Search

Actuator faults, which are common in industrial processes, can make the controller fail to achieve the desired control objectives, which may lead to the degradation of control performance. In order to solve this problem, this paper proposes a predictive functional control based on genetic algorithm optimization. Firstly, an extended dimension discrete switched model is constructed, which consists of a state difference variable, tracking error and a new state variable including tracking error. In this model, the performance index function based on a genetic optimization algorithm is selected, and its parameters are adjusted and the controller is designed. Then, under the obtained control law, the switching signal is designed and the range of uncertainty caused by the actuator fault is given to realize the robustness of the system. At the same time, the corresponding robustly sufficient conditions are presented. The advantage of this design is to avoid the disadvantages of manually adjusting the performance parameters, and the system has good tracking performance. Finally, taking the typical injection molding process of chemical production process as an example, the speed and pressure parameters are controlled, and compared with the traditional control method, the effectiveness and feasibility of the proposed method are verified.

Interweave Dynamic spectrum sharing is adistributive opportunistic spectrum access for wireless users to access the spectrum any time dynamically. This proposed approach provides a spectrum allocation technique to the users based on a multi-objective genetic optimization algorithm in interweave mode of spectrum sharing. The multiple objectives targeted are minimizing BER, minimizing Power consumption, and maximizing the Throughput. The proposed algorithm is compared with the existing Brute force algorithm and provides a gradual increase in the fitness value for an increase in the transmission BW.

Genetic optimization algorithm for construction and realization path of the precision funding for colleges with data monitoring model is defined in this paper. For the efficient designing of the robust model, considering information of the different individuals cannot be exchanged directly, because the relationship between genes and individuals is very close, so the crossover operation in genetic algorithm cannot be used here. In order to obtain the optimal solution of the multi-objective problem, it is necessary to then make necessary coordination and compromise when optimizing each sub-objective. With this assistance, this research work will further apply the model into the study of the path estimation. The systematic performance is validated with the test on the robustness and efficiency.

The optimal transmitter position for maximum WIFI coverage in a residential home is investigated. A 60-GHz, 32 by 32 patch array antenna is implemented as the transmitter and the receiver antennas. The receivers are placed in each room of the home at equally spaced distances. The power received by each receiver is taken into account. By using genetic algorithm optimization in parallel, the optimal transmitter position is chosen as the one with the minimal number of receivers having received power less than −87.5 dBm. The GA chosen position results in acceptable received power at all but six receiver positions.

This paper uses PCA (principal component analysis) combined with bp neural network and neural network based on genetic algorithm optimization to predict Shanghai’s AQI (air quality index) respectively. Matlab is used for modeling and simulation. which the prediction and analysis are different The error value and the number of iterations under the algorithm. The results show that the neural network optimized by genetic algorithm can effectively reduce the prediction error of the air quality index compared with the combination of PCA and bp neural network, making the optimized neural network prediction accuracy rate of 90.7%, greatly improving the neural network The learning efficiency has a good performance in predicting the air quality in Shanghai.

Considering the air-condition system is difficult to realize the dynamic control of indoor thermal comfort, this paper put forward a new type of fuzzy controller design based on genetic algorithm optimization. At first, a genetic algorithm is used to optimize the fuzzy rules of the traditional fuzzy control, realize the design of the air conditioning fuzzy controller. Then the optimized fuzzy air conditioning controller is acted on the indoor environment. Finally, a simulation and experimental test is used to verify the validity of the method. The results show that the fuzzy controller for real-time control is effective on the indoor thermal environment and is suitable for the non-linear indoor environment system.

Distribution networks (DN) have transformed more than ever before due to the penetration level of distributed energy resources. One of the promising technologies to generate power at the consumer level is the photovoltaic system (PV). To facilitate a higher level of PV penetration, DN planning and system operators encounter several challenges related to power reliability, stability, and quality that are affected by the intermittent nature of PV. A practical solution to overcome the uncertainty behavior of PV s is to use a Battery Energy Storage System (BESS). However, the appropriate placement of the BESS in the DN plays a significant role to mitigate the higher level of power losses. Hence, optimal allocation is extremely desirable to maximize the benefits of BESS. In this paper, the optimal allocation of BESS in a DN with a high penetration level of the PV system is examined towards power losses reduction. The optimal allocation of BESS in DN performed using a genetic algorithm optimization technique. The optimal placement of BESS in DN was compared between an aggregated BESS and distributed BESS. The outcomes of both of them showed a reduction in power losses, where the optimal allocation in distributed BESS has the highest power losses reduction.

