Search Results (717)

The rotating parts of large and complex equipment are key components that ensure the normal operation of the equipment. Accurate fault diagnosis is crucial for the safe operation of these systems. To simultaneously extract both local and global valuable fault feature information from key components of complex equipment, this study proposes a fault diagnosis network model, named MultiDilatedFormer, which is based on the fusion of transformer and multi-head dilated convolution. The newly designed multi-head dilated convolution module is sequentially integrated into the transformer-encoder architecture, constructing a feature extraction module where the complementary advantages of both components enhance overall performance. Firstly, the sample is expanded into a two-dimensional feature map and then input into the newly designed feature extraction module. Finally, the diagnostic output is performed by the designed patch feature fusion module and classifier module. Additionally, interpretability research is conducted on the proposed model, aiming to understand the decision-making mechanism of the model through visual analysis of the entire decision process. The experimental results on three different datasets indicate that the proposed model achieved high accuracy in fault diagnosis with relatively short data windows. The highest accuracy reached 97.95%, which was up to 10.97% higher than other models. Furthermore, the feasibility of the model is also verified in the actual dataset of the rotating parts of the injection molding machine. The excellent performance of the model on different datasets demonstrates its effectiveness in extracting comprehensive fault feature information and also proves its great potential in practical industrial applications. Full article

Leaf diseases such as Mosaic disease and Black Rot are among the most common diseases affecting apple leaves, significantly reducing apple yield and quality. Detecting leaf diseases is crucial for the prevention and control of these conditions. In this paper, we propose incorporating rotated bounding boxes into deep learning-based detection, introducing the ProbIoU loss function to better quantify the difference between model predictions and real results in practice. Specifically, we integrated the Plant Village dataset with an on-site dataset of apple leaves from an orchard in Weifang City, Shandong Province, China. Additionally, data augmentation techniques were employed to expand the dataset and address the class imbalance issue. We utilized the EfficientNetV2 architecture with inverted residual structures (FusedMBConv and S-MBConv modules) in the backbone network to build sparse features using a top–down approach, minimizing information loss. The inclusion of the SimAM attention mechanism effectively captures both channel and spatial attention, expanding the receptive field and enhancing feature extraction. Furthermore, we introduced depth-wise separable convolution and the CAFM in the neck network to improve feature fusion capabilities. Finally, experimental results demonstrate that our model outperforms other detection models, achieving 93.3% [email protected], 88.7% Precision, and 89.6% Recall. This approach provides a highly effective solution for the early detection of apple leaf diseases, with the potential to significantly improve disease management in apple orchards. Full article

Maintaining the reliability of rotating machinery in industrial environments entails significant challenges. The objective of this paper is to develop a methodology that can accurately predict the condition of rotating machinery in order to facilitate the implementation of effective preventive maintenance strategies. This article proposed a novel RUL-centric data augmentation method, designated as DF-MDAGRU, for the purpose of predicting the remaining useful life (RUL) of bearings. This model is based on an encoder–decoder framework that integrates time–frequency domain feature enhancement with multidimensional dynamic attention gated recurrent units for feature extraction. This method enhances time–frequency domain features through the Discrete Wavelet Downsampling module (DWD) and Convolutional Fourier Residual Block (CFRB). This method employs a Multiscale Channel Attention Module (MS-CAM) and a Multiscale Convolutional Spatial Attention Mechanism (MSSAM) to extract channel and spatial feature information. Finally, the output predictions are processed through linear regression to achieve the final RUL estimation. Experimental results demonstrate that the proposed method outperforms other state-of-the-art approaches on the FEMETO-ST and XJTU datasets. Full article

Currently, multi-posture robots have complex grasping robotic manipulators with low power density, making it difficult to miniaturize and integrate. In this paper, a multi-posture grasping manipulator actuated by shape memory alloy with different functional modules is presented. It is composed of deflection, translation, rotation and grasping modules. Based on a D-H parameter method, the end motion trajectory model is established and the end motion space is drawn. Finally, the grasping experiment of a light circular object is carried out to verify the validity of the multi-posture grasping function of the multi-module combination manipulator, which provides a choice for future intelligent robot manipulators. Full article

