中科微点-全球专利检索

  1. Login
  2. Sign Up

Search Results

10 records (took 0.009 seconds)

    METHOD AND APPARATUS FOR OPERATING AN AUTOMATION SYSTEM
    1.
    发明申请
    METHOD AND APPARATUS FOR OPERATING AN AUTOMATION SYSTEM 审中-公开
    运行自动化系统的方法和装置

    公开(公告)号：WO2016165923A1

    公开(公告)日：2016-10-20

    申请号：PCT/EP2016/056512

    申请日：2016-03-24

    Applicant: SIEMENS AKTIENGESELLSCHAFT

    Inventor： LAMPARTER, Steffen ,  LEPRATTI, Raffaello ,  RINGSQUANDL, Martin

    IPC: G06N7/06 ,  G06N5/02

    CPC classification number: G06N5/04 ,  G05B19/41875 ,  G05B2219/31368 ,  G05B2219/33002 ,  G05B2219/34351 ,  G06N5/022 ,  G06N99/005

    Abstract: The present invention relates generally to a method and an apparatus for operating an automation system. The method for operating an automation system comprises the method steps of: a) providing a learning-based prediction model (M) for the automation system trained by process data (D) comprising context of an automation process, b) receiving information about current context of the automation process, c) verifying context change by comparing the current context to the context of said process data, d) in the case of any context change verifying a concept drift by comparing pre-drift process data and post-drift process data, e) in the case of any concept drift re-training said model (M) with post-drift process data, f) in the case of no context change testing for random concept drift not detected by verifying context change, g) in the case of any random concept drift extend the current context by using data comprising previous context changes, h) otherwise no further method steps are required.

    Abstract translation: 本发明一般涉及用于操作自动化系统的方法和装置。 用于操作自动化系统的方法包括以下方法步骤：a）为由包括自动化过程的上下文的过程数据（D）训练的自动化系统提供基于学习的预测模型（M），b）接收关于当前上下文的信息 c）通过将当前上下文与所述过程数据的上下文进行比较来验证上下文变化，d）在通过比较预漂移过程数据和后漂移过程数据来验证概念漂移的任何上下文变化的情况下， e）在任何概念漂移的情况下，使用后漂移过程数据重新训练所述模型（M），f）在没有通过验证上下文变化来检测到随机概念漂移的上下文变化测试的情况下，g）在这种情况下 任何随机概念漂移通过使用包括先前上下文变化的数据来扩展当前上下文，h）否则不需要进一步的方法步骤。

    METHOD AND APPARATUS FOR EFFICIENT USE OF CNC MACHINE SHAPING TOOL INCLUDING CESSATION OF USE NO LATER THAN THE ONSET OF TOOL DETERIORATION BY MONITORING AUDIBLE SOUND DURING SHAPING
    2.
    发明申请
    METHOD AND APPARATUS FOR EFFICIENT USE OF CNC MACHINE SHAPING TOOL INCLUDING CESSATION OF USE NO LATER THAN THE ONSET OF TOOL DETERIORATION BY MONITORING AUDIBLE SOUND DURING SHAPING 审中-公开
    有效使用数控机床成形工具的方法和设备，包括在使用后停止使用，而不是通过在成形期间监测可听声音来检测工具是否失效

    公开(公告)号：WO2017192821A1

    公开(公告)日：2017-11-09

    申请号：PCT/US2017/031011

    申请日：2017-05-04

    Applicant: MASSACHUSETTS INSTITUTE OF TECHNOLOGY

    Inventor： JEONG, Hyunsoo

    IPC: B23Q17/09 ,  G05B19/4065

    CPC classification number: B23Q17/098 ,  G05B19/4065 ,  G05B2219/33002 ,  G05B2219/37337

    Abstract: A CNC machine shaping tool is efficiently used by monitoring human audible sound during shaping. A sound information set is created for a tool shaping a workpiece. Shaping sounds are recorded and sliced into short term units. A human operator assigns tool condition labels to each slice. Short term units are combined into mid term units. Noise is reduced by profiling. Mid term sound related features of time and frequency domains are extracted. Dimensionality is reduced by robust principal component analysis. The principal component set is balanced, e.g. by SMOTE. A classifier and principal components are selected. An information set of patterns of values of selected principal components for the tool is created. In an industrial setting, shaping sounds are recorded, noise reduced and select principal component vector values are compared to the tool condition labeled patterns of values in the information set to identify tool condition before deterioration.

