公开(公告)号：WO2016100814A1

公开(公告)日：2016-06-23

申请号：PCT/US2015/066664

申请日：2015-12-18

Applicant: UNITED TECHNOLOGIES CORPORATION

Inventor： GIERING, Michael J. ,  REDDY, Kishore K. ,  VENUGOPALAN, Vivek

IPC: G06K9/00 ,  G06N3/04

CPC classification number: G05B23/0254 ,  G05B23/0294 ,  G06K9/00791 ,  G06K9/4628 ,  G06K9/6273 ,  G06K9/6289 ,  G06N3/0454 ,  G06N3/08 ,  G06T7/248

Abstract: A method includes fusing multi-modal sensor data from a plurality of sensors having different modalities. At least one region of interest is detected in the multi-modal sensor data. One or more patches of interest are detected in the multi-modal sensor data based on detecting the at least one region of interest. A model that uses a deep convolutional neural network is applied to the one or more patches of interest. Post-processing of a result of applying the model is performed to produce a post-processing result for the one or more patches of interest. A perception indication of the post-processing result is output.

Abstract translation: 一种方法包括从具有不同模态的多个传感器融合多模式传感器数据。 在多模态传感器数据中检测到至少一个感兴趣的区域。 基于检测到所述至少一个感兴趣区域，在所述多模式传感器数据中检测感兴趣的一个或多个斑块。 使用深卷积神经网络的模型应用于一个或多个感兴趣的斑块。 执行应用模型的结果的后处理，以产生一个或多个感兴趣的补丁的后处理结果。 输出后处理结果的感知指示。

公开(公告)号：WO2017200524A1

公开(公告)日：2017-11-23

申请号：PCT/US2016/032696

申请日：2016-05-16

Applicant: UNITED TECHNOLOGIES CORPORATION

Inventor： GIERING, Michael J. ,  REDDY, Kishore K. ,  VENUGOPALAN, Vivek

IPC: G06K9/00

CPC classification number: G06K9/3241 ,  G06F16/55 ,  G06K9/00496 ,  G06K9/4604 ,  G06N5/046 ,  G06T7/0004 ,  G06T2207/20081 ,  G06T2207/20084 ,  G06T2207/30164

Abstract: A method includes detecting at least one region of interest in a frame of image data. One or more patches of interest are detected in the frame of image data based on detecting the at least one region of interest. A model including a deep convolutional neural network is applied to the one or more patches of interest. Post-processing of a result of applying the model is performed to produce a post-processing result for the one or more patches of interest. A visual indication of a classification of defects in a structure is output based on the result of the post-processing.

Abstract translation: 一种方法包括检测一帧图像数据中的至少一个感兴趣区域。 基于检测到至少一个感兴趣区域，在图像数据的帧中检测到一个或多个感兴趣的小片。 包括深卷积神经网络的模型被应用于一个或多个感兴趣的小片。 执行应用模型的结果的后处理以产生一个或多个感兴趣的小片的后处理结果。 根据后处理结果输出结构中缺陷分类的可视指示。

公开(公告)号：WO2016100816A1

公开(公告)日：2016-06-23

申请号：PCT/US2015/066673

申请日：2015-12-18

Applicant: UNITED TECHNOLOGIES CORPORATION

Inventor： GIERING, Michael J. ,  SHASHANKA, Madhusudana ,  SARKAR, Soumik ,  VENUGOPALAN, Vivek

IPC: G06N3/04 ,  G05B23/02

CPC classification number: G05B23/0254 ,  G05B23/0294 ,  G06K9/00791 ,  G06K9/4628 ,  G06K9/6273 ,  G06K9/6289 ,  G06N3/0454 ,  G06N3/08 ,  G06T7/248

Abstract: A method includes converting time-series data from a plurality of prognostic and health monitoring (PHM) sensors into frequency domain data. One or more portions of the frequency domain data are labeled as indicative of one or more target modes to form labeled target data. A model including a deep neural network is applied to the labeled target data. A result of applying the model is classified as one or more discretized PHM training indicators associated with the one or more target modes. The one or more discretized PHM training indicators are output.

Abstract translation: 一种方法包括将来自多个预测和健康监测（PHM）传感器的时间序列数据转换成频域数据。 频域数据的一个或多个部分被标记为指示一个或多个目标模式以形成标记的目标数据。 包括深神经网络的模型被应用于标记的目标数据。 应用模型的结果被分类为与一个或多个目标模式相关联的一个或多个离散PHM训练指示符。 输出一个或多个离散PHM训练指标。