Simulated Annealing Optimization Research Articles

Study on a hybrid algorithm combining enhanced ant colony optimization and double improved simulated annealing via clustering in the Traveling Salesman Problem (TSP).

In the process of solving the Traveling Salesman Problem (TSP), both Ant Colony Optimization and simulated annealing exhibit different limitations depending on the dataset. This article aims to address these limitations by improving and combining these two algorithms using the clustering method. The problems tackled include Ant Colony Optimization's susceptibility to stagnation, slow convergence, excessive computations, and local optima, as well as simulated annealing's slow convergence and limited local search capability. By conducting tests on various TSPLIB datasets, the algorithm proposed in this article demonstrates improved convergence speed and solution quality compared to traditional algorithms. Furthermore, it exhibits certain advantages over other existing improved algorithms. Finally, this article applies this algorithm to logistics transportation, yielding excellent results.

Machine learning–based optimal design of the in-situ leaching process parameter (ISLPP) for the acid in-situ leaching of uranium

The migration process of leached uranium in the in-situ leaching of uranium is considered a typical reactive transport problem. During this process, the lixiviant concentration and injection rate are important in-situ leaching process parameters (ISLPP) to efficiently recover uranium. However, several uncertain factors affect the outcomes of the ISLPP design. In addition, the repeated use of the reactive transport model (RTM) for investigating the acid in-situ leaching of uranium with the application of the Monte Carlo method leads to a substantial computational load. For this reason, a machine learning (ML)–based surrogate model was developed with the backpropagation neural network (BPNN) method to replace the RTM under the condition of uncertain parameters. Moreover, the simulated annealing optimisation model for ISLPP was created based on the proposed surrogate model. The optimal ISLPP was achieved that generated maximum profits from uranium recovery under different lixiviant prices, uranium prices and exploitation times. The optimal design framework of ISLPP based on the proposed ML algorithm was then applied in the Bayan-Uul sandstone-type uranium deposit in Inner Mongolia, China. From our analysis, it was demonstrated that the ML-based surrogate model exhibited great fitness with the RTM. The optimal results of the ISLPP indicated that the lixiviant concentration and injection rate could be adjusted based on the fluctuations in lixiviant price, uranium price and exploitation time. If the prices of sulphuric acid were high, a specific concentration of hydrogen peroxide could be injected into the injection well to promote the oxidation and dissolution of the uranium ore to increase the income from the uranium recovery. The optimisation model can also use the ISLPP scheme to boost the revenues from different lixiviant prices, uranium prices and exploitation times under the uncertainty of porosity, illustrating the applicability of the ML-based optimal design method of ISLPP in ISL mining. A general framework for developing surrogate models, as well as for conducting uncertainty analyses for a wide range of groundwater models was proposed here yielding valuable insights.

Vibrational Effects on the Acoustic Performance of Multi-Layered Micro-Perforated Metamaterials

Broadband noise reduction over the low–mid frequency range in the building and transportation sectors requires compact lightweight sound absorbers of a typical subwavelength size. The use of multi-layered, closely spaced (micro-)perforated membranes or panels, if suitably optimized, contributes to these objectives. However, their elasticity or modal behaviors often impede the final acoustical performance of the partition. The objective of this study is to obtain insights into the vibrational effects induced by elastic limp membranes or panel volumetric modes on the optimized sound absorption properties of acoustic fishnets and functionally graded partitions (FGP). The cost-efficient global optimization of the partitions’ frequency-averaged dissipation is achieved using the simulated annealing optimization method, while vibrational effects are included through an impedance translation method. A critical coupling analysis reveals how the membranes or panel vibrations redistribute the locations of the Hole-Cavity resonances, as well as their cross-coupling with the panels’ first volumetric mode. It is found that elastic limp micro-perforated membranes broaden the pass-band of acoustic fishnets, while smoothing out the dissipation ripples over the FGP optimization bandwidth. Moreover, the resonance frequency of the first panels mode sets an upper limit to the broadband optimization of FGPs, up to which a high dissipation, high absorption, and low transmission can be achieved.

