Search

Background and purpose: Gastric-type endocervical adenocarcinoma (G-EAC) is a rare variant of endocervical adenocarcinoma, characterized by atypical clinical manifestations and elusive lesions. Due to these factors, G-EAC is prone to being missed or misdiagnosed, significantly impacting the prognosis. Lobular endocervical glandular hyperplasia (LEGH) and atypical LEGH (aLEGH) are considered to be precancerous lesions of G-EAC. These conditions also present overlapping clinical, pathologic and imaging manifestations, making it challenging to differentiate between them preoperatively. The purpose of this study was to investigate the correlation between magnetic resonance imaging (MRI) findings of cystic-solid lesions in the cervix and their underlying pathology in order to enhance the accuracy of distinguishing between LEGH and G-EAC, ultimately aiding in the early diagnosis and appropriate management of these conditions. Methods: Clinical, imaging and pathological data of 37 LEGH and 53 G-EAC patients who attended the Obstetrics and Gynecology Hospital of Fudan University from July 2016 to August 2023 were collected. Analysis was conducted using Pearson Chi-square χ2, Fisher’s exact tests and so on. Multivariate analyses were performed using logistic regression. Receiver operating characteristic (ROC) curves were used for performance evaluation. Results: In this study, differences in age, symptoms, extent, size, composition, degree of enhancement, cervical stromal ring, endometrium invasion, pelvic lymph nodes enlargement, and hydrohystera were statistically significant between the two groups (P

Conventional pressure-relief drilling with large diameters causes significant disturbance to shallow surrounding rocks in tunnels, leading to increased support costs. This study focuses on the variable-diameter pressure-relief drilling method and uses theoretical analysis and numerical simulation methods to analyze its pressure-relief mechanism, drilling damage shape, pressure-relief radius, drilling layout, drilling length, and other factors, while comparing the advantages and disadvantages of different drilling schemes. The results show that the use of small-diameter drilling in shallow surrounding rocks can reduce deformation and disturbance, while large-diameter drilling in deep coal seams can provide more space for energy release and achieve better pressure-relief effect. When the vertical stress is greater than the horizontal stress, the drilling damage is in a “butterfly” shape; therefore, the use of double-row three-flower arrangement has the best effect. The length of the small-diameter segment should not exceed the original stress, which is 3 m, and the total length should not exceed the stress concentration zone, which is 25 m. The variable-diameter pressure-relief drilling method can effectively reduce disturbance to shallow surrounding rocks and achieve pressure relief.

With the increasing complexity of mechanical equipment and diversification of deep learning models, vibration signals collected from such equipment are susceptible to noise interference. Moreover, traditional neural network models struggle to be effectively deployed in production environments with limited computational resources, severely impacting the accurate extraction and effective diagnosis of FK fault characteristics. In response to this challenge, this study proposes a fault diagnosis method for rolling bearings, integrating a lightweight ShuffleNetV2 network with variational mode decomposition (VMD) and the fast kurtogram (FK) algorithm. Initially, this paper introduces an enhanced FK method where the VMD algorithm is employed for data denoising, extracting FK post-denoising. These feature maps not only preserve critical signal information but also simplify data complexity. Subsequently, these feature maps are utilized to train and test the ShuffleNetV2 model, facilitating effective fault identification and classification. Ultimately, by conducting experimental comparisons with several mainstream lightweight network models, such as MobileNet and SqueezeNet, as well as traditional convolutional neural network models, this study validates the effectiveness of the proposed method in extracting fault characteristics from vibration signals, demonstrating superior diagnostic accuracy and computational efficiency. This provides a novel technical approach for health monitoring and fault diagnosis of industrial bearings and offers theoretical and experimental support for the deployment of lightweight networks in industrial applications. [ABSTRACT FROM AUTHOR]

