公开(公告)号：WO2023064498A1

公开(公告)日：2023-04-20

申请号：PCT/US2022/046615

申请日：2022-10-13

Applicant: EMORY UNIVERSITY

Inventor： PANDARINATH, Chethan ,  WIMALASENA, Lahiru Neth ,  KESHTKARAN, Mohammadreza

IPC: A61B5/00 ,  A61B5/11 ,  G05B13/04

Abstract: Systems and methods that use data augmentation during the training of representation learning networks on neuromuscular data (e.g., EMG) with reconstruction cost. The method may include training network(s) on neuromuscular data received from channel(s) of neuromuscular sensor(s). The training may include randomly generating a first augment and a different, second augment for each channel. The training may include augmenting the data of each channel by applying the first and second augments to the data to generate first and second augmented data. The training may include processing at least the first augmented data through at least a first representation learning neural network to determine a first latent representation of one or more neuromuscular activation state variables. The training may include determining a reconstruction cost using the first latent representation and the second augmented data. The training may include updating the first representation learning neural network based on the reconstruction cost.

公开(公告)号：WO2023046699A1

公开(公告)日：2023-03-30

申请号：PCT/EP2022/076131

申请日：2022-09-20

Applicant: JOHN, Jean Pascal

Inventor： JOHN, Jean Pascal

IPC: G05B13/02 ,  G05B15/02 ,  G05B13/04

Abstract: Described is a set of computer readable data (400, 500) with relation to operating states of a device (200, 300), comprising: - request data (400) which forms a request to a data processing device (100), wherein the request data comprises data elements (DE1 to DE18) comprising raw data or pre-processed data representing operating states of the device (200, 300) in a chronological sequence, wherein the data elements comprise at least one physical parameter of the device (200, 300) or of a physical medium produced by the device (200, 300) and by at least one further parameter, wherein the at least one physical parameter and the at least one further parameter relate to other aspects than physical time or duration between two events, and - answer data (500) which form the answer of the data processing device (100) to a request of a user based on the request data (400), wherein the answer data comprises operating point data of operating points (OP_1 to OP_13) of the device (200, 300), wherein the operating points (OP_1 to OP_13) are defined by a respective value of the at least one physical parameter of the device (200, 300) or of physical medium (e.g. product) produced by the device (200, 300) and by a respective value of the at least one further parameter, and wherein the answer data defines a composed series of operating points (OP_1, OP_2, OP_4) comprising: - a first portion of the composed series of operating points (OP_1, OP_2) that is based on data elements (DE1 to DE11) of a first portion of the chronological series, and - a second portion of the composed series of operating points (OP_2, OP_4) that is based on data elements (DE1 to DE11) of a second portion of the chronological sequence, and wherein the composed series of operating points (OP_1, OP_2) is a recombination of portions of the chronological sequence of operating states.

公开(公告)号：WO2023044878A1

公开(公告)日：2023-03-30

申请号：PCT/CN2021/120801

申请日：2021-09-26

Applicant: 西门子股份公司 ,  西门子（中国）有限公司

Inventor： 王子健 ,  范顺杰

IPC: G05B13/04

Abstract: 一种运动控制方法（100），包括：确定受控对象的运动控制模型（211），根据运动控制模型（211）训练一在线强化学习模型（223），运动控制模型（211）输出一模型控制值，受控对象根据模型控制值和在线强化学习模型（223）输出的初始控制值产生一反馈值（110）；利用模型控制值和反馈值计算奖励（120）；在线强化学习模型（223）根据奖励、模型控制值和反馈值生成一残差控制值，根据残差控制值和模型控制值控制受控对象运动（130）。

