Dynamic Bayesian networks for reliability evaluation of subsea wellhead connector during service life based on Monte Carlo method

The subsea wellhead connector is a critical connection component between subsea Christmas tree and subsea wellhead for preventing the leakage of oil and gas in the subsea production system. Excited by cyclical loadings due to environmental forces and the other support forces, the subsea wellhead connector is prone to the failure, which could lead to the loss of subsea tree or wellhead integrity and even catastrophic accidents. With the Monte Carlo simulation method, this paper presents a reliability analysis approach based on dynamic Bayesian Networks, aiming to assess the failure probability of the subsea wellhead connector during service life. Take the driving ring component of the subsea wellhead connector as an example to demonstrate the reasonability of the proposed model. The generation data is processed by the transform between the numerical value and the state variable. Based on the stress-strength interference theory, the structure reliability of the driving ring with 96.26% is achieved by the proposed model with the consideration the aging of the material strength and the most influential factors are figured out. Meanwhile, the corresponding control measures are proposed effectively reduce the failure risk of the subsea wellhead connector during service life.     

走滑断层作用下X80管道设计应变规律和神经网络预测

走滑断层是埋地管道常见的地质灾害威胁，断层作用下管道会发生较大的拉压应变而失效。为得到X80管道的设计应变，基于有限元方法建立了走滑断层作用下管道的应变响应数值计算模型，模型使用壳单元模拟管道，非线性弹簧单元模拟土壤约束，采用西二线实际工程的管道应变影响参数范围，计算了管道的设计应变；为预测管道的设计应变值，基于以上参数化分析得到的4 817组设计应变结果，采用人工神经网络建立了管道设计应变预测模型。结果表明:该神经网络模型预测结果的最大相对误差小于10%，预测准确性良好，且该方法具有较高的计算效率，可以为断层作用下埋地管道的应变设计与评估提供参考。     

基于人工神经网络的气体泄爆最大超压预测研究

为解决传统经验公式在预测气体泄爆中最大超压出现时的较大偏差或过于保守的问题，提出使用人工神经网络预测气体泄爆最大超压。基于124组实验数据，采用BP与RBF神经网络，通过优化算法计算与迭代循环对泄爆样本中的影响因素进行降维与选择，并确定2类神经网络本身在学习与计算气体泄爆样本时的相关参数。结果表明:PCA（主成分分析法）在当前样本条件下的降维效果较差，而通过迭代对比确认气体泄爆样本中的5类特征全部保留时神经网络的训练模拟效果最好；通过对124组实验数据进行随机挑选训练集与测试集的训练模拟结果发现，神经网络对气体泄爆中最大超压的预测效果较好；通过对比Molkov提出的和经Fakandu等改进的NFPA 68经验公式以及2类神经网络的预测结果表明，神经网络相比于传统气体泄爆经验公式具有明显优势。     

基于BP神经网络的受限空间火灾联合探测方法

针对航空受限空间火灾探测高误报的问题，在现有技术成果基础上对多种火灾探测方式进行研讨，并提出1种基于BP神经网络技术的飞机机身内部受限空间火灾联合探测报警方法。该方法结合现有烟雾感应、气体传感器探测等常用火灾探测技术，以红外热成像探测为辅助手段，采用神经网络实现数据融合，对模拟实验舱火灾烟雾进行联合探测，在单一火灾探测方式基础上提高了探测准确率。     

Emergent conservation outcomes of shared risk perception in human-wildlife systems

Human perception of risks related to economic damages caused by nearby wildlife can be transmitted through social networks. Understanding how sharing risk information within a human community alters the spatial dynamics of human-wildlife interactions has important implications for the design and implementation of effective conservation actions. We developed an agent-based model that simulates farmer livelihood decisions and activities in an agricultural landscape shared with a population of a generic wildlife species (wildlife-human interactions in shared landscapes [WHISL]). In the model, based on risk perception and economic information, farmers decide how much labor to allocate to farming and whether and where to exclude wildlife from their farms (e.g., through fencing, trenches, or vegetation thinning). In scenarios where the risk perception of farmers was strongly influenced by other farmers, exclusion of wildlife was widespread, resulting in decreased quality of wildlife habitat and frequency of wildlife damages across the landscape. When economic losses from encounters with wildlife were high, perception of risk increased and led to highly synchronous behaviors by farmers in space and time. Interactions between wildlife and farmers sometimes led to a spillover effect of wildlife damage displaced from socially and spatially connected communities to less connected neighboring farms. The WHISL model is a useful conservation-planning tool because it provides a test bed for theories and predictions about human-wildlife dynamics across a range of different agricultural landscapes.     

