A novel immune genetic algorithm based on quasi secondary response

Combining the advantages of a genetic algorithm and an artificial immune system, a novel genetic algorithm named immune genetic algorithm based on quasi secondary response （IGA QSR） is proposed. IGA QSR employs a database to simulate the standard secondary response and the quasi secondary response. Elitist strategy, automatic extinction, clonal propagation, diversity guarantee, and selection based on comprehensive fitness are also used in the process of IGA QSR. Theoretical analysis, numerical examples of three benchmark mathematical optimization problems and a trave ling salesman problem all demonstrate that IGA-QSR is more effective not only on convergence speed but also on convergence probability than a simple genetic algorithm with the elitist strategy （ SGA ES）. Besides, IGA QSR allows the designers to stop and restart the optimization process freely with out losing the best results that have already been obtained. These properties make IGA QSR be a fea sible, effective and robust search algorithm for complex engineering problems.

Simulating the Folding Pathway of RNA Secondary Structure Using the Modified Ant Colony Algorithm

A new method for simulating the folding pathway of RNA secondary structure using the modified ant colony algorithmis proposed.For a given RNA sequence,the set of all possible stems is obtained and the energy of each stem iscalculated and stored at the initial stage.Furthermore,a more realistic formula is used to compute the energy ofmulti-branch loop in the following iteration.Then a folding pathway is simulated,including such processes as constructionof the heuristic information,the rule of initializing the pheromone,the mechanism of choosing the initial andnext stem and the strategy of updating the pheromone between two different stems.Finally by testing RNA sequences withknown secondary structures from the public databases,we analyze the experimental data to select appropriate values forparameters.The measure indexes show that our procedure is more consistent with phylogenetically proven structures thansoftware RNAstructure sometimes and more effective than the standard Genetic Algorithm.

Neural Network Based on GA-BP Algorithm and its Application in the Protein Secondary Structure Prediction

The advantages and disadvantages of genetic algorithm and BP algorithm are introduced. A neural network based on GA-BP algorithm is proposed and applied in the prediction of protein secondary structure, which combines the advantages of BP and GA. The prediction and training on the neural network are made respectively based on 4 structure classifications of protein so as to get higher rate of predication---the highest prediction rate 75.65%,the average prediction rate 65.04%.

Distributed Secondary Control Based on Dynamic Diffusion Algorithm for Current Sharing and Average Voltage Regulation in DC Microgrids

This paper introduces a distributed secondary control scheme for achieving current sharing and average voltage regulation objectives in a DC microgrid.The proposed scheme employs a dynamic diffusion algorithm(DDA)instead of the consensus algorithm to enable distributed communication among converters.To help understand DDA,the relation of DDA and other diffusion algorithms is discussed in detail and its superiority is shown by comparison with diffusion and consensus algorithms.Furthermore,considering the discrete nature and different sampling time of the digital controller and communication network,a z-domain model of the entire DC microgrid is established.The influence of communication and secondary control parameters on the system stability is investigated.Based on the established model,the tolerable communication rates are obtained.Real-time simulations conducted on the OPAL-RT platform validate the effectiveness of the proposed scheme,showcasing its advantages in terms of convergence speed and stability.

Self-adaptive learning based immune algorithm

A self-adaptive learning based immune algorithm （SALIA） is proposed to tackle diverse optimization problems, such as complex multi-modal and ill-conditioned prc,blems with the high robustness. The SALIA algorithm adopted a mutation strategy pool which consists of four effective mutation strategies to generate new antibodies. A self-adaptive learning framework is implemented to select the mutation strategies by learning from their previous performances in generating promising solutions. Twenty-six state-of-the-art optimization problems with different characteristics, such as uni-modality, multi-modality, rotation, ill-condition, mis-scale and noise, are used to verify the validity of SALIA. Experimental results show that the novel algorithm SALIA achieves a higher universality and robustness than clonal selection algorithms （CLONALG）, and the mean error index of each test function in SALIA decreases by a factor of at least 1.0×10^7 in average.

