Passenger drop-off scheduling strategy optimization method and system for intelligent monorail vehicle

Abstract

The invention relates to the technical field of intelligent traffic scheduling, in particular to an intelligent monorail vehicle-oriented passenger scheduling strategy optimization method and system, and the method comprises the steps: collecting multi-dimensional scheduling data through monorail vehicle-mounted sensing equipment, a platform monitoring unit and a passenger terminal, and building a dynamic database; based on a deep learning model, carrying out prediction analysis on the passenger getting-off demand, the station congestion state and the line operation parameters; a multi-objective optimization function is constructed in combination with a prediction result, and an optimal passenger getting-off scheduling scheme is solved by taking maximization of passenger getting-off efficiency, minimization of station residence time and optimization of line operation collaboration as objectives; a dispatching instruction is issued through a train-station-center three-level communication network, getting-off door control, platform guidance and train departure interval adjustment are executed in real time, and the dispatching effect is dynamically monitored for closed-loop optimization. According to the invention, through data-driven prediction analysis and multi-objective optimization, the intelligence and refinement of get-off scheduling and the operation efficiency of monorail traffic are improved.

Description

Technical Field

[0001] This invention relates to the field of intelligent transportation dispatching technology, specifically to a method and system for optimizing passenger disembarkation dispatching strategies for intelligent monorail vehicles. Background Technology

[0002] As an important component of urban rail transit, intelligent monorail vehicles possess advantages such as strong terrain adaptability, small footprint, and flexible operation, playing a crucial role in alleviating urban traffic congestion. Passenger disembarkation scheduling, as a core aspect of monorail vehicle operation scheduling, directly impacts passenger travel experience, platform operational order, and the overall transportation efficiency of the line.

[0003] However, existing monorail passenger disembarkation scheduling technology has many problems that urgently need to be solved: Demand response lag: Traditional scheduling strategies are mostly based on fixed rules, such as a fixed number of doors to open and a fixed stop duration, without fully considering the dynamic changes in real-time passenger disembarkation demand and platform congestion. This results in insufficient disembarkation channels during peak hours and wasted resources during off-peak hours, leading to an imbalance between supply and demand. Insufficient predictive capabilities: There is a lack of accurate prediction of the number of passengers getting off and congestion trends. Scheduling decisions rely on historical experience and cannot predict the passenger drop-off pressure at peak stations and during congested periods in advance, resulting in insufficient scheduling preparation. Single optimization objective: Existing scheduling schemes often focus only on a single objective such as passenger disembarkation speed or stop duration, neglecting key factors such as platform dwell time and line operation coordination. This can easily lead to conflicts between local optimization and overall efficiency. For example, simply shortening the stop duration can cause passenger congestion and affect the operation of subsequent vehicles. Lack of closed-loop management: After the scheduling plan is implemented, there is a lack of real-time monitoring and dynamic adjustment mechanisms. When emergencies occur, such as sudden illness of passengers or a surge in temporary passenger flow, the scheduling strategy cannot be responded to quickly and optimized, resulting in a continuous deterioration of the scheduling effect.

[0004] Therefore, there is an urgent need for a passenger disembarkation scheduling strategy based on data-driven, predictive, multi-objective optimization, and closed-loop management to address the core deficiencies in existing technologies and improve the intelligence and precision of intelligent monorail passenger disembarkation scheduling. Summary of the Invention

[0005] To address the aforementioned technical shortcomings, this invention provides a method and system for optimizing passenger disembarkation scheduling strategies for intelligent monorail vehicles. Through multi-source data collection, accurate predictive analysis, multi-objective optimization, and closed-loop adjustment, it achieves dynamic optimization and efficient management of passenger disembarkation scheduling.

[0006] This invention is achieved through the following technical solution: A method for optimizing passenger disembarkation scheduling strategies for intelligent monorail vehicles is provided, the method comprising the following steps: Step S10: Construct a multi-source data acquisition system, collect multi-dimensional scheduling data through vehicle-mounted sensing devices, platform monitoring devices, passenger terminals and line control center, establish a dynamic database and perform data preprocessing; Step S20: Based on the preprocessed multidimensional scheduling data, an improved deep learning model is used to predict passenger disembarkation demand, platform congestion level, and monorail vehicle operation status, and the prediction results are output. Step S30: Using the prediction results as constraints, construct a multi-objective passenger disembarkation scheduling optimization function, solve for the optimal scheduling parameters through an intelligent optimization algorithm, and generate a customized passenger disembarkation scheduling scheme; Step S40: Issue dispatch instructions through the three-level communication network of train-station-center, execute the passenger disembarkation dispatch plan and monitor the operation status in real time, and dynamically adjust the dispatch strategy based on feedback data to form a closed-loop management.

[0007] Preferably, the multi-dimensional scheduling data in step S10 includes: Onboard data: The data collected by the monorail vehicle includes passenger density, seat occupancy status, passenger distribution, disembarkation intentions, current vehicle speed, and remaining arrival time. Disembarkation intentions are determined by the distance between the passenger's standing area and the door. Platform data: Real-time passenger numbers, passenger distribution areas, platform congestion density, occupancy status of boarding and alighting passages, and operational status of platform service facilities, collected through platform infrared counters, lidar, and video surveillance equipment. Passenger data: Information collected through passenger travel apps and card terminals, including passenger travel destinations, transfer needs, reservation drop-off preferences, and real-time feedback. Line data: Information collected by the line control center, including monorail train departure intervals, congested sections of the line, the location of subsequent vehicles, the running time between stations, and temporary scheduling restrictions.

