Genetic Algorithm Optimization Research Articles

Thermal performance analysis and optimization of a heat pipe-based electronic thermal management system using experimental data-driven neuro-genetic technique

Heat pipes are highly efficient heat transfer devices and are used widely to dissipate heat generated by electronic components, thereby maintaining their operating temperatures and preventing overheating. The present study deals with the thermal performance prediction of a cylindrical heat pipe (length 380 mm) based electronic thermal management system using steady-state experimental investigation. The experiments are conducted under varying operational conditions, including heat inputs (10–50 W), condenser cooling water inlet temperatures (288.15, 293.15, and 298.15 K), and flow rates (10, 25, and 40 LPH). The study shows that the evaporator temperature of the heat pipe consistently rises with the increase in heat inputs for all tested conditions. The lowest evaporator temperature (311.42 K) is noticed for the cooling water inlet temperature of 288.15 K across all heat inputs. Notably, at 10 LPH, the heat pipe supplied with cooling water at 288.15 K exhibits reductions of up to 1.47 % and 2.29 % compared to 293.15 K and 298.15 K, respectively. Similar trends are also observed at 25 LPH and 40 LPH. The heat pipe’s thermal resistance is lowest (0.95 K/W) at a cooling water inlet temperature of 298.15 K. At 10 LPH, there are reductions of 10.19 % and 5.62 % compared to 288.15 K and 293.15 K, and at 40 LPH, reductions are 15.66 % and 7.89 %. The heat pipe’s evaporator heat transfer coefficient also plays a significant role and is maximum for the cooling water inlet temperature of 288.15 K at a flow rate of 10 LPH. To understand the complex behavior of the heat pipe and for better prediction of its thermal performance, a neuro-genetic (experimental data-driven artificial neural network and genetic algorithm) optimization technique is considered in the study. This predicts the optimal combination of operating parameters (heat input, cooling water inlet temperature, and flow rate) to minimize the heat pipe’s evaporator wall temperature which is found to be 312.54 K at a heat input of 10 W, flow rate of 10 LPH, and cooling water inlet temperature of 289.14 K. These input combinations are further validated through the experiments and the error in the heat pipe’s evaporator temperature is found to be 0.66 % only. Overall, this neuro-genetic technique underscores the importance of optimizing operational parameters for enhanced heat pipe performance and offers valuable insights for electronic cooling systems.

Genetic Algorithm Optimization of Sensor Placement for CO2 Concentration Observation

Genetic Algorithm Optimization of Sensor Placement for CO2 Concentration Observation

Improved Harmonic Mitigation and Power Injection Technique for Solar-fed DG System Using GA and PSO

This paper deals with Distributed Generation (DG) system requiring power quality features such as current harmonics, reactive power compensation, and power factor improvement in grid tied operation. The motivation is to combine DG system with the capabilities of shunt active filter to perform real power injection, current harmonics mitigation and power factor improvement. The control algorithm employed in this setup utilizes a reference current generator based on p-q theory together with a pulse width modulation controller for switching pulse generation. The control strategy utilizes PI controller with Genetic Algorithm (GA) and Particle Swarm Optimization (PSO) for finding optimal PI controller parameters. The effectiveness of the proposed method is verified using MATLAB/Simulink and experimental model developed for 3kWp inverter. The PI-PSO controller injects 0.588kW active power into the grid results in sharing 54% of load power demand and the current harmonics is reduced from 23.70% to 1.63%. The obtained results demonstrate that the grid tied inverter maintains harmonic standards in accordance with the IEEE-519 standard while injecting maximum possible active power to the line.

Development and application of an intelligent nitrogen removal diagnosis and optimization framework for WWTPs: Low-carbon and stable operation

Optimizing nitrogen removal is crucial for ensuring the efficient operation of wastewater treatment plants (WWTPs), but it is susceptible to variations in influent conditions and operational parameter constraints, and conflicts with the energy-saving and carbon emission reduction goals. To address these issues, this study proposes a hybrid framework integrating process simulation, machine learning, and multi-objective genetic algorithms for nitrogen removal diagnosis and optimization, aiming to predict the total nitrogen in effluent, diagnose nitrogen over-limit risks, and optimize the control strategies. Taking a full-scale WWTP as a case study, a process time-lag simulation-enhanced machine learning model (PTLS-ML) was developed, achieving R2 values of 0.94 and 0.79 for the training and testing sets, respectively. The proposed model successfully identified the potential reasons of nitrogen over-limit risks under different influent conditions and operational parameters, and accordingly provided optimization suggestions. In addition, the multi-objective optimization (MOO) algorithms analysis further demonstrated that maintaining 4–6 mg/L total nitrogen concentration in effluent by adjusting process operational parameters can effectively balance multiple objectives (i.e., effluent water quality, operating costs, and greenhouse gas emissions), achieving coordinated optimization. This framework can serve as a reference for stable operation, energy-saving, and emission reduction in the nitrogen removal of WWTPs.

