scholarly journals Using Machine Learning Tools to Predict Compressor Stall

2020 ◽  
Vol 142 (7) ◽  
Author(s):  
Samuel M. Hipple ◽  
Harry Bonilla-Alvarado ◽  
Paolo Pezzini ◽  
Lawrence Shadle ◽  
Kenneth M. Bryden
Keyword(s):  
Machine Learning ◽  
Power Systems ◽  
Gas Turbine ◽  
Clean Energy ◽  
Operating Conditions ◽  
Learning Tools ◽  
Power Sources ◽  
Load Following ◽  
Wide Range ◽  
Compressor Surge

Abstract Clean energy has become an increasingly important consideration in today’s power systems. As the push for clean energy continues, many coal-fired power plants are being decommissioned in favor of renewable power sources such as wind and solar. However, the intermittent nature of renewables means that dynamic load following traditional power systems is crucial to grid stability. With high flexibility and fast response at a wide range of operating conditions, gas turbine systems are poised to become the main load following component in the power grid. Yet, rapid changes in load can lead to fluid flow instabilities in gas turbine power systems. These instabilities often lead to compressor surge and stall, which are some of the most critical problems facing the safe and efficient operation of compressors in turbomachinery today. Although the topic of compressor surge and stall has been extensively researched, no methods for early prediction have been proven effective. This study explores the utilization of machine learning tools to predict compressor stall. The long short-term memory (LSTM) model, a form of recurrent neural network (RNN), was trained using real compressor stall datasets from a 100 kW recuperated gas turbine power system designed for hybrid configuration. Two variations of the LSTM model, classification and regression, were tested to determine optimal performance. The regression scheme was determined to be the most accurate approach, and a tool for predicting compressor stall was developed using this configuration. Results show that the tool is capable of predicting stalls 5–20 ms before they occur. With a high-speed controller capable of 5 ms time-steps, mitigating action could be taken to prevent compressor stall before it occurs.

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.

Using Machine Learning to Increase Model Performance for a Gas Turbine System

2020 ◽  
Author(s):  
Samuel M. Hipple ◽  
Zachary T. Reinhart ◽  
Harry Bonilla-Alvarado ◽  
Paolo Pezzini ◽  
Kenneth Mark Bryden
Keyword(s):  
Machine Learning ◽  
Power Plant ◽  
Gas Turbine ◽  
Clean Energy ◽  
Learning Model ◽  
Operating Conditions ◽  
Plant Performance ◽  
Outlet Temperature ◽  
Machine Learning Model ◽  
Critical Components

Abstract With increasing regulation and the push for clean energy, the operation of power plants is becoming increasingly complex. This complexity combined with the need to optimize performance at base load and off-design condition means that predicting power plant performance with computational modeling is more important than ever. However, traditional modeling approaches such as physics-based models do not capture the true performance of power plant critical components. The complexity of factors such as coupling, noise, and off-design operating conditions makes the performance prediction of critical components such as turbomachinery difficult to model. In a complex system, such as a gas turbine power plant, this creates significant disparities between models and actual system performance that limits the detection of abnormal operations. This study compares machine learning tools to predict gas turbine performance over traditional physics-based models. A long short-term memory (LSTM) model, a form of a recurrent neural network, was trained using operational datasets from a 100 kW recuperated gas turbine power system designed for hybrid configuration. The LSTM turbine model was trained to predict shaft speed, outlet pressure, and outlet temperature. The performance of both the machine learning model and a physics-based model were compared against experimental data of the gas turbine system. Results show that the machine learning model has significant advantages in prediction accuracy and precision compared to a traditional physics-based model when fed facility data as an input. This advantage of predicting performance by machine learning models can be used to detect abnormal operations.

