Soft sensor modelling of propylene conversion based on a Takagi-Sugeno fuzzy neural network optimized with independent component analysis and mutual information
Restricted accessResearch articleFirst published online February, 2019
Soft sensor modelling of propylene conversion based on a Takagi-Sugeno fuzzy neural network optimized with independent component analysis and mutual information
Propylene conversion is important to economic efficiency in the production of acrylic acid. Hence, the online measurement of propylene conversion is becoming more and more important. The current measurement method is mainly uses an offline meteorological chromatography analyser, which is difficult to measure accurately in real time. A soft sensor modelling method of propylene conversion based on Takagi-Sugeno (T-S) fuzzy neural network optimized by independent component analysis and mutual information is proposed in this paper. Firstly, fast independent component analysis-based denoising strategy is developed to remove the noise in the measurement of variables influenced by propylene conversion. Then, a mutual information-based variable selection method is proposed to select the key variables from multitudinous variables to reduce the influence of weak correlation. Finally, a T-S fuzzy neural network algorithm is employed to forecast the propylene conversion in the process of propylene oxidation. Simulation results show that the proposed soft sensor modelling method has better prediction accuracy and generalization ability. The method of this paper is obvious and effective.
AmariSCichockiAYangHH (1996) A new learning algorithm for blind signal separation. Advances in Neural Information Processing Systems, 8: 757–763.
2.
AminianAJahangiriM (2014) Predicting the velocity distribution of rushton turbine impeller in mixing of polymeric liquid using fuzzy neural network models. Korean Journal of Chemical Engineering31(5): 772–779.
3.
BispoVDSScheidCMCalcadaLA (2017) Development of an ANN-based soft-sensor to estimate the apparent viscosity of water-based drilling fluids. Journal of Petroleum Science and Engineering150: 69–73.
4.
CamposPJunMPuranmalkaR (2014) Production of acrylic acid from ethylene. Senior Design Reports (CBE) 61.
5.
ChengJParkJHZhangLet al. (2016) An asynchronous operation approach to event-triggered control for fuzzy markovian jump systems with general switching policies. IEEE Transactions on Fuzzy Systems26: 2–14.
6.
ChengJJuHPKarimiHRet al. (2017) Static output feedback control of nonhomogeneous Markovian jump systems with asynchronous time delays. Information Sciences399: 219–238.
7.
ChengJParkJHKarimiHRet al. (2017) A flexible terminal approach to sampled-data exponentially synchronization of Markovian neural networks with time-varying delayed signals. IEEE Transactions on Cybernetics:1–13.
8.
ChengZLiuXG (2015) Optimal online soft sensor for product quality monitoring in propylene polymerization process. Neurocomputing149: 1216–1224.
9.
ChoiHDAhnCKShiCKet al. (2015) L2-L∞ filtering for Takagi–Sugeno fuzzy neural networks based on Wirtinger-type inequalities. Neurocomputing153: 117–125.
10.
EseyeATZhangJHZhengDHet al. (2017) A double-stage hierarchical ANFIS model for short-term wind power prediction. 2017 the 2nd IEEE international conference on big data analysis, Beijing, China, 10–12 March 2017, pp.547–551.
11.
FangWGeQJYuJFet al. (2011) Catalytic selective oxidation of propane to acrylic acid in a fixed-bed reactor with an O2. Industrial & Engineering Chemical Research50(4): 1962–1967.
12.
HaoMSunZQFujiiM (2007) Image based visual servoing using Takagi–Sugeno fuzzy neural network controller. 22nd IEEE international symposium on intelligent control, Singapore, 1–3 October 2007, pp.53–58.
13.
HeHFGaoXWQiWH (2017) Sampled-data control of asynchronously switched non-linear systems via T-S fuzzy model approach. IET Control Theory & Applications11(16): 2817–2823.
14.
HyvärinenA (1997) A family of fixed-point algorithms for independent component analysis. IEEE International Conference on Acoustics5: 3917–3920.
15.
HyvärinenAOjaE (1997) A fast fixed-point algorithms for independent component analysis. Neural Computation9(7): 1483–1492.
16.
HyvärinenA (1997) Gaussian moments for noisy independent component analysis. IEEE Signal Processing Letters6(6): 145–147.
17.
HyvärinenA (1999) Fast ICA for noisy data using Gaussian moments. Proceedings of the International Symposium on Circuits & Systems: V57–V61.
18.
JekewitzTBlickhanNEndresSet al. (2012) The influence of water on the selective oxidation of acrolein to acrylic acid on Mo/V/W-mixed oxides. Catalysis Communications20: 22–28.
19.
