Genetic Algorithm Research Articles

Digital twin development for PEMFC degradation estimation and aging data generation

One obstacle limiting the commercialization of proton exchange membrane fuel cells is the uncertainties in their lifetime due to aging. Further research on the degradation is also constrained by the lack of aging data. This work proposes a digital twin based on physical models with embedded degradation mechanisms for both degradation estimation and generating aging data to address this issue. Semi-empirical models are adopted to quantify three degradation mechanisms within membrane electrode assembly (MEA), i.e., membrane conductivity decrease, active surface area reduction, and porosity loss. Open-access datasets are employed in determining those aging factors via genetic algorithm. The results indicate that the MEA undergoes rapid aging in the initial stages. The digital twin model can generate aging data with a maximum deviation of 5%. Moreover, the generated two-dimensional data further provides virtual reality features, which are also demonstrated on several accelerated degradation stressors, i.e., temperature, humidity, and voltage.

Multiscale topology optimization for designing locally resonant acoustic metamaterials with specified low-frequency bandgaps

Locally resonant acoustic metamaterials (LRAMs) have significant potential to isolate low-frequency vibrations and noise, whereas designing them with specified bandgaps is challenging. Compared to the monoscale method, the multiscale method can design microstructures that form equivalent materials to act as scatterers, coatings, and matrices. This may aid in obtaining LRAMs that are sometimes difficult to achieve with the monoscale method. Therefore, a multiscale topology optimization method is presented to design LRAMs with bandgaps that meet specified frequency constraints. Since bandgap optimizations are complicated, many local minimum solutions may exist when using sensitivity-based methods. To mitigate this issue, a macro-parameter optimization stage using a genetic algorithm (GA) is added between the macro and micro optimizations in this top-down multiscale framework. As a result, the method comprises three optimization stages: macro-bandgap optimization, macro-parameter optimization, and micro-optimization. Since the macrostructures consist of multiple microstructures and the microstructures consist of multiple materials, a parameterized level-set-based multi-material topology method is adopted to obtain topologies on both scales. The effectiveness of the proposed method is demonstrated through numerical examples of two optimization problems. The first is to obtain LRAMs with the maximum bandgap width while ensuring their bandgaps encompass specified frequency ranges. The other is to obtain LRAMs with specified bandgaps. Successfully obtained LRAMs with specified bandgaps demonstrate the application prospects of this method in designing structures and devices to address issues related to vibrations and noise.

Subwavelength broadband light-harvesting metacoating for infrared camouflage and anti-counterfeiting empowered by inverse design

Broadband mid-infrared (MIR) light harvesting is critical for a wide range of applications, including thermophotovoltaic conversion, thermal sensing and imaging, infrared camouflage and anti-counterfeiting technologies. In this study, we present the design and experimental validation of a deep-subwavelength broadband MIR light-harvesting metacoating (MMC), optimized through a genetic algorithm (GA)-based inverse design approach. The strength of this approach lies in its ability to automate and optimize the complex multilayer structure, encompassing both material selection and structural thickness, thereby achieving unparalleled performance in broadband MIR light absorption, with an average absorbance of approximately 0.85 across the 3–13 μm spectral range and nearly perfect absorption within the 4–12 μm range. This exceptional performance is attributed to strong electromagnetic localization within its multilayer configuration, facilitating efficient energy dissipation via high-loss materials such as bismuth and titanium. Notably, the MMC exhibits robust performance with respect to angle and polarization variations, maintaining high absorbance even at incident angles up to 70°. Its large-area fabrication capabilities and compatibility with various substrates further enhance its practical applicability. Two specific applications, long-wavelength infrared camouflage and anti-counterfeiting, highlight its potential for real-world deployment. In these applications, the MMC seamlessly integrates into high-emission environments and enables the modulation of patterned infrared emission, providing a lithography-free, cost-effective solution compared to conventional methods relying on artificially engineered structures. This work underscores the versatility of the developed MMC for a diverse array of MIR applications, ranging from camouflage technologies to advanced security measures.

