UUV control parameter optimization system based on virtual ocean field and CEP coupling evaluation and use method

Abstract

The invention provides a UUV control parameter optimization system based on virtual ocean field and CEP coupling evaluation and a use method, and belongs to the field of UUV control, and the UUV control parameter optimization system comprises an optimization and decision-making platform, a CROCO ocean model, a UUV digital prototype and a CEP calculation module; the system can realize full-process digitization and automation of design, evaluation and optimization of UUV control parameters, and solves the technical problems that the UUV control parameters in a traditional method depend on physical trial and error, the optimization period is long, the cost is high, and precision prediction and optimization cannot be carried out in a real ocean disturbance environment.

Description

TECHNICAL FIELD

[0001] The application belongs to the field of UUV design, and particularly relates to a UUV control parameter optimization system based on virtual ocean field and CEP coupling evaluation and a use method. BACKGROUND

[0002] The navigation and control performance of an underwater unmanned vehicle (UUV) is the core guarantee for its completion of underwater reconnaissance, detection, mapping and other mission tasks. Circular Error Probable (CEP) as a key indicator to measure the navigation accuracy directly reflects the ability of the UUV to accurately reach the target point. The smaller the value is, the higher the system accuracy and reliability are.

[0003] At present, the setting of the UUV control parameters and the evaluation of the influence of the UUV control parameters on the navigation accuracy (CEP) mainly rely on traditional methods. The existing technology has three core defects of "high evaluation cost", "long iteration period" and "poor environmental authenticity", which leads to low efficiency of the optimization design of the UUV control parameters and the difficulty in guaranteeing the final performance. SUMMARY

[0004] The purpose of the present application is to provide a UUV control parameter optimization system based on virtual ocean field and CEP coupling evaluation and a use method, which aims to solve the technical problems that the traditional method of UUV control parameter relies on physical trial and error, the optimization period is long, the cost is high, and the precision prediction and optimization cannot be carried out in the real ocean disturbance environment. The method can realize the innovation of fast and low-cost evaluation and prediction of CEP to overcome the limitations of the traditional method.

[0005] In order to realize the above technical features, the purpose of the present application is realized as follows: a UUV optimization design system based on an ocean simulator, comprising an optimization and decision platform, a CROCO ocean model, a UUV digital prototype and a CEP calculation module; The optimization and decision platform comprises a parameter management unit and an environment configuration interface, which is used to generate and issue a control parameter combination to the UUV digital prototype, update the ocean environment data to the CROCO ocean model, and receive the calculation results of the CEP calculation module to drive the intelligent optimization algorithm, so as to realize closed-loop feedback control; The CROCO ocean model comprises a multi-physical field data engine, which is used to generate a high-confidence virtual ocean field containing temperature, salinity, flow rate, depth and density elements, and provide real-time and dynamic ocean environment data to the UUV digital prototype; The UUV digital prototype comprises a kinematics model and a PI loop controller, which is used to receive the control parameters and real-time ocean environment data, perform high-fidelity closed-loop simulation, and output N terminal trajectory data generated by N times of Monte Carlo simulation to the CEP calculation module; The CEP calculation module comprises a data processor and a statistical evaluation unit, which is used for receiving terminal trajectory data, calculating distance errors of the terminal trajectory data relative to a target point, obtaining a median value through statistical sorting, and outputting a final CEP value to an optimization and decision-making platform.

[0006] In another aspect, the application provides a use method of a UUV optimization design system based on a marine simulator, characterized in that the method comprises the following steps: S1, initialization and parameter distribution: an optimization space of control parameters and an initial environment scenario are set through the optimization and decision-making platform; the platform distributes initial control parameter combinations to a UUV digital prototype and distributes environment configuration parameters to a CROCO marine model; S2, dynamic simulation and data interaction: the CROCO marine model generates a dynamic virtual marine field according to the configuration parameters; the UUV digital prototype receives the control parameters and requests real-time marine environment data from the CROCO marine model at each time step of the simulation, and the CROCO marine model responds to the request and provides the data; after completing the dynamic calculation, the UUV digital prototype feeds back new generation state parameters to the CROCO marine model, and the process is repeated until the simulation is completed; S3, terminal data acquisition and CEP calculation: the UUV digital prototype outputs N terminal trajectory data generated by N Monte Carlo simulations to a CEP calculation module; after receiving the data, the CEP calculation module calculates distance errors of each terminal point relative to a target point, statistically sorts all error values and obtains a median value, thereby obtaining a CEP value corresponding to the control parameter combination; S4, intelligent optimization and decision-making: the optimization and decision-making platform receives the CEP calculation result, analyzes the current performance through an intelligent optimization algorithm, and generates a new generation control parameter combination or updates the environment configuration parameters; the platform determines whether the optimization target is met, and if yes, outputs the optimal control parameters and a predicted CEP value, otherwise, jumps to step S1 to continue iterative optimization.