A high-pressure hydraulically adjusted servomotor is an electromechanical–hydraulic integrated system centered on a servo valve that plays a crucial role in ensuring the safe and stable operation of steam turbines. To address the issues of difficult fault diagnoses and the low maintenance efficiency of adjusted hydraulic servomotors, this study proposes a model for detecting abnormalities of hydraulically adjusted servomotors. This model uses a multi-scale one-dimensional residual neural network (M1D_ResNet) for feature extraction and a genetic algorithm (GA)-optimized support vector data description (SVDD). Firstly, the multi-scale features of the vibration signals of the hydraulically adjusted servomotor were extracted and fused using one-dimensional convolutional blocks with three different scales to construct a multi-scale one-dimensional residual neural network binary classification model capable of recognizing normal and abnormal states. Then, this model was used as a feature extractor to create a feature set of normal data. Finally, an abnormal detection model for the hydraulically adjusted servomotor was constructed by optimizing the support vector data domain based on this feature set using a genetic algorithm. The proposed method was experimentally validated on a hydraulically adjusted servomotor dataset. The results showed that, compared with the traditional single-scale one-dimensional residual neural network, the multi-scale feature vectors fused by the multi-scale one-dimensional convolutional neural network contained richer state-sensitive information, effectively improving the performance of detecting abnormalities in the hydraulically adjusted servomotor. [ABSTRACT FROM AUTHOR]

The sound signals of hydraulic pumps contain abundant key information reflecting their internal mechanical states. In environments characterized by high temperatures or high-speed rotation, or where sensor deployment is challenging, acoustic sensors offer non-contact and flexible arrangement features. Therefore, this study aims to develop an intelligent fault diagnosis method for hydraulic pumps based on acoustic signals. Initially, the Adaptive Chirp Mode Decomposition (ACMD) method is employed to remove environmental noise from the acoustic signals, enhancing the feature signals. Subsequently, the Mel spectrum is extracted as the acoustic fingerprint features of various fault states of the hydraulic pump, and these features are used to train the MobileViT network, achieving accurate identification of the different fault modes. The results indicate that the proposed Mel-MobileViT model effectively identifies and classifies various faults in constant pressure variable pumps, outperforming other models. This study not only provides an efficient and reliable intelligent method for the fault diagnosis of critical industrial equipment such as hydraulic pumps, but also offers new perspectives on the application of deep learning in acoustic pattern analysis. [ABSTRACT FROM AUTHOR]

Hydraulic pumps are the core components that provide power for hydraulic transmission systems, which are widely used in aerospace, marine engineering, and mechanical engineering, and their failure affects the normal operation of the entire system. This paper takes a single axial piston pump as the research object and proposes a small-sample fault diagnosis method based on the model migration strategy for the situation in which only a small number of training samples are available for axial piston pump fault diagnosis. To achieve end-to-end fault diagnosis, a 1D Squeeze-and-Excitation Networks (1D-SENets) model was constructed based on a one-dimensional convolutional neural network and combined with the channel domain attention mechanism. The model was first pre-trained with sufficient labeled fault data from the source conditions, and then, based on the model migration strategy, some of the underlying network parameters were fixed, and a small amount of labeled fault data from the target conditions was used to fine-tune the rest of the parameters of the pre-trained model. In this paper, the proposed method was validated using an axial piston pump fault dataset, and the experimental results show that the method can effectively improve the overfitting problem in the small sample fault diagnosis of axial piston pumps and improve the recognition accuracy. [ABSTRACT FROM AUTHOR]

The natural dispersion of oil depends on the oil types, wave-mixing energy, and the temperature and salinity of water. Laboratory experiments were conducted to investigate the effects of these factors on oil dispersion. The results demonstrated that the increase in temperature significantly enhanced the oil dispersion efficiency, particularly for low-viscosity oils. At 30 °C, the dispersion efficiency is 2 times higher than that at 15 °C, while salinity has no significant effect on dispersion efficiency. Nonlinear fitting results revealed an exponential increase in dispersion efficiency with the energy dissipation rate. Furthermore, partial correlation analysis was employed to examine the effects of oil density, viscosity, and surface tension on dispersion efficiency. The results indicated a high correlation between density, viscosity, and dispersion efficiency (r = −0.801, r = −0.812), whereas the correlation coefficient of surface tension was low (r = −0.286). Based on these findings, linear and nonlinear regression models were established between dispersion efficiency and density and viscosity, enabling a rough estimation of oil spill dispersion efficiency under low sea state conditions. [ABSTRACT FROM AUTHOR]