    Abstract translation: 通过在成型期间监控人类可听见的声音，CNC机器成形工具被有效地使用。 为工件成形工具创建一个声音信息集。 塑造声音被记录并切成短期单位。 操作人员为每个切片分配工具状态标签。 短期单位合并成中期单位。 通过分析来降低噪音。 提取时间和频率域的中期声音相关特征。 稳健的主成分分析降低了维度。 主成分集是平衡的，例如， 由SMOTE。 分类器和主要组件被选中。 创建该工具的选定主要组件的值的模式信息集。 在工业环境中，记录塑形声音，减少噪音，并选择主要成分矢量值与信息组中标记的数值模式的工具条件进行比较，以确定变质前的工具状态。

    VIRTUAL MOTION PROGRAMMING AND CONTROL
    3.
    发明申请
    VIRTUAL MOTION PROGRAMMING AND CONTROL 审中-公开
    虚拟运动编程与控制

    公开(公告)号：WO1997020280A1

    公开(公告)日：1997-06-05

    申请号：PCT/US1996018706

    申请日：1996-11-13

    Applicant: COARD TECHNOLOGY doing business as WESTREX

    Inventor： COARD TECHNOLOGY doing business as WESTREX ,  MOTOC, Bogdan

    IPC: G06F19/00

    CPC classification number: B25J9/1664 ,  G05B19/416 ,  G05B2219/31193 ,  G05B2219/33002 ,  G05B2219/36171 ,  G05B2219/37388 ,  G05B2219/39244 ,  G05B2219/43051 ,  G05B2219/43168 ,  Y10S706/90

    Abstract: An object oriented approach to virtual motion programming utilizes generic motion identifiers to construct universal generic motion descriptions (102) of complex motien events. A virtual motion controller (110) receives generic motion descriptions and breaks down the descriptions into their constituent parts. The controller (110) expands the generic motion identifiers into general acceleration profiles and processes the general acceleration profiles with the modifiers to generate ideal acceleration profiles that define the acceleration components for the generic motion description with reference to an ideal motion platform (38) having unlimited mechanical movement. The controller (110) translates the ideal acceleration profiles into customized position commands for the motion platform based upon the controller's knowledge of the platform's capabilities.

    Abstract translation: 虚拟运动编程的面向对象方法利用通用运动标识符构建复杂运动事件的通用运动描述（102）。 虚拟运动控制器（110）接收通用运动描述并将描述分解成其组成部分。 控制器（110）将通用运动标识符扩展成通用加速度分布，并且利用修改器处理一般加速度分布以产生理想的加速度分布，其参考具有无限制的理想运动平台（38）来定义通用运动描述的加速度分量 机械运动。 基于控制器对平台能力的了解，控制器（110）将理想加速度分布转换成用于运动平台的定制位置命令。

    METHOD OF AUTOMATICALLY RETRIEVING WORKING CONDITIONS IN ELECTRIC DISCHARGE
    5.
    发明申请
    METHOD OF AUTOMATICALLY RETRIEVING WORKING CONDITIONS IN ELECTRIC DISCHARGE 审中-公开
    自动回收电力放电工作条件的方法

