Particle Swarm Intelligence Algorithm Research Articles

Classification and evaluation for nearside/backside defect via magnetic flux leakage: A dual probe design with SVM and PSO intelligence algorithms

In automated magnetic flux leakage (MFL) applications, the defect location on the nearside/backside of the tested specimen is often unknown, posing challenges for evaluating defect parameters due to varying calibration relationships. To address this, we propose a combined scheme of defect classification followed by parameter evaluation for testing steel plates with nearside/backside defects. The innovative design of dual probes, featuring lift-off difference, is used for signal acquisition and analysis. An efficient defect classification is achieved through a PSO-SVM neural network, and defect parameter evaluation involves solving the inverse problem using a particle swarm intelligence algorithm. MFL signal from steel plates with circular hole defects of different sizes were tested using a self-developed system and dual probes. Finite element analysis, alongside experimental data, explores the change in MFL signal. Defect classification and parameter evaluation, based on experimental signals and simulations, confirm the effectiveness of scheme in quantitatively assessing defect parameters with an evaluation accuracy within 0.3 mm. This scheme serves as a reference for intelligent testing and evaluation using MFL signals.

A hybrid cloud load balancing and host utilization prediction method using deep learning and optimization techniques

Virtual machine (VM) integration methods have effectively proven an optimized load balancing in cloud data centers. The main challenge with VM integration methods is the trade-off among cost effectiveness, quality of service, performance, optimal resource utilization and compliance with service level agreement violations. Deep Learning methods are widely used in existing research on cloud load balancing. However, there is still a problem with acquiring noisy multilayered fluctuations in workload due to the limited resource-level provisioning. The long short-term memory (LSTM) model plays a vital role in the prediction of server load and workload provisioning. This research presents a hybrid model using deep learning with Particle Swarm Intelligence and Genetic Algorithm (“DPSO-GA”) for dynamic workload provisioning in cloud computing. The proposed model works in two phases. The first phase utilizes a hybrid PSO-GA approach to address the prediction challenge by combining the benefits of these two methods in fine-tuning the Hyperparameters. In the second phase, CNN-LSTM is utilized. Before using the CNN-LSTM approach to forecast the consumption of resources, a hybrid approach, PSO-GA, is used for training it. In the proposed framework, a one-dimensional CNN and LSTM are used to forecast the cloud resource utilization at various subsequent time steps. The LSTM module simulates temporal information that predicts the upcoming VM workload, while a CNN module extracts complicated distinguishing features gathered from VM workload statistics. The proposed model simultaneously integrates the resource utilization in a multi-resource utilization, which helps overcome the load balancing and over-provisioning issues. Comprehensive simulations are carried out utilizing the Google cluster traces benchmarks dataset to verify the efficiency of the proposed DPSO-GA technique in enhancing the distribution of resources and load balancing for the cloud. The proposed model achieves outstanding results in terms of better precision, accuracy and load allocation.

DSP‐based energy optimization management of household single‐phase electric energy router with historical and real‐time data

AbstractThe development and use of single‐phase electric energy router (SPEER) makes the household power system operate more reliably and bring economic income at the same time. This paper presents an economic energy optimization management method of SPEER with historical data of previous day and real‐time data in the grid‐connected mode of SPEER, which can be realized by DSP. First, based on the exchange power between the SPEER and the grid, the optimal charging and discharging power of the battery to make up for the energy difference between the previous day and the real time is obtained through the particle swarm intelligence algorithm, and the optimal economic model of SPEER operation is established. Then, on the hardware experimental platform, DSP is used to realize the real‐time optimization, and the optimal economic optimization algorithm proposed in this paper is implemented and verified on hardware experimental platform. The contradiction between the complexity of optimization algorithm and the limitation of hardware resources is solved in the proposed energy management system.

Predicting the deformation behaviour of concrete face rockfill dams by combining support vector machine and AdaBoost ensemble algorithm

The accurate evaluation of deformation behaviour is very important to the optimal design and safety evaluation of concrete face rockfill dams (CFRDs). Deformation prediction is a key problem in the CFRD construction. Based on statistical review of typical deformation behaviour of 94 CFRD cases, the relationship amongst three typical deformation indexes and six influencing factors of CFRDs is analysed using multiple linear regression method. The main influencing factors of the dam behaviour are discussed. An improved support vector machine (SVM) dam deformation prediction model is proposed based on the construction of an adaptive hybrid kernel function. The particle swarm intelligent optimisation algorithm is used to determine the main parameters. To solve the problem of nonlinear mutation and discreteness of case data, the SVM-AdaBoost prediction model of typical deformation indexes is established by iterative optimisation of the basic learner composed of the improved SVM model through the AdaBoost strategy. The comparative analysis of the proposed model and existing models shows that the proposed model has good prediction accuracy and can be used to predict the typical deformation behaviour of CFRDs accurately.

