CN102737504A - Method for estimating bus arrival time in real time based on drive characteristics - Google Patents

Abstract

The invention discloses a method for real-time estimation of bus arrival time based on driving characteristics, which comprises the following steps: firstly, analyzing the driving characteristics to obtain a driving characteristic correction factor; value; then estimate the delay time of the bus stop and the signal light delay time; finally get the estimated time of bus arrival. The invention divides the traveling time of the bus on the road network into road section travel time and delay time, and the accurate estimation of the road section travel time and the reasonable calculation of the bus stop time and signal light delay time are the decisive factors for the estimation of the arrival time of the floating bus. factor, the combination of the two parts of time is the arrival time of the bus floating vehicle from the current position to the target position. The method adopts different algorithms for calculation according to the different amount of road section data, and improves the prediction accuracy of the average travel time of the road section and the prediction accuracy of the bus arrival time.

Description

A Real-time Estimation Method of Bus Arrival Time Based on Driving Characteristics

technical field

The invention relates to the technical field of intelligent traffic systems, in particular to a method for real-time estimation of bus arrival time based on driving characteristics.

Background technique

In the study of intelligent transportation systems, the estimation of bus arrival time is related to factors such as traffic flow, the average speed of the road section, passing time, road conditions, and distance from the station. Based on the bus data that can be used to estimate the bus arrival time, the real-time information of the data includes: vehicle instantaneous speed (representing the current speed of the vehicle), mileage (representing the total mileage of the vehicle since the installation of the GPS device), stop mileage (representing the mileage of the vehicle from the starting station to the current GPS positioning point during one operation), driving direction (representing the starting direction of the vehicle, for example: the driving direction from the starting station to the terminal station is set as "1", and the terminal station to The driving direction of the starting station is set to "0"), vehicle status (representing the vehicle's entry situation, exit situation, arrival situation and station type, etc.), longitude and latitude position, current time (representing the year, month, and day of the current GPS positioning point , hours, minutes, seconds, etc.) and the vehicle speed limit value, etc., can better estimate the arrival time of the bus.

The previous bus arrival time estimation methods have two modes: static prediction and dynamic prediction. Static methods are difficult to adapt to complex and changeable road traffic conditions. In the dynamic method, on the one hand, the instantaneous speed of the vehicle is affected by the road environment and shows greater randomness and abruptness. The data with large fluctuations and frequent data have a greater impact on the prediction, which will lead to unreliable prediction. On the other hand, the bus is driving on a fixed route, the inherent conditions of the road are relatively stable, and the road state changes in a day will show a certain regularity, such as: morning peak and evening peak, and there will be certain changes with the weather , this law will affect the driving characteristics of the driver, making the driving characteristics have a certain regularity, but for different drivers, this law is not the same, so in order to improve the estimation accuracy, this law also needs to be considered.

At the same time, due to the impact of the road environment and traffic flow, there is a delay time for the bus during driving. The delay time mainly includes two parts. One is the arrival time of the bus, especially the significant difference between peak hours and non-peak hours. Therefore, they need to be considered separately; the second is the delay time of signal lights.

Therefore, there is an urgent need for a method of calculating bus arrival time based on different data sample sizes.

Contents of the invention

In view of this, the technical problem to be solved by the present invention is to provide a method for calculating bus arrival time based on different data sample sizes.

The realization process of the present invention is as follows:

The bus arrival time real-time estimation method based on driving characteristics provided by the present invention adopts the following formula to calculate the bus arrival time:

为车辆x的停站延误时间；D_p为车辆在信号灯处停车延误时间。Among them: T _ntk is the estimated time for bus k to arrive at station n from the current position at time t; T _t is the average travel time of bus vehicle from the current position to the downstream target station at time t;

is the parking delay time of vehicle x; D _p is the parking delay time of the vehicle at the signal light.

Further, the average travel time T _t of the bus vehicle from the current position to the downstream target site at the t moment comprises the average travel time estimation of the white shuttle bus;

The estimated average travel time of the daytime bus is calculated by the following formula:

$\stackrel{<span\; class="notranslate">\; \&OverBar;</span>}{{\mathrm{<span\; class="notranslate">\; T</span>}}_{\mathrm{<span\; class="notranslate">\; travel</span>}}^{\mathrm{<span\; class="notranslate">\; b</span>}}}<span\; class="notranslate">\; =</span>{\mathrm{<span\; class="notranslate">\; \&alpha;</span>}}_{<span\; class="notranslate">\; (</span>\mathrm{<span\; class="notranslate">\; j</span>}<span\; class="notranslate">\; ,</span>\mathrm{<span\; class="notranslate">\; x</span>}<span\; class="notranslate">\; )</span>}^{\mathrm{<span\; class="notranslate">\; k</span>}}\frac{\mathrm{<span\; class="notranslate">\; l</span>}}{\stackrel{<span\; class="notranslate">\; \&OverBar;</span>}{{\mathrm{<span\; class="notranslate">\; V</span>}}_{<span\; class="notranslate">\; (</span>\mathrm{<span\; class="notranslate">\; j</span>}<span\; class="notranslate">\; ,</span>\mathrm{<span\; class="notranslate">\; x</span>}<span\; class="notranslate">\; )</span>}}}<span\; class="notranslate">\; +</span>\underset{\mathrm{<span\; class="notranslate">\; i</span>}<span\; class="notranslate">\; =</span>\mathrm{<span\; class="notranslate">\; j</span>}<span\; class="notranslate">\; +</span>\mathrm{<span\; class="notranslate">\; 1</span>}}{\overset{\mathrm{<span\; class="notranslate">\; no</span>}}{\mathrm{<span\; class="notranslate">\; \&Sigma;</span>}}}\frac{{\mathrm{<span\; class="notranslate">\; \&alpha;</span>}}_{<span\; class="notranslate">\; (</span>\mathrm{<span\; class="notranslate">\; j</span>}<span\; class="notranslate">\; ,</span>\mathrm{<span\; class="notranslate">\; x</span>}<span\; class="notranslate">\; )</span>}^{\mathrm{<span\; class="notranslate">\; k</span>}}{\mathrm{<span\; class="notranslate">\; L</span>}}_{\mathrm{<span\; class="notranslate">\; i</span>}}}{\stackrel{<span\; class="notranslate">\; \&OverBar;</span>}{{\mathrm{<span\; class="notranslate">\; V</span>}}_{<span\; class="notranslate">\; (</span>\mathrm{<span\; class="notranslate">\; i</span>}<span\; class="notranslate">\; ,</span>\mathrm{<span\; class="notranslate">\; x</span>}<span\; class="notranslate">\; )</span>}}}<span\; class="notranslate">\; ;</span>$

为修正平均行程时间，

为车辆与最近站点间的路段j的区间平均速度；

为路段i的区间平均速度；j为车辆当前所在路段；L_i为路段i的长度；n为目标车站前面一个路段；

为情况k下，对路段i上车辆x的驾驶特性修正因子。in,

To correct the mean travel time,

is the interval average speed of the section j between the vehicle and the nearest station;

is the average speed of section i; j is the current section of the vehicle; L _i is the length of section i; n is a section in front of the target station;

is the correction factor for the driving characteristics of vehicle x on road section i in case k.