公开(公告)号：WO2022262362A1

公开(公告)日：2022-12-22

申请号：PCT/CN2022/084301

申请日：2022-03-31

Applicant: 江南大学

Inventor： 陶洪峰 ,  周龙辉 ,  庄志和 ,  黄彦德 ,  魏俊誉 ,  王瑞

IPC: G05B13/04

Abstract: 本发明公开了一种多质点车辆队列行驶系统的迭代学习控制方法，涉及迭代学习控制领域，该方法包括：首先利用有限差分法对多质点列车动力学方程进行离散化得到偏递推方程，然后将其转化为空间互联系统模型；其次，使用提升技术将空间互联系统模型转换为等价的一维动态模型，为补偿输入时滞，基于状态观测器设计迭代学习律；再次，根据迭代学习律将被控对象转化为等价的离散重复过程，基于重复过程的稳定性分析将控制器综合问题转换成线性矩阵不等式。该方法简单易于实现，解决了输入时滞引起的系统输出响应滞后的问题，并且考虑了系统的结构不确定性，具有良好的控制性能与鲁棒性。

公开(公告)号：WO2022215300A1

公开(公告)日：2022-10-13

申请号：PCT/JP2021/047454

申请日：2021-12-15

Applicant: MITSUBISHI ELECTRIC CORPORATION

Inventor： DI CAIRANO, Stefano ,  BONZANINI, Angelo Domenico ,  MESBAH, Ali

IPC: G06V20/58 ,  G05B13/04

Abstract: A controller of a machine determines jointly a sequence of control inputs defining a state trajectory of the machine and a desired knowledge of the environment by solving a multivariable constrained optimization of a model of dynamics of the machine relating the state trajectory with the sequence of control inputs subject to a constraint on admissible values of the states and the control inputs defined based on the desired knowledge of the surrounding environment represented by the state of the environment and the uncertainty of the state of the environment determined from the measurements of the environment. In such a manner, the controller performs joint but imbalance optimization of the control inputs and the sensing instructions to the sensor for learning the environment.

公开(公告)号：WO2022205840A1

公开(公告)日：2022-10-06

申请号：PCT/CN2021/125039

申请日：2021-10-20

Applicant: 深圳市优必选科技股份有限公司

Inventor： 周江琛 ,  麻星星 ,  刘益彰 ,  陈春玉 ,  熊友军

IPC: B25J9/16 ,  B62D57/032 ,  G05B13/04

Abstract: 一种机器人（5）及其步态控制方法和装置，该方法包括：获取机器人（5）在当前时刻的状态信息；根据所述状态信息，结合机器人（5）的参考轨迹，确定预先设定的三质点的步态优化模型对应的优化目标函数和约束模型；根据优化目标函数和约束模型，确定机器人（5）的优化的躯干质心轨迹和摆动腿轨迹；根据优化的躯干质心轨迹和摆动腿轨迹对机器人（5）进行步态控制。由于在进行步态控制时联合了摆动腿轨迹和躯干质心轨迹，与仅采用调整落脚点位置的方法相比，能够更好的承受外界干扰，提高机器人移动的稳定性。

公开(公告)号：WO2022169420A1

公开(公告)日：2022-08-11

申请号：PCT/SG2022/050052

申请日：2022-02-04

Applicant: SINGAPORE UNIVERSITY OF TECHNOLOGY AND DESIGN

Inventor： MANI IYER RAMANI, Gauthama Raman ,  MATHUR, Aditya

IPC: G05B13/04 ,  G06F21/55 ,  G06N5/00 ,  G05B19/418

Abstract: The present disclosure generally relates to a system (300) and method detecting anomalies in an industrial control system (100). The anomaly detection method comprises: determining state variables of the industrial control system (100) based on a system design (312) of the industrial control system (100); determining invariants governing the state variables based on the system design (312); receiving historical measurement data of the state variables of each invariant from the industrial control system (100); constructing a set of behavioural models (330,340) for each invariant using a set of machine learning algorithms and the historical measurement data of the respective state variables of the invariant, the behavioural models (330,340) representing normal behaviour of the respective state variables; predicting measurement data of the state variables of each invariant using the behavioural models and the historical measurement data of the respective state variables; receiving current measurement data of the state variables during operation of the industrial control system (100); and detecting the anomalies based on deviations between the current measurement data and predicted measurement data of the state variables of each invariant.