Security-constrained hybrid optimal energy flow model of multi-energy system considering N-1 component failure

The analysis and calculation of hybrid energy flow is the basis of planning, operation and market transaction of multi-energy systems. An optimal energy flow model of multi-energy systems considering N-1 component failure is proposed in this paper. The compressor and gas storage devices are modeled in the hybrid optimal energy flow model. The particle swarm intelligent optimization algorithm is used to solve this non-convex and non-linear optimization model. Case studies demonstrate the coupled and complementary operation of multi-energy systems can reduce the total operation cost by 8 % as compared to independent operation model. The hybrid optimal energy flow (HOEF) model of multi-energy systems with N-1 component failure can improve the robustness of HOEF results.

Modeling and optimization of hybrid renewable energy with storage system using flamingo swarm intelligence algorithms

AbstractThis paper unveils the simulation and optimum design of five models based on photovoltaic (PV), diesel generator (DG), and battery energy systems for rural area farmhouse load demand (agriculture and household). The choice for designing an optimal energy system is constructed on minimum technical considerations like loss of load probability (LOLP), economic (cost of electricity [COE] with net present cost [NPC]), environmental (CO2 aspects) using a novel flamingo swarm intelligence algorithm (FSIA). The optimization results are compared by particle swarm intelligence algorithm, improved particle swarm intelligence algorithm, genetic algorithms, and hybrid optimization of multiple energy resources (HOMER‐Pro). FSIA shows PV/DG/battery energy system to be an optimal system as regards NPC (Rs. 8 056 734), COE (12.14 Rs./kWh), CO2 (13 784 kg/y), and LOLP (0.00000501 per year). The saving of the fuel cost and CO2 emission from PV/DG/battery to DG only system is 66.10% and 61.26%, respectively.

Design of a Learning Path Recommendation System Based on a Knowledge Graph

Current learning platforms generally have problems such as fragmented knowledge, redundant information, and chaotic learning routes, which cannot meet learners' autonomous learning requirements. This paper designs a learning path recommendation system based on knowledge graphs by using the characteristics of knowledge graphs to structurally represent subject knowledge. The system uses the node centrality and node weight to expand the knowledge graph system, which can better express the structural relationship among knowledge. It applies the particle swarm fusion algorithm of multiple rounds of iterative simulated annealing to achieve the recommendation of learning paths. Furthermore, the system feeds back the students' learning situation to the teachers. Teachers check and fill in the gaps according to the performance of the learners in the teaching activities. Aiming at the weak links of students' knowledge points, the particle swarm intelligence algorithm is used to recommend learning paths and learning resources to fill in the gaps in a targeted manner.

Automated Knowledge Extraction of Liver Cysts From CT Images Using Modified Whale Optimization and Fuzzy C Means Clustering Algorithm

In this study, the integrated modified whale optimization and modified fuzzy c-means clustering algorithm using morphological operations are developed and implemented for appropriate knowledge extraction of a cyst from computer tomography (CT) images of the liver to facilitate modern intelligent healthcare systems. The proposed approach plays an efficient role in diagnosing the liver cyst. To evaluate the efficiency, the outcomes of the proposed approach have been compared with the minimum cross entropy based modified whale optimization algorithm (MCE and MWOA), teaching-learning optimization algorithm based upon minimum cross entropy (MCE and TLBO), particle swarm intelligence algorithm (PSO), genetic algorithm (GA), differential evolution (DE) algorithm, and k-means clustering algorithm. For this, various parameters such as uniformity (U), mean structured similarity index (MSSIM), structured similarity index (SSIM), random index (RI), and peak signal-to-noise ratio (PSNR) have been considered. The experimental results show that the proposed approach is more efficient and accurate than others.

A Study on Early Warnings of Financial Crisis of Chinese Listed Companies Based on DEA–SVM Model

