Search Algorithm Research Articles

Hybrid firefly algorithm–neural network for battery remaining useful life estimation

Abstract Accurately estimating the remaining useful life (RUL) of batteries is crucial for optimizing maintenance, preventing failures, and enhancing reliability, thereby saving costs and resources. This study introduces a hybrid approach for estimating the RUL of a battery based on the firefly algorithm–neural network (FA–NN) model, in which the FA is employed as an optimizer to fine-tune the network weights and hidden layer biases in the NN. The performance of the FA–NN is comprehensively compared against two hybrid models, namely the harmony search algorithm (HSA)–NN and cultural algorithm (CA)–NN, as well as a single model, namely the autoregressive integrated moving average (ARIMA). The comparative analysis is based mean absolute error (MAE) and root mean squared error (RMSE). Findings reveal that the FA–NN outperforms the HSA–NN, CA–NN, and ARIMA in both employed metrics, demonstrating superior predictive capabilities for estimating the RUL of a battery. Specifically, the FA–NN achieved a MAE of 2.5371 and a RMSE of 2.9488 compared with the HSA–NN with a MAE of 22.0583 and RMSE of 34.5154, the CA–NN with a MAE of 9.1189 and RMSE of 22.4646, and the ARIMA with a MAE of 494.6275 and RMSE of 584.3098. Additionally, the FA–NN exhibits significantly smaller maximum errors at 34.3737 compared with the HSA–NN at 490.3125, the CA–NN at 827.0163, and the ARIMA at 1.16e + 03, further emphasizing its robust performance in minimizing prediction inaccuracies. This study offers important insights into battery health management, showing that the proposed method is a promising solution for precise RUL predictions.

A comparison of recent optimization algorithms for build orientation problems in additive manufacturing

Abstract Build orientation in additive manufacturing technology is a pre-process application that affects many parameters, such as the volume of the support structure, part quality, build time, and cost. Determining the optimum build orientation for one or more objectives for complex parts is an error-prone puzzle. This study evaluates the behavior of cuckoo search algorithm, differential evolution, firefly algorithm, genetic algorithm, gray wolf optimizer, Harris hawks optimization, jaya algorithm, moth flame optimizer, multi-verse optimizer, particle swarm optimization, A Sine cosine algorithm, salp swarm algorithm, and whale optimization algorithm to determine the optimum build orientation of the component to be manufactured additively. The efficiency of these algorithms is evaluated on the build orientation problem of two complex components considering undercut area and build height as objective functions. Thus, the feasibility of these algorithms for real-world additive manufacturing problems is revealed. According to results obtained from the extensive analysis, the cuckoo search algorithm is the best alternative for minimizing undercut area, considering its robustness. However, the required time to solve the problem is as much as almost twice that of other algorithms. The firefly algorithm and particle swarm optimization algorithm are the best alternatives for minimizing build height.

Determination of Hydrogen Bonds in GROMACS: A New Implementation to Overcome Memory Limitation.

This work introduces a new faster implementation of the hydrogen bond network (complex arrangement of hydrogen bonds between or within molecules) search algorithm in biomacromolecules and their environment. Existing implementation of such an algorithm in GROMACS [Abraham et al. GROMACS 2024.2 Manual. 2024.] has limitations in the analysis of large structures and trajectories. The new implementation, in the form of a native GROMACS trajectory analysis module, allows for quick analysis of molecular dynamics trajectories without restrictions, thus overcoming the limitations of the original algorithm. The application of the developed method enabled the acquisition and analysis of hydrogen bond networks in the studied defensin-like protein Pentadiplandra brazzeana, as well as the study of hydrogen bond occupancies between the protein's residues and water molecules. The data obtained using the new implementation coincided with the experimental data.

Enhanced brain tumor classification using EfficientNetB0 and SVM with pareto search algorithm optimization

Classifying tumors by type, grade, and stage is crucial for treatment decisions and predicting outcomes. Deep learning, especially Convolutional Neural Networks (CNNs), has significantly advanced tumor classification by effectively analyzing complex patterns in magnetic resonance (MR) images. This work presents a hybrid image classification method using the EfficientNetB0 model and Support Vector Machine (SVM) to categorize brain MR images into pituitary tumor, glioma tumor, meningioma tumor, and normal brain. EfficientNetB0 model extracts deep features from the images, which are then classified by a linear SVM. To significantly enhance classification accuracy for brain images, we use the Pareto algorithm to determine the penalty parameter C for the linear SVM. The testing results showed that the proposed system achieved a classification accuracy of 99.30%, recall of 99.30%, precision of 99.30%, and F1-score of 99.30%, with a high specificity of 99.77%. These results demonstrate that the combination of the Pareto algorithm and SVM significantly contributes to improved classification accuracy for brain images.

