By substituting rock skeleton modulus expressions into Gassmann approximate fluid equation, we obtain a seismic porosity inversion equation. However, conventional rock skeleton models and their expressions are quite d...By substituting rock skeleton modulus expressions into Gassmann approximate fluid equation, we obtain a seismic porosity inversion equation. However, conventional rock skeleton models and their expressions are quite different from each other, resuling in different seismic porosity inversion equations, potentially leading to difficulties in correctly applying them and evaluating their results. In response to this, a uniform relation with two adjusting parameters suitable for all rock skeleton models is established from an analysis and comparison of various conventional rock skeleton models and their expressions including the Eshelby-Walsh, Pride, Geertsma, Nur, Keys-Xu, and Krief models. By giving the two adjusting parameters specific values, different rock skeleton models with specific physical characteristics can be generated. This allows us to select the most appropriate rock skeleton model based on geological and geophysical conditions, and to develop more wise seismic porosity inversion. As an example of using this method for hydrocarbon prediction and fluid identification, we apply this improved porosity inversion, associated with rock physical data and well log data, to the ZJ basin. Research shows that the existence of an abundant hydrocarbon reservoir is dependent on a moderate porosity range, which means we can use the results of seismic porosity inversion to identify oil reservoirs and dry or water-saturated reservoirs. The seismic inversion results are closely correspond to well log porosity curves in the ZJ area, indicating that the uniform relations and inversion methods proposed in this paper are reliable and effective.展开更多
In the process of traditional aircraft structure design, repetitive manual modeling of aircraft wing box parts is time consuming. Meanwhile, it＇s difficult to update associated models when product design changes. Aim...In the process of traditional aircraft structure design, repetitive manual modeling of aircraft wing box parts is time consuming. Meanwhile, it＇s difficult to update associated models when product design changes. Aiming at solving these problems, a method for rapid modeling and updating associated models was put forward. Based on skeleton model, combining with the technology of template re-use, it makes aircraft wing box rapid modeling and correct updating possible. The detailed implementation process of the method was given, and a certain aircraft wing box was taken as an instance to verify the feasibility and effectiveness of this method.展开更多
Lattice structures with excellent physical properties have attracted great research interest.In this paper,a novel volume parametric modeling method based on the skeleton model is proposed for the construction of thre...Lattice structures with excellent physical properties have attracted great research interest.In this paper,a novel volume parametric modeling method based on the skeleton model is proposed for the construction of threedimensional lattice structures.The skeleton model is divided into three types of nodes.And the corresponding algorithms are utilized to construct diverse types of volume parametric nodes.The unit-cell is assembled with distinct nodes according to the geometric features.The final lattice structure is created by the periodic arrangement of unit-cells.Several different types of volume parametric lattice structures are constructed to prove the stability and applicability of the proposed method.The quality is assessed in terms of the value of the Jacobian matrix.Moreover,the volume parametric lattice structures are tested with the isogeometric analysis to verify the feasibility of integration of modeling and simulation.展开更多
针对树木三维重构过程中面临的处理速度慢、重构精度低等问题,提出一种采用激光点云数据的单木骨架三维重构方法。首先,根据点云数据类型确定组合滤波方式,以去除离群点和地面点;其次,采用一种基于内部形态描述子(ISS)和相干点漂移算法(...针对树木三维重构过程中面临的处理速度慢、重构精度低等问题,提出一种采用激光点云数据的单木骨架三维重构方法。首先,根据点云数据类型确定组合滤波方式,以去除离群点和地面点;其次,采用一种基于内部形态描述子(ISS)和相干点漂移算法(CPD)的混合配准算法(Intrinsic Shape-Coherent Point Drift,IS-CPD),以获取单棵树木的完整点云数据;最后,采用Laplace收缩点集和拓扑细化相结合的方法提取骨架,并通过柱体构建枝干模型,实现骨架三维重构。试验结果表明,相比传统CPD算法,研究设计的配准方案精度和执行速度分别提高50%和95.8%,最终重构误差不超过2.48%。研究结果证明可有效地重构单棵树木的三维骨架,效果接近树木原型,为构建林木数字孪生环境和林业资源管理提供参考。展开更多
基金supported by the National Nature Science Foundation of China(Grant No.41174114)Important National Science and Technology Specific Projects(Grant No.2011ZX05025-005-010)
文摘By substituting rock skeleton modulus expressions into Gassmann approximate fluid equation, we obtain a seismic porosity inversion equation. However, conventional rock skeleton models and their expressions are quite different from each other, resuling in different seismic porosity inversion equations, potentially leading to difficulties in correctly applying them and evaluating their results. In response to this, a uniform relation with two adjusting parameters suitable for all rock skeleton models is established from an analysis and comparison of various conventional rock skeleton models and their expressions including the Eshelby-Walsh, Pride, Geertsma, Nur, Keys-Xu, and Krief models. By giving the two adjusting parameters specific values, different rock skeleton models with specific physical characteristics can be generated. This allows us to select the most appropriate rock skeleton model based on geological and geophysical conditions, and to develop more wise seismic porosity inversion. As an example of using this method for hydrocarbon prediction and fluid identification, we apply this improved porosity inversion, associated with rock physical data and well log data, to the ZJ basin. Research shows that the existence of an abundant hydrocarbon reservoir is dependent on a moderate porosity range, which means we can use the results of seismic porosity inversion to identify oil reservoirs and dry or water-saturated reservoirs. The seismic inversion results are closely correspond to well log porosity curves in the ZJ area, indicating that the uniform relations and inversion methods proposed in this paper are reliable and effective.
