旱涝灾害的遗传-神经网络集成预测方法研究

利用遗传算法的全局搜索能力同时进化设计三层BP神经网络的结构和连接权，并以进化后的网络结构和连接权作为新的神经网络结构和初始连接权，再进行新一轮附加动量的BP神经网络训练，把训练后的结果简单平均集成，以此建立旱涝灾害的遗传-神经网络集成预测新方法。应用该方法对广西桂林6月（主汛期1995～2005年）的降水量进行实例预测的结果表明，该方法的收敛速度快，预报精度高，易于操作，是一种具有较高应用价值的预测方法。

遗传BP算法在预测深厚软基沉降中的应用

依托某高速公路应用塑料排水板堆载预压法处理深厚软基的工程实践,运用皮尔-遗传神经网络对其沉降观测结果进行了分析、预测。结果显示,预测精度高。

遗传优化的灰色神经网络模型比较研究

针对灰色系统结合RBF神经网络时算法存在局部最优和收敛性等问题,引入遗传算法来辅助优化灰色神经网络预测模型。利用具有的较强全局搜索能力,且收敛速度快的遗传算法对GM(1,1)模型参数λ进行高效求解,然后融合RBF神经网络和改进的灰色GM(1,1)模型,构成两种不同结构的基于遗传算法的灰色RBF预测模型,一种是灰色RBF补偿预测模型GA-GRBF,另一种是灰色嵌入型GRBF模型。以某智能监控系统采集的风响应时程数据进行仿真分析,结果表明经过遗传算法优化的GRBF模型都要优于单一的GRBF模型,并且GA-GRBF模型建模简单,预测精度高,实用性强。

基于时间序列分析的航站楼安检旅客流量预测

对单位时间内通过安检的旅客流量进行预测是机场航站楼实时调控的重要依据,由此提出一种实时安检旅客流量预测方法,采用Wolf方法分析出安检旅客流量时间序列具有混沌特性;采用适用于混沌时间序列预测的遗传算法优化BP神经网络预测方法(GABP)预测安检旅客流量;分别设定时间尺度为2 min、5 min和10 min等,分析不同时间尺度对安检旅客流量预测精度的影响。基于北京首都国际机场T3航站楼实际安检旅客流量数据的实验结果表明,采用GABP神经网络对以2 min为时间尺度的安检旅客流量预测能取得较好的预测精准度。

基于GA-BP神经网络的大型公共建筑能耗预测研究

针对大型公共建筑高能耗问题,将影响能耗的因素进行定量与定性分析,提出了遗传算法和神经网络相结合的大型公共建筑能耗预测模型。采用GA算法优化BP神经网络的权值和阈值的方法对大型公建能耗预测模型进行分析,并结合实例验证了该模型的有效性。结果表明:较传统的BP神经网络,该模型能更准确地预测大型公共建筑能耗,并且为其确保用能定额和节能工作的开展提供了科学依据。

NEURAL NETWORK PREDICTIVE CONTROL WITH HIERARCHICAL GENETIC ALGORITHM

A kind of predictive control based on the neural network(NN) for nonlinear systems with time delay is addressed.The off line NN model is obtained by using hierarchical genetic algorithms (HGA) to train a sequence data of input and output.Output predictions are obtained by recursively mapping the NN model.The error rectification term is introduced into a performance function that is directly optimized while on line control so that it overcomes influences of the mismatched model and disturbances,etc.Simulations show the system has good dynamic responses and robustness.