Optimal Active Debris Removal mission planning to inform policy decisions

Active Debris Removal (ADR) will be important to ensure the long-term sustainability of the space environment and to preserve benefits derived from space for those here on Earth. Effective ADR relies on optimal mission planning to select Space Objects (SOs) with the highest risk. The Advanced Market Commitment (AMC) concept is discussed as a method to increase the quantity of ADR over market equilibrium to promote space sustainability and accelerate the development of commercial ADR. The MIT Orbital Capacity Assessment Tool - Monte Carlo (MOCAT-MC) is utilized to obtain information about the probability of collision with other SOs and the number of debris generated over a long propagation and is combined with the criticality of spacecraft index, a static ranking index, to obtain the MIT Risk Index (MITRI), which quantifies the risk posed by an SO. A Genetic Algorithm (GA) is used with a binary chromosome encoding to perform evolutionary optimization and identify the optimal mission route by solving a mixed integer nonlinear problem while respecting spacecraft Δv and thrust constraints. MITRI is demonstrated as an efficacy metric to inform subsidy pricing for an AMC. Three potential AMC case studies are described: a government customer selecting objects for removal, a servicer selecting and optimizing an object set based on total environmental risk and subsidy, and a commercial operator paying for optimized remediation in their particular region of space. MITRI provides a mechanism to align private and public incentives for risk reduction.

Optimization control of the D-shaped cylinder flow with genetic algorithm and Coanda pulsation jets

Optimization control of the D-shaped cylinder flow with genetic algorithm and Coanda pulsation jets

Application of monarch butterfly optimization algorithm for solving optimal power flow

This paper proposes a highly flexible, robust, and efficient constraint-handling approach for the solution of the optimal power flow (OPF) problem and this solution lies in the ability to solve the power system problem and avoid the mathematical traps. Centralized control of the power system has become inevitable, in the interest of secure, reliable, and economic operation of the system. In this work, OPF is solved by considering the three distinct objectives, generation cost minimization, power loss minimization, and enhancement of voltage stability index. These three objectives are solved separately by considering the evolutionary-based monarch butterfly optimization (MBO) algorithm. This MBO algorithm is validated on the IEEE 30 bus network and the obtained results are compared with differential evolution, particle swarm optimization, genetic algorithm, and Jaya algorithm. The obtained results reveal that among the various optimization algorithms considered in this work, the MBO evolves as the best algorithm for all three case studies.

Environmental impact assessment of a direct methanol fuel cell and strategic mitigation guidelines

Direct methanol fuel cells (DMFCs) are gaining attention as a viable technology for portable and remote applications due to the benefits of methanol as fuel. However, the environmental implications of this technology have not been thoroughly evaluated. This study aims to conduct a comprehensive assessment of the environmental impact of a DMFC throughout its entire life cycle, and based on the findings, propose guidelines for minimizing the impact. To eliminate any potential biases, a two-step design methodology is applied. The first step involves obtaining the optimal preliminary design, for which a genetic algorithm is implemented. The second step is to conduct the environmental impact study on that optimal configuration. As a study case, a DMFC for a highly demanding application, such as an unmanned aerial vehicle, is selected, using green methanol as fuel. The results reveal that extraction and production stage has the greatest effect on the environment (74.1%), compared to use (25.8%) and transport stages (0.1%). Among the components of the stack, the catalysts have the most significant environmental footprint, 93.3% of the total impact of the stack during the extraction and production stage, while bipolar plates represent only 5.9%, despite comprising 86% of the stack’s mass.

Research on performance curve prediction of centrifugal pump based on improved whale optimization algorithm and characteristic deformation method

This article proposes an improved hybrid method combining whale optimization algorithm (IMWOA) and the characteristic deformation method (CDM) to predict the performance curve of centrifugal pumps. The traditional whale optimization algorithm (WOA) is enhanced by introducing chaos mapping, adaptive weight, nonlinear convergence factor strategies, and mutation concept from the genetic algorithm. These improvements make IMWOA significantly superior to the traditional WOA in the basic criterion test functions. To address the limitations of sample set size and differences in data characteristics in practical applications, this paper also introduces CDM strategies, including dynamic parameter adjustment strategy and mixed standardization strategy. Comparative analysis shows that the IMWOA-CDM method achieves better results in various performance evaluation indicators. The final experimental results validated the high accuracy and reliability of the IMWOA-CDM method in predicting the performance curve of centrifugal pumps, with a maximum absolute error of 1.21 m for head and 1.08% for efficiency.

