Journal of Researches in Mechanics of Agricultural Machinery

Journal of Researches in Mechanics of Agricultural Machinery

Predicting Tractor Draft Force, Wheel Slippage, and Fuel Consumption Under Field Conditions Using Adaptive Neuro-Fuzzy Inference System (ANFIS)

Document Type : Research Paper

Authors
Kalam Babazadeh 1
Behzad Mohammadi Alasti 2
Mahdi Abbasgholipour 1
Asghar Mahmudi 3
1 Department of Mechanical Engineering of Biosystems, Bon.C., Islamic Azad University, Bonab, Iran.
2 Department of Mechanical Engineering of Biosystems, Bon.C., Islamic Azad University, Bonab, Iran
3 Department of Mechanical Engineering of Biosystems, Tabriz University, Tabriz, Iran
10.22034/jrmam.2026.15096.777
Abstract
In this study, the Adaptive Neuro-Fuzzy Inference System (ANFIS) was used to predict the traction force, wheel slip and tractor fuel consumption in field conditions during plowing operations with a plow and a harrow. Experiments were conducted in the fields of Iran Tractor Sazi Company using a two-tractor method. The independent variables included four levels of tillage depth (10, 20, 30 and 40 cm), three levels of soil moisture (approximately 12, 15 and 19 percent), and four levels of forward speed with heavy gears (1, 2.55, 4.40 and 6.58 km/h). A factorial experiment based on a randomized complete block design (RCBD) with three replications was used. Simultaneous prediction of key tractor performance indicators is one of the fundamental challenges in managing tillage operations and optimizing energy consumption because these indicators are affected by the complex and nonlinear interaction between soil properties and operating parameters, and conventional methods do not have sufficient accuracy to describe these relationships. Therefore, an intelligent framework based on (ANFIS) along with principal component analysis (PCA) was developed to simultaneously predict traction force, wheel slip and fuel consumption. The results showed that increasing soil depth and forward speed increased traction force, slip and fuel consumption, while increasing soil moisture improved this index due to the decrease in soil mechanical strength. The proposed model with high coefficients of determination for traction force (0.99996), slip (0.9997) and fuel consumption (0.99964) and very low RMSE values was able to simulate the real behavior of the soil tractor system with good accuracy. The results showed that the developed model is not only an accurate tool for predicting tractor performance but also can be used as a decision support system in selecting optimal operating conditions to reduce fuel consumption and tillage costs, control slip and improve energy efficiency in precision agriculture.
Keywords
Draft Force
Wheel slippage
Fuel consumption
Field conditions
ANFIS
Tillage operations
Subjects
Abbaspour-Gilandeh, Y., Rahimi-Ajdadi, F., Asli-Ardeh, E. A., Sharabiani, V. R., & Ardabili, M. (2009). Application of artificial neural network for predicting fuel consumption of tractor. International Agricultural Engineering Conference, Bangkok, Thailand.
 
Akbarnia, A., Mohammadi, A., Alimardani, R., & Farhani, F. (2014). Simulation of draft force of winged share tillage tool using artificial neural network model. Agricultural Engineering International: CIGR Journal, 16(4), 57–65.
 
Almaliki, S., Alimardani, R., & Omid, M. (2016). Artificial neural network based modeling of tractor performance at different field conditions. Agricultural Engineering International: CIGR Journal, 18(4), 262–274.
 
ASABE. (2011). Agricultural machinery management data. American Society of Agricultural and Biological Engineers.
 
