A redox flow battery includes a cell that has first and second electrodes and an ion-exchange layer there between, first and second circulation loops that are fluidly connected with, respectively, the first and second electrodes, first and second electrolyte storage tanks in, respectively, the first and second circulation loops, first and second electrolytes contained in, respectively, the first and second circulation loops, and a Raman spectrometer on at least one of the first or second circulation loops for determining a state-of-charge of at least one of the first or second electrolytes. The Raman spectrometer includes a laser source that is rated to emit a laser of a wavelength of 694 nanometers to 1444 nanometers.

A battery charger and method is disclosed for detecting when a battery has a low state of health while simultaneously charging or maintaining the battery. A battery charger includes a processor; a non-transitory memory device; a power management device to receive an input power and to output a charging current; a pair of electrical conductors to electrically couple with a battery, and a display electrically coupled to the processor. The display being configured to indicate a bad battery indicator when the battery has a low state of health and whether the battery is good to start.

An electronic device, including a memory; a processor; and a remaining useful life (RUL) prediction controller configured to: identify at least one parameter corresponding to at least one of a physical composition and a chemical composition of a plurality of used batteries during at least one of a charging and a discharging of the plurality of used batteries; determine a pattern of variations in at least one of a voltage, a current, a temperature, and a resistance during every cycle of the charging and the discharging of the plurality of used batteries until a failure; generate an artificial intelligence (AI) model which is trained based on a correlation between the determined pattern of variations and the at least one of the physical composition and the chemical composition; and evaluate a RUL of the plurality of used batteries using the AI model.

A method for determining a state value of a traction battery of an electric vehicle characterises the ageing state, preferably an SoH value. The traction battery is charged or discharged by a test load and a respective output voltage and load current value pair is acquired. An ohmic internal resistance is established on the basis of the acquired value pair. The state value is established on the basis of the established ohmic internal resistance. At least one normalisation variable characterizing the traction battery is established. On the basis of the established ohmic internal resistance and the normalisation variable, a normalised internal resistance based on a reference value of the normalisation variable is established. The state value is established on the basis of the normalised internal resistance. A diagnostics device has an evaluation unit which is directly or indirectly couplable to the traction battery and carries out the method.

A method for estimating the state of charge (SOC) of a lithium-ion battery system based on artificial intelligence (AI) is provided. In the method, the relationship between the charging data segments and the SOC of the battery system is established through deep learning, and the SOC at any stage of the charging process can be corrected. SOC in a discharging process is estimated through ampere-hour integration. The estimation method is adaptively updated with a change in the working state of the battery system.

A method for estimating the state of charge (SOC) of a lithium-ion battery system based on artificial intelligence (AI) is provided. In the method, the relationship between the charging data segments and the SOC of the battery system is established through deep learning, and the SOC at any stage of the charging process can be corrected. SOC in a discharging process is estimated through ampere-hour integration. The estimation method is adaptively updated with a change in the working state of the battery system.

An examination method of the present invention is characterized by including a step of bringing conductor probes into contact with surfaces of an examination target to measure voltage or electric resistance at a plurality of points on the surfaces of the examination target, the examination target being a resin current collector, an electrode sheet having an active material layer laminated on the resin current collector, a separator-attached electrode sheet in which a separator is combined with the electrode sheet, or a unit cell including one set of a positive electrode resin current collector, a positive electrode active material layer, a separator, a negative electrode active material layer, and a negative electrode resin current collector, which are laminated in order, and a step of determining whether or not a point at which the voltage or the electric resistance is out of an allowable range is present in the examination target.

An examination method of the present invention is characterized by including a step of bringing conductor probes into contact with surfaces of an examination target to measure voltage or electric resistance at a plurality of points on the surfaces of the examination target, the examination target being a resin current collector, an electrode sheet having an active material layer laminated on the resin current collector, a separator-attached electrode sheet in which a separator is combined with the electrode sheet, or a unit cell including one set of a positive electrode resin current collector, a positive electrode active material layer, a separator, a negative electrode active material layer, and a negative electrode resin current collector, which are laminated in order, and a step of determining whether or not a point at which the voltage or the electric resistance is out of an allowable range is present in the examination target.

A lithium ion battery lifetime prediction method executes, by a computer, acquiring training data including cycle measurement data and lifetime data of a battery, learning a lifetime prediction model using the training data with respect to one or more cycle numbers at which a prediction is made, to acquire a set of learned lifetime prediction models corresponding to the cycle numbers at which the prediction is made, respectively, successively acquiring cycle measurement data for prediction of a battery that is a prediction target, up to the cycle numbers at which the prediction is made, respectively, and inputting the cycle measurement data for prediction acquired up to the cycle numbers at which the prediction is made, to the learned lifetime prediction models of the corresponding cycle numbers at which the prediction is made, and acquiring a probability distribution of a lifetime at the cycle numbers at which the prediction is made, respectively, as an output.

A lithium ion battery lifetime prediction method executes, by a computer, acquiring training data including cycle measurement data and lifetime data of a battery, learning a lifetime prediction model using the training data with respect to one or more cycle numbers at which a prediction is made, to acquire a set of learned lifetime prediction models corresponding to the cycle numbers at which the prediction is made, respectively, successively acquiring cycle measurement data for prediction of a battery that is a prediction target, up to the cycle numbers at which the prediction is made, respectively, and inputting the cycle measurement data for prediction acquired up to the cycle numbers at which the prediction is made, to the learned lifetime prediction models of the corresponding cycle numbers at which the prediction is made, and acquiring a probability distribution of a lifetime at the cycle numbers at which the prediction is made, respectively, as an output.