A multi-sensor collaborative control method and system for floating installation

Abstract

The present invention provides a multi-sensor collaborative control method and system for floating installation. The method includes: S1, collecting real-time data from a sensor array; S2, extracting dynamic environmental features from a unified feature sequence, constructing a real-time ocean environment model, and predicting disturbance parameters at the next moment based on the real-time ocean environment model; S3, constructing a real-time mechanical model of the floating body; S4, transmitting an optimal control signal to the floating body execution system to drive the floating body to perform dynamic adjustment; S5, updating the optimal control signal for optimization. The present invention realizes a complete closed loop from environmental perception, attitude optimization to dynamic control during the floating installation process, significantly improves the accuracy and stability of floating installation, and at the same time has a high adaptability to the dynamic ocean environment.

Description

Technical Field

[0001] The present invention belongs to the field of multi-sensor collaborative control, and particularly relates to a multi-sensor collaborative control method and system for floating installation. Background Art

[0002] In ocean engineering, floating installation is a complex and critical technology, which is widely used in the transportation, positioning and fixing of floating wind power foundations, deep-sea oil platform modules and large underwater structures. This process needs to overcome many challenges in the marine environment, such as the dynamic changes of water flow, waves, wind force, and the complexity of seabed topography. These factors not only pose extremely high requirements for the stability and precise positioning of the floating body, but also have a profound impact on the efficiency, safety and cost-effectiveness of the entire installation process.

[0003] Current floating installation technologies mainly rely on manual operation and single-sensor control strategies. For example, traditional systems usually use water flow sensors or inertial measurement units (IMUs) to monitor the dynamic state of the floating body during installation alone. However, these methods have significant limitations:

[0004] Functional limitations of single sensors: Single sensors cannot comprehensively reflect the environmental complexity during floating installation. For example, a water flow sensor can monitor the flow rate, but it is difficult to provide attitude information; an IMU can monitor the attitude, but its ability to perceive environmental interference is insufficient.

[0005] Poor real-time adaptability to environmental changes: The marine environment is dynamic and highly unpredictable, and existing technologies cannot effectively model and predict the changing trends of water flow and waves. This lack of environmental perception and prediction ability often leads to increased installation deviation and task failure.

[0006] Lack of systematic collaborative control: Existing technologies are mostly single-point optimizations, and it is difficult to effectively fuse multiple sensor data, resulting in insufficient accuracy of floating body attitude adjustment and being easily affected by sudden environmental disturbances.

[0007] In the face of the above problems, in recent years, some scholars have tried to apply multi-sensor fusion technology and artificial intelligence to the floating installation scenario. However, these attempts often rely too much on a single technical point (such as data fusion algorithms), and fail to establish a complete closed-loop scheme that combines dynamic environment prediction, mechanical modeling and control optimization, and cannot comprehensively solve the accuracy and stability problems existing in the floating installation process. Summary of the Invention

[0008] The purpose of the present invention is to propose a multi-sensor collaborative control method and system for floating installation, which comprehensively solves the problems of precise control and stability during the floating installation process by performing multi-sensor collaborative control through real-time marine environment prediction and mechanical state optimization.

[0009] To achieve the above object, in the first aspect of the present invention, a multi-sensor collaborative control method for floating installation is provided, and the method includes:

[0010] S1. Collect real-time data from the sensor array, preprocess the real-time data and establish a multi-modal mapping matrix, map the preprocessed data to a unified feature space through the multi-modal mapping matrix, and obtain a unified feature sequence;

[0011] S2. Extract dynamic environment features from the unified feature sequence, construct a real-time ocean environment model combining time series trend and spatial correlation, and predict the disturbance parameters at the next moment based on the real-time ocean environment model; wherein, the disturbance parameters include the flow velocity, wave intensity and direction at the next time step;

[0012] S3. Based on the real-time ocean environment model and the predicted disturbance parameters, combined with the unified feature sequence, construct a real-time mechanical model of the floating dock, and estimate the real-time stress state and attitude parameters of the floating dock by combining the disturbance parameters in the dynamic ocean environment; wherein, the stress state is the total stress of the floating dock, that is, the total stress of the floating dock in the x, y, and z directions; the attitude parameters are the attitude parameters of the floating dock, that is, the rotation angles of the floating dock in the x, y, and z directions;

[0013] S4. Design an optimization objective function according to the estimated real-time stress state and attitude parameters of the floating dock and the predicted disturbance parameters at the next moment, calculate the optimal control signal of the floating dock, and transmit the optimal control signal to the floating dock execution system to drive the floating dock to perform dynamic adjustment;

[0014] S5. Monitor and collect the actual stress and attitude after the execution of the optimal control signal in real time, compare the actual stress and attitude after execution with the target stress and attitude, dynamically generate a compensation signal, and correct the compensation signal based on the comparison result of the actual stress and attitude parameters after execution and the target stress and attitude parameters, update the optimal control signal for optimization according to the corrected compensation signal, and finally obtain the final stress state and attitude parameters, and verify whether the final stable stress state and attitude parameters reach the target state by comparing with the target stress state and attitude parameters of the floating dock. If the error exceeds the tolerance range, perform dynamic feedback adjustment.

