A PID-based ROV motion control system and method

Abstract

The present invention relates to the technical field of control systems. A PID-based ROV motion control system and method provided by the present invention solve the deficiencies of existing PID control algorithms in the control of complex ROV systems. The system includes data acquisition, processing, detection, model matching, and optimization modules. By acquiring historical data and constructing an algorithm model knowledge base, it can match environmental data in real time to select the optimal control model, send control commands, and collect ROV operation data. If the real-time data is inconsistent with the expected data, a genetic algorithm is used to optimize the control model to generate optimized control commands. The present invention improves the control accuracy and environmental adaptability of the ROV, and enhances the system robustness and operation efficiency through dynamic optimization of the control strategy.

Description

Technical Field

[0001] The present invention relates to the technical field of control systems, and in particular to a PID-based ROV motion control system and method. Background Art

[0002] PID, namely Proportional (P), Integral (I), and Derivative (D) control, is a control algorithm. The PID control algorithm has the advantages of simple principle, easy implementation, wide application range, independent control parameters, and relatively simple parameter selection. The core of a PID controller is to calculate the deviation between the given value and the actual value, and linearly combine this deviation through three different adjustment actions of proportional, integral, and derivative to generate a control signal for controlling the controlled object. An ROV, that is, a Remotely Operated Vehicle, is a device that can move underwater, has a vision and perception system, and uses a manipulator or other tools through remote control or autonomous operation to replace or assist humans in completing underwater operations.

[0003] A PID-based ROV motion control system is an underwater ROV robot control solution that uses a PID (Proportional-Integral-Differential) control algorithm to calculate the deviation between the current position and the target position of the ROV (Remotely Operated Vehicle) in real time, and generates a control command through a linear combination of three adjustment actions of proportional, integral, and derivative. The control command is used to adjust the thruster output of the ROV to control its attitude and motion trajectory underwater.

[0004] In the actual operation process of the existing PID-based ROV motion control system, there are the following technical pain points. When the ROV moves underwater, it is affected by various factors such as water flow, waves, and load changes. The influence of these factors such as water flow, waves, and load changes is non-linear and time-varying. The existing PID control algorithm usually assumes that the system behavior is linear and time-invariant, resulting in the inability of PID control to provide accurate control effects when facing a complex system like an ROV. Summary of the Invention

[0005] Aiming at the deficiencies of the prior art, the present invention provides a PID-based ROV motion control system and method to solve the problem that the existing PID control algorithm usually assumes that the system behavior is linear and time-invariant, resulting in the inability of PID control to provide accurate control effects when facing a complex system like an ROV.

[0006] To solve the above technical problems, the specific technical solutions of the present invention are as follows:

[0007] In a first aspect, the present invention provides a PID-based ROV motion control system, including:

[0008] A data acquisition module for acquiring historical data of the motion control system. The historical data of the motion control system includes historical target position data, historical actual position data, historical deviation data, historical control parameter data, historical environmental data, historical sensor data, historical motion trajectory data, and historical control instruction data;

[0009] A data processing module for extracting data features from environmental data to obtain classified environmental data features, matching the classified environmental features with the historical data of the motion control system according to time information to obtain a classified environmental data feature dataset, dividing each type of environmental feature data in the classified environmental data feature dataset into a training set and a validation set, and using the divided training set and validation set of each type of environmental feature data to train a neural network model to obtain a set of motion control model data corresponding to the classified environmental data features, and constructing the set of motion control model data corresponding to the classified environmental data features into an algorithm model knowledge base;

[0010] A data detection module for receiving real-time target position data, real-time water flow data, real-time wave data, and real-time load data, obtaining target position natural environment data according to the real-time target position data, and summarizing the real-time water flow data, real-time wave data, real-time load data, and target position natural environment data to obtain a real-time environmental data set;

[0011] A model matching module for matching the real-time environmental data set in a preset algorithm model knowledge base to obtain a motion control model corresponding to the real-time environmental data, receiving a real-time control command, and substituting the real-time control command into the motion control model corresponding to the real-time environmental data to obtain expected operation data of the ROV robot;

[0012] A model optimization module for transmitting the real-time control command to the ROV robot, collecting real-time operation data of the ROV robot, comparing the real-time operation data of the ROV robot with the expected operation data of the ROV robot. If the real-time operation data of the ROV robot is inconsistent with the expected operation data of the ROV robot, the motion control model corresponding to the real-time environmental data is optimized using a genetic algorithm according to the error data between the real-time operation data of the ROV robot and the expected operation data of the ROV robot to obtain an optimized motion control model corresponding to the real-time environmental data, using the optimized motion control model corresponding to the real-time environmental data to process the real-time control command to generate an optimized control command for the ROV robot, and sending the optimized control command for the ROV robot to the ROV robot.

[0013] Further, for the ROV motion control system based on PID according to the present invention, the data detection module is further configured to:

[0014] The specific steps of matching the real-time environmental data in the preset algorithm model knowledge base to obtain the motion control model corresponding to the real-time environmental data include:

[0015] Extract features from the real-time environmental data set to obtain water flow speed features, wave height features, load weight features, water temperature features, salinity features, and seabed terrain features;

[0016] Combine the extracted features into a feature vector according to the preset format and order, and the feature vector will be used for searching and matching in the algorithm model knowledge base;

[0017] Use the feature vector to search in the algorithm model knowledge base to obtain the motion control model that best matches the real-time environmental data. The motion control model that best matches the real-time environmental data is used to calculate the similarity between the feature vector and the corresponding feature vectors of each model in the knowledge base;

[0018] According to the calculation result of the similarity, select the motion control model with the highest similarity as the best matching model corresponding to the current real-time environmental data.

[0019] Further, for the ROV motion control system based on PID according to the present invention, the model matching module is further configured to:

[0020] Send the real-time control command to the ROV robot through the communication link. The real-time control command includes a target position instruction, a speed instruction, and an attitude instruction;

[0021] After receiving the control command, the internal control system of the ROV robot analyzes the command and drives the corresponding actuator to perform motion;

[0022] During the process of the ROV robot executing the control command, the running data of the ROV robot is collected in real time through the sensors installed on the ROV robot. The sensors on the ROV robot include position sensors, speed sensors, and attitude sensors. The running data of the ROV robot includes the actual position, actual speed, actual attitude, motor current, and voltage;

[0023] Recalculate the expected running data of the ROV robot predicted by the motion control model based on the real-time environmental data and the control command;

[0024] Compare the preprocessed real-time running data of the ROV robot with the expected running data item by item, and output the comparison result to the model optimization module.

