利索-全球专利检索

  1. 登录
  2. 注册

搜索结果

91 条记录 (耗时 0.024 秒)

    ANOMALY DETECTION, FORECASTING AND ROOT CAUSE ANALYSIS OF ENERGY CONSUMPTION FOR A PORTFOLIO OF BUILDINGS USING MULTI-STEP STATISTICAL MODELING
    2.
    发明申请
    ANOMALY DETECTION, FORECASTING AND ROOT CAUSE ANALYSIS OF ENERGY CONSUMPTION FOR A PORTFOLIO OF BUILDINGS USING MULTI-STEP STATISTICAL MODELING 有权
    异常检测，预测和根本原因分析使用多步统计建模的建筑物组合能源消耗

    公开(公告)号：US20120278051A1

    公开(公告)日：2012-11-01

    申请号：US13098044

    申请日：2011-04-29

    申请人： Huijing Jiang ,  Young Min Lee ,  Fei Liu

    发明人： Huijing Jiang ,  Young Min Lee ,  Fei Liu

    IPC分类号： G06F17/10 ,  G06F19/00 ,  G01R19/00

    CPC分类号： G06Q10/04 ,  G06Q50/06

    摘要： Multi-step statistical modeling in one embodiment of the present disclosure enables anomaly detection, forecasting and/or root cause analysis of the energy consumption for a portfolio of buildings using multi-step statistical modeling. In one aspect, energy consumption data associated with a building, building characteristic data associated with the building, building operation and activities data associated with the building, and weather data are used to generate a variable based degree model. A base load factor, a heating coefficient and a cooling coefficient associated with the building and an error term are determined from the variable based degree model and used to generate a plurality of multivariate regression models. A time series model is generated for the error term to model seasonal factors which reflect monthly dependence on energy use and an auto-regressive integrated moving average model (ARIMA) which reflects temporal dependent patterns of the energy use.

    摘要翻译： 在本公开的一个实施例中的多步统计建模使得能够使用多步统计建模对建筑物组合的能量消耗进行异常检测，预测和/或根本原因分析。 一方面，使用与建筑物相关联的能量消耗数据，构建与建筑物相关联的特征数据，建筑物操作和与建筑物相关联的活动数据以及天气数据来生成基于变量的度模型。 从基于变量的度模型确定基础负荷因子，与建筑物相关联的加热系数和冷却系数以及误差项，并用于产生多个多元回归模型。 为误差项生成时间序列模型，以模拟每月依赖能源使用的季节因素和反映能量使用的时间依赖模式的自回归积分移动平均模型（ARIMA）。

    Anomaly detection, forecasting and root cause analysis of energy consumption for a portfolio of buildings using multi-step statistical modeling
    3.
    发明授权
    Anomaly detection, forecasting and root cause analysis of energy consumption for a portfolio of buildings using multi-step statistical modeling 有权
    使用多步统计建模的建筑物组合能耗的异常检测，预测和根本原因分析

    公开(公告)号：US08738334B2

    公开(公告)日：2014-05-27

    申请号：US13098044

    申请日：2011-04-29

    申请人： Huijing Jiang ,  Young Min Lee ,  Fei Liu

    发明人： Huijing Jiang ,  Young Min Lee ,  Fei Liu

    IPC分类号： G06F17/10

    CPC分类号： G06Q10/04 ,  G06Q50/06

    摘要： Multi-step statistical modeling in one embodiment of the present disclosure enables anomaly detection, forecasting and/or root cause analysis of the energy consumption for a portfolio of buildings using multi-step statistical modeling. In one aspect, energy consumption data associated with a building, building characteristic data associated with the building, building operation and activities data associated with the building, and weather data are used to generate a variable based degree model. A base load factor, a heating coefficient and a cooling coefficient associated with the building and an error term are determined from the variable based degree model and used to generate a plurality of multivariate regression models. A time series model is generated for the error term to model seasonal factors which reflect monthly dependence on energy use and an auto-regressive integrated moving average model (ARIMA) which reflects temporal dependent patterns of the energy use.

    摘要翻译： 在本公开的一个实施例中的多步统计建模使得能够使用多步统计建模对建筑物组合的能量消耗进行异常检测，预测和/或根本原因分析。 一方面，使用与建筑物相关联的能量消耗数据，构建与建筑物相关联的特征数据，建筑物操作和与建筑物相关联的活动数据以及天气数据来生成基于变量的度模型。 从基于变量的度模型确定基础负荷因子，与建筑物相关联的加热系数和冷却系数以及误差项，并用于产生多个多元回归模型。 为误差项生成时间序列模型，以模拟每月依赖能源使用的季节因素和反映能量使用的时间依赖模式的自回归积分移动平均模型（ARIMA）。

    Change point detection in causal modeling
    4.
    发明授权
    Change point detection in causal modeling 失效
    因果模型中的变化点检测

    公开(公告)号：US08645304B2

    公开(公告)日：2014-02-04

    申请号：US13213273

    申请日：2011-08-19

    申请人： Huijing Jiang ,  Fei Liu ,  Aurelie C. Lozano

    发明人： Huijing Jiang ,  Fei Liu ,  Aurelie C. Lozano

    IPC分类号： G06N5/02

    CPC分类号： G06N7/005 ,  G01W1/10

    摘要： Structural changes in causal relationship over time may be detected, for example, by a Markov switching vector autoregressive model that detects and infers the structural changes in the causal graphs.