[0015] Further, the sensor array includes a flow velocity sensor, a water depth pressure sensor, a sonar sensor and an inertial measurement unit;

[0016] The preprocessing includes performing time series consistency processing, specific noise filtering, normalization processing and mapping processing on the real-time data.

[0017] Further, the S2 specifically includes:

[0018] Design a weighted spatial feature mapping function according to the non-uniformity of multimodal data in the marine environment, and dynamically adjust the contributions of different modalities;

[0019] Construct a real-time marine environment model based on the weighted spatial feature mapping function, and output the hidden state, the mapping matrix from features to the hidden state, and the state transition matrix;

[0020] Predict the perturbation parameters at the next time step according to the hidden state, and introduce the fluid continuity constraint into the real-time marine environment model to ensure the physical rationality of the prediction.

[0021] Furthermore, the weighted spatial feature mapping function realizes the dynamic adjustment of the contributions of different modalities by introducing a sparse regularization term;

[0022] The real-time marine environment model uses the state transition formula to capture the dynamic change trend of the time series, and at the same time adds a specific perturbation term of the marine environment to output the hidden state;

[0023] Based on the output hidden state, use a recurrent neural network to predict the perturbation parameters at the next time step of.

[0024] Furthermore, the S3 specifically includes:

[0025] Design a basic mechanics model;

[0026] Add the anti-torsion performance constraint for floating installation and fluid continuity regularization to the basic mechanics model; wherein, the anti-torsion performance constraint is used to limit the change amount of the rotation angle, and the fluid continuity regularization is used to constrain its divergence to satisfy the fluid continuity condition;

[0027] Design the total optimization objective of the mechanics model.

[0028] Furthermore, the basic mechanics model is the total force on the real-time floating support, and the total force on the real-time floating support includes buoyancy, gravity, dynamically generated control signals, and drag force; wherein, the dynamically generated control signal represents the acting force of the floating support in the direction;

[0029] The anti-torsion performance constraint is used to limit the change amount of the rotation angle;

[0030] The fluid continuity regularization is used to constrain its divergence to satisfy the fluid continuity condition;

[0031] Iteratively solve the total force and attitude parameters of the real-time floating support by numerical optimization methods, and dynamically update the force state and attitude parameters.

[0032] Furthermore, the S4 specifically includes:

[0033] Design the control optimization objective function;

[0034] Use numerical optimization methods to solve for the optimal control signal;

[0035] Output the optimized control signal, adjust the force state and attitude of the floating support in real time, and transmit the control signal to the floating support execution system to drive the floating support for dynamic adjustment;

[0036] Among them, the control optimization objective function is used to achieve force balance and attitude adjustment. The force balance means that the total force is closest to the ideal force state, and the attitude adjustment is that the attitude parameters of the floating support tend to the target attitude in real time.

[0037] Further, add a dynamic disturbance compensation term and an energy consumption limit term to the design of the control optimization objective function; the dynamic disturbance compensation term is used to reduce the influence of the floating support response delay, and the energy consumption limit term is used to limit the intensity of the control signal.

[0038] Further, in S5, execute the optimal control signal, which acts on the floating support through the thrusters and the attitude adjustment device. The thrusters adjust the movement of the floating support in the direction, and the attitude adjustment device adjusts the rotation angle of the floating support according to the target attitude; the compensation signal is achieved by superimposing on the original control signal;

[0039] By correcting the compensation signal, design a dynamic disturbance correction term based on the prediction of the environmental disturbance correction vector generated by the marine environment model to reduce the impact of sudden environmental disturbances on the state of the floating support.

[0040] A multi-sensor collaborative control system for floating support installation, the system includes:

[0041] In another aspect of the present invention, there is provided a multi-sensor collaborative control system for floating support installation, the system includes:

[0042] A real-time data acquisition unit, which is used to collect real-time data from the sensor array, preprocess the real-time data and establish a multi-modal mapping matrix, and map the preprocessed data to a unified feature space through the multi-modal mapping matrix to obtain a unified feature sequence;

[0043] An environment prediction unit, which is used to extract dynamic environment features from the unified feature sequence, construct a real-time marine environment model combining time series trends and spatial correlations, and predict the disturbance parameters at the next moment based on the real-time marine environment model; among them, the disturbance parameters include the flow velocity, wave intensity and direction at the next time step;

[0044] The floating installation analysis unit is used to construct a real-time mechanical model of the floating body based on a real-time ocean environment model and predicted disturbance parameters, combined with a unified feature sequence, and estimate the real-time stress state and attitude parameters of the floating body by combining the disturbance parameters in the dynamic ocean environment; wherein, the stress state is the total stress of the floating body, that is, the total stress of the floating body in the x, y, and z directions; the attitude parameters are the attitude parameters of the floating body, that is, the rotation angles of the floating body in the x, y, and z directions.

