All Issue

2026 Vol.8, Issue 2 Preview Page

Research Article

Optimization of design variables for amaranth stem cutting blade using data-driven machine learning model and genetic algorithm
HoYun Yu1
,
DongGun Lee12
,
SungBo Shim1*
1Department of Bio Industrial Machinery Engineering, Kyungpook National University, Daegu 41566, Republic of Korea
2Department of Industrial Machinery DX, Korea Institute of Machinery and Materials, Daejeon 34103, Republic of Korea
*Corresponding Author
30 June 2026. pp. 107-122
PDF XML Citation
Abstract

This study investigated the optimal geometric design parameters of a cutting blade to minimize stalk cutting energy for improved energy efficiency in amaranth harvesting. As the industrial demand for amaranth grows, mechanized harvesting for mass production has become increasingly necessary, requiring optimized design of the cutting process, which accounts for a significant proportion of total energy consumption. The shear angle, bevel angle, sliding angle, and approach angle were selected as the primary design variables. A dataset of 519 cutting experiments was compiled, comprising 189 response surface methodology (RSM) experiments and 330 one-factor-at-a-time (OFAT) experiments, to analyze variable interactions and the effects of individual factors. The data were preprocessed and used to train a cutting strength prediction model based on the XGboost algorithm, achieving a coefficient of determination (R2 = 0.7098). Variable importance analysis identified the bevel angle as the dominant factor influencing cutting strength. The developed prediction model was then applied as the fitness function of a genetic algorithm to identify the optimal combination of design parameters. The optimization yielded a predicted minimum cutting strength of 0.1787 N/mm2, with a shear angle of 65.59°, a bevel angle of 16.72°, a sliding angle of 11.45°, and an approach angle of 37.78°. These results validate the proposed methodology combining machine learning and genetic algorithm optimization as an effective strategy for deriving cutting blade design parameters beyond the limitations of physical experimentation alone.

Keywords
Amaranth harvesting
Cutting strength
Design of experiments (DOE)
Genetic algorithm
Optimization
XGboost
References
1

Alamsyah, N., Budiman, B., Yoga, T.P., Alamsyah, R.Y.R. 2024. XGboost hyperparameter optimization using RandomizedSearchCV for accurate forest fire drought condition prediction. Jurnal Pilar Nusa Mandiri 20(2): 103-110. https://doi.org/10.33480/pilar.v20i2.5569

10.33480/pilar.v20i2.5569
2

Anggreainy, M.S. 2025. Hyperparameter optimization for stress level classification in university students: A comparative analysis of GridSearchCV and RandomizedSearchCV. In: Proceedings of 2025 Tenth International Conference on Informatics and Computing (ICIC), 1-6. https://ieeexplore.ieee.org/document/11309700

10.1109/ICIC68054.2025.11309700
3

Bogireddy, S.R., Murari, H. 2024. Enhancing crop yield prediction through random forest classifier: A comprehensive approach. In: Proceedings of 2024 5th International Conference on Smart Electronics and Communication (ICOSEC), 1663-1668. https://doi.org/10.1109/ICOSEC61587.2024.10722249

10.1109/ICOSEC61587.2024.10722249
4

Box, G.E.P., Behnken, D.W. 1960. Some new three level designs for the study of quantitative variables. Technometrics 2(4): 455-475. https://doi.org/10.1080/00401706.1960.10489912

10.1080/00401706.1960.10489912
5

Boydaş, M.G., Comakli, M., Sayinci, B., Kara, M. 2019. Effects of moisture content, internode region, and oblique angle on the mechanical properties of sainfoin stem. Turkish Journal of Agriculture and Forestry 43(2): 254-263. https://doi.org/10.3906/tar-1802-32

10.3906/tar-1802-32
6

Chen, T., Guestrin, C. 2016. XGboost: A scalable tree boosting system. In: Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, 785-794. https://doi.org/10.1145/2939672.2939785

10.1145/2939672.2939785
7

Chicco, D., Warrens, M.J., Jurman, G. 2021. The coefficient of determination R-squared is more informative than SMAPE, MAE, MAPE, MSE and RMSE in regression analysis evaluation. PeerJ Computer Science 7: e623. https://doi.org/10.7717/peerj-cs.623

