[1] Ma Ning, Dong Ze,. A novel heterogeneous ensemble of extreme learning machinesand its soft sensing application [J]. Journal of Southeast University (English Edition), 2020, 36 (1): 41-49. [doi:10.3969/j.issn.1003-7985.2020.01.006]

Copy

A novel heterogeneous ensemble of extreme learning machinesand its soft sensing application()

Share：

Journal of Southeast University (English Edition)[ISSN:1003-7985/CN:32-1325/N]

Volumn:

36

Issue:

2020 1

Page:

41-49

Research Field:

Energy and Power Engineering

Publishing date:

2020-03-20

Info

Title:

A novel heterogeneous ensemble of extreme learning machinesand its soft sensing application

Author(s):

Ma Ning;  Dong Ze

Hebei Technology Innovation Center of Simulation & Optimized Control for Power Generation, North China Electric Power University, Baoding 071003, China
School of Control and Computer Engineering, North China Electric Power University, Beijing 102206, China

Keywords:

soft sensor;  extreme learning machine;  least squares;  ensemble

PACS:

TK22

DOI:

10.3969/j.issn.1003-7985.2020.01.006

Abstract:

To obtain an accurate and robust soft sensor model in dealing with the increasingly complex industrial modeling data, an effective heterogeneous ensemble of extreme learning machines(HEELM)is proposed. Specifically, the kernel extreme learning machine(KELM)and four common extreme learning machine(ELM)models that have different internal activations are contained in the HEELM for enriching the diversity of sub-models. The number of hidden layer nodes of the extreme learning machine is determined by the trial and error method, and the optimal parameters of the kernel extreme learning machine model are determined by cross validation. Moreover, to obtain the best output of the ensemble model, least squares regression is applied to aggregate the outputs of all individual models. Two complex data sets of practical industrial processes are used to test the HEELM performance. The simulation results show that the HEELM has a high prediction accuracy. Compared with the individual ELM models, bagging ELM ensemble model, BP and SVM models, the prediction accuracy of the HEELM model is improved by 4.5% to 8.7%, and the HEELM model can obtain better generalization capability.

References:

[1] Wang T, Gao H J, Qiu J B. A combined adaptive neural network and nonlinear model predictive control for multirate networked industrial process control[J]. IEEE Transactions on Neural Networks and Learning Systems, 2016, 27(2): 416-425. DOI:10.1109/tnnls.2015.2411671.
[2] Yuan X F, Ge Z Q, Song Z H. Soft sensor model development in multiphase/multimode processes based on Gaussian mixture regression[J]. Chemometrics and Intelligent Laboratory Systems, 2014, 138: 97-109. DOI:10.1016/j.chemolab.2014.07.013.
[3] Zheng J H, Song Z H. Semisupervised learning for probabilistic partial least squares regression model and soft sensor application[J]. Journal of Process Control, 2018, 64: 123-131. DOI:10.1016/j.jprocont.2018.01.008.
[4] Popli K, Afacan A, Liu Q, et al. Development of online soft sensors and dynamic fundamental model-based process monitoring for complex sulfide ore flotation[J]. Minerals Engineering, 2018, 124: 10-27. DOI:10.1016/j.mineng.2018.04.006.
[5] Sun Y M, Wang Y L, Liu X G, et al. A novel Bayesian inference soft sensor for real-time statistic learning modeling for industrial polypropylene melt index prediction[J]. Journal of Applied Polymer Science, 2017, 134(40): 45384. DOI:10.1002/app.45384.
[6] Wang F F, Li P F, Mi J C, et al. A refined global reaction mechanism for modeling coal combustion under moderate or intense low-oxygen dilution condition[J]. Energy, 2018, 157: 764-777. DOI:10.1016/j.energy.2018.05.194.
[7] Bala Subramaniyan A, Pan R, Kuitche J, et al. Quantification of environmental effects on PV module degradation: A physics-based data-driven modeling method[J]. IEEE Journal of Photovoltaics, 2018, 8(5): 1289-1296. DOI:10.1109/jphotov.2018.2850527.
[8] Wang X X, Hu H L, Jia H Q, et al. SVM-based multisensor data fusion for phase concentration measurement in biomass-coal co-combustion[J]. Review of Scientific Instruments, 2018, 89(5): 055106. DOI:10.1063/1.5007100.
[9] Ge Z Q. Active probabilistic sample selection for intelligent soft sensing of industrial processes[J]. Chemometrics and Intelligent Laboratory Systems, 2016, 151: 181-189. DOI:10.1016/j.chemolab.2016.01.003.
[10] Li G Q, Chen B, Chan K C C, et al. Modeling thermal efficiency of a 300 MW coal-fired boiler by online least square fast learning network[J]. Journal of Chemical Engineering of Japan, 2018, 51(1): 100-106. DOI:10.1252/jcej.17we114.
[11] Mohanraj M, Jayaraj S, Muraleedharan C. Applications of artificial neural networks for refrigeration, air-conditioning and heat pump systems: A review[J]. Renewable and Sustainable Energy Reviews, 2012, 16(2): 1340-1358. DOI:10.1016/j.rser.2011.10.015.
[12] Naveen Kumar V, Lakshmi Narayana K V. Development of thermistor signal conditioning circuit using artificial neural networks[J]. IET Science, Measurement & Technology, 2015, 9(8): 955-961. DOI:10.1049/iet-smt.2015.0008.
[13] Hansen L K, Salamon P. Neural network ensembles[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1990, 12(10): 993-1001. DOI:10.1109/34.58871.
[14] Pham B T, Shirzadi A, Tien Bui D, et al. A hybrid machine learning ensemble approach based on a Radial Basis Function neural network and Rotation Forest for landslide susceptibility modeling: A case study in the Himalayan area, India[J]. International Journal of Sediment Research, 2018, 33(2): 157-170. DOI:10.1016/j.ijsrc.2017.09.008.
[15] Samiee K, Iosifidis A, Gabbouj M. On the comparison of random and Hebbian weights for the training of single-hidden layer feedforward neural networks[J]. Expert Systems with Applications, 2017, 83: 177-186. DOI:10.1016/j.eswa.2017.04.025.
[16] Li G Q, Niu P F, Duan X L, et al. Fast learning network: a novel artificial neural network with a fast learning speed[J]. Neural Computing and Applications, 2014, 24(7/8): 1683-1695. DOI:10.1007/s00521-013-1398-7.
[17] Huang G B, Zhu Q Y, Siew C K. Extreme learning machine: Theory and applications[J]. Neurocomputing, 2006, 70(1/2/3): 489-501. DOI:10.1016/j.neucom.2005.12.126.
[18] Huang G B, Wang D H, Lan Y. Extreme learning machines: A survey[J]. International Journal of Machine Learning and Cybernetics, 2011, 2(2): 107-122. DOI:10.1007/s13042-011-0019-y.
[19] Fortuna L, Graziani S, Xibilia M G. Soft sensors for product quality monitoring in debutanizer distillation columns[J]. Control Engineering Practice, 2005, 13(4): 499-508. DOI:10.1016/j.conengprac.2004.04.013.
[20] Shao W M. Research on adaptive soft sensing modeling method based on local learning [D]. Qingdao: China University of Petroleum, 2016.(in Chinese)
[21] Wu X, Shen J, Sun S Z, et al. Data-driven disturbance rejection predictive control for SCR denitrification system[J]. Industrial & Engineering Chemistry Research, 2016, 55(20): 5923-5930. DOI:10.1021/acs.iecr.5b03468.

Memo

Memo:

Biographies: Ma Ning(1992—), male, Ph.D. candidate; Dong Ze(corresponding author), male, doctor, professor, dongzencepuncepu@163.com.
Foundation items: The National Natural Science Foundation of China(No.71471060), the Natural Science Foundation of Hebei Province(No.E2018502111), Fundamental Research Funds for the Central Universities(No.2019QN134).
Citation: Ma Ning, Dong Ze.A novel heterogeneous ensemble of extreme learning machines and its soft sensing application[J].Journal of Southeast University(English Edition), 2020, 36(1):41-49.DOI:10.3969/j.issn.1003-7985.2020.01.006.

Common functions