Multi-objective Non-dominated Sorting Genetic algorithm-II Research Articles

Optimized k-nearest neighbors for classification of prosthetic hand movements using electromyography signal

Electromyography (EMG) signals are essential, as they are used to measure muscular activity in different parts of the human body. The measurement and analysis of EMG signal lead to various applications of muscle disorders such as muscular dystrophy, myopathy, hand movements, etc. In this paper, an improved and effective hand movement classification model is developed for amputee subjects. It includes: (1) EMG feature extraction using Discrete Wavelet Transform (DWT), (2) EMG feature selection using binary Global Best Guided Gaussian Artificial Bee Colony (BGGABC), (3) Hand movements classification using Optimized k-nearest neighbors (OKNN) classifier. The EMG signal is taken from the DB3 of NinaPro dataset comprising 17 different prosthetic hand movements recorded from 11 amputee subjects. Thereafter, DWT is applied to decompose the EMG signal for extracting features. An improved wrapper-based feature selection technique (BGGABC) is used to select the optimal feature subset for effective classification. The two variants of KNN, i.e. Smallest Modified KNN and Largest Modified KNN are taken in which item strength to a class is optimized for efficient classification. The strength of an item to a class depends on distance and weight of an item to a class. Therefore, a multi-objective Non-dominated sorting genetic algorithm-II (NSGA-II) is used for optimizing these two contradictory parameters (distance and weight) simultaneously to have optimized variants, namely: Optimized Smallest KNN (OSKNN) and Optimized Largest KNN (OLKNN). Extensive results show that the proposed method OKNN achieved the highest classification accuracy of 93.07% (OLKNN) and 89.43% (OSKNN) compared with KNN variants and competitors.

Linear LSA-NSGAII optimization: A case study in optimal switch placement in distribution network

In this paper, a new hybrid of lightning search algorithm (LSA) and non-dominated sorting genetic algorithm II (NSGAII) is proposed in order to increase the accuracy and efficiency of the conventional multi-objective NSGAII. In the proposed method, the important parameters of the NSGAII are optimized using LSA. To verify the effectiveness of the proposed algorithm, it is applied to 19 well-known standard test functions, including unconstrained functions, UF1–UF7, constrained functions, CF1–CF7, Schaffer1, Schaffer2, ZDT1, ZDT2, and ZDT3. The inverted generational distance (IGD) is used to check the efficiency of the proposed algorithm. Accordingly, the proposed algorithm is compared with the most used multi-objective algorithms. Besides, the proposed algorithm is applied to a practical case study of optimal switch, including reclosers and disconnectors, placement in the presence of distributed generation (DG) sources. The distribution networks are the Roy-Billinton test system (RBTS) and a part of the real network in Mazandaran province, in Iran. The simulation results confirm the superiority of the proposed method. For example, in practical case studies, the proposed algorithm for optimal recloser placement in the real network shows 47.09% and 4.691% cost improvement compared with multi-objective particle swarm optimization (MOPSO) and NSGAII, respectively. These improvements for RBTS-BUS2 are 3.725% and 3.502%, respectively. Also, for the RBTS-BUS2, the proposed algorithm result shows 1% and 0.732% reliability improvement compared with MOPSO and NSGAII, respectively.

