Application of Artificial Neural Network Strategies in Process Control

In the traditional optimization mathod, the process control parameters for fully mechanized mining face are determined by experts or technicians based on their own experience, which is lack of scientific basis, and need long production adjustment cycle. It is cause large loss, and not conducive to improving mine production efficiency. In order to solve this problem, the study proposes a process control parameter optimization method based on a mixed strategy of artificial neural network and genetic algorithm and uses a cross-entropy cost function to optimize an artificial neural network, which improves the learning speed and fitting accuracy of the neural network. Using the historical production data of a fully mechanized coal mining face, taking the pulling speed of the shearer, hydraulic support moving speed, chain speed of scraper conveyor, chain speed of stage loader, emulsion pump outlet pressure, and spray pump outlet pressure as the optimization objects and taking the value range of each process control parameter as a constraint condition to establish a mixed strategy optimization model of process control parameters for a fully mechanized mining face, each process control parameter is optimized with the output of coal per minute as the optimization goal. The results show that the method has high accuracy and short optimization process time and can effectively improve the production efficiency of the working face.

Download Full-text

Recognition of Process Disturbances for an SPC/EPC Stochastic System Using Support Vector Machine and Artificial Neural Network Approaches

Abstract and Applied Analysis ◽

10.1155/2014/519705 ◽

2014 ◽

Vol 2014 ◽

pp. 1-9 ◽

Cited By ~ 2

Author(s):

Yuehjen E. Shao

Keyword(s):

Neural Network ◽

Artificial Neural Network ◽

Support Vector Machine ◽

Process Control ◽

Support Vector ◽

Statistical Process ◽

Artificial Neural ◽

Artificial Neural Network Ann ◽

Process Disturbances ◽

Network Approaches

Because of the excellent performance on monitoring and controlling an autocorrelated process, the integration of statistical process control (SPC) and engineering process control (EPC) has drawn considerable attention in recent years. Both theoretical and empirical findings have suggested that the integration of SPC and EPC can be an effective way to improve the quality of a process, especially when the underlying process is autocorrelated. However, because EPC compensates for the effects of underlying disturbances, the disturbance patterns are embedded and hard to be recognized. Effective recognition of disturbance patterns is a very important issue for process improvement since disturbance patterns would be associated with certain assignable causes which affect the process. In practical situations, after compensating by EPC, the underlying disturbance patterns could be of any mixture types which are totally different from the original patterns. This study proposes the integration of support vector machine (SVM) and artificial neural network (ANN) approaches to recognize the disturbance patterns of the underlying disturbances. Experimental results revealed that the proposed schemes are able to effectively recognize various disturbance patterns of an SPC/EPC system.

Download Full-text

Process control of nonlinear time variant processes via artificial neural network

Proceedings of 26th Southeastern Symposium on System Theory ◽

10.1109/ssst.1994.287886 ◽

2002 ◽

Cited By ~ 2

Author(s):

M. Nikravesh ◽

A. Farell

Keyword(s):

Neural Network ◽

Artificial Neural Network ◽

Process Control ◽

Artificial Neural

Download Full-text

Artificial neural network real-time process control system for small utilities

American Water Works Association ◽

10.1002/j.1551-8833.2007.tb07961.x ◽

2007 ◽

Vol 99 (6) ◽

pp. 132-144

Author(s):

Qing J. Zhang ◽

Riyaz Shariff ◽

Daniel W. Smith ◽

Audrey Cudrak ◽

Stephen J. Stanley

Keyword(s):

Neural Network ◽

Artificial Neural Network ◽

Control System ◽

Process Control ◽

Real Time ◽

Process Control System ◽

Time Process ◽

Artificial Neural

Download Full-text