A new pattern recognition method of gas sensor array detection

BP neural network based gas sensor array detection pattern recognition has some disadvantages, such as slow convergence and local minimum problem. A modified immune neural network model which combines BP algorithm and immune algorithm is proposed to enhance global search capability and improve the performance of the neural network model. Orthogonal test is adopted to design the study samples of neural network. This ensures the accuracy of neural network while reducing the number of samples. The simulation results show that the proposed pattern recognition method solves the cross sensitivity of gas sensor effectively, overcomes the disadvantages of traditional BP neural network and improves the learning speed and detection accuracy.     

山西日光温室逐日极端气温预测模型研究

利用山西省忻州市日光温室的室内小气候观测数据及气象站资料,用BP神经网络及逐步回归法建立以多种输入变量的不同天气条件下的日光温室内最高温度、最低温度的模型。结果表明,利用BP神经网络及逐步回归法建立的模型R2均在0.96以上,RMSE与AE大部分在2℃之下。利用逐步回归方法在模拟日光温室内晴天最高、最低温度和寡照的最高温度精度较高,利用BP神经网络模型在多云的最高、最低温度与寡照的最低温度模拟的精度较高。选择精度更好的模型对日光温室的极端气温做准确的预测,可为山西省设施农业的管理和调控及小气候预报提供支持。     

The Neural Network Method for Searching Graph Minimal Cut Set

The new neural network algorithm for searching graph minimal cut set,called NNMC algorithm, is established on the basis of construction of Hopfield Network energy function according to the concrete problem.In NNMC algorithm, which suffciently uses the fast convergence of Hopfield Network, a way to avoid the local minimum is carried out.     

基于随机森林算法的日光温室内气温预测模型研究

开展日光温室气温预报,为农业生产提供参考,指导农户采取调控措施,为作物生长提供适宜条件,促进品质和产量提升。研究选取温室外气温、日照等气象因子,建立随机森林算法预测模型,就室内最低、最高气温进行拟合预测分析和预测因子重要性评估。结果表明,温室内最低、最高气温拟合值与观察值的拟合度分别达99.69%和99.85%,温室外最低气温是室内最低气温的重要预测因子,室外日照是室内最高气温的重要预测因子。同时建立支持向量机、神经网络、多元回归、逐步回归模型,通过对各个模型中平均绝对误差、均方根误差等3个指标进行比较,得出随机森林模型的预测精度优于其他模型。基于随机森林算法的气温预测模型精确度较高,可推广应用到后期日光温室气温预测中。     

BP neural network and genetic algorithm for thefilling properties optimization of crankshaft

The structure of wedge flash is proposed to improve the filling properties for deep cavity structure of crankshaft die with dimensional splitting mold. BP genetic algorithm is applied to optimize the structure parameters of wedge flash based on Matlab. Samples which are selected by orthogonal test are analyzed via FEM, and the minimum unfilled distance obtained are employed to conduct the BP neural network training. Then the optimum parameters with minimum unfilled distance are gained from genetic algorithm. Error between the parameters predicted and the results get from simulations is less than 5%. The productive practice indicates that the cavity is fully filled and the material utilization ratio increases from 75.7% to 81.4%, which confirms the correctness of optimization of wedge flash structure.     

基于遗传算法的BP神经网络在小麦蛋白质含量预测中的应用

为了快速、简便、准确地测定小麦蛋白质的含量,本文提出了应用近红外光谱分析技术结合遗传算法(GA)的BP神经网络的建模方法。采用SPXY算法对光谱数据进行了合理划分,并运用连续投影算法(SPA)将预处理过的数据压缩,对光谱数据提取最佳敏感波点作为GA-BP神经网络的输入,建立小麦蛋白质含量的校正模型。模型的预测均方根误差和预测相关系数为1.3379和0.979,并与BP神经网络所建立的校正模型进行了比较。结果表明：GA-BP神经网络所建模型收敛速度快、训练时间短、准确度也较高,能够实现对小麦蛋白质含量快速高效的检测。     

Fuzzy Backpropagation Algorithms and Their Convergence

The equivalence between fuzzy neural networks model for max-min fuzzy operator and S.Stoeva's is proved by studying the fuzzy neural networks model for max-min fuzzy based on S.Stoeva's.Then the paper proposes the fuzzy backpropagation learning algorithms for changing fuzzy power and probes their convergence properties.Finally,it simulates experiment such as state monitoring of turbo-generator set.The results show that the fuzzy backpropagation learning algorithms presented are convergent on condition that the output of training sample is between maximum and minimum of its input.     

