Ship port entering and leaving scheduling optimization method considering uncertainty of on-port navigation time

Abstract

The invention provides a ship port entering and leaving scheduling optimization method considering uncertainty of port navigation time. The method comprises the following steps: S1, considering uncertainty of in-port navigation time, and establishing a ship in-port and out-port scheduling opportunity constraint planning model; s2, converting the uncertainty ship entering and leaving scheduling opportunity constraint programming model into a deterministic scheduling optimization model by utilizing a probability distribution inverse transformation technology; and S3, designing an adaptive differential evolution algorithm, solving the deterministic ship port entering and leaving scheduling optimization model, and outputting an optimal feasible method. According to the opportunity constraint planning method, the ship in-port and out-port scheduling problem is researched mainly based on the ship in-port navigation time uncertainty, the ship scheduling problem under the port navigation time uncertainty is solved, and research in the field is enriched. According to the method, the high efficiency of the proposed model in dealing with the random ship traffic scheduling problem is shown, and the advantages of the model in improving the port service quality are highlighted.

Description

Technical Field

[0001] The present invention relates to the technical field of ship scheduling, and in particular to a method for optimizing ship entry and exit scheduling taking into account uncertain sailing time in port. Background Art

[0002] With the development of globalization and green transportation, shipping has taken on nearly 90% of world trade, which has brought tremendous pressure to ports and waterways. The dispatch of ships entering and leaving the port is an important stage of port operations, which can optimize resource utilization and improve waterway efficiency.

[0003] However, traditional scheduling assumes that all parameters are certain, but in reality, factors such as weather and equipment damage bring uncertainty, which may make the scheduling plan unreasonable or infeasible. At present, the optimization of ship inbound and outbound scheduling is mostly limited to deterministic environments, and there are few studies under uncertain conditions, mainly focusing on workshop scheduling, path planning, flight scheduling and other fields. Summary of the invention

[0004] According to the above-mentioned ship scheduling problem under the uncertainty of port sailing time, a ship entry and exit scheduling optimization method considering the uncertainty of port sailing time is provided. The present invention mainly studies the ship entry and exit scheduling problem based on the uncertainty of ship sailing time in port, proposes a chance constrained programming method to solve the ship scheduling problem under the uncertainty of port sailing time, and enriches the research in this field.

[0005] The technical means adopted by the present invention are as follows:

[0006] A method for optimizing the scheduling of ships entering and leaving a port considering the uncertainty of the sailing time in the port, comprising:

[0007] S1. Considering the uncertainty of sailing time in port, an opportunity-constrained programming model for ship entry and exit scheduling is established;

[0008] S2. Using the probability distribution inverse transformation technology, the uncertain ship entry and exit scheduling opportunity constraint programming model is transformed into a deterministic scheduling optimization model;

[0009] S3. Design an adaptive differential evolution algorithm to solve the deterministic ship entry and exit scheduling optimization model and output the optimal feasible method.

[0010] Furthermore, step S1 specifically includes:

[0011] S11. The design ensures the continuity of ships entering the port, and at the same time determines the time for ships to sail to the channel entrance, the channel exit and the berth constraints in sequence, as follows:

[0012]

[0013] In the above formula, T 1i T represents the time when ship i arrives at the channel entrance; 2i T represents the time when ship i arrives at the channel exit; fi represents the time when ship i completes the dispatch; dis1 i represents the distance from the anchorage to the channel entrance of ship i; dis2 represents the distance from the channel entrance to the channel exit, that is, the distance of the channel; dis3 i V represents the distance from the channel exit to the berth of ship i; i represents the average speed of ship i; N in Indicates the gathering of incoming ships;

[0014] S12. Design to ensure the navigation continuity of ships leaving the port, and determine the constraints of the time for ships to sail to the channel exit and channel entrance in sequence, as follows:

[0015]

[0016] In the above formula, T 1j T represents the time when ship j arrives at the channel entrance; fj represents the time when ship j completes the dispatch; dis3 j V represents the distance from the channel exit to the berth of ship j; j represents the average speed of ship j; N out Indicates the gathering of outbound ships;

[0017] S13. Design to ensure that the ship’s sailing time in the port is greater than or equal to A i and less than or equal to B i The probability of reaching at least a certain confidence level β is as follows:

