Soft-computing models for soot-blowing optimization in coal-fired utility boilers
Introduction
Deposition of ash particles during combustion on heat transfer surfaces is an undesired phenomenon, which causes important losses of availability and efficiency in thermal power stations, and may involve an annual economic impact of $1.2 billion only in US [1]. In addition, these troubles are more critical in biomass combustion and they make difficult the development of efficient technologies for industrial applications.
The deposits are classified in two categories: fused deposits in the radiant zone are known as slagging, while fouling are sintered deposits in the convective passes.
On-load cleaning of hardened deposits is usually performed by means of soot-blowers of air, steam or water, located on furnace and convective passes. Traditionally, the sequencing of soot-blowing has been conducted upon a periodic schedule or under the criteria of operator, resulting in over-blowing in many cases. However, there are penalties concerning soot-blowing to be considered. On the one hand, each blowing manoeuvre implies a loss of efficiency, as it represents an energetic and economic cost. On the other hand, soot-blowing over a clean section causes tube erosion, accelerating the degradation of surface tubes and reducing the longevity of the boiler.
So, the problem is of an optimization nature, as it aims to minimize the combined cost of fouling and soot-blowing operations. This fact was recognized very early in the field of boiler design [2], along with the possibilities of automated decision controls about soot-blowing activation to substitute preset sequences [3]. Intelligent soot-blowing (ISB) must be a combination of modelling, soft-computing techniques and on-line systems to monitor the boiler performance.
Consulting companies and some boiler manufactures have developed automatic systems with the goal of optimizing soot-blowing. In general, they are based in a monitoring system of heat-flux transfer and temperature of certain points of the boiler [4], [5], [6], [7], [8]. So, the optimized strategies of soot-blowing are established according to certain dirty levels or temperature thresholds [9], [10], [11], [12], [13], [14], [15], [16]. But published information about technical details is, unfortunately, very scarce. Many studies report great advantages in real applications, without even describing the techniques used (see, for example, Ref. [17]).
Artificial Neural Networks (ANN) have shown their versatility to model the behavior of complex systems in a wide number of scientific and commercial areas, including energy systems and fouling phenomena [18], [19], [20]. The main advantage of ANN is that it does not need any mathematical model, since it learns from historical data to recognize non-evident relations and patterns in a set of input–output variables, without any prior assumption about their nature.
Fuzzy logic and fuzzy set theory, introduced in 1965 [21], embrace a wide set of inference methods that interpret the values of an input vector according to certain simple rules and assign values to the output vectors. There are two main types of fuzzy inference systems, Mamdani-type [22] and Sugeno-type [23], varied in the way outputs are determined. Mamdani’s fuzzy inference method, which is the most commonly used, was proposed as an attempt to control a steam engine and boiler combination by implementing a set of linguistic control rules extracted from operator’s experience. A combination of neural network concept and fuzzy logic of Sugeno’s type has given rise to neuro-adaptive fuzzy networks (ANFIS) [24], which are able to automatically adjust the internal parameters in a learning process similar to that in ANN.
The use of ANN in the context of utility boilers soot-blowing optimization was first suggested in Ref. [25]. Several papers report the successful application of knowledge systems [26] or neural networks combined with simple models of deposits as a basis for theoretical development [27]. A previous work of Teruel et al. [28] was the first detailed publication about neural network models to predict fouling, in which this method was applied to a 350 MWe utility boiler furnace. ANN together with expert systems have been proposed for the optimized control of fouling in the superheater and convective passes of a 50 MWe biomass boiler [29]. Fouling and slagging in these areas show much less randomness than the furnace, and it is not measured locally but using indirect techniques based on thermal balance models. The outcome is a control strategy that compares the energetic cost of cleaning manoeuvres with the thermal improvements and decides about the activation of soot-blowers, representing potential savings up to 12 GWh/year in the case study.
The predictive system developed in Ref. [28] was divided into three local neural networks of simple and similar architecture. Preliminary results were excellent and very promising with respect to an application to an optimal control of soot-blowers’ strategies. The present paper aims to show the robustness and adequacy for control of such procedure. The main purposes of this work are threefold: (1) to improve the prediction model presented in [28], both introducing technical modifications, and model definition changes to facilitate the integration in an intelligent control system for soot-blowing; (2) to systematically evaluate the quality of predictions as an advisory tool for the operator staff; (3) to demonstrate the robustness of the method, by comparison of the predictions for several historical records and using two different techniques, Artificial Neural Networks (ANN) and Adaptive Neuro-Fuzzy Inference Systems (ANFIS).
The paper is organized as follows. Section 2 recalls the soft-computing techniques used for these tasks: ANN and ANFIS. The development of the improved predictive models based on historical data series is described in detail in Section 3. The quality of predictions for several historical data series is discussed in Section 4, including a comparison of ANN and ANFIS models. Section 5 outlines the application of the developed models as an advisory tool to recommend soot-blowing.
