A cloud data capsule bus-subway smart interaction device
Through the cloud data capsule bus-subway smart interactive device, the Osprey optimization algorithm and electronic angle technology are used to solve the problem of congestion at the subway station entrance, and efficient and orderly traffic for passengers to quickly reach their destinations, reducing the walking time and improving the Economic benefits.
Patent Information
- Application Number
- CN202311410559.7
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2023-10-26
- Publication Date
- 2024-11-05
- Estimated Expiration
- 2043-10-26
AI Technical Summary
In urban rail transit, congestion often occurs at the entrances of subway stations near the city center and commercial streets, leading to the negative impact of increased traffic pressure, slow travel and anxiety.
Adopt cloud data capsule bus-metro smart interactive device to collect passenger data in real time through cloud platform and big data system, use Osprey optimization algorithm to regulate the path planning of capsule buses, implement accurate and centralized station arrival strategies, and use electronic angles Technical wheels achieve flexible route adjustment.
Effectively reduce the congestion of people at the subway entrances and exits, help passengers arrive at their destination faster, improve the orderliness and efficiency of the driving process, reduce walking time, and provide new methods and economic benefits.
Smart Images

Figure CN117217397B_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the fields of intelligent transportation technology and intelligent optimization algorithms, and in particular to a cloud data capsule bus-subway intelligent interaction device. Background Art
[0002] The construction of urban rail transit is one of the indispensable factors for becoming a transportation power. In recent years, the construction of urban rail transit in my country has continued to advance. Only by promoting the orderly development of rail transit such as subways and light rails can we effectively support and lead the construction of new urbanization and make cities better. The construction of subways can facilitate people's travel, improve urban operation efficiency, and reduce the pressure of ground traffic congestion. However, some problems have also emerged over time. Usually, there will be crowds at subway stations near the city center and commercial streets, which will cause some traffic congestion and slow people's movement. At the same time, it will also cause people to be nervous during the morning commute and bring people anxiety and other negative emotions. Summary of the invention
[0003] Purpose of the invention: In view of the problems existing in the prior art, the present invention provides a cloud data capsule bus-subway intelligent interaction device, which can effectively help people reach their destination faster at congested subway entrances.
[0004] Technical solution: A cloud data capsule bus-subway intelligent interactive device, the solution includes: collecting real-time data of passengers on the subway who are about to arrive at the congested subway entrance, using cloud platform and big data system to collect information, the collected information mainly includes: the subway entrance where the passengers are about to exit, the final destination of the passengers after getting off the subway, and whether they accept getting off the bus in the designated area; after arriving at the station, the passengers can take a capsule bus, which will take the passengers to the designated destination; the intelligent optimization algorithm is used to control the planning of the route, and the precise arrival and concentrated arrival strategies are adopted. The precise arrival increases the number of stations where the passengers can get off; the concentrated arrival reduces the number of stations where the passengers can get off; the specific strategies are as follows: when the number of passengers is greater than 20 and the distance between the destinations is greater than 50 meters, concentrated arrival is adopted; when the number of passengers is greater than 20 and the distance between the destinations is less than 50 meters, precise arrival is adopted; when the number of passengers is less than 20 and the distance between the destinations is greater than 50 meters, concentrated arrival is adopted; when the number of passengers is less than 20 and the distance between the destinations is less than 50 meters, precise arrival is adopted;
[0005] Furthermore, the solution uses a cloud platform and a big data system to collect real-time data on passengers who are about to arrive at a congested subway entrance. The collected information mainly includes: the subway entrance where the passenger is about to get off, the passenger's final destination, and whether the passenger is willing to get off at a designated area;
[0006] Furthermore, the capsule bus adopts a capsule-shaped shell, and the wheels adopt a new technology called e-Corner, so that each wheel has integrated braking and electronic steering. Each wheel can accelerate, brake and steer independently, and can easily complete activities such as entering the elevator and turning around on the spot.
[0007] Furthermore, the cloud platform is composed of a resource layer, a virtual layer, a middleware layer and an application layer, and the big data system is composed of four parts: data collection, data storage, data processing and statistical analysis. Both are for collecting data on the subway entrance where the passenger is about to get off, the passenger's final destination and whether the passenger is allowed to get off at the designated area.
