CN107705591A - A kind of tramcar and the cooperative control method of social wagon flow - Google Patents

Abstract

The invention discloses a method for coordinated control of trams and social traffic flow, which comprises the following steps: (1) collection of road traffic basic data and determination of signal common periods, (2) setting and activation of detectors, (3) arrival After the detector detects the tram, the signal control machine generates a tram priority application, and adjusts the signal timing scheme according to the coordinated control method of the tram and the social traffic flow. open. This technical solution combines the technologies of forecasting, signal priority, and coordinated control to ensure that trams continue to pass preferentially at intersections, and at the same time make the delay of social vehicles at intersections as small as possible.

Description

A collaborative control method for trams and social traffic flow

technical field

The invention belongs to the technical field of bus signal control, is used for a tram system, and relates to a coordinated control method for a tram and social traffic flow considering the stop time of modern trams.

Background technique

Beginning in France in the 1990s, modern trams have gradually become popular as an efficient and clean form of public transportation, but trams need sufficient time and space right of way to ensure their driving efficiency and service level. In recent years, no matter in the field of scientific research or patent application, there are few methods involving tram signal priority, and very few of the methods involved are mainly active signal priority, giving trams a priority range Limited and lack of coordination with other modes of transportation will have a negative impact on the traffic of social vehicles, and this phenomenon is more obvious when the saturation is high. The present invention is produced under such background.

Contents of the invention

The present invention is to solve the problem of relatively large errors in thickness measurement of ground-coupled antennas, and provides a coordinated control method for trams and social traffic flow based on the principle of electromagnetic wave superposition, which provides an important basis for non-destructive testing of highways.

In order to achieve the above-mentioned purpose of the invention, the present invention adopts the following technical solutions: a coordinated control method for trams and social traffic flow, characterized in that the control method includes the following steps:

(1) Acquisition of road traffic basic data and determination of signal public cycle,

(2) Detector setup and activation,

(3) After the tram is detected by the arrival detector, the signal control machine generates a tram priority application, and adjusts the signal timing scheme according to the coordinated control method of the tram and the social traffic flow,

(4) Closing and opening of the tram arrival detector; the coordinated road section implements the optimized signal control scheme, which will temporarily close the tram arrival detector, and end the vehicle when the detector detects that the tram has left the coordination road section. The priority coordinated control process of the signal of the tram is restored to the original control scheme. At this time, the arrival detector of the tram is restarted, waiting for the signal priority of the next tram to be controlled. If the tram is detected again will re-enter step (3).

As a kind of improvement of the present invention, described step (1) is specifically as follows, this step adopts Webster's formula to calculate signal cycle, and gets maximum cycle in each crossing as the common cycle of coordinated control;

L= _∑I (l+IA);

The cycle duration (s) calculated by the C-Webster formula;

L-cycle loss time (s);

Y-intersection total flow ratio;

A- yellow light time (s);

I-green light interval time (s);

l- start-up loss time (s), look up the table;

y _i ＝max _j (q _ij /S _ij ), the flow ratio of the i-th phase;

q _ij – the hourly traffic flow of the jth lane in the ith phase;

S _ij - the traffic capacity of the jth lane of the i-th phase, obtained from the basic traffic capacity;

Through correlation analysis, the road traffic basic data required by the program include as follows: the number of lanes N _ij of each intersection and the prescribed lane directions include straight, left, right, straight left, straight right, left straight right, Static data such as left and right turns, distance l _ij of adjacent intersections, flow direction data of intersections (saturation of each entrance y _i ), signal timing status (yellow light time A, phase number i in one cycle, Dynamic data such as green light interval time I) and vehicle stop time series y, the actual arrival time of the tram x1, the number of people on board x2, the number of people getting off x3, the headway distance from the last incoming tram x4, the tram Length L _tr , intersection clearing distance L _d , tram speed Vtr and other data.

As an improvement of the present invention, the setting and activation of the detectors in step (2) are specifically as follows, the tram arrival detector is arranged at the upstream entrance of the coordinated control section, and the tram is arranged at the downstream exit of the coordinated control section After leaving the detector, when the first tram passes the departure detector, the arrival detector of the tram is activated and is in a state capable of receiving subsequent tram priority applications.

As an improvement of the present invention, in the step (3), after the arrival detector detects the tram, the signal control machine generates a tram priority application, and signals according to the coordinated control method of the tram and the social traffic flow. Timing scheme adjustment, when the detector detects a tram, the signal control machine generates a tram priority application, as follows;

31) Tram stop time prediction: the "tram stop time" in this invention is predicted based on SVM (Support Vector Machine), which can be operated by software such as C++;

32) Signal coordination optimization scheme: Through the prediction of the stop time of the tram station in 31), the time when the tram arrives at the stop line at the intersection can be obtained on this basis, and then the green light at the intersection can be obtained based on the nested algorithm combined with the arrival rate of social vehicles Time and phase difference and other parameters, and determine the signal coordination optimization scheme according to the "green light time and phase difference" index.

As an improvement of the present invention, the prediction of the stop time of the tram station in step (31) is specifically as follows, the prediction process of the time when the tram arrives at the stop line is simplified, and the main prediction is the stop time of the tram at the platform, that is, the time caused by the stop For the duration of abnormal driving, considering the stop time of trams and the characteristics of the tram system itself, the interaction between trams and passengers presents a nonlinear relationship, based on the SVM model design algorithm for nonlinear regression, the program uses polynomial kernel function algorithm , based on this algorithm to realize the prediction of the stop time; and based on this, predict the time when the tram arrives at the intersection;

The algorithm is as follows:

Among them, f(x) is a nonlinear regression function, with is the Lagrangian undetermined coefficient, which can be obtained by formula (3), SV _s represents the set of support vector machines, and ε is the insensitivity coefficient;

Among them, y is the sample sequence, which is the original sequence of the collected vehicle stop time, l is the number of support vectors, x=(x ₁ , x ₂ , x ₃ , x ₄ ) is the attribute variable, which is closely related to the tram stop time , are the actual arrival time of the tram, the number of people boarding, the number of people getting off, and the headway distance from the last incoming tram, all of which can be obtained through follow-up surveys.