    摘要翻译： 随着时间的推移，因果关系的结构变化可能被检测到，例如，通过马尔科夫切换向量自回归模型检测并推断因果图中的结构变化。

    CHANGE POINT DETECTION IN CAUSAL MODELING
    5.
    发明申请
    CHANGE POINT DETECTION IN CAUSAL MODELING 失效
    改变点检测在原始建模

    公开(公告)号：US20130046721A1

    公开(公告)日：2013-02-21

    申请号：US13213273

    申请日：2011-08-19

    申请人： Huijing Jiang ,  Fei Liu ,  Aurelie C. Lozano

    发明人： Huijing Jiang ,  Fei Liu ,  Aurelie C. Lozano

    IPC分类号： G06N5/02

    CPC分类号： G06N7/005 ,  G01W1/10

    摘要： Structural changes in causal relationship over time may be detected, for example, by a Markov switching vector autoregressive model that detects and infers the structural changes in the causal graphs.

    摘要翻译： 随着时间的推移，因果关系的结构变化可能被检测到，例如，通过马尔科夫切换向量自回归模型检测并推断因果图中的结构变化。

    Data Segmentation and Visualization
    7.
    发明申请
    Data Segmentation and Visualization 审中-公开
    数据分段和可视化

    公开(公告)号：US20160117373A1

    公开(公告)日：2016-04-28

    申请号：US14898067

    申请日：2013-06-13

    申请人： Yingnong DANG ,  Dongmei ZHANG ,  Rui Justin DING ,  Fei LIU ,  Haoyu JIANG ,  MICROSOFT TECHNOLOGY LICENSING, LLC

    发明人： Yingnong Dang ,  Rui Ding ,  Haoyu Jiang ,  Fei Liu ,  Dongmei Zhang

    IPC分类号： G06F17/30

    CPC分类号： G06F16/26 ,  G06F16/27 ,  G06F16/287

    摘要： The techniques described herein provide tools that summarize a dataset by creating a final set of segments that, when visually presented via a histogram or other data presentation tool, show the distribution of at least a portion of the data. To create the final set of segments, the techniques described herein may collect or receive a dataset with distinct values, and divide the dataset into a number of segments that is less than or equal to a segment presentation threshold (e.g., ten segments). After creating the final set of segments, the techniques may configure and/or present data visualizations, such as histograms, for the created segments so that an observer is provided with a good viewing experience.

    摘要翻译： 本文描述的技术提供了通过创建最终的段集合来总结数据集的工具，当通过直方图或其他数据呈现工具直观呈现时，该组段显示数据的至少一部分的分布。 为了创建最终的段集合，本文描述的技术可以收集或接收具有不同值的数据集，并将数据集划分成小于或等于段呈现阈值（例如，10个段）的多个段。 在创建最后一组片段之后，技术可以为创建的片段配置和/或呈现诸如直方图的数据可视化，使得向观察者提供良好的观看体验。

    Method for estimating state-of-charge of lithium ion battery
    8.
    发明授权
    Method for estimating state-of-charge of lithium ion battery 有权
    锂离子电池的充电状态估计方法

    公开(公告)号：US09121909B2

    公开(公告)日：2015-09-01

    申请号：US13695414

    申请日：2011-03-14

    申请人： Fei Liu ,  Xusong Ruan ,  Feng Wen

    发明人： Fei Liu ,  Xusong Ruan ,  Feng Wen

    IPC分类号： G01N27/416 ,  G01R31/36

    CPC分类号： G01R31/361 ,  G01R31/3624

    摘要： The invention relates to the technical field of lithium-ion batteries, in particular to a method for estimating the state of charge of a lithium-ion battery. The method includes: charging a lithium-ion battery, recording multiple groups of ampere-hour integral values, and states of charge and voltage values corresponding to the ampere-hour integral values; taking the maximum value in the multiple groups of ampere-hour integral values as the first ampere-hour integral value, the state of charge corresponding to the first ampere-hour integral value as the first state of charge, and the voltage value corresponding to the first ampere-hour integral value as the first voltage value; monitoring the lithium-ion battery in real time, recording a real-time second ampere-hour integral value and a second voltage value, obtaining a second state of charge by an ampere-hour measuring method; and if the second voltage value is consistent with the first voltage value and the second state of charge is inconsistent with the first state of charge, replacing the second state of charge with the first state of charge. The invention increases the reliable evidence for judging the online equalization of the battery pack and most importantly avoids the situation where the state of charge of the battery can be corrected only on condition that the battery pack works at the extreme state of charge, and lowers the influences of the full charge and discharge on the lifetime of the battery.

    摘要翻译： 本发明涉及锂离子电池的技术领域，特别涉及一种用于估计锂离子电池的充电状态的方法。 该方法包括：对锂离子电池充电，记录多组安培小时积分值，以及对应于安培小时积分值的充电状态和电压值; 将多组安培小时积分值中的最大值作为第一安培小时积分值，对应于作为第一充电状态的第一安培小时积分值的充电状态和对应于 第一安培小时积分值作为第一电压值; 实时监控锂离子电池，记录实时第二安培小时积分值和第二电压值，通过安培小时测量方法获得第二充电状态; 并且如果所述第二电压值与所述第一电压值一致并且所述第二充电状态与所述第一充电状态不一致，则用所述第一充电状态代替所述第二充电状态。 本发明增加了用于判断电池组的在线均衡的可靠证据，最重要的是避免了仅在电池组工作在极端充电状态的情况下可以仅修正电池的充电状态的情况，并且降低 充电和放电对电池寿命的影响。