Structural and optical properties of triple-layer for high-uniformity beam division

In this paper, a triple-layer grating beam splitter with three-port output is designed. Through the combination of rigorous coupled-wave analysis (RCWA) and simulated annealing algorithms (SAA), the calculation and optimization of each parameter of the grating is carried out to make the diffraction efficiency of the grating meet the conditions. At the incident wavelength of 800[Formula: see text]nm, the diffraction efficiencies of 0th order and ±1st order under TE polarization are 31.6% and 31.4%, respectively. The diffraction efficiencies of 0th order and ±1st order under TM polarization are 32.7% and 32.5%, respectively. It can be seen that not only the total diffraction efficiency under TE polarization and TM polarization exceeds 90%, but also the uniformity of diffraction efficiency at each order exceeds 99%. Finally, the influence of grating parameters and incident wave characteristics on diffraction efficiency is discussed.

A committee machine-based estimation of shear velocity log by combining intelligent systems and rock-physics model using metaheuristic algorithms

Estimation of reservoir parameters such as porosity, lithology and determination of elastic moduli is based on well-logging data and seismic velocity information. However, the lack of shear velocity log in many wells, and the high costs of its acquisition have led to developing different approaches for shear velocity estimation. Currently, shear velocity estimation is accomplished by common industrial methods such as empirical equations, regression analysis, intelligent methods and rock-physics models (RPMs). The current study proposes that robust, accurate and cost-effective intelligent methods coupled with suitable RPM provide reasonable estimations of the shear velocity in an optimal processing time. Hybridizing intelligent models with RPMs in the framework of a committee machine is an optimal solution for shear velocity estimation of carbonate reservoirs. The intelligent methods used in this study include neural network (NN), fuzzy logic (FL) and an adaptive-neuro fuzzy inference system (ANFIS). In this research, for each individual intelligent model and a developed RPM, the optimal weights were allocated by Metaheuristic optimization algorithms including genetic algorithm (GA), ant colony optimization routing (ACOR) and simulated annealing (SA)). To obtain the best results with the lowest mean squared error (MSE), a total of 9408, 10801 and 12288 models were created and tested in MATLAB to optimally parametrize the GA, ACOR and SA, respectively. The results showed that the combination of the applied intelligent models with the developed RPMs leads to a higher correlation coefficient with reference to the measured Shear velocity in test dataset. The use of a combination of intelligent methods in the form of committee-machine instead of individual methods has led to a reduction in error and improved the results by up to 2% Considering the high sensitivity of shear wave velocity in geomechanical and reservoir characterization studies, even small improvements in its estimation can significantly reduce error in the characterization of hydrocarbon reservoirs.

An Improved Genetic Algorithm for the Granularity-Based Split Vehicle Routing Problem with Simultaneous Delivery and Pickup

The Split Vehicle Routing Problem with Simultaneous Delivery and Pickup (SVRPSDP) consists of two subproblems, i.e., the Vehicle Routing Problem with Simultaneous Delivery and Pickup (VRPSDP) and the Split Delivery Vehicle Routing Problem (SDVRP). Compared to the subproblems, SVRPSDP is much closer to reality. However, some realistic factors are still ignored in SVRPSDP. For example, the shipments are integrated and cannot be infinitely subdivided. Hence, this paper investigates the Granularity-based Split Vehicle Routing Problem with Simultaneous Delivery and Pickup (GSVRPSDP). The characteristics of GSVRPSDP are that the demands of customers are split into individual shipments and both the volume and weight of each shipment are considered. In order to solve GSVRPSDP efficiently, a Genetic-Simulated hybrid algorithm (GA-SA) is proposed, in which Simulated Annealing (SA) is inserted into the Genetic Algorithm (GA) framework to improve the global search abilities of individuals. The experimental results indicate that GA-SA can achieve lower total costs of routes compared to the traditional meta-algorithms, such as GA, SA and Particle Swarm Optimization (PSO), with a reduction of more than 10%. In the further analysis, the space utilization and capacity utilization of vehicles are calculated, which achieve 86.1% and 88.9%, respectively. These values are much higher than those achieved by GA (71.2% and 74.8%, respectively) and PSO (60.9% and 65.7%, respectively), further confirming the effectiveness of GA-SA. And the superiority of simultaneous delivery and pickup is proved by comparing with separate delivery and pickup. Specifically, the costs of separate delivery and pickup are more than 80% higher than that of simultaneous delivery and pickup.

