Ground effect vehicle control method and ground effect vehicle for offshore wind turbine inspection

Abstract

The invention discloses a ground effect vehicle control method and a ground effect vehicle for inspection of offshore wind turbine generators. The method comprises: obtaining environmental data; combining the environmental data, the overall control system of the ground effect vehicle comprises three ground effect vehicle input compensations: ground effect vehicle compensation under non-wave disturbance, ground effect vehicle compensation under wave disturbance, and wind turbine generator compensation under wave disturbance; the three ground effect vehicle input compensations are added together as the real-time total input of the overall control system of the ground effect vehicle to control the state of the ground effect vehicle. The ground effect vehicle control method and the ground effect vehicle for inspection of offshore wind turbine generators disclosed by the invention can achieve the purpose of image stability and accuracy during the inspection process.

Description

Technical Field

[0001] The invention relates to the technical field of wind power generation, and in particular to a ground effect vehicle control method and a ground effect vehicle for inspecting offshore wind turbines. Background Art

[0002] As an important renewable energy source, offshore wind power generation has been widely used and developed rapidly due to its huge power generation potential and low environmental impact. However, the operating environment of offshore wind turbines is complex and the equipment is widely distributed. Traditional inspection methods are difficult to meet the needs of efficient, safe and accurate inspections.

[0003] Traditional offshore wind turbine inspections mainly rely on manual and drone inspections, including:

[0004] Manual inspection: Professional technicians regularly go to the offshore generator site by ship or helicopter to conduct visual inspections, take photos, record data, and perform necessary maintenance operations. Although this method is highly real-time and can detect complex problems through manual judgment, it has the disadvantages of high cost, high risk, low efficiency, and is difficult to implement, especially in bad weather conditions.

[0005] Fixed monitoring system: Fixed sensors and cameras are installed on the generator and its surroundings to monitor the equipment status in real time and transmit data to the monitoring center remotely. This method requires professionals and equipment to install fixed monitoring equipment, which is more complicated and expensive, especially in offshore environments. Equipment maintenance and regular calibration also require high costs. Its monitoring range is limited by the installation location and cannot cover all areas, especially some equipment interiors and underwater parts. In addition, fixed monitoring systems cannot be moved flexibly, making it difficult to respond to emergencies or temporary problems.

[0006] Drone inspection: Use drones with cameras and sensors to inspect and take pictures and videos of generators, or collect other data. Drones can be programmed to automate inspection routes. However, drone inspections have limited endurance, complex data processing, and are more susceptible to weather.

[0007] Robotic inspection: Inspections are carried out by deploying underwater or surface robots, which are particularly suitable for inspecting underwater parts or hard-to-reach areas. The robots are equipped with cameras, sensors, manipulators and other equipment. However, this technology is very complex, and not only is the equipment cost high, but it is also difficult to maintain.

[0008] As a special aircraft that uses the ground effect to fly, ground effect vehicles have significant advantages due to their low flying altitude, high speed and strong stability. When flying at a height close to the ground or water surface, ground effect vehicles can obtain higher lift and lower resistance due to aerodynamic effects, thereby improving flight efficiency and endurance. Using ground effect vehicles to inspect offshore wind turbines can effectively overcome the shortcomings of traditional inspection methods and provide an efficient, safe and stable inspection method.

[0009] However, in the marine environment, ground effect vehicles will encounter a chaotic state caused by a variety of complex factors, including: frequent and unpredictable changes in wind speed and direction, which will cause dramatic fluctuations in the attitude and trajectory of the vehicle; the movement of waves and tides not only causes the vehicle to shake, but also affects its stability when flying at low altitudes; random and strong airflow disturbances may suddenly change the flight path of the vehicle; and various environmental noises, such as electromagnetic interference and mechanical vibration, which will affect the stability of the vehicle's sensor data and control system. The above factors work together to make the ground effect vehicle exhibit highly sensitive, nonlinear and unpredictable dynamic behavior during marine inspections, forming a complex chaotic state. Due to complex environmental factors, the image quality captured during the inspection process is poor, and image misalignment is prone to occur. If this problem is not solved, the inspection effect will be greatly reduced. Summary of the invention

[0010] The technical problem to be solved by the present invention is to solve the chaotic state problem of ground effect vehicles during marine inspections.

