Adaptive Particle Swarm Optimization Algorithm Research Articles

Multi-model fusion stacking ensemble learning method for the prediction of berberine by FT-NIR spectroscopy

Rhizoma Coptidis is a Chinese herbal medicine with antibacterial and anti-inflammatory properties. It has extensive applications in modern medicine. The content of berberine in Rhizoma Coptidis directly determines its quality. Fourier transforms near-infrared (FT-NIR) spectroscopy is a commonly used non-destructive method for rapidly detecting berberine content. In contrast to single-supervised learning algorithms in machine learning, ensemble learning combines individual learning algorithms to create a stable and better-performing strong-supervised model. This study collected spectral data of Rhizoma Coptidis using FT-NIR spectroscopy technology and established a chemometric model using a stacking ensemble approach with multiple models. Partial Least Squares (PLS), Adaptive Boosting (AdaBoost), Gradient boosting decision trees (GBDT), random forest (RF), and extreme gradient boosting (XGBoost) regression models were chosen as alternative base models, different Stacking models were established by random combinations. To fully leverage the strengths of each model and enhance predictive capability, an adaptive inertia weight particle swarm optimization algorithm (AWPSO) was used to search for the optimal parameters. The correlation coefficient of the test (RT) and the root mean square error of the test (RMSET) systematically evaluated the model performance. Finally, AWPSO-RF, AWPSO-XGBoost, and AWPSO-AdaBoost were selected as the base models. The RMSET and RT for RF, XGBoost, and AdaBoost were 0.226, 0.250, 0.195, and 0.871, 0.830, 0.927. After optimizing with the AWPSO algorithm, the RMSET and RT for AWPSO-RF, AWPSO-XGBoost, and AWPSO-AdaBoost were 0.226, 0.245, 0.194, and 0.871, 0.843, 0.922, respectively. The RMSET and RT values for the stacking ensemble were 0.174 and 0.932. The prediction accuracy and generalization ability of multi-model fusion stacking ensemble learning are superior to the single-model regression methods. Therefore, the stacking ensemble learning method that combines AdaBoost, RF, and XGBoost regression models is effective and feasible for assisting in the detection of berberine content in Rhizoma Coptidis.

Hierarchical multi-objective optimization of proton exchange membrane fuel cell with parameter uncertainty

It is important to improve the performance indexes including the net power and system efficiency for polymer electrolyte membrane fuel cell (PEMFC), especially considering the parameter uncertainty. To this end, this paper proposes a hierarchical multi-objective optimization framework including the off-line and on-line optimization. Firstly, a steadystate non-linear PEMFC system model is established as the base model. Secondly, an adaptive multi-objective particle swarm optimization (AMPSO) algorithm scheme is proposed in the off-line optimization procedure for the exact optimization of operation parameters. Meanwhile, an adaptive flight parameter strategy based on the particle dispersity (PD) information is proposed to balance the convergence and diversity of Pareto solutions. Finally, to decrease the influence caused by parameter uncertainty, the interval optimization method is proposed in the on-line optimization layer based on the results of AMPSO. The convergence condition of the proposed optimization scheme is verified by theory analysis. The proposed AMPSO is compared with different algorithms in the numerical simulation and hardware-in-loop (HIL) experiments. Meanwhile, the performance of the proposed method is tested on four representative benchmark problems. These results demonstrate that the PEMFC system with the proposed optimization scheme performs better than the base model and classical optimization algorithms in terms of the net power and system efficiency indexes, revealing the success of this hierarchical optimization approach in solving the accurate optimization and parameter uncertainty problems. By using statistical test methods, the proposed algorithm performs better hypervolume (HV) metric from the Pareto solution distribution.

