Artificial Neural Networks for Renewable Energy Systems and Real-World Applications presents current trends for the solution of complex engineering problems in the application, modeling, analysis, and optimization of different energy systems and manufacturing processes. With growing research catering to the applications of neural networks in specific industrial applications, this reference provides a single resource catering to a broader perspective of ANN in renewable energy systems and manufacturing processes.
ANN-based methods have attracted the attention of scientists and researchers in different engineering and industrial disciplines, making this book a useful reference for all researchers and engineers interested in artificial networks, renewable energy systems, and manufacturing process analysis.
Author(s): Ammar Hamed Elsheikh, Mohamed Elasyed Abd Elaziz
Publisher: Academic Press
Year: 2022
Language: English
Pages: 288
City: London
Front Cover
Artificial Neural Networks for Renewable Energy Systems and Real-world Applications
Copyright Page
Contents
List of contributors
About the editors
1. Basics of artificial neural networks
1.1 Artificial neural networks
1.2 Types of neural networks
1.2.1 Multilayer perceptron neural network
1.2.2 Wavelet neural networks
1.2.3 Radial basis function
1.2.4 Elman neural network
1.2.5 Statistical performance evaluation criteria
1.3 Conclusion
References
2. Artificial neural network applied to the renewable energy system performance
Nomenclature
2.1 Introduction
2.2 Description of experimental equipment
2.3 Development of the neural network model
2.4 Neural network model
2.5 Conclusions
References
3. Applications of artificial neural networks in concentrating solar power systems
3.1 Introduction
3.2 Concentrating solar collectors
3.2.1 Parabolic trough collector
3.2.2 Solar dish collector
3.2.3 Linear Fresnel reflector
3.2.4 Central tower receiver
3.3 Artificial neural networks
3.3.1 Conceptual structure of artificial neural networks
3.3.2 Performance evaluation criteria of the artificial neural network model
3.4 Artificial neural network applications in concentrating solar power systems
3.5 Prospective and challenges
3.6 Conclusions and future recommendations
References
4. Neural simulation of a solar thermal system in low temperature
4.1 Introduction
4.2 Materials and methods
4.2.1 Meteorological data
4.2.2 Solar thermal system
4.2.3 Artificial neural networks of the components of the solar thermal system
4.2.4 Neural simulation of the solar thermal system
4.3 Results
4.3.1 Neural simulation during a day
4.3.1.1 Neural simulation during the day 10/10/2011
4.3.1.2 Neural simulation during the day 11/28/2011
4.3.2 Neural simulation during 2012
4.3.3 Neural simulation for 10 years
4.3.4 f-Chart method
4.3.5 Neural simulation versus f-chart method
4.4 Discussion
4.5 Conclusions
Acknowledgments
References
5. Solar energy modelling and forecasting using artificial neural networks: a review, a case study, and applications
5.1 Introduction
5.2 Solar radiation modeling
5.2.1 Solar constant and extraterrestrial radiation
5.2.2 Instantaneous and hourly solar radiation models
5.2.3 Modeling of daily global solar radiation (DGSR) and monthly average global solar radiation (MAGSR) based on ANN techn...
5.3 Used data and statistical analysis
5.3.1 Local weather information
5.3.2 Statistical analysis
5.4 Results and discussions
5.4.1 Best combinations of inputs in modeling and forecasting of DGSR
5.4.2 Best combinations of inputs in modeling and forecasting of MAGSR
5.5 Solar energy conversion systems: an overview
5.6 Conclusions
Appendix
References
6. Digital twin predictive maintenance strategy based on machine learning improving facility management in built environment
6.1 Introduction
6.2 Case study
6.2.1 Maintenance system
6.3 Proposed predictive maintenance strategy
6.4 Results and discussions
6.4.1 Digital twin for building management systems
6.5 Conclusions
References
7. Artificial neural network and desalination systems
7.1 Introduction
7.2 Methods of desalination
7.2.1 Multistage flash distillation
7.2.2 Multiple-effect distillation
7.2.3 Vapor compression distillation
7.2.4 Reverse osmosis
7.2.5 Freezing
7.2.6 Solar distillation
7.2.7 Potabilization
7.3 Economics related to desalination
7.4 Future expectance
7.5 Solar still
7.6 Types of solar still
7.6.1 Single-effect solar still
7.6.1.1 Active still
7.6.1.2 Passive still
7.6.2 Multieffect solar still
7.6.2.1 Active still
7.6.2.2 Passive still
7.7 Artificial neural network as a prediction method for the performance of desalination systems
7.7.1 Network architecture
7.7.2 Application of artificial neural networks in desalination systems
7.8 Conclusions
References
8. Artificial neural networks for engineering applications: a review
8.1 Introduction
8.2 Application of artificial neural networks in engineering fields
8.2.1 Chemical engineering
8.2.2 Civil engineering
8.2.3 Computer engineering
8.2.4 Power and energy engineering
8.2.5 Construction engineering
8.2.6 Mechanical engineering
8.2.7 Geotechnical engineering
8.3 Conclusion
Conflicts of interest
References
9. Incremental deep learning model for plant leaf diseases detection
9.1 Introduction
9.2 Related works
9.3 Proposed approach
9.3.1 The deep learning model
9.3.2 DataSelector and Memory
9.3.2.1 Feature-extractor
9.3.2.2 Principal component analysis
9.3.2.3 Clustering
9.3.2.4 K-neighbors
9.3.2.5 Selected data
9.3.2.6 Memory
9.4 Experimental results
9.4.1 Plant diseases dataset
9.4.2 The model’s architecture
9.4.3 Hyperparameters and evaluation
9.4.4 Influence of memory size and batches
9.4.5 Comparison with iCaRL
9.5 Conclusion
References
10. Incremental learning of convolutional neural networks in bioinformatics
10.1 Introduction
10.1.1 Replay-based methods
10.1.2 Regularization-based methods
10.1.3 Parameter isolation-based methods
10.2 Incremental learning of convolutional neural networks
10.2.1 iCaRL: incremental classifier and representation learning
10.2.2 LwF: learning without forgetting
10.2.3 Tree-CNN: tree convolutional neural networks
10.3 Incremental learning of convolutional neural networks in bioinformatics
10.3.1 SupportNet: a novel incremental learning framework through deep learning and support data
10.3.2 Continual class incremental learning for computerized tomography (CT) thoracic segmentation
10.4 Discussion
10.5 Conclusion
References
11. Hybrid Arabic classification techniques based on naïve Bayes algorithm for multidisciplinary applications
11.1 Introduction
11.2 Related works
11.2.1 Data mining
11.2.2 Text classification
11.2.2.1 Information retrieval using machine learning
11.2.2.2 Machine learning for text classification
11.2.3 Previous studies
11.3 The proposed method
11.3.1 Collecting information
11.3.2 Obtaining datasets
11.3.2.1 Open Source Arabic Corpus
11.3.2.2 BBC Arabic News
11.3.2.3 CNN Arabic News
11.3.3 Preprocessing
11.3.3.1 Tokenization
11.3.3.2 P stemmer
11.3.3.3 Term frequency—inverse document frequency
11.3.4 The classification process
11.3.4.1 WEKA data mining tool
11.3.4.2 Classifying algorithms
11.3.4.2.1 Naïve Bayes algorithm
11.3.4.2.2 New NBJ48
11.3.4.2.3 Support vector machine
11.3.4.2.4 Artificial neural networks
11.3.4.2.5 J48
11.3.5 Evaluation
11.4 Results and discussion
11.4.1 Results
11.5 Conclusion and future work
References
Index
Back Cover