[0007] Preferably, in step S1, the initialization and parameter distribution specifically comprises: S11, environment scenario configuration: through an environment configuration interface of the optimization and decision-making platform, a geographical range of a target sea area, a simulation time length, a time resolution and required physical field data are set; S12, parameter space definition: through a parameter management unit of the optimization and decision-making platform, UUV control parameters to be optimized are set, including a heading, proportional and integral gains Kp and Ki of a depth control loop, optimization upper and lower bounds and an initial sampling point number N; S13, initial parameter generation: an experimental design method is used to generate representative initial control parameter combinations in the defined parameter space; S14, parameter and instruction issuing: the generated initial control parameter combination is issued to the UUV digital prototype; the environmental scenario configuration parameter is issued to the CROCO ocean model, so that it starts to generate a virtual ocean field.

[0008] Preferably, in step S2, the dynamic simulation and data interaction specifically includes: S21, environment field generation and initialization: the CROCO ocean model initializes and generates a dynamic and high-resolution virtual ocean physical field containing temperature, salinity, flow rate, depth, and density elements according to the received environmental configuration parameter; S22, simulation step and data request: the UUV digital prototype initiates a data request to the CROCO ocean model at the beginning of each simulation time step, based on its current position and attitude, to request real-time ocean environment data at its location at the current time step; S23, environmental data response and provision: the CROCO ocean model responds to the data request of the UUV digital prototype, and provides accurate ocean environment data corresponding to the current spatio-temporal position by querying and interpolating; S24, kinematic simulation and state feedback: the UUV digital prototype receives the ocean environment data, combines the current control parameter, solves the kinematic simulation, and advances the UUV state; and feeds back the new position and attitude parameters of the new generation to the CROCO ocean model for data query and environmental field update at the next time step.

[0009] Preferably, in step S3, the terminal data acquisition and CEP calculation specifically include: S31, terminal trajectory data acquisition: the UUV digital prototype outputs the plane coordinates relative to the target point at the end of each simulation after completing N Monte Carlo simulations, forming a data set containing N terminal trajectory points; S32, distance error calculation: the CEP calculation module receives the terminal trajectory data, calculates the Euclidean distance between each terminal point and the preset target point, and obtains N terminal distance error values; S33, CEP value calculation and output: the CEP calculation module calculates the median of the N terminal distance error values, takes the median as the CEP value corresponding to the current control parameter combination, and outputs it to the optimization and decision platform.

[0010] Preferably, in step S4, intelligent optimization and decision specifically include: S41, CEP result receiving and performance evaluation: the optimization and decision platform receives the CEP value transmitted by the CEP calculation module, and evaluates the navigation accuracy performance of the current control parameter combination; S42, optimization algorithm execution and new parameter generation: the optimization and decision platform is based on intelligent optimization algorithm, analyzes the current performance, and generates a new generation of control parameter combination or environmental configuration parameter with better performance; S43, optimality determination: the optimization and decision platform determines whether the optimization target reaches the maximum number of optimization iterations; S44, decision output or iteration cycle: if the optimization target is met, the platform outputs the current optimal control parameter and the predicted CEP value; otherwise, the platform issues the new generation of parameters, and jumps to step S1 to start a new round of optimization iteration.

[0011] The present application has the following beneficial effects: 1. The present application realizes the digitization and automation of the evaluation process, greatly reducing the cost and cycle: by constructing a virtual ocean field to replace physical sea trial, using agent model and intelligent optimization to replace artificial trial and error, the traditional parameter setting and sea trial verification period is shortened to several days or even several hours, greatly reducing the economic and time cost.

[0012] 2. The present application ensures high confidence of the optimized environment and improves the reliability of the results in actual combat: by introducing the CROCO professional ocean model, the optimization process is carried out in a dynamic virtual environment containing real physical disturbances (ocean currents, internal waves, temperature and salinity changes), ensuring that the optimized parameters have strong anti-interference ability and environmental adaptability, solving the problem of "paper tiger".

