Prediction of generated power from steam turbine waste heat recovery mechanism system on naturally aspirated spark ignition engine using artificial neural network

Herawan, Safarudin Gazali; Talib, Kamarulhelmy; Putra, Azma; Ismail, Ahmad Faris; Shamsudin, Shamsul Anuar; Musthafah, M. T.

doi:10.1007/s00500-017-2873-3

Cited by 6 publications

(2 citation statements)

References 42 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The DC machine with either current control or torque compensation loop has been considered for representing the real wind turbine characteristics using Matlab TM software [32,33]. The verification of the emulator and algorithm has been demonstrated through several tests at step changes in wind speed in [34][35][36].…”

Section: Introductionmentioning

confidence: 99%

Design of Optimal Real Time Emulators for Steam and Wind Turbines for Avoiding Risky Severe Conditions

Zoghby

Ramadan

Alhelou

2022

Preprint

View full text Add to dashboard Cite

Modern energy infrastructures may face critical impacts on distributed generation and microgrids in presence of renewable and conventional energy sources. Fast restorations for these networks through proposing convenient proactive protection systems become mandatory for securing energy particularly after severe faults. This paper deals with presenting a descriptive modelling and comprehensive analysis of both steam and wind turbines using optimal real time emulators with unique testbench. Based on the dynamics of each turbine, both emulators are performed using 4kW, 180V, 1500r.p.m separately exited DC motor coupled to 2kW, 380V, 50Hz, 1500r.p.m three-phase synchronous generator. For real-time interface implementation, the mathematical models of steam and wind turbines are realized using LabVIEWTM software. The characterization and verification of both emulated steam and wind turbines are examined at different normal operating conditions in terms of steam valve position and wind speed, respectively. To regulate the current for both systems despite their diverse dynamics, a simple industrial proportional-integral (PI) controller is considered. Unlike other artificial intelligence-based controllers, the offline-controller gains are scheduled using genetic algorithm (GA) via MatlabTM software to ensure the due fast response to cope with unexpected faults. The experimental validity of both emulators is tested at the most severe abnormal operating conditions. The three-phase short circuit is considered at the generator terminals with different fault periods until reaching out-of-step conditions. From numerical analysis and experimental results, the characterization of both emulated steam and wind turbines explicitly mimics their real large-scale turbines in normal conditions. The emulators’ fast responses using the proposed GA-PI control approach are verified. Besides, the experimental dynamic behavior convergence and interoperability between the emulated and real systems for both steam and wind turbines are validated under severe conditions. The practical results confirm the fast-nature performance of the GA in avoid risky instability conditions.

show abstract

Section: Introductionmentioning

confidence: 99%

Design of Optimal Real Time Emulators for Steam and Wind Turbines for Avoiding Risky Severe Conditions

Zoghby

Ramadan

Alhelou

2022

Preprint

View full text Add to dashboard Cite

show abstract

“…On the other hand, artificial neural networks (ANNs) are widely used in the modeling of nonlinear systems due to their powerful nonlinear mapping ability and self-learning ability [19]. Ordieres et al [27] used multilayer perceptron and radial basis function (RBF) neural network to predict PM 2.5 concentration and found that the prediction results of RBF neural network are more accurate.…”

Section: Introductionmentioning

confidence: 99%

Prediction of $${\mathrm{PM}}_{2.5}$$ concentration based on multi-source data and self-organizing fuzzy neural network

Qiao

2020

SN Appl. Sci.

View full text Add to dashboard Cite

The fine particulate matter (PM 2.5) problem has become one of the biggest topics of concern in many cities, such as Beijing in China. This study attempts to employ a self-organizing fuzzy neural network (SOFNN) to predict the hourly concentration of PM 2.5 using multi-source data. The multi-source data including meteorological data, pollutant concentration data and image data are first obtained through different methods. Then, a novel SOFNN, which is optimized by an improved gradient descent algorithm, is proposed based on the mutual information (MI) and sensitivity analysis (SA). More importantly, MI and SA are introduced to effectively adjust the structure of fuzzy neural network without changing the performance of the original network. Finally, the MI-and SA-based SOFNN is deployed to infer PM 2.5 concentration at the study area. The experimental results show that our proposed model can achieve a more compact network structure, higher prediction performance and lower computation time as compared with state-of-the-art or popular methods.

show abstract

A prediction model of artificial neural networks in development of thermoelectric materials with innovative approaches

Kokyay

Kılınç

Uysal

et al. 2020

Engineering Science and Technology, an International Journal

View full text Add to dashboard Cite

Prediction of generated power from steam turbine waste heat recovery mechanism system on naturally aspirated spark ignition engine using artificial neural network

Cited by 6 publications

References 42 publications

Design of Optimal Real Time Emulators for Steam and Wind Turbines for Avoiding Risky Severe Conditions

Design of Optimal Real Time Emulators for Steam and Wind Turbines for Avoiding Risky Severe Conditions

Prediction of $${\mathrm{PM}}_{2.5}$$ concentration based on multi-source data and self-organizing fuzzy neural network

A prediction model of artificial neural networks in development of thermoelectric materials with innovative approaches

Contact Info

Product

Resources

About