As an improvement of the present invention, a nested algorithm is used in the step (32) to determine the duration of the green light and the phase difference, and the module one takes the minimum stop of the tram in the coordination section as the goal, and takes this goal as a new constraint into Module 2, that is, the minimum total delay of the control section is the optimization goal, which ensures that the trams continue to pass through the intersections and at the same time makes the delay of social vehicles at the intersections as small as possible;

Module 1: Green Wave Passage of Trams;

To realize the coordinated control of trams, the ideal state is that the trams can pass through the target section without stopping. Therefore, the objective function of module 1 is to minimize the accumulative parking times S _all of the trams applying for priority in the target section , the corresponding algorithm is as follows:

in, is the time when the green light of the tram passing phase at the jth intersection is turned on, o _j is the absolute phase difference of the jth intersection, a is a positive integer, and C is the duration of the public cycle of coordinated control;

is the time when the tram arrives at the jth intersection;

t _emp = (L _tr +L _d )/v _tr is the clearing time for the tram to cross the intersection; is the green time of the i-th phase of the j-th intersection, is the shortest green light time of the i-th phase of the j-th intersection, q _ij is the single-period traffic flow of the j-th intersection in the i-th phase, S _ij is the lane saturation flow rate of the j-th intersection in the i-th phase;

Formula (5) and formula (6) are solved by the integer space particle swarm optimization algorithm, and the solution result is brought into module 2 as a new constraint condition;

Module 2: Timing optimization based on expected delay;

The signal of trams gives priority to the passage time of vehicles occupying other phases. In order to ensure the right of way of trams, the signal timing should minimize the delay of passage of vehicles in other phases. The algorithm is as follows:

in, u _ij is the arrival rate of the jth phase of the i-th intersection after considering the influence of the upstream intersection;

The signal phase timing and phase difference of each intersection satisfying the objective function can be obtained by using the particle swarm optimization algorithm in the integer space.

Compared with the prior art, the beneficial effects of the present invention are as follows, (1) the present invention is a new attempt in the field of tram signal control, combining the techniques of forecasting, signal priority, and coordinated control to ensure that the tram While trams continue to give priority to passage between intersections, the delay of social vehicles at the intersection is minimized as much as possible, taking into account the interests of many aspects, and the intention is to make the system obtain the best implementation effect; (2) the method of the present invention does not require additional road reconstruction And infrastructure investment, so its capital investment is small, the financial requirements of the city are not high, and the operability of the invention is very strong.

Description of drawings

Fig. 1 is the flowchart of the inventive method;

Fig. 2 is a map of road information and dynamic data;

Figure 3 is a schematic diagram of the solution target.

detailed description

In order to deepen the knowledge and understanding of the present invention, the present invention will be further described below in conjunction with the accompanying drawings and specific embodiments.

Referring to Fig. 1-Fig. 3, as shown in Fig. 1, it is a flow chart of a coordinated control method for trams and social traffic flows, which will be further described in conjunction with examples below.

(1) Acquisition of road traffic basic data and determination of signal public cycle;

The present invention first uses Webster's formula to calculate the signal cycle, and takes the largest cycle in each intersection as the common cycle of coordinated control.

Cycle duration calculated by C-Webster formula (s)

L-cycle loss time (s)

Y-intersection total flow ratio

A-yellow light time (s)

I-green light interval time (s)

l- start-up loss time (s), look up the table to get

y _i ＝max _j (q _ij /S _ij ), the flow ratio of the i-th phase

q _ij – the hourly traffic flow of the jth lane in the ith phase

S _ij - the traffic capacity of the j-th lane in the i-th phase, obtained from the basic traffic capacity.

By correlation analysis, the required road traffic basic data of this invention comprises as follows: each intersection lane number N _ij and the lane direction of regulation (going straight, turning left, turning right, straight left, straight right, left straight right, turn left and right), the distance between adjacent intersections l _ij and other static data, the flow direction data of the intersection (saturation of each entrance y _i ), signal timing status (yellow light time A, phase number i in a cycle , green light interval time I) and other dynamic data and vehicle stop time series y, the actual arrival time of the tram x1, the number of people on the bus x2, the number of people getting off the bus x3, the headway distance from the last incoming tram x4, the tram Tram length L _tr , intersection clearance distance L _d , tram speed Vtr and other data.

In this example, the number of lanes N _ij of each intersection and the direction of the specified lanes (go straight, turn left, turn right, go straight left, go straight right, go straight left, go right, turn left), distance between adjacent intersections l _ij , intersection The flow direction data at the entrance (saturation y _i of each entrance), signal timing status (yellow light time A, phase number i in a cycle, green light interval time I), and tram length L _tr can be taken on-site investigation Obtained by the method; vehicle stop time series y, actual time of tram arrival x1, number of people on board x2, number of people getting off x3, headway distance from the last incoming tram x4, tram speed Vtr, etc. can be obtained by camera Acquisition by means of a video camera, that is, relevant video is collected by a camera, and the video information is processed by a special video processing software (for example, Adobe's PremierePro 2.0) to obtain the required data.

(2) Detector setup and activation:

The tram arrival detector is arranged at the upstream entrance of the coordination control section, and the tram departure detector is arranged at the downstream exit of the coordination control section. When the first tram passes the departure detector, the tram arrival detector Activated, in the state of being able to receive subsequent tram priority applications, the position of the detector is shown in Figure 2.

Note that the layout of the tram arrival detector should keep a certain distance from the stop site and the intersection, so as to avoid the impact of the overflow of the tram queuing.

(3) After the tram is detected by the arrival detector, the signal control machine generates a tram priority application, and adjusts the signal timing scheme according to the coordinated control method of the tram and the social traffic flow,

When the detector detects a tram, the signal control machine generates a tram priority application, as follows:

31) Tram stop time prediction: the "tram stop time" in this invention is predicted based on SVM (Support Vector Machine), which can be operated by software such as C++;

32) Signal coordination optimization scheme: Through the prediction of the stop time of the tram station in 1), the time when the tram arrives at the stop line at the intersection can be obtained on this basis, and then the green light at the intersection can be obtained based on the nested algorithm combined with the arrival rate of social vehicles Time and phase difference and other parameters, and determine the signal coordination optimization scheme according to the "green light time and phase difference" index.