[0013] 3. The present application forms a complete "simulation-evaluation-optimization" closed loop, enabling intelligent decision-making: the present application connects various modules into an automated closed loop system, which can autonomously find the global optimal solution and output the optimal parameters verified by the virtual environment with effective energy prediction (CEP value), providing engineers with a powerful digital design tool and decision support. BRIEF DESCRIPTION OF DRAWINGS

[0014] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings needed to be used in the embodiment or prior art description. Obviously, the drawings in the following description are only some embodiments of the present application, and for those skilled in the art, other drawings can also be obtained without creative labor on the basis of these drawings.

[0015] Figure 1 A principle block diagram of a UUV control parameter optimization system based on virtual ocean field and CEP coupling evaluation according to the present application.

[0016] Figure 2 A ground coordinate system diagram used by a UUV control parameter optimization system based on virtual ocean field and CEP coupling evaluation according to the present application.

[0017] Figure 3 A detailed flowchart of a use method flowchart of a UUV control parameter optimization system based on virtual ocean field and CEP coupling evaluation of the present application. DETAILED DESCRIPTION

[0018] In order to make the purpose, technical solutions and advantages of the present application clearer and more apparent, the present application will be further described in detail below in combination with the drawings and examples. It should be understood that the specific examples described herein are only used to explain the present application and do not limit the present application.

[0019] Example 1: Example 1: As shown in FIG. 1, a UUV control parameter optimization system based on virtual ocean field and CEP coupling evaluation includes an optimization and decision platform, a CROCO ocean model, a UUV digital prototype and a CEP calculation module.

[0020] The optimization and decision platform includes a parameter management unit and an environment configuration interface, which is used to generate and issue a control parameter combination to the UUV digital prototype, update ocean environment parameters to the CROCO ocean model, and receive CEP calculation results to drive an intelligent optimization algorithm, so as to realize closed-loop feedback control. The CROCO ocean model includes a multi-physical field data engine, which is used to generate a high-confidence virtual ocean field containing temperature, salinity, flow rate, depth, density and other elements, and provide real-time and dynamic ocean environment data to the UUV digital prototype. The UUV digital prototype includes a kinematics model and a PI loop controller, which is used to receive control parameters and real-time ocean field data, perform high-fidelity closed-loop simulation, and output N terminal trajectory data generated by N times of Monte Carlo simulation to the CEP calculation module. The CEP calculation module includes a data processor and a statistical evaluation unit, which is used to receive terminal trajectory data, calculate the distance error thereof from the target point, and output the final CEP value to the optimization and decision platform by sorting and finding the median.

[0021] Example 2: A use method of a UUV control parameter optimization design system based on the above-mentioned UUV control parameter optimization system based on virtual ocean field and CEP coupling evaluation, the method comprising the following steps S1-S4: Preferably, in step S1, the initialization and parameter issuance includes four sub-steps S11-S14. S11, environment scenario configuration: through the environment configuration interface of the optimization and decision platform, set the geographical range of the target sea area, the simulation time length, the time resolution and the required physical field elements (temperature, salinity, flow rate, depth, density and other parameters); The geographical range of the target sea area is set to East Longitude 115.5°-116.5°, North Latitude 18.5°-19.5°. The simulation duration is set to 12 hours on June 1, 2023 to reproduce the historical ocean current field in that period. The required core physical field elements are specified as flow velocity (u, v, w), temperature and salinity, and the horizontal grid resolution is configured as 1 / 10°x 1 / 10°.

[0022] S12, parameter space definition: through the parameter management unit of the decision-making platform, the UUV control parameters to be optimized, i.e. the heading, the proportional gain Kp, the integral gain Ki of the depth control loop, the optimization upper and lower bounds and the initial sampling point number N are set; Among the to-be-determined UUV control parameters, the optimization range of the proportional gain Kp is defined as 0.5 to 2.5. The optimization range of the integral gain Ki is defined as 0.01 to 0.2.

[0023] S13, initial parameter generation: representative initial control parameter combinations are generated in the defined parameter space by using an experimental design method; The experimental design method uses the Latin hypercube sampling method to generate 20 representative initial parameter combinations in the two-dimensional parameter space in S12 as the input of the first round of simulation.

