The content of the invention
The invention discloses a kind of highway danger road conditions identification and alarm suitable for vehicle-mounted short distance communication network
Method, it is main to realize it being that the recognition element of thing, fault car and crowded three factors of road as Dangerous Area is shed in selection.Know
Other method is to establish the bayesian network structure and algorithm of the dangerous identification in section first, then establishes judgement and sheds thing, failure
The bayesian network structure and algorithm of vehicle and crowded three recognition elements of road, recognition methods is by vehicle-mounted short haul connection
The heartbeat message comprising vehicle location that the trackside node of network receives vehicle-mounted node periodic broadcasting in coverage is each to obtain
The position of vehicle, so obtain vehicle speed and travel direction change, then obtained by Bayesian network shed thing,
The posterior probability of fault car and crowded three recognition elements of road, then again by Bayesian network, obtains section dangerous
Posterior probability, when probability higher than default threshold value when, to the vehicle broadcast alarms message in coverage.
Specifically, the invention discloses a kind of highway danger road conditions identification suitable for vehicle-mounted short distance communication network
And alarm method, methods described includes:
The recognition element of thing, fault car and crowded three factors of road as Dangerous Area is shed in selection, by vehicle-mounted
The trackside node of short distance communication network receives the letter of the heartbeat comprising vehicle location of vehicle-mounted node periodic broadcasting in coverage
Cease to obtain the position of each vehicle, and then obtain the change of the speed and travel direction of vehicle, then by Bayesian network come
The posterior probability of thing, fault car and crowded three recognition elements of road is shed in acquisition, then again by Bayesian network, is obtained
The dangerous posterior probability in section, when there is dangerous phenomenon, is alerted to the vehicle in coverage.
Preferably, after trackside node calculates the dangerous probability in section more than the threshold value of default, by vehicle-mounted short
Range communication network, to the vehicle broadcast alarms information in coverage.
Preferably, it is identified using Bayesian network, method is to establish the Bayesian network knot of the dangerous identification in section
Structure and algorithm, then establish judge shed thing, the bayesian network structure of fault car and crowded three recognition elements of road and
Algorithm.
Preferably, trackside node is that the vehicle region obtained by V2X networks is detoured and vehicle to shedding thing recognition element
Two information of jogging calculate the probability of generation.
Preferably, trackside node is that the vehicle obtained by V2X networks is stopped and vehicle is slow to fault car recognition element
Two information of row calculate the probability of generation.
Preferably, trackside node is that the vehicle obtained by V2X networks is stopped and vehicle is slow to the crowded recognition element of road
Two information of row calculate the probability of generation.
The vehicle-mounted node broadcasts that trackside node of the embodiment of the present invention using V2X network designs along highway is received
Heartbeat message, obtain trackside coverage in the range of vehicle position, and then obtain vehicle speed and vehicle line change,
By the change in location of vehicle, coordinate electronic map, the danger to highway is identified, when danger exceedes threshold value
When, to vehicle broadcast alarms information, so as to improve the travel safety of highway.
Specific embodiment
The present embodiment realizes a kind of highway danger road conditions identification suitable for vehicle-mounted short distance communication network and accuses
Alarm method, it is therefore an objective to which the trackside coverage scope by vehicle-mounted short haul connection is big, there is the advantage of link connection each other,
Receive the message comprising geographical position coordinates that the V2X mobile units periodic broadcasting in the range of trackside coverage in vehicle sends
(hereinafter referred to as heartbeat message), using Bayesian network model, the road conditions comprehensively satisfied the need in side gusset coverage carry out danger
Situation differentiates, if road conditions danger probability exceedes the threshold value of default, by warning information by this trackside node and neighbour
Near trackside node is broadcasted, and reminds driver to take appropriate measures early, so that the effectively traffic of Improving Expressway
Level of security.
Highway is very fast due to speed, and several factors make certain section turn into Dangerous Area, and three kinds of the present embodiment selection is right
Highway influences big factor, is respectively to shed thing or temporary obstructions, fault car or traffic accident vehicle, road are gathered around
Squeeze, synthetic determination is carried out by Bayesian network.
Highway sheds thing due to its Unpredictability, and great danger can be brought to the vehicle run at high speed.In addition
Provisional barrier or paroxysmal road abnormal conditions, fall within this kind of hazards.Vehicle runs into this kind of situation, one
As be regular detouring.Trackside node by receiving the heartbeat message that V2X mobile units are broadcasted in the vehicle in coverage,
This regular detouring can be identified, so that judging that road has sheds thing or the abnormal probability of road.
Fault car or traffic accident vehicle are that another can bring great hazards to the vehicle run at high speed,
The heartbeat message that this factor trackside node can be broadcasted by receiving fault car accurately obtains the positional information of vehicle, but
Need according to the position of fault car and the situation of occupancy road come the hazard recognition order of severity.
Road congested conditions trackside node can be carried out by the speed and vehicle density that receive by the vehicle in the section
Identification.
The degree of danger in section is related to several factors, and each factor has larger uncertainty, Bayesian network mould again
Type can be used for expressing and analyzing uncertain and probabilistic event, can be from incomplete, inaccurate or uncertain knowledge
Or reasoning is made in information, it is effective theoretical model in uncertain knowledge and reasoning field.The danger in section in highway
Property is an extremely complex system problem.Therefore, there is preferable feasibility using the method for probability theory.
In Bayesian network model, unavailable stochastic variable is inferred by obtainable stochastic variable, carried out general
Rate reasoning.Therefore, solving the dangerous differentiation in section using Bayesian network can be expressed as:Brought in existing road danger
Vehicle-state change empirical data in the case of, trackside node obtain real-time vehicle state under conditions of, road hazard shape
Condition is in the probability of various degree (dangerous, safety).