[0045] The installation adjustment control unit is used to design an optimization objective function according to the estimated real-time stress state and attitude parameters of the floating body and predict the disturbance parameters at the next moment, calculate the optimal control signal of the floating body, and transmit the optimal control signal to the floating body execution system to drive the floating body to perform dynamic adjustment.

[0046] The installation control optimization unit is used to monitor and collect the actual stress and attitude after the execution of the optimal control signal in real time, compare the actual stress and attitude after execution with the target stress and attitude, dynamically generate a compensation signal, and correct the compensation signal based on the comparison result of the actual stress and attitude parameters after execution and the target stress and attitude parameters. Update the optimal control signal for optimization according to the corrected compensation signal, and finally obtain the final stress state and attitude parameters. Verify whether the final stable stress state and attitude parameters reach the target state by comparing with the target stress state and attitude parameters. If the error exceeds the tolerance range, perform dynamic feedback adjustment.

[0047] The beneficial technical effects of the present invention are at least as follows:

[0048] (1) Through the data fusion of multiple sensors (such as water flow sensors, sonar sensors, pressure sensors, etc.), the present invention constructs a dynamic ocean environment model to predict the change trends of interference factors such as water flow and waves in real time. This technology solves the problem of poor adaptability to dynamic environmental changes in the prior art, ensuring comprehensive and accurate environmental information during the floating body installation process.

[0049] (2) Combining real-time environmental perception data, the present invention establishes an accurate mechanical model of the floating body, dynamically estimates its stress state (such as buoyancy, gravity, drag force), and adjusts the attitude of the floating body in real time through model predictive control (MPC). This technology overcomes the problem of lack of systematic mechanical optimization in traditional methods and realizes precise control of the floating body attitude.

[0050] (3) A multi-sensor collaborative control mechanism based on the extended Kalman filter (EKF) and adaptive control algorithm is designed to achieve efficient fusion and feedback of different sensor data. This mechanism improves the robustness of the system and solves the disadvantages of low utilization rate of sensor data and insufficient anti-interference ability in the prior art. Description of the Drawings

[0051] The present invention will be further described with reference to the accompanying drawings. However, the embodiments in the drawings do not constitute any limitation to the present invention. For those of ordinary skill in the art, other drawings can be obtained according to the following drawings without creative efforts.

[0052] Figure 1 It is a flowchart of a multi-sensor collaborative control method for floating installation according to an embodiment of the present invention.

[0053] Figure 2 It is a framework diagram of a multi-sensor collaborative control system for floating installation according to an embodiment of the present invention. Detailed implementation manners

[0054] The embodiments of the present invention will be described in detail below. The examples of the embodiments are shown in the accompanying drawings, in which the same or similar reference numerals denote the same or similar elements or elements with the same or similar functions throughout. The embodiments described below by referring to the drawings are exemplary and are only used to explain the present invention and should not be construed as a limitation to the present invention.

[0055] As Figure 1 shown, a multi-sensor collaborative control method for floating installation provided by an embodiment of the present invention includes:

[0056] S1. Collect real-time data from a sensor array, preprocess the real-time data and establish a multi-modal mapping matrix, and map the preprocessed data to a unified feature space through the multi-modal mapping matrix to obtain a unified feature sequence.

[0057] Specifically, collect real-time data from the sensor array and preprocess it through methods such as alignment, denoising, and modal mapping to provide high-quality input data for subsequent environmental modeling. During the floating installation process, a variety of heterogeneous sensors are involved, and their outputs have inconsistent time steps, formats, and noise characteristics. Therefore, the goal of this step is to generate consistent and reliable time series data through innovative specific modal processing and feature space construction methods.

[0058] Among them, the input is the real-time output data of the sensor array , where is the time step, represents the type of sensor (such as a flow velocity sensor, a water depth pressure sensor, a sonar sensor, and an inertial measurement unit).

[0059] Map to a time series matrix , is the number of sensors, is the data dimension output by each sensor (such as the three-dimensional vector of the flow velocity). For example, the output of the flow velocity sensor is , the sonar is a three-dimensional point cloud data matrix.