[0025] Further, for the ROV motion control system based on PID according to the present invention, the model optimization module is further configured to:

[0026] If the real-time operation data of the ROV robot is inconsistent with the expected operation data of the ROV robot, the specific steps of using the genetic algorithm to optimize the motion control model corresponding to the real-time environmental data and generating an optimized control command for the ROV robot include:

[0027] Calculate error data, which includes position error, speed error, and attitude error;

[0028] Take reducing the error as the optimization goal and define the fitness function;

[0029] Initialize the genetic algorithm, set the parameters of the genetic algorithm, and each individual represents a set of motion control model parameters;

[0030] Use each individual in the population, that is, the set of model parameters, to simulate the real-time control command, and obtain the simulated operation data of the ROV robot;

[0031] Calculate the error between the simulated data and the real-time operation data, and evaluate the fitness of each individual based on this;

[0032] Select excellent individuals as parents according to the fitness, perform crossover operations to generate offspring, and perform mutation operations on the offspring;

[0033] Repeat the steps of evaluating fitness, selection, crossover, and mutation until the preset number of iterations or the error range requirement is reached;

[0034] Select the individual with the highest fitness from the final population as the set of motion control model parameters corresponding to the optimized real-time environmental data;

[0035] Use the optimized motion control model to process the real-time control command to obtain the expected operation data of the ROV robot;

[0036] Based on the optimized expected operation data, generate an optimized control command for the ROV robot, and send the optimized control command for the ROV robot to the ROV robot through the communication link to adjust the motion state of the ROV robot so that the ROV robot reaches the expected operation state.

[0037] In a second aspect, the present invention provides a PID-based ROV motion control method, which is applied to the PID-based ROV motion control system, and includes:

[0038] Step S101, acquiring motion control system historical data, where the motion control system historical data includes target position historical data, actual position historical data, deviation historical data, control parameter historical data, environment historical data, sensor historical data, motion trajectory historical data, and control instruction historical data;

[0039] Step S102: extracting data features from the environmental data to obtain environmental data classification features, matching the environmental classification features with the motion control system historical data based on time information to obtain an environmental classification feature data set, dividing each type of environmental feature data in the environmental classification feature data set into a training set and a validation set, and using each type of environmental feature data divided into the training set and the validation set to train a neural network model to obtain a motion control model data set corresponding to the environmental classification features, and constructing the motion control model data set corresponding to the environmental classification features into an algorithm model knowledge base;

[0040] Step S103, receiving real-time target location data and real-time water flow data, real-time wave data, and real-time load data, obtaining target location natural environment data based on the real-time target location data, and aggregating the real-time water flow data, real-time wave data, real-time load data, and target location natural environment data to obtain a real-time environment data set;

[0041] Step S104: Match the real-time environment data set with a preset algorithm model knowledge base to obtain a motion control model corresponding to the real-time environment data, receive a real-time control command, substitute the real-time control command into the motion control model corresponding to the real-time environment data, and obtain the expected operation data of the ROV robot;

[0042] Step S105: transmit the real-time control command to the ROV robot, collect the real-time operation data of the ROV robot, compare the real-time operation data of the ROV robot with the expected operation data of the ROV robot, and if the real-time operation data of the ROV robot is inconsistent with the expected operation data of the ROV robot, optimize the motion control model corresponding to the real-time environment data using a genetic algorithm according to the error data between the real-time operation data of the ROV robot and the expected operation data of the ROV robot to obtain the optimized motion control model corresponding to the real-time environment data, use the optimized motion control model corresponding to the real-time environment data to perform data processing on the real-time control command, generate an optimized ROV robot control command, and send the optimized ROV robot control command to the ROV robot.

[0043] Furthermore, in the PID-based ROV motion control method of the present invention, step S103 includes:

[0044] The specific steps of matching the real-time environmental data set in the preset algorithm model knowledge base to obtain the motion control model corresponding to the real-time environmental data include:

[0045] Extract features from the real-time environmental data set to obtain water flow velocity features, wave height features, load weight features, water temperature features, salinity features, and seabed terrain features;

[0046] Combine the extracted features into a feature vector according to the preset format and order, and the feature vector will be used for searching and matching in the algorithm model knowledge base;

[0047] Use the feature vector to search in the algorithm model knowledge base to obtain the motion control model that best matches the real-time environmental data. The motion control model that best matches the real-time environmental data is used to calculate the similarity between the feature vector and the corresponding feature vectors of each model in the knowledge base;

[0048] According to the calculation result of the similarity, select the motion control model with the highest similarity as the best matching model corresponding to the current real-time environmental data.

[0049] Furthermore, in the ROV motion control method based on PID according to the present invention, step S104 includes:

[0050] Send the real-time control command to the ROV robot through the communication link. The real-time control command includes a target position instruction, a speed instruction, and an attitude instruction;

[0051] After receiving the control command, the internal control system of the ROV robot analyzes the command and drives the corresponding actuator to perform motion;

[0052] During the process of the ROV robot executing the control command, the running data of the ROV robot is collected in real time by the sensors installed on the ROV robot. The sensors on the ROV robot include position sensors, speed sensors, and attitude sensors. The running data of the ROV robot includes the actual position, actual speed, actual attitude, motor current, and voltage;

[0053] Recalculate the expected running data of the ROV robot predicted by the motion control model based on the real-time environmental data and the control command;

[0054] Compare the preprocessed real-time running data of the ROV robot with the expected running data item by item, and output the comparison result to the model optimization module.

[0055] Furthermore, in the ROV motion control method based on PID according to the present invention, step S105 includes:

[0056] If the real-time operation data of the ROV robot is inconsistent with the expected operation data of the ROV robot, the specific steps of using the genetic algorithm to optimize the motion control model corresponding to the real-time environmental data and generating the optimized control command for the ROV robot are as follows:

[0057] Calculate the error data, which includes position error, velocity error, and attitude error;

[0058] Take reducing the error as the optimization goal and define the fitness function;

[0059] Initialize the genetic algorithm, set the parameters of the genetic algorithm, and each individual represents a set of motion control model parameters;

[0060] Use each individual in the population, that is, the set of model parameters, to simulate the real-time control command, and obtain the simulated operation data of the ROV robot;

[0061] Calculate the error between the simulated data and the real-time operation data, and evaluate the fitness of each individual based on this;

[0062] Select excellent individuals as parents according to the fitness, perform crossover operations to generate offspring, and perform mutation operations on the offspring;

[0063] Repeat the steps of evaluating fitness, selection, crossover, and mutation until the preset number of iterations or error range requirements are met;

[0064] Select the individual with the highest fitness from the final population as the set of motion control model parameters corresponding to the optimized real-time environmental data;

[0065] Use the optimized motion control model to process the real-time control command to obtain the expected operation data of the ROV robot;

[0066] Based on the optimized expected operation data, generate the optimized control command for the ROV robot, and send the optimized control command for the ROV robot to the ROV robot through the communication link to adjust the motion state of the ROV robot so that the ROV robot reaches the expected operation state.