In order to improve the safety, comfort and economic performance during the braking process of electric vehicles, the electro-mechanical composite braking force control system was designed by the consideration of driver's intention, vehicle state and its driving environment. Firstly, apply the fuzzy control theory in the identification of driver's braking intention, and using the identification results to adjust the braking force and regenerative braking force . Then establish The regenerative braking force correction system to control the regenerative braking force within a reasonable range according to the change of the main influencing factors; Finally, with the goal of economic optimization and constraint of relevant laws and regulations, using the genetic algorithm to optimize the electromechanical compound braking force distribution scheme . The simulation results show that under the control of this new method ,the vehicle brake safety, comfort and economy performance are all improved.

Correlation electromagnetic analysis(CEMA) is one of the most powerful ways in side channel analysis. Because it don't need to modify the target device and even can be measured at distance. But in the real scenarios, only those interesting points relevant to the target intermediate value is helpful to recover the secret key. In this paper, we proposed a novel method based on genetic algorithm to select the interesting points, and the hamming distance between S-Box input and S-Box output in first round is chosen as the target intermediate value. We perform our experiment on Sakura-G board against AES-128 algorithm. Our experiment result shows our method is more effective which decreases about 9.1% in trace number than traditional CEMA for AES crypto algorithm to recover the secret key.

This paper considers the damping of the local-mode power system oscillation using Lead-Lag power system stabilizer (PSS). Thus, a simple single-machine infinite-bus power system is used. The Lead-Lag PSS parameters are tuned using Genetic Algorithm Optimization (GAs). Simulation results are presented with and without the proposed controller. Also, a comparison study is presented when using the conventional Lead-Lag PSS, Simple Genetic Algorithm Optimization-based PSS, and when using the Improved Genetic Algorithm Optimization-based PSS. The results obtained show the significance of using improved Genetic Algorithm Optimization as compared to using conventional PSS and Simple Genetic Algorithm based PSS.

This paper addresses the challenging problem of coordinated control of regional road network traffic signals. By analyzing the dynamic characteristics of regional road network traffic flow, we propose a regional vehicle delay model and establish the objective function of minimizing the vehicle average delay. Considering the high-dimensional characteristics of the objective function, a chaos genetic optimization algorithm is proposed to improve the efficiency of global optimization. Finally, we implement the real-world road network micro-simulation experiment to demonstrate that our proposed delay model and coordinated optimization method can effectively improve the traffic efficiency of the regional road network.

Direct alcohol fuel cells are one of the suitable candidates for sustainable power generation in portable applications. Among the different alcohol types that can be used in these fuel cells, DME, which is almost non-toxic at room temperature and easy to liquefy, and has a molecular structure similar to methanol, is one of the suitable options. For this reason, many studies have been carried out to develop direct dimethyl ether fuel cell (DDMEFC). Mathematical modeling studies also play an important role in the development of DDMEFC since they enable the understanding of the performance of the fuel cells more thoroughly. In this study, a model has been developed by using the principles of conservation chemical species and electrochemistry. A modeling study was performed using MATLAB. The values of some modeling parameters were estimated using the genetic algorithm optimization technique.

Aiming at the problems of long average waiting time of customers and long running distance of stacker during the scheduling of roadway stacking automatic stereoscopic garage, the goal of improving the operating efficiency of the stereoscopic garage is proposed by shortening the average waiting time of customers and the running distance of stacker. Through the analysis of the actual garage operation characteristics and the process of accessing the vehicle, a stereoscopic garage queuing model is established. The beam search based on improved genetic algorithm optimization is proposed to optimize the stacker running path, and then the results obtained by optimization algorithm are compared with those obtained by beam search algorithm. The simulation results show that the average waiting time of customers can be significantly reduced and the operation efficiency of the stereoscopic garage can be improved by using beam search based on the improved genetic algorithm to optimize the stacker’s running path.

