Unlock instant, AI-driven research and patent intelligence for your innovation.

Feature extraction method for vehicle low speed collision signals based on time domain range

A low-speed collision and time-domain technology, applied in the field of data processing, can solve problems such as the inability to directly find useful signal information and the impact of machine learning, and achieve the effect of providing accuracy and improving the accuracy of damage determination

Inactive Publication Date: 2016-11-02
DALIAN ROILAND SCI & TECH CO LTD
View PDF5 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0002] The vehicle driving signal collected in the remote loss assessment technology project is a discrete signal, which contains a variety of noise signals of different frequencies. If the signal is directly analyzed, not only the useful information of the signal cannot be directly found, but also the following machine learning will be generated. great influence

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 more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Feature extraction method for vehicle low speed collision signals based on time domain range

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0017] Embodiment 1: A method for feature extraction of vehicle low-speed collision signals based on the time domain range, including: S1. Extracting the speed signal from the collision signal from the occurrence to the end of the vehicle collision, and performing fixed frequency filtering; S2. For filtering From the final signal data, the maximum and minimum values ​​of the acceleration signal data are extracted, and the one with the larger absolute value is the maximum value. The maximum value (maximum value and minimum value) can reflect the speed of the vehicle at the time of the collision. When the collision object is a rigid body, the greater the driving speed, the greater the maximum value; and the absolute value of the maximum value and the minimum value Compared with the absolute value of the value, it can also reflect whether the vehicle is in a frontal collision or a rearward collision. S3. Extract time-domain features from the data obtained by extracting the speed ...

Embodiment 2

[0018] Embodiment 2: It has the same technical solution as Embodiment 1, more specifically: in the step S2, the extracted data also includes the average energy from the extreme point to the subsequent extreme point of the filtered signal data. The average energy from the maximum point to the subsequent extreme point can reflect the speed of energy loss of the vehicle during the collision process. Different collision objects will cause different energy losses of the vehicle during the collision process.

Embodiment 3

[0019] Embodiment 3: It has the same technical solution as Embodiment 1 or 2, more specifically: the data extracted in step S2 also includes the half-wave width of the maximum value and the half-wave width of the minimum value.

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

No PUM Login to View More

Abstract

The invention provides a feature extraction method for vehicle low speed collision signals based on time domain range, belongs to the field of data processing, and aims at enabling data influencing the collision data accuracy in the vehicle low speed collision signals to be extracted. The technical key points are that S1. the speed signals of the collision signals during the period from occurrence of collision to the end are extracted and fixed frequency filtering is performed; and S2 the extremum values of the speed signal data of the signal data after filtering are extracted. The effects are that the useful signal data are extracted so that the accuracy of the basic collision data can be enhanced in the damage assessment process and the damage assessment precision can be enhanced.

Description

technical field [0001] The invention belongs to the field of data processing and relates to a feature extraction method of low-speed collision signals. Background technique [0002] The vehicle driving signal collected in the remote loss assessment technology project is a discrete signal, which contains a variety of noise signals of different frequencies. If the signal is directly analyzed, not only the useful information of the signal cannot be directly found, but also the following machine learning will be generated. big impact. Which of the signal data to choose is related to the accuracy of collision data acquisition. Extracting useful and intuitive features from complex signals plays a vital role in learning models. Contents of the invention [0003] In order to solve the above technical problems, the present invention proposes a time-domain-based feature extraction method of vehicle low-speed collision signals, so that data affecting the accuracy of collision data ...

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
no application Login to View More
IPC IPC(8): G06K9/00
CPCG06F2218/08
Inventor 田雨农邹秋霞
Owner DALIAN ROILAND SCI & TECH CO LTD
Features
  • R&D
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2025 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com