# US 11,307,568 B2 · Estimating the remaining useful life for cooling fans based on a wear-out index analysis > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 11,307,568 B2 - Document ID: US11307568B2 - Status: Granted - Kind: B2 - Application number: 16/260,082 - Filed: 2019-01-28 - Published: 2020-07-30 - Granted: 2022-04-19 - Earliest claimed: 2019-01-28 - Assignees: Oracle International Corporation - Applicants: Oracle International Corporation - Inventors: Kenny C. Gross; Anton A. Bougaev; Aleksey M. Urmanov; David K. McElfresh - Web page: https://patentgrep.com/patent/US11307568B2 ## CPC - G05B 23/0283: {Predictive maintenance, e.g. involving the monitoring of a system and, based on the monitoring results, taking decisions on the maintenance schedule of the monitored system; Estimating remaining useful life [RUL] (preventive maintenance, i.e. planning maintenance according to the available resources without monitoring the system G06Q10/06)} - H05K 7/20727: {within server blades for removing heat from heat source} - G05B 23/024: {Quantitative history assessment, e.g. mathematical relationships between available data; Functions therefor; Principal component analysis [PCA]; Partial least square [PLS]; Statistical classifiers, e.g. Bayesian networks, linear regression or correlation analysis; Neural networks} - G06F 1/3215: Monitoring of peripheral devices - G06F 11/3006: {where the computing system is distributed, e.g. networked systems, clusters, multiprocessor systems (multiprogramming arrangements G06F9/46; allocation of resources G06F9/50)} - G06F 11/3058: {Monitoring arrangements for monitoring environmental properties or parameters of the computing system or of the computing system component, e.g. monitoring of power, currents, temperature, humidity, position, vibrations (thermal management in cooling arrangements of a computing system G06F1/206)} - H05K 7/2019: {Fan safe systems, e.g. mechanical devices for non stop cooling} - 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) - H05K: PRINTED CIRCUITS; CASINGS OR CONSTRUCTIONAL DETAILS OF ELECTRIC APPARATUS; MANUFACTURE OF ASSEMBLAGES OF ELECTRICAL COMPONENTS - G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N) ## Abstract The disclosed embodiments provide a system that estimates a remaining useful life (RUL) for a fan. During operation, the system receives telemetry data associated with the fan during operation of the critical asset, wherein the telemetry data includes a fan-speed signal. Next, the system uses the telemetry data to construct a historical fan-speed profile, which indicates a cumulative time that the fan has operated in specific ranges of fan speeds. The system then computes an RUL for the fan based on the historical fan-speed profile and empirical time-to-failure (TTF) data, which indicates a TTF for the same type of fan as a function of fan speed. Finally, when the RUL falls below a threshold, the system generates a notification indicating that the fan needs to be replaced. ## Claims ### Claim 1 A method for estimating a remaining useful life (RUL) for a fan, which is used to cool a critical asset, comprising: receiving telemetry data associated with the fan during operation of the critical asset, wherein the telemetry data includes a fan-speed signal; using the telemetry data to construct a historical fan-speed profile, which indicates a cumulative time that the fan has operated in specific ranges of fan speeds; computing an RUL for the fan based on the historical fan-speed profile and empirical TTF data, which indicates a time-to-failure (TTF) for the same type of fan as a function of fan speed; and when the RUL falls below a threshold, generating a notification indicating that the fan needs to be replaced; wherein prior to receiving the telemetry data, the method further comprises generating the TTF data, which involves: operating a pool of fans at different fan speeds, wherein the pool of fans is divided into separate fan-speed bins, and wherein fans in each fan-speed bin operate within a range of fan speeds associated with the fan-speed bin; detecting failures of fans in each fan-speed bin during operation of the pool of fans; and determining a TTF for each fan-speed bin based on the detected failures. ### Claim 2 (depends on 1) The method of claim 1, wherein the telemetry data associated with the fan includes: the fan-speed signal; a drive current for the fan; a drive voltage for the fan; a temperature of a component, which is being cooled by the fan; and an I/O rate for a disk drive, which is in proximity