Water environment unmanned ship autonomous navigation method and device based on concentration gradient, equipment and storage medium

Abstract

A water environment unmanned ship autonomous navigation method and device based on concentration gradient, equipment and storage medium are disclosed. The method comprises: collecting concentration data in the water environment through a sensor carried by the unmanned ship; constructing a time-averaged concentration gradient rapid inversion model, the time-averaged concentration gradient rapid inversion model comprising a simple model and a PINN model capable of directly calculating based on the current collected concentration data, and dynamically adjusting the weight proportion of the two models to process the collected concentration data to obtain the time-averaged concentration field of the water body; determining the expected navigation path of the next step according to the concentration gradient direction of the time-averaged concentration field obtained by inversion; and based on the expected navigation path, the movement characteristics of the unmanned ship and the water environment characteristics, the moving direction and speed of the unmanned ship are adjusted in real time. The present disclosure can realize efficient pollutant tracing and accurate water quality monitoring in the water environment.

Description

Technical Field

[0001] The present disclosure relates to the technical field of water environment monitoring and autonomous navigation, and in particular to a method, device, equipment and storage medium for autonomous navigation of an unmanned boat in a water environment based on a concentration gradient. Background Art

[0002] With industrialization and population growth, pollution, overexploitation, and climate change are jointly threatening global water resources, and water environmental issues have become a global concern. Effective monitoring and management of sewage outlets is a fundamental component of water environmental protection. Due to the widespread and hidden locations of sewage outlets, coupled with the increasing incidence of underwater sewage discharge, monitoring efforts face numerous challenges. Therefore, strengthening water environmental monitoring, particularly the inspection and monitoring of sewage outlets, is crucial for improving water quality and restoring the ecosystem.

[0003] With the advancement of automation and intelligent technology, robotics are increasingly being used in environmental water conservation. Robotic systems, such as autonomous underwater vehicles (AUVs) and unmanned surface vessels (USVs), are being extensively researched to enable automated and continuous monitoring of water quality parameters such as temperature, salinity, dissolved oxygen, pH, and turbidity. These systems can access areas difficult for humans to reach, such as the deep sea or remote waters, providing environmental scientists with unprecedented monitoring capabilities.

[0004] Concentration gradients play a crucial role in water quality monitoring and pollutant source tracing, especially when combined with autonomous patrol water quality monitoring robots. Concentration gradients, or the spatial variation in the concentration of one or more chemical components in water, provide key information for identifying pollution sources and understanding their spread. With the advancement of water quality monitoring robot technology, these autonomous mobile devices are able to implement efficient and accurate concentration gradient monitoring and analysis in water bodies. By combining the collected data with geographic information systems (GIS) and environmental models, concentration field inversion and pollutant source tracing can be achieved. This technology not only improves the efficiency and accuracy of water quality monitoring but also plays a vital role in the rapid response and handling of pollution incidents.

[0005] Existing water quality monitoring technologies primarily utilize unmanned vessels and other equipment to automate the monitoring of water quality parameters. These systems typically include modules for sensor data acquisition, data transmission and processing, and navigation control. In practical applications, complex dynamic conditions in the aquatic environment (such as varying flow rates and obstructions) must be considered, as well as technical requirements such as data processing and real-time transmission. Furthermore, due to factors such as sparse sampling points and the influence of local water mixing on sampling equipment, further improvements in system monitoring efficiency and accuracy are needed.

[0006] Therefore, there is an urgent need for an autonomous navigation technology for unmanned water vessels that can achieve efficient pollutant tracing and water quality monitoring, and improve the scientific and refined level of water environment protection. Summary of the Invention

[0007] The present disclosure provides a method for autonomous navigation of unmanned boats in water environments based on concentration gradients. By combining a simple model with a PINN (Physics-Informed Neural Networks) model to dynamically invert the water concentration field, efficient pollutant tracing and precise water quality monitoring in water environments can be achieved.

[0008] According to one embodiment of the present disclosure, a method for autonomous navigation of an unmanned vessel in a water environment based on a concentration gradient is proposed, comprising:

[0009] Collect concentration data in the water environment through sensors carried by unmanned vessels;

[0010] Constructing a time-averaged concentration gradient rapid inversion model, which includes a simple model that can directly calculate based on currently collected concentration data and a physical information neural network (PINN) model, and dynamically adjusting the weight ratio of the two models to process the collected concentration data to obtain the time-averaged concentration field of the water body;

[0011] Determine the next desired navigation path based on the concentration gradient direction of the time-averaged concentration field obtained by inversion;

[0012] Based on the expected navigation path, combined with the unmanned ship's motion characteristics and environmental characteristics, the moving direction and speed of the unmanned ship are adjusted in real time.

