Hybrid Particle Swarm Algorithm Research Articles

Thermal parameter identification of concrete dams based on hybrid particle swarm optimization using distributed optical fiber monitoring data

The temperature of concrete arch dam during construction is affected by factors such as ambient temperature, cooling through water, and surface insulation. There is often a significant discrepancy between the actual thermal parameters and the values measured in indoor experimental tests. In this study, intelligent identification of thermal parameters is performed based on temperature monitoring data and an intelligence optimization algorithm so that the thermal characteristics of concrete in a real pouring environment can be obtained in real time. A hybrid algorithm of particle swarm optimization and grey wolf optimizer (HPSOGWO) is proposed. The performance of the hybrid particle swarm algorithm is verified to have some advantages over the other seven algorithms by twelve different test functions. Considering the influences of environmental temperature changes and multistage cooling water, HPSOGWO is utilized for inverse analysis of the thermal parameters of concretes with the same strength grade and concretes with different strength grades. The analysis results show that the concrete temperature values calculated based on the inversion of the HPSOGWO algorithm are in good agreement with the measured values, and the HPSOGWO algorithm has good adaptability in the inversion of thermal parameters of arch dams. The inversion results are of essential to clarify the relationship between temperature changes and thermal parameters.

Power Quality Conditioners-Based Fractional-Order PID Controllers Using Hybrid Jellyfish Search and Particle Swarm Algorithm for Power Quality Enhancement

Power quality (PQ) is a major issue in today’s electrical system that affects both utilities and customers. The proliferation of power electronics devices, smart grid technology, and renewable energy sources (RES) have all contributed to the emergence of PQ concerns in today’s power system. The Unified Power Quality Conditioner (UPQC) is a versatile tool that can be used to fix distribution grid issues caused by irregular voltage, current, or frequency. Several tuning parameters, however, restrict the effectiveness of the Fractional-Order Proportional Integral Derivative (FOPID) control technique, which is proposed to improve UPQC performance. To move beyond these restrictions and find the optimal solution for the FOPID controller problem, a hybrid optimization strategy called the Hybrid Jellyfish Search Optimizer and Particle Swarm Optimizer (HJSPSO) is employed. To meet the load requirement during PQ issue periods, the suggested model incorporates a renewable energy source into the grid system. Whether the load is linear or non-linear, the design maintains PQ problems to a minimum. Furthermore, the FOPID control technique is compared with other controllers. Results show that grid-connected RES systems using the proposed FOPID control approach for UPQC have fewer PQ problems. The presented UPQC with HJSPSO strategy significantly outperformed, with the shortest computing time of 127.474 s and an objective function value of 1.423.

Configuration design of reconfigurable single-product robotic assembly line for capacity scalability

Rapid product changes and fierce global competition force companies to react quickly to market changes associated with dynamic capacity. This paper investigates how to design and reconfigure configurations of the single-product scalable reconfigurable robotic assembly line (RAL) over multiple demand periods (DPs) with fluctuating demands. A two-phase approach is proposed, in phase 1, the configuration of RAL is designed to minimize the capital cost following the initial demand. In phase 2, the reconfiguration for each DP is performed according to demand fluctuations to minimize the sum of capital costs and reconfiguration costs between consecutive DPs. Mathematical models for the two phases are established. Then a hybrid particle swarm algorithm combined with simulated annealing (PSOSA) is proposed for practical-sized problems, and PSO and SA are chosen for comparison. Two other different approaches are selected for comparison. In approach 1 (robust strategy), each DP of the product lifecycle is calculated separately, and then a fixed configuration that can satisfy the maximal capacity of all DPs is obtained. In approach 2 (changeable strategy), the minimal-cost configuration for each DP is calculated separately first, and then the reconfiguration cost between adjacent DPs is counted. Furthermore, a set of instances is designed and the computational results of three approaches accompanied by PSOSA, PSO and SA versus the devised instances demonstrate the superiority and robustness of the proposed approach and PSOSA.

