scholarly journals Optimization of a 660 MWe Supercritical Power Plant Performance—A Case of Industry 4.0 in the Data-Driven Operational Management Part 1. Thermal Efficiency

Energies ◽  
2020 ◽  
Vol 13 (21) ◽  
pp. 5592
Author(s):  
Waqar Muhammad Ashraf ◽  
Ghulam Moeen Uddin ◽  
Syed Muhammad Arafat ◽  
Sher Afghan ◽  
Ahmad Hassan Kamal ◽  
...  
Keyword(s):  
Power Plant ◽  
Thermal Efficiency ◽  
Industry 4.0 ◽  
Process Model ◽  
Least Square ◽  
Process Models ◽  
Plant Performance ◽  
Support Vector ◽  
Unit Load ◽  
Artificial Neural Network Ann

This paper presents a comprehensive step-wise methodology for implementing industry 4.0 in a functional coal power plant. The overall efficiency of a 660 MWe supercritical coal-fired plant using real operational data is considered in the study. Conventional and advanced AI-based techniques are used to present comprehensive data visualization. Monte-Carlo experimentation on artificial neural network (ANN) and least square support vector machine (LSSVM) process models and interval adjoint significance analysis (IASA) are performed to eliminate insignificant control variables. Effective and validated ANN and LSSVM process models are developed and comprehensively compared. The ANN process model proved to be significantly more effective; especially, in terms of the capacity to be deployed as a robust and reliable AI model for industrial data analysis and decision making. A detailed investigation of efficient power generation is presented under 50%, 75%, and 100% power plant unit load. Up to 7.20%, 6.85%, and 8.60% savings in heat input values are identified at 50%, 75%, and 100% unit load, respectively, without compromising the power plant’s overall thermal efficiency.

scholarly journals Optimization of a 660 MWe Supercritical Power Plant Performance—A Case of Industry 4.0 in the Data-Driven Operational Management. Part 2. Power Generation

Energies ◽  
2020 ◽  
Vol 13 (21) ◽  
pp. 5619
Author(s):  
Waqar Muhammad Ashraf ◽  
Ghulam Moeen Uddin ◽  
Ahmad Hassan Kamal ◽  
Muhammad Haider Khan ◽  
Awais Ahmad Khan ◽  
...  
Keyword(s):  
Power Plant ◽  
Process Optimization ◽  
Process Modeling ◽  
Industry 4.0 ◽  
Process Models ◽  
Plant Performance ◽  
Data Driven ◽  
Support Vector ◽  
Process Data ◽  
Generation Capacity

Modern data analytics techniques and computationally inexpensive software tools are fueling the commercial applications of data-driven decision making and process optimization strategies for complex industrial operations. In this paper, modern and reliable process modeling techniques, i.e., multiple linear regression (MLR), artificial neural network (ANN), and least square support vector machine (LSSVM), are employed and comprehensively compared as reliable and robust process models for the generator power of a 660 MWe supercritical coal combustion power plant. Based on the external validation test conducted by the unseen operation data, LSSVM has outperformed the MLR and ANN models to predict the power plant’s generator power. Later, the LSSVM model is used for the failure mode recovery and a very successful operation control excellence tool. Moreover, by adjusting the thermo-electric operating parameters, the generator power on an average is increased by 1.74%, 1.80%, and 1.0 at 50% generation capacity, 75% generation capacity, and 100% generation capacity of the power plant, respectively. The process modeling based on process data and data-driven process optimization strategy building for improved process control is an actual realization of industry 4.0 in the industrial applications.