Optimizing thermal energy storage in rectangular unit: Exploring the impact of moving fin with phase change material

This research presents an innovative moving fin design for a latent heat storage unit, with the objective of improving thermal performance. The methodology integrates numerical simulation, a machine learning approach, and a multi-objective genetic optimization algorithm (NSGA-II). The study optimizes fin parameters, such as fin velocity (Vf), fin thickness (tf), fin length (Lf) and initial fin position (yf). The optimization process aims to maximize both power (P) and stored energy per mass (Em), assigning equal importance to both criteria. The outcomes reveal a considerable rise in power with minor compromises in stored energy per mass. The incorporation of moving fins in rectangular enclosure with PCM leads to a significant power boost while preserving stored latent energy with minimal compromise. In comparison to the no-fin condition, fixed 1-fin and fixed 3-fin configurations lead to stored energy losses of 4.16 % and 11.73 %, respectively, accompanied by power increases of 20.48 % and 51.17 %, respectively. Conversely, the optimized condition for maximum power with moving fins incurs a mere 2.73 % stored energy loss but achieves a remarkable 173.92 % increase in power. The optimized design parameters for maximizing power (P) include Vf = 22.5 × 10−3 mm/s, yf = 60 mm, tf = 2 mm, and Lf = 40 mm.

Video-based subtle vibration measurement in the presence of large motions

Recently, phase-based methods offer precise measurement of subtle vibrations from videos but face challenges when dealing with moving objects. This paper introduces a novel video-based method for measuring subtle vibrations in the presence of large motions. It employs complex steerable filters to capture phase variations at each pixel, extracting a composite motion signal. Based on the differences in acceleration characteristics between subtle vibrations and large motions, a band-passed acceleration filter is designed to separate them, relying only on limited prior knowledge of the frequency band. The filter design minimizes passband attenuation using a genetic algorithm for iterative parameter optimization. By further incorporating a Gaussian amplitude kernel, we suppress large-amplitude nonlinear motion interference and extract subtle vibrations with acceleration characteristics. Both simulation experiments and real-world tests demonstrate that this method outperforms state-of-the-art techniques in terms of accuracy, providing a more effective approach for measuring subtle vibrations in moving objects.

Optimal cluster head localization for cluster-based wireless sensor network using free-space optical technology and genetic algorithm optimization

Optimal cluster head localization for cluster-based wireless sensor network using free-space optical technology and genetic algorithm optimization

Using genetic algorithm for optimisation of cracking time during the breaking of concrete bloc with expansive cement

In this paper, statistical, optimization methods like multiple parameter linear regression and genetic algorithm were used to establish a mathematical model of the demolition time (DT). The performance of the model was evaluated using the statistical indicators. The quality of the model was statistically evaluated, with a significant value of the correlation coefficient of 0.99081376, and low errors. Regarding the optimization of the demolition time by the genetic algorithms method, the results obtained are conclusive with a demolition time of unreinforced concrete of (17 h) which is lower than the demolition time obtained experimentally (36 h).

Advanced cyclic constitutive model and parameter calibration method for austenitic stainless steel

Austenitic stainless steel is recognized for its potential in improving structural seismic resistance due to its exceptional ductility. This study seeks to analyse the material characteristics and cyclic constitutive model of austenitic stainless steel under cyclic loading using a combination of experiments and numerical studies. The primary goal is to enhance the precision of numerical simulations predicting the seismic performance of stainless steel and to minimize the costs associated with calibrating the parameters of the cyclic constitutive model. By conducting cyclic loading experiments on stainless steel with different plate thicknesses, the hysteresis curves under different loading protocols were obtained. The loading protocol significantly influences the cyclic hardening behaviour of stainless steel. To calibrate material parameters in the Chaboche model more effectively, a new parameter calibration method based on genetic algorithm optimization is proposed. Additionally, a method is proposed to calibrate the material parameters of the Hu model by utilizing the monotonic tensile stress-strain curve of austenitic stainless steel, which provides a new material model option for the numerical simulation of stainless steel seismic performance. The applicability of the Chaboche model and the Hu model in numerical simulations of stainless steel members is then verified and compared using existing seismic performance test results. The findings indicate that the Hu model offers more accurate numerical simulations of cyclic loading on austenitic stainless steel members compared to the Chaboche model.

