CN102722989A - Expressway microclimate traffic early warning method based on fuzzy neural network - Google Patents

Abstract

The invention discloses an expressway microclimate traffic early warning method based on a fuzzy neural network. The expressway microclimate traffic early warning method comprises the following steps of distributing traffic flow and microclimate monitoring points; defining a traffic controller of the fuzzy neural network; training the traffic controller of the fuzzy neural network; using the optimal traffic controller of the fuzzy neural network to generate traffic safety travelling parameters; and issuing traffic control information. The expressway microclimate traffic early warning method uses the fuzzy neural network and issues vehicle operating limiting-velocity value, distance limiting value and overtaking limitation and lane changing limitation measures through comprehensive detection of meteorological parameters such as precipitation, snow quantity, temperature and visibility along the line of an expressway. The method is used in the expressway to improve travelling safety under severe weather conditions.

Description

Highway microclimate traffic prewarning method based on fuzzy neural network

Technical field

The present invention relates to a kind of traffic safety technology, especially a kind of highway microclimate traffic prewarning method based on fuzzy neural network.

Background technology

At present, along with the increase of highway mileage open to traffic, diastrous weather highlights the influence of expressway traffic safety day by day.Under inclement weather conditions; The driver more is difficult in time obtaining information warning; Thereby cause the major accident of hundreds of rear-end collision to happen occasionally, therefore, highway can only be closed under boisterous situation; The quick early warning and the intelligent management of highway more and more receive people's attention and attention.

Find through the retrieval paper: Cheng Conglan, Li Xun, Zheng Zuofang; Wang Zaiwen, Liang Xudong. road meteorological warning index in Beijing makes up and Preliminary Applications the 27th Meteorology Society of China's year meeting paper collection; 2010,10. Feng Min learns, the meteorological intelligent early warning system research that detects of freeway traffic; Nanjing Information engineering Univ's PhD dissertation, 2005. long monarchs, Zou Kaiqi. the research of highway NN control system under the bad weather condition; Computer engineering and application, 2007,43 (4): 210-212. king flies less; The pass can. the expressway weather information service system. and the Chinese transportation information industry, 2007 (1): the above-mentioned research of 116-119. provides meteorological early warning information analyzing on the basis of DIFFERENT METEOROLOGICAL CONDITIONS to traffic capacity influence to DIFFERENT METEOROLOGICAL CONDITIONS.But, do not provide traffic prewarning information directly from the angle of freeway management.Tang Junjun, high sea otter, Zhang Weihan. the research of Supervising System Structure for Expressways in Fog Area; Highway; 2005,8. Wang Wei is inferior. based on abominable weather monitoring of the highway of radio sensing network and traffic control model investigation, Chang An University; 2008. these people of willow; Highway security of operation control technology research under the diastrous weather, Tongji University's doctorate paper, 2008. above-mentioned researchs are being analyzed under visibility and the coefficient of road adhesion prerequisite to the express way driving safety influence; Through fuzzy control theory or meteorological department, freeway management department and a line driver practical experience and a test, speed limit and safe spacing under mist, snow, the rainy day gas are stipulated.There is three point problem: the one,, on the basis of comprehensive weather monitoring, vehicle driving safety not being carried out early warning, Consideration is comprehensive inadequately; The 2nd,, the fuzzy reasoning degree of membership is directly provided by experience, and subjectivity is strong.The 3rd,, do not consider the influence of road traffic flow situation.

One Chinese patent application 200910061448.3 discloses a kind of expressway weather monitoring system.And application number: 200910060562.4 disclose a kind of highway rear-end collision prevention early warning system.One Chinese patent application 200710077671.8 discloses a kind of weather information prompt system for speedway.Foregoing invention all designs to highway early warning system hardware facility, does not relate on the data acquisition basis, as obtains the method for safe driving parameter and traffic prewarning.

Summary of the invention

The objective of the invention is for overcoming the deficiency of above-mentioned prior art; A kind of highway microclimate traffic prewarning method based on fuzzy neural network is provided; This method is through the comprehensive detection of meteorologic parameters such as highway rainfall amount along the line, snowfall, temperature, visibility; Utilize the method for fuzzy neural network, issue vehicle operating speed limit, spacing limits value, the measures such as the restriction and the restriction of changing trains of overtaking other vehicles.On highway, use this method, can under severe weather conditions, improve travel safety.