A Stochastic Drone-Scheduling Problem with Uncertain Energy Consumption

In this paper, we present a stochastic drone-scheduling problem where the energy consumption of drones between any two nodes is uncertain. Considering uncertain energy consumption as opposed to deterministic energy consumption can effectively enhance the safety of drone flights. To address this issue, we developed a two-stage stochastic programming model with recourse cost, and we employed a fixed-sample sampling strategy based on Monte Carlo simulation to characterize uncertain variables, followed by the design of an efficient variable neighborhood search algorithm to solve the model. Case study results indicate the superiority of our algorithm over genetic algorithms. Additionally, a comparison between deterministic and stochastic models suggests that considering the uncertainty in energy consumption can significantly enhance the average returns of unmanned aerial vehicle scheduling systems.

Agricultural UAV Path Planning Based on a Differentiated Creative Search Algorithm with Multi-Strategy Improvement

A differentiated creative search algorithm with multi-strategy improvement (MSDCS) is proposed for the path planning problem for agricultural UAVs under different complicated situations. First, the good point set and oppositional learning strategies are used to effectively improve the quality of population diversity; the adaptive fitness–distance balance reset strategy is proposed to motivate the low performers to move closer to the region near the optimal solution and find the potential optimal solution; and the vertical and horizontal crossover strategy with random dimensions is proposed to improve the computational accuracy of the algorithm and the ability to jump out of the local optimum. Second, the MSDCS is compared to different algorithms using the IEEE_CEC2017 test set, which consists of 29 test functions. The results demonstrate that the MSDCS achieves the optimal value in 23 test functions, surpassing the comparison algorithms in terms of convergence accuracy, speed, and stability by at least one order of magnitude difference, and it is ranked No. 1 in terms of comprehensive performance. Finally, the enhanced algorithm was employed to address the issue of path planning for agricultural UAVs. The experimental results demonstrate that the MSDCS outperforms comparison algorithms in path planning across various contexts. Consequently, the MSDCS can generate optimal pathways that are both rational and safe for agricultural UAV operations.

Constructability-driven design of frame structures with state-space search methods

In the design of frames and trusses, the relationship between the structural form, the construction sequence, and the structural behavior during construction is rarely systematically considered. This paper proposes a method to systematically consider constructability in design, specifically focusing on minimizing the maximum displacement or stress during construction. The paper presents the formulation of the optimal assembly sequencing problem as a state-space search with a unique design of the search heuristic and constraint bounding schemes. It proposes three variants of heuristic search algorithms for finding a feasible sequence, a diverse set of feasible sequences, and an optimal sequence, respectively. These algorithms are tested on a case study structure to showcase their ability to navigate the combinatorial space of assembly sequences, and provide means for designers to incorporate sequence-related performance into conceptual structural design.

How Rare Are TESS Free-floating Planets?

Recently, Kunimoto et al. claimed that a short-lived signal in the Transiting Exoplanet Survey Satellite (TESS) Sector 61 database was possibly caused by a microlensing event with a terrestrial-mass free-floating planet (FFP) lens. In this study, we investigate TESS’s ability to detect microlensing FFPs by considering the detailed source information (e.g., distance and radius), the TESS photometric accuracy, and finite-source effects. Using the FFP mass function from microlensing surveys toward the Galactic bulge, we find that only 0.0018 microlensing events are expected to be detected in TESS Sector 61 for the entire planetary mass range. The reported signal is unlikely to be a real microlensing event, which is consistent with the evidence from the long-term Optical Gravitational Lensing Experiment data that the signal was likely due to a stellar flare. By extrapolating our result to fainter stars until T = 16 mag and adopting a possible optimized search algorithm, we find that only ∼1 FFP event can be detected in the entire TESS mission within the first 7 yr. Significant improvements in our understanding of FFPs still require future satellite missions, such as Roman and Earth 2.0, which can detect thousands of FFPs.

