Systems and methods for automatically adapting an electric output of an electric power system

1 . An electric power system comprising:

a plurality of capacitors;

one or more sensors;

one or more processors;

one or more control switches; and

a memory in communication with the one or more processors and storing instructions that, when executed by the one or more processors, are configured to cause the electric power system to:

iteratively, until termination:

detect, by the one or more sensors, one or more properties of the plurality of capacitors;

determine, utilizing one or more machine learning models, whether the detected one or more properties exceed a threshold;

responsive to determining the detected one or more properties exceed the threshold;

generate, by the one or more machine learning models, control switch reconfiguration options for modifying contact between the plurality of capacitors;

modify, by the one or more control switches, the contact between the plurality of capacitors according to the control switch reconfiguration options, thereby resulting in automatic adaptation of an electric output of the electric power system; and

update the one or more machine learning models based on the modified contact.

2 . The electric power system of claim 1 , wherein each of the plurality of capacitors comprises a nano-structured carbon material.

3 . The electric power system of claim 2 , wherein the nano-structured carbon material has a density of approximately 0.7 g/cm 3 .

4 . The electric power system of claim 2 , wherein the nano-structured carbon material is configured to be fracture resistant.

5 . The electric power system of claim 2 , wherein the nano-structured carbon material comprises approximately 96 percent carbon by weight.

6 . The electric power system of claim 2 , wherein each of the plurality of capacitors is an electrochemical capacitor and comprises:

a first panel comprising:

a positive current collector; and

a positive electrode comprising the nano-structured carbon material;

a second panel comprising:

a negative current collector; and

a negative electrode comprising the nano-structured carbon material;

an electrode separator disposed between the first and second panels; and

an O-ring configured to form a seal between the first and second panels.

7 . The electric power system of claim 1 , wherein:

the one or more properties comprise one or more of voltage, magnetic field, vibration, resistance, capacitance, induction, pressure, temperature, or combinations thereof, and

the one or more machine learning models are trained to compare the detected one or more properties to previous property predictions to determine whether the detected one or more properties exceed the threshold.

8 . A method for automatically adapting an electric output of an electronic power system, the method comprising:

continuously detecting, using one or more sensors, one or more properties of a plurality of capacitors;

determining, using one or more machine learning models, whether the detected one or more properties exceed a threshold;

responsive to determining the detected one or more properties exceed the threshold:

generating, by the one or more machine learning models, control switch reconfiguration options for modifying contact between the plurality of capacitors;

modifying, by one or more control switches, the contact between the plurality of capacitors according to the control switch reconfiguration options, thereby resulting in automatic adaptation of the electric output of the electric power system; and

updating the one or more machine learning models based on the modified contact.

9 . The method of claim 8 , wherein the one or more properties comprise one or more of voltage, magnetic field, vibration, resistance, capacitance, induction, pressure, temperature, or combinations thereof.

10 . The method of claim 8 , wherein the one or more machine learning models are trained to compare the detected one or more properties to previous property predictions to determine whether the detected one or more properties exceed the threshold.

11 . The method of claim 8 , wherein updating the one or more machine learning models comprises selecting a first option of the control switch reconfiguration options and updating the one or more machine learning models based on the first option.

12 . The method of claim 8 , wherein each of the plurality of capacitors comprises:

a first panel comprising:

a positive current collector and

a positive electrode comprising a nano-structured carbon material; and

a second panel comprising:

a negative current collector; and

a negative electrode comprising the nano-structured carbon material; and

an electrode separator disposed between the first and second panels.

13 . The method of claim 12 , wherein the nano-structured carbon material has a density between approximately 0.4 to 1.2 g/cm 3 .

14 . The method of claim 13 , wherein the nano-structured carbon material comprises between approximately 90 and 99.5 percent carbon by weight.

15 . The method of claim 12 , wherein the electrode separator is porous and non-conductive.

16 . The method of claim 12 , wherein each of the plurality of capacitors is an electrochemical capacitor.

17 . The method of claim 12 , wherein each of the plurality of capacitors further comprises a seal between the first and second panels.

18 . The method of claim 17 , wherein each of the plurality of capacitors further comprises an O-ring configured to form the seal between the first and second panels.

19 . The method of claim 12 , wherein the nano-structured carbon material has a density between approximately 0.5 to 1.1 g/cm 3 .

20 . The method of claim 12 , wherein the nano-structured carbon material has a density of approximately 0.7 g/cm 3 .