Multiple-objective optimization on ammonia decomposition using membrane reactor

Ammonia plays a key role in the renewable hydrogen economy nowadays, thus, the efficiency of ammonia decomposition for hydrogen production becomes an important research topic. In this study, a numerical model was built to study the performance of ammonia decomposition using a membrane reactor and Ru/Al2O3 catalyst under various operating conditions such as feed NH3 temperature and volume flow rate as well as retentate side pressure. The reactor performance was characterized by ammonia conversion, hydrogen recovery, and recovered hydrogen flow rate. Pre-exponential factor and activation energy of ammonia reaction rate were obtained by equilibrium conversion and two-step parametric sweeping. It was found that ammonia conversion can be increased by about 33% compared to a conventional fixed-bed reactor under the same operating conditions. H2 recovery can be enhanced when the reactant inlet temperature and the pressure difference between the retentate and permeate sides increase. The increase in feed NH3 flow rate (gas hourly space velocity, GHSV) decreased the ammonia conversion and H2 recovery. An optimum GHSV that results in a maximum recovered H2 flow rate can be found. Finally, optimum operation conditions for maximizing the hydrogen recovery and recovered hydrogen flow rate were analyzed using the multi-objective Non-dominated sorting genetic algorithm-II (NSGA-II). It was found that maximum H2 recovery with a value of 79.7% can be obtained under the conditions of inlet temperature of 336 °C, GHSV of 900 h−1, and retentate side pressure of 9.9875 bar. The maximum recovered hydrogen flow rate with a value of 9.55×10−14(mol·s−1) can be obtained under the conditions of an inlet temperature of 394 °C, GHSV of 1315 h−1, and retentate side pressure of 9.9879 bar.

Optimization of process parameters in turning of magnesium AZ91D alloy for better surface finish using genetic algorithm

This research examined at the optimum cutting parameters for producing minimum surface roughness and maximum Material Removal Rate (MRR) when turning magnesium alloy AZ91D. Cutting speed (m/min), feed (mm/rev), and cut depth (mm) have all been considered in the experimental study. To find the best cutting parameters, Taguchi's technique and Response Surface Methodology (RSM), an evolutionary optimization techniques Genetic Algorithm (GA) and Non-dominated Sorting Genetic Algorithm-II (NSGA-II) were employed. GA gives better results of 34.04% lesser surface roughness and 15.2% higher MRR values when compared with Taguchi method. The most optimal values of surface roughness and MRR is received in multi objective optimization NSGA-II were 0.7341 µm and 9460 mm3 /min for the cutting parameters cutting speed at 140.73m/min, feed rate at 0.06mm/min and 0.99mm depth of cut. Multi objective NSGA-II optimization provides several non-dominated points on Pareto Front model that can be utilized as decision making for choice among objectives

Optimization of Waste Transportation Routes using Multi-objective Non-dominated Sorting Genetic Algorithm II (MNSGA-II) in the Eastern and Southern Regions of Bandung City, Indonesia

Ensuring high-quality and effective urban waste management has been an important priority to achieve sustainable and environmental-friendly cities and communities mandated by Sustainable Development Goals (SDGs). The massively growing population in urban regions of developing countries, such as Bandung City, Indonesia, leads to the increasing volume of daily goods consumption and households waste production. The waste transportation route is one of the main determining factors for the cost of waste management. In this paper, we introduce the Multi-objective Non-dominated Sorting Genetic Algorithm II (MNSGA-II) to solve the waste transportation route optimization problem in the Eastern and Southern Regions of Bandung City, Indonesia. Compared to the existing traditional evolutionary algorithms, MNSGA-II offers three major important benefits: efficient computational complexity, no requirement of sharing parameters, and a non-elitism mechanism. Algorithm parameters include the number of generations, mutation rate, and crossover rate. Our extensive experiments suggest the best solution resulted in 14 routes with a total distance of 152,63 km. Further, our proposed route optimization is potentially beneficial to support the improvement of the sustainable waste management service system at Bandung City.

A static semi-kitting strategy system of JIT material distribution scheduling for mixed-flow assembly lines

The green scheduling plays an increasingly important role in many manufacturing enterprises and trading off the Just-in-Time (JIT) and energy efficiency is a complex optimization problem. A static semi-kitting strategy is proposed to deal with a bi-objective JIT material distribution scheduling problem considering energy consumption (BJMDSP-EC) for mixed-flow assembly lines. A mathematical model that aims to minimize the total energy consumption and the total line-side inventory is established, which meets the request of energy saving and JIT. Due to the NP-hard nature of the proposed problem, a Memory-based Bi-objective Chaotic Gravitational Search Algorithm (MBCGSA) is developed to solve the BJMDSP-EC, which hybridizes the Gravitational Search Algorithm (GSA) and the non-dominated sorting genetic algorithm-II (NSGA-II). The memory-based search strategy and the chaotic gravity constant are applied to the bi-objective optimization algorithm to balance exploration and exploitation. Moreover, clustering and Cauchy deviates are utilized to initialize the population, and two local search optimization operators are designed to optimize two objectives. Finally, computational experiments are performed to evaluate the performance of the MBCGSA by being compared with two other bi-objective optimization algorithms, the multi-objective particle swarm optimization (MOPSO) and NSGA-II, and the results reveal the effectiveness and efficiency of the MBCGSA when solving BJMDSP-EC.