Bayesian network is with two tuple BN=<G,Θ>The probability uncertain inference network of statement, G be node with it is discrete
Stochastic variable { X1,X2,...,XnOne-to-one directed acyclic graph, directed edge determines between then representing variable by conditional probability
Dependence;Θ is the set for describing BN local conditions probability distribution parametersRepresent nodes XiIn his father
Set of node YiA certain valued combinations state yiUnder conditional probability distribution.BN can be by between conditional probability quantization chance event
Causality, thus be accordingly used in the identification of fatigue driving.
The implementation of the present embodiment includes three parts, and flow is as shown in Figure 1.
Part I, the bayesian network structure and algorithm of establishing the dangerous identification in section.
1.1st, Bayesian network is constructed with directed acyclic graph, the element that node therein is used for section dangerous discernment is corresponding
Variable, directed edge represents the condition dependence of variable.
1.2nd, the Bayesian Network Topology Structures of the present embodiment are as shown in Figure 2.Road hazard identification in the present embodiment
Using acceleration and deceleration characteristic, deviation characteristic, three characteristics of direction of traffic characteristic, hereinafter referred to as three characteristics of fatigue identification.Father saves
Point (Rd) represents that section is dangerous, and child node (Ao) represents thing factor of shedding, and child node (Fv) represents fault car factor, sub- section
Point (Rc) represents the crowded factor of road.Line between father node (Rd) and child node (Ao), child node (Fv), child node (Rc)
Represent section it is dangerous with shed the conditional probability p (Ao | Rd) of thing factor, fault car factor and the crowded factor of road, p (Fv |
) and p (Rc | Rd) Rd.
1.3rd, the dangerous Bayes net algorithm for differentiating in section.The dangerous size in section using Probability p (Rd | Ao,
Fv, Rc) represent, according to Bayesian formula,
In the present embodiment, the bar of line between father node and child node in Bayesian network is determined according to expertise first
After part probability, then obtain 3 prior probabilities of node, it is possible to obtain the dangerous posterior probability p in section (Rd | Ac, Fv,
Rc)。
Be simplified operation, each state value be with and without, respectively correspond to 0 and 1, then:
Part II, the bayesian network structure and algorithm of establishing each recognition element of judgement.
2.1st, bayesian network structure and algorithm that thing (Ao) is shed in identification are established.In this fact Example, the identification of thing is shed
Be detoured (Aa) by vehicle region and vehicle jogging (Va) two vehicle running characteristics be identified.Shed the probability of thing presence
Represented with p (Ao | Aa, Va), according to Bayesian formula,
Wherein, p (Aa, Va)=p (Aa | Va) p (Va), p (Aa, Va | Ao)=p (Aa | Va, Ao) p (Va | Ao), above-mentioned general
Obtained in the historical data that rate can be collected from trackside node.
2.2nd, the bayesian network structure and algorithm of identification fault car (Fv) are established.In this fact Example, the knowledge of disabled vehicle
It is not to be identified by vehicle stopping (Vs) and vehicle jogging (Va) two vehicle running characteristics.The probability that fault car is present
P (Fv | Vs, Va) represent, according to Bayesian formula,
Wherein, p (Vs, Va)=p (Vs | Va) p (Va), p (Vs, Va | Fv)=p (Vs | Va, Fv) p (Va | Fv), above-mentioned general
Obtained in the historical data that rate can be collected from trackside node.
2.3rd, the bayesian network structure and algorithm of identification road crowded (Rc) are established.In this fact Example, road is crowded
It is identified by vehicle stopping (Vs) and vehicle jogging (Va) two vehicle running characteristics is identified.It is general that fault car is present
Rate p (Rc | Vs, Va) represent, according to Bayesian formula,
Wherein, p (Vs, Va)=p (Vs | Va) p (Va), p (Vs, Va | Rc)=p (Vs | Va, Rc) p (Va | Rc), above-mentioned general
Obtained in the historical data that rate can be collected from trackside node.
Part III, express highway section degree of danger are sailed knowledge and are alerted.
3.1st, highway trackside node on the way is deployed in by receiving vehicle on-board V2X device broadcasts in coverage
The message comprising vehicle geographical location information for sending;
3.2nd, trackside node is according to the positional information of the vehicle for receiving, and the form change in location for obtaining, so that can
Judged with the probability for detouring, walking or drive slowly and stopping to vehicle.Judge to be carried out by the way of setting time section inside counting:
Wherein, CAaIt is that the vehicle fleet size deflected to same direction, C occur in one placeVsIt is occur to stop phenomenon
Vehicle fleet size, CVaIt is that the slow vehicle fleet size of speed occurs, C is total vehicle fleet size of identification section.
3.3rd, when V2X tracksides node device is initialized, can be according to the electronic map in this section, by the experience number for setting
According to then by formula (1) to formula (6), the danger classes in this section can be obtained;
3.4th, after the risk probability in section exceedes threshold value, by warning information by V2X networks to the car in coverage
Broadcasted, after vehicle-mounted V2X equipment receives warning information, can be using sound and display at that time to the danger of Dangerous Area
Factor and generation position are reminded;
3.5th, by posterior probability p (Rd | Ao, Fv, Rc) now as the prior probability p (Rd) of next calculating cycle,
Prediction is set more to meet current character of road.
The above is presently preferred embodiments of the present invention and its know-why used, for those skilled in the art
For, without departing from the spirit and scope of the present invention, it is any based on technical solution of the present invention on the basis of equivalent change
Change, simply replacement etc. obviously changes, belong within the scope of the present invention.