# US 11,906,575 B2 · Electrical power analyzer for large and small scale devices for environmental and ecological optimization > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 11,906,575 B2 - Document ID: US11906575B2 - Status: Granted - Kind: B2 - Application number: 16/854,776 - Filed: 2020-04-21 - Published: 2021-10-21 - Granted: 2024-02-20 - Earliest claimed: 2020-04-21 - Assignees: International Business Machines Corporation - Applicants: International Business Machines Corporation - Inventors: Jia Liu; Zhiyuan Li; Dean Steuer; Hyman David Chantz - Web page: https://patentgrep.com/patent/US11906575B2 ## CPC - G01R 31/2839: {using signal generators, power supplies or circuit analysers (G01R31/2879 takes precedence; multimeters G01R15/12, network analysers G01R27/28)} - G06F 1/28: Supervision thereof, e.g. detecting power-supply failure by out of limits supervision - G01R 21/133: by using digital technique - G01R 31/2846: {using hard- or software simulation or using knowledge-based systems, e.g. expert systems, artificial intelligence or interactive algorithms} - G06F 1/305: {in the event of power-supply fluctuations} - G06N 20/00: Machine learning - H02J 13/12: Monitoring network conditions, e.g. electrical magnitudes or operational status - H02J 13/1331: {using wireless data transmission} - H02J 2105/40: characterised by the loads connecting to the networks or being supplied by the networks - G01R: MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES (indicating correct tuning of resonant circuits H03J3/12) - G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N) - G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS - H02J: ELECTRIC POWER NETWORKS; CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY ## Abstract A device, system, and a computer-implemented method a for identifying an anomaly in an operation of a device includes comparing, by an electrical power analyzer, a current power draw signature of the device with a known power draw signature of the device. There is a determining as to whether at least one anomaly is present in the current power draw signature. A warning is generated in response to determining the at least one anomaly is present in the current power draw signature. ## Claims ### Claim 1 A computer-implemented method of identifying an anomaly in an operation of a device, comprising: measuring voltages of lead pairs connected to respective prongs of an electrical plug; determining, based on the measurement, a current power draw signature of the device based on an analog waveform data stream of the device; digitizing the analog waveform data stream; comparing, by an electrical power analyzer coupled to an electrical outlet, the current power draw signature of the device with a known power draw signature of the device; determining whether at least one anomaly is present in the current power draw signature indicating an imminent failure of the device; and generating a warning in response to determining the at least one anomaly is present in the current power draw signature. ### Claim 2 (depends on 1) The computer-implemented method of claim 1, further comprising storing the current power draw signature. ### Claim 3 (depends on 1) The computer-implemented method of claim 1, wherein the generating of the warning further comprises recommending at least one of repair or replacement of the device based on the at least one anomaly. ### Claim 4 (depends on 1) The computer-implemented method of claim 1, wherein the device is a first device and the electrical analyzer is coupled to an Internet of Things (IoT) network, and the method further comprising identifying by a power draw signature additional devices coupled to the first device, and receiving device profiles over the Internet from a repository. ### Claim 5 (depends on 1) The computer-implemented method of claim 1, wherein the device comprises a first device, and further comprising identifying a power draw signature of additional devices coupled to a same branch circuit as the first device. ### Claim 6 (depends on 1) The computer-implemented method of claim 1, further comprising receiving, by the electrical power analyzer, a device power profile including the known power draw signature of the device. ### Claim 7 (depends on 6) The computer-implemented method according to claim 6, further comprising receiving the device power profile from a plurality of similarly-classified types of devices. ### Claim 8 (depends on 1) The computer-implemented method according to claim 1, further comprising utilizing machine learning in determining the at least one anomaly, and that the at least one anomaly includes failure-indicating activity. ### Claim 9 (depends on 1) The computer-implemented method according to claim 1, wherein the comparing of the current power draw signature of the device with the known power draw signature further comprises: reviewing a plurality of power draw signatures of the device over a predetermined time period; and determining whether the at least one anomaly over the predetermined time period indicates a degraded operation of the device. ### Claim 10 An electrical power analyzer, comprising: a voltage measurement module configured to measure voltages of lead pairs connected to respective prongs