# US 12,001,180 B2 · Condition-based method for malfunction prediction > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 12,001,180 B2 - Document ID: US12001180B2 - Status: Granted - Kind: B2 - Application number: 17/342,133 - Filed: 2021-06-08 - Published: 2021-12-09 - Granted: 2024-06-04 - Earliest claimed: 2020-06-08 - Assignees: Hitachi Energy Ltd - Applicants: Hitachi Energy Ltd - Inventors: Pawel Stano; Frank Kirschnick - Web page: https://patentgrep.com/patent/US12001180B2 ## CPC - G05B 17/02: electric - G06Q 10/04: Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem" (market predictions or forecasting for commercial activities G06Q30/0202) - G01N 15/0618: {of the filter type (G01N15/0643 takes precedence)} - G06N 7/01: Probabilistic graphical models, e.g. probabilistic networks - G06Q 10/0635: Risk analysis of enterprise or organisation activities - G06Q 50/06: Energy or water supply - G05B: CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS (systems for controlling or regulating non-electric variables G05D; systems for regulating electric or magnetic variables G05F; control devices or systems insofar as characterised by mechanical features only G05G) - G06Q: INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR - G01N: INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES (measuring or testing apparatus or processes other than immunoassay, involving enzymes or microorganisms C12M, C12Q) - G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS ## Abstract To perform a prognostic health analysis for an asset (11-13), a stochastic simulation is performed to obtain a prognosis for the evolution of the asset health state. The prognosis is updated based on sensor measurements using a particle filter. ## Claims ### Claim 1 A method, the method being performed by at least one integrated circuit and comprising: determining a future evolution of an asset health state of an asset, the asset being a power transformer, a distributed energy resource, or a power generator, wherein determining the future evolution of the asset health state of the asset comprises iteratively repeating: performing a stochastic simulation to obtain a prognosis for the future evolution of the asset health state, wherein the stochastic simulation uses a model having a discrete state space; after performing the stochastic simulation to obtain the prognosis for the future evolution of the asset health state, reading sensor measurements from one or more sensors; and updating the prognosis based on the read sensor measurements using a particle filter; and generating output based on the determined future evolution of the asset health state; and automatically performing an action, wherein the action comprises at least one of scheduling a down-time of the asset based on the determined future evolution of the asset health state, scheduling maintenance work based on the determined future evolution of the asset health state, scheduling replacement work based on the determined future evolution of the asset health state, or changing maintenance intervals based on the determined future evolution of the asset health state, wherein the stochastic simulation uses a model having a discrete state space, wherein updating the prognosis comprises: computing, based on the prognosis, an expectation value for an observable quantity included in the sensor measurements; performing a comparison of the expectation value to the observable quantity included in the sensor measurements; and computing an updated initial state for a subsequent iteration of the stochastic simulation based on the comparison. ### Claim 2 (depends on 1) The method of claim 1, wherein the updating is triggered by a reading of the sensor measurements. ### Claim 3 (depends on 1) The method of claim 1, wherein the stochastic simulation uses a model having a discrete Markov Chain model. ### Claim 4 (depends on 1) The method of claim 1, wherein the stochastic simulation comprises a Markov Chain Monte Carlo simulation. ### Claim 5 (depends on 1) The method of claim 1, wherein the discrete state space comprises: at least one state in which operation of the asset is not adversely affected by a failure; at least one state in which operation of the asset is adversely affected by a failure, but the asset continues to operate; and a state in which the asset is inoperative due to a failure. ### Claim 6 (depends on 1) The method of claim 1, wherein updating the prognosis comprises mapping the sensor measurements to a scalar function, wherein different ranges of values of the scalar function correspond to different states of the discrete state space. ### Claim 7 (depends on 1) The method of claim 1, wherein the expectation value is computed based on a probability distribution in the discrete state space and state-dependent noise parameters. ### Claim 8 (depends on 7) The method of claim 7, wherein the state-dependent noise parameters are dependent on a variance of a noise term used to compute the expectation value. ### Claim 9 (depends on 7) The method of claim 7, wherein the state-dependent noise parameters are dependent on a state-dependent variance of Gaussian white noise. ### Claim 10 (depends on 1) The method of claim 1, further comprising computing confidence or variance information for the prognosis for the future evolution of the asset health state from the stochastic simulation and updating the confidence or variance information based on the sensor measurements, wherein the output is further generated based on the confidence or variance information. ### Claim 11 (depends on 1) The method of claim 1, further comprising reading the sensor measurements in a cyclic manner and synchronously with completion of a plurality of simulation steps of the stochastic