Ship transport capacity structure optimization method and device

Abstract

The invention discloses a ship transport capacity structure optimization method and device, and belongs to the technical field of water transport management and scheduling optimization, and the method comprises the steps: obtaining a feasible configuration scheme set of a ship transport capacity structure, and carrying out the clustering of the feasible configuration scheme set according to a Gaussian volume accumulation model, and obtaining a feasible solution set; and constructing a transport capacity structure optimization model, iteratively searching a feasible solution set in combination with a whale optimization algorithm, and determining an optimal configuration scheme. A feasible configuration scheme set of the ship transport capacity structure is screened by constructing a transport capacity structure optimization model, a configuration scheme meeting the requirement is obtained, and the rationality of the transport capacity structure is guaranteed; the whale optimization algorithm is used for carrying out iterative search on the configuration scheme, the maximum utilization rate of the lock chamber is used as a guide, the optimal configuration scheme is selected in a simulation mode, the optimal configuration scheme of the transport capacity structure is obtained, and resource waste is greatly reduced.

Description

Technical Field

[0001] The present invention relates to the technical field of water transport management and scheduling optimization, and in particular to a method and device for optimizing ship transport capacity structure. Background Art

[0002] With the rapid development of the global economy and the increasing frequency of trade activities, inland waterway transportation has become increasingly important in the cargo transportation system. As a low-cost and high-efficiency mode of transportation, inland waterway transportation is widely used for various types of bulk goods and long-distance transportation. With the increase in ship traffic on inland waterways, traffic congestion and resource waste have become increasingly prominent. The main manifestations are: (1) Unreasonable ship capacity structure: The distribution of ship types and sizes on inland waterways is unbalanced, and the capacity structure does not match the actual transportation demand. (2) Low utilization rate of traffic facilities: The arrangement and scheduling of ships of different sizes and types in traffic facilities are unreasonable, resulting in low utilization rate of traffic facility space.

[0003] At present, most inland waterway shipping management systems rely on fixed scheduling rules and manual experience to allocate and schedule capacity structures. They lack systematic optimization models and scientific and reasonable management mechanisms, making it difficult to effectively respond to the complex and changeable shipping environment and the ever-changing transportation needs. Especially when multiple types of ships pass through mixed traffic, scheduling errors and waste of resources are prone to occur.

[0004] Therefore, in the process of water transport management and scheduling, the existing technology has the problem of resource waste due to unreasonable transport capacity structure. Summary of the invention

[0005] In view of this, it is necessary to provide a method and device for optimizing the ship capacity structure to solve the problem of resource waste caused by unreasonable capacity structure in the process of water transport management and scheduling in the prior art.

[0006] In order to solve the above problems, the present invention provides a method for optimizing ship capacity structure, comprising: Obtain a set of feasible configuration solutions for ship capacity structure; Construct a capacity structure optimization model, which includes optimization objectives, constraints and multi-objective optimization functions; Based on the capacity structure optimization model, the feasible configuration scheme is optimized for multiple objectives, and combined with the whale optimization algorithm for iterative search to determine the optimal configuration scheme; Among them, the optimization goals include minimizing the capacity adjustment, maximizing the lock chamber utilization and minimizing the number of lock openings.

[0007] In a possible implementation, a multi-objective optimization is performed on feasible configuration schemes according to the capacity structure optimization model, including: Construct a multi-objective optimization function based on the optimization objectives and constraints; The target weights of the optimization targets are set respectively, and the multi-objective optimization function is adjusted according to the target weights to obtain the target capacity structure optimization model; The feasible solution set of feasible configuration schemes is screened out according to the target capacity structure optimization model.

[0008] In a possible implementation, the calculation formula of the multi-objective optimization function is:

[0009] ） in, is the objective function of the number of gate discharges, is the maximum number of gate trips within the specified time. is the objective function for optimizing the asymptotic performance of capacity, is the objective function of the lock chamber utilization, These are the corresponding weights for the three different objective functions.

[0010] In one possible implementation, the optimal configuration scheme is determined by combining the iterative search of the whale optimization algorithm, including: Initialize the parameters of the feasible solution set, set the population size and the maximum number of iterations; The fitness function is set based on the maximum utilization of the lock chamber and the minimum number of gate discharges; The fitness value of each whale in the population is calculated, and it is iteratively updated to the maximum number of iterations based on the whale optimization algorithm, and the feasible solution corresponding to the maximum fitness value is determined as the optimal configuration solution.

[0011] In a possible implementation, setting a target weight of an optimization target includes: Calculate the standard deviation of the first objective based on the feasible solution set; Calculate the distance correlation between the first target and the remaining targets respectively; The target weight of the first target is determined based on the standard deviation and distance correlation.

[0012] In a possible implementation, obtaining a feasible configuration solution set of a ship capacity structure includes: Obtain cargo transportation demand for each route based on historical data; Generate multiple ship capacity structure configuration plans that meet cargo transportation needs and obtain a set of feasible configuration plans; Among them, the ship capacity structure configuration plan includes a combination of ships of different types, tonnages and numbers.

[0013] In a possible implementation, before performing multi-objective optimization on feasible configuration solutions according to the capacity structure optimization model, the following steps are also included: Cluster the feasible configuration scheme set according to the Gaussian convolution clustering model to obtain the feasible solution set; Multi-objective optimization is performed on the feasible solution set based on the capacity structure optimization model.

[0014] In a possible implementation, the feasible configuration solution set is clustered according to the Gaussian convolution clustering model to obtain a feasible solution set, including: Calculate density convolution estimation values ​​of all data points of the feasible configuration scheme, and determine the data points whose density convolution estimation values ​​are within a first preset range as candidate center points; The data point corresponding to the maximum value of the density convolution estimation is taken as the first center point, the ratio of the conditional probabilities between the remaining candidate center points and the first center point is calculated respectively, and the candidate center points whose conditional probability ratios are greater than the preset conditional probability threshold are removed to obtain the updated center point; The data point corresponding to the second largest value is estimated as the second center point by density convolution of the updated center point, and the conditional probability ratios between the remaining updated center points and the second center point are calculated respectively, and the candidate center points whose conditional probability ratios are greater than the preset conditional probability threshold are removed to obtain the secondary updated center point; Repeat the iteration until the minimum value of the density convolution estimate among the candidate center points is taken as the center point to obtain the initial principal component center point. After optimizing the parameters of the Gaussian convolution clustering model, the final principal component center point is determined based on the initial principal component center point, and the feasible configuration scheme corresponding to the final principal component center point is determined as the feasible solution set.

