Journal of Agricultural Machinery Engineering ISSN:2799-8673(Print) 2799-8819(Online) 농업기계공학

Due to the ongoing shortage of rural labor and the aging farming population, the farm size per farmer has increased, demanding durable and reliable agricultural equipment. In response to this demand, an accelerated life test (ALT) technique for the tractor axle was developed based on measured load data during actual field operations. Robust axle systems were required for high torque at low speeds of tractors, particularly during high-load operations such as plow tillage. In this study, axle torques and rotational speeds were measured for both the front and rear axles using telemetry torque sensors. The measured data were segmented into torque ranges, and a Load Duration Distribution (LDD) was analyzed. Equivalent torque was calculated by applying the Palmgren–Miner linear damage rule, and a fatigue damage exponent was assumed as 8.738. The equivalent torque was obtained as 6,310.99 Nm. The applied torque was approximately 8,170.08 Nm, which is 1.2 times the rated torque. The acceleration factor was calculated as 9.545, which reduced the durability test time from 3,000 to 314.3 hours. The proposed technique provides a quantifiable and efficient method for evaluating axle fatigue life under actual working conditions. It was expected that this technique could be adapted to other equipment in future research, contributing to enhanced drivetrain reliability, shortened product development cycles, and reduced maintenance and production costs of the agricultural machinery.

This study focused on resolving issues arising from a smart notification system developed to enhance the convenience and stability of a sweet potato shoot attachment machine. We identified issues arising from the existing system's sensing and notification methods and applied new sensing and improved notification methods to the improved system. And the improved system developed in this way was tested and its performance was compared and analyzed. Through this, we confirmed that the improved system outperforms the existing system in terms of performance. This paper proposes a development and verification method for an improved smart multi-functional notification system.

In agricultural harvesting robots, fruit pose information is essential for determining the grasping point. However, in greenhouse environments, frequent occlusion caused by leaves and stems considerably degrades the accuracy of existing models. This study aims to improve cucumber pose estimation performance in occluded scenes. To achieve robust estimation performance under various occlusion conditions, we designed an approach that infers the relative offsets of occluded keypoints from visible keypoints and reconstructs the entire pose. The training dataset consisted of images collected from an actual cucumber greenhouse under diverse capturing angles, while the test dataset was constructed by imposing various occlusion conditions using leaf patches to emulate realistic field distribution. In addition, a similarity-based offset loss was introduced to encourage consistent relative-offset regression among keypoints. For practical deployment in real-world applications, a YOLO (you only look once)-based model was adopted to simultaneously detect cucumbers, estimate keypoints, and regress the relative offsets between keypoints within a single architecture. Comparative experiments demonstrated that the proposed method achieved higher accuracy than existing approaches across various occlusion scenarios. These results indicate that the approach is capable of compensating for missing pose components by reasoning from partially visible regions. With continued research, this method is expected to enhance the precision of vision pipelines for cucumber harvesting robots operating under real greenhouse conditions.

This paper attempts to introduce the development contents of a steering control system using the displacement difference ridge tracking method of a self-propelled onion harvester, a representative bulbous equipment. Currently, the self-propelled onion harvester is operated manually, and it is easy to automate because it performs repetitive and regular movements and operations in a regularized ridge area. Therefore, we studied a method that can control the steering so that it does not deviate from the path or invade the side ridge while following the center of the ridge being worked. The purpose of this study is to increase the work efficiency and convenience of the self-propelled onion harvester used in field farming.