Skip to main content

Advertisement

SpringerLink
Log in

A Variable Speed Control Strategy for Impurity Removal Fan of Sugarcane Combine Harvester based on GA-SVR Model

  • Research Article
  • Published:
Sugar Tech Aims and scope Submit manuscript

Abstract

The sugarcane harvest quality of the sugarcane combine harvester directly determines its popularity and application. In this paper, a genetic algorithm-support vector machine for regression (GA-SVR) model was proposed that used the loading pressure signal and speed signal acquired from a sugarcane combine harvester’s cutting mechanism, walking mechanism, chopper mechanism, and fan mechanism as input variables, and the impurity rate and loss rate as output variables. Then, a variable speed control strategy to match the fan speed and walking speed based on the model was established. The results of the GA-SVR model showed that the predicted value of the sugarcane harvest quality’s mean square error and the determination coefficient (R2) were 0.0144 and 0.9661, respectively. The prediction accuracy was the best among the different models, which included the radial basis kernel function SVR model, sigmoid kernel function SVR model, and polynomial kernel function SVR model. Finally, the GA-SVR model was chosen to determine the optimal matching relation between walking speed and fan speed. According to the matching results, a field experiment was conducted and the results revealed that the average impurity rate and loss rate were 4.88% and 0.46%, respectively. Compared with the industry standard, the impurity rate and loss rate were decreased by 3.12% and 6.54%, respectively. The speed tracking error of the fan mechanism and the walking mechanism was less than 2% after 0.6 s. This control strategy provided a feasible scheme for reducing the impurity rate and loss rate of the sugarcane combine harvester.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9

Similar content being viewed by others

References

  • Abdiansah, N., and W. Retantyo. 2015. Time complexity analysis of support vector machines (SVM) in LibSVM. International Journal Computer Applications 128: 28–34.

    Article  Google Scholar 

  • Bahadori, T., and S. Norris. 2018. Optimization of farm management for reducing cane losses during mechanized sugarcane harvesting by using SCHLOT software model. International Sugar Journal 120: 462–464.

    Google Scholar 

  • Dai, F., G.H. Nie, and Y. Chen. 2020. The municipal solid waste generation distribution prediction system based on FIG–GA-SVR model. Journal of Material Cycles and Waste Management 22: 1352–1369.

    Article  Google Scholar 

  • Dang, T., and N.C. Peng. 2017. Forecasting lijiang domestic tourism demand based on the GM-ES-GASVR combination model. Mathematics in Practice and Theory 47: 279–287.

    Google Scholar 

  • Fan, L.X., W.W. Yang, and Q. Li. 2018. Research on the method of extracting the main feature of the settlement in the flotation machine based on data mining and the soft-sensing technology. Mining & Metallurgy 27: 83–85.

    Google Scholar 

  • Feng, D.S. 2020. Problems and strategies of the mechanization of sugarcane harvesting in Guangxi. Agriculture Mechanization Research 51: 39–40.

    Google Scholar 

  • Geng, R. 2017. Process analysis and electro-hydraulic control system of new sugarcane harvester. MS Thesis. Qinhuangdao: Yanshan University

  • Gu, B., V.S. Sheng, K.Y. Tay, W. Romano, and S. Li. 2015. Incremental support vector learning for ordinal regression. IEEE Transactions on Neural Networks and Learning Systems 26: 1403–1416.

    Article  Google Scholar 

  • Guo, L.J., S.Y. Sun, and X.S. Duan. 2008. Research for support vector machines and kernel function. Science Technology and Engineering 8: 487–490.

    Google Scholar 

  • Huang, Z., F.Y. Sun, S.X. Huang, and D.T. Yang. 2017. Fluent simulation of Inner-Flow-Field of axial-excluder devices for sugarcane harvester. Journal of Agriculture Mechanization Research 39(03): 32–36.

    Google Scholar 

  • Hyunchul, A., K. Seongjin, and K.K. Jae. 2014. GA-optimized support vector regression for an improved emotional state estimation model. KSII Transactions on Internet and Information Systems (TIIS) 8: 2056–2069.

    Article  Google Scholar 

  • Kisi, O., and K.S. Parmar. 2016. Application of least square support vector machine and multivariate adaptive regression spline models in long term prediction of river water pollution. Journal of Hydrology 534: 104–112.

    Article  CAS  Google Scholar 

  • Li, H. 2001. The method of modifying polynomial kernel function in SVM and research of exon-intron feature sequence. MS Thesis. Beijing: Beijing University of Technology.

  • Li, H.G., Y.H. Yu, X.F. Shen, and L. Huang. 2018. Research on the soft sensing technology based on KPCA and SVR for fermentation tank. Process Automation Instrumentation 39: 12–16.

    CAS  Google Scholar 

  • Liao, J.Q., H. Wang, and X.P. Wang. 2020. Soft measurement of ultrasonic extracted product concentration by LSSVM of improved fruit fly optimization algorithm. Technical Acoustics 39: 169–175.

    Google Scholar 

  • Ling, Y.F., and J. Wang. 2003. The selection and appliance of the force transducer. Journal of Yunnan University for Nationalities (Natural Sciences Edition) 12: 192–194.

    Google Scholar 

  • Liu, M. 2009. Research on Sigmoid kernel function in support vector machines. MS Thesis. Xian: Xidian University. https://doi.org/10.7666/d.y1668921.

  • Liu, X.M., W. Wang, Z.H. Guo, and C. Wang, and C. Tu. 2019. Research on adaptive SVR indoor location based on GA optimization. Wireless Personal Communications 109: 1095–1120.

