Physical and chemical indexes of synthetic base oils based on a wavelet neural network and genetic algorithm

2019 ◽  
Vol 72 (1) ◽  
pp. 116-121 ◽  
Author(s):  
Guomin Wang ◽  
Yuanyuan Wu ◽  
Haifu Jiang ◽  
Yanjie Zhang ◽  
Jiarong Quan ◽  
...  

Purpose The purpose of this paper is to use the wavelet neural network and genetic algorithm to study the effects of polyalphaolefin, TMP108 and OCP0016 on the kinematic viscosity, viscosity index and pour point of lubricating oil. Design/methodology/approach Wavelet neural network is used to train the known samples, test the unknown samples and compare the obtained results with those obtained with a traditional empirical formula. Findings It is found that the wavelet neural network prediction value is closer to the experimental value than the traditional empirical formula calculation value. Originality/value The results show that the wavelet neural network can be used to study the physical and chemical indexes of lubricating oil.

2021 ◽  
Vol 261 ◽  
pp. 03052
Author(s):  
Zhe Lv ◽  
Jiayu Zou ◽  
Zhongyu Zhao

In recent years, more and more people choose to travel by bus to save time and economic costs, but the problem of inaccurate bus arrival has become increasingly prominent. The reason is the lack of scientific planning of departure time. This paper takes the passenger flow as an important basis for departure interval, proposes a passenger flow prediction method based on wavelet neural network, and uses intelligent optimization algorithm to study the bus elastic departure interval. In this paper, the wavelet neural network prediction model and the elastic departure interval optimization model are established, and then the model is solved by substituting the data, and finally the theoretical optimal departure interval is obtained.


2011 ◽  
Vol 121-126 ◽  
pp. 4847-4851 ◽  
Author(s):  
Hui Zhen Yang ◽  
Wen Guang Zhao ◽  
Wei Chen ◽  
Xu Quan Chen

Wavelet Neural Network (WNN) is a new form of neural network combined with the wavelet theory and artificial neural network. The wavelet neural network model based on Morlet wavelet and the corresponding learning algorithm were studied in this paper. And through learning the wavelet neural network model is applied to all kinds of engineering examples, it proved that the wavelet neural network prediction model which has a more flexible and efficient function approximation ability and strong fault tolerance, and with high predicting precision.


2021 ◽  
Author(s):  
Kunyu Cao ◽  
Yongdang Chen ◽  
Xinxin Song ◽  
Shan Liu

Abstract A new sales forecasting model based on an Improved Immune Genetic Algorithm (IIGA), IIGA that optimizes the BPNN (IIGA-BP) has been proposed. The IIGA presents a new way of population initialization, a regulatory mechanism of antibody concentration, and a design method of adaptive crossover operator and mutation operator, which effectively improved the convergence ability and optimization anility of IIGA. And IIGA can optimize the BPNN’s initial weights and threshold and improve the randomness of network parameters as well as the drawbacks that lead to output instability of BPNN and easiness into local minimum value. It taking the past records of sales figures of a certain steel enterprise as an example, utilizing the Matlab to construct the BP neural network, Immune Genetic Algorithm that optimizes the BPNN (IGA-BP), IGA-BP neural network, and IIGA-BP neural network prediction models for simulation and comparative analysis. The experiment demonstrates that IIGA-BP neural network prediction model possessing a higher prediction accuracy and more stable prediction effects.


2019 ◽  
Vol 296 ◽  
pp. 01004
Author(s):  
Shouwei XIE ◽  
Yadong YANG

In recent years, the traffic volume of the Yangtze River has increased dramatically. In order to provide more favorable assistance to port planning and traffic management, the accuracy of port ship traffic volume prediction is very important. In this paper, genetic algorithm and wavelet analysis and neural network are used to construct the genetic wavelet neural network model prediction model, and BP neural network prediction model is established. The ship volume of Jiujiang Port is used as experimental data to simulate and analyze. The results show that the prediction accuracy of the genetic wavelet neural network prediction model is significantly higher than that of the BP neural network prediction model. It is proved that the genetic wavelet neural network has broad application prospects for ship traffic flow prediction in the Yangtze River port. This method has practical application significance.


Sign in / Sign up

Export Citation Format

Share Document