In this study, artificial neural networks (ANNs) were used to predict the draft force of a rigid tine chisel cultivator. The factorial experiment based on the randomized complete block design (RCBD) was used to obtain the required data and to determine the factors affecting the draft force. The draft force of the chisel cultivator was measured using a three-point hitch dynamometer and data were collected using a DT800 datalogger. A recurrent back-propagation multilayer network was selected to predict the draft force of the cultivator. The gradient descent algorithm with momentum, Levenberg–Marquardt algorithm, and scaled conjugate gradient descent algorithm were used for network training. The tangent sigmoid transfer function was the activation functions in the layers. The draft force was predicted based on the tillage depth, soil moisture content, soil cone index, and forward speed. The results showed that the developed ANNs with two hidden layers (24 and 26 neurons in the first and second layers, respectively) with the use of the scaled conjugate gradient descent algorithm outperformed the networks developed with other algorithms. The average simulation accuracy and the correlation coefficient for the prediction of draft force of a chisel cultivator were 99.83% and 0.9445, respectively. The linear regression model had a much lower accuracy and correlation coefficient for predicting the draft force compared to the ANNs.

A time-optimal problem for redundantly actuated robots moving on a specified path is a challenging problem. Although the problem is well explored and there are proposed solutions based on phase plane analysis, there are still several unresolved issues regarding calculation of solution curves. In this paper, we explore the characteristics of the maximum velocity curve (MVC) and propose an efficient algorithm to establish the solution curve. Then we propose a straightforward method to calculate the maximum or minimum possible acceleration on the path based on the pattern of saturated actuators, which substantially reduces the computational cost. Two numerical examples are provided to illustrate the issues and the solutions.

In this study, the effects of tillage depth, forward speed and soil moisture content during the cultivator operation on the draft force, energy requirement, and soil disturbance were investigated using five types of cultivators. The experiments were performed in the factorial design based on the randomized complete block design (RCBD) with three replications in loamy sand soil. Different soil moisture contents (factor A) from 5 to 16% for dry soils and 17 to 35% for wet soils, forward speed of tractor (factor B) at four levels of 1.16, 1.61, 1.97, and 3.82 km/hand working depth (factor C) at two levels of 10 and 20 cm were selected. The analysis of variance results showed that the main effects on the draft force, energy requirement, and soil disturbance were significant. With increasing the forward speed, working depth, and blade width, the draft force, energy requirement, and soil disturbance significantly increased. As the soil moisture content increased, the amount of draft force decreased. The average maximum draft force and energy requirement are related to the crescent cultivator and the lowest ones to the cultivator with a sweep blade. The maximum amounts of draft force and energy requirement at the speed of 3.82 km/h were 296.702 N and 0.03708 MJ in the dry conditions, respectively. The average maximum draft force and energy requirement are related to the crescent cultivator and the lowest ones to the cultivator with a sweep blade. The average maximum draft force and energy requirement in dry soil at 10–20 cm depth were 313.534 N and 0.039204 MJ, respectively, and the lowest values were 189 N and 0.019512 MJ in wet soil at the depth of 0–10 cm, respectively. The highest mean value of the area obtained from the profiles was 254.62 cm2 related to the dry conditions and forward speed of 3.82 km/h, and the lowest mean value of the area obtained in the wet conditions was 199.6 cm2 at the forward speed of 1.16 km/h. The highest average area obtained from the profiles was observed in the dry conditions for C4 as 434.813 cm2 and the lowest one was 57.94 cm2 in the wet conditions for the cultivator with a chisel blade and L-shaped shank. The highest average area created by cultivators at the 10–20 cm depth in the dry conditions was 332.875 cm2 and the lowest one at the 0–10 cm depth in the wet conditions was 123.55 cm2. The results of this study can help the designers and manufacturers of agricultural machinery to effectively design and manufacture the machinery with optimum draft and energy requirements.

No abstract