scholarly journals Prediction of combined cycle power plant electrical output power using machine learning regression algorithms

2021 ◽  
Vol 6 (8 (114)) ◽  
Author(s):  
Nader S. Santarisi ◽  
Sinan S. Faouri
Keyword(s):  
Power Plant ◽  
Power Output ◽  
Mean Squared Error ◽  
Electrical Power ◽  
Combined Cycle ◽  
Full Load ◽  
Squared Error ◽  
Dimensionality Reduction Technique ◽  
Regression Algorithms ◽  
Electrical Power Output

In order to monitor the performance and related efficiency of a combined cycle power plant (CCPP), in addition to the best utilization of its power output, it is vital to predict its full load electrical power output. In this paper, the full load electrical power output of CCPP was predicted employing practically efficient machine learning algorithms, including linear regression, ridge regression, lasso regression, elastic net regression, random forest regression, and gradient boost regression. The original data came from an actual confidential power plant, which was working on a full load for 6 years, with four major features: ambient temperature, relative humidity, atmospheric pressure, and exhaust vacuum, and one target (electrical power output per hour). Different regression performance measures were used, including R2 (coefficient of determination), MAE (Mean Absolute Error), MSE (Mean Squared Error), RMSE (Root Mean Squared Error), and MAPE (Mean Absolute Percentage Error). Research results revealed that the gradient boost regression model outperformed other models with and without using the dimensionality reduction technique (PCA) with the highest R2 of 0.912 and 0.872, respectively, and had the lowest MAPE of 0.872 % and 1.039 %, respectively. Moreover, prediction performance dropped slightly after using the dimensionality reduction technique almost in all regression algorithms used. The novelty in this work is summarized in predicting electrical power output in a CCPP based on a few features using simpler algorithms than reported deep learning and neural networks algorithms combined. That means a lower cost and less complicated procedure as per each, however, resulting in practically accepted results according to the evaluation metrics used.

scholarly journals Genetic Algorithm Approach to Design of Multi-Layer Perceptron for Combined Cycle Power Plant Electrical Power Output Estimation

Energies ◽  
2019 ◽  
Vol 12 (22) ◽  
pp. 4352 ◽  
Author(s):  
Ivan Lorencin ◽  
Nikola Anđelić ◽  
Vedran Mrzljak ◽  
Zlatan Car
Keyword(s):  
Genetic Algorithm ◽  
Power Plant ◽  
Power Output ◽  
Electrical Power ◽  
Combined Cycle ◽  
Training Dataset ◽  
Multi Layer Perceptron ◽  
Combined Cycle Power Plant ◽  
Data Points ◽  
Electrical Power Output

In this paper a genetic algorithm (GA) approach to design of multi-layer perceptron (MLP) for combined cycle power plant power output estimation is presented. Dataset used in this research is a part of publicly available UCI Machine Learning Repository and it consists of 9568 data points (power plant operating regimes) that is divided on training dataset that consists of 7500 data points and testing dataset containing 2068 data points. Presented research was performed with aim of increasing regression performances of MLP in comparison to ones available in the literature by utilizing heuristic algorithm. The GA described in this paper is performed by using mutation and crossover procedures. These procedures are utilized for design of 20 different chromosomes in 50 different generations. MLP configurations that are designed with GA implementation are validated by using Bland - Altman (B-A) analysis. By utilizing GA, MLP with five hidden layers of 80,25,65,75 and 80 nodes, respectively, is designed. For aforementioned MLP, k - fold cross-validation is performed in order to examine its generalization performances. The Root Mean Square Error ( R M S E ) value achieved with aforementioned MLP is 4.305 , that is significantly lower in comparison with MLP presented in available literature, but still higher than several complex algorithms such as KStar and tree based algorithms.

scholarly journals Powering Ahead

2011 ◽  
Vol 133 (05) ◽  
pp. 30-33 ◽  
Author(s):  
Lee S. Langston
Keyword(s):  
Power Plant ◽  
Gas Turbine ◽  
Gas Turbines ◽  
Nuclear Power ◽  
Electrical Power ◽  
The United States ◽  
Combined Cycle ◽  
Electrical Power System ◽  
Efficient Technology ◽  
The Military

