Ship lock navigation scheduling optimization method and system based on AI algorithm

Abstract

The invention discloses a ship lock navigation scheduling optimization method and system based on an AI algorithm, and belongs to the technical field of ship lock navigation scheduling, and the method comprises the steps: collecting ship data, hydro meteorological data and ship lock state data, and obtaining original collection data; the method comprises the following steps: preprocessing original acquisition data to obtain processing data, and integrating the processing data according to an acquisition timestamp to obtain ship monitoring data; performing feature extraction on the ship monitoring data to obtain key features related to ship lock navigation scheduling; key features are extracted from ship monitoring data, a ship lock navigation scheduling optimization model is established, and a ship lock navigation scheduling scheme is formulated by determining a target optimization function and constraint conditions; and solving the ship lock navigation scheduling optimization model through a genetic algorithm and a particle swarm optimization algorithm to obtain an optimal ship lock navigation scheduling scheme.

Description

Technical Field

[0001] The present invention relates to the technical field of lock navigation scheduling, and in particular to a lock navigation scheduling optimization method and system based on an AI algorithm. Background Art

[0002] With the continuous development of inland waterway transportation, the importance of navigation scheduling of ship locks, as key hubs connecting waterways with different water levels, has become increasingly prominent. Traditional ship lock navigation scheduling mainly relies on manual experience or simple rule algorithms, which has many limitations.

[0003] On the one hand, it is difficult for manual dispatchers to fully and timely grasp the large amount of dynamically changing lock-related data, ship information, and surrounding environment information, resulting in inaccurate and in-time dispatch decisions; On the other hand, simple rule-based algorithms lack the ability to adapt to complex actual situations and cannot fully consider special circumstances such as hydrological and meteorological changes. This can easily cause long waiting times for passing through locks, reduce the passage efficiency of locks and the utilization rate of shipping resources, and restrict the further development of inland waterway shipping. Summary of the invention

[0004] The purpose of the present invention is to overcome the deficiencies of the prior art and provide a method and system for optimizing lock navigation scheduling based on an AI algorithm to solve the problems raised in the above-mentioned background technology.

[0005] The purpose of the present invention can be achieved by the following technical solutions: A method and system for optimizing navigation scheduling of ship locks based on AI algorithm, comprising: The data collection and preprocessing module is used to collect ship data, hydrological and meteorological data, and lock status data to obtain original collected data; the original collected data is preprocessed to obtain processed data, and the collected data is integrated according to the collected timestamp and the corresponding processed data to obtain ship monitoring data; The feature extraction module is used to extract features from ship monitoring data and obtain key features related to lock navigation scheduling; The model building module establishes a ship lock navigation scheduling optimization model based on the key features extracted from the ship monitoring data, and formulates a ship lock navigation scheduling plan by determining the target optimization function and constraint conditions; The optimization solution module solves the optimization model of lock navigation scheduling through genetic algorithm and particle swarm optimization algorithm to obtain the optimal scheduling plan for lock navigation.

[0006] As a further solution of the present invention, the method for obtaining the original collected data is as follows: Using AIS equipment and BeiDou positioning system, the ship ID, ship position, speed and heading are obtained according to the collection frequency, and the cargo type and load information are input and synchronized in real time through the ship entry registration system to determine the ship data; Obtain hydrological and meteorological data based on hydrological monitoring stations and meteorological stations, including water level, flow rate, wind speed and visibility, and update them in real time; The lock chamber water level, gate status and equipment operation parameters are collected through the lock equipment sensors; among them, when the gate status is open, it is recorded as 1, and when the gate status is closed, it is recorded as 0.

[0007] As a further solution of the present invention, preprocessing is performed on the original collected data, including: Perform data cleaning on the original collected data. For ship data, use the outlier detection algorithm to screen out data points that exceed the reasonable sailing speed range or have sudden changes in heading; For the missing values ​​of water level, the LSTM time series model is used to learn the long-term dependencies of water level data and predict and fill in the missing values ​​of water level over a long period of time.

