Fault Diagnosis Method of Polymerization Kettle Equipment Based on Rough Sets and BP Neural Network

Polyvinyl chloride (PVC) polymerizing production process is a typical complex controlled object, with complexity features, such as nonlinear, multivariable, strong coupling, and large time-delay. Aiming at the real-time fault diagnosis and optimized monitoring requirements of the large-scale key polymerization equipment of PVC production process, a real-time fault diagnosis strategy is proposed based on rough sets theory with the improved discernibility matrix and BP neural networks. The improved discernibility matrix is adopted to reduct the attributes of rough sets in order to decrease the input dimensionality of fault characteristics effectively. Levenberg-Marquardt BP neural network is trained to diagnose the polymerize faults according to the reducted decision table, which realizes the nonlinear mapping from fault symptom set to polymerize fault set. Simulation experiments are carried out combining with the industry history datum to show the effectiveness of the proposed rough set neural networks fault diagnosis method. The proposed strategy greatly increased the accuracy rate and efficiency of the polymerization fault diagnosis system.

Download Full-text

Intelligent Fault Diagnosis Method Based on Operating Parameters in Nuclear Power Plant

Volume 1: Operations and Maintenance, Engineering, Modifications, Life Extension, Life Cycle and Balance of Plant; I&C, Digital Controls, and Influence of Human Factors ◽

10.1115/icone25-66494 ◽

2017 ◽

Author(s):

Zhiwu Ke ◽

Xu Hu ◽

Dawei Teng ◽

Mo Tao

Keyword(s):

Neural Network ◽

Fault Diagnosis ◽

Real Time ◽

Bp Neural Network ◽

Nuclear Power ◽

Operating Parameters ◽

Feed Water ◽

Mechanical Equipment ◽

Single Fault ◽

Diagnosis Method

The safety of mechanical equipment is more important, it directly determines the safety of nuclear power plant operation, and even nuclear safety. So it is necessary to monitor the operating state of NPP system and mechanical equipment in real time by inspecting operating parameters. However, the key technology is real-time fault diagnosis of the mechanical equipment in NPP. Traditional fault diagnosis method based on analytic model is difficult to diagnose relevant and superimposed fault because of model error, disturbance and noise. This paper studies the application of fault diagnosis method based on BP neural network in NPP, and proposes an improved method for neural BP network method. For the feed-water system in the variable load operation process, we select the normal operation, the single feed-water valve fault, feed-water pump and feed-water valve superimposed fault as the analysis objects. One hundred points of data are extracted as BP algorithm training elements in these three processes averagely. The normal and abnormal conditions (including single fault and superimposed fault) can be accurately judged, but the single fault and superimposed failure would produce miscarriage of justice, about 2.4% of the single fault is diagnosed as superimposed fault, the diagnosis time delay is less than 1 second. These results meet the accuracy and real-time requirements. Then we study the application of support vector machine (SVM), which can make up for the deficiency of BP neural network. The results of this paper are useful for the real-time and reliable fault diagnosis of NPP.

Download Full-text

Research on Fault Diagnosis Method Based Rough Sets Theory and Neural Network

2009 International Forum on Information Technology and Applications ◽

10.1109/ifita.2009.554 ◽

2009 ◽

Author(s):

Zou Wensheng ◽

Zhang Jianlin ◽

Long Chengzhi

Keyword(s):

Neural Network ◽

Fault Diagnosis ◽

Rough Sets ◽

Rough Sets Theory ◽

Diagnosis Method ◽

Sets Theory

Download Full-text

A Fault Diagnosis Method Based on Combination of Neural Network and Fault Dictionary

Advanced Materials Research ◽

10.4028/www.scientific.net/amr.765-767.2078 ◽

2013 ◽

Vol 765-767 ◽

pp. 2078-2081

Author(s):

Ya Feng Meng ◽

Sai Zhu ◽

Rong Li Han

Keyword(s):

Neural Network ◽

Neural Networks ◽

Fault Diagnosis ◽

Real Time ◽

Large Scale ◽

Fault Dictionary ◽

Diagnosis Method ◽

The Neural Networks ◽

Trained Neural Network ◽

Complex Circuits

Neural network and Fault dictionary are two kinds of very useful fault diagnosis method. But for large scale and complex circuits, the fault dictionary is huge, and the speed of fault searching affects the efficiency of real-time diagnosing. When the fault samples are few, it is difficulty to train the neural network, and the trained neural network can not diagnose the entire faults. In this paper, a new fault diagnosis method based on combination of neural network and fault dictionary is introduced. The fault dictionary with large scale is divided into several son fault dictionary with smaller scale, and the search index of the son dictionary is organized with the neural networks trained with the son fault dictionary. The complexity of training neural network is reduced, and this method using the neural networks ability that could accurately describe the relation between input data and corresponding goal organizes the index in a multilayer binary tree with many neural networks. Through this index, the seeking scope is reduced greatly, the searching speed is raised, and the efficiency of real-time diagnosing is improved. At last, the validity of the method is proved by the experimental results.

Download Full-text

Research on Roller Bearing with Fault Diagnosis Method Based on EMD and BP Neural Network

Advanced Materials Research ◽

10.4028/www.scientific.net/amr.1014.501 ◽

2014 ◽

Vol 1014 ◽

pp. 501-504 ◽

Cited By ~ 2

Author(s):

Shu Guo ◽

You Cai Xu ◽

Xin Shi Li ◽

Ran Tao ◽

Kun Li ◽

...

Keyword(s):

Neural Network ◽

Fault Diagnosis ◽

Bp Neural Network ◽

Roller Bearing ◽

Vibration Signal ◽

Classification Performance ◽

Outer Race ◽

Mode Decomposition ◽

Diagnosis Method ◽

Main Fault

In order to discover the fault with roller bearing in time, a new fault diagnosis method based on Empirical mode decomposition (EMD) and BP neural network is put forward in the paper. First, we get the fault signal through experiments. Then we use EMD to decompose the vibration signal into a series of single signals. We can extract main fault information from the single signals. The kurtosis coefficient of the single signals forms a feature vector which is used as the input data of the BP neural network. The trained BP neural network can be used for fault identification. Through analyzing, BP neural network can distinguish the fault into normal state, inner race fault, outer race fault. The results show that this method can gain very stable classification performance and good computational efficiency.

Download Full-text