[0067] Advantages of the present invention:

[0068] By dynamically selecting and optimizing the motion control model, the present invention can more accurately predict and control the motion state of the ROV robot, reduce position error, velocity error, and attitude error, thereby improving the control accuracy. The present invention constructs an algorithm model knowledge base using historical data and real-time environmental data, and selects the most suitable motion control model for different environmental conditions, such as water flow velocity, wave height, load weight, etc., enhancing the adaptability of the system to the complex and changeable underwater environment.

[0069] By optimizing the motion control model through genetic algorithms, the present invention can continuously learn and adjust the model parameters to adapt to new environments and control requirements, improving the robustness of the system. During real-time operation, the present invention continuously compares the real-time operation data and the expected operation data of the ROV robot, and optimizes the control model according to the error data, thereby being able to generate more reasonable control commands and optimize the control strategy.

[0070] Through precise control and optimized motion trajectories, the present invention enables the ROV robot to reach the target position more quickly, complete underwater operation tasks, and improve operation efficiency. By optimizing control commands and reducing unnecessary movements, the present invention can reduce the energy consumption of the ROV robot and extend its underwater operation time.

[0071] The present invention combines a variety of advanced technologies such as PID control algorithms, neural network models, and genetic algorithms, providing new ideas and methods for the intelligent control of ROV robots and promoting the intelligent development of underwater robot technology.

[0072] In summary, through the dynamic selection and optimization of the motion control model, the present invention significantly improves the control accuracy, environmental adaptability, and system robustness of the ROV robot in complex underwater environments, while optimizing the control strategy, improving operation efficiency, and reducing energy consumption. BRIEF DESCRIPTION OF THE DRAWINGS

[0073] In order to more clearly illustrate the technical solutions of the present invention, the following will briefly introduce the drawings required in the embodiments. Obviously, for those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on the drawings.

[0074] Figure 1 It is a schematic flowchart of the ROV motion control method based on PID provided by an embodiment of the present invention.

[0075] Figure 2 It is a schematic diagram of the modules of the ROV motion control system based on PID provided by an embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0076] To make the objectives, technical solutions, and advantages of the present invention clearer, the technical solutions of the present invention will be clearly and completely described below in conjunction with specific embodiments of the present invention and the corresponding drawings. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts fall within the scope of protection of the present invention. The technical solutions provided by each embodiment of the present invention will be described in detail below with reference to the drawings. To better understand the objectives of the present invention, the present invention will be further described in detail below.

[0077] In a first aspect, please refer to Figure 2 , the present invention provides a PID-based ROV motion control system, including: <*

[0078] A data acquisition module that acquires historical data of the motion control system, where the historical data of the motion control system includes historical data of target positions, historical data of actual positions, historical data of deviations, historical data of control parameters, historical data of the environment, historical data of sensors, historical data of motion trajectories, and historical data of control instructions;

[0079] Historical data of target positions: Records the information of the target positions that the ROV robot was instructed to reach in the past.

[0080] Historical data of actual positions: Records the information of the actual positions reached by the ROV robot during actual operation.

[0081] Historical data of deviations: Calculates and records the differences between target positions and actual positions, reflecting the accuracy of the control system.

[0082] Historical data of control parameters: Records various parameter values used to control the ROV robot, such as the proportional, integral, and derivative coefficients of the PID controller, etc.

[0083] Historical data of the environment: Records various environmental information encountered by the ROV robot during past operations, such as water flow speed, wave height, load weight, water temperature, salinity, and seabed topography, etc.

[0084] Historical data of sensors: Collects historical data from various sensors on the ROV robot, such as position sensors, speed sensors, attitude sensors, etc., and these data provide a detailed record of the operating state of the ROV robot.

[0085] Historical data of motion trajectories: Records the complete motion trajectories of the ROV robot during past operations, which helps to analyze the motion patterns and performance of the ROV.

[0086] Control instruction historical data: Records all control instructions sent to the ROV robot, including target position instructions, speed instructions, attitude instructions, etc.

[0087] Support model training: The collected historical data provides rich samples for the subsequent training of neural network models, helping the models learn control laws in various environments.

[0088] Improve control accuracy: By comparing the historical data of the target position and the actual position, the accuracy of the control system can be evaluated, and the control strategy can be adjusted accordingly to improve the control precision.

[0089] Enhance system adaptability: Environmental historical data and sensor historical data provide the system with an understanding of complex environments, helping the system make more reasonable control decisions when facing new environments.

[0090] Optimize control parameters: The historical data of control parameters provides a basis for adjusting and optimizing the parameters of the PID controller, helping to improve the performance of the control system.

[0091] The data processing module extracts data features from the environmental data to obtain environmental data classification features, matches the environmental classification features with the historical data of the motion control system according to time information to obtain an environmental classification feature dataset, divides each type of environmental feature data in the environmental classification feature dataset into a training set and a validation set, and uses each type of environmental feature data divided into a training set and a validation set to train the neural network model to obtain a set of motion control model data corresponding to the environmental classification features, and constructs the set of motion control model data corresponding to the environmental classification features into an algorithm model knowledge base;

[0092] The data processing module first extracts features from the environmental historical data. The environmental data includes various factors such as water flow speed, wave height, load weight, water temperature, salinity, and seabed topography.

[0093] Through feature extraction technology, the data processing module identifies key feature information from the original environmental data. The feature information will be used for subsequent data classification and model training. Based on the extracted environmental data features, the data processing module further classifies the data to form environmental data classification features. The purpose of classification is to match the historical data of the motion control system with the corresponding environmental conditions, so as to more accurately reflect the motion control characteristics of the ROV robot under different environments.

[0094] The data processing module matches the environmental classification features with the historical data of the motion control system according to time information. Through matching, the data processing module can construct multiple environmental classification feature datasets, and each dataset contains the operation data and control parameters of the ROV robot under specific environmental conditions.