Identification of Sound Power Levels and Surface Absorption Coefficientsin Multi-Source Industrial Buildings by Using a Simplified Diffusion Model

This article deals with the identification of sound powers and absorption surface coefficients in multisource industrial buildings from the knowledge of the sound pressure levels (SPLs) at several monitoring points. This inverse problem is formulated as one of optimisation in which the objective function is the difference between the measured and predicted SPLs. The methodology combines the use of a simplified acoustic diffusion model with the simulated annealing optimisation technique. The former is a recently developed model for estimating the SPLs in a fast and sufficiently accurate form. The low computational cost of the model constitutes the major advantage for the optimisation procedure due to the great number of simulations required. Numerical examples are given to show the efficiency of the proposed approach.

Exploring the design of ecological and energy-saving residential buildings adapted to climate change based on a simulated annealing algorithm

Abstract In the context of the digital development of big data and information in recent years, performance-based residential building design and its optimization methods have gradually become a research hotspot of domestic and international attention. The simulated annealing algorithm is a major component of residential buildings’ optimal energy efficiency design. Although the crossover operator under the computational traditional simulated annealing algorithm incorporates the respective advantages of the genetic algorithm and simulated annealing algorithm, the purely optimal genetic simulated annealing algorithm is more effective for the evaluation of index analysis and better reflects the superiority of the algorithm. In the Energy Plus model, the three algorithms were used to analyze the design indexes of ecological energy-efficient residential buildings, and the SS values of the MOSA algorithm fluctuated between 10% and 24%, and the performance of the recommended genetic simulated annealing algorithm was significantly better than the other two algorithms. This study effectively solves the difficulties of low efficiency and high failure rate common in design practice when using this technique and is of historical importance to the development of energy-efficient residential buildings in China.

Comparative Analysis of Intelligent Optimization Algorithms for Atmospheric Duct Inversion Using Automatic Identification System Signals

Using intelligent optimization algorithms to retrieve atmospheric duct parameters by monitoring automatic identification system (AIS) signals at sea is a new passive remote sensing technology for atmospheric ducts. To thoroughly compare and analyze the inversion results of different intelligent optimization algorithms and optimize the parameters of the algorithms, this study considered a simulated atmospheric duct environment for atmospheric duct inversion using the genetic, simulated annealing, and particle swarm optimization (PSO) algorithms. The results indicated that the PSO algorithm exhibited the best inversion performance. The inversion results of the simulated annealing particle swarm optimization (SAPSO) and PSO algorithms under different inversion parameters were further statistically analyzed, and the atmospheric duct parameters were obtained from measured AIS signals based on the SAPSO algorithm. The inversion results verified the effectiveness of the proposed algorithm, and they continuously improved with additional calculations in the inversion algorithm. However, the changing trend gradually slowed. Therefore, in practical applications, the inversion time consumption should be balanced with the inversion effect to optimize the inversion parameters.

