Feed-forward (e.g., Predictive) Patents (Class 700/44)
  • Patent number: 11106997
    Abstract: An online system uses multiple machine learning models to select content for providing to a user of the online system. Specifically, the online system trains a general model that intakes a first set of features and outputs predictions at a general level. The online system further trains a residual model that intakes a second set of features. The residual model predicts a residual (e.g., an error) of the predictions outputted by the general model. Therefore, the predicted residual from the residual model is combined with the prediction from the general model in order to correct for the over-generality of the general model. The online system may use the combined prediction to send content to users.
    Type: Grant
    Filed: September 29, 2017
    Date of Patent: August 31, 2021
    Assignee: Facebook, Inc.
    Inventors: Andrew Donald Yates, Gunjit Singh, Kurt Dodge Runke
  • Patent number: 11030551
    Abstract: The dynamic complexity and the operational risk inherent in a system are defined and incorporated into a mathematical model of the system. The mathematical model is emulated to predict the states of instability that can occur within the operation of the system. Dynamic complexity of a service is demonstrated where there is an observed effect where the cause can be multiple and seemingly inter-related effects of a many-to-one or many-to-many relationship. Having assessed the dynamic complexity efficiency and the operational risk index of a service (e.g., a business, process or information technology), these indexes can be employed to emulate all attributes of a service, thereby determining how a service responds in multiple states of operation, the states where the dynamic complexity of a service can occur, optimal dynamic complexity efficiency of a service, and the singularities wherein a service becomes unstable.
    Type: Grant
    Filed: April 1, 2020
    Date of Patent: June 8, 2021
    Assignee: X-ACT SCIENCE INC.
    Inventor: Nabil A. Abu El Ata
  • Patent number: 11023235
    Abstract: Embodiments detailed herein relate to systems and methods to zero a tile register pair. In one example, a processor includes decode circuitry to decode a matrix pair zeroing instruction having fields for an opcode and an identifier to identify a destination matrix having a PAIR parameter equal to TRUE; and execution circuitry to execute the decoded matrix pair zeroing instruction to zero every element of a left matrix and a right matrix of the identified destination matrix.
    Type: Grant
    Filed: December 29, 2017
    Date of Patent: June 1, 2021
    Assignee: Intel Corporation
    Inventors: Raanan Sade, Simon Rubanovich, Amit Gradstein, Zeev Sperber, Alexander Heinecke, Robert Valentine, Mark J. Charney, Bret Toll, Jesus Corbal, Elmoustapha Ould-Ahmed-Vall, Menachem Adelman, Eyal Hadas
  • Patent number: 10977281
    Abstract: A method of determining a requirements characterization profile for an entity is disclosed. The method comprises the steps of receiving classification parameters defining a requirement for an entity and selecting, in dependence on the classification parameters, a set of entities from a database of previously assessed entities. The method further comprises retrieving from the database characterization parameters of the selected set of entities, and constructing, in dependence on the characterization parameters, a requirements characterization profile for the entity. An apparatus is provided that comprised means for performing such a method.
    Type: Grant
    Filed: March 27, 2014
    Date of Patent: April 13, 2021
    Assignee: SHL Group Ltd
    Inventors: David Bartram, Steven John Fleck
  • Patent number: 10942837
    Abstract: Methods and apparatus are described by which time-series data captured during the automated testing of software applications may be analyzed. Change-point detection is used to partition the time-series data, and an expected variance of data within each partition is determined. Because the partitioning of the test data provides a high level of confidence that the data points in a given partition conform to the same distribution, data points that represent meaningful changes in application performance can be more confidently and efficiently identified.
    Type: Grant
    Filed: May 13, 2019
    Date of Patent: March 9, 2021
    Assignee: Sauce Labs Inc.
    Inventors: Fernando Vidal, Benjamin H Ellis
  • Patent number: 10929472
    Abstract: A parameter optimization method includes: a parameter search is performed on an input parameter, an output response value and a target value through a plurality of optimization schemes to search for a plurality of candidate recommended parameters. Each optimization scheme is assigned to a weight value according to user historical decision information. At least one recommended parameter is selected from the candidate recommended parameters according to the weight values. An user interface is provided for a user to input a decision instruction. A new input parameter is selected from the at least one recommended parameter according to the decision instruction; the new input parameter is inputted into the target system; and a new output response value is evaluated whether meets a specification condition. The user historical decision information is updated based on the decision instruction to adjust the weight values.