[0015] In a possible implementation, after determining the optimal configuration solution, the following steps are further included: Select the index calculation factor of ship congestion; Obtain the factor set and evaluation set of the optimal configuration solution based on the indicator measurement factors; The factor set and the evaluation set are compounded by the interval average method to obtain a comprehensive index.

[0016] In order to solve the above problems, the present invention also provides a ship capacity structure optimization device, comprising: A feasible configuration solution set acquisition module is used to acquire a feasible configuration solution set of the ship capacity structure; The capacity structure optimization model building module is used to build the capacity structure optimization model. The capacity structure optimization model includes optimization objectives, constraints and multi-objective optimization functions; The optimal configuration scheme determination module is used to perform multi-objective optimization of feasible configuration schemes based on the capacity structure optimization model, and combine the whale optimization algorithm to iteratively search and determine the optimal configuration scheme; Among them, the optimization goals include minimizing the capacity adjustment, maximizing the lock chamber utilization and minimizing the number of lock openings.

[0017] The beneficial effect of adopting the above embodiment is as follows: the present invention provides a method for optimizing the ship capacity structure. First, by constructing a capacity structure optimization model, a set of feasible configuration schemes for the ship capacity structure is screened to obtain a configuration scheme that meets the needs, thereby ensuring the rationality of the capacity structure; then, the whale optimization algorithm is used to iteratively search for the configuration scheme, and the best is selected through simulation, guided by the maximum utilization of the lock chamber, thereby achieving the optimal configuration scheme for the capacity structure and greatly reducing resource waste. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] Figure 1 A schematic diagram of a flow chart of an embodiment of a method for optimizing ship capacity structure provided by the present invention; Figure 2 A schematic diagram of a flow chart of an embodiment of obtaining a feasible solution set provided by the present invention; Figure 3 A schematic diagram of a flow chart of an embodiment of multi-objective optimization of feasible configuration schemes provided by the present invention; Figure 4 A schematic diagram of a flow chart of an embodiment of determining a first target weight provided by the present invention; Figure 5 A schematic diagram of a flow chart of an embodiment of determining an optimal configuration solution provided by the present invention; Figure 6 A schematic diagram of a flow chart of an embodiment of a whale optimization algorithm provided by the present invention; Figure 7 A schematic diagram of a flow chart of an embodiment of evaluating a ship congestion state provided by the present invention; Figure 8 A schematic diagram of a flow chart of an embodiment of obtaining and evaluating the optimal configuration of the transport capacity structure provided by the present invention; Fig. 9 A structural block diagram of an embodiment of a ship transport capacity structure optimization device provided by the present invention; Fig.10 This is a structural block diagram of an embodiment of an electronic device provided by the present invention. DETAILED DESCRIPTION

[0019] The preferred embodiments of the present invention will be described in detail below in conjunction with the accompanying drawings, wherein the accompanying drawings constitute a part of the present invention and are used together with the embodiments of the present invention to illustrate the principles of the present invention, but are not used to limit the scope of the present invention.

[0020] The Gaussian convolution clustering model, especially the Gaussian mixture model (GMM), is a clustering algorithm based on probability distribution. Specifically, GMM assumes that the data comes from multiple different Gaussian distributions, each of which represents a cluster. It can not only handle the uncertainty of the data, but also consider the probability of data points belonging to different clusters, so it is called soft clustering. Compared with hard clustering algorithms such as K-means, GMM may be more suitable when dealing with data with irregular cluster shapes or correlation between clusters.

[0021] The ship capacity structure refers to the composition and configuration of ships of different types and specifications in a shipping company or fleet, which usually depends on multiple factors such as the shipping company's operating strategy, market demand, ship technical characteristics and operating costs.

[0022] The whale optimization algorithm can efficiently solve complex optimization problems by simulating whales' strategies such as encirclement, spiral predation, and collision avoidance. The algorithm regards the position of each humpback whale as a feasible solution, and the process of searching for a solution is regarded as several whales constantly updating their positions until they tightly encircle the target prey (i.e., the optimal solution).

[0023] The ship capacity structure determines the effect of water transport management and scheduling. Due to the unreasonable ship capacity structure, the utilization rate of traffic facilities is low, and the overall efficiency of the inland waterway transportation system is seriously restricted. Therefore, in the process of water transport management and scheduling, the existing technology has the problem of resource waste due to the unreasonable capacity structure.

[0024] In order to solve the above problems, the present invention provides a method and device for optimizing the ship capacity structure, which are described in detail below.

[0025] Figure 1 A schematic diagram of a flow chart of an embodiment of a method for optimizing ship transport capacity structure provided by the present invention, as shown in FIG. Figure 1 As shown in Figure 2, the ship capacity structure optimization method includes: S101: Obtain a feasible configuration solution set for the ship capacity structure; S102: constructing a transport capacity structure optimization model, which includes optimization objectives, constraints and multi-objective optimization functions; S103: Perform multi-objective optimization on feasible configuration schemes based on the capacity structure optimization model, and perform iterative search with the whale optimization algorithm to determine the optimal configuration scheme; Among them, the optimization goals include minimizing the capacity adjustment, maximizing the lock chamber utilization and minimizing the number of lock openings.

[0026] In this embodiment, firstly, a feasible configuration scheme set of the ship capacity structure is screened by constructing a capacity structure optimization model to obtain a configuration scheme that meets the needs, thereby ensuring the rationality of the capacity structure; then, the whale optimization algorithm is used to iteratively search for the configuration scheme, and the best is selected through simulation with the maximum utilization of the lock chamber as the guide, thereby achieving the optimal configuration scheme of the capacity structure and greatly reducing resource waste.

[0027] As a preferred embodiment, in S101, in order to obtain a set of feasible configuration schemes for the ship capacity structure, first, the cargo transportation demand of each route is obtained based on historical data; then, multiple ship capacity structure configuration schemes that meet the cargo transportation demand are generated to obtain a set of feasible configuration schemes.

[0028] Among them, the ship capacity structure configuration plan includes a combination of ships of different types, tonnages and numbers.