[0011] In order to solve the above technical problems, the present invention provides the following technical solutions:

[0012] A method for controlling a ground effect vehicle for inspecting an offshore wind turbine generator comprises:

[0013] Obtain environmental data;

[0014] Combined with environmental data, the overall control system of the ground effect vehicle includes three types of ground effect vehicle input compensation: ground effect vehicle compensation under no wave disturbance, ground effect vehicle compensation under wave disturbance, and wind turbine compensation under wave disturbance;

[0015] The three ground effect vehicle input compensations are added together as the real-time total input of the ground effect vehicle's overall control system to control the ground effect vehicle's state.

[0016] Advantages: The present invention adds three types of ground effect vehicle input compensations to obtain a total control input of the ground effect vehicle, thereby achieving the purpose of ensuring that the ground effect vehicle is not disturbed by environmental factors and that the image is stable and accurate during the inspection process.

[0017] In one embodiment of the present invention, obtaining ground effect vehicle compensation under non-wave disturbance includes the following steps:

[0018] Obtain historical and real-time data on offshore environment, including at least wind speed and direction;

[0019] In the simulation environment, historical and real-time data of the marine environment are input to simulate the flight state of the ground effect vehicle, including the yaw angle, speed and roll angle, and the relationship between the marine environment data and the flight state of the ground effect vehicle is obtained as a relational data set;

[0020] After preprocessing the relational data set, it is input into the deep neural network and trained based on the marine environment data to predict the optimal vehicle state of the ground effect vehicle;

[0021] The optimal vehicle state of the ground effect vehicle is used as the input of the PID controller, and the output of the PID controller is used as the compensation of the ground effect vehicle under non-wave disturbance.

[0022] In one embodiment of the present invention, the output of the PID controller is obtained by the following formula:

[0023] ;

[0024] ;

[0025] ;

[0026] In the formula, It is represented as the yaw angle output by the PID controller, Expressed as the speed output by the PID controller, Expressed as the roll angle output by the PID controller, Expressed as a scale parameter, Expressed as the integration parameter, Expressed as a differential parameter, Represents the optimal yaw angle predicted by the deep neural network, Denotes the optimal speed predicted by the deep neural network, Denotes the optimal roll angle predicted by the deep neural network, Represents the current yaw angle, Represents the current speed, Represents the current roll angle, Expressed as time;

[0027] Then, the compensation of ground effect vehicle under non-wave disturbance is for: .

[0028] In one embodiment of the present invention, an internal model dynamic compensator is used to obtain compensation of a ground effect vehicle under wave disturbance; wherein the internal model dynamic compensator is obtained by the following formula:

[0029] = ;

[0030] ;

[0031] In the formula, It is expressed as the compensation of ground effect vehicle under wave disturbance, It is represented by the flight state of the ground effect vehicle at the current moment in the internal model controller. , is represented as the identity matrix, is expressed as a non-singular moment, It is represented as the control input of the ground effect vehicle at the current moment under the wave disturbance.

[0032] In one embodiment of the present invention, the modeling step of the internal model dynamic compensator includes:

[0033] Establishing the initial ground effect vehicle control equation under the sea wave disturbance, the equation parameters include the flight state of the ground effect vehicle at the current moment, the ground effect vehicle control input at the current moment and the sea wave disturbance;

[0034] Set up wave disturbance according to the action of waves;

[0035] According to the internal model control method, the angular velocity, the flight state of the ground effect vehicle at the current moment, the control input of the ground effect vehicle at the current moment and the steady-state value of the wave disturbance are obtained, and the initial internal model control compensation equation group is obtained by combining the relationship between the angular momentum and the angular velocity of the ground effect vehicle and the initial ground effect vehicle control equation;