[0013] In some possible embodiments, the PINN model uses the control equation of the hydrodynamic-water quality model as a physical constraint condition in the training process, and the loss function includes a data fitting term and a physical constraint term. The data fitting term is used to measure the deviation between the predicted concentration value and the observed concentration value of the observation data sampling point, and the physical constraint term is used to measure the fit between the predicted concentration value of the constraint sampling point and the physical law.

[0014] In some possible implementations, the data fitting term is determined according to the following formula:

[0015] Among them, Θ is the PINN network parameter, x (i) is the spatial coordinate point, is the number of observation data sampling points, For PINN network in x (i) The predicted concentration value at g(x (i) ) is in x (i) The concentration values ​​collected at It means to find the square of L2 norm.

[0016] In some possible implementations, the method further includes:

[0017] A spatiotemporal concentration variation data set is obtained by LES simulation, wherein the spatiotemporal concentration variation data set includes the flow velocity and concentration value of each grid point in the flow field at different times;

[0018] Constraint sampling points are selected based on the spatiotemporal concentration variation dataset, wherein the constraint sampling points in areas with large flow velocity or concentration gradient variations are denser than those in areas with small flow velocity or concentration gradient variations.

[0019] In some possible implementations, the physical constraint term L is determined according to the following formula: Ω (Θ):

[0020]

[0021] Among them, N Ω is the number of sampling points under the constraint condition, x (i) is a spatial coordinate point, v represents the physical parameter of the control equation used to establish the physical constraint, D(x (i) ; v) means x (i) Substitute the predicted concentration value at into the residual calculated by the control equation, It means to find the square of L2 norm.

[0022] In some possible implementations, under complex flow field conditions, the physical constraint term is obtained by substituting the predicted concentration value of the constraint condition sampling point into the LES calculation residual.

[0023] In some possible embodiments, the time-averaged concentration gradient rapid inversion model integrates the outputs of the simple model and the PINN model according to the following formula:

[0024]

[0025] Among them, w simple +w PINN =1, is the final time-averaged concentration field output by the time-averaged concentration gradient fast inversion model, The calculation results of the simple model are: is the calculation result of PINN model, w simple and w PINN is the weight coefficient.

[0026] In some possible implementations, dynamically adjusting the weight ratio of the two models includes:

[0027] Increased with the number of sampling points exist The weight ratio in .

[0028] In some possible implementations, dynamically adjusting the weight ratio of the two models includes:

[0029] Calculate the concentration gradient direction error and concentration inversion error of the calculation results of the simple model;

[0030] If either the concentration gradient direction error or the concentration inversion error exceeds the corresponding preset threshold, then w is set simple =0,w PINN =1.

[0031] In some possible implementations, adjusting the moving direction and speed of the unmanned vessel in real time includes:

[0032] Use sensors to monitor the surrounding environment in real time and identify and avoid obstacles in the water;

[0033] Adjust the steering angle and acceleration according to the unmanned vessel's own inertia characteristics;

[0034] Adjust course and speed according to current water conditions;

[0035] Reduce travel speed in areas of high concentration gradient to increase sampling density.

[0036] According to one embodiment of the present disclosure, a concentration gradient-based autonomous navigation device for an unmanned vessel in a water environment is also proposed, comprising:

[0037] A real-time acquisition unit, used to collect concentration data in the water environment through sensors carried by unmanned vessels;

[0038] A model inversion unit is used to construct a time-averaged concentration gradient rapid inversion model, which includes a simple model that can be directly calculated based on the currently collected concentration data and a physical information neural network (PINN) model, and dynamically adjusts the weight ratio of the two models to process the collected concentration data to obtain the time-averaged concentration field of the water body;

[0039] A path determination unit is used to determine the next desired navigation path according to the concentration gradient direction of the time-averaged concentration field obtained by inversion;

[0040] The real-time navigation unit is used to adjust the moving direction and speed of the unmanned ship in real time based on the expected navigation path and in combination with the motion characteristics of the unmanned ship and the environmental characteristics.

[0041] According to one embodiment of the present disclosure, an electronic device is provided, comprising a memory and a processor, wherein the memory is used to store computer instructions executable on the processor, and the processor is used to implement any of the above methods when executing the computer instructions.

[0042] According to one embodiment of the present disclosure, a computer-readable storage medium is provided, on which a computer program is stored. When the program is executed by a processor, the method described in any one of the above items is implemented.