Site selection and capacity determination of charging stations considering the uncertainty of users’ dynamic charging demands

Aiming at the problems of high investment and low efficiency in the planning and construction of electric vehicle (EV) charging stations in cities, an optimization model for site selection and capacity determination of charging stations considering the uncertainty of users’ dynamic charging demands is proposed. Firstly, based on the travel chain theory and the Origin-Destination (OD) matrix, the travel characteristics of EVs are studied, and the spatial and temporal distribution prediction model of EV charging load is established through the dynamic Dijkstra algorithm combined with the Monte Carlo method. Secondly, a site selection model for the charging station is established which takes the minimum annualized cost of the charging station operator and the annualized economic loss of the EV users as the goal. At the same time, the weighted Voronoi diagram and Adaptive Simulated Annealing Particle Swarm Optimization algorithm (ASPSO) are adopted to determine the optimal number/site selection and service scope of charging stations. Finally, an uncertain scenario set is introduced into the capacity determination model to describe the uncertainty of the users’ dynamic charging demands, and the robust optimization theory is utilized to solve the capacity of the charging station. A case study is carried out for the EV charging station planning problem in some urban areas of a northern city, and the validity of the model is verified.

Path planning of unmanned vehicles based on adaptive particle swarm optimization algorithm

Path planning technology is the basis of autonomous driving of unmanned vehicles. However, there are some problems in the traditional path planning technology. For example, high-quality global paths can't be generated quickly; Lacking of security verification ability; The performance of dynamic obstacle avoidance is poor. Therefore, this paper proposes a path planning method of unmanned vehicles based on adaptive particle swarm optimization algorithm (APSO). Firstly, a map simplification strategy (MSS) is proposed. The grid map is preprocessed by map simplification strategy to reduce the search space and time of path planning algorithm; Secondly, an APSO algorithm is proposed. The algorithm coordinates the search of particles through three adaptive factors and Levy flight strategy. Then, a security checking strategy is proposed. Security checking strategy can be used to verify the safety of global path; Finally, a dynamic obstacle avoidance strategy based on behavior is proposed. Vehicles can independently analyze the types of collision and adopt corresponding obstacle avoidance strategies. The simulation results show that MSS-APSO algorithm and APSO algorithm surpass original algorithms and comparison algorithms; MSS-APSO algorithm has strong applicability in real map environment; The obstacle avoidance strategy has great obstacle avoidance ability and real-time performance; The map simplification strategy can improve iterations of the algorithm and quality of the global path.

A temporal and spatial electric vehicle charging optimization scheme with DSO-EVA coordination framework

Burdens of increasing penetration of electric vehicles (EVs) on distribution systems have attracted wide attention to the research of EV charging coordination. Nevertheless, existing coordination lacks the joint consideration of the temporal-spatial flexibility of EVs, which could reduce load fluctuations when meeting the EV charging demands. Moreover, a thorough investigation is required for the coordination of the benefits to the distribution system operator (DSO), EV aggregator (EVA), and EVs. In this paper, a novel EV charging scheme considering the temporal-spatial features of EVs is proposed, achieving the coordination of DSO, EVA, and EVs in two steps. First, a mixed-integer second-order cone programming (MISOCP)-based EV charging schedule is developed for DSO. Second, the temporal-spatial features of EVs are exploited by EVA to track the charging schedule. Specifically, a dynamic charging price mechanism based on active power margin is proposed for public charging facilities and a specific load regulation is designed for private charging facilities. On this basis, the modified adaptive multi-objective particle swarm optimization (AMOPSO) algorithm is proposed, including adaptive flight parameter adjustment and termination mechanisms. Case studies demonstrate the proposed strategy can attenuate load variance and raise EVA revenue. Further, the impact analysis of penalty price and the price elasticity of electricity demand can provide references for stable distribution network operation, higher EVA revenue, and charging cost reduction.