[0024] S14, parameter and instruction issuing: the generated initial control parameter combinations are issued to the UUV digital prototype; the environmental scenario configuration parameters are issued to the CROCO ocean model.

[0025] Preferably, in step S2, the dynamic simulation and data interaction includes four sub-steps S21-S24; S21, environment field generation and initialization: the CROCO ocean model initializes and generates dynamic and high-resolution virtual ocean physical fields containing temperature, salinity, flow velocity, depth, density and other elements according to the received environmental configuration parameters; S22, simulation step and data request: the UUV digital prototype initiates a data request to the CROCO ocean model at the beginning of each simulation time step based on its current position and attitude, requesting real-time ocean environment data at its location at the current time step; S23, environmental data response and provision: the CROCO ocean model responds to the data request of the UUV digital prototype and provides accurate ocean environment data corresponding to the current spatio-temporal position by querying and interpolating; The marine environmental parameters include three-dimensional flow velocity (u, v, w), temperature (T), salinity (S) and density (p) and other space-time variation parameters. These data are generated by the CROCO ocean model and provided in real time to the UUV digital prototype as environmental input for kinematic simulation. Among them, the three-dimensional flow velocity field directly participates in the calculation of the relative velocity in the UUV dynamics equation, affecting the fluid power and torque it receives; temperature and salinity indirectly change the buoyancy and fluid power characteristics of the UUV by determining the density of seawater, and ultimately jointly act on the evolution of the linear velocity, angular velocity and spatial pose of the UUV.

[0026] S24, kinematic simulation and state feedback: the UUV digital prototype receives environmental data, combines the current control parameters, solves the kinematic simulation, and promotes the UUV state; and feeds back the new position and new attitude parameters of the new generation after solving to the CROCO ocean model for data query and environmental field update at the next time step.

[0027] The kinematic simulation selects the ground coordinate system as a fixed reference coordinate system, with the launch point as the origin, the axis is vertical upward, the axis is selected as the forward direction, the axis is perpendicular to and the axis. represents the pitch angle of the UUV, is the yaw angle, represents the roll angle, , , and

[0028] The spatial motion model of the UUV is as follows: ; ; ; ; ;

[0029] ; ; ; In the formula: is the pitch angle; is the roll angle; is the yaw angle; , respectively are the UUV's position in the ground coordinate system the rotational angular velocity of the axis; respectively are the UUV's position in the ground coordinate system the velocity of the axis; respectively are the UUV's position in the ground coordinate system the coordinates of the axis; is the UUV's velocity vector in the ground coordinate system, i.e. the speed; is the angle of attack; is the sideslip angle.

[0030] Preferably, in step S3, the terminal data acquisition and CEP calculation includes three sub-steps S31-S33; S31, terminal trajectory data acquisition: after the UUV digital prototype completes N times of Monte Carlo simulation, it outputs the planar coordinates relative to the target point at the end of each simulation, forming a data set containing N terminal trajectory points; The terminal trajectory data is the final result of the UUV six-degree-of-freedom kinematics model, reflecting the termination position of each simulation under specific control parameters and ocean environment disturbances S32, distance error calculation: the CEP calculation module receives the terminal trajectory data, calculates the Euclidean distance between each terminal point and the preset target point, and obtains N terminal distance error values; The Euclidean distance: S33, CEP value calculation and output: the CEP calculation module calculates the median of the N terminal distance error values, takes the median as the CEP value corresponding to the current control parameter combination, and outputs it to the optimization and decision platform.

[0031] The CEP value is a statistical quantity, indicating that under this set of control parameters, the UUV has a 50% probability that its terminal landing point will fall within the circular region with the target point as the center and the value as the radius; the smaller the value, the higher the navigation accuracy.

[0032] Preferably, in step S4, the intelligent optimization and decision-making includes four sub-steps S41-S44.