[0008] Furthermore, the Osprey optimization algorithm is used to control the path planning of the capsule bus. The specific steps are as follows:
[0009] 1) Population initialization:
[0010] A target population is randomly generated, each individual is randomly placed in the space, the maximum number of iterations of the algorithm is set, the search space of the algorithm is set according to the number of iterations, and the population is randomly initialized in the optimization space:
[0011]
[0012] x i,j =lb j +r i,j ·(ub j -lb j ),i=1,2,...,N,j=1,2,...,m
[0013] Among them, x i,j is the population individual, N is the number of ospreys, m is the dimension, lb j is the optimal lower bound, ub j is the upper boundary of optimization, r i,j is a random number between [0,1];
[0014] 2) Evaluate its performance according to a predetermined objective function,
[0015] The objective function formula is as follows:
[0016]
[0017] in, is the optimal path selection factor, V is the average speed, α is the step size control factor, R is the step size improvement strategy, T1 is the total time, △L is the distance difference between different get-off locations, is the total mileage of the route formed by the centralized drop-off location and the precise drop-off location obtained by the algorithm, i is a positive integer from 1 to T; T is the maximum number of iterations;
[0018] 3) Bring the initial population into the objective function for evaluation, and set the group value of the passenger's best boarding location to X best ;
[0019] 4) In this algorithm, for each passenger, all the information filled in through the cloud platform and big data system has a better objective function value in the search space. The position formula of each osprey is as follows:
[0020] FP i ={X k |k∈{1,2,…,N}∧F k <F i}∪{X best}
[0021] Among them, FP i is the set of fish of the i-th osprey, and also the set of path information. Finding the optimal path position increases the exploration ability of the algorithm in identifying the best area and escaping from the local optimum;
[0022] 5) Plan a continuous optimal route and continuously update the drop-off location. The Osprey position formula is as follows:
[0023]
[0024] in, is the new position of the i-th osprey in the j-th dimension, SF i,j is the information of the prey, r is a random number between [0,1], and the value of I is one of {1,2}.
[0025] 6) Calculate the fitness. If the difference between the drop-off destinations of different passengers is no more than 50 meters, the following drop-off location is better, and it replaces the drop-off location in step 5). The updated Osprey position formula is as follows:
[0026]
[0027] in, yes The corresponding fitness value, the fitness is the location where the passenger gets off, that is, the location information of the Osprey;
[0028] 7) In order to improve the global search capability, the search step size is optimized and improved. The formula is as follows:
[0029] R=α*e -(β*t) / T
[0030] Among them, α is the step size control factor, β is the exponential control factor, t is the current number of iterations, and T is the maximum number of iterations;
[0031] 8) According to the number of passengers in the car, the design is whether to arrive at the station accurately or at a concentrated station. According to the destination information collected above, the information of the drop-off location within the radius of the destination less than or equal to 50 meters is screened and set to arrive at the concentrated station. The formula for the suitable location for the osprey to eat fish when returning is as follows:
[0032]
[0033]
[0034] Where t is the current iteration number, T is the maximum iteration number, N is the number of ospreys, and m is the dimension;
[0035] 9) If the radius of the selected destination is greater than 50 meters, the exact destination is selected and the location selected by the passenger is taken as the standard. The value of the objective function is improved at this new location, so it replaces the previous location of the Osprey according to the following formula:
[0036]
[0037] This new position enhances the ability to search locally and converge to better solutions near the found solutions.
[0038] 10) Taking the information collected by the cloud platform and big data as input, the best path is selected to output the optimal solution. The larger the path selection factor, the better the path. Determine whether the stopping condition is met. The stopping condition is to output the same optimal path selection factor twice in a row. If the stopping condition is met, exit and output the result. Otherwise, repeat steps 3-9 and finally output the optimal solution. For capsule bus path optimization, its movement path is limited to normal road traffic and abides by traffic rules.
[0039] Beneficial effects: The present invention can effectively help people reach their destination faster at congested subway entrances, improve the orderliness and efficiency of the driving process, effectively increase economic benefits, and provide a new method and new idea for the construction of green subway transportation. BRIEF DESCRIPTION OF THE DRAWINGS
[0040] Figure 1 It is a structural schematic diagram of the present invention;
[0041] Figure 2 It is a schematic diagram of the hardware framework of the present invention;
[0042] Figure 3 The flowchart of the Osprey optimization algorithm used in the present invention; DETAILED DESCRIPTION
[0043] The technical solution of the present invention is further described below in conjunction with the accompanying drawings.