(4) Closing and opening of the tram arrival detector;

The coordinated road section implements the optimized signal control scheme, and the tram arrival detector will be temporarily turned off. After the detector detects that the tram has left the coordinated road section, the signal priority coordinated control process of this tram is ended, and the tram arrives. Detector restarts, waits to enter the signal priority cooperative control of next streetcar, if the arrival of streetcar is detected again, can enter step (3) again.

By adjusting the intersection signal timing according to the above method, a coordinated control method of trams and social traffic flow can be obtained, which can realize the priority of trams and minimize the delay of social vehicles at the intersection as much as possible.

Application example: In order to verify the effectiveness of the present invention, the present invention will be further described below in conjunction with the actual survey data and VISSIM of a certain city's tram.

Assume that a certain arterial road has 5 intersections sequentially, numbered 1, 2, 3, 4, 5 in sequence. This area contains signal priority coordination control intersections: Tongjiang-Taihu Road intersection (2), Tongjiang-Longjin Road intersection (3) and Tongjiang-Longcheng Road intersection (4), while 1 and 5 intersections As a transitional intersection for coordinated control, various indicators are not included in the statistics to offset the impact of the upstream intersection on the control effect. As shown in Figure 2:

(1) Through the collection of basic data, the results obtained are as follows:

Information such as the signal cycle, phase scheme, intersection channelization, intersection distance, specific location of bus stops, and flow direction of each intersection of major intersections in the collaborative priority control area is shown in Figure 2;

(2) Effect analysis;

In order to verify the effect of the present invention, the coordinated control method under the tram priority condition is compared with the original signal timing and the static two-way green wave control method that only considers social vehicles, that is to say, each signal timing method is in The effect analysis corresponds to a type of signal timing strategy, which is the actual signal timing control. The timing data is shown in Figure 2. The traditional static two-way green wave, that is, the public signal period is determined by Webster's formula, and then according to the flow rate of each phase Finally, the phase difference between intersections satisfying the maximum green wave bandwidth of social vehicles is solved by numerical solution method, and a coordinated control method of trams and social traffic flows proposed by the present invention.

Traffic demand fluctuations are often encountered in actual engineering, so the invention is not limited to optimizing the traffic efficiency under the current flow rate. In order to further test the stability of the signal control effect of the method of the present invention under different traffic volumes, the above three signal Five traffic levels are set under the timing strategy, which are 80%, 90%, 100%, 110% and 120% of the original traffic. That is to say, in this effect analysis, a total of 3 signal control strategies are constructed, and each strategy tests 5 traffic conditions. The specific settings of the effect analysis are shown in Table 1.

Table 1 Signal Timing Strategy Design

The driving speed of the vehicle is an important parameter to estimate the time when the vehicle reaches the stop line, so as to realize the signal control through the nested algorithm. The input of the vehicle speed in VISSIM is defined in the form. On urban roads, due to the influence of signal control, the arrival rate of traffic flow to the downstream intersection is not uniform. Therefore, in the effect analysis, the upstream of the signal coordination section is equipped with transitional signal lights to ensure the appearance of the convoy. Therefore, it is closer to the actual situation of traffic operation, and these intersections will not be included in the final index statistics, such as intersections 1 and 5 in Figure 2.

The stop time of the tram at the platform has an important influence on the effect of signal priority. The effect analysis sets different passenger arrival rates in different time intervals to ensure that the number of passengers carried by the tram is consistent with the observation data in Table 1, so as to infer the stop process of the tram at the platform. Another important factor affecting the tram stop time and arrival time at the intersection is the moment when the vehicle enters the signal coordination section. The survey collects the time of trams entering the signal coordination section through video, and enters these times into the effect analysis system in the form of a timetable, that is, each car corresponds to a time of entering the effect analysis system.

The entire effect analysis time is 3600s, and the corresponding real time period is the evening peak of the research area from 17:15 to 18:15. In Table 1, 10 effect analyzes are carried out for each flow condition of each scenario, and different random seeds are used for each effect analysis.

(3) Results of effect analysis;

(31) Analysis of the prediction results of the stop time of the tram platform;

There are 4 stations in the coordinated control section that affect the prediction of the time when the tram arrives at the stop line, which have been marked in Figure 2. Since the stop time prediction of the tram is related to its own characteristics, the present invention uses the relevant data of the tram Yuantong Station in Hexi District, Nanjing to calibrate the penalty factor E, insensitivity coefficient ε and kernel function parameters based on the SVM model algorithm. γ, and then bring the attribute vectors of the four stations in the research section into the regression function to predict the stop time of the tram. The stop time y of the tram at Yuantong Station and the related attribute vector x=(x ₁ , x ₂ , x ₃ , x ₄ ), the sample size is 115. Among them, x ₁ ~ x ₄ are attribute variables, which are closely related to the stop time of the tram. Here, they are the actual arrival time of the tram, the number of people getting on the bus, the number of people getting off the bus, and the headway distance from the last tram that entered the station. The parameter calibration results are: E=24.619, ε=0.4972, γ=0.9997. The average relative percentage error (MAPE) and mean square error (MSE) of the algorithm are 8.12% and 37.58s ² respectively, both of which are relatively small, which proves that the prediction effect of the algorithm based on the SVM model is relatively reliable, and it is also a good example for the prediction The arrival time of trams at intersections and the coordinated control scheme of setting signal priority provide a sufficient basis.

(32) Impact on trams;

Minimizing the unnecessary stay time and parking times of trams on the road section is the main goal of improving its operating efficiency. Therefore, the delay and parking rate are the main evaluation indicators for the coordinated signal priority control of trams. One of the strongest and most effective arguments for the tram signal priority control strategy. According to the evaluation index output by VISSIM, the flow sensitivity results of the three control strategies are shown in Table 2.

