An intelligent navigation data processing system for combined fleets

Abstract

The present invention relates to the technical field of combined fleet navigation, and discloses an intelligent navigation data processing system for a combined fleet, comprising: a data acquisition unit, for collecting navigation data and lock data of each ship in the combined fleet in real time, fusing the pre-processed navigation data and lock data to obtain a comprehensive data set, and capturing the spatiotemporal characteristics of a velocity mutation zone when the lock is opened and closed in real time through dynamic data fusion and adaptive grid division, breaking through the limitation of traditional algorithms that rely on a static environment, generating a dynamic power distribution strategy based on flow field characteristics and navigation data, combining propeller efficiency priority with an adaptive weight algorithm, achieving precise power matching, shortening response time, improving collaborative efficiency, avoiding heading deviation, building a multi-level early warning and time difference judgment mechanism, evaluating power margin in real time, adjusting weights, speed and formation according to risk levels, ensuring that the power distribution adjustment of the entire fleet does not lag behind water flow changes, and ensuring the normal heading of the fleet.

Description

Technical Field

[0001] The present invention relates to the technical field of combined fleet navigation, and in particular to an intelligent navigation data processing system for a combined fleet. Background Art

[0002] At present, in inland waterway shipping, in order to meet the needs of shipping, combined fleets are usually used for shipping. When passing through a lock, multiple ships form a fleet to wait for the lock. Before entering the narrow lock chamber, due to the narrow lock and complex water flow, each ship dynamically adjusts its power according to its own load and resistance to ensure that the combined fleet passes through the lock smoothly.

[0003] When existing combined fleets pass through locks, a multi-objective particle swarm algorithm is used for power distribution, and multi-thruster collaborative control is achieved by integrating data such as ship load, thruster efficiency, and energy consumption. However, this algorithm relies on a static environment, such as a preset water velocity and a constant direction. The sudden turbulence generated during the opening and closing of the lock has strong nonlinear and unsteady characteristics, which leads to areas of sudden flow rate changes. The fleet often lags behind water flow changes when adjusting power distribution after data processing, which may eventually cause the fleet's course to deviate. Summary of the Invention

[0004] In view of the deficiencies in the prior art, the present invention provides a combined fleet intelligent navigation data processing system to solve the above problems.

[0005] The above technical objectives of the present invention are achieved through the following technical solutions:

[0006] A combined fleet intelligent navigation data processing system, comprising:

[0007] The data acquisition unit is used to collect the navigation data and lock data of each ship in the combined fleet in real time, and fuse the pre-processed navigation data and lock data to obtain a comprehensive data set;

[0008] The positioning unit is used to extract and analyze the features of the comprehensive data set, locate the position and range of the flow velocity mutation area when the lock is opened and closed, and generate a flow field characteristic parameter set;

[0009] The distribution unit is used to analyze the flow field characteristic parameter set and navigation data to generate power distribution instructions;

[0010] The determination unit is used to calculate the comprehensive data set to obtain the time difference between the power and the flow field, and determine whether to execute the power distribution instruction based on the time difference between the power and the flow field.

[0011] Furthermore, the pre-processed navigation data and lock data are fused to obtain a comprehensive dataset, including:

[0012] Analyze the pre-processed navigation data and lock data to obtain the correlation matrix;

[0013] Based on the correlation matrix, the pre-processed navigation data and lock data are fused to obtain the fused data set;

[0014] The fused dataset is processed for exceptions to obtain a comprehensive dataset.

[0015] Furthermore, feature extraction and analysis are performed on the comprehensive data set to locate the location and range of the flow velocity mutation zone when the ship lock is opened and closed, and a flow field characteristic parameter set is generated, including:

[0016] Separate the spatiotemporal fluctuation modes of the flow field from the comprehensive data set and generate the dynamic flow field feature vector;

[0017] Extract the velocity information of each spatial position and time point in the dynamic flow field feature vector, use the central difference method to calculate the velocity gradient modulus of each spatial point in the adjacent spatial and time steps, and set three gradient thresholds: high, medium, and low.

[0018] When the velocity gradient modulus High gradient threshold, which divides the flow field space into high-speed change areas. For the high-speed change areas, the grid spacing is reduced to half of the original spacing;

[0019] When the low gradient threshold Flow rate gradient modulus Medium gradient threshold, which divides the flow field space into medium-speed change areas, and the grid spacing is adjusted to three-quarters of the original spacing;

[0020] When the velocity gradient modulus Low gradient threshold, the flow field space is divided into low-speed change areas, and the grid spacing is increased to twice the original spacing for sparse processing;

[0021] The Delaunay triangulation algorithm is used to regenerate grid nodes based on the new grid division, determine the three-dimensional spatial coordinates of the grid nodes, and construct a grid association matrix by analyzing the connection relationship between nodes, recording the information of adjacent grid units, and finally obtaining a dynamic grid topology structure;

[0022] The dynamic grid topology structure is decomposed into a steady-state velocity field and a transient turbulence field, generating a steady-state velocity distribution matrix and a transient vortex intensity matrix respectively.

[0023] The vortex velocity of the transient vortex intensity matrix is ​​compared with the reference value of the steady-state velocity distribution matrix to generate a velocity mutation difference field. Specifically, the vortex velocity and the reference flow at each grid node are normalized, the square sum of the differences is calculated, and finally the square root is taken to obtain an overall measure of the normalized velocity difference at all nodes. The overall measure is divided by the number of grid divisions so that the overall difference is averaged to each grid, and the spatially averaged velocity difference parameter is obtained.

[0024] Normalize the time rate of change of the transient vortex velocity to obtain the ratio of the current velocity change rate to the maximum change rate. Then, divide the normalized ship length and the effective length of the lock to obtain the ratio of the ship length to the effective length of the lock. Multiply the ratio of the current velocity change rate to the maximum change rate by the ratio of the ship length to the effective length of the lock and add 1 to form a correction factor.

[0025] Multiply the spatially averaged velocity difference parameter by the correction factor to obtain the velocity mutation difference field.

[0026] Furthermore, feature extraction and analysis are performed on the comprehensive data set to locate the position and range of the flow velocity mutation area when the lock is opened and closed, and to generate a flow field characteristic parameter set, including:

[0027] Identify the boundary of the mutation area of ​​the velocity mutation difference field and obtain the velocity mutation boundary coordinate set;

[0028] The velocity gradient components of each grid node in the steady-state velocity distribution matrix in the horizontal, longitudinal and vertical directions are calculated by the central difference method. These three components are combined into a spatial gradient vector, and the amplitude of the vector is calculated to obtain the spatial gradient amplitude.

[0029] Extract the transient flow velocity data of each node at different times from the dynamic grid topology structure, and calculate the attenuation rate and attenuation multiple based on the transient flow velocity data;

[0030] The spatial gradient amplitude, attenuation rate and attenuation multiple are combined to generate a turbulence intensity gradient parameter set;

[0031] The velocity mutation boundary coordinate set and the turbulence intensity gradient parameter set are fused to generate the flow field characteristic parameter set.

[0032] Furthermore, the flow field characteristic parameter set and navigation data are analyzed to generate power distribution instructions, including:

[0033] The flow field characteristic parameter set is analyzed to obtain the peak velocity difference and turbulence influence gradient in the velocity mutation area. Specifically, the maximum value of the velocity gradient in the three directions in the space is extracted, and then multiplied by the ship's draft to obtain the maximum velocity gradient and draft. The value is then divided by the average steady-state velocity to obtain the velocity gradient-draft relative parameter.

[0034] Divide the ship's draft by the effective water depth of the lock to get the water depth ratio, then divide the lock opening and closing time by the fleet's lock processing time to get the time ratio. Multiply the two ratios and add 1 to get the lock-time correlation correction coefficient.

[0035] The difference between the peak velocity in the velocity mutation area and the current speed of the ship is divided by the maximum steady-state velocity and then added 1 to obtain the velocity difference-steady-state velocity correction coefficient;

[0036] The turbulence influence gradient is obtained by multiplying the velocity gradient-draft relative parameter, the lock-time correlation correction coefficient and the velocity difference-steady-state velocity correction coefficient;

[0037] Subtract the current speed of the ship from the peak speed in the velocity mutation area to obtain the peak speed difference;

[0038] Calculate the peak velocity difference and the ship's draft data to obtain the power increment;

[0039] The turbulence influence gradient is combined with the power increment and corrected to obtain a corrected power increment;

[0040] The current output power of the main engine and the corrected power increment are calculated to obtain the power margin coefficient. If the power margin coefficient is less than 1, the graded warning mechanism is triggered as follows: the basic power demand of the current operating conditions of each ship in the fleet is corrected, and then the sum is obtained to obtain the corrected total power demand of the fleet. The total power demand is subtracted from the current total output power of the main engine to obtain the difference between the current output power of the main engine and the corrected total power demand of the fleet. The difference between the current output power of the main engine and the corrected total power demand of the fleet is then divided by the rated reserve power of the main engine to obtain the power margin coefficient.