In the era of big data, investor sentiment will have an impact on personal decision making and asset pricing in the securities market. This paper uses the Easteconomy stock forum and Sina stock forum as the carrier of investor sentiment to measure the positive sentiment index based on stockholders’ comments and to construct an evaluation index system for the public opinion dimension. In addition, the evaluation index system is constructed from four dimensions, which include operation, innovation, finance and financing, to evaluate the overall condition of listed companies from multiple perspectives. In this paper, the SBM model in the data envelopment analysis method is used to measure the efficiency values of each dimension of the multidimensional efficiency evaluation index system, and the efficiency values of each dimension are the multidimensional efficiency indicators. Subsequently, two sets of input feature indicators of the SVM model were established: one set contains traditional financial indicators and multidimensional efficiency indicators, and another set has only traditional financial indicators. The early warning accuracy of the two sets of input feature indicators was empirically analyzed based on the support vector machine early warning model. The results show that the early warning model incorporating multidimensional efficiency indicators has improved the accuracy compared with the early warning model based on traditional financial indicators. Then, the model was optimized by the particle swarm intelligent optimization algorithm, and the robustness of the results was tested. Moreover, six mainstream machine learning methods, including Logistic Regression, GBDT, CatBoost, AdaBoost, Random Forest and Bagging, were used to compare with the early warning effect of the DEA–SVM model, and the empirical results show that DEA–SVM has high early warning accuracy, which proves the superiority of the proposed model. The findings of this study have a positive effect on further preventing and controlling the financial crisis risk of Chinese-listed companies and promoting as well as facilitating the healthy growth of Chinese-listed companies.

Towards energy efficient Smart city services: A software defined resource management scheme for data centers

With the rapid advancements in the services computing paradigm, cloud computing has been a fundamental requirement for enabling practically all sophisticated applications and services, particularly for Smart cities. However curbincs energy dissipation in the data centers (DC) has been a key effort, albeit while fulfilling the quality of service (QoS) requirement of DCs are characterized by complex interconnections among their servers. Maintenance of these servers under dynamic scenarios while ensuring scalability and performance demands Software Defined Networks (SDNs) for easy and efficient resource management. This paper addresses the QoS requirement and energy-efficient operation for Software-Defined DCs for resource management by means of (i) selectively activating a subset of switches, (ii) propounding multi-path routing for all scheduled flows, (iii) aggregating data and routing structure to avoid network congestion and (iv) installation of appropriate forwarding rules across the network switches. These issues are collectively put together in the outline of ILP problem, but due to its computational complexity, a heuristic optimization approach called particle swarm intelligence is articulated. The particle swarm intelligence (PSI) algorithm is employed for feature selection to obtain the minimum cost of the generated energy while satisfying the network traffic demand. The presented simulation result lay the efficacy of the proposed algorithm.

Research on the Combination of Firefly Intelligent Algorithm and Asphalt Material Modulus Back Calculation.

The modulus of asphalt pavement material is a necessary parameter for the design, strength measuring and stability evaluation of asphalt pavement. To get more precise test data for asphalt pavement material modulus, a new modulus back calculation method is proposed in this article, named as the Firefly Asphalt Back Calculation Method (FABCM). This novel method uses the firefly optimization algorithm, which is a kind of particle swarm intelligence algorithm imitating the information transfer process among fireflies. To demonstrate the reliability and stability of FABCM, and to study the feasibility of multi-parameter modulus back calculation methods, this article used theoretical deflection curves calculated by BISAR3.0 and the actual measurement data of deflection curves and vertical pressures on the subgrade top surfaces on the full-scale test circular track in the Research Institute of Highway, Ministry of Transport (RIOHTrack) to conduct a modulus back calculation. The results show that FABCM only takes 0.5–1 s for each calculation, and the back calculation errors in the verification of FABCM are mostly smaller than 1%, which means that the firefly optimization algorithm was modified effectively in this article. Moreover, this article also indicates some key factors influencing the accuracy of modulus back calculation, and several reasonable suggestions to the application of modulus back calculation.

Multi-robot co-operation for stick carrying application using hybridization of meta-heuristic algorithm

The paper offers a novel technique for resolving the multi-robot cooperation for stick carrying applications. The problem addresses the computation of a collision-free optimal path from a predefined initial position to target position during transportation of stick or object cooperatively by robot pair in the multi-robot environment. The stick carrying application has been resolved by embedding the modified Q-learning into the hybrid process of an improved version of particle swarm optimization and intelligent water drop algorithm. In the present context, modified Q-learning generates the best solution for particle swarm optimization and particle swarm optimization is upgraded through the perception of cubic spline and generate the optimal position in the successive iteration using intelligent water drop algorithm and also enhances the intensification and diversification capability of particle swarm optimization. The proposed hybrid algorithm computes the collision-free subsequent position for each robot pair by avoiding the obstacles in its path, avoiding the trapping at the local optima, improving the convergence speed, optimizing the path distance for every pair of robots, energy usage and path smoothness both in the static and dynamic environment’s. The validation of the proposed hybrid algorithm has been verified and checked the robustness of the algorithm through computer simulation and real robots through Webots simulator. Further, the efficiency of the proposed algorithm has been verified by comparing the result obtained proposed algorithm and its competitor algorithms and comparing the result of the proposed algorithm with the existing state-of arts. The comparison result shows that the proposed algorithm is superior to its competitor algorithms and state of arts for different matrices.

