Intelligent Prediction on the Quality of Cementing

2011 ◽  
Vol 84-85 ◽  
pp. 373-377
Author(s):  
Wei Zhang Wang
Keyword(s):  
Neural Network ◽  
Fuzzy Neural Network ◽  
Influential Factor ◽  
Software Systems ◽  
Neural Network Modeling ◽  
Quality Prediction ◽  
Modeling Tools ◽  
Fuzzy Neural ◽  
Neural Network System

The present solutions of well cementing are mostly designed by designers’ experience and calculation which can not predict the engineering quality after application of the designs. Meanwhile some questions in the designs can not be solved before construction. On the basis of detailed evaluation of every influential factor according to construction and environmental conditions, this article provides cementing fuzzy neural network model by means of 2nsoftEditor neural network modeling tools, and the stable software systems with the combination of artificial neural network and fuzzy logic rules are expected to improve the credibility of cementing quality prediction. Construction practice shows that cementing quality prediction with application of fuzzy neural network system before cementing can greatly reduce the cementing costs and improve the cementing success ratio.

Development and Research of Intelligent PID Controller Based on Fuzzy Neural Network

2014 ◽  
Vol 644-650 ◽  
pp. 341-345
Author(s):  
Ming Jun Li ◽  
Hua Tian ◽  
Xiao Jing Guo
Keyword(s):  
Neural Network ◽  
Intelligent Control ◽  
Pid Controller ◽  
Fuzzy Neural Network ◽  
Network System ◽  
Validity And Reliability ◽  
Fuzzy Neural ◽  
Neural Network System ◽  
Intelligent Pid ◽  
Matlab Programming

In this paper, intelligent fuzzy control theory is introduced in the model of neural network algorithm, and the neural network system is improved by the PID controller, which has realized the feedback and adjustment function of neural network system, and has made the reaction of the system be more accurate and stable. In order to verify the validity and reliability of the designed intelligent control PID algorithm based on the fuzzy neural network in this paper, the algorithm is carried on the programming by using Matlab programming software, and the control process of PID is calculated by NNbox simulation toolbox, at last, it has obtained the curve of PID control response changing over time. From the response curve, it can be seen that after the PID proportional coefficient is regulated by using fuzzy neural network intelligent control algorithm, it can quickly and steadily obtain the control curve, which has realized better intelligent control effect, and has provided technical reference for the research of intelligent PID controller.

Intelligent Analogy on Wireless Communication Link Performance of Industry Wireless Sensor Networks

2011 ◽  
Vol 317-319 ◽  
pp. 366-369
Author(s):  
Guang Zhu Chen ◽  
Cheng Ming Luo
Keyword(s):  
Neural Network ◽  
Wireless Sensor Networks ◽  
Sensor Networks ◽  
Fuzzy Neural Network ◽  
Environmental Parameters ◽  
Wireless Sensor ◽  
Neural Network Modeling ◽  
Communication Link ◽  
Key Factor ◽  
Fuzzy Neural

The received signal strength indication (RSSI) is the key factor in the communication link for industry wireless sensor networks, while it is very difficult to model the value of RSSI to the distance of two communication nodes. This paper presented a fuzzy neural network modeling method to solve the shortcoming of the theoretical modeling. After the value of RSSI and the distance value of two communication nodes are fuzzed by Gaussian membership function, a fuzzy controlling rule is also presented, and then the output value of fuzzy neural network, namely the error distance of two communication nodes can be attained. Finally, simulation results show that without correcting the environmental parameters, the estimated error value of the distance of two communication nodes through RSSI in fuzzy neural network model is less than in quadratic fit method. So, the method presented by this paper can provide precise data support for wireless sensor networks for industry environment.

Sign in / Sign up

Export Citation Format

Share Document