[0033] ​​​​​​​​​​​​​S41, CEP result receiving and performance evaluation: the optimization and decision platform receives the CEP value transmitted by the CEP calculation module, and evaluates the navigation accuracy performance of the current control parameter combination; The performance evaluation is based on the received CEP value, which directly quantifies the statistical level of the terminal navigation accuracy of the UUV in the virtual ocean field in multiple simulations under the current control parameters; S42, optimization algorithm execution and new parameter generation: the platform analyzes the current performance based on the intelligent optimization algorithm, and generates a new generation of control parameter combination or environmental configuration parameter with better performance; The intelligent optimization algorithm uses genetic algorithm, which uses historical parameter combinations and their corresponding CEP values as training data to build a proxy model to predict the performance of unexplored areas, and finds the global optimal solution based on the acquisition function, thereby generating a new generation of parameter combination expected to improve the most; S43, optimality determination: the platform determines whether the optimization target is reached and whether the optimization iteration is the maximum number of times; The optimality determination criterion is whether the iteration number reaches the preset maximum upper limit of 50 times; S44, decision output or iteration cycle: if the optimization target is met, the platform outputs the current optimal control parameter and the predicted CEP value; otherwise, the platform issues a new generation of parameters, and jumps to step S1 to start a new round of optimization iteration.

[0034] The decision output content includes: the recommended optimal control parameter combination and the predicted CEP value under the parameter; if iteration is needed, the new parameter combination will be issued as input to the simulation loop to start a new round of "simulation-evaluation-optimization" process.

[0035] Embodiment 3: Figure 3 is a flowchart of a UUV control parameter optimization design method according to an exemplary embodiment, as shown in Figure 3, the method includes the following steps: Step one: initialization and parameter issuance: set the optimization space of the control parameters and the initial environmental scenario through the optimization and decision platform; the platform issues the initial control parameter combination to the UUV digital mockup, and issues the environmental configuration parameters to the CROCO ocean model; Step two: dynamic simulation and data interaction: the CROCO ocean model generates a dynamic virtual ocean field according to the configuration parameters; the UUV digital mockup receives the control parameters, and at each time step of the simulation, requests real-time ocean environment data (temperature, salinity, flow rate, depth, density, etc. Parameters) from the CROCO ocean model, and the CROCO ocean model responds to the request and provides the data; after completing the dynamics calculation, the UUV digital mockup feeds back the new generation of state parameters to the CROCO ocean model, and the cycle continues until the simulation is completed; Step three: terminal data acquisition and CEP calculation: the UUV digital prototype outputs N terminal trajectory data generated by N times of Monte Carlo simulation to the CEP calculation module; after receiving the data, the CEP calculation module calculates the distance error between each terminal point and the target point, sorts all error values and takes the median to obtain the CEP value corresponding to the control parameter group; Step four: intelligent optimization and decision: the optimization and decision platform receives the CEP calculation result, analyzes the current performance through the intelligent optimization algorithm, and generates a new generation of control parameter combination or updates the environmental configuration parameter; the platform judges whether the optimization target is satisfied, if yes, outputs the optimal control parameter and the predicted CEP value, otherwise, jumps to step S1 to continue iterative optimization.

[0036] The present application is not limited to the precise construction which has been described above and illustrated in the accompanying drawings, and various modifications and changes can be made without departing from the scope thereof. The scope of the application is limited only by the appended claims.

Claims

1. A UUV optimization design system based on a marine simulator, characterized in that, The system comprises an optimization and decision platform, a CROCO ocean model, a UUV digital prototype, and a CEP calculation module. The optimization and decision platform comprises a parameter management unit and an environment configuration interface, which is used to generate and issue a control parameter combination to the UUV digital prototype, update ocean environment data to the CROCO ocean model, and receive the calculation results of the CEP calculation module to drive an intelligent optimization algorithm, thereby realizing closed-loop feedback control. The CROCO ocean model comprises a multi-physical field data engine, which is used to generate high-confidence virtual ocean fields containing temperature, salinity, flow velocity, depth, and density elements, and provide real-time and dynamic ocean environment data to the UUV digital prototype. The UUV digital prototype comprises a kinematics model and a PI loop controller, which is used to receive control parameters and real-time ocean environment data, perform high-fidelity closed-loop simulation, and output N terminal trajectory data generated by N Monte Carlo simulations to the CEP calculation module. The CEP calculation module comprises a data processor and a statistical evaluation unit, which is used to receive terminal trajectory data, calculate the distance error of the terminal trajectory data from a target point, and output the final CEP value to the optimization and decision platform by statistical sorting.