[0041] Furthermore, the flow field characteristic parameter set and navigation data are analyzed to generate power distribution instructions, which also includes:

[0042] Extract navigation data and generate a power allocation feasibility matrix;

[0043] The thrust efficiency coefficient and power demand increment of the power allocation feasibility matrix are fused according to weights, and the weighted summation algorithm is used to obtain the comprehensive efficiency value of each thruster. In a complex flow field, the thrusters are arranged from high to low according to the comprehensive efficiency value through a quick sorting algorithm, and the thruster efficiency priority is finally obtained.

[0044] The corrected power increment, power margin coefficient and power allocation feasibility matrix are integrated to generate a power allocation decision parameter set containing the comprehensive performance indicators of each thruster.

[0045] According to the propeller efficiency priority and power allocation decision parameter set, an adaptive weight algorithm is used to dynamically allocate the propeller power adjustment amount of each ship. The initial weight is allocated according to the ship propeller efficiency priority. Then, the weights of different ship propellers are quantitatively adjusted based on the flow field type and flow velocity classification. According to the adjusted weights, the total power adjustment amount is proportionally allocated to the propellers of each ship to generate power allocation instructions.

[0046] Furthermore, if the power margin coefficient 1, then trigger the graded warning mechanism, including:

[0047] When 0.8 Power margin factor At 1:00, the combined fleet is judged to be at a critical risk of residual power of the main engine, triggering a level 1 warning, and the yellow lights of the combined fleet flash;

[0048] When 0.5 Power margin factor At 0.8, the combined fleet was judged to be at risk of a shortage of main engine remaining power, triggering a Level 2 warning, with the orange lights of the combined fleet flashing;

[0049] When the power margin factor At 0.5, it was determined that there was a risk of serious insufficient remaining power of the main engine of the combined fleet, triggering a level 3 warning, and the red lights of the combined fleet flashed.

[0050] Furthermore, the integrated data set is calculated to obtain the time difference between the power and flow fields, and whether to execute the power distribution instruction is determined based on the time difference between the power and flow fields, including:

[0051] Extract flow field time parameters and dynamic time parameters of flow field changes from the comprehensive data set;

[0052] Calculate the difference between the flow field time parameter and the dynamic time parameter to obtain the dynamic and flow field time difference;

[0053] If the difference between the power and flow field time is ≤ 0, it means that the effective time of the power adjustment lags behind the time of the flow field change, and the power distribution instruction is determined not to be executed, and the forced trigger instruction is executed;

[0054] If the time difference between power and flow field is greater than 0, it means that the power adjustment can be completed and take effect before the sudden change of flow field affects the ship, and the power distribution instruction is determined to be executed.

[0055] Furthermore, the graded early warning mechanism also includes:

[0056] Level 1 warning: Based on the current flow field type, the current flow field type is divided into cross flow For both upstream and downstream vessels, based on the existing weight adjustment rules, the weight of high-efficiency thrusters for the top 50% of priority vessels will be increased by an additional 0.1, while the weight of low-efficiency thrusters for the bottom 50% of priority vessels will be reduced by the same amount.

[0057] Temporarily reduce target speed by 5%~10%;

[0058] During the Level 2 warning: temporarily increase the thrust efficiency coefficient weight to 0.7 and reduce the power demand increment weight to 0.3;

[0059] For the thrusters on the leeward side or in the auxiliary position, the weight limit is reduced to 0.2, and the weight of the thrusters on the upstream side or in the pilot ship is increased to 0.7-0.8, as follows:

[0060] In upstream or cross-current scenarios: the thruster weight of the main pusher vessel on the upstream side will be adjusted to the upper limit of the regulations, and the thruster weight of the auxiliary vessel on the downstream side will be reduced to a minimum of 0.05;

[0061] Downstream scenario: The thruster weight of the leading ship is reduced to below 0.3, while the thruster weight of the escort ships on both sides is increased to 0.35. The ship controls its course through side thrusters, reducing the power consumption of the main thruster.

[0062] The fleet changed to a "single column" formation, with the lead boat making a slight course adjustment of 5° to 10° to avoid the strong current and reduce the overall water resistance;

[0063] The speed is allowed to be temporarily lower than the target speed by 10% to 20%, with priority given to ensuring that the power system is not overloaded;

[0064] At level 3 warning: only the ship's thruster with the highest efficiency priority is enabled, and its weight is set to 1. The remaining thrusters are set to 0 to ensure weight conservation.

[0065] Immediately carry out a stop-and-go operation, shut down all non-essential loads, and keep only navigation and communication equipment running;

[0066] Send a distress signal to nearby ports or maritime authorities;

[0067] Among them, the third level warning Level 2 warning Level 1 warning: high-level warning measures automatically cover low-level warning measures.

[0068] Further, executing the forced trigger instruction includes:

[0069] An alarm is issued to remind the operator, allowing the operator to manually force the power adjustment in advance and enforce the power distribution instruction.

[0070] In summary, the present invention mainly has the following beneficial effects:

[0071] Through dynamic data fusion and adaptive grid division technology, a flow field analysis system that responds to sudden turbulence in real time was constructed. First, the navigation data and lock data were deeply integrated through the correlation matrix. After eliminating the interference of abnormal data, a comprehensive data set was formed to ensure the integrity and reliability of the input information. Then, the central difference method was used to calculate the velocity gradient in real time. The grid density was dynamically adjusted according to high, medium and low thresholds. The grid spacing in the velocity mutation area was refined to half of the original spacing. The low-speed change area was simultaneously sparsely processed. A dynamic grid topology structure was constructed through Delaunay triangulation, which effectively separated the steady-state velocity field and the transient turbulence field. A flow field characteristic parameter set containing the mutation boundary coordinates and turbulence attenuation characteristics was generated, and the spatiotemporal range of the velocity mutation during the opening and closing of the lock was accurately located. This mechanism breaks through the static environment assumption and can capture sudden turbulence with a large velocity gradient change rate in real time, providing high-precision flow field dynamic parameters for power distribution, fundamentally solving the adaptation lag problem of traditional algorithms for unsteady flow fields.

[0072] By analyzing the peak velocity difference and turbulence influence gradient in the velocity mutation zone and combining it with ship draft data to calculate the basic power increment, the turbulence influence gradient is then used to perform weight correction to ensure that the power adjustment amount is accurately matched to the flow field disturbance intensity. A power allocation feasibility matrix is ​​used to integrate key parameters such as the propeller efficiency coefficient and the power demand increment. The propeller efficiency priority is generated through a weighted summation algorithm. In countercurrent scenarios, the weight of the main pusher ship's propeller is increased, while the power consumption of the inefficient propeller of the auxiliary ship on the downstream side is suppressed. The power adjustment amount is dynamically allocated based on an adaptive weight algorithm. The initial weight is set according to the efficiency priority, and then secondary adjustments are made based on the flow field type (crosscurrent, downstream, and upstream). For example, in the downstream scenario, the weight of the front ship's propeller is reduced, while that of the escort ships on both sides is increased. This achieves the optimal propulsion power ratio, shortens the overall power allocation response time of the fleet, improves the coordinated efficiency of the propellers, and effectively avoids the risk of fleet heading deviation caused by power allocation lag.

[0073] Through precise calculation of the time difference between power and flow, and a graded early warning strategy, a full-process assurance system has been established, covering risk warning, dynamic adjustment, and emergency response. By extracting the time parameters of flow field changes and power response time parameters in real time, a power adjustment lag is determined when the time difference is ≤ 0, triggering a mandatory manual intervention mechanism. This mechanism prompts the operator to intervene in advance through audible and visual alarms, ensuring that power configuration is completed before sudden flow changes affect the ship. To address the issue of insufficient power margin, a three-level gradient early warning mechanism has been designed. At the first level, thruster weights are dynamically adjusted and the target speed is moderately reduced, reserving some power margin. At the second level, weights are redistributed, and the fleet formation is shifted to a "single file" formation with better current resistance, adjusting its course to reduce water resistance. At the third level, single-point control of the most efficient thrusters is activated, non-essential loads are simultaneously shut down, and a distress signal is transmitted. This creates a closed-loop control system from risk warning to emergency response, reducing the risk of power system overload and controlling the fleet's course deviation under sudden strong turbulence conditions, significantly improving the safety and reliability of the combined fleet's passage through the locks. BRIEF DESCRIPTION OF THE DRAWINGS

[0074] Figure 1 This is a block diagram of a combined fleet intelligent navigation data processing system of the present invention. DETAILED DESCRIPTION

[0075] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. 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 making creative efforts are within the scope of protection of the present invention.

