This article proposes a sensorless control method for the permanent magnet synchronous motors (PMSM) combining the fifth-order generalized integral flux observer (FOGIFO) and the extended state observer-based phase-locked loop (ESO_PLL). First, due to various nonideal factors, including parameter mismatch, sampling errors, and inverter nonlinearity, the rotor flux estimated by traditional flux observers suffers the dc offset and harmonics. To solve these issues, a FOGIFO incorporating a frequency-locked loop (FLL) is proposed, and the FLL ensures that FOGIFO dynamically tracks the frequency of the back electromotive force signal. This guarantees superior integral characteristics at the central frequency point. Meanwhile, the FOGIFO pole distribution is optimized to enhance the harmonic suppression performance. Subsequently, the analysis of the conventional phase-locked loop is carried out in terms of the error transfer function. The ESO_PLL is used for rotor position and speed observation, which significantly improves the dynamic tracking performance. Moreover, since the proposed method is based on a voltage model in stationary coordinate system, it is applicable to both surface and interior PMSM, and simulations and experiments have verified its effectiveness.

The residue hydrotreating process plays a significant role in the petroleum refining industry. In this process, modeling and simulation have critical importance for process development, control, and optimization. However, there is a lack of relevant reports of plant scale due to complexity in characterizing feedstock and determining reaction mechanisms. In this paper, reaction and fractionation models are constructed and simulated for a real-life industrial residue hydrotreating process based on Aspen HYSYS/Refining. Considering the heavier and inferior residue, analytical characterization is carried out for feedstock characterization based on laboratory analysis data. Moreover, two reactor models with parallel structures are proposed to implement the intricate reaction network, namely, a hydrocracker reactor and a plug flow reactor. The former simulates lighter petroleum hydrotreating based on the built-in reaction network. The latter emulates the conversion of a peculiar, heavier resin and asphaltene, using a six-lump model, which expands the scope of the feedstock and improves the accuracy of the model. To obtain a realistic simulation of fractionation, the database-based delumping method is adopted to model it with proper pseudo-components. The simulation results, including temperature rise, hydrogen consumption, temperature distribution, product yield, product properties, indicate that the model is capable of reflecting the realistic process accurately.

Clusters of dead trees are forest fires-prone. To maintain ecological balance and realize its protection, timely detection of dead trees in forest remote sensing images using existing computer vision methods is of great significance. Remote sensing images captured by Unmanned aerial vehicles (UAVs) typically have several issues, e.g., mixed distribution of adjacent but different tree classes, interference of redundant information, and high differences in scales of dead tree clusters, making the detection of dead tree clusters much more challenging. Therefore, based on the Multipath dense composite network (MDCN), an object detection method called LLAM-MDCNet is proposed in this paper. First, a feature extraction network called Multipath dense composite network is designed. The network’s multipath structure can substantially increase the extraction of underlying and semantic features to enhance its extraction capability for rich-information regions. Following that, in the row, column, and diagonal directions, the Longitude Latitude Attention Mechanism (LLAM) is presented and incorporated into the feature extraction network. The multi-directional LLAM facilitates the suppression of irrelevant and redundant information and improves the representation of high-level semantic feature information. Lastly, an AugFPN is employed for down-sampling, yielding a more comprehensive representation of image features with the combination of low-level texture features and high-level semantic information. Consequently, the network’s detection effect for dead tree cluster targets with high-scale differences is improved. Furthermore, we make the collected high-quality aerial dead tree cluster dataset containing 19,517 images shot by drones publicly available for other researchers to improve the work in this paper. Our proposed method achieved 87.25% mAP with an FPS of 66 on our dataset, demonstrating the effectiveness of the LLAM-MDCNet for detecting dead tree cluster targets in forest remote sensing images.

Tomato leaf disease control in the field of smart agriculture urgently requires attention and reinforcement. This paper proposes a method called LAFANet for image-text retrieval, which integrates image and text information for joint analysis of multimodal data, helping agricultural practitioners to provide more comprehensive and in-depth diagnostic evidence to ensure the quality and yield of tomatoes. First, we focus on six common tomato leaf disease images and text descriptions, creating a Tomato Leaf Disease Image-Text Retrieval Dataset (TLDITRD), introducing image-text retrieval into the field of tomato leaf disease retrieval. Then, utilizing ViT and BERT models, we extract detailed image features and sequences of textual features, incorporating contextual information from image-text pairs. To address errors in image-text retrieval caused by complex backgrounds, we propose Learnable Fusion Attention (LFA) to amplify the fusion of textual and image features, thereby extracting substantial semantic insights from both modalities. To delve further into the semantic connections across various modalities, we propose a False Negative Elimination-Adversarial Negative Selection (FNE-ANS) approach. This method aims to identify adversarial negative instances that specifically target false negatives within the triplet function, thereby imposing constraints on the model. To bolster the model’s capacity for generalization and precision, we propose Adversarial Regularization (AR). This approach involves incorporating adversarial perturbations during model training, thereby fortifying its resilience and adaptability to slight variations in input data. Experimental results show that, compared with existing ultramodern models, LAFANet outperformed existing models on TLDITRD dataset, with top1, top5, and top10 reaching 83.3% and 90.0%, and top1, top5, and top10 reaching 80.3%, 93.7%, and 96.3%. LAFANet offers fresh technical backing and algorithmic insights for the retrieval of tomato leaf disease through image-text correlation.

The automatic recognition of CT (Computed Tomography) images of liver cancer is important for the diagnosis and treatment of early liver cancer. However, there are problems such as single model structure and loss of pooling layer information when using a traditional convolutional neural network to recognize CT images of liver cancer. Therefore, this paper proposes an efficient method for liver CT image recognition based on the capsule network (CapsNet). Firstly, the liver CT images are preprocessed, and in the process of image denoising, the traditional non-local mean (NLM) denoising algorithm is optimized with a superpixel segmentation algorithm to better protect the information of image edges. After that, CapsNet was used for image recognition for liver CT images. The experimental results show that the average recognition rate of liver CT images reaches 92.9% when CapsNet is used, which is 5.3% higher than the traditional CNN model, indicating that CapsNet has better recognition accuracy for liver CT images.

Deep reinforcement learning-based object detection approaches center around a pivotal concept: hierarchically scaling image segments that harbor more intricate details. Compared with the traditional object detection approaches, this approach significantly curbs the quantity of region proposals. This reduction holds paramount significance in curtailing the computational overhead. However, common deep reinforcement learning-based approaches suffer from a significant defect in terms of precision. This issue arises from inadequacies in representing image states appropriately and the unstable learning ability exhibited by the agent. To address these issues, we present the LHAR-RLD. First, we design the Low-dimensional RepVGG(LDR) feature extractor to reduce memory consumption and to reduce the difficulty of fitting downstream networks. Second, we propose the Hybrid DQN(HDQN) to enhance the agent’s ability to determine the state-action of images in complex environments. Then, the Adaptive Dynamic Reward Function(ADR) is crafted to dynamically adjust the reward based on shifts within the agent’s exploration environment. Finally, the ROI Align-based bounding box regression network (RABRNet) is proposed, which aims at further regressing the localization results of reinforcement learning to improve the detection precision. Our method accomplishes 74.4% mAP on the VOC2007, 76.2% mAP on the COCO2017, 75.2% Precision on the SF dataset, with 1.43G FLOPs. The precision outperforms the advanced deep reinforcement learning approaches and the computational cost is far less than them and mainstream object detection methods. This method facilitates highly accurate object localization with minimal computational demands, which means it has notable applications on resource-constrained devices.