基于极差分析法与GA-ELM的电器连接器壳体注射成型工艺优化

以某电器连接壳体为例,借助Moldflow软件对正交试验方案组合进行模拟,对正交试验模拟结果进行极差分析,得到各工艺参数对塑件翘曲变形量的影响程度为:保压时间>模具温度>注射时间>熔体温度>保压压力。极差分析得到的最优工艺参数组合对应的翘曲变形量与正交试验方案中最小翘曲变形量相比降低了6.7%。关键点采用遗传算法优化后的预测模型(GA-ELM)对塑件翘曲变形量进行预测。由于传统极限学习算法(ELM)的权值和阈值随机产生,网络系统预测稳定性及精度较差,故通过GA全局寻优能力寻找最佳的权值和阈值,得到GA-ELM。选择正交试验前80%样本作为训练集训练ELM与GA-ELM模型,通过样本后20%作为测试集验证ELM与GA-ELM模型预测精度。对比分析可看到:使用GA-ELM预测模型比直接使用ELM预测模型预测结果有更高预测精度及稳定性。此GA-ELM模型可用来预测该塑件翘曲变形量。对同类模具设计优化提供一定的思路及理论参考。

Research on a non-linear chaotic prediction model for urban traffic flow

In order to solve serious urban transport problems, according to the proved chaotic characteristic of traffic flow, a non linear chaotic model to analyze the time series of traffic flow is proposed. This model reconstructs the time series of traffic flow in the phase space firstly, and the correlative information in the traffic flow is extracted richly, on the basis of it, a predicted equation for the reconstructed information is established by using chaotic theory, and for the purpose of obtaining the optimal predicted results, recognition and optimization to the model parameters are done by using genetic algorithm. Practical prediction research of urban traffic flow shows that this model has famous predicted precision, and it can provide exact reference for urban traffic programming and control.

Rock burst prediction based on genetic algorithms and extreme learning machine

Rock burst is a kind of geological disaster in rock excavation of high stress areas.To evaluate intensity of rock burst,the maximum shear stress,uniaxial compressive strength,uniaxial tensile strength and rock elastic energy index were selected as input factors,and burst pit depth as output factor.The rock burst prediction model was proposed according to the genetic algorithms and extreme learning machine.The effect of structural surface was taken into consideration.Based on the engineering examples of tunnels,the observed and collected data were divided into the training set,validation set and prediction set.The training set and validation set were used to train and optimize the model.Parameter optimization results are presented.The hidden layer node was450,and the fitness of the predictions was 0.0197 under the optimal combination of the input weight and offset vector.Then,the optimized model is tested with the prediction set.Results show that the proposed model is effective.The maximum relative error is4.71%,and the average relative error is 3.20%,which proves that the model has practical value in the relative engineering.

Prediction method of rock burst proneness based on rough set and genetic algorithm

A new method based on rough set theory and genetic algorithm was proposedto predict the rock burst proneness. Nine influencing factors were first selected, and then,the decision table was set up. Attributes were reduced by genetic algorithm. Rough setwas used to extract the simplified decision rules of rock burst proneness. Taking the practical engineering for example, the rock burst proneness was evaluated and predicted bydecision rules. Comparing the prediction results with the actual results, it shows that theproposed method is feasible and effective.

Development of viscosity model for aluminum alloys using BP neural network

Viscosity is one of the important thermophysical properties of liquid aluminum alloys,which influences the characteristics of mold filling and solidification and thus the quality of castings.In this study,315 sets of experimental viscosity data collected from the literatures were used to develop the viscosity prediction model.Back-propagation(BP)neural network method was adopted,with the melt temperature and mass contents of Al,Si,Fe,Cu,Mn,Mg and Zn solutes as the model input,and the viscosity value as the model output.To improve the model accuracy,the influence of different training algorithms and the number of hidden neurons was studied.The initial weight and bias values were also optimized using genetic algorithm,which considerably improve the model accuracy.The average relative error between the predicted and experimental data is less than 5%,confirming that the optimal model has high prediction accuracy and reliability.The predictions by our model for temperature-and solute content-dependent viscosity of pure Al and binary Al alloys are in very good agreement with the experimental results in the literature,indicating that the developed model has a good prediction accuracy.

An Optimal Control Strategy Combining SVM with RGA for Improving Fermentation Titer

An optimal control strategy is proposed to improve the fermentation titer,which combines the support vector machine(SVM)with real code genetic algorithm(RGA).A prediction model is established with SVM for penicillin fermentation processes,and it is used in RGA for fitting function.A control pattern is proposed to overcome the coupling problem of fermentation parameters,which describes the overall production condition.Experimental results show that the optimal control strategy improves the penicillin titer of the fermentation process by 22.88%,compared with the routine operation.