Overall, under the current flow conditions, the static two-way green wave control did not take into account the differences in the driving characteristics of trams and social vehicles, but caused greater travel delays for trams in the study section, while The tram parking rate has only slightly improved compared to the original situation. After implementing the coordinated control method of trams and social traffic flow, the travel delay and parking rate of trams are greatly reduced by 76.46% and 95.05%.

What is more noteworthy is that it is easy to find out through the flow sensitivity that the actual signal timing control and the traditional static two-way green wave belong to the static timing method, so the running index of the tram does not change due to the change of the road traffic, and is always in the lower level. The signal control strategy of the present invention can significantly reduce the travel delay of trams by more than 77% no matter what the saturation is, and correspondingly, the parking rate is also sharply reduced by more than 90% compared with the current signal control scheme. This fully proves the strict goal of Module 1, that is, the trams that apply for priority should stop and pass as few times as possible in the target section, which is of great significance to improving the efficiency of tram traffic, and also indirectly verifies the accuracy of tram stop time prediction. Accuracy and outstanding contribution to this control algorithm.

Table 2 Various indicators of trams under different signal control strategies

(33) Impact on social traffic flow

The original intention of giving tram signal priority is not to sacrifice the right of passage of social vehicles, so it is necessary to make statistics on the driving indicators of social vehicles to evaluate the impact of signal priority algorithm on social vehicles. The invention not only counts the delays of social vehicles at each node, but also analyzes the average queue length of each node in consideration of the constraints of the intersection road geometry. The results are shown in Table 3.

Table 3 Various indicators of social vehicles under different signal control strategies

Note: 1 represents the average value of the delay generated by vehicles traveling from intersection 2 to intersection 4 in the target section of coordinated control, that is, in Figure 2.

** indicates that the index has dropped by more than 50% compared with the current situation, indicating that the control method can significantly improve the driving efficiency of the vehicle.

*Indicates that the index has decreased by 20% to 50% relative to the current situation, indicating that the control method has a certain effect on improving the efficiency of vehicle traffic.

From the perspective of delay and parking rate indicators, under the current traffic conditions, the traditional static two-way green wave only reduces the vehicle delay and parking rate by about 20%, while the coordinated control method of trams and social traffic not only greatly reduces the north-south The delay of trams in this direction, the driving efficiency of social vehicles in this direction is also greatly improved, and its delay and parking rate are further reduced by 74.49% and 73.06% compared with the static two-way green wave.

Under normal circumstances, vehicles passing during non-green waves are susceptible to interference from coordinated control. Under current traffic conditions, the static two-way green wave strategy not only failed to significantly improve the traffic efficiency of social vehicles, but increased its delay and parking at some intersections. Rate. In contrast, although the coordinated control method of trams and social traffic flow cannot guarantee that vehicles in all phases can travel as efficiently as vehicles passing through the green wave period, it can still make the average delay and parking rate of each intersection relatively Significantly decreased from the current situation.

Efficient control of traffic flow under different saturations is the embodiment of the superiority and robustness of the signal control algorithm. Comparing the vehicle operation indicators under different flow ratios, it is easy to find that with the increase of flow, the delay reduction value of vehicles passing in the north-south direction due to the static two-way green wave presents a gradual decline trend, and the delay and queuing at each intersection in the section Length was also mostly negatively affected. Although the increase in traffic flow has also affected the delay reduction of vehicles in the north-south direction under the control of the coordinated control method of trams and social traffic flow, under various saturation levels, the coordinated control method of trams and social traffic flow It can still provide much higher traffic efficiency than the static two-way green wave.

The above-mentioned large number of evaluation indicators have proved the great advantages of the coordinated control method of trams and social traffic flow in giving priority to trams with strong signals while reducing interference to other social vehicles. The multi-flow sensitivity test also shows that this The stability and robustness of the method to deal with different traffic flow saturation.

The above is only a preferred embodiment of the present invention, it should be pointed out that for those of ordinary skill in the art, without departing from the principle of the present invention, some predictable improvements and modifications can also be made, these improvements And retouching should also be regarded as the protection scope of the present invention.

Claims (6)