10.7717/peerj-cs.62334307865PMC8279135
8

Eliçin, A.K., Sessiz, A., Pekitkan, F.G. 2019. Effect of various knife type, cutting angle and speed on cutting force and energy of grape cane. Avrupa Bilim ve Teknoloji Dergisi 15: 519-525. https://doi.org/10.31590/ejosat.532914

10.31590/ejosat.532914
9

Ferreira, S.L.C., Bruns, R.E., Ferreira, H.S., Matos, G.D., David, J.M., Brandão, G.C., da Silva, E.G.P., Portugal, L.A., dos Reis, P.S., Souza, A.S., dos Santos, W.N.L. 2007. Box-Behnken design: An alternative for the optimization of analytical methods. Analytica Chimica Acta 597(2): 179-186. https://doi.org/10.1016/j.aca.2007.07.011

10.1016/j.aca.2007.07.011
10

Galedar, M.N., Tabatabaeefar, A., Jafari, A., Sharifi, A., O'Dogherty, M.J., Rafee, S., Richard, G. 2008. Effects of moisture content and level in the crop on the engineering properties of alfalfa stems. Biosystems Engineering 101(2): 199-208. https://doi.org/10.1016/j.biosystemseng.2008.07.006

10.1016/j.biosystemseng.2008.07.006
11

Global Market Insight (GMI) Inc. 2024. Food culture market size & share, statistics report 2025-2034. https://www.gminsights.com/industry-analysis/food-culture-market

12

Gundoshmian, T.M., Ardabili, S., Mosavi, A., Várkonyi-Kóczy, A.R. 2020. Prediction of combine harvester performance using hybrid machine learning modeling and response surface methodology. In: Várkonyi-Kóczy, A.R. (Ed.), Engineering for Sustainable Future, Lecture Notes in Networks and Systems, Vol. 101, Springer International Publishing, Cham, 345-360. https://doi.org/10.1007/978-3-030-36841-8_34

10.1007/978-3-030-36841-8_34
13

Ghahraei, O., Ahmad, D., Khalina, A., Suryanto, H., Othman, J. 2011. Cutting tests of Kenaf stems. Transactions of the ASABE 54(1): 51-56. https://doi.org/10.13031/2013.36252

10.13031/2013.36252
14

Hu, Y., Xiang, W., Duan, Y., Yan, B., Ma, L., Liu, J., Lyu, J. 2023. Calibration of ramie stalk contact parameters based on the discrete element method. Agriculture 13(5): 1070. https://doi.org/10.3390/agriculture13051070

10.3390/agriculture13051070
15

İnce, A., Uğurluay, S., Güzel, E., Özcan, M.T. 2005. Bending and shearing characteristics of sunflower stalk residue. Biosystems Engineering 92(2): 175-181. https://doi.org/10.1016/j.biosystemseng.2005.07.003

10.1016/j.biosystemseng.2005.07.003
16

Kraber, S. 2023. Augmenting one-factor-at-a-time data to build a DOE. Journal of Plastic Film & Sheeting 39(1): 15-18. https://doi.org/10.1177/87560879221147984

10.1177/87560879221147984
17

Moiz, A.A., Pal, P., Probst, D., Pei, Y., Zhang, Y., Som, S., Kodavasal, J. 2018. A machine learning-genetic algorithm (ML-GA) approach for rapid optimization using high-performance computing. SAE International Journal of Commercial Vehicles 11(2018-01-0190): 291-306. https://doi.org/10.4271/2018-01-0190

10.4271/2018-01-0190
18

Momin, M.A., Wempe, P.A., Grift, T.E., Hansen, A.C. 2017. Effects of four base cutter blade designs on sugarcane stem cut quality. Transactions of the ASABE 60(5): 1551-1560. https://doi.org/10.13031/trans.12345

10.13031/trans.12345
19

Montgomery, D. C. 2017. Design and Analysis of Experiments (9th ed.). John Wiley & Sons, Hoboken, NJ, USA.