    Type: Grant
    Filed: December 28, 2017
    Date of Patent: February 23, 2021
    Assignee: Industrial Technology Research Institute
    Inventors: Po-Yu Huang, Hong-Chi Ku, Sen-Chia Chang, Te-Ming Chen, Pei-Yi Lo
  • Patent number: 10921755
    Abstract: According to some embodiments a competence module is provided to: receive an objective; select a machine learning model associated with the objective; receive data from the at least one data source; determine at least one next input based on the received data; determine whether the at least one next input is in a competent region or is in an incompetent region of the machine learning model; when the at least one next input is inside the competent region, generate an output; determine an estimate of uncertainty for the generated output; when the uncertainty is below an uncertainty threshold, the machine learning model is competent and when the uncertainty is above the uncertainty threshold, the machine learning model is incompetent; and operate the physical asset based on one of the competent and incompetent state of the machine learning model. Numerous other aspects are provided.
    Type: Grant
    Filed: December 17, 2018
    Date of Patent: February 16, 2021
    Assignee: GENERAL ELECTRIC COMPANY
    Inventors: Nurali Virani, Abhishek Srivastav
  • Patent number: 10901374
    Abstract: The settling time of machine learning is shortened. A machine learning device is configured to perform machine learning related to optimization of coefficients of a transfer function of an IIR filter of a feedforward calculation unit with respect to a servo control device configured to control a servo motor configured to drive an axis of a machine tool, a robot, or an industrial machine using feedforward control by a feedforward calculation unit having the IIR filter. The machine learning device represents a zero-point at which the transfer function of the IIR filter is zero and a pole at which the transfer function diverges infinitely in polar coordinates using a radius r and an angle ?, respectively, and searches for and learns, within a predetermined search range, the radius r and the angle ? to thereby perform the optimization of the coefficients of the transfer function of the IIR filter.
    Type: Grant
    Filed: June 10, 2019
    Date of Patent: January 26, 2021
    Assignee: FANUC CORPORATION
    Inventors: Ryoutarou Tsuneki, Satoshi Ikai, Naoto Sonoda
  • Patent number: 10877443
    Abstract: A system implements changes to improve control effectiveness. The system is typically configured for determining at least one stored control of a plurality of controls similar or identical to a present control from a control library comprising the plurality of controls; extracting a consideration set of indicators associated with the stored control from the control library; applying a regression algorithm on the consideration set of indicators; determining a threshold correlation or threshold number of indicators for inclusion in a final equation relating a subset of the consideration set of indicators with control effectiveness of the control; reducing a number of the subset of the consideration set of indicators based on the threshold correlation or threshold number; finalizing the final equation with the number of the subset, each having a corresponding coefficient; and automatically performing an action configured to improve effectiveness of the control based on the final equation.
    Type: Grant
    Filed: September 20, 2017
    Date of Patent: December 29, 2020
    Assignee: BANK OF AMERICA CORPORATION
    Inventor: Brandon Sloane
  • Patent number: 10871629
    Abstract: An imaging apparatus includes a clamp level is multiplied by a first feedback gain, and correct a signal of a part of photoelectric conversion portions of a unit pixel in an opening region based on a result of multiplication in which an error amount between a signal of a part of a photoelectric conversion portions of the unit pixel in a light-shielded region and a clamp level is multiplied by a second feedback gain, and thus the signal of the unit pixel can be corrected precisely.
    Type: Grant
    Filed: July 14, 2017
    Date of Patent: December 22, 2020
    Assignee: CANON KABUSHIKI KAISHA
    Inventor: Mineo Uchida
  • Patent number: 10867251
    Abstract: An estimation results display system that, in the case of displaying an estimation result derived using a learning model, enables persons to recognize how condition determination is performed to select the learning model is provided. Input means 91 receives input of information associating information indicating a learning model selected depending on a determination result of whether or not an attribute in estimation data including one or more types of attributes satisfies one or more types of conditions and an estimation result derived using the learning model. Display means 92 displays the estimation result, in association with the information indicating the learning model used for deriving the estimation result and a condition subjected to determination of whether or not satisfied by the attribute in the estimation data when selecting the learning model.
    Type: Grant
    Filed: April 30, 2015
    Date of Patent: December 15, 2020
    Assignee: NEC Corporation
    Inventor: Yousuke Motohashi
  • Patent number: 10860027
    Abstract: The present disclosure relates to a method of trajectory planning for maneuvers for an ego vehicle (E) equipped with a sensor systems, a prediction systems, a control system, and a decision-making system. The method includes determining possible lateral motion trajectories of a requested maneuver, longitudinal safety critical zones which correspond to each of the determined possible lateral motion trajectories, a longitudinal motion trajectory of the requested maneuver, lateral safety critical zones which correspond to the determined longitudinal motion trajectory of the requested maneuver, and a lateral motion trajectory of the requested maneuver. The present disclosure also relates to a driver assistance system arranged to perform the method and a vehicle including such a system.
