Classifications

• • G—PHYSICS
  • G06—COMPUTING OR CALCULATING; COUNTING
  • G06F—ELECTRIC DIGITAL DATA PROCESSING
  • G06F30/00—Computer-aided design [CAD]
  • G06F30/20—Design optimisation, verification or simulation
• • G—PHYSICS
  • G05—CONTROLLING; REGULATING
  • G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
  • G05B17/00—Systems involving the use of models or simulators of said systems
  • G05B17/02—Systems involving the use of models or simulators of said systems electric
• • G—PHYSICS
  • G05—CONTROLLING; REGULATING
  • G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
  • G05B19/00—Program-control systems
  • G05B19/02—Program-control systems electric
  • G05B19/18—Numerical control [NC], i.e. automatically operating machines, in particular machine tools, e.g. in a manufacturing environment, so as to execute positioning, movement or co-ordinated operations by means of program data in numerical form
  • G05B19/406—Numerical control [NC], i.e. automatically operating machines, in particular machine tools, e.g. in a manufacturing environment, so as to execute positioning, movement or co-ordinated operations by means of program data in numerical form characterised by monitoring or safety
  • G05B19/4063—Monitoring general control system
• • G—PHYSICS
  • G06—COMPUTING OR CALCULATING; COUNTING
  • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
  • G06N20/00—Machine learning
• • G—PHYSICS
  • G05—CONTROLLING; REGULATING
  • G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
  • G05B2219/00—Program-control systems
  • G05B2219/30—Nc systems
  • G05B2219/32—Operator till task planning
  • G05B2219/32058—Execute program as function of deviation from predicted state, result
• • G—PHYSICS
  • G05—CONTROLLING; REGULATING
  • G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
  • G05B23/00—Testing or monitoring of control systems or parts thereof
  • G05B23/02—Electric testing or monitoring
  • G05B23/0205—Electric testing or monitoring by means of a monitoring system capable of detecting and responding to faults
  • G05B23/0218—Electric testing or monitoring by means of a monitoring system capable of detecting and responding to faults characterised by the fault detection method dealing with either existing or incipient faults
  • G05B23/0243—Electric testing or monitoring by means of a monitoring system capable of detecting and responding to faults characterised by the fault detection method dealing with either existing or incipient faults model based detection method, e.g. first-principles knowledge model

