Servo motors play an important role in automation equipment and have been used in several manufacturing fields. However, the commonly used control methods need their parameters to be set manually, which is rather difficult, and this means that these methods generally cannot adapt to changes in operation conditions. Therefore, in this study, we propose an intelligent control method for a servo motor based on reinforcement learning and that can train an agent to produce a duty cycle according to the servo error between the current state and the target speed or torque. The proposed method can adjust its control strategy online to reduce the servo error caused by a change in operation conditions. We verify its performance on three different servo motors and control tasks. The experimental results show that the proposed method can achieve smaller servo errors than others in most cases.

With the growing popularity of unmanned aerial vehicles (UAVs), their improper use is significantly disrupting society. Individuals and organizations have been continuously researching methods for detecting UAVs. However, most existing detection methods fail to account for the impact of similar flying objects, leading to weak anti-interference capabilities. In other words, when such objects appear in the image, the detector may mistakenly identify them as UAVs. Therefore, this study aims to enhance the anti-interference ability of UAV detectors by constructing an anti-interference dataset comprising 5062 images. In addition to UAVs, this dataset also contains three other types of flying objects that are visually similar to the UAV targets: planes, helicopters, and birds. This dataset can be used in model training to help detectors distinguish UAVs from these nontarget objects and thereby improve their anti-interference capabilities. Furthermore, we propose an anti-interference UAV detection method based on YOLOv9-C in which the dot distance is used as an evaluation index to assign positive and negative samples. This results in an increased number of positive samples, improving detector performance in the case of small targets. The comparison of experimental results shows that the developed method has better anti-interference performance than other algorithms. The detection method and dataset used to test the anti-interference capabilities in this study are expected to assist in the development and validation of related research methods.

With the development of artificial intelligence, reinforcement-learning-based intelligent control algorithms, which generally learn control strategies through trial and error, have received more attention in the automation equipment and manufacturing fields. Although they can intelligently adjust their control strategy without the need for human effort, the most relevant algorithms for servo motors only consider the overall performance, while ignoring the risks in special cases. Therefore, overcurrent problems are often triggered in the training process of the reinforcement learning agent. This can damage the motors’ service life and even burn it out directly. To solve this problem, in this study we propose a risk-sensitive intelligent control algorithm based on value distribution, which uses the quantile function to model the probability distribution of cumulative discount returns and employs the condition value at risk to measure the loss caused by overcurrent. The agent can accordingly learn a control strategy that is more sensitive to environmental restrictions and avoid the overcurrent problem. The performance is verified on three different servo motors with six control tasks, and the experimental results show that the proposed method can achieve fewer overcurrent occurrences than others in most cases.

The deepening of human fatigue will lead to the reduction of exercise ability and work efficiency, the increase of errors and accidents, and even the occurrence of organic diseases. Obviously, it is significant to understand the impact of human fatigue on the health, safe production and safe work of different people. At present, fatigue detection is mostly carried out through EEG and EMG signals. These methods usually have the disadvantages of contact and non-realtime. In response to the aforementioned issues in the process of human fatigue detection, this article effectively applies the visual image analysis method of spectrograms to human fatigue detection and proposes a cross-modal human fatigue detection method based on speech spectral image recognition. First, Mel spectrograms of speech segments in the corpus are extracted, and a fatigue spectrogram data set is established. A deep learning model is established through convolutional neural network (CNN) and extreme learning machine (ELM) for spectral image recognition and fatigue detection. CNN is used to extract features from the input image. The feature mapping will eventually be encoded into a one-dimensional vector and sent to ELM for classification. The experimental results indicate that the speech spectrum image features extracted by this method have better fatigue characterization ability than traditional acoustic features.

Crop leaf diseases cause 10–40% annual yield losses, yet timely field diagnosis remains difficult. Vision-language models (VLMs) lift recognition accuracy with rich textual descriptions, but multimodal pipelines are too slow for real-time field use because they require text processing at inference. We present MTL-AWL, a framework built on a training–inference asymmetry: VLM text serves as privileged training-time supervision, and two coupled mechanisms—one retaining VLM semantics in the image encoder and one exploiting them—enable image-only deployment at multimodal accuracy. A modal-dropout strategy ($p=0.6$) intermittently masks the VLM text sequence during training, forcing the image encoder to retain cross-modal representations independently. An adaptive multi-task loss jointly optimizes InfoNCE contrastive alignment, attention diversity, and modality consistency under learnable softmax weights, consistently converging to a dominant contrastive weight (55% on soybean, 68% on PlantDoc)—identifying cross-modal alignment as the primary mechanism of VLM knowledge transfer. At inference, the model reaches 818 FPS (3.7× faster than multimodal methods) at only 0.41% accuracy cost, attaining 99.30%/98.89% (multimodal/image-only) on soybean and 72.65%/68.80% on PlantDoc—compact enough for real-time, offline field screening.

Sorting defective cocoons is a critical procedure in the silk reeling industry to ensure the quality of raw silk products. Currently, this process relies heavily on manual inspection, which is labor-intensive, subjective, and inefficient. While automated sorting based on machine vision offers a promising alternative, existing object detection algorithms struggle to balance accuracy and computational complexity, particularly when detecting tiny surface defects or distinguishing morphologically similar cocoons in dense scenarios. To address these challenges, this paper proposes an efficient silkworm cocoon defect detection model named LMD-YOLO, based on the YOLOv10 architecture. In this model, we introduce three key improvements to enhance feature extraction and multi-scale perception. First, we integrate a Large Separable Kernel Attention (LSKA) module into the C2f structure (C2f-LSKA) of the backbone. This design decomposes large kernels to capture global shape features with minimal computational cost, effectively distinguishing double cocoons from normal ones. Second, we replace standard upsampling with a DySample module in the neck, which utilizes dynamic point sampling to recover fine-grained texture details of tiny defects like surface stains. Third, a Multi-Scale Dilated Attention (MSDA) mechanism is embedded before the detection heads to aggregate semantic information across different scales, improving robustness against background interference. YOLOv10 was selected as the baseline due to its NMS-free characteristic, which mitigates the latency caused by post-processing in high-speed sorting tasks. Evaluations on a self-constructed multi-category dataset indicate that LMD-YOLO surpasses established detectors, including YOLOv8n and Faster R-CNN. Relative to the YOLOv10n baseline, our method improves mAP@0.5 by 3.11%, achieving 94.46%. Notably, Precision and Recall are increased by 3.50% and 2.97%, reaching 89.98% and 93.61%, respectively. With a compact size of 2.68 M parameters and an inference speed of 115 FPS, the proposed model offers a practical trade-off between accuracy and latency for real-time cocoon defect detection.