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。     

Application of Incremental Genetic RBF NN in Converter Vanadium Recover

Converter vanadium recover is a very sophisticate reaction which is diverse and non- line. From the point of view of statistics and reaction mechanism, it is difficult to build up end- point control static model. Aim at this problem, the paper puts forward a model identify method based on incremental genetic RBF neural network to build up such a model, which can perfectly resolve the problem of random selection of RBF cluster center number and sample data clustering. Furthermore, in order to ensure structure of neural network to fit with continuous incremental data set, the paper presents a method of incremental data dealing, which is applied to amend the parameters of neural network. Then the request of continuous production is satisfied. Finally the result of test shows that after adopting the algorithm, the error of result is less than before and end- point hitting ratio satisfies to ninety percent. These indicate the algorithm has the engineering practicability.     

Artificial Neural Network Fault Diagnosis System Based on Rough Set Theory

On the basis of fault diagnosis neural network model, in this paper, knowledge representation system of rough set theory is taken as a major tool to delaminate the complex neural network and in which unnecessary properties are eliminated. This method overcomes some shortcomings, such as network scale is too large and the rate of classification is slow. The good effect that reduces the matching quantity of pattern search in classification course is gotten. The structure and algorithm of layered-mining neural network model based on rough set theory are also given. The example shows that this system has higher reference value in practical application.     

大型商场建筑夏季冷负荷动态预测模型

夏季建筑冷负荷的正确预测是实现大型复杂中央空调优化运行、节能降耗的关键。笔者探讨了商场建筑冷负荷的主要影响因素,确定了建筑动态冷负荷预测模型的输入,提出了夏季基于新风机组供电频率的商场顾客率间接测量方法,解决了商场内顾客量难以检测的难题。还提出了AFC-HCMAC神经网络预测模型算法,实现了大型商场建筑冷负荷的动态预测。仿真结果表明:顾客率在商场冷负荷预测中占有重要地位,在冷负荷预测模型中增加商场顾客率可显著提高预测精度;AFC-HCMAC神经网络预测算法与传统的HCMAC神经网络算法比较,可有效降低神经网络节点数,提高预测精度。     

Drift error compensation algorithm for fiber optic gyro based on T-S fuzzy modeling

A drift error nonlinear compensation algorithm for Fiber Optic Gyro (FOG) is presented based on T-S fuzzy model with the antecedent parameters identified by G-K clustering algorithm and the error model of T-S fuzzy model with the consequent parameters identified by least square algorithm. The computed results show that this model can compensate the original data effectively, while the error principles of FOG do not need to be understood well. Comparing with the original data, compensation with linear fitting and compensation with neural network, the absolute error of the proposed model reduces by 99%, 96% and 10%, respectively. The error variance reduces by 99%, 98% and 20%, respectively. The results indicate that this proposed algorithm can be simply operated with high precision and easy to realize in engineering.     

An artificial immunity based predictive method for neural networks and its applications

A radial basis function (RBF) neural network learning algorithm based on immune recognition was proposed to improve the low forecast precision and the slow convergence speed of such networks. In the algorithm, artificial immunity was used to determine the center and width parameters of the Gauss basis function. The recognized data were regarded as antigens and the compression mapping of antigens were taken as antibodies, i.e., the centers of the hidden layer. The recursion least square algorithm (RLS) was employed to determine the output layer weights. The algorithm improved the convergence speed and precision of the RBF neural networks. The model was applied to the blast furnace of a large iron and steel company. The results show that the model has forecast precision far superior to existing models and requires less training time than they do.     