[0060] Furthermore, a sensor synchronization module is defined to align asynchronous data to a unified time step through interpolation , ensuring that the timestamps are exactly the same. Interpolation formula:

[0061] ;

[0062] where and are the sampling values at the two nearest time points, is the alignment time.

[0063] Furthermore, spatial direction filtering is applied to the sonar data to divide the signal into two parts: background noise and reflected data:

[0064] For the point cloud matrix , by defining the angle between the direction vector and the reflection point :

[0065] ;

[0066] where is the position of the sonar sensor, is the detection direction of the sensor, and only the points with an angle less than the set threshold are retained .

[0067] For the flow velocity data, Fourier transform is used to eliminate interference signals at specific frequencies, and the conversion formula is defined:

[0068] ;

[0069] Then only the low-frequency band signals are retained for inverse transformation .

[0070] Furthermore, to unify the data format and scale, a multi-modal mapping matrix is established to map all sensor outputs to a unified feature space:

[0071] ;

[0072] Through the definition of the feature selection matrix, for example, the intensity is selected for the flow velocity, and the point cloud density is extracted for the sonar. Finally, a unified feature sequence is obtained, where is the dimension of the unified feature space.

[0073] Pair Standardize to ensure that the features have a distribution with a mean of 0 and a variance of 1.

[0074] Finally, output the unified time series after alignment, denoising, mapping, and standardization , as the input for subsequent steps, with high quality and consistency.

[0075] S2. Extract dynamic environmental features from the unified feature sequence, construct a real-time ocean environment model that combines time series trends and spatial correlations, and predict the perturbation parameters at the next moment based on the real-time ocean environment model; where the perturbation parameters include the flow velocity, wave intensity, and direction at the next time step.

[0076] Specifically, initialize the hidden state , is the dimension of the hidden state, used to capture dynamic change trends. The initial value of the hidden state can be set to a zero vector, i.e., .

[0077] Furthermore, for the non-uniformity of multi-modal data in the ocean environment, an improved weighted spatial feature mapping method is proposed, and the dynamic adjustment of the contributions of different modalities is achieved by introducing an innovative weight regularization term:

[0078] ;

[0079] where, is the weight matrix of the feature mapping, is the output feature dimension; is the bias vector; is the sparse regularization term, is the sparse coefficient, used to enhance the contribution of low-dimensional significant features to the final prediction; is the non-linear activation function (such as ReLU or Tanh). The output feature mapping is used for subsequent dynamic transfer modeling.

[0080] Furthermore, use the state transfer formula to capture the dynamic change trends of the time series, and at the same time add a specific perturbation term of the ocean environment, and the modeling formula is as follows:

[0081] ;

[0082] where, is the mapping matrix from features to hidden states; is the state transfer matrix; is the state bias vector; is the innovative perturbation term, is the perturbation weight, Construct based on physical features extracted from multimodal data (such as the gradient field of flow velocity or the rate of change of wave frequency). Output the hidden state as the dynamic feature for the next time step.

[0083] Furthermore, based on the hidden state predict the perturbation parameters for the next time step , and introduce the fluid continuity constraint into the output prediction model to ensure the physical rationality of the prediction:

[0084] ;

[0085] where is the output weight matrix; is the output bias; is the fluid continuity constraint term, represents the divergence of the flow velocity field, controlling the prediction result to satisfy the physical continuity condition.

[0086] Finally, output the environmental dynamic model to describe the dynamic change relationship of the marine environment. Output the predicted perturbation parameters , including the flow velocity, wave intensity and direction for the next time step, for subsequent mechanical state estimation.

[0087] This scheme captures the regularity of the time series and introduces additional constraint terms with clear physical meanings (such as fluid continuity and perturbation terms) through innovative dynamic time series modeling and regularization design for marine environmental characteristics, making the prediction results more suitable for the complex environment of the floating installation scenario.

[0088] S3. Based on the real-time marine environment model and the predicted perturbation parameters, combined with the unified feature sequence, construct the real-time mechanical model of the floating crane barge, and estimate the real-time force state and attitude parameters of the floating crane barge by combining the perturbation parameters in the dynamic marine environment.

[0089] Specifically, initialize the variables: : the total force on the floating crane barge in three directions; : the attitude parameters of the floating crane barge, describing the rotation angles in its three directions.

[0090] Furthermore, design the basic mechanical model:

[0091] The total force on the floating crane barge consists of the following force terms:

[0092] ;

[0093] Buoyancy : based on the submerged volume , calculated from the water depth data of the sensor Calculate;

[0094] Gravity : Determined by the floating mass and the acceleration due to gravity;

[0095] Drag force : Proportional to the predicted flow velocity through the cross-sectional area facing the flow and the drag coefficient Determine;

[0096] Control force : Dynamically generated in subsequent steps to counteract environmental disturbances.