是通过以下步骤来计算：Interval average speed for the section in question

is calculated by the following steps:

First divide the road section by station, obtain the station information and driving direction information in the GPS data, and then obtain the data of all floating cars in the same direction as the estimated average travel time in the road section within this time period, and finally obtain the data from the floating car data Take the average speed of the road section

Further, the average travel time T _t of the bus vehicle from the current position to the downstream target site at the t moment also includes the average travel time estimation of the night bus;

The average travel time estimation of described night bus comprises short-distance target station average travel time estimation and long-distance target station average travel time estimation;

The estimated average travel time of the short-distance target station is calculated by the following formula:

$\stackrel{<span\; class="notranslate">\; \&OverBar;</span>}{{\mathrm{<span\; class="notranslate">\; T</span>}}_{\mathrm{<span\; class="notranslate">\; travel</span>}}^{\mathrm{<span\; class="notranslate">\; no</span>}}}<span\; class="notranslate">\; =</span>\frac{{\mathrm{<span\; class="notranslate">\; L</span>}}_{\mathrm{<span\; class="notranslate">\; d</span>}}}{\stackrel{<span\; class="notranslate">\; \&OverBar;</span>}{\mathrm{<span\; class="notranslate">\; V</span>}}}<span\; class="notranslate">\; ;</span>$

为该夜班车到下游目标站点的平均行程时间，L_d表示利用GPS数据里的车辆里程信息来确定的车辆与目标站点间的距离，

表示该时间段内的平均速度；in,

is the average travel time of the night bus to the downstream target site, L _d represents the distance between the vehicle and the target site determined by the vehicle mileage information in the GPS data,

Indicates the average speed during the time period;

The estimated average travel time of the long-distance target station is calculated by the following formula:

$\stackrel{<span\; class="notranslate">\; \&OverBar;</span>}{{\mathrm{<span\; class="notranslate">\; T</span>}}_{\mathrm{<span\; class="notranslate">\; travel</span>}}^{\mathrm{<span\; class="notranslate">\; no</span>}}}<span\; class="notranslate">\; =</span>\frac{\mathrm{<span\; class="notranslate">\; 1</span>}}{\stackrel{<span\; class="notranslate">\; \&OverBar;</span>}{\mathrm{<span\; class="notranslate">\; V</span>}}}<span\; class="notranslate">\; +</span>\underset{\mathrm{<span\; class="notranslate">\; i</span>}<span\; class="notranslate">\; =</span>\mathrm{<span\; class="notranslate">\; j</span>}}{\overset{\mathrm{<span\; class="notranslate">\; no</span>}}{\mathrm{<span\; class="notranslate">\; \&Sigma;</span>}}}{\mathrm{<span\; class="notranslate">\; t</span>}}_{<span\; class="notranslate">\; (</span>\mathrm{<span\; class="notranslate">\; i</span>}<span\; class="notranslate">\; ,</span>\mathrm{<span\; class="notranslate">\; r</span>}<span\; class="notranslate">\; )</span>}^{\mathrm{<span\; class="notranslate">\; k</span>}}<span\; class="notranslate">\; ;</span>$

为在情况k下，车辆经过路段i所需的平均站间行驶时间，l为车辆与最近站点间的距离。Among them, n is the previous road section of the target site; j is the next road section that the vehicle will arrive at;

is the average inter-station travel time required for the vehicle to pass through road section i in case k, and l is the distance between the vehicle and the nearest station.

通过以下公式来计算：the average speed

Calculated by the following formula:

$\stackrel{<span\; class="notranslate">\; \&OverBar;</span>}{\mathrm{<span\; class="notranslate">\; V</span>}}<span\; class="notranslate">\; =</span>\frac{\mathrm{<span\; class="notranslate">\; 1</span>}}{\mathrm{<span\; class="notranslate">\; m</span>}}\underset{\mathrm{<span\; class="notranslate">\; i</span>}<span\; class="notranslate">\; =</span>\mathrm{<span\; class="notranslate">\; 1</span>}}{\overset{\mathrm{<span\; class="notranslate">\; m</span>}}{\mathrm{<span\; class="notranslate">\; \&Sigma;</span>}}}{\mathrm{<span\; class="notranslate">\; v</span>}}_{\mathrm{<span\; class="notranslate">\; i</span>}}<span\; class="notranslate">\; ;</span>$

Among them, M is the number of valid GPS data of the vehicle collected, and v _i is the corresponding speed of each vehicle in the GPS data.

通过以下公式来计算：Further, the stop delay time of the vehicle x

Calculated by the following formula:

$\stackrel{<span\; class="notranslate">\; \&OverBar;</span>}{{\mathrm{<span\; class="notranslate">\; D.</span>}}_{\mathrm{<span\; class="notranslate">\; x</span>}}}<span\; class="notranslate">\; =</span>{\mathrm{<span\; class="notranslate">\; D.</span>}}_{\mathrm{<span\; class="notranslate">\; b</span>}}<span\; class="notranslate">\; +</span>\underset{\mathrm{<span\; class="notranslate">\; i</span>}<span\; class="notranslate">\; =</span>\mathrm{<span\; class="notranslate">\; j</span>}}{\overset{\mathrm{<span\; class="notranslate">\; no</span>}}{\mathrm{<span\; class="notranslate">\; \&Sigma;</span>}}}{\mathrm{<span\; class="notranslate">\; t</span>}}_{<span\; class="notranslate">\; (</span>\mathrm{<span\; class="notranslate">\; i</span>}<span\; class="notranslate">\; ,</span>\mathrm{<span\; class="notranslate">\; the\; s</span>}<span\; class="notranslate">\; )</span>}^{\mathrm{<span\; class="notranslate">\; k</span>}}<span\; class="notranslate">\; ;</span>$

Among them, n is the previous station of the target station; j is the downstream station closest to the current position of the vehicle; is the average residence time of vehicles at station i in case k;

通过以下公式来计算：The average stop time of each station in different time periods

Calculated by the following formula:

D _b =αT ₀ +βT ₁ +γT ₂ ;

Among them: α, β, γ are the time correction coefficients; T ₀ is the time to decelerate and approach the station; T ₁ is the time to board and unload passengers at the stop; T ₂ is the time to accelerate to leave the station.

Further, the parking delay time D _p of the vehicle at the signal light is calculated through the following steps:

S51: use the GPS data to obtain the positioning position and instantaneous speed of the bus in real time;

S52: Determine whether the bus vehicle is already in the signal light area;

S53: According to the driving state of the vehicle, calculate the staying time of the vehicle at the current traffic light position by the following formula:

S54: When the vehicle encounters a red light, the sum of the parking delay time from the current position to the estimated stop time of all signal lights between the stations is ${\mathrm{D.}}_p=\underset{p=1}{\overset{q}{\mathrm{\&Sigma;}}}\underset{x=1}{\overset{m}{\mathrm{\&Sigma;}}}P\left(x\right)T_{\mathrm{px}};$

S55: When the vehicle encounters a green light, the sum of the parking delay time from the next signal light at the current position to the estimated stop time of all signal lights between stations is ${\mathrm{D.}}_p=\underset{p=2}{\overset{q}{\mathrm{\&Sigma;}}}\underset{x=1}{\overset{m}{\mathrm{\&Sigma;}}}P\left(x\right)T_{\mathrm{px}};$

S56: When the vehicle is not in the signal light area, the sum of the parking delay time from the current position to all signal lights between stations is estimated to be ${\mathrm{D.}}_p=\underset{p=1}{\overset{q}{\mathrm{\&Sigma;}}}\underset{x=1}{\overset{m}{\mathrm{\&Sigma;}}}P\left(x\right)T_{\mathrm{px}};$

Among them, P(x) represents the probability distribution of x vehicles arriving at the signal light area during the time interval length t, T _px is the random delay time of the vehicle parking at the signal light p, and M is the time at the signal light p within a cycle Vehicle arrivals.