[0036] According to the requirement that the ground effect vehicle is in a stable state, the ground effect vehicle stability compensation equation is obtained through the initial internal model control compensation equation group: ;in, is the steady-state value of the wave disturbance, It is represented as the steady-state value of the ground effect vehicle control input at the current moment, It is expressed as the general parameter matrix of the initial WIG compensation equation;

[0037] Existence constant and constant ,make Relative to time The secondary derivative, then the ground effect vehicle stability compensation equation has the following expression:

[0038] ;

[0039] Setting parameter values , and order , and take its derivative to obtain the intermediate variable and the parameter matrix ; and according to the parameter value , intermediate variables and the parameter matrix , obtain the steady-state value of the ground effect vehicle control input at the current moment; where, Represented as transposed;

[0040] Select a pair of controllable matrices , combined with the intermediate variables and the parameter matrix , get the non-singular moments ;in, Expressed as the Hurwitz matrix, Represented as a normal constant matrix;

[0041] According to the controllable matrix and non-singular moments , construct internal model dynamic compensator and internal model controller.

[0042] In one embodiment of the present invention, the internal model controller is used to predict the flight state of the ground effect vehicle under wave disturbance; wherein the internal model controller is obtained by the following formula:

[0043] ;

[0044] In the formula, It represents the flight state of the ground effect vehicle at the next moment predicted by the internal model controller. It is represented by the flight state of the ground effect vehicle at the current moment in the internal model controller. It is represented as the control input of the ground effect vehicle at the current moment under the wave disturbance.

[0045] In one embodiment of the present invention, the steps for obtaining compensation for a wind turbine under wave disturbance include: designing a ground effect vehicle to sway at the same frequency as the wind turbine, observing the swaying of the wind turbine through a visual sensing device, and then compensating through a roll angle so that the captured image is positive.

[0046] In one embodiment of the present invention, the wind turbine generator compensation under wave disturbance is obtained by the following formula:

[0047] ;

[0048] In the formula, It is expressed as the compensation of wind turbine under wave disturbance, Expressed as the compensation of the roll angle, It is represented as the initial roll angle.

[0049] In one embodiment of the present invention, the overall control system of the ground effect vehicle is constructed by reusing the initial ground effect vehicle control equations under the disturbance of ocean waves.

[0050] The present invention also provides a ground effect vehicle, wherein the ground effect vehicle control method for inspecting offshore wind turbines is stored inside the ground effect vehicle.

[0051] Compared with the prior art, the invention has the following beneficial effects: the invention utilizes the low altitude, high speed and high stability characteristics of ground effect vehicles to design a patrol system and method specifically for offshore wind turbines, so as to improve patrol efficiency, reduce patrol costs, and enhance safety during the patrol process. In addition, during the patrol process, the periodic swing of wind turbines with the waves is considered in depth, and relative stillness after the swing synchronization is achieved, so as to obtain more accurate patrol images and improve image quality.

[0052] The present invention is based on a chaotic state recognition and modeling method of a deep neural network, which recognizes and predicts the chaotic state in advance through real-time analysis of environmental data. By collecting historical data and real-time data of the marine environment, including wind speed and wind direction, these data are trained using a deep neural network to construct a chaotic state prediction model to realize real-time input of environmental data, and the model outputs chaotic state prediction results. According to the chaotic state prediction results, the flight parameters of the aircraft are dynamically adjusted to achieve real-time compensation and stable control. According to the chaotic state prediction results, the adjustment parameters required by the aircraft are calculated. Using the PID control algorithm, the attitude, speed and direction of the aircraft are adjusted in real time.

