Intelligent Scheduling System and Method for Vehicle Barrier Gate Passage Based on Big Data

Abstract

The present invention relates to the technical field of vehicle scheduling, and discloses an intelligent scheduling system and method for vehicle barrier access based on big data. First, the present invention divides the initial vehicle barrier access data set to obtain a frequently used vehicle barrier access data set and an infrequently used vehicle barrier access data set, and then performs preprocessing; secondly, a neural network is constructed, and according to the frequently used vehicle barrier access data set, a predicted value is output; then, a vehicle barrier access objective function is established based on the predicted value, and the multi-strategy fusion Genghis shark optimization algorithm is used to solve the vehicle barrier access objective function to obtain a global optimal solution and generate a vehicle barrier access scheduling plan; finally, by using the infrequently used vehicle barrier access data set, the vehicle barrier access scheduling plan is adjusted in real time. The present invention realizes the purpose of intelligent scheduling of vehicle barrier access by analyzing and processing vehicle barrier access data, and the method is accurate and objective.

Description

Technical Field

[0001] The present invention relates to the technical field of vehicle scheduling, and specifically to a vehicle gate passage intelligent scheduling system and method based on big data. Background Art

[0002] Chinese patent CN115641750B discloses a Beidou-based ship navigation scheduling method and system. The method specifically includes: using a Beidou communication device to obtain the number of ships and ship position information within a waterway; using the Beidou communication device to divide the waterway into several areas; calculating the congestion density in the several areas based on the number of ships and ship position information to obtain the congestion density within the waterway; then obtaining the ship flow rate and average ship speed within the waterway; combining the congestion density to establish a waterway state model and output a waterway state result; setting a state threshold, comparing the waterway state result with the state threshold, determining the navigation state, and completing ship navigation scheduling. This invention only performs scheduling based on congestion density, and the effectiveness and applicability of the scheduling method need to be improved.

[0003] Traditional vehicle gate traffic scheduling methods usually require vehicle inspections, which often lead to traffic congestion and even vehicle accidents. At the same time, due to the lack of the use of big data, artificial intelligence and other technologies, dynamic real-time scheduling cannot be achieved during the vehicle gate traffic scheduling process, and there is room for improvement in shortening vehicle congestion time and improving traffic capacity. Summary of the Invention

[0004] In response to the problems in the related art, the present invention provides a vehicle gate passage intelligent scheduling system and method based on big data to overcome the above-mentioned technical problems existing in the existing related art.

[0005] To solve the above technical problems, the present invention is achieved through the following technical solutions:

[0006] The present invention is a method for intelligently dispatching vehicle gate passage based on big data, comprising the following steps:

[0007] S1. Obtaining vehicle entry and exit gate passage records to obtain an initial vehicle gate passage data set, identifying and preprocessing a frequently used vehicle gate passage data set and an infrequently used vehicle gate passage data set in the initial vehicle gate passage data set to obtain a processed vehicle gate passage data set;

[0008] S2. Based on the processed vehicle gate passage data set, predict the vehicle gate passage flow and vehicle gate anomaly based on a neural network and a time series, respectively, to obtain a vehicle gate passage flow prediction value set and a vehicle gate anomaly prediction value set;

[0009] S3. Based on the predicted vehicle access flow value set and the predicted vehicle access anomaly set of the vehicle access control, establish a vehicle access control objective function based on the principle of the best access control capacity, and use the multi-strategy fusion Genghis Khan shark optimization algorithm to solve the vehicle access control objective function to obtain the global optimal solution;

[0010] S4. Generate a vehicle access control scheduling plan according to the global optimal solution, and introduce the set of vehicle access data for infrequently used vehicle access controls to adjust the vehicle access control scheduling plan in real time to obtain the final vehicle access control scheduling plan.

[0011] The present invention obtains the initial vehicle access control data set, identifies the commonly used vehicle access control data and the infrequently used vehicle access control data, and preprocesses the commonly used vehicle access control data; this method only processes the commonly used data through data partitioning, reducing the data processing time-consuming. After data preprocessing, the data validity and accuracy are improved, and the subsequent prediction error is reduced; secondly, the vehicle access control flow and vehicle access anomalies are predicted based on neural networks and time series respectively to obtain the prediction results. Since there are few vehicle access anomalies and they do not have good predictability, it is easy to find the change rules according to the time series and the cumulative flow, improving the prediction effect; the LSTM recurrent neural network overcomes the problems of gradient disappearance and gradient explosion, can determine the time lag length, and has good prediction performance; then establish a vehicle access control objective function, and use the multi-strategy fusion Genghis Khan shark optimization algorithm to solve the vehicle access control objective function to obtain the global optimal solution; the objective function models the optimization problem, facilitating algorithm optimization. The multi-strategy fusion Genghis Khan shark optimization algorithm searches for the optimal solution by simulating the predation and survival behaviors. Compared with traditional algorithms, it avoids falling into local optimal solutions during the iteration process, speeds up the convergence speed, improves the population quality and exploration ability during the iteration process, shortens the vehicle congestion time, and effectively improves the vehicle access control efficiency; finally, generate a vehicle access control scheduling plan and adjust the vehicle access control scheduling plan in real time, considering special vehicles and emergencies, reducing the occurrence of vehicle accidents, and improving the reliability of the scheduling plan.