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

2020 ◽  
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 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 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.

scholarly journals Heat Transfer Effect on Micro Gas Turbine Performance for Solar Power Applications

Energies ◽  
2021 ◽  
Vol 14 (20) ◽  
pp. 6745
Author(s):  
Mahmoud A. Khader ◽  
Mohsen Ghavami ◽  
Jafar Al-Zaili ◽  
Abdulnaser I. Sayma
Keyword(s):  
Heat Transfer ◽  
Power Systems ◽  
Gas Turbine ◽  
Computational Study ◽  
Thermodynamic Cycle ◽  
Operating Conditions ◽  
Micro Gas Turbine ◽  
Turbine Performance ◽  
Wide Range ◽  
The Cost

This paper presents an experimentally validated computational study of heat transfer within a compact recuperated Brayton cycle microturbine. Compact microturbine designs are necessary for certain applications, such as solar dish concentrated power systems, to ensure a robust rotodynamic behaviour over the wide operating envelope. This study aims at studying the heat transfer within a 6 kWe micro gas turbine to provide a better understanding of the effect of heat transfer on its components’ performance. This paper also investigates the effect of thermal losses on the gas turbine performance as a part of a solar dish micro gas turbine system and its implications on increasing the size and the cost of such system. Steady-state conjugate heat transfer analyses were performed at different speeds and expansion ratios to include a wide range of operating conditions. The analyses were extended to examine the effects of insulating the microturbine on its thermodynamic cycle efficiency and rated power output. The results show that insulating the microturbine reduces the thermal losses from the turbine side by approximately 11% without affecting the compressor’s performance. Nonetheless, the heat losses still impose a significant impact on the microturbine performance, where these losses lead to an efficiency drop of 7.1% and a net output power drop of 6.6% at the design point conditions.

scholarly journals Development of the PGT 25 High Efficiency Gas Turbine: Part 2 — Aerodynamic Design and Performance

1984 ◽  
Author(s):  
E. Benvenuti ◽  
B. Innocenti ◽  
R. Modi
Keyword(s):  
Gas Turbine ◽  
High Efficiency ◽  
Performance Testing ◽  
Operating Conditions ◽  
Aerodynamic Design ◽  
Direct Drive ◽  
Gas Generator ◽  
Full Load ◽  
Wide Range ◽  
Overall Performance

This paper outlines parameter selection criteria and major procedures used in the PGT 25 gas turbine power spool aerodynamic design; significant results of the shop full-load tests are also illustrated with reference to both overall performance and internal flow-field measurements. A major aero-design objective was established as that of achieving the highest overall performance levels possible with the matching to latest generation aero-derivative gas generators; therefore, high efficiencies were set as a target both for the design point and for a wide range of operating conditions, to optimize the turbine’s uses in mechanical drive applications. Furthermore, the design was developed to reach the performance targets in conjunction with the availability of a nominal shaft speed optimized for the direct drive of pipeline booster centrifugal compressors. The results of the full-load performance testing of the first unit, equipped with a General Electric LM 2500/30 gas generator, showed full attainment of the design objectives; a maximum overall thermal efficiency exceeding 37% at nominal rating and a wide operating flexibility with regard to both efficiency and power were demonstrated.

Uncertainty Analysis of Inflow Conditions on an HPT Gas Turbine Nozzle: Effect on Particle Deposition

2020 ◽  
Author(s):  
R. Friso ◽  
N. Casari ◽  
M. Pinelli ◽  
A. Suman ◽  
F. Montomoli
Keyword(s):  
Gas Turbine ◽  
Energy Efficient ◽  
Gas Turbines ◽  
Particle Deposition ◽  
Operating Conditions ◽  
Wide Range ◽  
And Performance ◽  
Gas Turbine Nozzle ◽  
The Impact ◽  
Inflow Conditions

Abstract Gas turbines (GT) are often forced to operate in harsh environmental conditions. Therefore, the presence of particles in their flow-path is expected. With this regard, deposition is a problem that severely affects gas turbine operation. Components’ lifetime and performance can dramatically vary as a consequence of this phenomenon. Unfortunately, the operating conditions of the machine can vary in a wide range, and they cannot be treated as deterministic. Their stochastic variations greatly affect the forecasting of life and performance of the components. In this work, the main parameters considered affected by the uncertainty are the circumferential hot core location and the turbulence level at the inlet of the domain. A stochastic analysis is used to predict the degradation of a high-pressure-turbine (HPT) nozzle due to particulate ingestion. The GT’s component analyzed as a reference is the HPT nozzle of the Energy-Efficient Engine (E3). The uncertainty quantification technique used is the probabilistic collocation method (PCM). This work shows the impact of the operating conditions uncertainties on the performance and lifetime reduction due to deposition. Sobol indices are used to identify the most important parameter and its contribution to life. The present analysis enables to build confidence intervals on the deposit profile and on the residual creep-life of the vane.

