Systems and methods of dynamic adaptive fast charging in batteries to reduce lithium plating

One or more tangible, non-transitory computer-readable media storing instructions that, when executed, cause one or more processing devices to:

• determine whether an anode potential offset of a battery pack has reached an upper threshold of a target range;
• responsive to determining that the anode potential offset of the battery pack has reached the upper threshold of the target range, receive tear-down data associated with the battery pack;
• train, based on the tear-down data associated with the battery pack, one or more cloud prediction models that are trained to predict a likelihood of occurrence of lithium plating associated with battery packs;
• and
• transmit, to one or more edge processors of one or more fleet vehicles, one or more parameters associated with the one or more trained prediction models to cause the one or more edge processors to train one or more edge prediction models using the one or more edge processors, wherein the one or more edge processors modify a battery charging policy based on a prediction from the one or more edge prediction models.

A system comprising:

• one or more memory devices storing instructions;
• and
• one or more processing devices communicatively coupled to the one or more memory devices, the one or more processing devices execute the instructions to:
• determine whether an anode potential offset of a battery pack has reached an upper threshold of a target range;
• responsive to determining that the anode potential offset of the battery pack has reached the upper threshold of the target range, receive tear-down data associated with the battery pack;
• train, based on the tear-down data associated with the battery pack, one or more cloud prediction models that are trained to predict a likelihood of occurrence of lithium plating associated with battery packs;
• and
• transmit, to one or more edge processors of one or more fleet vehicles, one or more parameters associated with the one or more trained prediction models to cause the one or more edge processors to train one or more edge prediction models using the one or more edge processors, wherein the one or more edge processors modify a battery charging policy based on a prediction from the one or more edge prediction models.

An apparatus comprising:

• one or more memory devices storing instructions;
• and
• one or more processing devices communicatively coupled to the one or more memory devices, the one or more processing devices execute the instructions to:
• determine whether an anode potential offset of a battery pack has reached an upper threshold of a target range;
• responsive to determining that the anode potential offset of the battery pack has reached the upper threshold of the target range, receive tear-down data associated with the battery pack;
• train, based on the tear-down data associated with the battery pack, one or more cloud prediction models that are trained to predict a likelihood of occurrence of lithium plating associated with battery packs;
• and
• transmit, to one or more edge processors of one or more fleet vehicles, one or more parameters associated with the one or more trained prediction models to cause the one or more edge processors to train one or more edge prediction models using the one or more edge processors, wherein the one or more edge processors modify a battery charging policy based on a prediction from the one or more edge prediction models.