Particle Swarm Optimization Algorithm Research Articles

Optimal Scheduling of Island Microgrids with Seawater Pumped Storage Plants for Multi‐Energy Complementarity

The rapid development of new energy sources, such as offshore wind power and photovoltaic power, has provided a new solution to the problem of power supply for islands far from the mainland. Wave energy is a kind of renewable energy originated from the ocean, but the existing island power supply programs seldom consider this favorable natural condition. In addition, seawater variable‐speed pumped storage is a new idea to consume offshore wind power and improve the reliability of coastal and island power systems. In view of the stochastic and intermittent nature of new energy sources, this paper adopts seawater variable‐speed pumped storage power plants as energy storage equipment, and put forward an island power supply scheme with wind power, photovoltaic power generation, wave power generation, pumped storage power plants and diesel generator sets as a multifunctional complementary isolated grid. Firstly, wave energy generators, wind farms, photovoltaic farms, pumped storage power stations and diesel generator sets are modeled separately. Then, considering their respective operating conditions, constraints and load requirements, the optimal scheduling of island microgrids with multi‐energy complementarity is constructed. Finally, based on the improved particle swarm optimization algorithm, the model is solved. According to the wind power photovoltaic and wave power output curves of several typical scenarios in an island far away from the mainland, the cost and benefit of different schemes are compared to verify the effectiveness of the optimal scheduling in this paper. © 2024 Institute of Electrical Engineers of Japan and Wiley Periodicals LLC.

Research on adaptive feature optimization and drilling rate prediction based on real-time data

In the drilling process, the rate of penetration (ROP) is an essential indicator of drilling efficiency. Accurate prediction of the rate of penetration (ROP) is crucial for improving drilling efficiency and minimizing costs. Conventional ROP predictions are typically made post-drilling, often resulting in low accuracy and limited applicability. To predict ROP more efficiently and accurately, an adaptive feature-optimized ROP prediction method based on real-time data was proposed. Initially, a fusion feature selection algorithm based on historical drilling data was designed and optimized using the Particle Swarm Optimization algorithm (PSO). On this basis, adaptive feature optimization was performed on real-time drilling datasets, and four different machine learning ROP prediction models were established using the selected feature parameters. The result shows that compared with the non-adaptive methods, the accuracy of the ROP prediction model using adaptive feature optimization is improved. The improvements are 27%, 44%, 47% and 47%, respectively, it demonstrates the significant advantages of using the designed adaptive feature optimization.

Comparison of Interval Type-3 Mamdani and Sugeno Models for Fuzzy Aggregation Applied to Ensemble Neural Networks for Mexican Stock Exchange Time Series Prediction

In this work, interval type-2 and type-3 fuzzy systems were designed, of Mamdani and Sugeno types, for time series prediction. The aggregation performed by the type-2 and type-3 fuzzy systems was carried out by using the results of an optimized ensemble neural network (ENN) obtained with the particle swarm optimization algorithm. The time series data that were used were of the Mexican stock exchange. The method finds the best prediction error. This method consists of the aggregation of the responses of the ENN with type-2 and type-3 fuzzy systems. In this case, the systems consist of five inputs and one output. Each input is made up of two membership functions and there are 32 possible fuzzy if-then rules. The simulation results show that the approach with type-2 and type-3 fuzzy systems provides a good prediction of the Mexican stock exchange. Statistical tests of the comparison of type-1, type-2, and type-3 fuzzy systems are also presented.

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

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

Explainable machine learning-driven predictive performance and process parameter optimization for caproic acid production

In this study, four machine learning (ML) prediction models were developed to predict and optimize the production performance of caproic acid based on substrates, products, and process parameters. The XGBoost outperformed others, with a high R2 of 0.998 on the training set and 0.885 on the test set. Feature importance analysis revealed hydraulic retention time (HRT) and butyric acid concentration are decisive. The SHAP method offered profound insights into the interplay and cumulative effects of substrate composition, identified the synergistic effects between butyric acid and lactic acid, and emphasized adding glucose can benefit caproic with lactic acid co-fermentation. By integrating the Adaptive Variation Particle Swarm Optimization (AVPSO) algorithm, the optimal process conditions to achieve a maximum caproic acid production of 8.64 g/L was obtained. This study not only advances caproic acid production but contributes a versatile ML-driven strategy applicable to bioprocess optimizations, potentially transformative for sustainable and economically viable bioproduction.