[0012] Preferably, the S1 includes the following steps:

[0013] S11. Obtain the access records of vehicles entering and leaving the access control. The historical access records of vehicles entering and leaving the access control include vehicle license plate information, vehicle entry and exit times, vehicle type information, etc., which are recorded as vehicle access control related information to obtain vehicle access control data; use the vehicle license plate information in the vehicle access control data as the main body to construct an initial vehicle access control data set , where represents the ma subset of vehicle barrier passing data, where the subset of vehicle barrier passing data is vehicle license plate information, and under each vehicle license plate information, there is other vehicle barrier passing data;

[0014] S12. Obtain the vehicle entry and exit times in the initial set of vehicle barrier passing data. Within the time period t, count the number of vehicle entry and exit times. Based on the time period t and the number of vehicle entry and exit times, calculate the vehicle barrier passing frequency. Set a frequency threshold. When the vehicle barrier passing frequency is greater than the frequency threshold, record the corresponding vehicle license plate information as frequently used vehicles to obtain a set of frequently used vehicle barrier passing data, otherwise record the corresponding vehicle license plate information as infrequently used vehicles to obtain a set of infrequently used vehicle barrier passing data;

[0015] S13. Preprocess the set of frequently used vehicle barrier passing data, delete the abnormal vehicle barrier passing data in the set of frequently used vehicle barrier passing data, and perform filling. Convert the set of frequently used vehicle barrier passing data into a processed set of vehicle barrier passing data. The specific steps are as follows:

[0016] S131. Within the time period t, divide the time period t by month to obtain a set of vehicle barrier passing months , where represents the n th vehicle barrier passing month; Calculate the average value and standard deviation of the vehicle barrier passing data in each vehicle barrier passing month according to the set of vehicle barrier passing months in the initial set of vehicle barrier passing data, and delete the vehicle barrier passing data corresponding to the maximum standard deviation and the minimum standard deviation. Set an average threshold. When the difference between the average value of the vehicle barrier passing data and the vehicle barrier passing data is less than or equal to the average threshold, the corresponding vehicle barrier passing data is recorded as normal vehicle barrier passing data, otherwise obtain abnormal vehicle barrier passing data and delete the abnormal vehicle barrier passing data to obtain a processed set of vehicle barrier passing data;

[0017] S132. Select any vehicle barrier passing month in the set of vehicle barrier passing months, denoted as vehicle barrier passing month , and then select the adjacent vehicle barrier passing months of vehicle barrier passing month ; In the processed set of vehicle barrier passing data, count the missing vehicle barrier passing data in vehicle barrier passing month , calculate the average value of the vehicle barrier passing data in the adjacent vehicle barrier passing months, and use the average value of the vehicle barrier passing data to fill the missing vehicle barrier passing data in vehicle barrier passing month ; Fill the missing vehicle barrier passing data in other vehicle barrier passing months in turn to obtain a processed set of vehicle barrier passing data.

[0018] The invention obtains the access data of common vehicle gate barriers and the access data of uncommon vehicle gate barriers through recognition, only processes the common data through data division, reduces the time consumption of data processing, preprocesses the access data of common vehicle gate barriers, improves the effectiveness and accuracy of the data, and reduces the subsequent prediction error.

[0019] Preferably, S2 includes the following steps:

[0020] S21. Obtain the operation information of the vehicle gate barrier in the processed vehicle gate barrier access data set. The operation information of the vehicle gate barrier includes the normal operation and the failure of the vehicle gate barrier. Divide the processed vehicle gate barrier access data set into a vehicle gate barrier access normal operation data set and a vehicle gate barrier access failure data set according to the operation information of the vehicle gate barrier;

[0021] S22. For the vehicle gate barrier access normal operation data set, train an LSTM recurrent neural network prediction model to predict the vehicle gate barrier access flow and obtain a vehicle gate barrier access flow prediction value set. The specific steps are as follows:

[0022] S221. Obtain the vehicle entry and exit time and the number of vehicle entries and exits in the vehicle gate barrier access normal operation data set. Use the vehicle entry and exit time as a time series to obtain a vehicle gate barrier access time series , where represents the th vehicle gate barrier access time point; According to the number of vehicle entries and exits, calculate the vehicle gate barrier access flow between each vehicle gate barrier access time point in turn to obtain a vehicle gate barrier access flow set. Each vehicle gate barrier access flow in the vehicle gate barrier access flow set corresponds to a vehicle gate barrier access time point;

[0023] S222. Obtain the historical access records of the vehicle entering and exiting the gate barrier again to obtain a vehicle gate barrier access historical data set. Preprocess the vehicle gate barrier access historical data set and calculate the vehicle gate barrier access historical flow to obtain a vehicle gate barrier access historical time series and a vehicle gate barrier access flow sample set. Divide the vehicle gate barrier access flow sample set into a sample training set and a sample test set; Set the LSTM recurrent neural network to learn according to the stochastic gradient descent method, set a time sliding window, place the time sliding window on the vehicle gate barrier access historical time series, obtain the sample training set included in the vehicle gate barrier access historical time series within the time sliding window, and input it into the LSTM recurrent neural network in turn for iteration until the LSTM recurrent neural network converges to obtain a trained LSTM recurrent neural network;

[0024] S223. Place the time sliding window on the vehicle gate passing historical time series to obtain a sample test set included in the vehicle gate passing historical time series within the time sliding window, and input it into the trained LSTM recurrent neural network in sequence. Set an accuracy threshold. When the accuracy of the output prediction value is greater than the accuracy threshold, obtain the LSTM recurrent neural network prediction model; otherwise, adjust the weights until the accuracy of the output prediction value is greater than the accuracy threshold.