Remote sensing technology has found extensive application in agriculture, providing critical data for analysis. The advancement of semantic segmentation models significantly enhances the utilization of point cloud data, offering innovative technical support for modern horticulture in nursery environments, particularly in the area of plant cultivation. Semantic segmentation results aid in obtaining tree components, like canopies and trunks, and detailed data on tree growth environments. However, obtaining precise semantic segmentation results from large-scale areas can be challenging due to the vast number of points involved. Therefore, this paper introduces an improved model aimed at achieving superior performance for large-scale points. The model incorporates direction angles between points to improve local feature extraction and ensure rotational invariance. It also uses geometric and relative distance information for better adjustment of different neighboring point features. An external attention module extracts global spatial features, and an upsampling feature adjustment strategy integrates features from the encoder and decoder. A specialized dataset was created from real nursery environments for experiments. Results show that the improved model surpasses several point-based models, achieving a Mean Intersection over Union ($mIoU$) of 87.18%. This enhances the precision of nursery environment analysis and supports the advancement of autonomous nursery managements. Full article

Diffractive multispectral optical imaging plays an essential role in optical sensing, which typically suffers from the image blurring problem caused by the spatially variant point spread function. Here, we propose a novel high-quality and efficient hybrid space calibrated 3D network “HSC3D” for spatially variant diffractive multispectral imaging that utilizes the 3D U-Net structure combined with space calibration modules of magnification and rotation effects to achieve high-accuracy eight-channel multispectral restoration. The algorithm combines the advantages of the space calibrated module and U-Net architecture with 3D convolutional layers to improve the image quality of diffractive multispectral imaging without the requirements of complex equipment modifications and large amounts of data. A diffractive multispectral imaging system is established by designing and manufacturing one diffractive lens and four refractive lenses, whose monochromatic aberration is carefully corrected to improve imaging quality. The mean peak signal-to-noise ratio and mean structural similarity index of the reconstructed multispectral images are improved by 3.33 dB and 0.08, respectively, presenting obviously improved image quality compared with a typical Unrolled Network algorithm. The new algorithm with high space calibrated ability and imaging quality has great application potential in diffraction lens spectroscopy and paves a new method for complex practical diffractive multispectral image sensing. Full article

Cover crops have gained attention due to their potential benefits for the soil and physiological performance of subsequent crops. This study aimed to evaluate the physiological and productive aspects of maize grown in succession to cover crops in northeastern Brazil. A randomized complete block design with four repetitions was employed, in which the treatments consisted of the following cover crops: sunn hemp, spectabilis, pigeon pea, Brachiaria sp., jack bean, millet, and fallow. Physiological aspects and production components of maize were evaluated at the tasseling (VT) and smooth grain (R3) phenological stages. Millet cover increased carotenoid content in maize leaves by up to 78% at R3. Maize grown after pigeon pea, millet, and Brachiaria sp. showed up to 42% greater CO₂ assimilation efficiency compared to jack bean. Carboxylation efficiency increased by up to 34% in maize grown after millet and Brachiaria sp., while water use efficiency improved by up to 76% in maize after sunn hemp and pigeon pea at R3. Sunn hemp, spectabilis, and jack bean reduced soil temperature by 2 °C compared to fallow. The highest maize yield was observed after jack bean, with an 8% increase over fallow. These findings demonstrate the benefits of incorporating cover crops into maize cultivation systems in the semi-arid region of Brazil. Full article

PVDF polymer dielectrics, renowned for their ultra-high-power density, ultra-fast response times, remarkable toughness, and lightweight properties, constitute the essential material foundation for the development of dielectric capacitors. Nevertheless, the low-energy density of these dielectrics presents a challenge to the advancement of dielectric capacitors. In this paper, in the process of preparing monolayer pure PVDF dielectric films by the solution casting method, a fixed-direction magnetic field and a rotating magnetic field were introduced in the horizontal direction, respectively, and this investigation explores the impact of magnetic field modulation on the polymer films’ free-volume pore size, grain size, phase structure, dielectric properties, and energy storage capabilities by altering the duration and orientation of the magnetic field’s influence. This study also discusses how microscopic alterations, particularly in the free-volume pore size, affect the macroscopic dielectric properties. Polymer films treated with a magnetic field of constant orientation for 3 min were obtained with the smallest free-volume hole size of 2.91 Å, the highest γ-phase contents of 54.8%, the smallest grain size of 68 Å, the largest electrical displacement of 10.64 and a very high discharge energy density of 12.68 J/cm³ (a 200% enhancement over pure PVDF). Full article