Enhanced sound absorption performance of stepped-type multi-cavity acoustic absorbers using a hybrid particle swarm algorithm

A stepped-type multi-cavity combined sound absorber (SMCSA) was developed to improve the low and mid-frequency sound absorption capabilities of micro-perforated panels. The sound absorption characteristics of the SMCSA were thoroughly investigated using experimental methods, theoretical calculations, and numerical simulation. The particle swarm optimization algorithm was employed to optimize the SMCSA parameters. The findings revealed that the board thickness, hole size, and cavity depth significantly influenced the sound absorption properties of the SMCSA. When the hole size ranged from 0.4–0.6 mm, the sound absorption coefficient of the SMCSA reached 0.9, and the resonance frequency was 600–800 Hz. After optimization utilizing the hybrid particle swarm algorithm, the maximum sound absorption coefficients at the resonance frequency of the two-step, four-step, and eight-step structures were all 0.99.

An Optimized Deep Learning Approach for Predicting the Electric Motor Temperature Using IOT Sensors

Based on that, the Internet of Things (IoT) is used in industrial applications for monitoring and controlling various sensor operations. In existing work, IoT-based monitoring and controlling operations for industries are proposed. But, in this, real-time monitoring of the data is performed to take necessary actions. This may fail at a fraction of a second when the device crossed its breakpoint or threshold value. Hence, in this, an optimized deep learning approach (Convolutional Neural Network) is proposed for monitoring and controlling the temperature in electrical motors. Here, the controlling is performed by predicting the temperature using a deep learning approach. This helps to improve the controlling operations in the IoT environment and protect the device from Malfunctioning. The proposed approach is tested on the Kaggle Sensor dataset for electrical motors. The optimal hyperparameters for the CNN are determined through the hybrid particle swarm and genetic algorithm by minimizing the cost function. The cost function is to reduce the RMSE rate. This method’s presentation is evaluated and the fidelity of root mean square merits. The whole process is implemented using MATLAB R2020a version under Windows 10 environment.

Hybrid Particle Swarm Algorithm Based on Differential Evolution for the Research on Space-Time Conflict Optimization of Prefabricated Buildings

Hybrid Particle Swarm Algorithm Based on Differential Evolution for the Research on Space-Time Conflict Optimization of Prefabricated Buildings

Adaptive distributionally robust cluster-based healthcare network design problem under an uncertain environment

County medical alliances (CMAs) in China are considered to be effective in optimizing the layout of medical resources and improving primary healthcare services. To facilitate the implementation of CMAs in multiple geographical clusters, we examine a cluster-based healthcare network design (CHND) problem with patient referral in uncapacitated and capacitated cases. Considering the uncertainty of health demand and unit referral cost, we develop adaptive distributionally robust models for the CHND problem, where the location and allocation decisions anticipate the worst-case expected patient treatment and referral cost over an ambiguity set. In terms of tractability, we reformulate the adaptive distributionally robust models as tractable forms. Further, a hybrid genetic algorithm that combines a genetic algorithm with a commercial solver is designed to improve the computational efficiency for large-scale instances. Finally, we apply our models to a real-world case in Shenzhen, China, to verify the effectiveness of the proposed algorithm and assess the value of the adaptive distributionally robust models over the corresponding robust model. The results show that our algorithm has outstanding efficiency and accuracy when compared to the hybrid particle swarm algorithm and the commercial solver. Moreover, the adaptive distributionally robust model outperforms the robust model in terms of solution quality.

Collaborative decision-making model for capacity allocation of photovoltaics energy storage system under Energy Internet in China

Solving the problem of photovoltaics abandonment and power limitation and improving resource utilization is particularly important to promote the sustainable development of the PV industry. With the innovative development and continuous application of energy storage technology, energy storage has become an indispensable part of photovoltaic power generation, realizing the consuming goal of abandoned photovoltaics. This paper studies the synergistic management of PV power generation based on the perspective of value chain, and constructs a complex value chain system with PV power generation subsystem and energy storage subsystem as the key subsystem—photovoltaics energy storage system (PVESS). Firstly, a value co-creation analysis framework for promoting capacity allocation of PVESS under the Energy Internet is analyzed. Secondly, the basic model of hybrid energy storage system (HESS) combining battery energy storage system (BESS) and superconducting magnetic energy storage system (SMES) is constructed. Thirdly, a multi-objective collaborative decision model is established with the objective functions of minimum economic cost, minimum abandoned photovoltaics and minimum load outage rate for the hybrid energy storage system (HESS). And the hybrid particle swarm algorithm (HPSO) algorithm and Vlsekriterijumska Optimizacija I Kompromisno Resenje (VIKOR) method are used to determine the optimal system configuration. Finally, the validity and feasibility of the model are proved by the results of collaborative decision making and sensitivity analysis. The proposed collaborative decision suggestions for capacity allocation is adopted to facilitate the collaborative and effective operation of the system. This study can also provide insightful enlightenment for PVESS project investors, collaborative decision-making professionals and decision makers.