Application of Pattern Search and Genetic Algorithms to Optimize HDPE Pipe Joint Profiles and Strength in the Butt Fusion Welding Process

The rapid spread of the use of high-density polyethylene (HDPE) pipes is due to the wide variety of methods for connecting them. This study keeps pace with the developments of butt fusion welding of HDPE pipes by exploring the relationship between the performance of the weld joints by studying ultimate tensile strength and exploring the joint welding profiles by studying the shape of the joint at the outer surface of the pipe (height and width of the joint cap) and the shape of the joint at the internal surface (height and width of the joint root). Welding pressure, heater temperature, stocking time, and cooling time were the parameters for the welding process. Regression was analyzed using ANOVA, and an ANN was used to analyze the experimental results and predict the outputs. Two optimization techniques (pattern search and genetic algorithm) were applied to obtain the ideal operating conditions and compare their performance. The results showed that pattern search and genetic algorithms can determine the optimal output results and corresponding welding parameters. In comparison between the two methods, pattern search has a limited relative advantage. The optimal values for the obtained outputs revolved around a tensile strength of 35 MPa (3.45 and 4.5 mm for the cap and root heights, and 8 and 6.98 mm for the cap and root widths, respectively). When comparing the effects of welding parameters on the results, welding pressure had the best effect on tensile strength, and plate surface temperature had the most significant effect on the welding profile geometries.

Development and application of a low-cost and portable multi-channel spectral detection system for mutton adulteration

It is important to develop low-cost, fast and portable meat adulteration detection systems to ensure the meat authenticity and safety in complex market environments. A multi-channel spectral detection system for meat adulteration was developed in this study. The core hardware of the system mainly includes a designed spectral module and a Raspberry pi controller. The spectral module consists of three multi-channel spectral sensors and LED lamps with specific wavelengths, containing 18 channels covering a range of 410–940 nm. The software was developed based on PyQt5. After completing the construction of the system, the detection distance was discussed and determined to be 4 mm. Based on the spectral data collected by the developed system, the models for classifying pure mutton, pure pork, mutton flavour essence adulteration, colourant adulteration and adulterated mutton with pork were established and compared. Four intelligent optimisation algorithms were further used to improve the model performance. The results of the test set showed that the support vector classification (SVC) model optimised by a sparrow search algorithm (SSA) obtained the best classification performance, with an accuracy of 97.59% and a Kappa coefficient of 0.9696. After the SSA-SVC was incorporated into the sensor software, the system performance was evaluated using external validation samples. The overall accuracy of the system was 94.29%. The system took about 5.31 s to detect a sample, and the total weight of the system was 1.55 kg. Overall, the developed portable spectral system has considerable potential to rapidly and accurately discriminate adulterated mutton in the field.

Optimal power management for hybrid electrical vehicle

This paper introduces an innovative optimal energy management strategy tailored for a hybrid electric-powered hydraulic excavator system. The aim is to bolster power performance, extend the lifespan of power sources, and optimize hydrogen usage. In this system, the fuel cell serves as the primary power source, while integrating supercapacitors and batteries offers benefits such as enhancing power performance and storing regenerative energy for future use. To efficiently distribute power among these three sources and maximize the utilization of regenerative energy, we propose an energy management strategy. This strategy combines fuzzy logic control with a rule-based algorithm. Moreover, we optimize the parameters of the fuzzy logic system using a combination of the backtracking search algorithm and sequential dynamic programming. This optimization aims to reduce hydrogen consumption and prolong the lifespan of the power sources. Simulation results demonstrate that our proposed energy management strategy significantly enhances vehicle performance, improves fuel economy of the hybrid electric-powered hydraulic excavator system, and enhances the durability and efficiency of the battery and supercapacitor systems within the fuel cell system.

Maximizing solar energy efficiency with efficient interleaved boost converter with Three-Level neutral point clamped inverter for Grid-Connected photovoltaic using hybrid approach

