公开(公告)号：US20130245975A1

公开(公告)日：2013-09-19

申请号：US13720389

申请日：2012-12-19

Applicant: FUJITSU LIMITED

Inventor： Takashi KOBAYASHI ,  Mitsunobu OKANO ,  Shogo FUJIMORI ,  Hiroyuki ORIHARA

IPC: G01R19/00

CPC classification number: G01R19/0084 ,  G01R13/02

Abstract: A drawing device includes a memory and a processor coupled to the memory. The processor executes a process including measuring voltages of planes of layers in a laminated circuit board and drawing the voltages of the planes that are measured on a graph having a voltage set on one axis and having a layer set on the other axis.

Abstract translation: 绘图装置包括存储器和耦合到存储器的处理器。 处理器执行包括测量层叠电路板中的层的电压的电压并绘制在具有设定在一个轴上的电压并且具有另一轴上的层的图上测量的平面的电压的处理。

公开(公告)号：US20220129607A1

公开(公告)日：2022-04-28

申请号：US17468810

申请日：2021-09-08

Applicant: FUJITSU LIMITED

Inventor： Takashi YAMAZAKI ,  Shohei Yamane ,  Hiroaki Yamada ,  Masatoshi OGAWA ,  Yoichi Kochibe ,  Toshiyasu OHARA ,  Takashi KOBAYASHI

IPC: G06F30/27 ,  G06F30/367

Abstract: The present invention relates to a machine learning program for causing a computer to execute a process. In an example, the process executed by the computer when the program is executed includes: acquiring a current distribution image by an equivalent circuit simulation based on circuit information; acquiring a shape image that indicates a shape of a circuit based on the circuit information; acquiring an EMI value by electromagnetic field analysis based on the circuit information; and generating an EMI prediction model by machine learning based on training data that includes the current distribution image, the shape image, and the EMI value.

公开(公告)号：US20230252356A1

公开(公告)日：2023-08-10

申请号：US18193724

申请日：2023-03-31

Applicant: FUJITSU LIMITED

Inventor： Hiroaki YAMADA ,  Takashi YAMAZAKI ,  Shohei YAMANE ,  Takashi KOBAYASHI ,  Yoichi KOCHIBE ,  Toshiyasu OHARA

IPC: G06N20/00

CPC classification number: G06N20/00

Abstract: A non-transitory computer-readable recording medium storing a training data generation program for causing a computer to perform processing including: obtaining circuit information; determining whether or not a relationship between a distance between two lines included in the circuit information and a distance between the two lines and a GND layer satisfies a condition; when the relationship satisfies the condition, generating first current distribution information associated with the two lines by simulation and generating training data for machine learning based on the first current distribution information; and when the relationship does not satisfy the condition, generating second current distribution information associated with the two lines by synthesizing pieces of current distribution information associated with the respective two lines and generating the training data for machine learning based on the second current distribution information.

公开(公告)号：US20170068532A1

公开(公告)日：2017-03-09

申请号：US15229580

申请日：2016-08-05

Applicant: FUJITSU LIMITED

Inventor： Takashi KOBAYASHI

IPC: G06F9/445 ,  H04L29/08 ,  G06F9/44

CPC classification number: G06F8/65 ,  G06F8/71 ,  H04L67/34

Abstract: A management apparatus that manages data centers specifies a version of software to be used by a user. The management apparatus determines whether or not the software of the version specified is held in a first data center to be used by the user. The management apparatus instructs the first data center to download the software of the version from a second data center that holds the software of the version when the software of the version is not held in the first data center.

Abstract translation: 管理数据中心的管理装置指定要由用户使用的软件的版本。 管理装置确定指定的版本的软件是否被保存在用户要使用的第一数据中心内。 当版本的软件没有保持在第一数据中心时，管理装置指示第一数据中心从保存版本的软件的第二数据中心下载版本的软件。

公开(公告)号：US20220341979A1

公开(公告)日：2022-10-27

申请号：US17676828

申请日：2022-02-22

Applicant: FUJITSU LIMITED

Inventor： Shohei YAMANE ,  Yoichi KOCHIBE ,  Hiroaki YAMADA ,  Takashi YAMAZAKI ,  Takashi KOBAYASHI ,  Masatoshi OGAWA

IPC: G01R29/08 ,  G01R31/00

Abstract: A non-transitory computer-readable storage medium storing a n EMI calculation program that causes at least one computer to execute a process, the process includes inputting circuit information of a first circuit to a machine learning model; acquiring an EMI value at a certain frequency of the first circuit; selecting, based on an impedance characteristic of the first circuit and the EMI value at the certain frequency, first EMI information from a plurality of pieces of EMI information in each of which an impedance characteristic of each of a plurality of circuits is associated with EMI values at a plurality of frequencies of each of the plurality of circuits; and acquiring an EMI value at another frequency different from the certain frequency of the first circuit based on the EMI value at the certain frequency and the first EMI information.