SavedAdd your journal

Journals / Atmospheric Pollution Research / 2020 / Cilt: 11 - Sayı: 7

Multi-objective prediction of coal-fired boiler with a deep hybrid neural networks

Xiaobin HU
Peifeng NIU
Jianmei WANG
Xinxin ZHANG
Pages
1084–1090
DOI
—
🏛️Bibliographic metadata and full text access for this article are provided via DergiPark.
DergiPark Record ↗
✨

AI Summary & Key Takeaways

AI Insight
⚡ TL;DR(Too Long; Didn't Read)

The experimental results show that the performance of the hybridmodel is superior to that of the classical model; we diagram the detailed structure of the model and provide thecorresponding parameter settings in this paper.

📌 3 Key Takeaways

🎯
Objective & Hypothesis:Our works frequently examine the emission of pollutants and the prediction of the thermal efficiency of boilersfrom power plants.
📊
Key Findings & Data:In recent years, deep neural networks have gradually demonstrated their powerful capabilities.
💡
Conclusion & Impact:The experimental results show that the performance of the hybridmodel is superior to that of the classical model; we diagram the detailed structure of the model and provide thecorresponding parameter settings in this paper.
🔬Design:Modeling & Simulation
📍Scope:Comprehensive Sample
⚙️Variables:Domain Parameters

Özet

Our works frequently examine the emission of pollutants and the prediction of the thermal efficiency of boilersfrom power plants. Power plant systems are strongly coupled. Thus, multi-objective modelling and prediction isalways a difficult problem. Artificial neural network (ANN) modelling is one of the methods used to meet thischallenge. With the increasing requirements of environmental protection, the classical shallow neural networkcan no longer meet the needs of high precision. In recent years, deep neural networks have gradually demonstrated their powerful capabilities. However, can deep neural networks be used to improve model predictionperformance? After many experiments, we successfully construct a sophisticated and stable deep hybrid neuralnetwork model to achieve this requirement. The experimental results show that the performance of the hybridmodel is superior to that of the classical model; we diagram the detailed structure of the model and provide thecorresponding parameter settings in this paper.

🔖

Cite This Article

HU, X., NIU, P., WANG, J., ZHANG, X. (2020). Multi-objective prediction of coal-fired boiler with a deep hybrid neural networks. Atmospheric Pollution Research, Cilt: 11 - Sayı: 7, 1084–1090. https://ajindex.com/articles/351253

References (7)

  1. Acharya, U.R., Oh, S.L., Hagiwara, Y., Tan, J.H., Adeli, H., 2018. Deep convolutional neural network for the automated detection and diagnosis of seizure using eeg signals. Comput. Biol. Med. 100, 270–278.
  2. Ansari, H.R., Zarei, M.J., Sabbaghi, S., Keshavarz, P., 2018. A new comprehensive model for relative viscosity of various nanofluids using feed-forward back-propagation MLP neural networks. Int. Commun. Heat Mass Tran. 91, 158–164.
  3. Banerjee, I., Ling, Y., Chen, M.C., Hasan, S.A., Langlotz, C.P., Moradzadeh, N., Chapman, B., Amrhein, T., Mong, D., Rubin, D.L., et al., 2019. Comparative effectiveness of convolutional neural network (CNN) and recurrent neural network (RNN) architectures for radiology text report classification. Artif. Intell. Med. 97, 79–88.
  4. Bengio, Y.Delalleau, O. On the expressive power of deep architectures. arXiv e-prints (2011) 18–36arXiv:1605. https://link.springer.com/chapter/10.1007%2F978-3-642-24477-3_1 2688. Bengio, Y., LeCun, Y., et al., 2007. Scaling learning algorithms towards AI. Large-scale kernel machines 34 (5), 1–41. https://doi.org/10.1038/nature14539.
  5. Cybenko, G., 1989. Approximation by superpositions of a sigmoidal function. Mathematics of control, signals and systems 2 (4), 303–314. https://doi.org/10.1007/bf02551274.
  6. Eldan, R.Shamir, O. The power of depth for feedforward neural networks. arXiv e-prints 49 (2016) 907–940. arXiv:1512.03965. http://proceedings.mlr.press/v49/eldan16.pdf.
  7. Fukushima, K., 1980. Neocognitron: aself-organizing neural network model for a mechanism of pattern recognition unaffected by shift in position. Biol. Cybern. 36 (4), 193–202. https:// doi.org/10.1007/BF00344251. Glorot, X.Bengio, Y. Understanding the difficulty of training deep feedforward neural networks. arXiv e-prints (2010) 249–256arXiv:1104.3250. http://proceedings.mlr.press/v9/ glorot10a/glorot10a.pdf?hc_location=ufi. A. Graves, Generating Sequences with Recurrent Neural Networks, arXiv preprint arXiv:1308. 0850doi:10.1109/icassp.2013.6638947. A. Graves, N. Jaitly, Towards End-To-End Speech Recognition with Recurrent Neural Networks, arXiv e-prints (2014) 1764–1772arXiv:1303.5778, doi:10.1109/icassp.2017.7953077. Graves, A., Schmidhuber, J., 2011. Offline Handwriting Recognition with Multidimensional Recurrent Neural Networks. https://doi.org/10.1007/978-1-4471-4072-6_12. arXiv eprints (2009) 545–552arXiv:0705. Hao, Z., Kefa, C., Jianbo, M., 2001. Combining neural network and genetic algorithms to optimize low NOx pulverized coal c