Improving the performance of industrial boiler using artificial neural network modeling and advanced combustion control

Nazaruddin, Yul Y.; Aziz, Abdullah Nur; Sudibjo, W.

doi:10.1109/iccas.2008.4694411

Cited by 7 publications

(7 citation statements)

References 4 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Bank tube and water wall (2c) Downcomer pipe (3a,b) Superheater I&II tubes (4) Desuperheater (5) Fuel oil (6) Fuel gas (7) Combustion air supply (8) Flue gas path (9) Economizer (10) Boiler stack (11) Superheated steam…”

Section: Modeling Methodologymentioning

confidence: 99%

See 1 more Smart Citation

Structured Mathematical Modeling of Industrial Boiler

et al. 2014

Self Cite

View full text Add to dashboard Cite

As a major utility system in industry, boilers consume a large portion of the total energy and costs. Significant reduction of boiler cost operation can be gained through improvements in efficiency. In accomplishing such a goal, an adequate dynamic model that comprehensively reflects boiler characteristics is required. This paper outlines the idea of developing a mathematical model of a water-tube industrial boiler based on first principles guided by the bond graph method in its derivation. The model describes the temperature dynamics of the boiler subsystems such as economizer, steam drum, desuperheater, and superheater. The mathematical model was examined using industrial boiler performance test data. It can be used to build a boiler simulator or help operators run a boiler effectively.

show abstract

Section: Modeling Methodologymentioning

confidence: 99%

“…The second approach utilizes system identification techniques to develop black-box models that describe the system ina particular operating condition. A working example of the second approach can be found in Nazaruddin, et al [5,6].…”

Section: Introductionmentioning

confidence: 99%

Structured Mathematical Modeling of Industrial Boiler

et al. 2014

Self Cite

View full text Add to dashboard Cite

show abstract

“…The artificial neural networks (ANNs), as universal approximators of any nonlinear input-output mappings, have been used in advanced control and fault detection schemes, both as process models and as nonlinear controllers [15]. The ANNs confirmed their ability to utilize real-time data taken from a running boiler system and periodically adapt to changeable process characteristics [16,17]. Neural networks are also combined with fuzzy logic, both for modeling of a boiler system and for detection of process faults [18].…”

Section: Current Approaches To Fault Detection In a Pipeline System Omentioning

confidence: 99%

Multiway PCA for Early Leak Detection in a Pipeline System of a Steam Boiler—Selected Case Studies

Swiercz

Mroczkowska²

2020

Sensors

View full text Add to dashboard Cite

In the paper the usability of the Multiway PCA (MPCA) method for early detection of leakages in the pipeline system of a steam boiler in a thermal-electrical power plant is presented. A long segment of measurements of selected process variables was divided into a series of “batches” (representing daily recordings of normal behavior of the plant) and used to create the MPCA model of a “healthy” system in a reduced space of three principal components (PC). The periodically updated MPCA model was used to establish the confidence ellipsoid for the “healthy” system in the PC coordinates. The staff’s decision of the probable leak detection is supported by comparison of the current location of the operating point (on the “fault trajectory”) with the boundaries of the confidence ellipsoid. It must be emphasized that due to daily and seasonal changes of heat/electricity demands, the process variables have substantially greater variability than in the examples of batch processes studied in literature. Despite those real challenges for the MPCA method, numerical examples confirmed that the presented approach was able to foresee the leaks earlier than the operator, typically 3–5 days before the boiler shutdown. The presented methodology may be useful in implementation of an on-line system, developed to improve safety and maintenance of boilers in a thermal-electrical power plant.

show abstract

“…The effective ways to deal with this problem are accurate on-line monitoring of ash fouling and soot-blowing. Artificial neural network (ANN) has recently proved its availability to tackle with thermal engineering problems [10,11]. In this process, artificial neural networks are used to optimize the boiler soot-blowing model and mean impact values method is utilized to determine a set of key variables.…”

mentioning

confidence: 99%

“…Artificial neural network (ANN) has recently proved its availability to tackle with thermal engineering problems [10,11]. Artificial neural network (ANN) has recently proved its availability to tackle with thermal engineering problems [10,11].…”

mentioning

confidence: 99%

Ash fouling monitoring and key variables analysis for coal fired power plant boiler

Shi

Wang

2015

THERM SCI

View full text Add to dashboard Cite

Ash deposition on heat transfer surfaces is still a significant problem in coalfired power plant utility boilers. The effective ways to deal with this problem are accurate on-line monitoring of ash fouling and soot-blowing. In this paper, an online ash fouling monitoring model based on dynamic mass and energy balance method is developed and key variables analysis technique is introduced to study the internal behavior of soot-blowing system. In this process, artificial neural networks are used to optimize the boiler soot-blowing model and mean impact values method is utilized to determine a set of key variables. The validity of the models has been illustrated in a real case-study boiler, a 300 MW Chinese power station. The results on same real plant data show that both models have good prediction accuracy, while the artificial neural networks model II has less input parameters. This work will be the basis of a future development in order to control and optimize the soot-blowing of the coal-fired power plant utility boilers.tion. Therefore, optimization for soot blowing system according to the actual cleaning need becomes more and more important. At first, an appropriate assessment for the ash fouling level of each heat transfer surface of the boiler is needed. Monitoring techniques become more and more important for the study of boiler behaviors and ash fouling influence in coal-fired power plant boilers and have attracted extensive research effort recently [6][7][8].Ash fouling monitoring can be accomplished by means of on-line calculations and special power plant instrumentation or a combination of both techniques. On-line calculations always need to calculate the heat absorption of heat transfer surfaces. The conventional method of calculating the heat absorption rate is the log-mean-temperature-difference approach [6]. However, it is a static balance method which cannot show the dynamic behaviors of heat transfer surfaces. While special power plant instrumentation (i. e. heat fluxes meters [7]) can well reflect the status of heat absorption of heat transfer surfaces by providing a continuous signal, they induce significant increase of cost on sensors, installation, and maintenance. There are some commercial (ash fouling) boiler monitoring tools [8], but the internal behaviors of these applications are unclear.Key variables analysis is a tool that is often used to study the behavior of a system, or a model, and to attain the dependency of outputs on each or some of input parameters [9]. Artificial neural network (ANN) has recently proved its availability to tackle with thermal engineering problems [10,11]. ANN has also been used in system modeling, identification, control, forecasting, power systems and optimization [12][13][14]. ANN has also been proposed to deal with ash fouling [15], but it is not completely used for tackle the problem of variables influence. Some examples are important revisions of the ANN applications and references made in the field of energy [16].In this paper, the cleanliness factors (C...

show abstract

Improving the performance of industrial boiler using artificial neural network modeling and advanced combustion control

Cited by 7 publications

References 4 publications

Structured Mathematical Modeling of Industrial Boiler

Structured Mathematical Modeling of Industrial Boiler

Multiway PCA for Early Leak Detection in a Pipeline System of a Steam Boiler—Selected Case Studies

Ash fouling monitoring and key variables analysis for coal fired power plant boiler

Contact Info

Product

Resources

About