[0043] This paper proposes a concentration gradient-based autonomous navigation solution for unmanned vessels in water environments. This solution significantly improves the accuracy and computational efficiency of inversion results through an innovative concentration field inversion strategy. This approach combines a simple model with the PINN model. When sampled data is limited, the simple model can quickly provide an initial estimate, gradually transitioning to the more accurate PINN model as data increases, thus avoiding the limitations of a single model.

[0044] The proposed PINN model incorporates physical constraints into its design. By calculating residuals at constraint sampling points, the model ensures that predictions conform to hydrodynamic and water quality laws. Large Eddy Simulation (LES) is also used to optimize the distribution of constraint points, further improving prediction accuracy in complex flow fields. This physical constraint mechanism significantly enhances the model's generalization and predictive reliability.

[0045] In terms of navigation control, the present invention dynamically plans the navigation path based on the concentration gradient direction, and comprehensively considers the motion characteristics of the unmanned ship and the water environment characteristics. It improves the sampling efficiency through a reasonable speed control strategy and realizes efficient autonomous navigation.

[0046] The proposed concentration gradient-based autonomous navigation scheme for unmanned vessels in water environments is highly practical, simple, easy to implement, and highly adaptable to environmental conditions, meeting the needs of actual water environment monitoring. This scheme provides a new technical approach for water quality monitoring, improves the efficiency of pollution source tracing, and contributes to the development of water pollution control efforts.

[0047] Other features and advantages of the present disclosure are described in detail below. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the specification and, together with the description, serve to explain the principles of the specification.

[0049] Figure 1 A flow chart of a method for autonomous navigation of an unmanned vessel in a water environment based on a concentration gradient according to an embodiment of the present disclosure is shown.

[0050] Figure 2 A technical framework diagram according to an exemplary embodiment of the present disclosure is shown.

[0051] Figure 3A schematic diagram of a traceability line according to an exemplary embodiment of the present disclosure is shown.

[0052] Figure 4 It is a schematic structural diagram of an electronic device according to at least one embodiment of the present disclosure. DETAILED DESCRIPTION

[0053] Exemplary embodiments will be described in detail herein, with examples illustrated in the accompanying drawings. In the following description, when referring to the drawings, identical numerals in different figures represent identical or similar elements, unless otherwise indicated. The embodiments described in the following exemplary embodiments are not intended to represent all possible embodiments consistent with the present disclosure. Rather, they are merely examples of apparatus and methods consistent with certain aspects of the present disclosure, as detailed in the appended claims.

[0054] The disclosed embodiments may be applied to a computer system / server that is operable with numerous other general-purpose or special-purpose computing system environments or configurations. Examples of well-known computing systems, environments, and / or configurations suitable for use with the computer system / server include, but are not limited to, personal computer systems, server computer systems, thin clients, thick clients, handheld or laptop devices, microprocessor-based systems, set-top boxes, programmable consumer electronics, network personal computers, minicomputer systems, mainframe computer systems, and distributed cloud computing technology environments including any of the above, among others.

[0055] Computer systems / servers may be described in the general context of computer system-executable instructions, such as program modules, executed by a computer system. Generally, program modules may include routines, programs, objects, components, logic, data structures, and the like, that perform specific tasks or implement specific abstract data types. Computer systems / servers may be implemented in a distributed cloud computing environment where tasks are performed by remote processing devices linked through a communications network. In a distributed cloud computing environment, program modules may be located on local or remote computer system storage media, including storage devices.

[0056] Figure 1 A flow chart of a method for autonomous navigation of an unmanned vessel in a water environment based on a concentration gradient according to an embodiment of the present disclosure is shown. As shown in the figure, the method includes steps 1 to 4.

[0057] Step 1: Collect concentration data in the water environment through sensors carried by unmanned boats.

[0058] In this embodiment, concentration data from the water environment can be collected using sensors aboard an unmanned vessel. The vessel can be equipped with a high-frequency concentration sensor to record instantaneous concentration data in real time. Turbulence in the water environment causes concentration values ​​to fluctuate at high frequencies and irregularly over time and space. This concentration fluctuation can interfere with the inversion of the concentration gradient. Therefore, the sensor sampling frequency can be appropriately set, and experimental conditions such as water flow rate, turbulence intensity, and ambient temperature can be recorded.

[0059] During the acquisition process, the quality of concentration field data is affected by multiple factors, such as the sampling frequency, which affects the temporal resolution of the data; the trajectory of the unmanned vessel, which affects the spatial distribution of sampling points; and local water mixing, which interferes with the sampled concentration. To improve the quality of the sampled data, appropriate sampling frequencies can be selected based on the concentration variation characteristics, sampling density can be increased in areas with high concentration gradients, and key areas of the concentration field can be covered by sampling points with a reasonable spatial distribution.