Cyberbullying detection framework for short and imbalanced Arabic datasets

Cyberbullying detection has attracted many researchers to detect negative comments deployed on communication platforms as cyberbullying can take many forms: verbal, implicit, explicit, or even nonverbal. The successful growth of social media in recent years has opened new perspectives on the detection of cyberbullying, although related research still encounters several challenges, such as data imbalance and expression implicitness. In this paper, we propose an automated cyberbullying detection framework designed to produce satisfactory results, especially when imbalanced short text and different dialects exist in the Arabic text data. In the proposed framework a new method to solve the imbalance problem is suggested, where the modified simulated annealing optimization algorithm is used to find the optimal set of samples from the majority class to balance the training set. This method has been evaluated using traditional machine learning algorithms including support vector machine, and deep learning algorithms including Long Short-Term Memory (LSTM) and Bidirectional LSTM (Bi-LSTM). To generate a framework that can detect Arabic written cyberbullying on communication platforms, the accuracy, recall, specificity, sensitivity and mean squared error are used as the main performance indicators. The results indicate that the proposed framework can improve the performance of the tested algorithms, and Bi-LSTM outperforms other methods for cyberbullying classification.

Performance improvement of the solid oxide fuel cell using optimal parameters identification through fuzzy logic based-modeling and different optimization algorithms

Fuel Cells are novel devices that have been proposed as new power generation systems. The advantages of solid oxide fuel cells are higher efficiency, higher stability, fuel flexibility, lower emissions, and generally lower cost. In the present study, the fuzzy model is employed to build the model of the solid oxide fuel cell considering various sputtering power, thickness of electrolyte, and temperatures of cell. The maximum iterations for the adaptive neuro-fuzzy inference model was considered 50 iterations. About 3500 samples were applied for the training process, and almost 900 samples were utilized for the testing. After modeling process, the genetic algorithm, particle swarm, simulated annealing, and hybrid firefly-particle swarm optimizers are applied to achieve the optimum value of current and power densities. The results showed that proposed fuzzy model could approximate the model the system with a good agreement with experimental data. Additionally, the obtained data confirm the accuracy, high convergence speed, and robustness of the proposed hybrid optimizer compared to three efficient optimization algorithms. Accordingly, the correlation factor for the proposed fuzzy model for the training and testing dataset was obtained to be 0.9298 and 0.9289, correspondingly.

Aspects of Negative Entropy Flow in Cyclones: From Classical to Quantum

The study focuses on exploring the concept of negative entropy flow in cyclones and investigates the potential of applying quantum-inspired approaches to better understand and estimate the negentropy of these complex systems. By incorporating principles from quantum mechanics, such as the second law of thermodynamics and Gibbs energy, we aim to improve the accuracy of entropy predictions for cyclones. Classical methods for estimating entropy flow, such as Shannon entropy and von Neumann entropy, are examined, along with their limitations in capturing the complex dynamics of cyclonic systems. Additionally, the project utilizes the simulated annealing optimization method to explore the quantum aspects of entropy flow in cyclones. The objective is to provide insights into the negentropy of cyclones and its potential applications in weather forecasting. This project analyses data from two recent cyclones "Mocha" and "Biporjoy" and estimates their negentropy using the developed quantum-inspired algorithms. The findings contribute to a deeper understanding of the entropy dynamics in cyclones and showcase the potential of quantum-inspired techniques in weather forecasting and related fields.

Simulation-based decision support system for earthmoving operations using computer vision

A reliable Decision Support System (DSS), particularly in the construction domain, can be driven by quality input information. Although vision-based methods have been widely utilized to retrieve contextual information, their potential is not fully leveraged in construction simulation yet. This study introduces an automated framework that utilizes multi-view video footage for vision-based input modeling within simulation domains. The proposed framework addresses project uncertainties (e.g., equipment performance, operators’ skills, road network, and weather status) using a proactive approach where project task durations are modeled as probabilistic distributions. The modeled distributions are continuously calibrated using the Markov Chain Monte Carlo Bayesian Inference (MCMCBI) approach. A simulation-based Simulated Annealing (SA) optimization is also employed to provide an efficient resource assignment. The extracted vision-based data is validated statistically against actual and spatiotemporal data. The results demonstrate that the suggested vision-based approach can provide qualified DSS input. Statistical analysis also confirms that vision-based data is more consistent with actual data than spatiotemporal data. The presented approach is successfully applied to an actual case study of a large-scale earthmoving project.

