公开(公告)号：US20150279129A1

公开(公告)日：2015-10-01

申请号：US14625466

申请日：2015-02-18

Applicant: HITACHI HIGH-TECHNOLOGIES CORPORATION

Inventor： Masayoshi ISHIKAWA ,  Hideaki SUZUKI ,  Tomoaki HIRUTA ,  Toshio MASUDA ,  Ken KIKEGAWA

IPC: G07C5/08 ,  B60K35/00 ,  G06Q10/00

CPC classification number: G07C5/0808 ,  B60K35/00 ,  G05B23/0281 ,  G06Q10/20

Abstract: Selection of sensors requires the knowledge of individual sensors mounted on a target machine and the knowledge of mechanical features of the machine. In the past, experts having mechanical knowledge selected the sensors. The present invention involves analyzing sensor data at e of machine failure, extracting features from the sensor data regarding each failure cause, and comparing the extracted features so as to clarify the difference between the sensor data about the failure causes and present an operator with the clarified difference thereby to support sensor selection. The invention makes it possible to select more simply than before the sensors considered effective for classifying failure causes. For example, the sensors deemed effective for classifying failure causes without mechanical knowledge can be selected.

Abstract translation: 传感器的选择需要知道安装在目标机器上的各个传感器以及机器机械特性的知识。 过去，拥有机械知识的专家选择了传感器。 本发明涉及在机器故障的e处分析传感器数据，从传感器数据中提取关于每个故障原因的特征，并比较所提取的特征，以便澄清关于故障原因的传感器数据之间的差异，并向操作者呈现澄清 差异从而支持传感器选择。 本发明使得可以比在认为对分类故障原因有效的传感器之前更简单地进行选择。 例如，可以选择对于没有机械知识来分类故障原因的有效传感器。

公开(公告)号：US20190228522A1

公开(公告)日：2019-07-25

申请号：US16252061

申请日：2019-01-18

Applicant: Hitachi High-Technologies Corporation

Inventor： Shinichi SHINODA ,  Masayoshi ISHIKAWA ,  Yasutaka TOYODA ,  Yuichi ABE ,  Hiroyuki SHINDO

IPC: G06T7/00 ,  G06N20/00 ,  G06K9/20 ,  G06K9/03

Abstract: The image evaluation device includes a design data image generation unit that images design data; a machine learning unit that creates a model for generating a design data image from an inspection target image, using the design data image as a teacher and using the inspection target image corresponding to the design data image; a design data prediction image generation unit that predicts the design data image from the inspection target image, using the model created by the machine learning unit; a design data image generation unit that images the design data corresponding to the inspection target image; and a comparison unit that compares a design data prediction image generated by the design data prediction image generation unit and the design data image. As a result, it is possible to detect a systematic defect without using a defect image and generating misinformation frequently.

公开(公告)号：US20190295827A1

公开(公告)日：2019-09-26

申请号：US16287679

申请日：2019-02-27

Applicant: Hitachi High-Technologies Corporation

Inventor： Takeshi OHMORI ,  Hyakka NAKADA ,  Naoyuki KOFUJI ,  Masayoshi ISHIKAWA ,  Masaru KURIHARA

IPC: H01J37/32 ,  G06N5/02 ,  G05B19/4155

Abstract: The efficiency of operation in a semiconductor processing apparatus is improved. In order to search an input parameter value to be set in a semiconductor processing apparatus for processing into a target processed shape, a predictive model indicating a relationship between an input parameter value and an output parameter value is generated based on the input parameter value and the output parameter value which is a measured value of a processing result processed by setting the input parameter value in the semiconductor processing apparatus. In this case, when the measured value of the processing result processed by the semiconductor processing apparatus is the defective data, the predictive model is generated based on the input parameter value causing defective data and defective substitute data obtained by substituting the measured value which is the defective data.