1. a coordinated control method of streetcar and social traffic flow, it is characterized in that, described control method comprises the steps: (1) Acquisition of road traffic basic data and determination of signal public cycle, (2) Detector setup and activation, (3) After the tram is detected by the arrival detector, the signal control machine generates a tram priority application, and adjusts the signal timing scheme according to the coordinated control method of the tram and the social traffic flow, (4) Closing and opening of the tram arrival detector; the coordinated road section implements the optimized signal control scheme, which will temporarily close the tram arrival detector, and end the vehicle when the detector detects that the tram has left the coordination road section. The priority coordinated control process of the signal of the tram is restored to the original control scheme. At this time, the arrival detector of the tram is restarted, waiting for the signal priority of the next tram to be controlled. If the tram is detected again will re-enter step (3). 2. a kind of streetcar according to claim 1 and the cooperative control method of social traffic flow, it is characterized in that, step (1) is specifically as follows, this step adopts Webster's formula to calculate signal period, and gets the maximum in each crossing cycle as a public cycle for coordinated control; <mrow><mi>C</mi><mo>=</mo><mfrac><mrow><mn>1.5</mn><mi>L</mi><mo>+</mo><mn>5</mn></mrow><mrow><mn>1</mn><mo>-</mo><mi>Y</mi></mrow></mfrac><mo>;</mo></mrow> L= _∑I (l+IA); <mrow><mi>Y</mi><mo>=</mo><msubsup><mo>&amp;Sigma;</mo><mrow><mi>i</mi><mo>=</mo><mn>1</mn></mrow><mi>n</mi></msubsup><msub><mi>y</mi><mi>i</mi></msub><mo>;</mo></mrow> The cycle duration (s) calculated by the C-Webster formula; L-cycle loss time (s); Y-intersection total flow ratio; A- yellow light time (s); I-green light interval time (s); l- start-up loss time (s), look up the table; y _i ＝max _j (q _ij /S _ij ), the flow ratio of the i-th phase; q _ij – the hourly traffic flow of the jth lane in the ith phase; S _ij - the traffic capacity of the jth lane of the i-th phase, obtained from the basic traffic capacity; Through correlation analysis, the road traffic basic data required by the program include as follows: the number of lanes N _ij of each intersection and the prescribed lane directions include straight, left, right, straight left, straight right, left straight right, Static data such as left and right turns, distance l _ij of adjacent intersections, flow direction data of intersections (saturation of each entrance y _i ), signal timing status (yellow light time A, phase number i in one cycle, Dynamic data such as green light interval time I) and vehicle stop time series y, the actual arrival time of the tram x1, the number of people on board x2, the number of people getting off x3, the headway distance from the last incoming tram x4, the tram Length L _tr , intersection clearing distance L _d , tram speed Vtr and other data. 3. A kind of coordinated control method of tramcar and social traffic flow according to claim 2, it is characterized in that, the setting and activation of detector in the step (2) are specifically as follows, at the upstream entrance of the coordinated control section, there is arranged The tram arrival detector is arranged at the downstream exit of the coordinated control section. When the first tram passes the departure detector, the tram arrival detector is activated and is in the position of being able to receive subsequent trams. Priority application status. 4. according to claim 2 or 3 described a kind of coordinated control method of streetcar and social vehicle flow, it is characterized in that, in described step (3), after arrival detector detects streetcar, signal control machine generates Tram priority traffic application, according to the coordinated control method of tram and social traffic flow to adjust the signal timing plan, When the detector detects a tram, the signal control machine generates a tram priority application, as follows: 31) Tram station stop time prediction: 32) Signal coordination optimization scheme: Through the prediction of the stop time of the tram station in 31), the time when the tram arrives at the stop line at the intersection can be obtained on this basis, and then the green light at the intersection can be obtained based on the nested algorithm combined with the arrival rate of social vehicles Time and phase difference and other parameters, and determine the signal coordination optimization scheme according to the "green light time and phase difference" index. 