CN110400462B - Track traffic passenger flow monitoring and early warning method and system based on fuzzy theory - Google Patents
Track traffic passenger flow monitoring and early warning method and system based on fuzzy theory Download PDFInfo
- Publication number
- CN110400462B CN110400462B CN201910680632.XA CN201910680632A CN110400462B CN 110400462 B CN110400462 B CN 110400462B CN 201910680632 A CN201910680632 A CN 201910680632A CN 110400462 B CN110400462 B CN 110400462B
- Authority
- CN
- China
- Prior art keywords
- fuzzy
- passenger flow
- data
- area
- early warning
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/01—Detecting movement of traffic to be counted or controlled
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/01—Detecting movement of traffic to be counted or controlled
- G08G1/0104—Measuring and analyzing of parameters relative to traffic conditions
- G08G1/0125—Traffic data processing
Abstract
The invention relates to a track traffic passenger flow monitoring and early warning method and system based on a fuzzy theory, belongs to the technical field of traffic passenger flow monitoring, and solves the problem that the prior art cannot effectively improve the low operation efficiency of track traffic. The method comprises the following steps: collecting passenger flow in-out data in each area of the rail transit in real time; acquiring environmental factors in each region in real time, and quantizing each environmental factor respectively; and fuzzifying the passenger flow inlet and outlet data and the quantized data of the environmental factors in each area of the rail transit, inputting the obtained fuzzification result into a fuzzy inference judgment machine trained in advance, and generating the risk level of each area, future passenger flow inlet and outlet amount estimation and station evacuation time estimation. The method can replace manual monitoring and judgment with intelligent passenger flow detection and early warning, and has higher real-time performance and accuracy and stronger stability.
Description
Technical Field
The invention relates to the technical field of traffic passenger flow monitoring, in particular to a track traffic passenger flow monitoring and early warning method and system based on a fuzzy theory.
Background
In urban construction, rail transit is an important component of a travel system, plays an important role in improving urban transportation patterns, facilitating travel of citizens and the like, is also a symbolic representation of urban images, and is an attractive landscape.
At present, due to the limitation of various factors, the operation condition of rail transit is not optimistic, and the specific expression is that the route is single, the coverage is narrow, the waiting time is long, and getting on and off are crowded, namely the operation efficiency of rail transit is low. The current situation of low operation efficiency of the rail transit is improved, and the current situation becomes an important research subject of the current urban trip scheme.
In the prior art, researchers propose to install intelligent terminals on subways, trains, buses and the like, use electronic maps as carriers, and realize real-time monitoring and scheduling of operating vehicles by collecting, transmitting and processing vehicle, passenger flow and road information. The scheme relieves the problem of low operation efficiency of rail transit to a certain extent, but the accuracy of the judgment result is too dependent on the service level of a professional. In addition, the monitoring result has larger time delay, randomness and uncertainty, and is not beneficial to large-scale popularization and application.
Disclosure of Invention
In view of the foregoing analysis, the embodiments of the present invention provide a rail transit passenger flow monitoring and early warning system based on a fuzzy theory and a method thereof, so as to solve the problem that the prior art cannot effectively improve the low operation efficiency of rail transit.
On one hand, the embodiment of the invention provides a rail transit passenger flow monitoring and early warning method based on a fuzzy theory, which comprises the following steps:
collecting passenger flow in-out data in each area of the rail transit in real time;
acquiring environmental factors in each area in real time, and quantizing each environmental factor respectively;
and (3) quantizing the passenger flow inlet and outlet data in each area of the rail transit by using environmental factors, then respectively carrying out fuzzification processing on the data, inputting the obtained fuzzification processing result into a fuzzy inference judgment machine trained in advance, and generating the risk level faced by each area, future passenger flow inlet and outlet quantity estimation and station evacuation time estimation.
The beneficial effects of the above technical scheme are as follows: environmental factors are considered when rail transit passenger flow monitoring and early warning are carried out. After the environmental factors are quantized, the obtained analysis results such as risk levels of various regions, future passenger flow inlet and outlet volume estimation, station evacuation time estimation and the like are more accurate, and the calculation process is quicker. Through the technical scheme, the user can obtain passenger flow monitoring and early warning data of each area of the rail transit in real time, and the method is more sensitive to large passenger flows and can avoid risks in time, so that the user experience is excellent.
Based on further improvement of the method, the passenger flow in-out data comprises at least one of line transfer amount, station transfer amount, transfer channel passenger flow amount, station in-out peak hour coefficient, line net in-out peak hour coefficient, transfer station peak hour coefficient and hot spot area classification;
the environmental factors include at least one of weather conditions, mass transit congestion conditions, whether there is significant activity, whether there is holiday conditions.
The beneficial effects of the further technical scheme are as follows: through a large amount of practical experience, the passenger flow access data and the environmental factors are limited, the design time is saved, the data can be selected more accurately, and the data analysis is more accurate.
Further, training the fuzzy inference judgment machine comprises the following steps:
setting a representation input X in a fuzzy inference engineiAnd output YjAll fuzzy conditions of possible relationships; the format of the fuzzy condition comprises: if X is1＝A1，…，Xi＝Ai，…，Xn＝AnThen Y is1＝B1，…，Yj＝Bj，…，Ym＝Bm(ii) a Wherein n represents the number of inputs and m represents the number of outputs; a. thei、BjRespectively representing fuzzification processing results of input data and output data;
acquiring historical passenger flow in-and-out data and environmental factor quantitative data in each area of the rail transit as input data for training, and acquiring corresponding historical risk levels, passenger flow in-and-out amount in preset time and station evacuation time as output data for training;
and fuzzifying the input data for training and the output data for training respectively, inputting the obtained fuzzification result into a fuzzy inference judgment machine to train the set fuzzy conditions, obtaining the confidence coefficient of each fuzzy condition, removing the fuzzy conditions with the confidence coefficient lower than a preset value, reserving the fuzzy conditions with the confidence coefficient more than or equal to the preset value, completing the screening of the fuzzy conditions, and further completing the training of the fuzzy inference judgment machine.
