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

Abstract

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...

Experimental Study of a Coil Type Steam Boiler Operated on an Oil Field in the Subarctic Continental Climate

“…In connection with the listed advantages and further development prospects of the domestic market for the production of water-tube coil and fire-tube boilers, we chose a coil-type steam boiler produced in the Urals. The characteristics of the boilers developed by the authors were compared with the analogues presented by Chauhan and Khanam [22], dedicated to mini thermal power plants with low-pressure steam generators or Shi and Wang [23], in which a boiler of a similar type operating on solid fuel is considered.…”

Investigation of Operation of Coil-Flow Steam Generator of Serpentine Type in Conditions of Low Ambient Temperatures

“…In connection with the listed advantages and further development prospects of the domestic market for the production of water-tube coil and fire-tube boilers, we chose a coil-type steam boiler produced in the Urals. The characteristics of the boilers developed by the authors were compared with the analogues presented by Chauhan and Khanam [14], dedicated to mini thermal power plant with lowpressure steam generators, in which a boiler of a similar type operating on solid fuel is considered [15].…”

Deep Learning-Based Approach for Heat Transfer Efficiency Prediction with Deep Feature Extraction

“…Similarly, Tong et al 16 used Support vector regression (SVR) to complete the non-linear mapping relationship between 20 related variables of ash formation and actual fouling conditions (characterized by the thermal resistance of the ash layer calculated by the thermal balance mechanism model), which reached the test set 98.5% accuracy rate. Shi and Wang 17 on the basis of characterizing the health status of the heating surface also proposed an artificial neural network-based key variable analysis to study the internal behavior of ash pollution and thermal efficiency. Sivathanu and Subramanian 18 designed a dual extended Kalman filter (DEKF) to estimate the model parameters that affect the pollution of the heating surface of the reheater.…”