JumariNFYusofKM (2017) Comparison of melt flow index of propylene polymerization in loop reactors using first principle and artificial neural network models. Chemical Engineering Transactions56: 163–168.
20.
JumariNFYusofKM (2016) Comparison of product quality estimation of propylene polymerization in loop reactors using artificial neural network models. Jurnal Teknologi78: 95–100.
21.
KumSSParkYSMoonSH (2011) Improved performance of Mo-V-Te-Nb-Ox catalysts prepared from a solution containing drying control chemical additives in propane oxidation to acrylic acid. Korean Journal of Chemical Engineering28(6): 1364–1371.
22.
KuzilekJKremenVSoucekFet al. (2014) Independent component analysis and decision trees for EGG holter recording de-noising. PloS One9(6): 1–9.
23.
KünkelABeckerJBörgenLet al. (2016) Polymers biodegradableUllmanns Encyclopedia of Industrial Chemistry: 1–29.
24.
LiKHanY (2016) Modelling for motor load torque with dynamic load changes of beam pumping units based on a serial hybrid model. Transaction of the Institute of Measurement and Control40(3): 1–15.
25.
LongXXLiHDFanWet al. (2013) A model population analysis method for variable selection based on mutual information. Chemometrics and Intelligent Laboratory Systems121: 75–81.
26.
OgawaYYadaSTakasakiKet al. (2008) Process for producing acrylic acid. United States Patent, US20080128263A1.
27.
RasteiroLFVieiraLHPossatoLGet al. (2017) Pulcinelli hydrothermal synthesis of Mo-V mixed oxides possessing several crystalline phases and their performance in catalytic oxydehydration of glycerol to acrylic acid. Catalysis Today296: 10–18.
28.
RehmanAKhanFKhanB (2016) Analysis of adaptive filter and ICA for noise cancellation from a video frame. IEEE international conference on intelligent system engineering, Islamabad, Pakistan, 15–18 January 2016, pp.250–255.
29.
SardouieSHAlberaLBagherMet al. (2015) An efficient Jacobi-like deflationary ICA algorithm application to EGG denoising. IEEE Signal Processing Letters22(8): 1198–1202.
30.
SliškovićDGrbićRHocenskiZ (2011) Methods for plant data-based process modeling in soft-sensor development. Automatika52(4): 306–318.
31.
SoodS (1995) One step oxidation of propylene to acrylic acid. master’s thesis, University of Alberta.
32.
StojanovićMBBožićMMStojanovićMMet al. (2014) A methodology for training set instance selection using mutual information in time series prediction. Neurocomputing141: 236–245.
33.
SunYZhangLBMaM (2012) Soft sensor modeling based on fuzzy system optimization. Fuzzy Engineering and Operations Research147: 109–114.
34.
TanimotoMOnoderaH (2013) Process for producing acrolein and acrylic acid. United States Patent, US8404889B2.
35.
TakagiTSugenoM (1985) Fuzzy identification of systems and its application to modeling and control. IEEE Transactions on System, Man and Cybernetics15(1): 116–132.
36.
TianZDLiSJWangYH (2016) A multi-model fusion soft sensor modelling method and its application in rotary kiln calcination zone temperature prediction. Transaction of the Institute of Measurement and Control38(1): 110–124.
37.
WangBChengJAl-BarakatiAet al. (2017) A mismatched membership function approach to sampled-data stabilization for T-S fuzzy systems with time-varying delayed signals. Signal Processing140: 161–170.
38.
WangLJBasinMLiHYet al. (2017) Observer-based composite adaptive fuzzy control for nonstrict-feedback systems with actuator failures. IEEE Transactions on Fuzzy Systems DOI: 10.1109/TFUZZ.2017.2774185.
ZhangJHZhouSQRenMFet al. (2016) Adaptive neural network cascade control system with entropy-based design. The Institution of Engineering and Technology10(10): 1151–1160.
41.
ZhangJHChuCCMunozJet al. (2009) Minimum entropy based run-to-run control semiconductor processes with uncertain metrology delay. Journal of Process Control19: 1688–1697.
42.
ZhangJHLinMMChenJHet al. (2017) PLS-based multi-loop robust H2 control for improvement of operating efficiency of waste heat energy conversion systems with organic Rankine cycle. Energy123: 460–472.
43.
ZhangJHKuaiYMRenMFet al. (2016) Controller design for nonlinear and non-Gaussian multivariable systems based on survival information potential criterion. Journal of the Franklin Institute353: 3786–3798.
44.
ZhouQLiHYWangLJet al. (2017) Prescribed performance observer-based adaptive fuzzy control for nonstrict-feedback stochastic nonlinear systems. IEEE Transactions on Systems, Man, and Cybernetics: Systems DOI: 10.1109/TSMC.2017.2738155.
