Application of Artificial Neural Networks for the Prediction of Pollutant Emissions and Outlet Temperature in a Fuel-Staged Gas Turbine Combustion Rig

2014 ◽  
Author(s):  
Warren G. Lamont ◽  
Mario Roa ◽  
Robert P. Lucht
Keyword(s):  
Gas Turbine ◽  
Experimental Validation ◽  
Operating Conditions ◽  
Optimum Operating ◽  
Outlet Temperature ◽  
Ann Model ◽  
Optimum Operating Condition ◽  
Operating Condition ◽  
Artificial Neural ◽  
The Difference

This study deals with artificial neural network (ANN) modelling of a fuel-staged gas turbine combustion rig to predict exhaust emissions and combustor outlet temperature. The data used for ANN training and testing was acquired from a natural gas burning test rig at various operating conditions. The ANN model uses a multi-layer feed-forward network architecture and was trained with experimental data using backpropagation. The ANN has 8 input neurons, 27 neurons in the hidden layer and 3 output neurons. The ANN model can predict the experimental results quite well with correlation coefficients in the range of 0.96 to 0.99. The ANN model was then used to create performance maps (response surfaces) and to predict two operating conditions that optimize the conflicting criteria of low emissions and high gas outlet temperature. The ANN predicted optimum operating conditions yielded NOx emissions below 20 ppm corrected to 15% O2 and a combustor outlet temperature of 1838 K. These optimum operating conditions were then experimental validated. The experimental validation showed that the first ANN predicted optimum operating condition was poorly predicted: the difference between the ANN predicted equivalence ratio and that of the experimental validation data for the optimum point was over 0.1. The second ANN predicted optimum operating condition was accurately predicted within the experimental uncertainty of the measurements. The difference in validity between the ANN predictions can be attributed to the sparsity of the data: for the first optimum operating condition there were 28 highly clustered training points, while the second optimum operating condition had 40 points that spanned a greater operating region.

scholarly journals A Comparative Study on Fault Detection Methods for Gas Turbine Combustion Systems

Energies ◽  
2021 ◽  
Vol 14 (2) ◽  
pp. 389
Author(s):  
Jinfu Liu ◽  
Zhenhua Long ◽  
Mingliang Bai ◽  
Linhai Zhu ◽  
Daren Yu
Keyword(s):  
Fault Detection ◽  
Gas Turbine ◽  
Gas Turbines ◽  
Operating Conditions ◽  
Detection Methods ◽  
Distribution Model ◽  
Outlet Temperature ◽  
Combustion System ◽  
Comparison Results ◽  
Gas Turbine Combustion

As one of the core components of gas turbines, the combustion system operates in a high-temperature and high-pressure adverse environment, which makes it extremely prone to faults and catastrophic accidents. Therefore, it is necessary to monitor the combustion system to detect in a timely way whether its performance has deteriorated, to improve the safety and economy of gas turbine operation. However, the combustor outlet temperature is so high that conventional sensors cannot work in such a harsh environment for a long time. In practical application, temperature thermocouples distributed at the turbine outlet are used to monitor the exhaust gas temperature (EGT) to indirectly monitor the performance of the combustion system, but, the EGT is not only affected by faults but also influenced by many interference factors, such as ambient conditions, operating conditions, rotation and mixing of uneven hot gas, performance degradation of compressor, etc., which will reduce the sensitivity and reliability of fault detection. For this reason, many scholars have devoted themselves to the research of combustion system fault detection and proposed many excellent methods. However, few studies have compared these methods. This paper will introduce the main methods of combustion system fault detection and select current mainstream methods for analysis. And a circumferential temperature distribution model of gas turbine is established to simulate the EGT profile when a fault is coupled with interference factors, then use the simulation data to compare the detection results of selected methods. Besides, the comparison results are verified by the actual operation data of a gas turbine. Finally, through comparative research and mechanism analysis, the study points out a more suitable method for gas turbine combustion system fault detection and proposes possible development directions.

Into Mesh Lubrication of Spur Gears With Arbitrary Offset Oil Jet. Part 1: For Jet Velocity Less Than or Equal to Gear Velocity

1983 ◽  
Vol 105 (4) ◽  
pp. 713-718 ◽  
Author(s):  
L. S. Akin ◽  
D. P. Townsend
Keyword(s):  
Inclination Angle ◽  
Gear Tooth ◽  
Optimum Operating ◽  
Spur Gears ◽  
Optimum Operating Condition ◽  
Operating Condition ◽  
The Common ◽  
Jet Velocity ◽  
Oil Jet

An analysis was conducted for into mesh oil jet lubrication with an arbitrary offset and inclination angle from the pitch point for the case where the oil jet velocity is equal to or less than pitch line velocity. The analysis includes the case for the oil jet offset from the pitch point in the direction of the pinion and where the oil jet is inclined to intersect the common pitch point. Equations were developed for the minimum oil jet velocity required to impinge on the pinion or gear and the optimum oil jet velocity to obtain the maximum impingement depth. The optimum operating condition for best lubrication and cooling is provided when the oil jet velocity is equal to the gear pitch line velocity with both sides of the gear tooth cooled. When the jet velocity is reduced from pitch line velocity the drive side of the pinion and the unloaded side of the gear is cooled. When the jet velocity is much lower than the pitch line velocity the impingement depth is very small and may completely miss the pinion.

