Probabilistic learning on manifolds (PLoM) with partition

The probabilistic learning on manifolds (PLoM) introduced in 2016 has solved difficult supervised problems for the “small data” limit where the number N of points in the training set is small. Many extensions have since been proposed, making it possible to deal with increasingly complex cases. However, the performance limit has been observed and explained for applications for which N is very small and for which the dimension of the diffusion-map basis is close to N. For these cases, we propose a novel extension based on the introduction of a partition in independent random vectors. We take advantage of this development to present improvements of the PLoM such as a simplified algorithm for constructing the diffusion-map basis and a new mathematical result for quantifying the concentration of the probability measure in terms of a probability upper bound. The analysis of the efficiency of this extension is presented through two applications.     

多堆厂址始发事件分析探讨

多堆厂址一级概率安全评价（PSA）研究中，机组数目的增加使得建模工作量剧增，给整个核电厂的风险评估带来困难。结合已有基础，本文研究了多堆厂址始发事件分析的筛选方法，提出利用堆芯损伤频率（CDF）上下限值评估方法，分析厂址内不同机组数对厂址CDF的影响。结果表明，双机组厂址适合优先进行具体分析。针对双机组核电站，对多堆厂址内各始发事件进行筛选。结果表明，丧失厂外电、丧失热阱等事件适合建模分析，并对其他筛选结果给出后续分析建议，为多堆厂址一级PSA后续事故序列建模工作提供了重要基础。     

基于船载卫星通信三轴天线的跟踪搜索技术

针对船载卫星通信三轴天线跟踪系统,介绍了船载三轴天线的系统组成,提出了一种基于捷联惯导的船载三轴天线跟踪搜索技术。天线以目标地理角为中心,通过坐标转换将目标地理角转换为天线的目标甲板角,调整AEC三轴使其及时准确地跟随目标甲板角。目前,该方法已经成功应用于多种船载三轴天线。实践表明,该方法能够快速准确地搜索到目标卫星,并实现对目标卫星的稳定跟踪。     

Integration of imitation learning using GAIL and reinforcement learning using task-achievement rewards via probabilistic graphical model

The integration of reinforcement learning (RL) and imitation learning (IL) is an important problem that has long been studied in the field of intelligent robotics. RL optimizes policies to maximize the cumulative reward, whereas IL attempts to extract general knowledge about the trajectories demonstrated by experts, i.e, demonstrators. Because each has its own drawbacks, many methods combining them and compensating for each set of drawbacks have been explored thus far. However, many of these methods are heuristic and do not have a solid theoretical basis. This paper presents a new theory for integrating RL and IL by extending the probabilistic graphical model (PGM) framework for RL, control as inference. We develop a new PGM for RL with multiple types of rewards, called probabilistic graphical model for Markov decision processes with multiple optimality emissions (pMDP-MO). Furthermore, we demonstrate that the integrated learning method of RL and IL can be formulated as a probabilistic inference of policies on pMDP-MO by considering the discriminator in generative adversarial imitation learning (GAIL) as an additional optimality emission. We adapt the GAIL and task-achievement reward to our proposed framework, achieving significantly better performance than policies trained with baseline methods.     

CBK searching (chemistry-biology-keyword): Performing cross-discipline collaborative searches

A debate over whether a search is a chemistry or a biology search is becoming increasingly more frequent within search teams. The line between non-text chemistry and biology searching has become blurred in recent years. The appearance of “non-natural” amino acids and modified peptides, for example, has given rise to the questions: Is it a structure? Is it a sequence? Could it be both? It may not be a question of one or the other, but perhaps working with a colleague to bring the best possible answer to the client. Several examples clarify the line and present guidance when beginning a search. Consider the size of the molecule, how many amino acids are present and what the client needs in order to best cover all bases and create a more comprehensive search report.     

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.     

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.     

基于节点1-邻居图相似性的社会网络匿名技术

利用传统的k匿名技术在社会网络中进行隐私保护时会存在聚类准则单一、图中数据信息利用不足等问题. 针对该问题, 提出了一种利用Kullback-Leibler (KL)散度衡量节点1-邻居图相似性的匿名技术(anonymization techniques for measuring the similarity of node 1-neighbor graph based on Kullback-Leibler divergence, SNKL). 根据节点1-邻居图分布的相似性对原始图节点集进行划分, 按照划分好的类进行图修改, 使修改后的图满足k匿名, 完成图的匿名发布. 实验结果表明, SNKL方法与HIGA方法相比在聚类系数上的改变量平均降低了17.3%, 同时生成的匿名图与原始图重要性节点重合度保持在95%以上. 所提方法在有效保证隐私的基础上, 可以显著的降低对原始图结构信息的改变.     

基于概率神经网络的自行火炮发动机状态监控系统

为有效发挥自行火炮发动机效率,减少对发动机寿命的影响,建立了自行火炮发动机状态监控模型。分析了概率神经网络结构和训练算法,以某型底盘所采用的12150L型发动机为例,选取发动机状态监控有效性指标,通过多种状态数据的引入和量化,评测发动机实时工作情况。结果表明:该模型能成功对故障进行分类,分类速度快,能有效进行自行火炮发动机状态监控,进一步提高状态监控准确率和实用程度。     

基于ANSYS/PDS模块的油缸可靠性设计

阐述了机械可靠性设计理论和蒙特卡罗方法。运用ANSYS软件的PDS模块,将有限元方法和可靠性设计理论相结合,对油缸进行二维参数化建模,并编制APDL命令流,建立可靠性分析文件对油缸进行了可靠性设计。设计结果经过了实践的检验,对类似油缸的轻量化设计具有一定的参考价值。