[0095] For each environmental classification feature dataset, the data processing module divides it into a training set and a validation set. The training set is used to train the neural network model, while the validation set is used to evaluate the performance of the model.

[0096] Using the divided dataset, the data processing module trains the neural network model. Through continuous learning and optimization, the model can learn how to effectively control the movement of the ROV robot under different environmental conditions.

[0097] After training, the data processing module combines the motion control model data corresponding to each environmental classification feature to construct an algorithm model knowledge base. The algorithm model knowledge base contains motion control models under various environmental conditions and can quickly select the most suitable control model according to the current environmental conditions during the real-time control process.

[0098] The data detection module receives real-time target position data, real-time water flow data, real-time wave data, and real-time load data. It obtains the natural environmental data of the target position based on the real-time target position data, and summarizes the real-time water flow data, real-time wave data, real-time load data, and the natural environmental data of the target position to obtain a real-time environmental data set;

[0099] The data detection module receives data from different sources in real-time, including real-time target position data, real-time water flow data, real-time wave data, and real-time load data. The data is transmitted to the data detection module in real-time through sensors, communication systems, or other data interfaces.

[0100] Based on the received real-time target position data, the data detection module further obtains the natural environmental data of that position.

[0101] The natural environmental data involves querying a pre-stored environmental database or requesting environmental information from other systems (such as a marine environmental monitoring system) in real-time. The natural environmental data includes water temperature, salinity, seabed topography, water flow speed, wave height, etc.

[0102] The data detection module summarizes and integrates the received real-time water flow data, real-time wave data, real-time load data, and the obtained natural environmental data of the target position. Through data cleaning, format conversion, and unit unification and other processing steps, the accuracy of all data is ensured. The integrated data forms a real-time environmental data set, which includes all the key environmental factors that the ROV robot will encounter currently and in the future. The real-time environmental data set is transmitted to other modules of the system (such as the model matching module) for further processing and analysis.

[0103] The model matching module matches the real-time environmental data set in the preset algorithm model knowledge base to obtain the motion control model corresponding to the real-time environmental data, receives the real-time control command, substitutes the real-time control command into the motion control model corresponding to the real-time environmental data, and obtains the expected operation data of the ROV robot;

[0104] The model matching module receives the real-time environmental data set from the data detection module. In the preset algorithm model knowledge base, the module matches according to the characteristics of the real-time environmental data set to find the motion control model that best matches the current environmental conditions.

[0105] The algorithm model knowledge base usually includes motion control models under various different environmental conditions. The motion control models are obtained through training with historical data and can reflect the influence of different environments on the motion control of the ROV robot.

[0106] Through the matching process, the model matching module selects the motion control model that best matches the real-time environmental data set from the algorithm model knowledge base. The best-matching motion control model will be used for subsequent control command processing and expected operation data generation.

[0107] The model matching module receives the real-time control commands from the control system. These commands include requirements such as target position, speed, and attitude. The module substitutes the real-time control commands into the selected motion control model, and through the calculation and reasoning of the model, generates the expected operation data of the ROV robot. The expected operation data includes key parameters such as the expected position, speed, attitude, and thrust of the ROV robot.

[0108] The model matching module outputs the generated expected operation data to the actuator of the ROV robot to guide its actual motion control. At the same time, the model matching module also compares and analyzes the expected operation data with the actual operation data to evaluate the control effect and provide feedback to the control system for parameter adjustment or model optimization.

[0109] By matching the motion control model that best suits the current environmental conditions, the model matching module can significantly improve the control accuracy of the ROV robot. Facing the complex and changeable underwater environment, the model matching module can flexibly select and adjust the motion control model, enabling the ROV robot to better adapt to the operation requirements under different environmental conditions. Through the substitution of real-time control commands and the generation of expected operation data, the model matching module provides important reference and basis for the control system, helping to optimize the control strategy and improve the control efficiency.

[0110] In summary, the model matching module is an indispensable part of the ROV motion control system. Through functions such as real-time environmental data matching, motion control model selection, and real-time control command substitution, the model matching module provides strong support for the precise control and efficient operation of the ROV robot.

[0111] The model optimization module transmits the real-time control command to the ROV robot, collects the real-time operation data of the ROV robot, compares the real-time operation data of the ROV robot with the expected operation data of the ROV robot. If the real-time operation data of the ROV robot is inconsistent with the expected operation data of the ROV robot, the motion control model corresponding to the real-time environmental data is optimized using the genetic algorithm based on the error data between the real-time operation data of the ROV robot and the expected operation data of the ROV robot, obtaining the optimized motion control model corresponding to the real-time environmental data, using the optimized motion control model corresponding to the real-time environmental data to process the real-time control command, generating the optimized ROV robot control command, and sending the optimized ROV robot control command to the ROV robot.

[0112] The model optimization module in the ROV (Remotely Operated Vehicle) motion control system is responsible for continuously optimizing the motion control model according to the actual operation situation to ensure that the ROV robot can respond to control commands more precisely. The following is a detailed description of the functions of the model optimization module:

[0113] The model optimization module first receives the real-time control command from the control system and transmits it to the ROV robot to perform corresponding actions. At the same time, the module collects the operation data of the ROV robot in real time through sensors or data interfaces, including key parameters such as position, speed, attitude, and thrust.

[0114] The real-time operation data of the ROV robot collected is compared with the expected operation data generated by the previous model matching module. Analyze the differences between the two, calculate the error data, and these error data reflect the deviation between the actual operation and the expected operation.

[0115] When it is found that the real-time operation data of the ROV robot is inconsistent with the expected operation data, the model optimization module starts the optimization process. Using optimization techniques such as the genetic algorithm, the motion control model corresponding to the real-time environmental data is iteratively optimized based on the error data. The genetic algorithm searches for the optimal solution in the model parameter space by simulating natural selection and genetic mechanisms to minimize the error. After multiple iterations, the optimized motion control model corresponding to the real-time environmental data is obtained, and this model can more accurately reflect the motion characteristics of the ROV robot in the current environment.

[0116] The optimized motion control model is used to process the real-time control commands, generating optimized ROV robot control commands. The optimized control commands take into account the differences between the actual operation and the expected operation, and can more accurately guide the movement of the ROV robot. Finally, the optimized ROV robot control commands are sent to the ROV robot to achieve more precise control. The model optimization module also includes a feedback mechanism for evaluating the optimized control effect and feeding back the evaluation results to the control system for further adjustment or optimization.