Proportional–integral-derivative controller with inlet derivative filter fine-tuning of a double-pendulum gantry crane system by a multi-objective genetic algorithm

ABSTRACTOverhead cranes are widely used in industry to move extremely heavy and bulky loads through the overhead space in a facility instead of through aisles or on the floor. Unfortunately, the natural sway of a crane's payload is a huge safety problem which needs more research by control engineers, as the sway of the payload affects both the safety and productivity of a factory. This article introduces an optimized mathematical model of a double-pendulum overhead crane with control schemes: scheme 1 uses three proportional -integral-derivative (PID) controllers with inlet derivative filters; scheme 2 uses one PID controller for accurate trolley positioning and two anti-swing proportional -derivative controllers to eliminate hooks and payload sway, all with inlet derivative filters. The controllers include up to nine gains which are tuned using the multi-objective non-dominated sorting genetic algorithm-II with five fitness functions and weighted function to choose a suitable solution from Pareto solutions.

Optimum design of hydraulic water retaining structures incorporating uncertainty in estimating heterogeneous hydraulic conductivity utilizing stochastic ensemble surrogate models within a multi-objective multi-realisation optimisation model

AbstractIn order to find optimum and reliable designs for hydraulic water retaining structures (HWRSs), a reliability based optimum design (RBOD) model was used to quantify uncertainty in estimates of seepage characteristics due to uncertainty in heterogeneous hydraulic conductivity (HHC). This included incorporating reliability measures into minimum-cost HWRS designs and utilising a multi-realisation optimisation technique based on various stochastic ensemble surrogate models. To improve the efficiency of the RBOD model and the direct search optimisation solver, a multi-objective multi-realisation optimisation (MOMRO) model was employed. Some of the stochastic optimisation constraints could be formulated as a second objective function to be minimised in the MOMRO model. This can significantly improve the search efficiency of the multi-objective non-dominated sorting genetic algorithm-II (NSGA-II) that was used, and help determine more feasible candidate solutions in the search space. Gaussian process regression was used to develop the surrogate models, which were trained on numerous datasets created from numerical seepage simulations. The effect of uncertainty was also considered for other HWRS safety factors and conditions, such as overturning, flotation, sliding and eccentric loading. The results demonstrate that uncertainty in HHC estimates significantly impacts optimum HWRS design. Therefore, deterministic optimum solutions that are created based on expected values of hydraulic conductivity are not adequate for reliable HWRS design. The developed MOMRO model, which was based on an ensemble approach, addresses some of the uncertainty in HHC values that affects HWRS design. Also, the MOMRO technique improves the efficiency of the optimisation search process and facilitates a direct search process to provide many optimum alternatives.Highlights The uncertainty in HHC affects the optimum HWRS design. MOMR is used to quantify the reliability based on stochastic ensemble surrogate models. The MOMR technique improves the direct search optimization process based NSGA-II. Exit gradient is influenced by the uncertainty of HHC and affects the HWRS optimum designs.

