Multi-ship lock cooperative ship navigation scheduling method based on complex scene self-adaptation

Abstract

The application discloses a multi-ship lock cooperative ship navigation scheduling method based on complex scene self-adaption, comprising: acquiring static and dynamic data of a multi-ship lock system, constructing a basic complex network model, calculating by using the basic complex network model to obtain a basic data calculation result; acquiring new real-time data based on the basic data calculation result and preprocessing to obtain processed dynamic characteristic data; optimizing the basic complex network model by using the processed dynamic characteristic data, constructing a cascade effect prediction model; predicting congestion propagation based on the cascade effect prediction model to obtain a prediction result, executing cooperative scheduling, realizing intelligent monitoring and cascade effect prevention control of the multi-ship lock system. The application quantifies the correlation between ship lock operation synchronism and congestion diffusion, realizes accurate prediction of a risk propagation path, effectively reduces the congestion cross-ship lock propagation probability, and further shortens the average fault recovery time required.

Description

Technical Field

[0001] This invention relates to the field of navigation scheduling technology, and in particular to a multi-lock collaborative vessel navigation scheduling method based on complex scenarios. Background Technology

[0002] In recent years, inland waterway transportation has become an important component of the modern logistics system, and its navigation efficiency directly impacts regional economic development. Ship locks, as key facilities for overcoming differences in waterway levels, bear the core responsibility of vessel navigation. With the increasing number of vessels and their trend towards larger and more diverse vessels, traditional single-lock scheduling can no longer meet navigation demands under complex scenarios (such as peak traffic, cascading failures, or severe weather). Multi-lock collaborative scheduling optimizes vessel passage through networked connections and intelligent algorithms, aiming to improve overall transportation efficiency. Existing technologies are mostly based on queuing theory or simple graph theory, combined with data from AIS, video surveillance, etc., initially achieving information sharing and scheduling optimization between ship locks.

[0003] However, existing technologies for multi-lock collaborative scheduling typically rely on static topology analysis or fixed rules, which are insufficient to effectively address cascading failures in complex scenarios. Specifically, when a lock malfunctions or experiences a surge in traffic, existing scheduling methods lack dynamic prediction and intervention mechanisms for the propagation of congestion across locks. This results in the inability to promptly halt the chain reaction, leading to decreased navigation efficiency or system instability. Therefore, it is necessary to design an adaptive multi-lock collaborative vessel navigation scheduling method based on complex scenarios to address these issues. Summary of the Invention

[0004] The purpose of this section is to outline some aspects of embodiments of the present invention and to briefly describe some preferred embodiments. Simplifications or omissions may be made in this section, as well as in the abstract and title of this application, to avoid obscuring the purpose of these documents; however, such simplifications or omissions should not be construed as limiting the scope of the invention.

[0005] In view of the problems existing in the above-mentioned adaptive multi-lock collaborative vessel navigation scheduling method based on complex scenarios, this invention is proposed.

[0006] Therefore, the purpose of this invention is to provide an adaptive multi-lock collaborative vessel navigation scheduling method based on complex scenarios. This method is suitable for solving the problem that existing scheduling methods lack dynamic prediction and intervention mechanisms for the propagation of congestion across locks, which leads to the inability to promptly block the chain effect, resulting in decreased navigation efficiency or system instability.

[0007] To solve the above-mentioned technical problems, the present invention provides the following technical solution:

[0008] In a first aspect, embodiments of the present invention provide an adaptive multi-lock collaborative vessel navigation scheduling method based on complex scenarios, including:

[0009] The static and dynamic data of the multi-lock system are acquired, and a basic complex network model is constructed. The basic complex network model is used to perform calculations to obtain the basic data calculation results.

[0010] Based on the calculation results of the basic data, new real-time data is obtained and preprocessed to obtain processed dynamic feature data.

[0011] The basic complex network model is optimized using the processed dynamic feature data to construct a cascade effect prediction model;

[0012] Based on the cascading effect prediction model, congestion propagation is predicted, the prediction results are obtained, and coordinated scheduling is performed to realize intelligent monitoring and cascading effect prevention and control of the multi-lock system.

[0013] As a preferred embodiment of the multi-lock collaborative vessel navigation scheduling method based on complex scenarios described in this invention, obtaining the static data of the multi-lock system refers to collecting the lock chamber capacity, average passage time, failure history rate, channel connection distance, and capacity limit of the locks through the lock management system.

[0014] Acquiring dynamic data of the multi-lock system refers to collecting real-time ship positions, immediate fault events, ship flow fluctuation sequences, and synchronization phase offsets between locks through AIS terminals, laser scanners, and video surveillance.

[0015] As a preferred embodiment of the multi-lock collaborative vessel navigation scheduling method based on complex scenarios described in this invention, the construction of the basic complex network model includes the following steps:

[0016] By introducing an exponential function to process the composite effects of lock node attributes, a node capacity correction value is obtained, thereby enhancing the response capability of the basic complex network model to scenarios with high failure rates or long lock passage times. The specific formula is as follows:

[0017] ;

[0018] in, This is the node capacity correction value, representing the correction value for the capacity of the i-th lock affected by the average lock passage time and the historical failure rate. It reflects the effective carrying capacity of the node in complex scenarios. The lock chamber capacity is derived from static data in the lock management system. The average gate passage time is derived from historical gate passage records. Let be the historical failure rate of the i-th lock, derived from failure log statistics. The exponential adjustment coefficient is used to control the sensitivity of time and faults to capacity correction, and is determined through regression analysis of historical data. The combined influence of channel edge attributes is quantified by introducing a fractional structure to obtain edge weight values, thereby reducing the interference of connection distance and faults on edge connection strength in the basic complex network model. The specific formula is as follows:

[0019] ;

[0020] in, The edge weight value represents the channel connectivity strength between the i-th lock and the j-th lock, reflecting the interaction between channel capacity, distance, and faults. The upper limit of channel capacity is derived from channel design parameters. The distance between the two locks is derived from a geographic information system. The denominator adjustment coefficient is used to balance the effects of distance and failure history rate. By introducing a summation correction term to process the differences in lock node connections, the node degree value is obtained, thereby improving the adaptability of the basic complex network model under different connection density conditions. The specific formula is as follows:

[0021] ;

[0022] in, Let be the node degree value of the i-th lock, representing the total connection strength of that lock;

[0023] Based on the obtained node capacity correction values, edge weight values, and node degree values, a basic complex network model is constructed to comprehensively evaluate the impact of lock capacity, channel connection strength, and network connection density on ship navigation efficiency.