[0025] S224. According to the vehicle gate passing time series, input the vehicle gate passing flow rate set into the LSTM recurrent neural network prediction model, and output the vehicle gate passing flow rate prediction values in sequence to form a vehicle gate passing flow rate prediction value set.

[0026] S23. For the vehicle gate passing fault data set, set the vehicle gate fault time, and use the vehicle gate fault time as the time series to obtain the vehicle gate passing fault time series , where represents the th vehicle gate fault time; calculate the vehicle gate passing flow rate between each vehicle gate fault time, and accumulate it according to the vehicle gate passing fault time series to obtain the vehicle gate passing accumulated flow rate; use the vehicle gate passing fault time series as the abscissa and the vehicle gate passing accumulated flow rate as the ordinate to generate an accumulated flow rate graph. Select the curve segment corresponding to the minimum curve slope in the accumulated flow rate graph, denote it as the sample curve segment, determine the smoothing coefficient, and use the least squares method to fit the sample curve segment to obtain the vehicle gate fault time prediction value. Denote the vehicle gate fault time prediction value as the vehicle gate anomaly prediction value to form a vehicle gate anomaly prediction value set.

[0027] This invention predicts the vehicle gate passing flow rate and vehicle gate anomalies respectively based on neural networks and time series. Since there are few vehicle gate anomalies and they do not have good predictability, it is easy to find the change law according to the time series and accumulated flow rate, improving the prediction effect; the LSTM recurrent neural network overcomes the problems of gradient disappearance and gradient explosion, can determine the time lag length, and has good prediction performance.

[0028] Preferably, the S3 includes the following steps:

[0029] S31. Set the vehicle gate passing quantity as , combining the vehicle gate traffic flow prediction value set and the vehicle gate abnormality prediction value set, based on the optimal gate traffic capacity principle, determining the average vehicle speed, obtaining the vehicle gate traffic average delay time function and the vehicle gate traffic queue length function; selecting the minimum value of the vehicle gate traffic average delay time function and the minimum value of the vehicle gate traffic queue length function as the vehicle gate traffic objective function, and introducing a constraint condition to satisfy the vehicle gate opening time being less than or equal to the vehicle gate maximum opening time;

[0030] S32. Introduce the Genghis Khan Shark Optimization Algorithm, and integrate the inferior individual classification strategy and the quasi-adversarial learning strategy to improve the Genghis Khan Shark Optimization Algorithm to obtain a multi-strategy fusion Genghis Khan Shark Optimization Algorithm. Use the multi-strategy fusion Genghis Khan Shark Optimization Algorithm to solve the vehicle gate passage objective function and obtain the global optimal solution. The specific steps are as follows:

[0031] S321. The process of solving the objective function of vehicle barrier passage is regarded as a search space. There is a Genghis Khan shark population in the search space. The Genghis Khan shark individuals in the Genghis Khan shark population represent candidate solutions of the objective function of vehicle barrier passage. The number of Genghis Khan shark population is set to i , the individual dimension of Genghis Khan shark is j , set the current number of iterations to b , initialize the Genghis Khan shark population, and get the b +1 iteration i Genghis Khan shark individual locations During the migration phase, the Genghis Khan shark population updates its position based on the concentration of prey odor. The odor intensity coefficient is set to , c represents a non-negative constant, represents a random number between the interval [0, 1], then the olfactory intensity , set the b The optimal Genghis Khan shark individual position at the iteration is , No. b The first iteration i Genghis Khan shark individual locations , get the b +1 iteration i New location of Genghis Khan shark , at this time the position To update, ;

[0032] Get the fitness function value corresponding to the position of the Genghis Khan shark at this time, and record the current best fitness function value and the current worst fitness function value as and , No.i The fitness function value corresponding to the Genghis Khan shark individual is recorded as , introduce the inferior individual classification strategy, calculate pheromone , when the pheromone is less than or equal to 0.3, select Genghis Khan shark individual locations Hedi Genghis Khan shark individual locations , for position Update and set Indicates a random number of 0 or 1. ;

[0033] S322, Genghis Khan shark population is in the foraging stage, set the step length parameter to , based on the optimal Genghis Khan shark individual position Position Update again, this time introduce the quasi-adversarial learning strategy, set the upper and lower bounds of the search space to be and , dual value , dual position , calculate the fitness function value corresponding to the dual position, and compare it with the current best fitness function, and use the dual position to replace the position , to achieve position Updates;

[0034] In the self-protection stage of the Genghis Khan shark population, the Genghis Khan shark individuals use self-protection strategies to position Update to get b +1 iteration i The final position of the Genghis Khan shark individual is obtained, the Genghis Khan shark population is screened, and the next iteration is entered; the maximum number of iterations is set, and when the current number of iterations reaches the maximum number of iterations, the iteration is stopped to obtain the global best position, which is the global optimal solution.

[0035] This invention establishes a vehicle barrier passage objective function and uses the Genghis Khan shark optimization algorithm with multi-strategy fusion to solve the vehicle barrier passage objective function, modeling the optimization problem to facilitate algorithm optimization processing. Compared with traditional algorithms, the Genghis Khan shark optimization algorithm with multi-strategy fusion avoids falling into local optimal solutions during the iteration process, accelerates the convergence speed, improves the population quality and exploration ability of the iteration process, shortens vehicle congestion time, and effectively improves the vehicle barrier passage efficiency.

