Particle swarm optimization with oscillating parameter strategy

A novel oscillating parameter strategy (OPS) is proposed for the particle swarm optimization algorithm to improve its performance after a predefined number of generations.To efficiently control the local search and convergence to the global optimum solution, the OPS method alternates exploration and exploitation many times during the whole optimization course.For implementing the alternative of exploration and exploitation, the inertia weight and acceleration coefficients are oscillated during the search process.The oscillating inertia weight and acceleration coefficients can enhance the global search in the early part and not fall into premature status.This also encourages the particle to converge toward the global optima at the end of the search.Empirical simulations showed that the OPS method outperformed all the methods considered in this investigation for most of the functions.     

罗非鱼池塘养殖溶解氧预测研究

为及时有效地掌握池塘养殖中溶解氧浓度的变化趋势,保障罗非鱼稳定高效养殖,在对罗非鱼池塘养殖实际情况进行研究和分析的基础上,采用粒子群算法对BP神经网络模型进行参数优化,针对无锡市2015 年8 月23—11 月4 日这段时间内南泉实验基地的水产养殖溶解氧进行预测。同时,将粒子群优化BP神经网络模型与BP神经网络模型的训练结果和预测结果进行对比。研究结果表明,PSO-BP优化模型的训练和预测结果远远优于普通BP神经网络模型,除异常点外,误差率基本均低于0.5%。同时,该模型收敛速度快,计算复杂性低,能够较好的体现和预测罗非鱼池塘养殖的溶解氧趋势,也为其他水质指标的预测提供了研究方向。     

改进的粒子群算法及在数值函数优化中应用

为提高粒子群算法的优化能力,提出了一种改进的粒子群优化算法。在该算法中,采用Beta分布初始化种群,采用逆不完全伽马函数更新惯性权重,在速度更新式中,引入了基于差分进化的新算子,对于粒子的越界处理,采用了基于边界对称映射的新方法。以50个不同类型的数值函数作为优化实例,基于威尔柯克斯符号秩检验的测试结果表明,该算法明显优于普通粒子群优化算法、差分进化算法、人工蜂群优化算法和量子行为粒子群算法。     

Beam pumping process modeling and parameters optimization based on generalized regression neural networks for energy conservation

This paper presents a data-mining-based beam pumping unit process modeling and parameters optimization method to solve the problem of inefficiency and energy-intensive of beam pumping unit. The ideality of process parameters is one of the main factors influencing system efficiency and energy consumption, while the effectiveness of mode plays a key role in process parameters choosing. Beam pumping unit system is a complicated nonlinear system, and is hardly to be precisely described by precise mathematical models. Generalized regression neural network (GRNN), which is powerful in nonlinear mapping and generalization, is suitable for nonlinear systems. Therefore, GRNN is proposed to model the beam pumping unit in this paper, and the experimental results show that the fitness is good. Then the trained model is applied to optimize the decision parameters by vector evaluated particle swarm optimization based on Pareto (VEPSO-BP), and at last the resulting parameters are applied to the production. Experimental results show that after using the optimal parameters, the efficiencies and energy consumptions increase more than 6.6% and decrease more than 4.1% respectively, which illustrates the feasibility and effectiveness of the proposed method.     

SA-PSO算法在CNN边缘提取模板设计中的应用

提出了一种用于边缘提取的细胞神经网络（CNN）模板的设计方法,该方法在基本粒子群算法的基础上引入模拟退火机制,形成模拟退火粒子群算法（SA-PSO）对模板参数值进行搜寻。在搜索过程中,用退火温度调节粒子的突跳概率,轮盘赌策略确定粒子的全局最优的替代值,这样能有效避免基本PSO算法容易陷入局部最优解的问题。同时,为了保证每轮搜寻产生的解均能使CNN网络稳定,用CNN反馈模板的研究结论对粒子群解空间进行约束。模拟实验表明,文章算法设计出的CNN模板有良好的边缘提取能力。     

Cotton Image Segmentation Algorithm Based on Fusion Method of Markov Random Field and Quantum Particle Swarm Cluster