[0008] As a further solution of the present invention, feature extraction is performed on the ship monitoring data, including: For ship data, obtain the lock location coordinates and ship location, and calculate the estimated time for each ship to arrive at the lock; The calculation formula is as follows: ; In the formula, YS is the estimated time for the ship to arrive at the lock; t1 is the current acquisition time; is the ship position of any ship at the current collection time; v is the speed of the ship at the current collection time; (X, Y) represents the position coordinates of the lock; Based on the cargo type and load information of the ship, the priority p of the ship passing through the lock is determined; among which, the ship type and the corresponding priority include: dangerous goods ship p=3, passenger ship p=2, and ordinary cargo ship p=1; For hydrological and meteorological data, the formula Calculate the rate of change of water level; where, Indicates the water level at the current collection time; Indicates the water level at the previous collection time, Indicates the collection time interval; For the lock status data, the time series of the lock chamber status is analyzed to determine the idle time of the lock chamber, which is used to arrange the time for ships to pass through the lock; The time series of the lock chamber state is a discrete value consisting of 0 and 1, and each value corresponds to a start time and an end time; When a continuous sequence of 0s is found, it means the time period when the gate is closed. The start and end time of each continuous sequence of 0s is counted to get the idle time of the gate chamber. Based on the estimated time of ship arrival at the lock, the priority p of the ship passing through the lock, the water level change rate and the idle time of the lock chamber, the key characteristics related to the lock navigation scheduling are determined.

[0009] As a further solution of the present invention, determining the target optimization function includes: Minimize the waiting time of ships: By calculating the waiting time of each ship and summing it up, the total waiting time of all ships is obtained, making the total waiting time as small as possible; where the waiting time of a ship is equal to its actual time passing through the lock minus its arrival time; The calculation formula is as follows: ; In the formula, minW represents minimizing the ship waiting time; Indicates whether ship i passes through the lock in the jth time period. If ship i passes through the lock in the jth time period, then =1, if ship i does not pass through the lock in the jth time period, then =0; represents the estimated time of arrival of ship i at the lock; i represents ship i; j represents the jth time period, and i and j are positive integers; Maximize the utilization rate of the lock: By calculating the usage of the lock in each time period and taking the average value, the utilization rate of the lock is obtained, so that the utilization rate of the lock is maximized; The utilization rate of the lock refers to the proportion of the time the lock is used to the total time, which is equivalent to maximizing ; Indicates whether the lock is used in the jth time period. If a ship passes through the lock in the jth time period, =1; if no ship passes through the lock in the jth time period, then =0; The calculation formula is as follows: ; In the formula, maxU represents the maximum lock utilization rate; i represents ship i; j represents the jth time period, and i and j are positive integers; Based on minimizing ship waiting time and maximizing lock utilization, the objective optimization function is established through weight distribution to maximize the navigation benefits of the lock. The calculation formula is as follows: ; Where f represents the target optimization function; and They represent the weight coefficients corresponding to the ship waiting time and the lock utilization rate respectively; W represents the ship waiting time, and U represents the lock utilization rate.

[0010] As a further solution of the present invention, determining the constraint conditions includes: Ship safety distance constraint: The distance between two adjacent ships should be greater than the safety distance threshold; Lock capacity constraints: The total length and width of a ship passing through the lock each time cannot exceed the length and width of the lock chamber; Hydrometeorological conditions constraints: Under severe hydrometeorological conditions, ships are restricted from passing through the locks or their speed is adjusted; Ship passing lock sequence constraint: Based on the ship type and corresponding priority, for a number of ships in the same batch that arrive at the lock one after another, the ship with a higher priority is allowed to pass through the lock first; if the ships have the same priority, they will pass through the lock in the order of their arrival time.