Optimization design of a windshield for a 12,000 TEU container ship based on a support vector regression surrogate model

This study presents the design of a windshield for a 12,000 TEU container ship using a multidisciplinary optimization system aimed at enhancing its aerodynamic performance. The framework integrates parametric modeling, design of experiment (DOE), numerical simulation, support vector regression (SVR)-based approximation, and a genetic algorithm (GA). Initially, the flow field around the ship is predicted using Reynolds-averaged Navier–Stokes (RANS) equations, with accuracy validated against computational fluid dynamics (CFD) and experimental fluid dynamics (EFD) results. The windshield’s shape is then defined by three Bezier curves, and six design variables are selected based on these curves to ensure smooth deformation. Subsequently, 120 sample points are chosen within the design space using the DOE method, and an SVR-based surrogate model is established. Optimization is performed using the multi-island genetic algorithm to determine the windshield configuration. Validation tests confirm the robustness of the optimization process. On this basis, the drag reduction mechanism of the windshield is summarized and analyzed. Results demonstrate that the optimization system effectively enhances the aerodynamic performance of the container ship, achieving a maximum drag reduction rate of 20.67% under headwind conditions and significant improvement across wind angles from 0° to 60°.

Design, Synthesis, Computational Studies and Evaluation of Novel 2, 4, 5-Trisubstituted Pyrimidine Derivatives for Anticancer Activity against MCF-7 and A549 Cell Lines

Synthesized novel trisubstituted pyrimidine derivatives (U 01-15) were tested for anti-cancer efficacy against two cancer cell line MCF-7 and A549. Several spectroscopic methods assisted to characterized and confirmed all synthesized compounds. Some of the synthesized pyrimidine derivatives showed strong effectiveness, with IC50 values comparable to the standard drug doxorubicin and gefitinib. Compounds U-02, U-04, U-07, U-10 and U-11 showed good anti-cancer activity for both cell lines having IC50 values in range from 12.06 µM to 22.45 µM, while compounds U-06 and U-03 showed moderate potency against both the cell lines, respectively. Using PyRx software (based on Auto Dock 4 and a genetic algorithm), all the synthesized compounds were put through a molecular docking with receptor tyrosine-protein kinase erbB-4 and docking score was compared to approved drugs, gefitinib and lapatinib. Interestingly almost all derivatives showed good docking score as compared to reference drugs. Molecular dynamics simulation of the U-11 protein-ligand complex over 100 ns revealed key insights into stability and conformational changes. RMSD analysis indicated stability between 10-20 ns with fluctuations up to 5.71 Å, while RMSF showed an average fluctuation of 1.74 Å, particularly in the loop regions. Molecular interactions, including hydrogen bonds, were observed with key residues such as ASP836, MET774, and LEU769.Future studies could focus on optimizing the most promising pyrimidine derivatives, such as U-02, U-04, U-07, U-10, and U-11, for enhanced potency and selectivity through advanced biological testing and structure-activity relationship studies may provide deeper insights into their therapeutic potential against cancer.

Surrogate-based positioning optimization of hip prostheses for minimal stress shielding

The stress shielding phenomenon causes undesirable changes in stress distribution in the bones in which implants are implanted. This phenomenon leads to a gradual decrease in bone density in the vicinity of the implant and ultimately loosening. To improve the endurance of the prosthesis and postpone the revision surgery the prosthesis should be designed and positioned in such a way that the post-implant stress distribution within the bones is as close to the natural distribution as possible.We formulate the problem of achieving a near-normal stress distribution as a constrained optimization problem in which the difference between pre- and post-implant stress distributions constitutes the loss function and five positional and dimensional parameters, including Femoral Anteversion, Neck Shaft Angle, Femoral Head Offset, Cup Version, and Cup Inclination comprise the set of design variables. Finite Elements (FE) analysis is used to obtain the stress distribution in bones before and after the implantation. To create a FE model, first a three-dimensional model of the patient's hip is created using CT images. The model is then subjected to the loads obtained from the patient's gait analysis, and the Stress Shielding Index (SSI) is calculated at critical points of the bones before and after the implantation. The difference between pre- and post-implant SSI values defines the cost function. To reduce the computational cost of numerous cost function evaluations a surrogate model (a 5 × 1 MLP neural network) is employed to predict the value of the cost function. Design Of Experiments (DOE) is used to sample the hyperspace of the design variables and generate training, test and validation data. The optimization problem is solved using Genetic Algorithms and the results are compared with with the results of the best set of initial samples.Results from the proposed approach show a significant reduction in the difference between pre- and post-implant stress distributions and a 12% reduction in the Stress Shielding Index.