[0053] Since the impact of waves on wind turbines and aircraft is different, in order to completely eliminate the impact of waves, the internal model control method is first used to estimate the wave effect, and then compensate on the aircraft to prevent the aircraft from being affected by the waves. Then, the visual equipment on the aircraft is used to observe the shaking of the wind turbine in real time, and then the roll angle is compensated to achieve the synchronous shaking of the aircraft and the wind turbine. BRIEF DESCRIPTION OF THE DRAWINGS

[0054] Figure 1 The present invention is a flow chart of a method for controlling a ground effect vehicle for inspecting offshore wind turbines according to an embodiment of the present invention.

[0055] Figure 2 The present invention is a general control flow chart of the general control system of the ground effect vehicle according to the embodiment of the present invention.

[0056] Figure 3 The figure is a flow chart of compensation of a ground effect vehicle under non-wave disturbance according to an embodiment of the present invention.

[0057] Figure 4 This is a block diagram of wind turbine generator compensation under sea wave disturbance according to an embodiment of the present invention. DETAILED DESCRIPTION

[0058] In order to facilitate those skilled in the art to understand the technical solution of the present invention, the technical solution of the present invention is further described in conjunction with the accompanying drawings of the specification.

[0059] The terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of the features. In the description of this application, the meaning of "plurality" is two or more, unless otherwise clearly and specifically defined.

[0060] See also Figure 1 and Figure 2 As shown, the present invention provides a ground effect vehicle control method for offshore wind turbine inspection, comprising:

[0061] S100, obtaining environmental data.

[0062] In one embodiment of the present invention, historical data and real-time data of the marine environment, including but not limited to wind speed, wind direction, airflow changes, etc., are collected through data acquisition equipment such as weather stations, ocean buoys, sensors on aircraft, etc.

[0063] S200, combined with environmental data, the overall control system of the ground effect vehicle includes three types of ground effect vehicle input compensation: ground effect vehicle compensation under non-wave disturbance, ground effect vehicle compensation under wave disturbance, and wind turbine compensation under wave disturbance.

[0064] See also Figures 1 to 3 As shown, in one embodiment of the present invention, obtaining ground effect vehicle compensation under non-wave disturbance includes the following steps:

[0065] S111, obtaining historical data and real-time data of the marine environment, including at least wind speed and wind direction.

[0066] S112, in the simulation environment, input historical data and real-time data of the marine environment, simulate the flight state of the ground effect vehicle, control the yaw angle, speed and roll angle, obtain the relationship between the marine environment data and the flight state of the ground effect vehicle, and use it as a relationship data set.

[0067] In one embodiment of the present invention, in the simulated environment, the simulated ground effect vehicle should keep what kind of attitude, speed and direction could keep stable.Specifically, the relationship between the marine environment data obtained and the flight state of the ground effect vehicle should comprise the ground effect vehicle optimal state data, such as yaw angle, roll angle, speed, marine environment data such as wind speed, wind direction etc.Wherein, the simulated environment for example can be simulink or X-Plane Flight Simulator etc. of matlab.

[0068] S113, after preprocessing the relational data set, the data set is input into the deep neural network, and after training based on the marine environment data, the optimal aircraft state of the ground effect vehicle is predicted.

[0069] In one embodiment of the present invention, the relational data set preprocessing includes sequentially performing data clarification, noise removal, outlier removal, and normalization to make the data suitable for input into a deep neural network. The deep neural network predicts the optimal aircraft state of the ground effect vehicle, which is expressed by the following formula:

[0070] ;

[0071] In the formula, Represents the optimal yaw angle predicted by the deep neural network, Denotes the optimal speed predicted by the deep neural network, Denotes the optimal roll angle predicted by the deep neural network, Represented as a deep neural network, Expressed as wind speed, The wind direction is represented by the wind direction. The present invention does not improve the deep neural network.

[0072] S114, taking the optimal aircraft state of the ground effect vehicle as the input of the PID controller, and the output of the PID controller as the ground effect vehicle compensation under non-wave disturbance.