Metaheuristic Algorithm-Based Proportional–Integrative–Derivative Control of a Twin Rotor Multi Input Multi Output System

Metaheuristic algorithms are computational techniques based on the collective behavior of swarms and the study of organisms acting in communities. These algorithms involve different types of organisms. Finding controller values for nonlinear systems is a challenging task using classical approaches. Hence, using metaheuristics to find the controller values of a twin rotor multi-input multi-output system (TRMS), one of the nonlinear systems studied in the literature, seems to be more appropriate than using classical methods. In this study, different types of metaheuristic algorithms were used to find the PID controller values for a TRMS, including a genetic algorithm (GA), a dragonfly algorithm, a cuckoo algorithm, a particle swarm optimization (PSO) algorithm, and a coronavirus optimization algorithm (COVIDOA). The obtained graphs were analyzed based on certain criteria for the main rotor and tail rotor angles to reach the reference value in the TRMS. The experimental results show that when the rise and settlement times of the TRMS are compared in terms of performance, the GA took 1.5040 s (seconds) and the COVIDOA took 9.59 s to increase the pitch angle to the reference value, with the GA taking 0.7845 s and the COVIDOA taking 2.4950 s to increase the yaw angle to the reference value. For the settling time, the GA took 11.67 s and the COVIDOA took 28.01 s for the pitch angle, while the GA took 14.97 s and the COVIDOA took 26.69 s for the yaw angle. With these values, the GA and COVIDOA emerge as the foremost algorithms in this context.

Optimal ultra-broadband sound-absorption performance design for coiled up space structures with nonlinear robustness

In this paper, based on a high- sound-pressure microperforated plate model, a nonlinear sound-absorption model for multi-unit couplings based on coiled-up space structures is proposed. The sound absorption performance and relative impedance of two-unit coupled structures (TUCSs) were studied. The results show that the TUCS sound-absorption performance, which is good at low sound pressures, decreases significantly as the incident sound pressure increases owing to impedance mismatch. Furthermore, the influence of parameters such as aperture size, plate thickness, perforation rate, and equivalent length on the unit’s structural sound-absorption performance was studied. By employing the particle swarm optimization algorithm, we optimized the parameters of an eight-unit coupled structure (EUCS) using the proposed model. The optimization results reveal the nonlinear robust sound-absorption characteristics of the structure, which means the EUCS can maintain a stable and good sound-absorption performance when the incident sound pressure level and frequency are within 125–155 dB and 400–3000 Hz, respectively. Experimental assessments of the EUCS sound-absorption performance within the 300–1900 Hz range confirmed the accuracy of the proposed model and the efficacy of the optimized sound-absorption capabilities of the structure. Consequently, the proposed model and sound-absorption structure demonstrated potential applications in the acoustic lining design of aircraft engines.

Integrating machine learning and thermodynamic modeling for performance prediction and optimization of supercritical CO2 and gas turbine combined power systems

The supercritical carbon dioxide (SCO2) cycle has drawn attention to extracting energy and generating power from low-grade heat resources due to its higher efficiency, lower cost, and compactness. Combining the SCO2 cycle with a gas turbine (GT) is a promising field of research with applications in industries such as waste heat recovery (WHR) systems. In this research, three different configurations of power generation SCO2 cycles, including recuperation, precompression, and reheating, were thermodynamically designed and modeled. Extracting the main parameters of cycles, and the appropriate objective, which is cycle energy efficiency, up to 80,000 data constructed. Random forest (RF) and support vector regression (SVR), machine learning (ML) techniques, are used for the performance prediction of cycles. The results show the strength of the RF method to predict the cycle efficiency with up to 3% error and the SVR method with more than 90% accuracy. Sensitivity analysis and Particle Swarm Optimization (PSO) algorithm are employed for optimizing the recuperation cycle. The outcomes of the optimization model, based on the prediction models as proxies, have results in nearly close to those of traditional optimization, which is based on a thermodynamic model. In conclusion, ML models can be used in industry for prediction and maintenance since the methods are up to 5 times faster than thermodynamic models.