[0011] As a further solution of the present invention, the genetic algorithm comprises: The ship lock passing sequence and lock passing time are encoded as integers; each integer represents a ship, the sequence represents the lock passing sequence, and the lock passing time is set as an additional code; Based on the coding rules, a number of chromosomes are randomly generated, which is the first initial population; each chromosome represents a scheduling scheme; The target optimization function is set as the fitness function, and the quality of each chromosome is evaluated according to the fitness function; Performing genetic operations on the first initial population, including selection, crossover and mutation; The selection operation adopts a roulette wheel selection method, and according to the fitness function value of each chromosome, a chromosome whose fitness function value is greater than or equal to a preset standard is selected to enter the next generation population; The crossover operation adopts a partial mapping crossover method, randomly selects two chromosomes, exchanges some gene fragments between them, generates new offspring chromosomes, and increases the diversity of the population; The mutation operation randomly changes certain genes in the chromosome with a preset probability to prevent the algorithm from falling into a local optimal solution; After multiple iterations of genetic operations, when the number of iterations reaches the preset N1 times, the iteration is stopped and several better chromosomes, that is, the better scheduling plan, are obtained.

[0012] As a further solution of the present invention, the particle swarm optimization algorithm comprises: The generated optimal scheduling scheme is used as the second initial population of the particle swarm optimization algorithm; each particle represents a better scheduling scheme, the position of the particle represents the ship passing sequence and time in the better scheduling scheme, and the speed of the particle represents the rate of change of the position; The fitness value of each particle is calculated by setting the fitness function to evaluate the pros and cons of the better scheduling scheme represented by the particle; the same fitness function is used as the genetic algorithm; For each particle, if the current fitness value is ≥ the preset optimal standard value, the individual optimal position is updated; at the same time, the particle with the best fitness value among all particles is found and the global optimal position is updated; Determine whether the number of iterations N2 has been reached. If so, stop the particle swarm optimization algorithm and output the global optimal position as the optimal scheduling plan for lock navigation; otherwise, continue iterating.

[0013] In order to solve the above problems, the present invention also provides a method for optimizing navigation scheduling of ship locks based on an AI algorithm, comprising the following steps: Collect ship data, hydrological and meteorological data, and lock status data to obtain original collected data; obtain processed data by preprocessing the original collected data, and integrate them according to the collection timestamp and the corresponding processed data to obtain ship monitoring data; Extract features from ship monitoring data to obtain key features related to lock navigation scheduling; Based on the key features extracted from ship monitoring data, a ship lock navigation scheduling optimization model is established, and a ship lock navigation scheduling plan is formulated by determining the target optimization function and constraint conditions; The optimization model of lock navigation scheduling is solved by genetic algorithm and particle swarm optimization algorithm to obtain the optimal scheduling plan for lock navigation.

[0014] Compared with the existing solutions, the present invention achieves the following beneficial effects: The present invention can comprehensively and accurately obtain ship monitoring data by collecting multi-source data such as ships, hydrological and meteorological data, and lock status, and after preprocessing and integration, providing a solid foundation for subsequent scheduling. By extracting key features related to lock navigation scheduling, scheduling decisions are more targeted and scheduling efficiency is effectively improved. The present invention establishes a ship lock navigation scheduling optimization model by determining the target optimization function and constraint conditions, formulates a ship lock navigation scheduling plan, and uses genetic algorithm and particle swarm optimization algorithm to solve the model. This not only improves the navigation capacity of the ship lock, reduces the waiting time of ships, reduces operating costs, and improves the overall operating efficiency of the ship lock and the efficiency of shipping resource utilization. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] The present invention will be further described below in conjunction with the accompanying drawings.

[0016] Figure 1 This is a module structure diagram of the lock navigation scheduling optimization system based on AI algorithm proposed in the present invention.

[0017] Figure 2 This is a flowchart of the ship lock navigation scheduling optimization method based on AI algorithm proposed in the present invention. DETAILED DESCRIPTION

[0018] The technical solutions in the embodiments of the present invention will be described clearly and completely below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all the embodiments.