[0073] In one embodiment of the present invention, the ground effect vehicle compensation strategy under non-wave disturbance adopts a hybrid method combining deep neural network and PID control, that is, first predicting the optimal aircraft state based on the marine environment data, and then using the optimal amount output by the deep neural network as the input of the PID controller to calculate the actual control input. Among them, the output of the PID controller is obtained by the following formula:

[0074] ;

[0075] ;

[0076] ;

[0077] In the formula, It is represented as the yaw angle output by the PID controller, Expressed as the speed output by the PID controller, Expressed as the roll angle output by the PID controller, Expressed as a scale parameter, Expressed as the integration parameter, Expressed as a differential parameter, Represents the current yaw angle, Represents the current speed, Represents the current roll angle, is expressed as time. Then, the compensation of ground effect vehicle under non-wave disturbance is for: .

[0078] In one embodiment of the present invention, an internal model dynamic compensator is used to obtain compensation of a ground effect vehicle under wave disturbance. The modeling steps of the internal model dynamic compensator include:

[0079] S211, establishing an initial ground effect vehicle control equation under sea wave disturbance, wherein the equation parameters include the flight state of the ground effect vehicle at the current moment, the ground effect vehicle control input at the current moment, and the sea wave disturbance.

[0080] In one embodiment of the present invention, for the convenience of explanation, the initial ground effect vehicle control equation can be abstractly interpreted as the following formula:

[0081] ;

[0082] In the formula, It represents the flight state of the ground effect vehicle at the next moment. It represents the flight status of the ground effect vehicle at the current moment. It is represented as the control input of the ground effect vehicle at the current moment under the wave disturbance, is represented by the ocean wave disturbance, and Represented as two ordinary parameter matrices. In the next step, the wave disturbance is modeled for the subsequent design of the internal model controller.

[0083] S212, setting the wave disturbance according to the wave action.

[0084] In one embodiment of the present invention, because the action form of the sea wave has a strong periodicity, the sea wave disturbance can be reasonably modeled into the following formula:

[0085] ;

[0086] In the formula, Expressed as The constant disturbance of the waves, , and They are the frequencies of disturbances to yaw angle, velocity and roll angle, respectively. , and They are respectively expressed as the phase of the yaw angle, velocity and roll angle disturbance, , and They are respectively expressed as the amplitude of the disturbance to the yaw angle, velocity and roll angle.

[0087] The above wave disturbance is further expanded to reduce the dimension for easy calculation and the wave disturbance is expressed as ;

[0088] Among them, the intermediate variable for:

[0089] ;

[0090] Intermediate variables for:

[0091] ;

[0092] Among them, the intermediate variable The time derivative of is:

[0093] ;

[0094] ;

[0095] in, is a matrix composed of the frequencies of yaw angle, velocity and roll angle disturbances. Through the measurement data of the inertial measurement unit carried by the aircraft, by fast Fourier transform, we can easily obtain the frequency domain analysis data of the ground effect vehicle. Therefore, it is relatively easy to know the disturbance frequency of the wave disturbance online, and Z is a matrix of known parameters. However, it is difficult to know the amplitude and phase of the wave disturbance without adding new expensive force and torque sensors. The internal model control method has a good effect in dealing with periodic disturbances. Specifically, it constructs a suitable internal model for the disturbance and combines it with the original system to form an enhanced system. In this way, the anti-interference control problem of the ground effect vehicle is transformed into the stability problem of the enhanced system.

[0096] S213, according to the internal model control method, the angular velocity, the flight state of the ground effect vehicle at the current moment, the control input of the ground effect vehicle at the current moment and the steady-state value of the wave disturbance are obtained, and the initial internal model control compensation equation group is obtained by combining the relationship between the angular momentum and angular velocity of the ground effect vehicle and the initial ground effect vehicle control equation.

[0097] In this embodiment, the relationship between the angular momentum and angular velocity of the ground effect vehicle is:

[0098] ;

[0099] ;

[0100] In the formula, and Represented as two defined values. No specific meaning, Expressed as the moment of inertia, Expressed as angular velocity, is represented as a parameter matrix.

