrate how we leverage the trade-off between accuracy and interpretability in an NFIS called Genetic Algorithm and Rough Set Incorporated Neural Fuzzy Inference System (GARSINFIS). In a nutshell, GARSINFIS self-organizes its network structure with a small …

An Improved Smote Algorithm Based On Genetic Algorithm For Imbalanced Data Collection, Qiong Gu, Xian-Ming Wang, Zhao Wu, Bing Ning, Chun-Sheng Xin

Electrical & Computer Engineering Faculty Publications

Classification of imbalanced data has been recognized as a crucial problem in machine learning and data mining. In an imbalanced dataset, minority class instances are likely to be misclassified. When the synthetic minority over-sampling technique (SMOTE) is applied in imbalanced dataset classification, the same sampling rate is set for all samples of the minority class in the process of synthesizing new samples, this scenario involves blindness. To overcome this problem, an improved SMOTE algorithm based on genetic algorithm (GA), namely, GASMOTE was proposed. First, GASMOTE set different sampling rates for different minority class samples. A combination of the sampling rates …

A Heuristic Evolutionary Method For The Complementary Cell Suppression Problem, Hira B. Herrington

CCAC Theses and Dissertations

Cell suppression is a common method for disclosure avoidance used to protect sensitive information in two-dimensional tables where row and column totals are published along with non-sensitive data. In tables with only positive cell values, cell suppression has been demonstrated to be non-deterministic NP-hard. Therefore, finding more efficient methods for producing low-cost solutions is an area of active research.

Genetic algorithms (GA) have shown to be effective in finding good solutions to the cell suppression problem. However, these methods have the shortcoming that they tend to produce a large proportion of infeasible solutions. The primary goal of this research was …

Genetic Algorithm Based Model In Text Steganography, Christine K. Mulunda, Peter W. Wagacha, Alfayo O. Adede

The African Journal of Information Systems

Steganography is an ancient art. It is used for security in open systems. It focuses on hiding secret messages inside a cover medium. The most important property of a cover medium is the amount of data that can be stored inside it without changing its noticeable properties. There are many sophisticated techniques with which to hide, analyze, and recover that hidden information. This paper discusses an exploration in the use of Genetic Algorithm operators on the cover medium. We worked with text as the cover medium with the aim of increasing robustness and capacity of hidden data. Elitism is used …