Visual harvest maturity is a key visual phenotype for orchard management and harvesting decisions, yet chestnut fruits in natural orchards often exhibit weak color contrast, subtle texture variation, blurred boundaries, and frequent occlusion under complex illumination. This study addresses RGB-based visual harvest maturity recognition and proposes AHM-YOLO, an improved instance segmentation model built upon YOLOv11n-seg. The proposed model enhances maturity-related feature representation by strengthening color- and edge-sensitive cues, stabilizing spatial dependencies under occlusion and illumination variation, and improving cross-scale semantic consistency in dense orchard scenes. A chestnut dataset collected from a typical orchard in Shandong Province is annotated into three visual harvest maturity stages (unripe, semi-ripe, and ripe). To ensure reliable evaluation, the dataset is partitioned at the acquisition unit level, and all experiments are conducted using multi-seed repeated runs. Experimental results show that AHM-YOLO achieves 84.3% Mask mAP50 and 72.2% Mask mAP50–95, demonstrating consistent improvements over the baseline model in complex orchard environments.

The wear condition of a piston pin is a main factor in determining the operational continuity and life cycle of a diesel engine; identifying its vibration feature is of paramount importance in carrying out necessary maintenance in the early wear stage. As the dynamic vibration features are susceptible to environmental disturbance during operation, an effective signal processing method is necessary to improve the accuracy and fineness of the extracted features, which is essential to build a reliable and precise binary classifier model to identify piston pin wear based on the features. Aiming at the feature extraction requirements of anti-noise, accuracy and effectiveness, this paper proposes a piston pin wear feature extraction algorithm based on dynamic principal component analysis (DPCA) combined with variational mode decomposition (VMD) and singular value decomposition (SVD). An orthogonal sensor layout is applied to collect the vibration signal under normal and worn piston pin conditions, which proved effective in reducing environmental vibration disturbance. DPCA is utilized to extract dynamical vibration features by introducing time lag. Then, the dynamic principal component matrix is further decomposed by VMD to obtain intrinsic mode functions (IMFs) as finer features and is finally decomposed by SVD to compress the features, thus improving the classification efficiency based on the features. To validate the significance of the features extracted by the proposed method, a support vector machine (SVM) is employed to model binary classifiers to evaluate the classification performance trained by different features. A modeling dataset containing 80 samples (40 normal samples and 40 worn samples) is employed, and five-round cross-validation is adopted. For each round, two binary classifier models are trained by features extracted by the proposed method and the empirical mode decomposition (EMD)–auto regressive (AR) spectrum method, fast Fourier transform (FFT) and continuous wavelet transform (CWT), respectively; the classification precision, recall ratio, accuracy and F1 ratio are obtained on the testing set by contrasting the overall performances of the five-round cross-validation, and the proposed method is proved to be more effective in noise reduction and significant feature extraction, which is able to improve the accuracy and efficiency of binary classification for piston pin wear identification.