Search

This paper enhanced the autonomy of a mobile agricultural robot in a structured environment to find an optimal path to perform selective and variable spraying of pesticides. To materialize these, a robust VRP (Vehicle Routing Problem) scheme with deterministic variable demand and nonlinear travel time is designed to navigate the robot while making decisions to fulfill the pesticide demand at each node. The nonlinear time function obtained from experiments necessitates the consideration of three objectives simultaneously. The NSGA (non-dominated sorting genetic algorithm)-III algorithm is adopted to determine the optimal path for the robot. To achieve this, the mixed integer algorithm is modified to handle the full integer complex routing problem to optimize three test case scenarios. Finally, the NSGA-III has shown the capability to solve the full integer constraint problem based on the proposed modifications. [ABSTRACT FROM AUTHOR]

Summary: In this paper, the adaptive neuro‐fuzzy inference system (ANFIS) for solar maximum power point tracking (MPPT) has been proposed for quick and accurate tracking at different weather conditions and different load variations with high efficiency. The solar irradiance sensor does not always give accurate irradiance readings, plus the use of the sensor will be cost‐effective since the PV module is influenced by the solar irradiance. This paper proposed the ANFIS‐based MPPT with the elimination of the irradiance sensor. In addition to minimization of the data training, which leads to less computation burden. To enhance the response time of the system for fast varying load variations, the proposed method was combined with a constant impedance method. The proposed method is evaluated in various weather conditions. Experimental results indicate positive monitoring of the proposed method in all the different cases that were tested. A comparison of the proposed method with well‐established conventional (Perturb and Observe) and soft computing‐based particle swarm optimization methods have been evaluated. The results showed the superiority of the approach proposed in terms of the reduced tracking period. In addition, the proposed method provides fast convergence and obtains a steady state in less than 0.12 second. [ABSTRACT FROM AUTHOR]

Controlling of a rotational inverted pendulum is considered as a challenging problem, mainly due to the system's inherent nonlinear and unstable dynamics. In fact, the goal of this control is to maintain the pendulum vertically upward regardless of external disturbances. This paper aims to optimally design a model reference adaptive proportional integral derivative (PID) control for rotary inverted pendulum system based on a novel hybrid particle swarm optimization algorithm, combining sine cosine algorithm and levy flight distribution. Evaluation of the performance quality of the proposed adaptive controller is accomplished based on the stabilization and tracking control of rotary inverted pendulum system. In addition, two other PID controllers are designed to get a better understanding of the performance and robustness of the proposed controller. To make a complete comparison, the performance of the hybrid particle swarm optimization algorithm is examined against two other optimization techniques known as simple particle swarm optimization and whale optimization algorithm. Finally, the obtained simulation results demonstrate that the proposed optimal adaptive controller is superior to the other controllers, especially in terms of the transient response characteristics and the magnitude of control output signal. [ABSTRACT FROM AUTHOR]

This work proposed an automatic mixing system of nutrient solution for rock melon fertigation according to the required electrical conductivity (EC) level. Compared to the manual practice, this automatic system will ensure continuous supply of mixed nutrient solution without the need to daily check and mix new nutrient. Thus, this easy to use and low cost automatic system will reduce the burden of the farmers. This system uses an EC sensor to automatically check the concentration level of the mixed nutrient solution. Other than that, the system only consists of electronic pumps for mixing process and an Arduino board as the controller. The controller will monitor the EC level and run the mixing process when the EC level is below the required level. By calibrating the EC sensors, the test shows that the automatic mixing system is able to accurately keep the mixed nutrient solution concentration in a 400 L mixing reservoir at several required levels. [ABSTRACT FROM AUTHOR]

Multi Objective Optimization (MOO) problem involves simultaneous minimization or maximization of many objective functions. Various MOO algorithms have been introduced to solve the MOO problem. Traditional gradient-based techniques are one of the methods used to solve MOO problems. However, in the traditional gradient-based technique only one solution is generated. Thus, an alternative approach such as Particle Swarm Optimization (PSO), which able to produce a number of possible solutions are highly desirable. In PSO, particles search the optimum solution under the influence of a better solution known as leader. This leader facilitates cooperation between all particles. However, this strategy to select the leader has to be changed when it is used for MOO problems. This paper presents an overview of the multi-objective PSO algorithms, which emphasize on the leader selection. In addition, the description of PSO and multi-objective optimization problems are also provided. [ABSTRACT FROM AUTHOR]