[0101] Among them, the initial internal model control compensation equation group is obtained by the following formula:

[0102] ;

[0103] ;

[0104] In the formula, is expressed as the steady-state value of the angular velocity, It is expressed as the steady-state value of the flight state of the ground effect vehicle at the current moment, It is represented as the steady-state value of the ground effect vehicle control input at the current moment, Represents the steady-state value of the wave disturbance.

[0105] S214, according to the requirement that the ground effect vehicle is in a stable state, the ground effect vehicle stability compensation equation is obtained through the initial internal model control compensation equation group: ;in, is the steady-state value of the wave disturbance, It is represented as the steady-state value of the ground effect vehicle control input at the current moment, It is expressed as the general parameter matrix of the initial WIG compensation equations.

[0106] In one embodiment of the present invention, the requirement for the ground effect vehicle to be in a stable state is that the system output is 0, that is, , , then the ground effect vehicle stability compensation equation is: .

[0107] In the following steps S215 and S216, find the stability compensation equation of the ground effect vehicle. The details are as follows:

[0108] S215, existence constant and constant ,make Relative to time The secondary derivative, then the ground effect vehicle stability compensation equation has the following expression:

[0109] ;

[0110] S216, set parameter value , and order , and take its derivative to obtain the intermediate variable and the parameter matrix ; and according to the parameter value , intermediate variables and the parameter matrix , obtain the steady-state value of the ground effect vehicle control input at the current moment; where, Represented as transposed.

[0111] In this embodiment, the parameter value The derivative is obtained by the following formula:

[0112] ;

[0113] In the formula, Represented as parameter value The derivative of . Among them, the intermediate variable for:

[0114] ;

[0115] ;

[0116] in, Represented as the identity matrix.

[0117] The steady-state value of the ground effect vehicle control input at the current moment is obtained by the following formula:

[0118] ;

[0119] S217, select a pair of controllable matrices , combined with the intermediate variables and the parameter matrix , get the non-singular moments ;in, Expressed as the Hurwitz matrix, is represented as an ordinary constant matrix.

[0120] In one embodiment of the present invention, the non-singular moments It can be obtained by solving the Sylvester equation:

[0121] ;

[0122] In order to obtain the solution of non-singular moments , you can also do the following:

[0123] According to the non-singular moment For parameter values Perform a similarity transformation where the non-singular moments For parameter values The matrix after similarity transformation can be expressed as . Then according to , for the matrix after similarity transformation, we have:

[0124] ;

[0125] In the formula, Expressed as The derivative of , through the differential equation method, is more convenient to solve the non-singular moment .

[0126] S219, according to the controllable matrix and non-singular moments , construct internal model dynamic compensator and internal model controller.

[0127] In one embodiment of the present invention, through the above preparations, an internal model dynamic compensator and an internal model controller having the following expressions are constructed:

[0128] ;

[0129] = ;

[0130] ;

[0131] In the formula, It is expressed as the compensation of ground effect vehicle under wave disturbance, It is represented by the flight state of the ground effect vehicle at the current moment in the internal model controller. It represents the flight state of the ground effect vehicle at the next moment predicted by the internal model controller. It is represented as the control input of the ground effect vehicle at the current moment under the wave disturbance, Represented as an intermediate variable.

[0132] See also Figures 1 to 4As shown, in one embodiment of the present invention, since it is impossible to directly allow the wind turbine to eliminate the influence of the sea wave disturbance, the ground effect vehicle is designed to follow the wind turbine to shake at the same frequency to achieve the effect of eliminating the influence of the sea wave disturbance on the wind turbine. The ground effect vehicle observes the shaking of the wind turbine through a visual sensor device, and then compensates through the roll angle. Among them, the compensation of the wind turbine under the sea wave disturbance is obtained by the following formula:

[0133] ;

[0134] In the formula, It is expressed as the compensation of wind turbine under wave disturbance, Expressed as the compensation of the roll angle, It is expressed as the initial roll angle. Since the wave action will not cause huge shaking to large wind turbines, the image position will not deviate too much from the center, so the position offset of the shooting point is ignored, and the main thing is to ensure that the captured image is positive.

