Optimization Method and System for Ship Automatic Mooring Control Strategy Based on Multi-Source Data

Abstract

The present invention provides a method and system for optimizing the automatic mooring control strategy of a ship based on multi-source data. First, multi-source perception data of the target ship is obtained, and a standardized data set is formed through preprocessing. A sliding time window is used to extract dynamic characteristic parameters from the preprocessed data, including the dynamic offset of the ship, the intensity of environmental interference, and the distribution parameters of mooring energy consumption. A dynamic optimization strategy generation model is called, and an optimization parameter set is generated based on the difference between the dynamic offset of the ship and the safety threshold, the matching degree between the environmental interference and the interference threshold, and the deviation between the mooring energy consumption and the optimization target. According to this set, the parameters of the actuator of the ship's automatic mooring control system are dynamically adjusted to generate a control command. At the same time, the attitude offset of the ship and the fluctuation of the cable tension during mooring are monitored in real time. Finally, based on the monitoring results, the optimization parameter set is feedback-corrected to obtain a corrected control strategy, thereby realizing the continuous optimization of the ship's automatic mooring control strategy and effectively improving the safety and efficiency of mooring.

Description

Technical Field

[0001] The present invention relates to the field of computer technology, and in particular, to a method and system for optimizing a ship automatic mooring control strategy based on multi-source data. Background Art

[0002] At present, with the rapid development of ship automation and intelligent technologies, the ship automatic mooring system, as a key technology to ensure the safe and efficient berthing of ships, the optimization of its performance has always been the focus of the industry. However, the existing ship automatic mooring control strategies still have many limitations when dealing with complex and changeable actual environments, and it is difficult to meet the growing ship mooring requirements.

[0003] On the one hand, most of the existing mooring control strategy generation methods adopt static or simple dynamic adjustment mechanisms. During the mooring process, characteristic parameters such as the dynamic offset of the ship, the intensity of environmental interference, and the mooring energy consumption distribution will change continuously over time. However, the existing technologies often cannot capture these dynamic changes in real time and adjust the control strategy in a timely manner according to the changes. For example, when encountering sudden strong winds, rapid currents and other harsh environmental conditions, the existing mooring systems may not be able to respond effectively in time, resulting in excessive ship attitude offsets, severe fluctuations in cable tensions, and even mooring safety accidents. At the same time, the existing technologies also have deficiencies in mooring energy consumption optimization and cannot perform refined energy consumption control according to the real-time energy consumption distribution, resulting in serious energy waste during the mooring process and reducing the operation efficiency of the ship.

[0004] In addition, the existing ship automatic mooring control systems lack an effective feedback correction mechanism. During the mooring process, even if the system can monitor key parameters such as the ship attitude offset and cable tension fluctuations in real time, it often cannot effectively feedback these monitoring data into the optimization process of the control strategy and cannot dynamically adjust and correct the control strategy according to the real-time monitoring results. This makes the mooring control strategy prone to deviations during the actual execution process and cannot always maintain good control effects, affecting the reliability and stability of the ship automatic mooring system. Summary of the Invention

[0005] In view of the above-mentioned problems, in combination with the first aspect of the present invention, embodiments of the present invention provide a method for optimizing a ship automatic mooring control strategy based on multi-source data, the method comprising:

[0006] Obtain a multi-source perception data set of a target ship, and perform data preprocessing on the multi-source perception data set to obtain a preprocessed multi-source perception data set, the multi-source perception data set including ship dynamic parameters, environmental interference parameters and historical mooring parameters;

[0007] Performing dynamic feature parameter extraction processing on the preprocessed multi-source perception data set based on a sliding time window to generate ship dynamic offset parameters, environmental interference intensity parameters, and mooring energy consumption distribution parameters;

[0008] Invoking a dynamic optimization strategy generation model, and generating an optimized parameter set for the ship automatic mooring control strategy according to the difference degree between the ship dynamic offset parameter and a preset ship safe mooring threshold, the matching degree between the environmental interference intensity parameter and a preset environmental interference threshold, and the deviation degree between the mooring energy consumption distribution parameter and a preset energy consumption optimization target;

[0009] Dynamically adjusting the actuator parameters of the ship automatic mooring control system according to the optimized parameter set to generate an adjusted ship automatic mooring control instruction, and real-time monitoring the ship attitude offset and cable tension fluctuation during the mooring process;

[0010] Performing feedback correction processing on the optimized parameter set based on the ship attitude offset and cable tension fluctuation to obtain a corrected ship automatic mooring control strategy, and updating the corrected ship automatic mooring control strategy to the ship automatic mooring control system.

[0011] On the other hand, an embodiment of the present invention further provides a ship automatic mooring control strategy optimization system based on multi-source data, including a processor and a machine-readable storage medium. The machine-readable storage medium is connected to the processor. The machine-readable storage medium is used to store programs, instructions, or codes, and the processor is used to execute the programs, instructions, or codes in the machine-readable storage medium to implement the above method.

[0012] Based on the above aspects, the embodiments of the present invention significantly improve the intelligent level and safety of ship automatic mooring. By acquiring the multi-source perception data set of the target ship and performing comprehensive data preprocessing, key information such as ship dynamic parameters, environmental interference parameters, and historical mooring parameters is effectively integrated. Based on the extraction and processing of dynamic characteristic parameters using a sliding time window, key characteristics such as ship dynamic offset, environmental interference intensity, and mooring energy consumption distribution can be captured in real time. By invoking the dynamic optimization strategy generation model, an optimized parameter set for the ship automatic mooring control strategy can be intelligently generated according to the difference between the ship dynamic offset parameter and the safety threshold, the matching degree between the environmental interference intensity parameter and the interference threshold, and the deviation degree between the mooring energy consumption distribution parameter and the energy consumption optimization target, realizing the refined control of the mooring process. Further, the actuator parameters of the ship automatic mooring control system are dynamically adjusted according to the optimized parameter set, and the ship attitude offset and cable tension fluctuation during the mooring process are monitored in real time. Finally, based on the ship attitude offset and cable tension fluctuation, feedback correction processing is performed on the optimized parameter set to obtain the corrected ship automatic mooring control strategy and update it to the ship automatic mooring control system, realizing the continuous optimization and adaptive adjustment of the control strategy. Thus, the robustness, safety, and energy efficiency of ship automatic mooring are effectively improved. Description of the Drawings

[0013] Figure 1 It is a schematic flowchart of the execution process of the method for optimizing the ship automatic mooring control strategy based on multi-source data provided by the embodiments of the present invention.

[0014] Figure 2 It is a schematic diagram of exemplary hardware and software components of the system for optimizing the ship automatic mooring control strategy based on multi-source data provided by the embodiments of the present invention. Detailed Embodiments

[0015] The present invention will be specifically described below in conjunction with the accompanying drawings of the specification. Figure 1 It is a flowchart of the method for optimizing the ship automatic mooring control strategy based on multi-source data provided by an embodiment of the present invention. The method for optimizing the ship automatic mooring control strategy based on multi-source data will be introduced in detail below.

[0016] Step S110: Acquire the multi-source perception data set of the target ship, and perform data preprocessing on the multi-source perception data set to obtain the preprocessed multi-source perception data set, where the multi-source perception data set includes ship dynamic parameters, environmental interference parameters, and historical mooring parameters.

[0017] In this embodiment, to optimize the automatic mooring control strategy of a ship, the primary task is to obtain a multi-source perception data set of the target ship, which includes ship dynamic parameters, environmental interference parameters, and historical mooring parameters. These data are the basis for subsequent analysis and strategy formulation. Different types of data reflect the state and environmental conditions of the ship during mooring from different perspectives. By comprehensively processing and analyzing these data, the safety and efficiency of ship mooring can be more accurately evaluated, and thus a more reasonable control strategy can be formulated.

[0018] Step S111: Obtain ship dynamic parameters through the ship's own sensors. The ship dynamic parameters include the real-time displacement of the ship, the change rate of the ship's attitude angle, the ship's mass distribution parameters, and the cable tension distribution parameters.

[0019] In this step, the ship is equipped with a variety of sensors to obtain ship dynamic parameters. For the real-time displacement of the ship, a Global Positioning System (GPS) sensor is usually used. The GPS sensor can accurately measure the position of the ship on the earth by receiving satellite signals. Suppose at the initial time t0, the position coordinates of the ship recorded by the GPS sensor are (x0, y0, z0), and at time t1, the recorded position coordinates become (x1, y1, z1). Then the real-time displacement of the ship during the time period [t0, t1] can be obtained by calculating the coordinate difference, that is, the displacement vector ΔS = (x1 - x0, y1 - y0, z1 - z0). This displacement vector reflects the position change of the ship in three-dimensional space and provides an important basis for subsequent analysis of the ship's motion trajectory and state.

[0020] The change rate of the ship's attitude angle can be obtained through a gyroscope sensor. The gyroscope can measure the angular velocity of the ship around three coordinate axes (roll axis, pitch axis, and yaw axis). Let the three angular velocities recorded by the gyroscope at time t be ωx(t), ωy(t), and ωz(t), and the angular velocities recorded at time t + Δt be ωx(t + Δt), ωy(t + Δt), and ωz(t + Δt). Then during the time period [t, t + Δt], the change rates of the ship's attitude angles around the roll axis, pitch axis, and yaw axis are (ωx(t + Δt) - ωx(t)) / Δt, (ωy(t + Δt) - ωy(t)) / Δt, and (ωz(t + Δt) - ωz(t)) / Δt respectively. These change rates of the attitude angles reflect the change speed of the ship's attitude and are very important for judging the stability and maneuverability of the ship.

[0021] The acquisition of the ship's mass distribution parameters is related to the ship's structure and the loading of goods. The mass distribution information of the ship's own structure can be obtained from the ship design drawings, and combined with the cargo loading list and the distribution of goods in the cargo hold to determine comprehensively. For example, the ship is divided into multiple small areas, and the mass of each area can be estimated according to the weight and distribution of the goods. Suppose the ship is divided into n areas, the mass of the i-th area is mi, and its coordinates are (xi, yi, zi), then the centroid coordinates (Xc, Yc, Zc) of the ship can be calculated by the following formulas: Xc = Σ(mi * xi) / Σmi, Yc = Σ(mi * yi) / Σmi, Zc = Σ(mi * zi) / Σmi. The ship's mass distribution parameters are crucial for analyzing the force conditions and stability of the ship during mooring.

[0022] The cable tension distribution parameters are measured by tension sensors installed on the cables. The tension sensors can monitor the tension of each cable in real time. Suppose the ship uses m cables for mooring, and the tension value measured by the tension sensor on the j-th cable at time t is Tj(t), then the cable tension distribution parameters at time t can be expressed as a vector T(t) = (T1(t), T2(t),..., Tm(t)). This vector reflects the force conditions of each cable at this moment and is of great significance for adjusting the cable tension and ensuring the stability of ship mooring.

[0023] Step S112: Obtain the environmental interference parameters through the port environment perception device, and the environmental interference parameters include the water flow velocity gradient distribution parameters, the wind direction and wind force vector parameters, and the wave height change parameters.

[0024] Next, the port environment perception device is used to obtain the environmental interference parameters. The acquisition of the water flow velocity gradient distribution parameters requires arranging multiple water flow sensors at different depths and positions in the port water area. Suppose p water flow sensors are arranged at different positions in the port water area, and each sensor measures the water flow velocity at different depths q. At time t, the water flow velocity measured by the water flow sensor at the k-th position and the q-th depth is vkq(t). In order to obtain the water flow velocity gradient distribution parameters, the difference in water flow velocity between adjacent positions or adjacent depths can be calculated. For example, at the same depth q, the difference in water flow velocity between adjacent positions k and k + 1 is Δvkq(t) = v(k + 1)q(t) - vkq(t) / Δx; at the same position k, the difference in water flow velocity between adjacent depths q and q + 1 is Δvk(q + 1)(t) = vk(q + 1)(t) - vkq(t) / Δx. These differences reflect the spatial variation of the water flow velocity, that is, the water flow velocity gradient. By processing the water flow velocity data at multiple positions and depths, a more comprehensive water flow velocity gradient distribution parameter can be obtained for analyzing the force distribution of the water flow on the ship.

[0025] The wind direction and wind force vector parameters are obtained through a wind vane and an anemometer. The wind vane can measure the direction of the wind, usually expressed in angles. For example, 0° represents the due north direction, 90° represents the due east direction, etc. The anemometer can measure the wind speed. At time t, the wind direction angle measured by the wind vane is θ(t), and the wind speed measured by the anemometer is v_wind(t). Then the wind direction and wind force vector can be expressed as a two-dimensional vector V_wind(t) = (v_wind(t) * cos(θ(t)), v_wind(t) * sin(θ(t))), where the x-component represents the force of the wind in the east-west direction, and the y-component represents the force of the wind in the north-south direction. This vector reflects the impact of the wind direction and intensity on the ship.

[0026] The wave height change parameters are monitored through wave sensors. The wave sensor can measure the wave height in real time. Assume that the wave height measured by the wave sensor at time t is h(t), and a series of wave height values {h(t1), h(t2),..., h(tn)} are continuously measured within a period of time. To analyze the characteristics of the waves, parameters such as the average wave height, maximum wave height, and minimum wave height can be calculated. For example, the average wave height h_avg can be calculated by the formula h_avg = Σh(ti) / n, where n is the number of measurement time points. The wave height change parameters are very important for evaluating the impact of waves on the ship and the stability of the ship mooring.

[0027] Step S113: Extract historical mooring parameters from the historical mooring database, where the historical mooring parameters include the ship displacement adjustment amount, cable tension optimization value, and environmental interference threshold in historical mooring success cases.

[0028] Then, extract historical mooring parameters from the historical mooring database. The historical mooring database records a large number of mooring cases, which contain mooring information of different ships under different environmental conditions. For the ship displacement adjustment amount, in each historical mooring success case, the position change of the ship from the start of mooring to the final stable state is recorded. Assume that in the s-th historical mooring success case, the position coordinates of the ship at the start of mooring are (xs0, ys0, zs0), and the position coordinates at the mooring stable moment are (xs1, ys1, zs1), then the ship displacement adjustment amount in this case is the displacement vector ΔSs = (xs1 - xs0, ys1 - ys0, zs1 - zs0). By analyzing multiple historical mooring success cases, the statistical laws and typical values of the ship displacement adjustment amount under different environmental conditions can be obtained.

[0029] The optimized value of the cable tension is the cable tension setting value that enables the stable mooring of the ship in historical successful mooring cases. In each case, the tension change of each cable during the mooring process and the tension value at the final stability are recorded. Suppose in the s-th case, the ship uses m cables for mooring, and the tension value of the j-th cable at the final stability is Tsj. Through the analysis of multiple cases, the optimized range and typical values of the cable tension under different environmental conditions can be obtained. For example, the average value and standard deviation of the tension of each cable under a certain specific environmental condition can be calculated as a reference for the optimized value of the cable tension under this environmental condition.

[0030] The environmental interference threshold refers to the situation in historical successful mooring cases where when the environmental interference parameter exceeds this threshold, the mooring may face risks. For the water flow velocity, by analyzing the influence of the water flow velocity on the mooring stability in multiple cases, a water flow velocity threshold v_threshold_flow can be determined. When the actual water flow velocity exceeds this threshold, the difficulty and risk of the ship mooring will increase significantly. Similarly, for the wind direction and wind force and the wave height, the corresponding thresholds v_threshold_wind and h_threshold_wave can be determined respectively. These environmental interference thresholds provide an important reference for judging the safety of the mooring under the current environmental conditions.

[0031] Step S114: Align the timestamps of the ship dynamic parameters, the environmental interference parameters, and the historical mooring parameters to generate a time-synchronized multi-source perception data set.

[0032] After obtaining the ship dynamic parameters, environmental interference parameters, and historical mooring parameters, since these data may be collected at different time points, in order to ensure the consistency and accuracy of the data, timestamp alignment processing is required. Suppose the acquisition time series of the ship dynamic parameters is {t1_ship, t2_ship,..., tn_ship}, the acquisition time series of the environmental interference parameters is {t1_env, t2_env,..., tm_env}, and the timestamp information of the historical mooring parameters has a certain corresponding relationship with the current acquisition time.

[0033] First, determine a unified time reference. One of the data acquisition time series can be selected as the reference. For example, the acquisition time series of the ship's dynamic parameters can be chosen. Then, for the environmental interference parameters and historical mooring parameters, align their timestamps with the reference time series through interpolation or matching methods. For the environmental interference parameters, if a certain moment t is in the acquisition time series of the ship's dynamic parameters but not in the acquisition time series of the environmental interference parameters, the linear interpolation method can be used to calculate the value of the environmental interference parameters at this moment. Assume that t is between the acquisition times t_i_env and t_(i + 1)_env of the environmental interference parameters, and the corresponding environmental interference parameter values are E_i and E_(i + 1) respectively. Then the value of the environmental interference parameters at time t can be calculated through the linear interpolation formula E(t) = E_i + (E_(i + 1) - E_i) * (t - t_i_env) / (t_(i + 1)_env - t_i_env).

[0034] For the historical mooring parameters, according to the time relationship between the current acquisition time and the historical mooring cases, select the historical mooring case that is closest to the current environmental conditions and ship status as a reference. For example, based on the current environmental interference parameters (such as water flow velocity, wind direction and force, wave height, etc.) and ship dynamic parameters (such as the real-time displacement of the ship, the change rate of the ship's attitude angle, etc.), search for the most similar cases in the historical mooring database. Then associate and align the timestamps of the historical mooring parameters such as the ship displacement adjustment amount, the optimized value of the cable tension, and the environmental interference threshold in this case with the currently acquired data.

[0035] Through the above timestamp alignment process, integrate the ship's dynamic parameters, environmental interference parameters, and historical mooring parameters into a unified time series to generate a time-synchronized multi-source perception data set. The data in this set is consistent in time, providing a reliable basis for subsequent data analysis and processing.

[0036] Step S115: Perform data preprocessing on the time-synchronized multi-source perception data set. The data preprocessing includes data filtering and noise reduction processing, missing data interpolation and compensation processing, and multi-source data fusion processing to obtain a preprocessed multi-source perception data set.

[0037] After obtaining the time-synchronized multi-source perception data set, it is necessary to perform data preprocessing on it to improve the quality and usability of the data. Data filtering and noise reduction processing is to remove the noise interference in the data and make the data smoother and more accurate. For the real-time displacement data in the ship's dynamic parameters, due to factors such as signal interference that the GPS sensor may be affected by, there is certain noise in the measured data. The sliding average filtering method can be used to process the displacement data. Assuming that the real-time displacement data sequence is {S1, S2,..., Sn} and the size of the sliding window is k. For the i-th data point Si, its filtered value S_i_filtered can be obtained by calculating the average value of the data within the window, that is, S_i_filtered = (S_(i-(k-1) / 2) +... + Si +... + S_(i+(k-1) / 2)) / k (when i-(k-1) / 2 < 1 or i+(k-1) / 2 > n, boundary processing is required). In this way, the high-frequency noise in the displacement data can be effectively removed and the displacement data becomes smoother.

[0038] For the water flow velocity data in the environmental interference parameters, a similar filtering method can also be used for processing. The data measured by the water flow sensor may be affected by factors such as water flow fluctuations, resulting in noise in the data. Through filtering processing, more stable water flow velocity data can be obtained, which can more accurately reflect the actual situation of the water flow.

[0039] Missing data interpolation and compensation processing is to fill in the missing values in the data. During the data acquisition process, due to reasons such as sensor failures and communication interruptions, some data may be missing. For the ship's attitude angle change rate data in the ship's dynamic parameters, if the attitude angle change rate data at a certain moment is missing, the linear interpolation method can be used for compensation. Assuming that the attitude angle change rate data at times t_i and t_(i+1) are ω_i and ω_(i+1) respectively, and the data at time t (t_i < t < t_(i+1)) is missing, then the attitude angle change rate value at this moment can be calculated through the linear interpolation formula ω(t) = ω_i + (ω_(i+1) - ω_i) * (t - t_i) / (t_(i+1) - t_i).

[0040] For the missing data in the environmental interference parameters and historical mooring parameters, a similar interpolation method can also be used for compensation. If there is a large amount of missing data, the statistical laws and correlation relationships of historical data can also be combined for more complex interpolation processing to improve the accuracy of interpolation.

[0041] Multi-source data fusion processing is to organically fuse ship dynamic parameters, environmental interference parameters, and historical mooring parameters to extract more comprehensive and valuable information. A weighted fusion method can be adopted to assign different weights according to the importance and reliability of different types of data. For example, for the real-time displacement of the ship and the water flow speed in the environmental interference parameters, since they have a greater impact on the ship mooring state, higher weights can be assigned; while for some auxiliary information in the historical mooring parameters, lower weights can be assigned.

[0042] Step S120: Based on a sliding time window, perform dynamic feature parameter extraction processing on the preprocessed multi-source perception data set to generate ship dynamic offset parameters, environmental interference intensity parameters, and mooring energy consumption distribution parameters.

[0043] In this step, in order to further analyze the dynamic characteristics during the ship mooring process, a sliding time window is used to process the preprocessed multi-source perception data set. The sliding time window is a commonly used data analysis method, which can slide on time series data, analyze and process the data within each window, so as to extract the dynamic characteristics of the data.

[0044] Step S121: Determine the window length and sliding step size parameters of the sliding time window, and divide the preprocessed multi-source perception data set into multiple window data subsets according to the time series.

[0045] First of all, it is necessary to determine the window length and sliding step size parameters of the sliding time window. The window length determines the number of data points contained in each window, and the sliding step size determines the distance that the window slides each time. Assume that the time series length of the preprocessed multi-source perception data set is N, the window length is L, and the sliding step size is S. Starting from the starting point of the time series, the data points contained in the first window are from the 1st to the Lth, and the data points contained in the second window are from the (1 + S)th to the (L + S)th, and so on. Until the end point of the window exceeds the length N of the time series. In this way, the preprocessed multi-source perception data set is divided into multiple window data subsets according to the time series. For example, if N = 100, L = 10, and S = 5, then (100 - 10) / 5 + 1 = 19 window data subsets can be obtained. Each window data subset contains the information of ship dynamic parameters, environmental interference parameters, and historical mooring parameters during this time period.

[0046] Step S122: Extract the displacement change rate of the ship dynamic parameters in each window data subset, calculate the ratio of the absolute value of the difference between the real-time displacements of the ship at adjacent timestamps to the time interval, and generate a ship displacement instantaneous velocity sequence.

[0047] Next, extract the displacement change rate of the ship's dynamic parameters in each window data subset. For the ship's real-time displacement data in each window data subset, calculate the ratio of the absolute value of the difference between the ship's real-time displacements at adjacent timestamps to the time interval. Suppose in a certain window data subset, the ship's real-time displacement data sequence is {S1, S2,..., SL}, and the corresponding timestamp sequence is {t1, t2,..., tL}. For the i-th and i + 1-th timestamps, the ship's real-time displacements are Si and S_(i+1) respectively, and the time interval is Δt = t_(i+1) - ti. Then the instantaneous velocity vi of the ship's displacement at the i-th moment can be calculated by the formula vi = |S_(i+1) - Si| / Δt. By calculating for each adjacent timestamp pair within the window, a sequence of the ship's displacement instantaneous velocities {v1, v2,..., v_(L-1)} can be generated. This sequence reflects the displacement change speed of the ship within this window time period and is very important for analyzing the ship's dynamic motion situation.

[0048] Step S123: Conduct range statistical analysis within the window for the sequence of the ship's displacement instantaneous velocities, and extract the difference between the maximum value and the minimum value as the ship's dynamic offset parameter.

[0049] Then, conduct range statistical analysis within the window for the sequence of the ship's displacement instantaneous velocities. The range is a statistic that describes the degree of data dispersion, and it is equal to the difference between the maximum value and the minimum value in the data. For the sequence of the ship's displacement instantaneous velocities {v1, v2,..., v_(L-1)}, find the maximum value v_max and the minimum value v_min among them. Then the ship's dynamic offset parameter D_offset can be calculated by the formula D_offset = v_max - v_min. This ship's dynamic offset parameter reflects the change amplitude of the ship's displacement speed within this time window and embodies the instability degree of the ship's motion. A larger ship's dynamic offset parameter means that the ship's displacement speed fluctuates greatly within this time period, and it may face greater dynamic risks, such as being subjected to greater external force interference or improper operation, etc.

[0050] Step S124: Conduct vector synthesis processing on the environmental interference parameters in each window data subset.

[0051] Next, conduct vector synthesis processing on the environmental interference parameters in each window data subset to obtain more comprehensive environmental interference information. This includes converting the water flow velocity gradient distribution parameter, the wind direction and wind force vector parameter, and the wave height change parameter into corresponding acting forces respectively and performing superposition.

[0052] Step S1241: Convert the water flow velocity gradient distribution parameter into the acting force of the water flow on the ship through a hydrodynamics model.

[0053] In this step, the water flow velocity gradient distribution parameter needs to be converted into the force exerted by the water flow on the ship. The hydrodynamics model can calculate the water flow force based on factors such as the water flow velocity, the geometric shape of the ship, and the draft depth. Assume that the cross-sectional area of the underwater part of the ship is known as A, and the distribution of the water flow velocity at different positions of the ship is v(x, y, z), where x, y, and z represent the position coordinates of the ship in three-dimensional space. According to the principles of hydrodynamics, the force dF exerted by the water flow on the infinitesimal area dA of the ship can be expressed as being proportional to the water flow density ρ, the square of the water flow velocity v, and the infinitesimal area dA, and the proportionality coefficient is a drag coefficient Cd related to the fluid characteristics and the ship surface shape. By performing an integration operation over the entire surface area of the underwater part of the ship, the total force F_flow exerted by the water flow on the ship can be obtained. Specifically, first divide the underwater surface of the ship into numerous small infinitesimal areas, calculate the water flow force exerted on each infinitesimal area, and then sum up the forces on all infinitesimal areas. It should be noted here that the water flow force is a vector, and its direction is related to the direction of the water flow velocity. The unit of the water flow density ρ is kilograms per cubic meter, the unit of the water flow velocity v is meters per second, the unit of the area A is square meters, and the drag coefficient Cd is dimensionless. Then, the unit of the water flow force F_flow calculated according to the above relationship is Newton, which ensures the consistency of dimensions.

[0054] Step S1242: Convert the wind direction and wind force vector parameter into wind force through the wind pressure formula.

[0055] The wind direction and wind force vector parameter needs to be converted into wind force through the wind pressure formula. The wind pressure formula can be expressed as the wind pressure P being proportional to the air density ρ_air and the square of the wind speed v_wind, and the proportionality coefficient is 0.5. And the wind force F_wind is equal to the product of the wind pressure P and the windward area A_wind of the ship. The unit of the air density ρ_air is kilograms per cubic meter, the unit of the wind speed v_wind is meters per second, the unit of the windward area A_wind is square meters. The unit of the wind pressure P calculated through the above formula is Pascal, that is, Newton per square meter. After multiplying by the windward area A_wind, the unit of the wind force F_wind obtained is Newton, ensuring the dimensional consistency. The wind direction and wind force vector parameter itself contains information about the direction and magnitude of the wind, and the converted wind force is also a vector, and its direction is the same as the wind direction.

[0056] Step S1243: Convert the wave height change parameter combined with the wave period and the draft area of the ship into wave force.

[0057] The wave height change parameter, combined with the wave period and the ship's draft area, can be converted into wave force. The calculation of wave force usually needs to consider the characteristics of the wave (such as wave height, wave period) and the draft situation of the ship. Assume the wave height is \(h_{wave}\), the wave period is \(T_{wave}\), and the ship's draft area is \(A_{draft}\). The wave force \(F_{wave}\) can be calculated through some empirical formulas or theoretical models. For example, the specific formula can be: Wave force \(F_{wave}=(0.5\times\rho\times C_d\times A_{draft}\times(\pi\times h_{wave} / T_{wave})^2)+(\rho\times C_m\times V\times(2\times\pi^2\times h_{wave} / T_{wave}^2))\).

[0058] Among them, \(\rho\) is the seawater density (unit: \(kg / m^3\)), \(C_d\) is the drag coefficient (dimensionless, calibrated by experiment), \(A_{draft}\) is the ship's draft area (unit: \(m^2\)), \(h_{wave}\) is the wave height (unit: \(m\)), \(T_{wave}\) is the wave period (unit: \(s\)), \(C_m\) is the added mass coefficient (dimensionless, calibrated by experiment), \(V\) is the ship's draft volume (unit: \(m^3\), \(V = A_{draft}\times L\), \(L\) is the ship's characteristic length), and \(\pi\) is the pi (\(\approx3.14159\)).

[0059] Step S1244: Project and superimpose the water flow acting force, wind force, and wave force in the spatial direction to generate the resultant vector of environmental interference.

[0060] After obtaining the water flow force \(F_{flow}\), wind force \(F_{wind}\) and wave force \(F_{wave}\), it is necessary to project and superimpose them in the spatial direction to generate the resultant environmental interference force vector \(F_{total}\). Since these three forces are all vectors with direction and magnitude information, in three-dimensional space, they need to be decomposed into the x, y, and z coordinate axes directions respectively. Assume that the components of the water flow force in the x, y, and z directions are \(F_{flow\_x}\), \(F_{flow\_y}\), \(F_{flow\_z}\) respectively, the components of the wind force in the x, y, and z directions are \(F_{wind\_x}\), \(F_{wind\_y}\), \(F_{wind\_z}\) respectively, and the components of the wave force in the x, y, and z directions are \(F_{wave\_x}\), \(F_{wave\_y}\), \(F_{wave\_z}\) respectively. Then the components of the resultant environmental interference force vector \(F_{total}\) in the x, y, and z directions are \(F_{total\_x}=F_{flow\_x}+F_{wind\_x}+F_{wave\_x}\), \(F_{total\_y}=F_{flow\_y}+F_{wind\_y}+F_{wave\_y}\), \(F_{total\_z}=F_{flow\_z}+F_{wind\_z}+F_{wave\_z}\). It is necessary to ensure that the dimensions of the components of each force are consistent when adding them, and they are all in Newtons. Through this method of projection and superposition, the resultant environmental interference force vector \(F_{total}\) obtained can comprehensively reflect the overall force of environmental factors on the ship within this time window.

[0061] Step S1245: Calculate the moving average of the modulus of the resultant environmental interference force vector changing with time to generate an environmental interference intensity parameter.

[0062] To obtain the environmental interference intensity parameter, it is necessary to calculate the moving average of the magnitude of the resultant vector of environmental interference changing with time. The magnitude |F_total| of the resultant vector F_total of environmental interference can be calculated by the formula |F_total| = square root of (the square of F_total_x + the square of F_total_y + the square of F_total_z). However, since the formula editor cannot be used here, we describe it in words. The unit of its magnitude is still Newton. The calculation of the moving average is to smooth the fluctuations of the magnitude of the resultant vector of environmental interference with time, so that the obtained environmental interference intensity parameter can better reflect the overall trend of environmental interference. Assume the number of time windows is M, and the magnitudes of the resultant vectors of environmental interference corresponding to each time window are |F_total_1|, |F_total_2|,..., |F_total_M|. Select a moving average window length m. For the i-th time window, its environmental interference intensity parameter I_env can be obtained by calculating the average value of the magnitudes of the resultant vectors of environmental interference corresponding to the time windows from the (i - m + 1)-th to the i-th, that is, I_env = (|F_total_(i - m + 1)| +... + |F_total_i|) / m (when i - m + 1 < 1, boundary processing is required). The unit of the calculated environmental interference intensity parameter I_env is also Newton, which is consistent with the unit of the magnitude of the resultant vector of environmental interference, ensuring the unity of dimensions.

[0063] Step S125: Assign energy consumption weights to the historical mooring parameters in each window data subset.

[0064] Next, assign energy consumption weights to the historical mooring parameters in each window data subset to determine the energy consumption distribution during the mooring process. This mainly involves the calculation of the energy consumption of cable adjustment and thruster energy consumption and the combination of their weights.

[0065] Step S1251: Take the product of the cable tension distribution parameter and the cable adjustment rate as the cable adjustment power, and integrate and accumulate the power within the time window to generate the cable adjustment energy consumption.

[0066] In this step, the energy consumption for cable adjustment needs to be calculated. The cable adjustment power \(P_{cable}\) can be obtained by multiplying the cable tension distribution parameter \(T_{cable}\) by the cable adjustment rate \(v_{cable}\). The cable tension distribution parameter \(T_{cable}\) is a vector, which represents the tension magnitude of each cable, and the cable adjustment rate \(v_{cable}\) is also a vector, representing the adjustment speed of each cable. For each cable, its adjustment power \(P_{cable\_i}=T_{cable\_i}*v_{cable\_i}\) (where \(i\) represents the \(i\)-th cable). Then, by integrating and accumulating the power within the time window, the cable adjustment energy consumption \(E_{cable}\) can be obtained. Suppose the start time of the time window is \(t_{start}\) and the end time is \(t_{end}\). During this time period, the change of the cable adjustment power with time is \(P_{cable}(t)\). By performing an integration operation on \(P_{cable}(t)\) within the time period \([t_{start}, t_{end}]\), that is, \(E_{cable}=\int_{t_{start}}^{t_{end}}P_{cable}(t)dt\). In actual calculation, the time window can be discretized into multiple small time intervals \(\Delta t\). It is considered that the cable adjustment power is constant within each time interval, and then the power within each time interval is multiplied by the time interval and accumulated, that is, \(E_{cable}=\sum(P_{cable}(t_j)*\Delta t)\), where \(t_j\) represents the start time of the \(j\)-th time interval. The unit of the cable tension is Newton, the unit of the cable adjustment rate is meter per second, so the unit of the cable adjustment power is Watt, and the unit of the cable adjustment energy consumption obtained by integrating the power over time is Joule, ensuring the consistency of dimensions.

[0067] Step S1252: Integrate and accumulate the thruster power parameters according to the duration within the time window to generate the thruster energy consumption.

[0068] The calculation of the thruster energy consumption is to integrate and accumulate the thruster power parameter P_prop over the duration within the time window. The thruster power parameter P_prop is the power of the thruster during operation, which may vary over time. Similarly, assume that the start time of the time window is t_start, the end time is t_end, and the variation of the thruster power over time is P_prop(t). By integrating P_prop(t) over the time period [t_start, t_end], that is, E_prop = integral of P_prop(t) from t_start to t_end. In actual calculation, the time window can also be discretized into multiple small time intervals Δt. It is considered that the thruster power is constant within each time interval, and then the power within each time interval is multiplied by the time interval and accumulated, that is, E_prop = sum(P_prop(t_j)*Δt), where t_j represents the start time of the j-th time interval. The unit of the thruster power is watt, and the unit of the thruster energy consumption obtained by integrating the power over time is joule, which is the same as the unit of the cable adjustment energy consumption.

[0069] Step S1253: Combine the cable adjustment energy consumption and the thruster energy consumption according to a preset weight to generate a mooring energy consumption distribution parameter.

[0070] After obtaining the cable adjustment energy consumption E_cable and the thruster energy consumption E_prop, they need to be combined according to a preset weight to generate a mooring energy consumption distribution parameter E_total. Assume that the weight of the cable adjustment energy consumption is w_cable, the weight of the thruster energy consumption is w_prop, and w_cable + w_prop = 1. Then the mooring energy consumption distribution parameter E_total = w_cable*E_cable + w_prop*E_prop. Since the units of both the cable adjustment energy consumption and the thruster energy consumption are joules and the weight is dimensionless, the unit of the calculated mooring energy consumption distribution parameter E_total is also joules, ensuring the consistency of dimensions. This mooring energy consumption distribution parameter reflects the total energy consumption situation during the ship mooring process within this time window.

[0071] Step S126: Normalize and splice the ship dynamic offset parameter, the environmental disturbance intensity parameter, and the mooring energy consumption distribution parameter in the order of the time window to form a dynamic characteristic parameter set.

[0072] Finally, the ship dynamic offset parameters, environmental interference intensity parameters, and mooring energy consumption distribution parameters are normalized and concatenated in the order of time windows to form a set of dynamic characteristic parameters. The normalization process is to eliminate the differences in dimensions and numerical ranges between different parameters, making them comparable when concatenated. For the ship dynamic offset parameter D_offset, assuming its maximum value is D_offset_max and its minimum value is D_offset_min, then the normalized ship dynamic offset parameter D_offset_norm = (D_offset - D_offset_min) / (D_offset_max - D_offset_min). For the environmental interference intensity parameter I_env, assuming its maximum value is I_env_max and its minimum value is I_env_min, then the normalized environmental interference intensity parameter I_env_norm = (I_env - I_env_min) / (I_env_max - I_env_min). For the mooring energy consumption distribution parameter E_total, assuming its maximum value is E_total_max and its minimum value is E_total_min, then the normalized mooring energy consumption distribution parameter E_total_norm = (E_total - E_total_min) / (E_total_max - E_total_min). The normalized ship dynamic offset parameters, environmental interference intensity parameters, and mooring energy consumption distribution parameters corresponding to each time window are concatenated in order to form a set of dynamic characteristic parameters. This set contains the dynamic characteristic information of the ship during mooring at different time windows, providing an important basis for generating the optimization parameter set of the ship automatic mooring control strategy in the future.

[0073] Step S130: Invoke the dynamic optimization strategy generation model, and generate an optimization parameter set for the ship automatic mooring control strategy according to the difference degree between the ship dynamic offset parameter and the preset ship safe mooring threshold, the matching degree between the environmental interference intensity parameter and the preset environmental interference threshold, and the deviation degree between the mooring energy consumption distribution parameter and the preset energy consumption optimization target.

[0074] In this step, it is necessary to invoke the dynamic optimization strategy generation model and combine the relationships between the ship dynamic offset parameter, environmental interference intensity parameter, and mooring energy consumption distribution parameter with the corresponding thresholds and targets to generate an optimization parameter set for the ship automatic mooring control strategy.

[0075] Step S131: Input the ship dynamic offset parameter into the preset genetic algorithm optimization module to generate a first optimization parameter for the ship displacement adjustment amount, and the first optimization parameter is used to control the output thrust and direction of the ship thruster.

[0076] First, input the ship's dynamic offset parameter into a preset genetic algorithm optimization module. The genetic algorithm is an optimization algorithm based on the principles of biological evolution, which searches for the optimal solution by simulating natural selection and genetic mechanisms. In this embodiment, the goal of the genetic algorithm optimization module is to generate the first optimization parameter of the ship's displacement adjustment amount based on the ship's dynamic offset parameter. The ship's dynamic offset parameter reflects the instability degree of the ship's movement. Through the genetic algorithm, the optimal parameters that can adjust the ship's displacement to the safe range can be searched. Assume that the ship's dynamic offset parameter is D_offset. The population of the genetic algorithm contains multiple individuals, and each individual represents a set of possible ship's displacement adjustment amount parameters. By defining a fitness function, which can measure the quality of the ship's displacement adjustment scheme corresponding to each individual. For example, the deviation between the ship's displacement after adjustment and the preset safe displacement range can be used as a measure of fitness. Then, through genetic operations such as selection, crossover, and mutation, the population is continuously evolved until the individual with the optimal fitness is found, and the parameters corresponding to this individual are the first optimization parameter of the ship's displacement adjustment amount. This first optimization parameter can be used to control the output thrust and direction of the ship's thruster to achieve effective adjustment of the ship's displacement.

[0077] Step S132: Input the environmental interference intensity parameter into a preset fuzzy control module to generate the second optimization parameter of the environmental interference compensation force, and the second optimization parameter is used to adjust the distribution weight of the cable tension.

[0078] Next, input the environmental interference intensity parameter into a preset fuzzy control module. Fuzzy control is a control method based on fuzzy logic, which can handle uncertain and fuzzy information. The environmental interference intensity parameter reflects the magnitude of the overall force of environmental factors on the ship. The fuzzy control module generates the second optimization parameter of the environmental interference compensation force based on this parameter. The fuzzy control module includes a fuzzy rule base and a fuzzy inference mechanism. First, the environmental interference intensity parameter is fuzzified and mapped to a fuzzy set in the fuzzy universe of discourse. Then, according to the rules in the fuzzy rule base, fuzzy inference is performed to obtain a fuzzy output. Finally, the fuzzy output is defuzzified to obtain the specific second optimization parameter of the environmental interference compensation force. This second optimization parameter is used to adjust the distribution weight of the cable tension to compensate for the impact of environmental interference on the ship mooring and ensure the stability of the ship mooring.

[0079] Step S133: Input the mooring energy consumption distribution parameter into a preset particle swarm optimization module to generate the third optimization parameter for minimizing the mooring energy consumption, and the third optimization parameter is used to optimize the matching relationship between the thruster power and the cable tension adjustment rate.

[0080] Then, input the mooring energy consumption distribution parameters into a preset particle swarm optimization module. The particle swarm optimization algorithm is an optimization algorithm based on swarm intelligence, which finds the optimal solution by simulating the group behavior of bird flocks or fish schools. In this embodiment, the goal of the particle swarm optimization module is to generate the third optimization parameter that minimizes the mooring energy consumption according to the mooring energy consumption distribution parameters. The mooring energy consumption distribution parameters reflect the total energy consumption during the ship mooring process. The particle swarm optimization algorithm continuously iterates and updates the positions and velocities of the particles to find the matching relationship between the thruster power and the cable tension adjustment rate that minimizes the mooring energy consumption. Assume that the particle swarm contains multiple particles, and each particle represents a set of parameter combinations of the thruster power and the cable tension adjustment rate. By defining a fitness function, which can measure the energy consumption corresponding to each particle. For example, the mooring energy consumption can be used as a measure of fitness. Then, based on the fitness values of the particles and the information sharing among the particles, update the positions and velocities of the particles until the particle with the optimal fitness is found. The parameters corresponding to this particle are the third optimization parameter that minimizes the mooring energy consumption. This third optimization parameter is used to optimize the matching relationship between the thruster power and the cable tension adjustment rate to reduce the energy consumption during mooring.

[0081] Step S134: Construct a multi-objective constraint function according to the first optimization parameter, the second optimization parameter, and the third optimization parameter, and solve the optimal solution of the multi-objective constraint function through the gradient descent algorithm to obtain an optimization parameter set of the ship automatic mooring control strategy.

[0082] After obtaining the first optimization parameter, the second optimization parameter, and the third optimization parameter, it is necessary to construct a multi-objective constraint function based on them. The multi-objective constraint function comprehensively considers the three objectives of ship displacement adjustment, environmental disturbance compensation, and mooring energy consumption minimization. Assume that the first optimization parameter is p1, the second optimization parameter is p2, and the third optimization parameter is p3. The multi-objective constraint function can be expressed as a function F(p1, p2, p3) that includes these three parameters. This function needs to balance the effect of ship displacement adjustment, the degree of environmental disturbance compensation, and the magnitude of mooring energy consumption.

[0083] Step S1341: Set the weight coefficients of the multi-objective constraint function, where the weight coefficients include the ship stability weight, the environmental disturbance compensation weight, and the energy consumption optimization weight.

[0084] First, it is necessary to set the weight coefficients of the multi-objective constraint function. These weight coefficients are the ship stability weight w1, the environmental disturbance compensation weight w2, and the energy consumption optimization weight w3, respectively, and w1 + w2 + w3 = 1. These weight coefficients are used to adjust the importance of different objectives in the multi-objective constraint function. For example, if more attention is paid to the ship stability, the ship stability weight w1 can be set to a larger value; if more attention is paid to reducing energy consumption, the energy consumption optimization weight w3 can be set to a larger value.

[0085] Step S1342: Calculate the product of the ship's dynamic offset parameter and the ship stability weight to generate a first constraint term.

[0086] Calculate the product of the ship's dynamic offset parameter D_offset and the ship stability weight w1 to obtain the first constraint term C1 = w1 * D_offset. The ship's dynamic offset parameter reflects the instability degree of the ship's movement. By multiplying it with the ship stability weight, the importance of ship stability in the multi-objective constraint function is emphasized.

[0087] Step S1343: Calculate the product of the environmental interference intensity parameter and the environmental interference compensation weight to generate a second constraint term.

[0088] Calculate the product of the environmental interference intensity parameter I_env and the environmental interference compensation weight w2 to obtain the second constraint term C2 = w2 * I_env. The environmental interference intensity parameter reflects the influence degree of environmental factors on ship mooring. After multiplying it with the environmental interference compensation weight, the role of environmental interference compensation in the multi-objective constraint function is highlighted. Here, the ship's dynamic offset parameter D_offset and the environmental interference intensity parameter I_env may have been normalized in previous steps. If not, it is necessary to ensure that their products with the weight coefficients are reasonable in terms of dimension and numerical range to ensure the effectiveness of the multi-objective constraint function. For example, if the unit of the ship's dynamic offset parameter is meters per second and the weight coefficient is dimensionless, the unit of the first constraint term after multiplication is still meters per second; similarly, if the unit of the environmental interference intensity parameter is Newton and it is multiplied by the dimensionless environmental interference compensation weight, the unit of the second constraint term is still Newton.

[0089] Step S1344: Calculate the product of the mooring energy consumption distribution parameter and the energy consumption optimization weight to generate a third constraint term.

[0090] Multiply the mooring energy consumption distribution parameter E_total by the energy consumption optimization weight w3 to obtain the third constraint term C3 = w3 * E_total. The mooring energy consumption distribution parameter reflects the total energy consumption situation during the ship mooring process. By multiplying it with the energy consumption optimization weight, the importance of energy consumption optimization in the multi-objective constraint function is reflected. Since the unit of the mooring energy consumption distribution parameter is joule and the energy consumption optimization weight is dimensionless, the unit of the third constraint term is joule, ensuring the consistency of dimensions.

[0091] Step S1345: Normalize and add the first constraint term, the second constraint term, and the third constraint term to obtain the total loss value of the multi-objective constraint function.

[0092] To reasonably sum up the first constraint term, the second constraint term, and the third constraint term, it is necessary to normalize them first. Assume that the maximum value of the first constraint term is C1_max and the minimum value is C1_min. The normalized first constraint term C1_norm = (C1 - C1_min) / (C1_max - C1_min); similarly, for the second constraint term, assume its maximum value is C2_max and the minimum value is C2_min. The normalized second constraint term C2_norm = (C2 - C2_min) / (C2_max - C2_min); for the third constraint term, assume its maximum value is C3_max and the minimum value is C3_min. The normalized third constraint term C3_norm = (C3 - C3_min) / (C3_max - C3_min). The purpose of normalization is to eliminate the differences in dimension and numerical range between different constraint terms, making them comparable when added. After normalization, the total loss value L of the multi-objective constraint function is L = C1_norm + C2_norm + C3_norm. Here, the normalized constraint terms are all dimensionless, and the total loss value obtained by addition is also dimensionless, ensuring the unity of dimension in the calculation process.

[0093] Step S1346: Iteratively adjust the parameter values in the set of optimization parameters through the gradient descent algorithm to minimize the total loss value until it converges to the preset accuracy range.

[0094] The gradient descent algorithm is an iterative optimization algorithm. Its core idea is to update the parameters along the negative gradient direction of the objective function to gradually reduce the value of the objective function. In this embodiment, the goal is to minimize the total loss value L of the multi-objective constraint function. First, initialize the parameter values in the set of optimization parameters, denoted as p = (p1, p2, p3), where p1, p2, and p3 correspond to the first optimization parameter, the second optimization parameter, and the third optimization parameter respectively. Then, calculate the gradient ∇L(p) of the total loss value L with respect to the parameter p. The gradient represents the rate of change of the total loss value in the parameter space. According to the update rule of the gradient descent algorithm, the update formula for the parameter p is p_new = p - α * ∇L(p), where α is the learning rate, which controls the step size of each parameter update. If the learning rate is too large, the algorithm may not converge; if the learning rate is too small, the convergence speed will be slow. In each iteration, update the value of the parameter p according to the update formula and recalculate the total loss value L. Repeat this process until the change in the total loss value L is less than the preset accuracy range. At this time, it is considered that the algorithm converges, and the obtained parameter p is the set of optimized parameters for the ship's automatic mooring control strategy.

[0095] Step S135: Perform a feasibility verification process on the set of optimization parameters. The verification content includes the ship attitude stability threshold, the safe range of cable tension, and the energy consumption reduction rate, and generate a set of optimized parameters that pass the verification.

[0096] After obtaining the optimized parameter set, it is necessary to perform a feasibility verification process. This is to ensure that the generated optimized parameter set is feasible in practical applications and will not cause safety problems or non-compliance with energy consumption requirements during the ship mooring process.

[0097] For the verification of the ship attitude stability threshold, apply the optimized parameter set to the ship mooring model, simulate the ship mooring process, and calculate the change in the attitude angle of the ship under these parameters. Compare the calculated attitude angle with the preset ship attitude stability threshold. If the ship attitude angle is within the stability threshold range, it is considered that the optimized parameter set meets the ship attitude stability requirements; otherwise, the optimized parameter set needs to be adjusted.

[0098] For the verification of the safety range of cable tension, also apply the optimized parameter set to the ship mooring model and calculate the tension value of each cable during the mooring process. Compare the calculated cable tension value with the preset safety range of cable tension. If the tension values of all cables are within the safety range, it is considered that the optimized parameter set meets the cable tension safety requirements; otherwise, the optimized parameter set needs to be corrected.

[0099] For the verification of the energy consumption reduction rate, calculate the actual energy consumption during the ship mooring process according to the optimized parameter set, compare it with the energy consumption before optimization, and calculate the energy consumption reduction rate. Compare the calculated energy consumption reduction rate with the preset energy consumption reduction rate target. If the energy consumption reduction rate reaches or exceeds the target value, it is considered that the optimized parameter set meets the energy consumption reduction requirements; otherwise, the optimized parameter set needs to be further optimized.

[0100] Only when the optimized parameter set simultaneously meets the requirements of the ship attitude stability threshold, the safety range of cable tension, and the energy consumption reduction rate, is it considered that the optimized parameter set passes the feasibility verification, and the verified optimized parameter set is generated. This verified optimized parameter set will be used to dynamically adjust the actuator parameters of the ship automatic mooring control system later.

[0101] Step S140: Dynamically adjust the actuator parameters of the ship automatic mooring control system according to the optimized parameter set, generate the adjusted ship automatic mooring control command, and real-time monitor the ship attitude offset and cable tension fluctuation during the mooring process.

[0102] In this step, based on the verified optimized parameter set, dynamically adjust the actuator parameters of the ship automatic mooring control system to achieve safe and efficient mooring of the ship, and real-time monitor the key parameters during the mooring process.

[0103] Step S141: Calculate the target thrust vector and action duration of the ship's thruster according to the ship displacement adjustment amount in the optimization parameter set, and generate a thruster control command.

[0104] The ship displacement adjustment amount in the optimization parameter set reflects the distance and direction that the ship needs to move. Based on this, calculate the target thrust vector and action duration of the ship's thruster. The target thrust vector of the ship's thruster determines the magnitude and direction of the force that the thruster needs to exert to achieve the ship displacement adjustment. Assume that the ship displacement adjustment amount is ΔS and the mass of the ship is m. According to Newton's second law F = ma (described in words here: force equals mass times acceleration), the acceleration a required to achieve this displacement adjustment can be calculated. Considering factors such as the resistance of the ship in water, the calculated acceleration needs to be corrected. Then, based on the corrected acceleration and the dynamic model of the ship, calculate the target thrust vector F_target of the ship's thruster. The direction of the target thrust vector is related to the direction of the ship displacement adjustment, and the magnitude is determined according to factors such as the acceleration and the ship mass.

[0105] The action duration t of the ship's thruster needs to be determined according to the ship displacement adjustment amount and the target thrust vector. It can be calculated through the kinematic model of the ship. Assume that the ship starts from the initial state and accelerates under the action of the target thrust vector. When it reaches a certain speed, it may be necessary to adjust the thrust or maintain a uniform motion until the target displacement is reached. By analyzing and calculating the ship's motion process, determine the time t that the thruster needs to act continuously. According to the calculated target thrust vector and action duration, generate a thruster control command, which will be sent to the ship's thruster to control its output thrust and action time.

[0106] Step S142: Adjust the output tension value and adjustment rate of the cable tension adjustment mechanism according to the environmental interference compensation force in the optimization parameter set, and generate a cable tension control command.

[0107] The environmental interference compensation force in the optimization parameter set is used to adjust the output tension value and adjustment rate of the cable tension adjustment mechanism. The environmental interference compensation force reflects the additional force that needs to be provided through cable tension adjustment to offset the influence of environmental factors on ship mooring. According to the magnitude and direction of the environmental interference compensation force, calculate the tension value that each cable needs to be adjusted. Assume that the environmental interference compensation force is F_compensation and the ship mooring uses n cables. According to the cable layout and force analysis, distribute the environmental interference compensation force to each cable to obtain the tension increment ΔT_i (i = 1, 2,..., n) that each cable needs to be adjusted.

[0108] The adjustment rate of the cable tension adjustment mechanism also needs to be adjusted according to the changes in environmental disturbances. If the environmental disturbances change rapidly, it is necessary to increase the adjustment rate of the cable tension adjustment mechanism to quickly respond to environmental changes; if the environmental disturbances are relatively stable, the adjustment rate can be appropriately reduced. According to the calculated tension increment and adjustment rate of each cable, a cable tension control command is generated, and this command will be sent to the cable tension adjustment mechanism to control its output tension value and adjustment rate.

[0109] Step S143: Send the thruster control command and the cable tension control command to the actuator of the ship automatic mooring control system to trigger the coordinated action of the thruster and the cable tension adjustment mechanism.

[0110] Send the generated thruster control command and cable tension control command to the actuator of the ship automatic mooring control system, that is, the ship thruster and the cable tension adjustment mechanism. The ship thruster outputs the corresponding thrust and action time according to the thruster control command to push the ship to adjust its displacement; the cable tension adjustment mechanism adjusts the tension value and adjustment rate of the cable according to the cable tension control command to compensate for the influence of environmental disturbances on ship mooring. The thruster and the cable tension adjustment mechanism need to act in coordination to jointly achieve the safe mooring of the ship. For example, when the thruster pushes the ship to move, the cable tension adjustment mechanism needs to correspondingly adjust the cable tension to ensure the stable attitude and mooring safety of the ship.

[0111] Step S144: Collect the actual output thrust of the actuator, the actual cable tension value and the real-time displacement of the ship in real time to generate execution status monitoring data.

[0112] During the process of the thruster and the cable tension adjustment mechanism executing the control command, collect the actual output thrust of the actuator, the actual cable tension value and the real-time displacement of the ship in real time. The actual output thrust of the thruster can be measured in real time through a thrust sensor installed on the thruster; the actual cable tension value can be measured in real time through a tension sensor installed on the cable; the real-time displacement of the ship can be obtained in real time through the positioning system of the ship. Organize and record these collected data to generate execution status monitoring data. These data reflect the actual working status of the actuator and the real-time movement of the ship, providing a basis for subsequent feedback correction processing.

[0113] Step S145: Compare the execution status monitoring data with the target parameters in the optimization parameter set. If the deviation exceeds the preset threshold, trigger the feedback correction process.

[0114] Compare the execution status monitoring data with the target parameters in the optimization parameter set. The target parameters in the optimization parameter set include the target thrust vector and target action duration of the ship's thruster, the target tension value and target adjustment rate of the cable, and the target displacement of the ship, etc. For the actual output thrust of the thruster, compare it with the target thrust vector and calculate the thrust error; for the actual cable tension value, compare it with the target tension value and calculate the tension error; for the real-time displacement of the ship, compare it with the target displacement and calculate the displacement error.

[0115] Set preset thresholds, including thrust error threshold, tension error threshold, displacement error threshold, etc. If the calculated error exceeds the corresponding preset threshold, it is considered that there is a large deviation between the execution state and the target state, and feedback correction processing is triggered. The purpose of the feedback correction processing is to adjust the optimization parameter set to correct the deviation in the execution process and make the ship mooring process return to the expected state.

[0116] Step S1451: It is detected that the deviation between the real-time displacement of the ship and the target displacement continuously exceeds the first threshold for T1 seconds.

[0117] When it is detected that the deviation between the real-time displacement of the ship and the target displacement continuously exceeds the first threshold for T1 seconds, this is a condition for triggering the feedback correction processing. Continuously exceeding the first threshold for T1 seconds means that the displacement deviation of the ship is not a short-term fluctuation, but is in an abnormal state for a long time, which may affect the mooring safety of the ship. For example, the first threshold can be set according to the safety requirements and actual situation of ship mooring, assumed to be ΔS_threshold_1; T1 seconds can be determined according to factors such as the motion characteristics of the ship and the mooring environment, assumed to be 30 seconds. When the deviation |ΔS_real - ΔS_target| between the real-time displacement of the ship and the target displacement > ΔS_threshold_1 lasts for 30 seconds, the feedback correction processing is triggered.

[0118] Step S1452: It is detected that the standard deviation of the cable tension fluctuation exceeds the second threshold.

[0119] The standard deviation of the cable tension fluctuation reflects the degree of cable tension fluctuation. When it is detected that the standard deviation of the cable tension fluctuation exceeds the second threshold, it indicates that the cable tension is unstable, which may pose a safety hazard to ship mooring. For example, the second threshold can be set according to factors such as the material, strength, and mooring requirements of the cable, assumed to be σ_T_threshold. Through statistical analysis of the cable tension data over a period of time, calculate the standard deviation σ_T of the cable tension fluctuation. If σ_T > σ_T_threshold, the feedback correction processing is triggered.

[0120] Step S1453: It is detected that the error rate between the actual output thrust of the thruster and the target thrust exceeds the third threshold.

[0121] The error rate between the actual output thrust of the thruster and the target thrust reflects the control accuracy of the thruster. When it is detected that the error rate between the actual output thrust of the thruster and the target thrust exceeds the third threshold, it indicates that there is a large deviation between the actual working state of the thruster and the expectation, and the displacement adjustment target of the ship may not be achieved. For example, the third threshold can be set according to factors such as the performance of the thruster and the mooring requirements, and is assumed to be ε_F_threshold. The error rate ε_F between the actual output thrust of the thruster and the target thrust can be calculated by the formula ε_F = |F_real - F_target| / F_target (the formula is described in words here). If ε_F > ε_F_threshold, then the feedback correction process is triggered.

[0122] If any of the above conditions is met, a feedback correction trigger signal is generated and the feedback correction process is started. The feedback correction process will adjust the set of optimization parameters to correct the deviation during the execution process and ensure the safety and stability of ship mooring.

[0123] Step S150: Based on the ship attitude offset and the mooring line tension fluctuation, perform a feedback correction process on the set of optimization parameters to obtain a corrected ship automatic mooring control strategy, and update the corrected ship automatic mooring control strategy to the ship automatic mooring control system.

[0124] In this step, the set of optimization parameters is feedback-corrected according to the ship attitude offset and the mooring line tension fluctuation to improve the accuracy and stability of the ship automatic mooring control strategy.

[0125] Step S151: Obtain the real-time monitored ship attitude offset, calculate the deviation degree between the ship attitude offset and the preset safe attitude range, and generate an attitude correction coefficient.

[0126] Real-time monitor the ship attitude offset. The ship attitude offset can be measured by an attitude sensor installed on the ship, which reflects the difference between the current ship attitude and the ideal attitude. The preset safe attitude range is determined according to the safety requirements and design standards of ship mooring. When the ship attitude is within this range, the stability of mooring can be ensured. Calculate the deviation degree between the ship attitude offset and the preset safe attitude range. Assume the ship attitude offset is θ_offset and the preset safe attitude range is [θ_min, θ_max], then the deviation degree d_θ can be calculated by the formula d_θ=(θ_offset - θ_min) / (θ_max - θ_min) (when θ_offset < θ_min) or d_θ=(θ_max - θ_offset) / (θ_max - θ_min) (when θ_offset > θ_max) (describe the formula in words here). Generate an attitude correction coefficient k_θ according to the deviation degree. The attitude correction coefficient is used to adjust the parameters related to the ship attitude in the optimization parameter set. For example, the attitude correction coefficient can be obtained through linear or non-linear mapping according to the size of the deviation degree. When the deviation degree is larger, the attitude correction coefficient is larger to adjust the optimization parameter set more strongly.

[0127] Step S152: Obtain the real-time monitored cable tension fluctuation amount, extract the fluctuation frequency and amplitude of the cable tension, and generate a tension stability evaluation parameter.

[0128] Real-time monitor the cable tension fluctuation amount, and collect the cable tension data through a tension sensor installed on the cable. Perform signal processing on the collected cable tension data to extract the fluctuation frequency and amplitude of the cable tension. The fluctuation frequency reflects the speed of change of the cable tension, and the amplitude reflects the amplitude of change of the cable tension. For example, methods such as Fourier transform can be used to perform spectral analysis on the cable tension data to obtain the fluctuation frequency components of the cable tension; the amplitude of the cable tension can be obtained by calculating the difference between the maximum and minimum values of the data. Generate a tension stability evaluation parameter s_T according to the fluctuation frequency and amplitude of the cable tension. The tension stability evaluation parameter is used to evaluate the stability degree of the cable tension. For example, the fluctuation frequency and amplitude can be weighted and combined to obtain the tension stability evaluation parameter, such as s_T = w_f * f_T + w_A * A_T, where w_f and w_A are weight coefficients, f_T is the fluctuation frequency, and A_T is the amplitude.

[0129] Step S153: Input the attitude correction coefficient and the tension stability evaluation parameter into a preset fuzzy PID controller to generate a feedback correction parameter.

[0130] Step S1531: Perform a normalization mapping process on the attitude correction coefficient, map the numerical range of the attitude correction coefficient to a preset fuzzy domain interval, and generate a first fuzzy input quantity.

[0131] Perform a normalization mapping process on the attitude correction coefficient k_θ. The preset fuzzy domain interval is a predefined range, usually [0, 1]. Assume that the original numerical range of the attitude correction coefficient k_θ is [k_θ_min, k_θ_max]. Through the normalization formula k_θ_norm=(k_θ - k_θ_min) / (k_θ_max - k_θ_min) (describe the formula in words here), map the numerical range of the attitude correction coefficient to the preset fuzzy domain interval to obtain the first fuzzy input quantity k_θ_norm. The purpose of the normalization process is to make the attitude correction coefficient comparable and reasonable in the fuzzy inference process.

[0132] Step S1532: Perform a normalization mapping process on the tension stability evaluation parameter, map the numerical range of the tension stability evaluation parameter to the fuzzy domain interval, and generate a second fuzzy input quantity.

[0133] Similarly, perform a normalization mapping process on the tension stability evaluation parameter s_T. Assume that the original numerical range of the tension stability evaluation parameter s_T is [s_T_min, s_T_max]. Through the normalization formula s_T_norm=(s_T - s_T_min) / (s_T_max - s_T_min) (describe the formula in words here), map the numerical range of the tension stability evaluation parameter to the preset fuzzy domain interval to obtain the second fuzzy input quantity s_T_norm.

[0134] Step S1533: Input the first fuzzy input quantity and the second fuzzy input quantity into a preset fuzzy rule base, match the corresponding relationship between the predefined fuzzy conditions and fuzzy output quantities in the fuzzy rule base, and generate a fuzzy output set of the proportional parameter adjustment amount, integral parameter adjustment amount, and derivative parameter adjustment amount.

[0135] Input the normalized first fuzzy input quantity k_θ_norm and the second fuzzy input quantity s_T_norm into the preset fuzzy rule base. The fuzzy rule base contains a series of predefined fuzzy conditions and corresponding fuzzy output quantities. These fuzzy conditions are set based on the experience and knowledge in the ship mooring process. For example, if the attitude correction coefficient is large and the tension stability evaluation parameter is small, it indicates that the ship attitude deviation is large and the cable tension is unstable. At this time, the control parameters need to be adjusted significantly.

[0136] Fuzzy rules are usually expressed in the form of "if... then...". For example, a fuzzy rule might be "if k_θ_norm is 'large' and s_T_norm is'small', then the adjustment amount of the proportional parameter is 'large', the adjustment amount of the integral parameter is'medium', and the adjustment amount of the derivative parameter is'small'". Here, "large","medium","small", etc. are the linguistic values of fuzzy sets. In the fuzzy rule base, there are multiple such rules. By matching the first fuzzy input quantity and the second fuzzy input quantity of the input with the conditional parts of these rules, it is determined which rules are triggered.

[0137] For each triggered rule, according to its corresponding fuzzy output quantity, the corresponding fuzzy output is calculated through a fuzzy inference method (such as the Mamdani inference method). Finally, the fuzzy outputs of all triggered rules are synthesized to obtain the fuzzy output set of the adjustment amount of the proportional parameter, the adjustment amount of the integral parameter, and the adjustment amount of the derivative parameter. Each element in this fuzzy output set is a fuzzy set, representing the adjustment amount of the parameter to different degrees.

[0138] Step S1534: Defuzzify the adjustment amount of the proportional parameter, the adjustment amount of the integral parameter, and the adjustment amount of the derivative parameter in the fuzzy output set, and reverse-map the fuzzy domain interval of the fuzzy output quantity to the actual dimension range to generate the actual adjustment amount of the proportional parameter, the actual adjustment amount of the integral parameter, and the actual adjustment amount of the derivative parameter.

[0139] After obtaining the fuzzy output set, defuzzification processing is required to reverse-map the fuzzy output quantity from the fuzzy domain interval to the actual dimension range. Common defuzzification methods include the centroid method, the maximum membership degree method, etc. Taking the centroid method as an example, for the fuzzy output set of the adjustment amount of the proportional parameter, first determine the membership function of this fuzzy set, and then calculate the centroid position of the region enclosed by the membership function curve and the abscissa. The abscissa value corresponding to this centroid position is the value of the defuzzified adjustment amount of the proportional parameter in the fuzzy domain interval.

[0140] Next, reverse-map this value to the actual dimension range. Assume that the minimum value of the adjustment amount of the proportional parameter in the actual dimension range is ΔK_p_min, the maximum value is ΔK_p_max, the range in the fuzzy domain interval is [0, 1], and the value in the fuzzy domain interval after defuzzification is ΔK_p_norm. Then the actual adjustment amount of the proportional parameter ΔK_p can be calculated by the formula ΔK_p = ΔK_p_min + ΔK_p_norm * (ΔK_p_max - ΔK_p_min).

[0141] Using the same method, the fuzzy output sets of the integral parameter adjustment amount and the differential parameter adjustment amount are defuzzified to obtain the actual integral parameter adjustment amount ΔK_i and the actual differential parameter adjustment amount ΔK_d respectively. In this way, the fuzzy parameter adjustment amount is converted into an adjustment amount with actual physical meaning, which is used for subsequent correction of the parameters of the fuzzy PID controller.

[0142] Step S1535: According to the actual proportional parameter adjustment amount, the actual integral parameter adjustment amount, and the actual differential parameter adjustment amount, the initial proportional coefficient, the initial integral coefficient, and the initial differential coefficient of the fuzzy PID controller are superimposed and corrected to obtain the corrected proportional coefficient, the corrected integral coefficient, and the corrected differential coefficient.

[0143] After obtaining the actual proportional parameter adjustment amount ΔK_p, the actual integral parameter adjustment amount ΔK_i, and the actual differential parameter adjustment amount ΔK_d, the initial proportional coefficient K_p0, the initial integral coefficient K_i0, and the initial differential coefficient K_d0 of the fuzzy PID controller are superimposed and corrected. The corrected proportional coefficient K_p = K_p0 + ΔK_p, the corrected integral coefficient K_i = K_i0 + ΔK_i, and the corrected differential coefficient K_d = K_d0 + ΔK_d. It should be noted here that the superimposed correction should ensure the consistency of dimensions. The dimensions of the initial coefficient and the adjustment amount should be the same. For example, if the dimension of the initial proportional coefficient is dimensionless, then the actual proportional parameter adjustment amount should also be dimensionless, so that the corrected proportional coefficient obtained by adding them is also dimensionless.

[0144] Step S1536: Linearly superimpose the corrected proportional coefficient, the corrected integral coefficient, and the corrected differential coefficient according to a preset weight combination relationship to generate the feedback correction parameter.

[0145] The preset weight combination relationship is used to linearly superimpose the corrected proportional coefficient K_p, the corrected integral coefficient K_i, and the corrected differential coefficient K_d to generate the feedback correction parameter. Suppose the preset weights are w_p, w_i, and w_d respectively, and w_p + w_i + w_d = 1. Then the feedback correction parameter F_correction = w_p * K_p + w_i * K_i + w_d * K_d. Here, the weights are dimensionless, and the dimensions of the corrected coefficients and the feedback correction parameter should be determined according to specific control requirements and physical meanings to ensure the unity of dimensions in the whole calculation process.

[0146] Step S154: Dynamically adjust the thruster thrust, the cable tension adjustment rate, and the energy consumption allocation weight in the optimization parameter set according to the feedback correction parameter to obtain the corrected automatic ship mooring control strategy.

[0147] After obtaining the feedback correction parameters, the thruster thrust, cable tension adjustment rate, and energy consumption distribution weight in the optimization parameter set are dynamically adjusted according to them. For the thruster thrust, the feedback correction parameters may increase or decrease the thruster thrust to correct the attitude deviation and displacement deviation of the ship. For example, if the feedback correction parameters indicate that the ship's attitude deviation is large and the thruster thrust needs to be increased to adjust the ship's attitude, then according to the mapping relationship between the feedback correction parameters and the thruster thrust adjustment, a new thruster thrust value is calculated.

[0148] For the cable tension adjustment rate, the feedback correction parameters can adjust its magnitude to better cope with the fluctuations of the cable tension. If the feedback correction parameters show that the cable tension is unstable, it may be necessary to increase the cable tension adjustment rate to speed up the adjustment of the cable tension. Similarly, according to the mapping relationship between the feedback correction parameters and the cable tension adjustment rate adjustment, a new cable tension adjustment rate is calculated.

[0149] For the energy consumption distribution weight, the feedback correction parameters can redistribute the weights of the thruster energy consumption and the cable adjustment energy consumption. For example, if the feedback correction parameters indicate that the current thruster energy consumption is too high and the cable adjustment can replace the role of the thruster to a certain extent, then the weight of the thruster energy consumption can be appropriately reduced and the weight of the cable adjustment energy consumption can be increased. By dynamically adjusting these parameters in the optimization parameter set, a corrected automatic ship mooring control strategy is obtained.

[0150] Step S155: Match the similarity between the corrected automatic ship mooring control strategy and the historical successful strategy. If the similarity is lower than the preset threshold, an artificial intervention instruction is triggered.

[0151] Match the similarity between the corrected automatic ship mooring control strategy and the historical successful strategy. The historical successful strategy is the control strategy for successful mooring extracted from the historical mooring database under similar environments and ship states. The similarity matching can be carried out from multiple aspects, such as comparing the magnitude and change trend of the thruster thrust, the setting of the cable tension adjustment rate, the energy consumption distribution weight, etc.

[0152] Some similarity measurement methods can be adopted, such as Euclidean distance, cosine similarity, etc. Taking the Euclidean distance as an example, the corrected automatic ship mooring control strategy and the historical successful strategy are represented as multi-dimensional vectors, and the Euclidean distance between them is calculated. The smaller the Euclidean distance, the more similar the two strategies are.

[0153] A similarity threshold is preset. If the calculated similarity is lower than this threshold, it indicates that there is a significant difference between the corrected ship automatic mooring control strategy and the historical successful strategy, and there may be a relatively high risk. At this time, an artificial intervention instruction is triggered to notify the operator to perform artificial intervention on the ship mooring process to ensure the safety of ship mooring. The operator can further adjust and optimize the control strategy according to the actual situation.

[0154] Figure 2 FIG. shows a schematic diagram of exemplary hardware and software components of a ship automatic mooring control strategy optimization system 100 based on multi-source data that can implement the idea of the present application. For example, the processor 120 can be used on the ship automatic mooring control strategy optimization system 100 based on multi-source data and is used to execute the functions in the present application.

[0155] The ship automatic mooring control strategy optimization system 100 based on multi-source data can be a general-purpose server or a special-purpose server, both of which can be used to implement the ship automatic mooring control strategy optimization method based on multi-source data of the present application. Although only one server is shown in the present application, for convenience, the functions described in the present application can be implemented in a distributed manner on multiple similar platforms to balance the processing load.

[0156] For example, the ship automatic mooring control strategy optimization system 100 based on multi-source data can include a network port 110 connected to the network, one or more processors 120 for executing program instructions, a communication bus 130, and different forms of storage media 140, such as disks, ROM, or RAM, or any combination thereof. Exemplarily, the ship automatic mooring control strategy optimization system 100 based on multi-source data can also include program instructions stored in ROM, RAM, or other types of non-transitory storage media, or any combination thereof. According to these program instructions, the method of the present application can be implemented. The ship automatic mooring control strategy optimization system 100 based on multi-source data also includes an I / O interface 150 between the computer and other input / output devices.

[0157] For ease of explanation, only one processor is described in the ship automatic mooring control strategy optimization system 100 based on multi-source data. However, it should be noted that the ship automatic mooring control strategy optimization system 100 in the present application may also include multiple processors. Therefore, the steps executed by one processor described in the present application may also be jointly executed or separately executed by multiple processors. For example, if the processor of the ship automatic mooring control strategy optimization system 100 based on multi-source data executes step A and step B, it should be understood that step A and step B may also be jointly executed by two different processors or separately executed in one processor. For example, the first processor executes step A, the second processor executes step B, or the first processor and the second processor jointly execute steps A and B.

[0158] In addition, an embodiment of the present invention further provides a readable storage medium, in which computer-executable instructions are preset. When the processor executes the computer-executable instructions, the above-mentioned ship automatic mooring control strategy optimization method based on multi-source data is implemented.

[0159] It should be noted that, in order to simplify the description of the present invention disclosure and thus help the understanding of one or more embodiments of the present invention, in the foregoing description of the embodiments of the present invention, sometimes multiple features are merged into one embodiment, drawing or description thereof.

Claims

1. An optimization method for ship automatic mooring control strategy based on multi-source data, characterized in that, The method includes: Obtaining a multi-source perception data set of a target ship, and performing data preprocessing on the multi-source perception data set to obtain a preprocessed multi-source perception data set, where the multi-source perception data set includes ship dynamic parameters, environmental interference parameters, and historical mooring parameters; Performing dynamic feature parameter extraction processing on the preprocessed multi-source perception data set based on a sliding time window to generate ship dynamic offset parameters, environmental interference intensity parameters, and mooring energy consumption distribution parameters; Invoking a dynamic optimization strategy generation model, and generating an optimization parameter set of the ship automatic mooring control strategy according to the difference degree between the ship dynamic offset parameter and a preset ship safe mooring threshold, the matching degree between the environmental interference intensity parameter and a preset environmental interference threshold, and the deviation degree between the mooring energy consumption distribution parameter and a preset energy consumption optimization target; Dynamically adjusting the actuator parameters of the ship automatic mooring control system according to the optimization parameter set to generate an adjusted ship automatic mooring control instruction, and real-time monitoring the ship attitude offset amount and cable tension fluctuation amount during the mooring process; Performing feedback correction processing on the optimization parameter set based on the ship attitude offset amount and cable tension fluctuation amount to obtain a corrected ship automatic mooring control strategy, and updating the corrected ship automatic mooring control strategy to the ship automatic mooring control system.

2. The optimization method for the automatic mooring control strategy of a ship based on multi-source data according to claim 1, wherein The obtaining of the multi-source perception data set of the target ship includes: Obtaining ship dynamic parameters through ship's own sensors, where the ship dynamic parameters include ship real-time displacement amount, ship attitude angle change rate, ship mass distribution parameters, and cable tension distribution parameters; Obtaining environmental interference parameters through port environment perception devices, where the environmental interference parameters include water flow velocity gradient distribution parameters, wind direction and wind force vector parameters, and wave height change parameters; Extracting historical mooring parameters from a historical mooring database, where the historical mooring parameters include ship displacement adjustment amounts, cable tension optimization values, and environmental interference thresholds in historical successful mooring cases; Performing timestamp alignment processing on the ship dynamic parameters, the environmental interference parameters, and the historical mooring parameters to generate a time-synchronized multi-source perception data set; Performing data preprocessing on the time-synchronized multi-source perception data set, where the data preprocessing includes data filtering and noise reduction processing, missing data interpolation and compensation processing, and multi-source data fusion processing, to obtain a preprocessed multi-source perception data set.

3. The method for optimizing the automatic mooring control strategy of a ship based on multi-source data according to claim 1, wherein The performing of dynamic feature parameter extraction processing on the preprocessed multi-source perception data set based on a sliding time window to generate ship dynamic offset parameters, environmental interference intensity parameters, and mooring energy consumption distribution parameters includes: Determining the window length and sliding step size parameters of the sliding time window, and dividing the preprocessed multi-source perception data set into multiple window data subsets according to the time series; Extracting the displacement change rate of the ship dynamic parameters in each window data subset, calculating the ratio of the absolute value of the difference between the ship real-time displacement amounts at adjacent timestamps to the time interval, and generating a ship displacement instantaneous velocity sequence; Perform range statistical analysis within a window on the instantaneous velocity sequence of the ship's displacement, and extract the difference between the maximum value and the minimum value as the ship's dynamic offset parameter; Perform vector synthesis processing on the environmental interference parameters in each window data subset: Convert the water flow velocity gradient distribution parameter into the water flow force exerted on the ship through a hydrodynamics model; Convert the wind direction and wind force vector parameter into wind force through a wind pressure formula; Convert the wave height change parameter into wave force by combining the wave period and the ship's draft area; Project and superimpose the water flow force, wind force, and wave force in the spatial direction to generate an environmental interference resultant force vector; Calculate the moving average of the modulus of the environmental interference resultant force vector changing with time to generate an environmental interference intensity parameter; Perform energy consumption weight allocation on the historical mooring parameters in each window data subset: Take the product of the cable tension distribution parameter and the cable adjustment rate as the cable adjustment power, and integrate and accumulate the power within the time window to generate the cable adjustment energy consumption; Integrate and accumulate the thruster power parameter according to the duration within the time window to generate the thruster energy consumption; Combine the cable adjustment energy consumption and the thruster energy consumption according to a preset weight to generate a mooring energy consumption distribution parameter; Normalize and splice the ship's dynamic offset parameter, environmental interference intensity parameter, and mooring energy consumption distribution parameter in the order of time windows to form a dynamic characteristic parameter set.

4. The method for optimizing the automatic mooring control strategy of a ship based on multi-source data according to claim 1, characterized in that The dynamic optimization strategy generation model is called to generate, according to the difference degree between the ship's dynamic offset parameter and the preset ship safety mooring threshold, the matching degree between the environmental interference intensity parameter and the preset environmental interference threshold, and the deviation degree between the mooring energy consumption distribution parameter and the preset energy consumption optimization target, an optimization parameter set for the ship's automatic mooring control strategy, including: Input the ship's dynamic offset parameter into a preset genetic algorithm optimization module to generate a first optimization parameter for the ship's displacement adjustment amount, and the first optimization parameter is used to control the output thrust and direction of the ship's thruster; Input the environmental interference intensity parameter into a preset fuzzy control module to generate a second optimization parameter for the environmental interference compensation force, and the second optimization parameter is used to adjust the distribution weight of the cable tension; Input the mooring energy consumption distribution parameter into a preset particle swarm optimization module to generate a third optimization parameter for minimizing the mooring energy consumption, and the third optimization parameter is used to optimize the matching relationship between the thruster power and the cable tension adjustment rate; Construct a multi-objective constraint function according to the first optimization parameter, the second optimization parameter, and the third optimization parameter, and solve the optimal solution of the multi-objective constraint function through a gradient descent algorithm to obtain an optimization parameter set for the ship's automatic mooring control strategy; Perform feasibility verification processing on the optimization parameter set, and the verification content includes the ship attitude stability threshold, the cable tension safety range, and the energy consumption reduction rate, to generate a verified optimization parameter set; Among them, the dynamic optimization strategy generation model includes the genetic algorithm optimization module, the fuzzy control module, the particle swarm optimization module, and the multi-objective constraint function.

5. The method for optimizing the automatic mooring control strategy of a ship based on multi-source data according to claim 4, wherein Solving the optimal solution of the multi-objective constraint function through the gradient descent algorithm to obtain an optimized parameter set for the ship automatic mooring control strategy, including: Setting the weight coefficients of the multi-objective constraint function, where the weight coefficients include the ship stability weight, the environmental disturbance compensation weight, and the energy consumption optimization weight; Calculating the product between the ship dynamic offset parameter and the ship stability weight to generate a first constraint term; Calculating the product between the environmental disturbance intensity parameter and the environmental disturbance compensation weight to generate a second constraint term; Calculating the product between the mooring energy consumption distribution parameter and the energy consumption optimization weight to generate a third constraint term; Normalizing and adding the first constraint term, the second constraint term, and the third constraint term to obtain the total loss value of the multi-objective constraint function; Iteratively adjusting the parameter values in the optimized parameter set through the gradient descent algorithm to minimize the total loss value until it converges to a preset accuracy range.

6. The method for optimizing the automatic mooring control strategy of a ship based on multi-source data according to claim 1, wherein Dynamically adjusting the actuator parameters of the ship automatic mooring control system according to the optimized parameter set to generate an adjusted ship automatic mooring control command, including: Calculating the target thrust vector and the action duration of the ship thruster according to the ship displacement adjustment amount in the optimized parameter set to generate a thruster control command; Adjusting the output tension value and the adjustment rate of the cable tension adjustment mechanism according to the environmental disturbance compensation force in the optimized parameter set to generate a cable tension control command; Sending the thruster control command and the cable tension control command to the actuators of the ship automatic mooring control system to trigger the coordinated action of the thrusters and the cable tension adjustment mechanism; Real-time collecting the actual output thrust of the actuator, the actual cable tension value, and the ship real-time displacement amount to generate execution status monitoring data; Comparing the execution status monitoring data with the target parameters in the optimized parameter set, and if the deviation exceeds the preset threshold, triggering the feedback correction process.

7. The method for optimizing the automatic mooring control strategy of a ship based on multi-source data according to claim 6, wherein The conditions for triggering the feedback correction process include: Detecting that the deviation between the ship real-time displacement amount and the target displacement amount continuously exceeds the first threshold for T1 seconds; Detecting that the standard deviation of the cable tension fluctuation amount exceeds the second threshold; Detecting that the error rate between the actual output thrust of the thruster and the target thrust exceeds the third threshold; If any condition is satisfied, generating a feedback correction trigger signal and starting the feedback correction process.

8. The method for optimizing the automatic mooring control strategy of a ship based on multi-source data according to claim 1, characterized in that Performing a feedback correction process on the optimized parameter set based on the ship attitude offset amount and the cable tension fluctuation amount to obtain a corrected ship automatic mooring control strategy, including: Obtaining the real-time monitored ship attitude offset amount, calculating the deviation degree between the ship attitude offset amount and the preset safe attitude range, and generating an attitude correction coefficient; Obtaining the real-time monitored cable tension fluctuation amount, extracting the fluctuation frequency and amplitude of the cable tension, and generating a tension stability evaluation parameter; Inputting the attitude correction coefficient and the tension stability evaluation parameter into a preset fuzzy PID controller to generate feedback correction parameters; Dynamically adjust the thruster thrust, cable tension adjustment rate, and energy consumption allocation weight in the set of optimized parameters according to the feedback correction parameters to obtain a corrected ship automatic mooring control strategy; Match the similarity between the corrected ship automatic mooring control strategy and the historical successful strategy. If the similarity is lower than the preset threshold, trigger an artificial intervention instruction.

9. The method for optimizing the automatic mooring control strategy of a ship based on multi-source data according to claim 8, characterized in that The process of inputting the attitude correction coefficient and the tension stability evaluation parameter into a preset fuzzy PID controller to generate feedback correction parameters includes: Perform a normalization mapping process on the attitude correction coefficient, map the numerical range of the attitude correction coefficient to a preset fuzzy domain interval, and generate a first fuzzy input quantity; Perform a normalization mapping process on the tension stability evaluation parameter, map the numerical range of the tension stability evaluation parameter to the fuzzy domain interval, and generate a second fuzzy input quantity; Input the first fuzzy input quantity and the second fuzzy input quantity into a preset fuzzy rule base, match the corresponding relationship between the predefined fuzzy conditions and fuzzy output quantities in the fuzzy rule base, and generate a fuzzy output set of proportional parameter adjustment amount, integral parameter adjustment amount, and differential parameter adjustment amount; Perform defuzzification processing on the proportional parameter adjustment amount, integral parameter adjustment amount, and differential parameter adjustment amount in the fuzzy output set, reverse-map the fuzzy domain interval of the fuzzy output quantity to the actual dimension range, and generate the actual proportional parameter adjustment amount, actual integral parameter adjustment amount, and actual differential parameter adjustment amount; Superpose and correct the initial proportional coefficient, initial integral coefficient, and initial differential coefficient of the fuzzy PID controller according to the actual proportional parameter adjustment amount, actual integral parameter adjustment amount, and actual differential parameter adjustment amount to obtain the corrected proportional coefficient, corrected integral coefficient, and corrected differential coefficient; Linearly superpose the corrected proportional coefficient, corrected integral coefficient, and corrected differential coefficient according to a preset weight combination relationship to generate the feedback correction parameter.

10. A system for optimizing the automatic mooring control strategy of a ship based on multi-source data, characterized in that, The ship automatic mooring control strategy optimization system based on multi-source data includes a processor and a memory. The memory is connected to the processor. The memory is used to store programs, instructions, or codes, and the processor is used to execute the programs, instructions, or codes in the memory to implement the ship automatic mooring control strategy optimization method according to any one of claims 1-9 above.

Images