This article explores the increasing use of natural gas in different turbine industries and in turn creating an efficient electrical system. All indications are that the aviation market will be good for gas turbine production as airlines and the military replace old equipment and expanding economies such as China and India increase their air travel. Gas turbines now account for some 22% of the electricity produced in the United States and 46% of the electricity generated in the United Kingdom. In spite of this market share, electrical power gas turbines have kept a much lower profile than competing technologies, such as coal-fired thermal plants and nuclear power. Gas turbines are also the primary device behind the modern combined power plant, about the most fuel-efficient technology we have. Mitsubishi Heavy Industries is developing a new J series gas turbine for the combined cycle power plant market that could achieve thermal efficiencies of 61%. The researchers believe that if wind turbines and gas turbines team up, they can create a cleaner, more efficient electrical power system.

Performance Analysis of Near-Field Thermophotovoltaic With a Multilayer Metallodielectric Emitter

2016 ◽  
Author(s):  
Y. Yang ◽  
J. Y. Chang ◽  
L. P. Wang
Keyword(s):  
Heat Flux ◽  
Power Output ◽  
Indium Tin Oxide ◽  
Effective Medium Theory ◽  
Near Field ◽  
Electrical Power ◽  
Electrical Contacts ◽  
Alumina Layer ◽  
Photon Transport ◽  
Electrical Power Output

The photon transport and energy conversion of a near-field thermophotovoltaic (TPV) system with a selective emitter composed of alternate tungsten and alumina layers and a photovoltaic cell sandwiched by electrical contacts are theoretically investigated in this paper. Fluctuational electrodynamics along with the dyadic Green’s function for a multilayered structure is applied to calculate the spectral heat flux, and photocurrent generation and electrical power output are solved from the photon-coupled charge transport equations. The tungsten and alumina layer thicknesses are optimized to match the spectral heat flux with the bandgap of TPV cell. The spectral heat flux is much enhanced when plain tungsten emitter is replaced with the multilayer emitter due to the mechanism of surface plasmon polariton coupling in the tungsten thin film. In addition, the invalidity of effective medium theory to predict photon transport in the near field with multilayer emitters is discussed. Effects of a gold back reflector and indium tin oxide front coating with nanometer thickness, which could practically act as the electrodes to collect the photon-generated charges on the TPV cell, are explored. Conversion efficiency of 23.7% and electrical power output of 0.31 MW/m2 are achieved at 100 nm vacuum gap when the emitter and receiver are respectively at temperatures of 2000 K and 300 K.

scholarly journals Evaluating Energy Generation Capacity of PVDF Sensors: Effects of Sensor Geometry and Loading

Materials ◽  
2021 ◽  
Vol 14 (8) ◽  
pp. 1895
Author(s):  
Mohammad Uddin ◽  
Shane Alford ◽  
Syed Mahfuzul Aziz
Keyword(s):  
Surface Area ◽  
Power Output ◽  
Energy Harvester ◽  
Mechanical Strain ◽  
Electrical Power ◽  
Human Movement ◽  
Loading Frequency ◽  
Dielectric Thickness ◽  
Generating Capacity ◽  
Electrical Power Output

This paper focuses on the energy generating capacity of polyvinylidene difluoride (PVDF) piezoelectric material through a number of prototype sensors with different geometric and loading characteristics. The effect of sensor configuration, surface area, dielectric thickness, aspect ratio, loading frequency and strain on electrical power output was investigated systematically. Results showed that parallel bimorph sensor was found to be the best energy harvester, with measured capacitance being reasonably acceptable. Power output increased with the increase of sensor’s surface area, loading frequency, and mechanical strain, but decreased with the increase of the sensor thickness. For all scenarios, sensors under flicking loading exhibited higher power output than that under bending. A widely used energy harvesting circuit had been utilized successfully to convert the AC signal to DC, but at the sacrifice of some losses in power output. This study provided a useful insight and experimental validation into the optimization process for an energy harvester based on human movement for future development.