The beneficial effects of the further technical scheme are as follows: the analysis of historical data and the screening of the fuzzification conditions enable the fuzzy inference judgment machine to predict risks more accurately, and interference of useless data and useless fuzzy conditions on results is prevented.
Further, the fuzzification processing executes the following steps:
respectively taking the passenger flow inlet and outlet data in each region and the quantized data of the environmental factors as fuzzy variables, and respectively fuzzifying each fuzzy variable to obtain a corresponding fuzzy set;
and calculating a membership function and a non-membership function of the fuzzy set in the domain corresponding to each fuzzy variable as fuzzification processing results, and sending the fuzzification processing results as fuzzy inference input to a fuzzy inference judgment machine.
The beneficial effects of the above further improved scheme are: through complete fuzzification data processing, the training efficiency of the fuzzy inference judgment machine is improved, and the method is simple and easy to implement.
Further, a confidence level S (R) of each of the fuzzy conditionsm) Is calculated by the following formula
S(Rm)＝S(A0,Ax)⊙S(B0,Bx)…⊙S(a0,ax)⊙S(b0,bx)…
Wherein
In the formula, K0A fuzzy value, K, representing a fuzzy variable in the fuzzy conditionxRepresenting each element of the fuzzy set corresponding to the fuzzy variable, mu representing the membership degree of the fuzzy variable, v representing the non-membership degree of the fuzzy variable, Kx(mu) a membership function, K, of said fuzzy variablex(v) A non-membership function, S (K), representing said fuzzy variable0,Kx) Represents K0And KxThe similarity between two fuzzy values, A, B, …, a, b …, represents all fuzzy variables related to the fuzzy condition, A, B, … represent inputs, a, b … represent outputs, Abs () represents absolute value calculation, ⊙ represents large or small calculation.
The beneficial effects of the above further improved scheme are: through calculation of confidence coefficients of different fuzzy conditions, accuracy of collected data can be better improved through the confidence coefficients, and more accurate data can be selected to predict passenger flow information (risk level of each area, future passenger flow inlet and outlet volume estimation and station evacuation time estimation).
On the other hand, the embodiment of the invention provides a rail transit passenger flow monitoring and early warning system based on a fuzzy theory, which comprises the following components:
the data acquisition equipment is used for acquiring passenger flow in and out data in each area of the rail transit in real time;
the environment factor acquisition module is used for acquiring environment factors in each area at the current moment and quantizing the environment factors respectively;
and the data processing module is used for respectively carrying out fuzzification processing on the passenger flow inlet and outlet data and the data after the environmental factors are quantized in each area, inputting the obtained fuzzification processing result into a fuzzy inference judgment machine trained in advance, and generating the risk level faced by each area, future passenger flow inlet and outlet volume estimation and station evacuation time estimation.
The beneficial effects of the above technical scheme are as follows: environmental factors are considered when rail transit passenger flow monitoring and early warning are carried out. After the environmental factors are quantized, the obtained analysis results such as risk levels of various regions, future passenger flow inlet and outlet volume estimation, station evacuation time estimation and the like are more accurate, and the calculation process is quicker. Through the technical scheme, the user can obtain passenger flow monitoring and early warning data of each area of the rail transit in real time, and the scheme is more sensitive to large passenger flows, so that risks can be avoided in time, and the user experience is excellent.
Based on the further improvement of above-mentioned system, this track traffic passenger flow monitoring early warning system based on fuzzy theory, its characterized in that still includes:
the statistical analysis module is used for obtaining line transfer amount, station transfer amount, transfer channel passenger flow amount, station in-out peak hour coefficient, line in-out peak hour coefficient, transfer station peak hour coefficient and hot spot area classification according to the passenger flow in-out data in each area of the rail transit collected by the data collection equipment, and outputting the data to the data processing module as the passenger flow in-out data in each area;
and the monitoring and early warning module is used for comparing the risk level output by the data processing module with a preset value to judge whether to send out acousto-optic early warning, and when the risk level is greater than the preset value, judging to send out acousto-optic early warning of a corresponding level, otherwise, not carrying out early warning.
The beneficial effects of the above further improved scheme are: the statistical analysis module is arranged in the rail transit passenger flow monitoring and early warning system, so that collected data can be effectively managed and classified, the working efficiency of the data processing module is improved, and the monitoring and early warning module can timely early warn about possible passenger flow risks to remind workers to take corresponding measures.
Further, the data processing module comprises:
the input data fuzzification module is used for fuzzifying each fuzzy variable by taking the passenger flow inlet and outlet data and the quantized data of the environmental factors in each area as fuzzy variables respectively to obtain corresponding fuzzy sets respectively, calculating a membership function and a non-membership function of the fuzzy set corresponding to each fuzzy variable in a domain as fuzzification processing results, and sending the fuzzification processing results as fuzzy inference input to the fuzzy inference judgment machine;
and the fuzzy inference judgment machine is used for obtaining the risk level of each area, future passenger flow inlet and outlet volume estimation and station evacuation time estimation according to the input fuzzification processing result and each pre-trained fuzzy condition.
The beneficial effects of the above further improved scheme are: the input fuzzy variable can be efficiently fuzzified by the arranged input data fuzzification module, and then a fuzzy inference result (future passenger flow, risk level and evacuation time) which accords with objective facts is obtained by the fuzzy inference judgment machine.