Optimization Design and Nonlinear Bending of Bio-Inspired Helicoidal Composite Laminated Plates

Inspired by the bionic Bouligand structure, helicoidal carbon fiber-reinforced polymer composite (CFRPC) laminates have been proven to own outstanding out-of-plane mechanical properties. This work aims to further explore the excellent bending characteristics of helicoidal CFRPC laminated plates and find out the optimal helicoidal layup patterns. The optimization design of laminated plates stacked with single-form and combination-form helicoidal layup sequences are carried out by using the finite element method (FEM) and adaptive simulated annealing (ASA) optimization algorithm on the Isight platform. Then, the nonlinear bending responses of optimal helicoidal CFRPC laminated plates are investigated via the FEM for the first time. The helicoidal CFRPC laminated plates under three different types of boundary conditions subjected to transverse uniformly distributed load are considered. The numerical results reveal that the combination-form helicoidal layup sequences can decrease the dimensionless bending deflection of laminated plates by more than 5% compared with the quasi-isotropic plate and enhance the out-of-plane bending characteristics of CFRPC laminated plates effectively. The boundary conditions can significantly influence the nonlinear bending responses of helicoidal CFRPC laminated plates.

An Improvement to the 2-Opt Heuristic Algorithm for Approximation of Optimal TSP Tour

The travelling salesman problem (TSP) is perhaps the most researched problem in the field of Computer Science and Operations. It is a known NP-hard problem and has significant practical applications in a variety of areas, such as logistics, planning, and scheduling. Route optimisation not only improves the overall profitability of a logistic centre but also reduces greenhouse gas emissions by minimising the distance travelled. In this article, we propose a simple and improved heuristic algorithm named 2-Opt++, which solves symmetric TSP problems using an enhanced 2-Opt local search technique, to generate better results. As with 2-Opt, our proposed method can also be applied to the Vehicle Routing Problem (VRP), with minor modifications. We have compared our technique with six existing algorithms, namely ruin and recreate, nearest neighbour, genetic algorithm, simulated annealing, Tabu search, and ant colony optimisation. Furthermore, to allow for the complexity of larger TSP instances, we have used a graph compression/candidate list technique that helps in reducing the computational complexity and time. The comprehensive empirical evaluation carried out for this research work shows the efficacy of the 2-Opt++ algorithm as it outperforms the other well-known algorithms in terms of the error margin, execution time, and time of convergence.

Shear stiffening gel under low-speed impact: Mechanical behavior characterization and protective performance analysis

According to the controlled shear rate (CSR) test, the shear stiffening gel (SSG) exhibited viscoelastic behavior, which can be fully described by the general Maxwell model. A specific analytical model was established to identify the material parameters automatically based on simulated annealing (SA) optimization. Besides, according to the CSR tests under different temperatures, the influence of temperature and strain rate on the mechanical behavior of SSG was assumed to be decoupled. And an applicable engineering relation was introduced for parameter adjustment of the Maxwell model near room temperature. The reliability of the material parameters was verified through the results comparison of the low-speed impact tests of SSG and corresponding FE simulations.Based on field analysis of the FE simulations, the mechanism of the stress dispersion ability of SSG was elaborated. A feasible design idea was introduced to fully utilize this property. In order to verify the effectiveness of the design idea, a series of egg impact tests were developed, conducted, and analyzed. And the protective idea proved helpful in fully invoking the stress dispersion potential of SSG assembly for impact protection and improving the lightweight design.