[0117] Specifically, for the ROV motion control system based on PID, the data detection module includes:

[0118] The specific steps of matching the real-time environmental data set in the preset algorithm model knowledge base to obtain the motion control model corresponding to the real-time environmental data include:

[0119] Extract features from the real-time environmental data set to obtain water flow velocity features, wave height features, load weight features, water temperature features, salinity features, and seabed terrain features;

[0120] Combine the extracted features into a feature vector in a preset format and order. The feature vector will be used for searching and matching in the algorithm model knowledge base;

[0121] Use the feature vector to search in the algorithm model knowledge base to obtain the motion control model that best matches the real-time environmental data. The motion control model that best matches the real-time environmental data is used to calculate the similarity between the feature vector and the corresponding feature vectors of each model in the knowledge base;

[0122] According to the calculation results of the similarity, select the motion control model with the highest similarity as the best matching model corresponding to the current real-time environmental data.

[0123] In the ROV motion control system based on PID (Proportional-Integral-Differential), the data detection module matches the real-time environmental data set with the preset algorithm model knowledge base to find the motion control model most suitable for the current environmental conditions.

[0124] The specific steps of model matching in the data detection module extract key features from the real-time environmental data set. These features can reflect the impact of the environment on the motion control of the ROV robot. The extracted features include water flow velocity features, wave height features, load weight features, water temperature features, salinity features, and seabed terrain features, etc.

[0125] The extracted features are combined into a feature vector according to a preset format and order. Each element of the feature vector corresponds to a specific environmental feature, and its value represents the specific numerical value or state of the feature in the current environment. The purpose of combining the feature vector is to facilitate searching and matching in the algorithm model knowledge base.

[0126] Use the combined feature vector to search in the algorithm model knowledge base. The algorithm model knowledge base is a database containing multiple motion control models and their corresponding feature vectors. The purpose of the search is to find the motion control model that best matches the current real-time environmental data.

[0127] During the search process, calculate the similarity between the feature vector and the feature vectors corresponding to each model in the knowledge base. The similarity can be obtained by calculating the Euclidean distance, cosine similarity or other similarity measurement methods between two vectors. The higher the similarity, the closer the current real-time environmental data is to the environmental conditions corresponding to the model.

[0128] According to the calculation result of the similarity, select the motion control model with the highest similarity as the best matching model corresponding to the current real-time environmental data.

[0129] Specifically, for the ROV motion control system based on PID described in the present invention, the model matching module includes:

[0130] Send the real-time control command to the ROV robot through the communication link. The real-time control command includes target position instruction, speed instruction and attitude instruction;

[0131] After receiving the control command, the internal control system of the ROV robot analyzes the command and drives the corresponding actuators to perform motion;

[0132] During the process of the ROV robot executing the control command, the running data of the ROV robot is collected in real time by the sensors installed on the ROV robot. The sensors on the ROV robot include position sensors, speed sensors and attitude sensors. The running data of the ROV robot includes actual position, actual speed, actual attitude, motor current and voltage;

[0133] Recalculate the expected running data of the ROV robot predicted by the motion control model based on the real-time environmental data and the control command;

[0134] Compare the preprocessed real-time running data of the ROV robot with the expected running data item by item, and output the comparison result to the model optimization module.

[0135] In a PID (Proportional-Integral-Differential) based ROV (Remotely Operated Vehicle) motion control system, the model matching module is not only responsible for matching real-time environmental data to the most suitable motion control model, but also involves the sending of control commands, the acquisition of real-time operation data, and the recalculation and comparison of expected operation data.

[0136] Send real-time control commands to the ROV robot through a communication link (such as wireless or wired communication). Real-time control commands usually include target position instructions, speed instructions, and attitude instructions, which define the position, speed, and attitude that the ROV robot should reach.

[0137] After receiving the control commands, the internal control system of the ROV robot analyzes the commands. According to the analyzed commands, the ROV robot drives the corresponding actuators (such as thrusters, servos, etc.) to perform motion.

[0138] During the process of the ROV robot executing control commands, its operation data is collected in real-time through sensors installed on the ROV robot. The sensors include position sensors (such as GPS, depth sensors), speed sensors (such as tachometers), attitude sensors (such as gyroscopes, accelerometers), and motor current and voltage sensors. The collected operation data includes the actual position, actual speed, actual attitude, motor current, and voltage of the ROV robot.

[0139] Use the current real-time environmental data and control commands to recalculate the expected operation data of the ROV robot through the previously matched motion control model. The expected operation data is the state that the model predicts the ROV robot should reach according to the current environment and control requirements.

[0140] Preprocess the collected real-time operation data of the ROV robot, such as filtering, denoising, etc., to ensure the accuracy of the data. Compare the preprocessed real-time operation data item by item with the recalculated expected operation data. The comparison results include position error, speed error, attitude error, and motor working status, etc.

[0141] Output the comparison results to the model optimization module. The model optimization module adjusts and optimizes the motion control model using optimization algorithms (such as genetic algorithms, particle swarm algorithms, etc.) according to these comparison results to improve the accuracy of the model.

[0142] Specifically, for the PID-based ROV motion control system described in the present invention, the model optimization module includes:

[0143] If the real-time operation data of the ROV robot is inconsistent with the expected operation data of the ROV robot, the specific steps of using the genetic algorithm to optimize the motion control model corresponding to the real-time environmental data and generating the optimized control commands for the ROV robot include:

[0144] Calculate error data, which includes position error, velocity error, and attitude error;

[0145] Take reducing the error as the optimization objective and define the fitness function;

[0146] Initialize the genetic algorithm, set the parameters of the genetic algorithm, and each individual represents a set of motion control model parameters;

[0147] Use each individual in the population, that is, the set of model parameters, to simulate the real-time control command and obtain the simulated ROV robot operation data;

[0148] Calculate the error between the simulated data and the real-time operation data, and evaluate the fitness of each individual based on this;

[0149] Select excellent individuals as parents according to the fitness, perform crossover operations to generate offspring, and perform mutation operations on the offspring;

[0150] Repeat the steps of evaluating fitness, selection, crossover, and mutation until the preset number of iterations or error range requirements are met;

[0151] Select the individual with the highest fitness from the final population as the set of motion control model parameters corresponding to the optimized real-time environment data;

[0152] Use the optimized motion control model to process the real-time control command and obtain the expected operation data of the ROV robot;

[0153] Based on the optimized expected operation data, generate an optimized ROV robot control command, and send the optimized ROV robot control command to the ROV robot through the communication link to adjust the motion state of the ROV robot so that the ROV robot reaches the expected operation state.

