| Research Article |
|
|
|
|
|
A prediction method for wall cooling efficiency of combustor chamber based on neural network |
| LIU Jiangfan1, GE Bing2, LI Shanshan1, LU Xiang2 |
1. China United Gas Turbine Technology Co., Ltd., Beijing 100016, China;
2. Key Laboratory of Power Machinery and Engineering of Ministry of Education, Shanghai Jiao Tong University, Shanghai 200240, China |
|
|
|
|
Abstract [Objective] The effusion cooling technique is applied to hot sections in the modern heavy-duty gas turbine combustor, for example, the liner provides efficient protection from high-temperature gas using a small amount of cooling air. However, establishing a theoretical model or empirical correlations for regression and prediction of wall cooling efficiency is difficult. Because it is affected by many factors, including cooling hole type, patterns, and other flow parameters. The prediction methods based on computational fluid dynamics (CFD) techniques also have the disadvantages of long-term consumption and resource occupation. This paper proposes a prediction method based on artificial neural networks, namely back propagation (BP) and radial basis function (RBF) networks, that reach high accuracy for field reconstruction and cooling efficiency prediction. [Methods] This study collects simulation data from the design process of an industrial combustor and analyzed all dimensions of the wall adiabatic film cooling efficiency data set from the working conditions. Artificial feature selection, mini-batch, and normalization are used to preprocess the data. Important feature regions A and B are manually extracted by calculating the standard deviations of the cooling efficiency matrix considering different cooling air pressure loss conditions combined with CFD analysis. Then, the training set, the validation set, and the test set are divided based on cross-validation. For the field reconstruction, the BP network and the RBF network are selected. For its fast convergence and high precision, the BP network adopts the L-M algorithm. For the prediction, the BP network and generalized regression neural network (GRNN) are selected. The BP network adopts a Bayesian regularization algorithm to avoid overfitting. The GRNN network outperforms the RBF network for prediction and also takes less time for grid searching. For regression, mean square error (mse) and network prediction accuracy (accu) are defined to measure variance and deviation, respectively. [Results] The results showed that: 1) Through artificial feature selection and mini-batch, the samples in region A were compressed by ten times while perfectly extracting cooling efficiency characteristics. 2) For the field reconstruction, under the non-reactive condition 3, the field reconstruction accuracy of the optimized BP and RBF networks reached 92.2% and 95.5%, respectively. Under the reactive condition 10, the same networks reached 90.5% and 92.0% respectively. Compared with the BP network, the RBF network had better global approximation ability than the BP network. 3) For the prediction, under the reactive condition 10, the prediction accuracy of the BP and GRNN networks reached 88.3% and 86.8%, respectively, both lower than the field reconstruction accuracies. [Conclusions] The rapid field reconstruction and high prediction for wall adiabatic film cooling efficiency are realized by proposing a universal data preprocessing technique for the combustor wall cooling efficiency data set and an optimization technique for the BP and RBF networks. In summary, the field reconstruction accuracy reaches above 90%, and the prediction accuracy reaches above 85%, meeting the actual engineering requirements in the modern industrial gas turbine combustor design.
|
| Keywords
gas turbine
effusion cooling
wall cooling efficiency
neural network
performance prediction
|
|
Issue Date: 22 April 2023
|
|
|
[1] KREWINKEL R. A review of gas turbine effusion cooling studies[J]. International Journal of Heat and Mass Transfer, 2013, 66:706-722.
[2] 焦李成,杨淑媛,刘芳,等.神经网络七十年:回顾与展望[J].计算机学报, 2016, 39(8):1697-1716. JIAO L C, YANG S Y, LIU F, et al. Seventy years beyond neural networks:Retrospect and prospect[J]. Chinese Journal of Computers, 2016, 39(8):1697-1716.(in Chinese)
[3] 丛爽.面向MATLAB工具箱的神经网络理论与应用:3版[M].合肥:中国科学技术大学出版社, 2009. CONG S. Neural network theory and applications with MATLAB toolboxes:3rd ed[M]. Hefei:University of Science and Technology of China Press, 2009.(in Chinese)
[4] SUN J, ZHANG W G, NING D F. Fault-diagnosis system of flight control system based on neural network[J].Measurement&Control Technology, 2008, 27(5):65-67, 83.
[5] 何长虹,黄全义,申世飞,等.基于BP神经网络的森林可燃物负荷量估测[J].清华大学学报(自然科学版), 2011, 51(2):230-233. HE C H, HUANG Q Y, SHEN S F, et al. Forest fuel loading estimates based on a back propagation neutral network[J]. Journal of Tsinghua University (Science&Technology), 2011, 51(2):230-233.(in Chinese)
[6] 呙润华,苏婷婷,马晓伟. BP神经网络联合模板匹配的车牌识别系统[J].清华大学学报(自然科学版), 2013, 53(9):1221-1226. GUO R H, SU T T, MA X W. License plate recognition system using a BP neural network and template matching[J]. Journal of Tsinghua University (Science&Technology), 2013, 53(9):1221-1226.(in Chinese)
[7] 杨淑娥,黄礼.基于BP神经网络的上市公司财务预警模型[J].系统工程理论与实践, 2005, 25(1):12-18. YANG S E, HUANG L. Financial crisis warning model based on BP neural network[J]. Systems Engineering-Theory&Practice, 2005, 25(1):12-18.(in Chinese)
[8] ASGARI H, CHEN X Q. Gas turbines modeling, simulation, and control[M]. Boca Raton:CRC Press, 2015.
[9] WERBOS P J. The roots of backpropagation:From ordered derivatives to neural networks and political forecasting[J]. Neural Networks, 1996, 9(3):543-544.
[10] RUMELHART D E, HINTON G E, WILLIAMS R J. Learning representations by back-propagating errors[J]. Nature, 1986, 323(6088):533-536.
[11] FUNAHASHI K I. On the approximate realization of continuous mappings by neural networks[J]. Neural Networks, 1989, 2(3):183-192.
[12] CYBENKO G. Approximation by superpositions of a sigmoidal function[J]. Mathematics of Control, Signals and Systems, 1989, 2(4):303-314.
[13] BROOMHEAD D S, LOWE D. Radial basis functions, multi-variable functional interpolation and adaptive networks[R]. Great Malvern:Royal Signals and Radar Estab-lishment, 1988.
[14] PARK J, SANDBERG I W. Universal approximation using radial-basis-function networks[J]. Neural Computation, 1991, 3(2):246-257. |
|
Viewed |
|
|
|
Full text
|
|
|
|
|
Abstract
|
|
|
|
|
Cited |
|
|
|
|
| |
Shared |
|
|
|
|
| |
Discussed |
|
|
|
|
2023,
Vol. 63