to the fan. ### Claim 3 (depends on 1) The method of claim 1, wherein the historical fan-speed profile associates each fan-speed measurement with a specific fan-speed bin for a specific range of fan speeds; wherein the historical fan-speed profile indicates a TTF for each fan-speed bin; and wherein computing the RUL for the fan involves computing [TTF(bin1)*DT(bin1)+TTF(bin2)*DT(bin2)+ . . . +TTF(binN)*DT(binN)]−U, wherein TTF(bini) represents the TTF for bini, wherein DT(bini) represents a fraction of time that the fan spends running at a fan speed associated with bini, and wherein U represents a cumulative operation time for the fan. ### Claim 4 (depends on 1) The method of claim 1, wherein while detecting failures of fans in each fan-speed bin, a failure is detected for a given fan when one or more of the following occurs: a current for the given fan exceeds a threshold current in cases where the given fan is controlled to operate at a fixed fan speed; a speed for the given fan droops below a threshold speed in cases where the given fan is controlled to operate at a fixed drive current; a temperature of a component, which is being cooled by the given fan, exceeds a threshold temperature in cases where the given fan is controlled to operate at a fixed current and voltage; and an I/O rate for a disk drive, which is in proximity to the given fan, falls below a threshold I/O rate. ### Claim 5 (depends on 1) The method of claim 1, wherein generating the notification indicating that the fan needs to be replaced involves generating a notification indicating that a subset of fans in the critical asset having shortest RULs need to be replaced. ### Claim 6 (depends on 1) The method of claim 1, wherein the critical asset comprises one of the following: an enterprise computing system; a component in a power generation system; and a component in a power transmission system. ### Claim 7 A non-transitory, computer-readable storage medium storing instructions that when executed by a computer cause the computer to perform a method for estimating a remaining useful life (RUL) for a fan, which is used to cool a critical asset, the method comprising: receiving telemetry data associated with the fan during operation of the critical asset, wherein the telemetry data includes a fan-speed signal; using the telemetry data to construct a historical fan-speed profile, which indicates a cumulative time that the fan has operated in specific ranges of fan speeds; computing an RUL for the fan based on the historical fan-speed profile and empirical TTF data, which indicates a time-to-failure (TTF) for the same type of fan as a function of fan speed; and when the RUL falls below a threshold, generating a notification indicating that the fan needs to be replaced; wherein prior to receiving the telemetry data, the method further comprises generating the TTF data, which involves: operating a pool of fans at different fan speeds, wherein the pool of fans is divided into separate fan-speed bins, and wherein fans in each fan-speed bin operate within a range of fan speeds associated with the fan-speed bin; detecting failures of fans in each fan-speed bin during operation of the pool of fans; and determining a TTF for each fan-speed bin based on the detected failure. ### Claim 8 (depends on 7) The non-transitory, computer-readable storage medium of claim 7, wherein the telemetry data associated with the fan includes: the fan-speed signal; a drive current for the fan; a drive voltage for the fan; a temperature of a component, which is being cooled by the fan; and an I/O rate for a disk drive, which is in proximity to the fan. ### Claim 9 (depends on 7) The non-transitory, computer-readable storage medium of claim 7, wherein the historical fan-speed profile associates each fan-speed measurement with a specific fan-speed bin for a specific range of fan speeds; wherein the historical fan-speed profile indicates a TTF for each fan-speed bin; and wherein computing the RUL for the fan involves computing [TTF(bin1)*DT(bin1)+TTF(bin2)*DT(bin2)+ . . . +TTF(binN)*DT(binN)]−U, wherein TTF(bini) represents the TTF for bini, wherein DT(bini) represents a fraction of time that the fan spends running at a fan speed associated with bini, and wherein U represents a cumulative operation time for the fan. ### Claim 10 (depends on 7) The non-transitory, computer-readable storage medium of claim 7, wherein while detecting failures of fans in each fan-speed bin, a failure is detected for a given fan when one or more of the following occurs: a current for the given fan