[0097] Furthermore, two innovative constraint terms for the floating installation scenario are added to the mechanical model:

[0098] Anti-torsion performance constraint:

[0099] The attitude change of the floating body needs to meet the anti-torsion design, restricting the change in the rotation angle :

[0100] ;

[0101] where , is the angular velocity, is the weight coefficient.

[0102] Fluid continuity regularization:

[0103] Using the flow velocity field predicted in step S2 , constraining its divergence to satisfy the fluid continuity condition:

[0104] ;

[0105] This regularization ensures that the mechanical estimation results are consistent with the actual fluid behavior.

[0106] Furthermore, to ensure the stability and force balance of the floating body, the overall optimization objective is designed:

[0107] ;

[0108] where, is the ideal force balance state; and are the constraint weight coefficients. Solve and iteratively through numerical optimization methods (such as the gradient descent method), and dynamically update the force state and attitude parameters.

[0109] Finally, output the estimated total uplift force , which is the real-time force state of the uplift in the dynamic environment; output the attitude parameters , describing the rotation angle of the uplift, and providing the core input for the dynamic control optimization in step S4. This result effectively adapts to the dynamic disturbances in the complex environment and provides high-precision mechanical data support for subsequent optimal control.

[0110] In this step, by innovatively combining fluid continuity regularization and anti-torsion performance constraints, a mechanical estimation model suitable for the uplift installation scenario is constructed.

[0111] S4. Design an optimization objective function based on the estimated real-time force state and attitude parameters of the uplift and the predicted disturbance parameters at the next moment, calculate the optimal control signal of the uplift, and transmit the optimal control signal to the uplift execution system to drive the uplift for dynamic adjustment.

[0112] Specifically : The dynamically generated control signal represents the acting force of the uplift in the direction; : The target attitude defines the ideal rotation angle of the uplift.

[0113] Furthermore, to meet the requirements of uplift force balance and attitude control, design a control optimization objective function and prioritize the following two points

[0114] Force balance: The total force should be close to the ideal force state ;

[0115] Attitude adjustment: The real-time attitude should tend to the target attitude .

[0116] Furthermore, integrating the above requirements, the core part of the optimization objective function is

[0117] ;

[0118] where , which has been defined in step 3, represents the ideal balanced force state; is the weight coefficient for attitude adjustment, used to adjust the priority of force balance and attitude control.

[0119] Furthermore, to adapt to the special requirements of uplift installation, the following innovative regularization terms are added to the optimization objective function

[0120] Dynamic disturbance compensation term: For the dynamic environment disturbance predicted in step 2, design a compensation mechanism to reduce the impact of uplift response delay

[0121] ;

[0122] wherein is the current sensor data, is the compensation intensity coefficient.

[0123] Energy consumption limit item: To reduce the energy consumption of the control system, the intensity of the control signal is restricted:

[0124] ;

[0125] wherein is the energy consumption limit coefficient, which is used to constrain the magnitude of.

[0126] The final optimized objective function is:

[0127] ;

[0128] Control signal generation method

[0129] Use numerical optimization methods (such as the gradient descent method) to solve the optimal control signal :

[0130] Initial value: ;

[0131] Update rule:

[0132] ;

[0133] wherein is the learning rate, is the gradient of the objective function, and each part of the gradient is calculated by decomposition according to the above formula.

[0134] Finally, output the optimized control signal , which is used to adjust the force state and attitude of the floating support in real time; transmit the control signal to the floating support execution system (such as the propulsion device, attitude adjustment mechanism) to drive the floating support for dynamic adjustment; further optimize the dynamic stability of the floating support through subsequent feedback closed-loop control (step S5).

[0135] In this step, an innovative control optimization objective function including dynamic disturbance compensation and energy consumption limit is designed to generate the optimal control signal that meets the requirements of floating support installation.

[0136] S5. Monitor and collect the actual force and attitude after the execution of the optimal control signal in real time, compare the actual force and attitude after execution with the target force and attitude, dynamically generate a compensation signal, correct the compensation signal based on the comparison result of the actual force and attitude parameters after execution and the target force and attitude parameters, update the optimal control signal for optimization according to the corrected compensation signal, and finally obtain the final force state and attitude parameters. Verify whether the final stable force state and attitude parameters reach the target state by comparing them with the target force and attitude parameters. If the error exceeds the tolerance range, perform dynamic feedback adjustment.

[0137] Specifically, the control execution and feedback closed-loop is the core execution part of the entire patent solution. By applying the control signal generated in step S4 Adjust the motion state of the floating support and monitor the actual force in real time and attitude , compare it with the target state, and dynamically generate a compensation signal . The solution designs an innovative feedback adjustment strategy. By introducing the correction of the environmental disturbance term and the dynamic adjustment of the feedback gain, the adaptability and control accuracy of the system are improved, and finally an efficient closed-loop control mechanism is formed.