For realizing above-mentioned purpose, the present invention adopts following technical proposals:

A kind of highway microclimate traffic prewarning method based on fuzzy neural network may further comprise the steps: the laying of traffic flow and microclimate check point; Ambiguity in definition neural network traffic controller; The training of fuzzy neural network traffic controller; Utilize optimum fuzzy neural network traffic controller to generate traffic safety driving parameter; The traffic control information issue, the concrete operations step is following:

Step 1: whenever keeping at a certain distance away at the highway trackside is provided with some traffic flows and microclimate monitoring point; Detect this road traffic delay situation and microclimate supplemental characteristic; Pass through sensor Data Fusion; Obtain road traffic delay and weather information, traffic flow and microclimate data acquisition are prepared for next step Fuzzy Neural-network Control;

Step 2: (Gao Mu-Guan Ye) fuzzy neural network of reasoning makes up highway microclimate traffic controller based on Takagi-Sugeno in employing; Telecommunication flow information and weather information that definition step 1 collects are state variable; Input value as said controller; Definition Highway Control mode, speed limit and safe spacing value are control variable, as the output valve of said controller;

Step 3: the meteorology, traffic flow, control measure and the implementation result historical data base thereof that adopt meteorological department and vehicle supervision department; Make up the training sample of fuzzy neural network traffic controller in conjunction with expertise; Highway microclimate traffic controller is trained; Training error is reduced to predetermined threshold or reaches frequency of training, to obtain optimal controller;

Step 4: the telecommunication flow information that will gather in real time and the optimum fuzzy neural network traffic controller of microclimate information input; Generate Freeway Traffic Control scheme, comprise early warning measure, speed limit and safe spacing value to this moment traffic flow situation and weather information;

Step 5: lay the variable information plate in each traffic and the upper reaches, microclimate monitoring point, the safe driving early warning information of traffic controller output is issued.

Fuzzy neural network structure highway microclimate traffic controller is divided into five-layer structure in the said step 2:

Ground floor is an input layer, and input value is the supplemental characteristic that freeway traffic flow and microclimate check point are gathered, and is expressed as x={x ₁, x ₂, x ₃..., x _n, wherein, n representes the number of input parameter, n is the integer more than or equal to 1, and x ₁, x ₂... x _nRepresent respectively traffic flow parameter be speed, flow, occupation rate and microclimate parameter can degree of opinion, temperature, humidity, air pressure, wind direction, wind speed, ST;

Input parameter is divided into 5 grades according to from small to large order, is respectively { NB is negative big, and NS is negative little, and Z zero, and PS is just little, and PB is honest }, its meaning for the relevant parameters desired value be little, less, medium, greatly, bigger; The system of said controller is output as control model, speed limit and safe distance; Wherein, control model is divided into three kinds, and sealing completely, zone sealing and ring road control are promptly controlled according to traffic and meteorological condition and sailed the highway flow into; Speed limit and safe distance grade classification mode are identical with input parameter;

The second layer is the obfuscation layer, be used for representing input quantity belong to respectively NB, NS, Z, PS, the degree of membership of PB} does

In the formula, j is 1 to m _iInteger, m _iBe x _iThe fuzzy number of cutting apart, m here _i=5; c _IjAnd σ _IjCenter and the width of representing membership function respectively;

The 3rd layer is regular former piece layer, and each node is represented a fuzzy rule, and its effect is the former piece that is used for mating fuzzy rule, calculates the relevance grade a of every rule _j, formula is:

Or

$a_j={\mathrm{\μ}}_1^j\left(x_1\right){\mathrm{\μ}}_2^j\left(x_2\right)...{\mathrm{\μ}}_n^j\left(x_n\right);$

In the formula: a _jThe relevance grade of-fuzzy rule j;

-input x _iThe degree of membership that is under the jurisdiction of j grade, j is the integer between 1 to m, m is the integer more than or equal to 1;

Realize normalization calculating for the 4th layer, formula is:

wherein; J is the integer between 1 to m, and m is the integer more than or equal to 1;

The layer 5 output layer, formula does

$y=\underset{r=1}{\overset{m}{\mathrm{\Σ}}}{w}_r\stackrel{\‾}{a_r},r=\mathrm{1,2},...,m$

Wherein, w _rBe connection weight, r is the integer between 1 to m, and m is the integer more than or equal to 1.