[0036] Preferably, the S4 comprises the following steps:

[0037] S41. The global optimal solution of the vehicle gate passing objective function is obtained to get the minimum value of the average delay time function of vehicle gate passing and the minimum value of the queuing length function of vehicle gate passing, and a vehicle gate opening time scheduling scheme and a vehicle gate passing quantity scheduling scheme are generated. The vehicle gate controls the opening of the vehicle gate according to the vehicle gate opening time scheduling scheme, and the vehicle gate controls the passing quantity of the vehicle gate according to the vehicle gate passing quantity scheduling scheme, so as to obtain a vehicle gate passing scheduling scheme.

[0038] S42. According to the set of passing data of the infrequently used vehicle gates, the vehicle entry and exit times and vehicle type information of the infrequently used vehicles are obtained, and priorities are set according to the vehicle type information to obtain high-priority vehicles and low-priority vehicles. When a high-priority vehicle passes through the vehicle gate, the passing quantity of the vehicle gate is increased or the opening time of the vehicle gate is extended, and the vehicle gate passing scheduling scheme is adjusted in real time to obtain the final vehicle gate passing scheduling scheme.

[0039] The present invention reduces the occurrence of vehicle accidents and improves the reliability of the scheduling scheme by generating a vehicle gate passing scheduling scheme, adjusting the vehicle gate passing scheduling scheme in real time, and considering special vehicles and emergencies.

[0040] This embodiment also discloses a system for an intelligent scheduling method for vehicle gate passing based on big data, which specifically includes: a passing data division and processing module, a passing flow and anomaly prediction module, an objective function solving module, and a passing scheduling scheme generation module.

[0041] The passing data division and processing module is used to divide the initial vehicle gate passing data according to whether it is frequently used and perform preprocessing.

[0042] The passing flow and anomaly prediction module is used to predict the passing flow of the vehicle gate and the anomalies of the vehicle gate.

[0043] The objective function solving module is used to solve the vehicle gate passing objective function using a multi-strategy fusion Genghis Khan shark optimization algorithm.

[0044] The passing scheduling scheme generation module is used to generate and adjust the vehicle gate passing scheduling scheme.

[0045] The present invention has the following beneficial effects:

[0046] 1. By identifying the frequently used vehicle gate passing data and the infrequently used vehicle gate passing data, and only processing the frequently used data through data division, the present invention reduces the time-consuming of data processing, preprocesses the frequently used vehicle gate passing data, improves the effectiveness and accuracy of the data, and reduces the subsequent prediction error.

[0047] 2. This invention predicts vehicle gate traffic flow and vehicle gate anomalies based on neural networks and time series respectively. Since vehicle gate anomalies are rare and not very predictive, it is easier to find the changing patterns based on time series and accumulated flow, thereby improving the prediction effect. The LSTM recurrent neural network overcomes the problems of gradient vanishing and gradient exploding, can determine the length of time lag, and has good prediction performance.

[0048] 3. This invention establishes a vehicle barrier passage objective function, uses the multi-strategy fusion Genghis Khan shark optimization algorithm to solve the vehicle barrier passage objective function, models the optimization problem, and facilitates algorithm optimization processing. Compared with traditional algorithms, the multi-strategy fusion Genghis Khan shark optimization algorithm avoids falling into local optimal solutions during the iteration process, accelerates the convergence speed, improves the population quality and exploration ability of the iteration process, shortens vehicle congestion time, and effectively improves the vehicle barrier passage efficiency.

[0049] 4. The invention generates a vehicle gate passage scheduling plan, adjusts the vehicle gate passage scheduling plan in real time, takes special vehicles and emergencies into consideration, reduces vehicle accidents, and improves the reliability of the scheduling plan.

[0050] Of course, any product implementing the present invention does not necessarily need to achieve all of the advantages described above at the same time. BRIEF DESCRIPTION OF THE DRAWINGS

[0051] In order to more clearly illustrate the technical solutions of the embodiments of the invention, the following briefly introduces the drawings required for describing the embodiments. Obviously, the drawings described below are only some embodiments of the invention. For ordinary technicians in this field, they can also obtain drawings based on these drawings without paying any creative work.

[0052] Figure 1 The present invention provides a flow chart of the intelligent scheduling of vehicle gate passage in the vehicle gate passage intelligent scheduling system based on big data. DETAILED DESCRIPTION

[0053] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making any creative efforts shall fall within the scope of protection of the present invention.

[0054] In the description of the present invention, it should be understood that the terms "open hole", "upper", "lower", "top", "middle", "inner", etc. indicating orientation or positional relationships are only for the convenience of describing the invention and simplifying the description, rather than indicating or implying that the components or elements referred to must have a specific orientation, be constructed and operated in a specific orientation, and thus should not be construed as a limitation to the invention.

[0055] Embodiment 1

[0056] Please refer to Figure 1 , this embodiment discloses an intelligent scheduling method for vehicle gate access based on big data, which specifically includes the following content:

[0057] S1. Obtain the access records of vehicles entering and leaving the gate to obtain the initial vehicle gate access data set, identify and preprocess the common vehicle gate access data set and the uncommon vehicle gate access data set in the initial vehicle gate access data set, and obtain the processed vehicle gate access data set;

[0058] The S1 includes the following steps:

[0059] S11. Obtain the access records of vehicles entering and leaving the gate. The historical access records of vehicles entering and leaving the gate include vehicle license plate information, vehicle access time, vehicle type information, etc., which are recorded as vehicle gate access related information to obtain vehicle gate access data; taking the vehicle license plate information in the vehicle gate access data as the main body, construct the initial vehicle gate access data set , where represents the m th vehicle gate access data subset, and the vehicle gate access data subset is the vehicle license plate information, and each vehicle license plate information includes other vehicle gate access data;

