Journal of Agricultural Machinery

Abstract The Dubas bug (Ommatissus lybicus) poses a significant threat to agriculture in the Middle East by weakening palm trees and reducing fruit production. Effective pest control depends on accurate and timely localization of the infestation. However, regular field inspections are difficult and time-consuming, especially for large areas. This research investigates the potential of Sentinel-2 satellite imagery for detecting Dubas bug infestations. The aim is to improve monitoring capabilities, accelerate intervention strategies, and mitigate the associated economic impact. The field trial to assess the infestation occurred in May 2023, coinciding with the peak of the pest outbreak. The severity of the infestation was assessed through pest counts conducted in date palm groves within the urban area of Bam, Iran. Sentinel-2 multispectral images of a specific area were acquired and processed for correction, raw data preparation, and information extraction. The Fast Line-of-sight Atmospheric Analysis of Spectral Hypercubes (FLAASH) method was used for the atmospheric correction of the acquired images. The Nearest Neighbor Interpolation method was used to resample satellite images, standardizing all bands to a uniform 10-meter resolution. Following the pre-processing phase, the KD-tree-based K-Nearest Neighbor classifier model was selected to develop a model specifically designed for identifying areas infested by the Dubas bug. For training, 70% of the measured field data were used, including uninfested areas and areas with three levels of infestation from light to heavy, as well as other land features such as buildings, roads, etc. The remaining 30% of the data was utilized to evaluate the trained model, using the correct prediction rate as the assessment criterion. The trained classifier, validated against the ground truth data, achieved an accuracy of approximately 83% on the test dataset. This accuracy highlights the ability of Sentinel-2 multispectral imagery and machine learning to detect Dubas bug infestations in date palm groves and can facilitate targeted and sustainable pest management strategies.

Abstract Bean planting systems are essential to global agriculture, serving as a vital food source for many populations. Optimizing these planting methods is crucial for enhancing efficiency and reducing environmental impacts. This study evaluates the energy inputs and outputs associated with two pinto bean cultivation techniques: flat and strip systems. Conducted in Fars province, southern Iran, the research involved 90 farms, 60 employing flat systems and 30 utilizing strip systems. Energy consumption was assessed in MJ ha^-1 for various inputs, including labor, machinery, diesel, chemical fertilizers, biocides, electricity, and seeds. The flat system exhibited energy consumption of 20,067.12 MJ ha^-1, while the strip system utilized 18,171.76 MJ ha^-1. In terms of yield, the flat system produced 3000 kg ha^-1, in comparison to 3500 kg ha^-1 from the strip system. Energy efficiency metrics indicated that the strip system outperformed the flat system with a higher energy use efficiency ratio (3.85 against 2.99) and better energy productivity (0.19 kg MJ^-1 vs. 0.15 kg MJ^-1). Additionally, the strip system demonstrated lower specific energy consumption at 5.19 MJ kg^-1, compared to 6.69 MJ kg^-1 for the flat system. The net energy gain was also greater for the strip system, recording 51,828.24 MJ ha^-1 versus 39,932.88 MJ ha^-1 for the flat system. Overall, the results highlight the favorable energy requirements and efficiency of the strip planting method over the traditional flat system, underscoring its potential for optimized resource allocation in pinto bean cultivation. The MOGA results indicated that strip systems achieve substantial energy savings of 3749.11 MJ ha^-1 (25.99%), compared to flat systems, which save 3707.62 MJ ha^-1 (22.66%). This further highlights the efficiency benefits of strip planting.

Abstract This research aimed to enhance the design and functionality of an integrated enset processing machine by focusing on key components such as the shaft, cylinder drum, breastplate, and drum blade. Existing enset processing machines suffer from inefficiencies due to component wear, mechanical breakdowns, and suboptimal design, leading to operational challenges. To address these issues, targeted design modifications were planned for the machine’s components. The materials for these components were selected according to ASTM standards. The modified components were rigorously analyzed using the Finite Element Method in the Workbench module of ANSYS 2023 R1 software at Adama Science and Technology University, Adama, Ethiopia. The study reported maximum stresses of 120 MPa, 250 MPa, 400 MPa, and 260 MPa, and minimum stresses of 30 MPa, 70 MPa, 120 MPa, and 80 MPa for the shaft, cylinder drum, blade, and breastplate, respectively. Maximum deformations were found to be 0.15 mm, 0.3 mm, 0.55 mm, and 0.35 mm for these components, with a maximum safety factor of 15 for all. These results indicate that the modifications provide safe working conditions. The design ensures that the drum, drum blade, and breastplate possess sufficient rigidity to withstand operational forces, with minimal deformation (2.39×10⁻⁶ mm for the drum blade), remaining within a safety factor limit of 1.25. Additionally, the machine demonstrated excellent energy dissipation and vibrational response, indicating structural robustness.

