China Petroleum Processing and Petrochemical Technology Simulation and Optimization

2016, Vol. 18, No. 3, pp 102-109

September 30, 2016

Prediction of Coke Yield of FCC Unit Using Different Artificial Neural Network Models Su Xin; Wu Yingya; Pei Huajian; Gao Jinsen; Lan Xingying (State Key Laboratory of Heavy Oil Processing, China University of Petroleum, Beijing 102249) Abstract: In fluid catalytic cracking (FCC) unit, it is greatly important to control the coke yield, since the increase of coke yield not only leads to the reduction of total liquid yield, but also affects the heat balance and operation of FCC unit. Consequently, it is significant to predict the coke yield accurately. The coke formation and burning reactions are affected by many parameters which influence each other, so it is difficult to establish a prediction model using traditional models. This paper combines the industrial production data and establishes a generalized regression neural network (GRNN) model and a back propagation (BP) neural network model to predict the coke yield respectively. The comparison and analysis results show that the accuracy and stability of the BP neural network prediction results are better than that of the GRNN. Then, the particle swarm optimization to optimize BP neural network (PSO-BP) and genetic algorithm to optimize the BP neural network (GA-BP) were further used to improve the prediction precision. The comparison of these models shows that they can improve the prediction precision. However, considering the accuracy and stability of the prediction results, the GA-BP model is better than PSO-BP model. Key words: FCC; coke yield; GRNN neural network; BP neural network

1　Introduction Fluid catalytic cracking (FCC) is one of the important processes for converting the heavy petroleum hydrocarbons into light oil products including dry gas, LPG, gasoline and diesel and into by-products, such as slurry oil and coke, at high temperature and in the presence of catalyst. Currently, the residual FCC (RFCC) dominates the catalytic cracking techniques in China and the residual oil is co-processed in more than 95% of the RFCC units[1]. As feedstock oil becomes increasingly heavier and inferior, the coke yield increases in the FCC process. The coke is formed from the condensation reaction during the cracking of feedstock oil. The increase of the coke yield will decrease the yields of the desired light oil products like gasoline and diesel. The coke will deposit on the surface of the catalyst, which reduces the catalytic activity of the catalyst and further reduces the yield of the light oil products[2]. In addition, the coke yield in the FCC process determines the heat balance[3] and the fluctuation of the coke yield will affect the heat balance of the unit and increase the operation complexity[4]. Therefore, it is of great impor·

102 ·

tance to control the coke yield at lower levels and a small scale fluctuation to improve the operating stability and to increase economic benefits, which is highly dependent on the prediction of the coke yield of the unit accurately under its current state. The coke yield is closely related to the reaction extent of feedstock oil and also to the regeneration process of the catalyst. The FCC process is complex and continuous and involves large amount of reactions, which are complicated[5] and are affected by the properties of feedstock oil, the activity of catalyst and the operating conditions of the reaction-regeneration system. It is difficult to describe the whole reaction process in the FCC with traditional models[6]. Currently, the establishment of the mathematical models based on the data analysis has become a new tool to deal with the FCC process. The artificial neural network (ANN) is a promising modeling technique which tries to simulate the brain’s problem solving process. ANN can deal with non-linear problems and it has strong ability of self-learning and Received date: 2016-03-07; Accepted date: 2016-04-24. Corresponding Author: Dr. Lan Xingying, E-mail: lanxy@ cup.edu.cn.

Su Xin, et al. China Petroleum Processing and Petrochemical Technology, 2016, 18(3): 102-109

self-adaptation. ANN has the ability of parallel processing and can deal with the multivariable systems and nonlinear problems[7-9]. Currently, some mature techniques of the neural network include the Back Propagation (BP) Neural Network[10], the General Regression Neural Network (GRNN)[11], the Radial Basis Function (RBF) Neural Network[12], etc. Guo, et al.[13] applied the GRNN neural network to develop a model for the thickness of the heavy and medium plate mill and it was found that this technique could correctly predict the change of the thickness of the mill bar and the relative error was small, and in addition, the accuracy and the stability of the GRNN were better than the BP neural network. Fan, et al. [14] applied the BP neural network to develop a model in order to predict the power of the wind-driven generator and they also developed a model to predict the error, and they confirmed the feasibility of the BP neural network in predicting the power of the wind-driven generator and its error. Zhang, et al.[15] applied the genetic algorithm (GA) to optimize the BP neural network and they developed a model to improve the prediction accuracy for the gasoline yield of RFCC unit. Their results showed that the optimized BP neural network had better accuracy. According to the previous studies, different neural networks have their merits and demerits in dealing with different systems. However, none of the current neural networks can directly predict the coke yield of FCC process based on the actual production data. Therefore, the models, which are based on the GRNN, the BP neural network and the optimized neural network for predicting the coke yield of a FCC unit, have been developed in the present study. 2　Neural Network With the development of computer science and data analysis techniques, the approach of mathematical modeling emerges and its typical application of the mathematical modeling is to predict the future development of an event based on the neural network technique. ANN tries to simulate the function of human brain and it can achieve linear and non-linear mapping with the network and it can simulate the actual working conditions. The merits of ANN can be listed as follows: (1) It can approximate any non-linear mapping

