20MnCr5圆棒锯切困难原因分析

某厂在锯切20MnCr5圆棒过程中锯条容易断裂，采用光学显微镜(OM)和扫描电子显微镜(SEM)等观察分析手段，对锯条容易断裂的原因进行分析。分析结果表明：锯条断裂的原因为加工20MnCr5过程中粘刀崩齿。针对此类加工缺陷，提出了相应的改进措施。     

WavNet — Visual saliency detection using Discrete Wavelet Convolutional Neural Network

In the recent advancements in image and video analysis, the detection of salient regions in the image becomes the initial step. This plays a crucial role in deciding the performance of such algorithms. In this work, a Multi-Resolution Feature Extraction (MRFE) technique that makes use of Discrete Wavelet Convolutional Neural Network (DWCNN) for generating features is employed. An Enhanced Feature Extraction (EFE) module extracts additional features from the high level features of the DWCNN, which are used to frame both channel as well as spatial attention models for yielding contextual attention maps. A new hybrid loss function is also proposed, which is a combination of Balanced Cross Entropy (BCE) loss and Edge based Structural Similarity (ESSIM) loss that effectively identifies and segments the salient regions with clear boundaries. The method is tested exhaustively with five different benchmark datasets and is proved superior to the existing state-of-the-art methods with a minimum Mean Absolute error (MAE) of 0.03 and F-measure of 0.956.     

Impacts of slip and mass transpiration on Newtonian liquid flow over a porous stretching sheet

This article focuses on analytic solutions for Newtonian fluid flow with slip and mass transpiration on a porous stretching sheet using the differential transform method and Pade approximants of an exceptionally nonlinear differential equation. The impacts of different parameters including mass transpiration (suction/injection), Navier's slip, and Darcy number parameters on the velocity of the liquid and tangential stress are discussed. A comprehensive comparison of our results with the previous one in the literature is made, and the results showed good agreement. An investigation is conducted of a combination of magnetic liquids that are conceivably pertinent for wound medicines, skin repair, and astute coatings for natural gadgets. It is found that there is a decrease in the velocity profiles and the boundary layer thickness for the case of suction.     

Deterministic and probabilistic ship pitch prediction using a multi-predictor integration model based on hybrid data preprocessing,reinforcement learning and improved QRNN

The deterministic and probabilistic prediction of ship motion is important for safe navigation and stable real-time operational control of ships at sea. However, the volatility and randomness of ship motion, the non-adaptive nature of single predictors and the poor coverage of quantile regression pose serious challenges to uncertainty prediction, making research in this field limited. In this paper, a multi-predictor integration model based on hybrid data preprocessing, reinforcement learning and improved quantile regression neural network (QRNN) is proposed to explore the deterministic and probabilistic prediction of ship pitch motion. To validate the performance of the proposed multi-predictor integrated prediction model, an experimental study is conducted with three sets of actual ship longitudinal motions during sea trials in the South China Sea. The experimental results indicate that the root mean square errors (RMSEs) of the proposed model of deterministic prediction are 0.0254°, 0.0359°, and 0.0188°, respectively. Taking series #2 as an example, the prediction interval coverage probabilities (PICPs) of the proposed model of probability predictions at 90%, 95%, and 99% confidence levels (CLs) are 0.9400, 0.9800, and 1.0000, respectively. This study signifies that the proposed model can provide trusted deterministic predictions and can effectively quantify the uncertainty of ship pitch motion, which has the potential to provide practical support for ship early warning systems.     

Recent progress on the discrete element method simulations for powder transport systems: A review

Powder transport systems are ubiquitous in various industries, where they can encounter single powder flow, two-phase flow with solids carried by gas or liquid, and gas–solid–liquid three-phase flow. System geometry, operating conditions, and particle properties have significant impacts on the flow behavior, making it difficult to achieve good transportation of granular materials. Compared to experimental trials and theoretical studies, the numerical approach provides unparalleled advantages over the investigation and prediction of detailed flow behavior, of which the discrete element method (DEM) can precisely capture complex particle-scale information and attract a plethora of research interests. This is the first study to review recent progress in the DEM and coupled DEM with computational fluid dynamics for extensive powder transport systems, including single-particle, gas–solid/solid–liquid, and gas–solid–liquid flows. Some important aspects (i.e., powder electrification during pneumatic conveying, pipe bend erosion, non-spherical particle transport) that have not been well summarized previously are given special attention, as is the application in some new-rising fields (ocean mining, hydraulic fracturing, and gas/oil production). Studies involving important large-scale computation methods, such as the coarse grained DEM, graphical processing unit-based technique, and periodic boundary condition, are also introduced to provide insight for industrial application. This review study conducts a comprehensive survey of the DEM studies in powder transport systems.     