An expert 2DOF fractional order fuzzy PID controller for nonlinear systems

This work presents a generic two-degree-of-freedom fractional order fuzzy PI-D (2DOF FOFPI-D) controller dedicated to a class of nonlinear systems. The control law for proposed scheme is derived from basic 2DOF fractional order PID controller in discrete domain. Expert intelligence is embedded in overall derived control law by utilizing formula-based fuzzy design methodology. The controller structure comprises of fractional order fuzzy PI (FOFPI) and fractional order derivative filter to handle multiple issues and provides flexibility in design and self-tuning control feature. Further, the proposed scheme is compared with its integer order counterpart and 2DOF PI-D controller for coupled nonlinear 2-link robotic arm in real operating environment. The parameters of designed controllers are optimally tuned using multi-objective non-dominated sorting genetic algorithm-II for attaining low variation in control effort and error index. Intensive simulation studies are performed to analyze trajectory tracking, model uncertainty, disturbance due to cogging, sensor noise and noise as well as disturbance rejection simultaneously. Results demonstrate the superior performance of 2DOF FOFPI-D controller as compared to other designed controllers in the facets of different operating conditions.

A multi-objective decision model for investment in energy savings and emission reductions in coal mining

Coal-mining companies should clearly be investing in energy savings and treatment technologies aimed at reducing both their energy consumption and their pollution levels in order to meet the requirements of government regulations relating to environmental protection; however, when considering the types of technical equipment to use and the timing of their investment, these companies also need to consider their profits and the costs of such investment. We therefore propose a "multi-objective mixed integer non-linear programming" (MMINLP) model of investment in energy savings and emission reductions designed to handle this type of decision-making problem. Given three objectives (maximum profits, minimal energy consumption and minimal pollution), we develop a hybrid mixed-coding ``particle swarm optimization and multi-objective non-dominated sorting genetic algorithm-II" (PSO–NSGA-II) to optimize the continuous and discrete decision variables as a means of helping companies to reach the optimum decision. We also integrate the subtractive clustering-multi-criteria tournament decision-gain analysis method (SC–MTD–GAM) to select the best trade-off solutions on the optimal Pareto fronts. Finally, we carry out a case study of investment decisions on energy savings and emission reductions in the Zhenzhou Coal Industry (Group) Co., Ltd., China, with the results revealing that the proposed model can support decision making for energy savings and emission reductions in coal mining areas. As compared with the NSGA-II and ``non-dominated sorting particle swarm optimization" (NSPSO) algorithms, the proposed PSO–NSGA-II is found to have better convergence, coverage and uniformity.

Optimal semi-active control of seismically excited MR-equipped nonlinear buildings using FLC and multi-objective NSGAII algorithms considering ground excitations

Among the variety of control algorithms, fuzzy logic control (FLC) strategies have the advantage of not depending on the system model behavior, of being simple, and intrinsically robust, and therefore they have recently been used to control the dynamic response of multi-story buildings equipped with semi-active supplemental damping devices. However, their tuning has shown to be a difficult task, especially when they use a multi-objective strategy. Introducing several FLC-based control strategies, an optimal semi-active control strategy using an advanced multi-objective optimization procedure called Non-dominated Sorting Genetic Algorithm II (NSGAII) has been proposed in this paper to mitigate the nonlinear structural response of a new generation of benchmark buildings. Besides peak inter-story drift ratio and peak floor acceleration, the base shear force as an extra objective has been used as the three-objective function for the multi-objective optimal design problem. The robustness of the optimized semi-active algorithms which were produced using binary tournament-based parents has been assessed for 3-story and 20-story nonlinear benchmark buildings experiencing nonlinear behavior during a wide range of earthquake records. The results showed that the performance of optimized semi-active control systems is acceptable and in some cases work much better than the non-optimized controllers taken in previous studies.

NSGA-II based optimal control scheme of wind thermal power system for improvement of frequency regulation characteristics

Abstract This work presents a methodology to optimize the controller parameters of doubly fed induction generator modeled for frequency regulation in interconnected two-area wind power integrated thermal power system. The gains of integral controller of automatic generation control loop and the proportional and derivative controllers of doubly fed induction generator inertial control loop are optimized in a coordinated manner by employing the multi-objective non-dominated sorting genetic algorithm-II. To reduce the numbers of optimization parameters, a sensitivity analysis is done to determine that the above mentioned three controller parameters are the most sensitive among the rest others. Non-dominated sorting genetic algorithm-II has depicted better efficiency of optimization compared to the linear programming, genetic algorithm, particle swarm optimization, and cuckoo search algorithm. The performance of the designed optimal controller exhibits robust performance even with the variation in penetration levels of wind energy, disturbances, parameter and operating conditions in the system.

