pso algorithm

The long-distance transportation of heavy commercial vehicles is facing increasing pressure. Low wind resistance and low fuel consumption will become the objective requirements and development trend of heavy commercial vehicles. In this paper, the 1:1 complex model of commercial vehicle is taken as the research object to study the passive drag reduction of the commercial vehicle. First, simulation analysis is conducted, and then the wind tunnel test of the 1:2.5 complex model is performed to verify the accuracy of the simulation scheme and results. Then, the geometric shape of the cab is parameterized and controlled by 13 parameters. After determining the range of parameter changes, Latin hypercube sampling is selected, and large eddy simulation is used for numerical simulation to construct the sample space. Taking the shape parameter as the input factor and the coefficient of drag CD as the target response, the initial surrogate model is constructed, and the sample points are supplemented by the combination of global and local point addition strategies to improve the accuracy of the surrogate model. Finally, R2=0.812. The local details of the optimization results are optimized, and the low-wind-resistance shapes of the cabs of the three styling styles are obtained. Among them, the bullet model has the lowest CD. Compared with the basic model, the drag reduction rate is 28%, and the coefficient of drag is simulated. The error between the value and the test value is within 1%.

This article discusses about coordination of directional overcurrent relays (DOCRs) in the power system transmission lines. In these relays, 4 characteristics are used as variables to calculate coordination between of them. These 4 variables include PS, TMS, A and B, which are used to obtain optimal coordination between relays. In this article, to obtain optimal coordination, two fault locations are considered. One of them is near the relay (at the 10%-line beginning) and another is fault far from the relay (at the 90%-line end). The problem of coordination of relays is solved and optimized using the PSO optimization algorithm. The proposed method has been tested in the standard distribution 6-Buse IEEE System, and its results are stated. The results of the PSO optimization method that was obtained have been compared with traditional methods such as GA-NLP. Comparing the results of this method with the traditional methods presented in the other articles, found that the presented method obtains more optimal results than other traditional methods. Since the proposed method minimizes the operation time of DOCRs relays. This method is a reliable and effective method for calculating coordination between relays.

Nowadays, the gimbal stabilizes the line of sight and eliminates vibration in systems such as imaging, radar line of sight, and position stabilizers. The gimbal system tries to maintain the system's current state by dealing with the changes made in the system's current state. This system reduces unwanted motion disturbances and vibrations. The most common use of the gimbal system is in modern photography equipment. In this article, a single-axis gimbal stabilizer system that uses a PD_PI fuzzy controller has been investigated and the PSO algorithm has been used to optimize and calculate controller coefficients. The dynamic relations of the gimbal are described and the proposed control system based on the PD_PI fuzzy controller is optimized using the PSO algorithm. The controller coefficients have been optimized with the lowest possible settling time. The comparison of the obtained results shows that this controller has less settling time and much less overshoot than other controllers such as PID and fuzzy PID controllers.

Smart Grids are the result of the activation of consumers in the power system and their role in the planning and operation of the power system. The communication, control and measurement infrastructure as a smart communication bridge establishes two-way communication between consumers and the power network and provides the basis for the effective implementation of the load response program as well as direct load control. The purpose of solving the problem of economic load distribution in the power system is to plan the output of production units in such a way as to provide the required load demand with the lowest possible cost. In addition, it satisfies the constraints of equality or inequality of all units. In this research, PSO optimization method is taken into consideration by considering voltage deviation, voltage loss and system load capacity as part of the objective function.

The Load Frequency Control (LFC) has been a major subject in electric power system and is be-coming more significant system in recent decades. This paper targets to investigate the problem of LFC in interconnected power systems in order to obtain robust state. In this paper, a design method for a robust controller, based on PID, has been presented to overcome the robustness against uncertainties. To achieve optimal PID, Particle Swarm Optimization (PSO) has been em-ployed to obtain coefficients of the SMC. Variations of uncertain parameters are considered be-tween -40% and +40% of nominal values. The simulation results show that the system response with the proposed PID is better than the conventional PID controller. It is also shown that the transient response of the tie line power can be improved.

