公开(公告)号：WO2017139147A1

公开(公告)日：2017-08-17

申请号：PCT/US2017/015969

申请日：2017-02-01

Applicant: NEC LABORATORIES AMERICA, INC.

Inventor： CHENG, Wei ,  ZHANG, Kai ,  CHEN, Haifeng ,  JIANG, Guofei

IPC: H04L12/24

CPC classification number: G06F11/079 ,  G06F11/0709 ,  G06F11/0751 ,  G06F2201/805 ,  G06F2201/81 ,  G06N99/005

Abstract: A method is provided for root cause anomaly detection in an invariant network having a plurality of nodes that generate time series data. The method includes modeling anomaly propagation in the network. The method includes reconstructing broken invariant links in an invariant graph based on causal anomaly ranking vectors. Each broken invariant link involves a respective node pair formed from the plurality of nodes such that one of the nodes in the respective node pair has an anomaly. Each causal anomaly ranking vector is for indicating a respective node anomaly status for a given one of the plurality of nodes when paired. The method includes calculating a sparse penalty of the casual anomaly ranking vectors to obtain a set of time-dependent anomaly rankings. The method includes performing temporal smoothing of the set of rankings, and controlling an anomaly-initiating one of the plurality of nodes based on the set of rankings.

Abstract translation: 提供了一种用于在具有生成时间序列数据的多个节点的不变网络中进行根本原因异常检测的方法。 该方法包括对网络中的异常传播进行建模。 该方法包括基于因果异常排序向量重建不变图中的断裂不变链接。 每个断开的不变链路涉及由多个节点形成的相应节点对，使得相应节点对中的节点之一具有异常。 每个因果异常排名向量用于在配对时指示多个节点中给定的一个节点的相应节点异常状态。 该方法包括计算偶然异常排名向量的稀疏惩罚以获得一组时间异常排名。 该方法包括执行该组排名的时间平滑，并基于该组排名控制多个节点中的异常发起的一个。

公开(公告)号：WO2017015184A1

公开(公告)日：2017-01-26

申请号：PCT/US2016/042721

申请日：2016-07-18

Applicant: NEC LABORATORIES AMERICA, INC.

Inventor： ZHANG, Kai ,  CHEN, Haifeng ,  YOSHIHIRA, Kenji ,  JIANG, Guofei

IPC: G05B19/418

CPC classification number: F01K13/02 ,  F01K13/003 ,  G05B13/048

Abstract: Systems and methods are provided for optimizing system output in production systems, comprising. The method includes separating, by a processor, one or more initial input variables into a plurality of output variables, the output variables including environmental variables and system response variables. The method also includes building, using the processor, a nonparametric estimation that determines a relationship between one or more initial control variables and the system response variables, and estimating a global input-output mapping function, using the determined relationship, and a range of the environmental variables. The method further includes generating one or more optimal control variables from the initial control variables by maximizing the input-output mapping function and the range of the environmental variables. The method additionally includes incorporating one or more of the optimal control variables into a production system to increase production output of the production system.

Abstract translation: 提供了用于优化生产系统中的系统输出的系统和方法，包括。 该方法包括将处理器将一个或多个初始输入变量分离成多个输出变量，输出变量包括环境变量和系统响应变量。 该方法还包括使用处理器构建非参数估计，其确定一个或多个初始控制变量与系统响应变量之间的关系，以及使用所确定的关系估计全局输入 - 输出映射函数，以及范围的 环境变量。 该方法还包括通过最大化输入 - 输出映射函数和环境变量的范围从初始控制变量产生一个或多个最优控制变量。 该方法还包括将一个或多个最佳控制变量并入到生产系统中以增加生产系统的生产输出。

公开(公告)号：WO2016196079A1

公开(公告)日：2016-12-08

申请号：PCT/US2016/033905

申请日：2016-05-24

Applicant: NEC LABORATORIES AMERICA, INC.

Inventor： ZHANG, Kai ,  CHEN, Zhengzhang ,  CHEN, Haifeng ,  JIANG, Guofei

IPC: G06F17/18 ,  G06F9/48 ,  G06N99/00 ,  G06F15/18

CPC classification number: G06N99/005 ,  G06F19/34

Abstract: Systems and methods are provided for acquiring data from an input signal using multitask regression. The method includes: receiving the input signal, the input signal including data that includes a plurality of features; determining at least two computational tasks to analyze within the input signal; regularizing all of the at least two tasks using shared adaptive weights; performing a multitask regression on the input signal to create a solution path for all of the at least two tasks, wherein the multitask regression includes updating a model coefficient and a regularization weight together under an equality norm constraint until convergence is reached, and updating the model coefficient and regularization weight together under an updated equality norm constraint that has a greater l1-penalty than the previous equality norm constraint until convergence is reached; selecting a sparse model from the solution path; constructing an image using the sparse model; and displaying the image.