Innovative Method to Select Optimal Plugging Materials for Preventing Loss Circulation in Deep Fractured Reservoirs Using Machine Learning

Summary Lost circulation, a critical issue in drilling operations caused by drilling fluid loss into formation fractures, is a significant barrier in the exploration and production of oil, natural gas, and geothermal reservoirs. Effective design of the plugging formula to mitigate such losses is vital for the successful extraction of these resources. To efficiently design the plugging formula, in this paper we determine the key performance parameters of plugging materials based on the formation mechanism of the plugging zone, using them as feature input variables. We then use multitask learning (MTL) to establish a high-precision prediction model for the plugging formula, followed by the development of a mathematical optimization model for selecting performance parameters of the plugging formula, with displacement pressure and cumulative loss volume as the objective functions. An improved particle swarm optimization (PSO) algorithm is used to solve this mathematical model and determine the characteristic parameters of the plugging formula. Based on these parameters, the appropriate types of plugging materials, including bridging materials, fillers, and deformable reinforcement materials, are identified for the formula. The results show that the improved PSO algorithm outperforms the basic PSO algorithm, genetic algorithms, and whale optimization algorithms in solving the mathematical optimization model, with a performance improvement of about 10%. Additionally, sensitivity analysis confirms the model’s robustness, revealing that bridging materials play a critical role in the effectiveness of the plugging formula. As the variety of bridging, filling, and deformable reinforcement materials increases, their displacement pressure improves. More specifically, the analysis explores how the friction coefficient, D90 particle-size distribution, thermostability, compressive strength, and acid solubility of bridging materials affect displacement pressure and cumulative loss volume. Experimental findings validate that the innovative method to select optimal plugging materials for deep fractured reservoirs, leveraging MTL and intelligent optimization, facilitates the swift and effective development of deep fracture plugging strategies. This method not only assures effective fracture plugging but also minimizes material consumption in the formulations, thereby reducing overall material costs. The proposed method provides new novel perspectives and a theoretical foundation for the design of the deep fractured reservoir plugging formula.

An adaptive genetic algorithm with neighborhood search for integrated O2O takeaway order assignment and delivery optimization by e-bikes with varied compartments

To improve the dining experiences, online-to-offline (O2O) takeaway services with warm-keeping or refrigerated requirements are quickly expanding and becoming popular. However, single-compartment e-bikes are commonly used in takeaway platforms, which can only meet one kind of requirements and may result in an inflexible delivery. Within this context, a new type of e-bikes, namely e-bikes with mixed compartments, is introduced. Thus, warm-keeping and refrigerated orders can be delivered by one bike, namely on one route. This paper considers an integrated order assignment and delivery problem by e-bikes with warm, refrigerated, and mixed compartments (AD-EBM). To solve the problem, we develop a novel integer programming formulation to minimize the total cost by determining order assignments and finding optimal routes, and then some properties of the solutions are provided from the view of mathematics. An algorithm is designed by combining the self-adaptive genetic algorithm with the neighborhood search method (SGA-NS). Numerical experiments are conducted based on simulated different-scale takeaway instances. The experimental results highlight the excellent performance of the SGA-NS and the results are quite encouraging compared with Gurobi solver, SGA, and NS. The results of the model comparison demonstrate that the AD-EBM offers 12.38% total cost savings on average, compared to using only single-compartment e-bikes. A sensitivity analysis is performed to explore the effects of the mixed compartment costs, the customer acceptable delay time, the penalty costs for delays, and the e-bike capacity for the platform’s daily operations. Some management insights are provided to facilitate the O2O takeaway delivery.