Optimization of Fermentable Sugar Production from Pineapple Leaf Waste (Ananas comosus [L.] Merr) by Enzymatic Hydrolysis

2021 ◽  
Vol 18 (1) ◽  
pp. 73-80
Author(s):  
Yohanita Restu Widihastuty ◽  
Sutini Sutini ◽  
Aida Nur Ramadhani
Keyword(s):  
Enzymatic Hydrolysis ◽  
Complex Structure ◽  
Reducing Sugar ◽  
Sugar Yield ◽  
Ananas Comosus ◽  
Optimum Operating ◽  
Cellulose Content ◽  
Optimum Operating Condition ◽  
Operating Condition ◽  
Cellulase Enzyme

Pineapple leaf waste is one agricultural waste that has high cellulose content. Pineapple leaf waste's complex structure contains a bundle of packed fiber that makes it hard to remove lignin and hemicellulose structure, so challenging to produce reducing sugar. Dried pineapple leaf waste pretreated with a grinder to break its complex structure. Delignification process using 2% w/v NaOH solution at 87oC for 60 minutes has been carried out to remove lignin and hemicellulose structure so reducing sugar could be produced. Delignified pineapple leaf waste has been enzymatic hydrolyzed using cellulase enzyme (6 mL, 7 mL, and 8 mL) to produce reducing sugar. The sample was incubated in an incubator shaker at 155 rpm at 45, 55, and 60oC for 72 hours. Determination of reducing sugar yield had been carried out using the Dubois method and HPLC. The model indicated that the optimum operating condition of enzymatic hydrolysis is 7 mL of cellulase enzyme at 55oC to produce 96,673 mg/L reducing sugar. This result indicated that the enzymatic hydrolysis operating condition improved the reducing sugar yield from pineapple leaf waste. The optimum reducing sugar yield can produce biofuel by the saccharification process.

Combustion Tuning for a Gas Turbine Power Plant Using Data-Driven and Machine Learning Approach

2021 ◽  
Vol 143 (3) ◽  
Author(s):  
Suhui Li ◽  
Huaxin Zhu ◽  
Min Zhu ◽  
Gang Zhao ◽  
Xiaofeng Wei
Keyword(s):  
Machine Learning ◽  
Power Plant ◽  
Gas Turbine ◽  
Operating Conditions ◽  
Data Driven ◽  
Ann Model ◽  
Promising Alternative ◽  
Combustion Performance ◽  
Wide Range ◽  
Gas Turbine Power Plant

Abstract Conventional physics-based or experimental-based approaches for gas turbine combustion tuning are time consuming and cost intensive. Recent advances in data analytics provide an alternative method. In this paper, we present a cross-disciplinary study on the combustion tuning of an F-class gas turbine that combines machine learning with physics understanding. An artificial-neural-network-based (ANN) model is developed to predict the combustion performance (outputs), including NOx emissions, combustion dynamics, combustor vibrational acceleration, and turbine exhaust temperature. The inputs of the ANN model are identified by analyzing the key operating variables that impact the combustion performance, such as the pilot and the premixed fuel flow, and the inlet guide vane angle. The ANN model is trained by field data from an F-class gas turbine power plant. The trained model is able to describe the combustion performance at an acceptable accuracy in a wide range of operating conditions. In combination with the genetic algorithm, the model is applied to optimize the combustion performance of the gas turbine. Results demonstrate that the data-driven method offers a promising alternative for combustion tuning at a low cost and fast turn-around.

Magnetostrictive Methods of Detecting Torque from Case-Hardened Steel Shafts

1994 ◽  
Vol 360 ◽  
Author(s):  
Ichiro Sasada
Keyword(s):  
Excitation Frequency ◽  
Total Power ◽  
Optimum Operating ◽  
Torque Sensor ◽  
Excitation Current ◽  
Optimum Operating Condition ◽  
Operating Condition ◽  
Nickel Chromium ◽  
Low Profile ◽  
Molybdenum Steel

AbstractThis paper begins with a review of the current problems associated with the application of conventional magnetic-head-type shaft torque sensors. These sensors were first proposedin 1954. Newly developed low-profile magnetic heads for torque sensors which address the problems of the older type of sensors are then presented. The torque sensor which uses the lowprofile pick-up heads is described in detail. Experimental results showing the basicperformance of the torque sensor with carburized nickel chromium molybdenum steel shafts (SNCM 420 in JIS) are then described. In this combination of the heads and the shaft, thehysteresis of the inputoutput relationship is generally small and shows that the direction of traversal around the hysteresis loop changes as the amplitude of the excitation current changes. It is shown that an optimum operating condition exists for the torque sensorin which the hysteresis achieves a minimum value yet the sensitivity remains high. In a particular combination studied in this paper, the optimum excitation current was 0.3 A at the excitation frequency 60 kHz, where the total power loss at the pick-up heads was 0.37W. Under this operating condition, the hysteresis was extremely small, and the linearity was better than 0.6%.