Abstract translation: 提供了系统和方法，用于使用多任务回归从输入信号中获取数据。 所述方法包括：接收所述输入信号，所述输入信号包括包括多个特征的数据; 确定在输入信号内分析的至少两个计算任务; 使用共享自适应权重对所有至少两个任务进行规则化; 对输入信号执行多任务回归，以创建用于所有至少两个任务的解决路径，其中所述多任务回归包括在等式范数约束下一起更新模型系数和正则化权重直到达到收敛，并且更新所述模型 系数和正则化权重在更新的等式规范约束下一起，其具有比先前的等式范数约束更大的l1惩罚，直到达到收敛; 从解决路径中选择稀疏模型; 使用稀疏模型构建图像; 并显示图像。

公开(公告)号：WO2016094339A1

公开(公告)日：2016-06-16

申请号：PCT/US2015/064373

申请日：2015-12-08

Applicant: NEC LABORATORIES AMERICA, INC.

Inventor： YAN, Tan ,  JIANG, Guofei ,  CHEN, Haifeng ,  ZHANG, Kai

IPC: G06F11/34 ,  G06F11/00

CPC classification number: G07C3/00 ,  G05B23/0232 ,  G05B23/0283

Abstract: Systems and methods for managing components of physical systems, including decomposing raw time series by extracting an aging trend and a fluctuation term from the time series using an objective function of an optimization problem, the objective function minimizing reconstruction error and ensuring flatness of the fluctuation term over time. The optimization problem is transformed into a Quadratic Programming (QP) formulation including a monotonicity constraint and a non-negativity constraint, the constraints being merged together to reduce computational costs. An aging score and a confidence score are generated for the extracted aging trend to determine a severeness of aging for one or more components of the physical system, and the aging score and confidence score are fused to provide a fused ranking for the extracted aging trend for predicting future failures of the components.

Abstract translation: 用于管理物理系统组件的系统和方法，包括通过使用优化问题的目标函数从时间序列中提取老化趋势和波动项来分解原始时间序列，目标函数最小化重建误差并确保波动项的平坦度 随着时间的推移。 优化问题被转换成二次规划（QP）公式，包括单调约束和非负性约束，约束被合并在一起以减少计算成本。 对于提取的老化趋势产生老化评分和置信度分数，以确定物理系统的一个或多个组分的老化度，并且老化得分和置信度得分被融合，以提供提取的老化趋势的融合排名 预测组件的未来故障。

公开(公告)号：WO2017087440A1

公开(公告)日：2017-05-26

申请号：PCT/US2016/062140

申请日：2016-11-16

Applicant: NEC LABORATORIES AMERICA, INC.

Inventor： ZHANG, Kai ,  ZHANG, Hui ,  XU, Jianwu ,  JIANG, Guofei

IPC: G06F11/32 ,  G06F11/30

CPC classification number: G06F11/0775 ,  G06F11/0709 ,  G06F11/0751 ,  G06F11/079 ,  G06F11/3452 ,  G06F2201/83 ,  G06F2201/86 ,  G06N5/04 ,  G06N7/00

Abstract: An exemplary method for detecting one or more anomalies in a system includes building a temporal causality graph describing functional relationship among local components in normal period; applying the causality graph as a propagation template to predict a system status by iteratively applying current system event signatures; and detecting the one or more anomalies of the system by examining related patterns on the template causality graph that specifies normal system behaviors. The system can aligning event patterns on the causality graph to determine an anomaly score.

Abstract translation: 用于检测系统中的一个或多个异常的示例性方法包括：建立描述正常时期中的局部分量之间的函数关系的时间因果关系图; 通过迭代地应用当前系统事件签名来应用因果图作为传播模板来预测系统状态; 以及通过检查指定正常系统行为的模板因果关系图上的相关模式来检测系统的一个或多个异常。 系统可以对因果关系图上的事件模式进行排列，以确定异常分数。