Section snippets
ANN and ANFIS
This section serves as a brief reference introduction to the soft-computing techniques used in the work: feed-forward Artificial Neural Networks with automated Bayesian regularization, and adaptive neuro-fuzzy inference system with subtractive clustering.
Problem description
We consider several historical data series containing information on the fouling/slagging and soot-blowing in the furnace of a pulverized utility boiler. The boiler is a front wall-fired unit of parallel back-pass design, with natural recirculation, three stages of superheat, single reheat, balanced draft and primary and secondary air heating [41]. Its main operational parameters are listed in Table 1.
Our attention is focused on the furnace, which is the most critical section of the boiler with
Predictions: assessment and comparison
This section evaluates the predictive ability of each module for various historical data series and compares the reliability of each technique (ANN vs. ANFIS models) to reproduce the behavior of the system. In order to systematically evaluate the quality of predictions of individual models, several performance indices have been defined. These indices are intended to measure in a convenient and meaningful manner the differences between the predicted and observed values, according to the nature
Towards an advisory tool to recommend soot-blowing
As mentioned in the introductory section, the cleaning process under study is of an optimization nature, as a compromise must be found between the cost of soot-blowing manoeuvres and the benefit achieved with them. Naturally, one should incur on the cost of soot-blowing only in the cases when it is more likely to produce a benefit, in terms of thermal efficiency, which in the end results in a lesser fuel consumption, and lesser emissions, for the same production. To deal with this problem, two
Conclusions
Two different soft-computing techniques have been applied and evaluated in order to predict the effects of soot-blowing manoeuvres, with the purpose of integrating these predictions in a soot-blowing optimization schema.
Due to the dynamic complexity and randomness of the involved physical phenomena, single “black-box” models are not sufficient. We proposed a structured combination of partial and local models: MOD1 is trained to continuously predict the probability that a virtual soot-blowing
Acknowledgements
Authors are grateful to Prof. Cristóbal Cortés for many fruitful discussions. This work has been being carried out with a financial grant from the Research Fund for Coal and Steel of the European Community (research project RFCR-CT-2006-00008, Intelligent monitoring and selective cleaning control of deposits in pulverized coal boilers). Authors also wish to thank operators and personnel of Teruel power station (Spain) for their assistance.
References (44)
- et al.
Ash fouling in coal-fired utility boilers. Monitoring and optimization of on-load cleaning
Progress in Energy and Combustion Science
(1996) - et al.
Investigations on fouling rate in convective bundles of coal-fired boilers in relation to optimization of sootblower operation
Fuel
(2005) Artificial intelligence for the modeling and control of combustion processes: a review
Progress in Energy and Combustion Science
(2003)- et al.
Online fouling detection in electrical circulation heaters using neural networks
International Journal of Heat and Mass Transfer
(2003) Fuzzy sets
Information and Control
(1965)- et al.
An experiment in linguistic synthesis with a fuzzy logic controller
International Journal of Man–Machine Studies
(1975) - et al.
Concept of expert system for boiler fouling assessment
Applied Thermal Engineering
(1996) - et al.
Monitoring and prediction of fouling in coal-fired utility boilers using neural networks
Chemical Engineering Science
(2005) - et al.
Hybrid system for fouling control in biomass boilers
Engineering Applications of Artificial Intelligence
(2006) - et al.
Multilayer feedforward networks are universal approximators
Neural Networks
(1989)
Connectionist nonparametric regression: multilayer feedforward networks can learn arbitrary mappings
Neural Networks
Modelling of pulverized coal boilers: review and validation of on-line simulation techniques
Applied Thermal Engineering
The measurement of radiant heat flux in large boiler furnaces—II. Development of flux measuring instruments
International Journal of Heat and Mass Transfer
An accurate comparison of methods for quantifying variable importance in artificial neural networks using simulated data
Ecological modelling
A mathematical approach to automation of sootblower controls
The boiler cleaning control subloop
Transactions of the AIEE
A furnace wall ash monitoring system for coal fired boilers
Transactions of the ASME, Journal of Engineering for Power
An instrument system to monitor and control fouling and slagging in large utility boilers
Cited by (43)
Improvement of slagging monitoring and soot-blowing of waterwall in a 650MWe coal-fired utility boiler
2021, Journal of the Energy InstituteApplication of artificial intelligence in modeling, control, and fault diagnosis
2021, Applications of Artificial Intelligence in Process Systems EngineeringAsh fouling monitoring and soot-blow optimization for reheater in thermal power plant
2019, Applied Thermal EngineeringCitation Excerpt :Mohanty and Singru [3] have modelled shell and tube heat exchanger using wavelet neural network, considering various performance parameters such as shell and tube temperature differences and CF. The closeness of predicted output with that of experimental output is statistically analysed using correct directional change and coefficient of determination. Pena [5] has proposed a probabilistic model based on artificial neural network and adaptive neuro-fuzzy inference system to predict the effectiveness of soot-blow by considering unit load, current relative cleanliness, cleanliness after shedding event as inputs. Degereji et al. [6] have proposed a deposition model to predict slag deposits based on viscosity, static contact angle and surface energy.