[0138] Variable definition:

[0139] : The actual force state of the floating support, measured in real time by the sensor;

[0140] : The actual attitude of the floating support, monitored in real time by the inertial measurement unit (IMU);

[0141] : Force error vector;

[0142] : Attitude error vector.

[0143] Furthermore, execute the control signal , and act on the floating support through the thruster and the attitude adjustment device:

[0144] The thruster adjusts the movement of the floating support in the direction according to ;

[0145] The attitude adjustment device adjusts the rotation angle of the floating support according to the target attitude .

[0146] Monitor the actual force and attitude of the floating support in real time, and update the current state.

[0147] Furthermore, calculate the current force error and attitude error according to the real-time state, and generate a compensation signal :

[0148] ;

[0149] wherein, is the force feedback gain matrix, is the attitude feedback gain matrix; The compensation is realized by superimposing on the original control signal.

[0150] Furthermore, introduce a dynamic disturbance correction term, and correct the feedback error based on the environmental model in Step 2 to reduce the influence of the dynamic change of the marine environment on the control accuracy:

[0151] ;

[0152] wherein, is the correction vector of the environmental disturbance, which is predicted and generated by the dynamic environmental model in Step 2; is the correction weight coefficient, which is used to balance the intensity of error compensation and disturbance correction. Through the correction term, the influence of sudden environmental disturbances on the floating state can be further reduced.

[0153] Furthermore, the updated control signal is:

[0154] ;

[0155] Execute and loop feedback until the error meets the tolerance range:

[0156] ;

[0157] wherein and are the tolerance thresholds, which respectively represent the acceptable ranges of the force error and the attitude error.

[0158] Finally, output the final stable force state and attitude parameters to verify whether the floating support reaches the target state; if the error exceeds the tolerance range, the system continues dynamic feedback adjustment to form a closed-loop optimization to ensure the stable installation of the floating support.

[0159] In this step, by innovatively combining dynamic disturbance correction and feedback error compensation, an adaptive closed-loop control mechanism for the floating support installation scenario is formed. While reducing unnecessary formulas, a correction term for environmental disturbances is designed, providing a strong dynamic response ability and system stability guarantee for the patent solution.

[0160] As Figure 2 shown, in another embodiment of the present invention, a multi-sensor collaborative control system for floating installation is provided. The system includes:

[0161] A real-time data acquisition unit 1011, configured to collect real-time data from a sensor array, preprocess the real-time data and establish a multi-modal mapping matrix, map the preprocessed data to a unified feature space through the multi-modal mapping matrix, and obtain a unified feature sequence;

[0162] An environmental prediction unit 1012, configured to extract dynamic environmental features from the unified feature sequence, construct a real-time ocean environment model combining time series trends and spatial correlations, and predict disturbance parameters at the next moment based on the real-time ocean environment model; wherein, the disturbance parameters include the flow velocity, wave intensity and direction at the next time step;

[0163] A floating installation analysis unit 1013, configured to construct a real-time mechanical model of the floating body based on the real-time ocean environment model and the predicted disturbance parameters, combined with the unified feature sequence, and estimate the real-time stress state and attitude parameters of the floating body by combining the disturbance parameters in the dynamic ocean environment; wherein, the stress state is the total stress of the floating body, that is, the total stress of the floating body in the x, y, and z directions; the attitude parameters are the attitude parameters of the floating body, that is, the rotation angles of the floating body in the x, y, and z directions;

[0164] An installation adjustment control unit 1014, configured to design an optimization objective function according to the estimated real-time stress state and attitude parameters of the floating body and the predicted disturbance parameters at the next moment, calculate the optimal control signal of the floating body, and transmit the optimal control signal to the floating body execution system to drive the floating body to perform dynamic adjustment;

[0165] An installation control optimization unit 1015, configured to monitor and collect the actual stress and attitude after the execution of the optimal control signal in real time, compare the actual stress and attitude after execution with the target stress and attitude, dynamically generate a compensation signal, and correct the compensation signal based on the comparison result of the actual stress and attitude parameters after execution and the target stress and attitude parameters, update the optimal control signal for optimization according to the corrected compensation signal, and finally obtain the final stress state and attitude parameters, and verify whether the final stable stress state and attitude parameters reach the target state by comparing with the target stress and attitude parameters of the floating body. If the error exceeds the tolerance range, dynamic feedback adjustment is performed.

[0166] In summary, the present invention realizes a complete closed loop from environmental perception, attitude optimization to dynamic control during the floating installation process, significantly improves the accuracy and stability of the floating installation, and at the same time has a high adaptability to the dynamic ocean environment.