[0154] In a ROV (Remotely Operated Vehicle) motion control system based on PID (Proportional-Integral-Differential), it is responsible for optimizing the motion control model through the genetic algorithm and generating an optimized control command when the real-time operation data of the ROV robot is inconsistent with the expected operation data.

[0155] Calculate the error between the real-time operation data and the expected operation data of the ROV robot, and the error includes position error, velocity error, and attitude error.

[0156] Take reducing the error as the optimization objective and define the fitness function accordingly. The fitness function is the standard for evaluating the quality of each individual (i.e., the set of motion control model parameters) in the genetic algorithm. The fitness function is inversely proportional to the error data, that is, the smaller the error, the higher the fitness.

[0157] Set the parameters of the genetic algorithm, such as population size, number of iterations, crossover probability, mutation probability, etc. Each individual represents a set of motion control model parameters, which are the basis for the genetic algorithm to search and optimize. Use each individual (set of model parameters) in the population to simulate the real-time control commands and obtain the simulated ROV robot operation data. Calculate the error between the simulated data and the real-time operation data, and evaluate the fitness of each individual based on this. Fitness evaluation is the basis for the genetic algorithm to select excellent individuals.

[0158] Selection, crossover and mutation: Select excellent individuals as parents according to the fitness, and perform crossover operations to generate offspring.

[0159] Perform mutation operations on the offspring to increase the diversity of the population. Repeat the steps of fitness evaluation, selection, crossover and mutation until the preset number of iterations or error range requirements are met.

[0160] Select the optimal individual: Select the individual with the highest fitness from the final population as the set of motion control model parameters corresponding to the optimized real-time environment data. The optimal individual represents the motion control model parameters that can minimize the error under the current environmental conditions.

[0161] Use the optimized motion control model to process the real-time control commands to obtain the expected operation data of the ROV robot. Based on the optimized expected operation data, generate optimized ROV robot control commands. Send the optimized ROV robot control commands to the ROV robot through the communication link. After receiving the optimized control commands, the ROV robot will adjust its motion state to more accurately reach the expected operation state.

[0162] In a second aspect, please refer to Figure 1 , the present invention provides a PID-based ROV motion control method, which is applied to the PID-based ROV motion control system, and includes:

[0163] Step S101, obtain the historical data of the motion control system. The historical data of the motion control system includes historical data of the target position, historical data of the actual position, historical data of the deviation, historical data of the control parameters, historical data of the environment, historical data of the sensors, historical data of the motion trajectory, and historical data of the control instructions;

[0164] Step S102: Extract data features from the environmental data to obtain environmental data classification features. Match the environmental classification features with the historical data of the motion control system according to the time information to obtain an environmental classification feature data set. Divide each type of environmental feature data in the environmental classification feature data set into a training set and a validation set, and use each type of environmental feature data divided into a training set and a validation set to train the neural network model to obtain a motion control model data set corresponding to the environmental classification features. Construct the motion control model data set corresponding to the environmental classification features into an algorithm model knowledge base.

[0165] Step S103: Receive real-time target position data, real-time water flow data, real-time wave data, and real-time load data. Obtain the target position natural environment data according to the real-time target position data. Summarize the real-time water flow data, real-time wave data, real-time load data, and target position natural environment data to obtain a real-time environmental data set.

[0166] Step S104: Match the real-time environmental data set in the preset algorithm model knowledge base to obtain a motion control model corresponding to the real-time environmental data. Receive a real-time control command, substitute the real-time control command into the motion control model corresponding to the real-time environmental data to obtain the expected operation data of the ROV robot.

[0167] Step S105: Transmit the real-time control command to the ROV robot, collect the real-time operation data of the ROV robot, and compare the real-time operation data of the ROV robot with the expected operation data of the ROV robot. If the real-time operation data of the ROV robot is inconsistent with the expected operation data of the ROV robot, optimize the motion control model corresponding to the real-time environmental data using a genetic algorithm according to the error data between the real-time operation data of the ROV robot and the expected operation data of the ROV robot to obtain an optimized motion control model corresponding to the real-time environmental data. Use the optimized motion control model corresponding to the real-time environmental data to process the real-time control command to generate an optimized ROV robot control command, and send the optimized ROV robot control command to the ROV robot.

[0168] Specifically, for the ROV motion control method based on PID described in the present invention, step S103 includes:

[0169] The specific steps of matching the real-time environmental data set in the preset algorithm model knowledge base to obtain a motion control model corresponding to the real-time environmental data include:

[0170] Extract features from the real-time environmental data set to obtain water flow velocity features, wave height features, load weight features, water temperature features, salinity features, and seabed terrain features.

[0171] The extracted features are combined into a feature vector according to a preset format and order, and the feature vector will be used for searching and matching in the algorithm model knowledge base;

[0172] Use the feature vector to search in the algorithm model knowledge base to obtain the motion control model that best matches the real-time environmental data. The motion control model that best matches the real-time environmental data is used to calculate the similarity between the feature vector and the corresponding feature vectors of each model in the knowledge base;

[0173] According to the calculation result of the similarity, select the motion control model with the highest similarity as the best matching model corresponding to the current real-time environmental data.

[0174] Specifically, for the ROV motion control method based on PID described in the present invention, the step S104 includes:

[0175] Send the real-time control command to the ROV robot through the communication link. The real-time control command includes the target position instruction, speed instruction, and attitude instruction;

[0176] After receiving the control command, the internal control system of the ROV robot analyzes the command and drives the corresponding actuators to perform motion;

[0177] During the process of the ROV robot executing the control command, the running data of the ROV robot is collected in real time by the sensors installed on the ROV robot. The sensors on the ROV robot include position sensors, speed sensors, and attitude sensors. The running data of the ROV robot includes the actual position, actual speed, actual attitude, motor current, and voltage;

[0178] Recalculate the expected running data of the ROV robot predicted by the motion control model based on the real-time environmental data and control command;

[0179] Compare the preprocessed real-time running data of the ROV robot with the expected running data item by item, and output the comparison result to the model optimization module.