Study on the Location-Routing Problem in Network-Type Tractor-and-Trailer Transportation Mode

Under the trend of developing green transportation in China, tractor-and-trailer transportation has received more attention. This paper focuses on the network-type tractor-and-trailer transportation mode in the port hinterland, aiming to tackle the problems of low efficiency and customer satisfaction in the existing transportation network. The authors recommend considering opening several alternative depots and making vehicle scheduling decisions simultaneous in order to optimize the existing transportation network. Therefore, this paper constructs a bi-level programming model with a generalized total cost minimization as the objective function. The solution to the original problem is divided into two stages: the location-allocation problem and vehicle scheduling; a two-stage hybrid heuristic algorithm is designed to solve the problem. Through the continuous iteration of the upper genetic algorithm and the lower hybrid particle swarm algorithm, the overall optimization of the problem is achieved. Finally, a specific example verifies the model and the algorithm’s effectiveness. The results show that the method proposed in this paper can significantly improve customer satisfaction and reduce transportation costs to a certain extent. It can also provide effective theoretical decision support for logistics enterprises to carry out tractor-and-trailer transportation business and develop green transportation.

Optimization of the Multi-Level Spring Restrainer for Bridges by Hybrid Particle Swarm and Gravitational Search Algorithm

This paper proposes a new multi-level spring restrainer (MLSR) that exhibits multi stiffness performance in different levels of movement of bridge superstructure to prevent unseating during applied dynamic loads. The analytical model of the proposed MLSR was formulated and the fabricated prototype was tested using dynamic actuator. Based on the developed analytical mode, the function of MLSR device relied on 12 parameters that further complicated the design process to achieve the best performance. However, the conventional optimization techniques utilized only one or a few factors for simple systems. Therefore, a multi-objective optimization method is proposed in this study by introducing the hybridization of Particle Swarm Optimization and Gravitational Search algorithm (PSOGSA) to optimize the restrainer parameters, as well as to improve the seismic performance of bridges using the optimum design. The optimized MLSR was implemented in the bridge subjected to multi-directional ground motion and its multi-level action to prevent unseating of bridge deck when the applied excitation was evaluated. The optimization process revealed girder displacement in three directions and the number of plastic hinges decreased from 44 to 99% for the optimized design. The time history analysis disclosed that the use of optimized MLSR device decreased the structural seismic response, such as the 3D deck movements, from 79 to 90%. Next, the base shear and drift ratio of bridge bent reduced to 75 and 85% in longitudinal direction and to 72 and 90% in transverse direction, correspondingly. The outcomes signify that the proposed MLSR device and the optimization algorithm have successfully improved the bridge structure resistance against severe ground motions.

A hybrid GA-PSO strategy for computing task offloading towards MES scenarios.

As a new type of computing paradigm closer to service terminals, mobile edge computing (MEC), can meet the requirements of computing-intensive and delay-sensitive applications. In addition, it can also reduce the burden on mobile terminals by offloading computing. Due to cost issues, results in the deployment density of mobile edge servers (MES) is restricted in real scenario, whereas the suitable MES should be chosen for better performance. Therefore, this article proposes a task offloading strategy under the sparse MES density deployment scenario. Commonly, mobile terminals may reach MES through varied access points (AP) based on multi-hop transmitting mode. The transmission delay and processing delay caused by the selection of AP and MES will affect the performance of MEC. For the purpose of reducing the transmission delay due to system load balancing and superfluous multi-hop, we formulated the multi-objective optimization problem. The optimization goals are the workload balancing of edge servers and the completion delay of all task offloading. We express the formulated system as an undirected and unweighted graph, and we propose a hybrid genetic particle swarm algorithm based on two-dimensional genes (GA-PSO). Simulation results show that the hybrid GA-PSO algorithm does not outperform state-of-the-art GA and NSA algorithms in obtaining all task offloading delays. However, the workload by standard deviation approach is about 90% lower than that of the GA and NSA algorithms, which effectively optimizes the performance of load balancing and verifies the effectiveness of the proposed algorithm.

