采用轮廓特征匹配的红外-可见光视频自动配准

为了精确地配准近平面场景下的红外-可见光视频序列,本文提出了一种基于轮廓特征匹配的自动配准方法,通过迭代匹配目标轮廓特征来解决异源图像中配准特征的提取和匹配难题。首先,采用运动目标检测技术获取目标轮廓,并由曲率尺度空间(CSS)角点检测算法提取轮廓特征点。此后,建立全局形状上下文描述子和局部边缘方向直方图描述子描述特征,从而实现可靠的特征匹配。来自不同时刻的匹配点对被保存在一个基于高斯距离准则的特征匹配库中。最后,为了克服近平面场景中目标深度变化的影响,本文结合前景样本随机抽样策略计算配准矩阵的损失函数,完成对全局配准矩阵的更新。在LITIV数据库上对方法进行实验验证,结果表明本文方法的配准精度优于当前先进的对比方法,在9个测试视频上的平均重叠率误差仅为0.194,与对比方法相比下降了18.5%。基本满足了近平面场景下红外-可见光视频序列配准的精度要求,且具有较高的鲁棒性。     

Dynamic simulation of gas turbines via feature similarity-based transfer learning

Since gas turbine plays a key role in electricity power generating, the requirements on the safety and reliability of this classical thermal system are becoming gradually strict. With a large amount of renewable energy being integrated into the power grid, the request of deep peak load regulation for satisfying the varying demand of users and maintaining the stability of the whole power grid leads to more unstable working conditions of gas turbines. The startup, shutdown, and load fluctuation are dominating the operating condition of gas turbines. Hence simulating and analyzing the dynamic behavior of the engines under such instable working conditions are important in improving their design, operation, and maintenance. However, conventional dynamic simulation methods based on the physic differential equations is unable to tackle the uncertainty and noise when faced with variant real-world operations. Although data-driven simulating methods, to some extent, can mitigate the problem, it is impossible to perform simulations with insufficient data. To tackle the issue, a novel transfer learning framework is proposed to transfer the knowledge from the physics equation domain to the real-world application domain to compensate for the lack of data. A strong dynamic operating data set with steep slope signals is created based on physics equations and then a feature similarity-based learning model with an encoder and a decoder is built and trained to achieve feature adaptive knowledge transferring. The simulation accuracy is significantly increased by 24.6% and the predicting error reduced by 63.6% compared with the baseline model. Moreover, compared with the other classical transfer learning modes, the method proposed has the best simulating performance on field testing data set. Furthermore, the effect study on the hyper parameters indicates that the method proposed is able to adaptively balance the weight of learning knowledge from the physical theory domain or from the real-world operation domain.     

Effect of particle shape on methanol partial oxidation in a fixed bed using CFD reactor modeling

Particle shape is one of the most important parameters in the design and optimization of fixed-bed processes. To address the impact of particle shape on methanol partial oxidation to formaldehyde over molybdate catalyst, packings of spheres, cylinders, rings, and trilobes are numerically generated. The generated packings are used to carry out resolved particle Computational Fluid Dynamics (CFD) simulations under industrial conditions. Pressure drop, voidage and velocity profiles, radial heat transfer, and local and overall conversion and selectivity results are presented. Despite their lower particle surface area, lower particle effectiveness and more uneven flow distribution than trilobes, and lower overall heat transfer coefficient than cylinders, rings had the best conversion and selectivity due to their balance between the factors. Three longer tubes of rings, rings and cylinders, and rings and trilobes are simulated and show a small gain in selectivity for the rings and trilobes.     

Partial safety factors for laminated glass

Glass plies can be bonded together by polymeric interlayers to form laminated glass. Thanks to the capacity in finding alternative stress paths after partial breakage, it is commonly accepted that the more the layers are, the higher the safety level is. However, a negative aspect is that the tensile strength of glass carries a size effect in terms of surface area, which increases with lamination. Here we evaluate these competing factors by calibrating the partial safety factors to be used in semi-probabilistic (level-I) design, through comparison with probabilistic (level-III) methods in paradigmatic case-studies under wind, snow, and dead weight. Starting from a two-parameter Weibull distribution for glass strength, the “failure modes” approach determines the statistical distribution of strength for a multi-laminate as a function of the number of plies, which interferes with the statistics for actions. As a function of the target probability of failure for the assigned class of consequence, we introduce a new coefficient in the verification formula of level-I, to account for the effects of lamination with dependence upon the number of plies. We find that there is strong gain when passing from a monolith to a two-ply laminate, but the advantage fades by increasing the number of layers. Verification formulas of this type could avoid overconservative design.     