[0024] As a preferred embodiment of the multi-lock collaborative vessel navigation scheduling method based on complex scenarios described in this invention, the specific formula of the basic complex network model is as follows:

[0025] G = (V, E, W);

[0026] Wherein, G is the basic complex network model, representing the weighted undirected graph structure of the multi-lock system, V is the lock node set, containing n lock nodes, each node is associated with a node capacity correction value and a node degree value, E is the channel edge set, representing the channel connection between locks, and W is the edge weight matrix, used to quantify the ship passage efficiency and congestion propagation risk.

[0027] As a preferred embodiment of the multi-lock collaborative vessel navigation scheduling method based on complex scenarios described in this invention, the new real-time data includes the deviation between the real-time vessel flow and the calculation results of the basic data, the congestion propagation rate, and the congestion duration.

[0028] Obtaining new real-time data based on the calculation results of the aforementioned basic data includes the following steps:

[0029] Based on the calculation results of the basic data, if the deviation between the real-time ship flow and the calculation results of the basic data is less than or equal to the first flow threshold, it is determined to be a low flow deviation area. The time interval for real-time data collection is set to T1, and the real-time ship position, ship flow fluctuation sequence and lock synchronization phase offset data are obtained.

[0030] If the deviation between the real-time flow of the ship and the calculation result of the basic data is greater than the first flow threshold but less than the second flow threshold, it is determined to be a medium flow deviation area. The time interval for real-time data collection is set to T2, and the real-time position of the ship, the immediate fault event, and the synchronous phase offset data between the locks are obtained.

[0031] If the deviation between the real-time ship flow and the calculated result of the basic data is greater than or equal to the second flow threshold, it is determined to be a high flow deviation area. The time interval for real-time data collection is set to T3, and the real-time ship position, immediate fault events, ship flow fluctuation sequence and lock synchronization phase offset data are obtained.

[0032] As a preferred embodiment of the multi-lock collaborative vessel navigation scheduling method based on complex scenarios described in this invention, the construction of the cascading effect prediction model includes the following steps:

[0033] By introducing an instantaneous congestion coefficient, the degree to which ship traffic exceeds the lock's capacity is quantified, resulting in a real-time overload index for the waterway. This index reflects the risk of congestion triggering at the current node. The specific formula is as follows:

[0034] ;

[0035] in, Let be the instantaneous congestion coefficient of the i-th lock at time t. This represents the number of ships that actually arrived at the i-th lock at time t. The expected throughput of the i-th lock is calculated using a basic complex network model. By introducing a phase coordination attenuation factor, the synchronization deviation of adjacent lock operations is compensated, resulting in a channel coordination attenuation coefficient. This suppresses the spread of congestion caused by asynchronous lock operations. The specific formula is as follows:

[0036] ;

[0037] in, Let be the cooperative attenuation coefficient between channels i and j at time t. This represents the absolute value of the measured phase shift. This serves as the normalization reference for the phase offset.

[0038] Based on the instantaneous congestion coefficient and the coordinated attenuation coefficient, a cascading effect prediction model is constructed to obtain the node cascading risk index, which comprehensively reflects the combined risk level of local overload and global coordinated failure.

[0039] As a preferred embodiment of the multi-lock collaborative vessel navigation scheduling method based on complex scenarios described in this invention, the specific formula of the cascading effect prediction model is as follows:

[0040] ;

[0041] in, The node cascading risk index represents the probability that the i-th lock at time t will trigger cascading congestion in the waterway network. The number of adjacent waterways. This represents the summation of the coordination coefficients of all adjacent channels j of the i-th lock.

[0042] As a preferred embodiment of the multi-lock collaborative vessel navigation scheduling method based on complex scenarios described in this invention, the following steps are included: Congestion propagation prediction is performed based on the cascading effect prediction model to obtain the prediction results, and collaborative scheduling is then executed:

[0043] Based on the node cascade risk index and congestion propagation rate, the channel status is determined, and the following judgment is performed:

[0044] If the node cascade risk index is less than or equal to the cascade risk safety threshold, and the congestion propagation rate is less than or equal to the propagation rate threshold, then the current waterway status is determined to be normal passage status, the existing lock scheduling strategy is maintained, and real-time ship location data and lock operation parameters are continuously collected.

[0045] If the node cascade risk index is less than or equal to the cascade risk safety threshold, but the congestion propagation rate is greater than the propagation rate threshold, then the current waterway status is preliminarily determined to be a congestion spread warning state, and the next step is executed.

[0046] When the current waterway status is initially determined to be a congestion spread warning status, the judgment is upgraded based on the duration of congestion and the fluctuation sequence of ship traffic.

[0047] If the congestion duration is less than or equal to the duration threshold, and the variance of the ship flow fluctuation sequence is less than or equal to the fluctuation threshold, then it is finally determined to be a locally controllable congestion state, and the first scheduling scheme is executed.

