Battery Test System, Battery Test Bench and Server and Method for Assessing a Battery State

A battery test bench, wherein the battery test bench comprises:

• a measurement device configured for performing a battery capacity measurement and an electrical impedance spectrum measurement on an electrochemical battery connected to the measurement device, and
• a communication interface configured for communicating with a server via a communication network,
• wherein the battery test bench is configured for first performing first measurements on a number of batteries of a same kind to obtain first measurement data of each of the batteries, transmitting the first measurement data to the server via the communication network, and then performing a second measurement on at least one further battery of the same kind to obtain second measurement data, transmitting the second measurement data to the server via the communication network, and receiving from the server estimated battery state information relating to a battery capacity,
• wherein performing the first measurements includes measuring a battery capacity of a respective battery and measuring an electrical impedance spectrum of the battery,
• wherein performing the second measurement includes measuring an electrical impedance spectrum of a respective battery.

A server for assessing a battery state of electrochemical batteries, wherein the server comprises:

• a machine learning algorithm for processing a measured electrical impedance spectrum, and
• wherein the server is configured for first receiving first measurement data of each of a number of batteries of a same from a battery test bench via a communication network, training the machine learning algorithm based on the first measurement data, and then receiving second measurement data of at least one further battery of the same kind from the battery test bench via the communication network, and using the trained machine learning algorithm for evaluating the second measurement data,
• wherein the first measurement data include a measured battery capacity of the respective battery and a measured electrical impedance spectrum of the battery,
• wherein the second measurement data include the measured electrical impedance spectrum of the battery,
• wherein using the trained machine learning algorithm for evaluating the second measurement data includes inputting the measured electrical impedance spectrum of a respective battery to the machine learning algorithm, processing the measured electrical impedance spectrum by the machine learning algorithm, and generating an output by the machine learning algorithm, wherein the output represents battery state information relating to a battery capacity.

A method for assessing a battery state of electrochemical batteries, the method comprising:

• for each of a number of batteries of a same kind:
• performing a first measurement on the battery to obtain first measurement data of the battery, wherein the first measurement is performed by a measurement device of a battery test bench, wherein the first measurement is performed while the respective electrochemical battery is connected to the measurement device,
• transmitting the first measurement data from the battery test bench to the server via a communication network, and
• training a machine learning algorithm of the server, based on the first measurement data;
• and,
• for at least one further battery of the same kind:
• performing a second measurement on the battery to obtain second measurement data, wherein the second measurement is performed by the measurement device of the battery test bench, wherein the second measurement is performed while the respective electrochemical battery is connected to the measurement device,
• transmitting the second measurement data from the battery test bench to the server via the communication network, and
• the server using the trained machine learning algorithm for evaluating the second measurement data,
• wherein performing the first measurement includes measuring a battery capacity of a respective battery and measuring an electrical impedance spectrum of the battery,
• wherein performing the second measurement includes measuring an electrical impedance spectrum of the respective battery,
• wherein using the trained machine learning algorithm for evaluating the second measurement data includes inputting the measured electrical impedance spectrum of the respective battery to the machine learning algorithm, processing the measured electrical impedance spectrum by the machine learning algorithm, and generating an output by the machine learning algorithm, wherein the output represents battery state information relating to a battery capacity.