[0019] Embodiment 1, as Figure 1 As shown, the present invention is a ship lock navigation scheduling optimization system based on AI algorithm, including: a data collection and preprocessing module, a feature extraction module, a model building module and an optimization solution module; The data collection and preprocessing module is used to collect ship data, hydrological and meteorological data, and lock status data to obtain original collected data; the original collected data is preprocessed to obtain processed data, and the collected data is integrated according to the collected timestamp and the corresponding processed data to obtain ship monitoring data; The method to obtain the original collected data is as follows: Using AIS equipment and Beidou positioning system, the ship ID, ship position, speed and heading are obtained according to the collection frequency, and the cargo type and load information are input and synchronized in real time through the ship entry registration system to determine the ship data; the collection frequency can be set to once every 5 seconds; AIS equipment is an automatic identification system for ships, which is a new navigation aid system used for maritime safety and communication between ships and shores, and between ships; Obtain hydrological and meteorological data based on hydrological monitoring stations and meteorological stations, including water level, flow rate, wind speed and visibility, and update them in real time; The lock chamber water level, gate status and equipment operating parameters are acquired through the lock equipment sensors; the gate status is recorded as 1 when it is open, and 0 when it is closed; the equipment operating parameters include but are not limited to motor speed and oil pressure; Preprocess the raw data, including: Perform data cleaning on the original collected data. For ship data, use the outlier detection algorithm to screen out data points that exceed the reasonable sailing speed range or have a sudden change in heading. For example, when the ship speed exceeds the maximum speed of this type of ship under normal working conditions, or the heading changes drastically in a short period of time, it will be marked as abnormal data and corrected by data interpolation method based on the trend of historical data; For the missing values ​​of water level, the LSTM time series model is used to learn the long-term dependency of water level data, and the missing values ​​of long-term water level are predicted and filled; It should be noted that the LSTM time series model is a long short-term memory network time series model, which is an existing conventional algorithm model. The model structure includes an input layer, an LSTM layer, and a fully connected layer. The model is trained by the back propagation algorithm. The specific training steps are not described in detail here. The feature extraction module is used to extract features from ship monitoring data and obtain key features related to lock navigation scheduling; Feature extraction of ship monitoring data, including: For ship data, obtain the lock location coordinates and ship location, and calculate the estimated time for each ship to arrive at the lock; The calculation formula is as follows: ; In the formula, YS is the estimated time for the ship to arrive at the lock; t1 is the current acquisition time; is the ship position of any ship at the current collection time; v is the speed of the ship at the current collection time; (X, Y) represents the position coordinates of the lock; Based on the cargo type and load information of the ship, the priority p of the ship passing through the lock is determined; among which, the ship type and the corresponding priority include: dangerous goods ship p=3, passenger ship p=2, and ordinary cargo ship p=1; It should be noted that the cargo transported by dangerous goods ships is flammable, explosive, toxic and harmful. Once an accident occurs, the consequences will be disastrous. Therefore, they need to be given the highest priority to ensure that they can pass through the locks first and reduce their stay time on the waterway. Passenger ships carry passengers and have higher requirements for transportation time and safety, so they are given the second priority. Ordinary cargo ships are dispatched according to the order of arrival at the locks. For hydrological and meteorological data, the formula Calculate the rate of change of water level; where, Indicates the water level at the current collection time; Indicates the water level at the previous collection time, Indicates the collection time interval; For the lock status data, the time series of the lock chamber status is analyzed to determine the idle time of the lock chamber, which is used to arrange the time for ships to pass through the lock; The time series of the lock chamber state is a discrete value consisting of 0 and 1, and each value corresponds to a start time and an end time; When a continuous sequence of 0s is found, it means the time period when the gate is closed. The start and end time of each continuous sequence of 0s is counted to get the idle time of the gate chamber. Based on the estimated time of ship arrival at the lock, the priority p of the ship passing through the lock, the water level change rate and the idle time of the lock chamber, the key features related to the lock navigation scheduling are determined; In an embodiment of the present invention, key features related to lock navigation scheduling are extracted from ship monitoring data to provide support for building a scheduling optimization model.