    Type: Grant
    Filed: August 9, 2017
    Date of Patent: December 8, 2020
    Assignee: VOLVO CAR CORPORATION
    Inventor: Julia Nilsson
  • Patent number: 10810006
    Abstract: Embodiments of the present invention provide a system for indicator regression and modeling for implementing system changes to improve control effectiveness. The system is typically configured for presenting, prompting for and receiving a selection from a list of controls from a user, via a control effectiveness application user interface on a user device. The system is also for receiving two or more consideration indicators from the user device, via the control effectiveness application user interface forming a consideration set; applying a regression algorithm on the consideration set of indicators; reducing a number of the subset of the consideration set of indicators based on a threshold correlation or a threshold number; finalizing the final equation with the number of the subset, each having a corresponding coefficient; and, in response to finalizing the final equation, automatically performing an action configured to improve effectiveness of the control based on the final equation.
    Type: Grant
    Filed: August 28, 2017
    Date of Patent: October 20, 2020
    Assignee: BANK OF AMERICA CORPORATION
    Inventors: Brandon Sloane, John Brian Costello, Brian Diederich
  • Patent number: 10782673
    Abstract: A system and method for additive manufacturing of otherwise thermosetting polymers, such as PAI, is disclosed. The system includes fast-curing hardware that facilitates curing each deposited layer before a successive layer is deposited. This reduces the time to provide a finished part from weeks to hours.
    Type: Grant
    Filed: July 19, 2018
    Date of Patent: September 22, 2020
    Assignee: Arevo, Inc.
    Inventors: Hemant Bheda, Riley Reese
  • Patent number: 10759548
    Abstract: A controller arrangement includes a controller, an actuator, and a measuring element. The measuring element captures a control variable with a predetermined sampling rate in consecutive sampling cycles and transmits it to the controller. The controller compares the control variable with a predetermined reference variable and determines how the control variable differs from the reference variable. The controller, in a first cycle, starts with a predetermined regulating variable and outputs it to the actuator, and subsequently determines how the control variable differs from the reference variable; in a second cycle, the controller varies the regulating variable based on the difference of the control variable from the reference variable in the first cycle, and outputs it to the actuator, and subsequently determines how the control variable differs from the reference variable; in a third cycle, the controller varies the regulating variable and outputs it to the actuator.
    Type: Grant
    Filed: August 21, 2018
    Date of Patent: September 1, 2020
    Assignee: Tesat-Spacecom GmbH & Co. KG
    Inventor: Karl Georg Friederich
  • Patent number: 10762798
    Abstract: An autonomous driving method includes: determining a risk of a target vehicle based on either one or both of a driving characteristic and an appearance characteristic of the target vehicle; and autonomously controlling a host vehicle based on the risk.
    Type: Grant
    Filed: April 21, 2017
    Date of Patent: September 1, 2020
    Assignee: SAMSUNG ELECTRONICS CO., LTD.
    Inventor: Yoonsuk Hyun
  • Patent number: 10747193
    Abstract: To perform reinforcement learning enabling to prevent complicated adjustment of coefficients of backlash compensation and backlash acceleration compensation.
    Type: Grant
    Filed: June 4, 2018
    Date of Patent: August 18, 2020
    Assignee: FANUC CORPORATION
    Inventors: Satoshi Ikai, Tsutomu Nakamura, Tomoyuki Aizawa
  • Patent number: 10732595
    Abstract: Provided is a control parameter automatic-adjustment apparatus that adjusts a control parameter which is used when a control apparatus of a plant calculates an operational control signal, the apparatus including: a simulator that simulates operation of the plant; a learning unit that searches for an optimal control parameter using the simulator; and a knowledge database that stores knowledge information which associates an amount of change in the control parameter with an amount of change in a state of the plant, in which the learning unit includes a search range determination unit that determines a control parameter search range based on the knowledge information that is stored in the knowledge database.
    Type: Grant
    Filed: January 30, 2017
    Date of Patent: August 4, 2020
    Assignee: Mitsubishi Hitachi Power Systems, Ltd.
    Inventors: Yuya Tokuda, Takaaki Sekiai, Yasuhiro Yoshida, Takuya Yoshida, Kazunori Yamanaka, Norihiro Iyanaga, Fumiyuki Suzuki
  • Patent number: 10706326
    Abstract: A learning apparatus includes an acquisition unit, a creation unit, and a first learning unit. The acquisition unit acquires a plurality of leaning data sets including a plurality of images imaged by a plurality of imaging devices, and sensor information of the imaging devices when the plurality of respective images is imaged. The creation unit creates, from the plurality of the plurality of learning data sets, a plurality of subsets, wherein each of the plurality of subsets has a different combination of the plurality of images and the sensor information. The first learning unit learns a plurality of first classifiers respectively corresponding to the plurality of subsets based on the plurality of respective subsets.
    Type: Grant
    Filed: August 22, 2017
    Date of Patent: July 7, 2020
    Assignee: Canon Kabushiki Kaisha
    Inventors: Takamasa Tsunoda, Masakazu Matsugu
  • Patent number: 10648317
    Abstract: A method of detecting a fault in an oil and gas apparatus controlled by a controller is provided. The method includes collecting a test set of data using a sensor proximate to an oil and gas apparatus during the operation of the oil and gas apparatus under test operating conditions, the test set of data being associated with an operating parameter of the controller, determining a percentage of the test set of data that falls outside a normal operation region of the oil and gas apparatus, and configuring the controller in response to the percentage being between a fault-free percentage threshold and a fault percentage threshold.
