By Topic

Fault Diagnosis of the Blast Furnace Based on the Bayesian Network Model

Sign In

Cookies must be enabled to login.After enabling cookies , please use refresh or reload or ctrl+f5 on the browser for the login options.

Formats Non-Member Member
$31 $13
Learn how you can qualify for the best price for this item!
Become an IEEE Member or Subscribe to
IEEE Xplore for exclusive pricing!
close button

puzzle piece

IEEE membership options for an individual and IEEE Xplore subscriptions for an organization offer the most affordable access to essential journal articles, conference papers, standards, eBooks, and eLearning courses.

Learn more about:

IEEE membership

IEEE Xplore subscriptions

4 Author(s)
Pan Lian ; Coll. of Inf. Sci. & Eng., Wuhan Univ. of Sci. & Technol., Wuhan, China ; Ning Ning ; Chen Aiping ; Tong Yaobin

Blast furnace condition and stable operation for blast furnace is crucial, The production practice shows that only by maintaining the stability of blast furnace condition, could it achieve 'high yield, high quality, low consumption, longevity', obtain good technical and economic indexes. However, the process of smelting furnace is influenced by many factors, which will definitely cause the fluctuation in furnace condition. Therefore, the operator must be timely to judge change-trend and amplitude at the blast furnace condition, figure out the reasons for changing conditions in smelted induction, and adjust it promptly, only through which could maintain the stable smelted in induction. Due to the different levels of the operators, so the adjustment method is also different. Moreover, it will inevitably result in the fluctuation in furnace condition, for the operators have to face with a lot of operating parameters. Therefore, it is absolutely useful and necessary to summarize the experiences of excellent operators, to make the furnace operation unification and standardization through establishing the model of intelligent diagnosis, to forecast online as well as gives practical guidance in furnace condition. To solve the problem of blast furnace failure mode and effect analysis are unable to quantitative description of the occurrence probability of fault model. This paper puts forward a Bayesian network topology structure based on the FMEA--CFE (Cause Failure Effect)-type Bayesian diagnostic network. On the basis of the relationship between 'failure reason', 'failure mode' and 'failure fault' in FMEA, the diagnostic network topology structure can be confirmed, and the causality and gradation in system fault can be described. So, we can solve the probability of failure mode by adopting Bayesian network fault diagnosis of decision-making techniques. This method will provide theoretical basis for blast furnace fault diagnosis, and through the actual research, the- - validity of this method finally has been verified. It provides effective guidance to the actual production of blast furnace.

Published in:

Electrical and Control Engineering (ICECE), 2010 International Conference on

Date of Conference:

25-27 June 2010