For the data processing of the Rapid Prototyping Manufacturing, Boolean operation can offer a versatile tool for editing or modifying the STL model, adding the artificial construction, and creating the complex assista...For the data processing of the Rapid Prototyping Manufacturing, Boolean operation can offer a versatile tool for editing or modifying the STL model, adding the artificial construction, and creating the complex assistant support structure to meet the special technical requests. The topological structure of STL models was built firstly in order to obtain the neighborhood relationship among the triangular facets. The intersection test between every edge of one solid and every facet of another solid was taken to get the intersection points. According to the matching relationship of the triangle index recorded in the data structure of the intersection points, the intersection segments array and the intersection loop were traced out. Each intersected triangle was subdivided by the Constrained Delaunay Triangulations. The intersected surfaces were divided into several surface patches along the intersection loops. The inclusion prediction between the surface patch and the other solid was taken by testing whether the candidate point was inside or outside the solid region of the slice. Detecting the loops for determination of the valid intersection lines greatly increases the efficiency and the reliability of the process.展开更多
A kind of 3D color graphics display system for the STL model is developed by calling the functions from Open GL graphic library through VC++6.0 under the Windows environment in this paper. The STL model is a high qual...A kind of 3D color graphics display system for the STL model is developed by calling the functions from Open GL graphic library through VC++6.0 under the Windows environment in this paper. The STL model is a high quality one that can be quiescent or animated. This system is conducive to find out the disfigurement of the STL model in a rapid prototyping process and to repair it. Therefore, the component quality can be enhanced.展开更多
目的为了适应铸造CAE技术的网络化趋势,满足铸造CAE系统前置处理模块对STL模型高级渲染的功能性需求,开发一款足以媲美OpenGL渲染环境下复杂三维图形渲染效果的Web版的STL模型查看器程序——STLViewer。方法仿效Windows桌面程序的运行...目的为了适应铸造CAE技术的网络化趋势,满足铸造CAE系统前置处理模块对STL模型高级渲染的功能性需求,开发一款足以媲美OpenGL渲染环境下复杂三维图形渲染效果的Web版的STL模型查看器程序——STLViewer。方法仿效Windows桌面程序的运行方式和界面风格,选择单页面设计方案。选用Visual Studio 2019开发平台,利用HTML5、CSS3和JavaScript技术设计程序界面。深入研究基于WebGL的STL模型可视化技术,按照依托场景环境活动模型渲染的技术路线,进行STLViewer各功能模块的开发。结果设计并实现了STLViewer,该程序功能完整性良好、内部逻辑结构合理高效。STLViewer融隐式交互和显式交互于一体,具有本地STL模型的随机性访问、活动模型的多样化交互、模型姿态的智能化跟踪、视图动画的多方式呈现、模型导出的便捷化操作等特点,实现了网络环境下STL模型的高级渲染功能。结论STLViewer作为一款性能卓越的STL模型查看器程序,既可辅助用户制订合理的网格剖分方案,又能带来优良的用户体验,在实际应用中得到了良好效果。展开更多
对水质情况进行准确评估和预测对水污染防控至关重要,然而,由于水质受多种因素的影响,其时间序列数据常常具有趋势性、季节性和长期依赖关系,传统的预测方法往往无法很好地捕捉这些特征。为了解决这些问题,首先基于STL(Seasonal and Tre...对水质情况进行准确评估和预测对水污染防控至关重要,然而,由于水质受多种因素的影响,其时间序列数据常常具有趋势性、季节性和长期依赖关系,传统的预测方法往往无法很好地捕捉这些特征。为了解决这些问题,首先基于STL(Seasonal and Trend Decomposition using Loess)和TCN(Temporal Convolutional Network)构建STL-TCN水质预测模型。其中,通过STL模型对水质时间序列数据进行趋势和季节性分解,有效地提取时序数据的周期性特征;利用TCN模型中并行结构和残差连接有效捕捉时间序列数据的长期依赖关系,对分解后的数据进行多步预测。然后,选用福建省浪石断面河流的氨氮数据来验证STL-TCN水质预测模型的预测效果,并与基于长短时记忆网络(LSTM)和门控循环单元结构(GRU)的水质预测模型进行对比实验。实验结果表明,STL-TCN水质预测模型12步预测的MAE平均值达到0.0343、RMSE平均值达到0.0494、R^(2)平均值达到0.94737,相对LSTM和GRU,MAE平均提高7.8%和8.1%、RMSE平均提高2.2%和1.8%、R^(2)平均提高7.9%和7.8%。说明STL-TCN水质预测模型能够有效提高水质预测的准确性和稳定性,可以作为辅助水环境管理和决策的一种有效手段。展开更多
