A neural network-based production process modeling and variable importance analysis approach in corn to sugar factory

Abstract

Corn to sugar process has long faced the risks of high energy consumption and thin profits. However, it’s hard to upgrade or optimize the process based on mechanism unit operation models due to the high complexity of the related processes. Big data technology provides a promising solution as its ability to turn huge amounts of data into insights for operational decisions. In this paper, a neural network-based production process modeling and variable importance analysis approach is proposed for corn to sugar processes, which contains data preprocessing, dimensionality reduction, multilayer perceptron/convolutional neural network/recurrent neural network based modeling and extended weights connection method. In the established model, dextrose equivalent value is selected as the output, and 654 sites from the DCS system are selected as the inputs. LASSO analysis is first applied to reduce the data dimension to 155, then the inputs are dimensionalized to 50 by means of genetic algorithm optimization. Ultimately, variable importance analysis is carried out by the extended weight connection method, and 20 of the most important sites are selected for each neural network. The results indicate that the multilayer perceptron and recurrent neural network models have a relative error of less than 0.1%, which have a better prediction result than other models, and the 20 most important sites selected have better explicable performance. The major contributions derived from this work are of significant aid in process simulation model with high accuracy and process optimization based on the selected most important sites to maintain high quality and stable production for corn to sugar processes.

Key words： big data; corn to sugar factory; neural network; variable importance analysis

Acknowledgement

The authors are grateful for the financial supports of Special Foundation for State Major Basic Research Program of China (Grant No. 2021YFD2101000).

Electronic Supplementary Material

Supplementary material is available in the online version of this article at https://dx.doi.org/10.1007/s11705-022-2190-y and is accessible for authorized users.

References

1 Kirmse A, Kuschicke F, Hoffmann M. Industrial big data: from data to information to actions. 4th International Conference on Internet of Things. Big Data and Security, 2019,

2 Tian W, Ren Y, Dong Y, Wang S, Bu L. Fault monitoring based on mutual information feature engineering modeling in chemical process. Chinese Journal of Chemical Engineering, 2019, 27(10): 2491–2497

3 Kira K, Rendell L A. The feature selection problem: traditional methods and a new algorithm. AAAI-92 Proceedings: Tenth National Conference on Artificial Intelligence, 1992, 129–134

4 Barros R S M, Hidalgo J I G, Cabral D R L. Wilcoxon rank sum test drift detector. Neurocomputing, 2018, 275: 1954–1963

5 Malik H, Yadav A K. A novel hybrid approach based on relief algorithm and fuzzy reinforcement learning approach for predicting wind speed. Sustainable Energy Technologies and Assessments, 2021, 43: 100920

6 Wold S, Sjostrom M, Eriksson L. PLS-regression: a basic tool of chemometrics. Chemometrics and Intelligent Laboratory Systems, 2001, 58(2): 109–130

7 Li H, Xu Q, Liang Y. Random frog: an efficient reversible jump Markov Chain Monte Carlo-like approach for variable selection with applications to gene selection and disease classification. Analytica Chimica Acta, 2012, 740: 20–26

8 Cutler A, Cutler D R, Stevens J R. Random forests. Machine Learning, 2004, 45: 157–176

9 Zavaljevski N, Stevens F J, Reifman J. Support vector machines with selective kernel scaling for protein classification and identification of key amino acid positions. Bioinformatics, 2002, 18(5): 689–696

10 Li Z, Liu P, Wang W, Xu C. Using support vector machine models for crash injury severity analysis. Accident; Analysis and Prevention, 2012, 45: 478–486

11 Olden J D, Jackson D A. Illuminating the “black box”: a randomization approach for understanding variable contributions in artificial neural networks. Ecological Modelling, 2002, 154(1–2): 135–150

12 Yun Y H, Deng B C, Cao D S, Wang W T, Liang Y Z. Variable importance analysis based on rank aggregation with applications in metabolomics for biomarker discovery. Analytica Chimica Acta, 2016, 911: 27–34

13 Qin S J. Process data analytics in the era of big data. AIChE Journal, 2014, 60(9): 3092–3100

14 Dimopoulos Y, Bourret P, Lek S. Use of some sensitivity criteria for choosing networks with good generalization ability. Neural Processing Letters, 1995, 2(6): 1–4

15 Dimopoulos I, Chronopoulos J, Chronopoulou-Sereli A, Lek S. Neural network models to study relationships between lead concentration in grasses and permanent urban descriptors in Athens city (Greece). Ecological Modelling, 1999, 120(2–3): 157–165

16 Garson G D. Interpreting neural network connection weights. Artificial Intelligence Expert, 1991, 6: 47–51

17 Scardi M, Harding L W Jr. Developing an empirical model of phytoplankton primary production: a neural network case study. Ecological Modelling, 1999, 120(2–3): 213–223

18 Lek S, Belaud A, Baran P, Dimopoulos I, Delacoste M. Role of some environmental variables in trout abundance models using neural networks. Aquatic Living Resources, 1996, 9(1): 23–29