[0167] It should be noted that the above-described workflow is merely illustrative and does not limit the scope of protection of the present invention. In actual applications, those skilled in the art can select some or all of them according to actual needs to achieve the purpose of the solution of this embodiment, and no limitation is made here.

[0168] In addition, for the technical details not described in detail in this embodiment, reference can be made to the parameter operation method provided in any embodiment of the present invention, and details will not be repeated here.

[0169] It should be noted that in this article, the terms "include", "comprise" or any other variant thereof are intended to cover non-exclusive inclusion, so that a process, method, article or system including a series of elements not only includes those elements, but also includes other elements not explicitly listed, or further includes elements inherent to such a process, method, article or system. Without more limitations, an element defined by the statement "including one..." does not exclude the existence of another identical element in the process, method, article or system including that element.

[0170] The serial numbers of the above embodiments of the present invention are only for description and do not represent the superiority or inferiority of the embodiments.

[0171] Through the description of the above embodiments, those skilled in the art can clearly understand that the above-described embodiment methods can be implemented by means of software plus a necessary general hardware platform. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art can be embodied in the form of a software product. The computer software product is stored in a storage medium (such as a read-only memory / random access memory, magnetic disk, optical disk), and includes several instructions for causing a terminal device (which can be a mobile phone, a computer, a server, an air conditioner, or a network device, etc.) to execute the methods described in the various embodiments of the present invention.

[0172] The above are only the preferred embodiments of the present invention, and do not limit the patent scope of the present invention accordingly. Any equivalent structure or equivalent process transformation made by using the content of the specification and drawings of the present invention, or directly or indirectly applied to other related technical fields, shall be equally included in the patent protection scope of the present invention.

Claims

1. A multi-sensor collaborative control method for floating installation, characterized in that The method includes: S1. Collect real-time data from the sensor array, preprocess the real-time data and establish a multimodal mapping matrix, map the preprocessed data to a unified feature space through the multimodal mapping matrix, and obtain a unified feature sequence; S2. Extract dynamic environment features from the unified feature sequence, construct a real-time ocean environment model that combines time series trends and spatial correlations, and predict the disturbance parameters at the next moment based on the real-time ocean environment model; wherein, the disturbance parameters include the flow velocity, wave intensity and direction at the next time step; S3. Based on the real-time ocean environment model and the predicted disturbance parameters, combine with the unified feature sequence to construct a real-time mechanical model of the floating structure, and estimate the real-time force state and attitude parameters of the floating structure by combining the disturbance parameters in the dynamic ocean environment; wherein, the force state is the total force on the floating structure, that is, the total force on the floating structure in the x, y, and z directions; the attitude parameters are the attitude parameters of the floating structure, that is, the rotation angles of the floating structure in the x, y, and z directions; S4. Design an optimization objective function according to the estimated real-time force state and attitude parameters of the floating structure and the predicted disturbance parameters at the next moment, calculate the optimal control signal of the floating structure, and transmit the optimal control signal to the floating structure execution system to drive the floating structure to perform dynamic adjustment; S5. Monitor and collect the actual force and attitude after the execution of the optimal control signal in real time, compare the actual force and attitude after execution with the target force and attitude, dynamically generate a compensation signal, and correct the compensation signal based on the comparison result of the actual force and attitude parameters after execution and the target force and attitude parameters, update the optimal control signal according to the corrected compensation signal for optimization, and finally obtain the final force state and attitude parameters, verify whether the final stable force state and attitude parameters reach the target state by comparing with the target force state and attitude parameters of the floating structure, and if the error exceeds the tolerance range, perform dynamic feedback adjustment.

2. The multi-sensor collaborative control method for floating installation according to claim 1, wherein The sensor array includes a flow velocity sensor, a water depth pressure sensor, a sonar sensor and an inertial measurement unit; The preprocessing includes performing time series consistency processing, noise filtering, normalization processing and mapping processing on the real-time data.

3. A multi-sensor collaborative control method for floating installation according to claim 1, characterized in that, The S2 specifically includes: Design a weighted spatial feature mapping function according to the non-uniformity of multimodal data in the ocean environment to dynamically adjust the contributions of different modalities; Construct a real-time ocean environment model according to the weighted spatial feature mapping function, and output the hidden state, the mapping matrix from features to hidden states and the state transition matrix; Predict the disturbance parameters at the next time step according to the hidden state, and introduce a fluid continuity constraint in the real-time ocean environment model to ensure the physical rationality of the prediction.