Abstract Monitoring the status of machinery is a crucial aspect of production and service units to uphold operational efficiency. Timely changes in engine lubricant significantly contribute to enhanced performance and extended engine lifespan. However, determining the precise replacement time remains a challenge. Oil spectral analysis, while effective, is both expensive and time-intensive. This study aims to introduce an alternative method to engine lubricant spectral analysis. The investigation involves analyzing the results of spectral analysis and dielectric coefficients of 17 engine lubricant samples through statistical methods. The primary objective is to develop models for predicting oil contaminants based on dielectric properties, offering a substitute for spectral analysis. To achieve this, several intermediate goals are pursued. Multilayer perceptron artificial neural networks (MLP-ANN) and support vector machine (SVM) methods are employed for modeling. The performance of the two models is assessed using indicators such as Root Mean Square Error (RMSE), model efficiency, and R-squared (R²). The results indicate that the SVM model consistently demonstrates an efficiency exceeding 0.95 for all predicted indices (Fe, Pb, Cu, Al, Mo, Na, Si, and Vis@100). Consequently, dielectric spectroscopy of lubricant emerges as a viable alternative to traditional oil spectral analysis.

Abstract Agriculture is the most prominent industry in developing countries and also ranks as one of the most dangerous professions. Tractors and grain combine harvesters are two of the main self-propelled agricultural machines. Agricultural machines, despite their irreplaceable role in increasing productivity, contribute significantly to agricultural accidents. This study was conducted to investigate the current rates and severity of accidents and human casualties related to agricultural tractors and grain combine harvesters in Ilam province, Iran. Evaluations were conducted using data from the years 2019-2023.Over these five years, the accident frequency for agricultural combines and tractors was 61 and 43, respectively, indicating a statistically significant difference. Among the tractor drivers in this research, the most frequent accidents occurred due to the power take-off shaft (P.T.O.), helices, and feeding rollers. Among combine drivers, accidents were most common at the shear points of the machine (cutter bars, gears, etc.). This research evaluated the factors affecting field accidents related to tractors and combines and estimated the accident rates. Accident rates, including AFR (Accident Frequency Rate), ASR (Accident Severity Rate), FIR (Fatal Incident Rate), and FSI (Frequent Severity Index), were calculated. The rates of AFR, ASR, FIR, and FSI were 25.84, 45.82, 1.66, and 1.066% for combine harvesters, and 5.60, 12.63, 4.44, and 0.262% for tractor accidents, respectively. The nonfatal rate for combine harvesters was 6445 per 100,000, and for agricultural tractors, it was 4334 per 100,000. Tractor accidents had a higher fatality rate than combine harvesters, with 445 fatalities per 100,000 for tractors compared to 333 per 100,000 for combine harvesters.

Abstract In this research, the amount of vitamin C, aromatic compounds, and color change of orange powder was measured using chemical methods, an olfactory machine, and a scanner in four dryers at 45℃. These dryer apparatuses included normal atmospheric vacuum, atmospheric control vacuum, convective, and convective-infrared. The highest response of sensors to aromatic compounds in convective and lowest response in control vacuum and normal vacuum dryers was observed. The two main components of principal component analysis (PCA) explained 88% of the data variance. The structure of the artificial neural network (ANN) was 8-5-4. Further, based on loading diagrams of partial least squares (PLS) and principal component regression (PCR) models, the MQ3 and MQ6 sensors were the best to predict the amount of vitamin C and the color change of orange powder. MQ135 sensor can also be removed from the set of electronic nose sensors due to their low accuracy and cost reduction. The multiple linear regression (MLR), compared to PCR and PLS models, proved to be more accurate (i.e., R²= 0.83 and RMSE= 0.144 for vitamin C prediction and R²= 0.94 and RMSE= 0.68 for predicting color change). The highest and lowest values of measured color change was observed in convective dryer and atmospheric control vacuum dryer, respectively. Also, the highest and lowest measured vitamin C was observed in convective-infrared dryer and atmospheric control vacuum dryer, respectively. The best dryer to maintain the quality of the orange powder is the convective-infrared dryer. The results of this article showed that the data obtained from the olfactory machine is able to predict the color change and vitamin C of orange powder. Also, the olfactory machine can be used to identify and classify the type of dryer used to prepare orange powders with the least time and cost, without distorting the sample, and to determine the best dryer for preparing orange powder.

