Bayesian Calibration for Power Splitting in Single-Shaft Combined Cycle Plant Diagnostics

2015 ◽  
Vol 138 (5) ◽  
Author(s):  
Xiaomo Jiang ◽  
TsungPo Lin ◽  
Eduardo Mendoza
Keyword(s):  
Bayesian Inference ◽  
Power Plant ◽  
Gas Turbine ◽  
Combined Cycle ◽  
Operating Conditions ◽  
Plant Performance ◽  
Sensor Data ◽  
Power Splitting ◽  
Plant Level ◽  
Operational Data

Condition monitoring and diagnostics of a combined cycle gas turbine (CCGT) power plant has become an important tool to improve its availability, reliability, and performance. However, there are two major challenges in the diagnostics of performance degradation and anomaly in a single-shaft combined cycle (CC) power plant. First, since the gas turbine (GT) and steam turbine (ST) in such a plant share a common generator, each turbine's contribution to the total plant power output is not directly measured, but must be accurately estimated to identify the possible causes of plant level degradation. Second, multivariate operational data instrumented from a power plant need to be used in the plant model calibration, power splitting, and degradation diagnostics. Sensor data always contain some degree of uncertainty. This adds to the difficulty of both estimation of GT to ST power split (PS) and degradation diagnostics. This paper presents an integrated probabilistic methodology for accurate power splitting and the degradation diagnostics of a single-shaft CC plant, accounting for uncertainties in the measured data. The method integrates the Bayesian inference approach, thermodynamic physics modeling, and sensed operational data seamlessly. The physics-based thermodynamic heat balance model is first established to model the power plant components and their thermodynamic relationships. The model is calibrated to model the plant performance at the design conditions of its main components. The calibrated model is then employed to simulate the plant performance at various operating conditions. A Bayesian inference method is next developed to determine the PS between the GT and the ST by comparing the measured and expected power outputs at different operation conditions, considering uncertainties in multiple measured variables. The calibrated model and calculated PS are further applied to pinpoint the possible causes at individual components resulting in the plant level degradation. The proposed methodology is demonstrated using operational data from a real-world single-shaft CC power plant with a known degradation issue. This study provides an effective probabilistic methodology to accurately split the power for degradation diagnostics of a single-shaft CC plant, addressing the uncertainties in multiple measured variables.

Bayesian Calibration for Power Splitting in Single Shaft Combined Cycle Plant Diagnostics

2015 ◽  
Author(s):  
Xiaomo Jiang ◽  
Eduardo Mendoza ◽  
TsungPo Lin
Keyword(s):  
Power Plant ◽  
Steam Turbine ◽  
Gas Turbine ◽  
Combined Cycle ◽  
Plant Performance ◽  
Power Splitting ◽  
Power Split ◽  
Combined Cycle Plant ◽  
Plant Level ◽  
Operational Data

Condition monitoring and diagnostics of a combined cycle gas turbine power plant has become an important tool to improve its availability, reliability, and performance. However, there are two major challenges in the diagnostics of performance degradation and anomaly in a single shaft combined cycle power plant. First, since the gas turbine and steam turbine in such a plant share a common generator, each turbine’s contribution to the total plant power output is not directly measured, but must be accurately estimated to identify the possible causes of plant level degradation. Second, multivariate operational data instrumented from a power plant need to be used in the plant model calibration, power splitting and degradation diagnostics. Sensor data always contains some degree of uncertainty. This adds to the difficulty of both estimation of gas turbine to steam turbine power split and degradation diagnostics. This paper presents an integrated probabilistic methodology for accurate power splitting and the degradation diagnostics of a single shaft combined cycle plant, accounting for uncertainties in the measured data. The method integrates the Bayesian inference approach, thermodynamic physics modeling, and sensed operational data seamlessly. The physics-based thermodynamic heat balance model is first established to model the power plant components and their thermodynamic relationships. The model is calibrated to model the plant performance at the design conditions of its main components. The calibrated model is then employed to simulate the plant performance at various operating conditions. A Bayesian inference method is next developed to determine the power split between the gas turbine and the steam turbine by comparing the measured and expected power outputs at different operation conditions, considering uncertainties in multiple measured variables. The calibrated model and calculated power split are further applied to pinpoint the possible causes at individual components resulting in the plant level degradation. The proposed methodology is demonstrated using operational data from a real-world single shaft combined cycle power plant with a known degradation issue. This study provides an effective probabilistic methodology to accurately split the power for degradation diagnostics of a single shaft combined cycle plant, addressing the uncertainties in multiple measured variables.