Due to the small size of vehicle targets, complex background environments, and the discrete scattering characteristics of high-resolution synthetic aperture radar (SAR) images, existing deep learning networks face challenges in extracting high-quality vehicle features from SAR images, which impacts vehicle localization accuracy. To address this issue, this paper proposes a vehicle localization method for SAR images based on feature reconstruction and aggregation with rotating boxes. Specifically, our method first employs a backbone network that integrates the space-channel reconfiguration module (SCRM), which contains spatial and channel attention mechanisms specifically designed for SAR images to extract features. The network then connects a progressive cross-fusion mechanism (PCFM) that effectively combines multi-view features from different feature layers, enhancing the information content of feature maps and improving feature representation quality. Finally, these features containing a large receptive field region and enhanced rich contextual information are input into a rotating box vehicle detection head, which effectively reduces false alarms and missed detections. Experiments on a complex scene SAR image vehicle dataset demonstrate that the proposed method significantly improves vehicle localization accuracy. Our method achieves state-of-the-art performance, which demonstrates the superiority and effectiveness of the proposed method. Full article

The extraction of shale gas via horizontal drilling presents considerable challenges, primarily due to the accumulation of cuttings within the annular space, resulting in increased friction, torque, and potential drilling complications. To address this issue, the study proposes an experimental setup aimed at simulating cuttings transport under various operational conditions, with a particular emphasis on gas wells. The methodology encompasses the modulation of the drilling fluid flow rate and the drill’s rotational speed to examine the transport velocity of cuttings. Furthermore, the study analyzes the impact of annular eccentricity on return volume, transport time, and cuttings bed height. Critical initiation velocities for cuttings across different motion modes were also determined, and theoretical calculations were compared with empirical data. The findings indicate that an increased flow rate of drilling fluid and higher rotation speed substantially improve the transport of cuttings, thereby minimizing bed formation, whereas increased eccentricity hinders this process. The results revealed that the theoretical model showed a greater overestimation of the start-up velocity for spherical particles, with average errors ranging from 15.50% to 17.56%. In contrast, the model exhibited better accuracy for non-spherical (flaky) particles, with errors between 8.63% and 9.61%. Under non-rotating conditions, the average error of the model was approximately 8.32%, while the introduction of drill tool rotation increased the average error to 11.94%. These results have the potential to optimize operational parameters in shale gas well drilling and may contribute to the development of specialized borehole purification tools. Full article

Continuum joints use structural elastic deformations to enable joint motion, and their intrinsic compliance and inherent mechanical robustness are envisioned for applications in which the robot, the human, and the environment need to be safe during interaction. In particular, the intrinsic compliance makes continuum joints a competitor to soft articulated joints, which require additional integrated spring elements. For soft articulated joints incorporating rigid and soft parts, natural motions have been investigated in robotics research to exploit this energy-efficient motion property for cyclic motions, e.g., locomotion. To the best of the author’s knowledge, there is no robotic system to date that utilizes the natural motion of a continuum joint under periodic excitation. In this paper, the resonant behavior of a tendon-driven continuum joint under periodic excitation of the torsional axis is experimentally investigated in a functional sense. In the experiments, periodic inputs are introduced on the joint side of a tendon driven continuum joint with four tendons. By modulating the pretension of the tendons, both the resonant frequency and the gain can be shifted, from 3 to 4.3 Hz and 2.8 to 1.4, respectively, in the present experimental setup. An application would be the rotation of a humanoid torso, where gait frequencies are synchronized with the resonant frequency of the continuum joint. Full article

A 3D range-modulator (RM), optimized for a single energy and a specific target shape, is a promising and viable solution for the ultra-fast dose delivery in particle therapy. The aim of this work was to investigate the impact of potential beam and modulator misalignments on the dose distribution. Moreover, the FLUKA Monte Carlo model, capable of simulating 3D RMs, was adjusted and validated for the 250 MeV single-energy proton irradiation from a Varian ProBeam system. A 3D RM was designed for a cube target shape rotated 45° around two axes using a Varian-internal research version of the Eclipse treatment planning software, and the resulting dose distribution was simulated in a water phantom. Deviations from the ideal alignment were introduced, and the dose distributions from the modified simulations were compared to the original unmodified one. Finally, the FLUKA model and the workflow were validated with base-line data measurements and dose measurements of the manufactured modulator prototype at the HollandPTC facility in Delft. The adjusted FLUKA model, optimized particularly in the scope of a single-energy FLASH irradiation with a PMMA pre-absorber, demonstrated very good agreement with the measured dose distribution resulting from the 3D RM. Dose deviations resulting from modulator-beam axis misalignments depend on the specific 3D RM and its shape, pin aspect ratio, rotation angle, rotation point, etc. A minor modulator shift was found to be more relevant for the distal dose distribution than for the spread-out Bragg Peak (SOBP) homogeneity. On the other hand, a modulator tilt (rotation away from the beam axis) substantially affected not only the depth dose profile, transforming a flat SOBP into a broad, Gaussian-like distribution with increasing rotation angle, but also shifted the lateral dose distribution considerably. This work strives to increase awareness and highlight potential pitfalls as the 3D RM method progresses from a purely research concept to pre-clinical studies and human trials. Ensuring that gantry rotation and the combined weight of RM, PMMA, and aperture do not introduce alignment issues is critical. Given all the other range and positioning uncertainties, etc., not related to the modulator, the RM must be aligned with an accuracy below 1° in order to preserve a clinically acceptable total uncertainty budget. Careful consideration of critical parameters like the pin aspect ratio and possibly a novel robust modulator geometry optimization are potential additional strategies to mitigate the impact of positioning on the resulting dose. Finally, even the rotated cube 3D modulator with high aspect ratio pin structures (~80 mm height to 3 mm pin base width) was found to be relatively robust against a slight misalignment of 0.5° rotation or a 1.5 mm shift in one dimension perpendicular to the beam axis. Given a reliable positioning and QA concept, the additional uncertainties introduced by the 3D RM can be successfully managed adopting the concept into the clinical routine. Full article