In the microgrids, it can be used from the renewable energy resources (RERs) such as photovolta-ic panels, wind turbines, wave energy converters and current type tidal turbines to reduce the greenhouse gas (GHG) emission arisen from fossil fuel-based generation units. However, the generated electrical power of these RERs are dependent on the wave height and wave period, solar radiation, the wind speed, and the tidal current speed. Due to the wide variation in the RERs, the generated electrical power of these generation units changes a lot and so, to supply the local load in the isolated microgrid, the conventional generation units and the energy storage sys-tems (ESSs) can be utilized. In this paper, optimal scheduling of a microgrid containing conven-tional generation units, ESS and RERs including wind turbines, photovoltaic panels, current type tidal turbines and wave energy converters is performed to determine the generated power of each generation unit provided that the cost function is minimum. In the cost function, the operation cost of the generation units based on fossil fuel and the penalty cost associated to the load cur-tailment as the reliability cost are considered and using of the particle swarm optimization (PSO) algorithm, the cost function is minimized. To study the capability and effectiveness of the pre-sented approach, the numerical results associated to the optimal scheduling of a microgrid con-taining battery, RERs, and conventional units are presented.

Statistical process monitoring, maintenance policy, and production have commonly been studied separately in the literature, whereas their integration can lead to more favorable conditions for the entire production system. Among all studies on integrated models, the underlying process is assumed to generate independent data. However, there are practical examples in which this assumption is violated because of the extraction of correlation patterns. Autocorrelation causes numerous false alarms when the process is in the in-control state or makes the traditional control charts react slowly to the detection of an out-of-control state. The auto-regressive moving average (ARMA) control chart is selected as an effective tool for monitoring autocorrelated data. Therefore, an integrated model subject to some constraints is proposed to determine the optimal decision variables of the ARMA control chart, economic production quantity, and maintenance policy in the presence of autocorrelated data. Due to the complexity of the model, a particle swarm optimization (PSO) algorithm is applied to search for optimal decision variables. An industrial example and some comparisons are provided for more investigations. Moreover, sensitivity analysis is carried out to study the effects of model parameters on the solution of the economic-statistical design.

This paper investigates different intelligent methods of tuning feedback-linearization control coefficients. Feedback-linearization technique is an effective method of controlling nonlinear systems. The most critical part of designing this controller is tuning the gains, especially if the plant has complex nonlinear dynamics. In this research, to improve the performance of the overall closed-loop system, the feedback linearization method has been integrated with the conventional proportional-integral-derivative (PID) controller. Also, a quadratic performance index was used to compare the functionality of the controllers tuned by the proposed intelligent methods. These intelligent methods include Genetic Algorithms (GA), Particle Swarm Optimization (PSO), Fuzzy Logic, and Neural Network tuning algorithms. A quadrotor aircraft is used as the plant under study in order to evaluate the performance of the controllers tunned in this research. Finally, MATLAB simulation tests demonstrate the effectiveness of the presented algorithms. According to the results, it is demonstrated that the class of online algorithms performs better, even with the specified perturbation.

This paper contributes to the design, modeling, and planning of a distributed generation (DG) network with wind and solar by means of the particle swarm algorithm (PSO) algorithm in the IEEE 33-bus network, aiming to minimize The results indicate an adequate performance in a variety of environments, and the presence of distributed wind/solar energy generators decreases network stress by feeding loads locally. These systems (wind and solar) can be used in remote areas without power networks, or even in areas where there is a tendency to use renewable energy despite the presence of a power network. They can also supply the output load for most of the day and night. Probability distribution functions are used, and the outputs are expressed as probability density distribution functions instead of absolute numbers. In addition, there is a high degree of uncertainty regarding the state of the system, which is an associated renewable energy source within the power system elements. By means of MATLAB software, the proposed method is implemented in order to ensure effectiveness and validate the results.

Field experience shows that the cutting transportation and hole-cleaning phenomena are essential during the drilling phase. Particularly in directional drilling, when the accumulation of cutting has caused some drilling problems such as drill string sticking, formation failure, slow rate of penetration, drill bit abrasion, and the like. Through the study, a novel method for efficient hole cleaning, considering different parameters such as flow rate, the drill bit nozzles’ flow area, the consistency and flow behavior indices in the same time using PSO and ACO algorithms were implemented. Moreover, Power Law has been considered for the fluid rheology model. Based on this, the research parameter shows that the PSO algorithm is much more accurate than the ACO algorithm, improving objective function by 50% and 4%, respectively. The performance of each algorithm was evaluated, and the results show that hole cleaning has been significantly improved. The flow rate and the bit nozzle size, which play key roles, were selected as optimization variables. Effective parameters on hole cleaning were evaluated, and the results before and after optimization showed a significant improvement in the model. The PSO and ACO algorithms have been coded in MATLAB software, and the results are compared to the results of the ant colony. The amount of PV and YP has an inverse effect on the increment of minimum velocity required for cutting transport. Various model analyses reveal that the PSO algorithm is more accurate and robust than the Ant colony algorithm.