4. A multi-sensor collaborative control method for floating installation according to claim 3, characterized in that, The weighted spatial feature mapping function realizes the dynamic adjustment of the contributions of different modalities by introducing a sparse regularization term; The real-time ocean environment model uses the state transition formula to capture the dynamic change trend of the time series, and at the same time adds a disturbance term of the ocean environment to output the hidden state; Predict the perturbation parameter at the next time step using a recurrent neural network based on the output hidden state. ​ 5. A multi-sensor collaborative control method for floating installation according to claim 1, characterized in that, The S3 specifically includes: Design a basic mechanical model; Add anti-torsion performance constraints for floating installation and fluid continuity regularization to the basic mechanical model; wherein, the anti-torsion performance constraints are used to limit the change amount of the rotation angle, and the fluid continuity regularization is used to constrain its divergence to satisfy the fluid continuity condition; Design the total optimization objective of the mechanical model.

6. A multi-sensor collaborative control method for floating installation according to claim 5, characterized in that, The basic mechanical model is the total force on the real-time floating dock. The total force on the real-time floating dock includes buoyancy, gravity, dynamically generated control signals, and drag force. Among them, the dynamically generated control signals represent the acting force of the floating dock in the direction. The anti-torsion performance constraints are used to limit the change amount of the rotation angle; The fluid continuity regularization is used to constrain its divergence to satisfy the fluid continuity condition; Iteratively solve the total force and attitude parameters of the real-time floating dock through a numerical optimization method, and dynamically update the force state and attitude parameters.

7. A multi-sensor collaborative control method for floating installation according to claim 6, characterized in that, The S4 specifically includes: Design the control optimization objective function; Use a numerical optimization method to solve the optimal control signal; Output the optimized control signal, adjust the force state and attitude of the floating dock in real time, transmit the control signal to the floating dock execution system, and drive the floating dock to perform dynamic adjustment; Among them, the control optimization objective function is used to achieve force balance and attitude adjustment. The force balance means that the total force is closest to the ideal force state, and the attitude adjustment is that the attitude parameters of the real-time floating dock tend to the target attitude most.

8. A multi-sensor collaborative control method for floating installation according to claim 7, characterized in that Add a dynamic disturbance compensation term and an energy consumption limit term to the design control optimization objective function; the dynamic disturbance compensation term is used to reduce the influence of the floating dock response delay, and the energy consumption limit term is used to limit the intensity of the control signal.

9. A multi-sensor collaborative control method for floating installation according to claim 7, characterized in that In S5, the optimal control signal is executed and acts on the floating barge through thrusters and attitude adjustment devices. The thrusters adjust the movement of the floating barge in the direction, and the attitude adjustment device adjusts the rotation angle of the floating barge according to the target attitude; the compensation signal is compensated by being superimposed on the original control signal. By correcting the compensation signal, design a dynamic disturbance correction term based on the prediction of the ocean environment model to generate a correction vector of the environmental disturbance, which is used to reduce the influence of sudden environmental disturbances on the state of the floating dock.

10. A multi-sensor collaborative control system for floating installation, characterized in that, The system includes: A real-time data acquisition unit, which is used to collect real-time data from the sensor array, preprocess the real-time data and establish a multi-modal mapping matrix, map the preprocessed data to a unified feature space through the multi-modal mapping matrix, and obtain a unified feature sequence; An environment prediction unit, which is used to extract dynamic environment features from the unified feature sequence, construct a real-time ocean environment model combining time series trends and spatial correlations, and predict the disturbance parameters at the next moment based on the real-time ocean environment model; wherein, the disturbance parameters include the flow velocity, wave intensity and direction at the next time step; A floating dock installation analysis unit, which is used to construct a real-time mechanical model of the floating dock based on the real-time ocean environment model and the predicted disturbance parameters, combined with the unified feature sequence, and estimate the real-time force state and attitude parameters of the floating dock by combining the disturbance parameters in the dynamic ocean environment; wherein, the force state is the total force of the floating dock, that is, the total force of the floating dock in the x, y, and z directions; the attitude parameters are the attitude parameters of the floating dock, that is, the rotation angles of the floating dock in the x, y, and z directions; An installation adjustment control unit, which is used to design an optimization objective function according to the estimated real-time force state and attitude parameters of the floating dock and the predicted disturbance parameters at the next moment, calculate the optimal control signal of the floating dock, and transmit the optimal control signal to the floating dock execution system to drive the floating dock to perform dynamic adjustment; An installation control optimization unit is used to monitor and collect the actual force and attitude in real time after the optimal control signal is executed, compare the actual force and attitude after execution with the target force and attitude, dynamically generate a compensation signal, correct the compensation signal based on the comparison result of the actual force and attitude parameters after execution and the target force and attitude parameters, update the optimal control signal for optimization according to the corrected compensation signal, and finally obtain the final force state and attitude parameters. Verify whether the final stable force state and attitude parameters reach the target state by comparing them with the target force and attitude parameters of the floating support. If the error exceeds the tolerance range, perform dynamic feedback adjustment.

Images