The efficient interleaved boost converter (IBC) combined with the 3-level neutral point clamped (NPC) inverter for grid-connected photovoltaic systems (GCPVS) maximizes solar energy efficiency are presented. The proposed hybrid technique implies the combination of Double Attention Convolutional Neural Network (DACNN) and Starling Murmuration Optimization (SMO) algorithm and is usually referred as DACNN-SMO technique. Enhancing power quality at the Point of Common Coupling (PCC) while utilizing the rated capacity of the inverter into consideration is the main goal of the proposed approach. The grid-connected photovoltaic system additionally includes an efficient three-level NPC inverter and interleaved boost converter to decrease DC link voltage oscillation. In addition to preventing overheating, the inverter current controls reactive power adjustment, active power injection, and current harmonic filtering. Utilizing the SMO technique, By employing the SMO technique, the system effectively regulates output voltage, ensuring that the inverter output voltage. The DACNN enhances the system’s ability to monitor and diagnose faults. Using MATLAB, the proposed topology is implemented, and the results are contrasted with those of other existing techniques. The existing methods such as Heap Based Optimizer (HBO), Circle Search Algorithm (CSA) and Sparrow Search Algorithm (SSA) attains a higher THD of 3.7%, 4.7% and 5.3% respectively. The proposed method DACNN-SMO attains a THD of 2.5%. The proposed technique displays the efficiency is 99.86%. When compared to existing strategies, the proposed technique displays lower THD and high efficiency.

Innovative design for enhancing transient stability with an ATFOPID controller in hybrid power systems

In order to make multi-area power systems more efficient and stable, this study aims to create a new intelligent controller design based on adaptive property. The integrated power grid becomes more unstable as renewable energy sources become more prevalent, and system inertia decreases. Resultant, the penetration of renewable and load variance causes frequency changes to be more pronounced. Keeping frequency stable is essential for the electrical energy transmission system to work reliably and efficiently. This paper presents an adaptive design based on the tilt fractional order proportional integral derivative (TFOPID) controller by using an optimized property of bio inspired tunicate search algorithm (TSA). The gains of the TFOPID controller are continuously updated by utilizing the ancillary TPID controller, which is dependent on changes in area frequency. The suggested control system is implemented in the northern and southern regions, which consist of photovoltaic (PV), wind, redox flow battery (RFB), hydro, and thermal power plants. Therefore, this study contributes in the creation of more resilient and efficient power grids, which are critical for incorporating renewable energy sources and satisfying the increasing need for environmentally friendly power solutions.

Optimal integration of PV generators and D-STATCOMs into the electrical distribution system to reduce the annual investment and operational cost: A multiverse optimization algorithm and matrix power flow approach

In this work, we address the problem of optimally integrating photovoltaic distributed generators (PV) and distributed static compensators (D-STATCOMs) in distributed electrical systems (DES). Previous methods have struggled with the complexities of non-linear mathematical models and the integration of operating and investment costs while meeting the operational constraints of these devices. We propose a solution using a master-slave methodology that combines a discrete-continuous version of the multiverse optimization algorithm (MVO), with a matrix power flow method based on successive approximation (MAX). This approach aims to reduce annual costs by efficiently managing the grid’s operating costs and the investment and operational costs of PV and D-STATCOMs. Various researchers have suggested methodologies for solving the problem of optimal D-STATCOM integration in DES, focusing on minimizing investment and operating costs as the objective function. However, these studies often lack comparative methodologies and statistical analysis to validate the performance of their proposed approaches. Additionally, they do not consider the impact of variable power demand. We compared our methodology with other master-slave approaches that utilize different optimization algorithms, including the vortex search algorithm (VSA), crow search algorithm (CSA), a continuous genetic algorithm (GA), and the particle swarm optimization algorithm (PSO). These comparisons were made using two test systems with 33 and 69 nodes, which incorporate variations in power demand and PV production from a region in Colombia. Our statistical analysis included evaluations of the best and average solutions, standard deviations, differences between the best and average solutions, and a dispersion analysis using box-and-whisker plots. The results demonstrate that MVO outperforms other methods, providing the best results with reduced processing times in both test systems.

Computational design of residential units’ floor layout: A heuristic algorithm

Computer-aided intelligent design can improve the quality and efficiency of residential building design. However, the design conditions are diverse, and numerous combinations of spatial elements exist. We propose a heuristic algorithm—the combined Monte Carlo tree search (MCTS) and particle swarm optimization (PSO) algorithm (PSO-MCTS)—for the automated design of residential floor layouts. The MCTS algorithm deals with discrete variables (room locations). It considers architectural design experience and design standards during node pruning to compress the search space and simplify the computation. The PSO algorithm deals with continuous variables (room sizes) and accelerates the computing speed due to parallel processing. The PSO-MCTS algorithm achieves a good balance between computational efficiency and accuracy. It is suitable for various design conditions and requirements. The input parameters include the daylight façade, boundary scope, entrance location, room type and size, and relationships with adjacent rooms. The PSO-MCTS provides 100 %, 80 %, and 75 % better results than heuristic algorithms, designs by architects, and a state-of-the-art deep learning model, respectively.