Definitions

• Power plants, waste water treatment plants, lactones, airplanes, and automobiles are some examples of complex systems that include multiple machines operating to accomplish objectives These complex systems include physical components that degrade over time, components that fail, and components that are being used incorrectly or snb-opthnally.
• Degradation, failure, or incorrect or sub-optimal use of a given component in the system may affect other components of the system that depend on the given component.
• the component may be configured to operate differently during different operating states. For example, a machine may power up, warm up, run, cool down, and shut down. The machine may be configured to produce little or no output during the power up state, whereas the machine may be configured to produce maximum output during the run state. Regardless of how a component is configured, the component can behave unexpectedly in any operating state. In a complex system, multiple components may behave unexpectedly for a long period of time even though the system as a whole may operate relatively efficiently over that period of time.
• the overall health and efficiency of the system may be highly dependent on the knowledge, skill, expertise, and accuracy of the maintenance engineer, who is a human being.
• the overall health and efficiency of fee system may also depend on a variable degree of uncertainty surrounding the sensors and the behavior of the components in the systems.
• the output of a given system may be observed at a high level, there is usually little or no knowledge of how much better the maintenance engineer could be performing.
• Explanation for a condition at time, t, is the identification of the signals that are strongly associated with that condition result. In general, more than one Signal may be strongly associated with a condition value. The mapping of signals of interest from features used in modeling is performed. Models that produce good prediction results may produce poor explanation results, and to achieve quality explanation results, the produced model is independently built for explanation.
• the systems and methods generate independent models for prediction and explanation based on signal traces and any provided labels.
• the systems and methods operate in semi- supervised and unsupervised scenarios and provide explanation results directly in terms of the provided signals (as opposed to complex engineered features), and the results are not highly sensitive to the choice of signals used or redundancy among the signals chosen (as they can be for approaches like linear regression).
• FIG. I illustrates an embodiment of a signal classification and explanation system IGG
• FIG. 2 illustrates a feedback control system 200 in accordance with one embodiment.
• FIG. 3 illustrates a system diagnostic process 300 m accordance with one embodiment.
• FIG. 4 illustrates explaining the labeled point 3G4 m accordance with one embodiment.
• FIG 5 illustrates an embodiment of projecting the point into the signal subspace 406, forming a neighbor cluster around the point 408, and correlating point labels with labels of neighbors in the cluster 410.
• FIG. 6 illustrates a labeled point explanation 600 in accordance with one embodiment.
• FIG. 7 illustrates an explanation process 700 m accordance with one embodiment.
• FIG 8 is an example block diagram of a computing device 800 that may incorporate embodiments of the present invention
• a system and methods are disclosed to identify which signals are "significant" to each individual assessment result even in the presence of non-linearities and disjoint groupings of condition types
• the system enables sub-grouping of signals corresponding to system subcomponents or regions.
• Causality conclusions may then be reached with tins understanding of physical mechanisms in the system, and operational feedback to the system may be prescribed and implemented for the given condition and causality
• the causality conclusions can provide operation feedback to direct maintenance engineers that are assigned to oversee operation and maintenance of the system to remediate faulty components or otherwise address the identified conditions in order to promote overall health and efficiency of the system.
• a signal classification and explanation system 100 comprises an external system 102 and a signal data processing system 110.
• the external system 102 further comprises a complex system 104, a signal data repository' 106, and a monitoring display 108.
• the signal data processing system 110 further comprises feature identification logic 112, clustering logic 114, vector classification logic 116, signal receiving logic 118, signal data model maintenance logic 120, condition reporting logic 122, and causal analysis logic 126, which is the focus of this disclosure.
• the complex system 104 may represent a complex industrial machine such as complex factory equipment, commercial vehicles, aircrafts, or any other complex machinery that utilizes multiple sensors to monitor the state of the machinery
• the complex system 104 may also represent a complex sensor package that includes multiple types of sensors designed to function as an activity tracker, such as wireless-enabled wearable technology devices.
• the complex system 104 may be communicatively coupled to the signal data repository 106 for the purposes to sending a data stream of signal data from multiple sensors attached to the complex system 1 04
• the data stream of signal data may represent multiple data
• the purpose of the multiple sensors on the complex system 104 is to record observations occurring at various points within the complex system 104, For example, if the complex system 104 is at power plant made up of multiple windmills that generate energy from the wind, then the multiple sensors may include sensors that measure the rotational speed of each individual windmill, sensors that measure the electrical charge generated by each windmill, and sensors that mea sure the current storage levels of electricity generated by the electrical generators within the power plant.
• the complex system 1 04 may represent a wireless activity tracker.
• the multiple sensors may be configured to detect changes occurring to the wearer and positional changes based on movement.
• the set of sensors may include, but are not limited to, a global positioning sensor (GPS), a 3 -axis accelerometer, a 3--axis gyroscope, a digital compass, an optical heart rate monitor, and an altimeter
• the complex system 104 may represent a particular application, such as a commercial application.
• the particular application may include one or more computer classes that generate output such as log output, for the particular computer application.
• the log output generating classes may be considered built-in instrumentation that reports the current state of multiple classes and objects invoked within the particular computer application.
• the signal data repository 106 may represent a server computer that is configured ( re . programmed) to collect signal data produced by the multiple sensors on the complex system 104, store the signal data based on the signal data type, and create a tune series for the collected signal data, using one or more stored program that the server computer executes.