[0044] like Figure 1 , Figure 2 As shown, a cloud data capsule bus-subway intelligent interactive device is characterized in that the solution includes the use of a cloud platform and a big data system to collect real-time data on passengers who are about to arrive at a congested subway entrance on the subway. The collected information mainly includes: the subway entrance where the passenger is about to get off, the passenger's final destination, and whether the passenger is willing to get off in the designated area; the capsule bus is routed through an algorithm control unit, and precise arrival and concentrated arrival strategies are adopted.
[0045] Furthermore, the solution uses a cloud platform and a big data system to collect real-time data on passengers on the subway who are about to arrive at a congested subway entrance. The collected information mainly includes: the subway entrance where the passenger is about to exit, the final destination of the passenger after getting off the subway, and whether the passenger is willing to get off the bus in the designated area;
[0046] Furthermore, the capsule bus adopts a capsule-shaped shell, and the wheels adopt a new technology called e-Corner, so that each wheel has integrated braking and electronic steering. Each wheel can accelerate, brake and steer independently, and can easily complete activities such as entering the elevator and turning around on the spot.
[0047] Furthermore, the cloud platform is composed of a resource layer, a virtual layer, a middleware layer and an application layer, and the big data system is composed of four parts: data collection, data storage, data processing and statistical analysis. Both are for collecting data on the subway entrance where the passenger is about to get off, the passenger's final destination and whether the passenger is allowed to get off at the designated area.
[0048] like Figure 3 As shown in the figure, the Osprey optimization algorithm is used to control the path planning of the capsule bus. The specific steps are as follows:
[0049] 1) Population initialization:
[0050] A target population is randomly generated, each individual is randomly placed in the space, the maximum number of iterations of the algorithm is set, the search space of the algorithm is set according to the number of iterations, and the population is randomly initialized in the optimization space:
[0051]
[0052] x i,j =lb j +r i,j ·(ub j -lb j ),i=1,2,...,N,j=1,2,...,m
[0053] Among them, x i,j is the population individual, N is the number of ospreys, m is the dimension, lb j is the optimal lower bound, ub j is the upper boundary of optimization, r i,j is a random number between [0,1];
[0054] 2) Evaluate its performance according to a predetermined objective function,
[0055] The objective function formula is as follows:
[0056]
[0057] in, is the optimal path selection factor, V is the average speed, α is the step size control factor, R is the step size improvement strategy, T1 is the total time, △L is the distance difference between different get-off locations, is the total mileage of the route formed by the centralized drop-off location and the precise drop-off location obtained by the algorithm, i is a positive integer from 1 to T; T is the maximum number of iterations;
[0058] 3) Bring the initial population into the objective function for evaluation, and set the group value of the passenger's best boarding location to X best ;
[0059] 4) In this algorithm, for each passenger, all the information filled in through the cloud platform and big data system has a better objective function value in the search space. The position formula of each osprey is as follows:
[0060] FP i ={X k |k∈{1,2,…,N}∧F k <F i}∪{X best}
[0061] Among them, FP i is the set of fish of the i-th osprey, and also the set of path information. Finding the optimal path position increases the exploration ability of the algorithm in identifying the best area and escaping from the local optimum;
[0062] 5) Plan a continuous optimal route and continuously update the drop-off location. The Osprey position formula is as follows:
[0063]
[0064] in, is the new position of the i-th osprey in the j-th dimension, SF i,jis the information of the prey, r is a random number between [0,1], and the value of I is one of {1,2}.
[0065] 6) Calculate the fitness. If the difference between the drop-off destinations of different passengers is no more than 50 meters, the following drop-off location is better, and it replaces the drop-off location in step 5). The updated Osprey position formula is as follows:
[0066]
[0067] in, yes The corresponding fitness value, the fitness is the location where the passenger gets off, that is, the location information of the Osprey;
[0068] 7) In order to improve the global search capability, the search step size is optimized and improved. The formula is as follows:
[0069] R=α*e -(β*t) / T
[0070] Among them, α is the step size control factor, β is the exponential control factor, t is the current number of iterations, and T is the maximum number of iterations;
[0071] 8) According to the number of passengers in the car, the design is whether to arrive at the station accurately or at a concentrated station. According to the destination information collected above, the information of the drop-off location within the radius of the destination less than or equal to 50 meters is screened and set to arrive at the concentrated station. The formula for the suitable location for the osprey to eat fish when returning is as follows:
[0072]
[0073] Where t is the current iteration number, T is the maximum iteration number, N is the number of ospreys, and m is the dimension;
[0074] 9) If the radius of the selected destination is greater than 50 meters, the exact destination is selected and the location selected by the passenger is taken as the standard. The value of the objective function is improved at this new location, so it replaces the previous location of the Osprey according to the following formula:
[0075]
[0076] This new position enhances the ability to search locally and converge to better solutions near the found solutions.