Cloud manufacturing platform collects customers' orders and manages distributed manufacturing resources to accomplish orders, then transports products to customers. This paper discusses collaborative production planning problem between multi-enterprises in the cloud-manufacturing platform. We have presented a collaborative production-planning model for integrating order splitting and production planning decisions. This model could give two decisions: (1) which orders should be split, and the fraction of each order processed at each enterprise. (2) In which periods the order processed at the enterprise. A genetic algorithm optimization-based approach is developed to address the problem. Finally, an improved genetic algorithm-based approach is developed to address the problem.

This study aims to design a control scheme that is capable to improve performance and efficiency of brushless DC motor (BLDC) in operating condition. The control scheme is composed of sliding mode controller (SMC) with proportional-integral-derivative (PID) sliding surface. The PID sliding surface is used to improve the system transient response. Then, the SMC-PID is optimized by genetic algorithm optimization for further improvement on the stability and robustness against nonlinearities and disturbances. Chattering problem that appear in the SMC is minimized by employing an adaptive switching gain for the SMC that is integrated with Luenberger Observer. Lyapunov function candidate is applied to guarantee the stability of the system. Simulation on the proposed work is done in Matlab Simulink. Results of the simulation works indicate that the proposed control scheme can improve the transient response, the stability and robustness of the BLDC motor compared to the conventional SMC in the existence of nonlinearities and disturbances.

IEEE PES Asia-Pacific Power and Energy Engineering Conference (APPEEC) -- OCT 07-10, 2018 -- Kota Kinabalu, MALAYSIA WOS: 000455030900038 In PV systems, it is usually expected that power generation under varying conditions at any time should be maximum as much as possible. Therefore, it is essential to build a circuit model based on a widely used single or double diode model under instantly varying conditions with minimum estimation error through the measured values in the manufacturers' data sheet. It is fact that these approximate circuits models ease the performance analysis of PV systems if the unknown parameters are accurately estimated at various temperatures and unchanged irradiance levels or vice versa. This paper comparatively studies the performances of the two approximate circuit models for the four types of PV modules using the real-coded genetic algorithms. The results indicated that I-V characteristics obtained from the identified parameters exhibit almost similar trend with those given in manufacturers' data sheets under the same conditions. Besides, the estimated parameters obtained from using both models slightly show difference from each other and it can be said that the single diode model is solely satisfactory to model a typical PV model as long as they are accurately estimated. IEEE Power & Energy Soc, IEEE, Cenergi, Tenaga Nas, Tamco Switchgear Malaysia Sdn Bhd, Larsen & Toubro Grp Co, Sher Engn & Consultancy, Adv Power Solut Sdn Bhd, Ranhill, Limitless Green Energy Sdn Bhd, VELLD, MTE

Air pollution is still a big problem in China, and research on PM2.5 related issues is still a hot topic. Based on the data of Changsha City from 2016.01-2018.04, this paper uses Genetic algorithm optimization BP neural network to construct the evolutionary model of PM2.5 in Changsha. The validity, versatility and reliability of the model are verified by comparison with actual data.

Dioxin (DXN) is a highly toxic and persistent pollutant discharged from municipal solid waste incineration (MSWI). The first principal model of DXN is difficult to establish due to the complex physical and chemical characteristics of the incineration process. In the practical process, DXN emission concentration is off-line detected with monthly or seasonal periods. Aim at such small sample modeling problem, a soft measuring method based on selective ensemble (SEN) least square support vector machine (LSSVM) for modeling DXN emission concentration is proposed. At first, candidate training sub-samples are produced from original training samples. Then, different candidate sub-sub-models based on the same kernel parameter and regularization parameter are constructed by using LSSVM. Thirdly, ensemble sub-models are selected by using the genetic algorithm optimization tool box and prior knowledge. Finally, these ensemble sub-models are combined by using partial least squares algorithm in terms of reduction con-linearity among different prediction outputs. Simulation results show effectiveness of the proposed approach by using dataset in reference [18].

A new air-gap correction method for accurately measuring the broadband permittivity of materials based on the transmission/reflection theory is proposed. This method relaxes the fully filled requirement of the specimens and realizes accurate correction for the air-gap effect. A combination strategy of the electromagnetic finite element simulation and the genetic optimization algorithm is employed to extract the true values of the air-gap size and the material permittivity. This is accomplished by minimizing the errors between the measured and the simulated scattering parameters. The high accuracy and practical suitability of the proposed method are validated through experimental tests.