Further, the data processing module further comprises:
the training data fuzzification module is used for fuzzifying the passenger flow inlet and outlet data in each area and the quantized data of the environmental factors in the training data as input when the fuzzy inference judgment machine is trained, fuzzifying the actual risk level of each area, the future passenger flow data and the station evacuation time as output respectively, inputting the input and the output into the fuzzy inference judgment machine to train preset fuzzy conditions, obtaining the confidence coefficient of each fuzzy condition, removing the fuzzy conditions with the confidence coefficient lower than a preset value, and keeping the fuzzy conditions with the confidence coefficient larger than or equal to the preset value as the trained fuzzy conditions.
The beneficial effects of the above further improved scheme are: through the data fuzzification module for training, the fuzzy inference judging machine can be better trained, and the confidence coefficient of an analysis result is improved, namely the accuracy of fuzzy analysis is improved.
Further, when in use, after the fuzzy inference judgment machine obtains the risk level faced by each area, the future passenger flow inlet and outlet volume estimation and the station evacuation time estimation, the following procedures are also executed:
obtaining the evaluation coefficient G of each region according to each fuzzy condition trained in advanceiIs composed of
In the formula, TmRepresents the importance of the mth bar fuzzy condition;
according to the evaluation coefficient G of each regioniComparing with a preset value, GiAnd outputting and displaying the risk level corresponding to the area with the value greater than or equal to the preset value, the corresponding future passenger flow inlet and outlet volume estimation and station evacuation time estimation.
The beneficial effects of the above further improved scheme are: through the evaluation coefficient, whether the obtained risk level of each region and the corresponding future passenger flow inlet and outlet volume estimation and station evacuation time estimation are accurate or not can be better known, so that the analysis result can be more accurately predicted, and the analysis efficiency is improved.
In the invention, the technical schemes can be combined with each other to realize more preferable combination schemes. Additional features and advantages of the invention will be set forth in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention. The objectives and other advantages of the invention will be realized and attained by the structure particularly pointed out in the written description and drawings.
Drawings
The drawings are only for purposes of illustrating particular embodiments and are not to be construed as limiting the invention, wherein like reference numerals are used to designate like parts throughout.
Fig. 1 is a schematic diagram illustrating steps of a rail transit passenger flow monitoring and early warning method in embodiment 1 of the present invention;
FIG. 2 is a schematic diagram of the training procedure of the fuzzy inference engine in embodiment 2 of the present invention;
fig. 3 is a schematic diagram of a rail transit passenger flow monitoring and early warning system according to embodiment 3 of the present invention.
Fig. 4 is a schematic diagram of a rail transit passenger flow monitoring and early warning system according to embodiment 4 of the present invention.
Detailed Description
The accompanying drawings, which are incorporated in and constitute a part of this application, illustrate preferred embodiments of the invention and together with the description, serve to explain the principles of the invention and not to limit the scope of the invention.
Example 1
The invention discloses a rail transit passenger flow monitoring and early warning method based on a fuzzy theory, which comprises the following steps as shown in figure 1:
s1, collecting passenger flow in-out data in each area of rail transit in real time;
s2, acquiring environmental factors in each area in real time, and quantizing each environmental factor respectively;
and S3, respectively fuzzifying the passenger flow inlet and outlet data and the quantized data of the environmental factors in each area of the rail transit, inputting the obtained fuzzification processing result into a pre-trained fuzzy inference judgment machine, and generating the risk level of each area, future passenger flow inlet and outlet volume estimation and station evacuation time estimation.
Compared with the prior art, environmental factors are considered when the rail transit passenger flow monitoring and early warning are carried out in the method. After the environmental factors are quantized, the obtained analysis results such as risk levels of various regions, future passenger flow inlet and outlet volume estimation, station evacuation time estimation and the like are more accurate, and the calculation process is quicker. The user can obtain passenger flow monitoring and early warning data of each area of the rail transit in real time, and the method is more sensitive to large passenger flows and can avoid risks in time, so that the user experience is excellent. The fuzzy inference judger can continuously learn and improve, and realize automatic monitoring and early warning of passenger flow of rail transit (subway). The intelligent passenger flow monitoring and early warning replaces manual monitoring and judgment, so that the real-time performance is higher, the accuracy is higher, and the stability is stronger.
Example 2
The optimization is performed on the basis of the embodiment 1, and in the step S1 of the rail transit passenger flow monitoring and early warning method, the passenger flow in and out data includes line transfer volume, station transfer volume, transfer passage passenger flow volume, station in and out peak hour coefficient, line in and out peak hour coefficient, transfer station peak hour coefficient, and hot spot area classification.
Specifically, the line transfer amount, the station transfer amount, and the transfer passage passenger flow amount are classified into one group, which represents the target area stock, and for this group, the stock P is acquired only according to a group of passenger flow counters surrounding the target areaaCan be calculated by the following formula
Pa＝P0+∑P1-∑P2(1)
In the formula, P0Indicating an initial value of the amount of personnel in the target area, P1Indicating the number of persons entering the target area, P2Indicating the number of people leaving the target area.
P in formula (1)aError range E ofaIs composed of
Ea＝εa(∑P1+∑P2) (2)
In the formula, epsilonaIndicating the flux-counting device error rate.
The inventory P for the case of collecting from multiple sets of passenger flow counters enclosing a target areaaCan be calculated by the following formula:
Pa＝η·(∑Pi-Ec) (3)
where η denotes a statistical correction factor, obtainable by calibration, PiIndicating the respective passenger flow counter stock count, EcRepresenting the repeat count produced at the splice of the passenger flow counter.