Pelvic Floor Ultrasound under Particle Swarm Intelligent Optimization Algorithm in Preoperative and Postoperative Evaluation of Female Stress Urinary Incontinence

This study aimed to explore the application of pelvic floor ultrasound under particle swarm intelligent optimization algorithm in the preoperative and postoperative evaluation of female stress urinary incontinence (SUI) and provide a theoretical basis for clinical diagnosis. In this study, 90 patients with SUI were enrolled, which were randomly and equally assigned into a blank group (healthy physical examination), control group (perineal ultrasound), and experimental group (pelvic floor ultrasound based on particle swarm intelligence optimization algorithm). The ultrasonic image segmentation and processing were carried out by a particle swarm intelligence optimization algorithm. Patients with stress incontinence were classified as group A, and patients without stress incontinence were classified as group B. The results of previous surgical examinations were the standard to judge the accuracy of pelvic floor ultrasound diagnosis based on the swarm intelligence optimization algorithm. The accuracy of diagnosing stress UI in the experimental group was 90.38%, which was significantly higher than that of the control group (54.31%) and the blank group (38.95%) ( P < 0.05). The formation percentage of the urethral internal orifice in the experimental group was 82.5%, which was significantly higher than that of the control group (65.4%) and the blank group (12.5%), and there was a statistical difference among the groups ( P < 0.05). In the resting state, the vertical spacing y between the neck of the bladder and the edge of the pubis of patients in group B was greater than that in group B, the horizontal spacing x between the neck of the bladder and the edge of the pubis was smaller than in the blank group, and there were statistical differences among the groups ( P < 0.05). In the state of Valsalva, the vertical spacing y between the neck of the bladder and the edge of the pubis of patients in group B was smaller than that in group B, the horizontal spacing x between the neck of the bladder and the edge of the pubis was greater than that in group B. The distance of the bladder neck shifting downward was greater than that in group B, and there were statistical differences among the groups ( P < 0.05). In short, the pelvic floor ultrasound based on the particle swarm intelligent optimization algorithm was accurate in the diagnosis of stress UI. The application of pelvic floor ultrasound in the diagnosis of UI provided image data objectively for clinical diagnosis and had a high application value.

A method of workpiece location based on improved generalized Hough transform

In order to solve the problem that the workpiece is not easy to identify in the complex environment in the industrial processing, sorting and other automatic production links, a workpiece positioning method based on Improved Generalized Hough transform, also known as eif-ght, is proposed. In order to solve the problem of large time consumption and high memory consumption of traditional generalized Hough transform in target detection, this paper uses the rotation invariant feature angle formed by any two edge points in the image as the R table index under the condition of image preprocessing to realize the representation of target shape, and uses particle swarm intelligent evolutionary algorithm to speed up the search The final target is determined by similarity measurement. The experimental results show that when the workpiece rotates and shifts, and in the complex environment with noise, local occlusion, nonlinear illumination and so on, it can achieve stable and efficient positioning.

Unscented Particle Filter Algorithm Based on Divide-and-Conquer Sampling for Target Tracking

Unscented particle filter (UPF) struggles to completely cover the target state space when handling the maneuvering target tracing problem, and the tracking performance can be affected by the low sample diversity and algorithm redundancy. In order to solve this problem, the method of divide-and-conquer sampling is applied to the UPF tracking algorithm. By decomposing the state space, the descending dimension processing of the target maneuver is realized. When dealing with the maneuvering target, particles are sampled separately in each subspace, which directly prevents particles from degeneracy. Experiments and a comparative analysis were carried out to comprehensively analyze the performance of the divide-and-conquer sampling unscented particle filter (DCS-UPF). The simulation result demonstrates that the proposed algorithm can improve the diversity of particles and obtain higher tracking accuracy in less time than the particle swarm algorithm and intelligent adaptive filtering algorithm. This algorithm can be used in complex maneuvering conditions.

