公开(公告)号：US20210350818A1

公开(公告)日：2021-11-11

申请号：US17313878

申请日：2021-05-06

申请人： Feasible Inc.

发明人： Shaurjo BISWAS ,  Shan DOU ,  Aleksandr KIESSLING ,  Andrew HSIEH ,  Barry VAN TASSELL ,  Marc JUZKOW

IPC分类号： G10L25/51 ,  H04R1/34

摘要： Systems, techniques, and computer-implemented processes are provided for acoustic signal based analysis of thin-films, electrode coatings, and other components of batteries. Data analytics on signals obtained by ultrasound excitation of materials is used to analyze electrode coating parameters, analyzing separators, and other battery components. Using the disclosed techniques in battery manufacturing and production can lead to reduction in wastage of damaged/scrapped battery cells and shorten production time.

公开(公告)号：US20220155262A1

公开(公告)日：2022-05-19

申请号：US17455366

申请日：2021-11-17

申请人： FEASIBLE, INC.

发明人： Shaurjo BISWAS ,  Andrew HSIEH ,  Barry VAN TASSELL ,  Marc JUZKOW

IPC分类号： G01N29/44 ,  H01M10/04 ,  H01M4/04

摘要： Systems, techniques, and computer-implemented processes for acoustic signal based improvements to one or more process steps in the manufacture of battery cells. Information gathered based on an acoustic signal based analysis in one process step can be used in one or more other process steps using any suitable combination of feedback and/or feedforward of the acoustic signal based analysis. Such feedback and/or feedforward can improve the overall quality of battery cells produced using the manufacturing process, efficiency/cost of the manufacturing process, improvement in yield/reduction in wastage of the battery cells produced using the manufacturing process and/or improvements in individual process steps.

公开(公告)号：US20210365009A1

公开(公告)日：2021-11-25

申请号：US17327497

申请日：2021-05-21

申请人： Feasible, Inc.

发明人： Shaurjo BISWAS ,  Andrew HSIEH ,  Marc JUZKOW ,  Shan DOU ,  Barry VAN TASSELL

IPC分类号： G05B19/4155 ,  G10L25/51 ,  H04R1/08

摘要： Systems, methods, and computer-readable media are provided for controlling a battery manufacturing process. For instance, signal based analysis that can include audio signal analysis can be performed during a first process step of a battery manufacturing process. Based on the signal based analysis, at least one adjustment can be determined for a second process step of the battery manufacturing process. Information associated with the at least one adjustment can be provided to the second process step.

公开(公告)号：US20220206075A1

公开(公告)日：2022-06-30

申请号：US17457711

申请日：2021-12-06

申请人： FEASIBLE, INC. ,  The Trustees of Princeton University

发明人： Daniel STEINGART ,  Greg DAVIES ,  Shaurjo BISWAS ,  Andrew HSIEH ,  Barry VAN TASSELL ,  Thomas HODSON ,  Shan DOU

IPC分类号： G01R31/385 ,  G01N29/07 ,  G01N29/44 ,  G01N29/11 ,  G01N29/46 ,  G01N29/50 ,  H01M10/42 ,  G01N29/12 ,  G01N29/04 ,  G01N29/48 ,  G01R31/3835 ,  G06N20/00 ,  G06N5/04 ,  H01M10/48

摘要： Systems and methods for prediction of state of charge (SOH), state of health (SOC) and other characteristics of batteries using acoustic signals, includes determining acoustic data at two or more states of charge and determining a reduced acoustic data set representative of the acoustic data at the two or more states of charge. The reduced acoustic data set includes time of flight (TOF) shift, total signal amplitude, or other data points related to the states of charge. Machine learning models use at least the reduced acoustic dataset in conjunction with non-acoustic data such as voltage and temperature for predicting the characteristics of any other independent battery.

公开(公告)号：US20190072614A1

公开(公告)日：2019-03-07

申请号：US16117421

申请日：2018-08-30

申请人： Feasible, Inc. ,  The Trustees of Princeton University

发明人： Daniel A. STEINGART ,  Greg DAVIES ,  Shaurjo BISWAS ,  Andrew G. HSIEH ,  Barry VAN TASSELL ,  Thomas HODSON ,  Shan DOU

IPC分类号： G01R31/36 ,  H01M10/48 ,  G06N5/04 ,  G06F15/18 ,  H01M10/42

摘要： Systems and methods for prediction of state of charge (SOH), state of health (SOC) and other characteristics of batteries using acoustic signals, includes determining acoustic data at two or more states of charge and determining a reduced acoustic data set representative of the acoustic data at the two or more states of charge. The reduced acoustic data set includes time of flight (TOF) shift, total signal amplitude, or other data points related to the states of charge. Machine learning models use at least the reduced acoustic dataset in conjunction with non-acoustic data such as voltage and temperature for predicting the characteristics of any other independent battery.