X-Shooting ULLYSES: Massive Stars at low metallicity

Context. Current implementations of mass loss for hot, massive stars in stellar evolution models usually include a sharp increase in mass loss when blue supergiants become cooler than Teff ∼ 20 − 22 kK. Such a drastic mass-loss jump has traditionally been motivated by the potential presence of a so-called bistability ionisation effect, which may occur for line-driven winds in this temperature region due to recombination of important line-driving ions. Aims. We perform quantitative spectroscopy using UV (ULLYSES program) and optical (XShootU collaboration) data for 17 OB-supergiant stars in the LMC (covering the range Teff ∼ 14 − 32 kK), deriving absolute constraints on global stellar, wind, and clumping parameters. We examine whether there are any empirical signs of a mass-loss jump in the investigated region, and we study the clumped nature of the wind. Methods. We used a combination of the model atmosphere code FASTWIND and the genetic algorithm (GA) code Kiwi-GA to fit synthetic spectra of a multitude of diagnostic spectral lines in the optical and UV. Results. We find an almost monotonic decrease of mass-loss rate with effective temperature, with no signs of any upward mass loss jump anywhere in the examined region. Standard theoretical comparison models, which include a strong bistability jump thus severely overpredict the empirical mass-loss rates on the cool side of the predicted jump. Another key result is that across our sample we find that on average about 40% of the total wind mass seems to reside in the more diluted medium in between dense clumps. Conclusions. Our derived mass-loss rates suggest that for applications such as stellar evolution one should not include a drastic bistability jump in mass loss for stars in the temperature and luminosity region investigated here. The derived high values of interclump density further suggest that the common assumption of an effectively void interclump medium (applied in the vast majority of spectroscopic studies of hot star winds) is not generally valid in this parameter regime.

Dimensionality reduction enabled efficient kinetic parameters estimation and process optimization during continuous flow synthesis of ibuprofen

Complex reaction networks with multiple components and unknown kinetic parameters are commonly encountered in the process of reaction kinetic and reactor modeling. In this study, a dimensionality reduction strategy is used to effectively solve complex reaction kinetics-reactor coupled model. Ten unknown kinetic parameters from the synthesis of ibuprofen are identified based on genetic algorithm, which employs the elite and adaptation strategies. A convergence region is determined to compromise the accuracy and stability of the solutions. The statistical analyses are performed to clarify the reliability of the estimated parameters, which are also validated by the experimental data. Dynamic analyses show that only 1.2 times of the average residence time is required to make the flow-reaction process reach steady state. The sensitivity analyses help bridge the gap between the yield of ibuprofen and operating conditions. The proposed method can provide general guidelines for kinetic parameters estimation and optimization in similar systems.

A new approach based on genetic algorithm for computation off-loading optimization in multi-access edge computing networks

The proliferation of smart devices and the increasing demand for resource- intensive applications present significant challenges in terms of computational efficiency, leading to surge in data traffic. While cloud computing offers partial solutions, its centralized architecture raises concerns about latency. Multi-access edge computing (MEC) emerges as promising alternative by deploying servers at the network edge to bring computations closer to user devices. However, op- timizing computation offloading in the dynamic MEC environment remains a complex challenge. This paper introduces novel genetic algorithm-based ap- proach for efficient computation offloading in MEC, considering processing and transmission delays, user preferences, and system constraints. The pro- posed approach integrates computation offloading and resource allocation al- gorithm based on evolutionary principles, combined with a greedy strategy to maximize overall system performance. By utilizing genetic algorithms, the pro- posed method enables dynamic adaptation to changing conditions, eliminating the need for intricate mathematical models and providing an appealing solution to the complexities inherent in MEC. The urgency of this research arises from the critical need to enhance mobile application performance. Simulation re- sults demonstrate the robustness and efficacy of our approach in achieving near- optimal solutions while efficiently balancing computation offloading, minimiz- ing latency, and maximizing resource utilization. Our approach offers flexibility and adaptability, contributing to advancement of MEC networks and addressing the requirements of latency-sensitive applications.