theoretically; (2) It can deal with multivariable systems; (3) It can perform parallel distributed computing; (4) It has strong ability of self-learning and self-adaptation; and (5) It can simultaneously deal with various qualitative and quantitative data. Recently, the ANN has been widely applied[16], while the GRNN[17] and the BP neural network[18] have been predominating in the application field. 2.1　GRNN The GRNN was developed by Specht D. F. in 1991, and it is a radial basis network [19] which is often applied for function approximation. The GRNN is capable of dealing with non-linear mapping characteristic of high fault-tolerance and robustness. The GRNN is strong in approximation, self-learning and dealing with non-linear problems efficiently. The GRNN has been widely used in fields like signal processing, control decision system and financial sector. The GRNN has four layers as shown in Figure 1, viz.: the input layer, the pattern layer, the summation layer and the output layer. The format for the input is X=[x1, x2, …, xn]T and that for the output is Y=[y1, y2, …, yk]T.

Figure 1　The topological structure of GRNN

(1) Input layer: the number of neurons in this layer is equal to the number of the input vector dimensions in the sample and the neuron will propagate the input variable into the pattern layer. (2) Pattern layer: the number of neurons in this layer is equal to the number of samples in the training set.

 ( X − X i )T ( X − X i )  Pi = exp  −  2σ 2  

i = 1, 2, L,n

(1)

Equation (1) is the transfer function of neurons in the pattern layer. The output variable of neurons i can be expressed as the index of the square with the square of the ·

103 ·

Su Xin, et al. China Petroleum Processing and Petrochemical Technology, 2016, 18(3): 102-109

Euclid distance between the input variable and the corresponding sample X, D2i =(X-Xi)T×(X-Xi), in which X is the output variable and Xi refers to the corresponding learning sample of neurons i. (3) Summation layer: two kinds of neurons are usually used for summation and one is

 ( X − X i )T ( X − X i )  (2) exp ∑ −  2σ 2 i =1   and this equation arithmetically sums the output neurons from the pattern layer, and the connection weights between the pattern layer and every neuron is 1, with the transfer function equating to n

n

S D = ∑ Pi Another equation is n

 ( X − X i )T ( X − X i )   2σ 2  

∑ Y exp − i =1

i

(3)

i =1

(4)

and this equation performs weighted summation for the output neurons from the pattern layer. The connection weights between the neuron i in the pattern layer and the neuron j in the summation layer is the jth element of the ith output neuron Yi. And the propagation function is n

S Nj = ∑ yij Pi i =1

j = 1, 2, L , k

(5)

(4) Output layer: the number of neurons in the output layer is equal to the output vector dimensions k in the sample. 2.2　BP neural network BP neural network [18] is a neural network with multilayer and feed-forward. The BP neural network is characterized by the forward propagation of signals and backward propagation of errors. The S-shaped function (Log-Sigmoid or Tan-Sigmoid) is usually selected as the propagation function. The BP neural network contains three layers, namely: the input layer, the hidden layer and the output layer. If the output layer cannot output the desired result, the BP neural network will move backwards and return the error through the original path along which the signal is propagated. By modifying the weighted and the threshold values, the error signal can be minimized. The structure of the BP neural network is shown in Figure 2. ·