P in formula (3)aError range E ofaComprises the following steps:
Ea＝εaPa(4)
the peak hour coefficient is a ratio of the passenger flow input at the peak hour to the passenger flow input at the peak hour expanded to 1 hour, and is generally divided into a peak hour coefficient of 5min and a peak hour coefficient of 15 min. Wherein, the calculation formula of the peak hour coefficient in 5min is
PHF5 peak hour passenger flow volume/(peak 5min passenger flow volume 12) (5)
The calculation formula of the peak hour coefficient in 15min is as follows:
PHF5 peak hour passenger flow output/(peak 15min passenger flow output 4) (6)
Other passenger flow in and out data are common statistical data and are not described in detail.
Preferably, in step S2, the environmental factors include at least one of weather conditions, traffic congestion, whether there is significant activity, and whether there is holiday. The environmental factors are quantified, specifically, data quantification is carried out according to classification conditions of weather, public transportation, major activities and holiday conditions, the weather quantification is defined as 5 in sunny days, 4 in cloudy days, 3 in cloudy days, 2 in rainy days and 1 in heavy rain days, the public transportation quantification is defined as 5 in severe congestion, 4 in general congestion, 3 in light congestion, 2 in clear days and 1 in few vehicles, the major activity quantification is defined as 1 in meetings, 0 in non-meetings, the holiday condition quantification is defined as 1 in holiday days and 0 in non-holiday days. The user can define reasonable values according to different requirements.
In the blurring process in step S3, the following steps are performed:
s31, respectively taking the passenger flow inlet and outlet data and the quantized data of the environmental factors in each area as fuzzy variables, and fuzzifying each fuzzy variable through a fuzzification method to obtain a fuzzy set;
and S32, calculating a membership function and a non-membership function of the fuzzy set in the domain of discourse corresponding to each fuzzy variable, taking the membership function and the non-membership function corresponding to each fuzzy variable as fuzzification processing results, and sending the fuzzification processing results to a fuzzy inference judgment machine as input.
Optionally, the fuzzification method may adopt at least one of an archive fuzzy set method, an input point membership 1 method, a single-point fuzzy set method and a membership value method; the fuzzy set is represented by at least one of Zadeh operator, algebraic operator, bounded operator and Einstein operator.
Preferably, the fuzzy inference engine is trained, as shown in fig. 2, and includes the following steps:
s01, setting a representation input X in a fuzzy inference judging machineiAnd output YjAll fuzzy conditions of possible relations. The format of the ambiguity condition is' if X1＝A1，…，Xi＝Ai，…，Xn＝AnThen Y is1＝B1，…，Yj＝Bj，…，Ym＝Bm"; wherein, i is 1, …, n, j is 1, …, m; and calling from a preset knowledge rule base.
The meaning of the fuzzy condition format is that if the input fuzzification processing result X is input1…XnIf the preset conditions are met, outputting the risk grade Y faced by each area1And future passenger flow in-out estimation Y2Station evacuation time estimation Y3。
For example, if the weather is severe weather (weather conditions) such as rain, the in-and-out peak hour coefficient is increased, and the degree of increase is related to the severity of weather; if the road sections around the subway are congested (the congestion condition of public transport), the peak hour coefficient of the station entering and exiting will be increased; if the current day is legal holiday or weekend holiday (whether holiday conditions exist), the peak hour coefficient of the incoming and outgoing passenger flow is increased, and the increasing degree is related to the length of holiday. The station evacuation time is related to the peak hour coefficient of the in-station in-and-out peak and the transfer passenger flow, and the risk level is directly related to the peak hour coefficient of the in-station passenger flow.
S02, acquiring historical passenger flow in-out data and environmental factor quantitative data in each area of the rail transit as input data for training, and acquiring corresponding historical risk levels, passenger flow in-out amount in preset time and station evacuation time as output data for representing training;
and S03, fuzzifying the input data for training and the output data for training respectively, inputting the obtained fuzzification result into a fuzzy inference judgment machine to train the set fuzzy conditions, obtaining the confidence coefficient of each fuzzy condition, removing the fuzzy conditions with the confidence coefficient lower than a preset value, reserving the fuzzy conditions with the confidence coefficient more than or equal to the preset value, completing the screening of the fuzzy conditions, and further completing the training of the fuzzy inference judgment machine.
Preferably, in step S03, the confidence level S (R) of each of the fuzzy conditionsm) Can be calculated by the following formula
S(Rm)＝S(A0,Ax)⊙S(B0,Bx)…⊙S(a0,ax)⊙S(b0,bx)…
In the formula, K0A fuzzy value, K, representing a fuzzy variable in the fuzzy conditionxRepresenting each element of the fuzzy set corresponding to the fuzzy variable, mu representing the membership degree of the fuzzy variable, v representing the non-membership degree of the fuzzy variable, Kx(mu) a membership function, K, of said fuzzy variablex(v) A non-membership function, S (K), representing said fuzzy variable0,Kx) Represents K0And KxThe similarity between two fuzzy values, K-A, B, …, a, b …, represents all fuzzy variables related to the fuzzy condition, A, B, … represent inputs, a, b … represent outputs, Abs () represents an absolute value calculation, ⊙ represents a large or small calculation, and when "and" is represented, it is small, and when "or" is represented, it is large.
Preferably, the rail transit passenger flow monitoring and early warning method further comprises the following steps:
s41, obtaining an evaluation coefficient G of each area according to each fuzzy condition trained in advanceiIs composed of
In the formula, TmRepresents the importance of the mth bar fuzzy condition;
s42, evaluating coefficients G according to all the areasiComparing with a preset value, GiAnd outputting and displaying the risk level corresponding to the area with the value greater than or equal to the preset value, the corresponding future passenger flow inlet and outlet volume estimation and station evacuation time estimation.
Compared with the embodiment 1, in the method provided by the embodiment, under the technical framework of the fuzzy recognition system, a proper fuzzy condition is selected as the prediction model according to the confidence degree of the fuzzy condition, and then accurate prediction output is obtained.