    公开(公告)号：WO1992005005A1

    公开(公告)日：1992-04-02

    申请号：PCT/JP1991001215

    申请日：1991-09-12

    Applicant: FANUC LTD ,  SAKURAGAWA, Tomonobu ,  ASO, Toshiyuki

    Inventor： FANUC LTD

    IPC: B23H07/20

    CPC classification number: G05B19/40937 ,  B23H7/065 ,  B23H7/20 ,  G05B2219/33002 ,  G05B2219/37081 ,  G05B2219/45221 ,  Y02P90/265

    Abstract: A method of automatically retrieving working conditions in an electric discharge machine, wherein the said method is built up on the basis of an expert system and, even by an unskilled operator, optimal working conditions in the electric discharge machine can be set. A source knowledge base (6) prepared on the basis of the knowledge and experience of an expert (5) an including data on working conditions and production rules is converted into an object knowledge base (3) by a compiler (4), and subsequently, the knowledge base (3) together with an inference engine (2) are stored in a computer-incorporating type numerical control device (10) equipped on the electric discharge machine. When the operator (1) inputs the retrieving conditions including the diameter of the wire, the material quality of the work, the plate thickness of the work, the desirable mean working speed, the surface roughness, the working accuracy and the like via a manual input data device (25) in order to perform automatic retrieving of the working conditions, the inference engine successively processes the production rules relating to the retrieving conditions while utilizing the data on the working conditions relating to the production rules, retrieves the working conditions suitable for the retrieving conditions and displays them on a display screen.

    逻辑拓扑网络模型、人工智能控制方法及人工智能系统
    7.
    发明申请
    逻辑拓扑网络模型、人工智能控制方法及人工智能系统 审中-公开

    公开(公告)号：WO2011116673A1

    公开(公告)日：2011-09-29

    申请号：PCT/CN2011/071995

    申请日：2011-03-21

    Applicant: 林定伟

    Inventor： 林定伟

    IPC: G05B13/00

    CPC classification number: H04L41/12 ,  G05B2219/33002 ,  H04L41/16 ,  H04W40/026

    Abstract: 本发明公开了一种逻辑拓扑网络模型、人工智能控制方法及人工智能系统，所述方法包括：获取各个逻辑节点，连接具有因果关系的逻辑节点，建立逻辑拓扑网络模型；接收输入的文字信息，从所述逻辑拓扑网络模型中扫描出起点逻辑节点和终点逻辑节点，该起点逻辑节点是包括所述文字信息的逻辑节点，该终点逻辑节点是与所述起点逻辑节点具有因果关系的逻辑节点；显示扫描出的终点逻辑节点和起点逻辑节点间的连接路径。本发明可以建立逻辑拓扑网络模型，根据用户输入的文字信息扫描出起点逻辑节点和终点逻辑节点，该终点逻辑节点和起点逻辑节点间的连接路径即为解决问题的办法，起到了模拟人解决日常问题的作用。

    A METHOD FOR CONTROLLING A SUPPLY CHAIN
    8.
    发明申请
    A METHOD FOR CONTROLLING A SUPPLY CHAIN 审中-公开
    一种控制供应链的方法

    公开(公告)号：WO2010083592A1

    公开(公告)日：2010-07-29

    申请号：PCT/CA2010/000074

    申请日：2010-01-21

    Applicant: SICARD, Paul

    Inventor： SICARD, Paul

    IPC: G06Q10/00 ,  G06N5/00

    CPC classification number: G05B19/4183 ,  G05B19/41865 ,  G05B2219/31324 ,  G05B2219/33002 ,  G06Q10/083 ,  Y02P90/10 ,  Y02P90/20

