Identification, Prediction and Detection of the Process Fault in a Cement Rotary Kiln by Locally Linear Neuro-Fuzzy Technique

Abstract

In this paper, we use nonlinear system identification method to predict and detect process fault of a cement rotary kiln. After selecting proper inputs and output, an input-output model is identified for the plant. To identify the various operation points in the kiln, Locally Linear Neuro-Fuzzy (LLNF) model is used. This model is trained by LOLIMOT algorithm which is an incremental treestructure algorithm. Then, by using this method, we obtained 3 distinct models for the normal and faulty situations in the kiln. One of the models is for normal condition of the kiln with 15 minutes prediction horizon. The other two models are for the two faulty situations in the kiln with 7 minutes prediction horizon are presented. At the end, we detect these faults in validation data. The data collected from White Saveh Cement Company is used for in this study.

Prediction of activated sludge bulking based on a self-organizing RBF neural network

“…NNs were used in predicting the performance or effluent quality of WWTPs, creating software sensors and are also used fault detection and diagnosis [31]. Qualitative information about the presence of filamentous bacteria as well as quantitative data on water quality were used as inputs to a number of NNs and it was found that qualitative information exerted an important influence on plant output [32,33]. Due to their simple topological structure and universal approximation ability, radial basis function (RBF) neural networks have been widely used in nonlinear system modeling and control [34,35].…”

Conditions identification model based on LLNFM and RBR in cement raw meal calcination process

“…The conclusion parameters ij w was solved by using local linear model tree (LLMT) [1,5,9]. LLMT is a increasing tree structure algorithm, and the input space was divided by using orthogonal axis.…”

Particle swarm optimisation clustering for cement kilning system fault recognition

“…Therefore, the fast and accurate detection for the cement kilning system production is very significant for safe production of the cement. Nowadays, the research on the cement rotary kilns mainly focus on the simulation of the key process using mathematical computational models such as Mastorakos et al (1999), Mujumdar et al (2007), Sogut et al (2010) and soft computing models such as Sharifi et al (2012), Sadeghian and Fatehi (2011), Ku et al (2010), Alanis et al (2010), and Tellez et al (2010). Mastorakos et al (1999) propose computational fluid dynamics (CFD) models show promise in simulating details of combustion and burners designs.…”

“…Pazand et al (2009) study an approach which is described in simulating the mechanical behaviour of a rotary cement kiln via artificial neural networks. Sadeghian and Fatehi (2011) consider a non-linear system-based locally linear neuro-fuzzy technique which is used to predict and detect process fault of a cement rotary kiln. Sharifi et al (2012) take account of a method which hierarchical wavelet fuzzy inference system (HWFIS) is used to identify the cement rotary kiln.…”