[0018]

[0019] In the above formula, A i represents the shortest sailing time of ship i in port; B i represents the longest time that ship i spends in port; β represents the confidence level; Tsail i represents the sailing time of ship i in port;

[0020] S14. Design the constraints to ensure that ships entering and leaving the port adjust their application scheduling time according to the tidal window, and at the same time ensure that the time for ships entering the port to sail to the channel exit is less than the end time of the tidal window, as follows:

[0021]

[0022] In the above formula, T ei T represents the end time when ship i needs to enter and leave the port according to the tide; ai′ represents the application scheduling time of ship i adjustment; T bi represents the starting time when ship i needs to enter and leave the port with the tide; M represents a large positive integer; Io i represents a binary variable, which is 1 when ship i enters the port and 0 when it leaves the port; T i represents a binary variable, which is 1 if ship i needs to enter the port during the tide, otherwise it is 0;

[0023] S15. Design constraints to ensure that the start scheduling time is greater than or equal to the scheduling application time or the rescheduling application time, as follows:

[0024]

[0025] S16. The design ensures that ships travelling in the same direction should maintain certain constraints of safe spacing in the same direction, as follows:

[0026]

[0027] In the above formula, c1 represents the safe distance between ships in the same direction at the entrance or exit of the channel; c2 represents the safe distance between ships in different directions at the entrance or exit of the channel; Y ij represents a binary variable. For an incoming ship, if ship j is scheduled after ship i, it is 1, otherwise it is 0; H ij represents a binary variable. For outbound ships, if ship j is scheduled after ship i, it is 1, otherwise it is 0;

[0028] S17. The design ensures that ships travelling in the same direction should maintain certain constraints of safe spacing in the same direction, as follows:

[0029] In the above formula, dis1 j Io represents the distance from the anchorage to the channel entrance of ship j; j represents a binary variable, which is 1 if ship j enters the port and 0 if it leaves the port;

[0030] S18. Design the constraints for the binary decision variables as follows:

[0031]

[0032] Further, step S2 specifically includes:

[0033] S21. According to the given confidence level β, the chance constraint designed in step S14 is converted into a deterministic constraint:

[0034] S22. After the transformation in step S21, the final deterministic ship entry and exit scheduling optimization model is obtained, and its objective function is as follows:

[0035]

[0036] In the above formula, Min W represents the minimum total waiting time of ships; N represents the set of ships; T si represents the start time of dispatching ship i; T ai represents the time when ship i applies for scheduling, that is, the estimated arrival and departure time of the ship; the objective function satisfies the constraints designed in steps S12, step S13, step S15, step S16, step S17 and step S18.

[0037] Furthermore, step S21 specifically includes:

[0038] S211. Assume that the sailing time of each ship in the port is independent of each other and follows a normal distribution. where μ i is the mean of ship i, σ i is the standard deviation of ship i;

[0039] S212, estimated shortest Tsail i and the longest Tsail i , respectively using A i and B i Indicates that A i and B i The value of is estimated based on the relationship between the normal distribution function and the probability density function, that is, A i μ i -σ i ·F -1 (β) and B i =μ i σ i ·F -1 (β), where F -1 It is the inverse of the cumulative distribution function of the standard normal distribution;

[0040] S213, converting the chance constraint designed in step S13 into an equivalent deterministic form, as follows:

[0041] μ i -F -1 (β)·σ i ≤Tsail i ≤μ i +F -1 (β)·σ i .

[0042] Furthermore, step S3 specifically includes:

[0043] S31, using K-means clustering to generate the initial population encoded by the number of ships and the direction of entry and exit;

[0044] S32, using an adaptive crossover mutation operator to generate a group of mutant individuals, wherein the adaptive cooling factor parameter F is defined as follows:

[0045]

[0046] In the above formula, δ is the initial growth rate, which ranges from [0, +], the number of iterations is represented by g, and F min Indicates the minimum value of F, F max Indicates the maximum value of F;

[0047] S33, using an adaptive crossover operator to generate a group of crossover individuals, where the self-mutation probability parameter is set as follows:

[0048]

[0049] In the above formula, CR min Indicates the minimum value of F, CR max Indicates the maximum value of F;

[0050] S34, evaluating the fitness of the crossover individuals according to the fitness function, and selecting individuals with higher fitness as offspring;

[0051] S35, using a repair operator to repair the illegal chromosome generated in step S34;

[0052] S36, repeat the above steps S31 to S35 until the set maximum number of iterations is met, and then output the optimal feasible method.