of an electrical plug and to output analog waveform data streams of a device; a sampler and digitizer configured to generate a current power draw signature of the device based on received analog waveform data streams output from the voltage measurement module, and to digitize the analog waveform data streams; a memory configured to store the digitized waveform streams; and a communications module including a buffer, the communications module configured to receive and output the digitized waveform data streams; and a processor configured to compare the current power draw signature of the digitized waveform streams received from the communications module with a known power draw signature of the device, and to generate a warning in response to a determination that the waveform data streams include at least one of an anomaly or artifact. ### Claim 11 (depends on 10) The electrical power analyzer according to claim 10, wherein the processor is further configured to include in the generated warning a recommendation to repair or replace the device based on the determined at least one of anomaly or artifact in the waveform data streams. ### Claim 12 (depends on 10) The electrical power analyzer according to claim 10, further comprising a receptacle configured to receive the leads of a power cord of the device, and prongs configured to be connected to a power source. ### Claim 13 (depends on 12) The electrical power analyzer according to claim 12, wherein the analysis module is further configured to determine whether the device having the at least one anomaly includes a failure-indicating activity associated with an imminent failure of the device; and wherein the analysis module is further configured to determine whether the device having the failure-indicating activity is to be repaired or be replaced based on a smaller ecological footprint. ### Claim 14 (depends on 13) The electrical power analyzer according to claim 13, wherein the device comprises a first device, and wherein the electrical power analyzer is further configured to identify a power draw signature of additional devices coupled to a same branch circuit as the first device. ### Claim 15 (depends on 10) The electrical power analyzer according to claim 10, further comprising an analysis module configured to reiteratively analyze a plurality of power draw signatures of the device over a predetermined time period, and to determine whether there is a degradation of a device operation over the predetermined time period. ### Claim 16 (depends on 15) The electrical power analyzer according to claim 15, wherein the analysis module is arranged in a mobile communication terminal and configured to communicate with the communications module via short-range wireless communication. ### Claim 17 (depends on 10) The electrical power analyzer according to claim 10, configured for coupling to an Internet of Things (IoT) network, and further configured to: identify a power draw signature of additional devices coupled to the first device; and receive device profiles of the additional device over the internet from a repository and identify a device profile based on the power draw signature. ### Claim 18 An electrical power system for environmental and ecological optimization, the system comprising: an electrical power analyzer configured for insertion into a branch electrical outlet, the electrical power analyzer including at least three prongs with at least three separate analytical leads forming at least three lead pairs, and an input receptacle configured to be electrically connectable to a power cord from a device being monitored; a data acquisition module including an operational amplifier configured to measure a voltage of each of the three lead pairs; a sampler and digitizer configured to sample analog waveform data streams output from the data acquisition module and output a power draw signature of the digitized waveform data streams; and a communications module configured to record and transmit the power draw signature of the digitized waveform streams to an analysis module and to transmit a warning based on analysis of the power drawer signature performed by the analysis module; wherein the communications module is further configured to transmit a warning based on information received from the analysis module about an operational status of the device; and wherein the received information includes a potential failure risk of the device being monitored and recommended corrective action associated with the device being monitored. ### Claim 19 (depends on 18) The system according to claim 18, wherein the analysis module is configured to identify one or more anomalies in the received power draw signature of the device, and wherein the recommended corrective action includes an analysis of an environmental and ecological impact of a repair of the device versus a replacement of the device; and wherein the communications module is further configured to transmit the warning to one or more designated recipients. ### Claim 20 (depends on 19) The system according to claim 19, wherein the communications module is configured to send and receive information regarding the power draw signatures to the analysis module via at least one of a cloud or a local network.