Hydrodynamic simulation method and system for underwater robot

Abstract

The invention relates to the technical field of hydrodynamic simulation, and particularly discloses an underwater robot hydrodynamic simulation method and system, and the method comprises the steps: setting a pressure detection point on the surface of a robot model; instantaneous pressure containing position and time is obtained in real time based on the pressure detection point location, and a pressure sample is constructed; clustering the pressure samples, for each type of pressure samples, querying pose parameters and dynamic parameters of the underwater robot according to the time of the pressure samples, and constructing a regression model from the dynamic parameters to the pose parameters; for the pressure samples obtained in real time, determining a target type pressure sample in a clustering result, reading a regression model corresponding to the target type pressure sample, and performing hydrodynamic simulation on the dynamic parameters; according to the method, environmental conditions are determined based on sensing point locations, a regression model is read for hydrodynamic simulation, the workload of a control module only comprises data reading, function application and instruction output, and the response speed is extremely high on the premise that certain accuracy is achieved.

Description

Technical Field

[0001] The present invention relates to the technical field of hydrodynamic simulation, in particular to a method and system for simulating the hydrodynamics of an underwater robot. Background Art

[0002] Hydrodynamic simulation refers to the process of modeling and simulating the fluid dynamic behavior of underwater carriers (such as underwater robots, submarines, surface ships, etc.) in water through computational methods. The purpose is to predict key indicators such as force, motion response, propulsion efficiency, posture changes, energy consumption, etc., and provide a basis for design and control.

[0003] There is extremely high-performance finite element analysis software in the existing technology that can be used for hydrodynamic simulation and has extremely high performance. However, this requires a large amount of computing resources and is obviously impossible to install on the control module of an underwater robot. On the one hand, there is a memory problem, and on the other hand, the computing speed is insufficient. Therefore, how to provide a lightweight hydrodynamic simulation solution to provide hydrodynamic simulation functions on underwater robots is the technical problem that the technical solution of the present invention aims to solve. Summary of the Invention

[0004] The purpose of the present invention is to provide a method and system for simulating the hydrodynamics of an underwater robot to solve the problems raised in the above background technology.

[0005] To achieve the above object, the present invention provides the following technical solutions:

[0006] A method and system for simulating hydrodynamics of an underwater robot, the method comprising:

[0007] Obtaining a robot model of the underwater robot and setting pressure detection points on the surface of the robot model;

[0008] Based on the pressure detection points, the instantaneous pressure including position and time is obtained in real time to construct a pressure sample;

[0009] Clustering the pressure samples, querying the posture parameters and power parameters of the underwater robot for each type of pressure sample based on the time of the pressure sample, and constructing a regression model from the power parameters to the posture parameters; wherein the number of indicators of the posture parameters and the power parameters are both preset values;

[0010] For the pressure samples acquired in real time, the target class pressure samples are determined in the clustering results, the regression model corresponding to the target class pressure samples is read, and the hydrodynamic simulation of the dynamic parameters is performed.

[0011] As a further solution of the present invention: the step of obtaining a robot model of the underwater robot and setting pressure detection points on the surface of the robot model includes:

[0012] Obtain a robot model of the underwater robot;

[0013] Insert a wrapping mesh of preset accuracy on the surface of the robot model and obtain the characteristic value of each position in the wrapping mesh;

[0014] Select the position where the characteristic value reaches the preset characteristic value threshold as the pressure detection point;

[0015] Among them, the independent variables in the eigenvalue calculation process include two types, one is the distance between the position and the robot model, and the other is the distance between the position and the selected position.

[0016] As a further solution of the present invention, the step of acquiring instantaneous pressure including position and time in real time based on the pressure detection points and constructing a pressure sample includes:

[0017] Obtain instantaneous pressure based on the detection equipment installed at the pressure detection point, and record the position of the pressure detection point and the time when the instantaneous pressure is obtained;

[0018] Counting the instantaneous pressures of all positions at the same acquisition time and constructing an instantaneous pressure table; the instantaneous pressure table includes a position item and an instantaneous pressure item;

[0019] For any instantaneous pressure gauge, compare the instantaneous pressure gauge with the previous instantaneous pressure gauge and the next instantaneous pressure gauge respectively, and determine the first-order difference and second-order difference of the data at each position;

[0020] Determining a weight for each position based on the first-order difference and the second-order difference;

[0021] Construct the weight term, insert the instantaneous pressure table, and obtain the pressure sample.