simulation. ### Claim 12 (depends on 1) The method of claim 1, further comprising reading the sensor measurements asynchronously with completion of an integer number of simulation steps of the stochastic simulation. ### Claim 13 (depends on 1) The method of claim 1, wherein the output comprises at least one of: a representation of the future evolution of the asset health state; an alarm or warning generated based on the future evolution of the asset health state; or a control signal to control operation of the asset based on the future evolution of the asset health state. ### Claim 14 (depends on 1) The method of claim 1, wherein the asset is installed in an electric power system or industrial system having a decentralized control system comprising a central control and a plurality of local controllers, each local controller being associated with an asset of the electric power system or industrial system, wherein the method is performed by at least integrated circuit of a local controller of the decentralized control system. ### Claim 15 A method of operating and/or maintaining an asset, the asset being a power transformer, a distributed energy resource, or a power generator, the method comprising: determining a future evolution of an asset health state of the asset, comprising iteratively repeating: performing a stochastic simulation to obtain a prognosis for the future evolution of the asset health state, wherein the stochastic simulation uses a model having a discrete state space; after performing the stochastic simulation to obtain the prognosis for the future evolution of the asset health state, reading sensor measurements from one or more sensors; updating the prognosis based on the read sensor measurements using particle filter; reading the sensor measurements in a cyclic manner and synchronously with completion of a plurality of simulation steps of the stochastic simulation; and generating output based on the determined future evolution of the asset health state; and automatically performing an action, wherein the action comprises at least one of scheduling a down-time of the asset based on the determined future evolution of the asset health state, scheduling maintenance work based on the determined future evolution of the asset health state, scheduling replacement work based on the determined future evolution of the asset health state, or changing maintenance intervals based on the determined future evolution of the asset health state. ### Claim 16 A computing system operative to perform a prognostic health analysis for an asset, the asset being a power transformer, a distributed energy resource, or a power generator, the computing system comprising at least one integrated circuit operative to: compute a future evolution of an asset health state of the asset by iteratively repeating: performing a stochastic simulation to obtain a prognosis for the future evolution of the asset health state, wherein the stochastic simulation uses a model having a discrete state space, after performing the stochastic simulation to obtain the prognosis for the future evolution of the asset health state, reading sensor measurements from one or more sensors, updating the prognosis based on the read sensor measurements using a particle filter; and reading the sensor measurements in a cyclic manner and synchronously with completion of a plurality of simulation steps of the stochastic simulation; control generation of output based on the future evolution of the asset health state; and perform an action, wherein the action comprises at least one of scheduling a down-time of the asset based on the computed future evolution of the asset health state, scheduling maintenance work based on the computed future evolution of the asset health state, scheduling replacement work based on the computed future evolution of the asset health state, or changing maintenance intervals based on the computed future evolution of the asset health state. ### Claim 17 (depends on 16) The computing system of claim 16, wherein the stochastic simulation uses a model having a discrete state space comprising at least one state in which operation of the asset is not adversely affected by a failure, at least one state in which operation of the asset is adversely affected by a failure, but the asset continues to operate, and at least one state in which the asset is inoperative due to a failure. ### Claim 18 (depends on 16) An electric power system or industrial system, comprising: the asset; and the computing system of claim 16, the computing system configured to perform a prognostic asset health analysis for the asset. ### Claim 19 (depends on 18) The electric power system or industrial system of claim 18, wherein the computing system comprises a local controller of the electric power system or industrial system, local controller configured to control the asset. ### Claim 20 (depends on 16) The computing system of claim 16, wherein updating the prognosis comprises: computing, based on the prognosis, an expectation value for an observable quantity included in the sensor measurements; performing a comparison of the expectation value to the observable quantity included in the sensor measurements; and computing an updated initial state for a subsequent iteration of the stochastic simulation based on the comparison. ### Claim 21 (depends on 15) The method of claim 15, wherein updating the prognosis comprises: computing, based on the prognosis, an expectation value for an observable quantity included in the sensor measurements; performing a comparison of the expectation value to the observable quantity included in the sensor measurements; and computing an updated initial state for a subsequent iteration of the stochastic simulation based on the comparison.