[Objective] The aim of this study was to improve the cotton image segmentation accuracy in a picking robot image processing system. [Method] An image segmentation algorithm based on a fusion method of Markov random field and quantum particle swarm optimization clustering was proposed. The process of the proposed algorithm is as follows: first, transform the RGB (red, green, blue) images into grayscale; second, use it to segment these images; finally, the threshold of the connected area is set on the basis of the segmented image to obtain the target area. Then, the cotton front image and the cotton side image are selected from the images collected from different angles. The segmentation experiment was carried out by using this algorithm, and compared with the Otsu algorithm, the fuzzy C-means algorithm, the quantum particle swarm image segmentation algorithm and the Markov random field image segmentation algorithm. [Result] The results showed that the segmentation accuracy and peak signal to noise ratio of the proposed algorithm were 98.94% and 77.48 dB. When compared with the Otsu algorithm, fuzzy C-means algorithm, quantum particle swarm optimization algorithm and Markov random field algorithm, the average segmentation accuracy and peak signal to noise ratio of the proposed algorithm increased by 2.47%–4.56%, and 9.81–13.11 dB, respectively. [Conclusion] The proposed algorithm had higher segmentation accuracy and higher peak signal to noise ratio than the other algorithms tested.     

Hybrid Genetic Algorithms for Multimodal Optimization

Hybrid genetic algorithms, which are based on steepest descent algorithm and genetic algorithm, are investigated for the purpose of multimodal optimization. The performances of the hybrid genetic algorithms are evaluated with criteria such as convergence probability, average convergence time and average convergence value of the function in the case of solving global optimization for Schaffer function. It is shown that the performances of the hybrid genetic algorithms are better than steepest decent algorithm or genetic algorithm, and the hybrid genetic algorithm, in which the individuals used for local optimization by steepest decent method are chosen by chance in each generation population, is more efficient than that in which the individuals used for local optimization by steepest descent method are selected from excellent individuals.     

Application of a Particle Swarm Optimization Algorithm in Truss Structure Optimal Design

The particle swarm optimization (PSO) algorithm developed in recent years is a stochastic optimization algorithm based on swarm intelligence. It possesses advantages such as being a simple concept, ease of implementation and low resource occupation. The PSO algorithm was adopted to solve the problem of size optimization of truss structures with stress and displacement constraints. We present the basic principle of the original PSO algorithm in detail, and then introduce a constriction coefficient to modify it. Moreover, reasonable values of the coefficients are proposed for the modified PSO algorithm. Several classical problems are solved using the modified PSO algorithm, and the results compared with those using traditional optimization algorithms and genetic algorithms. Numerical results show that the modified PSO algorithm has good convergence and stability, and can be applied to the size optimization of truss structures.     

基于PSO优化LS-SVM的木材含水率软测量建模

木材含水率是木材干燥过程中重要的技术指标。针对木材干燥过程具有强耦合、大滞后、非线性的特点以及木材含水率检测存在的问题,提出一种软测量方法。利用最小二乘支持向量机(LS-SVM)对非线性系统时间序列数据进行学习,建立被控对象的软测量模型,同时通过粒子群优化(PSO)算法对LS-SVM的惩罚因子和核函数参数进行滚动优化,提高软测量模型的预测精度。将木材干燥窑内的温度、湿度以及木材含水率作为样本数据,通过PSO优化的LS-SVM方法建立木材含水率的软测量模型,进而利用该模型实现对目标检测点木材含水率的软测量。仿真结果表明,PSO-LSSVM软测量模型预测精度高,泛化能力强,满足木材干燥控制系统的实际测量要求。     

自适应加权最小二乘支持向量机的空调负荷预测

为了提高建筑空调负荷的预测精度,在分析空调负荷主要影响因素的基础上提出了一种基于自适应加权最小二乘支持向量机(AWLS-SVM)的建筑空调负荷预测方法。该方法根据预测误差的统计特性,采用基于改进正态分布加权规则,自适应地赋予每个建模样本不同的权值,以克服异常样本点对模型性能的影响。建模过程中采用粒子群优化(PSO)算法对模型参数进行优化,以进一步提高模型预测精度。基于DeST模拟数据将AWLS-SVM方法应用于南方地区某办公建筑的逐时空调负荷预测中,并与径向基神经网络(RBFNN)模型、LS-SVM模型及WLS-SVM模型作比较,其平均预测绝对误差分别降低了51.84 %、13.95 %和3.24 %,并进一步基于实际空调负荷数据将该方法应用于另一办公建筑的逐日空调负荷预测中。预测结果表明：AWLS-SVM预测的累积负荷误差为4.56 MW,亦优于其他3类模型,证明了AWLS-SVM具有较高的预测精度和较好的泛化能力,是建筑空调负荷预测的一种有效方法。     