Research on intelligent active disturbance rejection control algorithm for shock train leading edge of dual-mode scramjet

To prevent scramjet inlet unstart, stringent control over the shock train's leading edge in the isolator is necessary. Therefore, this study proposes a fuel flow active control scheme combining an adaptive particle swarm optimization algorithm (APSO) and active disturbance rejection control (ADRC) to enhance the traditional control (such as proportional-integral-derivative, PID) system's stability and anti-interference capabilities in complex and uncertain environments. Within this context, a simple, semi-empirical mathematical model of a dual-mode scramjet is constructed. An ADRC controller is designed to counteract the nonlinearity and disturbance of the dual-mode scramjet. ADRC, not requiring an accurate mathematical model, utilizes its extended state observer to estimate all uncertain factors affecting the controlled object based on the relationship between the shock train's leading edge and the controller's output, treating them as unknown disturbances for compensation, thereby exhibiting strong anti-interference capabilities. In order to optimize the performance, the APSO is introduced to fine-tune the ADRC controller parameters. The APSO reduces the rise time of ADRC from 22.28 to 11.39 ms, and the adjustment time from 40.05 to 13.64 ms. The APSO effectively tunes the parameters of the ADRC controller, which ensures rapidity comparable to the PID and all-coefficient adaptive control (ACAC) in managing the shock train's leading edge. At the same time, ADRC has stronger anti-interference ability and adaptive ability than ACAC and PID. This research preliminarily verifies the feasibility and advancement of the ADRC for shock train leading-edge control in scramjet isolators.

Adaptive Particle Swarm Optimization Algorithm and Application Model Based on Diversity-Driven Optimization

Adaptive Particle Swarm Optimization Algorithm and Application Model Based on Diversity-Driven Optimization

Strategy Adaptive Particle Swarm Optimization Algorithm for Solving Free-Form Surface Registration to Improve Detection Accuracy

Strategy Adaptive Particle Swarm Optimization Algorithm for Solving Free-Form Surface Registration to Improve Detection Accuracy

Research on innovative methods of virtual reality course content for tourism education

Abstract Tourism practice teaching is an important means to cultivate high-quality skilled tourism talents. When virtual reality is in tourism practice, teaching undoubtedly shows a beautiful blueprint for modern tourism education. The article demonstrates the advantages of the application of VR technology, designs a VR practical training system for tourism education, and develops VR resources and interface interaction design for tourism education. Based on the binocular stereo imaging model to obtain maximum and minimum parallax, and combined with the adaptive weight PSO algorithm for optimizing tourism virtual scene viewpoints. Then, a comparison test for teaching was designed using the VR training system for tourism education. By analyzing students’ eye movement data to understand the viewpoint optimization effect of the AW-PSO algorithm, we also verified their learning performance, learning experience, and academic mood changes. The edge strength and clarity of the virtual scene obtained by the AW-PSO algorithm were 67.06 and 14.71, respectively, and the theoretical score of the experimental class students was 83.15, which was 9.06% higher than that of the control class students. Based on tourism education, VR practical training systems can effectively enhance students’ learning interest and academic mood for tourism education courses and help develop high-quality tourism education courses in colleges and universities.

Optimization of subsea production facilities layout based on cluster manifold system considering seabed topography

High investment in deep-water development highlights the importance of optimizing the subsea layout, a properly optimized subsea production system reduces costs and contributes to production performance. Aiming at the minimum total construction cost of a subsea cluster manifold system, an integrated mathematical model considering the combination of subsea well grouping, cluster manifold layout, connection relationships, pipe routes and seabed topography is developed in this study. A modified adaptive particle swarm optimization (MAPSO) algorithm coupled with A-star algorithm, clustering algorithm and minimum spanning tree algorithm is used to solve the model by using a newly proposed process. The feasibility and practicality of the model is verified by designing the layout of a deep-water oil field, and the influence of manifold number and seabed topography is demonstrated by the difference in suggested cost. The model provides a new method which can be used to estimate costs more reliably.