Advanced Bottoming Cycle Optimisation for Large Alstom CCPP

2007 ◽  
Author(s):  
Michael Vollmer ◽  
Camille Pedretti ◽  
Alexander Ni ◽  
Manfred Wirsum
Keyword(s):  
Power Plant ◽  
Gas Turbines ◽  
Process Model ◽  
Combined Cycle ◽  
Plant Performance ◽  
Design Parameters ◽  
Economic Plant ◽  
Plant Design ◽  
Investment Cost ◽  
Definition Of

This paper presents the fundamentals of an evolutionary, thermo-economic plant design methodology, which enables an improved and customer-focused optimization of the bottoming cycle of a large Combined Cycle Power Plant. The new methodology focuses on the conceptual design of the CCPP applicable to the product development and the pre-acquisition phase. After the definition of the overall plant configuration such as the number of gas turbines used, the type of main cooling system and the related fix investment cost, the CCPP is optimized towards any criteria available in the process model (e.g. lowest COE, maximum NPV/IRR, highest net efficiency). In view of the fact that the optimization is performed on a global plant level with a simultaneous hot- and cold- end optimization, the results clearly show the dependency of the HRSG steam parameters and the related steam turbine configuration on the definition of the cold end (Air Cooled Condenser instead of Direct Cooling). Furthermore, competing methods for feedwater preheating (HRSG recirculation, condensate preheating or pegging steam), different HRSG heat exchanger arrangements as well as applicable portfolio components are automatically evaluated and finally selected. The developed process model is based on a fixed superstructure and copes with the full complexity of today’s bottoming cycle configurations as well with any constraints and design rules existing in practice. It includes a variety of component modules that are prescribed with their performance characteristics, design limitations and individual cost. More than 100 parameters are used to directly calculate the overall plant performance and related investment cost. Further definitions on payment schedule, construction time, operation regime and consumable cost results in a full economic life cycle calculation of the CCPP. For the overall optimization the process model is coupled to an evolutionary optimizer, whereas around 60 design parameters are used within predefined bounds. Within a single optimization run more than 100’000 bottoming cycle configurations are calculated in order to find the targeted optimum and thanks to today’s massive parallel computing resources, the solution can be found over night. Due to the direct formulation of the process model, the best cycle configuration is a result provided by the optimizer and can be based on a single-, dual or triple pressure system using non-reheat, reheat or double reheat configuration. This methodology enables to analyze also existing limitations and characteristics of the key components in the process model and assists to initiate new developments in order to constantly increase the value for power plant customers.

scholarly journals Experimental validation of an adsorbent-agnostic artificial neural network (ANN) framework for the design and optimization of cyclic adsorption processes

2021 ◽  
Author(s):  
Kasturi Nagesh Pai ◽  
Tai T.T. Nguyen ◽  
Vinay Prasad ◽  
Arvind Rajendran
Keyword(s):  
Surrogate Model ◽  
Process Model ◽  
Particle Density ◽  
Process Models ◽  
Training Data ◽  
Design And Optimization ◽  
Pressure Step ◽  
Adsorption Processes ◽  
Artificial Neural Network Ann ◽  
Cyclic Adsorption

The efficacy of an adsorbent agnostic machine-learning surrogate model for rapid design and optimization of a Skarstrom cycle vacuum swing adsorption (VSA) process is experimentally validated. The surrogate model is trained to predict the process performance using adsorbent features that include hypothetical Langmuir adsorption isotherm parameters, particle density, porosity and bed voidage, and process variables such as pressure, step duration and feed velocity. The training data was generated from a detailed process model for 20,000 unique combinations of the training variables. The model shows high accuracy of R2adj>0.99 for predicting key performance parameters such as product purity, recovery and productivity. The ability of this surrogate to predict the experimental performance for the purification of O2 from the air on two adsorbents, namely 13X and LiX zeolites, was studied. Two separate multi-objective optimization studies, to maximize purity and recovery, and to maximize productivity and purity were performed. For these optimization studies, the volumetrically measured isotherms of N2 and O2 were used as inputs to the surrogate model. Note that these isotherms were not a part of the dataset used to train the model. Nine points were chosen from the Parteo curves and the corresponding decision variables were used as set-points in a two-column lab-scale rig. The average difference between the calculated and experimentally measured purity, recovery and productivity was 3%, 5% and 9%, respectively. This study provides the necessary confidence to use surrogate-based process models for adsorbent screening and adsorption process optimization.