104 ·

Figure 2　The topological structure of BP neural network

3　Modelling Method 3.1　The pretreatment of industrial data More than 550 monitor data points were collected, based on the industrial data from the DCS system of a RFCC unit. According to the reaction-regeneration process of the FCC unit, 28 key parameters influencing the coke yield were selected and the production data spanning two months were studied. These data were pretreated based on the following principle: Each parameter had an effective value and its average value was used to substitute the odd value so that the time and frequency of the data collection were unified. 1 295 sets of data were obtained after pretreatment as shown in Table 1. The values of the parameters in Table 1 were regarded as the input values and the coke yields as the output values. 647 sets of the total data were selected as the training set and others were treated as the samples for prediction. 3.2　Development of the GRNN model The GRNN model was developed with the neural network toolbox in Matlab, and the development steps are shown as follows: Step 1: input the data for training and prediction; Step 2: use the newgrnn function to develop the GRNN for training and prediction; Step 3: use the trained GRNN to predict. 3.3　Development of the BP neural network model With the neural network toolbox of Matlab, the BP neural network model was developed as follows: Step 1, input data for training and prediction. Step 2, use the mapminmax function to normalize the data.

Su Xin, et al. China Petroleum Processing and Petrochemical Technology, 2016, 18(3): 102-109 Table 1 Data after pretreatment Sample points

Parameters

S1

S2

……

S1294

S1295

Flow rate of feedstock oil, t/h

136.38

148.89

……

149.89

147.59

Flow rate of hot vacuum gas oil, t/h

31.853

32.378

……

41.411

41.45

Flow rate of cold vacuum gas oil, t/h

39.429

23.195

……

3.24

4.021

Flow rate of feed vacuum gas oil, t/h

120.65

120.02

……

106.568

113.616

Flow rate of cold residual oil, t/h

0

0.06

……

0.057

0

Flow rate of feed residual oil, t/h

26.922

27.256

……

23.422

25.433

Flow rate of recycled slurry oil, t/h

20.008

19.075

……

25.273

24.455

Flow rate of feed cycled oil, t/h

0.373

10.943

……

20.591

12.354

Flow rate of recycled catalyst, t/h

468.49

694.85

……

571.025

549.646

Flow rate of pre-lifting steam, t/h

0.572 54

0.547 94

……

1.608 20

1.618 62

8.394 3

8.225 1

……

8.585 26

8.069 79

Flow rate of main air for coke combustion, m /min

399.25

400.32

……

399.60

400.46

Reaction pressure, MPa

0.169

0.174

……

0.167

0.174

Regeneration pressure drop at the slide valve, kPa

67.646

72.991

……

69.532

69.967

Feed temperature at the inlet, ℃

220.83

229.53

……

251.56

242.47

Temperature at the pre-mixing part, ℃

691.24

676.66

……

678.54

681.48

Temperature at the bottom of the secondary reactor, ℃

503.51

505.43

……

496.96

503.43

Reaction temperature, ℃

524.32

523.67

……

525.13

523.44

Temperature at the outlet of the secondary reactor, ℃

499.62

505.84

……

494.43

503.36

Temperature at the top of the coke combustor, ℃

684.02

666.62

……

667.19

673.33

Temperature at the bottom of the coke combustor, ℃

677.11

660.54

……

663.21

672.43

Temperature at the dense phase of the secondary regenerator, ℃

693.19

680.83

……

683.11

686.28

2.24

2.12

……

2.72

2.28

929.4

929.4

……

947.4

944.2

Asphaltenes and resins in feedstock oil, %

11.28

11.28

……

12.82

11.94

Coke content in the spent catalyst, %

1.149

1.158

……

1.17

1.238

Coke content in the regenerated catalyst, %

0.12

0.139

……

0.096

0.143

67

63

……

66

69

6.113

7.161

……

8.305

7.512

Flow rate of atomization steam, t/h 3

Carbon residue in feedstock oil, % Density of feedstock oil (20℃ ), kg/m

3

Micro-reaction activity index of the regenerated catalyst, % Coke yield, %

Step 3, use the newff function to develop the BP neural network for training and prediction; Step 4, renormalize the data from Step 3 and obtain the predicted results. The normalization equation is shown in Equation (7), X − X min X norm = (7) X max − X min In the present work, the values from 28 key parameters are normalized and regarded as the input values, and

the coke yield after renormalization is the output value. Therefore, the number of neurons is 28, with each one assigned for the input layer and the output layer, respectively. The number of nodes in the hidden layer is obtained from Equation (8) [12],

H = m + n + L (1 ≤ L ≤ 10) (8) where m is the node number in the input layer and n is the node number in the output layer. According to Equation (8), the number of nodes in the ·