20

Nam, K.W., Kim, C.S., Ahn, S.H. 2016. A study on wear damage of SKD11 steel material for a cutting mold jig. Journal of Power System Engineering 20(5): 5-13. https://doi.org/10.9726/kspse.2016.20.5.005

10.9726/kspse.2016.20.5.005
21

Osaba, E., Carballedo, R., Diaz, F., Onieva, E., De La Iglesia, I., Perallos, A. 2014. Crossover versus mutation: A comparative analysis of the evolutionary strategy of genetic algorithms applied to combinatorial optimization problems. The Scientific World Journal 2014: 1-22. https://doi.org/10.1155/2014/154676

10.1155/2014/15467625165731PMC4137700
22

Sadeghi, M., Behnia, F., Amiri, R. 2020. Window selection of the Savitzky–Golay filters for signal recovery from noisy measurements. IEEE Transactions on Instrumentation and Measurement 69(8): 5418-5427. https://doi.org/10.1109/TIM.2020.2966310

10.1109/TIM.2020.2966310
23

Schafer, R.W. 2011. What is a Savitzky-Golay filter? IEEE Signal Processing Magazine 28(4): 111-117. https://doi.org/10.1109/MSP.2011.941097

10.1109/MSP.2011.941097
24

Seflek, A.Y. 2017. Determining the physico-mechanical characteristics of maize stalks for designing harvester. Journal of Animal and Plant Sciences 27(3): 868-875. http://www.thejaps.org.pk/docs/v-27-03/22.pdf

25

Seliem, M.M. 2022. Handling outlier data as missing values by imputation methods: application of machine learning algorithms. Turkish Journal of Computer and Mathematics Education 13(1): 273-286. https://www.researchgate.net/publication/358565692_Handling_Outlier_Data_as_Missing_Values_by_Imputation_Methods_Application_of_Machine_Learning_Algorithms

26

Shabbir, J. 2021. An introduction to statistical learning with applications in R. Statistical Theory and Related Fields 5(1): 87-87. https://doi.org/10.1080/24754269.2021.1980261

10.1080/24754269.2021.1980261
27

Steel, R.G.D., Torrie, J.H. 1981. Principles and procedures of statistics: a biometrical approach. McGraw-Hill, New York.

28

Tian, K., Huang, J., Zhang, B., Ji, A., Xu, Z. 2024. Study on the impact of cutting platform vibration on stalk cutting quality in industrial hemp. Agriculture 14(2): 321. https://doi.org/10.3390/agriculture14020321

10.3390/agriculture14020321
29

Xue, Z., Fu, J., Fu, Q., Li, X., Chen, Z. 2023. Modeling and optimizing the performance of green forage maize harvester header using a combined response surface methodology–artificial neural network approach. Agriculture 13(10): 1890. https://doi.org/10.3390/agriculture13101890

10.3390/agriculture13101890
30

Yang, W.H., Tarng, Y.S. 1998. Design optimization of cutting parameters for turning operations based on the Taguchi method. Journal of Materials Processing Technology 84(1-3): 122-129. https://doi.org/10.1016/S0924-0136(98)00079-X

10.1016/S0924-0136(98)00079-X
31

Zargar, O., Pharr, M., Muliana, A. 2022. Modeling and simulation of creep response of sorghum stems: Towards an understanding of stem geometrical and material variations. Biosystems Engineering 217: 1-17. https://doi.org/10.1016/j.biosystemseng.2022.02.009

10.1016/j.biosystemseng.2022.02.009
32

Zhang, C., Chen, L., Xia, J., Zhang, J. 2019. Effects of blade sliding cutting angle and stem level on cutting energy of rice stems. International Journal of Agricultural and Biological Engineering 12(6): 75-81. https://doi.org/10.25165/j.ijabe.20191206.4604

10.25165/j.ijabe.20191206.4604
Information
  • Publisher :Korean Society of Precision Agriculture
  • Publisher(Ko) :한국정밀농업학회
  • Journal Title :Precision Agriculture Science and Technology
  • Journal Title(Ko) :정밀농업과학기술
  • Volume : 8
  • No :2
  • Pages :107-122
  • Received Date : 2026-06-05
  • Revised Date : 2026-06-19
  • Accepted Date : 2026-06-22
  • DOI :https://doi.org/10.22765/pastj.20260009
Journal Informaiton Precision Agriculture Science and Technology Precision Agriculture Science and Technology
Online Submission & Review System
  • NRF
  • KOFST
  • KISTI Current Status
  • KISTI Cited-by
  • KCI 문헌 유사도 검사
  • orcid
  • open access
  • ccl
Journal Informaiton Journal Informaiton - close