Battery degradation monitoring assessment and management
A vehicle includes a battery having a set of battery sensors. A controller is in communication with the set of battery sensors. The controller stores instructions for performing operations of: Receiving a data set including multiple data sources and multiple data collection cycles from the set of battery sensors. Data sources are classified within the data set based on a frequency of change in data from the data sources. Data is processed by determining an average value of each data element across each data collection cycle for data originating from data sources in the first classification and by partitioning data originating from data sources into a variable space. Processed data is applied to at least one risk assessment model and an indication of a chance of battery health deterioration for the battery is identified. A function of the battery is alerted in response to a chance of battery health deterioration.
1 . A vehicle comprising:
a battery including a set of battery sensors;
a controller in communication with the set of battery sensors, the controller having a non-transitory memory and a processor, wherein the non-transitory memory stores instructions for causing the controller to perform operations of:
receiving a data set from the set of battery sensors, the data set including multiple data sources and multiple data collection cycles of each data source;
classifying data sources within the data set into a first classification and a second classification based on a frequency of change in data from the data sources;
processing data in the data set by determining an average value of each data element across each data collection cycle for data originating from data sources in the first classification and by partitioning data originating from data sources in the second classification into a variable space;
applying processed data in the data set to at least one risk assessment model and identifying an indication of a chance of battery health deterioration for the battery; and
automatically altering at least one function of the battery in response to an identified indication of a chance of battery health deterioration.
2 . The vehicle of claim 1 , wherein the first classification is a slow dynamic data and the second classification is a fast dynamic data.
3 . The vehicle of claim 1 , wherein partitioning data originating from data sources in the second classification into a variable space comprises segmenting a variable space into a plurality of grids and assessing a suitability of the segmented variable space by comparing a number of grids in the variable space to a predefined value.
4 . The vehicle of claim 3 , further comprising responding to the number of grids exceeding the predefined value by determining the segmented variable space is suitable for transmission.
5 . The vehicle of claim 3 , further comprising responding to the number of grids being less than or equal to the predefined value by determining the segmented variable is unsuitable.
6 . The vehicle of claim 5 further comprising responding to the segmented variable space being unsuitable by identifying a region of interest including grids that meet a predefined set of parameters, and optimizing a cutoff value defining the segmented variable space based on the identified region of interest.
7 . The vehicle of claim 6 , further comprising re-segmenting the variable space using the optimized cutoff values.
8 . The vehicle of claim 1 , wherein the controller is in communication with an external data analysis system, and wherein processing data in the data set by determining an average value of each data element across each data collection cycle for data originating from data sources in the first classification and by partitioning data originating from data sources in the second classification into a variable space and applying processed data in the data set to at least one risk assessment model and identifying an indication of a chance of battery health deterioration for the battery are performed at the external data analysis system.
9 . The vehicle of claim 8 , further comprising losslessly encoding the data set into a low dimension latent space, transmitting the low dimension latent space from the vehicle to the external data analysis system and losslessly decoding the low dimension latent space.
10 . The vehicle of claim 8 , wherein identifying an indication of a chance of battery health deterioration for the battery further includes identifying at least one fleetwide modification to battery operations based on the identified indication of the chance of battery health deterioration.
11 . A method for monitoring a vehicle battery comprising:
Receiving, at a vehicle controller, a data set from a set of battery sensors, the data set including multiple data sources and multiple data collection cycles of each data source;
classifying data sources within the data set into a first classification and a second classification based on a frequency of change in data from the data sources;
processing data in the data set by determining an average value of each data element across each data collection cycle for data originating from data sources in the first classification and by partitioning data originating from data sources in the second classification into a variable space;
applying processed data in the data set to at least one risk assessment model and identifying an indication of a chance of battery health deterioration for a battery; and
automatically altering at least one function of the battery in response to an identified indication of a chance of battery health deterioration.
12 . The method of claim 11 , wherein the first classification is a slow dynamic data and the second classification is a fast dynamic data.
13 . The method of claim 11 , wherein partitioning data originating from data sources in the second classification into a variable space comprises segmenting a variable space into a plurality of grids and assessing a suitability of the segmented variable space by comparing a number of grids in the variable space to a predefined value.
14 . The method of claim 13 , further comprising responding to the number of grids exceeding the predefined value by determining the segmented variable space is suitable for transmission.
15 . The method of claim 13 , further comprising responding to the number of grids being less than or equal to the predefined value by determining the segmented variable is unsuitable.
16 . The method of claim 15 further comprising responding to the segmented variable space being unsuitable by identifying a region of interest including grids that meet a predefined set of parameters, and optimizing a cutoff value defining the segmented variable space based on the identified region of interest.
17 . The method of claim 16 , further comprising re-segmenting the variable space using the optimized cutoff values.
18 . The method of claim 11 , wherein the vehicle controller is in communication with an external data analysis system, and wherein processing data in the data set by determining an average value of each data element across each data collection cycle for data originating from data sources in the first classification and by partitioning data originating from data sources in the second classification into a variable space and applying processed data in the data set to at least one risk assessment model and identifying an indication of a chance of battery health deterioration for the battery are performed at the external data analysis system.
19 . The method of claim 18 , further comprising losslessly encoding the data set into a low dimension latent space, transmitting the low dimension latent space from the vehicle to the external data analysis system and losslessly decoding the low dimension latent space.
20 . The method of claim 18 , wherein identifying an indication of a chance of battery health deterioration for the battery further includes identifying at least one fleetwide modification to battery operations based on the identified indication of the chance of battery health deterioration.