A GASVM Algorithm for Predicting Protein Structure Classes

The research methods of protein structure prediction mainly focus on finding effective features of protein sequences and developing suitable machine learning algorithms. But few people consider the importance of weights of features in classification. We propose the GASVM algorithm (classification accuracy of support vector machine is regarded as the fitness value of genetic algorithm) to optimize the coefficients of these 16 features (5 features are proposed first time) in the classification, and further develop a new feature vector. Finally, based on the new feature vector, this paper uses support vector machine and 10-fold cross-validation to classify the protein structure of 3 low similarity datasets (25PDB, 1189, FC699). Experimental results show that the overall classification accuracy of the new method is better than other methods.

The Comparison between Random Forest and Support Vector Machine Algorithm for Predicting β-Hairpin Motifs in Proteins

Based on the research of predictingβ-hairpin motifs in proteins, we apply Random Forest and Support Vector Machine algorithm to predictβ-hairpin motifs in ArchDB40 dataset. The motifs with the loop length of 2 to 8 amino acid residues are extracted as research object and thefixed-length pattern of 12 amino acids are selected. When using the same characteristic parameters and the same test method, Random Forest algorithm is more effective than Support Vector Machine. In addition, because of Random Forest algorithm doesn’t produce overfitting phenomenon while the dimension of characteristic parameters is higher, we use Random Forest based on higher dimension characteristic parameters to predictβ-hairpin motifs. The better prediction results are obtained;the overall accuracy and Matthew’s correlation coefficient of 5-fold cross-validation achieve 83.3% and 0.59, respectively.

Using the Support Vector Machine Algorithm to Predict β-Turn Types in Proteins

The structure and function of proteins are closely related, and protein structure decides its function, therefore protein structure prediction is quite important.β-turns are important components of protein secondary structure. So development of an accurate prediction method ofβ-turn types is very necessary. In this paper, we used the composite vector with position conservation scoring function, increment of diversity and predictive secondary structure information as the input parameter of support vector machine algorithm for predicting theβ-turn types in the database of 426 protein chains, obtained the overall prediction accuracy of 95.6%, 97.8%, 97.0%, 98.9%, 99.2%, 91.8%, 99.4% and 83.9% with the Matthews Correlation Coefficient values of 0.74, 0.68, 0.20, 0.49, 0.23, 0.47, 0.49 and 0.53 for types I, II, VIII, I’, II’, IV, VI and nonturn respectively, which is better than other prediction.

Research on Distributed Coordination Control Method for Microgrid System Based on Finite-time Event-triggered Consensus Algorithm

Microgrids are networked control systems with multiple distributed generators(DGs).Microgrids are associated with many problems,such as communication delays,high sampling rates,and frequent controller updates,which make it challenging to realize coordination control among the DGs.Therefore,finite-time consensus algorithms and event-triggered control methods are combined to propose a distributed coordination control method for microgrid systems.The DG in the microgrid system serves as an agent node in the control network,and a distributed secondary controller is designed using finite-time consensus algorithm,such that the frequency and voltage restoration control has a faster convergence time and better anti-interference performance.The event-triggered function was designed based on the state information of the agents.The controller exchanges the state information at the trigger instants.System stability is analyzed using the Lyapunov stability theory,and it is verified that the controller cannot exhibit the Zeno phenomenon in the event-triggered process.A simulation platform was developed in Matlab/Simulink to verify that the proposed control method can effectively reduce the frequency of controller updates during communication delays and the burden on the communication network.

New Optimization Design Method for a Double Secondary Linear Motor Based on R-DNN Modeling Method and MCS Optimization Algorithm

Traditional linear motor optimization methods typically use analytical models combined with intelligent optimization algorithms.However,this approach has disadvantages,e.g.,the analytical model might not be accurate enough,and the intelligent optimization algorithm can easily fall into local optimization.A new linear motor optimization strategy combining an R-deep neural network(R-DNN)and modified cuckoo search(MCS)is proposed;additionally,the thrust lifting and thrust fluctuation reductions are regarded as optimization objectives.The R-DNN is a deep neural network modeling method using the rectified linear unit(RELU)activation function,and the MCS provides a faster convergence speed and stronger data search capability as compared with genetic algorithms,particle swarm optimization,and standard CS algorithms.Finally,the validity and accuracy of this work are proven based on prototype experiments.