Effect of Fuel Gas Cleanup Option on Air-Blown IGCC Power Plant Performance

1997 ◽  
Author(s):  
W. C. Yang ◽  
R. A. Newby ◽  
R. L. Bannister
Keyword(s):  
Power Plant ◽  
Process Model ◽  
Coal Gasification ◽  
Heat Rate ◽  
Combined Cycle ◽  
Plant Performance ◽  
Fuel Gas ◽  
Gas Cleaning ◽  
Plant Sensitivity ◽  
Parametric Studies

Air-blown coal gasification for combined-cycle power generation is a technology soon to be demonstrated. A process evaluation of air-blown IGCC performed to estimate the plant heat rate, electrical output and potential emissions are described in this paper. A process model of an air-blown IGCC power system based on the Westinghouse 501F combustion turbine was developed to conduct the performance evaluation. Parametric studies were performed to develop an understanding of the power plant sensitivity to the major operating parameters and process options. Advanced hot fuel gas cleaning and conventional cold fuel gas cleaning options were both considered.

scholarly journals Simulated Annealing Based Hybrid Forecast for Improving Daily Municipal Solid Waste Generation Prediction

2014 ◽  
Vol 2014 ◽  
pp. 1-7 ◽  
Author(s):  
Jingwei Song ◽  
Jiaying He ◽  
Menghua Zhu ◽  
Debao Tan ◽  
Yu Zhang ◽  
...  
Keyword(s):  
Simulated Annealing ◽  
Forecast Model ◽  
The United States ◽  
Partial Least Square ◽  
Least Square ◽  
Support Vector ◽  
Prediction Ability ◽  
Chaotic Model ◽  
Accurate Forecast ◽  
Artificial Neural Network Ann

A simulated annealing (SA) based variable weighted forecast model is proposed to combine and weigh local chaotic model, artificial neural network (ANN), and partial least square support vector machine (PLS-SVM) to build a more accurate forecast model. The hybrid model was built and multistep ahead prediction ability was tested based on daily MSW generation data from Seattle, Washington, the United States. The hybrid forecast model was proved to produce more accurate and reliable results and to degrade less in longer predictions than three individual models. The average one-week step ahead prediction has been raised from 11.21% (chaotic model), 12.93% (ANN), and 12.94% (PLS-SVM) to 9.38%. Five-week average has been raised from 13.02% (chaotic model), 15.69% (ANN), and 15.92% (PLS-SVM) to 11.27%.

Prediction of Properties of Cu-15Ni-8Sn Alloys Based on Least Square Support Vector Machines

2013 ◽  
Vol 813 ◽  
pp. 479-483
Author(s):  
Shan Feng Fang ◽  
Ming Pu Wang
Keyword(s):  
Support Vector Machines ◽  
Predictive Accuracy ◽  
Copper Alloys ◽  
Least Square ◽  
Support Vector ◽  
Promising Alternative ◽  
Vector Machines ◽  
Artificial Neural Network Ann ◽  
Experimental Values ◽  
Leave One Out

A new model based on least square support vector machines (LSSVM) and capable of forecasting mechanical and electrical properties of Cu-15Ni-8Sn alloys has been proposed. Data mining and artificial intelligence techniques of copper alloys are used to examine the forecasting capability of the model. In order to improve predictive accuracy and generalization ability of LSSVM model, leave-one-out-cross-validation (LOOCV) technique is adopted to determine the optimal hyper-parameters of LSSVM automatically. The forecasting performance of the LSSVM model and the artificial neural network (ANN) has been compared with the experimental values. The result shows that the LSSVM model provides slightly better capability of generalized prediction compared to ANN. The present calculated results are consistent with the experimental values, which suggest that the proposed LSSVM model is feasible and efficient and is therefore considerd to be a promising alternative method to forecast the variation of the hardness and electrical conductivity with aging temperature and aging time.