[0053] Compared with the prior art, the present invention has the following advantages:

[0054] 1. The present invention provides a method for optimizing the scheduling of ships entering and leaving the port considering the uncertainty of the sailing time in the port. First, a chance-constrained programming model for scheduling ships entering and leaving the port considering the uncertainty of the sailing time in the port is established; secondly, the model is converted into a deterministic scheduling optimization model using the inverse transformation technology of probability distribution; finally, an adaptive differential evolution algorithm is designed for solving the problem. The present invention demonstrates the high efficiency of the proposed model in dealing with random ship traffic scheduling problems and highlights its advantages in improving the quality of port services.

[0055] 2. The present invention provides an optimization method for scheduling ships entering and leaving a port taking into account the uncertainty of the sailing time in the port. It studies a novel ship scheduling problem taking into account the uncertainty of the sailing time in the port, and fills the theoretical gap in the current research on uncertain ship scheduling.

[0056] Based on the above reasons, the present invention can be widely promoted in the fields of ship dispatching and the like. BRIEF DESCRIPTION OF THE DRAWINGS

[0057] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.

[0058] Figure 1 The figure is a flow chart of the method of the present invention.

[0059] Figure 2 Convergence curves of ADEA, GA, MA and TS algorithms when the number of ships provided in the embodiment of the present invention is V=26 and 30. DETAILED DESCRIPTION

[0060] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described 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, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0061] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0062] like Figure 1 As shown, the present invention provides a method for optimizing the scheduling of ships entering and leaving a port considering the uncertainty of the sailing time in the port, comprising:

[0063] S1. Considering the uncertainty of sailing time in port, an opportunity-constrained programming model for ship entry and exit scheduling is established;

[0064] S2. Using the probability distribution inverse transformation technology, the uncertain ship entry and exit scheduling opportunity constraint programming model is transformed into a deterministic scheduling optimization model;

[0065] S3. Design an adaptive differential evolution algorithm to solve the deterministic ship entry and exit scheduling optimization model and output the optimal feasible method.

[0066] In specific implementation, as a preferred embodiment of the present invention, step S1 specifically includes:

[0067] S11. The design ensures the continuity of ships entering the port, and at the same time determines the time for ships to sail to the channel entrance, the channel exit and the berth constraints in sequence, as follows:

[0068]

[0069] In the above formula, T 1i T represents the time when ship i arrives at the channel entrance; 2i T represents the time when ship i arrives at the channel exit; fi represents the time when ship i completes the dispatch; dis1 i represents the distance from the anchorage to the channel entrance of ship i; dis2 represents the distance from the channel entrance to the channel exit, that is, the distance of the channel; dis3 i V represents the distance from the channel exit to the berth of ship i; i represents the average speed of ship i; N in Indicates the gathering of incoming ships;

[0070] S12. Design to ensure the navigation continuity of ships leaving the port, and determine the constraints of the time for ships to sail to the channel exit and channel entrance in sequence, as follows:

[0071]

[0072] In the above formula, T 1j T represents the time when ship j arrives at the channel entrance; fj represents the time when ship j completes the dispatch; dis3 j V represents the distance from the channel exit to the berth of ship j; j represents the average speed of ship j; N out Indicates the gathering of outbound ships;

[0073] S13. Design to ensure that the ship’s sailing time in the port is greater than or equal to A i and less than or equal to B i The probability of reaching at least a certain confidence level β is as follows:

[0074]

[0075] In the above formula, A i represents the shortest sailing time of ship i in port; B irepresents the longest time that ship i spends in port; β represents the confidence level; Tsail i represents the sailing time of ship i in port;

[0076] S14. Design the constraints to ensure that ships entering and leaving the port adjust their application scheduling time according to the tidal window, and at the same time ensure that the time for ships entering the port to sail to the channel exit is less than the end time of the tidal window, as follows:

[0077]