Transmission Power Reduction Based on an Enhanced Particle Swarm Optimization Algorithm in Wireless Sensor Network for Internet of Things

Transmission Power Reduction Based on an Enhanced Particle Swarm Optimization Algorithm in Wireless Sensor Network for Internet of Things

Optimization of Sailing Speed for Inland Electric Ships Based on an Improved Multi-Objective Particle Swarm Optimization (MOPSO) Algorithm

Sailing speed is a critical factor affecting the ship’s energy consumption and operating costs for a voyage. Inland waterways present a complex navigation environment due to their narrow channels, numerous curved segments, and significant variations in water depth and flow speed. This paper constructs a model of a ship’s energy consumption based on an analysis of ship resistance and the energy transfer relationship of ships. The K-means clustering algorithm is introduced to divide the Yangtze River waterway into multiple segments based on the similarity of navigation environments. Considering the constraints of the ship’s main engine and the desired arrival time, a multi-objective particle swarm optimization (MOPSO) algorithm, improved with cosine decreasing inertial weight and Gaussian random mutation, is employed to optimize segmented navigation speeds to achieve different goals. Finally, four cases are studied with a fully electric ship navigating the reaches of the Yangtze River. The results indicate that the optimized speed can reduce ship energy consumption by up to 6.18% and significantly reduce ship energy consumption and operational costs under different conditions.

Optimization Algorithms and Their Applications and Prospects in Manufacturing Engineering.

In modern manufacturing, optimization algorithms have become a key tool for improving the efficiency and quality of machining technology. As computing technology advances and artificial intelligence evolves, these algorithms are assuming an increasingly vital role in the parameter optimization of machining processes. Currently, the development of the response surface method, genetic algorithm, Taguchi method, and particle swarm optimization algorithm is relatively mature, and their applications in process parameter optimization are quite extensive. They are increasingly used as optimization objectives for surface roughness, subsurface damage, cutting forces, and mechanical properties, both for machining and special machining. This article provides a systematic review of the application and developmental trends of optimization algorithms within the realm of practical engineering production. It delves into the classification, definition, and current state of research concerning process parameter optimization algorithms in engineering manufacturing processes, both domestically and internationally. Furthermore, it offers a detailed exploration of the specific applications of these optimization algorithms in real-world scenarios. The evolution of optimization algorithms is geared towards bolstering the competitiveness of the future manufacturing industry and fostering the advancement of manufacturing technology towards greater efficiency, sustainability, and customization.

Design of Power Outage Monitoring and Warning System Based on Internet of Things

With the rapid development of distribution network and the high popularity of distributed generation, the research on risk assessment of distribution network is accelerated. When quantifying the degree of harm caused by abnormal situations, it is necessary to consider the severity of the harm and the impact on society to measure the severity of power failure and reduce the loss caused by power risk. To provide data support for the fine perception of the situation and its development trend, the monitoring system constructed by the power microservice further improves the ability and accuracy of sudden fault prediction. In this paper, through the monitoring system information to explore the transmission line fault early warning, the data analysis model is established. The particle swarm optimization algorithm and BP neural network are used to build the early warning model to predict the potential fault situation and cause analysis of the power grid under various indicators in a certain period in the future, which is to provide more scientific and reasonable risk management and control for the power grid. Through the statistical analysis of all kinds of information data collected by the power microservice, a power monitoring system based on early warning of power outage risk is established to enhance the operation adaptability of the power grid system under uncertain conditions and prevent the occurrence of tripping blackouts so that this study has an important function of intelligent decision-making. The experimental results show the feasibility and high efficiency of this study. The comparison of algorithm results shows that the performance of this method is improved by more than 10%. The stability is improved by 17%. The response time to various situations is shortened by 32% to judge the abnormal operation state of the power grid more efficiently. It can make emergency preparations in time, reduce the damage caused by accidents to the power grid and provide practical tools for the power grid to further enhance the disaster prevention ability of transmission equipment and effectively resist risk events.

PGA: A new particle swarm optimization algorithm based on genetic operators for the global optimization of clusters.

