Lithium ion battery SOC online predicting method based on data-driven method
A lithium-ion battery, data-driven technology, applied in the direction based on specific mathematical models, measuring electricity, measuring devices, etc., can solve the problem of low accuracy of state of charge prediction, and achieve low storage space and computational complexity, high speed, and accuracy. predicted effect
Inactive Publication Date: 2018-10-30
GUILIN UNIV OF ELECTRONIC TECH
View PDF6 Cites 3 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0004] What the present invention is to solve is the problem that the existing lithium-ion battery adopts the correlation vector machine algorithm to predict the low accuracy of the state-of-charge prediction offline, and provides a lithium-ion battery SOC online prediction method based on a data-driven method
Method used
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0031] In order to make the object, technical solution and advantages of the present invention clearer, the present invention will be further described in detail below in combination with specific examples and with reference to the accompanying drawings.
[0032] In the existing similar methods, as the number of samples gradually increases, its computational efficiency will be greatly reduced, and it requires a large amount of storage space, which puts forward higher requirements for the operating environment of online prediction, especially the operation of spatial applications. The environment restricts the application of online algorithms. The computational complexity of the correlation vector machine algorithm is O(m3), and the storage space is O(m2), where m is the number of basis functions. The training algorithm of RVM is divided into basic training algorithm and bottom-up basis function selection method. The basic training algorithm is the iterative training algorithm...
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More PUM
Login to View More Abstract
The invention discloses a lithium ion battery SOC online predicting method based on a data-driven method. The lithium ion battery SOC online predicting method comprises the steps that an incremental support vector machine method with low calculating amount is introduced into relevance vector machines. Sample data of an IRVM algorithm is composed of relevance vectors and new online samples, and dueto the fact that the relevance vector machines are sparse, namely, the number of the relevance vectors is far smaller than that of an initial sample set, m value of online training is extremely small, accordingly, online predicting is high in speed, high in efficiency, small in storage space and low in calculating complexity, and precision predicting for an lithium ion battery SOC is achieved. The predicting problem of online lithium ion battery SOC can be solved, and the problems are effectively solved that regarding a conventional incremental online training algorithm, an original trainingsample set needs to be kept online, and along with updating of online sample data, the online data set is gradually increased, so that the value of m is gradually increased, and the storage space andthe calculating complexity are improved.
Description
technical field [0001] The invention relates to the technical field of battery performance prediction, in particular to an online SOC prediction method for lithium-ion batteries based on a data-driven method. Background technique [0002] As the main means of transportation in the future, electric vehicles have certain requirements for their start-up, acceleration, climbing performance and cruising range, and these performances largely depend on the performance of the power battery. Battery state of charge (State of Charge, SOC) is a very important parameter in electric vehicles. Only by accurately estimating the SOC of the battery can the utilization efficiency of electric vehicles be effectively improved, driving optimized, and battery life extended. However, due to the complex structure of the battery, the state of charge of the battery is affected by many factors such as discharge current, internal temperature of the battery, self-discharge, battery aging, etc., making S...
Claims
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More Application Information
Patent Timeline
Login to View More IPC IPC(8): G01R31/36G06N7/00
CPCG06N7/01
Inventor 范兴明王超张鑫蔡茂高琳琳
Owner GUILIN UNIV OF ELECTRONIC TECH