[0029] It should be noted that the OD line (Origin-Destination Line) refers to the line connecting the origin and the destination, which is used to visually represent the connection between two geographical locations on the map. OD data is important information in transportation planning and can be used to analyze transportation demand, predict traffic flow, plan transportation facilities, etc.

[0030] In order to generate multiple ship capacity structure configuration schemes that meet the cargo transportation demand, firstly, by collecting historical transportation data, transportation plans submitted by shipping companies and actual transportation records, the transportation demand of different types of goods between different starting points and end points (OD) is statistically analyzed, and the fluctuation of cargo transportation demand in different seasons and specific time periods is analyzed to form a cargo transportation demand model for each OD line in different periods. Then, based on the cargo transportation demand obtained from the statistical analysis, the ship capacity structure configuration scheme that meets the transportation demand is generated. These schemes include different types (such as bulk carriers, dangerous goods ships, container ships, etc.), different tonnages (such as small tonnage ships, medium tonnage ships, large tonnage ships) and different number of ship combinations.

[0031] That is to say, based on each OD line, the cargo transportation demand is first obtained according to historical data, and then, based on the cargo transportation demand and basic information such as the type, transportation capacity and quantity of the ship, multiple ship capacity structure configuration plans that meet the needs are automatically generated and recorded as a feasible configuration plan set.

[0032] Furthermore, the feasible configuration scheme set only represents the ability to meet the needs, but there will definitely be a large amount of data redundancy. Therefore, in order to reduce the subsequent data comparison work, before performing multi-objective optimization on the feasible configuration scheme according to the capacity structure optimization model, the feasible configuration scheme set is clustered according to the Gaussian convolution clustering model to obtain a feasible solution set; then, the feasible solution set is multi-objective optimized according to the capacity structure optimization model.

[0033] In a specific embodiment, if Figure 2 As shown, Figure 2 A flow chart of an embodiment of obtaining a feasible solution set provided by the present invention includes: S201: Calculate density convolution estimation values ​​of all data points of the feasible configuration scheme, and determine data points whose density convolution estimation values ​​are within a preset first range as candidate center points; S202: taking the data point corresponding to the maximum value of density convolution estimation as the first center point, respectively calculating the ratios of conditional probabilities between the remaining candidate center points and the first center point, and removing the candidate center points whose conditional probability ratios are greater than a preset conditional probability threshold, to obtain an updated center point; S203: using density convolution of the updated center point to estimate the data point corresponding to the second maximum value as the second center point, respectively calculating the conditional probability ratios between the remaining updated center points and the second center point, and removing the candidate center points whose conditional probability ratios are greater than a preset conditional probability threshold, to obtain a secondary updated center point; S204: Repeat the iteration until the minimum value of the density convolution estimate among the candidate center points is used as the center point to obtain the initial principal component center point, optimize the parameters of the Gaussian convolution clustering model, determine the final principal component center point based on the initial principal component center point, and determine the feasible configuration scheme corresponding to the final principal component center point as the feasible solution set.

[0034] In this embodiment, the density of the configuration scheme is estimated through the Gaussian convolution model, and similar schemes are clustered to screen out a representative set of capacity structure configurations as a feasible solution set, which effectively reduces the number of candidate schemes and improves the optimization solution efficiency.

[0035] It should be noted that the calculation formula of the Gaussian mixture model is as follows: (1) (2) in, is the normal distribution density function, x is the data point, For the k The mean of the Gaussian components, For the k The covariance of the Gaussian components, For thek The weight coefficients of the Gaussian components, ≥0, and satisfies , M is the number of Gaussian components, π is the element periodicity, exp It means to find the exponential function of the formula in the brackets. Indicates a d dimensional data matrix, d represents the dimension of the data point, T Represents a vector Request transpose.

[0036] The calculation formula of Gaussian kernel function is as follows: (3) is the Gaussian kernel function, H is the covariance matrix of the Gaussian kernel function.

[0037] The calculation formula of the Gaussian mixture model based on Gaussian convolution is as follows: (4) Density Convolution f*H (x) The estimated calculation formula is as follows: (5) n is the number of data points, Indicates i data points.

[0038] As a preferred embodiment, in S201, in order to calculate the density convolution estimation value of all data points of the feasible configuration scheme, first, the Gaussian kernel function covariance matrix H is estimated. Specifically, first, the characteristic vector of each capacity structure configuration scheme is extracted, including information such as ship type, tonnage distribution, quantity, etc. Each capacity structure configuration scheme is represented as a characteristic vector matrix , solution set The dimension is d , the number of solutions is n , Indicates i The feature vector of the solution.

[0039] Secondly, the calculation solution set Two feature matrices of It is a set of solutions The range matrix of data formed by the range in each dimension reflects the size of the data distribution range, where d，= , diag It means converting the vector into a diagonal matrix. So is a Gaussian kernel function, a diagonal matrix constructed with the normalized value of the density of each sample point. represents the inverse matrix of the data range matrix, Indicates n The density value of the data point is estimated as follows: (6) (7) (8) Furthermore, in order to better perform cluster analysis and density estimation, the solution set Perform Gaussian convolution data transformation (GCDT). Specifically, each feature vector matrix X is transformed into a new data set Y represented as: (9) In the formula, , for The data range matrix is yes The inverse matrix of Can be considered as a data set Y and X The compression ratio matrix between This means that each data point is compressed according to its density value.

[0040] G For the solution set Gaussian convolution data transformation, that is, , G The weighted covariance matrix of (WCM) The calculation method is as follows: (10) In the formula, For the dataset The covariance matrix of for G The data range matrix is

[0041] Gaussian kernel function covariance matrix H The calculation formula is as follows: (11) (12) in, r is the correction factor, for The unit matrix, d Represents the dimensions of the data points.

[0042] According to the above formula, for any feasible configuration scheme, its corresponding density convolution estimate can be calculated. The density convolution estimate represents the distribution of feasible configuration schemes to a certain extent. Then, all data points of all feasible configuration schemes are calculated. }Dense convolution estimate , the convolution estimate Sort from large to small, select the points in the first preset range as candidate center points (the excluded points are regarded as isolated points), recorded as , an initial screening is achieved, and the isolated points are the feasible configuration solutions with poor quality that are deleted.

[0043] In a specific embodiment, the first preset range is selected as 80%. In other embodiments, the first preset range can be adaptively adjusted according to actual needs, which will not be elaborated here.