[0022] As a further solution of the present invention, the steps of clustering the pressure samples, querying the posture parameters and power parameters of the underwater robot according to the time of the pressure samples for each type of pressure samples, and constructing a regression model from the power parameters to the posture parameters include:

[0023] Compare the acquired pressure samples pairwise and calculate the sample distance between any two pressure samples;

[0024] Clustering the pressure samples based on the distance to obtain pressure samples of different classes;

[0025] For each type of pressure sample, query the time of each pressure sample in turn, and query the posture parameters and power parameters at that time in the underwater robot log as parameter samples;

[0026] For any index in the posture parameters, a regression model of the index is constructed based on the dynamic parameters;

[0027] The regression model of all indicators in the statistical posture parameters is used as the regression model from the dynamic parameters to the posture parameters of this type of pressure sample.

[0028] As a further solution of the present invention, the step of performing pairwise comparison on the acquired pressure samples and calculating the sample distance between any two pressure samples includes:

[0029] Pair the obtained pressure samples in pairs;

[0030] For the two paired pressure samples, select a position according to the descending order of weight, compare the data at that position, and calculate the data distance;

[0031] The accumulated data distance, when the data distance reaches the preset threshold, sets the sample distance to the preset maximum value;

[0032] When the data of all positions are calculated, the accumulated data distance is used as the sample distance.

[0033] As a further solution of the present invention, the steps of determining target class pressure samples in the clustering results for the pressure samples acquired in real time, reading the regression model corresponding to the target class pressure samples, and performing hydrodynamic simulation on the dynamic parameters include:

[0034] Read the latest pressure sample, compare it with various pressure samples, and calculate the matching degree;

[0035] Select a class of stress samples whose matching degree reaches a preset matching degree threshold as the target class stress samples;

[0036] Read the regression model of the target class pressure sample and perform hydrodynamic simulation on the current dynamic parameters based on the regression model;

[0037] The hydrodynamic simulation results are verified based on AI at regular intervals, the accuracy is calculated, and the application frequency of the AI is adjusted based on the accuracy; the application frequency is inversely proportional to the accuracy.

[0038] The technical solution of the present invention also provides an underwater robot hydrodynamic simulation system, the system comprising:

[0039] A pressure point creation module is used to obtain a robot model of the underwater robot and set pressure detection points on the surface of the robot model;

[0040] The pressure sample construction module is used to obtain instantaneous pressure including position and time based on the pressure detection points in real time and construct pressure samples;

[0041] A regression model creation module is used to cluster the pressure samples, query the posture parameters and power parameters of the underwater robot according to the time of each pressure sample, and build a regression model from the power parameters to the posture parameters; wherein the number of indicators of the posture parameters and the power parameters are both preset values;

[0042] The sample simulation module is used to determine the target class pressure samples in the clustering results for the pressure samples obtained in real time, read the regression model corresponding to the target class pressure samples, and perform hydrodynamic simulation on the dynamic parameters.

[0043] As a further solution of the present invention: the pressure point creation module includes:

[0044] A model acquisition unit, used to acquire a robot model of the underwater robot;

[0045] An eigenvalue calculation unit is used to insert a wrapping mesh of preset accuracy on the surface of the robot model and obtain the eigenvalue of each position in the wrapping mesh;

[0046] The position first-selecting unit is used to select the position where the characteristic value reaches the preset characteristic value threshold as the pressure detection point;

[0047] Among them, the independent variables in the eigenvalue calculation process include two types, one is the distance between the position and the robot model, and the other is the distance between the position and the selected position.

