A deployment method for a marine boarding system based on a hybrid mechanism

Abstract

A deployment method for an offshore boarding system based on a hybrid mechanism belongs to the field of marine engineering technology. It is designed to solve the problem of the shortcomings of traditional wave compensation systems. The controller of the present invention controls the gangway to the middle position so that the end of the gangway leaves the deck, constructs an RBF neural network adaptive controller model based on the electro-hydraulic servo system, collects hull attitude information data and position information data, and before the deployment state, actively compensates the hybrid mechanism to keep the end of the gangway stationary relative to the wind turbine platform; collects three-dimensional speed information data of the end of the gangway relative to the landing point of the wind turbine platform, solves the hybrid mechanism, and obtains the target speed of each joint; under the condition of ship dynamic positioning, collects ship attitude and position information data, and actively compensates the hybrid mechanism in the deployment state; determines whether the end of the gangway has reached the target point of the wind turbine platform. If it is, the deployment ends, otherwise, the deployment method is re-executed. The present invention has improved stability.

Description

Technical Field

[0001] The present invention belongs to the field of marine engineering technology, and in particular relates to a deployment method of a marine boarding system based on a hybrid mechanism. Background Art

[0002] With the rapid development of science and technology, the development and use of clean and green energy are receiving increasing attention. The vast oceans, which cover approximately 70% of the Earth's surface, are rich in offshore wind energy resources, leading to a significant increase in the number of wind farms. Offshore wind power has become one of the new energy sectors with the largest reserves, the most mature development technologies, and the broadest development prospects.

[0003] However, the booming development of wind power also presents numerous challenges. Offshore wind farms must withstand multiple loads, including wind and waves, and face more challenging and complex environmental conditions than onshore. Various environmental factors, including tides, typhoons, air currents, and lightning, make offshore wind turbines prone to failure. Transporting personnel from ships to wind turbine platforms is difficult and dangerous. To maintain the stability of the bridge and the safety of maintenance personnel, research on the deployment of offshore boarding systems based on hybrid mechanisms has become a top priority.

[0004] Research on hybrid-mechanism-based marine embarkation systems is relatively mature abroad, but not fully applicable to domestic conditions. Kinematic analysis of hybrid mechanisms is a key research topic for active wave compensation systems. Kinematic solutions are divided into forward and inverse kinematic solutions, with numerical and analytical methods currently the primary approaches for solving the forward kinematic solution. Gao Jianshe et al. used the vector method to solve the forward and inverse kinematic solutions for a series-parallel hybrid leg, assuming the optimal posture with the lowest energy consumption. Han Fangyuan et al. proposed a fast numerical method for solving the forward kinematic solution of a 3-PRS parallel mechanism, achieving a computational speed 1.5 times faster than conventional algorithms. Sung used optimization theory to find the optimal solution using the forward kinematic equations as constraints, but real-time applications require further exploration in optimization theory and hardware and software implementation. Joey used a genetic algorithm to perform trajectory planning, but the convergence of this iterative method, which randomly generates iterative variables (samples), cannot be guaranteed. Wolovich proposed a dynamic method based on the forward kinematic solution to solve the inverse kinematic solution for non-redundant robots, but this method requires high computer configuration and is difficult to implement. Summary of the Invention

[0005] The problem to be solved by the present invention is to address the shortcomings of traditional wave compensation systems and provide a deployment method for an offshore boarding system based on a hybrid mechanism, so as to achieve the connection requirements between the offshore boarding system and the offshore platform and provide theoretical support for engineering practice.

[0006] To achieve the above object, the present invention is implemented through the following technical solutions:

[0007] A method for deploying a marine boarding system based on a hybrid mechanism comprises the following steps:

[0008] S1. The controller moves the gangway ladder to the neutral position so that the end of the gangway ladder leaves the deck;

[0009] S2. Construct an RBF neural network adaptive controller model based on the electro-hydraulic servo system;

[0010] S3, using a position sensor and an attitude sensor to collect hull attitude information data and position information data;

[0011] S4. Based on the hull attitude information data and position information data collected in step S3, before the deployment state, actively compensate the hybrid mechanism to keep the end of the gangway stationary relative to the wind turbine platform;

[0012] S5. Collect three-dimensional velocity information data of the end of the gangway relative to the landing point of the wind turbine platform, solve the hybrid mechanism, and obtain the target velocity of each joint;

[0013] S6. Under the condition of ship dynamic positioning, collect ship attitude and position information data, and actively compensate the hybrid mechanism in the deployed state;

[0014] S7. Determine whether the end of the gangway has reached the target point of the wind turbine platform. If so, the deployment is completed and passive compensation is started. If not, return to step S5 and re-execute the deployment method of the marine boarding system based on the hybrid mechanism.

[0015] Furthermore, the specific implementation method of step S1 includes the following steps:

[0016] S1.1. Solve the inverse kinematics of the hybrid mechanism: Set α, β, and γ to be the rotation angles around the x, y, and z axes respectively. p ,Y p ,Z p is the position of the origin A of the upper platform coordinate system of the hybrid mechanism relative to the origin B of the lower platform coordinate system of the hybrid mechanism, E is the spatial inertial coordinate system, θ1 is the rotation angle of the revolute joint, θ2 is the pitch angle of the swing joint, and q3 is the telescopic length. The Stewart parallel platform homogeneous transformation matrix of the lower platform of the hybrid mechanism is obtained as follows: The expression is:

[0017]

[0018] Among them, cos(·)→c, sin(·)→s, the rotation matrix of the upper and lower platforms of the hybrid mechanism is P is the position vector of the origin A of the upper platform coordinate system relative to the origin B of the lower platform coordinate system of the hybrid mechanism;

[0019] S1.2, let the vector between the origin A and any point on the circumference of the hybrid mechanism be The vector between the origin B and any point on the circumference in the lower platform coordinate system of the hybrid mechanism is Then according to the upper and lower platform transformation matrix, we can get The relationship is expressed as:

[0020]

[0021] S1.3. Simplify the rotation matrices of the upper and lower platforms of the hybrid mechanism and express them as follows:

[0022]

[0023] Then substitute the expression in step S1.2 to obtain the expression:

[0024]

[0025] S1.4, the six connecting rods of the six-degree-of-freedom parallel platform of the hybrid mechanism are l i (1,2,3,4,5,6), the two ends of the same connecting rod correspond to the upper and lower platform hinge points respectively, then the expression of the connecting rod length vector is:

[0026]

[0027] Then, the matrix expression in step S1.3 is substituted into the final result to obtain the connecting rod length l of the six-degree-of-freedom parallel platform of the joint mechanism. i The expression is:

[0028]

[0029]

[0030] S1.5. The homogeneous transformation matrix of the upper platform in series with the 3-DOF manipulator for the hybrid mechanism is expressed as:

[0031]

[0032]

[0033] Furthermore, the specific implementation method of step S2 includes the following steps:

[0034] S2.1. Constructing the electro-hydraulic servo system model:

[0035] Defining state variables Converted into the state equation:

[0036]

[0037] Where y is the displacement of the hydraulic cylinder, is the speed of the hydraulic cylinder, p1 and p2 are the pressures on the left and right sides of the hydraulic cylinder respectively, m is the load mass of the hydraulic cylinder, A f S f are the modelable Coulomb friction amplitude, the continuous approximate Coulomb friction shape function, the external disturbance of the system and the unmodeled dynamics, β e is the elastic modulus of the hydraulic oil, A1 and A2 are the effective piston areas of the left and right chambers of the hydraulic cylinder, V 01 、V 02 are the dead volume of the left and right chambers of the hydraulic cylinder, C t is the hydraulic cylinder leakage coefficient, k i ,k q ,p s ,p r They are valve core current gain, valve core displacement flow gain, system oil source pressure, and return oil pressure; Q1 and Q2 are the flow rates of the two chambers of the hydraulic cylinder, and τ is the external load force on the hydraulic cylinder;

[0038] The flow rate of the two chambers of the hydraulic cylinder is set, and τ is the external load force on the hydraulic cylinder. The calculation formula is:

[0039] Q1=gR1u

[0040] Q2=gR2u

[0041]

[0042]

[0043]

[0044]

[0045] The expression is:

[0046]

[0047] S2.2. Define new state variables The nonlinear part is defined as g(x1,p1,p2), then the new state equation is:

[0048]

[0049] Wherein, u is the input signal of the servo valve;

[0050] S2.3 Definitions Then the expression is:

[0051]

[0052]

[0053] Among them, x is the input of the network, j is the jth node of the hidden layer of the network, h=[h j ] T is the Gaussian basis function output of the network, W * and V * are the ideal weights of the networks f(·) and g(·), ε f and ε g is the approximation error of the network, then the expression is:

[0054] |ε f |≤ε Mf ,|ε g |≤ε Mg

[0055]

[0056] f(·)=W *T h f (x)+ε f ,g(·)=V *T h g (x)+ε g

[0057]

[0058] S2.4. Define the expression of the Lyapunov function as:

[0059]

[0060] in, e=x1-x d γ1>0,γ2>0;

[0061] Then the following expression is obtained through transformation:

[0062]

[0063] S2.5. Define the expression of the design control law as:

[0064]

[0065] Substituting the expression in step S2.4, we obtain the following formula:

[0066]

[0067]

[0068] S2.6, take η>|ε| max , the expression of the adaptive law is:

[0069]

[0070]

[0071] Then we get Among them, the role of the robust term ηsgn(s) in the control law is to overcome the neural network approximation error to ensure system stability;

[0072] If and only if s=0, According to the LaSalle invariance principle, the closed-loop system is asymptotically stable, that is, when t→∞, s→0, and the convergence rate of the system depends on η.

[0073] Furthermore, the specific implementation method of step S3 is to use inertial navigation and ultrasonic rangefinders to collect hull attitude information data and position information data respectively, wherein the inertial navigation is used as the main attitude measurement equipment of the survey ship, and the hull position information data uses three ultrasonic rangefinders to measure the real-time relative position with the offshore wind power platform using the principle of three-point ranging.

[0074] Furthermore, the specific implementation method of step S4 includes the following steps:

[0075] S4.1. Assume that the changes of the six degrees of freedom of the hybrid mechanism under the influence of waves are α, β, γ, and d x ,d y ,d z , then the homogeneous transformation matrix of the gangway is:

[0076]

[0077] Among them, the unknown items in the homogeneous transformation matrix of the gangway are expressed as follows:

[0078]

[0079] x=d x +cγcβ((d3+q3+d4)cθ1cθ2+d2cθ1)+(cγsβsα-sγcα)((d3+q3+d4)sθ1cθ2+d2sθ1)+(cγsβcα+sγsα)(d1+(d3+q3+d4)sθ2)

[0080] y=d y+sγcβ((d3+q3+d4)cθ1cθ2+d2cθ1)+(sγsβsα+cγcα)((d3+q3+d4)sθ1cθ2+d2sθ1)+(sγsβcα-cγsα)(d1+(d3+q3+d4)sθ2)

[0081] z=d z -sβ((d3+q3+d4)cθ1cθ2+d2cθ1)+cβsα((d3+q3+d4)sθ1cθ2+d2sθ1)+cβcα(d1+(d3+q3+d4)sθ2)

[0082] S4.2. Perform inverse kinematic analysis on the three-degree-of-freedom tandem gangway ladder under the influence of waves. The coordinates of the end of the gangway ladder in the earth-fixed coordinate system are: a p4=[x,y,z], solve the equations to get the motion of each joint:

[0083]

[0084]

[0085]

[0086] in,

[0087] a=(xd x )cβcγ+(yd y )cβsγ-(zd z )sβ

[0088] b=(xd x )(sαsβcγ-cαsγ)+(yd y )(sαsβsγ+cαcγ)+(zd z )sαcβ

[0089] c=(xd x )(cαsβcγ+sαsγ)+(yd y )(cαsβsγ-sαcγ)+(zd z )cαcβ

[0090] The dynamic equation of the gangway under wave disturbance is calculated as follows:

[0091]

[0092] Among them, G and τ d are the gravity term and the interference term of the waves, respectively. τ is the vector composed of the three joint torques. The unknown terms in the equation are as follows:

[0093] m11 =m3[d2+(d3+d4+q3)cθ2] 2 +m2(d3cθ2+d2) 2 +m1d2 2

[0094] m 22 =m3(d3+d4+q3) 2 +m2d3 2

[0095] m 33 =m3

[0096] m 12 =m 21 =m 23 =m 32 =m 13 =m 31 =0

[0097]

[0098] c 12 =-c 21 =-{m3(d3+d4+q3)[(d3+d4+q3)cθ2+d2]+m2d3(d3cθ2+d2)}

[0099]

[0100]

[0101]

[0102] c 33 =0

[0103] G 11 =0

[0104] G 21 =[m3(d3+d4+q3)+m2d3]gcθ2

[0105] G 31 =m3gsθ2

[0106]

[0107] S4.3. Use the RBF neural network adaptive controller model based on the electro-hydraulic servo system constructed in step S2 to track the change in joint target and control the stationary state of the end of the gangway relative to the offshore wind turbine platform.

[0108] Furthermore, the specific implementation method of step S5 includes the following steps:

[0109] S5.1. Set the linear velocity of the end of the gangway relative to the landing point of the wind turbine platform as v x ,v y ,v z , use Newton's method to solve the velocity of each joint in each joint space as follows:

[0110]

[0111] The unknown terms in the equation are as follows:

[0112]

[0113]

[0114] k 11 =(d3+q3+d4)cθ1sθ2+d1cθ1

[0115] k 12 =[(d3+q3+d4)sθ1sθ2+d1sθ1]cα+[(d3+q3+d4)cθ2+d2]sα

[0116] k 13 =-[(d3+q3+d4)cθ1sθ2+d1cθ1]sβ+[(d3+q3+d4)sθ1sθ2+d1sθ1]sαcβ-[(d3+q3+d4)cθ2+d2]cαcβ

[0117] k 14 =sθ1,k 15 =-cθ1,k 16 =0

[0118] k 21 =(d2+d3+q3+d4)sθ1

[0119] k 22 =-(d2+d3+q3+d4)cαcθ1

[0120] k 23 =-(d2+d3+q3+d4)(sβsθ1+sαcβcθ1)

[0121] k 24 =0,k 25 =0,k 26 =1

[0122] k 31 =-d1sθ1,k 32 =d1cθ1cα,k 33 =d1sθ1sβ+d1cθ1sαcβ

[0123] k34 =0,k 35 =1,k 36 =0

[0124] r 11 =-sθ1cβcγ+cθ1(sαsβcγ-cαsγ)

[0125] r 12 =-sθ1cβsγ+cθ1(sαsβsγ+cαcγ)

[0126] r 13 =sθ1sβ+cθ1sαcβ

[0127] r 21 =-cθ1sθ2cβcγ-sθ1sθ2(sαsβcγ-cαsγ)+cθ2(cαsβcγ+sαsγ)

[0128] r 22 =-cθ1sθ2cβsγ-sθ1sθ2(sαsβsγ+cαcγ)+cθ2(cαsβsγ-sαcγ);

[0129] r 23 =cθ1sθ2sβ-sθ1sθ2sαcβ+cθ2cαcβ

[0130] r 31 =cθ1cθ2cβcγ+sθ1cθ2(sαsβcγ-cαsγ)+sθ2(cαsβcγ+sαsγ)

[0131] r 32 =cθ1cθ2cβsγ+sθ1cθ2(sαsβsγ+cαcγ)+sθ2(cαsβsγ-sαcγ)

[0132] r 33 =-cθ1cθ2sβ+sθ1cθ2sαcβ+sθ2cαcβ

[0133] S5.2. Based on the calculation of the control quantity of each joint in S5.1, the control quantity of each joint is tracked using the RBF neural network adaptive controller model based on the electro-hydraulic servo system constructed in step S2.

[0134] Furthermore, in step S6, in the deployed state, the RBF neural network adaptive controller model based on the electro-hydraulic servo system constructed in step S2 is used to actively compensate the hybrid mechanism.

[0135] Beneficial effects of the present invention:

[0136] The present invention describes a method for deploying a hybrid mechanism-based offshore boarding system. When solving inverse kinematics, the position parameters of the target point in space and the reasonable coordinate system establishment of the upper and lower platforms are included, including under waves and when the ship is stationary. The joint velocity calculation includes solving the relationship between the joint velocity and the absolute velocity of the gangway end relative to the earth, and calculating the speed of the six degrees of freedom generated by wave interference as an additional term. When the operator gives the desired absolute velocity of the gangway end, the velocity value of each joint can be obtained. The controller design includes designing an RBF neural network sliding mode control to address the time lag and strong nonlinearity of the electro-hydraulic servo system, and using the RBF neural network's universal approximation ability for nonlinear functions to fit the unknown parts of the electro-hydraulic servo system and the gangway dynamics under wave interference.

[0137] The deployment method of the offshore boarding system based on the hybrid mechanism described in the present invention compensates for the risk of unstable trajectory of the gangway end and collision with the offshore platform during the deployment of the offshore boarding system due to the interference of waves, and also avoids the inaccurate dynamic settlement caused by the interference of waves, thereby improving the control accuracy.

[0138] The deployment method of a hybrid mechanism-based offshore boarding system described in the present invention comprehensively considers the impact of waves on the ship's roll, pitch, bow pitch, sway, surge, and heave, and participates in dynamic and kinematic calculations, avoiding the model mismatch problem caused by simplified models.

[0139] The present invention discloses a method for deploying a marine boarding system based on a hybrid mechanism. By calculating the relationship between the joint velocity and the absolute velocity of the gangway end, an RBF neural network adaptive sliding mode controller is designed to enable the operator to control the absolute linear velocity of the gangway end, thereby achieving manual deployment.