在信息化蓬勃发展的今日,大量云计算资源的高效管理是运维领域的重要难题。准确的负载预测是应对这一难题的关键技术。针对该问题提出一种基于局部加权回归周期趋势分解算法(Seasonal and Trend decomposition using Loess,STL)、Holt-W...在信息化蓬勃发展的今日,大量云计算资源的高效管理是运维领域的重要难题。准确的负载预测是应对这一难题的关键技术。针对该问题提出一种基于局部加权回归周期趋势分解算法(Seasonal and Trend decomposition using Loess,STL)、Holt-Winters模型和深度自回归模型(DeepAR)的组合预测模型STL-DeepAR-HW。先采用快速傅里叶变换和自相关函数提取数据的周期性特征,以提取到的最优周期对数据做STL分解,将数据分解为趋势项、季节项和余项;并用DeepAR和Holt-Winters分别预测趋势项和季节项,最后组合得到预测结果。在公开数据集AzurePublicDataset上进行实验,结果表明,与Transformer、Stacked-LSTM以及Prophet等模型相比,该组合模型在负载预测中具有更高的准确性和适用性。展开更多
传统的混凝土拱坝位移预测模型主要关注水压、温度、时效等因素与拱坝位移之间的关系,未对拱坝位移数据中所包含的信息进行充分挖掘。为此,采用Seasonal and Trend decomposition using Loess算法(STL)将拱坝位移原始数据分解为趋势序...传统的混凝土拱坝位移预测模型主要关注水压、温度、时效等因素与拱坝位移之间的关系,未对拱坝位移数据中所包含的信息进行充分挖掘。为此,采用Seasonal and Trend decomposition using Loess算法(STL)将拱坝位移原始数据分解为趋势序列、周期序列及残差分量。在此基础上,采用鲸鱼优化算法(WOA)结合随机森林算法(RF)对三个分量进行预测,并使用Holt-Winters算法充分考虑趋势序列中的趋势信息对趋势序列的预测结果进行修正。最后将修正后的趋势序列预测结果和周期序列、残差分量预测结果相加,得出拱坝位移最终预测结果。工程实例表明,基于STL-Holt-WOA-RF的拱坝位移预测模型能够显著提高预测的准确性和稳定性,为拱坝位移预测提供了新的思路和方法。展开更多
基金Sponsored by the National High-Technology Research and Development Program of China(Grant No2002AA6Z3083)
文摘For the data processing of the Rapid Prototyping Manufacturing, Boolean operation can offer a versatile tool for editing or modifying the STL model, adding the artificial construction, and creating the complex assistant support structure to meet the special technical requests. The topological structure of STL models was built firstly in order to obtain the neighborhood relationship among the triangular facets. The intersection test between every edge of one solid and every facet of another solid was taken to get the intersection points. According to the matching relationship of the triangle index recorded in the data structure of the intersection points, the intersection segments array and the intersection loop were traced out. Each intersected triangle was subdivided by the Constrained Delaunay Triangulations. The intersected surfaces were divided into several surface patches along the intersection loops. The inclusion prediction between the surface patch and the other solid was taken by testing whether the candidate point was inside or outside the solid region of the slice. Detecting the loops for determination of the valid intersection lines greatly increases the efficiency and the reliability of the process.
文摘A kind of 3D color graphics display system for the STL model is developed by calling the functions from Open GL graphic library through VC++6.0 under the Windows environment in this paper. The STL model is a high quality one that can be quiescent or animated. This system is conducive to find out the disfigurement of the STL model in a rapid prototyping process and to repair it. Therefore, the component quality can be enhanced.
