Granted Patent B2

US 12,198,482 · App. 17/666,275 · Granted Jan 14, 2025

Inventors: Anurag Ganguli (Milpitas, CA); Rajinderjeet Singh Minhas (Mountain View, CA); Johan de Kleer (Los Altos, CA)

Assignee: XEROX CORPORATION

G07C5/0808G06Q10/20G06Q30/014G06Q30/018G07C5/006G06Q50/40

Abstract

Claims (37)

1. A method for determining vehicle component conditions, further comprising:

building a predictive model for a vehicle component;

mapping values for a feature of the vehicle component using the model;

applying a threshold to the mapped values;

predicting an occurrence of a fault of the vehicle component when one or more of the mapped values exceeds the threshold, wherein the fault comprises one or more of an object stuck in the vehicle component, an obstacle in a bottom rail of the vehicle component, bending or deformity of the bottom rail, loose bolts, a presence of dirt, and a lack of grease; and

identifying a probability distribution of time when the feature is expected to exceed the threshold at which the fault is predicted to occur.

2. The method according to claim 1 , comprising:

calculating a mean of the probability distribution; and

assigning the mean of the probability distribution as a time at which the fault of the vehicle component is predicted to occur.

3. The method according to claim 2 , wherein the further comprising:

determining an extended optimal interval for vehicle maintenance comprising a time period between a manually scheduled maintenance at a time T scheduled for the vehicle component and a time T 0 at which the fault of the vehicle component is predicted to occur.

4. The method according to claim 3 , further comprising:

scheduling the vehicle maintenance during the extended optimal interval.

5. The method according to claim 4 , wherein a time of the manually scheduled maintenance is extended to a time during the extended optimal interval.

6. The method according to claim 3 , further comprising:

scheduling the maintenance at a time of T 0 -3σ, wherein o represents standard distribution.

7. The method according to claim 1 , further comprising:

recommending maintenance of the vehicle component before the fault of the vehicle component is predicted to occur.

8. The method according to claim 1 , wherein the predictive model is based on one or more factors comprising time, temperature, and usage.

9. The method according to claim 1 , wherein the feature comprises one or more of a mean value of a motor current during a state of the vehicle component, a highest value of the motor current in that state, a lowest value of the motor current for that state, an amount of variation of the motor current from the mean value, a time span for the state, a mean of the motor current during opening of the vehicle component, a mean of the motor current during closing of the vehicle component, an average outside temperature, and an average temperature of a motor of a vehicle with the vehicle component.

10. A system for determining vehicle component conditions, further comprising:

a database to store a predictive model for a vehicle component; and

a server comprising memory and a processor, wherein the processor is configured to perform the following:

map values for a feature of the vehicle component using the model from the database;

apply a threshold to the mapped values;

predict an occurrence of a fault of the vehicle component when one or more of the mapped values exceeds the threshold, wherein the fault comprises one or more of an object stuck in the vehicle component, an obstacle in a bottom rail of the vehicle component, bending or deformity of the bottom rail, loose bolts, a presence of dirt, and a lack of grease; and

identify a probability distribution of time when the feature is expected to exceed the threshold at which the fault is predicted to occur.

11. The system according to claim 10 , wherein the processor performs the following:

calculating a mean of the probability distribution; and

assigning the mean of the probability distribution as the time at which the fault of the vehicle component is predicted to occur.

12. The system according to claim 11 , wherein an extended optimal interval for vehicle maintenance comprises a time period between a manually scheduled maintenance at a time T scheduled for the vehicle component and a time T 0 at which the fault of the vehicle component is predicted to occur.

13. The system according to claim 12 , wherein the processor schedules the vehicle maintenance during the extended optimal interval.

14. The system according to claim 13 , wherein a time of the manually scheduled maintenance is extended to a time during the extended optimal interval.

15. The system according to claim 12 , wherein the processor schedules the maintenance at a time of T 0 -3σ, wherein σ represents standard distribution.

16. The system according to claim 10 , wherein the processor recommends maintenance of the vehicle component before the fault of the vehicle component is predicted to occur.

17. The system according to claim 10 , wherein the predictive model is based on one or more factors comprising time, temperature, and usage.

18. The system according to claim 10 , wherein the feature comprises one or more of a mean value of a motor current during a state of the vehicle component, a highest value of the motor current in that state, a lowest value of the motor current for that state, an amount of variation of the motor current from the mean value, a time span for the state, a mean of the motor current during opening of the vehicle component, a mean of the motor current during closing of the vehicle component, an average outside temperature, and an average temperature of a motor of a vehicle with the vehicle component.

Assignments (7)

Continuity (3)

References Cited (23)