[0044] As a preferred embodiment, in S202, the conditional probability calculation formula of the i-th data point being generated by the k-th pivot center point is as follows: (13) (14) in, For each As the weight parameter of the pivot center, for The density convolution estimate of s is the number of candidate center points, H is the covariance matrix of the Gaussian kernel function, For the i The data points are k The conditional probability of the pivot center being generated.

[0045] Calculate the i The pivot centers are respectively k The pivot element is generated by i The ratio of the conditional probabilities of the pivots: (15) Then, select the initial pivot center point: Sort by convolution estimate value from large to small and select the convolution estimate value The maximum value corresponding to is the first pivot center point, expressed as .

[0046] Calculate the remaining points and The ratio of the conditional probabilities ,when When Delete from the maximum point sequence and update the sequence, denoted as , and Updated to ,in, is the preset conditional probability threshold; when When, keep , the sequence is not updated.

[0047] choose As the second pivot center point, it is expressed as ,when ） When Delete from the sequence of candidate centers and update the sequence, recorded as , and Updated to .

[0048] Repeat until the last point ,get M The initial pivot center points are recorded as the sequence .

[0049] The initial preset covariance and initial preset weight of each initial center point of the Gaussian mixture model are set as follows: (16) (17) is a sequence of M initial pivot points The data points in .

[0050] ⑥ Use the EM algorithm to solve the initial estimated values ​​of the mean, covariance, and weight coefficient of each initial center point, and the calculation is as follows: (18) (19) (20) (twenty one) in, Indicates i Data points By k The probability of the generation of a pivot center is For the k The mean of the pivot centers, also known as k The initial center point, Similarly, Indicates k The initial pre-weights of the pivot centers, Indicates j The initial preset weights of the pivot centers, Indicates k The initial mean estimate of the initial center points, n is the number of all data points, For the i data points, Indicates k The initial covariance estimate of the initial center points, Indicates k The initial weight estimates for the initial center points.

[0051] 4) Optimize the parameters of the Gaussian mixture model to determine the final parameters and principal component center of the model ① Use the initial estimated values ​​of each parameter to calculate the conditional probability matrix of the initial center point ,in For the The pivot center is The conditional probability of the generation of a pivot is calculated as follows: (twenty two) is the mean value calculated by formula (19), is the covariance calculated by formula (20), is the weight calculated by formula (21), M is the number of initial pivot center points screened, is the normal distribution density function.

[0052] ② Iterative optimization and selection of the main component center point sequence: Calculate the density convolution estimate of each initial center point ,Will Estimate by convolution Sort from largest to smallest, given a significance level ,choose As the first cluster center point of the model, and expressed as .when When Remove from the center point sequence. Represents the new center point sequence, and the conditional probability matrix Updated to ,choose As the second cluster center point of the model, the center point is represented as .when When, from the center point sequence Remove . Update the center point sequence and the conditional probability matrix. Repeat the above process until the last initial center point, and get The new sequence is .

[0053] ③ The initial covariance of each center point of the new sequence Set to Corresponding to the original covariance, the initial weight coefficient of each center point of the new sequence is calculated as follows: (twenty three) for The data points in the new sequence of pivot center points.

[0054] ④ Use equations 18 to 21 to update the estimated values ​​of the mean, covariance, and weight coefficient of each center point of the new center point sequence, and recalculate the conditional probability matrix using the new parameter estimates .

[0055] ⑤Repeat steps ①~④ until , is a threshold for stopping iteration, and the final central point of the principal component and the parameter estimates of each principal component center are obtained. The final central point and parameter estimates are used to cluster the schemes, screen out representative configuration schemes, and form an initial capacity structure set.

[0056] In this embodiment, by performing cluster calculation on the feasible configuration solution set, the reliability of the feasible solution set is greatly improved and the redundancy of data is reduced.

[0057] As a preferred embodiment, in S102, in order to perform multi-objective optimization on feasible configuration solutions according to the capacity structure optimization model, such as Figure 3 As shown, Figure 3 A flow chart of an embodiment of multi-objective optimization of feasible configuration schemes provided by the present invention includes: S301: construct a multi-objective optimization function according to the optimization objectives and constraints; S302: setting target weights of optimization targets respectively, and adjusting the multi-objective optimization function according to the target weights to obtain a target capacity structure optimization model; S303: Screen out a feasible solution set of feasible configuration schemes according to the target capacity structure optimization model.

[0058] In this embodiment, the optimization objectives are to minimize the capacity adjustment degree, maximize the lock chamber utilization rate and minimize the number of lock discharges. By taking the ship operating conditions as constraints and guided by the three optimization objectives, a multi-objective optimization function is constructed. In addition, in order to adapt to the needs of different environments, the target weights of the optimization objectives are set respectively, and the multi-objective optimization function is adjusted according to the target weights to obtain the target capacity structure optimization model, which realizes the merging of the three optimization objectives for the subsequent optimization steps.

[0059] Specifically, the capacity adjustment degree is represented by the difference between the optimized ship capacity structure and the current ship capacity structure, that is, the capacity progressiveness. The calculation method of the progressive objective function of the capacity structure optimization of any OD line is as follows: (twenty four) In the formula, For transport i Class goods j Number of vessels of this type; For transport i Total number of ships carrying this type of cargo; To transport the first i Class goods j Number of vessels of this type; To transport the first i Total number of ships carrying this type of cargo, For transport i Class goods j Progressive target value for ships of this type.

[0060] The lock chamber utilization rate is quantified by the lock chamber area utilization rate, which refers to the ratio of the projected area of ​​ships passing through the lock on the horizontal plane of the lock to the effective area of ​​the lock. The greater the demand for ships passing through the lock and the higher the degree of ship standardization, the greater the corresponding lock chamber area utilization rate, indicating that the economic benefits created by the lock are higher.

[0061] The calculation method of the lock chamber area utilization rate is as follows: (25) In the formula, is the area of ​​the lock chamber occupied by a ship in a lock, is the area of ​​a certain lock, is the lock chamber utilization rate.

[0062] The number of locks refers to the minimum number of locks required by the ship capacity structure to meet the cargo transportation demand. The more locks are required, the more likely it is to cause ship congestion when the maximum number of locks is exceeded. Conversely, the fewer locks are required, the more potential for ship capacity to be improved. Under a certain ship capacity structure, the number of locks required within a certain period of time is related to the number of ships, ship size, and lock size information, and the calculation method is as follows: (26) In the formula, It is the number of lock openings under a certain ship capacity structure; is the number of ships under this capacity structure; is the length of the vessel under this capacity structure; is the width of the ship under this capacity structure; is the area of ​​a certain lock.

