Weight Particle Swarm Optimization Research Articles

An improved ensemble particle swarm optimizer using niching behavior and covariance matrix adapted retreat phase

Over the past two decades, to overcome the limitations of certain algorithms, ensemble strategies or self-adaptive mechanisms for evolutionary computation algorithms have been proposed. Regardless of how these strategies or mechanisms were designed, their objective was to control the balance between the global and local search capabilities during the evolutionary process. Inspired by this, a novel ensemble strategy with three groups to improve the performance of the ensemble particle swarm optimizer (EPSO) is proposed. The first group uses a covariance matrix adapted retreat phase (CMAR), the second group induces the niching behavior for inertia weight particle swarm optimization (PSO), and the third group maintains the characteristics of a large subpopulation of EPSO. Furthermore, a sample pool and replacement mechanism are proposed to perturb the three groups. This strategy also recommends a group of empirical allocation rates for subpopulations based on various proportion combination tests. The performance of the proposed strategy is evaluated using CEC2005 benchmark functions with 10, 30, and 50-dimensional tests and compared with those of the state-of-the-art PSO variants: EPSO, a modified PSO using adaptive strategy (MPSO), PSO variant for single-objective numerical optimization (PSO-sono), terminal crossover and steering-based PSO (TCSPSO), self-adapting hybrid strategy PSO (SaHSPS), and pyramid PSO (PPSO). Experimental results demonstrate that the improved EPSO, using CMAR, niching behavior, and sample pool, performs best.

Optimization Strategy of Rolling Mill Hydraulic Roll Gap Control System Based on Improved Particle Swarm PID Algorithm

Medium and heavy plates are important strategic materials, which are widely used in many fields, such as large ships, weapons and armor, large bridges, and super high-rise buildings. However, the traditional control technology cannot meet the high-precision control requirements of the roll gap of the thick plate mill, resulting in errors in the thickness of the medium and heavy plate, thereby reducing the quality of the product. In response to this problem, this paper takes the 5500 mm thick plate production line as the research background, and establishes the model of the rolling mill plate thickness automatic control system, using the Ziegler-Nichol response curve method (Z-N), particle swarm optimization (PSO) algorithm and linear weight particle swarm optimization (LWPSO) algorithm, respectively, optimizes the parameter setting of the PID controller of the system, and uses OPC UA communication technology to realize the online semi-physical simulation of Siemens S7-1500 series PLC (Siemens, Munich, Germany) and MATLAB R2018b (The MathWorks, Natick, Massachusetts, United States). Comparative studies show that when the same roll gap displacement step signal is given, the overshoot of the system response using the LWPSO algorithm is reduced by 14.26% and 10.18% compared with the Z-N algorithm and the PSO algorithm, and the peak time is advanced by 0.31 s and 0.05 s. The stabilization time is reduced by 3.71 s and 4.31 s, which effectively improves the control accuracy and speed of the system and has stronger anti-interference ability. It has certain engineering reference and application value.

Research on a Novel Combined Cooling and Power Scheme for LNG-Powered Ship

Cold energy recovery in LNG-powered vessels can not only improve the utilization efficiency of energy, but also benefit environmental protection. This paper put forward a new cascade scheme for utilizing flue gas waste heat and LNG cold energy comprehensively. The scheme was integrated by a dual organic Rankine circulation system (ORC), a high- and low-temperature cold storage system (TCS), an air conditioning system (ACS) and a seawater desalination system (SDS). The working medium of the dual ORC system was firstly determined by considering exergy efficiency and economic index simultaneously. On this basis, the adaptive weighted particle swarm optimization algorithm was employed to enhance thermodynamic performance of the scheme with the net output power as the optimization objective. The maximum net power and annual net interest rate can reach 725.78 kW and $115,300, respectively. Furthermore, the economic benefit of the scheme was analyzed by referring to the running track and the operation condition of the target ship. The results showed that the proposed scheme is a potential large-scale cryogenic technology and can bring considerable economic benefits to ship navigation.