[0020] The model building module establishes a ship lock navigation scheduling optimization model based on the key features extracted from the ship monitoring data, and formulates a ship lock navigation scheduling plan by determining the target optimization function and constraint conditions; Determine the target optimization function, including: Minimize the waiting time of ships: By calculating the waiting time of each ship and summing it up, the total waiting time of all ships is obtained, making the total waiting time as small as possible; where the waiting time of a ship is equal to its actual time passing through the lock minus its arrival time; The calculation formula is as follows: ; In the formula, minW represents minimizing the ship waiting time; Indicates whether ship i passes through the lock in the jth time period. If ship i passes through the lock in the jth time period, then =1, if ship i does not pass through the lock in the jth time period, then =0; represents the estimated time of arrival of ship i at the lock; i represents ship i; j represents the jth time period, and i and j are positive integers; Maximize the utilization rate of the lock: By calculating the usage of the lock in each time period and taking the average value, the utilization rate of the lock is obtained, so that the utilization rate of the lock is maximized; The utilization rate of the lock refers to the proportion of the time the lock is used to the total time, which is equivalent to maximizing ; Indicates whether the lock is used in the jth time period. If a ship passes through the lock in the jth time period, =1; if no ship passes through the lock in the jth time period, then =0; The calculation formula is as follows: ; In the formula, maxU represents the maximum lock utilization rate; i represents ship i; j represents the jth time period, and i and j are positive integers; Based on minimizing ship waiting time and maximizing lock utilization, the objective optimization function is established through weight distribution to maximize the navigation benefits of the lock. The calculation formula is as follows: ; Where f represents the target optimization function; and They represent the weight coefficients corresponding to the ship waiting time and the lock utilization rate respectively; W represents the ship waiting time, and U represents the lock utilization rate; Identify constraints, including: Ship safety distance constraint: The distance between two adjacent ships should be greater than the safety distance threshold; Lock capacity constraints: The total length and width of a ship passing through the lock each time cannot exceed the length and width of the lock chamber; Hydrometeorological conditions constraints: Under adverse hydrometeorological conditions such as low water level, strong wind, and low visibility, restrict ships from passing through the lock or adjust the speed of passing through the lock; for example, when visibility is lower than the set value, suspend passing through the lock or reduce the speed of ships passing through the lock; Ship passing lock order constraint: Based on the ship type and corresponding priority, for a batch of ships that arrive at the lock one after another, the ship with a higher priority is allowed to pass through the lock first; if the ships have the same priority, they will pass through the lock in the order of their arrival time; The optimization solution module solves the optimization model of lock navigation scheduling through genetic algorithm and particle swarm optimization algorithm to obtain the optimal scheduling plan for lock navigation.