[0077] 10) Taking the information collected by the cloud platform and big data as input, the best path is selected to output the optimal solution. The larger the path selection factor, the better the path. Determine whether the stopping condition is met. The stopping condition is to output the same optimal path selection factor twice in a row. If the stopping condition is met, exit and output the result. Otherwise, repeat steps 3-9 and finally output the optimal solution. For capsule bus path optimization, its movement path is limited to normal road traffic and abides by traffic rules.
[0078] The present invention discloses a cloud data capsule bus-subway intelligent interactive device, the scheme includes: collecting real-time data of passengers who are about to arrive at the congested subway entrance on the subway, using a cloud platform and a big data system to collect information, and the collected information is mainly: the subway entrance where the passenger is about to get off, the passenger's final destination and whether to accept getting off in the designated area; after the passenger arrives at the station, he can take a capsule bus, which will take the passenger to the designated destination; the capsule bus adopts a capsule-shaped shell, and the wheel adopts a new technology called e-Corner, which adopts a four-wheel motor, each wheel can be controlled at will, and the activity of entering the elevator is easily completed; the intelligent optimization algorithm is used to control the planning of the path, so that the bus waits for a certain period of time, and adopts a precise arrival and centralized arrival strategy. The present invention can effectively control the flow of people at the subway entrance and exit, avoid the occurrence of crowded trampling, help people reach the destination faster at the congested subway entrance, improve the orderliness and efficiency of the driving process, effectively improve the economic benefits, and greatly save people's walking time.
[0079] The present invention proposes a cloud data capsule bus-subway intelligent interactive device, which can regulate the route planning of the capsule bus through an algorithm, so that a large number of passengers getting off the bus can arrive at the station in a concentrated manner, and a small number of passengers can arrive at the station accurately, making driving more standardized, intelligent and humane.
[0080] The cloud platform used in the present invention is composed of a resource layer, a virtual layer, a middleware layer and an application layer, and the big data system is composed of four parts: data collection, data storage, data processing and statistical analysis. Both are for collecting data on the subway entrance where the passenger is about to get off, the passenger's final destination and whether the passenger is allowed to get off in the designated area.
[0081] The capsule bus used in the present invention adopts a capsule-shaped shell, and the wheels adopt a new technology called e-Corner, so that each wheel has integrated braking and electronically controlled steering. Each wheel can accelerate, brake and steer independently, and can easily complete the activities of entering the elevator and turning around on the spot.
[0082] The Osprey algorithm proposed by the intelligent optimization module of the present invention has a relatively high degree of energy distribution control and path planning for fuel-to-electricity conversion. In addition, the algorithm has a simple structure and is easy to understand. By adding seasonal ocean current influence factors, the algorithm's exploration ability is improved, and a certain convergence accuracy can be achieved more quickly.
[0083] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.