An improved method of state of health prediction for lithium batteries considering different temperature

Due to the inaccurate extraction of battery aging characteristics, low accuracy of available capacity, and a large amount of training data, a data-driven algorithm is used to predict the functional capacity of Li-ion batteries. We propose a method to predict the health status of Li-ion batteries under different temperature conditions using health factor (HF) and weighted particle swarm optimization Gaussian process regression (WPSO-GPR) models. The health factor (HF) is extracted adaptively in the voltage and time profiles during the discharge stages for the HF extraction problem in different temperature predictions. A Gaussian process regression (GPR) model for SOH prediction is created for the capacity regeneration problem, with rational quadratic coefficients as the kernel function. An adaptive weight particle swarm algorithm is used to optimize the GPR model. The proposed framework for designing single-cell experiments on the cell data set is validated using two evaluation metrics: root mean square error (RMSE) and means absolute percentage error (MAPE). The results demonstrate that the proposed method has a short sample size, high prediction accuracy, and broad applicability.

Dynamic Parameter Identification of Collaborative Robot Based on WLS-RWPSO Algorithm

Parameter identification of the dynamic model of collaborative robots is the basis of the development of collaborative robot motion state control, path tracking, state monitoring, fault diagnosis, and fault tolerance systems, and is one of the core contents of collaborative robot research. Aiming at the identification of dynamic parameters of the collaborative robot, this paper proposes an identification algorithm based on weighted least squares and random weighted particle swarm optimization (WLS-RWPSO). Firstly, the dynamics mathematical model of the robot is established using the Lagrangian method, the dynamic parameters of the robot to be identified are determined, and the linear form of the dynamics model of the robot is derived taking into account the joint friction characteristics. Secondly, the weighted least squares method is used to obtain the initial solution of the parameters to be identified. Based on the traditional particle swarm optimization algorithm, a random weight particle swarm optimization algorithm is proposed for the local optimal problem to identify the dynamic parameters of the robot. Thirdly, the fifth-order Fourier series is designed as the excitation trajectory, and the original data collected by the sensor are denoised and smoothed by the Kalman filter algorithm. Finally, the experimental verification on a six-degree-of-freedom collaborative robot proves that the predicted torque obtained by the identification algorithm in this paper has a high degree of matching with the measured torque, and the established model can reflect the dynamic characteristics of the robot, effectively improving the identification accuracy.

Kinematics optimization of a novel 7-DOF redundant manipulator

Redundant manipulators can accomplish complex tasks due to the redundant degree of freedom (DOF). At the same time, their kinematics calculations are complicated. In this study, the kinematics solution for a self-designed 7-DOF redundant anthropomorphic manipulator is obtained, and an optimization method is provided to optimize the motion time of the manipulator in the same trajectory. Kinematics analysis of the spherical parallel shoulder joint was performed by using a geometric method and coordinate transformation. Kinematics analysis of the redundant manipulator was performed by a geometric method with an optimizing arm angle. Linearly decreasing weight particle swarm optimization (LDWPSO) was used to optimize the arm angle to minimize the motion time of the manipulator. The kinematics calculation of the shoulder joint was verified by a combination of SOLIDWORKSTM and MATLABTM software. The kinematics calculation of the redundant manipulator was verified by MATLABTM. The linear, circular and 8-shaped motion trajectories were used to evaluate the proposed method in the simulation. The simulation results showed that the motion time with optimization of the arm angle was only 16%–30% of that without optimization. Furthermore, the proposed method was evaluated through real manipulator experiments, and the experimental results were similar to those in the simulation.

Slope stability prediction based on adaptive CE factor quantum behaved particle swarm optimization-least-square support vector machine