[0048] If the congestion duration exceeds the duration threshold, or the variance of the ship flow fluctuation sequence exceeds the fluctuation threshold, it is determined to be a global spread state, and the second scheduling scheme is executed.

[0049] If the node cascading risk index is greater than the cascading risk safety threshold and the congestion propagation rate is greater than the propagation critical threshold, then it is directly determined to be a cascading out-of-control state, and the third scheduling scheme is executed.

[0050] In a second aspect, embodiments of the present invention provide a computer device, including a memory and a processor, wherein the memory stores a computer program, and the computer program, when executed by the processor, implements any step of the multi-lock cooperative vessel navigation scheduling method based on complex scenarios as described in the first aspect of the present invention.

[0051] Thirdly, embodiments of the present invention provide a computer-readable storage medium having a computer program stored thereon, wherein: when the computer program is executed by a processor, it implements any step of the multi-lock cooperative vessel navigation scheduling method based on complex scenario adaptation described in the first aspect of the present invention.

[0052] The beneficial effects of this invention are as follows: By integrating static attribute data and dynamic operation data of the locks, a basic complex network model is constructed, achieving for the first time a quantitative representation of the collaborative operation status of multiple locks. By introducing a node capacity correction index and a channel edge weight fractional algorithm, the model's adaptability to complex scenarios such as high failure rates and long-distance channels is significantly improved. By establishing a three-level flow deviation response mechanism (low / medium / high flow deviation areas), intelligent allocation of monitoring resources is achieved. High-frequency data acquisition is used in high-risk areas; only key parameters are collected in safe areas, significantly reducing the system's computational load while ensuring the accuracy of risk warnings.

[0053] By constructing a cascading effect prediction model, the correlation between the synchronicity of lock operations and congestion spread is quantified, enabling accurate prediction of risk propagation paths. Based on a three-level state determination mechanism of node cascading risk index, differentiated scheduling strategies are dynamically triggered, thereby effectively reducing the probability of congestion propagating across locks and shortening the average fault recovery time. This invention is not only applicable to large inland waterways but can also be extended to multi-node transportation network management, such as port cluster coordination or urban transportation hub scheduling. Attached Figure Description

[0054] To more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings used in the description of the embodiments 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. Wherein:

[0055] Figure 1 This is a schematic diagram of the overall process of the multi-lock collaborative vessel navigation scheduling method based on complex scenarios proposed in this invention;

[0056] Figure 2 This is a schematic diagram of the deviation area judgment logic of the multi-lock collaborative vessel navigation scheduling method based on complex scenarios proposed in this invention.

[0057] Figure 3 This is a schematic diagram of the state judgment logic of the adaptive multi-lock collaborative ship navigation scheduling method based on complex scenarios proposed in this invention. Detailed Implementation

[0058] To make the above-mentioned objects, features and advantages of the present invention more apparent and understandable, the specific embodiments of the present invention will be described in detail below with reference to the accompanying drawings.

[0059] Many specific details are set forth in the following description in order to provide a full understanding of the invention. However, the invention may also be practiced in other ways different from those described herein, and those skilled in the art can make similar extensions without departing from the spirit of the invention. Therefore, the invention is not limited to the specific embodiments disclosed below.

[0060] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The phrase "in one embodiment" appearing in different places in this specification does not necessarily refer to the same embodiment, nor is it a single or selective embodiment that is mutually exclusive with other embodiments.

[0061] Secondly, the present invention is described in detail with reference to the schematic diagrams. When detailing the embodiments of the present invention, for ease of explanation, the cross-sectional views illustrating the device structure may be partially enlarged, not according to the usual scale. Furthermore, the schematic diagrams are merely examples and should not limit the scope of protection of the present invention. In addition, actual fabrication should include three-dimensional spatial dimensions of length, width, and depth.

[0062] Example 1

[0063] Reference Figures 1-3 As an embodiment of the present invention, a multi-lock collaborative vessel navigation scheduling method based on complex scenarios is provided.

[0064] Existing technologies for multi-lock collaborative scheduling typically rely on static topology analysis or fixed rules, which are insufficient to effectively address cascading failures in complex scenarios. Specifically, when a lock malfunctions or experiences a surge in traffic, existing scheduling methods lack dynamic prediction and intervention mechanisms for the propagation of congestion across locks, resulting in the inability to promptly interrupt chain reactions, leading to decreased navigation efficiency or system instability.

[0065] This application provides a method that can effectively solve the problems mentioned above. The following will describe in detail how to implement the adaptive multi-lock collaborative ship navigation scheduling method based on complex scenarios using multiple embodiments.

[0066] Figure 1 The overall flowchart of the adaptive multi-lock collaborative vessel navigation scheduling method based on complex scenarios is shown, including:

[0067] S1: Obtain static and dynamic data of the multi-lock system, construct a basic complex network model, and use the basic complex network model to perform calculations to obtain the basic data calculation results.

[0068] Preferably, obtaining static data of a multi-lock system refers to collecting data on lock chamber capacity, average lock passage time, historical failure rate, channel connection distance, and capacity limit of the locks through the lock management system.

[0069] It should be noted that the lock management system is an important component of existing shipping management technology. It is primarily used to monitor and control the operational status of locks, collecting and managing data such as lock chamber capacity, average lock passage time, historical fault records, waterway connection distances, and capacity limits. This system typically integrates sensors, data acquisition terminals, and management software, and can interact with Automatic Identification System (AIS), video surveillance, and other auxiliary systems to support lock scheduling, operation and maintenance, and safety management. Currently, lock management systems are widely used in navigation management of inland waterways and port clusters.

[0070] Acquiring dynamic data of a multi-lock system refers to collecting real-time ship positions, immediate fault events, ship flow fluctuation sequences, and synchronization phase offsets between locks through AIS terminals, laser scanners, and video surveillance.