Coverage Optimization of Eureka Digital Sound Broadcasting Single Frequency Network Using Simulated Annealing and Particle Swarm Optimization

Due to scarcity of bandwidth available for sound broadcasting, Digital sound broadcasting Technology is emerging to be the Technology of resort in sound broadcasting industry towards replacing the analogue sound broadcasting currently dominated by FM Radio. There are many digital sound broadcasting systems being proposed with different performance and bandwidth efficiency. Static delays are artificial delays intentionally introduced at each Transmitter in order to minimize interference in a Single Frequency Network (SFN). In this paper, we have looked at the Terrestrial digital audio broadcasting (T-DAB) system specifically to optimize its final SFN coverage by finding an optimal set of static delays for transmitters. For the sake of simulation, hexagonal model of transmitters operating under Single Frequency Network (SFN) was used. The aim of this study is to maximize SFN coverage by using optimal set of artificial static delays, Particle Swarm Optimization (PSO) have strong ability in finding the global optimistic result while Stimulated Annealing (SA) algorithm has a strong ability to find the local Optimistic result and therefore based on their unique strength, these methods were selected so that our study can have a good comparison in terms of coverage by using both global and local optimistic results. We report the increase of coverage by 1.12% and 2.38% using Simulated Annealing and Particle Swarm Optimization technique respectively.

Maximum power tracking of wave power generation system based on improved particle swarm optimization

In a wave power generation system, traditional particle swarm optimization (PSO) is prone to premature convergence and local optimal solution when it is used to control the maximum power tracking. Therefore, an improved PSO is proposed, and simulated annealing adaptive particle swarm optimization (SAAPSO) is constructed. The algorithm controls the inertia weight coefficient factor by hyperbolic tangent function and makes the nonlinear adaptive change. Using a linear change strategy to control social learning factors and self-learning factors, a simulated annealing operation is introduced, and a temperature is set according to the initial state of the population. The population is guided to compare the fitness value with the random number in the Metropolis criterion and temperature, and whether a new solution is generated is judged, to improve the problem that the algorithm falls into a locally optimal solution. The simulation results show that the algorithm can effectively prevent the wave power generation system from falling into the local maximum power point, and the maximum wave energy capture ability is significantly improved.

Design of the particle swarm optimization simulated annealing MPPT control method based on motion shadow

Under the same environmental conditions, photovoltaic arrays at different operating voltages will significantly affect the size of solar power. To obtain as much power as possible, the maximum power point tracking (MPPT) control method has been invented. Previous studies focused on the tracking problem under local shadow conditions, but the dynamic shadow problem with rapid changes in local shadow was rarely discussed. To solve the tracking problem that the maximum power point has multi-peak and fast-changing characteristics under this condition, this paper proposes a simulated annealing MPPT control method based on particle swarm optimization, which compensates the disadvantages of the memoryless Markov chain in the optimization algorithm by adaptive asymmetric memory factor, thus improving the local search ability and convergence speed in the later stage. The control effect is verified by modeling and simulation in Simulink of MATLAB, and the adaptability of the heuristic control method is reflected by simulating the tracking mode under the moving shadow condition through the actual hardware deployment on the moving car.

Simulated annealing algorithm optimized GRU neural network for urban rainfall-inundation prediction

Abstract In the context of global climate change and the continuous development of urban areas, rainfall-inundation modeling is a common approach that provides critical support for the protection and early warning of urban waterlogging protection. The present study conducts a data-driven model for hourly urban rainfall-inundation depth prediction, which is based on a gated recurrent unit (GRU) neural network and uses the simulated annealing (SA) algorithm for the hyperparameter optimization of GRU, namely the SA-GRU model. To verify the performance of the proposed model, backpropagation, long short-term memory (LSTM), and bidirectional LSTM (BiLSTM) neural networks are set as benchmarks. Results show that the SA-GRU has high accuracy in the case of short-term inundation prediction, with the Nash–Sutcliffe efficiency from 0.999 to 0.596 for the 1-h-ahead to 8-h-ahead predictions. And further research reveals that the SA-GRU integrates the significant optimization of SA, with an average 20% reduction of the root mean square error within the first eight prediction periods, and the efficient training speed of GRU, with 23.7% faster than LSTM and 44.2% faster than BiLSTM. In conclusion, the SA-GRU excels in urban inundation prediction, demonstrating its value in flood management and decision-making.