    Abstract: The present document describes a method, a processor platform and a processor readable medium for controlling a supply chain for moving goods by agents according to orders. The method is for controlling globally and/or individually, and for optimizing based on live events, in real-time, in a single or multi company environment, simultaneously many well known business activities such as customer relationship management (CRM), pickup calls phone services, scheduling, monitoring of picking up and delivery of parcels and operations status, of transfer, of terminal, of interleaving and of deliveries, human resource management, pricing, maintenance, engine monitoring, device monitoring and invoicing, offering thus integrated solutions to each segment of the market of goods transportation in a single system. The method comprises: updating a knowledge base populated with statuses of the goods; statuses of the agents; rules for establishing expected behaviors of the goods and of the agents; and the orders. The method further comprises: determining, based on the knowledge base, instructions to be executed by the agents for moving the goods to achieve the orders, each one of the instructions having an expected completion duration; sending the instructions to the agents; receiving the instructions for execution by the agents; upon completion an instruction by an agent or when an event affects an instruction executed by an agent, the same agent sending the status of a good or its own status to the knowledge base; and returning to the updating a knowledge base, wherein each elapsed time between each agent sending the status of a good or its own status to the knowledge base and the same agent receiving an instruction is smaller that the expected completion duration of the same instruction.

    Abstract translation: 本文件描述了一种方法，处理器平台和处理器可读介质，用于根据订单控制代理商移动商品的供应链。 该方法用于全球和/或单独控制，并且可以在单个或多个公司环境中实时基于实时事件进行优化，同时还可以进行许多知名的业务活动，例如客户关系管理（CRM），接听电话 服务，调度，包裹运送和运输状况，运输，终端，交付和交货，人力资源管理，定价，维护，发动机监控，设备监控和发票的运输状况监测，为每个 货物运输市场在一个单一的系统。 该方法包括：更新填充有货物状态的知识库; 代理人的身份; 建立商品和代理人预期行为的规则; 和订单。 该方法还包括：基于知识库确定要由代理人执行的用于移动货物以实现订单的指令，每个指令具有预期的完成持续时间; 发送指示给代理人; 接收代理人执行的指示; 完成后，代理人的指示或当事件影响代理执行的指令时，同一代理人将知情状态或其自身状态发送给知识库; 并且返回到更新知识库，其中，每个向知识库发送一个好的状态或其本身状态的代理和接收指令的相同代理之间的经过时间小于相同指令的预期完成持续时间。

    DIAGNOSTIC NETWORK WITH AUTOMATED PROACTIVE LOCAL EXPERTS
    9.
    发明申请
    DIAGNOSTIC NETWORK WITH AUTOMATED PROACTIVE LOCAL EXPERTS 审中-公开
    具有自动化的本地专家的诊断网络

    公开(公告)号：WO01050099A1

    公开(公告)日：2001-07-12

    申请号：PCT/US2000/013521

    申请日：2000-05-17

    IPC: G01H1/00 ,  G05B19/4063 ,  G05B19/418

    CPC classification number: G05B19/4185 ,  G01H1/003 ,  G05B19/4063 ,  G05B2219/31151 ,  G05B2219/31156 ,  G05B2219/31158 ,  G05B2219/33002 ,  G05B2219/33284 ,  G05B2219/37351 ,  G05B2219/37434 ,  G05B2219/37435 ,  Y02P90/18 ,  Y02P90/86

    Abstract: A method is provided for invoking condition monitoring among a plurality of machines, comprising establishing a network of automated local experts at generally fixed locations and interconnected by at least one network connection ,configuring each of the local experts to receive vibration data from at least one of the plurality of machines which is located in relative physical proximity thereto and configuring each of the local experts to analyze the received vibration data and to diagnose a condition of the machine providing the received vibration data based on the received vibration, and configuring each of the local experts to transmit diagnostic information relating to the condition of the respective machines via the at least one network connection.

    Abstract translation: 提供了一种用于在多个机器之间调用状态监视的方法，包括：在大体上固定的位置建立自动化本地专家的网络并通过至少一个网络连接互连，配置每个本地专家以从以下各项中的至少一个接收振动数据： 所述多个机器位于相对物理接近处，并且配置每个本地专家以分析所接收的振动数据，并且基于接收到的振动来诊断提供接收到的振动数据的机器的状况，并且配置每个本地 专家通过至少一个网络连接传送与各个机器的状况有关的诊断信息。

Patent Agency Ranking