A Sequential Approach for Gas Turbine Power Plant Preventative Maintenance Scheduling

2005 ◽  
Vol 128 (4) ◽  
pp. 796-805 ◽  
Author(s):  
Yongjun Zhao ◽  
Vitali Volovoi ◽  
Mark Waters ◽  
Dimitri Mavris
Keyword(s):  
Power Plant ◽  
Gas Turbine ◽  
Preventive Maintenance ◽  
Combined Cycle ◽  
Operating Conditions ◽  
Maintenance Scheduling ◽  
Plant Performance ◽  
Optimization Approach ◽  
Sequential Approach ◽  
Gas Turbine Power Plant

Traditionally, gas turbine power plant preventive maintenance schedules are set with constant intervals based on recommendations from the equipment suppliers. Preventive maintenance is based on fleet-wide experience as a guideline as long as individual unit experience is not available. In reality, the operating conditions for each gas turbine may vary from site to site and from unit to unit. Furthermore, the gas turbine is a repairable deteriorating system, and preventive maintenance usually restores only part of its performance. This suggests a gas turbine needs more frequent inspection and maintenance as it ages. A unit-specific sequential preventive maintenance approach is therefore needed for gas turbine power plant preventive maintenance scheduling. Traditionally, the optimization criteria for preventive maintenance scheduling is usually cost based. However, in the deregulated electric power market, a profit-based optimization approach is expected to be more effective than the cost-based approach. In such an approach, power plant performance, reliability, and the market dynamics are considered in a joint fashion. In this paper, a novel idea that economic factors drive maintenance frequency and expense to more frequent repairs and greater expense as equipment ages is introduced, and a profit-based unit-specific sequential preventive maintenance scheduling methodology is developed. To demonstrate the feasibility of the proposed approach, a conceptual level study is performed using a base load combined cycle power plant with a single gas turbine unit.

A Sequential Approach for Gas Turbine Power Plant Preventive Maintenance Scheduling

2005 ◽  
Author(s):  
Yongjun Zhao ◽  
Vitali Volovoi ◽  
Mark Waters ◽  
Dimitri Mavris
Keyword(s):  
Power Plant ◽  
Gas Turbine ◽  
Preventive Maintenance ◽  
Gas Turbines ◽  
Combined Cycle ◽  
Operating Conditions ◽  
Maintenance Scheduling ◽  
Plant Performance ◽  
Optimization Approach ◽  
Gas Turbine Power Plant

Traditionally the gas turbine power plant preventive maintenances are scheduled with constant maintenance intervals based on recommendations from the equipment suppliers. The preventive maintenances are based on fleet wide experiences, and they are scheduled in a one-size-fit-all fashion. However, in reality, the operating conditions for each gas turbine may vary from site to site, and from unit to unit. Furthermore, the gas turbine is a repairable deteriorating system, and preventive maintenance usually restores only part of its performance. This suggests the gas turbines need more frequent inspection and maintenance as it ages. A unit specific sequential preventive maintenance approach is therefore needed for gas turbine power plants preventive maintenance scheduling. Traditionally the optimization criteria for preventive maintenance scheduling is usually cost based. In the deregulated electric power market, a profit based optimization approach is expected to be more effective than the cost based approach. In such an approach, power plant performance, reliability, and the market dynamics are considered in a joint fashion. In this paper, a novel idea that economics drive maintenance expense and frequency to more frequent repairs and greater expense as the equipment and components age is introduced, and a profit based unit specific sequential preventive maintenance scheduling methodology is developed. To demonstrate the feasibility of the proposed approach, this methodology is implemented using a base load combined cycle power plant with single gas turbine unit.

