-
公开(公告)号：US20160358106A1
公开(公告)日：2016-12-08
申请号：US15173927
申请日：2016-06-06
Applicant: SAS INSTITUTE INC.
Inventor： Thomas Dale Anderson , James Edward Duarte , Milad Falahi
CPC classification number: G06N99/005 , G05B23/0254 , G05B23/0283 , G06F11/00 , G06N7/005
Abstract: A computing device predicts a probability of a transformer failure. An analysis type indicator defined by a user is received. A worth value for each of a plurality of variables is computed. Highest worth variables from the plurality of variables are selected based on the computed worth values. A number of variables of the highest worth variables is limited to a predetermined number based on the received analysis type indicator. A first model and a second model are also selected based on the received analysis type indicator. Historical electrical system data is partitioned into a training dataset and a validation dataset that are used to train and validate, respectively, the first model and the second model. A probability of failure model is selected as the first model or the second model based on a comparison between a fit of each model.
Abstract translation: 计算设备预测变压器故障的概率。 接收由用户定义的分析类型指示符。 计算多个变量中的每一个的值。 基于所计算的值，选择来自多个变量的最高值变量。 基于接收到的分析类型指示符，将最高价值变量的多个变量限制为预定数量。 还基于接收到的分析类型指标来选择第一模型和第二模型。 历史电气系统数据被分为训练数据集和验证数据集，分别用于训练和验证第一模型和第二模型。 基于每个模型的拟合之间的比较，选择故障概率模型作为第一模型或第二模型。
-
公开(公告)号：US09652723B2
公开(公告)日：2017-05-16
申请号：US15173927
申请日：2016-06-06
Applicant: SAS Institute Inc.
Inventor： Thomas Dale Anderson , James Edward Duarte , Milad Falahi
CPC classification number: G06N99/005 , G05B23/0254 , G05B23/0283 , G06F11/00 , G06N7/005
Abstract: A computing device predicts a probability of a transformer failure. An analysis type indicator defined by a user is received. A worth value for each of a plurality of variables is computed. Highest worth variables from the plurality of variables are selected based on the computed worth values. A number of variables of the highest worth variables is limited to a predetermined number based on the received analysis type indicator. A first model and a second model are also selected based on the received analysis type indicator. Historical electrical system data is partitioned into a training dataset and a validation dataset that are used to train and validate, respectively, the first model and the second model. A probability of failure model is selected as the first model or the second model based on a comparison between a fit of each model.
-
Search Results
2
records
(took 0.011 seconds)