[0060] S12. Obtain the vehicle access time in the initial vehicle gate access data set, count the number of vehicle access times within the time period t, and calculate the vehicle gate access frequency according to the time period t and the number of vehicle access times; set a frequency threshold, when the vehicle gate access frequency is greater than the frequency threshold, record the corresponding vehicle license plate information as a common vehicle to obtain the common vehicle gate access data set, otherwise record the corresponding vehicle license plate information as an uncommon vehicle to obtain the uncommon vehicle gate access data set;

[0061] S13. Preprocess the common vehicle gate access data set, delete the abnormal vehicle gate access data in the common vehicle gate access data set and fill it, and convert the common vehicle gate access data set into a processed vehicle gate access data set. The specific steps are as follows:

[0062] S131. Within the time period t, divide the time period t by month to obtain the vehicle gate passing month set , where represents the n th vehicle gate passing month; calculate the average value and standard deviation of the vehicle gate passing data in each vehicle gate passing month according to the vehicle gate passing month set of the initial vehicle gate passing data set, and delete the vehicle gate passing data corresponding to the maximum standard deviation and the minimum standard deviation; set an average threshold. When the difference between the average value of the vehicle gate passing data and the vehicle gate passing data is less than or equal to the average threshold, the corresponding vehicle gate passing data is recorded as normal vehicle gate passing data, otherwise obtain abnormal vehicle gate passing data, and delete the abnormal vehicle gate passing data to obtain the processed vehicle gate passing data set;

[0063] S132. Select any vehicle gate passing month in the vehicle gate passing month set, denoted as the vehicle gate passing month , and then select the adjacent vehicle gate passing month of the vehicle gate passing month ; in the processed vehicle gate passing data set, count the missing vehicle gate passing data in the vehicle gate passing month , calculate the average value of the vehicle gate passing data in the adjacent vehicle gate passing month, and use the average value of the vehicle gate passing data to fill the missing vehicle gate passing data in the vehicle gate passing month , and fill the missing vehicle gate passing data of other vehicle gate passing months in turn to obtain the processed vehicle gate passing data set;

[0064] S2. Based on the processed vehicle gate passing data set, predict the vehicle gate passing flow and vehicle gate anomalies respectively based on the neural network and time series to obtain the vehicle gate passing flow prediction value set and the vehicle gate anomaly prediction value set;

[0065] The S2 includes the following steps:

[0066] S21. Obtain the vehicle gate operation information in the processed vehicle gate passing data set. The vehicle gate operation information includes normal operation of the vehicle gate and vehicle gate failure. Divide the processed vehicle gate passing data set into a vehicle gate passing normal operation data set and a vehicle gate passing failure data set according to the vehicle gate operation information;

[0067] S22. For the vehicle gate passing normal operation data set, train an LSTM recurrent neural network prediction model to predict the vehicle gate passing flow to obtain the vehicle gate passing flow prediction value set. The specific steps are as follows:

[0068] S221. Obtain the vehicle entry and exit times and the number of vehicle entries and exits in the normal operation data set of the vehicle gate, use the vehicle entry and exit times as a time series to obtain the vehicle gate passage time series , where represents the th vehicle gate passage time point; According to the number of vehicle entries and exits, calculate the vehicle gate passage flow between each vehicle gate passage time point in turn to obtain the vehicle gate passage flow set, and each vehicle gate passage flow in the vehicle gate passage flow set corresponds to a vehicle gate passage time point;

[0069] S222. Obtain the historical passage records of vehicles entering and exiting the gate again to obtain the vehicle gate passage historical data set, preprocess the vehicle gate passage historical data set and calculate the vehicle gate passage historical flow to obtain the vehicle gate passage historical time series and the vehicle gate passage flow sample set, and divide the vehicle gate passage flow sample set into a sample training set and a sample test set; Set the LSTM recurrent neural network to learn according to the stochastic gradient descent method, set the time sliding window, place the time sliding window on the vehicle gate passage historical time series, obtain the sample training set included in the vehicle gate passage historical time series within the time sliding window, and input it into the LSTM recurrent neural network in turn for iteration until the LSTM recurrent neural network converges to obtain a trained LSTM recurrent neural network;

[0070] S223. Place the time sliding window on the vehicle gate passage historical time series, obtain the sample test set included in the vehicle gate passage historical time series within the time sliding window, and input it into the trained LSTM recurrent neural network in turn. Set the accuracy threshold. When the accuracy of the output prediction value is greater than the accuracy threshold, obtain the LSTM recurrent neural network prediction model, otherwise adjust the weights until the accuracy of the output prediction value is greater than the accuracy threshold;

[0071] S224. According to the vehicle gate passage time series, input the vehicle gate passage flow set into the LSTM recurrent neural network prediction model, and output the vehicle gate passage flow prediction values in turn to form a vehicle gate passage flow prediction value set;

[0072] S23. For the vehicle gate passage failure data set, set the vehicle gate failure time, use the vehicle gate failure time as a time series to obtain the vehicle gate passage failure time series , where represents the vehicle barrier failure time; calculating the vehicle barrier flow rate between each vehicle barrier failure time, and accumulating the vehicle barrier flow rate according to the vehicle barrier failure time series to obtain the vehicle barrier flow rate; using the vehicle barrier failure time series as the horizontal coordinate and the vehicle barrier flow rate as the vertical coordinate to generate a cumulative flow rate graph, selecting a curve segment corresponding to the minimum curve slope in the cumulative flow rate graph, recording it as a sample curve segment, determining a smoothing coefficient, and fitting the sample curve segment using the least squares method to obtain a vehicle barrier failure time prediction value, recording the vehicle barrier failure time prediction value as a vehicle barrier abnormality prediction value, and forming a vehicle barrier abnormality prediction value set;