• the signal data repository 106 may also be capable of sendi ng either real-time data or stored signal data to the monitoring display 108 for the purposes of presenting signal data values to a user for monitormg purposes.
• the signal data repository 106 may also aggregate the signal data to create aggregated statistics showing changes in signal values over periods of time.
• Embodiments of the signal data repository 106 features are not limited to the features described above.
• the signal data repository 106 may be implemented using any commercially available monitoring programs and may utilize any monitoring features within the commercially available products.
• the monitoring display 108 represents a computer-implemented machine programmed to display the signal data received from the signal data repository 106,
• the monitormg display 108 may be capable of directly receiving data input from signal data processing system 1 10.
• the signal data processing system 1 10 is configured to receive a data stream of signal data from the signal data repository 106 and identity physical conditions related to the signal data received.
• the signal data processing system 1 10 is further configured to send the identified physical conditions to the external system 102, either by sending data back io the signal data repository 106 or by sending data directly to the monitoring display 108 so that a user can better identify conditions related to the incoming signal data.
• the signal data processing system 1 10 contains specially configured logic including, but not limited to, feature identification logic 112, clustering logic 1 14, vector classification logic 1 16, signal receiving logic 1 18, signal data model maintenance logic 120, condition reporting logic 122, and causal analysis logic 126.
• feature identification logic 112 may comprise executable instructions loaded into a set of pages in RAM that contain instructions which when executed cause
• the feature identification logic 112 may provide
• Feature vectors represent sets of signal data from one or more sensors for a particular range of time.
• the feature identification logic 112 provides instructions to identify patterns from multiple signal data sets Patterns are based upon variations across different signals and over a specific period of time.
• the feature identification logic 112 may also provide instructions to determine the optimal time window size for evaluating multiple sets of signal data in order to identify meaningful patterns.
• the feature identification logic 112 may provide instruction to reduce the set of signal data points within the time duration window to generate a feature vector of reduced dimensionality.
• the feature identification logic 112 provides instruction to aggregated signal data sets to generate feature vectors using a recurrent neural network
• the feature identification logic 112 may also provide instruction to create mapping between the signal data sets and their corresponding feature vectors.
• the signal receiving logic 118 provides instructions to receive multiple sets of signal data representing observed data values from multiple sensors attached to the complex system
• the feature identification logic 112 provides instructions to aggregate the multiple sets of signal data into one or more feature vectors. Feature vectors represent sets of signal data from one or more sensors for a particular range of time.
• the clustering logic 114 provides
• the vector classification logic 116 provides instructions to receive feedback input that describes one or more
• classification labels that may be assigned to feature vectors based upon previously observed sensor data.
• the feedback may be characterized as a sample episode
• a sample episode includes signal data in the form of a sample feature vector and an assigned classification label for the sample feature vector.
• the classification label may describe a particularly identified condition that occurred to the complex system 104.
• the vector classification logic 116 provides further instructions to determine classification labels for fee generated dusters of feature vectors Upon determining classification labels for the generated clusters of feature vectors, the vector classification logic 116 provides instructions to generate and store, within a storage medium, a signal data, model that defines identified signal conditions based upon the associated cluster, feature vectors, and classification label.
• the vector classification logic 116 provides further instructions to update a previously generated signal data model using the identified signal conditions based upon the associated clusters, feature vectors, and classification labels.
• the signal data model maintenance logic 120 provides instructions to maintain one or more signal data models within digital storage media.
• the condition reporting logic 122 provides instructions to send identified classification labels that are associated to the one or more feature vectors to the external system 102.
• a feedback control system 200 comprises a complex system 104 that generates tune senes signals 124.
• the feedback control system 200 includes logic to extract signal features 204 from the time series signals 124, thus forming feature vectors 206 that are subjected to clustering and classification 208, producing clusters and labels 210 that are used to identity and explain conditions 202 so as to adapt the behavior of the complex system 104.
• a system diagnostic process 300 comprises generating a labeled point 302, explaining the labeled point 304, and returning the explanation 306,
• the system diagnostic process 300 provides the high level structure of causal analysis logic 126
• explaining the labeled point 304 comprises, in one embodiment, selecting a point 402, getting a first signal 404, projecting the point into the signal subspace 406, forming a neighbor cluster around the point 408, and correlating point labels with labels of neighbors m the cluster 410 This is repeated for all time-series signals from the system.
• Figure 5 shows an example of projecting the labeled point into the signal subspace 406, forming a neighbor cluster around the point 408, and correlating point labels with labels of neighbors in the cluster 41 0
• a first feature axis projection 506 is generated on a first signal feature axis F1
• a second feature axis projection 508 is generated on a second signal feature axis F2.
• Also generated are a first feature projection of the explanation point 510 (F1 axis) amid a projection of a first feature neighborhood 514 on F1
• a second feature projection of the explanation point 512 amid a projection of a second feature neighborhood 516 on F2.
• the system model data 502 is a set of values, C(t), F s (t), where Ctt) is the label and Fi(t) is the feature vector components to be assessed.
• C(t) is depicted as a circle or a square. These symbols represent the status or condition of a system or device in some embodiments, corresponding to an associated label such as "operational”, “non-operational”, “warning", “norma!, etc.
• the value of Ft(t) is depicted here as a location in two dimensional space, as two features, F1 and F 2, are depicted. In some embodiments, more than two features may be assessed.
• fee system model data 502 has 64 values.
• the explanation point 504 has a value of C(t'), Fi(t')