2. A method of using a UUV optimization design system based on a marine simulator according to claim 1, characterized in that, The system comprises the following steps: S1, initialization and parameter issuance: the optimization and decision platform is used to set the optimization space of control parameters and the initial environment scenario; the platform issues the initial control parameter combination to the UUV digital prototype and the environment configuration parameters to the CROCO ocean model; S2, dynamic simulation and data interaction: the CROCO ocean model generates dynamic virtual ocean fields according to the configuration parameters; the UUV digital prototype receives the control parameters and requests real-time ocean environment data from the CROCO ocean model at each time step of the simulation, and the CROCO ocean model responds to the request and provides the data; after the UUV digital prototype completes the dynamics calculation, it feeds back the new generation of state parameters to the CROCO ocean model, and the process is repeated until the simulation is completed; S3, terminal data acquisition and CEP calculation: the UUV digital prototype outputs N terminal trajectory data generated by N Monte Carlo simulations to the CEP calculation module; after receiving the data, the CEP calculation module calculates the distance error of each terminal point from the target point, statistically sorts all error values, and takes the median to obtain the CEP value corresponding to the control parameter combination; S4, intelligent optimization and decision: the optimization and decision platform receives the CEP calculation results, analyzes the current performance through an intelligent optimization algorithm, generates a new generation of control parameter combination or updates the environment configuration parameters, and judges whether the optimization target is met; if yes, the optimal control parameters and the predicted CEP value are output, otherwise, the process jumps to step S1 for iterative optimization.

3. The method of claim 2, wherein: In step S1, the initialization and parameter issuance specifically comprises: S11, environment scenario configuration: the environment configuration interface of the optimization and decision platform is used to set the geographical range, simulation duration, time resolution, and required physical field data of the target sea area. S12, parameter space definition: through the parameter management unit of the decision-making platform, set the UUV control parameters to be optimized, including the heading, the proportional and integral gain Kp, Ki of the depth control loop, the optimization upper and lower bounds, and the initial sampling point number N; S13, initial parameter generation: using the experimental design method to generate a representative initial control parameter combination in the defined parameter space; S14, parameter and instruction issuing: issuing the generated initial control parameter combination to the UUV digital prototype; issuing the environmental scenario configuration parameters to the CROCO ocean model to start generating a virtual ocean field.

4. The method of claim 2, wherein the method further comprises: In step S2, the dynamic simulation and data interaction specifically includes: S21, environment field generation and initialization: the CROCO ocean model initializes and generates a dynamic, high-resolution virtual ocean physical field containing temperature, salinity, flow rate, depth, and density elements according to the received environmental configuration parameters; S22, simulation step and data request: the UUV digital prototype initiates a data request to the CROCO ocean model at the beginning of each simulation time step based on its current position and attitude, requesting real-time ocean environment data at its location at the current time step; S23, environmental data response and provision: the CROCO ocean model responds to the data request of the UUV digital prototype, providing accurate ocean environment data corresponding to the current spatiotemporal location through querying and interpolation; S24, kinematic simulation and state feedback: the UUV digital prototype receives the ocean environment data, combines the current control parameters, solves the kinematic simulation, and advances the UUV state; and feeds back the new position and attitude parameters of the new generation to the CROCO ocean model for data querying and environmental field updating at the next time step.

5. The method of claim 2, wherein: In step S3, the terminal data acquisition and CEP calculation specifically includes: S31, terminal trajectory data acquisition: the UUV digital prototype outputs the plane coordinates relative to the target point at the end of each simulation after completing N Monte Carlo simulations, forming a data set containing N terminal trajectory points; S32, distance error calculation: the CEP calculation module receives the terminal trajectory data, calculates the Euclidean distance between each terminal point and the preset target point, and obtains N terminal distance error values; S33, CEP value calculation and output: the CEP calculation module calculates the median of the N terminal distance error values, takes the median as the CEP value corresponding to the current control parameter combination, and outputs it to the optimization and decision-making platform.

6. The method of claim 2, wherein: In step S4, intelligent optimization and decision-making specifically includes: S41, CEP result reception and performance evaluation: the optimization and decision-making platform receives the CEP value transmitted by the CEP calculation module and evaluates the navigation accuracy performance of the current control parameter combination; S42, optimization algorithm execution and new parameter generation: the optimization and decision-making platform analyzes the current performance based on intelligent optimization algorithms to generate a new generation of control parameter combination or environmental configuration parameters with better performance; S43, optimality determination: the optimization and decision-making platform determines whether the optimization target has reached the maximum number of optimization iterations. S44, decision output or iteration cycle: if the optimization target is met, the platform outputs the current optimal control parameters and the predicted CEP value; otherwise, the platform issues a new generation of parameters, and jumps to step S1 to start a new round of optimization iteration.

Images