[0071] Furthermore, constructing a basic complex network model includes the following steps:

[0072] By introducing an exponential function to process the composite effects of lock node attributes, a node capacity correction value is obtained, thereby enhancing the response capability of the basic complex network model to scenarios with high failure rates or long lock passage times. The specific formula is as follows:

[0073] ;

[0074] in, This is the node capacity correction value, representing the correction value for the capacity of the i-th lock affected by the average lock passage time and the historical failure rate. It reflects the effective carrying capacity of the node in complex scenarios. The lock chamber capacity is derived from static data in the lock management system. The average gate passage time is derived from historical gate passage records. Let be the historical failure rate of the i-th lock, derived from failure log statistics. This is the exponential adjustment coefficient, used to control the sensitivity of time and faults to capacity correction, and is determined through regression analysis of historical data;

[0075] By introducing a fractional structure to quantify the composite influence of channel edge attributes, edge weight values ​​are obtained, thereby reducing the interference of connection distance and faults on edge connection strength in the basic complex network model. The specific formula is as follows:

[0076] ;

[0077] in, The edge weight value represents the channel connectivity strength between the i-th lock and the j-th lock, reflecting the interaction between channel capacity, distance, and faults. The upper limit of channel capacity is derived from channel design parameters. The distance between the two locks is derived from a geographic information system. This is the adjustment coefficient in the denominator, used to balance the effects of distance and failure history rate;

[0078] By introducing a summation correction term to process the differences in lock node connections, the node degree value is obtained, thereby improving the adaptability of the basic complex network model under different connection density conditions. The specific formula is as follows:

[0079] ;

[0080] in, Let be the node degree value of the i-th lock, representing the total connection strength of that lock;

[0081] Based on the obtained node capacity correction values, edge weight values, and node degree values, a basic complex network model is constructed to comprehensively evaluate the impact of lock capacity, channel connectivity strength, and network connectivity density on ship navigation efficiency. The specific formulas for the basic complex network model are as follows:

[0082] G = (V, E, W);

[0083] Where G is the basic complex network model, representing the weighted undirected graph structure of the multi-lock system, and V is the lock node set containing n lock nodes, with each node associated with a capacity correction value. and node degree value E is the channel edge set, representing the channel connection between locks, and W is the edge weight matrix, used to quantify the efficiency of ship passage and the risk of congestion propagation.

[0084] It should be noted that the lock node set V is represented as:

[0085] ;

[0086] in, This represents the i-th lock node. The above structure shows that each lock node is simultaneously associated with a node capacity correction value. and node degree value Two core attributes are used to evaluate the mobility of nodes and their network connectivity characteristics in complex network analysis;

[0087] The edge weight matrix W is represented as:

[0088] ;

[0089] When there is no direct channel connection between two locks, the edge weight is 0.

[0090] In this embodiment of the application, the exponential adjustment coefficient and denominator adjustment coefficient The values ​​can be determined by combining data-driven approaches with engineering experience: On the one hand, based on historical AIS data, lock operation logs, fault records, and traffic efficiency observations, an offline calibration process can be constructed with congestion prediction errors or navigation efficiency deviations as the target. Data training or optimization algorithms (such as gradient descent methods, Bayesian optimization, or grid search) can be used to fit the coefficients to obtain the optimal values ​​suitable for the target waterway or typical operating scenarios. On the other hand, in scenarios where historical data is insufficient or needs to be deployed as soon as possible, navigation management and shipping engineering experts can provide initial values ​​based on typical lock chamber parameters, common lock passage time distributions, and maintenance fault statistics, and then calibrate them through simulation backtesting (scenario playback), on-site testing, or retrospective verification.

[0091] S2: Based on the calculation results of the basic data, new real-time data is obtained and preprocessed to obtain the processed dynamic feature data.

[0092] Preferably, the new real-time data includes the deviation between real-time ship traffic and the calculated results of basic data, the congestion propagation rate, and the congestion duration;

[0093] Furthermore, such as Figure 2 As shown, obtaining new real-time data based on the calculation results of basic data includes the following steps:

[0094] Based on the calculation results of the basic data, if the deviation between the real-time flow of the ship and the calculation results of the basic data is less than or equal to the first flow threshold, it is determined to be a low flow deviation area. The time interval for real-time data collection is set to T1, and the real-time position of the ship, the ship flow fluctuation sequence and the synchronous phase offset data between the locks are obtained.

[0095] If the deviation between the real-time flow of the ship and the calculation result of the basic data is greater than the first flow threshold but less than the second flow threshold, it is determined to be a medium flow deviation area. The time interval for real-time data collection is set to T2, and the real-time position of the ship, the immediate fault event, and the synchronous phase offset data between the locks are obtained.

[0096] If the deviation between the real-time ship flow and the calculated result of the basic data is greater than or equal to the second flow threshold, it is determined to be a high flow deviation area. The time interval for real-time data collection is set to T3, and the real-time ship position, immediate fault events, ship flow fluctuation sequence and lock synchronization phase offset data are obtained.

[0097] It should be noted that the thresholds for judging deviation values ​​are first based on the actual deviation characteristics of ship traffic. Historical AIS data, lock operation logs, and monitoring records are collected under typical navigation sections, different time periods, and different navigation conditions. Statistical analysis and hierarchical classification are then performed, and deviation magnitudes are categorized in conjunction with navigation efficiency and safety indicators. Finally, the optimal first and second flow thresholds are obtained through simulation playback, backtracking verification, and sensitivity analysis. Secondly, regarding the setting of historical data collection intervals, a comprehensive evaluation of deviation trend capture accuracy and data transmission / processing costs should be conducted. The detection rate, false alarm rate, and calculation delay of deviation trends at different collection intervals should be compared to determine the trade-off between accuracy and resource consumption. For navigation sections with insufficient historical data or requiring rapid deployment, initial thresholds and collection intervals can be provided by navigation management or shipping engineering experts based on typical lock chamber parameters and lock passage statistics, and then gradually calibrated through on-site tests and short-term backtesting.