[0063] Regarding constraints, the capacity structure optimization model needs to meet the following constraints: 1) Cargo transportation demand refers to the number of ships required for each type of cargo on each OD route within a certain period of time is not less than the number of ships of the same type that need to be deployed during that period of time.

[0064] (27) In the formula, The total amount of goods to be transported; The number of ships of a certain type; For transport i Class goods j Maximum deadweight tonnage of a ship of this type; For transport i Class goods j The loading rate of the ship.

[0065] 2) Vessel waiting time refers to the time delay caused by ships queuing to pass through the lock due to traffic congestion in the lock.

[0066] (28) In the formula, The waiting time for the vessel at the lock shall not exceed 72 hours.

[0067] 3) Ship lock: The sum of the areas of all ships passing through the lock at one time must not exceed the area of ​​the lock chamber.

[0068] (29) (30) (31) Formula (29) indicates that the sum of the areas of the ships arranged in the lock cannot exceed the ship area, For ships i The area of is the lock area. In formula (30), For ships i Length; is the length of the ship lock. In formula (31), For ships i Width; is the width of the lock.

[0069] 4) Ship loading means that the sum of the cargo tonnage of all cargo ships must be greater than the total weight of the cargo, taking into account the loading rate.

[0070] (32) In the formula, Indicates i The load of the ship, Indicates the total weight of the cargo.

[0071] 5) The lock passing rules mean that ordinary ships and dangerous goods ships cannot pass through the locks at the same time, and dangerous goods ships must be arranged to pass through the locks separately.

[0072] (33) Formula (33) represents the lock rule constraints for different ship types. Indicates that the ship is passing through the lock once. Indicates an ordinary ship. Indicates a dangerous goods vessel.

[0073] In S302, under the premise of satisfying the above constraints, the capacity adjustment degree and the number of gate discharges are minimized, the utilization rate of the gate chamber is maximized, and a multi-objective optimization function is constructed based on the above optimization objectives and various sub-objectives. The multi-objective optimization function is described as follows:

[0074] In S303, in order to simplify the form of the multi-objective optimization function, the target weights of the optimization targets are set respectively, and the multi-objective optimization function is adjusted according to the target weights, and the expression of the target capacity structure optimization model is obtained as follows: (34) In the formula, is the objective function of the number of gate discharges, is the maximum number of gate trips within the specified time. is the objective function for optimizing the asymptotic performance of capacity, is the objective function of the lock chamber utilization, These are the corresponding weights for the three different objective functions.

[0075] In order to standardize the target weights of the optimization targets, in S302, the target weights need to be regulated. For example, the first target Figure 4 As shown, Figure 4 A flow chart of an embodiment of determining a first target weight provided by the present invention includes: S401: Calculate the standard deviation of the first target according to the feasible solution set; S402: Calculating the distance correlation between the first target and the remaining targets respectively; S403: Determine a first target weight according to the standard deviation and the distance correlation.

[0076] In a specific embodiment, first, the data is standardized, and the calculation formula is as follows: (35) in, is the original data, is the standardized data, It is Configuration Scheme No. i The original value of the target, It is Configuration Scheme No. i The target value after standardization of the target, For the Configuration Scheme No. i The minimum value of the target, For the Configuration Scheme No. i The maximum value of the targets.

[0077] For each target i, calculate its standard deviation: (36) in, It is Configuration Scheme No. i The value of the target, It is i The average value of the targets, n is the number of configuration options.

[0078] For each pair of targets and , calculate the distance correlation between them : ① Calculate the distance matrix: For each target, calculate the Euclidean distance between configuration options , ,in and is the target X In the configuration plan and The corresponding value.

[0079] ② Distance matrix DX Perform dual centralization processing, and the calculation formula is as follows: (37) in, is a matrix DX No. The average value of the row, is a matrix DX No. The mean of the column, is a matrix DX The average value of all elements of .

[0080] ③Calculate distance covariance and distance variance , the calculation formula is as follows: (38) (39) Respectively represent the target X, Y The distance matrix DX The corresponding value after double centering is, n is the number of configuration options, For the goal X and Y The distance covariance of For the goal X The distance variance of .

[0081] ④ The distance correlation between two targets X and Y is calculated as follows: (40) 4) Calculate the weight of each target , the calculation formula is as follows: (41) in, is the goal The standard deviation of is the goal and goals The distance correlation between Same reason.

[0082] In this embodiment, the first target weight is quantified based on the distance correlation between each target, which can effectively ensure the objectivity of the first target weight.

[0083] After determining the capacity structure optimization model, since the capacity structure optimization model needs to be optimized for multiple objectives, in order to determine the optimal configuration solution, it is necessary to combine the whale optimization algorithm to iteratively search for feasible solutions, such as Figure 5 As shown, Figure 5 A flow chart of an embodiment of determining an optimal configuration scheme provided by the present invention includes: S501: Initialize the parameters of the feasible solution set, set the population size and the maximum number of iterations; S502: Setting a fitness function based on the maximum utilization rate of the lock chamber and the minimum number of gate discharges; S503: Calculate the fitness value of each whale individual in the population, and iterate and update it to the maximum number of iterations based on the whale optimization algorithm, and determine that the optimization configuration scheme corresponding to the maximum fitness value is the optimal configuration scheme.

[0084] In this embodiment, after obtaining the feasible solution set, in order to select the most appropriate optimal solution from it, it is also necessary to construct a sub-model of the lock capacity, which is used to optimize the overall transportation time efficiency of the ships passing through the dam after the capacity adjustment. First, the ship priority is determined, and then the lock chamber arrangement optimization model is established with the highest overall priority of the ship as the objective function, and the optimization algorithm is used to make the model continuously converge to the maximum lock chamber utilization.

[0085] The appropriate lock layout plan should comprehensively consider the lock chamber area utilization and ship priority. 1) Determine the objective function of the model This model takes the highest overall priority of ships passing through the lock as the objective function, and uses an optimization algorithm to make the model converge to the maximum utilization of the lock chamber. The constraints obeyed by the objective function are the lock constraints and lock passage rule constraints in the previous ship capacity structure optimization model. The ship priority and lock chamber utilization comprehensive maximization function in the model is described as follows: (42) In the formula, Indicates the queue of ships waiting for the lock. Indicates Whether a ship is selected, Indicates ship i priority.