Enhancing agricultural land valuation in land consolidation projects through cooperative game theory and genetic algorithm optimization

The purpose of land valuation in land consolidation projects is to determine the relative value between lands of different quality, location and etc. This principle is crucial for ensuring fairness and justice among participants. Efficient land utilization and rural progress are hindered by the fragmentation of agricultural lands, necessitating land consolidation. However, fair valuation of parcels remains a challenge, impeding the success of consolidation efforts. This study delves into the intricate issues related to land consolidation and complex dynamics of decision-making in agricultural land valuation. This study aims to address the challenge of fair valuation in land consolidation projects by introducing a novel methodology that integrates cooperative game theory with metaheuristic algorithms. The goal is to increase the likelihood of stakeholders accepting land consolidation schemes by utilizing the interactive components of the decision-making process. This approach takes into account individual preferences of land owners and utilizes game theory to model competition, interaction, and cooperation among them. Central to this concept are genetic algorithm, which plays a key role in producing diverse solutions taking into account various landowners' priorities. A case study in Fartan village, Esfarayen city, Iran, is conducted to evaluate the effectiveness of the method. Two scenarios are examined: one combining unanimity fallback bargaining technique with Nash bargaining, and another incorporating fallback bargaining with impasse technique with Nash bargaining. Upon comparative analysis, the second scenario proves to be better in ensuring equity among stakeholders. It encourages landowners to negotiate decisively, using a process that integrates fallback bargaining with impasse and Nash bargaining, taking into account the varying levels of each owner's negotiation power in both steps. This ensures a negotiated outcome that respects the diverse priorities of each landowner. This scenario considers variations in individual negotiating power not only in Nash bargaining step but also in fallback bargaining and ensures a comprehensive and fair decision-making process during land valuation. This research introduces a novel strategy to enhance group decision-making in agricultural land valuation, fostering stakeholders' agreement and facilitating successful land consolidation projects. The proposed method provides a land valuation approach that can receive high degree of farmers' agreement and provides a good base to enter the next stages of the land consolidation.

QUALITY AND PRODUCTIVITY IMPROVEMENT IN THE MILLING OF POLYOXYMETHYLENE CO-POLYMER (POM C) USING RSM, SVM AND GENETIC ALGORITHM

This paper aims to conduct an economic and environmental machining procedure (dry condition) during face milling of the Polyoxymethylene Co-polymer. In this context, an experimental study based on Taguchi’s design was conducted to develop empirical models using Response Surface Methodology (RSM) on one hand and Support Vector Machine (SVM) for regression on the other hand. The ANalysis of VAriance (ANOVA) is conducted to determine the contribution and the significance of each cutting parameter on the surface quality and productivity (MRR). The obtained models are being compared to determine the most efficient approach. The last part is to find the optimum cutting combination by using Genetic Algorithm (GA) optimization based on SVM models, whether to minimize surface roughness Ra, or for composite objective to improve the quality and to increase the productivity. The results show that feed per tooth (fz) is the most affecting parameter on Ra followed by depth of cut (ap) and then the cutting velocity (Vc). SVM was more robust than RSM with less deviation error.

The surrogate model for short-term extreme response prediction based on ANN and Kriging algorithm

Numerical simulation is a common method for calculating the short-term extreme response of floating offshore wind turbines (FOWTs). However, it requires significant computational resources. This study presents a dynamic response database for a 5MW semi-submersible FOWT under complex environmental conditions, including wind speed, effective wave height, and wave spectral peak period, using a numerical model. The peak over threshold (POT) method can be used to obtain the parametric database of short-term extreme responses, which includes the short-term extreme response distribution parameters for four responses: float surge, mooring tension, outward bending moment at the leaf root surface (OoPBM) and tower base pitching moment (TBPM). And the parameter database is applied to train models such as the Genetic Algorithm optimization Back Propagation neural network (GA-BP) and Kriging algorithm models. The research indicates that a correlation can be established between environmental conditions and short-term extreme response parameters using two algorithms. The accuracy of surrogate model prediction for some parameters can be improved by grouping the data based on wind speed and training separately. Additionally, selecting the appropriate surrogate model for each parameter separately can improve the accuracy of short-term extreme response prediction.

