Modeling Soil Pressure-Sinkage Characteristic as Affected by Sinkage rate using Deep Learning Optimized by Grey Wolf Algorithm
Journal Title: Journal of Agricultural Machinery - Year 2024, Vol 14, Issue 1
Abstract
Due to the numerous variables that may influence the soil-machine interaction systems, predicting the mechanical response of soil interacting with off-road traction equipment is challenging. In this study, deep neural networks (DNNs) are chosen as a potential solution for explaining the varying soil sinkage rates because of their ability to model complex, multivariate, and dynamic systems. Plate sinkage tests were carried out using a Bevameter in a fixed-type soil bin with a 24 m length, 2 m width, and 1 m depth. Experimental tests were conducted at three sinkage rates for two plate sizes, with a soil water content of 10%. The provided empirical data on the soil pressure-sinkage relationship served as the basis for an algorithm capable of discerning the soil-machine interaction. From the iterative process, it was determined that a DNN, specifically a feed-forward back-propagation DNN with three hidden layers, is the optimal choice. The optimized DNN architecture is structured as 3-8-15-10-1, as determined by the Grey Wolf Optimization algorithm. While the Bekker equation had traditionally been employed as a widely accepted method for predicting soil pressure-sinkage behavior, it typically disregarded the influence of sinkage velocity of the soil. However, the findings revealed the significant impact of sinkage velocity on the parameters governing the soil deformation response. The trained DNN successfully incorporated the sinkage velocity into its structure and provided accurate results with an MSE value of 0.0871.
Authors and Affiliations
B. Golanbari,A. Mardani,A. Hosainpour,H. Taghavifar,
Keywords
Related Articles
- EP ID EP731762
- DOI https://doi.org/10.22067/jam.2023.84339.1188
- Views 44
- Downloads 0
Comparison of biogas production from rapeseed and wheat residues in compound with cattle manure
Introduction Seventy million tons of agricultural crops are produced from 18 million hectares of agricultural lands in Iran every year. Since 80% of the crops (wt. basis) ends up as residues, therefore, about 50 million...
Study of Potential, Characteristics and Parameters of the Wind Energy Case study: Dehloran County
Introduction Geographical location and climatic conditions are the important factors affecting the wind energy potential of each region. Iran is a vast country with different climates and the exploitation of its wind ene...
Effect of Parameters on the Separation of Almond Shell and Kernel, and Design and Development a Pneumatic Separator
IntroductionAlmonds (Prunus amygdalus) belongs to the family of Rosaceae and the subspecies of Pronoideae. Its kernel contains a lot of energy, amino acids, sugars and mineral elements. Iran is ranked fifth in terms of p...
Introducing a Strategy for Selection of Plowing Systems Using Hybrid SWOT-AHP Method (Khodabandeh, Zanjan)
For improvement or change in a plowing system, it is crucial that all important parameters to be taken in account. Recommendation of a tillage system should receive supports from research data as well as from skilled far...
Investigation of Kinetics and Energy Consumption of Thin Layer Drying of Corn
In this study thin layer drying of corn in a convective dryer was investigated at air temperatures of 50, 60 and 70ºC and air flow rates of 1, 1.4 and 1.8 kg min-1. Experiments were performed in Completely Randomized De...