[0078] In the above formula, T ei T represents the end time when ship i needs to enter and leave the port according to the tide; ai T represents the application scheduling time of ship i adjustment; bi represents the starting time when ship i needs to enter and leave the port with the tide; M represents a large positive integer; Io i represents a binary variable, which is 1 when ship i enters the port and 0 when it leaves the port; T i represents a binary variable, which is 1 if ship i needs to enter the port during the tide, otherwise it is 0;

[0079] S15. Design constraints to ensure that the start scheduling time is greater than or equal to the scheduling application time or the rescheduling application time, as follows:

[0080]

[0081] S16. The design ensures that ships travelling in the same direction should maintain certain constraints of safe spacing in the same direction, as follows:

[0082]

[0083] In the above formula, c1 represents the safe distance between ships in the same direction at the entrance or exit of the channel; c2 represents the safe distance between ships in different directions at the entrance or exit of the channel; Y ij represents a binary variable. For an incoming ship, if ship j is scheduled after ship i, it is 1, otherwise it is 0; H ij represents a binary variable. For outbound ships, if ship j is scheduled after ship i, it is 1, otherwise it is 0;

[0084] S17. The design ensures that ships travelling in the same direction should maintain certain constraints of safe spacing in the same direction, as follows:

[0085]

[0086] In the above formula, dis1 j Io represents the distance from the anchorage to the channel entrance of ship j; j represents a binary variable, which is 1 if ship j enters the port and 0 if it leaves the port;

[0087] S18. Design the constraints for the binary decision variables as follows:

[0088]

[0089] In specific implementation, as a preferred embodiment of the present invention, step S2 specifically includes:

[0090] S21. According to the given confidence level β, the chance constraint designed in step S14 is converted into a deterministic constraint:

[0091] S22. After the transformation in step S21, the final deterministic ship entry and exit scheduling optimization model is obtained, and its objective function is as follows:

[0092]

[0093] In the above formula, Min W represents the minimum total waiting time of ships; N represents the set of ships; T si represents the start time of dispatching ship i; T ai represents the time when ship i applies for scheduling, that is, the estimated arrival and departure time of the ship; the objective function satisfies the constraints designed in steps S12, step S13, step S15, step S16, step S17 and step S18.

[0094] In specific implementation, as a preferred embodiment of the present invention, step S21 specifically includes:

[0095] S211. Assume that the sailing time of each ship in the port is independent of each other and follows a normal distribution. where μ i is the mean of ship i, σ i is the standard deviation of ship i;

[0096] S212, estimated shortest Tsail i and the longest Tsail i , respectively using A i and B i Indicates that A i and B i The value of is estimated based on the relationship between the normal distribution function and the probability density function, that is, A i =μ i -σ i ·F -1 (β) and B i =μ i +σ i ·F -1 (β), where F -1 It is the inverse of the cumulative distribution function of the standard normal distribution;

[0097] S213, converting the chance constraint designed in step S13 into an equivalent deterministic form, as follows:

[0098] μ i -F -1 (β)·σ i ≤Tsail i ≤μ i +F -1 (β)·σ i .

[0099] In specific implementation, as a preferred embodiment of the present invention, step S3 specifically includes:

[0100] S31, using K-means clustering to generate the initial population encoded by the number of ships and the direction of entry and exit;

[0101] S32, using an adaptive crossover mutation operator to generate a group of mutant individuals, wherein the adaptive cooling factor parameter F is defined as follows:

[0102]

[0103] In the above formula, δ is the initial growth rate, which ranges from [0, +], the number of iterations is represented by g, and F min Indicates the minimum value of F, which is 0.5. max Indicates the maximum value of F, which is 1;

[0104] S33, using an adaptive crossover operator to generate a group of crossover individuals, where the self-mutation probability parameter is set as follows:

[0105]

[0106] In the above formula, CR min Indicates the minimum value of F, which is 0.5, CR max Indicates the maximum value of F, which is 1;

[0107] S34, evaluating the fitness of the crossover individuals according to the fitness function, and selecting individuals with higher fitness as offspring;

[0108] S35, using a repair operator to repair the illegal chromosome generated in step S34;

[0109] S36, repeat the above steps S31 to S35 until the set maximum number of iterations is met, and then output the optimal feasible method.

[0110] Example

[0111] This example is based on a certain port area to illustrate the ship scheduling opportunity constrained programming model and adaptive differential evolution algorithm proposed in the present invention.