[0098] Specifically, preprocessing refers to cleaning, aligning, and smoothing the raw observations such as deviation values, deviation change rates, and deviation durations to obtain robust deviation trend inputs. This preprocessing includes, but is not limited to: missing value imputation and timestamp alignment (resampling AIS, video, and gate logs to a unified time base), outlier removal and robust smoothing (e.g., smoothing strategies such as moving average, exponentially weighted moving average, or median filtering), and calculating and normalizing the instantaneous change rate and duration of the deviation time series. Simultaneously, phase smoothing and consistency checks are performed on the inter-lock synchronization phase offset data to eliminate artifacts introduced by sensor jitter or short-term communication interruptions. The smoothed deviation trend, deviation change rate, deviation duration, and phase offset correction obtained after the above preprocessing are used as processed dynamic feature data to improve the input quality and prediction stability of subsequent cascading effect prediction models.

[0099] Preferably, this invention proposes an adaptive acquisition strategy with three time intervals based on the magnitude of the deviation: a longer acquisition interval T1 is used in the low-deviation region, a moderate acquisition interval T2 is used in the medium-deviation region, and a shorter acquisition interval T3 is used in the high-deviation region, to balance the accuracy of deviation trend capture with data acquisition / processing efficiency. This switching mechanism can be automatically triggered based on the first and second deviation thresholds obtained above optimization, and can be supplemented with switching confirmation rules (e.g., requiring a certain number of consecutive samples to meet the threshold condition before switching the sampling frequency) to avoid frequent switching due to short-term jitter.

[0100] S3: Optimize the basic complex network model using the processed dynamic feature data to construct a cascading effect prediction model.

[0101] Constructing a cascade effect prediction model includes the following steps:

[0102] By introducing an instantaneous congestion coefficient, the degree to which ship traffic exceeds the lock's capacity is quantified, resulting in a real-time overload index for the waterway. This index reflects the risk of congestion triggering at the current node. The specific formula is as follows:

[0103] ;

[0104] in, Let be the instantaneous congestion coefficient of the i-th lock at time t. This represents the number of ships that actually arrived at the i-th lock at time t. The expected throughput of the i-th ship-lock is calculated using a basic complex network model.

[0105] By introducing a phase coordination attenuation factor, compensation calculations are performed to address the synchronization deviation of operations at adjacent locks, resulting in a channel coordination attenuation coefficient. This helps to suppress the spread of congestion caused by asynchronous lock operations. The specific formula is as follows:

[0106] ;

[0107] in, Let be the cooperative attenuation coefficient between channels i and j at time t. This represents the absolute value of the measured phase shift. As a normalized benchmark for phase offset, the phase coordination factor is a factor that quantifies the impact of the difference in operation time between two adjacent locks on the coordination capability. The phase refers to the time phase of the two locks in the operation cycle (e.g., opening, entering, releasing water, closing), similar to the phase difference of a waveform. If the phase difference between the two locks is zero, it means that the operation is completely synchronized and the attenuation factor approaches 1; the larger the phase difference, the smaller the attenuation factor, indicating that the coordination effect is weaker.

[0108] Based on the instantaneous congestion coefficient and the coordinated attenuation coefficient, a cascading effect prediction model is constructed to obtain the node cascading risk index, which comprehensively reflects the combined risk level of local overload and global coordinated failure.

[0109] As a preferred embodiment of the multi-lock collaborative vessel navigation scheduling method based on complex scenarios in this invention, the specific formula for the cascade effect prediction model is as follows:

[0110] ;

[0111] in, The node cascading risk index represents the probability that the i-th lock at time t will trigger cascading congestion in the waterway network. The number of adjacent waterways. This represents the summation of the coordination coefficients of all adjacent channels j of the i-th lock.

[0112] In the embodiments of this application, the measured absolute value of phase offset Normalized reference for phase offset The parameters can be determined by minimizing the prediction error using historical congestion propagation data, thereby determining the coefficient values ​​most suitable for the current navigation scenario. Initial values ​​can also be set by combining expert experience methods. This embodiment does not make specific limitations on this.

[0113] Preferably, this invention significantly improves the accuracy of congestion prediction by using a cascading effect prediction model that combines the dynamic effects of flow overload and synchronization deviation. The instantaneous congestion coefficient introduces a ratio structure to capture the interactive effect of ship flow exceeding the expected capacity, enhancing the response capability to sudden overload. The phase-coordinated attenuation factor quantifies the combined effect of asynchronous operations of adjacent locks in an exponential form, reducing cascading diffusion and network disturbance interference. The final formula integrates overload indicators and attenuation coefficients to optimize the node cascading risk index. Compared with the traditional static topology model, it is more in line with the actual dynamic laws of waterways, improving prediction accuracy and system resilience.

[0114] S4: Based on the cascading effect prediction model, congestion propagation is predicted, the prediction results are obtained, and coordinated scheduling is performed to realize intelligent monitoring and cascading effect prevention and control of the multi-lock system.

[0115] Figure 3 This is a schematic diagram of the state judgment logic of the multi-lock collaborative vessel navigation scheduling method based on complex scenarios proposed in this invention.

[0116] Based on a cascading effect prediction model, congestion propagation is predicted, and the predicted results are used to execute coordinated scheduling, including the following steps:

[0117] Based on the node cascade risk index and congestion propagation rate, the channel status is determined, and the following judgment is performed:

[0118] If the node cascade risk index is less than or equal to the cascade risk safety threshold, and the congestion propagation rate is less than or equal to the propagation rate threshold, then the current waterway status is determined to be normal passage status, the existing lock scheduling strategy is maintained, and real-time ship location data and lock operation parameters are continuously collected.