[0180] Specifically, for the ROV motion control method based on PID described in the present invention, the step S105 includes:

[0181] If the real-time running data of the ROV robot is inconsistent with the expected running data of the ROV robot, the specific steps of using the genetic algorithm to optimize the motion control model corresponding to the real-time environmental data and generating the optimized control command for the ROV robot include:

[0182] Calculate the error data, which includes position error, speed error, and attitude error;

[0183] Taking error reduction as the optimization goal, define the fitness function;

[0184] Initialize the genetic algorithm, set the parameters of the genetic algorithm, and each individual represents a set of motion control model parameters;

[0185] Use each individual in the population, that is, the set of model parameters, to simulate the real-time control command, and obtain the simulated ROV robot operation data;

[0186] Calculate the error between the simulated data and the real-time operation data, and evaluate the fitness of each individual based on this;

[0187] Select excellent individuals as parents according to the fitness, perform crossover operations to generate offspring, and perform mutation operations on the offspring,

[0188] Repeat the steps of evaluating fitness, selection, crossover, and mutation until the preset number of iterations or error range requirements are met;

[0189] Select the individual with the highest fitness from the final population as the set of motion control model parameters corresponding to the optimized real-time environment data;

[0190] Use the optimized motion control model to process the real-time control command, and obtain the expected operation data of the ROV robot;

[0191] Based on the optimized expected operation data, generate an optimized ROV robot control command, and send the optimized ROV robot control command to the ROV robot through the communication link to adjust the motion state of the ROV robot so that the ROV robot reaches the expected operation state.

[0192] The present invention solves the problem that the existing PID control algorithm cannot provide accurate control effects when facing complex systems such as ROVs through the following technical solutions:

[0193] Obtain the historical data of the motion control system, including historical data of the target position, historical data of the actual position, historical data of the deviation, historical data of the control parameters, historical data of the environment, historical data of the sensors, historical data of the motion trajectory, and historical data of the control instructions.

[0194] Extract the features of the environmental data to obtain the classification features of the environmental data, and match these features with the historical data of the motion control system according to the time information to construct an environmental classification feature data set. Use these data sets to train the neural network model to obtain a set of motion control model data corresponding to different environmental classification features, and finally construct an algorithm model knowledge base.

[0195] Receive real-time target position data, as well as real-time water flow data, real-time wave data, real-time load data, etc., obtain the natural environment data of the target position, and aggregate these data into a real-time environment data set. Match the real-time environment data set in the preset algorithm model knowledge base, and select the motion control model that best matches the current real-time environment data through steps such as feature extraction, combination of feature vectors, search, and calculation of similarity.

[0196] Receive real-time control commands (such as target position commands, speed commands, attitude commands, etc.), substitute them into the motion control model corresponding to the real-time environment data, and calculate the expected operation data of the ROV robot. Transmit the real-time control commands to the ROV robot and collect the real-time operation data of the ROV robot. Compare the real-time operation data of the ROV robot with the expected operation data. If the two are inconsistent, use the genetic algorithm to optimize the motion control model corresponding to the real-time environment data according to the error data (such as position error, speed error, attitude error, etc.). The genetic algorithm iteratively optimizes the model parameters through operations such as selection, crossover, and mutation until the preset number of iterations or error range requirements are met, thereby obtaining an optimized motion control model.

[0197] Use the optimized motion control model to process the real-time control commands and generate optimized ROV robot control commands. Send the optimized control commands to the ROV robot to adjust its motion state to make it reach the expected operation state.

[0198] Through the above technical solutions, the present invention can dynamically select and optimize the motion control model when the ROV faces a complex and changeable underwater environment, thereby providing a more accurate control effect and solving the deficiencies of the traditional PID control algorithm in the face of non-linear and time-varying systems.

Claims

1. A PID-based ROV motion control system, characterized in that: include: A data acquisition module is used to acquire historical data of the motion control system, which includes target position historical data, actual position historical data, deviation historical data, control parameter historical data, environment historical data, sensor historical data, motion trajectory historical data, and control instruction historical data; A data processing module is used to extract data features from environmental data to obtain environmental data classification features, match the environmental classification features with historical data of the motion control system based on time information to obtain an environmental classification feature data set, divide each type of environmental feature data in the environmental classification feature data set into a training set and a validation set, and use each type of environmental feature data divided into the training set and the validation set to train a neural network model to obtain a motion control model data set corresponding to the environmental classification features, and construct the motion control model data set corresponding to the environmental classification features into an algorithm model knowledge base; a data detection module for receiving real-time target location data and real-time water flow data, real-time wave data, and real-time load data, obtaining target location natural environment data based on the real-time target location data, and aggregating the real-time water flow data, real-time wave data, real-time load data, and target location natural environment data to obtain a real-time environment data set; The model matching module is used to match the real-time environment data set with the preset algorithm model knowledge base to obtain the motion control model corresponding to the real-time environment data, receive the real-time control command, substitute the real-time control command into the motion control model corresponding to the real-time environment data, and obtain the expected operation data of the ROV robot; a model optimization module, which is used to transmit the real-time control command to the ROV robot, collect the real-time operation data of the ROV robot, compare the real-time operation data of the ROV robot with the expected operation data of the ROV robot, and if the real-time operation data of the ROV robot is inconsistent with the expected operation data of the ROV robot, optimize the motion control model corresponding to the real-time environment data using a genetic algorithm according to the error data between the real-time operation data of the ROV robot and the expected operation data of the ROV robot, obtain the optimized motion control model corresponding to the real-time environment data, use the optimized motion control model corresponding to the real-time environment data to perform data processing on the real-time control command, generate an optimized ROV robot control command, and send the optimized ROV robot control command to the ROV robot; The model matching module is further used to: Sending real-time control commands to the ROV robot through a communication link. The real-time control commands include target position commands, speed commands, and posture commands. After the ROV robot receives the control command, the ROV robot's internal control system interprets the command and drives the corresponding actuator to perform movement; During the execution of control commands by the ROV robot, the operating data of the ROV robot is collected in real time through sensors installed on the ROV robot. The sensors on the ROV robot include position sensors, speed sensors and attitude sensors. The operating data of the ROV robot include actual position, actual speed, actual attitude, motor current and voltage; Recalculate the expected operation data of the ROV robot predicted by the motion control model based on real-time environmental data and control commands; Compare the pre-processed real-time operation data of the ROV robot with the expected operation data item by item, and output the comparison results to the model optimization module; The model optimization module is further used to: Calculate error data, including position error, velocity error, and attitude error; Taking reducing the error as the optimization goal, define the fitness function; Initialize the genetic algorithm and set the parameters of the genetic algorithm. Each individual represents a set of motion control model parameters. Use each individual in the population, i.e., the model parameter set, to simulate the real-time control command and obtain the simulated ROV robot operation data; Calculate the error between the simulated data and the real-time running data, and use it to evaluate the fitness of each individual; According to the fitness, excellent individuals are selected as parents, crossover operations are performed to generate offspring, and mutation operations are performed on the offspring. Repeat the steps of fitness evaluation, selection, crossover, and mutation until the preset number of iterations or error range requirements are reached; The individual with the highest fitness is selected from the final population as the motion control model parameter set corresponding to the optimized real-time environmental data; Use the optimized motion control model to process the real-time control commands and obtain the expected operation data of the ROV robot; Based on the optimized expected operation data, an optimized ROV robot control command is generated, and the optimized ROV robot control command is sent to the ROV robot through a communication link to adjust the ROV robot motion state so that the ROV robot reaches the expected operation state.

