Convolutional neural network-based deep transfer learning for fault detection of gas turbine combustion chambers

2021 ◽  
Vol 302 ◽  
pp. 117509
Author(s):  
Mingliang Bai ◽  
Xusheng Yang ◽  
Jinfu Liu ◽  
Jiao Liu ◽  
Daren Yu
Keyword(s):  
Neural Network ◽  
Fault Detection ◽  
Convolutional Neural Network ◽  
Gas Turbine ◽  
Transfer Learning ◽  
Combustion Chambers ◽  
Gas Turbine Combustion

scholarly journals Fault Detection for Gas Turbine Hot Components Based on a Convolutional Neural Network

Energies ◽  
2018 ◽  
Vol 11 (8) ◽  
pp. 2149 ◽  
Author(s):  
Jiao Liu ◽  
Jinfu Liu ◽  
Daren Yu ◽  
Myeongsu Kang ◽  
Weizhong Yan ◽  
...  
Keyword(s):  
Neural Network ◽  
Fault Detection ◽  
Convolutional Neural Network ◽  
Gas Turbine ◽  
Detection Sensitivity ◽  
Large Temperature ◽  
Gas Temperature ◽  
Ambient Conditions ◽  
Real World Data ◽  
The Impact

Gas turbine hot component failures often cause catastrophic consequences. Fault detection can improve the availability and economy of hot components. The exhaust gas temperature (EGT) profile is usually used to monitor the performance of the hot components. The EGT profile is uniform when the hot component is healthy, whereas hot component faults lead to large temperature differences between different EGT values. The EGT profile swirl under different operating and ambient conditions also cause temperature differences. Therefore, the influence of EGT profile swirl on EGT values must be eliminated. To improve the detection sensitivity, this paper develops a fault detection method for hot components based on a convolutional neural network (CNN). This paper demonstrates that a CNN can extract the information between adjacent EGT values and consider the impact of the EGT profile swirl. This paper reveals, in principle, that a CNN is a viable solution for dealing with fault detection for hot components. Based on the distribution characteristics of EGT thermocouples, the circular padding method is developed in the CNN. The sensitivity of the developed method is verified by real-world data. Moreover, the developed method is visualized in detail. The visualization results reveal that the CNN effectively considers the influence of the EGT profile swirl.

On the Prediction of Nitrogen Oxides From Gas Turbine Combustion Chambers Using Neural Networks

2008 ◽  
Author(s):  
Marc LaViolette ◽  
Michael Strawson
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Gas Turbine ◽  
Empirical Model ◽  
Empirical Models ◽  
Coefficient Of Determination ◽  
Combustion Chambers ◽  
Nitrogen Emissions ◽  
Gas Turbine Combustion ◽  
Semi Empirical

This paper describes a method of predicting the oxides of nitrogen emissions from gas turbine combustion chambers using neural networks. A short review of existing empirical models is undertaken and the reasoning behind the choice of correlation variables and mathematical formulations is presented. This review showed that the mathematical functions obtained from the underlying theory used to develop the semi-empirical model ultimately limit their general applicability. Under these conditions, obtaining a semi-empirical model with a large domain and good accuracy is difficult. An overview of the use of neural networks as a modelling tool is given. Using over 2000 data points, a neural network that can predict NOx emissions with greater accuracy than published correlations was developed. The coefficients of determination of the prediction for the previous published semi-empirical models are 0.8048 and 0.7885. However one tends to grossly overpredict and the other underpredict. The coefficient of determination is 0.8697 for the model using a neural network. Because of the nature of neural networks, this more accurate model does not allow better insight into the physical and chemical phenomena. It is however, a useful tool for the initial design of combustion chambers.

scholarly journals Effectiveness of transfer learning for enhancing tumor classification with a convolutional neural network on frozen sections

2020 ◽  
Vol 10 (1) ◽  
Author(s):  
Young-Gon Kim ◽  
Sungchul Kim ◽  
Cristina Eunbee Cho ◽  
In Hye Song ◽  
Hee Jin Lee ◽  
...  
Keyword(s):  
Neural Network ◽  
Deep Learning ◽  
Convolutional Neural Network ◽  
Transfer Learning ◽  
Frozen Section ◽  
Medical Center ◽  
External Validation ◽  
Model Performance ◽  
Classification Model ◽  
Training Dataset

AbstractFast and accurate confirmation of metastasis on the frozen tissue section of intraoperative sentinel lymph node biopsy is an essential tool for critical surgical decisions. However, accurate diagnosis by pathologists is difficult within the time limitations. Training a robust and accurate deep learning model is also difficult owing to the limited number of frozen datasets with high quality labels. To overcome these issues, we validated the effectiveness of transfer learning from CAMELYON16 to improve performance of the convolutional neural network (CNN)-based classification model on our frozen dataset (N = 297) from Asan Medical Center (AMC). Among the 297 whole slide images (WSIs), 157 and 40 WSIs were used to train deep learning models with different dataset ratios at 2, 4, 8, 20, 40, and 100%. The remaining, i.e., 100 WSIs, were used to validate model performance in terms of patch- and slide-level classification. An additional 228 WSIs from Seoul National University Bundang Hospital (SNUBH) were used as an external validation. Three initial weights, i.e., scratch-based (random initialization), ImageNet-based, and CAMELYON16-based models were used to validate their effectiveness in external validation. In the patch-level classification results on the AMC dataset, CAMELYON16-based models trained with a small dataset (up to 40%, i.e., 62 WSIs) showed a significantly higher area under the curve (AUC) of 0.929 than those of the scratch- and ImageNet-based models at 0.897 and 0.919, respectively, while CAMELYON16-based and ImageNet-based models trained with 100% of the training dataset showed comparable AUCs at 0.944 and 0.943, respectively. For the external validation, CAMELYON16-based models showed higher AUCs than those of the scratch- and ImageNet-based models. Model performance for slide feasibility of the transfer learning to enhance model performance was validated in the case of frozen section datasets with limited numbers.

Sign in / Sign up

Export Citation Format

Share Document