Experimental Investigation of a Flat Plate Photovoltaic/Thermal Collector

2018 ◽  
Author(s):  
Mohamad Modrek ◽  
Ali Al-Alili
Keyword(s):  
Mass Flow Rate ◽  
Mass Flow ◽  
Flow Rate ◽  
Power Output ◽  
Electrical Power ◽  
Solar Thermal ◽  
Pv Panel ◽  
Solar Thermal Collectors ◽  
Electrical Power Output ◽  
Electrical Output

Photovoltaic thermal collectors (PVT) combines technologies of photovoltaic panels and solar thermal collectors into a hybrid system by attaching an absorber to the back surface of a PV panel. PVT collectors have gained a lot of attention recently due to the high energy output per unit area compared to a standalone system of PV panels and solar thermal collectors. In this study, performance of a liquid cooled flat PVT collector under the climatic conditions of Abu Dhabi, United Arab Emirates was experimentally investigated. The electrical performances of the PVT collector was compared to that of a standalone PV panel. Moreover, effect of sand accumulation on performance of PVT collectors was examined. Additionally, effect of mass flow rate on thermal and electrical output of PVT collector was studied. Electrical power output is slightly affected by changes in mass flow rate. However, thermal energy increased by 22% with increasing flow rate. Electrical power output of a PV panel was found to be 38% lower compared to electrical output of PVT collectors. Dust accumulation on PVT surface reduced electrical power output up to 7% compared with a reference PVT collector.

scholarly journals Design of a Hybrid Photovoltaic Thermal System in Lebanon

2018 ◽  
Vol 171 ◽  
pp. 02002
Author(s):  
Elie Karam ◽  
Patrick Moukarzel ◽  
Maya Chamoun ◽  
Charbel Habchi ◽  
Charbel Bou-Mosleh
Keyword(s):  
Power Output ◽  
Electrical Power ◽  
Hot Water ◽  
Thermal System ◽  
Conduction Model ◽  
Electrical Efficiency ◽  
Pv Module ◽  
Temperature Loss ◽  
Photovoltaic Thermal System ◽  
Electrical Power Output

Due to global warming and the high toxic gas emissions of traditional power generation methods, renewable energy has become a very active topic in many applications. This study focuses on one versatile type of solar energy: Hybrid Photovoltaic Thermal System (hybrid PV/T). Hybrid PV/T combines both PV and thermal application and by doing this the efficiency of the system will increase by taking advantage of the temperature loss from PV module. The solar radiation and heat will be harnessed to deliver electricity and hot water simultaneously. In the present study a solar system is designed to recycle the heat and improve the temperature loss from PV module in order to supply both electricity and domestic hot water. The project was tested twice in Zouk Mosbeh - Lebanon; on May 18, 2016, and June 7, 2016. The average electrical efficiency was around 11.5% with an average electrical power output of 174.22 W, while with cooling, the average electrical efficiency reaches 11% with a power output of 200 W. The temperature increases by about 7 degrees Celsius from the inlet. The 1D conduction model is also performed in order to design the hybrid PV/T system.

The Elephant in the Room–Gas Turbine Power

2010 ◽  
Vol 132 (12) ◽  
pp. 57-57
Author(s):  
Lee S. Langston
Keyword(s):  
Power Plant ◽  
Electric Power ◽  
Gas Turbine ◽  
Power Plants ◽  
Electrical Power ◽  
Electric Power Industry ◽  
Hydrocarbon Fuel ◽  
Combined Cycle ◽  
Electrical Generator ◽  
Gas Turbine Exhaust

This article presents an overview of gas turbine combined cycle (CCGT) power plants. Modern CCGT power plants are producing electric power as high as half a gigawatt with thermal efficiencies approaching the 60% mark. In a CCGT power plant, the gas turbine is the key player, driving an electrical generator. Heat from the hot gas turbine exhaust is recovered in a heat recovery steam generator, to generate steam, which drives a steam turbine to generate more electrical power. Thus, it is a combined power plant burning one unit of fuel to supply two sources of electrical power. Most of these CCGT plants burn natural gas, which has the lowest carbon content of any other hydrocarbon fuel. Their near 60% thermal efficiencies lower fuel costs by almost half compared to other gas-fired power plants. Their installed capital cost is the lowest in the electric power industry. Moreover, environmental permits, necessary for new plant construction, are much easier to obtain for CCGT power plants.

Sign in / Sign up

Export Citation Format

Share Document