[0140] The present invention discloses a method for deploying a marine boarding system based on a hybrid mechanism. The wave compensation system uses a hybrid mechanism, which combines the advantages of a series mechanism and a parallel mechanism, increases the movement space, and improves the stability. BRIEF DESCRIPTION OF THE DRAWINGS

[0141] Figure 1 This is a flow chart of a deployment method of a marine boarding system based on a hybrid mechanism according to the present invention;

[0142] Figure 2 A schematic diagram of deployment of an active wave compensation system for a deployment method of a marine boarding system based on a hybrid mechanism according to the present invention;

[0143] Figure 3 A schematic diagram of the active wave compensation system structure of a deployment method of a marine boarding system based on a hybrid mechanism according to the present invention;

[0144] Figure 4 This is a kinematic model diagram of the active wave compensation system of the deployment method of the marine boarding system based on the hybrid mechanism described in the present invention;

[0145] Figure 5 A schematic diagram of three-point positioning of an active wave compensation system in a deployment method of a marine boarding system based on a hybrid mechanism according to the present invention;

[0146] Figure 6 This is a diagram of the RBF neural network structure of a deployment method for a marine boarding system based on a hybrid mechanism according to the present invention;

[0147] Figure 7 This is a control system structure diagram of a deployment method of a marine boarding system based on a hybrid mechanism according to the present invention;

[0148] Figure 8 This is a simulation block diagram of the electro-hydraulic servo system AMEsim for the deployment method of the marine boarding system based on the hybrid mechanism described in the present invention;

[0149] Figure 9 This is a comparative curve diagram of tracking effects of a deployment method of a marine boarding system based on a hybrid mechanism according to the present invention;

[0150] Figure 10 This is a tracking error comparison curve diagram of a deployment method for a marine boarding system based on a hybrid mechanism described in the present invention. DETAILED DESCRIPTION

[0151] In order to make the objectives, technical solutions, and advantages of the present invention more clearly understood, the present invention is further described in detail below with reference to the accompanying drawings and specific embodiments. It should be understood that the specific embodiments described herein are only intended to explain the present invention and are not intended to limit the present invention. That is, the specific embodiments described herein are only some embodiments of the present invention, not all embodiments. Generally, the components of the specific embodiments of the present invention described and illustrated in the drawings herein can be arranged and designed in various different configurations, and the present invention can also have other embodiments.

[0152] Therefore, the following detailed description of the specific embodiments of the present invention provided in the accompanying drawings is not intended to limit the scope of the invention as claimed, but is merely representative of selected specific embodiments of the present invention. All other specific embodiments obtained by those skilled in the art based on the specific embodiments of the present invention without making any creative efforts shall fall within the scope of protection of the present invention.

[0153] In order to further understand the content, features and effects of the present invention, the following specific embodiments are given as examples, and the attached Figure 1 -Attached Figure 10The detailed instructions are as follows: Specific implementation method one:

[0155] A method for deploying a marine boarding system based on a hybrid mechanism comprises the following steps:

[0156] S1. The controller moves the gangway ladder to the neutral position so that the end of the gangway ladder leaves the deck;

[0157] Furthermore, the specific implementation method of step S1 includes the following steps:

[0158] S1.1. Solve the inverse kinematics of the hybrid mechanism: Set α, β, and γ to be the rotation angles around the x, y, and z axes respectively. p ,Y p ,Z p is the position of the origin A of the upper platform coordinate system of the hybrid mechanism relative to the origin B of the lower platform coordinate system of the hybrid mechanism, E is the spatial inertial coordinate system, θ1 is the rotation angle of the revolute joint, θ2 is the pitch angle of the swing joint, and q3 is the telescopic length. The Stewart parallel platform homogeneous transformation matrix of the lower platform of the hybrid mechanism is obtained as follows: The expression is:

[0159]

[0160] Among them, cos(T)→c, sin(·)→s, the rotation matrix of the upper and lower platforms of the hybrid mechanism is P is the position vector of the origin A of the upper platform coordinate system relative to the origin B of the lower platform coordinate system of the hybrid mechanism;

[0161] S1.2, let the vector between the origin A and any point on the circumference of the hybrid mechanism be The vector between the origin B and any point on the circumference in the lower platform coordinate system of the hybrid mechanism is Then according to the upper and lower platform transformation matrix, we can get The relationship is expressed as:

[0162]

[0163] S1.3. Simplify the rotation matrices of the upper and lower platforms of the hybrid mechanism and express them as follows:

[0164]

[0165] Then substitute the expression in step S1.2 to obtain the expression:

[0166]

[0167] S1.4, the six connecting rods of the six-degree-of-freedom parallel platform of the hybrid mechanism are li (1,2,3,4,5,6), the two ends of the same connecting rod correspond to the upper and lower platform hinge points respectively, then the expression of the connecting rod length vector is:

[0168]

[0169] Then, the matrix expression in step S1.3 is substituted into the final result to obtain the connecting rod length l of the six-degree-of-freedom parallel platform of the joint mechanism. i The expression is:

[0170]

[0171]

[0172] S1.5. The homogeneous transformation matrix of the upper platform in series with the 3-DOF manipulator for constructing the hybrid mechanism is expressed as:

[0173]

[0174]

[0175] S2. Construct an RBF neural network adaptive controller model based on the electro-hydraulic servo system;

[0176] Furthermore, the specific implementation method of step S2 includes the following steps:

[0177] S2.1. Constructing the electro-hydraulic servo system model:

[0178] Defining state variables Converted into the state equation:

[0179]

[0180] Where y is the displacement of the hydraulic cylinder, is the speed of the hydraulic cylinder, p1 and p2 are the pressures on the left and right sides of the hydraulic cylinder respectively, m is the load mass of the hydraulic cylinder, A f S f are the modelable Coulomb friction amplitude, the continuous approximate Coulomb friction shape function, the external disturbance of the system and the unmodeled dynamics, β e is the elastic modulus of the hydraulic oil, A1 and A2 are the effective piston areas of the left and right chambers of the hydraulic cylinder, V 01 、V 02 are the dead volume of the left and right chambers of the hydraulic cylinder, C t is the hydraulic cylinder leakage coefficient, k i ,k q ,p s ,p rThey are valve core current gain, valve core displacement flow gain, system oil source pressure, and return oil pressure; Q1 and Q2 are the flow rates of the two chambers of the hydraulic cylinder, and τ is the external load force on the hydraulic cylinder;

