Processing

Please wait...

Settings

Settings

Goto Application

1. US20200202643 - Systems And Methods To Diagnose Vehicles Based On The Voltage Of Automotive Batteries

Note: Text based on automatic Optical Character Recognition processes. Please use the PDF version for legal matters

[ EN ]

Claims

1. A method to facilitate vehicle diagnostics, the method comprising:
measuring a voltage of a battery and one or more operating parameters;
equating the voltage of the battery with the one or more operating parameters to create one or more correlations between the voltage and the one or more operating parameters;
determining that a state of the one or more operating parameters is anomalous when the one or more correlations between the voltage and the one or more operating parameters signifies that the state is anomalous; and
generating an alert that the state of the one or more operating parameters is anomalous.
2. The method of claim 1, further comprising:
mapping measured voltage to one or more measured operating parameters using machine learning,
constructing a predictive norm model that includes predicted correlations between the voltage of the battery and the one or more operating parameters; and
cross-validating the measured voltage and the one or more measured operating parameters with the predicted correlations of the predictive norm model.
3. The method of claim 2, wherein cross-validating further comprises determining that the state of the one or more operating parameters is anomalous when the measured voltage and the one or more measured operating parameters differ from the predicted correlations of the predictive norm model.
4. The method of claim 3, further comprising verifying that the state of the operating parameters is anomalous by comparing the one or more measured operating parameters with one or more other known correlations.
5. The method of claim 2, wherein cross-validating further comprises determining that the state of the one or more operating parameters is normal when the measured voltage and the one or more measured operating parameters align with the predicted correlations of the predictive norm model.
6. The method of claim 1, wherein equating the voltage of the battery with the one or more operating parameters further comprises mapping measured voltage to one or more measured operating parameters using machine learning.
7. The method of claim 6, wherein mapping the measured voltage to the one or more measured operating parameters further comprises constructing a predictive norm model, and wherein the predictive norm model includes predicted correlations between the voltage of the battery and the one or more operating parameters.
8. A system to facilitate vehicle diagnostics, the system comprising:
a processor;
a battery monitor to collect voltage of a battery in real-time and to generate a corresponding voltage signal;
a converter to transform the voltage signal into digital signal;
a communications module to collect vehicle information from an in-vehicle network; and
a machine learning engine, under the control of the processor, to:
ingest the vehicle information and the digital signal; and
generate a correlation between the digital signal and the vehicle information to determine an anomalous state within a vehicle system.
9. The system of claim 8, wherein the machine learning engine:
maps the digital signal to the vehicle information to create a one to one correlation between the digital signal and the vehicle information,
creates a predictive norm model to determine whether a state of the vehicle system is anomalous or normal, wherein predictive norm model comprises predicted correlations between the digital signal the vehicle information,
compares the one to one correlation between the vehicle signal and the digital signal with the predicted correlations of the predictive norm model.
10. The system of claim 9, wherein the machine learning engine determines that the state of the vehicle system is anomalous when the one to one correlation between the digital signal and the vehicle information differs from the predicted correlations of the predictive norm model.
11. The system of claim 10, wherein, upon determining the state of the vehicle system is anomalous, the machine learning engine validates that the state of the vehicle system is anomalous by comparing the vehicle information to other known correlations.
12. The system of claim 8, wherein the machine learning engine creates a predictive norm model to identify when a state of the vehicle system is anomalous, and wherein the predictive norm model includes predicted correlations between the digital signal and the vehicle information.
13. The system of claim 12, wherein the machine learning engine cross-validates the digital signal and the vehicle information, collected in real time, with the predicted correlations of the predictive norm model to identify whether the vehicle system is operating in an anomalous state or a normal state.
14. The system of claim 8, wherein the communications module, upon verification that an anomaly has occurred, notifies a vehicle operator that an anomaly has occurred.
15. A system to facilitate vehicle diagnostics, the system comprising:
a memory having stored thereon one or more predictive correlations between a voltage of a battery and one or more operating states of components within a machine;
a diagnostic module to determine an operating condition of the machine, wherein the operating condition includes an anomalous state and a normal state,
wherein the normal state is indicative of a convergence between the one or more predictive correlations and the operating condition of the machine,
wherein the anomalous state is indicative of a divergence between the one or more predictive correlations and the operating condition of the machine; and
a communication system to generate an alert that the state of the operating condition of the machine is anomalous.
16. The system of claim 15, wherein the diagnostic module, using machine learning, associates measured voltage signals of the machine to one or more measured operating states of the machine to create a correlation between the measured voltage signals and the one or more operating states.
17. The system of claim 16, wherein the diagnostic module to compares the correlation between the measured voltage signals and the one or more operating states with the one or more predictive correlations of the memory.
18. The system of claim 17, wherein the diagnostic module determines that the anomalous state occurred in the operating condition of the machine when the correlation between the measured voltage signals and the one or more operating states of the machine differs from the with the one or more predictive correlations of the memory.
19. The system of claim 18, wherein the diagnostic module, prior to the generation of the alert, validates that the anomalous state has occurred in by comparing the operating condition of the machine to other known correlations.
20. The system of claim 17, wherein the diagnostic module determines that the normal state occurred in the operating condition of the machine when the correlation between the measured voltage signals and the one or more operating states of the machine aligns with the one or more predictive correlations of the memory.