Simulation of power plant transients with artificial neural networks: Application to an existing combined cycle

1998 ◽  
Vol 212 (5) ◽  
pp. 299-313 ◽  
Author(s):  
F Fantozzi ◽  
U Desideri
Keyword(s):  
Neural Networks ◽  
Monitoring System ◽  
High Performance ◽  
Combined Cycle ◽  
Transient Behaviour ◽  
Cascade Arrangement ◽  
On Line ◽  
Combined Cycles ◽  
The Difference ◽  
Using Data

To maintain the high performance of gas-turbine-based combined cycles, transients must be properly taken into account in the design phase and efficiently monitored in the operational phase, because they are not negligible time intervals. The use of artificial intelligence techniques such as expert systems, fuzzy sets and neural networks (NNs), coupled with advanced measurement and monitoring devices, can provide a reliable and efficient monitoring system. An existing two-pressure-level combined cycle has been simulated by dividing its simplified model into blocks representative of the main elements. An NN is associated with each of these blocks. Once the training and testing of the NN are complete, using data from a simulator, the blocks are put either in a cascade arrangement or in a parallel arrangement, providing reliable systems that can predict the load-change transient behaviour of the entire plant. The parallel approach was then tested on data from the real plant. The excessive simplification introduced with the simulator required the addition of selected real cases to the training set that are able to fit the NN response to reality. The results obtained are encouraging for use in an on-line monitoring system which evaluates the difference between the measured data and the predicted data.

scholarly journals Use of Artificial Neural Networks for the Simulation of Combined Cycle Transients

1997 ◽  
Author(s):  
Umberto Desideri ◽  
Francesco Fantozzi ◽  
Gianni Bidini ◽  
Philippe Mathieu
Keyword(s):  
Neural Networks ◽  
Monitoring System ◽  
Combined Cycle ◽  
Pollutant Emissions ◽  
Plant Performance ◽  
Load Range ◽  
On Line ◽  
Transient Data ◽  
Combined Cycles ◽  
Economic Assets

Due to techno-economic assets, the demand of combined cycles (CC) is currently growing. Nowadays, in a diversified electricity mix, these plants are often used on a load cycling duty or in the intermediate load range. The ability to start quickly and reliably may be a decisional criterion for the selection of the plant, in addition to the design performance, the cost and the pollutant emissions. Therefore, together with the simulation of CC transients, a proper monitoring system aimed at keeping high plant performance during the transients is required. With the help of advanced measurement and monitoring devices, artificial intelligence (AI) techniques as expert systems (ES) and neural networks (NN) can fulfill this duty. The goal of this paper is to show that a NN technique can be used reliably to obtain the response of a complex energetic system, such as CCs, during a slow transient and consequently as part of an on-line monitoring system. In this work, a CC power plant is simulated by dividing it into three blocks, which are representative of the three main elements of the CC: namely the gas turbine (GT), the heat recovery steam generator (HRSG) and the steam turbine (ST). To each of them a NN is associated. Once the training and testing of the NNs is carried out, the blocks are then arranged in a series cascade, the output of a block being the input of the subsequent one. With this solution, the NN-based system is able to produce the transient response of a CC plant when the input information are the GT inlet parameters. The transient data, not easy to obtain from measurements on existing plants, are provided by the CCDYN simulator (Dechamps, 1995). The performance obtained by the NN based system are observed to be in good agreement with those given by CCDYN, the latter being validated on the basis of measurements in an existing plant. The NN code, providing the departures of the measured data from the predicted ones, can be considered as a proper system for on-line monitoring and diagnosis.

Automatic seismogram analysis: Statistical phase picking and locating methods using one-station three-component data

1992 ◽  
Vol 82 (2) ◽  
pp. 860-869 ◽  
Author(s):  
Matti Tarvainen
Keyword(s):  
Maximum Likelihood Method ◽  
Statistical Data ◽  
Polarization State ◽  
Adaptive Method ◽  
Likelihood Method ◽  
Arrival Times ◽  
On Line ◽  
The Difference ◽  
Data Adaptive ◽  
Using Data

Abstract Seismic events at local and regional distances are located using data from the Vaasa (VAF 63.0 °N, 22.7 °E) three-component station in western Finland. The analysis is performed off-line after pseudo on-line detections. The continuous data are first recorded on long disk loops. These loops can cover 10 days of data. The events are picked using Murdock-Hutt detector and after that they are recorded as separate files for further analysis. The direction of approach, which estimates the polarization state of the signal, is determined by the well-established maximum likelihood method. The difference between the arrival times of P and S phases is used to estimate the distance. Phases observed up to 185 km distance from the source are assumed to be Pg and Sg and beyond that Pn and Sn. The onset times of the phases are estimated by a statistical data-adaptive method. The onsets calculated in this way are very accurate when compared with earlier methods like STA/LTA. Epicenter locations are similar to those of FINSA network reported in Helsinki bulletins. The median of the location differences is about 50 km.