通过以下步骤获得：Further, the driving characteristic correction factor

Obtained by the following steps:

S61: Obtain vehicle site information and station entry and exit information in the GPS data;

S62: calculating the average travel time between stations;

S63: According to the ratio of the cluster center where the vehicle is located to the average inter-station travel time, obtain the driving characteristic correction factor of the vehicle.

The present invention has the advantages that: the present invention mainly divides the travel time of the bus on the road network into two parts: road travel time and delay time, high-precision estimation and For the reasonable calculation of bus stop time and signal light delay time, the combination of the two parts of time is the arrival time of the bus floating car from the current position to the target position, and the instantaneous speed substitution method and the instantaneous speed Composite integral method, compound road section weight method and other calculation algorithms improve the prediction accuracy of the average travel time of the road section, and improve the prediction accuracy of the bus arrival time. The high-precision estimation of the average travel time of the current position of the bus floating vehicle to the downstream station and the reasonable calculation of the bus stop time and signal light delay time are the decisive factors in determining the estimation of the arrival time of the bus floating vehicle.

Three aspects are mainly considered in the analysis of the characteristics of the average travel time of the bus floating vehicle: ① The travel time of the current section of the bus floating vehicle must be related to the current traffic section. Different road sections with different geographical characteristics have different driving rules; ②In the middle of the night, the traffic conditions faced by night buses are significantly different from those in the daytime, and the traffic conditions in the middle of the night are simpler than those in the daytime; ③The road section itinerary of the floating bus Time will also be related to the current driver's own driving characteristics. At the same time period, different drivers will have different driving characteristics on road sections with the same geographical features.

In the analysis of the delay time characteristics of the bus floating car, two aspects are mainly considered: ①There are a certain number of traffic lights in the bus floating car route, and the delay in the traffic light area has a certain randomness; ②There are a certain number of traffic lights in the bus floating car route. At bus stations, the residence time of vehicles at bus stations is significantly different under different weather conditions and at different times, especially during peak hours and non-peak hours, so it needs to be considered separately.

Other advantages, objects and features of the present invention will be set forth in the following description to some extent, and to some extent, will be obvious to those skilled in the art based on the investigation and research below, or can be obtained from It is taught in the practice of the present invention. The objectives and other advantages of the invention may be realized and attained by the structure particularly pointed out in the written description and claims hereof as well as the appended drawings.

Description of drawings

In order to make the purpose, technical solutions and advantages of the present invention clearer, the present invention will be described in further detail below in conjunction with the accompanying drawings, wherein:

FIG. 1 is a diagram of a method for estimating the arrival time of a bus provided by an embodiment of the present invention.

Detailed ways

The preferred embodiments of the present invention will be described in detail below in conjunction with the accompanying drawings; it should be understood that the preferred embodiments are only for illustrating the present invention, rather than limiting the protection scope of the present invention.

Fig. 1 is the method diagram of the bus arrival time estimation that the embodiment of the present invention provides, as shown in the figure: the bus arrival time real-time estimation method based on driving characteristic provided by the present invention, adopts following formula to calculate bus arrival time:

为车辆x的停站延误时间；D_p为车辆在信号灯处停车延误时间。Among them: T _ntk is the estimated time for bus k to arrive at station n from the current position at time t; T _t is the average travel time of bus vehicle from the current position to the downstream target station at time t;

is the parking delay time of vehicle x; D _p is the parking delay time of the vehicle at the signal light.

The average travel time T t of the bus vehicle from the current position to the downstream target site at the time _t includes the average travel time estimate of the daytime bus;

The estimated average travel time of the daytime bus is calculated by the following formula:

$\stackrel{<span\; class="notranslate">\; \&OverBar;</span>}{{\mathrm{<span\; class="notranslate">\; T</span>}}_{\mathrm{<span\; class="notranslate">\; travel</span>}}^{\mathrm{<span\; class="notranslate">\; b</span>}}}<span\; class="notranslate">\; =</span>{\mathrm{<span\; class="notranslate">\; \&alpha;</span>}}_{<span\; class="notranslate">\; (</span>\mathrm{<span\; class="notranslate">\; j</span>}<span\; class="notranslate">\; ,</span>\mathrm{<span\; class="notranslate">\; x</span>}<span\; class="notranslate">\; )</span>}^{\mathrm{<span\; class="notranslate">\; k</span>}}\frac{\mathrm{<span\; class="notranslate">\; l</span>}}{\stackrel{<span\; class="notranslate">\; \&OverBar;</span>}{{\mathrm{<span\; class="notranslate">\; V</span>}}_{<span\; class="notranslate">\; (</span>\mathrm{<span\; class="notranslate">\; j</span>}<span\; class="notranslate">\; ,</span>\mathrm{<span\; class="notranslate">\; x</span>}<span\; class="notranslate">\; )</span>}}}<span\; class="notranslate">\; +</span>\underset{\mathrm{<span\; class="notranslate">\; i</span>}<span\; class="notranslate">\; =</span>\mathrm{<span\; class="notranslate">\; j</span>}<span\; class="notranslate">\; +</span>\mathrm{<span\; class="notranslate">\; 1</span>}}{\overset{\mathrm{<span\; class="notranslate">\; no</span>}}{\mathrm{<span\; class="notranslate">\; \&Sigma;</span>}}}\frac{{\mathrm{<span\; class="notranslate">\; \&alpha;</span>}}_{<span\; class="notranslate">\; (</span>\mathrm{<span\; class="notranslate">\; j</span>}<span\; class="notranslate">\; ,</span>\mathrm{<span\; class="notranslate">\; x</span>}<span\; class="notranslate">\; )</span>}^{\mathrm{<span\; class="notranslate">\; k</span>}}{\mathrm{<span\; class="notranslate">\; L</span>}}_{\mathrm{<span\; class="notranslate">\; i</span>}}}{\stackrel{<span\; class="notranslate">\; \&OverBar;</span>}{{\mathrm{<span\; class="notranslate">\; V</span>}}_{<span\; class="notranslate">\; (</span>\mathrm{<span\; class="notranslate">\; i</span>}<span\; class="notranslate">\; ,</span>\mathrm{<span\; class="notranslate">\; x</span>}<span\; class="notranslate">\; )</span>}}}<span\; class="notranslate">\; ;</span>$

为路段i的区间平均速度；j为车辆当前所在路段；L_i为路段i的长度；n为目标车站前面一个路段；

为情况k下，对路段i上车辆x的驾驶特性修正因子。in, To correct the average travel time, is the interval average speed of the section j between the vehicle and the nearest station;

is the average speed of section i; j is the current section of the vehicle; L _i is the length of section i; n is a section in front of the target station;

is the correction factor for the driving characteristics of vehicle x on road section i in case k.