[0021] The genetic algorithm comprises: The ship lock passing sequence and lock passing time are encoded as integers; each integer represents a ship, the sequence represents the lock passing sequence, and the lock passing time is set as an additional code; Based on the coding rules, a number of chromosomes are randomly generated, which is the first initial population; each chromosome represents a scheduling scheme; The target optimization function is set as the fitness function, and the quality of each chromosome is evaluated according to the fitness function; Performing genetic operations on the first initial population, including selection, crossover and mutation; The selection operation adopts a roulette wheel selection method, and according to the fitness function value of each chromosome, a chromosome with a fitness function value greater than or equal to a preset standard is selected to enter the next generation population; wherein the preset standard is set by experts in the field in combination with relevant knowledge; The crossover operation adopts a partial mapping crossover method, randomly selects two chromosomes, exchanges some gene fragments between them, generates new offspring chromosomes, and increases the diversity of the population; The mutation operation randomly changes certain genes in the chromosome with a preset probability to prevent the algorithm from falling into a local optimal solution; wherein the preset probability is set to 0.05; After multiple iterations of genetic operations, when the number of iterations reaches the preset N1 times, the iteration is stopped and several better chromosomes, i.e., better scheduling solutions, are obtained; The particle swarm optimization algorithm comprises: The generated optimal scheduling scheme is used as the second initial population of the particle swarm optimization algorithm; each particle represents a better scheduling scheme, the position of the particle represents the ship passing sequence and time in the better scheduling scheme, and the speed of the particle represents the rate of change of the position; The fitness value of each particle is calculated by setting the fitness function to evaluate the pros and cons of the better scheduling scheme represented by the particle; the same fitness function is used as the genetic algorithm; For each particle, if the current fitness value is ≥ the preset optimal standard value, the individual optimal position is updated; at the same time, the particle with the best fitness value among all particles is found and the global optimal position is updated; if the updated particle position exceeds the value range of the variable, it is adjusted to the boundary value; It should be noted that the preset optimal standard value is set based on the optimal fitness value obtained from the historical ship lock navigation scheduling plan data; Determine whether the number of iterations N2 has been reached. If so, stop the particle swarm optimization algorithm and output the global optimal position as the optimal scheduling plan for lock navigation; otherwise, continue iterating.

[0022] In the embodiment of the present invention, a genetic algorithm is first used to perform a global search to find a better solution, and then a particle swarm optimization algorithm is used to perform a local search near the better solution, thereby improving the accuracy and efficiency of the solution.

[0023] Embodiment 2, as Figure 2 As shown, the present invention is a method for optimizing navigation scheduling of ship locks based on AI algorithm, comprising: Collect ship data, hydrological and meteorological data, and lock status data to obtain original collected data; obtain processed data by preprocessing the original collected data, and integrate them according to the collection timestamp and the corresponding processed data to obtain ship monitoring data; Extract features from ship monitoring data to obtain key features related to lock navigation scheduling; Based on the key features extracted from ship monitoring data, a ship lock navigation scheduling optimization model is established, and a ship lock navigation scheduling plan is formulated by determining the target optimization function and constraint conditions; The optimization model of lock navigation scheduling is solved by genetic algorithm and particle swarm optimization algorithm to obtain the optimal scheduling plan for lock navigation.

[0024] In the several embodiments provided by the present invention, it should be understood that the disclosed system can be implemented in other ways. For example, the above-described embodiments of the invention are only illustrative, for example, the division of modules is only a logical function division, and there may be other division methods in actual implementation.

[0025] The modules described as separate accessories may or may not be physically separated, and the accessories shown as modules may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0026] In addition, each functional module in each embodiment of the present invention may be integrated into one processing unit, each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of hardware plus software functional modules.

[0027] It is obvious to those skilled in the art that the present invention is not limited to the details of the above exemplary embodiments, and that the present invention can be implemented in other specific forms without departing from the spirit or essential characteristics of the present invention.

[0028] Finally, it should be noted that the above embodiments are only used to illustrate the technical solution of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solution of the present invention can be modified or replaced by equivalents without departing from the spirit and scope of the technical solution of the present invention.

Claims

1. The ship lock navigation scheduling optimization system based on AI algorithm is characterized by: include: Data collection and preprocessing module, used to collect ship data, hydrological and meteorological data and lock status data to obtain original collected data; By preprocessing the original collected data, the processed data is obtained, and the collected data and the corresponding processed data are integrated to obtain the ship monitoring data; The feature extraction module is used to extract features from ship monitoring data and obtain key features related to lock navigation scheduling; The model building module establishes a ship lock navigation scheduling optimization model based on the key features extracted from the ship monitoring data, and formulates a ship lock navigation scheduling plan by determining the target optimization function and constraint conditions; The optimization solution module solves the optimization model of lock navigation scheduling through genetic algorithm and particle swarm optimization algorithm to obtain the optimal scheduling plan for lock navigation.