Modeling and Performance Analysis of Combined-Cycle Based Ship Power Plant

2010 ◽  
Vol 44-47 ◽  
pp. 1240-1245 ◽  
Author(s):  
Hong Zeng ◽  
Xiao Ling Zhao ◽  
Jun Dong Zhang
Keyword(s):  
Diesel Engine ◽  
Power Plant ◽  
Performance Analysis ◽  
Combined Cycle ◽  
Operating Conditions ◽  
Fuel Oil ◽  
Plant Performance ◽  
Oil Consumption ◽  
Combined Cycle Power Plant ◽  
Simulation Performance

For combined-cycle power plant performance analysis, a ship power plant mathematical model is developed, including diesel engine, controllable pitch propeller, exhaust gas boiler, turbine generator and shaft generator models. The simulation performance characteristic curves of diesel engine under various loads are given. Comparison of simulation results and experimental data shows the model can well predict the performance of diesel engine in various operating conditions. The specific fuel oil consumption contours of combined-cycle power plant and the relations between engine operating conditions and steam cycle parameters are given. The influence of diesel engine operating conditions to the overall performance of combined-cycle power plant is discussed.

Short-Term Optimization of a Combined Cycle Power Plant Integrated With an Inlet Air Conditioning Unit

2020 ◽  
Author(s):  
Weimar Mantilla ◽  
José García ◽  
Rafael Guédez ◽  
Alessandro Sorce
Keyword(s):  
Power Plant ◽  
Gas Turbine ◽  
Gas Turbines ◽  
Air Conditioning ◽  
Combined Cycle ◽  
Plant Performance ◽  
Mixed Integer ◽  
Environmental Load ◽  
Turbine Inlet ◽  
The Impact

Abstract Under new scenarios with high shares of variable renewable electricity, combined cycle gas turbines (CCGT) are required to improve their flexibility, in terms of ramping capabilities and part-load efficiency, to help balance the power system. Simultaneously, liberalization of electricity markets and the complexity of its hourly price dynamics are affecting the CCGT profitability, leading the need for optimizing its operation. Among the different possibilities to enhance the power plant performance, an inlet air conditioning unit (ICU) offers the benefit of power augmentation and “minimum environmental load” (MEL) reduction by controlling the gas turbine inlet temperature using cold thermal energy storage and a heat pump. Consequently, an evaluation of a CCGT integrated with this inlet conditioning unit including a day-ahead optimized operation strategy was developed in this study. To establish the hourly dispatch of the power plant and the operation mode of the inlet conditioning unit to either cool down or heat up the gas turbine inlet air, a mixed-integer linear optimization (MILP) was formulated using MATLAB, aiming to maximize the operational profit of the plant within a 24-hours horizon. To assess the impact of the proposed unit operating under this dispatch strategy, historical data of electricity and natural gas prices, as well as meteorological data and CO2 emission allowances price, have been used to perform annual simulations of a reference power plant located in Turin, Italy. Furthermore, different equipment capacities and parameters have been investigated to identify trends of the power plant performance. Lastly, a sensitivity analysis on market conditions to test the control strategy response was also considered. Results indicate that the inlet conditioning unit, together with the dispatch optimization, increases the power plant’s operational profit by achieving a wider operational range, particularly important during peak and off-peak periods. For the specific case study, it is estimated that the net present value of the CCGT integrated with the ICU is 0.5% higher than the power plant without the unit. In terms of technical performance, results show that the unit reduces the minimum environmental load by approximately 1.34% and can increase the net power output by 0.17% annually.