• the C(t'), label, for the explanation point 504 is represented by a circle, which, similar to the system mode! data 502. represents a status or condition of the system with its own associated label.
• the explanation point 504 has also been located m the two dimensional space by F ⁇ (f).
• the explanation point 504 may have been determined utilizing a classification model
• the first feature axis projection 506 is a projection on the first feature axis F1 of the system model data 502 and the explanation point 504.
• the symbols on F1 represent the 64 projections F1 (t) of the system mode! data 502 and the projection F1 (f) for the explanation point 504 onto symbol feature axis F1.
• some of the F1 projections overlap In these overlapping cases a single symbol is depicted for simplification.
• the second feature axis projection 508 is a projection of the system mode! data 502 and the explanation point 504 onto the second symbol feature axis F2.
• the symbols on I 2 represent the 64 projection values F2(t) for the system mode! data 502 and the value for F2(t') for the explanation point 504 projected onto F2. Again, some of the symbols on F2 overlap in which case they are depicted as a single symbol.
• the first feature neighborhood 514 is a subset of the first feature axis projection 506 projected from a constrained neighborhood around the explanation point 504
• the first feature neighborhood 514 may be selected from the first feature axis projection 506 based on the first feature projection of the explanation point 510 and the number of values m the system mode! data 502, In one embodiment a number, N, of values is a square root of the total number of values in the system model data 502. Here, N is equal to eight (8).
• the first feature neighborhood 514 may then be the N (here, eight) points in first feature axis projection 506 closest to the first feature projection of the explanation point 510
• a distance function may be utilized to determine the first feature neighborhood 514 from the first feature axis projection
• the routine may utilize a random selection for points in the first feature axis projection 506 with the same value.
• the second feature neighborhood 516 is a subset of the second feature axis projection 508 also projected from fee constrained neighborhood around explanation point 504. this time onto axis F2
• a metric may be determined for both Fi and Fs.
• the metric may be determined by first determining fee percentages of C(t) in the first feature neighborhood 514 and the second feature neighborhood 516 equal to the C(f) of the explanation point 504.
• the percentage for the first feature neighborhood 514 is 100%
• the percentage for the second feature neighborhood 516 is 50%
• labeled point explanation 600 process comprises receiving the labeled point and the featunzed signals from which the labeled point was derived 602, and projecting the model training data into each featunzed signal subspace 604 along with projecting the labeled point into each featunzed signal subspace 606.
• the labeled point explanation 600 continues by constraining the analysis neighborhood 608, and finding neighbors of the labeled point in each feature subspace of the selected signal 610
• the contribution of the point to known conditions is ascertained.
• the contribution may be further refined by determining the relative density of the label in the neighborhood to fee density of the label in the model overall 616, determining a contribution of the signal to the condition represented by the labeled point 618, and sorting fee signals by contribution 622, Signals higher in the son may be displayed as more likely contributors for the condition associated with the labeled point. In an embodiment, the highest 10% of signals in the sort are displayed, but other ranges could be displayed in other embodiments
• a first ratio or percent for finding the signal contribution may be formed as (! ) a numerator that is the number of points in the constrained neighborhood of mode! data points around the point being evaluated and having a same label as the point, and
• a denominator feat is the total number of model data points in the constrained neighborhood.
• a second ratio or percent for finding the signal contribution may be formed as (1) a numerator that is the number of points m the model data having a same label as the point, and (2) a denominator that ts the total number of model data points in tire constrained neighborhood.
• the signal contribution to the condition associated with the labeled point may then be computed from a ratio or percent of the first ratio and second ratio or the first percent and the second percent.
• the sorted list of signal contributions is then applied by displaying and applying the list 624 for adapting the complex system from winch the signal time senes were obtained.
• an explanation process 700 begins with a labeled point 702.
• the explanation process 700 continues by generating a signal projection space 704 for a first signal to analyze, and retrieving a feature vector for the signal 706. These steps are repeated for each signal and each feature vector associated with the selected signal.
• the explanation process 700 continues by assigning distance and significance of the feature vector to the labeled point's neighbors 708. This is repeated for each feature vector associated with the signal
• the explanation process 700 continues by sorting the neighbors of the labeled point by feature distance 710, constraining the neighborhood volume around the point 712,
• Example logic to implement the explanation process 700 on a computer system is:
• Figure 8 is an example block diagram of a computing device 800 that may incorporate embodiments of the present invention.
• Figure 8 is merely illustrative of a machine sys tem to carry out aspects of the teehnical processes described herein, and does not limit the scope of the claims.
• the computing device 800 typically includes a monitor or graphical user interface 802, a data processing system 820, a communication network interface 812, input device(s) 808, output devioe(s) 806, and the like.
• the data processing system 820 may include one or more processors ) 804 that communicate with a number of peripheral devices via a bus subsystem 818.
• peripheral devices may include input device(s) 808, output device(s) 806, communication network interface 812, and a storage subsystem, such as a volatile memory 810 and a nonvolatile memory 814,
• the volatile memory 810 and/or the nonvolatile memory 814 may store oomputer- executable instructions and thus forming logic 822 that when applied to and executed by the processor s) 804 implement embodiments of the system condition explanation and control processes disclosed herein.
• Hie input device(s) 808 include devices and mechanisms for inputting information to the data processing system 820 These may include a keyboard, a keypad, a touch screen incorporated into the monitor or graphical user interface 802, audio input devices such as voice recognition systems, microphones, and other types of input devices.
• the input device(s) 808 may be embodied as a computer mouse, a trackball, a track pad, a joystick, wireless remote, drawing tablet, voice command system, eye tracking system, and the like
• the input device(s) 808 typically allow a user to select objects, icons, control areas, text and the like that appear on the monitor or graphical user interface 802 via a command such as a click of a button or the like.
