Vehicle driving condition prediction method based on Markov chain and neural network
A technology of Markov chain and neural network, which is applied in forecasting, instrumentation, data processing applications, etc., and can solve the problems that the accurate forecasting effect needs to be further improved.
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0047] see Figure 1 to Figure 7 , a method for predicting vehicle driving conditions based on Markov chains and neural networks, which mainly includes the following steps:
[0048] 1) Obtain the characteristic parameters representing the driving conditions of the vehicle and n historical adjacent vehicle speeds V t-1 , V t-2 ,...V t-n . Divide the feature parameters into two groups, the first group of data is recorded as X (n) , the second set of data is denoted as S (n) . Put n history close to vehicle speed V t-31 , V t-32 ,...V t-3n Recorded as the third set of data.
[0049] Further, the characteristic parameters mainly include the average vehicle speed v m , Driving average speed v md , speed variance v var , acceleration variance a var , Inertia energy variance va var , acceleration time ratio P acc , Deceleration time ratio P dec , specific speed time ratio P con , Idle time ratio P idl , the maximum acceleration a max , minimum acceleration a min ,...
Embodiment 2
[0129] An experiment of a method for predicting vehicle driving conditions based on Markov chains and neural networks mainly includes the following steps:
[0130] 1) Obtain the characteristic parameters representing the driving conditions of the vehicle and n historical adjacent vehicle speeds V t-11 , V t-12 ,...V t-1n . Divide the feature parameters into two groups, the first group of data is recorded as X (n) , the second set of data is denoted as S (n) . Put n history close to vehicle speed V t-11 , V t-12 ,...V t-1n Recorded as the third set of data.
[0131] The prediction of driving conditions in the short-term time domain is a nonlinear and non-static random process, so the model training data should be randomly selected, and the data should include high-speed working conditions, suburban working conditions, urban working conditions and other working conditions. In this section, a variety of standard cycle working conditions will be selected from ADVISOR and ...
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