    Type: Grant
    Filed: October 22, 2015
    Date of Patent: May 12, 2020
    Assignee: Halliburton Energy Services, Inc.
    Inventors: Jason D. Dykstra, Zhijie Sun
  • Patent number: 10642613
    Abstract: A memory 11 stores therein first data and second data each of which has element data that forms a matrix. Arithmetic units 51 to 53 repeat, for each of a first predetermined row of the first data and a second predetermined row of the second data that are stored in the memory 11, by using the element data included in the first predetermined row and the element data included in the second predetermined row, a row portion operation based on the number of columns in the second data and performs, by using results of the row portion operations, an arithmetic operation process that acquires the operation results of the operation that uses the first data and the second data.
    Type: Grant
    Filed: July 15, 2019
    Date of Patent: May 5, 2020
    Assignee: FUJITSU LIMITED
    Inventor: Masahiro Kuramoto
  • Patent number: 10519759
    Abstract: The present disclosure describes the use of growth models and data driven models that are combined for quickly and efficiently modeling SAGD reservoir oil production. Growth function surrogate models are used for efficient and reliable reservoir modeling and production forecasting as opposed to CPU intensive simulations based on finite difference models. A data-driven technique can then compare the growth function surrogate model with real field data to find discrepancies and inconsistencies between the two, allowing for an updates and improvements of the growth function model.
    Type: Grant
    Filed: April 13, 2015
    Date of Patent: December 31, 2019
    Assignee: ConocoPhillips Company
    Inventor: Hector M. Klie
  • Patent number: 10514666
    Abstract: The present invention simplifies the processing for compensating an influence for a controlled quantity generated from shaping interference in motion control. A controller (10) as a model predictive control device computes an error between an actually measured value of a controlled quantity in a certain action cycle when shaping interfering is applied and a predictive value of the controlled quantity in the certain action cycle, i.e., the model predictive error, and corrects the predictive value in the action cycle after the certain action cycle by using the computed model predictive error.
    Type: Grant
    Filed: February 22, 2017
    Date of Patent: December 24, 2019
    Assignee: OMRON Corporation
    Inventor: Masaki Namie
  • Patent number: 10489221
    Abstract: A method for creating a context aware application and a user terminal are provided, where the method includes: obtaining a creation instruction used to create the context aware application, where the creation instruction includes a creation factor, and the creation factor is entered by a user and/or generated by a user terminal; determining, according to the creation factor, at least one terminal device related to the creation factor, and obtaining context information and action information of the at least one terminal device; generating at least one operation item according to the context information and the action information of the at least one terminal device; and generating the context aware application according to the at least one operation item. Thereby resolving a technical problem that development steps of the context aware application are tedious, and achieving beneficial effects of simplifying the development steps and improving the development efficiency.
    Type: Grant
    Filed: February 22, 2017
    Date of Patent: November 26, 2019
    Assignee: Huawei Technologies Co., Ltd.
    Inventors: Qingwei Zhao, Heng Chang, Qifeng Ma
  • Patent number: 10409303
    Abstract: A manipulated variable calculator having a plurality of control loops and configured to calculate manipulated variables to be respectively given to a plurality of temperature adjusters includes: a reference model output generator configured to generate a reference model that is a response output until reaching a temperature setpoint when, in the plurality of control loops, a manipulated variable of a control loop having the slowest response speed is defined as 100%; a simulator configured to sequentially search for a switching time to determine a manipulated variable pattern; a reference model configured to generate a reference model output based on the searched switching time; and a control switching unit configured to switch to a feed-back control using an error between the reference model outlet and the temperature setpoint when the reference model outlet reaches a predetermined time or a predetermined temperature after the reference model outlet starts.
    Type: Grant
    Filed: March 15, 2017
    Date of Patent: September 10, 2019
    Assignee: KELK Ltd.
    Inventor: Kazuhiro Mimura
  • Patent number: 10409232
    Abstract: An engineering tool and a method for parameterizing a model-based predictive controller for controlling a process-engineering process. A quality determining module for determining the quality of the model, which contains the model-based predictive controller for the behavior of the process-engineering process that is to be controlled, uses measurement data to ascertain errors in various model parameters as model errors. The weighting factors used to weight manipulated variable changes in a quality criterion are determined by a weighting factor module such that manipulated variable changes of a model-based predictive controller designed taking into account model errors are the same as those of a predictive controller designed based on the assumption of an error-free model. This advantageously results in good performance with simultaneously adequate stability of the controller.