The vector evaluated particle swarm optimisation (VEPSO) algorithm was previously improved by incorporating nondominated solutions for solving multiobjective optimisation problems. However, the obtained solutions did not converge close to the Pareto front and also did not distribute evenly over the Pareto front. Therefore, in this study, the concept of multiple nondominated leaders is incorporated to further improve the VEPSO algorithm. Hence, multiple nondominated solutions that are best at a respective objective function are used to guide particles in finding optimal solutions. The improved VEPSO is measured by the number of nondominated solutions found, generational distance, spread, and hypervolume. The results from the conducted experiments show that the proposed VEPSO significantly improved the existing VEPSO algorithms. [ABSTRACT FROM AUTHOR]

A two wheeled inverted pendulum (TWIP) mobile robot is an under-actuated mechanical system, which is inherently open-loop unstable with highly nonlinear dynamics. This property attracts the interest of researchers worldwide in recent years. This paper presents the development of a linearized model of the TWIP mobile robot based on its nonlinear dynamical model using Takagi-Sugeno (T-S) fuzzy modeling technique, which can allow the application of linear control techniques in analyzing and efficiently controlling such under-actuated nonlinear system. The complete nonlinear dynamical equations of motion of the TWIP mobile robot were first derived using Kane's Method. Based on the nonlinear dynamical equations of motion, a T-S fuzzy model of the TWIP robot was then developed using local approximation technique. To validate the proposed model, simulations study was carried out and the results show that the proposed model approximates the original nonlinear TWIP mobile robot in the pre-specified domains to certain degree of accuracy. [ABSTRACT FROM AUTHOR]

Precise control of the stepper motor has always been a topic of interest and also a challenging issue among control engineering researchers due to the nonlinear nature of the motor dynamic. Abrupt influences of the uncertainties on the model's dynamic and control performance, on the other hand, must be taken into account for providing a control methodology including the characteristics of adaption and flexibility. Lack of these items in most of the classic control approaches results in degradation of the control action. The main purpose of this paper is to provide an intelligent approach for improving the functionality of conventional PID controller in the problem of trajectory tracking in permanent magnet stepper motor (PMSM). Combination of a meta-heuristic algorithm called imperialist competitive algorithm (ICA) and fuzzy logic is employed for online tuning of PID controller. This, consequently, establishes an intelligent structure, fuzzy-PID controller (FPID), which is more flexible and accurate both in certain and uncertain situations. Using a systematic approach in designing the optimal fuzzy structure based on the ICA is our contribution here which leads to better performance of PMSM. Comparing the results of simulations, done in Matlab Simulink, between the suggested control strategy and performance of the PID, expresses the remarkable capability of FPID in overcoming the complexity of control of the nonlinear and uncertain systems. [ABSTRACT FROM AUTHOR]

The vector evaluated particle swarm optimisation (VEPSO) algorithm was previously improved by incorporating nondominated solutions for solving multiobjective optimisation problems. However, the obtained solutions did not converge close to the Pareto front and also did not distribute evenly over the Pareto front. Therefore, in this study, the concept of multiple nondominated leaders is incorporated to further improve the VEPSO algorithm. Hence, multiple nondominated solutions that are best at a respective objective function are used to guide particles in finding optimal solutions. The improved VEPSO is measured by the number of nondominated solutions found, generational distance, spread, and hypervolume. The results from the conducted experiments show that the proposed VEPSO significantly improved the existing VEPSO algorithms.

The Vector Evaluated Particle Swarm Optimisation algorithm is widely used to solve multiobjective optimisation problems. This algorithm optimises one objective using a swarm of particles where their movements are guided by the best solution found by another swarm. However, the best solution of a swarm is only updated when a newly generated solution has better fitness than the best solution at the objective function optimised by that swarm, yielding poor solutions for the multiobjective optimisation problems. Thus, an improved Vector Evaluated Particle Swarm Optimisation algorithm is introduced by incorporating the nondominated solutions as the guidance for a swarm rather than using the best solution from another swarm. In this paper, the performance of improved Vector Evaluated Particle Swarm Optimisation algorithm is investigated using performance measures such as the number of nondominated solutions found, the generational distance, the spread, and the hypervolume. The results suggest that the improved Vector Evaluated Particle Swarm Optimisation algorithm has impressive performance compared with the conventional Vector Evaluated Particle Swarm Optimisation algorithm.