[0008] Preferably, the data preprocessing process in step S10 includes: Data cleaning: An outlier detection algorithm is used to remove abnormal data caused by sensor malfunctions and signal interference based on the 3σ principle. Missing data is supplemented by mean imputation method, with a missing data rate of ≤5%. Data standardization: Normalize data from different dimensions by using Min-Max normalization to the [0,1] interval to eliminate differences in units, including scaling passenger density and congestion density proportionally and converting time-related data into standardized duration factors; Data fusion: A weighted average fusion algorithm is used to fuse multi-source data of the same monitoring object. For example, the weight of vehicle sensor data is 0.6, the weight of platform monitoring data is 0.3, and the weight of passenger feedback data is 0.1, to generate unified state representation data. Data storage: The preprocessed data is categorized by timestamp and stored in a dynamic database. The time-series database InfluxDB is used to support high-concurrency read and write operations and historical data backtracking analysis.

[0009] Preferably, step S20, which involves using an improved deep learning model to predict passenger disembarkation demand, platform congestion levels, and monorail vehicle operating status, includes: Passenger drop-off demand prediction: An improved LSTM long short-term memory network model is adopted, and an attention mechanism is introduced to strengthen the weight of key influencing factors. Inputting data such as historical passenger drop-off volume, real-time passenger distribution and travel time characteristics, the model predicts the number of passengers, the concentrated drop-off area and the duration of drop-off by the monorail at the target station, with a prediction error of ≤8%. Platform congestion level prediction: Based on the XGBoost model, using real-time platform passenger volume, congestion density, historical congestion data, and station type as input features (station types are categorized as hub stations, regular stations, and suburban stations), platform congestion levels are divided into 5 levels, with level 1 being unobstructed (density ≤ 0.5 people / m²). 2 Level 2 is basically unobstructed, with a density of 0.5 < density ≤ 1.0 people / m³. 2 Level 3 is light congestion, with a density of 1.0 < density ≤ 1.5 people / m². 2 Level 4 is moderate congestion, with a density of 1.5 people to 2.0 people per square meter. 2 Level 5 indicates severe congestion, with a density > 2.0 people / m². 2 Output the congestion level prediction results for the target station within the next 3 minutes; Operational status prediction: The GRU gated cyclic unit model is adopted. The inputs include real-time operation data of the line, historical running time and external influencing factors. The operation data includes current vehicle speed, station spacing and distance to the preceding vehicle. External influencing factors include weather, passenger flow fluctuations, etc. The system predicts the precise time of the monorail vehicle to reach the target station, the optimal station stopping time and subsequent line operation coordination parameters. The prediction time error is ≤10 seconds.

[0010] Preferably, the step of constructing the multi-objective passenger disembarkation scheduling optimization function in step S30 includes: Construct a multi-objective optimization function: The optimization function is constructed with three core objectives: 1) Maximize passenger disembarkation efficiency, maxf1=α×(number of passengers disembarking / stop time), where f1 is the passenger disembarkation efficiency and α is the efficiency weight coefficient; 2) Minimize platform dwell time, minf2=β×(average passenger platform dwell time), where f2 is the platform dwell time and β is the dwell time weight coefficient; 3) Optimize line coordination, maxf3=γ×(1-|actual departure interval-optimal departure interval| / optimal departure interval), where f3 is the line coordination of objective 3 and γ is the coordination weight coefficient, and α+β+γ=1; The constraints include the maximum stop time limit for monorail vehicles, the limit on the number of doors opened, the platform safety density threshold, and the line operation interval threshold. Intelligent optimization solution: An improved particle swarm optimization (PSO) algorithm is used to solve the multi-objective optimization function. By dynamically adjusting the inertia weight and learning factor, and adopting a linear decreasing strategy with an initial value of 0.9 and a final value of 0.4, the algorithm's convergence speed and global optimal solution search capability are improved. The passenger disembarkation scheduling parameters are used as the particle dimension, and the optimal parameter combination is obtained through iterative solution. Generate a scheduling plan: Based on the optimal parameter combination, generate a customized passenger disembarkation scheduling plan, including door control strategy, platform guidance strategy, stop duration allocation strategy, and suggestions for adjusting the departure interval of subsequent vehicles. The door control strategy includes the opening of single / multiple doors and the opening sequence. The platform guidance strategy includes LED screen indication and voice broadcast to guide passenger flow.