Adaptive sliding mode observers‐based dissipative Hamilton finite time optimization control for the speed and tension system of reversible cold strip rolling mill

SummaryFor the complex time‐varying uncertain nonlinear speed and tension system of reversible cold strip rolling mill, an adaptive sliding mode observers (ASMOs)‐based dissipative Hamilton finite time optimization control method is given in this article. First, the ASMOs are developed to observe rolling mill system's unmatched uncertainties, and their observation errors can converge to the origin in finite time. Second, combined with rolling mill system's physical structure characteristics, its dissipative Hamilton model is established by pre‐feedback processing, and then the dissipative Hamilton finite time controllers are designed based on interconnection and damping configuration and energy shaping method, and the system states can converge in finite time. Third, the adaptive mutation particle swarm optimization algorithm is adopted to optimize the controller parameters, which can further improve rolling mill system's control performance. Finally, the simulation results verify the validity of the given method based on actual field data.

A non-intrusive load recognition method combining adaptive PSO algorithm and CNN model

Real-time monitoring of electricity usage details through load monitoring techniques is a crucial aspect of smart power grid management and monitoring, allowing for the acquisition of information on the electricity usage of individual appliances for power users. Accurate detection of electricity load is essential for refined load management and monitoring of power supply quality, facilitating the improvement of power management at the user side and enhancing power operation efficiency. Non-intrusive load monitoring (NILM) techniques require only the analysis of total load data to achieve load monitoring of electricity usage details, and offer advantages such as low cost, easy implementation, high reliability, and user acceptance. However, with the increasing number of distributed new load devices on the user side and the diversification of device development, simple load recognition algorithms are insufficient to meet the identification needs of multiple devices and achieve high recognition accuracy. To address this issue, a non-intrusive load recognition (NILR) model that combines an adaptive particle swarm optimization algorithm (PSO) and convolutional neural network (CNN) has been proposed. In this model, pixelated images of different electrical V-I trajectories are used as inputs for the CNN, and the optimal network layer and convolutional kernel size are determined by the adaptive PSO optimization algorithm during the CNN training process. The proposed model has been validated on the public dataset PLAID, and experimental results demonstrate that it has achieved a overall recognition accuracy of 97.26% and F-1 score of 96.92%, significantly better than other comparison models. The proposed model effectively reduces the confusion between various devices, exhibiting good recognition and generalization capabilities.

Data-Driven Optimal Control for Municipal Solid Waste Incineration Process

Municipal solid waste incineration (MSWI) is a dynamic industrial process involving complex physical and chemical reactions. Due to the uncertain municipal solid waste (MSW) composition and dynamic operation conditions, it is difficult to guarantee optimal operation for the MSWI process. To solve this problem, a data-driven optimal control scheme is proposed with a hierarchical control structure. In the set points optimization stage, an online adaptive fuzzy neural network (OAFNN) is designed to construct the objective functions, including combustion efficiency and NOx emission concentration. An adaptive mutation particle swarm optimization (AMPSO) algorithm is developed to obtain the optimal set points of oxygen content in flue gas. In the control stage, a double long short-term memory neural networks-based model predictive control (DLSTM-MPC) strategy is exploited. A self-organizing long short-term memory (SOLSTM) network is employed to predict the oxygen content in flue gas with a compact structure. To reduce the influences from dynamic disturbances and further improve the tracking control performance, another long short-term memory (LSTM) neural network is established to correct the prediction results. Finally, the set points optimization method and DLSTM-MPC strategy are combined to realize the optimal operation of the MSWI process. The effectiveness of the proposed optimal control scheme is verified by real industrial data. The experimental results demonstrate that the optimal control scheme can achieve promising tracking control performance of oxygen content in flue gas and improve the operational performance of the MSWI process.