Multi-variable Dependent Forecast Algorithm for Predicting Secondary Arc

Hybrid reactive power compensation(HRPC)combines step-controlled shunt reactors and series compensation,and will be employed in ultra-high-voltage(UHV)power systems.The single-phase auto-reclosure characteristics of secondary arcs in systems with HRPC require further investigation.In this paper,both the arc-recalling voltage and subsidiary variations in arc current are investigated with and without HRPC.The frequency components of the secondary arc current and variations in arcing time are analyzed for various influential factors,such as the neutral reactor,arc resistance,fault location,degrees of compensation of HRPC,and the length of the transmission line.The non-dominated sorting genetic algorithm II(NSGA-II)and support vector machine regression are combined to create a multi-variable dependent forecasting algorithm to predict the characteristics of the secondary arc in UHV systems with HRPC.This paper provides a theoretical reference for optimizing the parameters of HRPC,and for developing adaptive auto-reclosure schemes and protection equipment.

Convergence analysis of filtered-X LMS algorithm with secondary path modeling error

A more relaxed sufficient condition for the convergence of filtered-X LMS (FXLMS) algorithm is presented. It is pointed out that if some positive real condition for secondary path transfer function and its estimates is satisfied within all the frequency bands, FXLMS algorithm converges whatever the reference signal is like. But if the above positive real condition is satisfied only within some frequency bands, the convergence of FXLMS algorithm is dependent on the distribution of power spectral density of the reference signal, and the convergence step size is determined by the distribution of some specific correlation matrix eigenvalues.Applying the conclusion above to the Delayed LMS (DLMS) algorithm, it is shown that DLMS algorithm with some error of time delay estimation converges in certain discrete frequency bands, and the width of which are determined only by the 'time-delay estimation error frequency' which is equal to one fourth of the inverse of estimated error of the time delay.

SUPPRESSION OF THE SECONDARY FLOWS IN A BEND PIPE USING NAVIER-STOKES SOLVER AND EVOLUTIONARY ALGORITHMS

Hydrodynamic optimization design of the bend pipe from pump using theNavier-Stokes solver and evolutionary algorithms was conducted. The minimization of the totalpressure loss of the bend pipe was chosen as the design object in order to obtain the uniform exitflows through suppressing the secondary flows. The 3-D Navier-Stokes solver was applied to evaluatethe hydrodynamic performance of the bend-pipe flows. A 7th-order Bezier curve was used toparameterize the meridional section and elliptic representation was adopted to represent thecross-section profiles of the bend pipe. Evolutionary algorithms were applied in optimization. Theobtained results show that the designed bend pipe shape has much more uniform exit flows comparedwith the initial one and much weaker secondary flows, and that the evolutionary algorithms and CFDtechnique are the powerful optimization tools for the fluid machinery desiga

Performance analysis of FXLMS algorithm with secondary path modeling error

Performance analysis of filtered-X LMS (FXLMS) algorithm with secondary path modeling error is carried out in both time and frequency domain. It is shown firstly that the effects of secondary path modeling error on the performance of FXLMS algorithm are determined by the distribution of the relative error of secondary path model along with frequency. In case of that the distribution of relative error is uniform the modeling error of secondary path will have no effects on the performance of the algorithm. In addition, a limitation property of FXLMS algorithm is proved, which implies that the negative effects of secondary path modeling error can be compensated by increasing the adaptive filter length. At last, some insights into the 'spillover' phenomenon of FXLMS algorithm are given.

Winding Function Theory Based Thrust Calculation on Nested-loop Secondary Linear Machine Adapted to Linear Metro

With advantages of strong drive capability,nested-loop secondary linear machine(NLS-LM)has great potentiality in linear metro.For its secondary structure with multiple loops,it is difficult to calculate the electromagnetic thrust of NLS-LM reasonably.Hence,in this paper,one thrust calculation method is proposed considering variable loop inductance and transient loop current.Firstly,to establish the secondary winding function,the modeling domain is confined to a limited range,and the equivalent loop span is employed by analyzing the coupling relationship between primary and secondary.Then,in order to obtain the secondary flux density,the transient secondary current is solved based on the loop impedance and induced voltage.Finally,the electromagnetic thrust can be calculated reasonably by the given primary current sheet and the calculated secondary flux density.Comprehensive simulations and experiments have demonstrated the effectiveness of the proposed method.