[0076] refer to Figure 1 , a combined fleet intelligent navigation data processing system, comprising:

[0077] The data acquisition unit is used to collect the navigation data and lock data of each ship in the combined fleet in real time, and fuse the pre-processed navigation data and lock data to obtain a comprehensive data set;

[0078] The positioning unit is used to extract and analyze the features of the comprehensive data set, locate the position and range of the flow velocity mutation area when the lock is opened and closed, and generate a flow field characteristic parameter set;

[0079] The distribution unit is used to analyze the flow field characteristic parameter set and navigation data to generate power distribution instructions;

[0080] The determination unit is used to calculate the comprehensive data set to obtain the time difference between the power and the flow field, and determine whether to execute the power distribution instruction based on the time difference between the power and the flow field.

[0081] Real-time data integration is achieved through the data acquisition unit, overcoming the data integration lag problem in existing technologies and providing an accurate and comprehensive data basis for subsequent processing. The positioning unit accurately identifies the flow velocity mutation zone, effectively responds to the complex flow field changes when the lock is opened and closed, and avoids the fleet's heading deviation caused by sudden turbulence; the distribution unit generates adaptive power distribution instructions based on the flow field characteristics and navigation data, and the judgment unit ensures the timeliness of power adjustment through time difference verification, significantly improving the navigation stability and safety of the fleet in the dynamic flow field. In addition, this system breaks through the limitations of traditional static algorithms and constructs a closed-loop control system of precise perception-intelligent decision-making-dynamic regulation, which greatly enhances the reliability and efficiency of the combined fleet's lock-passing operation and can realize the collaborative operation of ships in complex water flow environments.

[0082] In one case of this embodiment, the pre-processed navigation data and the lock data are fused to obtain a comprehensive data set, including:

[0083] Navigation data includes: ship position data, speed data, heading data, ship attitude data, ship draft data, main engine power data and propeller speed data;

[0084] Ship lock data include: ship lock water level data, ship lock flow velocity data, gate opening and closing time data, ship lock flow field characteristic time data, ship lock structural parameter data and ship lock water flow sediment content data;

[0085] The pre-processed navigation data and lock data were analyzed to obtain a correlation matrix. Specifically, the pre-processed navigation data and lock data were aligned by time stamp to construct a unified data set. The Pearson correlation coefficient algorithm was used to calculate the correlation coefficients between the variables of the navigation data (ship position, speed) and the variables of the lock data (lock water level, flow rate). These coefficients were arranged in rows and columns according to the corresponding variables, and the diagonal elements were set to 1 to form a correlation matrix.

[0086] Based on the correlation matrix, the pre-processed navigation data and lock data are fused to obtain a fused data set, which specifically includes: carrying out the fusion work according to the Pearson correlation coefficient in the correlation matrix, setting the threshold value of 0.7 for the correlation coefficient between the navigation data variable and the lock data variable in the correlation matrix, and if the absolute value of the correlation coefficient is greater than or equal to the threshold, it means that the two variables are highly correlated. At this time, the weighted average method is used to fuse the data, using the correlation coefficient as the weight, and calculating the weighted average value as the fused data value. If the absolute value of the correlation coefficient is less than the threshold, it indicates that the correlation is weak. The original data of the two variables are retained separately without fusion processing, and the data of all variables are integrated in chronological order. The processed and retained data are arranged in order to form a fused data set that contains both navigation data features and lock data features.

[0087] The fused data set is processed for anomalies to obtain a comprehensive data set, specifically including: using the box plot method to process the fused data set, first calculating the first quartile (lower quartile) and third quartile (upper quartile) of each variable data, determining the distribution interval of the middle 50% range of the data, and then calculating the reasonable range boundary of the data fluctuation through the distribution interval, and determining the data below the lower boundary or above the upper boundary as an outlier. For anomalies, if the sample size of the data set is 30, then directly exclude, if the sample size 30, the median of the same variable data is used to replace and correct the outliers, and finally the cleaned comprehensive data set is obtained.

[0088] By carefully dividing and classifying various navigation data, such as ship position and speed, and lock data, such as lock water level and flow rate, the comprehensiveness and accuracy of the original data were ensured. After preprocessing, the Pearson correlation coefficient algorithm was used to construct a correlation matrix, quantifying the correlation between each variable between navigation data and lock data, providing an objective basis for subsequent fusion. Based on the correlation matrix, reasonable thresholds were set, and a weighted average method was used to fuse strongly correlated variables, fully considering the importance and relevance of each variable. The fused data set retained the characteristics of both navigation data and lock data, effectively integrating multi-source information, providing high-quality, comprehensive data support for subsequent operations such as power allocation, and greatly enhancing the intelligent decision-making basis for combined fleet lock operations.

[0089] By using the boxplot method to handle anomalies in the fused dataset, the reasonable range boundaries are determined based on the data quartiles, and outliers are accurately identified. For anomalies of different sample sizes, a strategy of elimination or correction with median replacement is adopted, fully considering the impact of data sample size on the anomaly handling effect. This can not only effectively remove noise data, but also avoid data information loss due to too small a sample size. The final comprehensive dataset is highly accurate and reliable, which provides a solid guarantee for subsequent feature extraction and analysis of the comprehensive dataset, as well as the generation and determination of power distribution instructions. It ensures that the combined fleet can make intelligent navigation decisions based on accurate and reliable data in complex lock environments, effectively reducing navigation risks caused by data anomalies and improving the safety and stability of the fleet passing through the locks.

[0090] In one case of this embodiment, feature extraction and analysis are performed on the comprehensive data set to locate the position and range of the flow velocity mutation area when the ship lock is opened and closed, and generate a flow field feature parameter set, including:

[0091] Separate the spatiotemporal fluctuation modes of the flow field from the comprehensive data set and generate a dynamic flow field eigenvector. This includes: extracting flow field-related data (ship lock flow velocity, water level) from the comprehensive data set, constructing a spatiotemporal matrix with spatial positions as rows and time points as columns, and performing singular value decomposition on the spatiotemporal matrix to obtain three matrices: the left singular matrix represents the spatial mode, the right singular matrix represents the temporal mode, and the singular value matrix represents the energy contribution of each mode. These are sorted by singular value size, and the top 10 modes with the highest energy contribution are selected as the main spatiotemporal fluctuation modes. The vectors of these modes are extracted from the corresponding matrices and combined into a dynamic flow field eigenvector.

[0092] Extract the velocity information of each spatial position and time point in the dynamic flow field feature vector, use the central difference method to calculate the velocity gradient modulus of each spatial point in the adjacent spatial and time steps, and set three gradient thresholds: high, medium, and low.

[0093] When the velocity gradient modulus High gradient threshold, which divides the flow field space into high-speed change areas. For the high-speed change areas, the grid spacing is reduced to half of the original spacing;

[0094] When the low gradient threshold Flow rate gradient modulus Medium gradient threshold, which divides the flow field space into medium-speed change areas, and the grid spacing is adjusted to three-quarters of the original spacing;

[0095] When the velocity gradient modulus Low gradient threshold, the flow field space is divided into low-speed change areas, and the grid spacing is increased to twice the original spacing for sparse processing;

[0096] Based on the initial mesh division, the three-dimensional spatial coordinates of the existing mesh nodes are clarified. The mesh nodes are regenerated according to the new mesh division through the Delaunay triangulation algorithm, and the coordinate positions of these new nodes in three-dimensional space are determined. On this basis, the connection relationship between the old and new nodes is analyzed, and the adjacent situation of each node is clarified. Based on the clear node connection relationship, a mesh association matrix is ​​constructed. This matrix accurately records the connection status of each node with other nodes. If adjacent, it is marked as 1, otherwise it is 0. It also comprehensively records the information of adjacent mesh units, covering the faces, edges and nodes shared between units. Finally, all node coordinates, connection relationships and unit adjacent information are integrated to construct a dynamic mesh topology structure that can dynamically reflect mesh changes.

[0097] The dynamic grid topology structure is decomposed into a steady-state velocity field and a transient turbulence field, and a steady-state velocity distribution matrix and a transient vortex intensity matrix are generated respectively. Specifically, the method includes: obtaining the velocity data of each node at different times from the dynamic grid topology structure;

[0098] For the steady-state velocity field, the average velocity of each grid node in the entire time period is calculated by the time averaging method. These average velocity values ​​are used as matrix elements to construct the steady-state velocity distribution matrix, in which each element represents the reference velocity value of the corresponding grid node.

[0099] For the transient turbulent flow field, the transient component is obtained by subtracting the corresponding reference flow velocity from the node flow velocity at each moment. The vorticity tensor is calculated based on the transient component. The vorticity tensor is analyzed using the Q criterion to identify the vortex core area and obtain the core position coordinates of the vortex core area. For each identified vortex core area, the vortex modulus is calculated based on the vortex tensor, and the vortex modulus is used as the rotation intensity of the vortex. The vortex core areas are clustered using the DBSCAN clustering algorithm, and the vortex cores that are spatially close are classified into one category to obtain the clustering results. Combined with the time series correlation, the clustering results at different moments are analyzed to track the entire process of each vortex from its generation to its extinction, determine its life cycle, and organize the core position coordinates, rotation intensity and life cycle of the vortex into a matrix form to generate a transient vortex intensity matrix.

[0100] The vortex velocity of the transient vortex intensity matrix is ​​compared with the reference value of the steady-state velocity distribution matrix to generate the velocity mutation difference field. The specific calculation formula is as follows:

[0101] ;

[0102] Where, represents the velocity mutation difference field, and Respectively represent the number of grid divisions in the horizontal and vertical directions, represents the first Rank The vortex velocity at the column grid nodes, represents the maximum value of the vortex velocity, represents the reference flow velocity of the corresponding grid node in the steady-state flow velocity distribution matrix, Indicates the maximum value of the reference flow rate, Indicates the time rate of change of the transient vortex velocity, which is used to reflect the speed of flow velocity change. Indicates the maximum value of the time rate of change, Indicates the length of the ship, Indicates the effective length of the lock, Indicates the length reference, and and The dimensions are consistent;

[0103] Through decomposition based on the space-time matrix, the main fluctuation modes with high energy proportion can be separated from the complex ship lock flow velocity and water level data, effectively filtering out noise and retaining key dynamic characteristics. The flow gradient modulus is calculated by combining the central difference method, and the grid spacing is dynamically adjusted according to the gradient threshold, so that the grid density in high-speed change areas (such as the strong shear flow area when the ship lock is opened and closed) is automatically encrypted, while the low-speed change area is sparsely processed. This significantly improves the computational efficiency while ensuring the calculation accuracy. Through adaptive grid division, it avoids the computational redundancy caused by the global dense grid and prevents the loss of key details caused by the sparse grid. It is particularly suitable for strong non-uniform flow scenarios caused by sudden changes in boundary conditions in the flow field near the ship lock. In addition, the dynamic grid topology structure constructed based on Delaunay triangulation can accurately record the node connection relationship and unit adjacent information, providing a solid data foundation for flow field analysis and ensuring the accuracy and reliability of locating the flow velocity mutation area.

[0104] By constructing a steady-state velocity distribution matrix using the time averaging method, the baseline flow state of the flow field can be clearly presented, providing a stable reference framework for identifying abnormal flows. By analyzing transient vortices, accurate identification, intensity quantification, and life cycle tracking of the vortex core area are achieved, effectively capturing the complex vortex motion caused by sudden changes in velocity during the opening and closing of the lock (such as shear vortices near the gate, vortices in the recirculation zone, etc.). The velocity mutation difference field generated by comparing the vortex velocity with the steady-state baseline value is introduced into parameters such as ship length and effective length of the lock, closely integrating the flow field analysis with actual navigation needs. This difference field can not only locate the spatial position of the velocity mutation (such as the high-gradient area upstream and downstream of the gate), but also provide an analytical basis for safety assessment of ships passing through the lock and optimization of lock scheduling strategies by quantifying the coupling effect of the time rate of velocity change and the characteristic length, thereby facilitating dynamic adjustment of lock operating parameters.

[0105] In one case of this embodiment, feature extraction and analysis are performed on the comprehensive data set to locate the position and range of the flow velocity mutation area when the ship lock is opened and closed, and a flow field feature parameter set is generated, which also includes:

[0106] The boundary of the mutation area of ​​the velocity mutation difference field is identified to obtain the velocity mutation boundary coordinate set, which specifically includes: firstly, the Sobel operator is used to perform edge detection on the velocity mutation difference field, and the gradient size (reflecting the mutation magnitude) and gradient direction (reflecting the mutation direction) of each point are obtained by calculating the velocity change rate in the horizontal and vertical directions of each grid point. Then, the gradient size matrix is ​​adaptively threshold segmented by the Otsu algorithm. By analyzing the grayscale distribution of the data histogram, a threshold is set, and the area with a gradient value higher than the threshold is marked as the velocity mutation candidate area, and the stable area with a low gradient is excluded. For the marked velocity mutation candidate area, the MarchingSquares algorithm is used to extract the boundary contour, and the grid cells are scanned row by row and column by column to detect the transition point on the cell edge where the gradient value changes from higher than the threshold to lower than the threshold. By linear interpolation, the precise coordinates of the boundary point can be calculated based on the coordinates of the two end points of the edge. The gradient size and gradient direction of the point previously calculated by the Sobel operator are integrated with the newly calculated coordinates and recorded in sequence, thereby forming a velocity mutation boundary coordinate set containing coordinates, mutation magnitude and direction.

[0107] The velocity gradient components of each grid node in the steady-state velocity distribution matrix in the horizontal, longitudinal and vertical directions are calculated by the central difference method. These three components are combined into a spatial gradient vector. The velocity gradient components in the three directions are then squared and added together. The square root of the sum is taken. The resulting scalar value is the spatial gradient amplitude.

[0108] The transient velocity data of each node at different times are extracted from the dynamic grid topology. The pulsating velocity is obtained by subtracting the baseline velocity (steady-state average velocity) of the corresponding node from the transient velocity. The root mean square value of the pulsating velocity at each time is taken to generate a turbulence intensity sequence for each node that varies with time. For the turbulence intensity sequence, the sliding window difference method is used to calculate the decay rate of adjacent time steps (i.e., the difference between the turbulence intensity at the next moment and the previous moment divided by the time interval). The overall trend of the sequence is fitted using the least squares method, and the slope of the fitted line is extracted as the overall decay rate of the turbulence intensity at that node. At the same time, the ratio of the initial value to the final value of the sequence is calculated as the decay multiple to quantify the decay amplitude of the turbulence intensity over time.

[0109] In the integration phase, the spatial coordinates of each grid node ( ) is used as the positioning reference, and the spatial gradient amplitude (reflecting the spatial variation characteristics of the velocity), attenuation rate (reflecting the time attenuation speed) and attenuation multiple (reflecting the time attenuation amplitude) of the node are used as characteristic attributes. They are organized in a matrix form of "one row, one node, one column, one parameter", and finally a turbulence intensity gradient parameter set containing node location information, velocity spatial gradient characteristics and turbulence time attenuation characteristics is generated;

[0110] The velocity mutation boundary coordinate set and the turbulence intensity gradient parameter set are fused to generate a flow field characteristic parameter set, specifically including: based on the boundary point coordinates of the velocity mutation boundary coordinate set, the coordinates of the boundary points are extracted and an array is constructed; according to the spatial distribution of the boundary point coordinates, the spatial gradient amplitude, attenuation rate and attenuation multiple of each grid node in the turbulence intensity gradient parameter set are interpolated to obtain the turbulence intensity parameter value at the corresponding position of the boundary point; the spatial coordinates, mutation magnitude and mutation direction of the boundary point are integrated with the turbulence intensity parameters obtained by interpolation; with the boundary point as the spatial positioning reference, the mutation magnitude, mutation direction, spatial gradient amplitude, attenuation rate and attenuation multiple of the point are arranged in sequence to generate a flow field characteristic parameter set including node position information, velocity spatial gradient characteristics and turbulence time attenuation characteristics.

[0111] The Sobel operator is used to detect the edge of the velocity mutation difference field, and the gradient size and direction of each grid point are accurately calculated. The Otsu algorithm is then used for adaptive threshold segmentation to effectively distinguish between velocity mutation and stable areas. Finally, the MarchingSquares algorithm is used to extract the boundary contour and accurately calculate the coordinates of the boundary points to form a velocity mutation boundary coordinate set containing coordinates, mutation magnitude and direction. At the same time, the central difference method is used to calculate the spatial gradient of the steady-state velocity distribution matrix. The sliding window difference method and the least squares method are combined to calculate the attenuation rate and attenuation multiple of the turbulence intensity, generating a comprehensive turbulence intensity gradient parameter set, realizing the refined extraction of flow field characteristics, and providing a high-precision data basis for the subsequent generation of flow field characteristic parameter sets. It also improves the combined fleet's ability to perceive potential risk areas in complex lock environments, helps to formulate more accurate navigation strategies, and ensures the fleet's safe passage through the locks.

[0112] By deeply integrating the velocity mutation boundary coordinate set and the turbulence intensity gradient parameter set, a comprehensive flow field characteristic parameter set is generated. Based on the boundary point coordinates, the turbulence intensity gradient parameters are interpolated and calculated. The spatial coordinates, mutation magnitude, mutation direction and turbulence intensity parameters of the boundary points are integrated to form a complete parameter set including node position information, velocity spatial gradient characteristics and turbulence time attenuation characteristics. This fully integrates the spatiotemporal characteristics of the flow field and realizes the organization of multi-dimensional flow field information, providing richer and more accurate flow field characteristic data for ship power distribution and navigation decision-making. Based on this flow field characteristic parameter set, ships can more accurately predict flow field changes, adjust power distribution and navigation attitude in advance, effectively respond to velocity mutations during lock opening and closing, reduce navigation risks, and improve the passage efficiency and safety of the combined fleet in complex lock environments.

[0113] In one case of this embodiment, analyzing the flow field characteristic parameter set and the navigation data to generate a power distribution instruction includes:

[0114] The flow field characteristic parameter set is analyzed to obtain the peak velocity difference and turbulence influence gradient in the velocity mutation area. The specific calculation formula is as follows:

[0115] ;

[0116] Where, Indicates the turbulence gradient, which is used to indicate the rate of change of flow velocity from the edge to the center of the velocity mutation zone. 、 and Represent the velocity gradients in three directions of space, represents the average value of the steady-state flow velocity, Indicates the ship's draft. Indicates the effective water depth of the lock. Indicates the lock opening and closing time, Indicates the fleet lock processing time, Indicates the peak flow velocity in the flow velocity mutation area, Indicates the current speed of the ship. Indicates the maximum value of steady-state flow rate;

[0117] ;

[0118] Where, represents the peak velocity difference;

[0119] The peak velocity difference and the ship draft data are calculated to obtain the power increment. The specific calculation formula is as follows:

[0120] ;

[0121] Where, Indicates the power increment, Indicates the resistance coefficient related to the ship shape and fluid properties. It means that the effect of draft on power increment increases in a quadratic relationship;

[0122] The turbulence effect gradient is combined with the power increment and corrected to obtain the corrected power increment. The specific calculation method is as follows:

[0123] ;

[0124] Where, represents the corrected power increment, where the power increment has no dimension. Expressed as the modified weight coefficient;

[0125] Calculate the current output power of the main engine and the corrected power increment to obtain the power margin coefficient. If the power margin coefficient is less than 1, the graded warning mechanism is triggered. The specific calculation formula is as follows:

[0126] ;

[0127] Where, Indicates the power margin coefficient, which is used to measure the matching degree between the host's current output power and the required power increment. Indicates the current total output power of the host. represents the number of ships in the fleet, Indicates the The basic power requirements of a ship under current working conditions, Indicates the rated reserve power of the host.

[0128] Through precise analysis of the flow field characteristic parameter set, the peak velocity difference and turbulence influence gradient in the velocity mutation zone are obtained. The calculation formula fully considers multi-dimensional parameters such as ship draft, effective water depth of lock, lock opening and closing time, and fleet lock processing time, ensuring the accuracy and adaptability of the calculation results. At the same time, the power increment is accurately calculated based on the ship draft data, and a correction weight coefficient is introduced to organically combine the turbulence influence gradient with the power increment to obtain the corrected power increment, further improving the scientificity and rationality of the power allocation decision. Finally, by calculating the power margin coefficient and triggering the graded warning mechanism when the power margin coefficient is less than 1, the fleet is provided with real-time and accurate power adjustment basis and risk warning, effectively ensuring the fleet's navigation safety and stability in complex flow field environments.

[0129] By generating power distribution, in this process, the flow field characteristic parameter set and navigation data are deeply integrated, and the risk degree faced by ships in the velocity mutation area is quantified. The calculated peak velocity difference intuitively reflects the difference between the ship speed and the peak velocity in the velocity mutation area, providing a key basis for power adjustment. The corrected power increment fully considers the dynamic changes of the turbulence influence gradient on the ship's navigation resistance, ensuring that the power distribution not only meets the current navigation needs but also has a certain safety redundancy. The calculation of the power margin coefficient and the triggering of the graded early warning mechanism enable the fleet to predict the risk of insufficient power in advance and take timely response measures to avoid accidents such as heading deviation or collision due to insufficient power, which significantly improves the power management efficiency and navigation safety assurance level of the combined fleet in complex lock environments.

[0130] In one case of this embodiment, analyzing the flow field characteristic parameter set and the navigation data to generate the power distribution instruction further includes:

[0131] Extract navigation data and generate a power allocation feasibility matrix (efficiency parameters of different propellers under current flow field conditions). Specifically, the following steps are performed: The ship's current speed, target speed, propeller rotation speed, water velocity, and flow field characteristic parameter set are integrated through a data fusion algorithm. The theoretical thrust of each propeller is compared with the actual thrust to calculate the thrust efficiency coefficient. The power demand increment of each propeller is then calculated based on the ship's draft and the velocity distribution in the flow field. The thrust efficiency coefficients and power demand increments of each propeller are then organized into a matrix, namely the power allocation feasibility matrix, in which each element represents the efficiency performance of a propeller under current flow field conditions.

[0132] The thrust efficiency coefficient and power demand increment of the power allocation feasibility matrix are fused according to weights, and the weighted summation algorithm is used to obtain the comprehensive efficiency value of each thruster. In complex flow fields, the thrust efficiency coefficient weight can be set to 0.6, and the power demand increment weight can be set to 0.4. The thrusters are then sorted from high to low according to the comprehensive efficiency value using a quick sorting algorithm to finally obtain the thruster efficiency priority.

[0133] The corrected power increment, power margin coefficient, and power allocation feasibility matrix are fused to generate a power allocation decision parameter set containing the comprehensive performance indicators of each propeller. Specifically, the thrust efficiency coefficient, power demand increment, corrected power increment, and power margin coefficient of each propeller are weighted and fused, where the thrust efficiency weight coefficient is 0.3, the power demand increment weight coefficient is 0.2, the corrected power increment weight coefficient is 0.4, and the power margin coefficient weight coefficient is 0.1. A weighted summation algorithm is used to calculate the comprehensive performance indicators of each propeller, and the comprehensive performance indicators of all propellers are organized into a parameter set, namely the power allocation decision parameter set.

[0134] Based on the propeller efficiency priority and the power allocation decision parameter set, an adaptive weighting algorithm is used to dynamically allocate the propeller power adjustment amount of each ship. The initial weight is assigned according to the ship propeller efficiency priority. Then, the weights of different ship propellers are quantitatively adjusted based on the flow field type and flow velocity classification. Based on the adjusted weights, the total power adjustment amount is proportionally allocated to each ship's propeller to generate a power allocation instruction.

[0135] The initial weights are assigned based on the ship propulsion efficiency priority, as follows:

[0136] Ship formation: weights decrease in an arithmetic progression, ensuring that the sum of all weights is 1, for example:

[0137] 2-ship formation: The initial weight of the ship with the highest efficiency priority is set to 0.6, and the weight of the ship with the second highest efficiency priority is set to 0.4;

[0138] 3-ship formation: The thruster weights of the ship with the highest efficiency priority are 0.5, 0.3, and 0.2 from high to low;

[0139] The weights of different ship propulsion systems are quantitatively adjusted based on the flow field type and flow velocity classification, as follows:

[0140] When in a cross-current with a complex flow field (perpendicular to the fleet's heading):

[0141] In low-speed cross flow (flow rate of 1m s-3m s), the cross current has a relatively small impact on the ship's heading stability. At this time, the thruster weight of the ship on the upstream side (the ship in the direction of the cross current of the fleet) is increased by 0.1, and the thruster weight of the ship on the downstream side (the ship in the opposite direction of the cross current) is reduced by 0.1 (the reduction is evenly distributed);

[0142] Because although there is a cross flow, the flow rate is not high, the ship's own power system can easily overcome the impact of the cross flow. A small adjustment of the weight can ensure the ship's heading stability and avoid resource waste;

[0143] For example, a freight fleet consisting of 1 main cargo ship and 2 auxiliary cargo ships in a certain sea area encountered a 2m In a transverse current of s, the main cargo ship was located on the upstream side of the formation. The initial thruster weight was 0.5, but after adjustment, the thruster weight became 0.6. The two auxiliary cargo ships were located on the downstream side. The thruster weights were reduced from 0.3 and 0.2 to 0.25 and 0.15, respectively. The total weight after adjustment was 0.6 + 0.25 + 0.15 = 1. Through this adjustment, the fleet maintained a stable course with minimal power consumption and successfully completed the cargo transportation mission.

[0144] In high-speed cross flow (flow rate of 3m s-5m s), the cross current will have a significant impact on the ship's heading stability. At this time, the thruster weight of the ship on the upstream side needs to be increased by 0.3, and the thruster weight of the ship on the downstream side needs to be reduced by 0.3 (the reduction is evenly distributed);

[0145] Because high-speed cross-currents can produce significant lateral torques on the fleet, causing it to have a greater tendency to deflect, by significantly increasing the thruster weight of the ships on the upstream side, the ships on the upstream side can generate sufficient thrust to overcome the cross-current resistance and maintain the fleet's course. At the same time, appropriately reducing the thruster weight of the ships on the downstream side can prevent the fleet from deflecting excessively to the downstream side, ensuring stable navigation of the fleet.

[0146] For example, in a certain sea area, a fleet of three ships consisting of a large cargo ship and two small escort cargo ships encountered a 4m In a crosscurrent of s, the large freight ship is located on the upstream side, and the initial thruster weight is 0.6, which is increased to 0.9 after adjustment. The two small escort freight ships are located on the downstream side, and the thruster weights are reduced from 0.2 and 0.2 to 0.05 and 0.05 respectively. The total weight after adjustment is 0.9+0.05+0.05=1. By greatly enhancing the thrust of the freight ship on the upstream side and reducing the power output of the escort freight ship on the downstream side, the fleet was successfully prevented from being deflected by the crosscurrent.

[0147] When in a complex upstream flow (opposite to the fleet's course):

[0148] When the countercurrent flow rate is slow (the flow rate is 1m s-2m s), the impact on ship navigation is relatively limited, then the thruster weight of the front pilot ship (the first ship in the direction of the current) is increased by 0.1, and the thruster weight of the rear auxiliary ship is reduced by 0.1 (the reduction is evenly distributed);

[0149] Because the impact of a gentle countercurrent on the fleet's navigation is relatively limited, increasing the thruster weight of the front pilot ship can enhance its main propulsion power, making it easier for it to overcome the resistance of the gentle countercurrent. The thruster weight of the rear auxiliary ship can be appropriately reduced in power, which can not only help the pilot ship maintain the formation, but also balance the energy consumption of the entire fleet and achieve efficient energy utilization.

[0150] For example, a cargo fleet consisting of 1 pilot ship and 2 auxiliary ships can move at a speed of 1.5m in a river. When sailing upstream at s, the initial thruster weight of the pilot ship is 0.5, which is adjusted to 0.6; the initial thruster weights of the two auxiliary ships are both 0.25, which are reduced to 0.2 after adjustment. The total weight after adjustment is 0.6+0.2+0.2=1. After the adjustment, the pilot ship increases its power to smoothly propel the fleet forward, while the auxiliary ships reduce their power to reduce energy consumption. The entire fleet completes cargo transportation with lower fuel consumption;

[0151] When the countercurrent flow rate is faster (the flow rate is 2m s-4m s), it will significantly hinder the ship's progress. At this time, the thruster weight of the front pilot ship increases by 0.2, and the thruster weight of the rear auxiliary ship decreases by 0.1 each;

[0152] Because strong countercurrents can significantly hinder the fleet's progress, the front-row pilot ship needs to provide greater thrust to overcome the strong countercurrent resistance and ensure that the fleet's actual speed is close to the target speed. Although the rear-row auxiliary ships can help the fleet maintain a stable course to a certain extent, reducing their power consumption can optimize the overall power distribution, achieving efficient navigation while ensuring navigation.

[0153] For example, in a certain section of the channel, a 3-ship formation consisting of a high-power main cargo ship and two medium-sized auxiliary cargo ships encountered a 3m In the face of a strong countercurrent of s, the main cargo ship, as the pilot ship, had an initial thruster weight of 0.6, which was increased to 0.8 after adjustment. The initial thruster weights of the two auxiliary cargo ships were 0.2 and 0.2 respectively, and the adjusted weights became 0.1 and 0.1. The total weight after adjustment was 0.8+0.1+0.1=1. By enhancing the power of the main cargo ship and reasonably reducing the power of the auxiliary cargo ships, the fleet successfully maintained its speed, avoided being stranded in dangerous waters due to the slow countercurrent speed, and completed the cargo transportation on time.

[0154] When in a complex downstream flow (same heading as the fleet):

[0155] When the downstream flow rate is faster (the flow rate is 3m s-5m s), the ship is likely to go too fast due to the downstream, making it difficult to accurately control the course. At this time, the thruster weight of the front ship in the downstream direction is reduced by 0.2, and the thruster weight of the escort ships on both sides is increased by 0.1 each (the total adjustment is balanced);

[0156] Because when the downstream speed is fast, the fleet is prone to excessive speed due to the downstream, making it difficult to accurately control the course. Reducing the weight of the front ship in the downstream direction can prevent the fleet from losing control due to excessive acceleration. At the same time, increasing the weight of the escort ships on both sides can help the fleet adjust the course when necessary to ensure navigation safety.

[0157] For example, a three-ship freight formation consisting of a pusher ship and two escort ships can When transporting large cargo downstream at s, the leading ship is positioned downstream, with its initial thruster weight of 0.6 reduced to 0.4 after adjustment. The initial thruster weights of the two escorting ships are both 0.2, but increased to 0.3 after adjustment. The total weight after adjustment is 0.4 + 0.3 + 0.3 = 1. By reducing the power of the leading ship and enhancing the control capabilities of the escorting ships on both sides, the formation effectively avoids the risk of loss of control due to excessive downstream acceleration, and safely delivers the cargo to its destination.

[0158] The above quantitative weight adjustment needs to meet the following constraints:

[0159] 1. The principle of weight conservation is as follows:

[0160] During each adjustment, the total increase or decrease in thruster weights of all ships in the fleet is strictly balanced to ensure that the sum of all weights is always 1 and the total power distribution base remains unchanged;

[0161] 2. The weight boundaries of a single ship are as follows:

[0162] After adjustment, the thruster weight of a single ship must meet 0 Weight 1;

[0163] For example, if the initial weight of a ship's thruster is 0.2 and needs to be reduced by 0.3, the actual reduction is 0.2 (the final weight is 0);

[0164] For example, if the initial weight of a ship's thruster is 0.9 and needs to be increased by 0.2, the actual increase is 0.1 (the final weight is 1).

[0165] Through in-depth extraction and analysis of navigation data, an accurate power distribution feasibility matrix is ​​generated, which comprehensively reflects the efficiency performance of different propellers under current flow field conditions. The matrix is ​​based on the weighted fusion of thrust efficiency coefficient and power demand increment, combined with a quick sorting algorithm to derive the propeller efficiency priority, providing a scientific basis for subsequent power distribution. The corrected power increment, power margin coefficient and power distribution feasibility matrix are weighted and fused to generate a power distribution decision parameter set containing the comprehensive performance indicators of each propeller. This process fully considers the actual working status and flow field characteristics of each propeller, and realizes the refined management of power distribution. Based on the propeller efficiency priority and power distribution decision parameter set, the power adjustment amount of each propeller is dynamically allocated through an adaptive weight algorithm to generate accurate power distribution instructions, ensuring that the fleet can respond to flow velocity changes with the optimal power configuration in complex flow fields, thereby ensuring navigation safety and efficiency.

[0166] By quantitatively adjusting the propulsion weights of ships according to different flow field types and velocity classifications, and adhering to the principle of weight conservation and the boundary constraints of individual ship weights, the system ensures that the total power distribution base remains unchanged and that the individual ship weights are always within a reasonable range. Under complex flow conditions such as crosscurrent, countercurrent, and downstream, the system can precisely adjust the propulsion weights of ships in different positions, such as the upstream side, downstream side, front pilot ship, and rear auxiliary ship, based on the specific flow velocity and direction, to achieve effective power distribution. For example, in low-speed crosscurrent, small adjustments to the propulsion weights of ships on the upstream and downstream sides can ensure ship heading stability while avoiding power waste. In high-speed crosscurrent, the propulsion weights of ships on the upstream side are significantly increased, ensuring that the fleet can overcome the lateral torque of the strong crosscurrent and maintain a stable course. This dynamic weight adjustment mechanism based on flow field characteristics significantly improves the fleet's heading stability and power utilization efficiency in complex flow fields, providing a solid power guarantee for the combined fleet's navigation in complex waters.

[0167] In one case of this embodiment, if the power margin coefficient 1, then trigger the graded warning mechanism, including:

[0168] When 0.8 Power margin factor At 1:00, the combined fleet is judged to be at a critical risk of residual power of the main engine, triggering a level 1 warning, and the yellow lights of the combined fleet flash;

[0169] When 0.5 Power margin factor At 0.8, the combined fleet was judged to be at risk of a shortage of main engine remaining power, triggering a Level 2 warning, with the orange lights of the combined fleet flashing;

[0170] When the power margin factor At 0.5, it was determined that there was a risk of serious insufficient remaining power of the main engine of the combined fleet, triggering a level 3 warning, and the red lights of the combined fleet flashed.

[0171] In one case of this embodiment, calculating the integrated data set to obtain the power and flow field time difference, and determining whether to execute the power distribution instruction based on the power and flow field time difference includes:

[0172] Extracting flow field time parameters and dynamic time parameters of flow field changes from the comprehensive data set, specifically including: extracting flow field time parameters of flow field changes from the comprehensive data set, sliding the flow velocity data sequence on the time axis according to the set window length (5s) through the sliding window difference algorithm, calculating the difference in the mean flow velocity of adjacent windows, and locating the flow velocity mutation point when the difference exceeds the threshold (1m / s), and the corresponding time is the flow field time parameter; screening the dynamic distribution instruction record from the comprehensive data set, extracting the instruction issuance timestamp, and if the instruction is executed in stages, taking the start time of each stage as the dynamic time parameter;

[0173] Calculating the difference between the flow field time parameter and the dynamic time parameter to obtain the dynamic and flow field time difference, specifically comprising: subtracting the dynamic time parameter from the flow field time parameter to obtain the dynamic and flow field time difference;

[0174] If the difference between the power and flow field time is ≤ 0, it means that the power adjustment takes effect later than the flow field change impact time, indicating that the power effective time is ≥ the flow field impact time (the power adjustment takes effect after or at the same time as the flow field impact). In this case, the power distribution instruction is not executed and the forced trigger instruction is executed.

[0175] If the time difference between power and flow field is greater than 0, it means that the power adjustment can be completed and take effect before the sudden change of flow field affects the ship, indicating that the power effective time is less than the flow field impact time (the power adjustment takes effect before the flow field change affects the system), and it is determined that the power distribution instruction will be executed.

[0176] By accurately extracting flow field time parameters and power time parameters from the comprehensive data set, using the sliding window difference algorithm to process the flow velocity data sequence, accurately identifying the flow velocity mutation points and determining the flow field time parameters, and extracting the power time parameters from the power distribution instruction records, the accuracy of time parameter acquisition is ensured. By calculating the difference between the flow field time parameters and the power time parameters, the time relationship between power adjustment and flow field change can be clarified, providing a key basis for whether to execute the power distribution instruction, and improving the navigation safety and stability of the fleet in complex flow field environments.

[0177] By accurately determining the time difference between power and flow, the system achieves scientific execution and management of power allocation instructions. When the time difference is ≤0, the system determines not to execute the power allocation instruction and triggers a mandatory instruction, effectively avoiding potential risks caused by delayed power adjustment. When the time difference is >0, the system determines to execute the power allocation instruction, ensuring that the power adjustment can take effect before the flow field changes affect the ship, ensuring that the fleet can adapt to flow field changes in a timely manner and maintain a stable navigation state. This time difference-based instruction decision-making mechanism significantly improves the fleet's navigation efficiency and safety in complex lock environments and reduces navigation risks caused by inappropriate power adjustment timing.

[0178] In one case of this embodiment, the hierarchical warning mechanism further includes:

[0179] During a Level 1 alert, based on the current flow type (crossflow, countercurrent, or downstream), the weights of the high-efficiency thrusters of the top 50% of priority ships will be increased by an additional 0.1, while the weights of the low-efficiency thrusters of the bottom 50% of priority ships will be reduced by the same amount (ensuring that the sum of the weights is 1).

[0180] Temporarily reduce the target speed by 5% to 10% to release margin by reducing the total power demand while maintaining heading stability;

[0181] During the Level 2 warning period: temporarily increase the thrust efficiency coefficient weight to 0.7 (originally 0.6), and reduce the power demand increment weight to 0.3;

[0182] The weight limit for ship thrusters on the downstream side or in auxiliary positions is reduced to 0.2 (originally 0.4), and the weight for thrusters on the upstream side or in the pilot ship is increased to 0.7-0.8 (not exceeding 1), as follows:

[0183] In upstream or cross-current scenarios: Adjust the thruster weight of the main propulsion vessel on the upstream side to the upper limit of the regulations (for example, directly increase it by 0.3 in high-speed cross-current, regardless of whether the initial weight is close to 1, and ensure it does not exceed 1). Reduce the thruster weight of the auxiliary vessel on the downstream side to a minimum of 0.05 (not less than 0);

[0184] Downstream scenario: The thruster weight of the leading ship is reduced to below 0.3, while the thruster weight of the escort ships on both sides is increased to 0.35. The ship controls its course through side thrusters, reducing the power consumption of the main thruster.

[0185] The fleet changes to a "single longitudinal" formation (to reduce the resistance area), and the lead boat makes a slight course adjustment of 5° to 10° to avoid the direction of the strong current and reduce the overall water resistance;

[0186] The speed is allowed to be temporarily lower than the target speed by 10% to 20%, with priority given to ensuring that the power system is not overloaded;

[0187] At level 3 warning: only the ship thruster with the highest efficiency priority is activated (the weight is directly set to 1, and the remaining thrusters are set to 0 to ensure weight conservation);

[0188] Immediately carry out a stop-and-go operation, shut down all non-essential loads, and keep only navigation and communication equipment running;

[0189] Send a distress signal to nearby ports or maritime authorities;

[0190] Among them, the third level warning Level 2 warning In the first-level warning, high-level warning measures automatically override lower-level ones to avoid adjustment strategy conflicts (for example, in the case of a third-level warning, inefficient thrusters are directly disabled without the need to perform fine-tuning for the first-level warning).

[0191] The power margin coefficient is used to accurately trigger different levels of warnings and take corresponding measures. During the first-level warning, the system adjusts the weight of the ship's thrusters based on the flow field type, increases the weight of high-efficiency thrusters, and reduces the weight of inefficient ones. At the same time, it moderately reduces the target speed to release the power margin and maintain heading stability. During the second-level warning, the thrust efficiency coefficient and the power demand increment weight are adjusted, the upper limit of the weight of the leeward side or auxiliary ship thrusters is limited, the weight of the upstream side or pilot ship thrusters is increased, and the formation and speed of the fleet are optimized, giving priority to ensuring that the power system is not overloaded. During the third-level warning, only the most efficient thrusters are enabled, the ship is stopped immediately, non-essential loads are turned off, and a distress signal is sent. This graded warning and response measure can maximize the navigation safety of the fleet at different risk levels, reduce the risk of power system overload, and improve emergency response capabilities.

[0192] In one case of this embodiment, executing the forced trigger instruction includes:

[0193] An alarm is issued to remind the operator, allowing the operator to manually force the power adjustment in advance and enforce the power distribution instruction.

[0194] While embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions, and variations may be made to these embodiments without departing from the principles and spirit of the invention, and that the scope of the invention is defined by the appended claims and their equivalents.

Claims

1. A combined fleet intelligent navigation data processing system, characterized in that: include: The data acquisition unit is used to collect the navigation data and lock data of each ship in the combined fleet in real time, and fuse the pre-processed navigation data and lock data to obtain a comprehensive data set; The positioning unit is used to extract and analyze the features of the comprehensive data set, locate the position and range of the flow velocity mutation area when the ship lock is opened and closed, and generate a flow field characteristic parameter set, including: separating the spatiotemporal fluctuation mode of the flow field from the comprehensive data set and generating a dynamic flow field feature vector; Extract the velocity information of each spatial position and time point in the dynamic flow field feature vector, use the central difference method to calculate the velocity gradient modulus of each spatial point in the adjacent spatial and time steps, and set three gradient thresholds: high, medium, and low. When the velocity gradient modulus High gradient threshold, which divides the flow field space into high-speed change areas. For the high-speed change areas, the grid spacing is reduced to half of the original spacing; When the low gradient threshold Flow rate gradient modulus Medium gradient threshold, which divides the flow field space into medium-speed change areas, and the grid spacing is adjusted to three-quarters of the original spacing; When the velocity gradient modulus Low gradient threshold, the flow field space is divided into low-speed change areas, and the grid spacing is increased to twice the original spacing for sparse processing; The Delaunay triangulation algorithm is used to regenerate grid nodes based on the new grid division, determine the three-dimensional spatial coordinates of the grid nodes, and construct a grid association matrix by analyzing the connection relationship between nodes, recording the information of adjacent grid units, and finally obtaining a dynamic grid topology structure; The dynamic grid topology structure is decomposed into a steady-state velocity field and a transient turbulence field, generating a steady-state velocity distribution matrix and a transient vortex intensity matrix respectively. The vortex velocity of the transient vortex intensity matrix is ​​compared with the reference value of the steady-state velocity distribution matrix to generate a velocity mutation difference field; The distribution unit is used to analyze the flow field characteristic parameter set and navigation data to generate power distribution instructions; The determination unit is used to calculate the comprehensive data set to obtain the time difference between the power and the flow field, and determine whether to execute the power distribution instruction based on the time difference between the power and the flow field.

2. The combined fleet intelligent navigation data processing system according to claim 1, characterized in that: The pre-processed navigation data and lock data are fused to obtain a comprehensive dataset, including: Analyze the pre-processed navigation data and lock data to obtain the correlation matrix; Based on the correlation matrix, the pre-processed navigation data and lock data are fused to obtain the fused data set; The fused dataset is processed for exceptions to obtain a comprehensive dataset.

3. The combined fleet intelligent navigation data processing system according to claim 2, characterized in that: Feature extraction and analysis of the comprehensive data set are performed to locate the location and range of the flow velocity mutation area when the lock is opened and closed, and a flow field characteristic parameter set is generated, including: Identify the boundary of the mutation area of ​​the velocity mutation difference field and obtain the velocity mutation boundary coordinate set; The velocity gradient components of each grid node in the steady-state velocity distribution matrix in the horizontal, longitudinal and vertical directions are calculated by the central difference method. These three components are combined into a spatial gradient vector, and the amplitude of the vector is calculated to obtain the spatial gradient amplitude. Extract the transient flow velocity data of each node at different times from the dynamic grid topology structure, and calculate the attenuation rate and attenuation multiple based on the transient flow velocity data; The spatial gradient amplitude, attenuation rate and attenuation multiple are combined to generate a turbulence intensity gradient parameter set; The velocity mutation boundary coordinate set and the turbulence intensity gradient parameter set are fused to generate the flow field characteristic parameter set.

4. The combined fleet intelligent navigation data processing system according to claim 3, characterized in that: Analyze the flow field characteristic parameter set and navigation data to generate power distribution instructions, including: The flow field characteristic parameter set is analyzed to obtain the peak velocity difference and turbulence influence gradient in the velocity mutation area; Calculate the peak velocity difference and the ship's draft data to obtain the power increment; The turbulence influence gradient is combined with the power increment and corrected to obtain a corrected power increment; The current output power of the main engine is calculated with the corrected power increment to obtain the power margin coefficient. If the power margin coefficient is less than 1, the graded warning mechanism is triggered.

5. The combined fleet intelligent navigation data processing system according to claim 4, characterized in that: Analyze the flow field characteristic parameter set and navigation data to generate power distribution instructions, including: Extract navigation data and generate a power allocation feasibility matrix; The thrust efficiency coefficient and power demand increment of the power allocation feasibility matrix are fused according to weights, and the weighted summation algorithm is used to obtain the comprehensive efficiency value of each thruster. In a complex flow field, the thrusters are arranged from high to low according to the comprehensive efficiency value through a quick sorting algorithm, and the thruster efficiency priority is finally obtained. The corrected power increment, power margin coefficient and power allocation feasibility matrix are integrated to generate a power allocation decision parameter set containing the comprehensive performance indicators of each thruster. According to the propeller efficiency priority and power allocation decision parameter set, an adaptive weight algorithm is used to dynamically allocate the propeller power adjustment amount of each ship. The initial weight is allocated according to the ship propeller efficiency priority. Then, the weights of different ship propellers are quantitatively adjusted based on the flow field type and flow velocity classification. According to the adjusted weights, the total power adjustment amount is proportionally allocated to the propellers of each ship to generate power allocation instructions.

6. The combined fleet intelligent navigation data processing system according to claim 4, characterized in that: If the power margin factor 1, then trigger the graded warning mechanism, including: When 0.8 Power margin factor At 1:00, the combined fleet is judged to be at a critical risk of residual power of the main engine, triggering a level 1 warning, and the yellow lights of the combined fleet flash; When 0.5 Power margin factor At 0.8, the combined fleet was judged to be at risk of a shortage of main engine remaining power, triggering a Level 2 warning, with the orange lights of the combined fleet flashing; When the power margin factor At 0.5, it was determined that there was a risk of serious insufficient remaining power of the main engine of the combined fleet, triggering a level 3 warning, and the red lights of the combined fleet flashed.

7. The combined fleet intelligent navigation data processing system according to claim 5, characterized in that: Calculate the integrated data set to obtain the time difference between the power and flow fields, and determine whether to execute the power distribution instruction based on the time difference between the power and flow fields, including: Extract flow field time parameters and dynamic time parameters of flow field changes from the comprehensive data set; Calculate the difference between the flow field time parameter and the dynamic time parameter to obtain the dynamic and flow field time difference; If the difference between the power and flow field time is ≤ 0, it means that the effective time of the power adjustment lags behind the time of the flow field change, and the power distribution instruction is determined not to be executed, and the forced trigger instruction is executed; If the time difference between power and flow field is greater than 0, it means that the power adjustment can be completed and take effect before the sudden change of flow field affects the ship, and the power distribution instruction is determined to be executed.

8. The combined fleet intelligent navigation data processing system according to claim 6, characterized in that: The graded early warning mechanism also includes: Level 1 warning: Based on the current flow field type, the current flow field type is divided into cross flow For both upstream and downstream vessels, based on the existing weight adjustment rules, the weight of high-efficiency thrusters for the top 50% of priority vessels will be increased by an additional 0.1, while the weight of low-efficiency thrusters for the bottom 50% of priority vessels will be reduced by the same amount. Temporarily reduce target speed by 5%~10%; During the Level 2 warning: temporarily increase the thrust efficiency coefficient weight to 0.7 and reduce the power demand increment weight to 0.3; For the thrusters on the leeward side or in the auxiliary position, the weight limit is reduced to 0.2, and the weight of the thrusters on the upstream side or in the pilot ship is increased to 0.7-0.8, as follows: In upstream or cross-current scenarios: the thruster weight of the main pusher vessel on the upstream side will be adjusted to the upper limit of the regulations, and the thruster weight of the auxiliary vessel on the downstream side will be reduced to a minimum of 0.05; Downstream scenario: The thruster weight of the leading ship is reduced to below 0.3, while the thruster weight of the escort ships on both sides is increased to 0.

35. The ship controls its course through side thrusters, reducing the power consumption of the main thruster. The fleet changed to a "single column" formation, with the lead boat making a slight course adjustment of 5° to 10° to avoid the strong current and reduce overall water resistance. The speed is allowed to be temporarily lower than the target speed by 10% to 20%, with priority given to ensuring that the power system is not overloaded; At level 3 warning: only the ship's thruster with the highest efficiency priority is enabled, and its weight is set to 1. The remaining thrusters are set to 0 to ensure weight conservation. Immediately carry out a stop-and-go operation, shut down all non-essential loads, and keep only navigation and communication equipment running; Send a distress signal to nearby ports or maritime authorities; Among them, the third level warning Level 2 warning Level 1 warning: high-level warning measures automatically cover low-level warning measures.

9. The combined fleet intelligent navigation data processing system according to claim 7, characterized in that: Execute mandatory trigger instructions, including: An alarm is issued to remind the operator, allowing the operator to manually force the power adjustment in advance and enforce the power distribution instruction.

Images