Multicriteria Recommendation Method of Tourist Routes Based on Tourist Clustering

A multicriteria recommendation algorithm for tourist routes under the multidimensional expanded spatial grid structure model based on fuzzy C-means clustering of tourist preferences is proposed. The purpose of the proposed structure is to improve the multicriteria intelligent recommendation ability of tourist routes under the multidimensional expanded spatial grid structure model of popular tourist core circle. The multidimensional enlarged spatial grid structure model of the well-known tourist core circle is used to develop the tourist correlation model of travel routes under the restricted sample training. Under the popular traveler core circle’s multidimensional enlarged spatial grid structure framework, the mixed kernel use and global kernel use are created to extract the correlation characteristics of tourist route recommendation. Under the multidimensional enlarged spatial grid structure model of the well-known tourist core circle, the adaptive learning of tourist route selection is carried out using the hybrid particle swarm algorithm. To manage the convergence of the suggestion process, maps of logistical chaos are employed, utilizing culture’s universalism and ergodicity resources and examining the aesthetic resources along tourism routes. The simulation results demonstrate that the multidimensional extended spatial grid structure model’s tourism route information recommendation accuracy is decent, and a solid swarm intelligence junction is observed in this analysis, preventing tourism route recommendations from settling for the local optimal solution and enhancing their intelligence and global stability.

Optimisation of regional energy demand networks based on flexible load model

The existing literature on integrated energy station-grid planning studies focuses on configuration planning. Therefore, a multi-objective hybrid particle swarm algorithm is used in this paper to solve a multi-objective optimisation model and combines a multi-indicator evaluation method based on evidence-based reasoning to select the solution with the highest evaluation value from multiple candidates (Pareto solution set) as the optimal solution. The optimal planning solution is selected from multiple candidates (Pareto solution set) by a multi-indicator evaluation method based on evidence-based reasoning, and the effectiveness of the proposed model is verified utilizing an example. The customer participation demand response optimises the demand curve by adjusting the flexible load, reduces the system operation cost and investment construction cost, and maximises the economic, environmental and reliability benefits of the integrated regional energy station grid.

High-frequency magnetic energy loss based on J-A model for gallium iron alloy rod under variable stress conditions

Magnetostrictive rods have stress-sensitive properties. They are the core component of high-frequency high-power magnetostrictive sensor and actuator devices. In practical high frequency applications, a certain compressive stress needs to be applied to improve the magnetostrictive coefficient of the material. However, unsuitable operating conditions can lead to increased magnetic energy losses and deterioration of device performance. Therefore, the loss modelling as well as other physical behaviour of the material need to be investigated before designing magnetostrictive devices. This paper builds a test platform for high frequency magnetic properties of magnetostrictive materials. The high frequency magnetic properties of rod gallium iron alloy were measured and analyzed under different exciting conditions (different compressive stress σ, magnetic field frequency f, and magnetic field strength H). Then, based on the experimental data and the classical static J-A model, a high-frequency dynamic model for rod gallium iron alloy taking into account compressive stress was developed. The novelty of the model is that the variation pattern of the J-A model parameters with frequency and compressive stress is obtained by importing the experimental data into a parameter identification program written based on a hybrid particle swarm algorithm. The trend is fitted as a polynomial function of frequency and compressive stress to account for its effect on the magnetic properties of the material. The model can effectively predict the change of high frequency magnetic loss of materials under variable compressive stress conditions. Comparing the calculated values of magnetic energy loss with the measured ones show that the maximum error is 4.37% and the average error is 2.57%, which verifies the accuracy and feasibility of the model.

A Robust Power Allocation Algorithm for Cognitive Radio Networks Based on Hybrid PSO.

The use of a cognitive radio power allocation algorithm is an effective method to improve spectral utilization. However, there are three problems with traditional cognitive radio power allocation algorithms: (1) based on the ideal channel model analysis, channel fluctuation is not considered; (2) they do not consider fairness among cognitive users; and (3) some algorithms are complex and locating the optimal power allocation scheme is not an easy task. For the above problems, this study establishes a robust model which adds the cognitive user transmission rate variance constraint to solve the maximum channel capacity time power allocation scheme by considering the worst-case channel transmission model, and finally solves this complex non-convex optimization problem by using the hybrid particle swarm algorithm. Simulation results show that the algorithm has good robustness, improves the fairness among the cognitive users, makes full use of the channel resources under the constraints, and has a simple algorithm, fast convergence, and good optimization results.