Since the prediction of slope stability is affected by the combination of geological and engineering factors with uncertainties such as randomness, vagueness and variability, the traditional qualitative and quantitative analysis cannot match the recent requirements to judge them accurately. In this study, we expect that the adaptive CE factor quantum behaved particle swarm optimization (ACE-QPSO) and least-square support vector machine (LSSVM) can improve the prediction accuracy of slope stability. To ensure the global search capability of the algorithm, we introduced three classical benchmark functions to test the performance of ACE-QPSO, quantum behaved particle swarm optimization (QPSO), and the adaptive dynamic inertia weight particle swarm optimization (IPSO). The results show that the ACE-QPSO algorithm has a better global search capability. In order to evaluate the stability of the slope, we followed the actual project and research literature and selected the unit weight, slope angle, height, internal cohesion, internal friction angle and pore water pressure as the main indicators. To determine whether the algorithm is scientifically and practically feasible for slope deformation prediction, the ACE-QPSO-, QPSO-, IPSO-LSSVM and single least-square support vector machine algorithms were trained and tested based on a real case of slope project with six index factors as the input layer of the LSSVM model and the safety factor as the output layer of the model. The results show that the ACE-QPSO-LSSVM algorithm has a better model fit (R2=0.8030), minor prediction error (mean absolute error=0.0825, mean square error=0.0110) and faster convergence (second iteration), which support that the ACE-QPSO-LSSVM algorithm emthod is more feasible and efficient in predicting slope stability.

An improved dynamic weighted particle swarm optimization (IDW-PSO) for continuous optimization problem

An improved dynamic weighted particle swarm optimization (IDW-PSO) for continuous optimization problem

Detection of Breast Cancer Based on Feature Extraction Using WPSO in Conjunction with CNN

According to cancer reports from the past few years in India, thirty percent of instances are breast cancer, and furthermore, it is possible that this percentage would increase in the near future. In addition, one woman is given a diagnosis every two minutes, and another woman passes away every nine minutes as a result of her condition. People who are diagnosed with cancer at an earlier stage have a better chance of survival. Micro calcifications are one of the most important symptoms to look out for when trying to diagnose breast cancer in its earlier stages. Several scientific investigations have been carried out in an effort to combat this illness, for which techniques related to machine learning can be utilized to a significant extent. Particle swarm optimization, often known as PSO, is acknowledged as one of several effective and promising methods for identifying breast cancer. This method helps medical professionals administer treatment that is both timely and appropriate. The weighted particle swarm optimization (WPSO) approach is utilized in this work for the purpose of extracting textural information from the segmented mammography picture for the purpose of classifying micro calcifications as normal, benign, or malignant, hence increasing the accuracy. A portion of the cancerous growth is removed from the breast region using optimizing techniques. In this article, Convolutional Neural Networks (CNNs) are presented for the purpose of identifying breast cancer in order to cut down on the amount of manual overhead. The CNN framework is built in order to extract features as effectively as possible. This algorithm was developed to identify areas in mammograms (MG) that are suspicious for cancer and to classify those areas as normal or abnormal as quickly as possible. This model makes use of MG pictures that were gathered from a variety of hospitals in the surrounding area.

Low-Carbon Cold-Chain Logistics Path Optimization Problem Considering the Influence of Road Impedance

An improved road impedance function in conformity with Chinese city road traffic is designed for calculating the actual transportation time based on real-time traffic information and the complex road environment in the city. The objective function minimizes the total distribution cost, including fixed cost, transportation cost, damage cost, energy cost, penalty cost, and carbon emission cost. A mathematical model is constructed for cold-chain logistics distribution path optimization considering the influence of road impedance. The model is solved using three particle swarm optimization algorithms with improved weights. The experimental results show that the self-adaptive weighted particle swarm optimization algorithm is more efficient in solving this model. Experimental results obtained from the cold-chain logistics path optimization model considering road impedance compared to those of the model without road impedance indicate that the former are closer to the actual situation. Based on the changes in carbon emission and total cost under different carbon taxes, we analyze the critical carbon tax value and the optimal carbon tax value range to improve the economic and environmental benefits in the distribution process. This study should prove to be of great practical significance and application value for logistics enterprises to conduct rational planning of path problems.