Low-frequency broadband acoustic metamaterial absorber based on nested resonator and synergistic coupled weak resonances

Utilizing absorbers with sub-wavelength thickness for low-frequency broadband noise control is a challenging problem, and rapid on-demand design of structures based on target noise frequency has received continuous attention. In this work, nested cavities are introduced into the typical neck-embedded Helmholtz resonator (NEHR) to obtain the nested neck-embedded Helmholtz resonator (NNEHR), which exhibits better cavity partitioning volume fraction and covers wider sound absorption band. Both theoretical analysis and simulations demonstrate that NNEHR possesses superior acoustic properties: generating an additional absorption peak, lowering the position of the first absorption peak by 11 %, and increasing the absorption coefficient by 4.7 %. Instantaneous velocity fields and thermal-viscous energy dissipation density illustrate that the efficient sound absorption of NNEHR originates from resonant dissipation in the neck and surrounding areas. Furthermore, by combining the theoretical model with genetic algorithms, three sets of NNEHR metasurfaces are optimized. The optimized structures achieve average absorption coefficients of 0.831, 0.913, and 0.885 in the range of 250–550 Hz, 400–1000 Hz, and 500–2000 Hz, with a thickness of only 50 mm, reflecting sub-wavelength, low-frequency broadband sound absorption characteristics. The excellent absorption stems from synergistic coupled weak resonances and higher-order absorption peaks of constituent units, and the overdamping characteristic ensures the realization of the optimal structure with minimal thickness. The contribution of weak resonant units to the total sound absorption performance can be measured by the surface admittance normalized by the total incident area, and the essence of the coupling effect is the strong interaction between units with adjacent absorbing frequencies. The proposed structure exhibits good sound absorption performance and great adjustability, while the genetic algorithm optimization based on the theoretical model demonstrates high efficiency and robustness, providing a methodology for the design and on-demand optimization of low-frequency broadband structures.

TL-LFF Net: transfer learning based lighter, faster, and frozen network for the detection of multi-scale mixed intracranial hemorrhages through genetic optimization algorithm

TL-LFF Net: transfer learning based lighter, faster, and frozen network for the detection of multi-scale mixed intracranial hemorrhages through genetic optimization algorithm

A two-stage optimization model for relief distribution to disaster survivors under two-fold uncertainty

Disasters are unforeseen occurrences requiring extensive transport deployment to support and relieve victims. Sometimes, this transportation is not feasible directly from some supply points to some destination points. Due to this tragedy, it is unclear precisely what is available at supply points, what is needed at destinations, how much transportation capacity there is, and what the routes are like. In this study, we investigate a two-stage multi-item fixed charge four-dimensional transportation problem using the concept of big data theory under the two-fold uncertainties. Here, the model’s parameters such as unit transportation costs, availabilities of items at the suppliers, fixed charges, capacities of conveyances, and demands of the items at the retailers are considered type-2 zigzag uncertain variables. Using big data theory and based on uncertain programming theory, two novel uncertain models are developed such as chance-constrained programming and expected value programming model. These two uncertain models transformed into the deterministic form via uncertainty inverse distribution theory. A critical value based reduction method with three categories (i.e., expected value, pessimistic value, and optimistic value) is applied to reduce the type-2 zigzag uncertain variable to the type-1 zigzag uncertain variable. The genetic algorithm and particle swarm optimization techniques have been proposed to find the optimal solution for the two deterministic models. The efficiency of our proposed approach is demonstrated with a real-life numerical example.

Indoor Infrared Sensor Layout Optimization for Elderly Monitoring Based on Fused Genetic Gray Wolf Optimization (FGGWO) Algorithm.

With the increasing aging of the global population, the efficiency and accuracy of the elderly monitoring system become crucial. In this paper, a sensor layout optimization method, the Fusion Genetic Gray Wolf Optimization (FGGWO) algorithm, is proposed which utilizes the global search capability of Genetic Algorithm (GA) and the local search capability of Gray Wolf Optimization algorithm (GWO) to improve the efficiency and accuracy of the sensor layout in elderly monitoring systems. It does so by optimizing the indoor infrared sensor layout in the elderly monitoring system to improve the efficiency and coverage of the sensor layout in the elderly monitoring system. Test results show that the FGGWO algorithm is superior to the single optimization algorithm in monitoring coverage, accuracy, and system efficiency. In addition, the algorithm is able to effectively avoid the local optimum problem commonly found in traditional methods and to reduce the number of sensors used, while maintaining high monitoring accuracy. The flexibility and adaptability of the algorithm bode well for its potential application in a wide range of intelligent surveillance scenarios. Future research will explore how deep learning techniques can be integrated into the FGGWO algorithm to further enhance the system's adaptive and real-time response capabilities.

