Abstract: The present disclosure provides a method and a system for improving the state of health (SoH) of rechargeable batteries. The method comprises receiving a plurality of battery parameters during charging of a battery and estimating model parameters of the battery using a mathematical model. The method also comprises comparing the estimated model parameters of the battery and the received battery parameters to determine degradation parameters of the battery in real-time, determining new charging current profile of the battery based on the degradation parameters of the battery, and applying the determined new charging current profile to the battery for improving the SoH of the battery.

Abstract: The embodiments herein disclose a method and system for designing molecules by using a machine learning algorithm. The method includes representing molecular structures included in a dataset by using a Simplified Molecular Input Line Entry System (SMILES), where the SMILES uses a series of characters, converting a SMILES representation of the molecular structures into a binary representation, pre-training a stack of Restricted Boltzmann Machines (RBMs) by using the binary representation of the molecular structures, constructing a Deep Boltzmann Machine (DBM) by using the stack of the RBMs, determining limited molecular property data for a subset of the molecule structures in the dataset, training the DBM with the limited molecular property data, combining the pre-trained stack of the RBMs and the trained DBM in a Bayesian inference framework, and generating a sample of molecules with target properties by using the Bayesian inference framework.

Abstract: Disclosed is an electronic device including a battery, a charging circuit configured to charge the battery, a measurement circuit configured to measure a state of the battery, and a processor configured to be electrically connected with the battery, the charging circuit, and the measurement circuit, to charge the battery using the charging circuit set by a first charging parameter, determine state information corresponding to a state of the battery based on data associated with the state of the battery obtained using the measurement circuit, determine a second charging parameter for reducing loss of a capacity of the battery based on the state information, and charge the battery using the charging circuit set by the second charging parameter.

Abstract: The present disclosure provides a method and a system for improving the state of health (SoH) of rechargeable batteries. The method comprises receiving a plurality of battery parameters during charging of a battery and estimating model parameters of the battery using a mathematical model. The method also comprises comparing the estimated model parameters of the battery and the received battery parameters to determine degradation parameters of the battery in real-time, determining new charging current profile of the battery based on the degradation parameters of the battery, and applying the determined new charging current profile to the battery for improving the SoH of the battery.

Abstract: Embodiments herein provide a method for real time adaptive charging of a battery. The method includes receiving at least one battery parameter. Further, the method includes determining a present battery condition. Further, the method includes correcting the at least one battery parameter based on the present battery condition. Further, the method includes determining a real time optimal current used for charging the battery based on the at least one corrected battery parameter. Further, the method includes charging the battery based on the determined real time optimal current, where a battery management system configures a charger integrated circuit to charge the battery. Further, the method includes updating and storing the at least one battery parameter in real time in a memory after charging the battery at the optimal current.

Abstract: The present subject refers to a method for battery fault diagnosis and prevention of hazardous conditions. The method comprises determining a plurality of parameters defined as one or more of current, voltage, or state of charge during operation of a battery-powered device. Further, one or more likelihood ratios related to malfunctioning of the battery are evaluated based on determined parameters. At least one of: a current battery-state or a type of current battery state are determined based on the one or more likelihood ratios as evaluated.

Abstract: Disclosed is a battery state of charge (SOC) determining method and a battery managing apparatus that acquires a stochastic reduced order model (SROM) and a mean using battery conservation equations acquired based on a stochastic Pseudo 2-dimensional electrochemical thermal (P2D-ECT) model, measures state information, and assimilates the state information with the SROM and the mean to determine an accurate SOC at a relatively low calculation cost.

Abstract: The embodiments herein disclose a method and system for designing molecules by using a machine learning algorithm. The method includes representing molecular structures included in a dataset by using a Simplified Molecular Input Line Entry System (SMILES), where the SMILES uses a series of characters, converting a SMILES representation of the molecular structures into a binary representation, pre-training a stack of Restricted Boltzmann Machines (RBMs) by using the binary representation of the molecular structures, constructing a Deep Boltzmann Machine (DBM) by using the stack of the RBMs, determining limited molecular property data for a subset of the molecule structures in the dataset, training the DBM with the limited molecular property data, combining the pre-trained stack of the RBMs and the trained DBM in a Bayesian inference framework, and generating a sample of molecules with target properties by using the Bayesian inference framework.

Abstract: Embodiments herein provide a method and electronic device for detecting an internal short circuit in a battery. The method includes obtaining, by a battery management system, battery gauge data. Further, the method includes estimating, by the battery management system, an internal resistance of the battery using the battery gauge data. Furthermore, the method includes detecting, by the battery management system, the internal short circuit in the battery by comparing a change in the internal resistance with a pre-defined resistance change threshold value.

Abstract: Disclosed is an electronic device including a battery, a charging circuit configured to charge the battery, a measurement circuit configured to measure a state of the battery, and a processor configured to be electrically connected with the battery, the charging circuit, and the measurement circuit, to charge the battery using the charging circuit set by a first charging parameter, determine state information corresponding to a state of the battery based on data associated with the state of the battery obtained using the measurement circuit, determine a second charging parameter for reducing loss of a capacity of the battery based on the state information, and charge the battery using the charging circuit set by the second charging parameter.

Abstract: Embodiments herein provide a method and electronic device for detecting an internal short circuit in a battery. The method includes obtaining, by a battery management system, battery gauge data. Further, the method includes estimating, by the battery management system, an internal resistance of the battery using the battery gauge data. Furthermore, the method includes detecting, by the battery management system, the internal short circuit in the battery by comparing a change in the internal resistance with a pre-defined resistance change threshold value.

Abstract: Disclosed is a battery state of charge (SOC) determining method and a battery managing apparatus that acquires a stochastic reduced order model (SROM) and a mean using battery conservation equations acquired based on a stochastic Pseudo 2-dimensional electrochemical thermal (P2D-ECT) model, measures state information, and assimilates the state information with the SROM and the mean to determine an accurate SOC at a relatively low calculation cost.