基于遗传-神经网络方法的广西台风灾害评估模型研究

选取1981—2018年影响广西且灾情记录比较完整的86个台风样本,基于台风灾害伤亡人数、直接经济损失划分灾情等级,选取致灾因子,利用遗传算法与神经网络相结合的方法建立广西台风灾害评估模型。结果表明:选取的台风灾害致灾因子与台风灾情等级之间具有显著的相关性,构建的遗传—神经网络集合预报模型对台风灾情预估效果较好,训练样本拟合一致率为86.1%,测试样本预报准确率为71.4%,其中严重和较重的台风灾情等级预报结果与实况基本一致,较轻等级的预报准确率达83.3%。

Evolving Neural Networks Using an Improved Genetic Algorithm

A novel real coded improved genetic algorithm (GA) of training feed forward neural network is proposed to realize nonlinear system forecast. The improved GA employs a generation alternation model based the minimal generation gap (MGP) and blend crossover operators (BLX α). Compared with traditional GA implemented in binary number, the processing time of the improved GA is faster because coding and decoding are unnecessary. In addition, it needn t set parameters such as the probability value of crossove...

Combining the genetic algorithms with artificial neural networks for optimization of board allocating

This paper introduced the Genetic Algorithms (GAs) and Artificial Neural Networks (ANNs), which have been widely used in optimization of allocating. The combination way of the two optimizing algorithms was used in board allocating of furniture production. In the experiment, the rectangular flake board of 3650 mm 1850 mm was used as raw material to allocate 100 sets of Table Bucked. The utilizing rate of the board reached 94.14 % and the calculating time was only 35 s. The experiment result proofed that the method by using the GA for optimizing the weights of the ANN can raise the utilizing rate of the board and can shorten the time of the design. At the same time, this method can simultaneously searched in many directions, thus greatly in-creasing the probability of finding a global optimum.

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EMD-GA-BP与EMD-PSO-LSSVM的中国碳市场价格预测

由于碳交易市场价格的波动性大及相互影响关系的复杂性,本文试图构建碳价格长期和短期的最优预测模型。考虑到碳交易价格波动的趋势性和周期性特点,基于经验模态分解算法(EMD)、遗传算法(GA)—神经网络(BP)模型、粒子群算法(PSO)—最小二乘支持向量机(LSSVM)模型及由它们构建的组合预测模型,对中国碳市场交易价格进行短期预测和长期预测。实证分析中将影响碳交易价格的不同宏观经济因素和碳价格时间序列因素做为输入变量,分别代入组合模型进行预测。研究结果表明,在短期预测中,EMD-GA-BP模型预测效果优于GABP模型和PSO-LSSVM模型;而在长期预测中,组合模型EMD-PSO-LSSVM模型预测效果优于只考虑碳价格波动趋势性或周期性预测效果。

Evolving Neural Network Using Variable String Genetic Algorithm for Color Infrared Aerial Image Classification

Coastal wetlands are characterized by complex patterns both in their geomorphlc and ecological teatures. Besides field observations, it is necessary to analyze the land cover of wetlands through the color infrared （CIR） aerial photography or remote sensing image. In this paper, we designed an evolving neural network classifier using variable string genetic algorithm （VGA） for the land cover classification of CIR aerial image. With the VGA, the classifier that we designed is able to evolve automatically the appropriate number of hidden nodes for modeling the neural network topology optimally and to find a near-optimal set of connection weights globally. Then, with backpropagation algorithm （BP）, it can find the best connection weights. The VGA-BP classifier, which is derived from hybrid algorithms mentioned above, is demonstrated on CIR images classification effectively. Compared with standard classifiers, such as Bayes maximum-likelihood classifier, VGA classifier and BP-MLP （multi-layer perception） classifier, it has shown that the VGA-BP classifier can have better performance on highly resolution land cover classification.

A neurofuzzy system based on rough set theory and genetic algorithm

This paper presents a hybrid soft computing modeling approach for a neurofuzzy system based on rough set theory and the genetic algorithms (NFRSGA). The fundamental problem of a neurofuzzy system is that when the input dimension increases, the fuzzy rule base increases exponentially. This leads to a huge infrastructure network which results in slow convergence. To solve this problem, rough set theory is used to obtain the reductive rules, which are used as fuzzy rules of the fuzzy system. The number of rules decrease, and each rule does not need all the conditional attribute values. This results in a reduced, or not fully connected, neural network. The structure of the neural network is relatively small and thus the weights to be trained decrease. The genetic algorithm is used to search the optimal discretization of the continuous attributes. The NFRSGA approach has been applied in the practical application of building a soft sensor model for estimating the freezing point of the light diesel fuel in a Fluid Catalytic Cracking Unit (FCCU), and satisfying results are obtained.