[0011] Preferably, the steps in step S40 of issuing scheduling instructions, executing the passenger disembarkation scheduling plan, and monitoring the operational status in real time include: Command Issuance and Execution: Through a three-level communication network of vehicle-station-center combined with 5G and edge computing, the commands in the scheduling plan are issued to the monorail vehicle onboard control system, the platform intelligent guidance system, and the line dispatch center. The monorail vehicle onboard control system receives the door control command, the platform intelligent guidance system receives the guidance command, and the line dispatch center receives the departure interval adjustment command. After the monorail vehicle arrives at the station, it opens the corresponding door according to the command. The platform LED screen displays the passenger disembarkation passage guidance in real time, and the voice broadcast system continuously prompts passengers to divert. Real-time monitoring and feedback: The dispatch execution data is collected in real time through on-board sensors and platform monitoring equipment, including the actual number of passengers getting off, the time taken to get off, changes in platform congestion density and passenger dwell time, etc., and the feedback data is uploaded to the line control center every 5 seconds. Closed-loop optimization and adjustment: The line control center compares the actual execution effect with the optimization target value. When the deviation exceeds the preset threshold, the dynamic adjustment mechanism is triggered, the optimization algorithm of step S30 is called again, the scheduling parameters are updated based on the latest feedback data, the adjusted scheduling plan is generated and issued for execution, and the scheduling effect is continuously optimized.

[0012] Furthermore, to achieve the above objectives, this invention also proposes a passenger disembarkation scheduling strategy optimization system for intelligent monorail vehicles, the system comprising: Monorail vehicle multi-source data acquisition module: used to build a multi-source data acquisition system, collect multi-dimensional scheduling data through on-board sensing equipment, platform monitoring equipment, passenger terminals and line control center, establish a dynamic database and perform data preprocessing; Predictive Analysis Module: Based on preprocessed multidimensional scheduling data, this module uses an improved deep learning model to predict passenger disembarkation demand, platform congestion levels, and monorail vehicle operating status, and outputs the prediction results. Multi-objective optimization and scheduling scheme generation module: It is used to construct a multi-objective passenger disembarkation scheduling optimization function with the prediction results as constraints, solve for the optimal scheduling parameters through intelligent optimization algorithms, and generate a customized passenger disembarkation scheduling scheme; The scheduling execution and closed-loop optimization module is used to issue scheduling instructions through the three-level communication network of train-station-center, execute passenger disembarkation scheduling plan and monitor the operation status in real time, and dynamically adjust the scheduling strategy based on feedback data to form closed-loop management.

[0013] Furthermore, to achieve the above objectives, the present invention also proposes a device for optimizing passenger disembarkation scheduling strategies for intelligent monorail vehicles. The device includes: a memory, a processor, and programs such as an algorithm for optimizing passenger disembarkation scheduling strategies for intelligent monorail vehicles stored in the memory and executable on the processor. The algorithm for optimizing passenger disembarkation scheduling strategies for intelligent monorail vehicles comprises the steps for implementing the method for optimizing passenger disembarkation scheduling strategies for intelligent monorail vehicles as described above.

[0014] In addition, to achieve the above objectives, the present invention also provides a computer program product, which includes programs such as a passenger disembarkation scheduling strategy optimization algorithm for intelligent monorail vehicles. When the processor executes the programs such as the passenger disembarkation scheduling strategy optimization algorithm for intelligent monorail vehicles, it implements the passenger disembarkation scheduling strategy optimization method for intelligent monorail vehicles as described above.

[0015] The advantages and effects of this invention are: This invention proposes a method and system for optimizing passenger disembarkation scheduling strategies for intelligent monorail vehicles. Through multi-source data acquisition and an improved deep learning model, it achieves accurate prediction of passenger disembarkation demand, congestion levels, and operational status. Simultaneously, it overcomes the limitations of single-objective optimization, taking into account passenger disembarkation efficiency, platform dwell time, and line coordination. Dynamic weight adjustments adapt to different time-of-day demands, achieving a balance between local optimization and overall efficiency. Furthermore, based on the prediction results and optimization algorithms, it generates a fully customized solution encompassing door control, platform guidance, stop duration, and interval adjustments, adapting to different station types and passenger flow scenarios, resulting in more rational resource allocation. In addition, through real-time monitoring and a deviation triggering mechanism, it achieves dynamic optimization of the scheduling strategy, enabling rapid response to emergencies and ensuring consistently optimal scheduling performance. This provides an efficient, accurate, and flexible passenger disembarkation scheduling solution for intelligent monorail transit systems. Attached Figure Description

[0016] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0017] Figure 1 This is a flowchart of the passenger disembarkation scheduling strategy optimization method for intelligent monorail vehicles according to the present invention.

[0018] Figure 2 This is a schematic diagram of the passenger disembarkation scheduling strategy optimization system for intelligent monorail vehicles according to the present invention.

[0019] Figure 3 This is a schematic block diagram of the electronic equipment structure for optimizing passenger disembarkation scheduling strategies for intelligent monorail vehicles according to the present invention. Detailed Implementation

[0020] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0021] like Figure 1 As shown, in one embodiment of the present invention, the method for optimizing passenger disembarkation scheduling strategy for intelligent monorail vehicles includes the following steps: Step S10: Construct a multi-source data acquisition system, collect multi-dimensional scheduling data through vehicle-mounted sensing devices, station monitoring devices, passenger terminals and line control center, establish a dynamic database and perform data preprocessing.

