IP Library › Granted Patent US 11,300,631
Granted Patent B1
US 11,300,631 · App. 17/192,877 · Granted Apr 12, 2022

Method and system for key predictors and machine learning for configuring cell performance

Inventors: Sam Keene (Long Beach, CA); Giulia Canton (Irvine, CA); Ian Browne (Orange, CA); Xianyang Li (Irvine, CA); Hong Zhao (Aliso Viejo, CA); Benjamin Park (Mission Viejo, CA)
Assignee: ENEVATE CORPORATION
G01R31/396G01R31/367G01R31/392
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 11,300,631
App. No.
17/192,877
Granted
Apr 12, 2022
Kind
B1
Abstract

A method for key predictors and machine learning for configuring battery cell performance may include providing a cell that includes a cathode, a separator, and a silicon-dominant anode; measuring a plurality of parameters of the cell; and using a machine learning model to determine cycle life based on the plurality of measured parameters, where one of the measured parameters includes second cycle coulombic efficiency. The plurality of parameters may include initial coulombic efficiency, cell impedance values, open-circuit voltage, cell thickness, and impedance after degassing. A first subset of the plurality of parameters may be measured before a formation process. A second subset of the plurality of parameters may be measured during a formation process, where the plurality of parameters may include a voltage reached during a first 10% of a first formation cycle. A third subset of the plurality of parameters may be measured during cycling of the cell.

Claims (108)

1. A method of predicting battery performance, the method comprising:

providing a cell comprising a cathode, a separator, and a silicon-dominant anode;

measuring, via a measurement apparatus configured for obtaining particular types of measurements relating to cells and operations of cells, a plurality of parameters of the cell; and

using a machine learning model to predetermine cycle life based on the plurality of measured parameters;

wherein the plurality of parameters comprise characteristics of cell components or raw materials prior to assembly; and

wherein the data prior to assembly comprises, for electrodes, one or more of: loading, conductivity, mechanical strength, wettability, pyrolysis temperature, resin formulation, active material type, and active material particle size.

2. The method of claim 1 , wherein the plurality of parameters comprise initial coulombic efficiency.

3. The method of claim 1 , wherein the plurality of measured parameters comprises second cycle coulombic efficiency.

4. The method of claim 1 , wherein the plurality of parameters comprise cell impedance values.

5. The method of claim 1 , wherein the plurality of parameters comprise open-circuit voltage.

6. The method of claim 1 , wherein the plurality of parameters comprise cell thickness.

7. The method of claim 1 , wherein the plurality of parameters comprise impedance after degassing.

8. The method of claim 1 , comprising measuring a first subset of the plurality of parameters before a formation process.

9. The method of claim 1 , comprising measuring a second subset of the plurality of parameters during a formation process.

10. The method according to claim 9 , wherein the plurality of parameters comprise a voltage reached during a first 10% of a first formation cycle.

11. The method of claim 1 , comprising measuring a third subset of the plurality of parameters during cycling of the cell.

12. The method of claim 11 , wherein the plurality of parameters comprise a comparison of two different voltage curves of the cell within a first ten cycles, wherein the voltage curves comprise voltage vs. capacity data points that are acquired as the cell is cycled.

13. The method of claim 11 , wherein the plurality of parameters comprise a charge capacity of the cell within a first ten cycles.

14. The method of claim 11 , wherein the plurality of parameters comprise a discharge capacity of the cell within a first ten cycles.

15. The method according to claim 1 , wherein the cycle life is defined as a number of cycles to reach 60-80% of initial capacity.

16. A method of predicting battery performance, the method comprising:

providing a cell comprising a cathode, a separator, and a silicon-dominant anode;

measuring, via a measurement apparatus configured for obtaining particular types of measurements relating to cells and operations of cells, a plurality of parameters of the cell; and

using a machine learning model to predetermine cycle life based on the plurality of measured parameters;

wherein the plurality of parameters comprise characteristics of cell components or raw materials prior to assembly; and

wherein the data prior to assembly comprises, for electrolytes, one or more of: conductivity, viscosity, and formulation.