Research on extended AHP method with the aid of RST

Analytic Hierarchy Process (AHP) method can be used to solve the tasks of multi-criterion decision system fields, but some complicated questions processed by AHP cannot be easily solved by means of the general method. It is because of being unsatisfied with consistency condition or judgment matrix too intricate to solve, which causes AHP invalidation. So in order to resolve this problem, AHP knowledge systems reduced with the aid of Genetic Algorithms (GA) were proposed, which directly acquired the order of AHP issue through the rule of Rough Sets Theory (RST) method, or solved the tasks reduced by RST with classical AHP method. On this condition, the compare decision system of region informatization level was solved, and the results solved were the same to those by classical AHP, which denoted that this method was more simple and reliable, besides the four rules of changing AHP system into RST Decision System.

Nuclear power plant fault diagnosis based on genetic-RBF neural network

It is necessary to develop an automatic fault diagnosis system to avoid a possible nuclear disaster caused by an inaccurate fault diagnosis in the nuclear power plant by the operator. Because Radial Basis Function Neural Network (RBFNN) has the characteristics of optimal approximation and global approximation. The mixed coding of binary system and decimal system is introduced to the structure and parameters of RBFNN, which is trained in course of the genetic optimization. Finally, a fault diagnosis system according to the frequent faults in condensation and feed water system of nuclear power plant is set up. As a result, Genetic-RBF Neural Network (GRBFNN) makes the neural network smaller in size and higher in generalization ability. The diagnosis speed and accuracy are also improved.

Groundwater level prediction based on hybrid hierarchy genetic algorithm and RBF neural network

As the traditional non-linear systems generally based on gradient descent optimization method have some shortage in the field of groundwater level prediction, the paper, according to structure, algorithm and shortcoming of the conventional radial basis function neural network （RBF NN）, presented a new improved genetic algorithm （GA）： hybrid hierarchy genetic algorithm （HHGA）. In training RBF NN, the algorithm can automatically determine the structure and parameters of RBF based on the given sample data. Compared with the traditional groundwater level prediction model based on back propagation （BP） or RBF NN, the new prediction model based on HHGA and RBF NN can greatly increase the convergence speed and precision.

Optimization of Fermentation Media for Enhancing Nitrite-oxidizing Activity by Artificial Neural Network Coupling Genetic Algorithm

Two artificial intelligence techniques, artificial neural network and genetic algorithm, were applied to optimize the fermentation medium for improving the nitrite oxidization rate of nitrite oxidizing bacteria. Experiments were conducted with the composition of medium components obtained by genetic algorithm, and the experimental data were used to build a BP (back propagation) neural network model. The concentrations of six medium components were used as input vectors, and the nitrite oxidization rate was used as output vector of the model. The BP neural network model was used as the objective function of genetic algorithm to find the optimum medium composition for the maximum nitrite oxidization rate. The maximum nitrite oxidization rate was 0.952 g 2 NO-2-N·(g MLSS)-1·d-1 , obtained at the genetic algorithm optimized concentration of medium components (g·L-1 ): NaCl 0.58, MgSO 4 ·7H 2 O 0.14, FeSO 4 ·7H 2 O 0.141, KH 2 PO 4 0.8485, NaNO 2 2.52, and NaHCO 3 3.613. Validation experiments suggest that the experimental results are consistent with the best result predicted by the model. A scale-up experiment shows that the nitrite degraded completely after 34 h when cultured in the optimum medium, which is 10 h less than that cultured in the initial medium.

Semi-autogenous mill power prediction by a hybrid neural genetic algorithm

There are few methods of semi-autogenous(SAG)mill power prediction in the full-scale without using long experiments.In this work,the effects of different operating parameters such as feed moisture,mass flowrate,mill load cell mass,SAG mill solid percentage,inlet and outlet water to the SAG mill and work index are studied.A total number of185full-scale SAG mill works are utilized to develop the artificial neural network(ANN)and the hybrid of ANN and genetic algorithm(GANN)models with relations of input and output data in the full-scale.The results show that the GANN model is more efficient than the ANN model in predicting SAG mill power.The sensitivity analysis was also performed to determine the most effective input parameters on SAG mill power.The sensitivity analysis of the GANN model shows that the work index,inlet water to the SAG mill,mill load cell weight,SAG mill solid percentage,mass flowrate and feed moisture have a direct relationship with mill power,while outlet water to the SAG mill has an inverse relationship with mill power.The results show that the GANN model could be useful to evaluate a good output to changes in input operation parameters.

Model of Land Suitability Evaluation Based on Computational Intelligence

A novel model of land suitability evaluation is built based on computational intelligence (CI). A fuzzy neural network (FNN) is constructed by the integration of fuzzy logic and artificial neural network (ANN). The structure and process of this network is clear. Fuzzy rules (knowledge) are expressed in the model explicitly, and can be self-adjusted by learning from samples. Genetic algorithm (GA) is employed as the learning algorithm to train the network, and makes the training of the model efficient. This model is a self-learning and self-adaptive system with a rule set revised by training.

Simulation and Optimization for Thermally Coupled Distillation Using Artificial Neural Network and Genetic Algorithm

In this paper, a new approach using artificial neural network and genetic algorithm for the optimization of the thermally coupled distillation is presented. Mathematical model can be constructed with artificial neural network based on the simulation results with ASPEN PLUS. Modified genetic algorithm was used to optimize the model. With the proposed model and optimization arithmetic, mathematical model can be calculated, decision variables and target value can be reached automatically and quickly. A practical example is used to demonstrate the algorithm.