5. a kind of streetcar according to claim 4 and the coordinated control method of social traffic flow, it is characterized in that, in the step (31), the stop time prediction of the tram station is specifically as follows, the time when the tram arrives at the stop line The prediction process is simplified, mainly predicting the stop time of the tram at the platform, that is, the duration of abnormal driving caused by the stop. The program uses a polynomial kernel function algorithm, based on which the prediction of the stop time is realized; the time when the tram arrives at the intersection; The algorithm is as follows: <mrow><mi>f</mi><mrow><mo>(</mo><mi>x</mi><mo>)</mo></mrow><mo>=</mo><munder><mo>&amp;Sigma;</mo><mrow><mi>S</mi><mi>V</mi><mi>s</mi></mrow></munder><mrow><mo>(</mo><mover><msub><mi>&amp;alpha;</mi><mi>i</mi></msub><mo>-</mo></mover><mo>-</mo><mover><msubsup><mi>&amp;alpha;</mi><mi>i</mi><mo>*</mo></msubsup><mo>-</mo></mover><mo>)</mo></mrow><mi>K</mi><mrow><mo>(</mo><msub><mi>x</mi><mi>i</mi></msub><mo>,</mo><mi>x</mi><mo>)</mo></mrow><mo>-</mo><mo>-</mo><mo>-</mo><mrow><mo>(</mo><mn>1</mn><mo>)</mo></mrow><mo>;</mo></mrow> <mrow><msub><mi>L</mi><mi>&amp;epsiv;</mi></msub><mrow><mo>(</mo><mi>N</mi><mo>)</mo></mrow><mo>=</mo><mfenced open = "{" close = ""><mtable><mtr><mtd><mn>0</mn></mtd><mtd><mrow><mo>|</mo><mi>f</mi><mrow><mo>(</mo><msub><mi>x</mi><mi>i</mi></msub><mo>)</mo></mrow><mo>-</mo><msub><mi>N</mi><mi>i</mi></msub><mo>|</mo><mo>-</mo><mi>&amp;epsiv;</mi><mo>&lt;</mo><mn>0</mn></mrow></mtd></mtr><mtr><mtd><mrow><mo>|</mo><mi>f</mi><mrow><mo>(</mo><msub><mi>x</mi><mi>i</mi></msub><mo>)</mo></mrow><mo>-</mo><msub><mi>N</mi><mi>i</mi></msub><mo>|</mo><mo>-</mo><mi>&amp;epsiv;</mi></mrow></mtd><mtd><mrow><mo>|</mo><mi>f</mi><mrow><mo>(</mo><msub><mi>x</mi><mi>i</mi></msub><mo>)</mo></mrow><mo>-</mo><msub><mi>N</mi><mi>i</mi></msub><mo>|</mo><mo>-</mo><mi>&amp;epsiv;</mi><mo>&gt;</mo><mo>=</mo><mn>0</mn></mrow></mtd></mtr></mtable></mfenced><mo>-</mo><mo>-</mo><mo>-</mo><mrow><mo>(</mo><mn>2</mn><mo>)</mo></mrow><mo>;</mo></mrow> Among them, f(x) is a nonlinear regression function, with is the Lagrangian undetermined coefficient, which can be obtained by formula (3), SV _s represents the set of support vector machines, and ε is the insensitivity coefficient; <mrow><munder><mi>max</mi><mrow><mi>&amp;alpha;</mi><mo>,</mo><msup><mi>&amp;alpha;</mi><mo>*</mo></msup></mrow></munder><mi>W</mi><mrow><mo>(</mo><mi>&amp;alpha;</mi><mo>,</mo><msup><mi>&amp;alpha;</mi><mo>*</mo></msup><mo>)</mo></mrow><mo>=</mo><munder><mi>max</mi><mrow><mi>&amp;alpha;</mi><mo>,</mo><msup><mi>&amp;alpha;</mi><mo>*</mo></msup></mrow></munder><mo>{</mo><mo>-</mo><mfrac><mn>1</mn><mn>2</mn></mfrac><munderover><mo>&amp;Sigma;</mo><mrow><mi>i</mi><mo>=</mo><mn>1</mn></mrow><mi>l</mi></munderover><munderover><mo>&amp;Sigma;</mo><mrow><mi>j</mi><mo>=</mo><mn>1</mn></mrow><mi>l</mi></munderover><mrow><mo>(</mo><msubsup><mi>&amp;alpha;</mi><mi>i</mi><mo>*</mo></msubsup><mo>-</mo><msub><mi>&amp;alpha;</mi><mi>i</mi></msub><mo>)</mo></mrow><mrow><mo>(</mo><msubsup><mi>&amp;alpha;</mi><mi>j</mi><mo>*</mo></msubsup><mo>-</mo><msub><mi>&amp;alpha;</mi><mi>j</mi></msub><mo>)</mo></mrow><mi>K</mi><mrow><mo>(</mo><msub><mi>x</mi><mi>i</mi></msub><mo>,</mo><msub><mi>x</mi><mi>j</mi></msub><mo>)</mo></mrow><mo>+</mo><munderover><mo>&amp;Sigma;</mo><mrow><mi>i</mi><mo>=</mo><mn>1</mn></mrow><mi>l</mi></munderover><msubsup><mi>&amp;alpha;</mi><mi>i</mi><mo>*</mo></msubsup><mrow><mo>(</mo><msub><mi>y</mi><mi>i</mi></msub><mo>-</mo><mi>&amp;epsiv;</mi><mo>)</mo></mrow><mo>-</mo><msub><mi>&amp;alpha;</mi><mi>i</mi></msub><mrow><mo>(</mo><msub><mi>y</mi><mi>i</mi></msub><mo>+</mo><mi>&amp;epsiv;</mi><mo>)</mo></mrow><mo>}</mo><mo>-</mo><mo>-</mo><mo>-</mo><mrow><mo>(</mo><mn>3</mn><mo>)</mo></mrow><mo>;</mo></mrow> <mrow><mi>s</mi><mo>.</mo><mi>t</mi><mo>.</mo><mfenced open = "{" close = ""><mtable><mtr><mtd><mrow><mn>0</mn><mo>&amp;le;</mo><msub><mi>&amp;alpha;</mi><mi>i</mi></msub><mo>&amp;le;</mo><mi>E</mi><mo>,</mo><mi>i</mi><mo>=</mo><mn>1</mn><mo>,</mo><mn>...</mn><mo>,</mo><mi>l</mi></mrow></mtd></mtr><mtr><mtd><mrow><mn>0</mn><mo>&amp;le;</mo><msubsup><mi>&amp;alpha;</mi><mi>i</mi><mo>*</mo></msubsup><mo>&amp;le;</mo><mi>E</mi><mo>,</mo><mi>i</mi><mo>=</mo><mn>1</mn><mo>,</mo><mn>...</mn><mo>,</mo><mi>l</mi></mrow></mtd></mtr><mtr><mtd><mrow><munderover><mo>&amp;Sigma;</mo><mrow><mi>i</mi><mo>=</mo><mn>1</mn></mrow><mi>l</mi></munderover><mrow><mo>(</mo><msubsup><mi>&amp;alpha;</mi><mi>i</mi><mo>*</mo></msubsup><mo>-</mo><msub><mi>&amp;alpha;</mi><mi>i</mi></msub><mo>)</mo></mrow><mo>=</mo><mn>0</mn></mrow></mtd></mtr></mtable></mfenced><mo>-</mo><mo>-</mo><mo>-</mo><mrow><mo>(</mo><mn>4</mn><mo>)</mo></mrow><mo>;</mo></mrow> Among them, y is the sample sequence, which is the original sequence of the collected vehicle stop time, l is the number of support vectors, x=(x ₁ , x ₂ , x ₃ , x ₄ ) is the attribute variable, which is closely related to the tram stop time , are the actual arrival time of the tram, the number of people boarding, the number of people getting off, and the headway distance from the last incoming tram, all of which can be obtained through follow-up surveys. 