Advanced Control for Clusters of SOFC/Gas Turbine Hybrid Systems

2018 ◽  
Vol 140 (5) ◽  
Author(s):  
Iacopo Rossi ◽  
Valentina Zaccaria ◽  
Alberto Traverso
Keyword(s):  
Fuel Cell ◽  
Power Systems ◽  
Gas Turbine ◽  
Power Plants ◽  
Numerical Approach ◽  
Computational Time ◽  
Target System ◽  
Wide Range ◽  
Advanced Control ◽  
Complex Target

The use of model predictive control (MPC) in advanced power systems can be advantageous in controlling highly coupled variables and optimizing system operations. Solid oxide fuel cell/gas turbine (SOFC/GT) hybrids are an example where advanced control techniques can be effectively applied. For example, to manage load distribution among several identical generation units characterized by different temperature distributions due to different degradation paths of the fuel cell stacks. When implementing an MPC, a critical aspect is the trade-off between model accuracy and simplicity, the latter related to a fast computational time. In this work, a hybrid physical and numerical approach was used to reduce the number of states necessary to describe such complex target system. The reduced number of states in the model and the simple framework allow real-time performance and potential extension to a wide range of power plants for industrial application, at the expense of accuracy losses, discussed in the paper.

Experimental Investigations of Pressure Drop in the Combustion Chamber of Gas Turbine

1989 ◽  
Author(s):  
Marek Dzida ◽  
Krzysztof Kosowski
Keyword(s):  
Pressure Drop ◽  
Combustion Chamber ◽  
Gas Turbine ◽  
Gas Turbines ◽  
Operating Conditions ◽  
Experimental Results ◽  
Experimental Investigations ◽  
Relative Pressure ◽  
Wide Range ◽  
Few Data

In bibliography we can find many methods of determining pressure drop in the combustion chambers of gas turbines, but there is only very few data of experimental results. This article presents the experimental investigations of pressure drop in the combustion chamber over a wide range of part-load performances (from minimal power up to take-off power). Our research was carried out on an aircraft gas turbine of small output. The experimental results have proved that relative pressure drop changes with respect to fuel flow over the whole range of operating conditions. The results were then compared with theoretical methods.

Analysis of Indirectly Fired Gas Turbine Power Systems

2007 ◽  
Author(s):  
J. E. Donald Gauthier
Keyword(s):  
Power Generation ◽  
Power Systems ◽  
Gas Turbine ◽  
Gas Turbines ◽  
Turbine Engines ◽  
Inlet Temperature ◽  
Turbine Engine ◽  
Engine Design ◽  
Wide Range ◽  
System Configurations

This paper describes the results of modelling the performance of several indirectly fired gas turbine (IFGT) power generation system configurations based on four gas turbine class sizes, namely 5 kW, 50 kW, 5 MW and 100 MW. These class sizes were selected to cover a wide range of installations in residential, commercial, industrial and large utility power generation installations. Because the IFGT configurations modelled consist of a gas turbine engine, one or two recuperators and a furnace; for comparison purpose this study also included simulations of simple cycle and recuperated gas turbine engines. Part-load, synchronous-speed simulations were carried out with generic compressor and turbine maps scaled for each engine design point conditions. The turbine inlet temperature (TIT) was varied from the design specification to a practical value for a metallic high-temperature heat exchanger in an IFGT system. As expected, the results showed that the reduced TIT can have dramatic impact on the power output and thermal efficiency when compared to that in conventional gas turbines. However, the simulations also indicated that several configurations can lead to higher performance, even with the reduced TIT. Although the focus of the study is on evaluation of thermodynamic performance, the implications of varying configurations on cost and durability are also discussed.

Sign in / Sign up

Export Citation Format

Share Document