An improved brain emotional learning algorithm for accurate and efficient data analysis

To overcome the deficiencies of high computational complexity and low convergence speed in traditional neural networks, a novel bio-inspired machine learning algorithm named brain emotional learning （BEL） is introduced. BEL mimics the emotional learning mechanism in brain which has the superior features of fast learning and quick reacting. To further improve the performance of BEL in data analysis, genetic algorithm （GA） is adopted for optimally tuning the weights and biases of amygdala and orbitofrontal cortex in BEL neural network. The integrated algorithm named GA-BEL combines the advantages of the fast learning of BEL, and the global optimum solution of GA. GA-BEL has been tested on a real-world chaotic time series of geomagnetic activity index for prediction, eight benchmark datasets of university California at Irvine （UCI） and a functional magnetic resonance imaging （fMRI） dataset for classifications. The comparisons of experimental results have shown that the proposed GA-BEL algorithm is more accurate than the original BEL in prediction, and more effective when dealing with large-scale classification problems. Further, it outperforms most other traditional algorithms in terms of accuracy and execution speed in both prediction and classification applications.

Airport Aviation Noise Prediction Based on an Optimized Neural Network

In order to alleviate noise pollution and improve the sustainability of airport operation,it is of great significance to develop an effective method to predict airport aviation noise. A three-layer neural network is constructed to gain computational simplicity and execution economy. With the preferred node number and transfer functions obtained in comparative tests,the constructed network is further optimized through the genetic algorithm for performance improvements in prediction. Results show that the proposed model in this paper is superior in accuracy and stability for airport aviation noise prediction,contributing to the assessment of future environmental impact and further improvement of operational sustainability for civil airports.

A weighted selection combining scheme for cooperative spectrum prediction in cognitive radio networks

A weighted selection combining （WSC） scheme is proposed to improve prediction accuracy for cooperative spectrum prediction in cognitive radio networks by exploiting spatial diversity. First, a genetic algorithm-based neural network （GANN） is designed to perform spectrum prediction in consideration of both the characteristics of the primary users （PU） and the effect of fading. Then, a fusion selection method based on the iterative self-organizing data analysis （ISODATA） algorithm is designed to select the best local predictors for combination. Additionally, a reliability-based weighted combination rule is proposed to make an accurate decision based on local prediction results considering the diversity of the predictors. Finally, a Gaussian approximation approach is employed to study the performance of the proposed WSC scheme, and the expressions of the global prediction precision and throughput enhancement are derived. Simulation results reveal that the proposed WSC scheme outperforms the other cooperative spectrum prediction schemes in terms of prediction accuracy, and can achieve significant throughput gain for cognitive radio networks.

Nonlinear model predictive control based on support vector machine and genetic algorithm

This paper presents a nonlinear model predictive control(NMPC) approach based on support vector machine(SVM) and genetic algorithm(GA) for multiple-input multiple-output(MIMO) nonlinear systems.Individual SVM is used to approximate each output of the controlled plant Then the model is used in MPC control scheme to predict the outputs of the controlled plant.The optimal control sequence is calculated using GA with elite preserve strategy.Simulation results of a typical MIMO nonlinear system show that this method has a good ability of set points tracking and disturbance rejection.

Times Series Prediction to Basis of a Neural Network Conceived by a Real Genetic Algorithm

Neural network and genetic algorithms are complementary technologies in the design of adaptive intelligent system. Neural network learns from scratch by adjusting the interconnections betweens layers. Genetic algorithms are a popular computing framework that uses principals from natural population genetics to evolve solutions to problems. Various forecasting methods have been developed on the basis of neural network, but accuracy has been matter of concern in these forecasts. In neural network methods forecasted values depend to the choose of neural predictor structure, the number of the input, the lag. To remedy to these problem, in this paper, the authors are investing the applicability of an automatic design of a neural predictor realized by real Genetic Algorithms to predict the future value of a time series. The prediction method is tested by using meteorology time series that are daily and weekly mean temperatures in Melbourne, Australia, 1980-1990.