Performance Benefit Assessment of Ceramic Components in an MS9001FA Gas Turbine

1998 ◽  
Author(s):  
Clayton M. Grondahl ◽  
Toshiaki Tsuchiya
Keyword(s):  
Power Plant ◽  
Gas Turbine ◽  
Combined Cycle ◽  
Plant Performance ◽  
Cooling Flow ◽  
Standard Design ◽  
Ceramic Components ◽  
Compressor Inlet ◽  
Turbine Component ◽  
Plant Configuration

The introduction of a ceramic gas turbine component in commercial power generation service will require significant effort. A careful assessment of the power plant performance benefit achievable from the use of ceramic components is necessary to rationalize the priority of this development compared to other alternatives. This paper overviews a study in which the performance benefit from ceramic components was evaluated for an MS9001FA gas turbine in a combined cycle power plant configuration. The study was performed with guidelines of maintaining constant compressor inlet airflow and turbine exit NOx emissions, effectively setting the combustion reaction zone temperature. Cooling flow estimates were calculated to maintain standard design life expectancy of all components. Monolithic silicon nitride ceramic was considered for application to the transition piece, stage one and two buckets, nozzles and shrouds. Performance benefit was calculated both for ceramic properties at 1093C (2200F) and for the more optimistic 1315C (2400F) oxidatian limit of the ceramic. Hybrid ceramic-metal components were evaluated in the less optimistic case.

Allocating the Causes of Performance Deterioration in Combined Cycle Gas Turbine Plants

2002 ◽  
Vol 124 (2) ◽  
pp. 256-262 ◽  
Author(s):  
K. Mathioudakis ◽  
A. Stamatis ◽  
E. Bonataki
Keyword(s):  
Power Plant ◽  
Gas Turbine ◽  
Combined Cycle ◽  
Operating Conditions ◽  
Test Cases ◽  
Performance Deterioration ◽  
Baseline Values ◽  
The Way

A method for defining which parts of a combined cycle gas turbine (CCGT) power plant are responsible for performance deviations is presented. When the overall performances deviate from their baseline values, application of the method allows the determination of the component(s) of the plant, responsible for this deviation. It is shown that simple differentiation approaches may lead to erroneous conclusions, because they do not reveal the nature of deviations for individual components. Contributions of individual components are then assessed by separating deviations due to permanent changes and deviations due to change of operating conditions. A generalized formulation is presented together with the way of implementing it. Test cases are given, to make clearer the ideas put forward in the proposed method.

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.

An Expanded Cost of Electricity Model for Highly Flexible Power Plants

2012 ◽  
Vol 135 (1) ◽  
Author(s):  
S. Can Gülen ◽  
Indrajit Mazumder
Keyword(s):  
Power Generation ◽  
Power Plant ◽  
Gas Turbine ◽  
Power Plants ◽  
Combined Cycle ◽  
Plant Performance ◽  
Cost Of Electricity ◽  
Renewable Power ◽  
Effective Performance ◽  
The Impact

Cost of electricity (COE) is the most widely used metric to quantify the cost-performance trade-off involved in comparative analysis of competing electric power generation technologies. Unfortunately, the currently accepted formulation of COE is only applicable to comparisons of power plant options with the same annual electric generation (kilowatt-hours) and the same technology as defined by reliability, availability, and operability. Such a formulation does not introduce a big error into the COE analysis when the objective is simply to compare two or more base-loaded power plants of the same technology (e.g., natural gas fired gas turbine simple or combined cycle, coal fired conventional boiler steam turbine, etc.) and the same (or nearly the same) capacity. However, comparing even the same technology class power plants, especially highly flexible advanced gas turbine combined cycle units with cyclic duties, comprising a high number of daily starts and stops in addition to emissions-compliant low-load operation to accommodate the intermittent and uncertain load regimes of renewable power generation (mainly wind and solar) requires a significant overhaul of the basic COE formula. This paper develops an expanded COE formulation by incorporating crucial power plant operability and maintainability characteristics such as reliability, unrecoverable degradation, and maintenance factors as well as emissions into the mix. The core impact of duty cycle on the plant performance is handled via effective output and efficiency utilizing basic performance correction curves. The impact of plant start and load ramps on the effective performance parameters is included. Differences in reliability and total annual energy generation are handled via energy and capacity replacement terms. The resulting expanded formula, while rigorous in development and content, is still simple enough for most feasibility study type of applications. Sample calculations clearly reveal that inclusion (or omission) of one or more of these factors in the COE evaluation, however, can dramatically swing the answer from one extreme to the other in some cases.

Sign in / Sign up

Export Citation Format

Share Document