[0135] S300, adding the three ground effect vehicle input compensations as the real-time total input of the total control system of the ground effect vehicle to control the state of the ground effect vehicle.

[0136] In one embodiment of the present invention, the overall control system of the ground effect vehicle is constructed by reusing the initial ground effect vehicle control equation under the wave disturbance. ;in, It represents the flight state of the ground effect vehicle at the next moment predicted by the overall control system. It represents the flight status of the ground effect vehicle at the current moment in the overall control system. Expressed as three types of ground effect vehicle input compensation, , are two ordinary parameter matrices. It is worth noting that in the control system, the parameter matrices generally referred to are pure digital matrices. Unless explicitly defined, they are generally set by themselves. For example, in the embodiment, the explicitly defined parameter matrices are The parameter matrix you set yourself is as follows , , , , wait.

[0137] In this embodiment, the three ground effect vehicle compensations are added together to obtain the total ground effect vehicle control input, so as to achieve the purpose of preventing the ground effect vehicle from being disturbed by environmental factors and ensuring the stability and accuracy of the image during the inspection process.

[0138] See also Figures 1 to 4As shown, the present invention also provides a ground effect vehicle, in which the ground effect vehicle has stored therein the above-mentioned ground effect vehicle control method for inspecting offshore wind turbines.

[0139] It is obvious to those skilled in the art that the present invention is not limited to the details of the exemplary embodiments described above, and that the present invention can be implemented in other specific forms without departing from the spirit or essential features of the present invention. Therefore, the embodiments should be regarded as exemplary and non-limiting from any point of view, and the scope of the present invention is defined by the appended claims rather than the above description, and it is intended that all changes falling within the meaning and scope of the equivalent elements of the claims are included in the present invention, and any reference numerals in the claims should not be regarded as limiting the claims involved.

[0140] The above-described embodiments merely represent implementation methods of the invention. The protection scope of the present invention is not limited to the above-described embodiments. For those skilled in the art, several modifications and improvements may be made without departing from the concept of the present invention, which all belong to the protection scope of the present invention.

Claims

1. A ground effect vehicle control method for offshore wind turbine inspection, characterized in that: include: Obtain environmental data; Combined with environmental data, the overall control system of the ground effect vehicle includes three types of ground effect vehicle input compensation: ground effect vehicle compensation under no wave disturbance, ground effect vehicle compensation under wave disturbance, and wind turbine compensation under wave disturbance; The three ground effect vehicle input compensations are added together as a real-time total input of the total control system of the ground effect vehicle to control the state of the ground effect vehicle; The internal model dynamic compensator is used to obtain the compensation of the ground effect vehicle under the wave disturbance; wherein the internal model dynamic compensator is obtained by the following formula: = ； ； In the formula, It is expressed as the compensation of ground effect vehicle under wave disturbance, It is represented by the flight state of the ground effect vehicle at the current moment in the internal model controller. , is represented as the identity matrix, is expressed as a non-singular moment, It is represented as the control input of the ground effect vehicle at the current moment under the wave disturbance; And, the steps for obtaining compensation for wind turbines under wave disturbance include: designing a ground effect vehicle to sway at the same frequency as the wind turbine, observing the swaying of the wind turbine through visual sensing equipment, and then compensating through the roll angle to make the captured image positive.

2. The ground effect vehicle control method for offshore wind turbine inspection according to claim 1, characterized in that: Obtaining ground effect vehicle compensation without sea wave disturbance includes the following steps: Obtain historical and real-time data on offshore environment, including at least wind speed and direction; In the simulation environment, historical and real-time data of the marine environment are input to simulate the flight state of the ground effect vehicle, including the yaw angle, speed and roll angle, and the relationship between the marine environment data and the flight state of the ground effect vehicle is obtained as a relational data set; After preprocessing the relational data set, it is input into the deep neural network and trained based on the marine environment data to predict the optimal vehicle state of the ground effect vehicle; The optimal vehicle state of the ground effect vehicle is used as the input of the PID controller, and the output of the PID controller is used as the compensation of the ground effect vehicle under non-wave disturbance.