MDBPSO算法优化的全波段光谱数据协同冠层SIF监测小麦条锈病

为了从全波段光谱数据中提取对小麦条锈病敏感的特征参量,提高小麦条锈病遥感探测模型的运行效率和精度,本文首先从惯性权重和粒子更新方式两个方面对传统离散粒子群算法(discretebinaryparticleswarmoptimization, DBPSO)进行改进,利用改进离散粒子群算法(modified discrete binary particle swarm optimization, MDBPSO)从全波段光谱数据中优选遥感探测小麦条锈病严重度的特征变量,然后与冠层日光诱导叶绿素荧光(solar-inducedchlorophyllfluorescence,SIF)数据相结合作为自变量分别利用随机森林(randomforest,RF)和后向传播(backpropagation,BP)神经网络算法构建小麦条锈病遥感探测模型,并将其与相关系数(correlationcoefficient,CC)分析法和DBPSO算法提取特征参量构建模型的精度进行对比分析。结果表明:(1) MDBPSO算法比传统DBPSO算法具有更快的收敛速度和更高的寻优精度,改进前后其迭代次数从395次减少到156次,最优适应度函数(optimumfitnessvalue,OFV)值从0.145减小到0.127。(2)采用MDBPSO算法选择特征变量时,RF和BP神经网络两种方法构建的模型精度均高于CC分析法和DBPSO算法,其中RF算法预测病情指数(diseaseindex,DI)值和实测DI值间的检验集决定系数(validation set determination coefficient, R2V)比CC分析法和DBPSO算法分别提高了9%和3%,均方根误差(validation set root mean square error, RMSEV)分别降低了28%和11%, BP神经网络算法预测DI值和实测DI值间的R2V比CC分析法和DBPSO算法分别提高了13%和6%,RMSEV分别降低了21%和10%,利用MDBPSO算法优选特征参量能够提高小麦条锈病的遥感探测精度。(3)在MDBPSO、DBPSO和CC分析法3种特征选择算法中,RF算法构建的模型精度均高于BP神经网络算法,其中RF模型预测DI值和实测DI值间的R2V比BP神经网络算法至少提高了7%,平均提高了9%,RMSEV至少降低了15%,平均降低了20%。以MDBPSO算法优选的特征参量为自变量利用RF方法构建的小麦条锈病遥感探测的MDBPSO-RF模型是小麦条锈病遥感探测适宜模型,该研究结果为进一步实现作物健康状况大面积高精度遥感监测提供了新的思路。     

A Simulated Annealing Arithmetic Based on Uniform Design

Some ideas of uniform design in the test design are introduced into Simulated Annealing Arithmetic and a new method of design based on uniform design is discussed. The global optimal solutions of nonlinear multi-peak function can be found by this method. A series of uniformly distributed points are generated by the principle of the uniform design in variable design space. These points are regarded as a series of start points of the optimization model. The Simulated Annealing Arithmetic is chosen to compute and a series of local minimum values can be gained. Before compared with each other, the best value of all local minimum values can be found out, the value is thought as the global minimum in some degree. According to the method, a program is compiled and an example of design is implemented. The result of the example testifies that the method is feasible.     

Particle Size Analysis of Clay by Malvern Laser Particle Analyzer

In order to study the particle size distribution of fine grained soil, the Malvern Mastersizer 2000 laser diffraction grain size analyzer and traditional densimeter method were used to test the clay in Hefei. According to the work principle and affecting factors of laser method, the parameters, such as the refractive index, concentration, ultrasonic displacement and time, pumping speed of the apparatus, were altered in turn. Then the influence of these control parameters on the particle size was investigated, and the best parameters for the clay in Hefei were identified. The grain size distributions measured by laser method under the best condition and traditional densimeter method were compared, which shows that laser method has a wider measuring range, higher accuracy and better repetitiveness in measuring the particle size distribution of fine grained soil.     

Fault diagnosis of rotating machinery based on fuzzy clusteringoptimized by chaos embedded particle swarm optimization

A method of weighted fuzzy clustering optimized by chaos embedded particle swarm algorithm(CPSO) is put forward and applied in vibration fault diagnosis of rotating machinery. In the method, CPSO is used to displace the traditional stochastic-gradient algorithm to optimize parameters of weighted fuzzy C-means (WFCM). The best clustering num and clustering centers are automatically attained according to clustering validity function. The experimental results show that the method effectively increases the convergence velocity and precision of WFCM and so does the correctness rate of fault diagnosis for rotating machinery.     