[0022] Specifically, the multi-dimensional scheduling data in step S10 includes: Onboard data: Passenger density (people / m²) is collected via infrared sensors installed inside the monorail car. 2 Each carriage has 8 pressure sensors evenly distributed; pressure sensors are installed under the seats to collect seat occupancy status; 4 high-definition cameras per carriage cover the door area to collect passenger distribution location and disembarkation intention. Passenger distribution location is divided into near / middle / far door areas. Standing in the near door area for ≥30 seconds is considered as having the intention to disembark; the on-board control system collects the vehicle's current speed and remaining arrival time, and calculates based on GPS positioning and electronic route map. Platform data: Real-time passenger numbers are collected via infrared counters at platform entrances; lidar installed on the platform top collects platform congestion density; video surveillance equipment collects passenger distribution areas (near / middle / far end of the platform) and passenger boarding / alighting occupancy status (unobstructed / occupied / blocked) every 10 meters; and equipment monitoring modules collect the operational status (normal / faulty) of service facilities such as escalators and accessible elevators. Passenger data: Passengers' travel destinations, transfer needs, and drop-off preferences are collected through the passenger travel APP. Card terminals (gates, vehicle card readers) collect passenger entry time and travel duration. Transfer needs can be booked in advance. The APP feedback module collects real-time evaluations of passengers' drop-off experience, such as congested / smooth / average. Line data: The line control center collects the current departure interval of monorail vehicles, the congestion status of each section of the line (smooth / lightly congested / moderately congested / severely congested), the real-time running location of subsequent vehicles, the standard running time between stations, and temporary scheduling restrictions, such as construction and weather impacts.

[0023] Specifically, the data preprocessing process in step S10 includes: Data cleaning: Abnormal data is identified and removed using the 3σ principle, such as data with a density of 0 or exceeding the reasonable range due to sensor failure. Data with a missing rate ≤5% is supplemented using the mean imputation method, while data with a missing rate >5% is supplemented by interpolation of similar data from adjacent time periods. Data standardization: Min-Max normalization was performed on data of different dimensions to standardize passenger density (0-5 people / m²). 2 Congestion density (0-3 people / m²) 2 Data such as runtime (0-300 seconds) are uniformly mapped to the [0,1] interval to eliminate the impact of dimensional differences on subsequent model training; Data fusion: A weighted average fusion algorithm is used to fuse multi-source data for the same monitoring indicator. For example, in passenger density data, the weight of vehicle infrared sensor data is 0.6, the weight of camera recognition data is 0.3, and the weight of passenger feedback correction coefficient is 0.1, to ensure the accuracy and reliability of the data. Data storage: The preprocessed data is stored using the InfluxDB time-series database, which is classified and stored according to a three-dimensional index of "vehicle number-station number-time stamp". It supports high-concurrency read and write and fast historical data backtracking, providing data support for subsequent prediction and optimization.

[0024] Step S20: Based on the preprocessed multidimensional scheduling data, an improved deep learning model is used to predict passenger disembarkation demand, platform congestion level, and monorail vehicle operation status, and the prediction results are output.

[0025] Specifically, step S20, which uses an improved deep learning model to predict passenger disembarkation demand, platform congestion levels, and monorail vehicle operating status, includes the following steps: Passenger drop-off demand prediction: An improved LSTM model with an attention mechanism is adopted. The model input features include historical passenger drop-off volume (same time period and same station in the past 7 days), real-time passenger distribution (percentage of passengers near / mid / far of the door), travel time characteristics (weekday / weekend, peak / off-peak / low-peak), station type (hub station / ordinary station / suburban station), and transfer demand ratio. The attention mechanism strengthens the role of key features such as peak time and hub station by calculating the influence weight of each feature on passenger drop-off volume. The model is trained using at least 100,000 historical data covering different scenarios, with an initial adaptive learning rate of 0.001, decaying by 50% every 100 epochs. The loss function is mean squared error (MSE). An early stop mechanism is adopted to prevent overfitting. After training, the model predicts the number of passengers dropping off at the target station, the concentrated drop-off area at the door, and the duration of drop-off, with a prediction error ≤8%. Platform congestion level prediction: Based on the XGBoost model, input features include real-time platform passenger volume, current congestion density, historical congestion data for the same period, station type, service facility operation status, and external weather conditions; platform congestion levels are divided into 5 levels, with level 1 being unobstructed, density ≤ 0.5 people / m². 2 Level 2 is basically unobstructed, with a density of 0.5 < density ≤ 1.0 people / m³. 2 Level 3 is light congestion, with a density of 1.0 < density ≤ 1.5 people / m². 2 Level 4 is moderate congestion, with a density of 1.5 people to 2.0 people per square meter. 2 Level 5 indicates severe congestion, with a density > 2.0 people / m². 2 The model optimizes parameters through 5-fold cross-validation, achieving a classification accuracy of ≥93%, and outputs a prediction of the congestion level of the target site within the next 3 minutes. Operational status prediction: The model adopts the GRU gated cyclic unit model. The inputs are real-time operation data of the line, historical running time and external influencing factors. The operation data includes the current speed, station spacing and distance to the preceding vehicle. The external influencing factors include weather, passenger flow fluctuations, etc. The model outputs the precise time of the monorail vehicle to the target station, the optimal station stopping time and subsequent line operation coordination parameters. The prediction time error is ≤10 seconds.

[0026] Step S30: Using the prediction results as constraints, construct a multi-objective passenger disembarkation scheduling optimization function, solve for the optimal scheduling parameters through an intelligent optimization algorithm, and generate a customized passenger disembarkation scheduling scheme.