[0048] As a further solution of the present invention: the pressure sample construction module includes:

[0049] a data acquisition unit, configured to acquire instantaneous pressure based on a detection device installed at a pressure detection point, and record the position of the pressure detection point and the time when the instantaneous pressure is acquired;

[0050] A pressure gauge construction unit, configured to count the instantaneous pressures at all positions at the same acquisition time and construct an instantaneous pressure gauge; the instantaneous pressure gauge includes a position item and an instantaneous pressure item;

[0051] A differential calculation unit is used to compare any instantaneous pressure gauge with the previous instantaneous pressure gauge and the next instantaneous pressure gauge, respectively, to determine the first-order difference and second-order difference of the data at each position;

[0052] a weight determination unit, configured to determine a weight for each position based on the first-order difference and the second-order difference;

[0053] The weight item construction unit is used to construct the weight item, insert the instantaneous pressure gauge, and obtain the pressure sample.

[0054] As a further solution of the present invention: the regression model creation module includes:

[0055] A sample distance calculation unit is used to compare the acquired pressure samples in pairs and calculate the sample distance between any two pressure samples;

[0056] a sample clustering unit, configured to cluster the pressure samples based on the distance to obtain pressure samples of different classes;

[0057] A parameter sample generating unit is used to query the time of each pressure sample in turn for each type of pressure sample, and query the posture parameters and power parameters at that time in the log of the underwater robot as parameter samples;

[0058] An execution unit is constructed to construct a regression model of any index in the posture parameters based on the dynamic parameters;

[0059] The statistical unit is used to calculate the regression model of all indicators in the posture parameters, which serves as the regression model from the dynamic parameters of this type of pressure sample to the posture parameters.

[0060] Compared with the prior art, the present invention has the following beneficial effects:

[0061] The present invention installs multiple sensor points on the underwater robot to obtain different environmental conditions. For the same environmental conditions, the posture parameters and power parameters under the environmental conditions are read, and a mapping relationship from the power parameters to the posture parameters is constructed. At this time, the mapping relationship itself is a function. In actual use, the environmental conditions are determined according to the sensor points, and the mapping relationship is read to perform hydrodynamic simulation. The workload of the control module of the underwater robot is only to read data, apply functions and output instructions. Under the premise of a certain accuracy, the response speed is extremely fast. BRIEF DESCRIPTION OF THE DRAWINGS

[0062] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments of the present invention.

[0063] Figure 1 The overall flow chart of the underwater robot hydrodynamic simulation method is shown.

[0064] Figure 2 Shows the structural diagram of the underwater robot hydrodynamic simulation system. DETAILED DESCRIPTION

[0065] In order to make the technical problems, technical solutions and beneficial effects to be solved by the present invention more clearly understood, the present invention is further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0066] Figure 1 The figure is a general flow chart of a method and system for simulating the hydrodynamics of an underwater robot. In an embodiment of the present invention, a method for simulating the hydrodynamics of an underwater robot includes:

[0067] Step S100: obtaining a robot model of the underwater robot, and setting pressure detection points on the surface of the robot model;

[0068] When designing an underwater robot, there will be a component model, called a robot model. In the technical solution of the present invention, the robot model is considered to be known data. The robot model is analyzed, pressure detection points are set on the surface of the robot model, and patch sensors are installed at the pressure detection points to obtain underwater pressure or pressure intensity.

[0069] Step S200: acquiring instantaneous pressure including position and time based on the pressure detection points in real time to construct a pressure sample;

[0070] A patch pressure sensor is installed at the pressure detection point to obtain underwater pressure. When obtaining underwater pressure, the instantaneous pressure is obtained, and the position and time need to be saved. One acquisition operation can obtain the instantaneous pressure at all positions at that time, which is called a pressure sample.

[0071] Step S300: clustering the pressure samples, querying the posture parameters and power parameters of the underwater robot for each type of pressure sample based on the time of the pressure sample, and constructing a regression model from the power parameters to the posture parameters; wherein the number of indicators of the posture parameters and the power parameters are both preset values;

[0072] The process of acquiring pressure samples is real-time. When the underwater robot is placed in an underwater environment, the sensors installed at the pressure detection points work in real time, and a large number of pressure samples are obtained. In addition, in the test simulation stage, the number of underwater robots used can be multiple, so that the number of pressure samples obtained is even greater. All the pressure samples obtained are clustered. After the clustering is completed, each type of pressure sample is analyzed separately, and the posture parameters and power parameters of the underwater robot are queried according to the time of each pressure sample. The posture parameters and power parameters are obtained by relevant existing modules. These modules are the basic modules of the underwater robot, and the obtained data are also considered to be default known data. Then, a mapping relationship from power parameters to posture parameters is constructed. The mapping relationship constructed by the technical solution of the present invention is a regression model.