Example 3
The invention further discloses a rail transit passenger flow monitoring and early warning system based on the method of the embodiment 1, which comprises a data acquisition device, an environmental factor acquisition module and a data processing module, as shown in fig. 3. The output ends of the data acquisition equipment and the environmental factor acquisition module are respectively connected with the input end of the data processing module.
And the data acquisition equipment is used for acquiring the passenger flow in-out data in each area of the rail transit in real time.
And the environment factor acquisition module is used for acquiring weather, public transportation, major activities and holiday conditions in each area at the current moment and quantizing the conditions respectively. In particular, it may be acquired through a network.
And the data processing module is used for respectively carrying out fuzzification processing on the passenger flow inlet and outlet data and the data after the environmental factors are quantized in each area, inputting the obtained fuzzification processing result into a fuzzy inference judgment machine trained in advance, and generating the risk level faced by each area, future passenger flow inlet and outlet volume estimation and station evacuation time estimation. The data processing module can be generated programmatically on the computer.
Example 4
On the basis of the embodiment 3, the invention also discloses a rail transit passenger flow monitoring and early warning system using the method shown in the embodiment 2, which is shown in fig. 4.
The data acquisition equipment comprises an infrared passenger flow counter, a binocular stereo vision sensor and a laser ranging sensor.
The infrared passenger flow counter is arranged at the inlet and outlet positions of each area of the rail transit and used for collecting the number of pedestrians passing through the arrangement position.
The binocular stereoscopic vision sensor is arranged at a proper position of a channel, a station hall and a platform of each area of the rail transit, and is used for tracking the generated events of one-way, two-way, crossing the warning surface and entering the warning area by adopting the crowd density and the pedestrian passing speed of the distributed area.
The laser ranging sensor is arranged at the proper positions of an inlet, an outlet, a channel, a station hall and a platform of each area of the rail transit and is used for collecting size data of the inlet, the outlet, the channel, the station hall and the platform.
Preferably, the rail transit passenger flow monitoring and early warning system further comprises a monitoring and early warning module and a display and alarm module, which are not shown in fig. 4. The input end of the early warning monitoring module is connected with the output end of the data processing module, and the input end of the display warning module is connected with the output ends of the data acquisition equipment and the detection early warning module.
And the monitoring and early warning module is used for comparing the risk level output by the data processing module with a preset value to judge whether to send out acousto-optic early warning, and when the risk level is greater than the preset value, judging to send out acousto-optic early warning of a corresponding level, otherwise, not carrying out early warning.
And the display warning module is used for displaying the events which are acquired by the binocular stereoscopic vision sensor and enter a warning area in a one-way, two-way and crossing warning surface mode on a map, sending corresponding warning information, and displaying acousto-optic warning of corresponding levels sent by the monitoring and warning module, future passenger flow inlet and outlet volume estimation and station evacuation time estimation.
Preferably, the rail transit passenger flow monitoring and early warning system further comprises a statistical analysis module. The input end of the statistical analysis module is arranged between the data acquisition equipment and the data processing module.
And the statistical analysis module is used for obtaining line transfer amount, station transfer amount, transfer channel passenger flow amount, station in-out peak hour coefficient, line in-out peak hour coefficient, transfer station peak hour coefficient and hot spot region classification according to the passenger flow in-out data of each region of the rail transit collected by the data collection equipment, and outputting the line transfer amount, the station transfer amount, the transfer channel passenger flow amount, the station in-out peak hour coefficient, the line in-.
Preferably, the data processing module comprises an input data fuzzification module and a fuzzy inference judgment machine which are connected in sequence. During training, the data processing module further comprises a training data fuzzification module, wherein the output end of the training data fuzzification module is connected with the input end of the fuzzy inference judging machine, and the training data fuzzification module can be dismounted after training.
And the input data fuzzification module is used for respectively fuzzifying the passenger flow inlet and outlet data in each area and the quantized data of the environmental factors, and inputting the obtained fuzzification processing result into a previously trained fuzzy inference judgment machine.
And the fuzzy inference judging machine is used for verifying the fuzzy conditions trained in advance respectively for the passenger flow inlet and outlet data and the fuzzification processing results corresponding to the weather, public transportation, major activities and holiday conditions in each area, and generating the risk level faced by each area, future passenger flow inlet and outlet volume estimation and station evacuation time estimation.
The training data fuzzification module is used for fuzzifying the passenger flow inlet and outlet data in each area and the quantized data of the environmental factors in the training data as input when the fuzzy inference judgment machine is trained, fuzzifying the actual risk level of each area, the future passenger flow data and the station evacuation time as output, inputting the input and the output into the fuzzy inference judgment machine to train preset fuzzy conditions, obtaining the confidence coefficient of each fuzzy condition, removing the fuzzy conditions with the confidence coefficient lower than a preset value, keeping the fuzzy conditions with the confidence coefficient more than or equal to the preset value as the trained fuzzy conditions, and generating a knowledge base.
Preferably, the data processing module further comprises a fuzzy module, and the input end of the fuzzy module is connected with the output end of the fuzzy inference judging machine.
And the ambiguity resolution module is used for generating the risk level of each region, future passenger flow inlet and outlet volume estimation and station evacuation time estimation according to the output of the fuzzy inference judgment machine. The deblurring method is inverse to the input data blurring direction.
The fuzzification processing comprises the following steps:
s31, respectively taking the passenger flow inlet and outlet data and the quantized data of the environmental factors in each area as fuzzy variables, and fuzzifying each fuzzy variable through a fuzzification method to obtain a fuzzy set;
and S32, calculating a membership function and a non-membership function of the fuzzy set in the domain of discourse corresponding to each fuzzy variable, taking the membership function and the non-membership function corresponding to each fuzzy variable as fuzzification processing results, and sending the fuzzification processing results to a fuzzy inference judgment machine.