[0027] Specifically, step S30, which involves constructing the multi-objective passenger disembarkation scheduling optimization function, includes: Constructing a multi-objective optimization function: The optimization function is constructed based on three core objectives: 1) Maximizing passenger disembarkation efficiency: maxf1 = α × (number of passengers disembarking / stop duration), where f1 is the passenger disembarkation efficiency and α is the efficiency weighting coefficient, 0.4 ≤ α ≤ 0.6; 2) Minimizing platform dwell time: minf2 = β × (average passenger platform dwell time), where f2 is the platform dwell time for objective two and β is the dwell time weighting coefficient, 0.2 ≤ β ≤ 0.3; 3) Optimizing line coordination: maxf3 = γ ×(1-|Actual departure interval-Optimal departure interval| / Optimal departure interval), where f3 is the target three-line coordination, γ is the coordination weight coefficient, 0.2≤γ≤0.3, and α+β+γ=1; the constraints include the maximum monorail vehicle stopping time limit, the number of doors opened limit, the platform safety density threshold, and the line operation interval threshold. The maximum monorail vehicle stopping time limit is ≤60 seconds for ordinary stations and ≤120 seconds for hub stations. The number of doors opened is adjustable from 1 to 4. The platform safety density threshold is ≤2.0 people / m². 2 The minimum interval between trains on the line is ≥2 minutes. Intelligent optimization solution: An improved particle swarm optimization algorithm (PSO) is used to solve the multi-objective optimization function. Scheduling parameters are used as the dimensions of the particles, such as door opening combinations, opening duration, platform guidance direction, and stopping duration, with a dimension count of 6. Door opening combinations are encoded in binary, while opening and stopping durations are encoded using continuous values. The algorithm employs a dynamic inertia weight strategy, with an initial value of 0.9 that linearly decreases to 0.4 with each iteration, enhancing global search capability. The learning factors include an individual learning factor c1 = 1.5 and a global learning factor c2 = 2.0. The iteration count is set to 100, and the population size is 50. The optimal parameter combination that maximizes the optimization function F is obtained through iterative solution. Generate a scheduling plan: Based on the optimal parameter combination, generate a customized passenger disembarkation scheduling plan, including door control strategy, platform guidance strategy, stop duration allocation strategy, and suggestions for adjusting the departure interval of subsequent vehicles. The door control strategy includes the opening of single / multiple doors and the opening sequence. The platform guidance strategy includes LED screen indication and voice broadcast to guide passenger flow.

[0028] Specifically, generating a customized passenger disembarkation scheduling plan includes: Door control strategy: Clearly define the door number, opening order, and opening duration. For example, the opening order is to open the nearest door first and then the middle door. The opening duration is to extend the door opening time to 40 seconds during congestion. Platform guidance strategy: LED screens display recommended drop-off channels, voice announcements guide passenger flow and escalator / elevator directions, and voice announcements guide passenger flow such as "Please go to doors 2 and 4 to drop off passengers to avoid congestion"; Stop duration allocation: Specify the precise stop duration of the vehicle at the target station, such as 35 seconds; Train interval adjustment: Provide the line control center with suggestions for adjusting the departure interval of subsequent vehicles, such as shortening the departure interval from 3 minutes to 2.5 minutes during peak hours.

[0029] Step S40: Issue dispatch instructions through the three-level communication network of train-station-center, execute the passenger disembarkation dispatch plan and monitor the operation status in real time, and dynamically adjust the dispatch strategy based on feedback data to form a closed-loop management.

[0030] Specifically, step S40, which involves issuing scheduling instructions, executing the passenger disembarkation scheduling plan, and monitoring the operational status in real time, includes the following steps: Command Issuance and Execution: Through a three-level communication network of vehicle-station-center combined with 5G and edge computing, the commands in the scheduling plan are issued to the monorail vehicle onboard control system, the platform intelligent guidance system, and the line dispatch center. The monorail vehicle onboard control system receives the door control command, the platform intelligent guidance system receives the guidance command, and the line dispatch center receives the departure interval adjustment command. After the monorail vehicle arrives at the station, it opens the corresponding door according to the command. The platform LED screen displays the passenger disembarkation passage guidance in real time, and the voice broadcast system continuously prompts passengers to divert. Real-time monitoring and feedback: Onboard sensors and platform monitoring equipment collect execution data every 5 seconds, including the actual number of passengers disembarking, disembarkation time, changes in platform congestion density, passenger dwell time, and door operation status, which are uploaded to the line control center in real time through a three-level communication network; at the same time, passengers can provide real-time feedback on their disembarkation experience (congested / smooth / average) through the APP as supplementary feedback data. Closed-loop optimization and adjustment: The line control center compares the actual execution effect with the optimization target value and sets deviation thresholds, such as a 10% deviation threshold for passenger disembarkation efficiency, a 15-second deviation threshold for dwell time, a level 1 threshold for congestion level increase, and a 30% threshold for passenger negative feedback. When any deviation threshold is exceeded, the dynamic adjustment mechanism is triggered, the optimization algorithm in step S30 is called again, and the scheduling parameters are updated based on the latest feedback data, such as increasing the number of doors opened or extending the stop time. An adjusted scheduling plan is generated and immediately issued for execution. When the deviation is within the threshold range, the current scheduling plan is maintained until the next station or the next scheduling cycle (5 minutes) for further optimization and update.