[0073] Specifically, the number of indicators of the posture parameters and the power parameters are all preset values, among which the posture parameters mainly include attitude parameters, which are used to describe the orientation or rotation state of the robot, and are usually represented by Euler angles or quaternions, including: roll: rotation around the x-axis (rolling left and right); pitch: rotation around the y-axis (nodding up and down); yaw: rotation around the z-axis (horizontal turning); the power parameters are the source power of each power component. The types and quantities of power components of the underwater robot are not unique, but not too many, which are used to adjust the posture parameters.

[0074] Step S400: for the pressure samples acquired in real time, determine the target class pressure samples in the clustering results, read the regression model corresponding to the target class pressure samples, and perform hydrodynamic simulation on the dynamic parameters;

[0075] Step S400 is the application process. For the pressure sample obtained in real time, it is compared with each pressure sample to determine which category the pressure sample obtained in real time belongs to, which is called the target class pressure sample. The regression model corresponding to the target class pressure sample is read, and then the power parameters to be used are obtained. The power parameters are input into the regression model to obtain the predicted posture parameters. The function of this architecture is that when posture adjustment is required, some power parameters can be generated first. With the help of the obtained regression model, the posture corresponding to each power parameter can be predicted to assist the self-adjustment process of the underwater robot, introducing a simulation function with very little resource demand for the underwater robot.

[0076] Regarding step S100, the steps of obtaining a robot model of the underwater robot and setting pressure detection points on the surface of the robot model include:

[0077] Obtain a robot model of the underwater robot;

[0078] Insert a wrapping mesh of preset accuracy on the surface of the robot model and obtain the characteristic value of each position in the wrapping mesh;

[0079] The position where the characteristic value reaches the preset characteristic value threshold is selected as the pressure detection point.

[0080] The robot model of the underwater robot is a known model and can be directly obtained. A wrapping grid with preset accuracy is inserted on the surface of the robot model. The wrapping grid is a grid inserted on the surface of the robot model. A grid can be generated first and then wrapped on the surface of the robot model. Therefore, it is called a wrapping grid. Generating a grid is a basic function in many existing software and will not be repeated here. The accuracy corresponds to the cell size of the grid. The smaller the cell size, the higher the accuracy. On this basis, the characteristic values of each position in the wrapping grid are obtained, and the position where the characteristic value reaches the preset characteristic value threshold is selected as the pressure detection point.

[0081] The independent variables in the eigenvalue calculation process include two types: one is the distance between the position and the robot model, and the other is the distance between the position and the selected position. A feasible solution is:

[0082] The robot model is divided based on a three-dimensional grid of another precision to obtain multiple three-dimensional points inside the robot model, and the importance of the component at each three-dimensional point is queried (used to characterize the importance of the component); for any position on the covering grid, its distance from all three-dimensional points is calculated, and the importance of each three-dimensional point is divided by its distance, and then accumulated to obtain the importance of each position in the covering grid. The closer to the important component, the higher the importance of the position; on this basis, the nearest selected position of each position is queried, its distance is calculated, and the importance is divided by the distance (an adjustment coefficient can be introduced). The value obtained is called the eigenvalue. In summary, the closer to the important component and the farther away from the nearest selected position, the larger the eigenvalue of the position and the more likely it is to be selected; for a piece of important components, the number of selected points is also greater.

[0083] Regarding step S200, the step of acquiring instantaneous pressure including position and time based on the pressure detection points in real time and constructing a pressure sample includes:

[0084] Obtain instantaneous pressure based on the detection equipment installed at the pressure detection point, and record the position of the pressure detection point and the time when the instantaneous pressure is obtained;

[0085] Counting the instantaneous pressures of all positions at the same acquisition time and constructing an instantaneous pressure table; the instantaneous pressure table includes a position item and an instantaneous pressure item;

[0086] For any instantaneous pressure gauge, compare the instantaneous pressure gauge with the previous instantaneous pressure gauge and the next instantaneous pressure gauge respectively, and determine the first-order difference and second-order difference of the data at each position;

[0087] Determining a weight for each position based on the first-order difference and the second-order difference;

[0088] Construct the weight term, insert the instantaneous pressure table, and obtain the pressure sample.