    Type: Grant
    Filed: March 29, 2010
    Date of Patent: September 10, 2019
    Assignee: Siemens Aktiengesellschaft
    Inventors: Lena Webersinke, Bernd-Markus Pfeiffer
  • Patent number: 10394197
    Abstract: A controller (10) corrects a predictive value in a certain predictive error variation cycle by using the predictive error in a predictive error variation cycle prior to the certain predictive error variation cycle, wherein the predictive error variation cycle is a cycle of a time change of an error, i.e., predictive error, between an actually measured value and a predictive value of the controlled quantity.
    Type: Grant
    Filed: February 22, 2017
    Date of Patent: August 27, 2019
    Assignee: OMRON Corporation
    Inventor: Masaki Namie
  • Patent number: 10374882
    Abstract: Embodiments of this disclosure filter a set of key performance indicators (KPIs) based on various criteria to reduce the number of root causes that are considered when adjusting the wireless configuration parameters. In particular, the set of KPIs may be filtered based on various criteria. In one example, KPIs having a hit-ratio below a hit-ratio threshold are removed from the set of KPIs. In another example, KPIs having a slope of linear regression below a threshold slope are removed from the set of KPIs. In yet another example, a KPI is removed from the set of KPIs when a causal relationship between the KPI and another KPI in the set of KPIs exceeds a threshold. In yet another example, a KPI is removed from the set of KPIs when the KPI has a prediction impact score that fails to exceed a prediction impact threshold.
    Type: Grant
    Filed: March 16, 2016
    Date of Patent: August 6, 2019
    Assignee: Futurewei Technologies, Inc.
    Inventors: Baoling S. Sheen, Ying Li, Jin Yang
  • Patent number: 10353354
    Abstract: The present invention simplifies the processing for compensating an influence for a controlled quantity generated from shaping interference in motion control. A controller (10) as a model predictive control device computes an error between an actually measured value of a controlled quantity in a certain action cycle when shaping interfering is applied and a predictive value of the controlled quantity in the certain action cycle, i.e., the model predictive error, and corrects the predictive value in the action cycle after the certain action cycle by using the computed model predictive error.
    Type: Grant
    Filed: February 22, 2017
    Date of Patent: July 16, 2019
    Assignee: OMRON Corporation
    Inventor: Masaki Namie
  • Patent number: 10352142
    Abstract: A method for increasing efficiency in emulsion production for a steam-assisted gravity drainage (SAGD) oil well system includes generating a multiple time step model of the SAGD oil well system and training the multiple time step model of the SAGD oil well system utilizing historical time series data relating to one or more SAGD oil wells at one or more SAGD production sites of the SAGD oil well system. The historical time series data is obtained from a plurality of sensors in the SAGD oil well system. The method also includes utilizing the multiple time step model to determine, based on a set of objectives and subject to one or more constraints, two or more sets of values for control parameters associated with one or more of the SAGD production sites of the SAGD oil well system for respective ones of two or more time steps.
    Type: Grant
    Filed: September 26, 2016
    Date of Patent: July 16, 2019
    Assignee: International Business Machines Corporation
    Inventors: Andrew R. Conn, Lior Horesh, Matthias Kormaksson, Moshood O. Saliu, Theodore G. van Kessel
  • Patent number: 10325222
    Abstract: Embodiments may include machine learning, including decision tree machine learning. Predictive variables may be selected for the machine learning through an iterative process. Predictive power of the predictive variables and collinearity between the predictive variables may be considered when selecting a set of the predictive variables for the machine learning.
    Type: Grant
    Filed: February 8, 2016
    Date of Patent: June 18, 2019
    Assignee: ACCENTURE GLOBAL SERVICES LIMITED
    Inventors: James Hoover, Jeffrey Scott Miller
  • Patent number: 10321336
    Abstract: Quality of service problems in wireless networks can be identified, and in some cases resolved, autonomously using an optimization technique that adjusts parameters of the wireless network based on relationships between key quality indicators (KQIs) and key performance indicators (KPIs). A KQI may be used to gauge the quality of service/experience collectively observed by users/devices when communicating a particular type of traffic in a wireless network or wireless network area. A KPI may be any specific performance metric of a wireless network tending to have a causal or correlative relationship with a KQI. Different types of relationships between a KQI and KPIs may be used to evaluate a quality of service problem, including correlation coefficients, slopes of linear regression, hit-ratios, and others.
    Type: Grant
    Filed: March 16, 2016
    Date of Patent: June 11, 2019
    Assignee: Futurewei Technologies, Inc.