Digital twin modeling for district heating network based on hydraulic resistance identification and heat load prediction

As a vital infrastructure in modern cities, district heating (DH) systems provide stable high-quality heat sources. To satisfy the demands of energy-saving, emission-reduction policies, and user preferences, a high-precision digital simulation platform is essential for district heating network (DHN) scheduling. In this paper, a method for digital twin (DT) modeling based on hydraulic resistance identification using an online adaptive particle swarm optimization (APSO) algorithm is proposed. Additionally, Singular Spectrum Analysis and back propagation artificial neural network algorithms (SSA-BP) are proposed to achieve heat load prediction in order to provide sufficient conditions for DHN scheduling. The load prediction for the substation is completed by predicting the secondary return water temperature at the subsequent time step based on the historical outdoor temperature time series and secondary supply water temperature of the substation. Accordingly, simulation analysis has been conducted on its application to an existing DHN in Tianjin. With the proposed methods, the simulation errors are reduced for about 80 % substations in the case DHN compared to mechanistic models when simulating hydraulic conditions. Among these, 77.49 % of substations were reduced by 0 %–3 %, and 1.43 % of substations were reduced by 3 %–5 %. The prediction errors of secondary return water temperature for case substations A and B exhibit random variation trends, with maximum absolute errors within the range of 0.02 °C and 0.06 °C, respectively.

Single-Frequency GNSS Integer Ambiguity Solving Based on Adaptive Genetic Particle Swarm Optimization Algorithm

Single-Frequency GNSS Integer Ambiguity Solving Based on Adaptive Genetic Particle Swarm Optimization Algorithm

Performance investigation of a hybrid PV/T collector with a novel trapezoidal fluid channel

The photovoltaic-thermal collector (PV/T) is an innovative technology that combines PV cells and solar thermal collectors into a co-generation unit, enabling full-spectrum solar utilization. This research proposes and examines a hybrid PV/T system with novel trapezoidal fluid channels embedded in graphite, arranged in a parallel S-shaped structure under outdoor conditions of Beijing. Parametric discussions and daily performance analysis are conducted to assess its effectiveness and stability. A daily average of 12.7 °C reduction in cell temperature compared to PV modules results in a relative 5.20 % improvement in electrical output under the intensity of solar radiation is 597 W/m2. Similarly, the peak temperature of the water tank reaches 56.9 °C, and thermal efficiency is enhanced by 7.86 % over conventional sheet-tube PV/T collectors. For further optimization, a constrained adaptive particle swarm optimization algorithm (EPF-APSO) is constructed based on the experimental data, implementing a variable water flow rate (VWV) strategy. Compared to a constant water flow rate (CWV), the overall energy collected varies from 2.755 to 2.828 kWh per day, potentially reducing pump energy consumption by 17.93 %. The contribution of this paper provides references on structural and operational parameters optimization of PV/T collectors applying machine learning algorithms for better comprehensive efficiency.

Assessment and optimization of tunnel lighting quality based on drivers' visual comfort: From methodology to application

Drivers' visual comfort is directly affected by tunnel lighting quality. Currently, many built tunnels have poor-quality lighting with varying degrees of visual interference, which may lead to visual discomfort and traffic accidents. To solve this problem, this study proposes a method to assess and optimize the tunnel lighting quality, aiming to evaluate the lighting quality from the perspective of drivers' visual comfort and improve the lighting effect in each lighting zone of the tunnel. First, the visual characteristics of drivers and quantitative relationship between visual comfort and tunnel lighting environment are derived through field tests and mathematical statistics. Second, the comfort range based on visual characteristic indicators (VCIs) is obtained via a comprehensive analysis of objective physiological responses and subjective questionnaire survey results of drivers, which is used as the comfort criteria to assess the tunnel lighting quality. Subsequently, the effects of luminance, luminance uniformity, and flicker frequency on drivers' visual comfort are considered, and a lighting optimization model based on the adaptive penalty function particle swarm optimization algorithm is established by combining comfort constraints and energy-saving objectives. Finally, driving simulation experiments are performed using virtual reality technology, which verify the effectiveness of the assessment and optimization methods. The results show that drivers' visual comfort in the tunnel threshold zone increases with an increase in the luminance reduction coefficient and decrease in the vehicle speed, and drivers' visual comfort in the tunnel interior zone increases with an increase in the road surface illuminance and visibility. The comfort range of the VCIs classify the tunnel lighting quality into four evaluation levels. Therefore, the proposed method can accurately and quantitatively assess the comfort of the tunnel lighting environment, improving drivers' visual comfort in the tunnel by 48.08 %, while saving 12.03 % of energy.