[0089] The above content explains the construction process of the pressure sample. The instantaneous pressure is obtained based on the detection equipment installed at the pressure detection point. The detection equipment is a pressure sensor. When obtaining the instantaneous pressure, the time and position need to be recorded. Then, the instantaneous pressure of all positions at the same acquisition time is counted with time as the index to construct an instantaneous pressure table. When the time difference between the instantaneous pressures at two positions is small enough, they are considered to belong to the same acquisition time. For any instantaneous pressure table, the instantaneous pressure table is compared with the previous instantaneous pressure table and the next instantaneous pressure table respectively to determine the first-order difference and second-order difference of the data at each position. The calculation process of the first-order difference is to calculate the difference between the current data and the previous data, calculate the difference between the next data and the current data, and then calculate the mean to obtain the first-order difference; the calculation process of the second-order difference is to calculate the sum of the next data and the previous data, and then subtract twice the current data to obtain the second-order difference.

[0090] The weight of each position is determined according to the first-order difference and the second-order difference, a weight term is constructed, and the instantaneous pressure gauge is inserted to obtain a pressure sample; wherein the weight term is proportional to both the first-order difference and the second-order difference.

[0091] Regarding step S300, the steps of clustering the pressure samples, querying the posture parameters and power parameters of the underwater robot according to the time of the pressure samples for each type of pressure samples, and constructing a regression model from the power parameters to the posture parameters include:

[0092] Compare the acquired pressure samples pairwise and calculate the sample distance between any two pressure samples;

[0093] Clustering the pressure samples based on the distance to obtain pressure samples of different classes;

[0094] For each type of pressure sample, query the time of each pressure sample in turn, and query the posture parameters and power parameters at that time in the underwater robot log as parameter samples;

[0095] For any index in the posture parameters, a regression model of the index is constructed based on the dynamic parameters;

[0096] The regression model of all indicators in the statistical posture parameters is used as the regression model from the dynamic parameters to the posture parameters of this type of pressure sample.

[0097] A large number of pressure samples are obtained, and the obtained pressure samples are compared in pairs, and the sample distance between any two pressure samples is calculated. The pressure samples are clustered based on the distance to obtain pressure samples of different categories. The clustering scheme adopted by the technical solution of the present invention is a clustering scheme with no limit on the number of categories, such as the OPTICS clustering algorithm; after clustering is completed, each category of pressure samples is analyzed separately, and for each category of pressure samples, the time of each pressure sample is queried in turn, and the posture parameters and power parameters at the time are queried in the log of the underwater robot. The posture parameters and power parameters at the time constitute a data pair, called a parameter sample, one time corresponds to a parameter sample, the posture parameter is the dependent variable, and the power parameter is the independent variable. In order to make the processing process clearer, each indicator in the posture parameter is used as the dependent variable, and a regression model from the power parameter to each indicator is trained. The regression model of all indicators in the posture parameter is statistically analyzed as the regression model from the power parameter to the posture parameter of this type of pressure sample.

[0098] Specifically, the step of performing pairwise comparison on the acquired pressure samples and calculating the sample distance between any two pressure samples includes:

[0099] Pair the obtained pressure samples in pairs;

[0100] For the two paired pressure samples, select a position according to the descending order of weight, compare the data at that position, and calculate the data distance;

[0101] The accumulated data distance, when the data distance reaches the preset threshold, sets the sample distance to the preset maximum value;

[0102] When the data of all positions are calculated, the accumulated data distance is used as the sample distance.

[0103] In an example of the technical solution of the present invention, the calculation process of the sample distance is explained, the acquired pressure samples are paired in pairs, and for the two paired pressure samples, a position is selected according to the descending order of the weight, the data at the position is compared, and the data distance is calculated. The data distance can be the product of the weight and the absolute value of the difference; the accumulated data distance, when the data distance is large enough, the two pressure samples can be considered not to be samples of the same type, and the sample distance is directly set to a preset maximum value. When the data of all positions are calculated, the accumulated data distance is used as the sample distance; the advantage of introducing this process is that important data is analyzed first, and subsequent analysis is no longer performed on significantly different pressure samples, thereby improving the comparison efficiency.

