基于智能计算方法的水力机组优化运行算法

根据水力机组运行的特点,结合人工神经网络的非线性特性和遗传算法的全局搜索能力特性,给出了使用人工神经网络与遗传算法方法,构造水电厂内水力机组优化运行算法的详细过程,首先使用人工神经网络来构建各机组的动力特性模型,然后利用遗传算法来构建机组间的组合运行策略。将所构造的算法应用于开发石家庄混合蓄能水电厂内机组优化运行系统,系统的仿真运行表明,基于人工神经网络与遗传算法的水力机组优化运行算法具有较高的计算精度,是行之有效的。     

智能控制在电力系统中的应用

近年来,随着人工智能控制理论的不断发展,以模糊技术、人工神经网络和遗传算法为代表的智能控制方法在电力系统领域得到了广泛的应用。本文分别从短期负荷预测的人工神经网络建模与求解、无功优化的遗传算法建模与求解流程,以及发电机电压模糊控制方法下的建模与控制规则三个方面对人工智能控制在电力系统的应用进行了探讨。     

基于人工智能的模锻工艺优化平台开发

针对模锻件成形工艺特点,结合人工神经网络和遗传算法自主开发了模锻工艺优化平台。其中以Visual Basic为程序编程开发平台,以Matlab软件中的工具箱为基础,编程开发了所需的人工神经网络和遗传算法。并将开发的模锻工艺优化平台与有限元方法结合,对某涡轮盘模锻件的模锻成形工艺进行了优化设计,获得了好的结果。     

人工神经网络和遗传算法在导热反问题中的应用

论述了导热反问题在工程实际中的重要性,分析了引入新算法的必要性,简要介绍了人工神经网络和遗传算法;给出了用人工神经网络和遗传算法求解导热反问题的理论基础,建立了用两者求解导热反问题的数学模型,并对作者前期研究的求解结果做了必要分析．综合分析和前期研究结果表明将人工神经网络和遗传算法应用于导热反问题具有重要的理论意义和应用价值,有可能形成一个新的交叉学科,必将对导热反问题的研究起到巨大的推动作用．     

用优化参数降低芳烃抽提过程中丁烷的损耗量

针对如何降低芳烃抽取过程中的丁烷消耗问题，提出优化过程操作参数的解决方法．其中优化问题的模型用人工神经网络来描述，优化方法采用遗传算法．介绍了人工神经网络建模的过程和遗传算法寻优的步骤．     

基于遗传小波网络的舰船购置费预测研究

为克服人工神经网络算法的缺陷，将遗传算法、小波分析、人工神经网络结合起来，用遗传算法来学习小波网络层间的权值、尺度函数和位置函数；建立了基于遗传小波网络的舰船购置费预测模型。实验表明：该模型具有较高的预测精度。     

人工神经网络在虎杖提取过程质量控制的研究

针对人工神经网络收敛速度慢及容易陷入局部最优解的缺点,结合遗传算法全局搜索的特点,提出了一种基于遗传算法和人工神经网络建立近红外透射光谱快速测定虎杖提取液中虎杖苷和白藜芦醇含量的方法。结果表明,模型效果良好,方法简便、准确可靠。与偏最小二乘法(PLS)相比较,该方法具有更高的预测能力,适用性更强,有望应用于药物提取过程的中间控制。     

改进GA算法结合ANN用于酚类化合物的QSAR研究

采用改进的遗传算法(IGA)和BP人工神经网络相结合的方法,研究了50个酚类化合物的麻醉毒性和分子结构之间的相关性,并与单纯用BP人工神经网络建立的模型进行比较.结果表明,该方法克服了人工神经网络训练中的局部最优问题,采用最优交叉和变异等遗传策略,有效地解决了收敛过程中的振荡问题,所得模型的训练精度和预测精度均优于单纯的BP人工神经网络QSAR模型.     

基于神经网络的设备维修计划预测

分析了遗传算法与神经网络的优缺点，在此基础上，将遗传算法与人工神经网络有机结合。此外，利用长期进行的维修记录资料，采用遗传神经网络预测某厂设备维修计划。结果表明该研究工作是可行的，可以作为预测的一种有效手段。     

基于遗传算法的神经网络振动钻削参数优化

应用人工神经网络进行振动钻削仿真与参数优化时常用逆映射BP网 ,而BP网的逆映射极易陷入局部极小点。本文提出利用遗传算法与BP网的混合系统进行参数优化。实验结果表明 ,遗传算法是一种全局优化方法 ,可有效地应用于机械加工领域 ,为振动钻削的参数优化提供了一个新的研究方法。     

Relationship between fatigue life of asphalt concrete and polypropylene/polyester fibers using artificial neural network and genetic algorithm

While various kinds of fibers are used to improve the hot mix asphalt(HMA) performance, a few works have been undertaken on the hybrid fiber-reinforced HMA. Therefore, the fatigue life of modified HMA samples using polypropylene and polyester fibers was evaluated and two models namely regression and artificial neural network(ANN) were used to predict the fatigue life based on the fibers parameters. As ANN contains many parameters such as the number of hidden layers which directly influence the prediction accuracy, genetic algorithm(GA) was used to solve optimization problem for ANN. Moreover, the trial and error method was used to optimize the GA parameters such as the population size. The comparison of the results obtained from regression and optimized ANN with GA shows that the two-hidden-layer ANN with two and five neurons in the first and second hidden layers, respectively, can predict the fatigue life of fiber-reinforced HMA with high accuracy(correlation coefficient of 0.96).     