Effect of α phase morphology on fatigue crack growth behavior of Ti−5Al−5Mo−5V−1Cr−1Fe alloy

Taking a Ti−5Al−5Mo−5V−1Cr−1Fe alloy as exemplary case, the fatigue crack growth sensitivity and fracture features with various tailored α phase morphologies were thoroughly investigated using fatigue crack growth rate (FCGR) test, optical microscopy (OM) and scanning electron microscopy (SEM). The tailored microstructures by heat treatments include the fine and coarse secondary α phase, as well as the widmanstatten and basket weave features. The sample with coarse secondary α phase exhibits better comprehensive properties of good crack propagation resistance (with long Paris regime ranging from 15 to 60 MPa·m^1/2), high yield strength (1113 MPa) and ultimate strength (1150 MPa), and good elongation (11.6%). The good crack propagation resistance can be attributed to crack deflection, long secondary crack, and tortuous crack path induced by coarse secondary α phase.     

A process fault diagnosis method using multi-time scale dynamic feature extraction based on convolutional neural network

Unlike many other techniques used in process control, which are widely applied in practice and play significant roles, abnormal situation management (ASM) still relies heavily on human experience, not least because the problem of fault detection and diagnosis (FDD) has not been well addressed. In this paper, a process fault diagnosis method using multi-time scale dynamic feature extraction based on convolutional neural network (CNN) consisting of similarity measurement, variable ranking, and multi-time scale dynamic feature extraction is proposed. The CNN-based model containing the fixed multiple sampling (FMS) layer can extract dynamic characteristics of process data at different time scales. The benchmark Tennessee Eastman (TE) process is used to verify the performance of the proposed method.     

河流下浅埋深薄基岩煤层部分开采可行性分析

控制覆岩破坏高度是实现水体下安全开采的关键。针对“浅埋深、薄基岩、坚硬顶板”河流下压覆煤炭资源的问题，采用数值模拟的方法，计算了巷柱式和房柱式等部分开采的覆岩破坏高度，并从防水煤岩柱留设、岩梁极限跨度以及煤柱稳定性3个方面论述河流下部分开采的可行性。研究结果表明，部分开采能够很好地控制覆岩破坏高度，煤岩柱厚度基本满足留设防水安全煤岩柱要求；由于上覆基岩柱中存在厚度大于10 m的粗砂岩，在跨度小于8.53 m的情况下可以支撑上覆岩层；设计煤柱安全系数为1.28～1.81，均满足要求。采用采6 m、留6 m的巷柱（窄条带）式开采是最佳方案，面积采出率为50%，按总采出率45%计算，可解放河流压覆区域约52万t煤炭。     

基于VMD与时间序列分析的滚动轴承故障特征提取方法

为了在非线性、非平稳的滚动轴承故障振动信号中有效提取出敏感的故障特征,提出了基于变分模态分解(VMD)与时间序列分析相结合的特征提取方法。首先通过VMD将原始信号分解为不同预设尺度的本征模态分量(IMF),对各个IMF分量建立时间序列预测模型,通过叠加重构得到最终的预测模型,比较评价指标确定最优参数的选取。最后,通过仿真信号与滚动轴承实际故障数据分析,并与经验模式分解(EMD)进行对比,结果表明该方法能够有效的提取到故障特征频率。     

基于VMD瞬时能量与GA- RBF的滚动轴承故障诊断

针对滚动轴承早期故障的有效识别,提出了一种基于VMD瞬时能量与GA优化的RBF神经网络的滚动轴承故障诊断方法,可以有效对滚动故障做出诊断。首先,VMD将滚动轴承振动信号进行分解成合适数目的本证模态函数;其次,计算本证模态函数分量的瞬时能量并组成特征向量;最后,将特征向量输入到GA优化的RBF神经网络实现轴承故障识别。通过滚动轴承故障诊断实验对该方法进行验证。结果表明,该方法识别滚动轴承故障的准确率为96.43%,较默认参数的RBF神经网络和EEMD瞬时能量与GA-RBF神经网络有明显的提高,证明了所提方法的可行性。