A fast image segmentation algorithm with local C V active contour model

For the typical C V Algorithm, there exists the weakness of requiring multi iterative operations and long time computation to deal with large size image. Based on the analysis upon the relationship between the image size and the initialized approaching image with the number of iterations and computing time to obtain the stead results, an improved local C V image divisional algorithm based on the segmentation of threshold value and the connected domain labeled algorithm to deal with large size image is proposed. The OTSU method is used to divide the threshold value of image to reach the goal of label and local segmentation of image through the fast non recursion algorithm of connected domains. The segmented pieces and the result of its segmentation are used as the initialized approaching image of the C V algorithm model. Compared with the classical C V algorithm, the analysis and simulated result indicates that the improved C V algorithm reaches the steady solution quickly with fewer times of iterations. The proposed method can handle large size image with profound contour details quickly and effectively.     

Automatic method for aircraft target recognition in remotesensing images based on improved active shape model

We propose an estimation method for aircraft target direction based on histograms of oriented gradients (HOG), and then use the improved active shape model (ASM) to model the deformation between the different types of targets. Finally, we use kernel density estimation method (KDE) global statistical shape constraint to obtain the target to achieve the target recognition, and design a semi-automatic image feature point detection strategy for aircrafts, which improves the efficiency of training samples for calibration feature points. Recognition experiments on aircraft remote sensing images show the proposed method can better recognize aircraft targets than the existing methods.     

Reproducing kernel particle method for numerical analysis of Mindlin plate bending on a Winkler foundation

The reproducing kernel particle method (RKPM) is a typical meshless method based on kernel function simulation. Based on the interpolating shape function of RKPM and Mindlin plate theory, the governing equations of RKPM to the deflection solution of Mindlin plate bending on a Winkler elastic soil foundation are established. Numerical results indicate that the above method and the corresponding program are effective and accurate.     

Analysis on the Temperature-control Effect of the Particle Improved Roadbed in Qinghai-Tibet Railway

Based on the observerd ground-temperature data of the particle improved roadbed in Beiluhe test site of Qinghai-Tibet railway, the characteristics of the ground temperature to the particle improved roadbed and its temperature-control effect are analyzed ,and compared with other frozen soil protecting means. The result indicated that the ground temperature of the particle improved roadbed changes with the seasons,and its characteristics present as a sinusoidal curve. Compared with the normal roadbed, the paticle improved roadbed has cooling roadbed and the effect of protecting frozen soil in mean annual ground temperature. Compared with the normal duct-ventilation embankment, the cooling effect of the particle improved roadbed in cold season is less than that of the duct-ventilation roadbed,and the thermal shield effect is better than that of the particle improved roadbed in warm season. The ground temperature curve has the better tendency of the frozen soil protection. It is an active means of frozen soil protecton.     

电源分配网络阻抗分析及去耦电容优化

高速印制板电源分配网络（power delivery networks,PDN）受电电源端口具有瞬时电流大、目标阻抗小的特点。针对任意形状电源板的阻抗问题,提出一种基于解析式与有限差分法的互补模型,并在此基础上结合粒子群算法实现多个受电电源端口的阻抗优化。通过Matlab仿真,发现互补模型的结果与全波有限元法的基本吻合,计算时间则大幅缩短。测量结果表明,优化后实验板的多个受电电源端口阻抗均满足各自的目标值要求。     

Affine invariant shape recognition with particle swarmoptimization algorithm

Focusing on the problem that affine transformation will exist among the contour images due to variation of the viewpoints, a new approach to extract affine invariant features and matching strategy is proposed for shape recognition. First, the centroid distance and azimuth angle of each boundary point are computed. Then, with a prior defined angle interval, all the points in the neighbor region of the sample point are considered to calculate the average distance for eliminating noise. After that, the centroid distance ratios(CDRs) of any two contour points with angle difference of 180° are achieved as the representation of the shape, which would be invariant to affine transformation. Since the angles of contour points changed non linearly among affine related images, the CDRs should be resampled to build corresponding relationship. It could be regarded as an optimization problem of path planning. In our method, a PSO based path planning model is presented to address this problem. The experimental results demonstrate the efficiency of the proposed method in shape recognition with translation, scaling, rotation, distortion and noise interference.