Javascript must be enabled to continue!
Detecting Coal Pulverizing System Anomaly Using a Gated Recurrent Unit and Clustering
View through CrossRef
The coal pulverizing system is an important auxiliary system in thermal power generation systems. The working condition of a coal pulverizing system may directly affect the safety and economy of power generation. Prognostics and health management is an effective approach to ensure the reliability of coal pulverizing systems. As the coal pulverizing system is a typical dynamic and nonlinear high-dimensional system, it is difficult to construct accurate mathematical models used for anomaly detection. In this paper, a novel data-driven integrated framework for anomaly detection of the coal pulverizing system is proposed. A neural network model based on gated recurrent unit (GRU) networks, a type of recurrent neural network (RNN), is constructed to describe the temporal characteristics of high-dimensional data and predict the system condition value. Then, aiming at the prediction error, a novel unsupervised clustering algorithm for anomaly detection is proposed. The proposed framework is validated by a real case study from an industrial coal pulverizing system. The results show that the proposed framework can detect the anomaly successfully.
Title: Detecting Coal Pulverizing System Anomaly Using a Gated Recurrent Unit and Clustering
Description:
The coal pulverizing system is an important auxiliary system in thermal power generation systems.
The working condition of a coal pulverizing system may directly affect the safety and economy of power generation.
Prognostics and health management is an effective approach to ensure the reliability of coal pulverizing systems.
As the coal pulverizing system is a typical dynamic and nonlinear high-dimensional system, it is difficult to construct accurate mathematical models used for anomaly detection.
In this paper, a novel data-driven integrated framework for anomaly detection of the coal pulverizing system is proposed.
A neural network model based on gated recurrent unit (GRU) networks, a type of recurrent neural network (RNN), is constructed to describe the temporal characteristics of high-dimensional data and predict the system condition value.
Then, aiming at the prediction error, a novel unsupervised clustering algorithm for anomaly detection is proposed.
The proposed framework is validated by a real case study from an industrial coal pulverizing system.
The results show that the proposed framework can detect the anomaly successfully.
Related Results
Converting Slovianska TPP with the central coal pulverizing plant from anthracite to sub-bituminous coal
Converting Slovianska TPP with the central coal pulverizing plant from anthracite to sub-bituminous coal
Purpose. To develop scientific foundations and technical solutions and to implement the converting of the anthracite boiler of the 800 MW unit of Slovianska TPP with central coal p...
Scientific bases and peculiarities of conversion of CHPP anthracite boilers to sub-bituminous coal combustion
Scientific bases and peculiarities of conversion of CHPP anthracite boilers to sub-bituminous coal combustion
Scientific bases and peculiarities of conversion of CHPP anthracite boilers to sub-bituminous coal combustion Print EmailUser Rating: / 0 PoorBest Category: Content №1 2024 Last ...
Research on water immersion damage characteristics and equivalent width of coal pillar
Research on water immersion damage characteristics and equivalent width of coal pillar
Abstract
Affected by weakening effect of water in the goaf, the bearing capacity of coal pillar reduced, and coal pillar rock burst is prone to occur, which is a serious th...
The CO2 storage in coal seams at the influence of coal fines migration
The CO2 storage in coal seams at the influence of coal fines migration
Abstract: the pressure of the coal seam decays to a certain value due to the production of CH4, the production wells are switched to CO2 injection wells. The injection of CO2 can i...
Practical Aspects Of Coal Degasification
Practical Aspects Of Coal Degasification
Abstract
The increase in value of energy resources has generated serious interest in so-called "unconventional energy resource developments", Coal and coal gas re...
Adaption of Theoretical Adsorption Model on Coal: Physical Structure
Adaption of Theoretical Adsorption Model on Coal: Physical Structure
With the motivation to investigate the role of coal physical structure on the adsorption performance of coal reservoir, 18 different types of coal samples with different coal struc...
The development of the market of qualified coal fuels in Poland
The development of the market of qualified coal fuels in Poland
Abstract
The aim of this article is to discuss the changes that have been observed on the market of qualified coal fuels (the so-called eco-pea coal) over the last few years. T...