Analysis and improvement of the uniformity of magnetic field coil based on the cylindrical magnetic shield in atomic magnetometers

The magnetic field performance of the uniform coils will be affected by magnetic shields and produce errors in the atomic magnetometer. It is necessary to analyze the influencing factors and guide the coil design. Aiming at the above shortcomings, this paper analyzes the coupling effect of magnetic shield and coil and proposed a Lee-Whiting coil design method based on the linearly decreasing inertia weight particle swarm optimization (LDW-PSO) algorithm. Firstly, the magnetic field model under the ferromagnetic boundary is established, and the effects of the size, thickness and permeability of the magnetic shield on the magnitude and uniformity of the Lee-Whiting coil magnetic field are analyzed. The results show that the coupling coefficient of the coil changes monotonically with the change of the size of the magnetic shield, while the uniformity error has a minimum value with the change of the size of the shield. In addition, an improved Lee-Whiting coil is designed by combining the LDW-PSO algorithm, which improves the uniformity of the coil. Compared with the original coil, the measured uniformity error of the improved coil is reduced from 8.39 × 1 0 − 4 to 2.81 × 1 0 − 4 . The accuracy of the theoretical analysis is verified by experiments. This paper is of great significance to study the coupling and optimization design of the coil based on the magnetic shields in atomic magnetometers. • The influence of magnetic shield parameters on coil uniformity is analyzed. • The optimal coil size for the uniformity in magnetic shield is given by analysis and testing. • The improved Lee-Whiting coil is designed by intelligent optimization algorithm. • Improved Lee-Whiting coil overcomes the coupling effect between coil and magnetic shield. • The correctness of the analysis and the effectiveness of the design are proved by experiments.

An improved algorithm for resolving overlapping peaks in ion mobility spectrometry and its application to the separation of glycan isomers.

Despite the popularity of ion mobility spectrometry (IMS) for glycan analysis, its limited structural resolution hinders the effective separation of many glycan isomers. This leads to the overlap of IMS peaks, consequently impacting the accurate identification of glycan compositions. To this end, an improved algorithm, namely second-order differentiation combined with a simulated annealing particle swarm optimization algorithm based on sine adaptive weights (DWSA-PSO), was proposed for the separation of overlapping IMS peaks formed by glycan isomers. DWSA-PSO first performed second-order differentiation to automatically determine the number of components in overlapping peaks and exclude impossible single-peak combinations. It then introduced sinusoidal adaptive weights and a simulated annealing mechanism to improve the algorithm's search capability and global optimization performance, thereby enabling accurate and efficient separation of individual peaks. To evaluate the performance of DWSA-PSO and its application to the separation of glycan isomers, multiple sets of overlapping peaks with different degrees of overlap were simulated, and various types of multi-component overlapping peaks were formed using six disaccharide and four trisaccharide isomers. The experimental results consistently demonstrated that the DWSA-PSO algorithm outperformed both the improved particle swarm optimization (IPSO) algorithm and the dynamic inertia weight particle swarm optimization (DIWPSO) algorithm in terms of separation accuracy, running time, and fitness values. In addition, the DWSA-PSO algorithm was successfully applied to the separation of glycan isomers in malt milk beverage. All these results reveal the capability of the DWSA-PSO algorithm to facilitate the accurate identification of glycan isomers.

A novel deep learning-based forecasting model optimized by heuristic algorithm for energy management of microgrid

Recently, the integration of renewable energy sources (RESs) in microgrids (MGs) has risen significantly owing to extensive promotion of decarbonization and green energy. However, despite the environmental–economic benefits, RESs are intermittent, and increasing penetration of RESs into MG poses operation challenges in handling uncertainties. In this paper, a novel deep learning-based forecasting model is proposed for MG operation considering uncertainties of RESs, load, and day-ahead price (DAP). To handle the intrinsic uncertainties of MGs, a long short-term memory (LSTM) network is employed and a method for increasing prediction accuracy of the LSTM model based on a genetic algorithm–adaptive weight particle swarm optimization (GA-AWPSO) combination along with a global attention mechanism (GAM) is proposed. Herein, the hyperparameters of the LSTM model are optimized by the GA-AWPSO algorithm, and GAM is added to mine important features from input datasets to improve forecasting performance. To handle uncertainties through the demand side, A DM-CIDR program is developed for providing optimal incentive rate strategies to participants, as different customers exhibit diverse attitudes toward remunerated incentives. In this program, ordering points to identify the clustering structure (OPTICS) and k-nearest neighbor algorithms (k-NN) are used for clustering and classification, respectively, to determine reasonable incentive rates for customers according to their bid/offer data. A simulation was implemented on historical PJM datasets, the results of which revealed the performance and superiority of the proposed approach in handling uncertainties.