A novel approach for optimization of convolution neural network with hybrid particle swarm and grey wolf algorithm for classification of Indian classical dances.

Deep learning is the most dominant area to perform the complex challenging tasks such as image classification and recognition. Earlier researchers have been proposed various convolution neural network (CNN) with different architectures to improve the performance accuracy for the classification and recognition of images. However, the fine-tuning of hyper parameters, resulting the optimal network, regularization of parameters is the difficult task. The metaheuristic optimization algorithms are used for solving such kind of problems. In this paper we proffer a fine tune automate CNN with Hybrid Particle Swarm Grey Wolf (HPSGW). This novel algorithm used to discover the optimal parameters of the CNN like batch size, number of hidden layers, number of epochs and size of filters. The proffered optimized architecture is implemented on MNIST, CIFAR are two bench mark datasets and Indian Classical Dance (ICD) for the classification of 8 Indian Classical Dances. The Proffered method improves the model performance accuracy of 97.3% on ICD Dataset, and other benchmark datasets MNIST, CIFAR with an improved accuracy of 99.4% and 91.1%. This auto-tuned network improved the performance by 5.6% for Indian Classical Dance Forms Classification compared to earlier methods and also reduces the computational cost.

DDAPSO: Hybrid Discrete Dragonfly Algorithm and Particle Swarm Algorithm to Service Selection and Composition for the Internet of Things Applications

Recently, the Internet of Things (IoT) has quickly risen as one of the most essential technologies of this century. IoT allows users to connect to a vast network of smart devices, services, and data. An important and challenging research problem in the Internet of Things applications is how to select an appropriate service selection (SS). In the SS problem, users can combine several services from diverse sources (things or devices) to satisfy their needs. On the other hand, the SS problem is known for its complexity and is categorized as an NP-hard problem; such problems are typically solved utilizing heuristics like bio-inspired algorithms. In this research a new bio-inspired algorithm called DDAPSO is created to solve the SS problem where a new strategy is proposed to maintain a balance between the exploration and exploitation abilities. This hybrid algorithm is the result of coupling a Discrete Dragonfly Algorithm (DDA) with the particle swarm optimization algorithm (PSO). The suggested algorithm was properly tested using a variety of scenarios with different numbers of services and with different numbers of concrete services per each service set or task. The proposed algorithm is compared with the main recent well-known algorithms, i.e. GA, PSO, DDA, ABC and MVO for service selection. In a large-scale setting, the results clearly show that the DDAPSO algorithm outperforms other services selection algorithms reported in the literature in terms of selection optimally as well as execution time.

Reverse Design of Photonic Devices Based on a Hybrid Particle Swarm Algorithm

Reverse Design of Photonic Devices Based on a Hybrid Particle Swarm Algorithm

Evaluating the Effect of Optimized Voting Using Hybrid Particle Swarm and Grey Wolf Algorithm on the Classification of the Zoo Dataset

When there are numerous possible solutions for a given class in a given problem, majority voting or plurality voting is typically employed. One common technique for improving classification accuracy is bagging, which involves training many classifiers on slightly different datasets and then voting on the combined results. In this research, we examine how alternative voting procedures affect the efficiency of two distinct classification algorithms applied to datasets of varying complexity. Despite the increased computing cost associated with determining preference order, the results show that the single transferable vote can be a suitable alternative to plurality voting.

Parallel Hybrid Particle Swarm Algorithm for Workshop Scheduling Based on Spark

In hybrid mixed-flow workshop scheduling, there are problems such as mass production, mass manufacturing, mass assembly and mass synthesis of products. In order to solve these problems, combined with the Spark platform, a hybrid particle swarm algorithm that will be parallelized is proposed. Compared with the existing intelligent algorithms, the parallel hybrid particle swarm algorithm is more conducive to the realization of the global optimal solution. In the loader manufacturing workshop, the optimization goal is to minimize the maximum completion time and a parallelized hybrid particle swarm algorithm is used. The results show that in the case of relatively large batches, the parallel hybrid particle swarm algorithm can effectively obtain the scheduling plan and avoid falling into the local optimal solution. Compared with algorithm serialization, algorithm parallelization improves algorithm efficiency by 2–4 times. The larger the batches, the more obvious the algorithm parallelization improves computational efficiency.