是通过以下步骤来计算：Interval average speed for the section in question

is calculated by the following steps:

First divide the road section by station, obtain the station information and driving direction information in the GPS data, and then obtain the data of all floating cars in the same direction as the estimated average travel time in the road section within this time period, and finally obtain the data from the floating car data Take the average speed of the road section

The average travel time T _t of the bus vehicle at the time t from the current position to the downstream target site also includes an estimate of the average travel time of the night bus;

The average travel time estimation of described night bus comprises short-distance target station average travel time estimation and long-distance target station average travel time estimation;

The estimated average travel time of the short-distance target station is calculated by the following formula:

$\stackrel{<span\; class="notranslate">\; \&OverBar;</span>}{{\mathrm{<span\; class="notranslate">\; T</span>}}_{\mathrm{<span\; class="notranslate">\; travel</span>}}^{\mathrm{<span\; class="notranslate">\; no</span>}}}<span\; class="notranslate">\; =</span>\frac{{\mathrm{<span\; class="notranslate">\; L</span>}}_{\mathrm{<span\; class="notranslate">\; d</span>}}}{\stackrel{<span\; class="notranslate">\; \&OverBar;</span>}{\mathrm{<span\; class="notranslate">\; V</span>}}}<span\; class="notranslate">\; ;</span>$

为该夜班车到下游目标站点的平均行程时间，L_d表示利用GPS数据里的车辆里程信息来确定的车辆与目标站点间的距离，

表示该时间段内的平均速度；in,

is the average travel time of the night bus to the downstream target site, L _d represents the distance between the vehicle and the target site determined by the vehicle mileage information in the GPS data,

Indicates the average speed during the time period;

The estimated average travel time of the long-distance target station is calculated by the following formula:

$\stackrel{<span\; class="notranslate">\; \&OverBar;</span>}{{\mathrm{<span\; class="notranslate">\; T</span>}}_{\mathrm{<span\; class="notranslate">\; travel</span>}}^{\mathrm{<span\; class="notranslate">\; no</span>}}}<span\; class="notranslate">\; =</span>\frac{\mathrm{<span\; class="notranslate">\; 1</span>}}{\stackrel{<span\; class="notranslate">\; \&OverBar;</span>}{\mathrm{<span\; class="notranslate">\; V</span>}}}<span\; class="notranslate">\; +</span>\underset{\mathrm{<span\; class="notranslate">\; i</span>}<span\; class="notranslate">\; =</span>\mathrm{<span\; class="notranslate">\; j</span>}}{\overset{\mathrm{<span\; class="notranslate">\; no</span>}}{\mathrm{<span\; class="notranslate">\; \&Sigma;</span>}}}{\mathrm{<span\; class="notranslate">\; t</span>}}_{<span\; class="notranslate">\; (</span>\mathrm{<span\; class="notranslate">\; i</span>}<span\; class="notranslate">\; ,</span>\mathrm{<span\; class="notranslate">\; r</span>}<span\; class="notranslate">\; )</span>}^{\mathrm{<span\; class="notranslate">\; k</span>}}<span\; class="notranslate">\; ;</span>$

为在情况k下，车辆经过路段i所需的平均站间行驶时间，l为车辆与最近站点间的距离。Among them, n is the previous road section of the target site; j is the next road section that the vehicle will arrive at;

is the average inter-station travel time required for the vehicle to pass through road section i in case k, and l is the distance between the vehicle and the nearest station.

通过以下公式来计算：the average speed

Calculated by the following formula:

$\stackrel{<span\; class="notranslate">\; \&OverBar;</span>}{\mathrm{<span\; class="notranslate">\; V</span>}}<span\; class="notranslate">\; =</span>\frac{\mathrm{<span\; class="notranslate">\; 1</span>}}{\mathrm{<span\; class="notranslate">\; m</span>}}\underset{\mathrm{<span\; class="notranslate">\; i</span>}<span\; class="notranslate">\; =</span>\mathrm{<span\; class="notranslate">\; 1</span>}}{\overset{\mathrm{<span\; class="notranslate">\; m</span>}}{\mathrm{<span\; class="notranslate">\; \&Sigma;</span>}}}{\mathrm{<span\; class="notranslate">\; v</span>}}_{\mathrm{<span\; class="notranslate">\; i</span>}}<span\; class="notranslate">\; ;</span>$

Among them, M is the number of valid GPS data of the vehicle collected, and v _i is the corresponding speed of each vehicle in the GPS data.

通过以下公式来计算：The stop delay time of the vehicle x

Calculated by the following formula:

$\stackrel{<span\; class="notranslate">\; \&OverBar;</span>}{{\mathrm{<span\; class="notranslate">\; D.</span>}}_{\mathrm{<span\; class="notranslate">\; x</span>}}}<span\; class="notranslate">\; =</span>{\mathrm{<span\; class="notranslate">\; D.</span>}}_{\mathrm{<span\; class="notranslate">\; b</span>}}<span\; class="notranslate">\; +</span>\underset{\mathrm{<span\; class="notranslate">\; i</span>}<span\; class="notranslate">\; =</span>\mathrm{<span\; class="notranslate">\; j</span>}}{\overset{\mathrm{<span\; class="notranslate">\; no</span>}}{\mathrm{<span\; class="notranslate">\; \&Sigma;</span>}}}{\mathrm{<span\; class="notranslate">\; t</span>}}_{<span\; class="notranslate">\; (</span>\mathrm{<span\; class="notranslate">\; i</span>}<span\; class="notranslate">\; ,</span>\mathrm{<span\; class="notranslate">\; the\; s</span>}<span\; class="notranslate">\; )</span>}^{\mathrm{<span\; class="notranslate">\; k</span>}}<span\; class="notranslate">\; ;</span>$

为在情况k下，车辆在车站i的平均停留时间；Among them, n is the previous station of the target station; j is the downstream station closest to the current position of the vehicle;

is the average residence time of vehicles at station i in case k;

The delay time D _b of the vehicle stopping in the station area of the current station b is calculated by the following formula:

D _b =αT ₀ +βT ₁ +γT ₂ ;

Among them: α, β, γ are the time correction coefficients; T ₀ is the time to decelerate and approach the station; T ₁ is the time to board and unload passengers at the stop; T ₂ is the time to accelerate to leave the station.

其中，为在情况k下，车辆在车站b内停留的平均时间。The vehicle entry and exit time, that is, T ₀ and T ₂ can be replaced by experience values. but

in, is the average time that vehicles stay in station b under condition k.

When the vehicle decelerates and enters the station, at this time α∈(0,1) (indicating that α takes a random value between 0 and 1), β=γ=1;

When the vehicle stays in the station area, α=0, β∈(0,1) (indicating that β takes a random value between 0 and 1), γ=1;

When the vehicle accelerates to leave the station, α=0, β=0, γ∈(0,1) (indicating that γ takes a random value between 0 and 1);

When the vehicle is not in the station area, α=β=γ=0 at this time.

是根据新终端GPS数据中车辆的进出站信息，然后利用这些大量的历史数据，统计车辆的进出站数据，得到其时间信息，用同一站点的出站时间减去进站时间即得到该车在该站点的停站时间。然后分别得到晴天高峰时段、晴天非高峰时段、雨天高峰时段和雨天非高峰时段这4种情况下，各个站点的平均停站时间（其中k表示上述4种情况，i表示车站号）。其分析方法与车辆站间平均行驶时间的分析方法相同，因此不再赘述。The average stop time of each station in different time periods

It is based on the entry and exit information of the vehicle in the GPS data of the new terminal, and then use these large amounts of historical data to count the entry and exit data of the vehicle to obtain its time information, and subtract the entry time from the exit time of the same station to get the The stop time for this station. Then get the average stop time of each station under the four conditions of sunny peak hours, sunny off-peak hours, rainy peak hours and rainy off-peak hours (where k represents the above four situations, and i represents the station number). Its analysis method is the same as that of the average travel time between stations, so it will not be repeated here.