    Inventors: Ying Li, Baoling S. Sheen, Jin Yang
  • Patent number: 10317902
    Abstract: A method and system for evaluating inter-vehicle traffic gaps and time instances to perform a lane change maneuver is described. The method includes determining a set of trajectories which respectively constitutes an approximation of the feasible motion of the ego vehicle, evaluating the set of trajectories on the available inter-vehicle traffic gaps and time instances to perform the lane change maneuver over a prediction horizon to select a subset of feasible inter-vehicle traffic gaps and time instances to perform the lane change maneuver and to establish a corresponding set of lane change trajectories, evaluating the set of lane change trajectories on the subset of feasible inter-vehicle traffic gaps and time instances from a safety critical perspective, and selecting a preferred lane change trajectory, with corresponding inter-vehicle traffic gap and time instance, to perform the lane change maneuver.
    Type: Grant
    Filed: February 17, 2017
    Date of Patent: June 11, 2019
    Assignee: VOLVO CAR CORPORATION
    Inventors: Julia Nilsson, Mattias Erik Brannstrom
  • Patent number: 10088818
    Abstract: A system having a plurality of electronic devices, at least one of the plurality of electronic devices having one or more processors and memory storing instructions for execution by the one or more processors, collects usage information of one or more of the plurality of electronic devices for a plurality of known users within a premise. The system then identifies, for a first user, a usage pattern of the one or more electronic devices based on the collected usage information, and determines a correlation factor of the usage pattern. Based on the determined correlation factor of the usage pattern for the first user, the system generates, for the first user, an operational profile with which to operate the one or more electronic devices, and operates the one or more electronic devices in accordance with the operational profile for the first user.
    Type: Grant
    Filed: December 23, 2014
    Date of Patent: October 2, 2018
    Assignee: GOOGLE LLC
    Inventors: Jeffrey P. Mathews, Lee R. Taylor, Andrew J. Zimmer
  • Patent number: 10067485
    Abstract: The present invention provides novel techniques for optimizing and controlling production plants using parametric multifaceted models. In particular, the parametric multifaceted models may be configured to convert a first set of parameters (e.g., control parameters) relating to a production plant into a second set of parameters (e.g., optimization parameters) relating to the production plant. In general, the first set of parameters will be different than the second set of parameters. For example, the first set of parameters may be indicative of low-level, real-time control parameters and the second set of parameters may be indicative of high-level, economic parameters. Utilizing appropriate parameterization may allow the parametric multifaceted models to deliver an appropriate level of detail of the production plant within a reasonable amount of time.
    Type: Grant
    Filed: September 21, 2015
    Date of Patent: September 4, 2018
    Assignee: Rockwell Automation Technologies, Inc.
    Inventors: Bijan Sayyar-Rodsari, Carl Anthony Schweiger
  • Patent number: 9910057
    Abstract: A method and apparatus for governing sensor data readings from a plurality of input sensors onboard a communications device. An inventory of available input sensors is generated, and a set of requested input sensors from an application running on the communications device is received. The requested input sensors that are absent from the inventory of available input sensors is identified, and based upon received measured values from the available input sensors, equivalent values for those absent input sensors are derived. The accuracy and precision of the measured and equivalent sensor values are estimated, and those measurements not meeting certain thresholds are filtered. The measured values and the derived equivalent values meeting the predetermined thresholds for accuracy and precision, and the filtered measured values and the filtered derived equivalent values are output to the application.
    Type: Grant
    Filed: November 30, 2016
    Date of Patent: March 6, 2018
    Assignee: Adtile Technologies Inc.
    Inventors: Nils Forsblom, Maximilian Metti, Angelo Scandaliato
  • Patent number: 9886417
    Abstract: The present disclosure relates to a method and an apparatus for controlling a voltage in a wind farm. The method includes: collecting measured values of parameters as initial values of the prediction values; inputting the initial values into a preset control model for optimizing a model predictive control; solving the preset control model to obtain a first solution sequence of the reactive power setting values of the wind turbines and a second solution sequence of the terminal voltage setting values of the static var generators; and sending first values in the first solution sequence to the wind turbines and first values in the second solution sequence to the static var generators, such that a voltage control in the wind farm is realized.
    Type: Grant
    Filed: August 29, 2015
    Date of Patent: February 6, 2018
    Assignee: TSINGHUA UNIVERSITY
    Inventors: Qinglai Guo, Hongbin Sun, Bin Wang, Boming Zhang, Wenchuan Wu, Fengda Xu
  • Patent number: 9830747
    Abstract: A method of monitoring the health of a gas turbine engine of at least a pair of engines of an aircraft for example. The method comprising the steps of: a) obtaining steady state readings from predetermined sensors on the engines; b) calculate a percentage difference of the steady state readings from a unique engine linear synthesis model for each engine; c) compare the difference between the percentage differences for each engine and d) where this difference exceeds a predetermined value issue a warning as to an engine health problem. Maintenance of the engine can therefore be advantageously scheduled.