Towards Improved Prediction of Aero-Engine Combustor Performance Using Large Eddy Simulations

2008 ◽  
Author(s):  
S. James ◽  
M. S. Anand ◽  
B. Sekar
Keyword(s):  
Gas Turbine ◽  
Radial Profile ◽  
Design Tool ◽  
Operating Conditions ◽  
Outlet Temperature ◽  
Gas Turbine Combustor ◽  
Systematic Assessment ◽  
Eddy Simulation ◽  
Large Eddy ◽  
Aero Engine

The paper presents an assessment of large eddy simulation (LES) and conventional Reynolds averaged methods (RANS) for predicting aero-engine gas turbine combustor performance. The performance characteristic that is examined in detail is the radial burner outlet temperature (BOT) or fuel-air ratio profile. Several different combustor configurations, with variations in airflows, geometries, hole patterns and operating conditions are analyzed with both LES and RANS methods. It is seen that LES consistently produces a better match to radial profile as compared to RANS. To assess the predictive capability of LES as a design tool, pretest predictions of radial profile for a combustor configuration are also presented. Overall, the work presented indicates that LES is a more accurate tool and can be used with confidence to guide combustor design. This work is the first systematic assessment of LES versus RANS on industry-relevant aero-engine gas turbine combustors.

A Novel Approach for Gas Turbine Condition Monitoring Combining CUSUM Technique and Artificial Neural Network

2009 ◽  
Author(s):  
Magnus Fast ◽  
Thomas Palme´ ◽  
Magnus Genrup
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Gas Turbine ◽  
Condition Monitoring ◽  
Sequential Analysis ◽  
Ann Model ◽  
Novel Approach ◽  
Artificial Neural ◽  
Artificial Neural Network Ann ◽  
Operational Data

Investigation of a novel condition monitoring approach, combining artificial neural network (ANN) with a sequential analysis technique, has been reported in this paper. For this purpose operational data from a Siemens SGT600 gas turbine has been employed for the training of an ANN model. This ANN model is subsequently used for the prediction of performance parameters of the gas turbine. Simulated anomalies are introduced on two different sets of operational data, acquired one year apart, whereupon this data is compared with corresponding ANN predictions. The cumulative sum (CUSUM) technique is used to improve and facilitate the detection of such anomalies in the gas turbine’s performance. The results are promising, displaying fast detection of small changes and detection of changes even for a degraded gas turbine.

An Estimation of 3-Way Catalyst Performance Using Artificial Neural Networks During Idle Speed

2004 ◽  
Author(s):  
P. N. Botsaris ◽  
D. Bechrakis ◽  
P. D. Sparis
Keyword(s):  
Neural Networks ◽  
Artificial Neural Networks ◽  
Steady State ◽  
Expert Knowledge ◽  
Operating Conditions ◽  
Experimental Results ◽  
Outlet Temperature ◽  
Practical Applications ◽  
Idle Speed ◽  
Artificial Neural

The intelligent control as fuzzy or artificial is based on either expert knowledge or experimental data and therefore it possesses intrinsic qualities like robustness and ease implementation. Lately, many researchers present studies aim to show that this kind of control can be used in practical applications such as the idle speed control problem in automotive industry. In this study, an estimation of an automobile three-way catalyst performance with artificial neural networks is presented. It may be an alternative approach for an on board diagnostic system (OBD) to predict the catalyst performance. This method was tested using data sets from two kind of catalysts, a brand new and an old one on a laboratory bench at idle speed. The catalyst operation during the “steady state” phase (the phase that the catalyst has reached its operating conditions and works normally) is examined. Further experiments are needed for different catalyst typed before the methods is proposed generally. It consists of 855 elements of catalyst inlet-outlet temperature difference (DT), hydrocarbons (HC), and carbon monoxide (CO) and carbon dioxide (CO2) emissions. The simulation: detects the values of HC, CO, CO2 using the DT as an input to our network forms a neural network. Results showed serious indications that artificial neural networks (or fuzzy logic control laws) could estimate the catalyst performance adequately depending their training process, if certain information about the catalyst system and the inputs and output of such system are known. In this study the “steady state” period experimental results are presented. In this paper the “steady state” period experimental results are presented.

Sign in / Sign up

Export Citation Format

Share Document