Neural network modelling of a 200 MW boiler system

Irwin, G.W.; Brown, M.; Hogg, B.W.; Swidenbank, E.

doi:10.1049/ip-cta:19952293

Cited by 51 publications

(20 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As expected the simulated ARX model output temperature and pressure show good prediction behavior as shown in Figure 15 and Figure 17. This is expected because the plant is modeled around its operating point [23,40,41,43]. Hence only marginal improvement is observed in the neural network model shown in Figure 11 and Figure 12.…”

Section: Test Results Test Results Test Results Test Resultsmentioning

confidence: 90%

“…There is no constraint as to whether the plant is linear or nonlinear, provided that the training data covers the envelope of plant operation [11,13] Successful identification of nonlinear plant models is more problematic since, in addition to stimulating the be exercised across the operating range over which modeling is needed. One able results in earlier work to step the control inputs to drive the plant through its range of operating points while superimposing ry signals at the same time [23]. This operation is difficult to effect while the boiler is in operation.…”

mentioning

confidence: 99%

“…heat correlations), and may be considered as knowledge models [21,22]. However, to justify the basic structure of oil-fired boilers control systems, a different kind of model may be very helpful where only first dynamics is captured in order to reveal the essential input-output interactions [23]. Such models may be called interpretation or identification models.…”

mentioning

confidence: 99%

See 2 more Smart Citations

Neural Network Based Model of an Industrial Oil-Fired Boiler System

Orosun¹,

Adamu²

2014

Nig. J. Tech.

View full text Add to dashboard Cite

ABSTRACT ABSTRACTIn this study, an oil In this study, an oil In this study, an oil In this study, an oil----fired boiler system is modeled as a multivariable plant with fired boiler system is modeled as a multivariable plant with fired boiler system is modeled as a multivariable plant with fired boiler system is modeled as a multivariable plant with fired flow rate) and two outputs (steam temperature and pressure). The plant parameters are mod fired flow rate) and two outputs (steam temperature and pressure). The plant parameters are mod fired flow rate) and two outputs (steam temperature and pressure). The plant parameters are mod fired flow rate) and two outputs (steam temperature and pressure). The plant parameters are mod artificial neural network, based on experimental data col artificial neural network, based on experimental data col artificial neural network, based on experimental data col artificial neural network, based on experimental data col forward neural network with Hyperbolic tangent sigmoid transfer function (Tansigmoid) and line forward neural network with Hyperbolic tangent sigmoid transfer function (Tansigmoid) and line forward neural network with Hyperbolic tangent sigmoid transfer function (Tansigmoid) and line forward neural network with Hyperbolic tangent sigmoid transfer function (Tansigmoid) and line neurons (Purelin) are neurons (Purelin) are neurons (Purelin) are neurons (Purelin) are used at the hidden used at the hidden used at the hidden used at the hidden network model is network model is network model is network model is then trained off then trained off then trained off then trained off----l l l line with Levenberg ine with Levenberg ine with Levenberg ine with Levenberg neural network model when neural network model when neural network model when neural network model when subjected to test, u subjected to test, u subjected to test, u subjected to test, u outputs for both temperature and pressure agree closely with the actual plan outputs for both temperature and pressure agree closely with the actual plan outputs for both temperature and pressure agree closely with the actual plan outputs for both temperature and pressure agree closely with the actual plan 0.

show abstract

Section: Test Results Test Results Test Results Test Resultsmentioning

confidence: 90%

mentioning

confidence: 99%

mentioning

confidence: 99%

See 1 more Smart Citation

Neural Network Based Model of an Industrial Oil-Fired Boiler System

Orosun¹,

Adamu²

2014

Nig. J. Tech.

View full text Add to dashboard Cite

show abstract

“…The development of ANN models for the steam process of a biomass and coal co-fired combined heat and power plant using real plant data has already been reported by the same group [29,30]. However, there are a few reported works [31][32][33][34][35] on the modeling of conventional coal-fired boilers using ANN, and only one of them [35] used real plant data.…”

mentioning

confidence: 89%

Prediction of power output of a coal-fired power plant by artificial neural network

Smrekar

Pandit

Fast

et al. 2009

Neural Comput & Applic

View full text Add to dashboard Cite

Accurate modeling of thermal power plant is very useful as well as difficult. Conventional simulation programs based on heat and mass balances represent plant processes with mathematical equations. These are good for understanding the processes but usually complicated and at times limited with large number of parameters needed. On the other hand, artificial neural network (ANN) models could be developed using real plant data, which are already measured and stored. These models are fast in response and easy to be updated with new plant data. Usually, in ANN modeling, energy systems can also be simulated with fewer numbers of parameters compared to mathematical ones.Step-by-step method of the ANN model development of a coal-fired power plant for its base line operation is discussed in this paper. The ultimate objective of the work was to predict power output from a coal-fired plant by using the least number of controllable parameters as inputs. The paper describes two ANN models, one for boiler and one for turbine, which are eventually integrated into a single ANN model representing the real power plant. The two models are connected through main steam properties, which are the predicted parameters from boiler ANN model. Detailed procedure of ANN model development has been discussed along with the expected prediction accuracies and validation of models with real plant data. The interpolation and extrapolation capability of ANN models for the plant has also been studied, and observed results are reported.

show abstract

“…Gordon and Joseph (1996) presented nonlinear control oriented boiler models in fourth order, time delays, measurement noise, and load disturbance components, which provides basis for boiler control strategy development. In recent years, artificial intelligence has been incorporated in the modelling of steamboiler system, such as the boiler model identification method (Chawdhry, 1989), neural network modelling of a 200 MW boiler system (Irwin et al, 1995).…”

Section: Introductionmentioning

confidence: 99%