2. The ship lock navigation scheduling optimization system based on AI algorithm according to claim 1 is characterized in that: The method to obtain the original collected data is as follows: Using AIS equipment and BeiDou positioning system, the ship ID, ship position, speed and heading are obtained according to the collection frequency, and the cargo type and load information are input and synchronized in real time through the ship entry registration system to determine the ship data; Obtain hydrological and meteorological data based on hydrological monitoring stations and meteorological stations, including water level, flow rate, wind speed and visibility, and update them in real time; The lock chamber water level, gate status and equipment operation parameters are collected through the lock equipment sensors; among them, when the gate status is open, it is recorded as 1, and when the gate status is closed, it is recorded as 0.

3. The ship lock navigation scheduling optimization system based on AI algorithm according to claim 2 is characterized in that: Preprocess the raw data, including: Perform data cleaning on the original collected data. For ship data, use the outlier detection algorithm to screen out data points that exceed the reasonable sailing speed range or have sudden changes in heading; For the missing values ​​of water level, the LSTM time series model is used to learn the long-term dependencies of water level data and predict and fill in the missing values ​​of water level over a long period of time.

4. The ship lock navigation scheduling optimization system based on AI algorithm according to claim 3 is characterized in that: Feature extraction of ship monitoring data, including: For ship data, obtain the lock location coordinates and ship location, and calculate the estimated time for each ship to arrive at the lock; The calculation formula is as follows: ; In the formula, YS is the estimated time for the ship to arrive at the lock; t1 is the current acquisition time; is the ship position of any ship at the current collection time; v is the speed of the ship at the current collection time; (X, Y) represents the position coordinates of the lock; Based on the cargo type and load information of the ship, the priority p of the ship passing through the lock is determined; among which, the ship type and the corresponding priority include: dangerous goods ship p=3, passenger ship p=2, and ordinary cargo ship p=1; For hydrological and meteorological data, the formula Calculate the rate of change of water level; where, Indicates the water level at the current collection time; Indicates the water level at the previous collection time, Indicates the collection time interval; For the lock status data, the time series of the lock chamber status is analyzed to determine the idle time of the lock chamber, which is used to arrange the time for ships to pass through the lock; The time series of the lock chamber state is a discrete value consisting of 0 and 1, and each value corresponds to a start time and an end time; When a continuous sequence of 0s is found, it means the time period when the gate is closed. The start and end time of each continuous sequence of 0s is counted to get the idle time of the gate chamber. Based on the estimated time of ship arrival at the lock, the priority p of the ship passing through the lock, the water level change rate and the idle time of the lock chamber, the key characteristics related to the lock navigation scheduling are determined.

5. The ship lock navigation scheduling optimization system based on AI algorithm according to claim 4 is characterized in that: Determine the target optimization function, including: Minimize the waiting time of ships: By calculating the waiting time of each ship and summing them up, the total waiting time of all ships is obtained, making the total waiting time as small as possible; where the waiting time of a ship is equal to its actual time passing through the lock minus its arrival time; The calculation formula is as follows: ; In the formula, minW represents minimizing the ship waiting time; Indicates whether ship i passes through the lock in the jth time period. If ship i passes through the lock in the jth time period, then =1, if ship i does not pass through the lock in the jth time period, then =0; represents the estimated time of arrival of ship i at the lock; i represents ship i; j represents the jth time period, and i and j are positive integers; Maximize the utilization rate of the lock: By calculating the usage of the lock in each time period and taking the average value, the utilization rate of the lock is obtained, so that the utilization rate of the lock is maximized; The utilization rate of the lock refers to the proportion of the time the lock is used to the total time, which is equivalent to maximizing ; Indicates whether the lock is used in the jth time period. If a ship passes through the lock in the jth time period, =1; if no ship passes through the lock in the jth time period, then =0; The calculation formula is as follows: ; In the formula, maxU represents the maximum lock utilization rate; i represents ship i; j represents the jth time period, and i and j are positive integers; Based on minimizing ship waiting time and maximizing lock utilization, the objective optimization function is established through weight distribution to maximize the navigation benefits of the lock. The calculation formula is as follows: ; Where f represents the target optimization function; and They represent the weight coefficients corresponding to the ship waiting time and the lock utilization rate respectively; W represents the ship waiting time, and U represents the lock utilization rate.