文摘目的为了适应铸造CAE技术的网络化趋势,满足铸造CAE系统前置处理模块对STL模型高级渲染的功能性需求,开发一款足以媲美OpenGL渲染环境下复杂三维图形渲染效果的Web版的STL模型查看器程序——STLViewer。方法仿效Windows桌面程序的运行方式和界面风格,选择单页面设计方案。选用Visual Studio 2019开发平台,利用HTML5、CSS3和JavaScript技术设计程序界面。深入研究基于WebGL的STL模型可视化技术,按照依托场景环境活动模型渲染的技术路线,进行STLViewer各功能模块的开发。结果设计并实现了STLViewer,该程序功能完整性良好、内部逻辑结构合理高效。STLViewer融隐式交互和显式交互于一体,具有本地STL模型的随机性访问、活动模型的多样化交互、模型姿态的智能化跟踪、视图动画的多方式呈现、模型导出的便捷化操作等特点,实现了网络环境下STL模型的高级渲染功能。结论STLViewer作为一款性能卓越的STL模型查看器程序,既可辅助用户制订合理的网格剖分方案,又能带来优良的用户体验,在实际应用中得到了良好效果。
文摘对水质情况进行准确评估和预测对水污染防控至关重要,然而,由于水质受多种因素的影响,其时间序列数据常常具有趋势性、季节性和长期依赖关系,传统的预测方法往往无法很好地捕捉这些特征。为了解决这些问题,首先基于STL(Seasonal and Trend Decomposition using Loess)和TCN(Temporal Convolutional Network)构建STL-TCN水质预测模型。其中,通过STL模型对水质时间序列数据进行趋势和季节性分解,有效地提取时序数据的周期性特征;利用TCN模型中并行结构和残差连接有效捕捉时间序列数据的长期依赖关系,对分解后的数据进行多步预测。然后,选用福建省浪石断面河流的氨氮数据来验证STL-TCN水质预测模型的预测效果,并与基于长短时记忆网络(LSTM)和门控循环单元结构(GRU)的水质预测模型进行对比实验。实验结果表明,STL-TCN水质预测模型12步预测的MAE平均值达到0.0343、RMSE平均值达到0.0494、R^(2)平均值达到0.94737,相对LSTM和GRU,MAE平均提高7.8%和8.1%、RMSE平均提高2.2%和1.8%、R^(2)平均提高7.9%和7.8%。说明STL-TCN水质预测模型能够有效提高水质预测的准确性和稳定性,可以作为辅助水环境管理和决策的一种有效手段。
文摘在信息化蓬勃发展的今日,大量云计算资源的高效管理是运维领域的重要难题。准确的负载预测是应对这一难题的关键技术。针对该问题提出一种基于局部加权回归周期趋势分解算法(Seasonal and Trend decomposition using Loess,STL)、Holt-Winters模型和深度自回归模型(DeepAR)的组合预测模型STL-DeepAR-HW。先采用快速傅里叶变换和自相关函数提取数据的周期性特征,以提取到的最优周期对数据做STL分解,将数据分解为趋势项、季节项和余项;并用DeepAR和Holt-Winters分别预测趋势项和季节项,最后组合得到预测结果。在公开数据集AzurePublicDataset上进行实验,结果表明,与Transformer、Stacked-LSTM以及Prophet等模型相比,该组合模型在负载预测中具有更高的准确性和适用性。
文摘海表温度(sea surface temperature,SST)是海洋科学研究的重要内容之一。SST的异常波动导致海洋灾害、气象灾害现象时有发生,SST的精确预测对海洋环境保护和海洋经济发展有重要意义。针对SST序列的季节性、非平稳性,首先利用周期趋势分解算法(seasonal-trend decomposition procedure based on loess, STL)对数据进行预处理,分解得到季节分量、趋势分量和残差分量子序列,依次选择相应的预测方法构建组合模型。季节分量应用具有时间嵌入编码模块的Transformer网络预测,充分挖掘序列全局信息,解决时间序列长时间依赖问题;趋势分量应用线性回归模型预测;残差分量应用自回归模型预测。选取南海海域单点SST数据,应用基于STL的SST组合预测模型建模,预测5 d的SST值。实验结果表明,本文模型在单点SST预测任务中,能够有效捕获SST变化规律,提高预测精度。
文摘传统的混凝土拱坝位移预测模型主要关注水压、温度、时效等因素与拱坝位移之间的关系,未对拱坝位移数据中所包含的信息进行充分挖掘。为此,采用Seasonal and Trend decomposition using Loess算法(STL)将拱坝位移原始数据分解为趋势序列、周期序列及残差分量。在此基础上,采用鲸鱼优化算法(WOA)结合随机森林算法(RF)对三个分量进行预测,并使用Holt-Winters算法充分考虑趋势序列中的趋势信息对趋势序列的预测结果进行修正。最后将修正后的趋势序列预测结果和周期序列、残差分量预测结果相加,得出拱坝位移最终预测结果。工程实例表明,基于STL-Holt-WOA-RF的拱坝位移预测模型能够显著提高预测的准确性和稳定性,为拱坝位移预测提供了新的思路和方法。