Integration and diversity of IOT terminals and their applicable programs make them more vulnerable to many intrusive attacks. Thus, designing an intrusion detection model that ensures the security, integrity, and reliability of IOT is vital. Traditional intrusion detection technology has the disadvantages of low detection rates and weak scalability that cannot adapt to the complicated and changing environment of the Internet of Things. Hence, one of the most widely used traditional methods is the use of neural networks and also the use of evolutionary optimization algorithms to train neural networks can be an efficient and interesting method. Therefore, in this paper, we use the PSO algorithm to train the neural network and detect attacks and abnormalities of the IOT system. Although the PSO algorithm has many benefits, in some cases it may reduce population diversity, resulting in early convergence. Therefore,in order to solve this problem, we use the modified PSO algorithm with a new mutation operator, fuzzy systems and comparative equations. The proposed method was tested with CUP-KDD data set. The simulation results of the proposed model of this article show better performance and 99% detection accuracy in detecting different malicious attacks, such as DOS, R2L, U2R, and PROB.

In this paper, an ultrasonic horn based on the PSO algorithm for emulsion homogenization is optimized and fabricated. The application of various ultrasonic instruments such as horns in different industrial procedures is increasingly expanding and developing. Horn is a tool that has played a crucial role in the energy transfer to fluid. Longitudinal frequency, vibration amplitude, length-to-diameter ratio, a distance of frequency from other frequency modes, wide distribution of cavitation along with the horn’s length, and increasing the area of acoustic energy transfer are the main characteristics of the horn design procedure. Therefore considering these important features with using the PSO algorithm and electro-mechanical circuit method to finding resonance frequency, the design procedure of the optimized horn is performed. The definition of the objective function is based on the horn’s amplification factor, and the rest of the other characteristics are defined as design constraints. The simulation results show a 15% improvement in the natural frequency compared to the target frequency and a suitable frequency distance of 2.5 kHz between the previous and next modes. According to the barbell part of the horn, the amplification factor of 14 was obtained for the proposed horn, the frequency and amplitude of the vibration were evaluated. The experimental results were very close in terms of amplification factor and frequency to the simulation results with reasonable accuracy.

One of the issues of reliable performance in the power grid is the existence of electromechanical oscillations between interconnected generators. The number of generators participating in each electromechanical oscillation mode and the frequency oscillation depends on the structure and function of the power grid. In this paper, to improve the transient nature of the network and damping electromechanical fluctuations, a decentralized robust adaptive control method based on dynamic programming has been used to design a stabilizing power system and a complementary static var compensator (SVC) controller. By applying a single line to ground fault in the network, the robustness of the designed control systems is demonstrated. Also, the simulation results of the method used in this paper are compared with controllers whose parameters are adjusted using the PSO algorithm. The simulation results show the superiority of the decentralized robust adaptive control method based on dynamic programming for the stabilizing design of the power system and the complementary SVC controller. The performance of the control method is tested using the IEEE 16-machine, 68-bus, 5-area is verified with time domain simulation.

 Detection of attacks and anomalies is one of the new challenges in promoting e-commerce technologies. Detecting anomalies of a network and the process of detecting destructive activities in e-commerce can be executed by analyzing the behavior of network traffic. Data mining systems/techniques are used extensively in intrusion detection systems (IDS) in order to detect anomalies. Reducing the size/dimensions of features plays an important role in intrusion detection since detecting anomalies, which are features of network traffic with high dimensions, is a time-consuming process. Choosing suitable and accurate features influences the speed of the proposed task/work analysis, resulting in an improved speed of detection. The present papers utilize a neural network for deep learning to detect e-commerce attacks and anomalies of e-commerce systems. Overfitting is a common event in multi-layer neural networks. In this paper, features are reduced by the firefly algorithm (FA) to avoid this effect. Simulation results illustrate that a neural network system performs with high accuracy using feature reduction. Ultimately, the neural network structure is optimized by using particle swarm optimization (PSO) to increase the accuracy of attack detection capability.