[0073] S3. Based on the vehicle gate flow prediction value set and the vehicle gate anomaly prediction set, a vehicle gate passage objective function is established based on the principle of optimal gate passage capacity, and the vehicle gate passage objective function is solved using the Genghis Khan Shark Optimization Algorithm with multi-strategy fusion to obtain a global optimal solution;

[0074] The S3 includes the following steps:

[0075] S31, set the number of vehicles passing through the gate to , combining the vehicle gate traffic flow prediction value set and the vehicle gate abnormality prediction value set, based on the optimal gate traffic capacity principle, determining the average vehicle speed, obtaining the vehicle gate traffic average delay time function and the vehicle gate traffic queue length function; selecting the minimum value of the vehicle gate traffic average delay time function and the minimum value of the vehicle gate traffic queue length function as the vehicle gate traffic objective function, and introducing a constraint condition to satisfy the vehicle gate opening time being less than or equal to the vehicle gate maximum opening time;

[0076] S32. Introduce the Genghis Khan Shark Optimization Algorithm, and integrate the inferior individual classification strategy and the quasi-adversarial learning strategy to improve the Genghis Khan Shark Optimization Algorithm to obtain a multi-strategy fusion Genghis Khan Shark Optimization Algorithm. Use the multi-strategy fusion Genghis Khan Shark Optimization Algorithm to solve the vehicle gate passage objective function and obtain the global optimal solution. The specific steps are as follows:

[0077] S321. The process of solving the objective function of vehicle barrier passage is regarded as a search space. There is a Genghis Khan shark population in the search space. The Genghis Khan shark individuals in the Genghis Khan shark population represent candidate solutions of the objective function of vehicle barrier passage. The number of Genghis Khan shark population is set to i , the individual dimension of Genghis Khan shark is j , set the current number of iterations to b , initialize the Genghis Khan shark population, and get the b +1 iteration i Genghis Khan shark individual locations During the migration phase, the Genghis Khan shark population updates its position based on the concentration of prey odor. The odor intensity coefficient is set to , c represents a non-negative constant, represents a random number between the interval [0, 1], then the olfactory intensity , set the b The optimal Genghis Khan shark individual position at the iteration is , No. b The first iteration i Genghis Khan shark individual locations , get the b +1 iteration i New location of Genghis Khan shark , at this time the position To update, ;

[0078] Get the fitness function value corresponding to the position of the Genghis Khan shark at this time, and record the current best fitness function value and the current worst fitness function value as and , No. i The fitness function value corresponding to the Genghis Khan shark individual is recorded as , introduce the inferior individual classification strategy, calculate pheromone , when the pheromone is less than or equal to 0.3, select Genghis Khan shark individual locations Hedi Genghis Khan shark individual locations , for position Update and set Indicates a random number of 0 or 1. ;

[0079] S322, Genghis Khan shark population is in the foraging stage, set the step length parameter to , based on the optimal Genghis Khan shark individual position Position Update again, this time introduce the quasi-adversarial learning strategy, set the upper and lower bounds of the search space to be and , dual value , dual position , calculate the fitness function value corresponding to the dual position, and compare it with the current best fitness function, and use the dual position to replace the position , to achieve position Updates;

[0080] In the self-protection stage of the Genghis Khan shark population, the Genghis Khan shark individuals use self-protection strategies to position Update to get b +1 iteration i The final position of the Genghis Khan shark individual is obtained, and the Genghis Khan shark population is screened to enter the next iteration; the maximum number of iterations is set, and when the current number of iterations reaches the maximum number of iterations, the iteration is stopped to obtain the global best position, which is the global optimal solution;

[0081] S4. Generate a vehicle gate passage scheduling plan based on the global optimal solution, and introduce the infrequently used vehicle gate passage data set to adjust the vehicle gate passage scheduling plan in real time to obtain a final vehicle gate passage scheduling plan;

[0082] The S4 comprises the following steps:

[0083] S41. Obtaining a global optimal solution for the vehicle barrier passage objective function, obtaining a minimum value of the vehicle barrier passage average delay time function and a minimum vehicle barrier passage queue length function, generating a vehicle barrier passage opening time scheduling plan and a vehicle barrier passage quantity scheduling plan, wherein the vehicle barrier gate controls the vehicle barrier gate opening according to the vehicle barrier gate opening time scheduling plan, and controls the vehicle barrier gate passage quantity according to the vehicle barrier gate passage quantity scheduling plan, thereby obtaining a vehicle barrier passage scheduling plan;

[0084] S42. Based on the infrequently used vehicle barrier gate passage data set, obtain the vehicle entry and exit time and vehicle type information of the infrequently used vehicles, set the priority according to the vehicle type information, and obtain high-priority vehicles and low-priority vehicles. When a high-priority vehicle passes through the vehicle barrier gate, increase the number of vehicle barrier gate passages or extend the vehicle barrier gate opening time, and adjust the vehicle barrier gate passage scheduling plan in real time to obtain the final vehicle barrier gate passage scheduling plan.

