Aiming at the surface defect inspection of carbon fiber reinforced composite, the differential and the direct measurement finite element simulation models of pulsed eddy current flaw detection were built. The principle of differential pulsed eddy current detection was analyzed and the sensitivity of defect detection was compared through two kinds of measurements. The validity of simulation results was demonstrated by experiments. The simulation and experimental results show that the pulsed eddy current detection method based on rectangular differential probe can effectively improve the sensitivity of surface defect detection of carbon fiber reinforced composite material.

Sugarcane stem node identification is the core technology required for the intelligence and mechanization of the sugarcane industry. However, detecting stem nodes quickly and accurately is still a significant challenge. In this paper, in order to solve this problem, a new algorithm combining YOLOv3 and traditional methods of computer vision is proposed, which can improve the identification rate during automated cutting. First, the input image is preprocessed, during which affine transformation is used to correct the posture of the sugarcane and a rotation matrix is established to obtain the region of interest of the sugarcane. Then, a dataset is built to train the YOLOv3 network model and the position of the stem nodes is initially determined using the YOLOv3 model. Finally, the position of the stem nodes is further located accurately. In this step, a new gradient operator is proposed to extract the edge of the image after YOLOv3 recognition. Then, a local threshold determination method is proposed, which is used to binarize the image after edge extraction. Finally, a localization algorithm for stem nodes is designed to accurately determine the number and location of the stem nodes. The experimental results show that the precision rate, recall rate, and harmonic mean of the stem node recognition algorithm in this paper are 99.68%, 100%, and 99.84%, respectively. Compared to the YOLOv3 network, the precision rate and the harmonic mean are improved by 2.28% and 1.13%, respectively. Compared to other methods introduced in this paper, this algorithm has the highest recognition rate.

Aiming to meet the growing need for automated harvesting, an automatic alignment method based on Euclidean clustering and K-means clustering is proposed to address issues of driver fatigue and inaccurate driving in manually operated corn harvesters. Initially, the corn field environment is scanned using LiDAR to obtain point cloud data, which are then subjected to pass-through filtering and statistical filtering to remove noise and non-corn contour points. Subsequently, Euclidean clustering and K-means clustering methods are applied to the filtered point cloud data. To validate the impact of Euclidean clustering on subsequent clustering, two separate treatments of the obtained point cloud data were conducted during experimental validation: the first used the K-means clustering algorithm directly, while the second involved performing Euclidean clustering followed by K-means clustering. The results demonstrate that the combined method of Euclidean clustering and K-means clustering achieved a success rate of 81.5%, representing a 26.5% improvement over traditional K-means clustering. Additionally, the Rand index increased by 0.575, while accuracy improved by 57% and recall increased by 61%.

Since Remote field eddy current (RFEC) detection technology is barely limited by the skin effect, it can realize the defect detection of large-thickness components. Whereas, the structure of the RFEC probe for the planar conductor is complicated, resulting in an oversized probe. This hinders the application and development of the RFEC testing technology. In this paper, finite element simulations and experimental verification are used to optimize the RFEC probe structure for flat conductors. The results have shown that the thickness of the magnetic shield is the dominant factor in achieving high performance of RFEC inspection of flat conductors. When inspecting both ferromagnetic and non-ferromagnetic flat conductors, cylindrical magnetic shields with appropriate thickness and appropriate excitation frequencies are preferred for improvement of RFEC testing.

To address the limitations of the feature extraction in LeGO-LOAM and the problems encountered in ground segmentation within indoor environments, this paper proposes an improved LeGO-LOAM algorithm that incorporates adaptive feature extraction and enhanced ground segmentation. The algorithm performs edge detection through normal vector estimation of points, determines the neighborhood size based on the point cloud density within a specified radius around the current point, and calculates smoothness and curvature. In the ground segmentation process, an uncertainty metric is introduced to emphasize the impact of height on ground point recognition as the horizontal distance increases. Subsequently, validation was performed using the KITTI dataset. The results show that compared with other SLAM algorithms, our algorithm achieves higher accuracy on the 00, 02, and 05 sequences of the KITTI dataset. Actual experiments were conducted in an indoor storage environment. The results indicate that the improved method proposed in this paper not only achieves a higher degree of matching with the real environment during map construction, but also realizes more stable poses along the y -axis, with the trough value increasing from −0.85 in LeGO-LOAM to −0.14.