ICONE15-10208 Integrated On-line Plant Monitoring System for HTTR Using Neural Networks

2007 ◽  
Vol 2007.15 (0) ◽  
pp. _ICONE1510-_ICONE1510
Author(s):  
Kunihiko NABESHIMA ◽  
Tomomi MATSUISHI ◽  
Jun MAKINO ◽  
Muhammad SUBEKTI ◽  
Tomio OHNO ◽  
...  
Keyword(s):  
Neural Networks ◽  
Monitoring System ◽  
On Line ◽  
Plant Monitoring ◽  
Line Plant

Modelling the Transient Behavior of Combined Cycle Plants

1994 ◽  
Author(s):  
P. J. Dechamps
Keyword(s):  
Gas Turbine ◽  
Transient Behavior ◽  
Combined Cycle ◽  
Unit Size ◽  
Gas Turbine Unit ◽  
Load Range ◽  
Transient Behaviour ◽  
Combined Cycles ◽  
Industrial Gas Turbine ◽  
Transient Measurements

The last decade has seen remarkable improvement in industrial gas turbine unit size and performances. The coming years and decades hold the promise of even more progress in these fields. Simultaneously, the fuel utilization achieved by combined cycles has been steadily increased, which is a combination of improvements both in the gas turbine technology and in the new combined cycle schemes with multiple pressure levels. These combined cycles quite often have to operate on a load cycling duty or in the intermediate load range, so that not only the design point performances but even the off design are sufficient to ensure the plant profitability. Its transient behaviour, its ability to start quickly and reliably, are key parameters when selecting the plant. This paper describes a method developed for the calculation of the transient performances of combined cycles, from no load situations, including cold conditions, to full load. The method is then applied and illustrated with a recently commissioned plant, for which some transient measurements are available.

scholarly journals Integrated On-line Plant Monitoring System for HTTR with Neural Networks

2008 ◽  
Vol 2 (1) ◽  
pp. 92-103
Author(s):  
Kunihiko NABESHIMA ◽  
Muhammad SUBEKTI ◽  
Tomomi MATSUISHI ◽  
Tomio OHNO ◽  
Kazuhiko KUDO ◽  
...  
Keyword(s):  
Neural Networks ◽  
Monitoring System ◽  
On Line ◽  
Plant Monitoring ◽  
Line Plant

Embedded Hardware and Software Co-Design in SOPC-Based Hydropower On-Line Monitoring System

2013 ◽  
Vol 805-806 ◽  
pp. 721-724
Author(s):  
Hui Deng ◽  
Hai Yu ◽  
Wei Wang ◽  
Gong Hou ◽  
Wen Shen
Keyword(s):  
Embedded System ◽  
System Design ◽  
Monitoring System ◽  
High Performance ◽  
Design Method ◽  
Good Stability ◽  
Practical Application ◽  
Embedded System Design ◽  
On Line ◽  
Software And Hardware

SoPC technology provides a more convenient, flexible and reliable hardware and software co-design for embedded system design. In this paper we use this method in respect of software and hardware to design a new high performance hydropower on-line monitoring system. The device has been successfully integrated in the hydropower on-line monitoring system. The practical application confirms it has high performance, good stability, scalability, and the design method for power occasions other similar applications are also of great referential significance.

Advanced Technology Biomass-Fueled Combined Cycle

2003 ◽  
Author(s):  
D. S. Liscinsky ◽  
J. J. Sangiovanni ◽  
R. L. Robson ◽  
R. S. Tuthill ◽  
A. G. Foyt ◽  
...  
Keyword(s):  
Power Systems ◽  
High Performance ◽  
Combined Cycle ◽  
Department Of Energy ◽  
Advanced Technology ◽  
Integrated Gasification Combined Cycle ◽  
Team Members ◽  
Cycle System ◽  
Combined Cycles ◽  
Integrated Gasification

Under the sponsorship of the U.S. Department of Energy/National Energy Technology Laboratory, a multidisciplinary team led by the United Technologies Research Center (UTRC) has identified a high performance biomass gasification/combined cycle system using Refuse Derived Fuel (RDF) as the major fuel resource. The system consists of fuel receiving/preparation/feed, advanced transport gasifier, high temperature gas cleanup and Pratt & Whitney Power Systems FT8 aero-derivative gas turbine with heat recovery steam generator and steam turbine. One of the team members, Connecticut Resource Recovery Agency (CRRA), currently processes approximately 2200 tons/day of municipal solid waste and delivers 1825 tons/day of RDF “across the fence” to a nominal 65 MWe steam plant. Based on the characteristics of the RDF from this plant, an 80 MWe combined cycle system having an estimated efficiency of 45% (RDF in/kW out) was identified. Other advanced cycle variations had even greater performance potential. The resulting cost of electricity for the biomass integrated gasification combined cycle (BIGCC) is competitive with that of natural gas fueled combined cycles, and the plant is projected to meet or exceed all environmental requirements.

Sign in / Sign up

Export Citation Format

Share Document