6. the coordinated control method of a kind of tram and social traffic flow according to claim 5, is characterized in that, adopts nested algorithm to determine green light duration and phase difference in the described step (32), module one uses tram The minimum parking in the coordination section is the goal, and this goal is brought into Module 2 as a new constraint, that is, the minimum total delay in the control section is the optimization goal, which ensures that the trams continue to pass at the intersection while making social vehicles The delay at the port is as small as possible; Module 1: Green Wave Passage of Trams; Module 1 takes the cumulative parking times S _all of the trams applying for priority in the target section as the minimum as the objective function, and the corresponding algorithm is as follows: <mrow><mi>min</mi><mi></mi><msub><mi>S</mi><mrow><mi>a</mi><mi>l</mi><mi>l</mi></mrow></msub><mo>=</mo><mi>min</mi><munderover><mo>&amp;Sigma;</mo><mrow><mi>j</mi><mo>=</mo><mn>1</mn></mrow><mi>n</mi></munderover><mi>S</mi><mi></mi><mi>S</mi><mo>=</mo><mfenced open = "{" close = ""><mtable><mtr><mtd><mn>0</mn></mtd><mtd><mtable><mtr><mtd><mrow><msubsup><mi>t</mi><mi>s</mi><mi>j</mi></msubsup><mo>&amp;le;</mo><msubsup><mi>t</mi><mrow><mi>a</mi><mi>r</mi><mi>r</mi></mrow><mi>j</mi></msubsup></mrow></mtd><mtd><mrow><mi>a</mi><mi>n</mi><mi>d</mi></mrow></mtd><mtd><mrow><msubsup><mi>t</mi><mrow><mi>a</mi><mi>r</mi><mi>r</mi></mrow><mi>j</mi></msubsup><mo>+</mo><msub><mi>t</mi><mrow><mi>e</mi><mi>m</mi><mi>p</mi></mrow></msub><mo>&amp;le;</mo><msubsup><mi>t</mi><mi>s</mi><mi>j</mi></msubsup><mo>+</mo><msubsup><mi>t</mi><mi>g</mi><mrow><mn>1</mn><mi>j</mi></mrow></msubsup></mrow></mtd></mtr></mtable></mtd></mtr><mtr><mtd><mn>1</mn></mtd><mtd><mrow><mi>e</mi><mi>l</mi><mi>s</mi><mi>e</mi></mrow></mtd></mtr></mtable></mfenced><mo>-</mo><mo>-</mo><mo>-</mo><mrow><mo>(</mo><mn>5</mn><mo>)</mo></mrow><mo>;</mo></mrow> <mrow><mi>s</mi><mo>.</mo><mi>t</mi><mo>.</mo><mfenced open = "{" close = ""><mtable><mtr><mtd><mrow><msubsup><mi>t</mi><mi>g</mi><mrow><mi>i</mi><mi>j</mi></mrow></msubsup><mo>&amp;GreaterEqual;</mo><msubsup><mi>t</mi><mrow><mi>g</mi><mi>min</mi></mrow><mrow><mi>i</mi><mi>j</mi></mrow></msubsup></mrow></mtd></mtr><mtr><mtd><mrow><munderover><mo>&amp;Sigma;</mo><mrow><mi>i</mi><mo>=</mo><mn>1</mn></mrow><mi>m</mi></munderover><msubsup><mi>t</mi><mi>g</mi><mrow><mi>i</mi><mi>j</mi></mrow></msubsup><mo>=</mo><mi>C</mi></mrow></mtd></mtr><mtr><mtd><mrow><mn>0</mn><mo>&amp;le;</mo><msub><mi>o</mi><mi>j</mi></msub><mo>&amp;le;</mo><mi>C</mi></mrow></mtd></mtr><mtr><mtd><mrow><msubsup><mi>t</mi><mi>g</mi><mrow><mi>i</mi><mi>j</mi></mrow></msubsup><mo>,</mo><msubsup><mi>t</mi><mrow><mi>g</mi><mi>min</mi></mrow><mrow><mi>i</mi><mi>j</mi></mrow></msubsup><mo>,</mo><msub><mi>o</mi><mi>j</mi></msub><mo>&amp;GreaterEqual;</mo><mn>0</mn><mo>&amp;Element;</mo><mi>int</mi><mi>e</mi><mi>g</mi><mi>e</mi><mi>r</mi></mrow></mtd></mtr></mtable></mfenced><mo>-</mo><mo>-</mo><mo>-</mo><mrow><mo>(</mo><mn>6</mn><mo>)</mo></mrow><mo>;</mo></mrow> in, is the time when the green light of the tram passing phase at the jth intersection is turned on, o _j is the absolute phase difference of the jth intersection, a is a positive integer, and C is the duration of the public cycle of coordinated control; is the time when the tram arrives at the jth intersection; t _emp = (L _tr +L _d )/v _tr is the clearing time for the tram to cross the intersection; is the green time of the i-th phase of the j-th intersection, is the shortest green light time of the i-th phase of the j-th intersection, q _ij is the single-period traffic flow of the j-th intersection in the i-th phase, S _ij is the lane saturation flow rate of the j-th intersection in the i-th phase; Formula (5) and formula (6) are solved by the integer space particle swarm optimization algorithm, and the solution result is brought into module 2 as a new constraint condition; Module 2: Timing optimization based on expected delay; Tram signals give priority to the passing time of vehicles occupying other phases. In order to ensure the right of way of trams, the signal timing should minimize the delay of passing vehicles in other phases. The algorithm is as follows: <mrow><mi>min</mi><mi></mi><msub><mi>D</mi><mrow><mi>a</mi><mi>l</mi><mi>l</mi></mrow></msub><mo>=</mo><mi>m</mi><mi>i</mi><mi>n</mi><munderover><mo>&amp;Sigma;</mo><mrow><mi>j</mi><mo>=</mo><mn>1</mn></mrow><mi>n</mi></munderover><munderover><mo>&amp;Sigma;</mo><mrow><mi>i</mi><mo>=</mo><mn>2</mn></mrow><mi>m</mi></munderover><msub><mi>D</mi><mrow><mi>i</mi><mi>j</mi></mrow></msub><mo>-</mo><mo>-</mo><mo>-</mo><mrow><mo>(</mo><mn>7</mn><mo>)</mo></mrow><mo>;</mo></mrow> <mrow><msub><mi>D</mi><mrow><mi>i</mi><mi>j</mi></mrow></msub><mo>=</mo>< mfenced