[0086] Before arranging the lock chambers, the priority of individual ships must be determined first.

[0087] Finally, the optimal solution of the lock capacity sub-model is calculated based on the whale optimization algorithm: ① Initialization parameters When calculating the ship formation combination of the lock, it is necessary to initialize the parameters and set the population size N and the maximum number of iterations T.

[0088] ② Initialize the population Randomly generate n initial solutions as the initial population, each solution represents a lock chamber arrangement strategy, and each whale individual in the population represents a potential lock arrangement plan (feasible solution). Each solution contains information such as the location of each ship and the lock it belongs to.

[0089] ③Fitness function design The fitness function is defined to evaluate the quality of the solution. The optimization goal of the model is to minimize the number of gates and improve the average area utilization of the gate chamber. The fitness function is designed based on these two goals. The fewer the number of gates, the higher the fitness. The average area utilization takes a negative value. The larger the value, the better the fitness. The specific expression is as follows:

[0090] is the number of lock openings under a certain ship capacity structure, is the area of ​​the lock chamber occupied by a ship in a lock, is the area of ​​a certain lock, It is the maximum number of gate discharge times within the specified time.

[0091] ④Iterative search for the optimal solution After the initial solution is generated, the fitness value of each whale in the initial population is calculated, and the individual with the best fitness value is found as the optimal position. Then, the whale's encirclement strategy, hunting behavior strategy (bubble net attack strategy) and search strategy are used to update the whale's position. The steps are as follows: a. Encirclement of prey strategy Whale individuals can identify the location of prey and surround it in a circle, but since the optimal position in the search space is unknown, the algorithm assumes that the optimal position of the current population is the target prey position, and other whales will try to approach the target prey position and surround it. In this process, other whale individuals use formula (43) to update their positions to approach the optimal individual: (43) (44) a (45) (46) a (47) In the formula, Search to The individual position of the whale that achieves the global optimal solution in the population at the generation time, For the The position of the individual at the iteration, For the The position of the individual at the iteration, represents the bracketing step length, and is the coefficient vector, is the maximum number of iterations, for A random number between , a is a number that gradually decreases from 2 to 0 during the iteration process.

[0092] b. Hunting behavior strategy (bubble net attack strategy) b1. Contraction and encirclement mechanism In the iterative process, by The value of is reduced from 2 to 0 to achieve shrinkage and encirclement, because The fluctuation range is [- ],when When decreasing, The fluctuation range of will also be reduced. Use equation (43) to update the position of individual whales.

[0093] b2. Spiral update position mechanism In order to simulate the spiral hunting method of whales, the individual positions of whales are updated using equation (48). is the distance between the current whale and the optimal prey, is a constant that controls the shape of the logarithmic spiral, is a random number on [-1, 1], and cos represents the cosine function. The formula is as follows: (48) (49) c. Searching for prey strategy In the prey search phase, the whale individual no longer selects the best individual as the target for position update, but randomly selects an individual from the current population as the target for position update, thereby increasing the search range and maintaining population diversity while finding the optimal solution. The calculation formula is as follows: (50) (51) In the formula, is the position of a whale individual randomly selected from the current individual, is the distance between the current whale and the random whale.

[0094] In order to simulate the spiral swimming behavior of whales, it is assumed that there is a 50% probability of choosing the shrinking and encircling mechanism or the spiral model to update the position of the whale during the optimization process, that is, there is a is a random number between [0, 1], when When , use formula (48) to update the position. When, according to The value of determines the update method. When , use formula (43) to update the position. | When , use formula (50) to update the position. The updated individuals are bounded and their fitness values ​​are recalculated. Then, the best individual is updated according to the greedy selection mechanism. , repeat the iterative optimization until the maximum number of iterations is reached, and output the optimal gate discharge plan.

[0095] In order to clearly describe the data processing process of the whale optimization algorithm, such as Figure 6 As shown, Figure 6 The figure is a flow chart of an embodiment of a whale optimization algorithm provided by the present invention. WOA (Whale Optimization Algorithm) refers to a whale optimization algorithm.

[0096] After the parameters are initialized, the coefficient vector is calculated and the whale position is continuously updated iteratively to achieve the optimal result by combining simulation technology. In summary, this embodiment achieves multi-objective optimization by iterating the configuration scheme set one by one and maximizing the offset of the fitness function according to the whale optimization algorithm, effectively ensuring the reliability of the optimal configuration scheme.

[0097] Furthermore, after determining the optimal configuration scheme, in order to better monitor and control water transport conditions, it is also necessary to evaluate the ship congestion status corresponding to the optimal configuration scheme, such as Figure 7 As shown, Figure 7 A flow chart of an embodiment of evaluating the congestion status of a ship provided by the present invention includes: S701: Selecting the index calculation factor of ship congestion; S702: Obtaining a factor set and an evaluation set of an optimal configuration solution based on the indicator measurement factors; S703: Perform compound operations on the factor set and the evaluation set by using the interval average method to obtain a comprehensive index.

[0098] As a preferred embodiment, in S701, it is necessary to select ship congestion index calculation factors based on the temporal and spatial characteristics of ship congestion, from the perspectives of duration, intensity, scope, etc. of the congestion problem, and based on factors that directly or indirectly affect the ship congestion status, such as lock capacity, ship traffic flow, lock scheduling, and anchorage.

[0099] As a preferred embodiment, in S702, four congestion evaluation indicators are selected as an evaluation set, namely the number of ships waiting for lock, the average waiting time of ships, the longest waiting time and the use status of the anchorage.

[0100] Among them, the factor set is a set of factors of the ship congestion index. Based on the selected congestion index, Factor set {maximum number of congested ships, average waiting time, longest waiting time, anchorage utilization rate}.

[0101] As a preferred embodiment, in S703, the congestion evaluation algorithm adopts the fuzzy comprehensive evaluation method. According to the fuzzy comprehensive idea, the steps of congestion evaluation modeling are as follows: first, determine the factor set of the object to be evaluated according to the congestion index; and evaluation set Then, the weights of each factor and its membership vector are determined respectively, and after fuzzy transformation, the fuzzy evaluation matrix is ​​obtained. Finally, the fuzzy evaluation matrix and the weight vector of the factor are fuzzy operated to obtain the fuzzy comprehensive evaluation set.