Aedes sierrensis在中国的潜在分布预测

目的预测Aedes sierrensi(sLudlow,1905)在我国的潜在分布。方法根据文献资料整理得出Ae. sierrensis稳定分布,应用预设预测规则的遗传算法(GARP)生态位模型对其在中国的潜在分布进行分析预测。结果Ae. sierrensis在我国的潜在分布区涉及大部分省(直辖市、自治区),高风险地区集中在我国中北部地区,包括新疆、内蒙古、宁夏、陕西、山西、河北、北京、天津、河南、山东、辽宁、吉林和黑龙江省(直辖市、自治区);中度适生区集中在安徽、河北南部、山东西南部、湖北北部、浙江西北部等地区;低度适生区集中在贵州、广西、湖南、重庆、湖北、江西、福建、台湾、海南等省(自治区)。结论Ae. sierrensis在我国潜在分布区广,风险等级高,应及时制定相应风险管理措施,严防该蚊入侵我国。

Discriminant Genetic Algorithm Extended (DGAE) model for seasonal sand and dust storm prediction

Here we use a Discriminant Genetic Algorithm Extended (DGAE) model to diagnose and predict seasonal sand and dust storm (SDS) activities occurring in Northeast Asia. The study employed the regular meteorological data, including surface data, upper air data, and NCEP reanalysis data, collected from 1980–2006. The regional, seasonal, and annual differences of 3-D atmospheric circulation structures and SDS activities in the context of spatial and temporal distributions were given. Genetic algorithms were introduced with the further extension of promoting SDS seasonal predication from multi-level resolution. Genetic probability was used as a substitute for posterior probability of multi-level discriminants, to show the dual characteristics of crossover inheritance and mutation and to build a non-linear adaptability function in line with extended genetic algorithms. This has unveiled the spatial distribution of the maximum adaptability, allowing the forecast field to be defined by the population with the largest probability, and made discriminant genetic extension possible. In addition, the effort has led to the establishment of a regional model for predicting seasonal SDS activities in East Asia. The model was tested to predict the spring SDS activities occurring in North China from 2007 to 2009. The experimental forecast resulted in highly discriminant intensity ratings and regional distributions of SDS activities, which are a meaningful reference for seasonal SDS predictions in the future.

Water Resource Allocation under Consideration of the National NIY Plan in Harbin, China

Water resource allocation （WRA） is a useful but complicated topic in water resource management. With the targets set out in the Plan of Newly Increasing Yield （NIY） of 10×1011 Jin （1 kg=2 Jin） from 2009 to 2020, the immediate question for the Songhua River Region （SHRR） is whether water is sufficient to support the required yield increase. Very few studies have considered to what degree this plan influences the solution of WRA and how to adapt. This paper used a multi-objective programming model for WRA across the Harbin region located in the SHRR in 2020 and 2030 （p=75%）. The Harbin region can be classified into four types of sub-regions according to WRA： Type I is Harbin city zone. With rapid urbanization, Harbin city zone has the highest risk of agricultural water shortage. Considering the severe situation, there is little space for Harbin city zone to reach the NIY goal. Type II is sub-regions including Wuchang, Shangzhi and Binxian. There are some agricultural water shortage risks in this type region. Because the water shortage is relatively small, it is possible to increase agricultural production through strengthening agricultural water-saving countermeasures and constructing water conservation facilities. Type III is sub-regions including Acheng, Hulan, Mulan and Fangzheng. In this type region, there may be a water shortage if the rate of urbanization accelerates. According to local conditions, it is needed to enhance water-saving countermeasures to increase agricultural production to a certain degree. Type IV is sub-regions including Shuangcheng, Bayan, Yilan, Yanshou and Tonghe. There are good water conditions for the extensive development of agriculture. Nevertheless, in order to ensure an increase in agricultural production, it is necessary to enhance the way in which water is utilized and consider soil resources. These results will help decision makers make a scientific NIY plan for the Harbin region for sustainable utilization of regional water resources and an increase in agricultural production.