open = "{" close = ""><mtable><mtr><mtd><mfrac><mrow><msup><mrow><mo>(</mo><msubsup><mi>t</mi><mi>s</mi><mrow><mi>i</mi><mi>j</mi></mrow></msubsup><mo>-</mo><msubsup><mi>t</mi><mrow><mi>a</mi><mi>a</mi></mrow><mrow><mi>i</mi><mi>j</mi></mrow></msubsup><mo>)</mo></mrow><mn>2</mn></msup><mo>&amp;times;</mo><msub><mi>u</mi><mrow><mi>i</mi><mi>j</mi></mrow></msub><mo>&amp;times;</mo><msub><mi>S</mi><mrow><mi>i</mi><mi>j</mi></mrow></msub></mrow><mrow><mn>2</mn><mo>&amp;times;</mo><mrow><mo>(</mo><msub><mi>S</mi><mrow><mi>i</mi><mi>j</mi></mrow></msub><mo>-</mo><msub><mi>u</mi><mrow><mi>i</mi><mi>j</mi></mrow></msub><mo>)</mo></mrow></mrow></mfrac></mtd><mtd><mrow><msubsup><mi>t</mi><mi>s</mi><mrow><mi>i</mi><mi>j</mi></mrow></msubsup><mo>&amp;GreaterEqual;</mo><msubsup><mi>t</mi><mrow><mi>a</mi><mi>a</mi></mrow><mrow><mi>i</mi><mi>j</mi></mrow></msubsup></mrow></mtd></mtr><mtr><mtd><mn>0</mn></mtd><mtd><mtable><mtr><mtd><mrow><msubsup><mi>t</mi><mi>s</mi><mrow><mi>i</mi>mi><mi>j</mi></mrow></msubsup><mo>&amp;le;</mo><msubsup><mi>t</mi><mrow><mi>a</mi><mi>a</mi></mrow><mrow><mi>i</mi><mi>j</mi></mrow></msubsup></mrow></mtd><mtd><mrow><mi>a</mi><mi>n</mi><mi>d</mi></mrow></mtd><mtd><mrow><msub><mi>q</mi><mrow><mi>i</mi><mi>j</mi></mrow></msub><mo>-</mo><msub><mi>u</mi><mrow><mi>i</mi><mi>j</mi></mrow></msub><mo>&amp;times;</mo><mrow><mo>(</mo><msubsup><mi>t</mi><mi>g</mi><mrow><mi>i</mi><mi>j</mi></mrow></msubsup><mo>-</mo><msubsup><mi>t</mi><mrow><mi>a</mi><mi>a</mi></mrow><mrow><mi>i</mi><mi>j</mi></mrow></msubsup><mo>+</mo><msubsup><mi>t</mi><mi>s</mi><mrow><mi>i</mi><mi>j</mi></mrow></msubsup><mo>)</mo></mrow><mo>&amp;GreaterEqual;</mo><mn>0</mn></mrow></mtd></mtr></mtable></mtd></mtr><mtr><mtd><mrow><mfrac><mn>1</mn><mn>2</mn></mfrac><mrow><mo>(</mo><mn>2</mn><mi>C</mi><mo>-</mo><mn>3</mn><msubsup><mi>t</mi><mi>s</mi><mrow><mi>i</mi><mi>j</mi></mrow></msubsup><mi>mod</mi><mi></mi><mi>C</mi><mo>-</mo><msubsup><mi>t</mi><mi>g</mi><mrow><mi>i</mi><mi>j</mi></mrow></msubsup><mo>+</mo><msubsup><mi>t</mi><mrow><mi>a</mi><mi>a</mi></mrow><mrow><mi>i</mi><mi>j</mi></mrow></msubsup><mi>mod</mi><mi></mi><mi>C</mi><mo>-</mo><msub><mi>q</mi><mrow><mi>i</mi><mi>j</mi></mrow></msub><mo>/</mo><msub><mi>u</mi><mrow><mi>i</mi><mi>j</mi></mrow></msub><mo>)</mo></mrow><mo>&amp;times;</mo><mrow><mo>(</mo><msub><mi>q</mi><mrow><mi>i</mi><mi>j</mi></mrow></msub><mo>-</mo><msub><mi>u</mi><mrow><mi>i</mi><mi>j</mi></mrow></msub><mo>&amp;times;</mo><mo>(</mo><mrow><msubsup><mi>t</mi><mi>g</mi><mrow><mi>i</mi><mi>j</mi></mrow></msubsup><mo>-</mo><msubsup><mi>t</mi><mrow><mi>a</mi><mi>a</mi></mrow><mrow><mi>i</mi><mi>j</mi></mrow></msubsup><mo>+</mo><msubsup><mi>t</mi><mi>s</mi><mrow><mi>i</mi><mi>j</mi></mrow></msubsup></mrow><mo>)</mo><mo>)</mo></mrow></mrow></mtd><mtd><mrow><mi>e</mi><mi>l</mi><mi>s</mi><mi>e</mi></mrow></mtd></mtr></mtable></mfenced><mo>-</mo><mo>-</mo><mo>-</mo><mrow><mo>(</mo><mn>8</mn><mo>)</mo></mrow><mo>;</mo></mrow> <mrow><mi>s</mi><mo>.</mo><mi>t</mi><mo>.</mo><mfenced open = "{" close = ""><mtable><mtr><mtd><mrow><msubsup><mi>t</mi><mi>g</mi><mrow><mi>i</mi><mi>j</mi></mrow></msubsup><mo>&amp;GreaterEqual;</mo><msubsup><mi>t</mi><mrow><mi>g</mi><mi>min</mi></mrow><mrow><mi>i</mi><mi>j</mi></mrow></msubsup></mrow></mtd></mtr><mtr><mtd><mrow><munderover><mo>&amp;Sigma;</mo><mrow><mi>i</mi><mo>=</mo><mn>1</mn></mrow><mi>m</mi></munderover><msubsup><mi>t</mi><mi>g</mi><mrow><mi>i</mi><mi>j</mi></mrow></msubsup><mo>=</mo><mi>C</mi></mrow></mtd></mtr><mtr><mtd><mrow><mn>0</mn><mo>&amp;le;</mo><msub><mi>o</mi><mi>j</mi></msub><mo>&amp;le;</mo><mi>C</mi></mrow></mtd></mtr><mtr><mtd><mrow><msubsup><mi>t</mi><mi>g</mi><mrow><mi>i</mi><mi>j</mi></mrow></msubsup><mo>,</mo><msubsup><mi>t</mi><mrow><mi>g</mi><mi>min</mi></mrow><mrow><mi>i</mi><mi>j</mi></mrow></msubsup><mo>,</mo><msub><mi>o</mi><mi>j</mi></msub><mo>&amp;GreaterEqual;</mo><mn>0</mn><mo>&amp;Element;</mo><mi>int</mi><mi>e</mi><mi>g</mi><mi>e</mi><mi>r</mi></mrow></mtd></mtr><mtr><mtd><mrow><mi>min</mi><mi></mi><msub><mi>S</mi><mrow><mi>a</mi><mi>l</mi><mi>l</mi></mrow></msub><mo>=</mo><mi>min</mi><munderover><mo>&amp;Sigma;</mo><mrow><mi>j</mi><mo>=</mo><mn>1</mn></mrow><mi>n</mi></munderover><mi>S</mi></mrow></mtd></mtr></mtable></mfenced><mo>-</mo><mo>-</mo><mo>-</mo><mrow><mo>(</mo><mn>9</mn><mo>)</mo></mrow><mo>;</mo></mrow> in, u _ij is the arrival rate of the jth phase of the i-th intersection after considering the influence of the upstream intersection; Using the particle swarm algorithm in integer space, the signal phase timing and phase difference of each intersection satisfying the objective function can be obtained.