Predictive charging to reduce battery capacity degradation

Abstract

According to an aspect, a system includes a battery configured to be charged by a power source, a charging circuit coupled to the battery, and a battery charging manager configured to communicate with the charging circuit to control a charging of the battery by the power source. The battery charging manager obtains a charge pattern including an end charge time corresponding to a time when the battery is estimated to be disconnected from the power source. The battery charging manager controls the charging circuit to charge, over a first charging period, the battery to a temporary charge level, maintain, over a relaxation period, a battery charge level between the temporary charge level and a maintenance charge level, and charge, over a second charging period after the relaxation period, the battery to a maximum battery charge level before the end charge time.

1 . (canceled) 
     
     
         2 . A system comprising:
 a battery configured to be charged by a power source;   a charging circuit coupled to the battery; and   a battery charging manager configured to communicate with the charging circuit to control a charging of the battery by the power source, the battery charging manager including a predictive model configured to generate a predicted charge pattern to charge the battery based on charging history data associated with a user of the system, the battery charging manager configured to control the charging of the battery based on the predicted charge pattern, including adjusting a charging rate during the charging of the battery.   
     
     
         3 . The system of  claim 2 , wherein the battery charging manager includes a prediction engine configured to compute the predicted charge pattern using the predictive model, the prediction engine configured to obtain one or more signals and input the one or more signals to the predictive model to compute the predicted charge pattern, the one or more signals comprising at least one of the charging history data, contextual data, or location data. 
     
     
         4 . The system of  claim 3 , wherein the one or more signals further comprise a temperature, and the prediction engine is configured to compute the predicted charge pattern based on the temperature. 
     
     
         5 . The system of  claim 3 , wherein the predictive model is configured to decrease a value of a temporary charge level based on a temperature being over a temperature threshold. 
     
     
         6 . The system of  claim 2 , wherein the battery charging manager is configured to determine the charging rate based on a predicted charge duration of the predicted charge pattern. 
     
     
         7 . The system of  claim 2 , wherein adjusting the charging rate includes:
 charging, over a first charging period, the battery at a first charging rate; and   charging, over a second charging period, the battery at a second charging rate.   
     
     
         8 . A non-transitory computer-readable medium storing executable instructions that when executed by a processor cause the processor to:
 communicate with a charging circuit to control a charging of a battery by a power source;   generate a predicted charge pattern to charge the battery based on charging history data associated with a user using a predictive model; and   control the charging of the battery based on the predicted charge pattern, including adjusting a charging rate during the charging of the battery.   
     
     
         9 . The non-transitory computer-readable medium of  claim 8 , wherein the executable instructions further cause the processor to: obtain one or more signals and input the one or more signals to the predictive model to compute the predicted charge pattern, the one or more signals comprising at least one of the charging history data, contextual data, or location data. 
     
     
         10 . The non-transitory computer-readable medium of  claim 9 , wherein the one or more signals further comprise a temperature, and the predicted charge pattern is computed based on the temperature. 
     
     
         11 . The non-transitory computer-readable medium of  claim 9 , wherein the predictive model is configured to decrease a value of a temporary charge level based on a temperature being over a temperature threshold. 
     
     
         12 . The non-transitory computer-readable medium of  claim 8 , wherein the executable instructions further cause the processor to: determine the charging rate based on a predicted charge duration of the predicted charge pattern. 
     
     
         13 . The non-transitory computer-readable medium of  claim 8 , wherein adjusting the charging rate includes charging, over a first charging period, the battery at a first charging rate; and charging, over a second charging period, the battery at a second charging rate. 
     
     
         14 . A method comprising:
 communicating, via a battery manager, with a charging circuit to control a charging of a battery by a power source;   generating a predicted charge pattern to charge the battery based on charging history data associated with a user using a predictive model; and   controlling the charging of the battery based on the predicted charge pattern, including adjusting a charging rate during the charging of the battery.   
     
     
         15 . The method of  claim 14 , further comprising:
 obtaining one or more signals and input the one or more signals to the predictive model to compute the predicted charge pattern, the one or more signals comprising at least one of the charging history data, contextual data, or location data.   
     
     
         16 . The method of  claim 15 , wherein the one or more signals comprise a temperature, and the predicted charge pattern is computed based on the temperature. 
     
     
         17 . The method of  claim 15 , wherein the predictive model is configured to decrease a value of a temporary charge level based on a temperature being over a temperature threshold. 
     
     
         18 . The method of  claim 14 , further comprising:
 determining the charging rate based on a predicted charge duration of the predicted charge pattern.   
     
     
         19 . The method of  claim 14 , wherein adjusting the charging rate includes charging, over a first charging period, the battery at a first charging rate; and charging, over a second charging period, the battery at a second charging rate.