3. The ground effect vehicle control method for offshore wind turbine inspection according to claim 2, characterized in that: The output of the PID controller is obtained by the following formula: ； ； ； In the formula, Expressed as the yaw angle output by the PID controller, Expressed as the speed output by the PID controller, Expressed as the roll angle output by the PID controller, Expressed as a scale parameter, Expressed as the integration parameter, Expressed as a differential parameter, Represents the optimal yaw angle predicted by the deep neural network, Denotes the optimal speed predicted by the deep neural network, Denotes the optimal roll angle predicted by the deep neural network, Represents the current yaw angle, Represents the current speed, Represents the current roll angle, Expressed as time; Then, the compensation of ground effect vehicle under non-wave disturbance is for: .

4. The ground effect vehicle control method for offshore wind turbine inspection according to claim 1, characterized in that: The modeling steps of the internal model dynamic compensator include: Establishing the initial ground effect vehicle control equation under the sea wave disturbance, the equation parameters include the flight state of the ground effect vehicle at the current moment, the ground effect vehicle control input at the current moment and the sea wave disturbance; Set up wave disturbance according to the action of waves; According to the internal model control method, the angular velocity, the flight state of the ground effect vehicle at the current moment, the control input of the ground effect vehicle at the current moment and the steady-state value of the wave disturbance are obtained, and the initial internal model control compensation equation group is obtained by combining the relationship between the angular momentum and the angular velocity of the ground effect vehicle and the initial ground effect vehicle control equation; According to the requirement that the ground effect vehicle is in a stable state, the ground effect vehicle stability compensation equation is obtained through the initial internal model control compensation equation group: ;in, is the steady-state value of the wave disturbance, It is represented as the steady-state value of the ground effect vehicle control input at the current moment, It is expressed as the general parameter matrix of the initial WIG compensation equation; Existence constant and constant ,make Relative to time The secondary derivative, then the ground effect vehicle stability compensation equation has the following expression: ； Setting parameter values , and order , and take its derivative to obtain the intermediate variable and the parameter matrix ; and according to the parameter value , intermediate variables and the parameter matrix , obtain the steady-state value of the ground effect vehicle control input at the current moment; where, Represented as transposed; Select a pair of controllable matrices , combined with the intermediate variables and the parameter matrix , get the non-singular moments ;in, Expressed as the Hurwitz matrix, Represented as a normal constant matrix; According to the controllable matrix and non-singular moments , construct internal model dynamic compensator and internal model controller.

5. The ground effect vehicle control method for offshore wind turbine inspection according to claim 4, characterized in that: The internal model controller is used to predict the flight state of the ground effect vehicle under wave disturbance; the internal model controller is obtained by the following formula: ； In the formula, It represents the flight state of the ground effect vehicle at the next moment predicted by the internal model controller. It is represented by the flight state of the ground effect vehicle at the current moment in the internal model controller. It is represented as the control input of the ground effect vehicle at the current moment under the wave disturbance.

6. The ground effect vehicle control method for offshore wind turbine inspection according to claim 1, characterized in that: The wind turbine generator compensation under wave disturbance is obtained by the following formula: ； In the formula, It is expressed as the compensation of wind turbine under wave disturbance, Expressed as the compensation of the roll angle, Denoted as the initial roll angle.

7. The ground effect vehicle control method for offshore wind turbine inspection according to claim 4, characterized in that: The overall control system of the WIG vehicle is constructed by reusing the initial WIG vehicle control equations under sea wave disturbance.

8. A ground effect vehicle, characterized in that: The ground effect vehicle has stored therein the ground effect vehicle control method for inspecting offshore wind turbines as described in any one of claims 1-7.

Images