17. The method of claim 16 , wherein the plurality of parameters comprise initial coulombic efficiency.

18. The method of claim 16 , wherein the plurality of measured parameters comprises second cycle coulombic efficiency.

19. The method of claim 16 , wherein the plurality of parameters comprise cell impedance values.

20. The method of claim 16 , wherein the plurality of parameters comprise open-circuit voltage.

21. The method of claim 16 , wherein the plurality of parameters comprise cell thickness.

22. The method of claim 16 , wherein the plurality of parameters comprise impedance after degassing.

23. The method of claim 16 , comprising measuring a first subset of the plurality of parameters before a formation process.

24. The method of claim 16 , comprising measuring a second subset of the plurality of parameters during a formation process.

25. The method according to claim 24 , wherein the plurality of parameters comprise a voltage reached during a first 10% of a first formation cycle.

26. The method of claim 16 , comprising measuring a third subset of the plurality of parameters during cycling of the cell.

27. The method of claim 26 , wherein the plurality of parameters comprise a comparison of two different voltage curves of the cell within a first ten cycles, wherein the voltage curves comprise voltage vs. capacity data points that are acquired as the cell is cycled.

28. The method of claim 26 , wherein the plurality of parameters comprise a charge capacity of the cell within a first ten cycles.

29. The method of claim 26 , wherein the plurality of parameters comprise a discharge capacity of the cell within a first ten cycles.

30. The method according to claim 16 , wherein the cycle life is defined as a number of cycles to reach 60-80% of initial capacity.

31. A method of predicting battery performance, the method comprising:

providing a cell comprising a cathode, a separator, and a silicon-dominant anode;

measuring, via a measurement apparatus configured for obtaining particular types of measurements relating to cells and operations of cells, a plurality of parameters of the cell; and

using a machine learning model to predetermine cycle life based on the plurality of measured parameters;

wherein the plurality of parameters comprise characteristics of cell components or raw materials prior to assembly; and

wherein the data prior to assembly comprises, for separators: porosity and/or tortuosity.

32. The method of claim 31 , wherein the plurality of parameters comprise initial coulombic efficiency.

33. The method of claim 31 , wherein the plurality of measured parameters comprises second cycle coulombic efficiency.

34. The method of claim 31 , wherein the plurality of parameters comprise cell impedance values.

35. The method of claim 31 , wherein the plurality of parameters comprise open-circuit voltage.

36. The method of claim 31 , wherein the plurality of parameters comprise cell thickness.

37. The method of claim 31 , wherein the plurality of parameters comprise impedance after degassing.

38. The method of claim 31 , comprising measuring a first subset of the plurality of parameters before a formation process.

39. The method of claim 31 , comprising measuring a second subset of the plurality of parameters during a formation process.

40. The method according to claim 39 , wherein the plurality of parameters comprise a voltage reached during a first 10% of a first formation cycle.

41. The method of claim 31 , comprising measuring a third subset of the plurality of parameters during cycling of the cell.

42. The method of claim 41 , wherein the plurality of parameters comprise a comparison of two different voltage curves of the cell within a first ten cycles, wherein the voltage curves comprise voltage vs. capacity data points that are acquired as the cell is cycled.

43. The method of claim 41 , wherein the plurality of parameters comprise a charge capacity of the cell within a first ten cycles.

44. The method of claim 41 , wherein the plurality of parameters comprise a discharge capacity of the cell within a first ten cycles.

45. The method according to claim 31 , wherein the cycle life is defined as a number of cycles to reach 60-80% of initial capacity.

46. A method of predicting battery performance, the method comprising:

providing a cell comprising a cathode, a separator, and a silicon-dominant anode;

measuring, via a measurement apparatus configured for obtaining particular types of measurements relating to cells and operations of cells, a plurality of parameters of the cell;

using a machine learning model to predetermine cycle life based on the plurality of measured parameters; and

measuring a third subset of the plurality of parameters during cycling of the cell;

wherein the plurality of parameters comprise a comparison of two different voltage curves of the cell within a first ten cycles, wherein the voltage curves comprise voltage vs. capacity data points that are acquired as the cell is cycled.