基于不变矩理论的腐蚀等级评定方法研究

基于腐蚀图像包含大量腐蚀信息的客观现实,将数字图像技术和不变矩理论应用于腐蚀图像预处理和特征提取,用腐蚀图像的7个不变矩特征值来描述腐蚀形貌特征,利用概率神经网络模式识别技术,建立了以不变矩为特征参数的概率神经网络模式识别模型,实现了金属材料腐蚀等级的评定。以铝合金材料在EXCO溶液中加速腐蚀等级评定为例,分析表明,不变矩作为一种高度浓缩的图像特征,能够表示腐蚀形貌与腐蚀特征的映射关系,该方法简单易行,识别率可达到87.95%,满足工程应用要求。     

智能化有害有毒气体污染源监测仪的研究

为了快速寻找有害有毒气体污染源,利用8个红外激光气体传感器,分别安装步进电机驱动旋转的圆盘圆周上在不同的方向上对污染气体进行数据采集。同时与二维热差式风速风向传感器采集到的风速风向数据,一并送入MSC1210单片机进行数据处理和运用智能人工神经网络进行模式训练与模式识别,从而识别出污染源的位置、浓度和种类。通过GPS全球卫星定位系统和GPRS无线传输网络,把监测到的信息发送给相关部门早做处理,并报警,避免污染进一步扩散。实验表明,该智能化追索气体污染源监测仪具有良好的可靠性、安全性和实用性。     

Synthesis of TiO2 nanoparticles in different thermal conditions and modeling its photocatalytic activity with artificial neural network

Titanium dioxide (TiO₂) nanoparticles were prepared by sol gel route. The preparation parameters were optimized in the removal of 4-nitrophenol (4-NP). All catalysts were analyzed by X-ray diffraction (XRD) and scanning electron microscopy (SEM). An artificial neural network model (ANN) was developed to predict the photocatalytic removal of 4-NP in the presence of TiO₂ nanoparticles prepared under desired conditions. The comparison between the predicted results by designed ANN model and the experimental data proved that modeling of the removal process of 4-NP using artificial neural network was a precise method to predict the extent of 4-NP removal under different conditions.     

面向实时人群动力学分析的深度基本图网络

当前行人疏散实验中基本图计算方法通常是通过对每个行人进行跟踪实现的。但这种跟踪方法难以实现实时人群动力学分析。针对这一问题,提出了深度基本图网络。实验提出的网络框架由两个模块组成,即多尺度递归卷积神经网络(MSR-Net)和光流模块,分别对行人密度和行人速度进行估计。具体来讲,MSR-Net学习了输入图像与行人密度图之间的映射关系。同时,光流模块实时计算出行人运动速度。基于密度图与速度图的空间对应关系,可以得到基本图。实验表明,我们的方法与传统方法有较好的一致性,而我们的方法可以直接得到行人运动信息,不需要先提取轨迹。同时,基于深度基本图网络还可以实现复杂场景下的异常检测,在人群动力学分析领域具有很好的应用前景。     

正矩阵因子分解法评价北京市PM_(10)和SO_2监测网络

为辨识北京市大气污染物变化规律相同的区域,筛选监测网络中表征冗余信息的监测点,使用正矩阵因子分解法分别对北京市PM10和SO2监测网络进行分析与评价.分析获得北京市PM10和SO2明显的季节变化特征:PM10浓度春季最高,夏季较低;SO2浓度冬季最高,夏季较低.采用正矩阵分解法对PM10监测网络解析出3个因子,对应北京市PM10污染变化特征相同的3个区域,分别为区域1代表监测点为车公庄与石景山古城,区域2代表监测点为位于城东的前门、天坛、农展馆与奥体中心,区域3代表监测点定陵.结果表明区域2监测点密度较大,存在表征冗余信息的监测点,可以考虑撤销或迁移部分监测点.对SO2监测网络解析出6个因子,分别对应北京市SO2污染变化特征相同的6个区域,代表监测点位分别为定陵、古城、东四、奥体中心、农展馆与天坛和前门与车公庄.评价结果表明北京市PM10和SO2监测网络都存在冗余信息的监测点,可以根据分区结果考虑撤销或者迁移部分监测点,优化监测网络.