[0181] The flow rate of the two chambers of the hydraulic cylinder is set, and τ is the external load force on the hydraulic cylinder. The calculation formula is:

[0182] Q1=gR1u

[0183] Q2=gR2u

[0184]

[0185]

[0186]

[0187]

[0188] The expression is:

[0189]

[0190] S2.2. Define new state variables The nonlinear part is defined as g(x1,p1,p2), then the new state equation is:

[0191]

[0192] Wherein, u is the input signal of the servo valve;

[0193] S2.3 Definitions Then the expression is:

[0194]

[0195]

[0196] Among them, x is the input of the network, j is the jth node of the hidden layer of the network, h=[h j ] T is the Gaussian basis function output of the network, W * and V * are the ideal weights of the networks f(·) and g(·), ε f and ε g is the approximation error of the network, then the expression is:

[0197] |ε f |≤ε Mf ,|ε g |≤ε Mg

[0198]

[0199] f(·)=W *T h f (x)+ε f ,g(·)=V *T h g (x)+ε g

[0200]

[0201] S2.4. Define the expression of the Lyapunov function as:

[0202]

[0203] in, e=x1-x d γ1>0,γ2>0;

[0204] Then the following expression is obtained through transformation:

[0205]

[0206] S2.5. Define the expression of the design control law as:

[0207]

[0208] Substituting the expression in step S2.4, we obtain the following formula:

[0209]

[0210]

[0211] S2.6, take η>|ε| max , the expression of the adaptive law is:

[0212]

[0213]

[0214] Then we get Among them, the role of the robust term ηsgn(s) in the control law is to overcome the neural network approximation error to ensure system stability;

[0215] If and only if s=0, According to the LaSalle invariance principle, the closed-loop system is asymptotically stable, that is, when t→∞, s→0, and the convergence rate of the system depends on η;

[0216] S3, using a position sensor and an attitude sensor to collect hull attitude information data and position information data;

[0217] Furthermore, the specific implementation method of step S3 is to use an inertial navigation system and an ultrasonic rangefinder to collect the hull attitude information data and position information data respectively, wherein the inertial navigation system serves as the main attitude measurement device of the survey ship, and the hull position information data uses three ultrasonic rangefinders to measure the real-time relative position of the hull to the offshore wind power platform using the principle of three-point ranging;

[0218] Using three ultrasonic rangefinders and three-point positioning, the calculation formula for the position change of the gangway relative to the target point of the wind turbine platform can be measured:

[0219]

[0220] [x i ,y i ,z i ], i = 1, 2, 3 are the coordinates of the fixed target points of the three ultrasonic rangefinders on the wind turbine platform, L1, L2, L3 are the lengths output by the three ultrasonic rangefinders;

[0221] Simplified:

[0222]

[0223] Pick:

[0224] a1=2(x2-x1), b1=2(y2-y1), d1=L1 2 -L2 2 -(x1 2 -x2 2 )-(y1 2 -y2 2 )

[0225] a2=2(x3-x2), b2=2(y3-y2), d2=L2 2 -L3 2 -(x2 2 -x3 2 )-(y2 2 -y3 2 )

[0226] According to Cramer's rule:

[0227]

[0228] Substituting into the original formula we get:

[0229]

[0230] S4. Based on the hull attitude information data and position information data collected in step S3, before the deployment state, actively compensate the hybrid mechanism to keep the end of the gangway stationary relative to the wind turbine platform;

[0231] Furthermore, the specific implementation method of step S4 includes the following steps:

[0232] S4.1. Assume that the changes of the six degrees of freedom of the hybrid mechanism under the influence of waves are α, β, γ, and d x ,d y ,d z , then the homogeneous transformation matrix of the gangway is:

[0233]

[0234] Among them, the unknown items in the homogeneous transformation matrix of the gangway are expressed as follows:

[0235]

[0236] x=d x +cγcβ((d3+q3+d4)cθ1cθ2+d2cθ1)+(cγsβsα-sγcα)((d3+q3+d4)sθ1cθ2+d2sθ1)+(cγsβcα+sγsα)(d1+(d3+q3+d4)sθ2)

[0237] y=d y +sγcβ((d3+q3+d4)cθ1cθ2+d2cθ1)+(sγsβsα+cγcα)((d3+q3+d4)sθ1cθ2+d2sθ1)+(sγsβcα-cγsα)(d1+(d3+q3+d4)sθ2)

[0238] z=d z -sβ((d3+q3+d4)cθ1cθ2+d2cθ1)+cβsα((d3+q3+d4)sθ1cθ2+d2sθ1)+cβcα(d1+(d3+q3+d4)sθ2)

[0239] S4.2. Perform inverse kinematic analysis on the three-degree-of-freedom tandem gangway ladder under the influence of waves. The coordinates of the end of the gangway ladder in the earth-fixed coordinate system are: a p4=[x,y,z], solve the equations to get the motion of each joint:

[0240]

[0241]

[0242]

[0243] in,

[0244] a=(xd x )cβcγ+(yd y )cβsγ-(zd z )sβ

[0245] b=(xd x )(sαsβcγ-cαsγ)+(yd y )(sαsβsγ+cαcγ)+(zd z )sαcβ

[0246] c=(xd x )(cαsβcγ+sαsγ)+(yd y )(cαsβsγ-sαcγ)+(zd z )cαcβ

[0247] The dynamic equation of the gangway under wave disturbance is calculated as follows:

[0248]

[0249] Among them, G and τ d are the gravity term and the interference term of the waves, respectively. τ is the vector composed of the three joint torques. The unknown terms in the equation are as follows:

[0250] m 11 =m3[d2+(d3+d4+q3)cθ2] 2 +m2(d3cθ2+d2) 2 +m1d2 2

[0251] m 22 =m3(d3+d4+q3) 2 +m2d3 2

[0252] m 33 =m3

[0253] m 12 =m 21 =m 23 =m 32 =m 13 =m 31 =0

[0254]

[0255] c 12 =-c 21=-{m3(d3+d4+q3)[(d3+d4+q3)cθ2+d2]+m2d3(d3cθ2+d2)}

[0256]

[0257]

[0258]

[0259] c 33 =0

[0260] G 11 =0

[0261] G 21 =[m3(d3+d4+q3)+m2d3]gcθ2

[0262] G 31 =m3gsθ2

[0263]

[0264] S4.3. Use the RBF neural network adaptive controller model based on the electro-hydraulic servo system constructed in step S2 to track the change in the joint target and control the end of the gangway to remain stationary relative to the offshore wind turbine platform;

[0265] S5. Collect three-dimensional velocity information data of the end of the gangway relative to the landing point of the wind turbine platform, solve the hybrid mechanism, and obtain the target velocity of each joint;

[0266] Furthermore, the specific implementation method of step S5 includes the following steps:

[0267] S5.1. Set the linear velocity of the end of the gangway relative to the landing point of the wind turbine platform as v x ,v y ,v z , use Newton's method to solve the velocity of each joint in each joint space as follows:

[0268]

[0269] The unknown terms in the equation are as follows:

[0270]

[0271]

[0272] k 11 =(d3+q3+d4)cθ1sθ2+d1cθ1

[0273] k 12=[(d3+q3+d4)sθ1sθ2+d1sθ1]cα+[(d3+q3+d4)cθ2+d2]sα

[0274] k 13 =-[(d3+q3+d4)cθ1sθ2+d1cθ1]sβ+[(d3+q3+d4)sθ1sθ2+d1sθ1]sαcβ

[0275] -[(d3+q3+d4)cθ2+d2]cαcβ

[0276] k 14 =sθ1,k 15 =-cθ1,k 16 =0

[0277] k 21 =(d2+d3+q3+d4)sθ1

[0278] k 22 =-(d2+d3+q3+d4)cαcθ1

[0279] k 23 =-(d2+d3+q3+d4)(sβsθ1+sαcβcθ1)

[0280] k 24 =0,k 25 =0,k 26 =1

[0281] k 31 =-d1sθ1,k 32 =d1cθ1cα,k 33 =d1sθ1sβ+d1cθ1sαcβ

[0282] k 34 =0,k 35 =1,k 36 =0

[0283]

[0284] S5.2. Based on the calculation of the control quantity of each joint in S5.1, the control quantity of each joint is tracked using the RBF neural network adaptive controller model based on the electro-hydraulic servo system constructed in step S2;

[0285] S6. Under the condition of ship dynamic positioning, collect ship attitude and position information data, and actively compensate the hybrid mechanism in the deployed state;

[0286] Furthermore, in step S6, in the deployed state, the RBF neural network adaptive controller model based on the electro-hydraulic servo system constructed in step S2 is used to actively compensate the hybrid mechanism;

[0287] S7. Determine whether the end of the gangway has reached the target point of the wind turbine platform. If so, the deployment is completed and passive compensation is started. If not, return to step S5 and re-execute the deployment method of the marine boarding system based on the hybrid mechanism.

[0288] from Figure 2 As can be seen, the offshore boarding system is fixed to the deck and is used for offshore operations and maintenance of offshore wind turbine platforms. The wind turbine platform is stationary relative to the Earth's coordinate system, while the maintenance vessel is constantly swaying on the sea surface due to the influence of waves, such as roll, pitch, bow pitch, sway, surge, and heave. This technical solution is to design an offshore boarding system based on a hybrid mechanism to ensure that the end of the gangway can complete the docking task with the offshore platform at the operator's desired speed under the influence of waves.

[0289] from Figure 3 As can be seen, the hybrid mechanism consists of an upper platform, a three-DOF serial platform, and a lower platform, a six-DOF parallel platform. The upper platform, a three-DOF serial platform, consists of a telescopic gangway, a pitch mechanism, a slewing mechanism, and an operating platform. The lower platform, a six-DOF parallel platform, is composed of six hinged supports and six servo cylinders.

[0290] The six-degree-of-freedom parallel platform's primary actuators are six servo cylinders. Their rod ends are hinged to upper hinge supports, which are fixed to the lower surface of the motion platform. The servo cylinder bases are hinged to lower hinge supports, which are fixed to the upper surface of the static platform. The static platform is secured to the deck via anchor bolts, providing safe and reliable support for motion compensation.

[0291] from Figure 4 It can be seen that the coordinate system is established at the center of the parallel platform's dynamic and static platforms, and the coordinate system of the upper platform's gangway is established based on the telescoping, pitching, and rotation of the series mechanism.

[0292] from Figure 7 To verify the effectiveness of the control algorithm, an electro-hydraulic servo system model was built in AMEsim, and an RBF neural network sliding mode controller was programmed in MATLAB / Simulink. Based on the analysis of stability and tracking speed, the system parameters were modified while ensuring system stability, resulting in an improved RBF neural network sliding mode controller. The control effect was then verified.

[0293] from Figure 9 and Figure 10As can be seen, simulation analysis of the PID controller and the RBF neural network controller before and after improvement was performed. According to the simulation results, it can be seen that the improved RBF neural network sliding mode controller has the best tracking effect on the desired speed and the smallest tracking error, which can meet the speed tracking requirements in deployment.

[0294] It should be noted that relational terms such as "first" and "second" are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the terms "comprises," "comprising," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus comprising a series of elements includes not only those elements, but also other elements not explicitly listed, or elements inherent to such process, method, article, or apparatus. In the absence of further limitations, an element defined by the phrase "comprising a ..." does not exclude the presence of additional identical elements in the process, method, article, or apparatus comprising the element.