[0085] Example 2

[0086] This embodiment also discloses a system for intelligent scheduling of vehicle gate traffic based on big data, specifically comprising: a traffic data division and processing module, a traffic flow and anomaly prediction module, an objective function solving module, and a traffic scheduling solution generation module;

[0087] The traffic data division and processing module is used to divide the initial vehicle gate traffic data according to whether it is frequently used and perform pre-processing;

[0088] The traffic flow and anomaly prediction module is used to predict the traffic flow and anomaly of the vehicle gate;

[0089] The objective function solving module is used to solve the vehicle gate passing objective function by using the multi-strategy fusion Genghis Khan shark optimization algorithm;

[0090] The passing scheduling scheme generation module is used to generate and adjust the vehicle gate passing scheduling scheme.

[0091] In the description of this specification, the description referring to terms such as "one embodiment", "example", "specific example", etc. means that the specific features, structures, materials or characteristics described in connection with the embodiment or example are included in at least one embodiment or example of the invention. In this specification, the schematic expressions of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described can be combined in a suitable manner in any one or more embodiments or examples.

[0092] The preferred embodiments of the invention disclosed above are only used to help explain the invention. The preferred embodiments do not describe all the details in detail, nor do they limit the invention to the specific embodiments described. Obviously, many modifications and variations can be made according to the content of this specification. These embodiments are selected and specifically described in this specification in order to better explain the principle and practical application of the invention, so that those skilled in the art can well understand and utilize the invention.

Claims

1. An intelligent scheduling method for vehicle gate access based on big data, characterized in that, The steps include: S1. Obtaining vehicle entry and exit gate passage records to obtain an initial vehicle gate passage data set, identifying and preprocessing a frequently used vehicle gate passage data set and an infrequently used vehicle gate passage data set in the initial vehicle gate passage data set to obtain a processed vehicle gate passage data set; S2. Based on the processed vehicle gate passage data set, predict the vehicle gate passage flow and vehicle gate anomaly based on a neural network and a time series, respectively, to obtain a vehicle gate passage flow prediction value set and a vehicle gate anomaly prediction value set; S3. Establishing a vehicle gate passage objective function based on the vehicle gate passage flow prediction value set and the vehicle gate anomaly prediction set based on the optimal gate passage capacity principle, solving the vehicle gate passage objective function, and obtaining a global optimal solution; S4. Generate a vehicle gate passage scheduling plan based on the global optimal solution, and introduce the infrequently used vehicle gate passage data set to adjust the vehicle gate passage scheduling plan in real time to obtain a final vehicle gate passage scheduling plan; S2 specifically includes: S21, dividing the processed vehicle gate passage data set into a vehicle gate passage normal operation data set and a vehicle gate passage fault data set; S22. Train the normal operation data set of the vehicle gate to obtain an LSTM recurrent neural network prediction model, predict the vehicle gate flow rate, and obtain a vehicle gate flow rate prediction value set; S23. Obtain a vehicle barrier gate passage failure time series from the vehicle barrier gate passage failure data set, predict vehicle barrier gate anomalies, and obtain a vehicle barrier gate anomaly prediction value set; S3 specifically includes: Determine the average vehicle speed, obtain the average delay time function of vehicle gate passage and the vehicle gate passage queue length function, and select the minimum value of the two functions as the vehicle gate passage objective function; then use the inferior individual classification strategy and quasi-adversarial learning strategy to improve the Genghis Khan shark optimization algorithm, and then use the improved optimization algorithm to solve the vehicle gate passage objective function and obtain the global optimal solution.

2. The intelligent scheduling method for vehicle gate passage based on big data according to claim 1, wherein, The S1 comprises the following steps: S11. Obtain the passage records of vehicles entering and exiting the gate, obtain vehicle gate passage data, and form an initial vehicle gate passage data set; S12, calculating the frequency of vehicles entering and exiting the gate, and dividing the initial vehicle gate passage data set into a frequently used vehicle gate passage data set and an infrequently used vehicle gate passage data set; S13. Preprocess the commonly used vehicle barrier gate passage data set, delete abnormal vehicle barrier gate passage data in the commonly used vehicle barrier gate passage data set, and perform data filling to obtain a processed vehicle barrier gate passage data set.

3. The intelligent scheduling method for vehicle gate passage based on big data according to claim 2, wherein The S13 comprises the following steps: S131. Within a time period t, set an average threshold, compare the average value of the vehicle gate passage data with the average threshold, identify and delete abnormal vehicle gate passage data, and obtain a processed vehicle gate passage data set; S132. Divide the time period t by month, and use the mean of the vehicle barrier passage data in the adjacent vehicle barrier passage months to fill in the missing data, so as to obtain a processed vehicle barrier passage data set.

4. The intelligent scheduling method for vehicle barrier access based on big data according to claim 1, wherein, The S22 includes the following steps: S221. Obtaining a vehicle gate passage time series and a vehicle gate passage flow rate set based on the vehicle gate passage normal operation data set; S222. Obtain historical records of vehicle entry and exit from the barrier gate to obtain a historical data set of vehicle barrier gate passage, preprocess the historical data set of vehicle barrier gate passage and calculate the historical vehicle barrier gate passage flow rate to obtain a historical time series of vehicle barrier gate passage and a sample set of vehicle barrier gate passage flow rate, and divide the sample set of vehicle barrier gate passage flow rate into a sample training set and a sample test set; set a time sliding window, and learn the LSTM recurrent neural network according to the stochastic gradient descent method, place the time sliding window on the historical time series of vehicle barrier gate passage, obtain the sample training set contained in the historical time series of vehicle barrier gate passage within the time sliding window, and sequentially input the sample training set into the LSTM recurrent neural network, iterate until the LSTM recurrent neural network converges, and obtain a trained LSTM recurrent neural network; S223: Place the time sliding window in the historical time series of vehicle gate passages, obtain a sample test set contained in the historical time series of vehicle gate passages within the time sliding window, and sequentially input the sample test set into the trained LSTM recurrent neural network. Set an accuracy threshold, and when the output prediction value accuracy is greater than the accuracy threshold, obtain the LSTM recurrent neural network prediction model. Otherwise, adjust the weights until the output prediction value accuracy is greater than the accuracy threshold. S224. According to the vehicle gate passage time series, the vehicle gate passage flow set is input into the LSTM recurrent neural network prediction model, and the vehicle gate passage flow prediction values are output in sequence to form a vehicle gate passage flow prediction value set.

