Flow battery stack optimal operation condition prediction method based on machine learning

Abstract

The invention belongs to the field of large-scale electrochemical energy storage, and particularly relates to a flow battery stack optimal operation condition prediction method based on machine learning. The method comprises the following steps: establishing a database; carrying out numeralization and standardization processing on the type variable parameters in the database; forming a multi-dimensional feature vector <X> by using the parameter variables, respectively taking the power cost and the energy cost of the electric pile as target functions y, and randomly cclassifying the multi-dimensional feature vector < X > and the target functions y into a training set and a test set; training a galvanic pile performance prediction model by using the parameter data in the training set; evaluating the trained flow battery galvanic pile performance prediction model by using parameter data in the test set, and constructing a cost prediction model; and predicting the materials and the cost variable parameters in the database by using the cost prediction model, and calculating the total system operation cost. According to the method, the optimal operation cost performance interval and the optimal operation parameters of each researched and developed flow battery stack can be determined through a small number of tests.

Description

technical field [0001] The invention belongs to the field of large-scale electrochemical energy storage, and specifically relates to a method for predicting optimal operating conditions of a liquid flow battery stack based on machine learning. Background technique [0002] Large-scale energy storage technology can solve the discontinuous, unstable, and uncontrollable problems in the renewable energy generation process. It is considered as a strategic technology to support the popularization of renewable energy, and is expected to play an important role in the development of power systems and energy transformation. Among many energy storage technologies, the electrochemical energy storage technology represented by the all-vanadium redox flow battery energy storage system has the advantages of environmental friendliness, high safety, independent design of power and capacity, etc. Broad prospects. However, there are no specific standards for the design of flow battery stacks. ...

AI Technical Summary

Problems solved by technology

However, there are no specific standards for the design of flow battery stacks. The development of flow battery stacks and the calculation of system operating costs are mainly based on a large number of tentative experiments. Operating under operating conditions, the operating costs of the system are also different. The relationship between the material and structure of the flow battery stack, operating parameters and system operating costs is very complex and complementary

Moreover, the research and development cost of the flow battery stack is high and the cycle is long. It takes a lot of manpower, material resources and time to determine the optimal operating conditions of the stack only through experiments.

Images