Evaluation and Modeling of Physical and Physiological Damage to Wheat Seeds under Successive Impact Loadings: Mathematical and Neural Networks Modeling

Abstract

Threshing wheat (Triticum aestivum L.) at high speeds is the main reason behind abnormal seedlings and vigor reduction of the seeds. This problem is expected to be severe in head‐stripper combines with successive impact loadings of stripping and threshing units. The aim of this study was to simulate the effects of impact velocities (IV), number of impact loadings (NL), and seed moisture content (MC) on percentage of physical damage (PPD) and percentage of loss in germination (PLG) to wheat seeds. Modeling the correlation between dependent and independent variables was performed using mathematical and artificial neural networks (ANN). The result showed that all the three independent variables significantly influenced PPD and PLG (P = 0.01). Increasing the IV from 5 to 30 m s−1 caused an increase in PPD and PLG from 0.17 to 35.8% and from 0.37 to 19.9%, respectively. It was found that the seeds with higher MC could better withstand physical and physiological damage than those with lower MC. With an increase in NL from 1 to 3 times, the mean values of PPD and PLG were increased by 2.9 and 2.6 times, respectively. An ANN model with two hidden layers, trained with a back‐propagation algorithm, successfully learned the relationship between the input and output variables. In comparison with regression models, ANN performed better when predicting PPD and PLG to wheat seeds.

A Mastercurve to predict annual ryegrass (Lolium rigidum) seed devitalisation when exposed to multiple single sided impacts

“…Despite very low devitalisation for 1, 2 and 4 impacts at 30 m s À1 , up to 48% devitalisation was achieved with 16 impacts at 30 m s À1 , which indicates that some accumulation of damage occurred even at low impact speeds. Damage accumulation was also seen by Khazaei et al (2008) and by Frą czek and…”

“…This testing only considers impact speeds that cause low levels of seed devitalisation but they do show some trends. Seed devitalisation increases with impact speed (Bartsch, Haugh, Athow, & Peart, 1986;Berry et al, 2014;Khazaei, Shahbazi, Massah, Nikravesh, & Kianmehr, 2008;Leonhardt, Zoerb, & Hamann, 1961); increases with the number of successive impacts (Frą czek & Slipek, 1998;Khazaei et al, 2008) and reduces with moisture content (Bartsch et al, 1986).…”

Estimation of in-situ horizontal stresses using the linear poroelastic model and minifrac test results in tectonically active area

“…A neural network is a parallel distributed processing system composed of two components: the node (also called processing element, artificial neuron or unit) and the connection [Khazaei and Shahbazi, 2005]. A parameter (weight) is associated with each connection between two cells.…”

“…A parameter (weight) is associated with each connection between two cells. Thus each cell in the upper layer receives weighted inputs from each node in the layer below and then processes these collective inputs before the unit sends a signal to other layers [Li and Bridgwater, 2000]. The application processes of an ANN model design include the following steps [Trippi and Turban, 1996]:…”

Spatial Relationships of Landscape Attributes and Wheat Yield Patterns

“…ANN modeling mimics the human brains and develops the ability to learn from the real world experimental data (Khazaei et al, 2008;Noori et al, 2011). They can learn the complex relationship (linear or non-linear) and are able to make intelligent predictions on the unseen data (Farooq & Cherif, 2008;Farooq, 2010).…”