We have developed a global optimization program named PGA based on particle swarm optimization algorithm coupled with genetic operators for the structures of atomic clusters. The effectiveness and efficiency of the PGA program can be demonstrated by efficiently obtaining the tetrahedral Au20 and double-ring tubular B20, and identifying the ground state clusters through the comparison between the simulated and the experimental photoelectron spectra (PESs). Then, the PGA was applied to search for the global minimum structures of (n = 3-30) clusters, new structures have been found for sizes n = 6, 7, 12, 14, and medium-sized 21-30 were first determined. The high consistency between the simulated spectra and the experimental ones once again demonstrates the efficiency of the PGA program. Based on the ground-state structures of these (n = 3-30) clusters, their structural evolution and electronic properties were subsequently explored. The performance on Au20, B20, , and (n = 3-30) clusters indicates the promising potential of the PGA program for exploring the global minima of other clusters. The code is available for free upon request.

Multi-objective preventive maintenance strategy and optimization considering unavailability and cost: A case study on VOBC

The Vehicle On-Board Controller (VOBC) is a core component of urban rail transit trains, with high maintenance costs and serious consequences in case of failure. Ensuring long-term VOBC operation while minimizing maintenance costs is of paramount importance. This paper proposes a multi-objective preventive maintenance (PM) strategy and optimization considering system unavailability and maintenance costs. Firstly, we provide a statement of the problem and analyze the impact of different maintenance actions on VOBC. Next, the decreasing process parameter is introduced to adjust the PM interval dynamically. The mathematical models of system unavailability and maintenance costs are derived to construct a multi-objective PM strategy. Then, we develop a hybrid heuristic algorithm including multi-objective particle swarm optimization and genetic algorithm (MOPSO-GA), which is used to obtain the optimal Pareto frontier for maintenance strategies. In the study, we select maintenance strategies by introducing an aversion factor to fulfill the preferences of different decision-makers. A comprehensive sensitivity analysis is performed to illustrate the impact of several critical parameters on the multi-objective PM strategy. The case study on Beijing subway’s VOBC is also executed. The outcomes indicate that the proposed method can dynamically adjust to match the preferences of diverse decision-makers and the MOPSO-GA algorithm has excellent robustness on most parameters. This approach allows for creating field maintenance strategies catering to the varied maintenance requirements of urban rail transit VOBC.

A Novel Multi-Objective Dynamic Reliability Optimization Approach for a Planetary Gear Transmission Mechanism

Planetary gear transmission mechanisms (PGTMs) are widely used in mechanical transmission systems due to their compact structure and high transmission efficiency. To implement the reliability design and optimization of a PGTM, a novel multi-objective dynamic reliability optimization approach is proposed. First, a multi-objective reliability optimization model is established. Furthermore, considering the strength degradation of gears during service, a dynamic reliability analysis is conducted based on the theory of nonlinear fatigue damage accumulation. In addition, to improve computing efficiency, a random forest surrogate model based on the particle swarm optimization algorithm is proposed. Finally, an adaptive multi-objective evolutionary algorithm based on decomposition (AMOEA/D) is designed to optimize the mechanism, along with an adaptive neighborhood updating strategy and a hybrid crossover operator. The feasibility and superiority of the proposed approach are verified through an NGW planetary gear reducer. The results show that the proposed surrogate model can reduce the calculation cost and has high accuracy. The AMOEA/D algorithm can improve transmission efficiency, reduce gear volume and ensure reliability at the same time. It can provide guidance for actual gear production.

A bi-evolutionary cooperative multi-objective algorithm for blocking group flow shop with outsourcing option

In this study, a multi-objective blocking group flow shop scheduling problem with outsourcing option (BGFSP_OO) is addressed, where three objectives, including makespan, total energy consumption (TEC) and outsourcing cost, are considered simultaneously. To solve the BGFSP_OO, a bi-evolutionary cooperative multi-objective algorithm (BECMOA) is proposed. First, a machine switching strategy based on machine idle and blocking time is used in the decoding part to optimize the objective value TEC. Then, an effective heuristic for classifying outsourcing groups is proposed. To balance convergence and diversity abilities, a bi-evolutionary mechanism is proposed. The particle swarm optimization algorithm based on the gravity factor (IPSO) is employed, which exploiting individual performance, can enhance the convergence ability. Cross evolutionary search (CES) strategy is developed which can improve search ability, aiming to ensure diversity of solutions and access to more non-dominated solutions. Finally, the experimental results show that BECMOA is effective in solving BGFSP_OO compared to the state-of-the-art methods.