[0102] In order to better identify the degree of congestion, the traffic congestion status is divided into five levels, namely severe congestion, obvious congestion, slight congestion, relatively smooth, and smooth. Therefore, the determined index calculation factor evaluation set is {smooth, relatively smooth, slightly congested, obviously congested, severely congested}. For the calculation of the evaluation value that integrates all congestion indicators, according to the fuzzy transformation principle, the interval average method is used to perform a composite operation on the evaluation result matrix and the interval average matrix, and the evaluation matrix is ​​converted into a comprehensive index. , also known as the ship congestion index.

[0103] Based on fuzzy mathematics theory, the ship congestion index is assumed to be The value of the interval. When When it comes to ship congestion at the waterway hub, it means that the problem of ship congestion at the waterway hub is extremely serious; The values ​​between reflect the different states of ship congestion in the waterway hub. According to the congestion levels defined previously, the index value ranges of the five levels of ship congestion states are determined, with the value ranges of 0~0.2, 0.2~0.4, 0.4~0.6, 0.6~0.8, and 0.8~1, corresponding to the congestion levels of v1~v5, respectively.

[0104] In order to clearly show the process of optimizing the configuration scheme of ship capacity structure, Figure 8 As shown, Figure 8A flow chart of an embodiment of obtaining and evaluating the optimal configuration of the capacity structure provided by the present invention. First, the capacity demand of the ship is constructed according to the operation demand of the ship and the existing ship operation data; then, the generated feasible solution set is preliminarily optimized according to the Gaussian algorithm, and some infeasible solutions are screened out, and constraints and optimization objective functions are set according to the capacity structure optimization model combined with the capacity demand, and then the preliminarily screened solutions are simulated and verified according to the whale optimization algorithm, so as to obtain the optimal configuration plan of the ship's capacity structure; finally, in order to better evaluate the reliability of the optimal configuration plan, a congestion model is specially set up to evaluate the congestion effect of the optimal configuration plan, so as to better assist water transport management and scheduling.

[0105] Through the above method, the feasible configuration scheme set of the ship capacity structure is screened by constructing a capacity structure optimization model, and the configuration scheme that meets the needs is obtained, thereby ensuring the rationality of the capacity structure; then, the whale optimization algorithm is used to iteratively search the configuration scheme, and the best is selected through simulation, guided by the maximum utilization of the lock chamber, to achieve the optimal configuration scheme of the capacity structure, which greatly reduces the waste of resources.

[0106] In order to solve the above problems, the present invention also provides a ship capacity structure optimization device, such as Fig. 9 As shown, Fig. 9 This is a structural block diagram of an embodiment of a ship transport capacity structure optimization device provided by the present invention. The ship transport capacity structure optimization device 900 includes: A feasible solution set acquisition module 901, a feasible configuration scheme set acquisition module, is used to acquire a feasible configuration scheme set of a ship capacity structure; A capacity structure optimization model building module 902 is used to build a capacity structure optimization model, which includes optimization objectives, constraints and multi-objective optimization functions; The optimal configuration scheme determination module 903 is used to perform multi-objective optimization on feasible configuration schemes based on the capacity structure optimization model, and combine the iterative search of the whale optimization algorithm to determine the optimal configuration scheme; Among them, the optimization goals include minimizing the capacity adjustment, maximizing the lock chamber utilization and minimizing the number of lock openings.

[0107] like Fig.10 As shown, the present invention also provides an electronic device 1000. The electronic device 1000 includes a processor 1001, a memory 1002 and a display 1003. Fig.10 Only some components of the electronic device 1000 are shown, but it should be understood that it is not required to implement all of the components shown, and more or fewer components may be implemented instead.

[0108] In some embodiments, the processor 1001 may be a central processing unit (CPU), a microprocessor or other data processing chip, used to run program codes or process data stored in the memory 1002, such as the ship capacity structure optimization method of the present invention.

[0109] In some embodiments, the processor 1001 may be a single server or a server group. The server group may be centralized or distributed. In some embodiments, the processor 1001 may be local or remote. In some embodiments, the processor 1001 may be implemented in a cloud platform. In one embodiment, the cloud platform may include a private cloud, a public cloud, a hybrid cloud, a community cloud, a distributed cloud, an internal cloud, a multi-cloud, etc., or any combination thereof.

[0110] In some embodiments, the memory 1002 may be an internal storage unit of the electronic device 1000, such as a hard disk or memory of the electronic device 1000. In other embodiments, the memory 1002 may also be an external storage device of the electronic device 1000, such as a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, etc., equipped on the electronic device 1000.

[0111] Furthermore, the memory 1002 may include both an internal storage unit of the electronic device 1000 and an external storage device. The memory 1002 is used to store application software installed in the electronic device 1000 and various data.

[0112] In some embodiments, the display 1003 may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, an OLED (Organic Light-Emitting Diode) touch device, etc. The display 1003 is used to display information of the electronic device 1000 and to display a visual user interface. The components 1001-1003 of the electronic device 1000 communicate with each other via a system bus.

[0113] In one embodiment, when the processor 1001 executes the ship capacity structure optimization program in the memory 1002, the following steps may be implemented: Acquire magnetic resonance imaging data and construct a brain functional network based on the magnetic resonance imaging data; Extract multi-scale topological features of brain functional networks; The multi-scale topological features are input into a well-trained target ship capacity structure optimization model to determine the category labels of magnetic resonance imaging data.

[0114] It should be understood that: when the processor 1001 executes the ship capacity structure optimization program in the memory 1002, in addition to the above functions, other functions can also be implemented. For details, please refer to the description of the corresponding method embodiment above.

[0115] Furthermore, the embodiment of the present invention does not specifically limit the type of the electronic device 1000 mentioned, and the electronic device 1000 may be a portable electronic device such as a mobile phone, a tablet computer, a personal digital assistant (PDA), a wearable device, a laptop computer, etc. Exemplary embodiments of portable electronic devices include but are not limited to portable electronic devices equipped with IOS, Android, Microsoft or other operating systems. The above-mentioned portable electronic device may also be other portable electronic devices, such as a laptop computer with a touch-sensitive surface (e.g., a touch panel). It should also be understood that in some other embodiments of the present invention, the electronic device 1000 may not be a portable electronic device, but a desktop computer with a touch-sensitive surface (e.g., a touch panel).