[0031] In addition, such as Figure 2 As shown, in one embodiment of the present invention, a passenger disembarkation scheduling strategy optimization system for intelligent monorail vehicles is proposed. The system includes: Monorail vehicle multi-source data acquisition module: used to build a multi-source data acquisition system, collect multi-dimensional scheduling data through on-board sensing equipment, platform monitoring equipment, passenger terminals and line control center, establish a dynamic database and perform data preprocessing; Predictive Analysis Module: Based on preprocessed multidimensional scheduling data, this module uses an improved deep learning model to predict passenger disembarkation demand, platform congestion levels, and monorail vehicle operating status, and outputs the prediction results. Multi-objective optimization and scheduling scheme generation module: It is used to construct a multi-objective passenger disembarkation scheduling optimization function with the prediction results as constraints, solve for the optimal scheduling parameters through intelligent optimization algorithms, and generate a customized passenger disembarkation scheduling scheme; The scheduling execution and closed-loop optimization module is used to issue scheduling instructions through the three-level communication network of train-station-center, execute passenger disembarkation scheduling plan and monitor the operation status in real time, and dynamically adjust the scheduling strategy based on feedback data to form closed-loop management.

[0032] The passenger disembarkation scheduling strategy optimization system for intelligent monorail vehicles provided in this application adopts the passenger disembarkation scheduling strategy optimization method for intelligent monorail vehicles in the above embodiments, which can solve the technical problems of delayed demand response, unreasonable resource allocation, and supply-demand imbalance in existing monorail vehicle passenger disembarkation scheduling. Compared with the prior art, the beneficial effects of the passenger disembarkation scheduling strategy optimization system for intelligent monorail vehicles provided in this application are the same as the beneficial effects of the passenger disembarkation scheduling strategy optimization method for intelligent monorail vehicles provided in the above embodiments, and other technical features of the passenger disembarkation scheduling strategy optimization system for intelligent monorail vehicles are the same as the features disclosed in the methods of the above embodiments, and will not be repeated here.

[0033] This application provides a device for optimizing passenger disembarkation scheduling strategies for intelligent monorail vehicles. The device includes: at least one processor; and a memory communicatively connected to the at least one processor. The memory stores instructions executable by the at least one processor, which are executed by the at least one processor to enable the at least one processor to execute the passenger disembarkation scheduling strategy optimization method for intelligent monorail vehicles described in Embodiment 1 above.

[0034] like Figure 3 As shown in one embodiment of the present invention, a structural schematic diagram of a passenger disembarkation scheduling strategy optimization device suitable for implementing the embodiments of this application is illustrated. The passenger disembarkation scheduling strategy optimization device for intelligent monorail vehicles in the embodiments of this application may include, but is not limited to, mobile terminals such as mobile phones, laptops, digital broadcast receivers, PDAs (Personal Digital Assistants), PADs (Portable Application Descriptions), PMPs (Portable Media Players), etc., and fixed terminals such as digital TVs, desktop computers, etc. Figure 3 The illustrated device for optimizing passenger disembarkation scheduling for intelligent monorail vehicles is merely an example and should not impose any limitations on the functionality and scope of use of the embodiments in this application.

[0035] Figure 3The illustrated passenger disembarkation scheduling optimization device for intelligent monorail vehicles may include a processor 1001 (e.g., a central processing unit, graphics processing unit, etc.), which can perform various appropriate actions and processes according to a program stored in read-only memory (ROM) 1002 or a program loaded from storage device 1003 into machine-readable storage medium (RAM) 1004. The RAM 1004 also stores various programs and data required for the operation of the passenger disembarkation scheduling optimization device for intelligent monorail vehicles. The processor 1001, ROM 1002, and RAM 1004 are interconnected via a bus 1005. An input / output (I / O) interface 1006 is also connected to the bus. Typically, the following systems can be connected to I / O interface 1006: input devices 1007 including, for example, touchscreens, touchpads, keyboards, mice, image sensors, microphones, accelerometers, gyroscopes, etc.; output devices 1008 including, for example, liquid crystal displays (LCDs), speakers, vibrators, etc.; storage devices 1003 including, for example, magnetic tapes, hard disks, etc.; and communication unit 1009. Communication unit 1009 allows the intelligent monorail passenger disembarkation scheduling strategy optimization device to exchange data with other devices wirelessly or via wired communication. Although the figure shows an intelligent monorail passenger disembarkation scheduling strategy optimization device with various systems, it should be understood that it is not required to implement or possess all the systems shown. More or fewer systems can be implemented alternatively.

[0036] Specifically, according to the embodiments disclosed in this application, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments disclosed in this application include a computer program product comprising a computer program carried on a computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via a communication unit, or installed from storage device 1003, or installed from ROM 1002. When the computer program is executed by processor 1001, it performs the functions defined in the methods of the embodiments disclosed in this application.