Multi-objective thermal analysis of a thermoelectric device: Influence of geometric features on device characteristics

Proper assessment of geometric features of a thermoelectric generator is important to design devices with improved performance features such as high efficiency and output power. In the present study, three the-state-of-the-art multi-objective evolutionary algorithms, namely, NSGA-II (Non-dominated Sorting Genetic Algorithm-II), GDE3 (Generalized Differential Evolution generation 3), and SMPSO (Speed-constrained Multi-objective Particle Swarm Optimization) are used to optimize the geometric features of a thermoelectric generator for improved efficiency and output power while incorporating different operating conditions. The parameters assessing geometric features of the device include shape factor and pin length size while operating parameters include temperature ratio and external load parameter. Thermal analysis incorporating geometric features and operating parameters of the device is introduced prior to the optimization study. The findings are validated against the results reported in the open literature. It is found that shape factor and pin length size have significant effect on the device performance. Increasing shape factor (S ≤ 0.5) first increases thermal efficiency to reach its maximum (∼17%), and furthermore, an increase in shape factor (S ≥ 0.5) lowers thermal efficiency significantly (∼8%). Device output power behaves similar to that of efficiency for small increment in shape factor, provided that further increase in shape factor does not influence output power of the device. A unique design configuration is present for a fixed operating condition of a thermoelectric generator; in which case, thermal efficiency and output power of the device attain high values.

Automatic generation control of multi-area power system using multi-objective non-dominated sorting genetic algorithm-II

Controllers design problems are multi objective optimization problems as the controller must satisfy several performance measures that are often conflicting and competing with each other. In multi-objective approach a set of solutions can be generated from which the designer can select a final solution according to his requirement and need. This paper presents the design and analysis Proportional Integral (PI) and Proportional Integral Derivative (PID) controller employing multi-objective Non-Dominated Shorting Genetic Algorithm-II (NSGA-II) technique for Automatic Generation Control (AGC) of an interconnected system. To minimize the effect of noise in the input signal, a filter is employed with the derivative term. Integral Time multiply Absolute Error (ITAE), minimum damping ratio of dominant eigenvalues and settling times in frequency and tie-line power deviations are considered as multiple objectives and NSGA-II is employed to generate Pareto optimal set. Further, a fuzzy-based membership value assignment method is employed to choose the best compromise solution from the obtained Pareto solution set. The proposed approach is first applied to a linear two-area power system model and then extended to a non-linear power system model by considering the effect of governor dead band non-linearity. The superiority of the proposed NSGA-II optimized PI/PID controllers has been shown by comparing the results with some recently published modern heuristic optimization approaches such as Bacteria Foraging Optimization Algorithm (BFOA), Genetic Algorithm (GA) and Craziness based Particle Swarm Optimization (CPSO) based controllers for the similar interconnected power systems.

Optimal per cent by weight of elements in diagnostic quality radiation shielding materials

By increasing the usage of radiation in all aspects of lives, the human body is becoming more exposed to ionising radiation. The purpose of this study is to find the optimal radiation shielding materials to protect humans from the radiation hazards of radiation. Some elements and compounds such as Ag, Bi, Pb, W, BaSO(4) were chosen on the basis of their attenuation coefficients and other characteristics to produce optimised radiation shielding compounds. Multi-objective non-dominated sorting genetic algorithm-II was used to optimise the weight fraction of the elements in compounds based on the dose equivalent rate, shield weight and cost. Consequently, sets of suitable compounds were obtained depending on various applications for energy 0.06 and 0.15 MeV. In addition, optimised lead free compounds were obtained. The results presented in a series of graphs should enable radiation shield designers to choose an appropriate combination according to their requirements.