Abstract This study proposes a novel method for identifying grape leaf diseases through RGB image analysis combined with weighted group decision-making. The investigation focused on five disease types, Black Measles, Black Rot, Leaf Blight, Powdery Mildew, and Downy Mildew, along with healthy leaves. Three machine learning classifiers, namely support vector machine (SVM), random forest (RF), and k-nearest neighbor (k-NN), were employed individually and in a weighted ensemble. Each classifier was assigned a weight based on its accuracy, and the final disease classification was determined using a majority voting strategy. To determine the most discriminative features related to texture, color, and shape, the Relief feature selection algorithm was applied, which identified the top five effective features in diagnosing grape leaf diseases. Experimental results indicated that the classification accuracies of SVM, RF, and k-NN were 88.33%, 80.08%, and 75%, respectively. Furthermore, the proposed weighted group decision-making approach improved the overall classification performance, achieving an accuracy of 91.67%.

Abstract The rapid growth of the global population and the increasing demand for energy, coupled with the urgent need for environmental conservation, have prompted researchers to explore renewable energy sources as viable alternatives to non-renewable fossil fuels. This study evaluates the performance enhancement of photovoltaic/thermal (PVT) systems using an immersion cooling method with copper oxide nanofluids. The experimental setup included a glass chamber immersing the panel surface, tested at nanofluid volume ratios of 0.025% and 0.05%, and flow rates of 0.01 and 0.02 L s^-1. The immersion height was 5 cm within the glass chamber. The tests were conducted under ambient conditions, which included an ambient temperature of 20.6-31.2 ℃ and an irradiance of 343-924 W m^-2. Results demonstrate that copper oxide nanofluids at a 0.05% volume ratio and a 0.02 L s^-1 flow rate improved thermal efficiency to 31.87% and reduced panel surface temperature by up to 11.8 °C compared to water cooling. Also, the electrical efficiency of the PVT system exceeded that of the reference panel. The overall efficiency of the PVT system reached 41.89%. These findings highlight the potential of nanofluid-based cooling to optimize PVT system efficiency by enhancing thermal management.

Abstract Grain harvesting operations account for approximately 25-30% of total direct energy consumption in crop production systems. Developing appropriate blades for harvesting canola (Brassica napus L.) is crucial due to its distinct characteristics compared to other cereal grains. This study investigated the effects of blade angles (placement angles: 30°, 45°, and 60°; sharpness angles: 30°, 45°, and 60°), reciprocating movement speed (800, 1100, and 1400 courses per minute), and moisture levels (19%, 22%, and 24%) on reducing force, shear stress, and energy consumption during canola harvesting. Results showed that a blade sharpness angle of 30° yielded the lowest shear stress (0.175 N mm^-2) compared to 60° (0.303 N mm^-2). The 45° blade placement angle demonstrated minimum shear stress (0.177 N mm^-2) versus 60° (0.320 N mm^-2). Increasing moisture content from 19% to 24% reduced shear stress from 0.256 N mm^-2 to 0.200 N mm^-2. The highest reciprocating speed (1400 courses per minute) resulted in the lowest shear stress (0.167 N mm^-2) compared to 800 courses per minute (0.286 N mm^-2). Life cycle assessment revealed that varying blade placement angles (30° to 60°) could increase marine aquatic ecotoxicity by up to 55,762.55 kg dichlorobenzene equivalent, while changes in blade sharpness angles and reciprocating speed could lead to increases of 377,429.87 kg and 143,185.69 kg dichlorobenzene equivalent, respectively. The optimal configuration—comprising a sharpness angle of 30°, a placement angle of 45°, a moisture content of 24%, and a reciprocating speed of 1400 courses per minute—significantly reduced both shear energy and environmental impact.

Abstract Smallholder maize production in sub-Saharan Africa, crucial for regional food security, grapples with persistent yield gaps driven by labor-intensive planting practices and a critical lack of mechanization specifically designed to accommodate the traits of native plant varieties. This study characterizes three maize varieties (CML-539, Melkassa 3, and Melkassa 6Q) to develop design parameters for adaptive multi-crop planters. Geometric properties including length, width, and thickness were measured using digital calipers, with 100 seeds per variety. Analysis was performed for elongation, geometric and arithmetic mean diameters, surface area, projected area, transverse cross-sectional area, sphericity, flakiness ratio, aspect ratio, shape index, and roundness. Gravimetric properties including bulk and true densities, porosity, thousand seed mass, and angle of repose were systematically analyzed to optimize seed-handling mechanisms in planter design. Physical property analysis revealed distinct varietal requirements: CML-539's irregular morphology (9.42 mm length, 49.30% porosity) necessitates vibration-assisted metering and aerated delivery systems; Melkassa 6Q's uniform properties (71.11± 6.66% sphericity, 811.62 kg m^-3 bulk density) permit gravity-fed mechanisms; and Melkassa 3's intermediate characteristics of > 2.3 elongation ratio and 19.31% density variation require adjustable furrow openers of 25-30° rake angles. Geometric variability necessitates the implementation of adaptive solutions, such as curved seed tubes and adjustable furrow openers, to effectively prevent tilt and bridging. The resulting modular planter system, incorporating moisture-responsive metering, adaptive cell sizing, and aerated delivery, aligns with Ethiopia’s agroecological standards of 75 cm row spacing and depth range of 4 to 7 centimeters. This framework offers a scalable, sustainable model for precision smallholder mechanization, transferable to global maize systems.

