Coal mill modeling by machine learning based on onsite measurements

Zhang, Y. G.; Wang, J.; Oluwande, G.; Matts, D.; Zhou, Xianchao

doi:10.1109/tec.2002.805182

Cited by 48 publications

(17 citation statements)

References 4 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Moreover it has been demonstrated that GA is robust in the parameter identification problem and can achieve good results [18,19]. GA processes are well explained elsewhere [20], and we present the identification process of GA in Figure 3. Tables 1 and 2 show the GA tuning parameters and final optimal parameters, respectively.…”

Section: Parameter Identificationmentioning

confidence: 77%

Nonlinear Modeling and Inferential Multi-Model Predictive Control of a Pulverizing System in a Coal-Fired Power Plant Based on Moving Horizon Estimation

Liang

et al. 2018

Energies

View full text Add to dashboard Cite

Fuel preparation is the control bottleneck in coal-fired power plants due to the unmeasurable nature or inaccurate measurement of key controlled variables. This paper proposes an inferential multi-model predictive control scheme based on moving horizon estimation for the fuel preparation system in coal-fired power plants, i.e., the pulverizing system, aimed at improving control precision of key operating variables that are unmeasurable or inaccurately measured, and improving system tracking performance across a wide operating range. We develop a first principle model of the pulverizing system considering the nonlinear dynamics of primary air, and then employ the genetic algorithm to identify the unknown model parameters. The outputs of the identified first principle model agree well with measured data from a real pulverizing system. Thereafter we derive a moving horizon estimation approach to estimate the desired, but unmeasurable or inaccurately measured, controlled variables. Estimation constraints are explicitly considered to reduce the influence of measurement uncertainty. Finally, nonlinearity of the pulverizing system is analyzed and a multi-model inferential predictive controller is developed using the extended input-output state space model to achieve offset-free performance. Simulation results show that the proposed soft sensor can provide improved estimates than conventional extended Kalman filter, and the proposed inferential control scheme can significantly improve performance of the pulverizing system.

show abstract

Section: Parameter Identificationmentioning

confidence: 77%

Nonlinear Modeling and Inferential Multi-Model Predictive Control of a Pulverizing System in a Coal-Fired Power Plant Based on Moving Horizon Estimation

Liang

et al. 2018

Energies

View full text Add to dashboard Cite

show abstract

“…Breakage matrix is considered to simulate the grinding process. Some relatively simplified models of mills are developed in [129,[136][137][138][139][140][141][142][143][144][145][146][147], where the coal in the pulverizer is divided into two groups, unpulverized and pulverized. These detailed and simplified models can be used for mill FDD purpose.…”

Section: Mill Fault Detection Using Quantitative Model-based Methodsmentioning

confidence: 99%

“…For example, the approaches based on the residual based fault detection or the process history based methods can provide early fault detection whereas the methods using qualitative based approach are best for fault isolation. Also, as pointed out earlier, several models of coal mills are developed [129][130][131][132][133][134][135][136][137][138][139][140][141][142][143][144][145][146][147] but they are not used for the fault diagnosis yet. Their applicability for the residual based fault detection as done by F.Q.…”

Section: Comparison Of Various Fault Diagnostic Approachesmentioning

confidence: 99%

Review of control and fault diagnosis methods applied to coal mills

Agrawal

Panigrahi

Subbarao

2015

Journal of Process Control

View full text Add to dashboard Cite

“…Dynamic models of coal mills are treated in numerous papers e.g. [1], [2], [3] and [4]. In these papers it is generally assumed that all moisture evaporates within the coal mill; in practice, however, this assumption does not always hold, as it requires a high inlet primary air temperature (typically at least 95…”

Section: Introductionmentioning

confidence: 99%

Coal moisture estimation in power plant mills

Andersen

Bendtsen

Pedersen

et al. 2009

2009 17th Mediterranean Conference on Control and Automation

View full text Add to dashboard Cite

Abstract-Knowledge of moisture content in raw coal feed to a power plant coal mill is of importance for efficient operation of the mill. The moisture is commonly measured approximately once a day using offline chemical analysis methods; however, it would be advantageous for the dynamic operation of the plant if an on-line estimate were available. In this paper we such propose an on-line estimator (an extended Kalman filter) that uses only existing measurements. The scheme is tested on actual coal mill data collected during a one-month operating period, and it is found that the daily measured moisture content agrees with the estimates.

show abstract

Coal mill modeling by machine learning based on onsite measurements

Cited by 48 publications

References 4 publications

Nonlinear Modeling and Inferential Multi-Model Predictive Control of a Pulverizing System in a Coal-Fired Power Plant Based on Moving Horizon Estimation

Nonlinear Modeling and Inferential Multi-Model Predictive Control of a Pulverizing System in a Coal-Fired Power Plant Based on Moving Horizon Estimation

Review of control and fault diagnosis methods applied to coal mills

Coal moisture estimation in power plant mills

Contact Info

Product

Resources

About