Research on Optimization Design of Heliostat Field Based on Particle Swarm Optimization Algorithm

Research on Optimization Design of Heliostat Field Based on Particle Swarm Optimization Algorithm

Design of Anti-Eccentric Load Sensor for Engineering Operation Early Warning Based on Particle Swarm Optimization.

The accuracy of aerial work platform weighing is essential for safety. However, in practice, the same weight placed at different locations on the platform can yield varying readings, which is a phenomenon known as eccentric load. Measurement errors caused by eccentric loads can lead to missed detections and false alarms in the vehicle safety system, seriously affecting the safety of aerial work. To overcome the influence of eccentric load, the current engineering practice relies on multiple measurements at multiple points and averaging the results to eliminate the eccentric load, which greatly increases the work intensity of workers. To address the aforementioned issues, this paper proposes a three-dimensional force/torque shear force compensation scheme based on bending torque and torsional torque for pressure. The goal is to ensure that the sensor on the aerial work vehicle platform can accurately measure the anti-eccentric load under single-point measurement conditions. A three-box structure anti-eccentric load-weighing sensor for the aerial work platform was designed. Its structure has the advantages of high mechanical strength and no radial effect, ensuring the safety of aerial work, improvement of measurement sensitivity, and enabling of real-time and accurate acquisition of force/torque in three directions. In order to further improve the measurement accuracy of 3D force/torque compensation, a particle swarm optimization algorithm was adopted to optimize the 3D force/torque shear force compensation, thereby improving the safety of engineering operations. Through the verification of a self-made testing platform, the anti-eccentric load sensor designed in this study can ensure that the measurement error of objects at any position on the platform is less than 1.5%, effectively improving the safety of high-altitude platform engineering operations.

A Low-Frequency Oscillation Suppression Method for Regional Interconnected Power Systems with High-Permeability Wind Power.

With the integration of large-scale wind power into the power grid, the impact on system stability, especially the issue of low-frequency oscillations caused by small disturbances, is becoming increasingly prominent. Therefore, this paper proposes a damping quantitative analysis method for regional interconnected power systems incorporating large-scale wind power. Using the cross-entropy particle swarm optimization (CE-PSO) algorithm, the control parameters of wind turbines are optimized to suppress low-frequency oscillations in interconnected systems. The method begins with the state equation of the interconnected power system in two regions; it deduces the characteristic polynomial of the interconnected system, including wind farms, and takes into account the influence of wind power integration on the electrical connectivity of the system. Subsequently, the influence of wind turbine control parameters on the system is quantified, and a quantitative analysis model of the impact of wind power integration on system damping characteristics is constructed. Based on this, an optimization model for wind turbine control parameters is established, and the CE-PSO algorithm is utilized to achieve suppression of low-frequency oscillations in interconnected power grids with wind power integration. Finally, the accuracy and effectiveness of the proposed method are verified through a typical electromagnetic transient simulation model of the two-region interconnected power system.

New compound XeN14 with high energy density

As a high-energy density material, polymeric nitrogen has attracted considerable attention, while the exceptionally high synthesis pressure hinders its studies and applications. A significant discovery indicates that the insertion of noble gas elements can effectively reduce the synthesis pressure of polymeric nitrogen compounds. This work utilized the particle swarm optimization algorithm and first-principles calculations to extensively explore the stoichiometry of Xe–N compounds under high pressures. Two phases of XeN14, P6mm and P-62m, have been discovered, which are energetically more stable than the basic mixture of Xe and N2. Evidence of charge transfer between Xe and N was found, verifying that Xe plays a crucial role in forming polymeric nitrogen compounds. These two compounds are kinetically stable at pressures ranging from 50 to 200 GPa and exhibit semiconductor properties. A unique channel-like structure was discovered in the P6mm phase. The energy densities of P6mm and P-62m phases are 7.39 and 7.59 kJ/g, respectively, significantly exceeding those of TNT (Trinitrotoluene) and HMX (Octogen), indicating their potential as high-energy density materials.