Two-step particle swarm optimization algorithm for effective deconvolution and resolution enhancement of various overlapping peaks.

The existing particle swarm optimization (PSO) algorithms are only effective in deconvoluting the overlapping peaks in ion mobility spectra with fewer than four component peaks, which limits the applicability of these algorithms. A high-performance two-step particle swarm optimization (TSPSO) algorithm was developed. Compared to the existing PSO algorithms, TSPSO can narrow the search ranges of all coefficients for the overlapping peaks through Gaussian model calculation, and thus can deconvolute various overlapping peaks with high accuracy, even for 30-component overlapping peaks. In addition, the TSPSO could be further applied to enhance the resolution of the spectra by narrowing the peak widths after the peak deconvolution. Simulated overlapping peaks were first used to evaluate the performance of TSPSO as compared to the dynamic inertia weight particle swarm optimization (DIWPSO) algorithm. The results showed that the profiles of the peaks deconvoluted by using TSPSO were more consistent with the original ones. The fitness values and the standard deviations of the fitness values from TSPSO were also at least an order of magnitude less than those from DIWPSO. By applying TSPSO, the overlapping peaks from both mass spectrometry (MS) and field asymmetric waveform ion mobility spectrometry (FAIMS) spectra can also be well deconvoluted. In addition, the resolutions of the MS and FAIMS spectra can be effectively enhanced after peak deconvolution. The enhanced spectra matched excellently with the experimental ones acquired at high-resolution modes. The experiment results convincingly demonstrate that the TSPSO algorithm is capable of both deconvoluting complex overlapping peaks and enhancing the spectrum resolution with high accuracy.

Research on Fault Early Warning of Wind Turbine Based on IPSO-DBN

Aiming at the problem of wind turbine generator fault early warning, a wind turbine fault early warning method based on nonlinear decreasing inertia weight and exponential change learning factor particle swarm optimization is proposed to optimize the deep belief network (DBN). With the data of wind farm supervisory control and data acquisition (SCADA) as input, the weights and biases of the network are pre-trained layer by layer. Then the BP neural network is used to fine-tune the parameters of the whole network. The improved particle swarm optimization algorithm (IPSO) is used to determine the number of neurons in the hidden layer of the model, pre-training learning rate, reverse fine-tuning learning rate, pre-training times and reverse fine-tuning training times and other parameters, and the DBN predictive regression model is established. The experimental results show that the proposed model has better performance in accuracy, training time and nonlinear fitting ability than the DBN model and PSO-DBN model.

Multilevel Thresholding Image Segmentation Based-Logarithm Decreasing Inertia Weight Particle Swarm Optimization

Abstract The image segmentatation technique that is often used is thresholding. Image segmentation is a process of dividing the image into different regions according to their similar characteristics. This research proposes a multilevel thresholding algorithm using modified particle swarm optimization to solve a segmentation problem. The threshold optimal values are determined by maximizing Otsu’s objective function using optimization technique namely particle swarm optimization based on the logarithmic decreasing inertia weight (LogDIWPSO). The proposed method reduces the computational time to find the optimum thresholds of multilevel thresholding which evaluated on several grayscale images. A detailed comparison analysis with other multilevel thresholding based techniques namely particle swarm optimization (PSO), iterative particle swarm optimization (IPSO), and genetic algorithms (GA), From the experiments, Modified particle swarm optimization (MoPSO) produces better performance compared to the other methods in terms of fitness value, robustness and convergence. Therefore, it can be concluded that MoPSO is a good approach in finding the optimal threshold value. Keywords: grayscale image, inertia weight, image segmentation, particle swarm optimization.

Effects of Dynamic IMU-to-Segment Misalignment Error on 3-DOF Knee Angle Estimation in Walking and Running.