• the output device(s) 806 include devices and mechanisms for outputting information from the data processing system 820 These may include the monitor or graphical user interface 802, speakers, printers, infrared LEDs, and so on as well understood in the art.
• the communication network interface 812 provides an interface to communication networks (e.g. , communication network 816) and devices external to the data processing system 820
• the communication network interface 812 may serve as an interface for receiving data from and transmitting data to other systems.
• Embodiments of the communication network interface 812 may include an Ethernet interface, a modem (telephone, satellite, cable, ISDN), (asynchronous) digital subscriber line (DSL-), FireWire, USB, a wireless communication interface such as BiueTooth or WiFi, a near field communication wireless interface, a cellular interface, and the like.
• the communication network interface 812 may be coupled to the communication network 816 via an antenna, a cable, or the like.
• the communication network interface 812 may be physically integrated on a circuit board of the data processing system 820, or in some cases may be implemented in software or firmware, such as "soft modems", or the like
• the computing device 800 may include logic that enables communications over a network using protocols such as HTTP, TCP/IP, RTP/RTSP, IPX, UDP and the like
• the volatile memory 810 and the nonvolatile memory 814 are examples of tangible media configured to store computer readable data and instructions to implement various embodiments of the processes described herein.
• Other types of tangible media include removable memory (e.g , pluggable USB memory devices, mobile device SIM cards), optical storage media such as CD-ROMS. DVDs, semiconductor memories such as flash memories, non-transitory read-only-memories (ROMS), battery -backed volatile memories, networked storage devices, and the like
• the volatile memory 810 and the nonvolatile memory 814 may be configured to store the basic programming and data constructs that provide the functionality of the disclosed processes and other embodiments thereof that fall within the scope of the present invention,
• Logic 822 that implements embodiments of the present invention may be stored in the volatile memory' 810 and/or the nonvolatile memory 814. Said logic 822 may be read from the volatile memory 810 and/or nonvolatile memory 814 and executed by the processor(s) 804. The volatile memory' 810 and the nonvolatile memory 814 may also provide a repository for storing data used by the logic 822
• the volatile memory 810 and the nonvolatile memory' 814 may include a number of memories including a mam random access memory (RAM) for storage of instructions and data during program execution and a read only memory (ROM) in which read-only non-transitory instructions are stored.
• the volatile memory 810 and the nonvolatile memory 814 may include a file storage subsystem providing persistent (non-volatile) storage for program and data files.
• the volatile memory 810 and the nonvolatile memory 814 may include removable storage systems, such as removable flash memory.
• the bus subsystem 818 provides a mechanism for enabling the various components and subsystems of data processing system 820 communicate with each other as intended. Although the communication network interface 812 is depicted schematically as a single bus, some embodiments of the bus subsystem 818 may utilize multiple distinct busses.
• the computing device 800 may be a device such as a smartphone, a desktop computer, a laptop computer, a rackmounted computer system, a computer server, or a tablet computer device. As commonly known in the art, the computing device 800 may be implemented as a collection of multiple networked computing devices. Further, the computing device 800 will typically include operating system logic (not illustrated) the types and nature of which are well known in the art.
• Circuitry in this context refers to electrical circuitry having at least one discrete electrical circuit, electrical circuitry having at least one integrated circuit, electrical circuitry having at least one application specific integrated circuit, circuitry forming a general purpose computing device configured by a computer program (e.g,, a general purpose computer configured by a computer program which at least partially carries out processes or devices described herein, or a microprocessor configured by a computer program which at least partially carries out processes or devices described herein), circuitry forming a memory device (e.g., forms of random access memory), or circuitry forming a communications device (e.g,, a modem, communications switch, or optical-electrical equipment).
• a computer program e.g, a general purpose computer configured by a computer program which at least partially carries out processes or devices described herein, or a microprocessor configured by a computer program which at least partially carries out processes or devices described herein
• circuitry forming a memory device e.g., forms of random access memory
• “Firmware” in this context refers to software logic embodied as processor-executable instructions stored i n read-only memories or media.
• Hardware m this context refers to logic embodied as analog or digital circuitry
• Logic in this context refers to machine memoiy circuits, non transitory machine readable media, and/or circuitry which by way of its material and/or material-energy
• configuration comprises control and/or procedural signals, and/or settings and values (such as resistance, impedance, capacitance, inductance, current/voltage ratings, etc.), that may be applied to influence the operation of a device.
• Magnetic media, electronic circuits, electrical and optical memory (both volatile and nonvolatile), and firmware configured with processor- executable instructions are examples of logic.
• Logic specifically excludes pure signals or software per se (however does not exclude machine memories comprising software and thereby forming configurations of matter).
• Software in this context refers to logic implemented as processor-executable instructions in a machine memory (e.g. read/write volatile or nonvolatile memory or media)
• references to “one embodiment” or “an embodiment” do not necessarily refer to the same embodiment, although they may Unless the context clearly requires otherwise, throughout the description and the claims, the words “comprise,” “comprising,” and the like are to be construed in an inclusive sense as opposed to an exclusive or exhaustive sense; that is to say, in the sense of “including, but not limited to “ Words using the singular or plural number also include the plural or singular number respectively, unless expressly limited to a single one or multiple ones Additionally, the words “herein,” “above,” “below” and words of similar import, when used in this application, refer to this application as a whole and not to any particular portions of this application When the claims use the word “or” in reference to a list of two or more items, that word covers all of the following interpretations of the word: any of the items in the list, all of the items in the list and any combination of the items in the list, unless expressly limited to one or the other. Any terms not expressly defined herein have their conventional meaning as