Abstract In botanical terms, the classification of plants reveals a multitude of species derived from different sources. The first step for quality control of herbal medicines is to identify their different species and genotypes. The present study investigated the classification of ten different mint genotypes using Gas Chromatography-mass Spectrometry (GC-MS) and an electronic nose (e-nose) system utilizing Metal Oxide Semiconductor (MOS) sensors. Leaf samples were harvested from various mint genotypes, and subsequently, the system sensors' responses to each of these samples were recorded. The classification of plants was performed using biplot diagrams based on GC and GC-MS data, with clustering facilitated by the Ward method. The responses of all e-nose sensors were further analysed through various approaches, including Principal Components Analysis (PCA), Linear Discriminant Analysis (LDA), Quadratic Discriminant Analysis (QDA), and Artificial Neural Network (ANN). The results from the qualitative analysis of essential oils via GC-MS demonstrate that more than 99% of the identified compounds belong to four chemical groups: hydrocarbon and oxygenated monoterpenes, as well as hydrocarbon and oxygenated sesquiterpenes. Also, based on biplot analysis, different mint populations could be generally divided into 8 groups. The results of principal component analysis showed that the first two main components can cover a total of 97% of the data variance. The classification accuracy achieved through e-nose data for LDA, QDA, and ANN was 98.9%, 99.9%, and 96%, respectively. Proper classification of mint genotypes by e-nose system could be used as a sensitive, reliable, and low-cost alternative to traditional methods.

Abstract Drying is a vital preservation method in the food industry, reducing moisture content while maintaining product quality and extending shelf life. This process involves complex heat and mass transfer mechanisms, necessitating accurate predictive models. This study compares various modeling approaches, including regression models, semi-empirical, and artificial intelligence (AI)-based methods, to simulate the drying process of potato slices. Experimental drying trials were run at 40°C, 50°C, and 60°C, both with and without phase change materials (PCM) and infrared radiation (IR). AI models (ANN, SVM, and RF) were trained and validated using experimental data. Their performance was evaluated against conventional and semi-empirical models using R², RMSE, MAE, and MBE. Results indicate that ANN achieved the highest predictive accuracy (R²= 0.998, RMSE= 0.0656 g water g^-1 dry matter), outperforming other models. SVM also demonstrated strong predictive capability, while RF performed slightly lower. Among semi-empirical models, the Midilli model provided the best fit but was less accurate than AI-based models. These findings highlight the superiority of AI-driven approaches, particularly ANN, in optimizing drying processes for the food industry.

Abstract Pickering emulsion-based edible biodegradable films have emerged as a promising sustainable alternative to conventional food packaging materials. These films exhibit enhanced mechanical properties, including tensile strength, flexibility, and water vapor barrier performance, which are critical for maintaining food integrity throughout storage and transportation. A key advancement in this field is the incorporation of essential oils into the emulsion matrix, which, despite their hydrophobic nature, significantly improve the functional and mechanical properties of polysaccharide-based films. This review examines the physicomechanical properties of polysaccharide-based edible biodegradable films incorporating Pickering emulsions, with a focus on flexibility, tensile strength, water vapor permeability, and moisture retention capacity. Furthermore, it explores the role of these films in extending food shelf life and analyzes how interactions between essential oils and polysaccharides influence their structural and barrier properties. Findings demonstrate that Pickering emulsions containing essential oils substantially enhance the mechanical and moisture barrier performance of edible biodegradable films. Solid stabilizing particles contribute to increased tensile strength, while essential oils improve flexibility—though excessive concentrations may compromise structural integrity. Additionally, these emulsions reduce water absorption and solubility, thereby improving film stability in humid conditions. Finally, this review examines the current challenges and identifies key research opportunities in the development of essential oil-loaded Pickering emulsion systems for polysaccharide-based biodegradable films, while outlining their potential for scalable industrial applications.