A new signal processing-based islanding detection method using pyramidal algorithm with undecimated wavelet transform for distributed generators of hydrogen energy

Machine learning-based fault detection methods are frequently combined with wavelet transform (WT) to detect an unintentional islanding condition. In contrast to this condition, these methods have long detection and computation time. Thus, selecting a useful signal processing-based approach is required for reliable islanding detection, especially in real-time applications. This paper presents a new modified signal processing-based islanding detection method (IDM) for real-time applications of hydrogen energy-based distributed generators. In the study, a new IDM using a modified pyramidal algorithm approach with an undecimated wavelet transform (UWT) is presented. The proposed method is performed with different grid conditions with the presence of electric noise in real-time. Experimental results show that oscillations in the acquired signal can be reduced by the UWT, and noise sensitivity is lower than other WT-based methods. The non-detection zone is zero and the maximum detection and computational time is also 75 ms at a close power match.     

Learn decision trees with deep visual primitives

In this paper, we strive to propose a self-interpretable framework, termed PrimitiveTree, that incorporates deep visual primitives condensed from deep features with a conventional decision tree, bridging the gap between deep features extracted from deep neural networks (DNNs) and trees’ transparent decision-making processes. Specifically, we utilize a codebook, which embeds the continuous deep features into a finite discrete space (deep visual primitives) to distill the most common semantic information. The decision tree adopts the spatial location information and the mapped primitives to present the decision-making process of the deep features in a tree hierarchy. Moreover, the trained interpretable PrimitiveTree can inversely explain the constituents of the deep features, highlighting the most critical and semantic-rich image patches attributing to the final predictions of the given DNN. Extensive experiments and visualization results validate the effectiveness and interpretability of our method.     

No-reference quality assessment of dynamic sports videos based on a spatiotemporal motion model

This paper proposes an approach to improve the performance of no-reference video quality assessment for sports videos with dynamic motion scenes using an efficient spatiotemporal model. In the proposed method, we divide the video sequences into video blocks and apply a 3D shearlet transform that can efficiently extract primary spatiotemporal features to capture dynamic natural motion scene statistics from the incoming video blocks. The concatenation of a deep residual bidirectional gated recurrent neural network and logistic regression is used to learn the spatiotemporal correlation more robustly and predict the perceptual quality score. In addition, conditional video block-wise constraints are incorporated into the objective function to improve quality estimation performance for the entire video. The experimental results show that the proposed method extracts spatiotemporal motion information more effectively and predicts the video quality with higher accuracy than the conventional no-reference video quality assessment methods.     

Effect of Operating Parameters on Gas‐Solid Hydrodynamics and Heat Transfer in a Spouted Bed

Through a combined computational fluid dynamics and discrete element method approach, the effect of the operating parameters on the hydrodynamics and heat‐transfer properties of gas‐solid two‐phase flows in a spouted bed are extensively investigated. Considering the high velocity in the fountain region, gas turbulence is resolved by employing the large‐eddy simulation. The rolling friction model is adopted for more precise predictions of solid behavior near the wall. Subsequently, the gas‐solid flow patterns, gas‐solid velocities, and temperature evolution are investigated. Moreover, different operating conditions and geometry configurations are evaluated with respect to heat‐transfer performance. The results provide a fundamental understanding of heat‐transfer mechanisms in spouted beds.     

Realizing fragment spawning and fragment growth in the parallelized Discrete Element Method (DEM) during modelling of comminution

The particle based Discrete Element Method (DEM) can be applied to examine comminution processes. In this study, a DEM framework has been extended to model particle breakage without mass loss. After a breakage event occurs, spherical particles, as often considered in the DEM, are replaced by size reduced spherical fragments. During the following time steps, the fragments grow to their desired sizes, so that the mass loss can be counterbalanced. Previously defined overlaps with adjacent unbroken and broken particles (fragments) as well as walls are allowed. The breakage model has been realized in a parallelized DEM framework because comminution processes are often attributed to large numbers of particles and by parallelization the computational time can be reduced efficiently. An oedometer (one-dimensional compression in axial direction of a confined particle bed) has been modelled to investigate the parallelization efficiency and the influence of the permitted overlaps during the growth process on the growth duration. A simplified roller mill has been considered to examine the applicability of the breakage procedure considering parallelization. The results show that parallelization reduces computational time considerably. The breakage procedure is suitable to model comminution processes involving even densely packed particle systems and is superior to existing approaches.