[0116] Correspondingly, an embodiment of the present invention also provides a computer-readable storage medium, which is used to store computer-readable programs or instructions. When the program or instructions are executed by a processor, it can implement the steps or functions of the ship capacity structure optimization method provided by the above-mentioned method embodiments.

[0117] Those skilled in the art will appreciate that all or part of the processes of the above-mentioned embodiments can be implemented by instructing related hardware (such as a processor, a controller, etc.) through a computer program, and the computer program can be stored in a computer-readable storage medium, wherein the computer-readable storage medium is a disk, an optical disk, a read-only storage memory, or a random access memory, etc.

[0118] The ship capacity structure optimization method and device provided by the present invention are introduced in detail above. Specific examples are used in this article to illustrate the principles and implementation methods of the present invention. The description of the above embodiments is only used to help understand the method of the present invention and its core idea; at the same time, for technical personnel in this field, according to the idea of ​​the present invention, there will be changes in the specific implementation method and application scope. In summary, the content of this specification should not be understood as a limitation on the present invention.

Claims

1. A method for optimizing ship capacity structure, characterized in that: include: Obtain a set of feasible configuration solutions for ship capacity structure; Constructing a transport capacity structure optimization model, wherein the transport capacity structure optimization model includes optimization objectives, constraint conditions, and a multi-objective optimization function; Based on the capacity structure optimization model, the feasible configuration scheme is optimized by multiple objectives, and combined with the iterative search of the whale optimization algorithm to determine the optimal configuration scheme; Among them, the optimization objectives include minimizing the capacity adjustment, maximizing the lock chamber utilization rate and minimizing the number of lock discharges.

2. The method for optimizing ship capacity structure according to claim 1, characterized in that: The performing multi-objective optimization on the feasible configuration scheme according to the transport capacity structure optimization model includes: Constructing a multi-objective optimization function according to the optimization objective and the constraint conditions; The target weights of the optimization targets are respectively set, and the multi-objective optimization function is adjusted according to the target weights to obtain a target capacity structure optimization model; A feasible solution set of the feasible configuration scheme is screened out according to the target capacity structure optimization model.

3. The method for optimizing ship capacity structure according to claim 2, characterized in that: The calculation formula of the multi-objective optimization function is: ） in, is the objective function of the number of gate discharges, is the maximum number of gate trips within the specified time. is the objective function for optimizing the asymptotic performance of capacity, is the objective function of the lock chamber utilization, These are the corresponding weights for the three different objective functions.

4. The method for optimizing ship capacity structure according to claim 2, characterized in that: The iterative search combined with the whale optimization algorithm to determine the optimal configuration solution includes: Initialize the parameters of the feasible solution set, set the population size and the maximum number of iterations; The fitness function is set based on the maximum utilization of the lock chamber and the minimum number of gate discharges; The fitness value of each whale individual in the population is calculated, and it is iteratively updated to the maximum number of iterations based on the whale optimization algorithm, and the feasible solution corresponding to the maximum fitness value is determined as the optimal configuration solution.

5. The method for optimizing ship capacity structure according to claim 2, characterized in that: The setting of the target weight of the optimization target includes: Calculate the standard deviation of the first objective according to the feasible solution set; Calculating the distance correlation between the first target and the remaining targets respectively; A target weight of the first target is determined based on the standard deviation and the distance correlation.

6. The method for optimizing ship capacity structure according to claim 1, characterized in that: The feasible configuration scheme set for obtaining the ship capacity structure includes: Obtain cargo transportation demand for each route based on historical data; Generating a plurality of ship capacity structure configuration schemes that meet the cargo transportation demand to obtain the feasible configuration scheme set; The ship capacity structure configuration scheme includes a combination of ships of different types, tonnages and numbers.

7. The method for optimizing ship capacity structure according to claim 1, characterized in that: Before performing multi-objective optimization on the feasible configuration scheme according to the transport capacity structure optimization model, the method further includes: Clustering the feasible configuration solution set according to a Gaussian convolution clustering model to obtain a feasible solution set; The feasible solution set is optimized by multiple objectives according to the transport capacity structure optimization model.

8. The method for optimizing ship capacity structure according to claim 7, characterized in that: The clustering of the feasible configuration scheme set according to the Gaussian convolution clustering model to obtain a feasible solution set includes: Calculate density convolution estimation values ​​of all data points of the feasible configuration scheme, and determine the data points whose density convolution estimation values ​​are within a first preset range as candidate center points; The data point corresponding to the maximum value of density convolution estimation is taken as the first center point, the conditional probability ratios between the remaining candidate center points and the first center point are calculated respectively, and the candidate center points whose conditional probability ratios are greater than a preset conditional probability threshold are removed to obtain an updated center point; The data point corresponding to the second maximum value is estimated as the second center point by density convolution of the updated center point, the conditional probability ratios between the remaining updated center points and the second center point are calculated respectively, and the candidate center points whose conditional probability ratios are greater than a preset conditional probability threshold are removed to obtain a secondary updated center point; Repeat the iteration until the minimum value of the density convolution estimate among the candidate center points is used as the center point to obtain the initial principal component center point, optimize the parameters of the Gaussian convolution clustering model, determine the final principal component center point based on the initial principal component center point, and determine the feasible configuration scheme corresponding to the final principal component center point as the feasible solution set.

9. The method for optimizing ship capacity structure according to claim 1, characterized in that: After determining the optimal configuration solution, it also includes: Select the index calculation factor of ship congestion; Obtaining a factor set and an evaluation set of the optimal configuration solution based on the indicator measurement factors; The factor set and the evaluation set are compounded by the interval average method to obtain a comprehensive index.

10. A ship capacity structure optimization device, characterized in that: include: A feasible configuration solution set acquisition module is used to acquire a feasible configuration solution set of a ship capacity structure; A capacity structure optimization model building module is used to build a capacity structure optimization model, wherein the capacity structure optimization model includes optimization objectives, constraints and multi-objective optimization functions; An optimal configuration scheme determination module is used to perform multi-objective optimization on the feasible configuration scheme based on the capacity structure optimization model, and determine the optimal configuration scheme by iterative search in combination with the whale optimization algorithm; Among them, the optimization objectives include minimizing the capacity adjustment, maximizing the lock chamber utilization rate and minimizing the number of lock discharges.

Images