[0112] In order to test the effectiveness of the proposed algorithm in solving the opportunity-constrained programming model for ship entry and exit scheduling, this embodiment designs a comparative experiment with different groups of ship numbers, and compares the genetic algorithm (GA), meme algorithm (MA) and taboo search algorithm (TS) with the adaptive differential evolution algorithm (ADEA) proposed in the present invention on the total waiting time of ships. All examples are generated based on the actual entry and exit ship data of a certain port area, and each example is solved ten times and the average value is taken. Table 1 records the solution results of ADEA, GA, MA, and TS for solving the opportunity-constrained programming model for ship entry and exit scheduling. As can be seen from Table 1, the best value (Best), average value (Avg) and worst value (Worst) of ADEA are better than the results generated by GA, MA and TS in all examples, which shows that ADEA has good performance.

[0113] Table 1 Comparison of the results of the proposed ADEA algorithm with those of GA, MA, and TS (unit: minutes)

[0114]

[0115] In order to evaluate the effectiveness of the proposed opportunity-constrained programming model for ship entry and exit scheduling in improving port service quality, the optimal, maximum, worst and variance values ​​of the objective function under the random and deterministic conditions of ship sailing time in the port are compared, as shown in Table 2. The confidence level is set to 0.6.

[0116] Table 2 Comparison results between deterministic and random port sailing times

[0117]

[0118] Table 2 shows that the average variance of the total waiting time of the ship in 10 runs is 5068.89 for random port sailing time, while it is 7531.39 for deterministic port sailing time. This shows that the fluctuation of the total waiting time is smaller when the port sailing time is random. Smaller fluctuations indicate that the proposed ship entry and exit scheduling opportunity constraint programming model can maintain the total waiting time more stably when faced with the uncertainty of port sailing time. This stability is crucial for port managers because it reduces the uncertainty introduced by fluctuations during operations and facilitates the planning and optimization of port resources. Therefore, smaller fluctuations mean that the proposed ship entry and exit scheduling opportunity constraint programming model has advantages in controlling port navigation efficiency.

[0119] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or replace some or all of the technical features therein with equivalents. However, these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for optimizing ship entry and exit scheduling considering the uncertainty of sailing time in port, characterized in that: include: S1. Considering the uncertainty of sailing time in port, an opportunity-constrained programming model for ship entry and exit scheduling is established; S2. Using the probability distribution inverse transformation technology, the uncertain ship entry and exit scheduling opportunity constraint programming model is transformed into a deterministic scheduling optimization model; S3. Design an adaptive differential evolution algorithm to solve the deterministic ship entry and exit scheduling optimization model and output the optimal feasible method.