Preferably, the fuzzification method includes at least one of an archive fuzzy set method, an input point membership 1 method, a single-point fuzzy set method, and a membership value method. The fuzzy set is represented by at least one of Zadeh operator, algebraic operator, bounded operator and Einstein operator.
Preferably, the confidence level S (R) of each of said fuzzy conditionsm) Is calculated by the following formula
S(Rm)＝S(A0,Ax)⊙S(B0,Bx)…⊙S(a0,ax)⊙S(b0,bx)…
In the formula, K0A fuzzy value, K, representing a fuzzy variable in the fuzzy conditionxRepresenting each element of the fuzzy set corresponding to the fuzzy variable, mu representing the membership degree of the fuzzy variable, v representing the non-membership degree of the fuzzy variable, Kx(mu) a membership function, K, of said fuzzy variablex(v) A non-membership function, S (K), representing said fuzzy variable0,Kx) Represents K0And KxThe similarity between two fuzzy values, A, B, …, a, b …, represents all fuzzy variables related to the fuzzy condition, A, B, … represent inputs, a, b … represent outputs, Abs () represents absolute value calculation, ⊙ represents large or small calculation.
And the fuzzy inference judging machine selects the result with the highest confidence coefficient of the fuzzy condition as output, and then deblurrs to obtain the risk level of each region, future passenger flow inlet and outlet volume estimation and station evacuation time estimation.
When the system is used, after the fuzzy inference judgment machine obtains the risk level faced by each area, the future passenger flow inlet and outlet volume estimation and the station evacuation time estimation, the following procedures are executed:
s41, obtaining an evaluation coefficient G of each area according to each fuzzy condition trained in advanceiIs composed of
In the formula, TmRepresents the importance of the mth bar fuzzy condition;
s42, evaluating coefficients G according to all the areasiComparing with a preset value, GiAnd outputting and displaying the risk level corresponding to the area with the value greater than or equal to the preset value, the corresponding future passenger flow inlet and outlet volume estimation and station evacuation time estimation.
The information required to be displayed can be screened out by evaluating the coefficient, irrelevant information is omitted, and the reading amount of a user is saved.
Compared with the embodiment 3, the device provided by the embodiment can better quantify risk factors, future passenger flows and evacuation time through evaluating the coefficients, so that the analysis result is accurately predicted, and the analysis efficiency is improved.
Those skilled in the art will appreciate that all or part of the flow of the method implementing the above embodiments may be implemented by a computer program, which is stored in a computer readable storage medium, to instruct related hardware. The computer readable storage medium is a magnetic disk, an optical disk, a read-only memory or a random access memory.
The above description is only for the preferred embodiment of the present invention, but the scope of the present invention is not limited thereto, and any changes or substitutions that can be easily conceived by those skilled in the art within the technical scope of the present invention are included in the scope of the present invention.
Claims (7)
1. A rail transit passenger flow monitoring and early warning method based on a fuzzy theory is characterized by comprising the following steps:
collecting passenger flow in-out data in each area of the rail transit in real time;
acquiring environmental factors in each region in real time, and quantizing each environmental factor respectively;
fuzzification processing is respectively carried out on passenger flow inlet and outlet data and data after environmental factor quantification in each area of the rail transit, the obtained fuzzification processing result is input into a fuzzy inference judgment machine which is trained in advance, and risk levels faced by each area, future passenger flow inlet and outlet amount estimation and station evacuation time estimation are generated;
the fuzzy inference judging machine is trained, and the method comprises the following steps:
setting a representation input X in a fuzzy inference engineiAnd output YjAll fuzzy conditions of possible relationships; the format of the fuzzy condition comprises: if X is1＝A1，…，Xi＝Ai，…，Xn＝AnThen Y is1＝B1，…，Yj＝Bj，…，Ym＝Bm(ii) a Wherein n represents the number of inputs and m represents the number of outputs; a. thei、BjRespectively representing fuzzification processing results of input data and output data;
acquiring historical passenger flow in-and-out data and environmental factor quantitative data in each area of the rail transit as input data for training, and acquiring corresponding historical risk levels, passenger flow in-and-out amount in preset time and station evacuation time as output data for training;
fuzzifying the input data for training and the output data for training respectively, inputting the obtained fuzzification result into a fuzzy inference judgment machine to train the set fuzzy conditions, obtaining the confidence coefficient of each fuzzy condition, removing the fuzzy conditions with the confidence coefficient lower than a preset value, reserving the fuzzy conditions with the confidence coefficient more than or equal to the preset value, completing the screening of the fuzzy conditions, and further completing the training of the fuzzy inference judgment machine;
confidence S (R) of each of the fuzzy conditionsm) Is calculated by the following formula
S(Rm)＝S(A0,Ax)⊙S(B0,Bx)…⊙S(a0,ax)⊙S(b0,bx)…
Wherein
In the formula, K0A fuzzy value, K, representing a fuzzy variable in the fuzzy conditionxRepresenting each element of the fuzzy set corresponding to the fuzzy variable, mu representing the membership degree of the fuzzy variable, v representing the non-membership degree of the fuzzy variable, Kx(mu) a membership function, K, of said fuzzy variablex(v) A non-membership function, S (K), representing said fuzzy variable0,Kx) Represents K0And KxThe similarity of two fuzzy values, A, B, …, a and b …, represents all fuzzy variables related to fuzzy conditions, A, B and … represent inputs, a and b … represent outputs, Abs () represents absolute value calculation, and ⊙ represents large or small calculation;
obtaining the evaluation coefficient G of each region according to each fuzzy condition trained in advanceiIs composed of
In the formula, TmDenotes the importance of the mth fuzzy condition, S (R)m) Watch (A)Showing the confidence coefficient of the mth fuzzy condition, wherein n represents the fuzzy condition number in the fuzzy inference judgment machine, and m is a variable in summation operation and represents the calculation of the mth fuzzy condition;
according to the evaluation coefficient G of each regioniComparing with the preset value to determine GiThe risk level corresponding to the area larger than or equal to the preset value;
g is to beiAnd comparing the risk grade corresponding to the area larger than or equal to the preset value with the preset value to judge whether to send out acousto-optic early warning, when the risk grade is larger than the preset value, judging to send out acousto-optic early warning of the corresponding grade, and otherwise, not sending out the early warning.