105 ·

Su Xin, et al. China Petroleum Processing and Petrochemical Technology, 2016, 18(3): 102-109

hidden layer varies from 6 to 16. The S-shaped propagation function (Tan-Sigmoid) is applied between the input layer and the hidden layer, and the linear propagation function is applied between the hidden layer and the output layer. The newff function is used for data training. The comparison of the relative errors between different hidden layers shows that the prediction is the best when the node number in the hidden layer is 12. Therefore, the present work is based on the 28-12-1 topological structure of BP neural network model. 3.4　PSO optimized BP neural network model (PSO-BP) PSO is an optimization algorithm based on the theory of swarm intelligence[20] and it is effective in global searching which can converge rapidly. Through the cooperation and competition of particles in the swarm, the searching is intellectually instructed and optimized. All the particles are updated at each iteration until a new generation set of particles is obtained. The optimization steps are shown as follows: Step 1: It starts with parameter initialization, including the size of the swarm, the acceleration coefficient, the learning rate and the iteration times; Step 2: Upon setting the end criterion, the algorithm will come to an end if the results are desired or the iteration times will exceed the upper limit. Otherwise, Step 1 will be executed; Step 3: For each particle, it propagates forward in the network and the error is evaluated for the output value; Step 4: During the iteration of the PSO algorithm, each particle updates its velocity and position according to its own extremum and the global extremum in order to find the value in its best position (P-best); Step 5: For each particle, the value in its best position (P-best) and the value in the historical best position (G-best) of the swarm are compared. If P-best is better than the G-best, the P-best is regarded as the new G-best or otherwise, the G-best is unchanged; Step 6: The best position of the swarm is used to update the weight and the threshold value of the BP neural network; Step 7: If the end criterion is achieved, the algorithm will be ended, or otherwise Step 4 will be performed. 3.5　GA optimized BP neural network model (GA-BP) GA is an optimization algorithm with the ability of par·

106 ·

allel random search [21]. GA is designed to mimic the principles of evolution in natural genetic system with the ‘survival of the fittest’. The GA can solve linear and non-linear problems by searching all regions of the state space and finding the promising area through operations of mutation, crossover, and selection, which are applied to individuals in the population[22]. The optimized initial weight and threshold value from the GA will improve the accuracy and stability of the BP neural network. The optimization steps are as follows: Step 1: The code for the weight value (threshold value) can randomly generate a group of linked weight value (threshold value) for the neural network; Step 2: Input the sample for training and calculate the error and define the total sum of absolute error as the fitness function. Lower error means a lower fitness; Step 3: Select the individual with lower fitness and pass down to the next generation; Step 4: Through operations of crossover and mutation for the current generations, new generations will be formed; Step 5: Repeat Step 2 to Step 4 in order to update the initial weight value (threshold value) for the neural network until the fitness of the evolution generation is unchanged. 4　Results and Discussion There are 1 295 groups of data after the pretreatment of industrial data. 647 groups are selected randomly as the training samples and the others are considered as the testing samples. The GRNN and BP neural network models are developed by using the training samples and tested by the testing samples. Then we use the GA and PSO to optimize the BP neural network to improve the accuracy and stability and compare the results of different prediction models. 4.1　Comparison between GRNN and BP neural network models The prediction models for the coke yield were developed based on the GRNN and the BP neural networks, respectively. The predicted coke yields were compared with industrial production data as shown in Figure 3. Figure 3 shows that the two models can both accurately predict the coke yield[23].

Su Xin, et al. China Petroleum Processing and Petrochemical Technology, 2016, 18(3): 102-109

Figure 5 further shows the comparison between the prediction results and the industrial production data, indicating that the BP model gave smaller prediction errors than the GRNN model.

Figure 3　Comparison between the industrial and predicted coke yield from GRNN and BP neural network models ■—Industrial data; ●—GRNN model; ▲—BP model

A part of Figure 3 was magnified for comparison analysis. During the time interval of 100—200 h and 500—600 h as shown in Figure 4, the trend from the predictions with BP neural network model agrees well with industrial production data, while the predictions by the GRNN model deviate from the industrial production data sometimes, indicating that the BP neural network model is better than the GRNN model.