Optimization of Microwave-Assisted Polyphenol Extraction and Antioxidant Activity from Papaya Peel Using Response Surface Methodology and Artificial Neural Network

The objective of the present study is to determine the optimal conditions of microwave-assisted extraction (MAE) such as microwave power (MWP), irradiation time (I-time), ethanol concentration (EtOH%), and solvent-to-solid ratio (S/S) for maximizing total polyphenol content (TPC) and 2,2-diphenyl-1-picrylhydrazyl (DPPH) radical scavenging activity from papaya peel. Box-Behnken design (BBD) was used considering MWP 300–600 W, I-time 60-120 s, EtOH% 30-70%, and S/S 30-70 mL/g. Additionally, response surface methodology (RSM) and artificial neural networks (ANN) were employed for modelling, with cross-validation to enhance reliability. These models were combined with the desirability function (DF) and/or genetic algorithm (GA) optimization approaches. Maximizing TPC and DPPH activity while maintaining MWP, I-time, EtOH%, and S/S within their respective ranges using hybrid optimization approaches (RSM-DF: TPC = 1058 mgGAE/100g, and DPPH = 83%, RSM-GA: TPC = 1064 mgGAE/100g and DPPH = 79%, and ANN-GA: TPC = 1086 mgGAE/100g, and DPPH = 83%,) yielded consistent optimal results. An additional optimization approach (RSM-DF: TPC = 955 mgGAE/100g, and DPPH = 90%), aimed at minimizing MWP, I-time, EtOH%, and S/S while maximizing TPC and DPPH activity, showed a significant reduction of approximately 3 L in ethanol consumption for each 100 g of dry samples. The maximized TPC and DPPH activity in all four approaches showed a significant (p < 0.05) alignment with their corresponding validation tests, demonstrating the better performance of these modelling and optimization processes. In terms of assessing the effectiveness of microwave assistance, conventional solvent extraction was also performed, maintaining a 70 mL/g S/S ratio of 55% ethanol at 60°C for 2 h. This method resulted in lower values of TPC (857 ± 23 g GAE/100g) yield and DPPH activity (72 ± 5%) compared to the optimized condition of MAE.

A novel heat load prediction model of district heating system based on hybrid whale optimization algorithm (WOA) and CNN-LSTM with attention mechanism

Machine learning models, particularly long short-term memory (LSTM) networks, have been extensively employed for heat load prediction in district heating systems (DHS). Nevertheless, the over-reliance on default hyperparameter settings in most methods hinders further enhancement of prediction accuracy. A novel load prediction model is presented, which integrates the whale optimization algorithm (WOA) to refine the hyperparameters of an LSTM model bolstered by an attention mechanism (ATT) and convolutional neural network (CNN). Three hybrid models (WOA-CNN-ATT-LSTM, PSO-CNN-ATT-LSTM and GA-CNN-ATT-LSTM) are constructed by comparing WOA with particle swarm optimization (PSO) and genetic algorithm (GA). The proposed hybrid models are evaluated against traditional LSTM models using an 1100-hour dataset from a real DHS. The outcomes reveal that the WOA-CNN-ATT-LSTM model surpasses both the PSO-CNN-ATT-LSTM and GA-CNN-ATT-LSTM models in heat load prediction accuracy, achieving improvements of 1.9% and 3.2% respectively, and attaining the highest prediction accuracy (R2=0.9962, MSE=0.0001, MAE=0.0082). Moreover, the WOA-CNN-ATT-LSTM model demonstrates superior performance across various time scales (half-day, one-day, three-days, and one-week), highlighting its robustness in heat load prediction. This novel model adaptively adjusts its hyperparameters to identify the optimal configuration, thereby significantly augmenting the overall predictive capabilities of the model.

Multi-physics coupling model Parameter identification of lithium-ion battery based on data driven method and genetic algorithm

Multi-physics coupling model Parameter identification of lithium-ion battery based on data driven method and genetic algorithm

Bistatic RCS Pattern Synthesis With a Receiver–Transmitter Metasurface and a Phase Distribution Optimization Algorithm

ABSTRACTThis paper proposes a metasurface design method to achieve bistatic radar cross‐section (RCS) pattern synthesis in space, based on a receiver–transmitter metasurface (RTMS) and a genetic algorithm for phase distribution optimization. Due to the slots on the ground between the adjacent metasurface elements, the unwanted interunit coupling effect is significantly reduced. Based on the theoretical analysis model of the phased array, the corresponding phase distribution of the required RCS pattern is optimized by a genetic algorithm. According to the required phase distribution, the corresponding RTMS units are designed, and the overall RTMS structure is finally constructed. The simulated results demonstrate that the electromagnetic (EM) waves scattered by the proposed RTMS are concentrated in the desired directions of 0° and ±49° which is consistent with the design intention. Both simulated and measured results verify that the proposed RTMS design methodology can realize the bistatic RCS control in space with a customized shape.