Askari, M., & Abbaspour-Gilandeh, Y. (2020). Predicting the Imposed Forces on the Tines and Tractor Fuel Consumption during Subsoiling Operation Using Adaptive Neuro-Fuzzy Inference System (ANFIS). Agricultural Mechanization and Systems Research, 21(74), 47–66. https://doi.org/10.22092/erams.2018.122163.1262
 
Borges, P. H. M., Mendoza, Z. M. S. H., Maia, J., Bianchini, A., & Fernándes, H. C. (2017). Estimation of fuel consumption in agricultural mechanized operations using artificial neural networks. Engenharia Agrícola, 37, 136–147. https://doi.org/10.1590/1809-4430-eng.agric.v37n1p136-147/2017
 
Damanauskas, V., & Janulevičius, A. (2022). Effect of tillage implement (spring tine cultivator, disc harrow), soil texture, forward speed, and tillage depth on fuel consumption and tillage quality. Journal of Agricultural Engineering, 53(3). https://doi.org/10.4081/jae.2022.1371
 
Dizaji, H. Z., Khorasani, M. E., Nategh, N. A., Sheikhdavoodi, M., & Andekaiezadeh, K. (2022). Specific draft modeling for combined and simple tillage implements. Agricultural Engineering International: CIGR Journal, 24(4).
 
Falahat Nejad Mahani, S., & Karami, A. (2023). Maize Tassel Detection and Counting Using Deep Learning Techniques. Journal of Agricultural Machinery, 13(2). https://doi.org/10.22067/jam.2022.72477.1062
 
Fallah, M., & Ghanbari Parmehr, E. (2023). Detection of Chilo Suppressalis using Smartphone Images and Deep Learning. Journal of Agricultural Machinery, 13(2). https://doi.org/10.22067/jam.2022.72647.1064
 
Foldager, F., Munkholm, L. J., Balling, O., Serban, R., Negrut, D., Heck, R. J., & Green, O. (2022). Modeling soil aggregate fracture using the discrete element method. Soil and Tillage Research, 218, 105295. https://doi.org/10.1016/j.still.2021.105295
 
Ghiasi, P., Masoumi, A., Hemmat, A., & Najafi, G. (2020). ANN-based Modeling of Sunflower Threshing Process and Defining the Optimal Operation Point for Separation Efficiency. Journal of Agricultural Machinery, 10(1), 73–82. https://doi.org/10.22067/jam.v10i1.76264
 
Han, J., Yan, X., & Tang, H. (2023). Method of controlling tillage depth for agricultural tractors considering engine load characteristics. Biosystems Engineering, 227, 95–106. https://doi.org/10.1016/j.biosystemseng.2023.01.011
 
Jalali, A., Mahmoudi, A., Valizadeh, M., & Skandari, I. (2015). The effect of conservation tillage forward speed and depth on farm fuel consumption. Journal of Agricultural Machinery, 5(2), 325–335. https://doi.org/10.22067/jam.v5i2.28517
 
Jalilnezhad, H., Abbaspour-Gilandeh, Y., Rasooli-Sharabiani, V., Mardani, A., Hernández-Hernández, J. L., Montero-Valverde, J. A., & Hernández-Hernández, M. (2023). Use of a convolutional neural network for predicting fuel consumption of an agricultural tractor. Resources, 12(4), 46. https://doi.org/10.3390/resources12040046
 
Jang, J.-S. (1993). ANFIS: adaptive-network-based fuzzy inference system. IEEE Transactions on Systems, Man, and Cybernetics, 23(3), 665–685. https://doi.org/10.1109/21.256541
 
Kepner, R.A., Bainer, R., & Bager, E.L. (1978). Principles of Farm Machinery (3rd ed). Westport.CT:AVI Publishing Company.
 
Kim, Y.-S., Lee, S.-D., Baek, S.-M., Baek, S.-Y., Jeon, H.-H., Lee, J.-H., Kim, W.-S., Shim, J.-Y., & Kim, Y.-J. (2022). Analysis of the effect of tillage depth on the working performance of tractor-moldboard plow system under various field environments. Sensors, 22(7), 2750. https://doi.org/10.3390/s22072750
 
Lithourgidis, A. S., Dhima, K. V, Damalas, C. A., Vasilakoglou, I. B., & Eleftherohorinos, I. G. (2006). Tillage effects on wheat emergence and yield at varying seeding rates, and on labor and fuel consumption. Crop Science, 46(3), 1187–1192. https://doi.org/10.2135/cropsci2005.09-0321  
 