2. The method for optimizing ship entry and exit scheduling considering the uncertainty of the sailing time in the port according to claim 1 is characterized in that: Step S1 specifically includes: S11. The design ensures the continuity of ships entering the port, and at the same time determines the time for ships to sail to the channel entrance, the channel exit and the berth constraints in sequence, as follows: In the above formula, T 1i T represents the time when ship i arrives at the channel entrance; 2i T represents the time when ship i arrives at the channel exit; fi represents the time when ship i completes the dispatch; dis1 i represents the distance from the anchorage to the channel entrance of ship i; dis2 represents the distance from the channel entrance to the channel exit, that is, the distance of the channel; dis3 i V represents the distance from the channel exit to the berth of ship i; i represents the average speed of ship i; N in Indicates the gathering of incoming ships; S12. Design to ensure the navigation continuity of ships leaving the port, and determine the constraints of the time for ships to sail to the channel exit and channel entrance in sequence, as follows: In the above formula, T 1j T represents the time when ship j arrives at the channel entrance; fj represents the time when ship j completes the dispatch; dis3 j V represents the distance from the channel exit to the berth of ship j; j represents the average speed of ship j; N out Indicates the gathering of outbound ships; S13. Design to ensure that the ship’s sailing time in the port is greater than or equal to A i and less than or equal to B i The probability of reaching at least a certain confidence level β is as follows: In the above formula, A i represents the shortest sailing time of ship i in port; B i represents the longest time that ship i spends in port; β represents the confidence level; Tsail i represents the sailing time of ship i in port; S14. Design the constraints to ensure that ships entering and leaving the port adjust their application scheduling time according to the tidal window, and at the same time ensure that the time for ships entering the port to sail to the channel exit is less than the end time of the tidal window, as follows: In the above formula, T ei T represents the end time when ship i needs to enter and leave the port according to the tide; ai ′ represents the application scheduling time of ship i adjustment; T bi represents the starting time when ship i needs to enter and leave the port with the tide; M represents a large positive integer; Io i represents a binary variable, which is 1 when ship i enters the port and 0 when it leaves the port; T i represents a binary variable, which is 1 if ship i needs to enter the port during the tide, otherwise it is 0; S15. Design constraints to ensure that the start scheduling time is greater than or equal to the scheduling application time or the rescheduling application time, as follows: S16. The design ensures that ships travelling in the same direction should maintain certain constraints of safe spacing in the same direction, as follows: In the above formula, c1 represents the safe distance between ships in the same direction at the entrance or exit of the channel; c2 represents the safe distance between ships in different directions at the entrance or exit of the channel; Y ij represents a binary variable. For an incoming ship, if ship j is scheduled after ship i, it is 1, otherwise it is 0; H ij represents a binary variable. For outbound ships, if ship j is scheduled after ship i, it is 1, otherwise it is 0; S17. The design ensures that ships travelling in the same direction should maintain certain constraints of safe spacing in the same direction, as follows: In the above formula, dis1 j Io represents the distance from the anchorage to the channel entrance of ship j; j represents a binary variable, which is 1 if ship j enters the port and 0 if it leaves the port; S18. Design the constraints for the binary decision variables as follows:

3. The method for optimizing ship entry and exit scheduling considering the uncertainty of the sailing time in the port according to claim 1 is characterized in that: Step S2 specifically includes: S21. According to the given confidence level β, the chance constraint designed in step S14 is converted into a deterministic constraint: S22. After the transformation in step S21, the final deterministic ship entry and exit scheduling optimization model is obtained, and its objective function is as follows: In the above formula, Min W represents the minimum total waiting time of ships; N represents the set of ships; T si represents the start time of dispatching ship i; T ai represents the time when ship i applies for scheduling, that is, the estimated arrival and departure time of the ship; the objective function satisfies the constraints designed in steps S12, step S13, step S15, step S16, step S17 and step S18.

4. The method for optimizing ship entry and exit scheduling considering the uncertainty of the sailing time in the port according to claim 1 is characterized in that: Step S21 specifically includes: S211. Assume that the sailing time of each ship in the port is independent of each other and follows a normal distribution. where μ i is the mean of ship i, σ i is the standard deviation of ship i; S212, estimated shortest Tsail i and the longest Tsail i , respectively using A i and B i Indicates that A i and B i The value of is estimated based on the relationship between the normal distribution function and the probability density function, that is, A i =μ i -σ i ·F -1 (β) and B i =μ i +σ i ·F -1 (β), where F -1 It is the inverse of the cumulative distribution function of the standard normal distribution; S213, converting the chance constraint designed in step S13 into an equivalent deterministic form, as follows: m i -F -1 (b)·s i ≤Tsail i ≤μ i +F -1 (b)·s i 。 5. The method for optimizing ship entry and exit scheduling considering the uncertainty of the sailing time in the port according to claim 1 is characterized in that: Step S3 specifically includes: S31, using K-means clustering to generate the initial population encoded by the number of ships and the direction of entry and exit; S32, using an adaptive crossover mutation operator to generate a group of mutant individuals, wherein the adaptive cooling factor parameter F is defined as follows: In the above formula, δ is the initial growth rate, which ranges from [0, +∞], the number of iterations is represented by g, and F min Indicates the minimum value of F, F max Indicates the maximum value of F; S33, using an adaptive crossover operator to generate a group of crossover individuals, where the self-mutation probability parameter is set as follows: In the above formula, CR min Indicates the minimum value of F, CR max Indicates the maximum value of F; S34, evaluating the fitness of the crossover individuals according to the fitness function, and selecting individuals with higher fitness as offspring; S35, using a repair operator to repair the illegal chromosome generated in step S34; S36, repeat the above steps S31 to S35 until the set maximum number of iterations is met, and then output the optimal feasible method.

Images