The parking delay time D _p of the vehicle at the signal light is calculated through the following steps:

Assuming that the red light time in a signal cycle is T _h , T _h can be obtained by actual investigation. T _px is defined as the random delay time of vehicles stopping at signal light p, we know that T _px is a random number and T _px ∈ (0, T _h ).

Assume that the arrival of vehicles in the road section obeys the Poisson distribution, so:

$\mathrm{<span\; class="notranslate">\; P</span>}<span\; class="notranslate">\; (</span>\mathrm{<span\; class="notranslate">\; x</span>}<span\; class="notranslate">\; )</span><span\; class="notranslate">\; =</span>\frac{{<span\; class="notranslate">\; (</span>\mathrm{<span\; class="notranslate">\; \&lambda;t</span>}<span\; class="notranslate">\; )</span>}^{\mathrm{<span\; class="notranslate">\; x</span>}}{\mathrm{<span\; class="notranslate">\; e</span>}}^{<span\; class="notranslate">\; -</span>\mathrm{<span\; class="notranslate">\; \&lambda;t</span>}}}{\mathrm{<span\; class="notranslate">\; x</span>}<span\; class="notranslate">\; !</span>}<span\; class="notranslate">\; =</span>\frac{{\mathrm{<span\; class="notranslate">\; d</span>}}^{\mathrm{<span\; class="notranslate">\; x</span>}}{\mathrm{<span\; class="notranslate">\; e</span>}}^{<span\; class="notranslate">\; -</span>\mathrm{<span\; class="notranslate">\; d</span>}}}{\mathrm{<span\; class="notranslate">\; x</span>}<span\; class="notranslate">\; !</span>}<span\; class="notranslate">\; ,</span>\mathrm{<span\; class="notranslate">\; t</span>}<span\; class="notranslate">\; ></span>\mathrm{<span\; class="notranslate">\; 0</span>}<span\; class="notranslate">\; ,</span>\mathrm{<span\; class="notranslate">\; x</span>}<span\; class="notranslate">\; =</span>\mathrm{<span\; class="notranslate">\; 0</span>}<span\; class="notranslate">\; ,</span>\mathrm{<span\; class="notranslate">\; 1,2</span>}<span\; class="notranslate">\; ,</span><span\; class="notranslate">\; .</span><span\; class="notranslate">\; .</span><span\; class="notranslate">\; .</span>\mathrm{<span\; class="notranslate">\; m</span>}<span\; class="notranslate">\; ;</span>$

The above formula expresses the probability that x vehicles arrive at the signal light area during the time interval length t; λ represents the average arrival rate of vehicles in the unit interval; d represents the average arrival rate of vehicles in the counting time interval t. M is defined as the number of vehicles arriving at signal light p in one cycle.

S51: use the GPS data to obtain the positioning position and instantaneous speed of the bus in real time;

S52: Determine whether the bus vehicle is already in the signal light area;

S53: According to the driving state of the vehicle, calculate the staying time of the vehicle at the current traffic light position by the following formula:

S54: When the vehicle encounters a red light, the sum of the parking delay time from the current position to the estimated stop time of all signal lights between the stations is ${\mathrm{D.}}_p=\underset{p=1}{\overset{q}{\mathrm{\&Sigma;}}}\underset{x=1}{\overset{m}{\mathrm{\&Sigma;}}}P\left(x\right)T_{\mathrm{px}};$

S55: When the vehicle encounters a green light, the sum of the parking delay time from the next signal light at the current position to the estimated stop time of all signal lights between stations is ${\mathrm{D.}}_p=\underset{p=2}{\overset{q}{\mathrm{\&Sigma;}}}\underset{x=1}{\overset{m}{\mathrm{\&Sigma;}}}P\left(x\right)T_{\mathrm{px}};$

S56: When the vehicle is not in the signal light area, the sum of the parking delay time from the current position to all signal lights between stations is estimated to be ${\mathrm{D.}}_p=\underset{p=1}{\overset{q}{\mathrm{\&Sigma;}}}\underset{x=1}{\overset{m}{\mathrm{\&Sigma;}}}P\left(x\right)T_{\mathrm{px}};$

Among them, P(x) represents the probability distribution of x vehicles arriving at the signal light area during the time interval length t, T _px is the random delay time of the vehicle parking at the signal light p, and M is the time at the signal light p within a cycle Vehicle arrivals.

通过以下步骤获得：The driving characteristic correction factor

Obtained by the following steps:

S61: Obtain the vehicle station information and inbound and outbound information in the GPS data; use the inbound and outbound data of the GPS data between the adjacent stations, and subtract the outbound time of the previous station from the inbound time of the next station to obtain the adjacent station The inter-station travel time of the station gets its time information.

S62: Calculate the average travel time between stations; the travel time between stations includes the average travel time between single stations and the average travel time between multiple stations; the classified station is obtained by hierarchically clustering the original data of travel time between stations Inter-station travel time data, so as to obtain the weight of the inter-station travel time in each interval, and use the weight to superimpose the average inter-station travel time of vehicles in each section of the road section,

The following example 1 is the calculation embodiment of the average travel time between single stations:

Example 1: Assuming non-peak hours, a set of inter-station travel time data (unit: second) of vehicle x on road section i on sunny days, as shown in Table 1 below is the raw data of inter-station travel time, and the average travel time between stations is calculated. Statistics are shown in Table 1:

Table 1

The classified inter-station travel time data obtained by hierarchical clustering are shown in Table 2:

Table 2

The weight of travel time between stations in each interval is obtained as:

${\mathrm{<span\; class="notranslate">\; f</span>}}_{\mathrm{<span\; class="notranslate">\; 1</span>}}<span\; class="notranslate">\; =</span>{\mathrm{<span\; class="notranslate">\; f</span>}}_{\mathrm{<span\; class="notranslate">\; 2</span>}}<span\; class="notranslate">\; =</span>\frac{{\mathrm{<span\; class="notranslate">\; 3</span>}}^{\mathrm{<span\; class="notranslate">\; 2</span>}}}{{\mathrm{<span\; class="notranslate">\; 3</span>}}^{\mathrm{<span\; class="notranslate">\; 2</span>}}<span\; class="notranslate">\; +</span>{\mathrm{<span\; class="notranslate">\; 3</span>}}^{\mathrm{<span\; class="notranslate">\; 2</span>}}<span\; class="notranslate">\; +</span>{\mathrm{<span\; class="notranslate">\; 5</span>}}^{\mathrm{<span\; class="notranslate">\; 2</span>}}<span\; class="notranslate">\; +</span>{\mathrm{<span\; class="notranslate">\; 2</span>}}^{\mathrm{<span\; class="notranslate">\; 2</span>}}}<span\; class="notranslate">\; =</span>\frac{\mathrm{<span\; class="notranslate">\; 9</span>}}{\mathrm{<span\; class="notranslate">\; 47</span>}}<span\; class="notranslate">\; ;</span>$