Figure 5　Comparison between the prediction results from GRNN and BP neural network models and the industrial production data ■—GRNN model; ●—BP model

4.2　Comparison between the PSO and GA optimized BP neural network models Since the initial weight value and threshold value were random in the BP neural network, the optimum initial weight value and threshold value were determined with the PSO and GA separately[24]. The prediction model for the coke yield is developed based on the PSO and GA optimized BP neural network. The predicted coke yields obtained from these two optimized models were compared with the industrial production data as shown in Figure 6. Figure 6 shows that the predicted coke yields from these two models agree well with the industrial data[25-26]

Figure 4　Comparison between the industrial and predicted

Figure 6　Comparison between the industrial and predicted

coke yield originated from GRNN and BP neural network

coke yield originated from PSO-BP and GA-BP neural

models at some time intervals

network models

■—Industrial data; ●—GRNN model; ▲—BP model

■—Industrial data; ●—GA-BP model; ▲—PSO-BP model ·

107 ·

Su Xin, et al. China Petroleum Processing and Petrochemical Technology, 2016, 18(3): 102-109

and a limited difference between these two model predictions can be observed. Figure 7 further shows the comparison between the industrial data and the prediction results obtained from the two optimized models. Figure 7 indicates that the trend of the GA-BP model is different from that of the PSO-BP model. While the prediction results from the two models agrees well with the industrial production data, the predicted coke yields obtained from the PSO-BP model largely fluctuate around the industrial production data, indicating to a larger error than GA-BP model. Therefore, the GABP model is better than the PSO-BP model in predicting the coke yield.

Figure 7　Comparison between the prediction results obtained from PSO-BP and GA-BP neural network models and industrial production data ■—GA-BP model; ●—PSO-BP model

The equations (9)—(11) are applied to calculate the average relative error and the mean square error (MSE), with the results shown in Table 2. Y - Xi (9) µi = i × 100% Xi n



µ=

∑µ i =1

i

n



n



MSE =

∑ (Y - X ) i =1

i

n

i

Table 2　Results obtained from different models Average relative error, %

MSE

GRNN

4.45

0.250

BP

3.40

0.127

PSO-BP

3.05

0.112

GA-BP

2.94

0.111

Neural network model

and stability than the original BP neural network model. Therefore, the GA-BP model is the best in predicting the coke yield for RFCC unit among the four models. 5　Conclusions Based on the FCC process, 28 key parameters (involving feedstock oil, catalyst and operating conditions) influencing the coke yield of the FCC unit were selected as the input values and the coke yield as the output value for establishing GRNN, BP, PSO-BP and GA-BP neural network models. The following conclusions can be obtained: 1) The prediction models for the coke yield can be developed with GRNN and BP neural network based on the industrial production data. 2) The BP neural network model is better in predicting the coke yield of the FCC unit than the GRNN model. 3) The optimized algorithm can provide the optimized initial weight value and threshold value, which can improve the accuracy and stability of the BP neural network model. 4) The optimized PSO-BP and GA-BP models can achieve better accuracy than the BP neural network model without optimization. The GA-BP model is also better in stability than the PSO-BP model. The GA-BP neural network model is better in predicting the coke yield of the FCC unit.

(10)

References [1]　Mi Yingze. Study on optimization technology of 1.2 Mt/a

2



(11)

vacuum residue RFCC unit [J]. Energy Chemical Industry, 2015, 36(2): 35-38 (in Chinese)

where μ is the average relative error, μi is the relative error, n is the sample number, MSE is the mean square error, Xi is the actual value and Yi is the predicted value.

[2]　Xu Chunming, Yang Zhaohe. Petroleum Processing Engi-

Table 2 indicates that the BP neural network model gives a smaller prediction error than the GRNN model. The optimized BP neural network model is better in accuracy

[3]　Chen Junwu. FCC Technology and Engineering [M].

·

108 ·

neering [M]. Beijing: Petroleum Industry Press. 2009: 294315 (in Chinese) Beijing: China Petrochemical Press, 2005: 896-901 (in Chinese)

Su Xin, et al. China Petroleum Processing and Petrochemical Technology, 2016, 18(3): 102-109 [4]　Cao Hanchang, Hao Xiren, Zhang Han. FCC Process Cal-

method for prediction of gasoline yield of RFCCU [J].

culation and Technical Analysis [M]. Beijing: Petroleum

Petroleum Processing and Petrochemicals, 2014, 45(7):

Industry Press. 2000: 150-153 (in Chinese)

91-96 (in Chinese)

[5]　Li Wei. Studies on Process Modeling and Its Application

[16]　Zhu Daqi. The research progress and prospects of artificial

for Catalytic Cracking [D]. Zhejiang University, 2010 (in

neural networks [J]. Journal of Jiangnan University (Natural

Chinese)

Science Edition), 2004, 3(1): 103-110 (in Chinese)