2. The track traffic passenger flow monitoring and early warning method based on the fuzzy theory as claimed in claim 1, wherein the passenger flow in and out data comprises at least one of line transfer amount, station transfer amount, transfer passage passenger flow amount, station in and out peak hour coefficient, line net in and out peak hour coefficient, transfer station peak hour coefficient and hot spot area classification;
the environmental factors include at least one of weather conditions, mass transit congestion conditions, whether there is significant activity, whether there is holiday conditions.
3. The rail transit passenger flow monitoring and early warning method based on the fuzzy theory as claimed in claim 2, wherein the fuzzification processing is carried out by the following steps:
respectively taking the passenger flow inlet and outlet data in each region and the quantized data of the environmental factors as fuzzy variables, and respectively fuzzifying each fuzzy variable to obtain a corresponding fuzzy set;
and calculating a membership function and a non-membership function of the fuzzy set in the domain corresponding to each fuzzy variable as fuzzification processing results, and sending the fuzzification processing results as fuzzy inference input to a fuzzy inference judgment machine.
4. The utility model provides a track traffic passenger flow monitoring early warning system based on fuzzy theory which characterized in that includes:
the data acquisition equipment is used for acquiring passenger flow in and out data in each area of the rail transit in real time;
the environment factor acquisition module is used for acquiring environment factors in each area at the current moment and quantizing the environment factors respectively;
the data processing module is used for respectively carrying out fuzzification processing on the passenger flow inlet and outlet data and the data after the environmental factor quantification in each area, inputting the obtained fuzzification processing result into a fuzzy inference judgment machine trained in advance, and generating the risk level faced by each area, future passenger flow inlet and outlet volume estimation and station evacuation time estimation;
after the fuzzy inference judgment machine obtains the risk level faced by each area, the future passenger flow inlet and outlet volume estimation and the station evacuation time estimation, the following procedures are also executed:
obtaining the evaluation coefficient G of each region according to each fuzzy condition trained in advanceiIs composed of
In the formula, TmDenotes the importance of the mth fuzzy condition, S (R)m) Representing the confidence coefficient of the mth fuzzy condition, n representing the fuzzy condition number in the fuzzy inference judgment machine, m being a variable in summation operation and representing the calculation of the mth fuzzy condition;
wherein the confidence S (R) of the m-th fuzzy conditionm) Is calculated by the following formula
S(Rm)＝S(A0,Ax)⊙S(B0,Bx)…⊙S(a0,ax)⊙S(b0,bx)…
Wherein
In the formula, K0Indicating the fuzzy conditionFuzzy value of medium fuzzy variable, KxRepresenting each element of the fuzzy set corresponding to the fuzzy variable, mu representing the membership degree of the fuzzy variable, v representing the non-membership degree of the fuzzy variable, Kx(mu) a membership function, K, of said fuzzy variablex(v) A non-membership function, S (K), representing said fuzzy variable0,Kx) Represents K0And KxThe similarity of two fuzzy values, A, B, …, a and b …, represents all fuzzy variables related to fuzzy conditions, A, B and … represent inputs, a and b … represent outputs, Abs () represents absolute value calculation, and ⊙ represents large or small calculation;
according to the evaluation coefficient G of each regioniComparing with a preset value, GiOutputting and displaying the risk level corresponding to the area with the value greater than or equal to the preset value, and corresponding future passenger flow inlet and outlet volume estimation and station evacuation time estimation;
and the monitoring and early warning module is used for comparing the risk level output by the data processing module with a preset value to judge whether to send out acousto-optic early warning, and when the risk level is greater than the preset value, judging to send out acousto-optic early warning of a corresponding level, otherwise, not carrying out early warning.
5. The fuzzy theory based rail transit passenger flow monitoring and early warning system as claimed in claim 4, further comprising:
and the statistical analysis module is used for obtaining line transfer amount, station transfer amount, transfer channel passenger flow amount, station in-out peak hour coefficient, line in-out peak hour coefficient, transfer station in-out peak hour coefficient and hot spot area classification according to the passenger flow in-out data in each area of the rail transit collected by the data collection equipment, and outputting the data to the data processing module as the passenger flow in-out data in each area.
6. The track traffic passenger flow monitoring and early warning system based on the fuzzy theory as claimed in claim 4 or 5, wherein the data processing module comprises;
the input data fuzzification module is used for fuzzifying each fuzzy variable by taking the passenger flow inlet and outlet data and the quantized data of the environmental factors in each area as fuzzy variables respectively to obtain corresponding fuzzy sets respectively, calculating a membership function and a non-membership function of the fuzzy set corresponding to each fuzzy variable in a domain as fuzzification processing results, and sending the fuzzification processing results as fuzzy inference input to the fuzzy inference judgment machine;
and the fuzzy inference judgment machine is used for obtaining the risk level of each area, future passenger flow inlet and outlet volume estimation and station evacuation time estimation according to the input fuzzification processing result and each pre-trained fuzzy condition.