A fundamental requirement of WSNs is the need for location information for the nodes. This is because in many applications of wireless sensor network information gathering from sensor node is only useful if they are attached with the location information of that particular node. In order to explain the above problem, we are proposing a genetic optimization algorithm depend on accurate localization algorithm for random deployed mobile unknown sensors nodes. The proposed algorithm find out the location information of the mobile unknown nodes with the help of parameter attenuation, path loss, fitness achievement and distance. We have found out an performance analysis for the proposed algorithm. The results of the proposed scheme proved that the proposed scheme works well as compared with the existing approaches.

Nonstationary signal (NSS) reconstruction from Time Varying (TV) coefficients of Time Varying Autoregressive (TVAR) process is presented in this paper. The proposed method consists of three steps, where in the first step, initial values for TVAR coefficients are estimated from synaptic weights of a three layer Artificial Neural Network (ANN) which is trained using Backpropagation (BP) learning algorithm. The estimated TVAR coefficients are then optimized using a Genetic Algorithm optimization algorithm for more accurate values in the second step. And finally once the TVAR coefficients are estimated using ANN and GA, it is then used to recover the original signal. Performance of proposed method has been evaluated by comparing reconstruction of various computer generated NSS from proposed methods with other methods. Five performance metrics was used for comparison where proposed method is shown to overcome the performance of other methods.

In the machining process, the rationalization of the cutting amount is an important way to effectively improve the productivity, reduce the cost and improve the quality of the workpiece. The rapid development of genetic algorithm has made remarkable achievements in solving the problem of nonlinear optimization. However, in the process of machining, there are many factors that affect the amount of cutting. The standard genetic algorithm is difficult to solve the problem quickly and accurately. In this paper, CNC lathe is used as the carrier, the optimization of the mathematical model of the cutting quantity is established, the optimization rules are analyzed, and the genetic optimization algorithm is used to solve the optimization problem of the cutting rate in the processing of the CNC lathe. The implementation method is illustrated by an example.

In recent years, with the high frequency of the infectious diseases outbreak, the prediction of the infectious diseases has become more and more important, so effective prediction of the infectious diseases can safeguard social stability and promote national economic prosperity. In order to improve the predictive accuracy of infectious diseases, the weight and threshold of BP neural network was optimized by using the improved genetic algorithm based on the PSO (particle swarm optimization algorithm) while the error function is the mean square error, the mean absolute error and the mean absolute percentage error. The simulation experimental results show that the optimized BP neural network can effectively reduce the mean square error, the mean absolute error and the mean absolute percentage error, and improve the prediction accuracy.

An optimal-arranged metasurface for broadband and wide-angle RCS reduction is proposed in this paper. To avoid directed scattering beams caused by the chessboard-like metasurface, the optimal arrangement for diffusion effect is searched out using genetic optimization algorithm. Furthermore, the proposed metasurface can obtain a wider 10-dB RCS reduction band which ranges from 5.16 GHz −7.94GHz (42.3% relative bandwidth) compared with the chessboard which ranges from 5.92GHz-6.1GHz (3.0% relative bandwidth). The scattering performances for the oblique incidence are also investigated in the full wave simulation, in which a more than 6-dB bistatic RCS reduction can be achieved from 5.14GHz-7.82GHz for both horizontal and vertical polarizations.

This paper presents a technique to increase the data throughput in Multiple Input Multiple Output (MIMO) systems. The technique uses a meta-heuristic to optimize the data throughput and to choose the best solution. The optimization is based on Genetic Algorithms (GA), with the objective of finding out the best antenna configuration to achieve the highest data throughput from the variation of the distance between the antenna array elements and the number of antennas. Simulation results show an increase of more than 15% in the data throughput considering 4×4 MIMO channels.

Planar W-band antenna tiles were created by defining pixelated subwavelength metal patterns on 4 mm square and 500 μm thick glass tiles space fed by an open-ended waveguide. The metal patterns were optimized to form beams and convert polarization. The metal patterns were found by genetic algorithm optimization of finite difference time domain simulations. Several antennas were fabricated, measured, and found to agree with the predictions.