Claims
1. A cloud data capsule bus-subway intelligent interaction device, characterized in that: The device includes a capsule bus, a cloud platform and a big data system; The cloud platform and big data system collect real-time data of passengers on the subway who are about to arrive at a congested subway entrance. The collected information includes: the subway entrance where the passenger is about to exit, the passenger's final destination after getting off the subway, and whether the passenger is allowed to get off the bus in the designated area; after getting off the subway, the passenger can choose to take a capsule bus, and the capsule bus will take the passenger to the designated destination; The algorithm control unit uses the Osprey optimization algorithm to plan the path of the capsule bus, and adopts the precise arrival and concentrated arrival strategies. The precise arrival increases the number of stations where the bus can get off; the concentrated arrival reduces the number of stations where the bus can get off. The specific strategies are as follows: when the number of passengers is greater than 20 and the distance between the destinations is greater than 50 meters, concentrated arrival is adopted; when the number of passengers is greater than 20 and the distance between the destinations is less than 50 meters, precise arrival is adopted; when the number of passengers is less than 20 and the distance between the destinations is greater than 50 meters, concentrated arrival is adopted; when the number of passengers is less than 20 and the distance between the destinations is less than 50 meters, precise arrival is adopted. The path planning method of the capsule bus is controlled by the Osprey optimization algorithm. The steps are as follows: 1) Population initialization; 2) Input the objective function; the objective function formula is as follows: in, is the optimal path selection factor, V is the average speed, α is the step size control factor, R is the step size improvement strategy, T1 is the total time, △L is the distance difference between different get-off locations, is the total mileage of the route formed by the centralized drop-off location and the precise drop-off location obtained by the algorithm, i is a positive integer from 1 to T; T is the maximum number of iterations; 3) Bring the initial population into the objective function for evaluation, and set the group value of the passenger's best boarding location to X best ; 4) Each passenger fills in the information through the cloud platform and big data system, and has a better objective function value in the search space; the position formula of each osprey is as follows: FP i ={X k ∣k∈{1,2,…,N}∧F k <F i }∪{X best } Among them, FP i is the fish set of the i-th osprey, and also the set of path information; 5) Plan a continuous optimal route and continuously update the passenger's drop-off location; the osprey's position formula is as follows: in, is the position of the i-th osprey in the first stage, its j-th dimension, SF i,j For prey information, r i,j is a random number between [0,1], I i,j The value of x is one of {1,2}; i,j is a population individual, lb j is the optimal lower bound, ub j is the upper boundary of optimization; 6) Calculate the fitness. If the difference between the drop-off destinations of different passengers is less than or equal to 50 meters, the drop-off location in the following formula is better and replaces the drop-off location updated in step 5); the updated location formula is as follows: in, yes The corresponding fitness value, F i,j is x i,j The fitness value is the location where the passengers get off the bus, i.e. the location information of the Osprey. 7) Optimize the search step length. The step length formula is as follows: R=α*e -(β*t) / T Among them, α is the step size control factor, β is the exponential control factor, and t is the current number of iterations; 8) According to the number of passengers in the car, the precise arrival or concentrated arrival is designed. According to the collected destination information, the drop-off location information with a radius of less than or equal to 50 meters is screened and set to the concentrated arrival station. The formula for the suitable location for the osprey to eat fish when returning is as follows: Where t is the current iteration number, T is the maximum iteration number, N is the number of ospreys, and m is the dimension; 9) If the radius of the selected destination is greater than 50 meters, the exact destination is selected and the location selected by the passenger is taken as the standard. The value of the objective function is improved at this new location, so it replaces the previous location of the Osprey according to the following formula: 10) Taking the information collected by the cloud platform and the big data system as input, the best path is selected to output the optimal solution. The larger the path selection factor, the better the path. Determine whether the stopping condition is met. If the stopping condition is met, exit and output the result. Otherwise, repeat steps 3)-9) and finally output the optimal solution. Step 1) Population initialization is as follows: A target population is randomly generated, each individual is randomly placed in the space, the maximum number of iterations is set, the search space of the algorithm is set according to the number of iterations, and the population is randomly initialized in the optimization space: x i,j =lb j +r i,j ·(ub j -lb j ),i=1,2,...,N,j=1,2,...,m Among them, x i,j is the population individual, N is the number of ospreys, m is the dimension, lb j is the optimal lower bound, ub j is the upper boundary of optimization, r i,j is a random number between [0,1].
2. A cloud data capsule bus-subway intelligent interaction device according to claim 1, characterized in that: The capsule bus adopts a capsule-shaped shell, and each wheel is integrated with brakes and electronically controlled steering. Each wheel can accelerate, brake and steer independently, and can complete the activities of entering the elevator and turning around on the spot.
3. The cloud data capsule bus-subway intelligent interaction device according to claim 1, characterized in that: The cloud platform consists of a resource layer, a virtual layer, a middleware layer and an application layer, and the big data system consists of four parts: data collection, data storage, data processing and statistical analysis.
4. The cloud data capsule bus-subway intelligent interaction device according to claim 1, characterized in that: Step 10) The stopping condition is that the same optimal path selection factor is output twice in succession.
5. The cloud data capsule bus-subway intelligent interaction device according to claim 1, characterized in that: The wheels of the capsule-type bus adopt the e-Corner technology.