[0119] It should be noted that maintaining the existing lock scheduling strategy means continuing to execute the preset lock intervals, vessel queuing rules, and flow balancing mechanisms under normal traffic conditions. For example, a fixed lock schedule based on historical average passage time and lock chamber capacity is used to ensure orderly vessel passage without introducing additional adjustments. At the same time, real-time vessel location data and lock operation parameters are continuously collected, including real-time acquisition of vessel latitude and longitude coordinates, heading, and speed information through AIS terminals, as well as monitoring parameters such as lock water level, gate opening, opening and closing time, and vibration response using laser scanners and video monitoring systems. The frequency of these data collections can be dynamically adjusted according to the system load, typically every 5-10 seconds, to support subsequent status monitoring and potential risk warnings.

[0120] If the node cascade risk index is less than or equal to the cascade risk safety threshold, but the congestion propagation rate is greater than the propagation rate threshold, then the current waterway status is preliminarily determined to be a congestion spread warning state, and the next step is executed.

[0121] When the current waterway status is initially determined to be a congestion spread warning status, the judgment is upgraded based on the duration of congestion and the fluctuation sequence of ship traffic.

[0122] If the congestion duration is less than or equal to the duration threshold, and the variance of the ship flow fluctuation sequence is less than or equal to the fluctuation threshold, then it is finally determined to be a locally controllable congestion state, and the first scheduling scheme is executed.

[0123] It should be noted that the first scheduling scheme operates as follows:

[0124] Multiply the node degree value by a preset adjustment factor to generate a new buffer coefficient, thereby reducing the magnitude of gate adjustment. The reduced buffer coefficient ensures more precise intervention measures.

[0125] A threshold pruning operation is performed on the node cascade risk index calculated in the cascade effect prediction model to limit the node cascade risk index to a preset range; the pruned node cascade risk index effectively prevents over-scheduling and maintains the stable operation of the lock network.

[0126] Based on the reduced buffer coefficient and the trimmed node cascade risk index, the lock sequence is updated; the updated sequence allows the multi-lock system to gradually approach the normal navigation threshold under local congestion conditions.

[0127] If the congestion duration exceeds the duration threshold, or the variance of the ship flow fluctuation sequence exceeds the fluctuation threshold, it is determined to be a global spread state, and the second scheduling scheme is executed.

[0128] It should be noted that the second scheduling scheme operates as follows:

[0129] The risk index of node cascade is weighted and amplified, and multiplied by a dynamically adjusted urgency coefficient to generate an enhanced intervention signal; the amplified intervention signal increases the intensity of dispatch response to cope with the global spread of congestion.

[0130] Based on the product of the channel coordination attenuation coefficient and the instantaneous congestion coefficient, a channel priority sequence is constructed; the sorted sequence clarifies the processing order of key congestion nodes, prioritizing the relief of locks with high load and low coordination.

[0131] Based on the enhanced intervention signal and the channel priority sequence, the lock sequence adjustment and phase synchronization optimization of multiple locks are performed. The adjusted lock sequence plan forcibly eliminates phase offset and allocates spare lock chamber capacity, so that the system can quickly recover from the global spread state to the controllable threshold range.

[0132] If the node cascading risk index is greater than the cascading risk safety threshold and the congestion propagation rate is greater than the propagation critical threshold, then it is directly determined to be a cascading out-of-control state, and the third scheduling scheme is executed.

[0133] It should be noted that the third scheduling scheme operates as follows:

[0134] The node cascade risk index is exponentially amplified and multiplied by a preset emergency response coefficient to generate the highest level intervention command; the amplified command triggers the system to enter the cascade runaway emergency mode and activates the network-wide collaborative intervention mechanism.

[0135] Based on the difference between the real-time overload index of the waterway and the coordinated attenuation coefficient, the priority of waterway blockage is dynamically calculated; the sorted priority sequence identifies the core congestion sources and key propagation paths, providing a basis for decision-making on forced diversion.

[0136] Based on the highest level intervention instructions and channel blockage priority, emergency lock freezing, reverse flow control, and backup channel activation operations were implemented for multiple locks. The forcibly adjusted scheduling scheme interrupted the congestion propagation chain and reset network phase synchronization, enabling the system to quickly recover from the cascading out-of-control state to the safe operating threshold.

[0137] It should be noted that, regarding the cascading risk safety threshold and propagation rate threshold for waterway status assessment, firstly, based on the congestion characteristics of the multi-lock system, data was collected under typical navigation scenarios, statistically analyzed, and risk levels were categorized in conjunction with navigation efficiency requirements. Ultimately, the optimal cascading risk safety threshold and propagation rate threshold were obtained through optimization. Secondly, for the threshold settings of congestion duration and vessel flow fluctuation sequences, the system stability and response timeliness were comprehensively evaluated, and the accuracy of status assessment and operating costs under different thresholds were calculated to determine the optimal threshold. Based on the historical operating data of the multi-lock system, by analyzing the node degree value correction effect, navigation efficiency change trend, and cascading risk propagation characteristics under different scheduling scenarios, and combining system stability requirements and response timeliness requirements, a multi-objective optimization algorithm was used for parameter fitting to ultimately determine the reasonable value of the adjustment factor. The scope is defined as follows: First, by statistically analyzing the distribution characteristics of the cascading risk index under typical navigation conditions and combining this with the requirements for stable ship traffic flow, a baseline value for the normal navigation threshold is determined. Second, for the dynamically adjusted emergency coefficient, based on the deviation between real-time ship traffic flow and the basic calculation results, the congestion propagation rate, and the synchronization phase offset data between locks, an emergency coefficient value that linearly increases with the degree of traffic flow deviation and phase offset is generated through a preset weight allocation rule (the weight parameters are determined based on the reverse verification of the navigation efficiency recovery effect in historical cascading events), and its value range is determined. The setting of the controllable threshold comprehensively considers the scheduling intervention effect and system recovery capability under local congestion conditions, and is optimized based on the statistical analysis results of historical intervention cases. The emergency response coefficient is determined by simulating cascading out-of-control scenarios, aiming to minimize the system recovery time, and using a reverse optimization method to determine the preset value. All parameters need to be verified through field tests and periodically calibrated based on actual operating data.