The inertial measurement unit (IMU)-to-segment (I2S) alignment is an important part of IMU-based joint angle estimation, and the accurate estimation of the three degree of freedom (3-DOF) knee angle can provide practical support for the evaluation of motions. In this paper, we introduce a dynamic weight particle swarm optimization (DPSO) algorithm with crossover factor based on the joint constraint to obtain the dynamic alignment vectors of I2S, and use them to perform the quaternion-based 3-DOF knee angle estimation algorithm. The optimization algorithm and the joint angle estimation algorithm were evaluated by comparing with the optical motion capture system. The range of 3-DOF knee angle root mean square errors (RMSEs) is 1.6°-5.9° during different motions. Furthermore, we also set up experiments of human walking (3 km/h), jogging (6 km/h) and ordinary running (9 km/h) to investigate the effects of dynamic I2S misalignment errors on 3-DOF knee angle estimation during different motions by artificially adding errors to I2S alignment parameters. The results showed differences in the effects of I2S misalignment errors on the estimation of knee abduction, internal rotation and flexion, which indicate the differences in knee joint kinematics among different motions. The IMU to thigh misalignment error has the greatest effect on the estimation of knee internal rotation. The effect of IMU to thigh misalignment error on the estimation of knee abduction angle becomes smaller and then larger during the two processes of switching from walking to jogging and then speeding up to ordinary running. The effect of IMU to shank misalignment error on the estimation of knee flexion angle is numerically the largest, while the standard deviation (SD) is the smallest. This study can provide support for future research on the accuracy of 3-DOF knee angle estimation during different motions.

Deconvolution of overlapping peaks in ion mobility spectrometry based on a multiobjective dynamic teaching-learning-based optimization.

Because of its powerful analytical ability, ion mobility spectrometry (IMS) plays an important role in the field of mass spectrometry. However, one of the main defects of IMS is its low structural resolution, which leads to the phenomenon of peak overlap in the analysis of compounds with similar mass charge ratio. A multiobjective dynamic teaching-learning-based optimization (MDTLBO) method was proposed to separate IMS overlapping peaks. This method prevents local optimization and identifies peak model coefficients efficiently. In addition, the position information of particles largely reflects the half-peak width of IMS, which makes single peaks difficult to appear and coefficient identification easier. The performance comparison of MDTLBO with other deconvolution methods (genetic algorithm, improved particle swarm optimization algorithm, and dynamic inertia weight particle swarm optimization algorithm) shows that the maximum deconvolution error of MDTLBO is only 0.7%, which is much lower than that for the other three methods. In addition, robustness is a performance index that reflects the advantages and disadvantages of the algorithm. MBTLBO is more robust than other algorithms for separating overlapping peaks. The algorithm can separate the heavily overlapped mobility peaks, produce better analysis results, and improve the resolution of IMS.

Synthesis of sparse square arrays with high beam collection efficiency under minimum element spacing constraints

AbstractThis letter presents a large spacing nonuniform distribution, uniform excitation sparse square array model to maximize beam collection efficiency (BCE) and minimize sidelobe level outside the collection area (CSL) of the transmitting antenna in microwave wireless power transmission (MWPT) systems. We improve the position update parameters in the dynamic weight particle swarm optimization (DWPSO) algorithm by adding multiobjective learning features (MODWPSO). We use MODWPSO to optimize the elements' positions to maximize BCE and minimize CSL and discuss the effect of the minimum element spacing value on BCE and CSL. By comparing the array performance with a typical array model, it can be concluded that the proposed large spacing sparse nonuniform distribution, uniform excitation square array model has higher BCE, lower CSL, and fewer costs.

Artificial Intelligence-Based Breast Cancer Detection Using WPSO

To detect breast cancer in the early stages, microcalcifications are considered a key symptom. Several scientific investigations were performed to fight against this disease for which machine learning techniques can be extensively used. Particle swarm optimization (PSO) is recognized as one among several efficient and promising approach for diagnosing breast cancer by assisting medical experts for timely and apt treatment. This paper uses weighted particle swarm optimization (WPSO) approach for extracting textural features from the segmented mammogram image for classifying microcalcifications as normal, benign, or malignant, thereby improving the accuracy. In the breast region, tumor part is extracted using optimization methods. Here, artificial intelligence (AI) is proposed for detecting breast cancer, which reduces the manual overheads. AI framework is constructed for extracting features efficiently. This designed model detects the cancer regions in mammogram (MG) images and rapidly classifies those regions as normal or abnormal. This model uses MG images obtained from hospitals.