[0295] Although the present application has been described above with reference to specific embodiments, various modifications may be made thereto and components may be substituted with equivalents without departing from the scope of the present application. In particular, as long as there are no structural conflicts, the various features of the embodiments disclosed herein may be combined with each other in any manner, and the omission of an exhaustive description of these combinations in this specification is solely for the sake of space and resource conservation. Therefore, the present application is not limited to the specific embodiments disclosed herein, but includes all technical solutions within the scope of the claims.

Claims

1. A method for deploying a marine boarding system based on a hybrid mechanism, characterized in that: The steps include: S1. The controller moves the gangway ladder to the neutral position so that the end of the gangway ladder leaves the deck; S2. Construct an RBF neural network adaptive controller model based on the electro-hydraulic servo system; The specific implementation method of step S2 includes the following steps: S2.

1. Constructing the electro-hydraulic servo system model: Defining state variables Converted into the state equation: Where y is the displacement of the hydraulic cylinder, is the speed of the hydraulic cylinder, p1 and p2 are the pressures on the left and right sides of the hydraulic cylinder respectively, m is the load mass of the hydraulic cylinder, A f S f are the modelable Coulomb friction amplitude, the continuous approximate Coulomb friction shape function, the external disturbance of the system and the unmodeled dynamics, β e is the elastic modulus of the hydraulic oil, A1 and A2 are the effective piston areas of the left and right chambers of the hydraulic cylinder, V 01 、V 02 are the dead volume of the left and right chambers of the hydraulic cylinder, C t is the hydraulic cylinder leakage coefficient, k i ,k q ,p s ,p r They are valve core current gain, valve core displacement flow gain, system oil source pressure, and return oil pressure; Q1 and Q2 are the flow rates of the two chambers of the hydraulic cylinder, and τ is the external load force on the hydraulic cylinder; The flow rate of the two chambers of the hydraulic cylinder is set, and τ is the external load force on the hydraulic cylinder. The calculation formula is: Q1=gR1u Q2=gR2u The expression is: S2.

2. Define new state variables The nonlinear part is defined as g(x1,p1,p2), then the new state equation is: Wherein, u is the input signal of the servo valve; S2.3 Definitions Then the expression is: Among them, x is the input of the network, j is the jth node of the hidden layer of the network, h=[h j ] T is the Gaussian basis function output of the network, W * and V * are the ideal weights of the networks f(·) and g(·), ε f and ε g is the approximation error of the network, then the expression is: |e f |≤e Mf ,|e g |≤e Mg f(·)=W *T h f (x)+ε f ,g(·)=V *T h g (x)+ε g S2.

4. Define the expression of the Lyapunov function as: in, e=x1-x d γ1>0,γ2>0; Then the following expression is obtained through transformation: S2.

5. Define the expression of the design control law as: Substituting the expression in step S2.4, we obtain the following formula: S2.6, take η>|ε| max , the expression of the adaptive law is: Then we get Among them, the role of the robust term ηsgn(s) in the control law is to overcome the neural network approximation error to ensure system stability; If and only if s=0, According to the LaSalle invariance principle, the closed-loop system is asymptotically stable, that is, when t→∞, s→0, and the convergence rate of the system depends on η; S3, using a position sensor and an attitude sensor to collect hull attitude information data and position information data; S4. Based on the hull attitude information data and position information data collected in step S3, before the deployment state, actively compensate the hybrid mechanism to keep the end of the gangway stationary relative to the wind turbine platform; S5. Collect three-dimensional velocity information data of the end of the gangway relative to the landing point of the wind turbine platform, solve the hybrid mechanism, and obtain the target velocity of each joint; S6. Under the condition of ship dynamic positioning, collect ship attitude and position information data, and actively compensate the hybrid mechanism in the deployed state; S7. Determine whether the end of the gangway has reached the target point of the wind turbine platform. If so, the deployment is completed and passive compensation is started. If not, return to step S5 and re-execute the deployment method of the marine boarding system based on the hybrid mechanism.

2. The method for deploying a marine boarding system based on a hybrid mechanism according to claim 1, characterized in that: The specific implementation method of step S1 includes the following steps: S1.

1. Solve the inverse kinematics of the hybrid mechanism: Set α, β, and γ to be the rotation angles around the x, y, and z axes respectively. p ,Y p ,Z p is the position of the origin A of the upper platform coordinate system of the hybrid mechanism relative to the origin B of the lower platform coordinate system of the hybrid mechanism, E is the spatial inertial coordinate system, θ1 is the rotation angle of the revolute joint, θ2 is the pitch angle of the swing joint, and q3 is the telescopic length. The Stewart parallel platform homogeneous transformation matrix of the lower platform of the hybrid mechanism is obtained as follows: The expression is: Among them, cos(·)→c, sin(·)→s, the rotation matrix of the upper and lower platforms of the hybrid mechanism is P is the position vector of the origin A of the upper platform coordinate system relative to the origin B of the lower platform coordinate system of the hybrid mechanism; S1.2, let the vector between the origin A and any point on the circumference of the hybrid mechanism be The vector between the origin B and any point on the circumference in the lower platform coordinate system of the hybrid mechanism is Then according to the upper and lower platform transformation matrix, we can get The relationship is expressed as: S1.

3. Simplify the rotation matrices of the upper and lower platforms of the hybrid mechanism and express them as follows: Then substitute the expression in step S1.2 to obtain the expression: S1.4, the six connecting rods of the six-degree-of-freedom parallel platform of the hybrid mechanism are l i (1,2,3,4,5,6), the two ends of the same connecting rod correspond to the upper and lower platform hinge points respectively, then the expression of the connecting rod length vector is: Then, the matrix expression in step S1.3 is substituted into the final result to obtain the connecting rod length l of the six-degree-of-freedom parallel platform of the joint mechanism. i The expression is: S1.

5. The homogeneous transformation matrix of the upper platform in series with the 3-DOF manipulator for constructing the hybrid mechanism is expressed as:

3. The method for deploying a marine boarding system based on a hybrid mechanism according to claim 2, characterized in that: The specific implementation method of step S3 is to use inertial navigation and ultrasonic rangefinders to collect hull attitude information data and position information data respectively, wherein the inertial navigation is used as the main attitude measurement equipment of the survey ship, and the hull position information data uses three ultrasonic rangefinders to measure the real-time relative position with the offshore wind power platform using the principle of three-point ranging.