Landscapes

• Engineering & Computer Science (AREA)
• Physics & Mathematics (AREA)
• Theoretical Computer Science (AREA)
• General Physics & Mathematics (AREA)
• Evolutionary Computation (AREA)
• Automation & Control Theory (AREA)
• Software Systems (AREA)
• General Engineering & Computer Science (AREA)
• Manufacturing & Machinery (AREA)
• Human Computer Interaction (AREA)
• Mathematical Physics (AREA)
• Medical Informatics (AREA)
• Artificial Intelligence (AREA)
• Computer Vision & Pattern Recognition (AREA)
• Computer Hardware Design (AREA)
• Geometry (AREA)
• Computing Systems (AREA)
• Data Mining & Analysis (AREA)
• Testing And Monitoring For Control Systems (AREA)

Priority Applications (3)

Applications Claiming Priority (2)

Publications (1)

Family

ID=67684503

Family Applications (1)

Country Status (4)

Families Citing this family (4)

Citations (6)

Family Cites Families (14)

• 2018
  • 2018-02-27 US US15/906,702 patent/US11972178B2/en active Active
• 2019
  • 2019-01-30 EP EP19760889.6A patent/EP3759456A4/en not_active Withdrawn
  • 2019-01-30 JP JP2020545103A patent/JP7158117B2/ja active Active
  • 2019-01-30 WO PCT/US2019/015802 patent/WO2019168625A1/en not_active Ceased
• 2022
  • 2022-10-07 JP JP2022162285A patent/JP7433395B2/ja active Active

Patent Citations (6)

Also Published As

Similar Documents

Legal Events