[0104] Regarding step S400, the steps of determining target class pressure samples in the clustering results for the pressure samples acquired in real time, reading the regression model corresponding to the target class pressure samples, and performing hydrodynamic simulation on the dynamic parameters include:

[0105] Read the latest pressure sample, compare it with various pressure samples, and calculate the matching degree;

[0106] Select a class of stress samples whose matching degree reaches a preset matching degree threshold as the target class stress samples;

[0107] Read the regression model of the target class pressure sample and perform hydrodynamic simulation on the current dynamic parameters based on the regression model;

[0108] The hydrodynamic simulation results are verified based on AI at regular intervals, the accuracy is calculated, and the application frequency of the AI is adjusted based on the accuracy; the application frequency is inversely proportional to the accuracy.

[0109] In an example of the technical solution of the present invention, the actual application stage is explained. The latest acquired pressure sample is read, compared with various types of pressure samples, the matching degree is calculated, and a type of pressure sample whose matching degree reaches a preset matching degree threshold is selected as the target type pressure sample. The regression model of the target type pressure sample is read, and hydrodynamic simulation of the current dynamic parameters is performed based on the regression model.

[0110] On this basis, AI is introduced to verify the hydrodynamic simulation results and determine the accuracy of the hydrodynamic simulation results. The AI verification process is slower and the results are more accurate. The application frequency of AI is adjusted according to the accuracy. When the accuracy is too low, the hydrodynamic simulation process of the present invention may have failed. At this time, the application frequency of AI must be higher. On the contrary, if the accuracy is higher, the application frequency of AI will be lower.

[0111] In addition, regarding the matching parameter, a feasible approach is to traverse various pressure samples using the latest obtained pressure sample, calculate the similarity in real time, and select the maximum similarity as the matching degree. Since the pressure samples use a table structure, the similarity calculation process of the table structure can be used to calculate the similarity.

[0112] Figure 2 FIG1 shows a structural diagram of an underwater robot hydrodynamic simulation system. In a preferred embodiment of the technical solution of the present invention, a system for underwater robot hydrodynamic simulation is also provided. The system 10 includes:

[0113] The pressure point creation module 11 is used to obtain a robot model of the underwater robot and set pressure detection points on the surface of the robot model;

[0114] The pressure sample construction module 12 is used to obtain the instantaneous pressure including position and time in real time based on the pressure detection points and construct a pressure sample;

[0115] A regression model creation module 13 is used to cluster the pressure samples, query the posture parameters and power parameters of the underwater robot according to the time of each pressure sample, and build a regression model from the power parameters to the posture parameters; wherein the index numbers of the posture parameters and the power parameters are all preset values;

[0116] The sample simulation module 14 is used to determine the target class pressure sample in the clustering results for the pressure samples acquired in real time, read the regression model corresponding to the target class pressure sample, and perform hydrodynamic simulation on the dynamic parameters.

[0117] Furthermore, the pressure point creation module 11 includes:

[0118] A model acquisition unit, used to acquire a robot model of the underwater robot;

[0119] An eigenvalue calculation unit is used to insert a wrapping mesh of preset accuracy on the surface of the robot model and obtain the eigenvalue of each position in the wrapping mesh;

[0120] The position first-selecting unit is used to select the position where the characteristic value reaches the preset characteristic value threshold as the pressure detection point;

[0121] Among them, the independent variables in the eigenvalue calculation process include two types, one is the distance between the position and the robot model, and the other is the distance between the position and the selected position.

[0122] Specifically, the pressure sample construction module 12 includes:

[0123] a data acquisition unit, configured to acquire instantaneous pressure based on a detection device installed at a pressure detection point, and record the position of the pressure detection point and the time when the instantaneous pressure is acquired;

[0124] A pressure gauge construction unit, configured to count the instantaneous pressures at all positions at the same acquisition time and construct an instantaneous pressure gauge; the instantaneous pressure gauge includes a position item and an instantaneous pressure item;

[0125] A differential calculation unit is used to compare any instantaneous pressure gauge with the previous instantaneous pressure gauge and the next instantaneous pressure gauge, respectively, to determine the first-order difference and second-order difference of the data at each position;

[0126] a weight determination unit, configured to determine a weight for each position based on the first-order difference and the second-order difference;

[0127] The weight item construction unit is used to construct the weight item, insert the instantaneous pressure gauge, and obtain the pressure sample.

