Lithium cobaltate batching system based production state prediction method

Abstract

The invention discloses a lithium cobaltate batching system based production state prediction method. The method includes building a health status evaluation index of a lithium cobaltate batching system; and performing prediction on the health index of the batching system by using a double weighted based kernel principal component regression least squares support vector machine algorithm, whereinthe prediction step includes the following steps: firstly, extracting non-linear characteristics of an input variable, and extracting a main constituent from large to small according to contribution rates; then, processing a data set, and determining the correlation between an input vector and an output vector; and finally, performing modeling prediction, performing local weighing on a training sample and an input sample, and optimizing model parameters. The method adopts the defined health index, primary and secondary weighting matrixes can be built during a modeling process through the correlation between the input sample and an output sample and the distance between the input sample and a query sample; and the primary weighting can be performed before the sample is input to the model, the secondary weighting can be adopted to a model estimation error during the modeling process, and therefore, the influence brought by production data errors or omission on prediction algorithms can be reduced.

Description

technical field [0001] The invention belongs to a control system for the production of a lithium cobalt oxide batching system, in particular to a production state prediction method based on a lithium cobalt oxide batching system. Background technique [0002] Lithium-ion batteries have the advantages of high specific energy and good cycle performance. They have been widely used in many fields such as smart phones and electric vehicles, and have become one of the most widely used and most promising batteries today. As a new type of energy material, lithium-ion battery cathode material accounts for 30% to 40% of the total cost of lithium-ion batteries, and directly determines the working voltage, life, capacity, safety and cost of batteries. important material. Nowadays, the market share of my country's cathode materials has accounted for 46% of the global share, but more than half of the supply is cathode materials of medium and lower quality, the share of high-end products ...

AI Technical Summary

Problems solved by technology

[0004] The problem solved by the present invention is to propose an evaluation system based on the health index for the occasional failure of the batching system, which is difficult to check in advance and timely repair.

Images