基于集合经验模态分解和多目标遗传算法的火-多储系统调频功率双层优化

针对分布于区域电网不同网络节点的多座储能电站参与电网调频功率调度问题,该文提出一种基于集合经验模态分解(EEMD)和多目标遗传算法(MOGA)的火-多储系统调频功率双层优化策略。该策略包含火-储调频功率优化层和多储能电站调频功率优化层:上层计及火-储调配资源各自优势及剩余调频能力,构建火-储调频功率优化分配模型,完成火-储调频功率的分配;下层引入关于调频成本和荷电状态(SOC)的自适应权重系数,以调频成本最低和SOC均衡为优化目标,完成调频功率在多储能电站之间的分配。仿真结果表明,所提策略可以提升区域电网调频效果并降低调频成本,均衡控制多个储能电站的调频成本和SOC,可以防止经济性较好的储能电站长期处于SOC越限边缘状态,提升储能电站参与调频的积极性和可持续性。

多目标金属露天矿配矿装载点选取问题及求解算法

目的:为了减少矿产资源浪费,提高贫矿的利用率,针对大型金属露天矿多装载点配矿问题,综合考虑矿石剩余量不足、铲装设备数量有限等因素对配装载点选取的影响,以品位偏差最小、生产成本最小、车辆总排队时间最短为目标建立配矿装载点选取模型。方法:采用二维矩阵整数编码法,并设计一种基于随机片段交叉与特定变异算子相结合的间接二次遗传优化算法对模型进行求解。结果:以国内某大型金属露天矿实际生产数据为例进行仿真实验,结果表明:所得出的装载点选取方案在受铲装设备数量限制、优先开采矿石剩余量相对较少装载点的条件下,仍能满足配矿计划需求。结论:所提模型、算法能普遍适用于大型金属露天矿山开采,使装载点的矿石得到充分利用。意义:提高了企业的经济效益和矿山整体开采效率。

孤岛微电网的虚拟同步发电机分布式协同二次调频控制

基于孤岛微电网中虚拟同步发电机一次控制存在的频率偏差问题,提出一种基于预定时系统的分布式二次频率控制策略。该策略通过预定时系统对一致性进行改进并适配虚拟同步发电机本体算法,使各逆变器仅依靠相邻单元的通信,即可实现系统有功缺额按容量分配与频率的无差控制。同时,预定时系统通过提前设定一致性的收敛时间,进一步提高频率的恢复速度,并且无需考虑初始容量与协议参数的影响,有利于分布式电源的即插即用,提高运行效率。最后通过仿真验证了所提控制策略的可行性和有效性。

基于航迹数据的改进DBSCAN聚类算法研究

为研究模拟训练航迹数据聚类,针对基于密度的噪声应用空间聚类(DBSCAN)算法参数选取不精准、聚类准确度不高的问题,提出一种改进的DBSCAN聚类算法.首先,通过KNN算法计算邻域半径并得到用于DBSCAN聚类的初始化核心数据对象,实现粗聚类;其次,根据数据对象的特点,加入航向特征进行二次聚类,既解决了DBSCAN算法随机初始化核心点和参数选取难的问题,又加入能够反映数据方向的特征;最后,进行了仿真实验.实验结果表明,改进DBSCAN算法比传统DBSCAN算法具有更好的聚类效果.

基于二次分解策略和BiLSTM的短期碳排放预测模型设计

针对现有短期碳排放预测模型残余噪声大、忽略全局信息的特性导致预测精度不高的问题,提出一种基于二次分解策略和双向长短期记忆神经网络(BiLSTM)的新的短期碳排放预测模型。利用改进的自适应噪声完全集成经验模态分解(ICEEMDAN)方法和二次分解思想,将原始时间序列分解为多个本征模态函数(imfs);利用鲸鱼优化算法(WOA)优化的双向长短期记忆神经网络(BiLSTM)对所有函数序列进行预测,并将每个函数序列的预测值累加得到最终结果。实验结果显示,该文提出模型的R2达到0.999,MAPE和RMSE分别为1.3×10-3和97.4,优于其他对比模型,有效降低了预测误差。