[0128] Furthermore, the regression model creation module 13 includes:

[0129] A sample distance calculation unit is used to compare the acquired pressure samples in pairs and calculate the sample distance between any two pressure samples;

[0130] a sample clustering unit, configured to cluster the pressure samples based on the distance to obtain pressure samples of different classes;

[0131] A parameter sample generating unit is used to query the time of each pressure sample in turn for each type of pressure sample, and query the posture parameters and power parameters at that time in the log of the underwater robot as parameter samples;

[0132] An execution unit is constructed to construct a regression model of any index in the posture parameters based on the dynamic parameters;

[0133] The statistical unit is used to calculate the regression model of all indicators in the posture parameters, which serves as the regression model from the dynamic parameters of this type of pressure sample to the posture parameters.

[0134] The above are only preferred embodiments of the present invention and are not intended to limit the patent scope of the present invention. Any equivalent structure or equivalent process transformation made using the contents of the present invention description and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present invention.

Claims

1. A method for simulating the hydrodynamics of an underwater robot, characterized in that: The method comprises: Obtaining a robot model of the underwater robot and setting pressure detection points on the surface of the robot model; Based on the pressure detection points, the instantaneous pressure including position and time is obtained in real time to construct a pressure sample; Clustering the pressure samples, querying the posture parameters and power parameters of the underwater robot for each type of pressure sample based on the time of the pressure sample, and constructing a regression model from the power parameters to the posture parameters; wherein the number of indicators of the posture parameters and the power parameters are both preset values; For the pressure samples acquired in real time, the target class pressure samples are determined in the clustering results, the regression model corresponding to the target class pressure samples is read, and the hydrodynamic simulation of the dynamic parameters is performed.

2. The underwater robot hydrodynamic simulation method according to claim 1, characterized in that: The steps of obtaining a robot model of the underwater robot and setting pressure detection points on the surface of the robot model include: Obtain a robot model of the underwater robot; Insert a wrapping mesh of preset accuracy on the surface of the robot model and obtain the characteristic value of each position in the wrapping mesh; Select the position where the characteristic value reaches the preset characteristic value threshold as the pressure detection point; Among them, the independent variables in the eigenvalue calculation process include two types, one is the distance between the position and the robot model, and the other is the distance between the position and the selected position.

3. The underwater robot hydrodynamic simulation method according to claim 1, characterized in that: The step of acquiring instantaneous pressure including position and time in real time based on the pressure detection point and constructing a pressure sample includes: Obtain instantaneous pressure based on the detection equipment installed at the pressure detection point, and record the position of the pressure detection point and the time when the instantaneous pressure is obtained; Counting the instantaneous pressures of all positions at the same acquisition time and constructing an instantaneous pressure table; the instantaneous pressure table includes a position item and an instantaneous pressure item; For any instantaneous pressure gauge, compare the instantaneous pressure gauge with the previous instantaneous pressure gauge and the next instantaneous pressure gauge respectively, and determine the first-order difference and second-order difference of the data at each position; Determining a weight for each position based on the first-order difference and the second-order difference; Construct the weight term, insert the instantaneous pressure table, and obtain the pressure sample.

4. The underwater robot hydrodynamic simulation method according to claim 3, characterized in that: The steps of clustering the pressure samples, querying the posture parameters and power parameters of the underwater robot according to the time of the pressure samples for each type of pressure samples, and constructing a regression model from the power parameters to the posture parameters include: Compare the acquired pressure samples pairwise and calculate the sample distance between any two pressure samples; Clustering the pressure samples based on the distance to obtain pressure samples of different classes; For each type of pressure sample, query the time of each pressure sample in turn, and query the posture parameters and power parameters at that time in the underwater robot log as parameter samples; For any index in the posture parameters, a regression model of the index is constructed based on the dynamic parameters; The regression model of all indicators in the statistical posture parameters is used as the regression model from the dynamic parameters to the posture parameters of this type of pressure sample.