Managing pharmaceuticals delivery service using a hybrid particle swarm intelligence approach

Medicines or drugs have unique characteristics of short life cycle, small size, light weight, restrictive distribution time and the need of temperature and humidity control (selected items only). Thus, logistics companies often use different types of vehicles with different carrying capacities, and considering fixed and variable costs in service delivery, which make the vehicle assignment and route optimization more complicated. In this study, we formulate the problem to a multi-type vehicle assignment and mixed integer programming route optimization model with fixed fleet size under the constraints of distribution time and carrying capacity. Given non-deterministic polynomial hard and optimal algorithm can only be used to solve small-size problem, a hybrid particle swarm intelligence (PSI) heuristic approach, which adopts the crossover and mutation operators from genetic algorithm and 2-opt local search strategy, is proposed to solve the problem. We also adapt a principle based on cost network and Dijkstra’s algorithm for vehicle scheduling to balance the distribution time limit and the high loading rate. We verify the relative performance of the proposed method against several known optimal or heuristic solutions using a standard data set for heterogeneous fleet vehicle routing problem. Additionally, we compare the relative performance of our proposed Hybrid PSI algorithm with two intelligent-based algorithms, Hybrid Population Heuristic algorithm and Improved Genetic Algorithm, using a real-world data set to illustrate the practical and validity of the model and algorithm.

A Novel Incipient Fault Diagnosis Method for Analog Circuits Based on GMKL-SVM and Wavelet Fusion Features

To enhance the reliability of analog circuits in complex electrical systems, a novel incipient fault diagnosis method is presented in this article. The wavelet packet feature quantities, which consist of the energy, fluctuation coefficient, skewness, and margin factor, are obtained via multiscale time-frequency analysis with wavelet packet transform (WPT). Then, generalized discriminant analysis (GDA) is employed to realize the fusion of wavelet packet feature quantities because it can handle the data nonlinearity and eliminate redundant information. Furthermore, the generalized multiple kernel learning support vector machine (GMKL-SVM), which has the advantages of a strong generalization ability and high accuracy, is developed to identify the incipient fault classes of analog circuits. Moreover, a new particle swarm intelligent optimization algorithm, the sine cosine algorithm (SCA), is adopted to optimize key parameters of GMKL-SVM because of its high convergence speed and strong global optimization ability. The method is fully evaluated with the Sallen-Key bandpass filter circuit, the four-op-amp biquad high-pass filter circuit, and the leapfrog filter circuit. The experimental results demonstrate that the proposed incipient fault diagnosis method for analog circuits can produce higher diagnosis accuracy than other typical incipient fault diagnosis methods.

Integrated kitchen design and optimization based on the improved particle swarm intelligent algorithm

AbstractThe layout and design of the integrated kitchen can affect the efficiency of people's cooking work greatly. An excellent integrated kitchen design requires each kitchen cabinet module to meet certain constraints and reach the highest work efficiency in a certain space. In this article, we proposed an improved particle swarm intelligence algorithm (IPSO, for short) method by initializing the population chaos, dynamically improving the inertia weight and adjusting the acceleration factor, and applied in the kitchen design and optimization. This method combines the mathematical intelligent algorithm with the integrated kitchen design for the first time, and further selects the optimal design scheme from the preliminary schemes according to the fitness curve of the kitchen mathematical model, which provides the theoretical basis for the refined design of kitchen products. The method can also be used in home design, interior design, and other related areas.

Study on Optimization of Coal Truck Flow in Open‐Pit Mine

A semicontinuous process system consisting of a single‐bucket excavator, truck, crushing station, and belt conveyor is the main coal mining process system of a large‐scale hard coal open‐pit mine. Through analyzing the coal mining production process, the key issues of coal mining truck flow optimization are obtained. Statistical method of using triangular fuzzy numbers analyzes the key time parameters of coal mining truck flow. Taking one shift, the minimum expected value of number of trucks, as the objective function, the fuzzy expectation of the coal mining semicontinuous process system is established with the constraints of the truck flow continuity at the loading and unloading point, the production capacity of the electric shovel, the production capacity of the crushing station, coal quality, and coal mining production tasks. The truck flow planning model is solved using particle swarm intelligence algorithm. The simulation results show that the result of truck flow planning can effectively reduce truck number, truck dispatching number, transportation costs, and truck queuing. The fuzzy expected truck flow planning model established by the study is suitable for solving the problem of optimizing and matching the production capacity in the process which links electric shovel, truck, and crushing station. It can effectively improve the production efficiency of electric shovel mining, truck transportation, and crushing station.

Optimization of A Five-Echelon Supply Chain Network using Particle Swarm Intelligence Algorithms

Technology has shrunk the global markets and information is accessible very quickly and effortlessly. Business organizations world over concentrate on their production systems to improve the quality of the end product, well distribute the product and optimize cost of resources. Transportation cost, inventory carrying cost and shortage costs constitute the major costs in cost of distribution. A competent supply chain always strives to manufacture the right quantity of end products and hold a minimum inventory across the entire supply chain. In thecurrent paper, a five echelon supply chain model is developed and it is optimized using particle swarm intelligence algorithm.