6. The ship lock navigation scheduling optimization system based on AI algorithm according to claim 1 is characterized in that: Identify constraints, including: Ship safety distance constraint: The distance between two adjacent ships should be greater than the safety distance threshold; Lock capacity constraints: The total length and width of a ship passing through the lock each time cannot exceed the length and width of the lock chamber; Hydrometeorological conditions constraints: Under severe hydrometeorological conditions, ships are restricted from passing through the locks or their speed is adjusted; Ship passing lock sequence constraint: Based on the ship type and corresponding priority, for a number of ships in the same batch that arrive at the lock one after another, the ship with a higher priority is allowed to pass through the lock first; if the ships have the same priority, they will pass through the lock in the order of their arrival time.

7. The ship lock navigation scheduling optimization system based on AI algorithm according to claim 1 is characterized in that: The genetic algorithm comprises: The ship lock passing sequence and lock passing time are encoded as integers; each integer represents a ship, the sequence represents the lock passing sequence, and the lock passing time is set as an additional code; Based on the coding rules, a number of chromosomes are randomly generated, which is the first initial population; each chromosome represents a scheduling scheme; The target optimization function is set as the fitness function, and the quality of each chromosome is evaluated according to the fitness function; Performing genetic operations on the first initial population, including selection, crossover and mutation; The selection operation adopts a roulette wheel selection method, and according to the fitness function value of each chromosome, a chromosome whose fitness function value is greater than or equal to a preset standard is selected to enter the next generation population; The crossover operation adopts a partial mapping crossover method, randomly selects two chromosomes, exchanges some gene fragments between them, generates new offspring chromosomes, and increases the diversity of the population; The mutation operation randomly changes certain genes in the chromosome with a preset probability to prevent the algorithm from falling into a local optimal solution; After multiple iterations of genetic operations, when the number of iterations reaches the preset N1 times, the iteration is stopped and several better chromosomes, that is, the better scheduling plan, are obtained.

8. The ship lock navigation scheduling optimization system based on AI algorithm according to claim 7 is characterized in that: The particle swarm optimization algorithm comprises: The generated optimal scheduling scheme is used as the second initial population of the particle swarm optimization algorithm; each particle represents a better scheduling scheme, the position of the particle represents the ship passing sequence and time in the better scheduling scheme, and the speed of the particle represents the rate of change of the position; The fitness value of each particle is calculated by setting the fitness function to evaluate the pros and cons of the better scheduling scheme represented by the particle; the same fitness function is used as the genetic algorithm; For each particle, if the current fitness value is ≥ the preset optimal standard value, the individual optimal position is updated; at the same time, the particle with the best fitness value among all particles is found and the global optimal position is updated; Determine whether the number of iterations N2 has been reached. If so, stop the particle swarm optimization algorithm and output the global optimal position as the optimal scheduling plan for lock navigation; otherwise, continue iterating.

9. A method for optimizing navigation scheduling of a ship lock based on an AI algorithm, using the ship lock navigation scheduling optimization system based on an AI algorithm as described in any one of claims 1 to 8, characterized in that: include: Collect ship data, hydrological and meteorological data, and lock status data to obtain original collected data; By preprocessing the original collected data, the processed data is obtained, and the collected data and the corresponding processed data are integrated to obtain the ship monitoring data; Extract features from ship monitoring data to obtain key features related to lock navigation scheduling; Based on the key features extracted from ship monitoring data, a ship lock navigation scheduling optimization model is established, and a ship lock navigation scheduling plan is formulated by determining the target optimization function and constraint conditions; The optimization model of lock navigation scheduling is solved by genetic algorithm and particle swarm optimization algorithm to obtain the optimal scheduling plan for lock navigation.

Images