Based on the training of the microclimate traffic controller of fuzzy neural network, particular content is following in the said step 3:

(1) selection of training

Training sample is considered to be made up of three parts: first, the historical data of meteorological part, freeway traffic regulation department, comprise historical meteorologic parameter information, traffic flow parameter information, the early warning information of taking at that time and issue after effect; Second portion, traffic engineering domain expert's questionnaire is through being provided with different meteorologies and traffic flow sight, the early warning measure that the inquiry expert possibly adopt; Third part after this system builds up, is added into historical data base with the traffic prewarning scheme implementation effect under different meteorologies, the traffic flow situation;

(2) training algorithm

The parameter that network need be learnt is the central value c of second layer membership function in the step 2 _IjAnd width cs _IjAnd layer 5 network connection weight w _r, the learning algorithm of this network is selected backpropagation BP algorithm; The BP algorithm is made up of forward-propagating and two processes of error back propagation; In the forward-propagating process, input information is successively handled through latent layer unit from input layer, after all latent layers, passes to output layer; In the process that hidden layer is successively handled, the neuronic state of each layer only exerts an influence to the following neuronic state of one deck; At output layer reality output and desired output are compared; If the difference of actual output and desired output no longer within the tolerance interval, then changes back-propagation process over to, the error between actual value and the desired output is returned along original connecting path; Through revising the neuronic connection weight of each layer error is reduced; And then changing the forward-propagating process over to, repeated calculation like this is till error is less than setting value;

The learning algorithm of said network is selected backpropagation BP algorithm, and step is following:

1. establish x _kBe input vector, x _k=(x ₁, x ₂..., x _n), k is the integer between 1 to K, in the formula: K is a number of samples, and n represents the number of characteristic parameter; The output vector of corresponding travel pattern is y _k, initialization network weight, threshold value;

2. each unit of the second layer is input as

$S_{\mathrm{ij}}^{\left(2\right)}=x_i,$

In the formula, x _iExpression system input, i.e. traffic flow parameter and meteorologic parameter value, i is the integer between 1 to n, n represents the number of characteristic parameter; J is 1 to m _iBetween integer, m _iRepresent the fuzzy number of cutting apart of i characteristic parameter;

Transport function between the ground floor and the second layer is membership function:

${\mathrm{\μ}}_i^j\left(x_i\right)=\exp [{(x_i-c_{\mathrm{ij}})}^2/{\mathrm{\σ}}_{\mathrm{ij}}^2]$

Then second layer unit is output as:

$y^{\left(2\right)}=\left\{{\mathrm{\μ}}_i^j\left(x_i\right)\right\}$

3. the input of the 3rd layer of each unit is the output of corresponding each unit of the second layer, for

$S_r^{\left(3\right)}=\left\{{\mathrm{\μ}}_i^r\left(x_i\right)\right\}$

Output layer is output as

$y_r^{\left(3\right)}=\min \left\{{\mathrm{\μ}}_i^l\left(x_i\right)\right\}$

In the formula, l is the integer between 1 to m, and m representes number of fuzzy rules;

4. the input of the 4th layer of each unit is the output of the 3rd layer of corresponding each unit, for

$S_r^{\left(4\right)}=\left\{y_r^{\left(3\right)}\right\}$

Output layer is output as

$y_r^{\left(4\right)}=\frac{y_r^{\left(3\right)}}{\underset{r=1}{\overset{m}{\mathrm{\Σ}}}{y}_r^{\left(3\right)}}$

5. the input of each unit of layer 5 is the output of the 4th layer of corresponding each unit, for

$S_r^{\left(5\right)}=\left\{y_r^{\left(4\right)}\right\}$

Output layer is output as

$y=w_r{y}_r^{\left(4\right)}$

So far accomplish a forward pass process;

6. in the error back propagation process, at first to carry out Error Calculation,

For fuzzy neural network, suppose t the error function E that sample is right _tBe defined as:

$E_t=\frac{1}{2}{(y_0\left(t\right)-y\left(t\right))}^2$

In the formula: y ₀(t) be system's desired output, y (t) is system's real output value, and t is the integer more than or equal to 1, the label of expression sample.

Backpropagation BP thought is used to supervised learning, through each weighted value of adjustment network, makes the error function value minimum, thereby reaches the purpose of revising membership function parameter and network connection power;

7. the next sample of picked at random is to offering network; The double counting process; Until network global error function less than predefined minimal value, i.e. a network convergence; Or learn number of times less than predefined value, promptly network can't be restrained; Wherein, K is the learning sample number;

8. finish study.

(Gao Mu-Guan Ye) fuzzy neural network of reasoning is a known technology to Takagi-Sugeno among the present invention, repeats no more at this.

The invention has the beneficial effects as follows that highway microclimate traffic control method is the situation according to real-time meteorology of highway and traffic flow, self-adaptation adjustment traffic control scheme has improved the travel safety and the traffic efficiency of highway under the inclement weather.Compare with the traffic prewarning method under other inclement weathers and to have following difference:

1, control law does not need to provide in advance, has adopted historical data and expertise to the model training, has improved the accuracy of controlling schemes and has abandoned the subjectivity that traffic administration person carries out traffic administration;

2, carry out the generation of traffic control scheme to the information of gathering in real time, and swim above that and utilize the firm and hard information of executing of variable information to issue, improved the efficient of inclement weather traffic prewarning.

Description of drawings

Fig. 1 microclimate detects the traffic prewarning system schematic;

Fig. 2 is traffic flow and microclimate check point arrangement synoptic diagram;

Embodiment

Below in conjunction with accompanying drawing and instance the present invention is further specified.

Structural drawing based on the microclimate traffic prewarning system of fuzzy neural network is as shown in Figure 1.This system is made up of three sub-systems: subsystem is unified, traffic and microclimate data acquisition system (DAS); Subsystem two, fuzzy neural network controller; Subsystem three, the traffic prewarning information issuing system.The relation of this three sub-systems is following: unified traffic of gathering of subsystem and microclimate information are as input value; Be input to subsystem two fuzzy neural network controller; Calculating output traffic prewarning scheme through this controller; Traffic prewarning scheme input subsystem three is published to the variable information plate as early warning information.

Step 1: traffic flow and microclimate check point are laid

Traffic flow and microclimate check point arrangement are as shown in Figure 2.Module 1 expression traffic flow and microclimate monitoring modular among Fig. 1, it is laid in trackside according to certain intervals.Earth coil is laid in the traffic flow monitoring point, to detect data such as this section traffic flow speed of a motor vehicle, flow and occupation rate; The microclimate check point is laid sensors such as visibility detecting device, Temperature Detector, ST detecting device, moisture detector, rainfall detecting device, freezing detecting device, air pressure detecting device, sand and dust detecting device, hail detecting device, accumulated snow detecting device and sand and dust detecting device, to detect this area meteorological information.Traffic flow and microclimate data acquisition will be prepared for next step Fuzzy Neural-network Control.

Step 2: the design of fuzzy neural network traffic controller

Described fuzzy neural network traffic controller is realized traffic prewarning information issue under the inclement weather; Be that some historical datas, priori or traffic engineering domain expert experience are included in the fuzzy rule, be convenient to obtain reasonably and traffic prewarning information meteorological and that telecommunication flow information adapts.The fuzzy neural network traffic controller is divided into five-layer structure:

Ground floor is an input layer, and input value is the supplemental characteristic that freeway traffic flow and microclimate check point are gathered, and is expressed as x={x ₁, x ₂, x ₃..., x _n, wherein, n representes the number of input parameter, and x ₁, x ₂... x _nRepresent traffic flow parameter (speed, flow, occupation rate) and microclimate parameter (visibility, temperature, humidity, air pressure, wind direction, wind speed, ST etc.) respectively.

Input parameter is divided into 5 grades according to from small to large order, is respectively { NB is negative big, and NS is negative little, and Z zero, and PS is just little, and PB is honest }, its meaning for the relevant parameters desired value be little, less, medium, greatly, bigger.System is output as control model, speed limit and safe distance.Wherein, control model is divided into three kinds, sealing completely, zone sealing and ring road control (control sail the highway flow into according to traffic and meteorological condition); Speed limit and safe distance grade classification mode are identical with input parameter.

The network second layer is the obfuscation layer, be used for representing input quantity belong to respectively NB, NS, Z, PS, the degree of membership of PB} does

J=1 in the formula, 2 ..., m _i, m _iBe x _iThe fuzzy number of cutting apart, m here _i=5.c _IjAnd σ _IjCenter and the width of representing membership function respectively;

The 3rd layer is regular former piece layer, and each node is represented a fuzzy rule, and its effect is the former piece that is used for mating fuzzy rule, calculates the relevance grade of every rule, and formula is:

Or

$a_j={\mathrm{\μ}}_1^j\left(x_1\right){\mathrm{\μ}}_2^j\left(x_2\right)...{\mathrm{\μ}}_n^j\left(x_n\right);$

In the formula: a _jThe relevance grade of-fuzzy rule j;

-input x _iThe degree of membership that is under the jurisdiction of j grade, j is the integer between 1 to m, m is the integer more than or equal to 1;

Realize normalization calculating for the 4th layer, formula is:

$\stackrel{\‾}{{\mathrm{\α}}_j}=\frac{{\mathrm{\α}}_j}{\underset{i=1}{\overset{m}{\mathrm{\Σ}}}{\mathrm{\α}}_i},j=\mathrm{1,2},...,m$

The layer 5 output layer, formula does

$y=\underset{r=1}{\overset{m}{\mathrm{\Σ}}}{w}_r\stackrel{\‾}{a_r},r=\mathrm{1,2},...,m$

Wherein, w _rBe connection weight,

Step 3: based on the training of the microclimate traffic controller of fuzzy neural network

(3) selection of training

Training sample is considered to be made up of three parts: first, the historical data of meteorological part, freeway traffic regulation department, comprise historical meteorologic parameter information, traffic flow parameter information, the early warning information of taking at that time and issue after effect; Second portion, traffic engineering domain expert's questionnaire is through being provided with different meteorologies and traffic flow sight, the early warning measure that the inquiry expert possibly adopt; Third part after this system builds up, is added into historical data base with the traffic prewarning scheme implementation effect under different meteorologies, the traffic flow situation.

(4) training algorithm

The parameter that network need be learnt mainly is the central value c of second layer membership function _IjAnd width cs _IjAnd the layer 5 network connects power w _rThe learning algorithm of this network is selected backpropagation BP (Back Propagation) algorithm.The BP algorithm is made up of forward-propagating and two processes of error back propagation.In the forward-propagating process, input information is successively handled through latent layer unit from input layer, after all latent layers, passes to output layer.In the process that hidden layer is successively handled, the neuronic state of each layer only exerts an influence to the following neuronic state of one deck.At output layer reality output and desired output are compared; If the difference of actual output and desired output no longer within the tolerance interval, then changes back-propagation process over to, the error between actual value and the desired output is returned along original connecting path; Through revising the neuronic connection weight of each layer error is reduced; And then changing the forward-propagating process over to, repeated calculation like this is till error is less than setting value.

The specific algorithm step of BP neural metwork training is following:

1. establish x _kBe input vector, x _k=(x ₁, x ₂..., x _n), k=1,2 ... K, in the formula: K is a number of samples, and n represents the number of characteristic parameter; The output vector of corresponding travel pattern is y _kInitialization network weight, threshold value and related parameter is arranged.

2. each unit of the second layer is input as

$S_{\mathrm{ij}}^{\left(2\right)}=x_i,i=\mathrm{1,2},...,n;j=\mathrm{1,2},...m_i$

In the formula, m _iRepresent the fuzzy number of cutting apart of i characteristic parameter.

Transport function between the ground floor and the second layer is membership function:

${\mathrm{\μ}}_i^j\left(x_i\right)=\exp [{(x_i-c_{\mathrm{ij}})}^2/{\mathrm{\σ}}_{\mathrm{ij}}^2]$

Then second layer unit is output as:

$y^{\left(2\right)}=\left\{{\mathrm{\μ}}_i^j\left(x_i\right)\right\}$

3. the input of the 3rd layer of each unit is the output of corresponding each unit of the second layer, for

$S_r^{\left(3\right)}=\left\{{\mathrm{\μ}}_i^r\left(x_i\right)\right\}$

Output layer is output as

$y_r^{\left(3\right)}=\min \left\{{\mathrm{\μ}}_i^l\left(x_i\right)\right\}$

In the formula, l=1,2 ..., m.M representes number of fuzzy rules.

4. the input of the 4th layer of each unit is the output of the 3rd layer of corresponding each unit, for

$S_r^{\left(4\right)}=\left\{y_r^{\left(3\right)}\right\}$

Output layer is output as

$y_r^{\left(4\right)}=\frac{y_r^{\left(3\right)}}{\underset{r=1}{\overset{m}{\mathrm{\Σ}}}{y}_r^{\left(3\right)}}$

5. the input of each unit of layer 5 is the output of the 4th layer of corresponding each unit, for

$S_r^{\left(5\right)}=\left\{y_r^{\left(4\right)}\right\}$

Output layer is output as

$y=w_r{y}_r^{\left(4\right)}$

So far accomplish a forward pass process.

6. in the error back propagation process, at first to carry out Error Calculation.

For fuzzy neural network, suppose that t the right error function of sample is defined as:

$E_t=\frac{1}{2}{(y_0\left(t\right)-y\left(t\right))}^2$

In the formula: y ₀(t) be system's desired output, y (t) is system's real output value, and backpropagation BP thought is used to supervised learning, through each weighted value of adjustment network, makes the error function value minimum, thereby reaches the purpose of revising membership function parameter and network connection power.

7. the next sample of picked at random is to offering network; The double counting process; Until network global error function

(wherein; K is the learning sample number) less than predefined minimal value, i.e. a network convergence; Or learn number of times less than predefined value, promptly network can't be restrained.

8. finish study.

Step 4: utilize optimum fuzzy neural network traffic controller to generate traffic prewarning information

The fuzzy neural network controller that the meteorologic parameter of gathering in real time and traffic flow parameter input are trained; Generate real-time traffic prewarning information, comprise Highway Control mode (close completely, the zone is closed, ring road control etc.), speed limit and safe driving spacing.

Step 5: early warning information issue

Utilize wireless communication technology, traffic prewarning information is sent to the variable information plate (module 2 as shown in Figure 1) of trackside, variable information plate institute information releasing should be the traffic prewarning information that its downstream controller obtains.

Though the above-mentioned accompanying drawing specific embodiments of the invention that combines is described; But be not restriction to protection domain of the present invention; One of ordinary skill in the art should be understood that; On the basis of technical scheme of the present invention, those skilled in the art need not pay various modifications that creative work can make or distortion still in protection scope of the present invention.

Claims (4)

1. the highway microclimate traffic prewarning method based on fuzzy neural network is characterized in that, may further comprise the steps: the laying of traffic flow and microclimate check point; Ambiguity in definition neural network traffic controller; The training of fuzzy neural network traffic controller; Utilize optimum fuzzy neural network traffic controller to generate traffic safety driving parameter; The traffic control information issue, the concrete operations step is following:

Step 1: some traffic flows and microclimate monitoring point are set at the every spacing distance of highway trackside; Detect this road traffic delay situation and microclimate supplemental characteristic; Pass through sensor Data Fusion; Obtain road traffic delay and weather information, traffic flow and microclimate data acquisition are prepared for next step Fuzzy Neural-network Control;

Step 2: adopt fuzzy neural network to make up highway microclimate traffic controller based on the Takagi-Sugeno reasoning; Telecommunication flow information and weather information that definition step 1 collects are state variable; Input value as said controller; Definition Highway Control mode, speed limit and safe spacing value are control variable, as the output valve of said controller;

Step 3: the meteorology, traffic flow, control measure and the implementation result historical data base thereof that adopt meteorological department and vehicle supervision department; Make up the training sample of fuzzy neural network traffic controller in conjunction with expertise; Highway microclimate traffic controller is trained; Training error is reduced to predetermined threshold or reaches frequency of training, to obtain optimal controller;

Step 4: the telecommunication flow information that will gather in real time and the optimum fuzzy neural network traffic controller of microclimate information input; Generate Freeway Traffic Control scheme, comprise early warning measure, speed limit and safe spacing value to this moment traffic flow situation and weather information;

Step 5: lay the variable information plate in each traffic and the upper reaches, microclimate monitoring point, the safe driving early warning information of traffic controller output is issued.

2. the highway microclimate traffic prewarning method based on fuzzy neural network as claimed in claim 1 is characterized in that, fuzzy neural network structure highway microclimate traffic controller is divided into five-layer structure in the said step 2:

Ground floor is an input layer, and input value is the supplemental characteristic that freeway traffic flow and microclimate check point are gathered, and is expressed as x={x ₁, x ₂, x ₃..., x _n, wherein, n representes the number of input parameter, n is the integer more than or equal to 1, and x ₁, x ₂... x _nRepresent respectively traffic flow parameter be speed, flow, occupation rate and microclimate parameter can degree of opinion, temperature, humidity, air pressure, wind direction, wind speed, ST;

Input parameter is divided into 5 grades according to from small to large order, is respectively { NB is negative big, and NS is negative little, and Z zero, and PS is just little, and PB is honest }, its meaning for the relevant parameters desired value be little, less, medium, greatly, bigger; The system of the controller of telling is output as control model, speed limit and safe distance; Wherein, control model is divided into three kinds, and sealing completely, zone sealing and ring road control are promptly controlled according to traffic and meteorological condition and sailed the highway flow into; Speed limit and safe distance grade classification mode are identical with input parameter;

The second layer is the obfuscation layer, be used for representing input quantity belong to respectively NB, NS, Z, PS, the degree of membership of PB} does

In the formula, j is 1 to m _iInteger, m _iBe x _iThe fuzzy number of cutting apart, m here _i=5; c _IjAnd σ _IjCenter and the width of representing membership function respectively;

The 3rd layer is regular former piece layer, and each node is represented a fuzzy rule, and its effect is the former piece that is used for mating fuzzy rule, calculates the relevance grade a of every rule _j, formula is:

Or

$a_j={\mathrm{\μ}}_1^j\left(x_1\right){\mathrm{\μ}}_2^j\left(x_2\right)...{\mathrm{\μ}}_n^j\left(x_n\right);$

In the formula: a _jThe relevance grade of-fuzzy rule j;

-input x _iThe degree of membership that is under the jurisdiction of j grade; J is the integer between 1 to m, and m is the integer more than or equal to 1;

Realize normalization calculating for the 4th layer, formula is:

wherein; J is the integer between 1 to m, and m is the integer more than or equal to 1;

The layer 5 output layer, formula does

$y=\underset{r=1}{\overset{m}{\mathrm{\Σ}}}{w}_r\stackrel{\‾}{a_r},r=\mathrm{1,2},...,m$

Wherein, w _rBe connection weight, r is the integer between 1 to m, and m is the integer more than or equal to 1.

3. the highway microclimate traffic prewarning method based on fuzzy neural network as claimed in claim 2 is characterized in that, based on the training of the microclimate traffic controller of fuzzy neural network, particular content is following in the said step 3:

Selection of training

Training sample is considered to be made up of three parts: first, the historical data of meteorological part, freeway traffic regulation department, comprise historical meteorologic parameter information, traffic flow parameter information, the early warning information of taking at that time and issue after effect; Second portion, traffic engineering domain expert's questionnaire is through being provided with different meteorologies and traffic flow sight, the early warning measure that the inquiry expert possibly adopt; Third part after this system builds up, is added into historical data base with the traffic prewarning scheme implementation effect under different meteorologies, the traffic flow situation;

Training algorithm

The parameter that network need be learnt is the central value c of second layer membership function in the step 2 _IjAnd width cs _IjAnd layer 5 network connection weight w _r, the learning algorithm of this network is selected backpropagation BP algorithm; The BP algorithm is made up of forward-propagating and two processes of error back propagation; In the forward-propagating process, input information is successively handled through latent layer unit from input layer, after all latent layers, passes to output layer; In the process that hidden layer is successively handled, the neuronic state of each layer only exerts an influence to the following neuronic state of one deck; At output layer reality output and desired output are compared; If the difference of actual output and desired output no longer within the tolerance interval, then changes back-propagation process over to, the error between actual value and the desired output is returned along original connecting path; Through revising the neuronic connection weight of each layer error is reduced; And then changing the forward-propagating process over to, repeated calculation like this is till error is less than setting value.

4. the highway microclimate traffic prewarning method based on fuzzy neural network as claimed in claim 3 is characterized in that, the learning algorithm of said network is selected backpropagation BP algorithm, and step is following:

1. establish x _kBe input vector, x _k=(x ₁, x ₂..., x _n), k is the integer between 1 to K, in the formula: K is a number of samples, and n represents the number of characteristic parameter; The output vector of corresponding travel pattern is y _k, initialization network weight, threshold value;

2. each unit of the second layer is input as

$S_{\mathrm{ij}}^{\left(2\right)}=x_i,$

In the formula, x _iThe input of expression system, i.e. traffic flow parameter and meteorologic parameter value; I is the integer between 1 to n, and n represents the number of characteristic parameter; J is 1 to m _iBetween integer, m _iRepresent the fuzzy number of cutting apart of i characteristic parameter;

Transport function between the ground floor and the second layer is membership function:

${\mathrm{\μ}}_i^j\left(x_i\right)=\exp [{(x_i-c_{\mathrm{ij}})}^2/{\mathrm{\σ}}_{\mathrm{ij}}^2]$

Then second layer unit is output as:

$y^{\left(2\right)}=\left\{{\mathrm{\μ}}_i^j\left(x_i\right)\right\}$

3. the input of the 3rd layer of each unit is the output of corresponding each unit of the second layer, for

$S_r^{\left(3\right)}=\left\{{\mathrm{\μ}}_i^r\left(x_i\right)\right\}$

Output layer is output as

$y_r^{\left(3\right)}=\min \left\{{\mathrm{\μ}}_i^l\left(x_i\right)\right\}$

In the formula, l is the integer between 1 to m, and m representes number of fuzzy rules;

4. the input of the 4th layer of each unit is the output of the 3rd layer of corresponding each unit, for

$S_r^{\left(4\right)}=\left\{y_r^{\left(3\right)}\right\}$

Output layer is output as

$y_r^{\left(4\right)}=\frac{y_r^{\left(3\right)}}{\underset{r=1}{\overset{m}{\mathrm{\Σ}}}{y}_r^{\left(3\right)}}$

5. the input of each unit of layer 5 is the output of the 4th layer of corresponding each unit, for

$S_r^{\left(5\right)}=\left\{y_r^{\left(4\right)}\right\}$

Output layer is output as

$y=w_r{y}_r^{\left(4\right)}$

So far accomplish a forward pass process;

6. in the error back propagation process, at first to carry out Error Calculation,

For fuzzy neural network, suppose t the error function E that sample is right _tBe defined as:

$E_t=\frac{1}{2}{(y_0\left(t\right)-y\left(t\right))}^2$

In the formula: y ₀(t) be system's desired output, y (t) is system's real output value, and t is the integer more than or equal to 1, the label of expression sample;

Backpropagation BP thought is used to supervised learning, through each weighted value of adjustment network, makes the error function value minimum, thereby reaches the purpose of revising membership function parameter and network connection power;

7. the next sample of picked at random is to offering network; The double counting process; Until network global error function less than predefined minimal value, i.e. a network convergence; Or learn number of times less than predefined value, promptly network can't be restrained; Wherein, K is the learning sample number;

8. finish study.

Images