[0037] The passenger disembarkation scheduling strategy optimization device for intelligent monorail vehicles provided in this application adopts the passenger disembarkation scheduling strategy optimization method for intelligent monorail vehicles in the above embodiments, which can solve the technical problems of delayed demand response, unreasonable resource allocation, and supply-demand imbalance in existing monorail vehicle passenger disembarkation scheduling. Compared with the prior art, the beneficial effects of the passenger disembarkation scheduling strategy optimization device for intelligent monorail vehicles provided in this application are the same as the beneficial effects of the passenger disembarkation scheduling strategy optimization method for intelligent monorail vehicles provided in the above embodiments, and other technical features in the passenger disembarkation scheduling strategy optimization device for intelligent monorail vehicles are the same as the features disclosed in the method of the previous embodiment, and will not be repeated here.

[0038] The various parts disclosed in this application can be implemented using hardware, software, firmware, or a combination thereof. In the description of the above embodiments, specific features, structures, materials, or characteristics can be combined in any suitable manner in one or more embodiments or examples.

[0039] This application also provides a computer program product, including a computer program that, when executed by a processor, implements the steps of the above-described method for optimizing passenger disembarkation scheduling strategies for intelligent monorail vehicles.

[0040] The computer program product provided in this application can solve the technical problems of delayed demand response, unreasonable resource allocation, and supply-demand imbalance in existing monorail vehicle passenger disembarkation scheduling. Compared with the prior art, the beneficial effects of the computer program product provided in this application are the same as those of the passenger disembarkation scheduling strategy optimization method for intelligent monorail vehicles provided in the above embodiments, and will not be repeated here.

[0041] Obviously, those skilled in the art can make various modifications and variations to this invention without departing from its spirit and scope. Therefore, if these modifications and variations fall within the scope of the claims of this invention and their equivalents, this invention also intends to include these modifications and variations.

Claims

1. A method for optimizing passenger disembarkation scheduling strategies for intelligent monorail vehicles, characterized in that, The method includes the following steps: Step S10: Construct a multi-source data acquisition system, collect multi-dimensional scheduling data through vehicle-mounted sensing devices, platform monitoring devices, passenger terminals and line control center, establish a dynamic database and perform data preprocessing; Step S20: Based on the preprocessed multidimensional scheduling data, an improved deep learning model is used to predict passenger disembarkation demand, platform congestion level, and monorail vehicle operation status, and the prediction results are output. Step S30: Using the prediction results as constraints, construct a multi-objective passenger disembarkation scheduling optimization function, solve for the optimal scheduling parameters through an intelligent optimization algorithm, and generate a customized passenger disembarkation scheduling scheme; Step S40: Issue dispatch instructions through the three-level communication network of train-station-center, execute the passenger disembarkation dispatch plan and monitor the operation status in real time, and dynamically adjust the dispatch strategy based on feedback data to form a closed-loop management.

2. The method for optimizing passenger disembarkation scheduling strategy for intelligent monorail vehicles according to claim 1, characterized in that, The multi-dimensional scheduling data in step S10 includes: Onboard data: The data collected by the monorail vehicle’s onboard infrared sensors, pressure sensors, and cameras includes passenger density, seat occupancy status, passenger distribution, disembarkation intentions, current vehicle speed, and remaining arrival time. Disembarkation intentions are determined by the distance between the passenger’s standing area and the door. Platform data: Real-time passenger numbers, passenger distribution areas, platform congestion density, occupancy status of boarding and alighting passages, and operational status of platform service facilities, collected through platform infrared counters, lidar, and video surveillance equipment. Passenger data: Information collected through passenger travel apps and card terminals, including passenger travel destinations, transfer needs, reservation drop-off preferences, and real-time feedback. Line data: Information collected by the line control center, including monorail train departure intervals, congested sections of the line, the location of subsequent vehicles, the running time between stations, and temporary scheduling restrictions.

3. The method for optimizing passenger disembarkation scheduling strategy for intelligent monorail vehicles according to claim 1, characterized in that, The data preprocessing process in step S10 includes: Data cleaning: An outlier detection algorithm is used to remove abnormal data caused by sensor malfunctions and signal interference based on the 3σ principle, and missing data is supplemented by mean imputation method; Data standardization: Normalize data from different dimensions by using Min-Max normalization to the [0,1] interval to eliminate differences in units, including scaling passenger density and congestion density proportionally and converting time-related data into standardized duration factors; Data fusion: A weighted average fusion algorithm is used to fuse multi-source data of the same monitoring object to generate unified state representation data; Data storage: The preprocessed data is categorized by timestamp and stored in a dynamic database. The time-series database InfluxDB is used to support high-concurrency read and write operations and historical data backtracking analysis.

4. The method for optimizing passenger disembarkation scheduling strategy for intelligent monorail vehicles according to claim 1, characterized in that, The step S20, which uses an improved deep learning model to predict passenger disembarkation demand, platform congestion levels, and monorail vehicle operating status, includes: Passenger drop-off demand prediction: An improved LSTM long short-term memory network model is adopted, and an attention mechanism is introduced to strengthen the weight of key influencing factors. Inputting historical passenger drop-off volume, real-time passenger distribution and travel time period characteristic data, the model predicts the number of passengers, the concentrated drop-off area and the duration of drop-off by the monorail at the target station. Platform congestion level prediction: Based on the XGBoost model, the platform congestion level is divided into 5 levels with real-time platform passenger volume, congestion density, historical congestion data and station type as input features, and the congestion level prediction result of the target station in the next 3 minutes is output. Operation status prediction: Using the GRU gated cyclic unit model, inputting real-time line operation data, historical running time and external influencing factors, predicts the precise time for the monorail vehicle to arrive at the target station, the optimal station stopping time and subsequent line operation coordination parameters.