[0138] For example, suppose in an inland waterway system, after a group of locks has been operating for one hour during peak hours, the intelligent monitoring system detects a slight but continuous surge in flow at the upstream lock. Although the cascade risk index of a single measurement does not exceed the cascade risk safety threshold, the system calculates the congestion propagation rate and finds that the risk is gradually spreading. When the congestion lasts for 20 minutes and the variance of the vessel flow fluctuation sequence increases slightly, the system automatically determines that it is in a congestion propagation warning state, further escalating it to a locally controllable congestion state. It then executes the first scheduling plan to adjust the lock intervals and pushes an APP notification to ships to slow down. The dispatchers then confirm that there is a slight synchronization offset at the downstream lock, optimize the phase in time, and restore normal navigation, avoiding a cascaded loss of control state caused by further risk expansion, and ensuring navigation efficiency and system stability.

[0139] It should be noted that traditional navigation scheduling systems typically use a single risk threshold for status monitoring, which is difficult to adapt to complex changes in traffic flow overload and synchronization deviation, leading to delayed responses or misjudgments. This embodiment, by designing a multi-level status judgment mechanism based on node cascade risk indices and congestion propagation rates, establishes a refined control system encompassing normal passage, congestion spread warning, locally controllable congestion, global spread, and cascaded loss of control. It comprehensively considers current risks and historical trends, achieving dynamic assessment of waterway status. This multi-level judgment mechanism overcomes the limitations of traditional single control, employing tiered response measures through multi-dimensional analysis of congestion duration and vessel traffic flow fluctuation sequences. It significantly improves the accuracy and intelligence of navigation processes, reduces congestion spread caused by untimely risk intervention, avoids resource waste due to over-scheduling, and optimizes the operational efficiency and maintenance costs of multi-lock systems.

[0140] In summary, by integrating static attribute data and dynamic operational data of the locks, a basic complex network model was constructed, achieving for the first time a quantitative representation of the collaborative operation status of multiple locks. By introducing a node capacity correction index and a channel edge weight fractional algorithm, the model's adaptability to complex scenarios such as high failure rates and long-distance channels was significantly improved. Furthermore, by establishing a three-level flow deviation response mechanism (low / medium / high flow deviation zones), intelligent allocation of monitoring resources was achieved. High-frequency data acquisition was used in high-risk areas, while only key parameters were collected in safe areas, significantly reducing the system's computational load while ensuring the accuracy of risk warnings.

[0141] By constructing a cascading effect prediction model, the correlation between the synchronicity of lock operations and congestion spread is quantified, enabling accurate prediction of risk propagation paths. Based on a three-level state determination mechanism of node cascading risk index, differentiated scheduling strategies are dynamically triggered, thereby effectively reducing the probability of congestion propagating across locks and shortening the average fault recovery time. This invention is not only applicable to large inland waterways but can also be extended to multi-node transportation network management, such as port cluster coordination or urban transportation hub scheduling.

[0142] Example 2

[0143] This is one embodiment of the present invention, which differs from the previous embodiment in that:

[0144] If a function is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this invention, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of the various embodiments of this invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0145] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as a sequenced list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by, or in conjunction with, an instruction execution system, apparatus, or device (such as a computer-based system, a processor-including system, or other system that can fetch and execute instructions from, an instruction execution system, apparatus, or device). For the purposes of this specification, "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transmit programs for use by, or in conjunction with, an instruction execution system, apparatus, or device.

[0146] More specific examples (a non-exhaustive list) of computer-readable media include: electrical connections (electronic devices) having one or more wires, portable computer disk drives (magnetic devices), random access memory (RAM), read-only memory (ROM), erasable and editable read-only memory (EPROM or flash memory), fiber optic devices, and portable optical disc read-only memory (CDROM). Furthermore, computer-readable media can even be paper or other suitable media on which programs can be printed, because programs can be obtained electronically, for example, by optically scanning the paper or other media, followed by editing, interpreting, or otherwise processing as necessary, and then stored in computer memory.

[0147] It should be understood that various parts of the present invention can be implemented in hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented in software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, it can be implemented using any one or a combination of the following techniques known in the art: discrete logic circuits having logic gates for implementing logical functions on data signals, application-specific integrated circuits (ASICs) having suitable combinational logic gates, programmable gate arrays (PGAs), field-programmable gate arrays (FPGAs), etc.

[0148] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention, and all such modifications or substitutions should be covered within the scope of the claims of the present invention.