${\mathrm{<span\; class="notranslate">\; f</span>}}_{\mathrm{<span\; class="notranslate">\; 3</span>}}<span\; class="notranslate">\; =</span>\frac{{\mathrm{<span\; class="notranslate">\; 5</span>}}^{\mathrm{<span\; class="notranslate">\; 2</span>}}}{{\mathrm{<span\; class="notranslate">\; 3</span>}}^{\mathrm{<span\; class="notranslate">\; 2</span>}}<span\; class="notranslate">\; +</span>{\mathrm{<span\; class="notranslate">\; 3</span>}}^{\mathrm{<span\; class="notranslate">\; 2</span>}}<span\; class="notranslate">\; +</span>{\mathrm{<span\; class="notranslate">\; 5</span>}}^{\mathrm{<span\; class="notranslate">\; 2</span>}}<span\; class="notranslate">\; +</span>{\mathrm{<span\; class="notranslate">\; 2</span>}}^{\mathrm{<span\; class="notranslate">\; 2</span>}}}<span\; class="notranslate">\; =</span>\frac{\mathrm{<span\; class="notranslate">\; 25</span>}}{\mathrm{<span\; class="notranslate">\; 47</span>}}<span\; class="notranslate">\; ;</span>$

${\mathrm{<span\; class="notranslate">\; f</span>}}_{\mathrm{<span\; class="notranslate">\; 4</span>}}<span\; class="notranslate">\; =</span>\frac{{\mathrm{<span\; class="notranslate">\; 2</span>}}^{\mathrm{<span\; class="notranslate">\; 2</span>}}}{{\mathrm{<span\; class="notranslate">\; 3</span>}}^{\mathrm{<span\; class="notranslate">\; 2</span>}}<span\; class="notranslate">\; +</span>{\mathrm{<span\; class="notranslate">\; 3</span>}}^{\mathrm{<span\; class="notranslate">\; 2</span>}}<span\; class="notranslate">\; +</span>{\mathrm{<span\; class="notranslate">\; 5</span>}}^{\mathrm{<span\; class="notranslate">\; 2</span>}}<span\; class="notranslate">\; +</span>{\mathrm{<span\; class="notranslate">\; 2</span>}}^{\mathrm{<span\; class="notranslate">\; 2</span>}}}<span\; class="notranslate">\; =</span>\frac{\mathrm{<span\; class="notranslate">\; 4</span>}}{\mathrm{<span\; class="notranslate">\; 47</span>}}<span\; class="notranslate">\; ;</span>$

Then the average travel time between stations on this road section is:

${\mathrm{<span\; class="notranslate">\; t</span>}}_{<span\; class="notranslate">\; (</span>\mathrm{<span\; class="notranslate">\; i</span>}<span\; class="notranslate">\; ,</span>\mathrm{<span\; class="notranslate">\; x</span>}<span\; class="notranslate">\; ,</span>\mathrm{<span\; class="notranslate">\; r</span>}<span\; class="notranslate">\; )</span>}^{\mathrm{<span\; class="notranslate">\; k</span>}}<span\; class="notranslate">\; =</span>\frac{\mathrm{<span\; class="notranslate">\; 9</span>}}{\mathrm{<span\; class="notranslate">\; 47</span>}}<span\; class="notranslate">\; \&times;</span><span\; class="notranslate">\; (</span>\frac{\mathrm{<span\; class="notranslate">\; 97</span>}<span\; class="notranslate">\; +</span>\mathrm{<span\; class="notranslate">\; 112</span>}<span\; class="notranslate">\; +</span>\mathrm{<span\; class="notranslate">\; 116</span>}}{\mathrm{<span\; class="notranslate">\; 3</span>}}<span\; class="notranslate">\; )</span><span\; class="notranslate">\; +</span>\frac{\mathrm{<span\; class="notranslate">\; 9</span>}}{\mathrm{<span\; class="notranslate">\; 47</span>}}<span\; class="notranslate">\; \&times;</span><span\; class="notranslate">\; (</span>\frac{\mathrm{<span\; class="notranslate">\; 120</span>}<span\; class="notranslate">\; +</span>\mathrm{<span\; class="notranslate">\; 133</span>}<span\; class="notranslate">\; +</span>\mathrm{<span\; class="notranslate">\; 139</span>}}{\mathrm{<span\; class="notranslate">\; 3</span>}}<span\; class="notranslate">\; )</span>$

$<span\; class="notranslate">\; +</span>\frac{\mathrm{<span\; class="notranslate">\; 25</span>}}{\mathrm{<span\; class="notranslate">\; 47</span>}}<span\; class="notranslate">\; \&times;</span><span\; class="notranslate">\; (</span>\frac{\mathrm{<span\; class="notranslate">\; 140</span>}<span\; class="notranslate">\; +</span>\mathrm{<span\; class="notranslate">\; 145</span>}<span\; class="notranslate">\; +</span>\mathrm{<span\; class="notranslate">\; 147</span>}<span\; class="notranslate">\; +</span>\mathrm{<span\; class="notranslate">\; 149</span>}<span\; class="notranslate">\; +</span>\mathrm{<span\; class="notranslate">\; 149</span>}}{\mathrm{<span\; class="notranslate">\; 5</span>}}<span\; class="notranslate">\; )</span><span\; class="notranslate">\; +</span>\frac{\mathrm{<span\; class="notranslate">\; 4</span>}}{\mathrm{<span\; class="notranslate">\; 47</span>}}<span\; class="notranslate">\; \&times;</span><span\; class="notranslate">\; (</span>\frac{\mathrm{<span\; class="notranslate">\; 190</span>}<span\; class="notranslate">\; +</span>\mathrm{<span\; class="notranslate">\; 251</span>}}{\mathrm{<span\; class="notranslate">\; 2</span>}}<span\; class="notranslate">\; )</span>$

$<span\; class="notranslate">\; =</span>\mathrm{<span\; class="notranslate">\; 142.2</span>}$

The following example 2 is the calculation embodiment of the average travel time between many stations:

From the method shown in Example 1, the average inter-station travel time of different vehicles on road section i can be obtained. On this basis, a certain method is used to analyze and obtain the average inter-station travel time of road section i. The method is shown in example 2.

Example 2: Assuming that the average inter-station travel time (unit: second) of different vehicles on road section i is obtained through statistics during non-peak hours on sunny days, as shown in the table below, the average inter-station travel time of road section i is calculated. Statistics are shown in Table 3:

Table 3 Statistical data of travel time between stations

The data of road section 1 is classified into vehicles by hierarchical clustering, and the classification results are shown in Table 4, and the corresponding vehicle numbers are in brackets:

Table 4 Results after classification

秒。From the method shown in Example 1, it can be concluded that the average inter-station travel time of road section i is

Second.

（其中k表示上述4种情况，i表示路段号）。Finally, for the four situations of sunny peak hours, sunny off-peak hours, rainy peak hours and rainy off-peak hours, the average travel time between stations of each road section in these four situations can be obtained using the above method

(where k represents the above four situations, and i represents the section number).

S63: According to the clusters of the average inter-station travel time of vehicles obtained by hierarchical clustering, the center of each cluster is calculated by the average value method, and this value is used as the average inter-station travel time of all vehicles in the cluster. Then according to the ratio of the average inter-station travel time of the vehicle to the average inter-station travel time of the road section, the driving characteristic correction factor of the vehicle is obtained.

According to the statistical results of the average travel time between stations, the analysis shows that the vehicle travel time on different road sections in the above four situations, namely, sunny peak hours, sunny off-peak hours, rainy peak hours, and rainy off-peak hours. Correction factor for driving characteristics. The analysis method is shown in example 3.