An Improved Thermal Management of Lithium Based Batteries Employing Genetic Algorithm Optimization

Lithium-based battery systems (LBS) are used in various applications, from the smallest electronic devices to power generation plants. LBS energy storage technology, which can offer high power and high energy density simultaneously, can respond to continuous energy needs and meet sudden power demands. The lifetime of LBSs, which are seen as a high-cost storage technology, depends on many parameters such as usage habits, temperature and charge rate. Since LBSs store energy electrochemically, they are seriously affected by temperature. High-temperature environments increase the thermal stress on the LBS and cause its chemical structure to deteriorate much faster. In addition, the fast charging feature of LBSs, which is presented as an advantage, increases the internal temperature of the cell and negatively affects the battery life. The proposed energy management approach ensures that the ambient temperature affects the charging speed of the battery and that the charging speed is adaptively updated continuously. So, the two parameters that harm battery health absorb each other, and the battery has a longer life. A new differential approach has been created for the proposed energy management system. The total amount of energy that can be withdrawn from the LBS is increased by 14.18% compared to the LBS controlled with the standard energy management system using the genetic algorithm optimized parameters. In this way, the LBS replacement period is extended, providing both cost benefits and environmentally friendly management by LBSs turning into chemical waste later.

Developing a predictive method based on the vibration behavior of a naval ship hull model using hybrid fuzzy meta-heuristic algorithms

Ships are complex structures composed of various components with exclusive dynamic behaviors and natural frequencies, so assessing their vibration behavior is essential. Some situations in practical applications could alter the ship's dynamic characteristics and cause significant changes in its vibration behavior. Since the ship's mass is one of the most important dynamic parameters in determining vibration behavior, local mass change can lead to changes in its dynamic characteristics and must be considered. This study aims to develop a method to predict the effect of the location and magnitude of mass change on the ship hull's vibration behavior. It would be feasible to enhance the dynamic behavior and reduce undesirable noises by locating the mass change on the ship hull. In this regard, experimental and numerical modal analysis is performed on a scaled model of a naval ship hull. The baseline FE model is used to calculate the variation in frequencies of the model caused by different local mass change scenarios. Using these measurements a fuzzy system is generated and optimized by Genetic and Particle Swarm Optimization algorithms. Finally, the efficiency of the fuzzy-PSO is validated by different mass change scenarios foreseen on the physical model of the ship hull.

Process Optimization for Antarctic Krill (Euphausia superba) Sauce Based on Back Propagation Neural Network Combined with Genetic Algorithm

Using Antarctic krill (Euphausia superba) as the research object, we optimized the process conditions for Antarctic krill sauce (AkS) by including three factors (salt addition, rock sugar addition, and the oil-to-material ratio) and sensory evaluation as response values. The data from the response surface were fed into the back propagation (BP) neural network training, generating a model mapping the process conditions and sensory scores, which were subsequently combined with the genetic algorithm (GA) for global optimization to determine the optimal process for AkS preparation. The results revealed that the response surface model was well suited to the BP neural network training and prediction sets, with correlation values of 0.98 and 0.95, respectively. The fitting prediction effect was obvious for the sensory scoring results of the product. The parameters obtained from the GA’s global optimization search accord with the analytical results of the response surface. The findings demonstrated that combining a BP neural network with a GA can enhance the AkS preparation technique. Under optimal processing conditions, AkS has a high sensory score and protein and carbohydrate contents, moderate fat content, minimal fat oxidation, and non-detectable pathogens, indicating that the AkS in this study was nutritious and safe to consume.

A computationally intelligent framework for traffic engineering and congestion management in software-defined network (SDN)

Software-defined networking (SDN) revolutionizes network administration by centralizing control and decoupling the data plane from the control plane. Despite its advantages, the escalating volume of network traffic induces congestion at nodes, adversely affecting routing quality and overall performance. Addressing congestion has become imperative due to its emergence as a fundamental challenge in network management. Previous strategies often faced drawbacks in handling congestion, with issues arising from the inability to efficiently manage heavy packet surges in specific network regions. In response, this research introduces a novel approach integrating a multiplicative gated recurrent neural network with a congestion-aware hunter prey optimization (HPO) algorithm for effective traffic management in SDN. The framework leverages machine learning and deep learning techniques, acknowledged for their proficiency in processing traffic data. Comparative simulations showcase the congestion-aware HPO algorithm's superiority, achieving a normalized throughput 3.4–7.6% higher than genetic algorithm (GA) and particle swarm optimization (PSO) alternatives. Notably, the proposed framework significantly reduces data transmission delays by 58–65% compared to the GA and PSO algorithms. This research not only contributes a state-of-the-art solution but also addresses drawbacks observed in existing methodologies, thereby advancing the field of traffic engineering and congestion management in SDN. The proposed framework demonstrates notable enhancements in both throughput and latency, providing a more robust foundation for future SDN implementations.