47. The method of claim 46 , wherein the plurality of parameters comprise initial coulombic efficiency.

48. The method of claim 46 , wherein the plurality of measured parameters comprises second cycle coulombic efficiency.

49. The method of claim 46 , wherein the plurality of parameters comprise cell impedance values.

50. The method of claim 46 , wherein the plurality of parameters comprise open-circuit voltage.

51. The method of claim 46 , wherein the plurality of parameters comprise cell thickness.

52. The method of claim 46 , wherein the plurality of parameters comprise impedance after degassing.

53. The method of claim 46 , comprising measuring a first subset of the plurality of parameters before a formation process.

54. The method of claim 46 , comprising measuring a second subset of the plurality of parameters during a formation process.

55. The method according to claim 46 , wherein the plurality of parameters comprise a voltage reached during a first 10% of a first formation cycle.

56. The method according to claim 46 , wherein the cycle life is defined as a number of cycles to reach 60-80% of initial capacity.

57. A method of predicting battery performance, the method comprising:

providing a cell comprising a cathode, a separator, and a silicon-dominant anode;

measuring, via a measurement apparatus configured for obtaining particular types of measurements relating to cells and operations of cells, a plurality of parameters of the cell;

using a machine learning model to predetermine cycle life based on the plurality of measured parameters; and

measuring a third subset of the plurality of parameters during cycling of the cell;

wherein the plurality of parameters comprise a charge capacity of the cell within a first ten cycles.

58. The method of claim 57 , wherein the plurality of parameters comprise initial coulombic efficiency.

59. The method of claim 57 , wherein the plurality of measured parameters comprises second cycle coulombic efficiency.

60. The method of claim 57 , wherein the plurality of parameters comprise cell impedance values.

61. The method of claim 57 , wherein the plurality of parameters comprise open-circuit voltage.

62. The method of claim 57 , wherein the plurality of parameters comprise cell thickness.

63. The method of claim 57 , wherein the plurality of parameters comprise impedance after degassing.

64. The method of claim 57 , comprising measuring a first subset of the plurality of parameters before a formation process.

65. The method of claim 57 , comprising measuring a second subset of the plurality of parameters during a formation process.

66. The method according to claim 65 , wherein the plurality of parameters comprise a voltage reached during a first 10% of a first formation cycle.

67. The method according to claim 57 , wherein the cycle life is defined as a number of cycles to reach 60-80% of initial capacity.

68. A method of predicting battery performance, the method comprising:

providing a cell comprising a cathode, a separator, and a silicon-dominant anode;

measuring, via a measurement apparatus configured for obtaining particular types of measurements relating to cells and operations of cells, a plurality of parameters of the cell;

using a machine learning model to predetermine cycle life based on the plurality of measured parameters; and

measuring a third subset of the plurality of parameters during cycling of the cell;

wherein the plurality of parameters comprise a discharge capacity of the cell within a first ten cycles.

69. The method of claim 68 , wherein the plurality of parameters comprise initial coulombic efficiency.

70. The method of claim 68 , wherein the plurality of measured parameters comprises second cycle coulombic efficiency.

71. The method of claim 68 , wherein the plurality of parameters comprise cell impedance values.

72. The method of claim 68 , wherein the plurality of parameters comprise open-circuit voltage.

73. The method of claim 68 , wherein the plurality of parameters comprise cell thickness.

74. The method of claim 68 , wherein the plurality of parameters comprise impedance after degassing.

75. The method of claim 68 , comprising measuring a first subset of the plurality of parameters before a formation process.

76. The method of claim 68 , comprising measuring a second subset of the plurality of parameters during a formation process.

77. The method according to claim 76 , wherein the plurality of parameters comprise a voltage reached during a first 10% of a first formation cycle.

78. The method according to claim 68 , wherein the cycle life is defined as a number of cycles to reach 60-80% of initial capacity.

Assignments (2)
SECURITY INTEREST Recorded Mar 10, 2026
From: ENEVATE CORPORATION
To: MCANDREWS, HELD & MALLOY LTD.
Reel/Frame 075093/0935 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Jan 12, 2022
From: KEENE, SAM; CANTON, GIULIA; BROWNE, IAN; LI, XIANYANG; ZHAO, HONG; PARK, BENJAMIN
To: ENEVATE CORPORATION
Reel/Frame 058636/0834 →