5. The intelligent scheduling method for vehicle gate access based on big data according to claim 1, characterized in that The method of determining the average vehicle speed, obtaining the average delay time function of the vehicle gate passage and the vehicle gate passage queue length function, and selecting the minimum value of the two functions as the vehicle gate passage objective function; then improving the Genghis Khan shark optimization algorithm using the inferior individual classification strategy and the quasi-adversarial learning strategy, and then using the improved optimization algorithm to solve the vehicle gate passage objective function to obtain a global optimal solution includes the following steps: S31. Set the number of vehicles passing through the gate to α, combine the vehicle gate flow prediction value set and the vehicle gate abnormality prediction set, determine the average vehicle speed based on the optimal gate capacity principle, and obtain the vehicle gate passage average delay time function and the vehicle gate passage queue length function; The minimum value of the average delay time function of the vehicle gate and the minimum length of the vehicle gate queue are selected as the vehicle gate passage objective function, and the constraint condition is introduced to ensure that the vehicle gate opening time is less than or equal to the vehicle gate maximum opening time; S32. Use the inferior individual classification strategy and the quasi-adversarial learning strategy to improve the Genghis Khan shark optimization algorithm to obtain a multi-strategy fusion Genghis Khan shark optimization algorithm, and use the multi-strategy fusion Genghis Khan shark optimization algorithm to solve the vehicle gate passage objective function to obtain the global optimal solution.

6. The intelligent scheduling method for vehicle gate access based on big data according to claim 5, characterized in that The S32 includes the following steps: S321. The process of solving the vehicle barrier pass objective function is regarded as a search space. The search space contains a Genghis Khan shark population. The Genghis Khan shark individuals in the Genghis Khan shark population represent candidate solutions to the vehicle barrier pass objective function. The number of Genghis Khan shark populations is set to i, the dimension of the Genghis Khan shark individuals is set to j, the current number of iterations is set to b, the Genghis Khan shark population is initialized, and the position of the i-th Genghis Khan shark individual at the b+1th iteration is obtained. During the migration phase, the Genghis Khan shark population updates its position based on the concentration of prey odor. The odor intensity coefficient is set to β, c represents a non-negative constant, and c1 represents a random number between the interval [0, 1]. Assume that the optimal Genghis Khan shark individual position at the bth iteration is Position Make updates; Obtain the fitness function value corresponding to the position of the Genghis Khan shark at this time, record the current best fitness function value and the current worst fitness function value as f1 and f2 respectively, and record the fitness function value corresponding to the i-th Genghis Khan shark as f'. Introduce the inferior individual classification strategy and calculate the pheromone When the pheromone is less than or equal to 0.3, select the position of the i′th Genghis Khan shark and the position of the i″th Genghis Khan shark Position Update and set c2 to represent a random number of 0 or 1. S322, Genghis Khan shark population in the foraging stage, set the step parameter to φ, according to the best Genghis Khan shark individual position Position Update again, this time introduce the quasi-opposition learning strategy, set the upper and lower bounds of the search space to d1 and d2 respectively, and the dual value Dual Position Calculate the fitness function value corresponding to the dual position, compare it with the current best fitness function, and use the dual position to replace the position Achieve position Updates; In the self-protection stage of the Genghis Khan shark population, the Genghis Khan shark individuals use self-protection strategies to position Update to obtain the final position of the i-th Genghis Khan shark individual at the b+1th iteration, screen the Genghis Khan shark population, and enter the next iteration; The maximum number of iterations is set. When the current number of iterations reaches the maximum number of iterations, the iteration is stopped to obtain the global optimal position, which is the global optimal solution.

7. The intelligent scheduling method for vehicle gate access based on big data according to claim 6, wherein The S4 comprises the following steps: S41, obtaining a global optimal solution for the vehicle gate passage objective function, generating a vehicle gate opening time scheduling plan and a vehicle gate passage quantity scheduling plan, and obtaining a vehicle gate passage scheduling plan; S42. According to the infrequently used vehicle gate passage data set, the vehicle gate passage scheduling plan is adjusted in real time to obtain a final vehicle gate passage scheduling plan.

8. A system for implementing the intelligent scheduling method for vehicle barrier access based on big data as described in any one of claims 1-7, characterized in that, Specifically include: Traffic data division and processing module, traffic flow and anomaly prediction module, objective function solution module and traffic scheduling plan generation module; The traffic data division and processing module is used to divide the initial vehicle gate traffic data according to whether it is frequently used and perform pre-processing; The traffic flow and anomaly prediction module is used to predict the traffic flow and anomaly of the vehicle gate; The objective function solving module is used to solve the vehicle gate passage objective function using the Genghis Khan Shark optimization algorithm with multi-strategy fusion; The traffic scheduling plan generation module is used to generate and adjust the vehicle gate traffic scheduling plan.

Images