Example 3: Assuming the average inter-station travel time (unit: second) of vehicles in sunny non-peak periods obtained from historical data statistics, as shown in the table below, calculate the driving characteristic correction factor of vehicle 1 on each road section (wherein, k represents the above four situations, i represents the section number, and x represents the vehicle number). Statistics are shown in Table 5:

Table 5 Statistical data of average travel time between stations

秒。由车辆1所在聚类中心与平均站间行驶时间的比值，可以得出车辆1的一个修正因子分量为

同理分别对后面8个路段计算可以得到， ${\mathrm{\&alpha;}}_{\left(\mathrm{2,1}\right)}^2=0.641,$ ${\mathrm{\&alpha;}}_{\left(\mathrm{3,1}\right)}^2=0.839,$ ${\mathrm{\&alpha;}}_{\left(\mathrm{4,1}\right)}^2=0.907,$ ${\mathrm{\&alpha;}}_{\left(\mathrm{5,1}\right)}^2=1.013,$ ${\mathrm{\&alpha;}}_{\left(\mathrm{6,1}\right)}^2=0.664,$ ${\mathrm{\&alpha;}}_{\left(\mathrm{7,1}\right)}^2=1.087,$ ${\mathrm{\&alpha;}}_{\left(\mathrm{8,1}\right)}^2=0.908,$ ${\mathrm{\&alpha;}}_{\left(\mathrm{9,1}\right)}^2=0.875.$ From the method shown in Example 2, it can be concluded that the average inter-stop travel time of road section 1 is 261.4 seconds. At this time, the center C ₁ of cluster 1 is equal to the average value of the data in cluster 1, namely

Second. From the ratio of the cluster center where vehicle 1 is located to the average travel time between stations, a correction factor component of vehicle 1 can be obtained as

In the same way, it can be calculated for the following 8 road sections respectively, ${\mathrm{\&alpha;}}_{\left(\mathrm{2,1}\right)}^2=0.641,$ ${\mathrm{\&alpha;}}_{\left(\mathrm{3,1}\right)}^2=0.839,$ ${\mathrm{\&alpha;}}_{\left(\mathrm{4,1}\right)}^2=0.907,$ ${\mathrm{\&alpha;}}_{\left(\mathrm{5,1}\right)}^2=1.013,$ ${\mathrm{\&alpha;}}_{\left(\mathrm{6,1}\right)}^2=0.664,$ ${\mathrm{\&alpha;}}_{\left(\mathrm{7,1}\right)}^2=1.087,$ ${\mathrm{\&alpha;}}_{\left(\mathrm{8,1}\right)}^2=0.908,$ ${\mathrm{\&alpha;}}_{\left(\mathrm{9,1}\right)}^2=0.875.$

Therefore, the value of the driving characteristic correction factor of vehicle 1 is shown in Table 6.

Table 6 Correction factor of vehicle 1 in sunny non-peak conditions

The above descriptions are only preferred embodiments of the present invention, and are not intended to limit the present invention. Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalent technologies, the present invention also intends to include these modifications and variations.

Claims (6)

1. A real-time estimation method of bus arrival time based on driving characteristics, characterized in that: the following formula is used to calculate the bus arrival time:

Among them: T _ntk is the estimated time for bus k to arrive at station n from the current position at time t; T _t is the average travel time of bus vehicle from the current position to the downstream target station at time t;

is the parking delay time of vehicle x; D _p is the parking delay time of the vehicle at the signal light. 2. the bus arrival time real-time estimation method based on driving characteristics according to claim 1, is characterized in that: the average travel time _T of the bus vehicle from the current position to the downstream target site at the t moment comprises the average Estimated travel time; The estimated average travel time of the daytime bus is calculated by the following formula: $\stackrel{<span\; class="notranslate">\; \&OverBar;</span>}{{\mathrm{<span\; class="notranslate">\; T</span>}}_{\mathrm{<span\; class="notranslate">\; travel</span>}}^{\mathrm{<span\; class="notranslate">\; b</span>}}}<span\; class="notranslate">\; =</span>{\mathrm{<span\; class="notranslate">\; \&alpha;</span>}}_{<span\; class="notranslate">\; (</span>\mathrm{<span\; class="notranslate">\; j</span>}<span\; class="notranslate">\; ,</span>\mathrm{<span\; class="notranslate">\; x</span>}<span\; class="notranslate">\; )</span>}^{\mathrm{<span\; class="notranslate">\; k</span>}}\frac{\mathrm{<span\; class="notranslate">\; l</span>}}{\stackrel{<span\; class="notranslate">\; \&OverBar;</span>}{{\mathrm{<span\; class="notranslate">\; V</span>}}_{<span\; class="notranslate">\; (</span>\mathrm{<span\; class="notranslate">\; j</span>}<span\; class="notranslate">\; ,</span>\mathrm{<span\; class="notranslate">\; x</span>}<span\; class="notranslate">\; )</span>}}}<span\; class="notranslate">\; +</span>\underset{\mathrm{<span\; class="notranslate">\; i</span>}<span\; class="notranslate">\; =</span>\mathrm{<span\; class="notranslate">\; j</span>}<span\; class="notranslate">\; +</span>\mathrm{<span\; class="notranslate">\; 1</span>}}{\overset{\mathrm{<span\; class="notranslate">\; no</span>}}{\mathrm{<span\; class="notranslate">\; \&Sigma;</span>}}}\frac{{\mathrm{<span\; class="notranslate">\; \&alpha;</span>}}_{<span\; class="notranslate">\; (</span>\mathrm{<span\; class="notranslate">\; j</span>}<span\; class="notranslate">\; ,</span>\mathrm{<span\; class="notranslate">\; x</span>}<span\; class="notranslate">\; )</span>}^{\mathrm{<span\; class="notranslate">\; k</span>}}{\mathrm{<span\; class="notranslate">\; L</span>}}_{\mathrm{<span\; class="notranslate">\; i</span>}}}{\stackrel{<span\; class="notranslate">\; \&OverBar;</span>}{{\mathrm{<span\; class="notranslate">\; V</span>}}_{<span\; class="notranslate">\; (</span>\mathrm{<span\; class="notranslate">\; i</span>}<span\; class="notranslate">\; ,</span>\mathrm{<span\; class="notranslate">\; x</span>}<span\; class="notranslate">\; )</span>}}}<span\; class="notranslate">\; ;</span>$ in,

To correct the average travel time, is the interval average speed of the section j between the vehicle and the nearest station;

is the average speed of section i; j is the current section of the vehicle; L _i is the length of section i; n is a section in front of the target station;

is the correction factor for the driving characteristics of vehicle x on road section i in case k. Interval average speed for the section in question

is calculated by the following steps: First divide the road section by station, obtain the station information and driving direction information in the GPS data, and then obtain the data of all floating cars in the same direction as the estimated average travel time in the road section within this time period, and finally obtain the data from the floating car data Take the average speed of the road section

3. the bus arrival time real-time estimation method based on driving characteristics according to claim 1, is characterized in that: the average travel time T of the bus vehicle from the current position to the downstream target site at the t moment _also includes the time of the night bus Average travel time estimates; The average travel time estimation of described night bus comprises short-distance target station average travel time estimation and long-distance target station average travel time estimation; The estimated average travel time of the short-distance target station is calculated by the following formula: $\stackrel{<span\; class="notranslate">\; \&OverBar;</span>}{{\mathrm{<span\; class="notranslate">\; T</span>}}_{\mathrm{<span\; class="notranslate">\; travel</span>}}^{\mathrm{<span\; class="notranslate">\; no</span>}}}<span\; class="notranslate">\; =</span>\frac{{\mathrm{<span\; class="notranslate">\; L</span>}}_{\mathrm{<span\; class="notranslate">\; d</span>}}}{\stackrel{<span\; class="notranslate">\; \&OverBar;</span>}{\mathrm{<span\; class="notranslate">\; V</span>}}}<span\; class="notranslate">\; ;</span>$ in,

is the average travel time of the night bus to the downstream target site, L _d represents the distance between the vehicle and the target site determined by the vehicle mileage information in the GPS data,

Indicates the average speed during the time period; The estimated average travel time of the long-distance target station is calculated by the following formula: $\stackrel{<span\; class="notranslate">\; \&OverBar;</span>}{{\mathrm{<span\; class="notranslate">\; T</span>}}_{\mathrm{<span\; class="notranslate">\; travel</span>}}^{\mathrm{<span\; class="notranslate">\; no</span>}}}<span\; class="notranslate">\; =</span>\frac{\mathrm{<span\; class="notranslate">\; 1</span>}}{\stackrel{<span\; class="notranslate">\; \&OverBar;</span>}{\mathrm{<span\; class="notranslate">\; V</span>}}}<span\; class="notranslate">\; +</span>\underset{\mathrm{<span\; class="notranslate">\; i</span>}<span\; class="notranslate">\; =</span>\mathrm{<span\; class="notranslate">\; j</span>}}{\overset{\mathrm{<span\; class="notranslate">\; no</span>}}{\mathrm{<span\; class="notranslate">\; \&Sigma;</span>}}}{\mathrm{<span\; class="notranslate">\; t</span>}}_{<span\; class="notranslate">\; (</span>\mathrm{<span\; class="notranslate">\; i</span>}<span\; class="notranslate">\; ,</span>\mathrm{<span\; class="notranslate">\; r</span>}<span\; class="notranslate">\; )</span>}^{\mathrm{<span\; class="notranslate">\; k</span>}}<span\; class="notranslate">\; ;</span>$ Among them, n is the previous road section of the target site; j is the next road section that the vehicle will arrive at;

is the average inter-station travel time required for the vehicle to pass through road section i in case k, and l is the distance between the vehicle and the nearest station. the average speed

Calculated by the following formula: $\stackrel{<span\; class="notranslate">\; \&OverBar;</span>}{\mathrm{<span\; class="notranslate">\; V</span>}}<span\; class="notranslate">\; =</span>\frac{\mathrm{<span\; class="notranslate">\; 1</span>}}{\mathrm{<span\; class="notranslate">\; m</span>}}\underset{\mathrm{<span\; class="notranslate">\; i</span>}<span\; class="notranslate">\; =</span>\mathrm{<span\; class="notranslate">\; 1</span>}}{\overset{\mathrm{<span\; class="notranslate">\; m</span>}}{\mathrm{<span\; class="notranslate">\; \&Sigma;</span>}}}{\mathrm{<span\; class="notranslate">\; v</span>}}_{\mathrm{<span\; class="notranslate">\; i</span>}}<span\; class="notranslate">\; ;</span>$ Among them, M is the number of valid GPS data of the vehicle collected, and v _i is the corresponding speed of each vehicle in the GPS data. 4. The bus arrival time real-time estimation method based on driving characteristics according to claim 1, characterized in that: the stop delay time of the vehicle x

Calculated by the following formula: $\stackrel{<span\; class="notranslate">\; \&OverBar;</span>}{{\mathrm{<span\; class="notranslate">\; D.</span>}}_{\mathrm{<span\; class="notranslate">\; x</span>}}}<span\; class="notranslate">\; =</span>{\mathrm{<span\; class="notranslate">\; D.</span>}}_{\mathrm{<span\; class="notranslate">\; b</span>}}<span\; class="notranslate">\; +</span>\underset{\mathrm{<span\; class="notranslate">\; i</span>}<span\; class="notranslate">\; =</span>\mathrm{<span\; class="notranslate">\; j</span>}}{\overset{\mathrm{<span\; class="notranslate">\; no</span>}}{\mathrm{<span\; class="notranslate">\; \&Sigma;</span>}}}{\mathrm{<span\; class="notranslate">\; t</span>}}_{<span\; class="notranslate">\; (</span>\mathrm{<span\; class="notranslate">\; i</span>}<span\; class="notranslate">\; ,</span>\mathrm{<span\; class="notranslate">\; the\; s</span>}<span\; class="notranslate">\; )</span>}^{\mathrm{<span\; class="notranslate">\; k</span>}}<span\; class="notranslate">\; ;</span>$ Among them, n is the previous station of the target station; j is the downstream station closest to the current position of the vehicle;

is the average residence time of vehicles at station i in case k; The average stop time of each station in different time periods

Calculated by the following formula: D _b =αT ₀ +βT ₁ +γT ₂ ; Among them: α, β, γ are the time correction coefficients; T ₀ is the time to decelerate and approach the station; T ₁ is the time to board and unload passengers at the stop; T ₂ is the time to accelerate to leave the station. 5. the bus arrival time real-time estimation method based on driving characteristic according to claim 1, is characterized in that: described vehicle stops and delays _D at signal light place and calculates by the following steps: S51: use the GPS data to obtain the positioning position and instantaneous speed of the bus in real time; S52: Determine whether the bus vehicle is already in the signal light area; S53: According to the driving state of the vehicle, calculate the staying time of the vehicle at the current traffic light position by the following formula: S54: When the vehicle encounters a red light, the sum of the parking delay time from the current position to the estimated stop time of all signal lights between the stations is ${\mathrm{D.}}_p=\underset{p=1}{\overset{q}{\mathrm{\&Sigma;}}}\underset{x=1}{\overset{m}{\mathrm{\&Sigma;}}}P\left(x\right)T_{\mathrm{px}};$ S55: When the vehicle encounters a green light, the sum of the parking delay time from the next signal light at the current position to the estimated stop time of all signal lights between stations is ${\mathrm{D.}}_p=\underset{p=2}{\overset{q}{\mathrm{\&Sigma;}}}\underset{x=1}{\overset{m}{\mathrm{\&Sigma;}}}P\left(x\right)T_{\mathrm{px}};$ S56: When the vehicle is not in the signal light area, the sum of the parking delay time from the current position to all signal lights between stations is estimated to be ${\mathrm{D.}}_p=\underset{p=1}{\overset{q}{\mathrm{\&Sigma;}}}\underset{x=1}{\overset{m}{\mathrm{\&Sigma;}}}P\left(x\right)T_{\mathrm{px}};$ Among them, P(x) represents the probability distribution of x vehicles arriving at the signal light area during the time interval length t, T _px is the random delay time of the vehicle parking at the signal light p, and M is the time at the signal light p within a cycle Vehicle arrivals. 6. the bus arrival time real-time estimation method based on driving characteristic according to claim 1, is characterized in that: described driving characteristic correction factor

Obtained by the following steps: S61: Obtain vehicle site information and station entry and exit information in the GPS data; S62: Calculate the average travel time between stations; S63: The ratio of the center of the cluster where the vehicle is located to the average travel time between stations after being classified according to the average travel time between stations is the driving characteristic correction factor of the vehicle.

Images