2. The ROV motion control system based on PID according to claim 1, characterized in that: The data detection module is further used to: Extract features from real-time environmental data sets to obtain water velocity features, wave height features, load weight features, water temperature features, salinity features, and seabed topography features; The extracted features are combined into feature vectors according to the preset format and order. The feature vectors will be used for searching and matching in the algorithm model knowledge base. The feature vector is used to search in the algorithm model knowledge base to obtain the motion control model that best matches the real-time environment data. The motion control model that best matches the real-time environment data is used to calculate the similarity between the feature vector and the corresponding feature vectors of each model in the knowledge base; According to the calculation results of the similarity, the motion control model with the highest similarity is selected as the best matching model corresponding to the current real-time environment data.

3. A PID-based ROV motion control method, applied to the PID-based ROV motion control system according to any one of claims 1 to 2, characterized in that: include: Step S101, acquiring motion control system historical data, where the motion control system historical data includes target position historical data, actual position historical data, deviation historical data, control parameter historical data, environment historical data, sensor historical data, motion trajectory historical data, and control instruction historical data; Step S102: extracting data features from the environmental data to obtain environmental data classification features, matching the environmental classification features with the motion control system historical data based on time information to obtain an environmental classification feature data set, dividing each type of environmental feature data in the environmental classification feature data set into a training set and a validation set, and using each type of environmental feature data divided into the training set and the validation set to train a neural network model to obtain a motion control model data set corresponding to the environmental classification features, and constructing the motion control model data set corresponding to the environmental classification features into an algorithm model knowledge base; Step S103, receiving real-time target location data and real-time water flow data, real-time wave data, and real-time load data, obtaining target location natural environment data based on the real-time target location data, and aggregating the real-time water flow data, real-time wave data, real-time load data, and target location natural environment data to obtain a real-time environment data set; Step S104: Match the real-time environment data set with a preset algorithm model knowledge base to obtain a motion control model corresponding to the real-time environment data, receive a real-time control command, substitute the real-time control command into the motion control model corresponding to the real-time environment data, and obtain the expected operation data of the ROV robot; Step S105: transmit the real-time control command to the ROV robot, collect the real-time operation data of the ROV robot, compare the real-time operation data of the ROV robot with the expected operation data of the ROV robot, and if the real-time operation data of the ROV robot is inconsistent with the expected operation data of the ROV robot, optimize the motion control model corresponding to the real-time environment data using a genetic algorithm according to the error data between the real-time operation data of the ROV robot and the expected operation data of the ROV robot to obtain the optimized motion control model corresponding to the real-time environment data, use the optimized motion control model corresponding to the real-time environment data to perform data processing on the real-time control command, generate an optimized ROV robot control command, and send the optimized ROV robot control command to the ROV robot.

4. The ROV motion control method based on PID according to claim 3, characterized in that: The step S103 includes: The specific steps of matching the real-time environment data set with the preset algorithm model knowledge base to obtain the motion control model corresponding to the real-time environment data include: Extract features from real-time environmental data sets to obtain water velocity features, wave height features, load weight features, water temperature features, salinity features, and seabed topography features; The extracted features are combined into feature vectors according to the preset format and order. The feature vectors will be used for searching and matching in the algorithm model knowledge base. The feature vector is used to search in the algorithm model knowledge base to obtain the motion control model that best matches the real-time environment data. The motion control model that best matches the real-time environment data is used to calculate the similarity between the feature vector and the corresponding feature vectors of each model in the knowledge base; According to the calculation results of the similarity, the motion control model with the highest similarity is selected as the best matching model corresponding to the current real-time environment data.

5. The ROV motion control method based on PID according to claim 3, characterized in that: The step S104 includes: Sending real-time control commands to the ROV robot through a communication link. The real-time control commands include target position commands, speed commands, and posture commands. After the ROV robot receives the control command, the ROV robot's internal control system interprets the command and drives the corresponding actuator to perform movement; During the execution of control commands by the ROV robot, the operating data of the ROV robot is collected in real time through sensors installed on the ROV robot. The sensors on the ROV robot include position sensors, speed sensors and attitude sensors. The operating data of the ROV robot include actual position, actual speed, actual attitude, motor current and voltage; Recalculate the expected operation data of the ROV robot predicted by the motion control model based on real-time environmental data and control commands; The preprocessed real-time operation data of the ROV robot is compared with the expected operation data item by item, and the comparison results are output to the model optimization module.

6. The ROV motion control method based on PID according to claim 5, characterized in that: The step S105 includes: If the real-time operating data of the ROV robot is inconsistent with the expected operating data of the ROV robot, the specific steps of using a genetic algorithm to optimize the motion control model corresponding to the real-time environmental data and generate the optimized ROV robot control command include: Calculate error data, including position error, velocity error, and attitude error; Taking reducing the error as the optimization goal, define the fitness function; Initialize the genetic algorithm and set the parameters of the genetic algorithm. Each individual represents a set of motion control model parameters. Use each individual in the population, i.e., the model parameter set, to simulate the real-time control command and obtain the simulated ROV robot operation data; Calculate the error between the simulated data and the real-time running data, and use it to evaluate the fitness of each individual; According to the fitness, excellent individuals are selected as parents, crossover operations are performed to generate offspring, and mutation operations are performed on the offspring. Repeat the steps of fitness evaluation, selection, crossover, and mutation until the preset number of iterations or error range requirements are reached; The individual with the highest fitness is selected from the final population as the motion control model parameter set corresponding to the optimized real-time environmental data; Use the optimized motion control model to process the real-time control commands and obtain the expected operation data of the ROV robot; Based on the optimized expected operation data, an optimized ROV robot control command is generated, and the optimized ROV robot control command is sent to the ROV robot through a communication link to adjust the ROV robot motion state so that the ROV robot reaches the expected operation state.

Images