# US 12,118,836 B2 · Probability neural network for reduced battery power drain > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 12,118,836 B2 - Document ID: US12118836B2 - Status: Granted - Kind: B2 - Application number: 17/490,170 - Filed: 2021-09-30 - Published: 2023-03-30 - Granted: 2024-10-15 - Earliest claimed: 2021-09-30 - Assignees: Ford Global Technologies, LLC - Applicants: Ford Global Technologies, LLC - Inventors: Vivek Kumar; Di Zhu; Sumanth Reddy Dadam - Web page: https://patentgrep.com/patent/US12118836B2 ## CPC - B60R 16/03: for supply of electrical power to vehicle subsystems {or for (circuit arrangements for charging batteries H02J7/00)} - G07C 5/0816: {Indicating performance data, e.g. occurrence of a malfunction} - G01R 31/382: Arrangements for monitoring battery or accumulator variables, e.g. SoC - G05B 13/027: {using neural networks only} - G01R 31/007: {using microprocessors or computers} - Y02T 10/70: Energy storage systems for electromobility, e.g. batteries - B60R: VEHICLES, VEHICLE FITTINGS, OR VEHICLE PARTS, NOT OTHERWISE PROVIDED FOR - 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 - G01R: MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES (indicating correct tuning of resonant circuits H03J3/12) - 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) - Y02T: CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION ## Abstract A processor, responsive to detecting a controller is drawing power from a battery to perform a task when a vehicle is parked and detecting a parameter indicative of a likelihood that the controller will complete the task within a predefined time period has a value less than a threshold value, generates a message for a user requesting whether the controller should be shut down without completing the task. ## Claims ### Claim 1 A vehicle comprising: a battery; a plurality of controllers; and a processor programmed to, responsive to detecting at least one of the controllers is drawing power from the battery to perform a task when the vehicle is parked and detecting a parameter has a value less than a threshold value, command the at least one controller to shut down without completing the task, wherein the threshold value depends on a state of charge of the battery and the task being performed such that different tasks have different threshold values. ### Claim 2 (depends on 1) The vehicle of claim 1, wherein the processor is further programmed to, responsive to detecting the at least one of the controllers is drawing power from the battery to perform a task when the vehicle is parked and detecting the parameter has a value greater than the threshold value, wait for the at least one controller to complete the task. ### Claim 3 (depends on 1) The vehicle of claim 1, wherein the threshold value further depends on ambient temperature. ### Claim 4 (depends on 1) The vehicle of claim 1, wherein the processor is further programmed to implement a probability neural network that generates the value. ### Claim 5 (depends on 1) The vehicle of claim 1, wherein the value indicates a likelihood that the at least one controller will complete the task within a predefined time period. ### Claim 6 A vehicle system comprising: a processor programmed to, responsive to detecting a controller is drawing power from a battery to perform a task when the vehicle is parked and detecting a parameter indicative of a likelihood that the controller will complete the task within a predefined time period has a value less than a threshold value, generate a message for a user requesting whether the controller should be shut down without completing the task, and responsive to detecting the controller is drawing power from the battery to perform the task when the vehicle is parked and detecting the parameter has a value greater than the threshold value, preclude shutting down the controller without completing the task. ### Claim 7 (depends on 6) The vehicle system of claim 6, wherein the processor is further programmed to, responsive to confirmation from the user that the controller should be shut down without completing the task, command the controller to shut down without completing the task. ### Claim 8 (depends on 6) The vehicle system of claim 6, wherein the threshold value depends on the task being performed such that different tasks have different threshold values. ### Claim 9 (depends on 6) The vehicle system of claim 6, wherein the threshold value depends on a state of charge of the battery. ### Claim 10 (depends on 6) The vehicle system of claim 6, wherein the threshold value depends on ambient temperature. ### Claim 11 (depends on 6) The vehicle system of claim 6, wherein the processor is further programmed to implement a probability neural network that generates the value. ### Claim 12 A method comprising: responsive to detecting a controller of a vehicle is drawing power from a battery to perform a task when the vehicle is parked and detecting a parameter has a value less than a threshold value that depends on the task being performed, commanding the controller to shut down without completing the task; and altering the value based on ambient temperature. ### Claim 13 (depends on 12) The method of claim 12 further comprising, responsive to detecting the controller is drawing power from the battery to perform a task when the vehicle is parked and the parameter having a value greater than the threshold value, waiting for the controller to complete the task. ### Claim 14 (depends on 12) The method of claim 12 further comprising altering the value based on a state of charge of the battery. ### Claim 15 (depends on 12) The method of claim 12 further comprising generating the value via a probability neural network. ### Claim 16 (depends on 12) The method of claim 12, wherein the value indicates a likelihood that the at least one controller will complete the task within a predefined time period.