19 Lek S, Delacoste M, Baran P, Dimopoulos I, Lauga J, Aulagnier S. Application of neural networks to modelling nonlinear relationships in ecology. Ecological Modelling, 1996, 90(1): 39–52

20 Balls G R, Palmer-Brown D, Sanders G E. Investigating microclimatic influences on ozone injury in clover (Trifolium subterraneum) using artificial neural networks. New Phytologist, 1996, 132(2): 271–280

21 Grahovac J, Jokic A, Dodic J, Vucurovic D, Dodic S. Modelling and prediction of bioethanol production from intermediates and byproduct of sugar beet processing using neural networks. Renewable Energy, 2016, 85: 953–958

22 Hao W R, Lu Z Z, Wei P F, Feng J, Wang B T. A new method on ANN for variance based importance measure analysis of correlated input variables. Structural Safety, 2012, 38: 56–63

23 de Sa C R. Variance-based feature importance in neural networks. Discovery Science, 22nd International Conference, 2019, 306–315

24 Hadzima-Nyarko M, Nyarko E K, Moric D. A neural network based modelling and sensitivity analysis of damage ratio coefficient. Expert Systems with Applications, 2011, 38(10): 13405–13413

25 Cortez P, Embrechts M J. Using sensitivity analysis and visualization techniques to open black box data mining models. Information Sciences, 2013, 225: 1–17

26 Hadjisolomou E, Stefanidis K, Papatheodorou G, Papastergiadou E. Assessing the contribution of the environmental parameters to eutrophication with the use of the “PaD” and “PaD2” methods in a hypereutrophic lake. International Journal of Environmental Research and Public Health, 2016, 13(8): 764

27 Yang B, Li H. A novel convolutional neural network based approach to predictions of process dynamic time delay 286 sequences. Chemometrics and Intelligent Laboratory Systems, 2018, 174: 56–61

28 Wang Y J, Li H G. A novel intelligent modeling framework integrating the convolutional neural network with an adaptive time-series window and its application to industrial process operational optimization. Chemometrics and Intelligent Laboratory Systems, 2018, 179: 64–72

29 Wang Y, Li H. Industrial process time-series modeling based on adapted receptive field temporal convolution networks concerning multi-region operations. Computers & Chemical Engineering, 2020, 139: 106877

30 Yang W, Yang C, Hao Z Y, Xie C Q, Li M Z. Diagnosis of plant cold damage based on hyperspectral imaging and convolutional neural network. IEEE Access: Practical Innovations, Open Solutions, 2019, 7: 118239–118248

31 Liu Q, Zhang L, Tang K, Liu L, Du J, Meng Q, Gani R. Machine learning-based atom contribution method for the prediction of charge density profiles and solvent design. AIChE Journal, 2021, 67(2): e17110

32 Liu Q, Jiang Y, Zhang L, Du J. A computational toolbox for molecular property prediction based on quantum mechanics and quantitative structure-property relationship. Frontiers of Chemical Science and Engineering, 2022, 16(2): 152–167

33 Chang Z, Zhang Y, Chen W. Electricity price prediction based on hybrid model of adam optimized LSTM neural network and wavelet transform. Energy, 2019, 187: 115804

34 Maples M P, Reichart D E, Konz N C, Berger T A, Trotter A S, Martin J R, Dutton D A, Paggen M L, Joyner R E, Salemi C P. Robust Chauvenet Outlier Rejection. Astrophysical Journal. Supplement Series, 2018, 238(1): 2

35 Elko G W, Sondhi M M, West J E. Noise reduction processing arrangement for microphone arrays. Journal of the Acoustical Society of America, 1989, 88(6): 2919

36 López-Medina C, Ladehesa-Pineda L, Puche-Larrubia M Á, Escudero-Contreras A, Font-Ugalde P, Collantes-Estévez E. Which factors explain the patient global assessment in patients with ankylosing spondylitis? A hierarchical cluster analysis on REGISPONSER-AS. Seminars in Arthritis and Rheumatism, 2021, 51(4): 1–5

37 Lin J, Li S. Sparse recovery with coherent tight frames via analysis Dantzig selector and analysis LASSO. Applied and Computational Harmonic Analysis, 2014, 37(1): 126–139

38 MacQueen J. Some methods for classification and analysis of multivariate observations. In: Proceedings of the 5^th Berkeley Symposium on Mathematical Statistics and Probability. Berkeley: University of California Press, 1967, 281–297

39 Ranade N, Nagarajan S, Sarvothaman V, Ranade V. ANN based modelling of hydrodynamic cavitation processes: biomass pre-treatment and wastewater treatment. Ultrasonics Sonochemistry, 2021, 72: 105428

40 Zhang X, Liu L, Long G, Jiang J, Liu S. Episodic memory govern schoices: an RNN-based reinforcement learning model for decision-making task. Neural Networks, 2021, 134: 1–10

41 Liu S, Lee I. Sequence encoding incorporated CNN model for email document sentiment classification. Applied Soft Computing, 2021, 102: 107104