基于LM-BP神经网络的耕地土壤养分等级划分模型──以皖南山区为例

研究旨在通过BP神经网络方法,构建起LM-BP网络结构(5-M-1)模型,达到对土壤养分等级划分的目的,为合理的土壤养分管理提供可靠依据。采用Levenberg-Marquardt (LM)训练算法,构建3层网络模型：一个输入层、一个隐含层、一个输出层,利用3层网络作为耕地土壤养分等级划分模型。利用土壤养分各级评价标准作为模型的训练样本和测试样本,以此来对BP神经网络进行训练和测试,并对歙县土壤养分进行综合评价。结果表明：LM-BP网络结构对测试样本输出的预测值和实际参考值是一致的。最终通过灰色关联模型和主成分分析方法对歙县土壤养分的综合评价结果与BP神经网络的模拟结果相对比,发现也是基本一致的。LM-BP网络结构应用于土壤养分等级划分中,得到了很好的预测效果,为智能算法应用于农业领域奠定了良好的基础。     

Bi-level Programming Model and Genetic Algorithms for the Selection of Vendors

The traditional vendor selection model often pay attention to the profit of the buyers and the selection behavior of vendor is ignored,but the vendors only trade with the buyers according with their rational selection,so the vendors selection bi-level programming model is presented with constraint of minimal batches,the ability of supply,product matching etc.A solution of the model based on genetic algorithm is proposed.The buyers' vendor selection of minimum cost is realized in the upper programming and the allocation of requirements is proposed in the lower programming.The application of the model and its algorithm are illustrated with a practical example.     

Improved BP Algorithm in Vibration Failure Diagosis of Steam Turbine-Generator Set

A failure diagnosis model of neural networks for the vibration failure feature of steam turbine-generator set is established on the basis of the improved BP algorithm ,and used for diagnosing practical generator set,the results of verification show that the method is effective.     

基于数值预报产品的地表温度预报方法研究

为了开展地表温度预报业务,提高逐日地表温度预报准确率,利用2007—2012年的ECMWF和T213数值预报产品资料及抚顺市的逐日地表温度资料,采用逐步回归分析方法和BP神经网络模型分别构建抚顺市地表温度预报模型,并对模型的精度进行检验。结果表明,地表温度与ECMWF的高度场、海平面气压场、温度场和T213的散度场、高度场、海平面气压场、地面气压场、海平面K指数、水汽通量、相对湿度、温度场、地面气温和场涡度场均呈显著相关。对预报模型进行精度检验显示,地表平均温度和地表最低温度的预报效果较好,≤3℃预报准确率均达到79%以上。2种模型对比显示,BP神经网络预报模型总体上优于逐步回归预报模型;逐步回归预报模型较BP神经网络预报模型稳定。     

Feed-forward Neural Network Based onGaussNewton-NL2SOL Algorithm and Its Application

Though the feed forward neural network based on GaussNewton algorithm and its derivation will converge with order two, it is only effective toward little residual problem. In order to solve the little and large residual problems at the same time, NL2SOL algorithm is introduced and combined with the GaussNewton algorithm so as to form a feed forward neural network based on GaussNewton-NL2SOL algorithm. The application shows that this neural network can solve the residual problem properly and the convergence and stability of it performs well.     

An optimal equivalent subchannel algorithm for low voltage power line communication system

According to the low voltage power line channel features,combined with adaptive bit loading and power allocation algorithm,an optimal equivalent subchannel algorithm is proposed.Under the condition of fixed amount of transmitted bits and the minimum transmitted power model,impact of optimal equivalent subchannel on the system performance is studied.The optimization algorithm sorts subchannels with similar transmission features into groups,thus the signaling load can be reduced,and the spectrum can be better used.The simulation results show that system can get lower bit error rate(BER) by adopting optimal equivalent subchannel algorithm.     

基于布谷鸟搜索神经网络的微波加热温度预测模型

微波加热是一种与被加热物直接相互作用的选择性加热方式,具有清洁、节能、减排等特点。针对工业物料作为微波加热负载时,其温度非线性变化的特点,以微波工业加热过程中的多维、海量参数为研究对象,基于泛函接神经网络模型提取样本数据的深度特征,提出了一种基于布谷鸟搜索算法,优化BP神经网络的网络参数,建立了以"数据驱动"为手段微波加热工业物料温度模型。仿真实验结果证明了所提出模型的准确性、实时性。