4. The method for deploying a marine boarding system based on a hybrid mechanism according to claim 3, characterized in that: The specific implementation method of step S4 includes the following steps: S4.

1. Assume that the changes of the six degrees of freedom of the hybrid mechanism under the influence of waves are α, β, γ, and d x ,d y ,d z , then the homogeneous transformation matrix of the gangway is: Among them, the unknown items in the homogeneous transformation matrix of the gangway are expressed as follows: x=d x +cγcβ((d3+q3+d4)cθ1cθ2+d2cθ1)+(cγsβα-sγcα)((d3+q3+d4)sθ1cθ2+d2sθ1) +(cγsβcα+sγsα)(d1+(d3+q3+d4)sθ2) y=d y +sγcβ((d3+q3+d4)cθ1cθ2+d2cθ1)+(sγsβα+cγcα)((d3+q3+d4)sθ1cθ2+d2sθ1) +(sγsβcα-cγsα)(d1+(d3+q3+d4)sθ2) z=d z -sβ((d3+q3+d4)cθ1cθ2+d2cθ1)+cβsa((d3+q3+d4)sθ1cθ2+d2sθ1) +cβcα(d1+(d3+q3+d4)sθ2) S4.

2. Perform inverse kinematic analysis on the three-degree-of-freedom tandem gangway ladder under the influence of waves. The coordinates of the end of the gangway ladder in the earth-fixed coordinate system are: a p4=[x,y,z], solve the equations to get the motion of each joint: in, a=(x-d x )cβcγ+(y-d y )cβsγ-(z-d z )sβ b=(x-d x )(sαsβcγ-cαsγ)+(y-d y )(sαsβsγ+cαcγ)+(z-d z )sαcβ c=(x-d x )(cαsβcγ+sαsγ)+(y-d y )(cαsβsγ-sαcγ)+(z-d z )cαcβ The dynamic equation of the gangway under wave disturbance is calculated as follows: Among them, G and τ d are the gravity term and the interference term of the waves, τ is the vector composed of the three joint torques, and the unknown terms in the equation are as follows: <h2 style=";text-align:left;direction:ltr">m<h2 style=";text-align:left;direction:ltr"> 11 <h2 style=";text-align:left;direction:ltr"> =m3[d2+(d3+d4+q3)cθ2]<h2 style=";text-align:left;direction:ltr"> 2 <h2 style=";text-align:left;direction:ltr"> +m2(d3cθ2+d2)<h2 style=";text-align:left;direction:ltr"> 2 <h2 style=";text-align:left;direction:ltr"> +m1d2<h2 style=";text-align:left;direction:ltr"> 2 m 22 =m3(d3+d4+q3) 2 +m2d3 2 <h2 style=";text-align:left;direction:ltr">m<h2 style=";text-align:left;direction:ltr"> 33 <h2 style=";text-align:left;direction:ltr"> =m3 m 12 =m 21 =m 23 =m 32 =m 13 =m 31 =0 c 12 -c 21 =-{m3(d3+d4+q3)[(d3+d4+q3)cθ2+d2]+m2d3(d3cθ2+d2)} c 33 ＝0 G 11 ＝0 G 21 [m3(d3+d4+q3)+m2d3]gcθ2 G 31 =m3gsθ2 S4.

3. Use the RBF neural network adaptive controller model based on the electro-hydraulic servo system constructed in step S2 to track the change in joint target and control the stationary state of the end of the gangway relative to the offshore wind turbine platform.

5. The method for deploying a marine boarding system based on a hybrid mechanism according to claim 4, characterized in that: The specific implementation method of step S5 includes the following steps: S5.

1. Set the linear velocity of the end of the gangway relative to the landing point of the wind turbine platform as v x ,v y ,v z , use Newton's method to solve the velocity of each joint in each joint space as follows: The unknown terms in the equation are as follows: k 11 =(d3+q3+d4)cθ1sθ2+d1cθ1 k 12 =[(d3+q3+d4)sθ1sθ2+d1sθ1]cα+[(d3+q3+d4)cθ2+d2]sα k 13 =-[(d3+q3+d4)cθ1sθ2+d1cθ1]sβ+[(d3+q3+d4)sθ1sθ2+d1sθ1]sαcβ -[(d3+q3+d4)cθ2+d2]cαcβ k 14 =sθ1,k 15 =-cθ1,k 16 =0 k 21 (d2+d3+q3+d4)sθ1 k 22 -(d2+d3+q3+d4)cαcθ1 k 23 =-(d2+d3+q3+d4)(sβsθ1+sαcβcθ1) k 24 =0,k 25 =0,k 26 =1 k 31 =-d1sθ1,k 32 =d1cθ1cα,k 33 =d1sθ1sβ+d1cθ1sαcβ k 34 =0,k 35 =1,k 36 =0 r 11 =-sθ1cβcγ+cθ1(sαsβcγ-cαsγ) r 12 =-sθ1cβsγ+cθ1(sαsβsγ+cαcγ) r 13 =sθ1sβ+cθ1sαcβ r 31 =cθ1cθ2cβcγ+sθ1cθ2(sαsβcγ-cαsγ)+sθ2(cαsβcγ+sαsγ) r 32 =cθ1cθ2cβsγ+sθ1cθ2(sαsβsγ+cαcγ)+sθ2(cαsβsγ-sαcγ) r 33 =-cθ1cθ2sβ+sθ1cθ2sαcβ+sθ2cαcβ S5.

2. Based on the calculation of the control quantity of each joint in S5.1, the control quantity of each joint is tracked using the RBF neural network adaptive controller model based on the electro-hydraulic servo system constructed in step S2.

6. The method for deploying a marine boarding system based on a hybrid mechanism according to claim 5, characterized in that: In step S6, in the deployed state, the RBF neural network adaptive controller model based on the electro-hydraulic servo system constructed in step S2 is used to actively compensate the hybrid mechanism.

Images