    Type: Grant
    Filed: May 14, 2008
    Date of Patent: November 28, 2017
    Assignee: ROLLS-ROYCE plc
    Inventors: David Apps, Timothy M. Smith
  • Patent number: 9697471
    Abstract: A plant model management device according to one embodiment includes a generation unit and a combining unit. The generation unit receives a first set of prior probability distributions of a first set of automatic operation parameters. The first set of automatic operation parameters define a condition required for modeling a plant model that is a model based on data concerning a plant. The generation unit generates a first set of posterior probability distributions of the first set of automatic operation parameters and a first set of probabilistic plant models based on the first set of prior probability distributions. The first set of posterior probability distributions reflect compatibility with learning data that is past time-series data concerning a first explanatory variable and a first objective variable. The combining unit combines the first set of probabilistic plant models using the first set of posterior probability distributions to generate a first plant model.
    Type: Grant
    Filed: April 7, 2014
    Date of Patent: July 4, 2017
    Assignee: YOKOGAWA ELECTRIC CORPORATION
    Inventors: Akio Nakabayashi, Shouta Ukai, Hidehiko Wada, Tetsuya Otani
  • Patent number: 9567006
    Abstract: A method for situation-related steering assistance in a lane keeping assistant for a vehicle includes: importing a collision signal; ascertaining a correction signal for adapting an intervention torque for the lane keeping assistant, in order to provide a situation-related steering assistance in the lane keeping assistant. The collision signal represents information about a risk of collision during a lane change, and the correction signal is ascertained using the collision signal.
    Type: Grant
    Filed: November 25, 2014
    Date of Patent: February 14, 2017
    Assignee: ROBERT BOSCH GMBH
    Inventor: Chengxuan Fu
  • Patent number: 9558036
    Abstract: We describe a high-level computational framework especially well suited to parallel operations on large datasets. In a system in accordance with this framework, there is at least one, and generally several, instances of an architecture deployment as further described. We use the term “architecture deployment” herein to mean a cooperating group of processes together with the hardware on which the processes are executed. This is not to imply a one-to-one association of any process to particular hardware. To the contrary, as detailed below, an architecture deployment may dynamically spawn another deployment as appropriate, including provisioning needed hardware. The active architecture deployments together form a system that dynamically processes jobs requested by a user-customer, in accordance with customer's monetary budget and other criteria, in a robust and automatically scalable environment.
    Type: Grant
    Filed: May 29, 2015
    Date of Patent: January 31, 2017
    Assignee: BigML, Inc.
    Inventors: Francisco J. Martin, Adam Ashenfelter, J. Justin Donaldson, Jos Verwoerd, Jose Antonio Ortega, Charles Parker
  • Patent number: 9442483
    Abstract: A manufacturing control apparatus of an electronic device is configured to implement processing to generate a first model function relating to a relationship between a characteristic of a component included in the electronic device. The apparatus is configured to implement processing to determine a first manufacturing condition value to obtain the characteristic of the component based on the first model function. The apparatus is configured to implement processing to calculate a squared prediction error of a measured value of the characteristic of the component. The apparatus is configured to implement processing to determine a second manufacturing condition value of the next electronic device according to the calculated squared prediction error.
    Type: Grant
    Filed: March 15, 2013
    Date of Patent: September 13, 2016
    Assignee: Kabushiki Kaisha Toshiba
    Inventor: Linting Huang
  • Patent number: 9182753
    Abstract: A method controls an operation of a system. The system is operated by a controller. The controller is model-based controller determined according to a model of the system. The method updates the model, during the operation, based on an extremum seeking, and updates the controller based on the updated model.
    Type: Grant
    Filed: May 10, 2012
    Date of Patent: November 10, 2015
    Assignee: Mitsubishi Electric Research Laboratories, Inc.
    Inventor: Mouhacine Benosman
  • Patent number: 9005261
    Abstract: A therapeutic laser with a source of pulsed electromagnetic radiation, a control device for controlling the intensity and/or the duration of the therapeutic laser applied to the tissue, and a detection device for detecting optoacoustic signals triggered by irradiating the living tissue with the pulsed electromagnetic radiation. The therapeutic laser is characterized by an evaluation device that acts on the control device and is used for calculating a degree of quality B(t) from the optoacoustic signals detected by the detection device for individual laser pulses applied to a predetermined laser spot and determining a fit function f(t) at a predetermined point in time ?t1, the fit function f(t) approximating the mean curve of B(t) for 0?t??t1. The intensity and/or the irradiation time of the therapeutic laser is defined by the parameters for the predetermined laser spot, the parameters being determined for the fit function f(t).
    Type: Grant
    Filed: October 24, 2008
    Date of Patent: April 14, 2015
    Assignee: Medizinisches Laserzentrum Luebech GmbH
    Inventor: Ralf Brinkmann
  • Patent number: 9002615
    Abstract: A method and system for online power management of a turbine engine is provided. The method includes operating an engine control system on a first bandwidth, filtering at least one data input from the engine control system to a second bandwidth, and receiving, by a power management system operating on the second bandwidth, the at least one filtered data input. The method also includes predicting an engine operating condition using the at least one filtered data input using a closed-loop engine model, determining an optimal engine power management based on the prediction, solving a constrained optimization for a desired optimization objective, and outputting the optimal engine power management to the engine control system.