遗传算法在神经网络趋势预示中的应用

当前旋转机组状态预测神经网络的结构参数主要靠人工经验和实验来确定,网络结构差、预测精度低,因而不能满足复杂工况的工业现场的应用。针对以上特点,结全工业现场的实际工况,利用ＧＡ并行搜索能力对ＢＰ网络结构参数进行动态优化,使神经网络能够根据不同的历史数据,动态的确定最优的网络结构参数,在现场应用中表明,经过遗传算法优化的神经网络在邦联趋势预示中取得了令人满意的在线预测的效果。     

ANN model of subdivision error based on genetic algorithm

According to the test data of subdivision errors in the measuring cycle of angular measuring system, the characteristics of subdivision errors generated by this system are analyzed. It is found that the subdivision errors are mainly due to the rotary-type inductosyn itself. For the characteristic of cyclical change, the subdivision errors in other measuring cycles can be compensated by the subdivision error model in one measuring cycle. Using the measured error data as training samples, combining GA and BP algorithm, an ANN model of subdivision error is designed. Simulation results indicate that GA reduces the uncertainty in the training process of the ANN model, and enhances the generalization of the model. Compared with the error model based on the least-mean-squared method, the designed ANN model of subdivision errors can achieve higher compensating precision     

A Hybrid Artificial Neural Network-based Scheduling Knowledge Acquisition Algorithm

It is a key issue that constructing successful knowledge base to satisfy an efficient adaptive scheduling for the com- plex manufacturing system.Therefore,a hybrid artificial neural network (ANN)-based scheduling knowledge acquisition algo- rithm is presented in this paper.We combined genetic algorithm (GA) with simulated annealing (SA) to develop a hybrid opti- mization method,in which GA was introduced to present parallel search architecture and SA was introduced to increase escaping probability from local optima and ability to neighbor search.The hybrid method was utilized to resolve the optimal attributes subset of manufacturing system and determine the optimal topology and parameters of ANN under different scheduling objectives;ANN was used to evaluate the fitness of chromosome in the method and generate the scheduling knowledge after obtaining the optimal at- tributes subset,optimal ANN's topology and parameters.The experimental results demonstrate that the proposed algorithm pro- duces significant performance improvements over other machine learning-based algorithms.     

基于进化神经网络的齿轮可靠性预测

人工神经网络模型中广泛应用的是BP(BackPropagation)模型 ,针对BP算法存在收敛速度慢 ,容易陷入局部最小点的缺陷 ,本文用遗传算法 (GeneticAlgorithm :GA)训练神经网络 (ArtificialNeuralNetwork :ANN) ,取代了一些传统的学习算法 ,设计了GA +BP学习算法 用遗传算法和神经网络相结合的方法求解了齿轮弯曲疲劳寿命的预测问题 仿真结果表明 ,组合GA与BP可以克服单纯使用BP易陷入局部极小等问题 ,取得了较为满意的效果 ,预测精度较高     

A novel chaotic optimization algorithm and its applications

This paper presents a chaos-genetic algorithm (CGA) that combines chaos and genetic algorithms. It can be used to avoid trapping in local optima profiting from chaos’randomness,ergodicity and regularity. Its property of global asymptotical convergence has been proved with Markov chains in this paper. CGA was applied to the optimization of complex benchmark functions and artificial neural network’s (ANN) training. In solving the complex benchmark functions,CGA needs less iterative number than GA and other chaotic optimization algorithms and always finds the optima of these functions. In training ANN,CGA uses less iterative number and shows strong generalization. It is proved that CGA is an efficient and convenient chaotic optimization algorithm.     

Research on Mineral Resource Prediction by GA-ANN

1　 IntroductionThe research objectives of mineral engineer-ing are usually large systems. Compared withprocessing industry,the mineral industry has itsown features,i.e.the operation objective is natu-ral occurrence of mineral and rock,the operationsite continually moves,and mineral production isa complex process composed of multiple links andprocedures.Therefore,there are two points thatshould be emphasized in the study on mineral en-gineering optimization[1] :1 ) The research on temporary an…     

基于遗传算法的室内热舒适指标PMV的神经网络预测

介绍了人工神经网络对室内热舒适指标PMV进行预测的方法,探索遗传算法与神经网络结合运用,得出了神经网络预测的结果,提出了神经网络预测可用于智能化空调运行的控制。     

结合N-W方法的L-M算法在变压器故障诊断中的应用

在分析Levenberg-Marquardt(L-M)算法和Nguyen-Widrow(N-W)方法原理的基础上,提出了一种多层前馈神经网络训练算法,该算法在使用N—W方法初始化神经网络可变参数的基础上使用L-M算法训练多层前馈神经网络。构造了适合于变压器油中溶解气体分析故障诊断的神经网络,使用了标准BP算法、加动量项BP算法和结合N-W方法的L-M算法训练该网络,结果表明算法收敛速度快、不容易陷入局部极小点。将训练所得网络用于变压器油中溶解气体分析故障诊断,诊断结果验证了该方法的有效性。     

液态挤压工艺ANN/GA建模与优化研究

利用人工神经网络方法(ANN)建立了工艺系统模型,用遗传算法(GA)对过程参数进行优化, 实验结果与预测值吻合良好, 为预测和控制该工艺成形质量提供了行之有效的手段。