A REAL-VALUED GENETIC ALGORITHM FOR OPTIMIZATION PROBLEM WITH CONTINUOUS VARIABLES

A real valued genetic algorithm(RVGA) for the optimization problem with continuous variables is proposed. It is composed of a simple and general purpose dynamic scaled fitness and selection operator, crossover operator, mutation operators and adaptive probabilities for these operators. The algorithm is tested by two generally used functions and is used in training a neural network for image recognition. Experimental results show that the algorithm is an efficient global optimization algorithm.

Prediction of resilient modulus for subgrade soils based on ANN approach

The resilient modulus(MR)of subgrade soils is usually used to characterize the stiffness of subgrade and is a crucial parameter in pavement design.In order to determine the resilient modulus of compacted subgrade soils quickly and accurately,an optimized artificial neural network(ANN)approach based on the multi-population genetic algorithm(MPGA)was proposed in this study.The MPGA overcomes the problems of the traditional ANN such as low efficiency,local optimum and over-fitting.The developed optimized ANN method consists of ten input variables,twenty-one hidden neurons,and one output variable.The physical properties(liquid limit,plastic limit,plasticity index,0.075 mm passing percentage,maximum dry density,optimum moisture content),state variables(degree of compaction,moisture content)and stress variables(confining pressure,deviatoric stress)of subgrade soils were selected as input variables.The MR was directly used as the output variable.Then,adopting a large amount of experimental data from existing literature,the developed optimized ANN method was compared with the existing representative estimation methods.The results show that the developed optimized ANN method has the advantages of fast speed,strong generalization ability and good accuracy in MR estimation.

Nonlinear modeling of molten carbonate fuel cell stack and FGA-based fuzzy control

To improve the performance of fuel cells, the operating temperature of molten carbonate fuel cell (MCFC) stack should be controlled within a specified range. In this paper, with the RBF neural network’s ability of identifying complex nonlinear systems, a neural network identification model of MCFC stack is developed based on the sampled input-output data. Also, a novel online fuzzy control procedure for the temperature of MCFC stack is developed based on the fuzzy genetic algorithm (FGA). Parameters and rules of the fuzzy controller are optimized. With the neural network identification model, simulation of MCFC stack control is carried out. Validity of the model and the superior performance of the fuzzy controller are demonstrated.

Prediction of blast-induced ground vibrations via genetic programming

Excessive ground vibrations, due to blasting, can cause severe damages to the nearby area. Hence, the blast-induced ground vibration prediction is an essential tool for both evaluating and controlling the adverse consequences of blasting. Since there are several effective variables on ground vibrations that have highly nonlinear interactions, no comprehensive model of the blast-induced vibrations are available. In this study, the genetic expression programming technique was employed for prediction of the frequency of the adjacent ground vibrations. Nine input variables were used for prediction of the vibration frequencies at different distances from the blasting face. A high coefficient of determination with low mean absolute percentage error(MAPE) was achieved that demonstrated the suitability of the algorithm in this case. The proposed model outperformed an artificial neural network model that was proposed by other authors for the same dataset.

Nonlinear modelling of a SOFC stack by improved neural networks identification

The solid oxide fuel cell (SOFC) is a nonlinear system that is hard to model by conventional methods. So far,most existing models are based on conversion laws,which are too complicated to be applied to design a control system. To facilitate a valid control strategy design,this paper tries to avoid the internal complexities and presents a modelling study of SOFC per-formance by using a radial basis function (RBF) neural network based on a genetic algorithm (GA). During the process of mod-elling,the GA aims to optimize the parameters of RBF neural networks and the optimum values are regarded as the initial values of the RBF neural network parameters. The validity and accuracy of modelling are tested by simulations,whose results reveal that it is feasible to establish the model of SOFC stack by using RBF neural networks identification based on the GA. Furthermore,it is possible to design an online controller of a SOFC stack based on this GA-RBF neural network identification model.

Crashworthiness optimization design of foam-filled tapered decagonal structures subjected to axial and oblique impacts

In this research,crashworthiness of polyurethane foam-filled tapered decagonal structures with different ratios of a/b=0,0.25,0.5,0.75 and 1 was evaluated under axial and oblique impacts.These new designed structures contained inner and outer tapered tubes,and four stiffening plates connected them together.The parameter a/b corresponds to the inner tube side length to the outer tube one.In addition,the space between the inner and outer tubes was filled with polyurethane foam.After validating the finite element model generated in LS-DYNA using the results of experimental tests,crashworthiness indicators of SEA(specific energy absorption)and Fmax(peak crushing force)were obtained for the studied structures.Based on the TOPSIS calculations,the semi-foam filled decagonal structure with the ratio of a/b=0.5 demonstrated the best crashworthiness capability among the studied ratios of a/b.Finally,optimum thicknesses(t1(thickness of the outer tube),t2(thickness of the inner tube),t3(thickness of the stiffening plates))of the selected decagonal structure were obtained by adopting RBF(radial basis function)neural network and genetic algorithm.