    Type: Grant
    Filed: January 18, 2012
    Date of Patent: April 7, 2015
    Assignee: General Electric Company
    Inventors: Aditya Kumar, Santanu Chatterjee, Pierino Gianni Bonanni, Avinash Vinayak Taware
  • Patent number: 8948936
    Abstract: A system includes a plurality of actuators and a management system operably associated with the plurality electronic and mechanical devices. The management architecture includes interfaces configured to the entire electronics and mechanics to provide a parameter to a computer. The computer includes a control and management architecture using modular finite state flow designs configured to analyze the parameter. The computer with a plurality of finite state machines can conduct a plurality of control laws operably associated with one or more actuators for finite functions of mobility. The method includes matching the parameter with the finite state machine and controlling the actuator via control law operably associated with finite state machine. The method can therefore be achieved either manually, semi-autonomously and autonomously with seamless and switchless control using a central control computer with integration of electronic and mechanic sensors and devices.
    Type: Grant
    Filed: June 11, 2013
    Date of Patent: February 3, 2015
    Assignee: Textron Innovations Inc.
    Inventors: Shyhpyng Jack Shue, John J. Shillings
  • Patent number: 8942866
    Abstract: A system includes a plurality of actuators and a control system operably associated with the plurality of actuators. The control system having a control logic architecture having a dynamic command input shaping model associated with an input command, a robust inner loop associated with the dynamic command input shaping model, and a time delay cancellation model. The method includes selecting a control law based upon a flight performance of an aircraft, decoupling the control law into a first individual component and a second individual component of the aircraft flight motion, analyzing each individual component separately, regrouping the component of flight motion, analyzing the control law with a time delay cancellation model and providing the necessary dynamic flight quickness with a different command input condition.
    Type: Grant
    Filed: June 25, 2013
    Date of Patent: January 27, 2015
    Assignee: Textron Innovations Inc.
    Inventors: Shyhpyng Jack Shue, John J. Schillings
  • Publication number: 20150005903
    Abstract: An on-line data analytics device can be installed in a process control system as a standalone device that operates in parallel with, but non-intrusively with respect to, the on-line control system to perform on-line analytics for a process without requiring the process control system to be reconfigured or recertified. The data analytics device includes a data analytics engine coupled to a logic engine that receives process data collected from the process control system in a non-intrusive manner. The logic engine operates to determine further process variable values not generated within the process control system and provides the collected process variable data and the further process variable values to the data analytics engine. The data analytics engine executes statistically based process models, such as batch models, stage models, and phase models, to produce a predicted process variable, such as an end of stage or end of batch quality variable for use in analyzing the operation of the on-line process.
    Type: Application
    Filed: June 28, 2013
    Publication date: January 1, 2015
    Applicant: FISHER-ROSEMOUNT SYSTEMS, INC.
    Inventors: Christopher J. Worek, Terrence L. Blevins, Robert B. Havekost, Dirk Thiele
  • Patent number: 8922938
    Abstract: A disk drive is disclosed comprising a servo control system operable to actuate a head over a disk. A disturbance signal is generated in response to a vibration, and the disturbance signal is filtered with a first filter comprising a frequency response to generate a filtered disturbance signal. The filtered disturbance signal is filtered with a model of the servo control system to generate a compensated disturbance signal. An error signal of the servo control system is filtered with a second filter comprising the frequency response to generate a filtered error signal. An adaptation control signal is generated in response to the compensated disturbance signal and the filtered error signal, and an adaptive filter is adapted in response to the adaptation control signal, wherein the adaptive filter filters the disturbance signal to generate feed-forward compensation values applied to the servo control system to compensate for the vibration.
    Type: Grant
    Filed: November 2, 2012
    Date of Patent: December 30, 2014
    Assignee: Western Digital Technologies, Inc.
    Inventors: Xu Chen, Jianguo Zhou, Wei Xi, Kuang-Yang Tu, Guoxiao Guo
  • Patent number: 8914134
    Abstract: Certain embodiments of the invention may include systems and methods for predicting transient operational characteristics of a power plant. According to an example embodiment of the invention, a method is provided for predicting transient operational characteristics of a power plant. The method can include receiving operating information associated with the power plant; using a power plant dynamics model for determining a current operating state of the power plant based at least in part on the received operating information; and using the power plant dynamics model and a power plant controls model for predicting one or more future operating parameters associated with power plant based at least in part on the determined current operating state and the received operating information.
    Type: Grant
    Filed: November 9, 2011
    Date of Patent: December 16, 2014
    Assignee: General Electric Company
    Inventors: Fernando Javier D'Amato, Christopher Long, Matthew Mosley