5. The underwater robot hydrodynamic simulation method according to claim 4, characterized in that: The step of performing pairwise comparison on the acquired pressure samples and calculating the sample distance between any two pressure samples includes: Pair the obtained pressure samples in pairs; For the two paired pressure samples, select a position according to the descending order of weight, compare the data at that position, and calculate the data distance; The accumulated data distance, when the data distance reaches the preset threshold, sets the sample distance to the preset maximum value; When the data of all positions are calculated, the accumulated data distance is used as the sample distance.

6. The underwater robot hydrodynamic simulation method according to claim 1, characterized in that: The steps of determining target class pressure samples in clustering results for the pressure samples acquired in real time, reading the regression model corresponding to the target class pressure samples, and performing hydrodynamic simulation on the dynamic parameters include: Read the latest pressure sample, compare it with various pressure samples, and calculate the matching degree; Select a class of stress samples whose matching degree reaches a preset matching degree threshold as the target class stress samples; Read the regression model of the target class pressure sample and perform hydrodynamic simulation on the current dynamic parameters based on the regression model; The hydrodynamic simulation results are verified based on AI at regular intervals, the accuracy is calculated, and the application frequency of the AI is adjusted based on the accuracy; the application frequency is inversely proportional to the accuracy.

7. An underwater robot hydrodynamic simulation system, characterized in that: The system comprises: A pressure point creation module is used to obtain a robot model of the underwater robot and set pressure detection points on the surface of the robot model; The pressure sample construction module is used to obtain instantaneous pressure including position and time based on the pressure detection points in real time and construct pressure samples; A regression model creation module is used to cluster the pressure samples, query the posture parameters and power parameters of the underwater robot according to the time of each pressure sample, and build a regression model from the power parameters to the posture parameters; wherein the number of indicators of the posture parameters and the power parameters are both preset values; The sample simulation module is used to determine the target class pressure samples in the clustering results for the pressure samples obtained in real time, read the regression model corresponding to the target class pressure samples, and perform hydrodynamic simulation on the dynamic parameters.

8. The underwater robot hydrodynamic simulation system according to claim 7, characterized in that: The pressure point creation module includes: A model acquisition unit, used to acquire a robot model of the underwater robot; An eigenvalue calculation unit is used to insert a wrapping mesh of preset accuracy on the surface of the robot model and obtain the eigenvalue of each position in the wrapping mesh; The position first-selecting unit is used to select the position where the characteristic value reaches the preset characteristic value threshold as the pressure detection point; Among them, the independent variables in the eigenvalue calculation process include two types, one is the distance between the position and the robot model, and the other is the distance between the position and the selected position.

9. The underwater robot hydrodynamic simulation system according to claim 7, characterized in that: The pressure sample building module includes: a data acquisition unit, configured to acquire instantaneous pressure based on a detection device installed at a pressure detection point, and record the position of the pressure detection point and the time when the instantaneous pressure is acquired; A pressure gauge construction unit, configured to count the instantaneous pressures at all positions at the same acquisition time and construct an instantaneous pressure gauge; the instantaneous pressure gauge includes a position item and an instantaneous pressure item; A differential calculation unit is used to compare any instantaneous pressure gauge with the previous instantaneous pressure gauge and the next instantaneous pressure gauge, respectively, to determine the first-order difference and second-order difference of the data at each position; a weight determination unit, configured to determine a weight for each position based on the first-order difference and the second-order difference; The weight item construction unit is used to construct the weight item, insert the instantaneous pressure gauge, and obtain the pressure sample.

10. The underwater robot hydrodynamic simulation system according to claim 9, characterized in that: The regression model creation module includes: A sample distance calculation unit is used to compare the acquired pressure samples in pairs and calculate the sample distance between any two pressure samples; a sample clustering unit, configured to cluster the pressure samples based on the distance to obtain pressure samples of different classes; A parameter sample generating unit is used to query the time of each pressure sample in turn for each type of pressure sample, and query the posture parameters and power parameters at that time in the log of the underwater robot as parameter samples; An execution unit is constructed to construct a regression model of any index in the posture parameters based on the dynamic parameters; The statistical unit is used to calculate the regression model of all indicators in the posture parameters, which serves as the regression model from the dynamic parameters of this type of pressure sample to the posture parameters.

Images