After studying the working principle of feed-forward neural network and analyzing network structure and the learning mechanism of BP neural network and the extreme learning machine (ELM), a prediction model, GA-ELM, is proposed based on genetic algorithm to optimize the learning machine limit. The genetic algorithm is used to select the weights and thresholds of ELM neural network, and the optimal weights and thresholds are used to determine the connection weights between the hidden layer and the output layer. Further, this model is combined with the grey system model to correct the residual of GM, and then GM-GA-ELM combination forecasting model is established. Compared with BP model, GA-BP model and standard ELM model, it is further verified that the predicting accuracy and running time of the proposed model are better.

The collector is an important component in a Gyro-Travelling Wave Tube. The performance influences the capability of tube. The curved geometry is employed to average the dissipated power distribution. Compared to the previous cylindrical geometry, the maximum dissipated power is reduced from 0.83 kW/cm2 to 0.396 kW/cm2. The temperature on inner wall is reduced from 227 °C to 116 °C. The capability of collector is improved. Also the stability analysis is done, and it shows the curved geometry can operate stably.

Use of cloud computing technology and its services have pawed its way into many applications and this is also true in case of Content Delivery Networks. The storage services of cloud environment are replacing the traditional Content Delivery Networks for more reliability and easy availability of contents to users. Most research in Content Delivery Networks mainly focuses on delivering contents to the users with less latency and traffic cost. Apart from this the overall cost incurred for the content providers in cases of bandwidth and storage should also be taken into consideration. Most existing Content Delivery Networks focus only on the bandwidth and in some cases latency. In this paper a novel Content Delivery Model is proposed that makes use of a Genetic Optimization Algorithm (GOA) combined with an efficient storage model that can achieve better content placement and delivery in Cloud based Content Delivery Networks. The proposed approach updates itself dynamically to avoid unwanted use of storage that achieves a much better placement of contents thus reducing the storage cost.

This paper proposes a simple and efficient extraction method for mm-wave modeling of GaN devices. The procedure based on S-parameters measurements at single pinch-off bias condition to extract the parameters of a distributed small-signal equivalent circuit model. Hybrid technique of genetic algorithm optimization and direct fitting has been developed and implemented for GaN HEMTs of different sizes. The extraction procedure has been optimized to consider measurements uncertainty and improve the reliability of the extraction. The model has been validated by S-parameters measurements at different bias conditions for different sizes devices. A very good agreement between simulations and measurements has been obtained.

External grounding grid is an effective measure to reduce grounding resistance of grounding grid. In order to meet the requirements of the grounding resistance in the most economical way, it is important to determine the distance and the area of the external grounding grid. Generally speaking, when the area is larger, the grounding resistance is smaller. When the distance of the external grounding grid increases, the grounding resistance decreases firstly and then increases. Therefore, there is a minimum of the external grounding grid area and the optimal distance to meet the requirements of the grounding resistance within the constraints. Also means to get the best economic design scheme that minimum material consumption and construction of the external grounding grid. In this paper, we establish the objective function of the minimum grounding resistance based on the area and the distance of the external grounding grid using the method of grounding grid unequal potential model. Through optimization theory and genetic algorithm optimization, the optimum parameters of the distance and the area size of the grounding grid are obtained. Provide important basis for the design of the grounding grid economically.

The collector is an important component in a Gyro-Travelling Wave Tube. The performance influences the capability of tube. The curved geometry is employed to average the dissipated power distribution. Compared to the previous cylindrical geometry, the maximum dissipated power is reduced from 0.83 kW/cm2 to 0.396 kW/cm2. The temperature on inner wall is reduced from 227°C to 116°C. The capability of collector is improved. Also the stability analysis is done, and it shows the curved geometry can operate stably.

The concept lattice is adopted as a tool of attribute reduction to reduce the redundant factors affecting coke ratio in this paper. On this basis, in order to solve the blindness and random problems in the parameters of artificial selection in support vector machine (SVM), this paper adopts genetic algorithm to optimize the penalty parameter C, kernel function parameters γ and insensitive loss coefficient e of support vector machine and put forward the prediction model based on the concept lattice and genetic algorithm optimization for support vector machine (Con-GA-SVM), which is applied to forecast coke rate of blast furnace. Through comparative experiment, this algorithm has better performance than PSO-SVM prediction model and Grid-SVM model.