A modeling study of micro-cracking processes of polyurethane coated cotton fabrics

2017 ◽  
Vol 88 (24) ◽  
pp. 2766-2781 ◽  
Author(s):  
Sinem Güneşoğlu ◽  
Mehmet Yüceer
Keyword(s):  
Industrial Applications ◽  
Least Square ◽  
Vector Model ◽  
Support Vector ◽  
Coated Fabric ◽  
Artificial Neural Network Ann ◽  
Coated Fabrics ◽  
Cracking Process ◽  
Visual Properties ◽  
Modeling Study

Polyurethane (PU) coating became popular in recent decades to achieve water resistance in clothing fabrics with enhanced visual properties. But reduced breathability of coated fabric is a setback for the clothing industry; therefore, there have been various attempts to achieve breathable water-resistant coatings. A new and facile method of enhancing breathability of PU-coated fabrics, which has been called micro-cracking, has been recently studied and highly encouraging outcomes have been obtained for the use of the process in industry. But when any process is considered to have industrial applications, it is essential to conduct not only the optimization but also modeling studies to find out whether the outputs are predictable; the process is controllable and allows us to see how the results are affected by process parameters. This work conducts a modeling study of micro-cracking processes of PU-coated samples to complete this evaluation. For this purpose, an artificial neural network (ANN) and a least square support vector model (LS-SVM) are developed for the prediction of various properties of PU-coated fabrics after micro-cracking. The results showed that the effects of micro-cracking process on various properties of coated fabric could be predicted through ANN or LS-SVM modeling; specifically, the ANN exhibited better performance in the test set of the data. Thus, it is concluded that the results and the measurements were found to be compatible for defining the process as an industrial alternative.

Defect Diagnostics of Power Plant Gas Turbine Using Hybrid SVM-ANN Method

2012 ◽  
Author(s):  
Sangmyeong Lee ◽  
Sanghun Lee ◽  
Juchang Lim ◽  
Sangbin Lee
Keyword(s):  
Power Plant ◽  
Gas Turbine ◽  
Hybrid Approach ◽  
Diagnostic System ◽  
Diagnostic Algorithm ◽  
Estimation Accuracy ◽  
Support Vector ◽  
Defect Diagnostics ◽  
Efficiency Estimation ◽  
Artificial Neural Network Ann

A hybrid method of an artificial neural network (ANN) combined with a support vector machine (SVM) has been developed for the defect diagnostic system applied to the power plant gas turbine. This method has been suggested to overcome the demerits of the general ANN with the local minima problem and low classification accuracy in case of many nonlinear data. This hybrid approach takes advantage of the reduction of learning data and converging time without any loss of estimation accuracy therefore it has been applied for the power plant monitoring system in order to detect fails and status of compressors and turbines in detail. The results have shown the suggested defect diagnostic algorithm has reliable and suitable efficiency estimation accuracy.

A Study of Power Spectral Density Models of Earthquake Ground Motion

2011 ◽  
Vol 90-93 ◽  
pp. 1503-1510
Author(s):  
Fu Jun Liu ◽  
Yu Hua Zhu ◽  
Xiao Hui Ma
Keyword(s):  
Random Process ◽  
Ground Motion ◽  
Process Model ◽  
Least Square Method ◽  
Least Square ◽  
Process Models ◽  
Earthquake Ground Motion ◽  
Power Spectral ◽  
Proposed Model ◽  
Power Spectral Densities

In this paper, a modified random process model of earthquake ground motion based on the model proposed by JinPing Ou is presented. The parameters in the model except the factor S0 are determined by using the least square method and the power spectral densities of 361 earthquake records. Then the method for determining the parameter S0 is proposed. The good performance of the proposed model in this paper in modeling the earthquake ground motion on firm ground is demonstrated by comparing it with other random process models.

Sign in / Sign up

Export Citation Format

Share Document