Mode clustering method of battery alarm characteristic data and accident characteristic identification technology
A feature data, clustering method technology, applied in character and pattern recognition, instruments, computer parts and other directions, can solve the problem of difficult to accurately distinguish the accident car and so on
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0047] A pattern clustering method for battery alarm feature data and an embodiment of accident feature recognition technology in the present invention are basically as attached figure 1 shown, including steps:
[0048] S1. Collect the operation data of the battery before and after the alarm during the operation of the accident vehicle and the normal vehicle;
[0049] S2. Perform dimensionality reduction processing on the operating data to obtain pattern characteristics;
[0050] S3. Carrying out cluster analysis on the pattern features after dimensionality reduction to obtain the classification features of the operating data;
[0051] S4, analyze the statistical difference between the accident car and the normal car according to the classification feature;
[0052] S5. Determine whether the vehicle is an accident vehicle by taking the statistical difference as a standard.
[0053] In this embodiment, taking a new energy vehicle as an example, some important operating param...
Embodiment 2
[0066] The only difference from Example 1 is that
[0067] The probability density distribution curve is used to analyze statistical differences, and it is judged whether the degree of deviation of the probability density distribution curve satisfies the preset condition. If the preset condition is met, the vehicle is judged to be an accident vehicle. The preset condition may be a deviation percentage, such as 2%. The probability density function is a function that describes the possibility of the output value of a random variable near a certain value point, and the probability that the value of the random variable falls within a certain area is the integral of the probability density function on this area . It can be seen that analyzing the statistical difference through the probability density distribution curve is more intuitive on the graph. Usually, the probability density distribution curve of a normal car satisfies the normal distribution. If a certain car deviates gr...
Embodiment 3
[0069] The only difference from Embodiment 2 is that the surface temperature of the battery cell is also used to assist in judging whether the battery cell is abnormal. The data of each battery cell uploaded by the new energy vehicle to the enterprise platform includes temperature data. These temperature data are collected by a temperature sensor. The probe or probe of the temperature sensor is in contact with the battery cell to measure the temperature of the battery cell in real time. surface temperature data.
[0070] In this embodiment, each battery cell has a preset number, and these numbers correspond to the location information of the battery cell, and the location information is specifically the horizontal distance and the vertical distance; where the horizontal distance refers to the distance between the battery cell and the The straight-line distance of the cabin, that is, the distance between the geometric center of the cockpit and the geometric center of the batter...
PUM
Abstract
Description
Claims
Application Information
- R&D Engineer
- R&D Manager
- IP Professional
- Industry Leading Data Capabilities
- Powerful AI technology
- Patent DNA Extraction
Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.
© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com