SOEKS-based intelligent vehicle knowledge expression and vehicle state abnormity determination method

Abstract

The invention belongs to the technical field of intelligent vehicle safety, and discloses an SOEKS-based intelligent vehicle knowledge expression and vehicle state abnormity determination method. Referred information having completely different properties and dimensions is abstracted to have an SOEKS-based uniform knowledge expression form; SOEKS-based uniform knowledge are accommodated in a hierarchical structured intelligent vehicle knowledge framework; vehicle normal-driving data is collected and then is stored according to SOEKS knowledge expression and framework structure, and storage information comprises original data and a summed simple rule; and, finally, for a complex combination which cannot be described by the simple rule, a vehicle normal-state model is established by utilizing a neural network technology. An abnormity is found through a difference with an acquisition training model in a normal condition, and a single-factor abnormity can be determined rapidly through simple rule experience recorded by the SOEKS structure, so determination efficiency is high; and experiments shows that the detection ratio aiming at whether a vehicle state is normal can reach more than 90%, and determination is at a millisecond grade, so a usage requirement is met.

Description

technical field [0001] The invention belongs to the technical field of intelligent vehicle safety, and in particular relates to a vehicle knowledge representation and state abnormality discrimination method based on SOEKS. Background technique [0002] At present, China is becoming the country with the largest production and purchase of vehicles in the world. The launch of Tesla vehicles has set off an upsurge in the informatization and intelligence of the vehicle industry, and the improvement of the intelligence of vehicles has become a trend. However, with the improvement of vehicle intelligence, some potential safety hazards have begun to be discovered by hackers. Users face the threat of cyber attacks while driving, which may cause vehicle loss of control, denial of service, etc., which seriously affect the safety of users' lives and property. Overall, the industry's exploration of vehicle information security systems is still in its infancy, and regulations, industry s...

AI Technical Summary

Problems solved by technology

[0006] Today's on-board systems of vehicles are vulnerable to remote network attacks, causing serious impacts such as loss of vehicle control and denial of service. The current on-board systems have no way to detect these attacks at all, and there is no way to defend against such attacks

However, most of the existing research is based on the external conditions of the vehicle, such as obstacles, etc., and seldom pays attention to the information of each ECU (Electronic Control Unit, electronic control unit) and CAN bus inside the vehicle system.

Images