Although significant progress has been made in understanding the cortical correlates underlying balance control, these studies focused on a single task, limiting the ability to generalize the findings. Different balance tasks may elicit cortical activations in the same regions but show different levels of activation because of distinct underlying mechanisms. In this study, twenty young, neurotypical adults were instructed to maintain standing balance while the standing support surface was either translated or rotated. The differences in cortical activations in the frontocentral region between these two widely used tasks were examined using electroencephalography (EEG). Additionally, the study investigated whether transcranial magnetic stimulation could modulate these cortical activations during the platform translation task. Higher delta and lower alpha relative power were found over the frontocentral region during the platform translation task when compared to the platform rotation task, suggesting greater engagement of attentional and sensory integration resources for the former. Continuous theta burst stimulation over the supplementary motor area significantly reduced delta activity in the frontocentral region but did not alter alpha activity during the platform translation task. The results provide a direct comparison of neural activations between two commonly used balance tasks and are expected to lay a strong foundation for designing neurointerventions for balance improvements with effects generalizable across multiple balance scenarios. Full article

Enhancing the transparency of high-transmission-ratio linear actuators is crucial for improving the safety and capability of high-force robotic systems having physical contact with humans in unstructured environments. However, realizing such enhancement is challenging. A proposed solution for active body weight support systems involves employing a macro–mini linear actuator incorporating an electrorheological-fluid brake to connect a high-force unit with an agile, highly back-drivable unit. This paper introduces the use of an electromagnetic (EM) brake with reduced rotor inertia to address this challenge. The increased torque capacity of the EM brake enables integration with a low-gear-ratio linear transmission. The agile translation of the endpoint is propelled by a low-inertia motor (referred to as the “mini”) via a pulley-belt mechanism to achieve high transparency. The rotor of the EM brake is linked to the pulley. Damping modulation under high driving force is achieved through the adjustment of the brake torque relative to the rotational speed of the pulley. When the brake is engaged, it prevents any relative motion between the endpoint and the moving carrier. The endpoint is fully controlled by the ball screw of the high-force unit, referred to as the “macro”. A scaled prototype was constructed to experimentally characterize the damping force generated by the mini motor and the EM brake. The macro–mini linear actuator, equipped with an intrinsic failsafe feature, can be utilized for active body weight support systems that demand high antigravity force. Full article

In this paper, we propose a wireless sensor network for pavement health monitoring exploiting the Zigbee technology. Accelerometers are adopted to measure local accelerations linked to pavement vibrations, which are then converted into displacements by a signal processing algorithm. Each device consists of an on-board unit buried in the roadway and a roadside unit. The on-board unit comprises a microcontroller, an accelerometer and a Zigbee module that transfers acceleration data wirelessly to the roadside unit. The roadside unit consists of a Raspberry Pi, a Zigbee module and a USB Zigbee adapter. Laboratory tests were conducted using a vibration table and with three different accelerometers, to assess the system capability. A typical displacement signal from a five-axle truck was applied to the vibration table with two different displacement peaks, allowing for two different vehicle speeds. The prototyped system was then encapsulated in PVC packaging, deployed and tested in a real-life road situation with a fatigue carousel featuring rotating truck axles. The laboratory and on-road measurements show that displacements can be estimated with an accuracy equivalent to that of a reference sensor. Full article