    Article  Google Scholar 

  • Loman, M., S. Abdullah, and N. Jamaluddin. 2009. Fatigue damage detection on metallic components using acoustic emission technique. Centre for Graduate Studies, Universiti Malaysia Pahang Editors: M.M. Noor; M.M. Rahman and K. Kadirgama. National Conference on Postgraduate Research (NCON-PGR), 227–233.

  • Meyer, D. 2009. Support vector machines. The interface to libsvm in package e1071: 1–8. https://xueshu.baidu.com/usercenter/paper/show?paperid=1b7fc437a016db6ca734d9ff41d3c4d4&site=xueshu_se&hitarticle=1. Accessed on 7 Oct 2020.

  • NY/T 2903–2016. 2016. Technical Specification of quality evaluation for sugarcane harvesters. http://www.doc88.com/p-9754962896437.html. Accessed on 7 Oct 2020.

  • Neves, J.L.M., K. Cypriani, N.D.C.T. Calori, and T.H.Y. Noleto. 2015. Improvement of the CTC model seed harvester. Sugar Industry/Zuckerindustrie 140: 364–369.

    Article  Google Scholar 

  • Peter, K., G. Bogdan, and S. Sibylle. 2009. Data-driven soft sensors in the process industry. Computers & Chemical Engineering 33: 795–814.

    Article  Google Scholar 

  • Pilsung, K., L. Hyoung-joo, C. Sungzoon, K. Dongil, P. Jinwoo, P. Chan-Kyoo, and D. Seungyong. 2009. A virtual metrology system for semiconductor manufacturing. Expert Systems with Applications 36: 12554–12561.

    Article  Google Scholar 

  • Song, Z., J.P. Gao, L.S. Pan, and J.G. Xi. 2020. Prediction for the state of health of lithium-ion batteries based on PCA and improved SVR. Automobile Technology. https://doi.org/10.19620/j.cnki.1000-3703.20191038.

    Article  Google Scholar 

  • Soualhi, A., K. Medjaher, and N. Zerhouni. 2015. Bearing health monitoring based on Hilbert–Huang transform, support vector machine and regression. IEEE Transactions on Instrumentation and Measurement 64: 52–62.

    Article  Google Scholar 

  • Sun, W., and C. Xu. 2020. Carbon price prediction based on modified wavelet least square support vector machine. The Science of the Total Environment 754: 142052.

    Article  Google Scholar 

  • Terry, H. 2015. Credit scoring using the clustered support vector machine. Expert Systems with Applications 42(2): 741–750.

    Article  Google Scholar 

  • Vladimir, D., K. Ljiljana, R. Suncica, and M. Boban. 2020. Bank CRM optimization using predictive classification based on the support vector machine method. Applied Artificial Intelligence 34: 941–955.

    Article  Google Scholar 

  • Wang, H.B., S.P. Li, F.L. Ma, and Z. Li. 2015. Pneumatic design of small sugarcane harvester fan. Journal of Agricultural Mechanization Research 37: 103–107.

    Google Scholar 

  • Wang, F.L., G.Y. Yang, W.L. Ke, and S.C. Ma. 2018. Effect of sugarcane chopper harvester extractor parameters on impurity removal and cane losses. IFAC Papers Online 51(17): 292–297.

    Article  Google Scholar 

  • Wright, M.E., J.J. Simoneaux, and B. Drouin. 1998. Automatic height control of a sugarcane harvester basecutter. SAE International Journal of Engines 107: 239–246.

    Google Scholar 

  • Xie, F.X., Y.G. Ou, Q.T. Liu, and J.M. Feng. 2012. Design and experiment of impurity discharging fan of sugarcane harvester. Transactions of the Chinese Society of Agricultural Engineering 28: 8–14.

    Google Scholar 

  • Ye, T. 2007. Theory and application of soft-measurement technology based on machine learning. MS Thesis. Guangzhou: South China University of Technology.

  • Yu, Z.Q., J.H. Liu, C.F. He, N.N. Liu, and Y.H. Shi. 2007. The application of Butterworth digital filter on the intelligent measurement and control system. Electrical Measurement & Instrumentation 44(497): 5–8.

    Google Scholar 

  • Zhang, H.D., M. Tang, and L. Zhang. 2013. Study on the GASVR_GM prediction model for endpoint temperature of EAF. Process Automation Instrumentation 34: 7–12.

    Google Scholar 

  • Zhao, Y. 2016. Extending situation and development proposal on sugarcane harvesting mechanization in China. Journal of Chinese Agricultural mechanization 37: 236–244.

    Google Scholar 

  • Zheng, X.Y. 2020. Brief analysis of several programming methods of PLC user program. Techniques of Automation and Applications 39: 69–73.

    Google Scholar 

  • Zuo, S., X.S. Guo, J. Wan, and Z.F. Zhou. 2007. Fast classification algorithm for polynomial kernel support vector machines. Computer Engineering 33: 27–32.

    Google Scholar 

Download references

Acknowledgements

The research presented in this paper was partially supported by the National Natural Science Foundation of China (NSFC). Any opinions, findings, and conclusions expressed in this paper are those of the authors and do not necessarily reflect the views of the NSF.

Author information

Authors and Affiliations

  1. Guangxi University, Nanning, China

    Yuanling Chen, Yang Zhang, Xiao Wang & Yingjie Sun

Authors
  1. Yuanling Chen
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Yang Zhang
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Xiao Wang
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Yingjie Sun
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Yuanling Chen.

Ethics declarations

Conflict of interest

The authors declare that they have no conflict of interest.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Chen, Y., Zhang, Y., Wang, X. et al. A Variable Speed Control Strategy for Impurity Removal Fan of Sugarcane Combine Harvester based on GA-SVR Model. Sugar Tech 23, 1126–1136 (2021). https://doi.org/10.1007/s12355-021-00987-3

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s12355-021-00987-3

Keywords

Search

Navigation