# US 11,308,738 B2 · Mobile work machine performance detection and control system > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 11,308,738 B2 - Document ID: US11308738B2 - Status: Granted - Kind: B2 - Application number: 16/734,712 - Filed: 2020-01-06 - Published: 2021-07-08 - Granted: 2022-04-19 - Earliest claimed: 2020-01-06 - Assignees: Deere & Company - Applicants: Deere & Company - Inventors: Douglas A. Thomas; Robert A. Hamilton - Web page: https://patentgrep.com/patent/US11308738B2 ## CPC - G07C 5/06: in graphical form - E01C 19/004: {Devices for guiding or controlling the machines along a predetermined path (for graders or bulldozers E02F3/841; for other soil-shifting machines E02F9/2045)} - E02F 9/205: {Remotely operated machines, e.g. unmanned vehicles (E02F3/8866 takes precedence)} - E02F 9/265: {with follow-up actions (e.g. control signals sent to actuate the work tool)} - E02F 9/267: {Diagnosing or detecting failure of vehicles} - G07C 5/0825: {using optical means} - A01D 41/127: Control or measuring arrangements specially adapted for combines - E01C 23/088: Rotary tools, e.g. milling drums {(for forming recesses to receive marking materials E01C23/0946)} - E01C 23/127: {rotary, e.g. rotary hammers} - E02F 9/2025: {Particular purposes of control systems not otherwise provided for (E02F3/16, E02F3/26, sub-groups of E02F3/43, E02F3/651, sub-groups of E02F3/84, E02F3/907, E02F5/145 take precedence)} - G07C: TIME OR ATTENDANCE REGISTERS; REGISTERING OR INDICATING THE WORKING OF MACHINES; GENERATING RANDOM NUMBERS; VOTING OR LOTTERY APPARATUS; ARRANGEMENTS, SYSTEMS OR APPARATUS FOR CHECKING NOT PROVIDED FOR ELSEWHERE - E01C: CONSTRUCTION OF, OR SURFACES FOR, ROADS, SPORTS GROUNDS, OR THE LIKE; MACHINES OR AUXILIARY TOOLS FOR CONSTRUCTION OR REPAIR (forming roads or like surfaces by compacting or grading snow or ice E01H) - E02F: DREDGING; SOIL-SHIFTING (winning peat E21C49/00) - A01D: HARVESTING; MOWING ## Abstract A mobile work machine includes a sensor configured to generate a sensor signal indicative of operation of the mobile work machine, a machine performance detection system configured to receive the sensor signal, generate a topological representation of the sensor signal, and determine a machine performance characteristic based on the topological representation relative to a reference model, and a control system configured to generate a control signal to control the mobile work machine based on the machine performance characteristic. ## Claims ### Claim 1 A mobile work machine comprising: a sensor configured to generate a sensor signal indicative of operation of the mobile work machine; a machine performance detection system configured to: receive the sensor signal; generate a topological representation of the sensor signal; and determine a machine performance characteristic based on the topological representation relative to a reference model; and a control system configured to generate a control signal to control the mobile work machine based on the machine performance characteristic. ### Claim 2 (depends on 1) The mobile work machine of claim 1, wherein the sensor signal is indicative of operation of the mobile work machine during a given time period, and the reference model comprises a topological representation of the sensor signal generated by the sensor during a prior time period that precedes the given time period. ### Claim 3 (depends on 1) The mobile work machine of claim 1, wherein the topological representation models a shape of the sensor signal over time. ### Claim 4 (depends on 3) The mobile work machine of claim 3, wherein the sensor signal defines a time series of feature values, and generating the topological representation comprises applying a topological data analysis algorithm to the time series of feature values. ### Claim 5 (depends on 4) The mobile work machine of claim 4, wherein the topological data analysis algorithm generates a persistence model that models persistence of homological features in the sensor signal over time. ### Claim 6 (depends on 5) The mobile work machine of claim 5, wherein the persistence model is generated using persistent homology. ### Claim 7 (depends on 4) The mobile work machine of claim 4, wherein the feature values represent acceleration of the mobile work machine in one or more directions. ### Claim 8 (depends on 3) The mobile work machine of claim 3, wherein the machine performance detection system is configured to apply a distance function between the topological representation and the reference model. ### Claim 9 (depends on 1) The mobile work machine of claim 1, wherein the sensor signal is indicative of vibration of the mobile work machine. ### Claim 10 (depends on 9) The mobile work machine of claim 9, wherein the sensor comprises an accelerometer. ### Claim 11 (depends on 9) The mobile work machine of claim 9, wherein the sensor comprises a hydraulic pressure sensor. ### Claim 12 (depends on 9) The mobile work machine of claim 9, wherein the sensor comprises a motor speed detector. ### Claim 13 (depends on 1) The mobile work machine of claim 1, wherein the sensor signal is indicative of an acoustic signal generated by the mobile work machine and detected by the sensor. ### Claim 14 (depends on 1) The mobile work machine of claim 1, wherein the machine performance characteristic comprises a wear indicator indicative of wear of one or more machine components. ### Claim 15 (depends on 1) The mobile work machine of claim 1, wherein the reference model is mapped to a machine anomaly record that identifies an anomalous machine operating condition. ### Claim 16 A method performed by a computing system associated with a mobile work machine, the method comprising: receiving, from a sensor associated with the mobile work machine, a sensor signal indicative of operation of the mobile work machine; generating a topological representation of the sensor signal; determining a machine performance characteristic based on the topological representation relative to a reference model; and generating a control signal to control the mobile work machine based on the machine performance characteristic. ### Claim 17 (depends on 16) The method of claim 16, wherein the sensor signal is indicative of operation of the mobile work machine during a given time period, and the reference model comprises a topological representation of the sensor signal generated by the sensor during a prior time period that precedes the given time period. ### Claim 18 (depends on 16) The method of claim 16, wherein the sensor signal defines a time series of feature values, and generating the topological representation comprises applying a topological data analysis algorithm to the time series of feature values to model persistence of the feature values over time. ### Claim 19 A computing system for a mobile work machine, the computing system comprising: at least one processor; and memory storing instructions executable by the at least one processor, wherein the instructions, when executed, cause the computing system to: receive a sensor signal that defines a time series of feature values; generate a topological representation that models a shape of the sensor signal over time by applying a topological data analysis algorithm to the time series of feature values; determine a machine performance characteristic based on the topological representation relative to a reference model; and generate a control signal to control the mobile work machine based on the machine performance characteristic. ### Claim 20 (depends on 19) The computing system of claim 19, wherein the instructions, when executed, cause the computing system to: generate a persistence model that models persistence of homological features in the sensor signal over time; and determine the machine performance characteristic based on the persistence model.