7. The fuzzy theory based rail transit passenger flow monitoring and early warning system as claimed in claim 6, wherein the data processing module further comprises:
the training data fuzzification module is used for fuzzifying the passenger flow inlet and outlet data in each area and the quantized data of the environmental factors in the training data as input when the fuzzy inference judgment machine is trained, fuzzifying the actual risk level of each area, the future passenger flow data and the station evacuation time as output respectively, inputting the input and the output into the fuzzy inference judgment machine to train preset fuzzy conditions, obtaining the confidence coefficient of each fuzzy condition, removing the fuzzy conditions with the confidence coefficient lower than a preset value, and keeping the fuzzy conditions with the confidence coefficient larger than or equal to the preset value as the trained fuzzy conditions.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910680632.XA CN110400462B (en) | 2019-07-26 | 2019-07-26 | Track traffic passenger flow monitoring and early warning method and system based on fuzzy theory |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910680632.XA CN110400462B (en) | 2019-07-26 | 2019-07-26 | Track traffic passenger flow monitoring and early warning method and system based on fuzzy theory |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110400462A CN110400462A (en) | 2019-11-01 |
| CN110400462B true CN110400462B (en) | 2020-06-16 |
Family
ID=68325068
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910680632.XA Active CN110400462B (en) | 2019-07-26 | 2019-07-26 | Track traffic passenger flow monitoring and early warning method and system based on fuzzy theory |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110400462B (en) |
Families Citing this family (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112365092A (en) * | 2020-12-01 | 2021-02-12 | 北京交通大学 | Urban rail transit road network large passenger flow risk self-adaptive pre-warning system |
| CN112862196A (en) * | 2021-02-19 | 2021-05-28 | 青岛理工大学 | Subway platform passenger distribution prediction system based on fuzzy logic theory |
| CN113628432B (en) * | 2021-10-13 | 2022-01-04 | 中通服建设有限公司 | Intelligent early warning system for subway people flow current limiting |
| CN114066038A (en) * | 2021-11-10 | 2022-02-18 | 上海市大数据股份有限公司 | Subway passenger flow prediction method and system |
Family Cites Families (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2827045B2 (en) * | 1990-09-05 | 1998-11-18 | 技術研究組合国際ファジィ工学研究所 | Fuzzy control method |
| CN102117510B (en) * | 2011-04-01 | 2012-12-12 | 上海电科智能系统股份有限公司 | Unknown transportation mean passenger source predictive method in big activities |
| CN104573873B (en) * | 2015-01-23 | 2017-08-25 | 哈尔滨工业大学 | A kind of terminal passenger departure's method for predicting based on fuzzy decision-tree |
| CN106651182B (en) * | 2016-12-25 | 2020-09-25 | 北京工业大学 | Entropy weight-based rail passenger flow congestion risk evaluation method |
| CN107273999B (en) * | 2017-04-27 | 2020-12-08 | 北京交通大学 | Urban rail transit passenger flow prediction method under emergency |
| CN107145985A (en) * | 2017-05-09 | 2017-09-08 | 北京城建设计发展集团股份有限公司 | A kind of urban track traffic for passenger flow Regional Linking method for early warning |
| CN109886444B (en) * | 2018-12-03 | 2023-07-11 | 深圳市北斗智能科技有限公司 | Short-time traffic passenger flow prediction method, device, equipment and storage medium |
-
2019
- 2019-07-26 CN CN201910680632.XA patent/CN110400462B/en active Active
Non-Patent Citations (1)
| Title |
|---|
| 基于广义动态模糊神经网络的;李春晓等;《学术探讨》;20150831;全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110400462A (en) | 2019-11-01 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110400462B (en) | Track traffic passenger flow monitoring and early warning method and system based on fuzzy theory | |
| CN109448361B (en) | Resident traffic travel flow prediction system and prediction method thereof | |
| CN111583639B (en) | Road traffic jam early warning method and system | |
| CN101710448B (en) | Road traffic state detecting device based on omnibearing computer vision | |
| Mazloumi et al. | An integrated framework to predict bus travel time and its variability using traffic flow data | |
| CN108648445B (en) | Dynamic traffic situation prediction method based on traffic big data | |
| CN109887283B (en) | Road congestion prediction method, system and device based on checkpoint data | |
| Li et al. | Identifying important variables for predicting travel time of freeway with non-recurrent congestion with neural networks | |
| CN101930668A (en) | Road traffic OD (Optical Density) information collection system for license plate recognition and processing method thereof | |
| CN113177657B (en) | Rail transit passenger flow prediction method and device | |
| KR20150072471A (en) | Traffic flow prediction system using spatiotemporal stochastic model | |
| CN112863182B (en) | Cross-modal data prediction method based on transfer learning | |
| Ram et al. | SMARTBUS: A web application for smart urban mobility and transportation | |
| CN114328675A (en) | Bus travel time prediction method based on double-attention machine system and bidirectional double-layer LSTM | |
| Padiath et al. | Prediction of traffic density for congestion analysis under Indian traffic conditions | |
| CN110021161A (en) | A kind of prediction technique and system of traffic direction | |
| CN116913088A (en) | Intelligent flow prediction method for expressway | |
| CN115995149A (en) | Multi-source data-based parking supply and demand characteristic dynamic evaluation method and system | |
| KR102359902B1 (en) | Crossroads LOS Prediction Method Based on Big Data and AI, and Storage Medium Having the Same | |
| CN117351702A (en) | Intelligent traffic management method based on adjustment of traffic flow | |
| CN117218836A (en) | Urban planning project comprehensive management information platform based on smart city | |
| Arsenio et al. | Assessing multimodal mobility trends using heterogeneous data sources: a case study for supporting sustainable policy goals within the region of Algarve | |
| CN116523093A (en) | Grid demand sensing system and method of energy system based on random source load prediction | |
| KR20150072470A (en) | System for analyzing dependence of spatiotemporal domain of traffic flow on the city and highway | |
| CN114139984A (en) | Urban traffic accident risk prediction method based on flow and accident collaborative perception |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |