Inland ship steering method and system based on preview and slip cooperative control

Abstract

The invention discloses an inland ship steering method based on preview and slip cooperative control, and the method comprises the steps: obtaining a preset navigation plan of a ship, generating an initial discrete waypoint sequence, and carrying out the smoothing of the initial discrete waypoint sequence, and obtaining a continuous target path; acquiring a current motion state of the ship in real time, dynamically determining a preview distance on the target path based on the current motion state, and determining an optimal target waypoint in the preview distance; based on the optimal target waypoint, the potential risk of ship steering is evaluated, a ship steering decision instruction is generated, and a ship steering decision comprises the expected value of the rotating speed difference of the left propeller and the right propeller; and dynamically adjusting the rotating speed difference of the left and right propellers through a control algorithm based on the rotating speed difference expected value of the left and right propellers so as to assist the ship in steering. According to the method and system provided by the invention, through intelligent preview and differential cooperative control, the steering safety, stability and control efficiency of the inland ship in the narrow water channel are improved.

Description

Technical Field

[0001] This invention relates to the field of ship maneuvering and control technology, and in particular to a method and system for steering inland waterway vessels based on coordinated control of anticipation and slip. Background Technology

[0002] Inland waterway transportation is a crucial component of the global logistics network, and inland cargo ships generally employ a twin-engine, twin-propeller, twin-rudder propulsion structure, providing redundancy and maneuverability for large-angle turns, berthing, and unberthing. However, in actual operation, twin-engine, twin-propeller, twin-rudder ships are quite difficult to control, especially in narrow, busy inland waterways, such as winding channels, ports, and bridge areas, when turning or avoiding obstacles. The following maneuvering challenges exist: First, the conflict between rudder effectiveness and speed: insufficient rudder effectiveness at low speeds leads to turning difficulties, while high speeds result in greater inertia and a larger turning radius, increasing the risk of collisions, making the operator highly dependent on experience; Second, the limitations of internal combustion engine speed regulation: diesel engine speed regulation suffers from response lag and low precision, making it difficult to accurately control the speed difference between the left and right propellers, affecting differential steering performance; Third, the heavy maneuvering load: the operator needs to simultaneously monitor multiple parameters such as the waterway, speed, rudder angle, and main engine speed, frequently operating the engine telegraph and rudder commands, resulting in a heavy physical and mental burden.

[0003] Existing steering assistance technologies include differential steering assist, multi-propeller coordinated control, and emergency side thrust devices, but they still have significant shortcomings: First, they are not adapted to the speed regulation characteristics of diesel engines; second, they are not combined with anticipation mechanisms and slip control to achieve smooth active control; and third, the systems are complex and costly to modify, making it difficult to promote them to existing inland waterway cargo ships. Summary of the Invention

[0004] In view of the above-mentioned shortcomings of the current steering of inland waterway twin-engine, twin-propeller diesel vessels, the present invention provides an inland waterway vessel steering method based on advance aiming and differential coordinated control. Through intelligent advance aiming and differential coordinated control, the steering safety, stability and maneuvering efficiency of inland waterway vessels in narrow waterways are improved.

[0005] To achieve the above objectives, the embodiments of the present invention adopt the following technical solutions:

[0006] A method for steering inland waterway vessels based on coordinated anticipation and slip control, the method comprising:

[0007] The ship's preset navigation plan is obtained, an initial discrete waypoint sequence is generated, and the initial discrete waypoint sequence is smoothed to obtain a continuous target path.

[0008] The ship's current motion status is acquired in real time, and the pre-aiming distance is dynamically determined on the target path based on the current motion status. The optimal target waypoint is then determined within the pre-aiming distance.

[0009] Based on the optimal target waypoint, the potential risk of ship turning is evaluated, and a ship turning decision instruction is generated, the ship turning decision including a left-right propeller speed difference expected value;

[0010] Based on the left-right propeller speed difference expected value, the speed difference of the left and right propellers is dynamically adjusted through a control algorithm to assist the ship turning.

[0011] According to one aspect of the present application, the initial discrete waypoint sequence is smoothed to obtain a continuous target path, including:

[0012] The initial discrete waypoint sequence is subjected to validity check and data cleaning processing;

[0013] Based on the processed discrete waypoint sequence, a non-uniform parameterized variable is generated;

[0014] Based on the processed discrete waypoint sequence and the non-uniform parameterized variable, a spline function is constructed to generate a continuous target path.

[0015] According to one aspect of the present application, the target path is adaptively discretized and sampled to generate a final discrete waypoint sequence for path preview.

[0016] According to one aspect of the present application, the preview distance is dynamically determined on the target path based on the current motion state, and the optimal target waypoint is determined within the preview distance, specifically including:

[0017] The preview distance is dynamically determined based on the speed, and the preview distance is proportional to the speed;

[0018] On the target path, all candidate waypoints within the preview distance are collected;

[0019] A ship kinematics model is constructed to simulate the future trajectory of the ship tracking each of the candidate waypoints from the current state, and the optimal target waypoint is determined.

[0020] According to one aspect of the present application, the evaluation of the potential risk of ship turning includes:

[0021] Based on the optimal target waypoint, the turning state of the ship is determined;

[0022] In combination with the ship kinematics model, the turning trajectory when relying only on rudder angle control is predicted, and the risk level is evaluated;

[0023] When the risk level is too high, the speed difference regulation interval is determined based on a preset speed difference strategy table, and the speed difference expected value is calculated by interpolation.

[0024] According to one aspect of the present application, the differential rotation strategy table sets different curvature intervals and corresponding differential rotation control ranges according to different ship types.

[0025] According to one aspect of the present application, the dynamic adjustment of the speed difference between the left and right propellers by the control algorithm comprises:

[0026] The actual speeds of the two main engines of the left and right propellers are collected in real time, and the actual speed difference is calculated;

[0027] Based on the speed difference expectation value and the actual speed difference, the speed deviation and the change rate are obtained;

[0028] The speed deviation and the change rate are input into the fuzzy PID controller, in which the preset fuzzy rule table and PID parameter update strategy table are queried, fuzzy reasoning and defuzzification are performed, and the adjustment amount of the PID parameter is output;

[0029] The parameters of the PID controller are updated according to the adjustment amount, and a speed adjustment control instruction is generated.

[0030] According to one aspect of the present application, the fuzzy rule table specifies the fuzzy output of the PID parameter adjustment amount corresponding to the combination of the fuzzy subsets of the speed deviation and the change rate; and the PID parameter update strategy table specifies the PID parameter adjustment amount corresponding to each fuzzy output.

[0031] According to one aspect of the present application, the dynamic adjustment of the speed difference between the left and right propellers by the control algorithm further comprises: feedforward compensation is performed on the speed adjustment control instruction to compensate for the response lag characteristic of the diesel engine speed regulation system.

[0032] An inland ship turning system based on pre-lookahead and differential rotation cooperative control, the system comprising:

[0033] A path planning module acquires a preset navigation plan of the ship, generates an initial discrete sequence of waypoints, and performs smoothing processing on the initial discrete sequence of waypoints to obtain a continuous target path;

[0034] A path pre-lookahead module acquires a current motion state in real time, dynamically determines a pre-lookahead distance on the target path based on the current motion state, and determines an optimal target waypoint within the pre-lookahead distance;

[0035] A turning decision module evaluates potential risks of ship turning based on the optimal target waypoint, and generates a ship turning decision instruction, the ship turning decision comprising a left and right propeller speed difference expectation value;

[0036] A differential rotation control module dynamically adjusts the speed difference between the left and right propellers by a control algorithm based on the left and right propeller speed difference expectation value to assist the ship turning.

[0037] The advantages of the embodiment of the present application: by introducing the pre-look and the differential speed cooperative control strategy, the intelligent decision and accurate execution of the steering process are realized. The initial waypoints are first smoothed to generate a continuous path, then the pre-look distance is dynamically determined according to the real-time speed and the optimal target point is selected, then the steering risk is evaluated and the speed difference expectation instruction is generated; finally, the left and right propeller speed difference is adjusted in real time through the fuzzy PID control algorithm, and the diesel engine response lag is suppressed by combining the feedforward compensation mechanism, so as to significantly reduce the operator's operating burden while ensuring the steering accuracy, and improve the maneuverability and safety of the ship in complex water areas such as curved river and port. BRIEF DESCRIPTION OF DRAWINGS

[0038] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following will briefly introduce the drawings needed to be used in the embodiments. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative labor.

[0039] Figure 1 A schematic flow chart of an inland river ship steering method based on pre-look and differential speed cooperative control according to the present application;

[0040] Figure 2 A structural schematic diagram of an inland river ship steering system based on pre-look and differential speed cooperative control according to the present application. DETAILED DESCRIPTION

[0041] The technical solutions in the embodiments of the present application will be described clearly and completely in the following with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only some embodiments of the present application, not all embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor are within the scope of protection of the present application.

[0042] Embodiment one

[0043] Step S1, obtaining a preset ship navigation plan, generating an initial discrete waypoint sequence, and smoothing the initial discrete waypoint sequence to obtain a continuous target path;

[0044] Step S2, obtaining the current motion state of the ship in real time, dynamically determining the pre-look distance on the target path based on the current motion state, and determining the optimal target waypoint within the pre-look distance;

[0045] Step S3, based on the optimal target waypoint, evaluating the potential risk of ship steering, and generating ship steering decision instruction, the ship steering decision including left and right propeller speed difference expectation value;

[0046] Step S4, based on the left and right propeller speed difference expectation value, the speed difference of the left and right propellers is dynamically adjusted through a control algorithm to assist the ship in turning.

[0047] Further, in step S1, the ship's preset navigation plan is obtained, an initial discrete waypoint sequence is generated, and the initial discrete waypoint sequence is smoothed to obtain a continuous target path, specifically including:

[0048] Step S111, validity check and data cleaning processing are performed on the initial discrete waypoint sequence;

[0049] The ship's preset navigation plan is obtained, such as key waypoints manually input by the driver or generated by the navigation system, to generate an initial discrete waypoint sequence , wherein, represents the planar coordinates of the ith waypoint. To ensure the effectiveness of the subsequent path smoothing algorithm, the number of points needs to be checked and the data needs to be cleaned:

[0050] Point number check: the number of waypoints in the sequence must be greater than 2, that is, at least the start point, end point and an intermediate point of the path are included. If not, it should be prompted to re-enter or report an error.

[0051] For the discrete waypoint sequence that passes the point number check, the following data cleaning operations are performed:

[0052] Format standardization: check the uniformity of the coordinates of all waypoints in the discrete waypoint sequence. If not, convert to the preset standard format, such as decimal latitude and longitude format in WGS-84 coordinate system, to ensure data consistency.

[0053] Redundancy elimination: traverse the discrete waypoint sequence and eliminate adjacent duplicate waypoints to prevent zero-length line segments in path calculation.

[0054] Finally, the processed discrete waypoint sequence is obtained.

[0055] Step S112, based on the processed discrete waypoint sequence, a non-uniform parameterized variable is generated;

[0056] For the processed discrete waypoint sequence , the straight-line distance between adjacent points is calculated, and the total path length is accumulated to map the accumulated distance to the [0, 1] interval to obtain the corresponding parameter of each valid discrete waypoint . Specifically:

[0057] Traverse the waypoint sequence, calculate the straight-line distance from the start point to any point The cumulative straight-line distances of the input discrete waypoint sequence are stored in an array distances:

[0058] wherein, and are the processed discrete waypoint sequence are the planar coordinate values of the kth waypoint, and are the processed discrete waypoint sequence are the planar coordinate values of the k-1th waypoint, and distances[0]=0.0.

[0059] The cumulative chord length distances[i] is normalized with the total path length distances[n] to obtain the parameter corresponding to each waypoint : wherein distances[n] is the cumulative chord length when i=n.

[0060] Thus, the processed discrete waypoint sequence

[0061] is obtained, and the corresponding non-uniform parameter sequence is obtained, wherein =0.

[0062] Step S113, based on the processed discrete waypoint sequence and the non-uniform parameterization variable, a spline function is constructed to generate a continuous target path.

[0063] An input processed discrete waypoint sequence with a waypoint number of n+1 and a corresponding non-uniform parameterization variable sequence is inputted to generate a continuous parameterization curve function, and the specific process is as follows:

[0064] Adaptive determination of the order k of the curve: if the waypoint number n+1≤4, then k=n, i.e., the order of the curve = the number of points -1. At this time, directly as the control point, and T as the corresponding node parameter, a k-order Bezier curve is constructed. The curve will accurately interpolate and pass through all the input waypoints. If the waypoint number n+1>4, then k=3 is fixed, i.e., a cubic Bezier curve. At this time, according to is segmented, and the control points of each segment of the cubic curve are calculated to generate a segmented cubic Bezier spline curve, which will approximate the input waypoints under the premise of ensuring global smoothness.

[0065] ​​Constructing parameterized spline function: according to the control point set and parameter sequence T determined above, a spline function C(u)=(x(u),y(u)) with parameter u as independent variable is constructed for plane coordinates x and y respectively, with domain [0,1]. The function is the target path after smoothing processing.

[0066] Further, the target path is adaptively discretely sampled to generate a final discrete waypoint sequence for path preview, specifically including:

[0067] Step S121, initial uniform sampling and curvature calculation

[0068] Based on non-uniform parameterization variable sequence Initial uniform sampling is performed in its parameter domain [0,1] to generate a basic sampling point sequence The number of sampling points is determined according to the relationship between the total length of the path and the ship length to ensure moderate sampling density. At the same time, the curvature k(t) of each sampling point is calculated.

[0069] Step S122, adaptive sampling density adjustment based on curvature

[0070] According to the curvature size, the sampling weight is set:

[0071] Where k(t) is the curvature, and the curvature threshold Can be set as L is the ship length to adapt to the typical turning characteristics of inland cargo ships.

[0072] The upper limit of the sampling weight is set to 5 to avoid too many sampling points. The weight cumulative sum is calculated and normalized to generate a new sampling parameter sequence So that the parameters in the high curvature area are more intensive.

[0073] Step S123, generating final discrete waypoints:

[0074] The adaptive sampling parameter sequence Is substituted into the spline function To calculate the final discrete waypoint sequence:

[0075] Where Is the final number of sampling points, determined by the basic number of points and weight adjustment.

[0076] The final discrete waypoint sequence Generated in this way is a continuous target path The path point set optimized under the premise of the geometric characteristics to adapt to the discrete processing characteristics of the digital control system. The sequence will be directly input, providing for subsequent operations. The "target path" described in the following steps refers to this discrete sequence of waypoints in actual control , while its geometric calculation basis, such as curvature calculation, depends on the original continuous target path .

[0077] Further, in step S2, the preview distance is dynamically determined on the target path based on the current motion state, and the optimal target waypoint is determined within the preview distance, which specifically includes:

[0078] Step S211, dynamically determining the preview distance based on the speed, and the preview distance is proportional to the speed;

[0079] In each control cycle, the current motion state of the ship is obtained in real time, including the current position, heading angle, speed and the like. The preview distance is calculated according to the current speed. The preview distance is proportional to the speed, so as to ensure that there is a longer preview at high speed, and fine tracking is performed at low speed.

[0080] Step S212, collecting all candidate waypoints within the preview distance on the target path;

[0081] Taking the current position as the center and the preview distance as the radius, all candidate waypoints located within the preview range on the target path are searched and screened out.

[0082] Step S213, constructing a ship kinematics model to simulate the future trajectory of the ship tracking each of the candidate waypoints from the current state, and determining the optimal target waypoint.

[0083] The ship kinematics model, such as the Nomoto model or the geometric model, is constructed to simulate the future trajectory that the ship may generate when tracking each of the candidate waypoints from the current state.

[0084] By calculating and comparing the final navigation trajectory deviation between the simulated trajectory and the target path, the tracking effect of each candidate point is evaluated. The evaluation comprehensively considers the weighted values of the average lateral deviation and the average heading deviation. The candidate waypoint with the optimal weighted evaluation result is selected as the optimal target waypoint of the current cycle.

[0085] Further, in step S3, the potential risk of ship turning is evaluated, which specifically includes:

[0086] Step S311, judging the ship turning state based on the optimal target waypoint;

[0087] The optimal target waypoint is obtained, and the path information of the point and several subsequent waypoints is read, including coordinates, curvature, etc. By analyzing the curvature trend and characteristics of this section of path, a comprehensive judgment is made on the turning state that the ship will face. For example, the turning state can be classified into different modes such as gentle turning, regular turning or sharp turning, etc., to provide a basis for subsequent differentiated control.

[0088] In step S312, the turning trajectory under the control of the rudder angle alone is predicted in combination with the ship kinematics model, and the risk level is evaluated;

[0089] In combination with the ship kinematics model, the expected trajectory of the ship if it relies on the rudder angle control for turning is predicted. The predicted trajectory is compared with the target path, and the risk level of the ship using the rudder effect alone to complete this turning maneuver in various aspects is comprehensively evaluated, including but not limited to trajectory tracking deviation, required water width, time required to complete turning, etc.

[0090] In step S313, when the risk level is too high, the turning speed difference regulation interval is determined based on the preset turning difference strategy table, and the turning speed difference expected value is calculated by interpolation.

[0091] Before this step, the turning difference strategy table needs to be preset first, as shown in Table 1. The turning difference strategy table sets different curvature intervals and corresponding turning difference regulation ranges according to different ship types.

[0092] Step S313 specifically: When the turning risk evaluation indicates that the risk is high, i.e. it is difficult to safely and effectively complete the turning relying on the rudder angle control alone, or it can be completed but the performance is poor, the turning difference control strategy is started.

[0093] According to the curvature size of the current path and the predefined curvature interval to which it belongs, such as gentle, regular and sharp turning, etc., the preset turning difference strategy table is queried to determine the corresponding turning difference regulation interval.

[0094] Table 1 Turning curvature and turning difference regulation decision

[0095]

[0096] According to the specific position of the actual path curvature value within its belonging curvature interval, the left and right propeller turning speed difference expected values required are accurately calculated within the turning difference regulation interval by linear interpolation or other adaptive calculation methods, to realize more fine control.

[0097] The finally generated turning decision instruction aims to cooperatively use the differential thrust generated by the propeller turning speed difference and the rudder force generated by the rudder angle to jointly constitute a composite turning maneuver instruction, so as to achieve a safe, stable and efficient turning process.

[0098] Further, in step S4, dynamically adjusting the speed difference of the left and right propellers by the control algorithm specifically includes:

[0099] Step S411, real-time acquisition of the two main engine speeds of the left and right propellers, and calculation of the actual speed difference;

[0100] Real-time reception of the left and right propeller speed difference expectation value.

[0101] Real-time acquisition of the two main engine speeds of the left and right propellers, and calculation of the current actual speed difference.

[0102] Step S412, based on the speed difference expectation value and the actual speed difference, the speed deviation and the change rate are obtained; specifically, based on the expected speed difference and the actual speed difference, the speed deviation e and the speed change rate ė are obtained. Wherein, the change rate ė is the speed acceleration.

[0103] Step S413, input the speed deviation and change rate into the fuzzy PID controller, in the fuzzy PID controller, query the preset fuzzy rule table and PID parameter update strategy table, carry out fuzzy reasoning and defuzzification, output the adjustment amount of PID parameter;

[0104] Before this step, the fuzzy rule table and the PID parameter update strategy table need to be preset, and when step S413 is executed, it can be directly called. Wherein, the fuzzy rule table stipulates that the fuzzy output of the PID parameter adjustment amount corresponding to the fuzzy subset combination of the speed deviation and the change rate; the PID parameter update strategy table stipulates the PID parameter adjustment amount corresponding to each fuzzy output.

[0105] The preset fuzzy rule table is shown in Table 2, the value range of the speed deviation e and the change rate ė is determined first, and then divided into 7 fuzzy subsets: NB (negative big), NM (negative medium), NS (negative small), ZO (zero), PS (positive small), PM (positive medium), PB (positive big); Finally, 49 fuzzy rules of their combination are constructed, and each rule corresponds to a group of PID parameter adjustment strategy.

[0106] Table 2 Fuzzy rule table

[0107]

[0108] The preset PID parameter update strategy table is shown in Table 3.

[0109] Step S413 specifically: the speed deviation e and the speed change rate ė are input into the fuzzy PID controller. The speed deviation e and the speed change rate ė are converted into "negative big (NB)", "negative medium (NM)", "zero (ZO)" and "positive big (PB)" and other fuzzy language description according to the preset membership function, and the membership degree of each fuzzy subset is calculated.

[0110] The membership of each fuzzy subset is inferred according to the pre-set fuzzy rule table. The output result obtained by fuzzy inference is converted into an accurate PID parameter adjustment amount through a defuzzification algorithm. Subsequently, according to a pre-defined PID parameter updating strategy, the proportional (P), integral (I), and differential (D) parameters of the PID controller are dynamically adjusted to make the controller parameters adapt to different speed deviation states. The initial parameters of the fuzzy PID speed controller are set as follows: the proportional coefficient P = 10.0, the integral coefficient I = 0.8, and the differential coefficient D = 80.0.

[0111] Table 3 PID parameter updating strategy table

[0112]

[0113] Step S414, updating the parameters of the PID controller according to the adjustment amount and generating a speed adjustment control instruction.

[0114] Based on the real-time adjusted PID parameters, the controller calculates an accurate control amount, such as an adjustment amount of the fuel rack position or the speed set value.

[0115] The control amount is output to an actuator, such as a main engine governor, to drive the left and right main engines to operate at the target speed difference.

[0116] Further, the dynamic adjustment of the speed difference between the left and right propellers by the control algorithm also includes: feedforward compensation is performed on the speed adjustment control instruction to compensate for the response lag characteristic of the diesel engine speed regulation system, specifically:

[0117] The control output of the fuzzy PID is feedforward compensated or fine-tuned by monitoring the control effect, such as the tracking error and response time of the speed difference, to compensate for the inherent response lag and non-linear characteristics of the diesel engine speed regulation system, ensuring the rapidity and stability of the speed difference control. Finally, independent and accurate control instructions for the speeds of the left and right main engines are output to ensure that the actual speed difference can quickly and smoothly track the expected speed difference instruction.

[0118] Further, if the system detects an emergency avoidance requirement, the maximum speed difference control mode is automatically activated to increase the speed difference to a pre-set upper limit to minimize the turning radius.

[0119] Embodiment Two

[0120] As shown in Figure 2 A river ship turning system based on pre-lookahead and speed difference cooperative control, the system comprises:

[0121] A path planning module M1 acquires a preset sailing plan of a ship, generates an initial discrete sequence of sailing waypoints, and performs smoothing processing on the initial discrete sequence of sailing waypoints to obtain a continuous target path.

[0122] A path preview module M2 acquires a current motion state in real time, dynamically determines a preview distance on the target path based on the current motion state, and determines an optimal target waypoint within the preview distance.

[0123] A turning decision module M3 evaluates potential risks of ship turning based on the optimal target waypoint, and generates a ship turning decision instruction, wherein the ship turning decision includes a left-right propeller speed difference expectation value.

[0124] A turning difference control module M4 dynamically adjusts a left-right propeller speed difference through a control algorithm based on the left-right propeller speed difference expectation value to assist ship turning.

[0125] The advantages of the implementation of the present application are as follows: by introducing a preview and turning difference cooperative control strategy, intelligent decision-making and precise execution of the turning process are realized. The initial sailing waypoints are first smoothed to generate a continuous path, then a preview distance is dynamically determined according to a real-time sailing speed and an optimal target point is selected, and then turning risks are evaluated and a speed difference expectation instruction is generated. Finally, a fuzzy PID control algorithm is used to adjust the left-right propeller speed difference in real time, and a feedforward compensation mechanism is combined to suppress the diesel engine response lag, so as to significantly reduce the operator's control burden while ensuring the turning accuracy, and to improve the maneuverability and safety of the ship in complex water areas such as curved river channels and ports.

[0126] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any changes or replacements within the scope of the disclosed technology can be easily thought of by those skilled in the art, and should be covered within the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claims.

Claims

1. A method for turning an inland waterway vessel based on a pre-look and a differential speed cooperative control, characterized in that, The method comprises: acquiring a preset sailing plan of a ship, generating an initial discrete waypoint sequence, and smoothing the initial discrete waypoint sequence to obtain a continuous target path; real-time acquisition of the current motion state of the ship, dynamic determination of a preview distance on the target path based on the current motion state, and determination of an optimal target waypoint within the preview distance; based on the optimal target waypoint, evaluating the potential risk of ship turning and generating ship turning decision instructions, the ship turning decision including left and right propeller speed difference expectation values; based on the left and right propeller speed difference expectation values, dynamically adjusting the speed difference of the left and right propellers through a control algorithm to assist the ship in turning.

2. The method of claim 1, wherein, The smoothing of the initial discrete waypoint sequence to obtain a continuous target path comprises: validity checking and data cleaning processing of the initial discrete waypoint sequence; generating a non-uniform parameterized variable based on the processed discrete waypoint sequence; based on the processed discrete waypoint sequence and the non-uniform parameterized variable, constructing a spline function to generate a continuous target path.

3. The method of claim 1, wherein, Adaptive discretization sampling of the target path to generate a final discrete waypoint sequence for path preview.

4. The method of claim 1, wherein, Dynamic determination of a preview distance on the target path based on the current motion state, and determination of an optimal target waypoint within the preview distance specifically comprises: dynamically determining the preview distance based on the speed, the preview distance being proportional to the speed; collecting all candidate waypoints within the preview distance on the target path; constructing a ship kinematics model to simulate the future trajectory of the ship tracking each of the candidate waypoints from the current state, and determining the optimal target waypoint.

5. The method of claim 1, wherein, The evaluation of the potential risk of ship turning comprises: judging the ship turning state based on the optimal target waypoint; predicting the turning trajectory relying only on the rudder angle control in combination with the ship kinematics model, and evaluating its risk level; when the risk level is too high, determining the speed difference regulation interval based on a preset speed difference strategy table, and calculating the speed difference expectation value by interpolation.

6. The method of claim 5, wherein, The speed difference strategy table sets different curvature intervals and corresponding speed difference regulation ranges according to different ship types.

7. The method of claim 1, wherein, The dynamic adjustment of the speed difference of the left and right propellers through the control algorithm comprises: real-time acquisition of the actual speeds of the left and right propellers, and calculation of the actual speed difference; based on the speed difference expectation value and the actual speed difference, obtaining the speed deviation and the change rate; inputting the speed deviation and the change rate into a fuzzy PID controller, querying a preset fuzzy rule table and a PID parameter update strategy table in the fuzzy PID controller, performing fuzzy reasoning and defuzzification, and outputting the adjustment amount of the PID parameters; updating the parameters of the PID controller according to the adjustment amount and generating a speed regulation control instruction.

8. The method of claim 7, wherein, The fuzzy rule table specifies the fuzzy output of the PID parameter adjustment amount corresponding to the fuzzy subset combination of the speed deviation and the change rate; and the PID parameter update strategy table specifies the PID parameter adjustment amount corresponding to each fuzzy output.

9. The method of claim 8, wherein, The dynamic adjustment of the speed difference of the left and right propellers by the control algorithm further comprises: feedforward compensation of the speed adjustment control instruction to compensate for the response lag characteristic of the diesel engine speed regulation system.

10. A turning system for inland waterway vessels based on the cooperative control of preview and slip, characterized in that, The system comprises: A path planning module acquires a preset sailing plan of a ship, generates an initial discrete sequence of sailing waypoints, and performs smoothing processing on the initial discrete sequence of sailing waypoints to obtain a continuous target path; A path preview module acquires a current motion state in real time, dynamically determines a preview distance on the target path based on the current motion state, and determines an optimal target waypoint within the preview distance; A turning decision module evaluates potential risks of ship turning based on the optimal target waypoint, and generates a ship turning decision instruction, wherein the ship turning decision comprises a left-right propeller speed difference expectation value; A speed difference control module dynamically adjusts the speed difference of the left and right propellers by a control algorithm based on the left-right propeller speed difference expectation value to assist the ship in turning.

Images