Claims

1. A multi-lock collaborative vessel navigation scheduling method based on adaptive complex scenarios, characterized in that, include: The static and dynamic data of the multi-lock system are acquired, and a basic complex network model is constructed. The basic complex network model is used to perform calculations to obtain the basic data calculation results. Based on the calculation results of the basic data, new real-time data is obtained and preprocessed to obtain processed dynamic feature data. The basic complex network model is optimized using the processed dynamic feature data to construct a cascading effect prediction model; based on the cascading effect prediction model, congestion propagation is predicted to obtain the prediction results, and coordinated scheduling is executed to realize intelligent monitoring and cascading effect prevention and control of the multi-lock system. Among them, obtaining the static data of the multi-lock system refers to collecting the lock chamber capacity, average lock passage time, failure history rate, waterway connection distance and capacity limit of the lock through the lock management system. Acquiring dynamic data of the multi-lock system refers to collecting real-time ship positions, immediate fault events, ship flow fluctuation sequences, and inter-lock synchronization phase offsets through AIS terminals, laser scanners, and video surveillance. The construction of the basic complex network model includes the following steps: By introducing an exponential function to process the composite effect of lock node attributes, a node capacity correction value is obtained, thereby enhancing the response capability of the basic complex network model to scenarios with high failure rates or long lock passage times. By introducing a fractional structure to quantify the composite influence of channel edge attributes, edge weight values ​​are obtained, thereby reducing the interference of connection distance and faults on edge connection strength in the basic complex network model. By introducing a summation correction term to process the differences in the connection of lock nodes, the node degree value is obtained, thereby improving the adaptability of the basic complex network model under different connection density conditions. Based on the obtained node capacity correction values, edge weight values, and node degree values, a basic complex network model is constructed to comprehensively evaluate the impact of lock capacity, channel connection strength, and network connection density on ship navigation efficiency. The specific formula for the basic complex network model is as follows: G = (V, E, W); Where G is the basic complex network model, V is the lock node set, E is the channel edge set, and W is the edge weight matrix. The new real-time data includes the deviation between real-time ship traffic and the calculation results of basic data, the congestion propagation rate, and the congestion duration; Obtaining new real-time data based on the calculation results of the aforementioned basic data includes the following steps: Based on the calculation results of the basic data, if the deviation between the real-time ship flow and the calculation results of the basic data is less than or equal to the first flow threshold, it is determined to be a low flow deviation area. The time interval for real-time data collection is set to T1, and the real-time ship position, ship flow fluctuation sequence and lock synchronization phase offset data are obtained. If the deviation between the real-time flow of the ship and the calculation result of the basic data is greater than the first flow threshold but less than the second flow threshold, it is determined to be a medium flow deviation area. The time interval for real-time data collection is set to T2, and the real-time position of the ship, the immediate fault event, and the synchronous phase offset data between the locks are obtained. If the deviation between the real-time ship flow and the calculated result of the basic data is greater than or equal to the second flow threshold, it is determined to be a high flow deviation area. The time interval for real-time data collection is set to T3, and the real-time ship position, immediate fault events, ship flow fluctuation sequence and lock synchronization phase offset data are obtained.

2. The multi-lock collaborative vessel navigation scheduling method based on complex scenario adaptation as described in claim 1, characterized in that: The construction of the cascade effect prediction model includes the following steps: By introducing an instantaneous congestion coefficient, the degree to which the ship flow exceeds the lock's carrying capacity is quantified, resulting in a real-time overload index for the waterway, which reflects the risk of congestion triggering at the current node. By introducing a phase coordination attenuation factor, the synchronization deviation of adjacent lock operations is compensated and calculated to obtain the channel coordination attenuation coefficient, thereby suppressing the spread of congestion caused by asynchronous lock operations. Based on the instantaneous congestion coefficient and the coordinated attenuation coefficient, a cascading effect prediction model is constructed to obtain the node cascading risk index, which comprehensively reflects the combined risk level of local overload and global coordinated failure.

3. The multi-lock collaborative vessel navigation scheduling method based on complex scenario adaptation as described in claim 2, characterized in that: The specific formula for the cascade effect prediction model is as follows: ; in, IEI is the node cascading risk index, representing the probability that the i-th lock at time t will cause cascading congestion in the waterway network. IEI represents the number of adjacent waterways. This represents the summation of the coordination coefficients of all adjacent channels j of the i-th lock.

4. The multi-lock collaborative vessel navigation scheduling method based on complex scenario adaptation as described in claim 3, characterized in that: Based on the cascading effect prediction model, congestion propagation is predicted, and the prediction results are obtained. Cooperative scheduling is then performed, including the following steps: Based on the node cascade risk index and congestion propagation rate, the channel status is determined, and the following judgment is performed: If the node cascading risk index is less than or equal to the cascading risk safety threshold, and the congestion propagation rate is less than or equal to the propagation rate threshold, If the current channel status is determined to be normal passage, the existing lock scheduling strategy will be maintained, and real-time ship location data and lock operation parameters will be continuously collected. If the node cascade risk index is less than or equal to the cascade risk safety threshold, but the congestion propagation rate is greater than the propagation rate threshold, then the current waterway status is preliminarily determined to be a congestion spread warning state, and the next step is executed. When the current waterway status is initially determined to be a congestion spread warning status, the judgment is upgraded based on the duration of congestion and the fluctuation sequence of ship traffic. If the congestion duration is less than or equal to the duration threshold, and the variance of the ship flow fluctuation sequence is less than or equal to the fluctuation threshold, then it is finally determined to be a locally controllable congestion state, and the first scheduling scheme is executed. If the congestion duration exceeds the duration threshold, or the variance of the ship flow fluctuation sequence exceeds the fluctuation threshold, it is determined to be a global spread state, and the second scheduling scheme is executed. If the node cascading risk index is greater than the cascading risk safety threshold and the congestion propagation rate is greater than the propagation critical threshold, then it is directly determined to be a cascading out-of-control state, and the third scheduling scheme is executed.

5. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that: When the processor executes the computer program, it implements the steps of the multi-lock cooperative ship navigation scheduling method based on complex scenarios as described in any one of claims 1-4.

6. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by the processor, it implements the steps of the multi-lock collaborative ship navigation scheduling method based on complex scenarios as described in any one of claims 1-4.

Images