exceeds a threshold current in cases where the given fan is controlled to operate at a fixed fan speed; a speed for the given fan droops below a threshold speed in cases where the given fan is controlled to operate at a fixed drive current; a temperature of a component, which is being cooled by the given fan, exceeds a threshold temperature in cases where the given fan is controlled to operate at a fixed current and voltage; and an I/O rate for a disk drive, which is in proximity to the given fan, falls below a threshold I/O rate. ### Claim 11 (depends on 7) The non-transitory, computer-readable storage medium of claim 7, wherein generating the notification indicating that the fan needs to be replaced involves generating a notification indicating that a subset of fans in the critical asset having shortest RULs need to be replaced. ### Claim 12 (depends on 7) The non-transitory, computer-readable storage medium of claim 7, wherein the critical asset comprises one of the following: an enterprise computing system; a component in a power generation system; and a component in a power transmission system. ### Claim 13 A system that estimates a remaining useful life (RUL) for a fan, which is used to cool a critical asset, comprising: at least one processor and at least one associated memory; and a notification mechanism that executes on the at least one processor, wherein during operation, the notification mechanism: receives telemetry data associated with the fan during operation of the critical asset, wherein the telemetry data includes a fan-speed signal; uses the telemetry data to construct a historical fan-speed profile, which indicates a cumulative time that the fan has operated in specific ranges of fan speeds; computes an RUL for the fan based on the historical fan-speed profile and empirical TTF data, which indicates a time-to-failure (TTF) for the same type of fan as a function of fan speed; and when the RUL falls below a threshold, generates a notification indicating that the fan needs to be replaced; wherein prior to receiving the telemetry data, the method further comprises generating the TTF data, which involves: operating a pool of fans at different fan speeds, wherein the pool of fans is divided into separate fan-speed bins, and wherein fans in each fan-speed bin operate within a range of fan speeds associated with the fan-speed bin; detecting failures of fans in each fan-speed bin during operation of the pool of fans; and determining a TTF for each fan-speed bin based on the detected failure. ### Claim 14 (depends on 13) The system of claim 13, wherein the telemetry data associated with the fan includes: the fan-speed signal; a drive current for the fan; a drive voltage for the fan; a temperature of a component, which is being cooled by the fan; and an I/O rate for a disk drive, which is in proximity to the fan. ### Claim 15 (depends on 13) The system of claim 13, wherein the historical fan-speed profile associates each fan-speed measurement with a specific fan-speed bin for a specific range of fan speeds; wherein the historical fan-speed profile indicates a TTF for each fan-speed bin; and wherein while computing the RUL for the fan, the notification mechanism computes [TTF(bin1)*DT(bin1)+TTF(bin2)*DT(bin2)+ . . . +TTF(binN)*DT(binN)]−U, wherein TTF(bini) represents the TTF for bini, wherein DT(bini) represents a fraction of time that the fan spends running at a fan speed associated with bini, and wherein U represents a cumulative operation time for the fan. ### Claim 16 (depends on 13) The system of claim 13, wherein while detecting failures of fans in each fan-speed bin, the system detects a failure for a given fan when one or more of the following occurs: a current for the given fan exceeds a threshold current in cases where the given fan is controlled to operate at a fixed fan speed; a speed for the given fan droops below a threshold speed in cases where the given fan is controlled to operate at a fixed drive current; a temperature of a component, which is being cooled by the given fan, exceeds a threshold temperature in cases where the given fan is controlled to operate at a fixed current and voltage; and an I/O rate for a disk drive, which is in proximity to the given fan, falls below a threshold I/O rate. ### Claim 17 (depends on 13) The system of claim 13, wherein while generating the notification indicating that the fan needs to be replaced, the notification mechanism generates a notification indicating that a subset of fans in the critical asset having shortest RULs need to be replaced.