Method for predicting by artificial intelligence the remaining life of an electrochemical battery cell and associated devices

A calculator adapted to predict a parameter relating to a remaining life of at least one electrochemical cell of a battery, the at least one electrochemical cell having an open circuit voltage-state of charge characteristic with a planar portion, the planar portion being a portion wherein a change of an open circuit voltage is less than 30 millivolts (mV) for a change of at least 10% of a state of charge, the planar portion extending between a first limit corresponding to a first value of the state of charge and a second limit corresponding to a second value of the state of charge, the calculator being adapted to:

• obtain voltage and current measurements of the at least one electrochemical cell during a discharge comprising a limit of the planar portion and beginning at an initial instant,
• detect the limit of the planar portion using a criterion depending on the voltage and current measurements,
• calculate a value of a first parameter at the detected limit and a value of a second parameter at the detected limit, the first parameter being a parameter relating to voltage and the second parameter being a parameter relating to an amount of charge lost since the initial instant,
• predict a resistance of the at least one electrochemical cell by applying a first prediction function to first input parameters, the first input parameters comprising the value of the first parameter at the detected limit and the value of the second parameter at the detected limit, the first prediction function being obtained by a first learning technique, so as to obtain a value of the predicted resistance,
• predict a capacitance of the at least one electrochemical cell by applying a second prediction function to second input parameters, the second input parameters comprising the value of the first parameter at the detected limit and the value of the second parameter at the detected limit, the second prediction function being obtained by a second learning technique, so as to obtain a value of the predicted capacitance, and
• predict the parameter relating to the remaining life of the at least one electrochemical cell from the value of the predicted resistance and the value of the predicted capacitance.

A battery comprising:

• at least one electrochemical cell, the at least one electrochemical cell having the terminals and the open circuit voltage-state of charge characteristic with the planar portion, the planar portion being the portion wherein the change of the open circuit voltage is less than 30 mV for the change of at least 10% of the state of charge, the planar portion extending between the first limit corresponding to the first value of the state of charge and the second limit corresponding to the second value of the state of charge, and
• a management system for the at least one electrochemical cell of the battery, the management system comprising
• a voltage sensor adapted to measure the voltage across the at least one electrochemical cell during the discharge including the planar portion, a current sensor adapted to measure current at the terminals of the at least one electrochemical cell during the discharge comprising the planar portion, and
• a calculator adapted to predict a parameter relating to a remaining life of the
• at least one electrochemical cell of the battery, the calculator being adapted to:
• obtain voltage and current measurements of the at least one electrochemical cell during a discharge comprising a limit of the planar portion and beginning at an initial instant,
• detect the limit of the planar portion using a criterion depending on the voltage and current measurements,
• calculate a value of a first parameter at the detected limit and a value of a second parameter at the detected limit, the first parameter being a parameter relating to voltage and the second parameter being a parameter relating to an amount of charge lost since the initial instant, predict a resistance of the at least one electrochemical cell by applying a first prediction function to first input parameters, the first input parameters comprising the value of the first parameter at the detected limit and the value of the second parameter at the detected limit, the first prediction function being obtained by a first learning technique, so as to obtain a value of the predicted resistance,
• predict a capacitance of the at least one electrochemical cell by applying a second prediction function to second input parameters, the second input parameters comprising the value of the first parameter at the detected limit and the value of the second parameter at the detected limit, the second prediction function being obtained by a second learning technique, so as to obtain a value of the predicted capacitance, and
• predict the parameter relating to the remaining life of the at least one electrochemical cell from the value of the predicted resistance and the value of the predicted capacitance.