PAPR, Spectral Efficiency, BER and SNR Analysis of OFDM: A Novel Partial Transmit Sequence-Particle Swarm Optimization Technique

Orthogonal frequency division multiplexing (OFDM) is a widely used multicarrier modulation (MCM) technique in the field of wireless communications, specifically designed to facilitate high-speed data transmission. The use of several subcarriers inside an OFDM system for the transmission of modulated symbols results in the generation of OFDM signals with a significant peak-to-average power ratio (PAPR). In this study, we propose a novel approach for mitigating the high PAPR in wireless communication systems (WCS). Our method utilizes a partial transmit sequence (PTS) strategy, which is enhanced by using an adaptive particle swarm optimization (PSO) algorithm. In this study, we present a description of an OFDM system employing the standard PTS technique in conjunction with PSO. To mitigate computational complexity, the suggested methodology efficiently explores the optimal amalgamation of phase rotation components. Experimental findings demonstrate that the computational complexity and PAPR have been greatly minimized by the suggested method.

Optimal hybrid photovoltaic distributed generation and distribution static synchronous compensators planning to minimize active power losses using adaptive acceleration coefficients particle swarm optimization algorithms

The paper aims to identify the optimum size and location of photovoltaic distributed generation systems and distribution static synchronous compensators (DSTATCOMs) systems to minimize active power losses in the distribution network and enhance the voltage profile. The methodology employed in this article begins by thoroughly discussing various acceleration algorithms used in Particle Swarm Optimization (PSO) and their variations with each iteration. Subsequently, a range of PSO algorithms, each incorporating different variations of acceleration coefficients was verified to solve the problem of active power losses and voltage improvement. Simulation results attained on Standard IEEE-33 bus radial distribution network prove the efficiency of acceleration coefficients of PSO; it was evaluated and compared with other methods in the literature for improving the voltage profile and reducing active power. Originality. Consists in determining the most effective method among the various acceleration coefficients of PSO in terms of minimizing active power losses and enhancing the voltage profile, within the power system. Furthermore, demonstrates the superiority of the selected method over others for achieving significant improvements in power system efficiency. Practical value of this study lies on its ability to provide practical solutions for the optimal placement and sizing of distributed generation and DSTATCOMs. The proposed optimization method offers tangible benefits for power system operation and control. These findings have practical implications for power system planners, operators, and policymakers, enabling them to make informed decisions on the effective integration of distributed generation and DSTATCOM technologies.

Nonlinear Dynamic Model-Based Position Control Parameter Optimization Method of Planar Switched Reluctance Motors

Currently, there are few systematic position control parameter optimization methods for planar switched reluctance motors (PSRMs); how to effectively optimize the control parameters of PSRMs is one of the critical issues that needs to be urgently solved. Therefore, a nonlinear dynamic model-based position control parameter optimization method of PSRMs is proposed in this paper. First, to improve the accuracy of the motor dynamics model, a Hammerstein–Wiener model based on the BP neural network input–output nonlinear module is established by combining the linear model and nonlinear model structures so that the nonlinear and linear characteristics of the system are characterized simultaneously. Then, a position control parameter optimization system of PSRMs is developed using the established Hammerstein–Wiener model. In addition, with a self-designed simulated annealing adaptive particle swarm optimization algorithm (SAAPSO), the position control parameter optimization system is performed offline iteratively to obtain the optimal position control parameters. Simulations and experiments are carried out and the corresponding results show that the optimal position control parameters obtained by the proposed method can be directly applied in the actual control system of PSRMs and the control performance is improved effectively using the obtained optimal control parameters.