[6] Michaelopoulos J, Papadokonstadakis S, Arampatzis G, et

[17] Liao Zhiwei, Ye Qinghua, Wang Gang, et al. Adaptive

al. Modelling of an industrial fluid catalytic cracking unit

multi-fault diagnosis of power system based on GRNN [J].

using neural networks [J]. Chemical Engineering Research

Journal of South China University of Technology (Natural

　

and Design, 2001, 79(2): 137-142

　

Science Edition), 2005, 33(9): 6-9 (in Chinese)

[7]　Liu Chunyan, Ling Jianchun, Kou Linyuan, et al. Perfor-

[18] Mao Yingke, Guan Zhicheng, Wang Liming, et al. Predic-

mance comparison between GA-BP neural network and BP

tion of leakage current of outdoor insulators based on BP

neural network [J]. Chinese Journal of Health Statistics,

artificial neural network [J]. Proceedings of the CSEE,

2013, 30(2): 173-176+181 (in Chinese) [8]　Deswal S, Pal M. Artificial neural network based modeling of evaporation losses in reservoirs [J]. International Journal of Mathematical, Physical and Engineering Sciences, 2008, 2(4): 177-181 [9]　Hao Xin. The Study of General Regression Neural Network and Genetic Algorithms and their Application for Chemical Engineering [D]. Zhejiang University, 2004 (in Chinese) [10]　Ding Yun, Yu Jingjiang, Zhou Chunhui. Quality estimation and supervision for a crude distillation column [J]. Petroleum Processing and Petrochemicals, 1994, 25(5): 23-28 (in Chinese) [11]　Zhao Chuang, Liu Kai, Li Diansheng. Freight volume forecast based on GRNN [J]. Journal of the China Railway Society, 2004, 26(1): 12-15 (in Chinese)

　

2007, 27(27): 7-12 (in Chinese) [19] Specht D F. A general regression neural network [J]. IEEE 　

Transactions on Neural Networks, 1991, 2(6): 568-576 [20]　Zeng Wanli, Wei Renyong, Chen Hongling. Research and application of BP neural network based on improved PSO algorithm [J]. Computer Technology and Development, 2008, 18(4): 49-51 (in Chinese) [21]　Wang Xiaochuan, Shi Feng, Yu Lei, et al. Matlab Neural Network 43 Case Studies [M]. Beijing: Beihang University Press, 2013: 20-32 (in Chinese) [22] Hou Mandan. Modeling and Optimization for the Pro　

cedure of Reaction Regeneration of Catalytic Cracking Based on Genetic Algorithms[D]. Harbin: Harbin Institute of Technology, 2007 (in Chinese) [23] Lu Chunhua, Liu Ronggui. Carbonation depth prediction 　

[12] Wang Wenxin, Pan Lideng, Li Rong, et al. Development

of pre-stressed concrete based on artificial neural network

of RBF neural network with double model structure and its

[J]. Journal of Harbin Institute of Technology, 2008,

　

application to atmospheric and vacuum distillation units

40(10): 1649-1652 (in Chinese)

[J]. Journal of Beijing University of Chemical Technology

[24] Wang Chongjun, Yu Wendi, Chen Zhaoqian, et al. A BP

(Natural Science Edition), 2004, 31(5): 23-28 (in Chinese)

neural network algorithm based on genetic algorithms and

[13]　Guo Bin, Meng Lingqi, Du Yong, et al. Thickness predic-

its application [J]. Journal of Nanjing University (Natural

tion of medium plate mill based on GRNN neural network [J]. Journal of Central South University (Science and Technology), 2011, 42(4): 960-965 (in Chinese)

　

Sciences), 2003, 39(5): 459-466 (in Chinese) [25] Chen Shouyu, Wang Dagang. Study on distribution of total 　

amount of drainage water pollutant in a region [J]. Journal

[14]　Fan Gaofeng, Wang Weisheng, Liu Chun, et al. Wind

of Hydraulic Engineering, 2003, 05: 116-121 (in Chinese)

power prediction based on artificial neural network [J].

[26]　Li Zuoyong, Wang Jiayang, Guo Chun, et al. A new

Proceedings of the CSEE, 2008, 28(34): 118-123 (in

method of BP network optimized based on particle swarm

Chinese)

optimization and simulation test [J]. Acta Electronica

[15]　Zhang Zhongyang, Li Zeqing, Li Yulong, et al. GA-ANN

Sinica, 2008, 36(11): 2224-2228 (in Chinese)

·

109 ·