Mamkagh, A. M. (2019). Review of fuel consumption, draft force and ground speed measurements of the agricultural tractor during tillage operations. Asian Journal of Advanced Research and Reports, 3(4), 1–9. https://doi.org/10.9734/ajarr/2019/v3i430093
 
 Mobtaker, H. G., Akram, A., & Keyhani, A. (2010). Economic modeling and sensitivity analysis of the costs of inputs for alfalfa production In Iran: A case study from Hamedan province. Ozean Journal of Applied Sciences, 3(3), 313–319.
 
Mohammadi, A. (2012). Modeling of draft force variation in a winged share tillage tool using fuzzy table look-up scheme. Agricultural Engineering International: CIGR Journal, 14(4), 262–268.
 
Mohd Salleh, M. N., & Hussain, K. (2016). A review of training methods of ANFIS for applications in business and economics. International Journal of U-and e-Service, Science and Technology, 9(7), 165–172. http://dx.doi.org/10.14257/ijunesst.2016.9.7.17  
 
Nagar, H., & Machavaram, R. (2022). Application of artificial intelligence for fuel consumption prediction of a tractor in different operating conditions. 2022 IEEE 7th International Conference for Convergence in Technology (I2CT), 1–7.
 
Rahimi-Ajdadi, F., & Abbaspour-Gilandeh, Y. (2011). Artificial neural network and stepwise multiple range regression methods for prediction of tractor fuel consumption. Measurement, 44(10), 2104–2111. https://doi.org/10.1016/j.measurement.2011.08.006
 
Regassa, A., Ali, A., & Taye, G. (2023). Soil classification. In The Soils of Ethiopia (pp. 71–75). Springer.
 
Roul, A. K., Raheman, H., Pansare, M. S., & Machavaram, R. (2009). Predicting the draught requirement of tillage implements in sandy clay loam soil using an artificial neural network. Biosystems Engineering, 104(4), 476–485.
https://doi.org/10.1016/j.biosystemseng.2009.09.004
 
Šarauskis, E., Vaitauskienė, K., Romaneckas, K., Jasinskas, A., Butkus, V., & Kriaučiūnienė, Z. (2017). Fuel consumption and CO2 emission analysis in different strip tillage scenarios. Energy, 118, 957–968. https://doi.org/10.1016/j.energy.2016.10.121
 
Shafaei, S. M., Loghavi, M., & Kamgar, S. (2021). Profound insight into tractor energy dissipation through inevitable interaction inside wheel-soil interface for the period of plowing works. Soil and Tillage Research, 211, 104998. https://doi.org/10.1016/j.still.2021.104998
 
Soylu, S., & Çarman, K. (2021). Fuzzy logic based automatic slip control system for agricultural tractors. Journal of Terramechanics, 95, 25–32. https://doi.org/10.1016/j.jterra.2021.03.001
 
Suresh, N. V. U., Sadeghi, A., & Yazdani-Asrami, M. (2023). Critical current parameterization of high temperature superconducting tapes: A novel approach based on fuzzy logic. Superconductivity, 5, 100036. https://doi.org/10.1016/j.supcon.2023.100036
 
Tayel, M. Y., Shaaban, S. M., & Mansour, H. A. (2015). Effect of plowing conditions on the tractor wheel slippage and fuel consumption in sandy soil. International Journal of ChemTech Research, 8(12), 151–159.
 
Vesović, M. V., & Jovanović, R. Ž. (2022). Adaptive neuro fuzzy Inference systems in identification, modeling and control: The state-of-the-art. Tehnika, 77(4), 439–446. https://doi.org/10.5937/tehnika2204439V
 
Ziółkowski, J., Oszczypała, M., Małachowski, J., & Szkutnik-Rogoż, J. (2021). Use of artificial neural networks to predict fuel consumption on the basis of technical parameters of vehicles. Energies, 14(9), 2639. https://doi.org/10.3390/en14092639