Study on the Fluctuating Load Characteristics of the Submerged Radial Gate in the High-Head Flood Discharge Outlet

The fluctuating pressure acting on the radial gate in the high-head flood discharge outlet is the main excitation source of flow-induced vibration. Therefore, this paper delves into the distribution characteristics of fluctuating pressure on the panel of the high-head submerged radial gate based on hydraulic model tests. Hydraulic tests were first conducted to obtain the distribution patterns of time-averaged pressure and the root mean square (RMS) of fluctuating pressure on the radial gate panel. Secondly, the improved complete ensemble empirical mode decomposition with adaptive noise (ICEEMDAN) and HHT method was employed to identify the causes of the fluctuating pressure on the gate panel. Finally, the ICEEMDAN-SSA (the sparrow search algorithm)–LSTM (long short-term memory) method was utilized to achieve accurate prediction of the fluctuating pressure on the gate panel. The results show that the time-averaged pressure in the middle of the gate panel is higher than that at the top and near the bottom edge, which differs significantly from the static pressure distribution. The RMS of the fluctuating pressure near the bottom edge is higher than that in the middle and at the top. The fluctuating pressure acting on the gate panel in the time domain can be regarded as a stationary process. The fluctuating pressure on the gate panel is caused by the combined diffusion and random mixing of multi-scale vortices in the turbulent eddy structure. The ICEEMDAN-SSA-LSTM combined method significantly improves the prediction accuracy of fluctuating pressure on the gate panel compared to the LSTM and ICEEMDAN-LSTM methods.

Optimizing mobility resource allocation in multiple MaaS subscription frameworks: a group method of data handling-driven self-adaptive harmony search algorithm

Optimizing mobility resource allocation in multiple MaaS subscription frameworks: a group method of data handling-driven self-adaptive harmony search algorithm

Device to Device Disaster Management: Squirrel Search Algorithm Approach

Device to Device Disaster Management: Squirrel Search Algorithm Approach

Co-optimizing electric bus dispatching and charging considering limited resources and battery degradation

This paper aims to formulate a mathematical model for a multi-type electric bus scheduling problem to determine the optimal fleet composition, bus-to-trip assignment, and partial charging schedule, where the battery degradation, nonlinear charging, and the constraint of charging station capacity are considered. A time-expanded network is proposed to represent the bus-to-trip assignment and partial charging. An adaptive large neighborhood search algorithm is designed to solve the problem. Using a multi-line bus network in Nanjing as the case, empirical operational data is used to generate monthly timetable samples to simulate the uncertainty of trip travel time and energy consumption. The result shows that the charging station capacity can be reduced from 20 (real-world case) to 12, considering the cost-effectiveness and robustness of the bus system. The result of this study also provides suggestions on the charging duration choices and the starting state-of-charge for different periods of the day. In peak and off-peak hours, 20-30-minute charging is recommended for electric buses with state-of-charge lower than 30 %, and 10-minute charging is more recommended when the state-of-charge of the electric bus is between 30 % and 70 %.

Hybrid differential evolution algorithm for Falkner-Skan flow with rotation

A hybrid differential evolution algorithm is used in this work to study the rotating transport of Falkner-Skan flow. The problem is modeled as an equivalent optimization problem by using Padé rational approximation functions. The primary model of the governing partial differential equations is imposed to subjugate the error between profiles. A hybrid evolutionary algorithm based on differential evolution and a convergent version of Nelder-Mead direct search algorithm is employed to perform global exploratory search along with an enhanced exploitation to improve the accuracy of the proposed solution scheme. The resulting scheme is named as evolutionary Padé approximation (EPA) scheme. The performance of the proposed EPA scheme on the Falkner-Skan boundary value problem is investigated by considering various values of the rotation parameters. The developed optimizer in EPA scheme was able to minimize the residuals up to10−10. Results are displayed graphically in order to study the effect of various types of parameters. EPA scheme determined that angular velocity increases or decreases accordingly as fluid parameter (β) and the rotation parameter (λ) but shows inverse behavior with respect to power law index(n). Similarly, the response of velocity profile along y−axis was decreasing function of β as well as n but increasing function of λ. The performance of the proposed EPA scheme has been demonstrated by comparing results with a hybrid neural network scheme and found in excellent agreement.