文摘In the process of traditional aircraft structure design, repetitive manual modeling of aircraft wing box parts is time consuming. Meanwhile, it＇s difficult to update associated models when product design changes. Aiming at solving these problems, a method for rapid modeling and updating associated models was put forward. Based on skeleton model, combining with the technology of template re-use, it makes aircraft wing box rapid modeling and correct updating possible. The detailed implementation process of the method was given, and a certain aircraft wing box was taken as an instance to verify the feasibility and effectiveness of this method.
基金supported by the National Nature Science Foundation of China under Grant No.52075340.
文摘Lattice structures with excellent physical properties have attracted great research interest.In this paper,a novel volume parametric modeling method based on the skeleton model is proposed for the construction of threedimensional lattice structures.The skeleton model is divided into three types of nodes.And the corresponding algorithms are utilized to construct diverse types of volume parametric nodes.The unit-cell is assembled with distinct nodes according to the geometric features.The final lattice structure is created by the periodic arrangement of unit-cells.Several different types of volume parametric lattice structures are constructed to prove the stability and applicability of the proposed method.The quality is assessed in terms of the value of the Jacobian matrix.Moreover,the volume parametric lattice structures are tested with the isogeometric analysis to verify the feasibility of integration of modeling and simulation.
文摘识别非驾驶行为是提高驾驶安全性的重要手段之一。目前基于骨架序列和图像的融合识别方法具有计算量大和特征融合困难的问题。针对上述问题,本文提出一种基于多尺度骨架图和局部视觉上下文融合的驾驶员行为识别模型(skeleton-image based behavior recognition network,SIBBR-Net)。SIBBR-Net通过基于多尺度图的图卷积网络和基于局部视觉及注意力机制的卷积神经网络,充分提取运动和外观特征,较好地平衡了模型表征能力和计算量间的关系。基于手部运动的特征双向引导学习策略、自适应特征融合模块和静态特征空间上的辅助损失,使运动和外观特征间互相引导更新并实现自适应融合。最终在Drive&Act数据集进行算法测试,SIBBR-Net在动态标签和静态标签条件下的平均正确率分别为61.78%和80.42%,每秒浮点运算次数为25.92G,较最优方法降低了76.96%。
文摘针对树木三维重构过程中面临的处理速度慢、重构精度低等问题,提出一种采用激光点云数据的单木骨架三维重构方法。首先,根据点云数据类型确定组合滤波方式,以去除离群点和地面点;其次,采用一种基于内部形态描述子(ISS)和相干点漂移算法(CPD)的混合配准算法(Intrinsic Shape-Coherent Point Drift,IS-CPD),以获取单棵树木的完整点云数据;最后,采用Laplace收缩点集和拓扑细化相结合的方法提取骨架,并通过柱体构建枝干模型,实现骨架三维重构。试验结果表明,相比传统CPD算法,研究设计的配准方案精度和执行速度分别提高50%和95.8%,最终重构误差不超过2.48%。研究结果证明可有效地重构单棵树木的三维骨架,效果接近树木原型,为构建林木数字孪生环境和林业资源管理提供参考。