5. The method for optimizing passenger disembarkation scheduling strategy for intelligent monorail vehicles according to claim 1, characterized in that, The step of constructing the multi-objective passenger disembarkation scheduling optimization function in step S30 includes: Construct a multi-objective optimization function: The optimization function is constructed with three core objectives: 1) Maximize passenger disembarkation efficiency, maxf1=α×(number of passengers disembarking / stop time), where f1 is the passenger disembarkation efficiency and α is the efficiency weight coefficient; 2) Minimize platform dwell time, minf2=β×(average passenger platform dwell time), where f2 is the platform dwell time and β is the dwell time weight coefficient; 3) Optimize line coordination, maxf3=γ×(1-|actual departure interval-optimal departure interval| / optimal departure interval), where f3 is the line coordination of objective 3 and γ is the coordination weight coefficient, and α+β+γ=1; The constraints include the maximum stop time limit for monorail vehicles, the limit on the number of doors opened, the platform safety density threshold, and the line operation interval threshold. Intelligent optimization solution: The improved Particle Swarm Optimization (PSO) algorithm is used to solve the multi-objective optimization function. By dynamically adjusting the inertia weight and learning factor, the convergence speed and global optimal solution search capability of the algorithm are improved. The passenger disembarkation scheduling parameters are used as the particle dimension, and the optimal parameter combination is obtained by iterative solution. Generate a scheduling scheme: Based on the optimal parameter combination, generate a customized passenger disembarkation scheduling scheme, including door control strategy, platform guidance strategy, stop duration allocation strategy, and suggestions for adjusting subsequent vehicle departure intervals.

6. The method for optimizing passenger disembarkation scheduling strategy for intelligent monorail vehicles according to claim 1, characterized in that, The steps in step S40, which involve issuing scheduling instructions, executing the passenger disembarkation scheduling plan, and monitoring the operational status in real time, include: Command issuance and execution: Through a three-level communication network of vehicle-station-center combined with 5G and edge computing, the commands in the scheduling plan are issued to the monorail vehicle on-board control system, the platform intelligent guidance system and the line dispatch center respectively. After the monorail vehicle arrives at the station, it opens the corresponding doors according to the command. The platform LED screen displays the passenger disembarkation channel guidance in real time, and the voice broadcast system continuously prompts passengers to divert. Real-time monitoring and feedback: The dispatch execution data is collected in real time through on-board sensors and platform monitoring equipment, including the actual number of passengers getting off, the time taken to get off, changes in platform congestion density and passenger dwell time, and the feedback data is uploaded to the line control center every 5 seconds; Closed-loop optimization and adjustment: The line control center compares the actual execution effect with the optimization target value. When the deviation exceeds the preset threshold, the dynamic adjustment mechanism is triggered, the optimization algorithm of step S30 is called again, the scheduling parameters are updated based on the latest feedback data, the adjusted scheduling scheme is generated and issued for execution.

7. A passenger disembarkation scheduling strategy optimization system for intelligent monorail vehicles, executing the method according to any one of claims 1 to 6, characterized in that, include: Monorail vehicle multi-source data acquisition module: used to build a multi-source data acquisition system, collect multi-dimensional scheduling data through on-board sensing equipment, platform monitoring equipment, passenger terminals and line control center, establish a dynamic database and perform data preprocessing; Predictive Analysis Module: Based on preprocessed multidimensional scheduling data, this module uses an improved deep learning model to predict passenger disembarkation demand, platform congestion levels, and monorail vehicle operating status, and outputs the prediction results. Multi-objective optimization and scheduling scheme generation module: It is used to construct a multi-objective passenger disembarkation scheduling optimization function with the prediction results as constraints, solve for the optimal scheduling parameters through intelligent optimization algorithms, and generate a customized passenger disembarkation scheduling scheme; The scheduling execution and closed-loop optimization module is used to issue scheduling instructions through the three-level communication network of train-station-center, execute passenger disembarkation scheduling plan and monitor the operation status in real time, and dynamically adjust the scheduling strategy based on feedback data to form closed-loop management.

8. A device for optimizing passenger disembarkation scheduling strategies for intelligent monorail vehicles, characterized in that: include: The system includes a memory, a processor, and a passenger disembarkation scheduling strategy optimization program for intelligent monorail vehicles stored in the memory and executable on the processor. When the processor executes the passenger disembarkation scheduling strategy optimization program for intelligent monorail vehicles, it implements the passenger disembarkation scheduling strategy optimization method for intelligent monorail vehicles as described in any one of claims 1 to 6.

9. A computer program product, characterized in that, The computer program product includes a passenger disembarkation scheduling strategy optimization program for intelligent monorail vehicles. When the passenger disembarkation scheduling strategy optimization program for intelligent monorail vehicles is executed by the processor, it implements the passenger disembarkation scheduling strategy optimization method for intelligent monorail vehicles as described in any one of claims 1 to 6.

Images