公开(公告)号：WO2022167522A1

公开(公告)日：2022-08-11

申请号：PCT/EP2022/052580

申请日：2022-02-03

Applicant: FRAUNHOFER-GESELLSCHAFT ZUR FÖRDERUNG DER ANGEWANDTEN FORSCHUNG E.V.

Inventor： NEVES PIMENTA, Daniel ,  DE BOER, Jan ,  WÖSSNER, Simon ,  KOUTSOMARKOS, Konstantinos

IPC: G06F30/13 ,  G05B13/04 ,  G05B17/00 ,  G06G7/68 ,  G09B25/04 ,  G06F30/31

Abstract: Die Erfindung betrifft ein Verfahren zur Simulation eines Komforterlebnisses in einem Raum (2), enthaltend die folgenden Schritte: Erstellen eines digitalen Modells A des Raumes (2); Definieren von Innen- und/oder Außenbedingungen YR, XR, welche auf den Raum einwirken; Berechnen eines ersten Komforterlebniss KR für zumindest einen Ort innerhalb des Raumes (2); Bereitstellen einer Testumgebung (1), welche zumindest einen Aktor (11, 12, 13, 14, 18, 19, 4) enthält, welcher auf einen Proband (3) einwirkt; Ändern des Zustands XMR des zumindest einen Aktors (11, 12, 13, 14, 18, 19, 4), so dass ein zweites Komforterlebnis KMR des Probanden (3) in der Testumgebung (1) im Wesentlichen dem ersten Komforterlebnis KR an dem zumindest einen Ort innerhalb des Raumes (2) entspricht. Weiterhin betrifft die Erfindung einen Datenträger mit darauf gespeicherten Daten und eine Testumgebung (1) zur Simulation eines Komforterlebniss.

公开(公告)号：WO2022166919A1

公开(公告)日：2022-08-11

申请号：PCT/CN2022/075157

申请日：2022-01-30

Applicant: 中国农业大学

Inventor： 李保明 ,  王阳 ,  郑炜超 ,  童勤

IPC: G05D27/02 ,  G05B13/04

Abstract: 一种畜禽舍养殖环境温度预测控制系统及其调控方法，控制系统包括：温湿度传感器、养殖环境温度动态需求模块、环境控制器和环境调控执行机构；其中，环境控制器分别连接养殖环境温度动态需求模块和温湿度传感器，环境调控执行机构连接环境控制器，并根据环境控制器的命令执行相应环境调控；调控方法根据畜禽养殖环境温度动态设定模型、基于GM(1,1)模型的畜禽舍养殖环境温度预测系统和基于GM(1,1)模型的灰色预测模糊系统控制养殖环境温度。解决了畜禽舍内温度难以及时调控、调控适应性差及不能做到防患于未然的问题，克服了畜禽舍基于检测结果的反馈式调控的局限。

公开(公告)号：WO2022147275A1

公开(公告)日：2022-07-07

申请号：PCT/US2021/065714

申请日：2021-12-30

Applicant: SCHNEIDER ELECTRIC SYSTEMS USA, INC.

Inventor： MILLER, Randy Marvin ,  APPLE, Stephen Mark

IPC: G07C5/08 ,  E02F9/26 ,  G05B13/02 ,  G05B13/04 ,  G06F17/18 ,  G06N99/00

Abstract: Systems and methods for providing operator variation analysis for an industrial operation are disclosed herein. In one aspect of this disclosure, a method for providing operator variation analysis includes processing input data received from one or more data sources to identify transient or non-steady state process data relating to the industrial operation and selecting one or more types of data in the transient or non-steady state process data to cluster for operator variation analysis. The one or more types of data are clustered using one or more data clustering techniques, and the clustered one or more types of data are analyzed to identify a best operator of a plurality of operators responsible for managing the industrial operation. Information is analyzed to determine if one or more gaps exist in the economic operation of the industrial operation due to operator variability between the best operator and other operators.