[0060] The collected concentration data can be transmitted to the processing module via a real-time communication system. The sampling frequency and data transmission scheme match the calculation rate of the inversion model to ensure the real-time performance of the system.

[0061] Specifically, in some embodiments, a real-time monitoring-inversion communication model can be established. This model can comprehensively consider the sampling frequency and accuracy of sensors such as concentration, velocity, and position, and combine it with the calculation rate of the time-averaged concentration gradient rapid inversion model to specify an appropriate data transmission scheme. For key data such as concentration, velocity, and position, an initial data judgment can be performed to ensure the validity of the data. The initial judgment link can promptly detect and eliminate abnormal data, preventing invalid or erroneous data from affecting the learning effect of the PINN network, thereby improving the overall performance of the system. This real-time communication mechanism runs through the entire process of unmanned ship navigation, ensuring the continuity and reliability of data acquisition, transmission, and processing.

[0062] In one example, the initial judgment stage can screen the data through physical rationality checks, time series anomaly detection, spatial correlation verification, etc.

[0063] For example, it is possible to check whether the concentration value is within the sensor range, whether the concentration change rate exceeds the physically possible maximum value, whether the concentration difference between adjacent sampling points conforms to the diffusion law, etc.

[0064] For example, the moving average and standard deviation can be used to detect mutation points, and data points that exceed 3 times the standard deviation can be marked. Multiple consecutive abnormal points may indicate sensor failure, etc.

[0065] For example, the concentration correlation of nearby sampling points can be calculated, abnormal jumps in space can be detected, and the diffusion trend predicted by the hydrodynamic model can be verified.

[0066] Only when data meets all of the above criteria will it be considered qualified sampling data in the initial judgment phase and fed into the subsequent time-averaged concentration gradient rapid inversion model for PINN network learning and reasoning. This multi-dimensional data quality control can effectively improve overall navigation performance.

[0067] Step 2: Construct a time-averaged concentration gradient rapid inversion model. The time-averaged concentration gradient rapid inversion model includes a simple model that can be directly calculated based on the currently collected concentration data and a physical information neural network PINN model, and dynamically adjusts the weight ratio of the two models to process the collected concentration data to obtain the time-averaged concentration field of the water body.

[0068] The characteristics of unmanned ship concentration measurement, such as the non-fixed sampling points, short sampling time, and local mixing of water bodies, can be taken into consideration to analyze the incomplete statistical characteristics of the instantaneous changes in pollutant emissions in turbulent flow. Combined with deep learning technologies such as PINN, a hydrodynamic-water quality simulation method combining artificial intelligence and numerical simulation is explored to construct a rapid inversion model of time-averaged concentration gradient for unmanned ship concentration measurement.

[0069] The time-averaged concentration gradient rapid inversion model proposed in this embodiment adopts a strategy that combines a simple model and a PINN model. The simple model can use the interpolation method to estimate the concentration field of existing sampling point data. Optional interpolation methods include nearest neighbor interpolation, linear interpolation, or Kriging interpolation. The simple model has a fast calculation speed and can directly obtain preliminary results based on the currently collected concentration data. It is suitable for the early stage of tracing back with less sampling data. The PINN model is a physical information neural network based on deep learning technology. Its core principle is to use automatic differentiation technology to embed partial differential equations into the loss function of the neural network, and use the control equations of the hydrodynamic-water quality model as physical constraints in the training process. After accumulating enough sampling data, the PINN model can fully learn the distribution characteristics of the concentration field and meet the physical constraints. At this time, its prediction performance is usually better than the simple model.

[0070] By combining the inversion results of the two models and dynamically adjusting the weight ratio, a simple model can be used for rapid calculations when the number of sampling points is small, avoiding delays in tracing the source due to waiting for the PINN model to converge. As data accumulates, the PINN model contribution can be gradually improved through a weight adjustment mechanism, achieving a smooth transition from rapid response to high-precision calculations. Furthermore, the PINN model introduces physical constraints to ensure that the calculation results conform to hydrodynamic and water quality laws, improving the reliability of the inversion results. This time-averaged concentration gradient rapid inversion model not only meets the requirements of each stage of tracing the source, but also improves computational efficiency and inversion accuracy, making it well suited to the real-time navigation needs of unmanned vessels.

[0071] In some embodiments, the PINN model can adopt a feedforward fully connected neural network structure, including an input layer, a hidden layer, and an output layer. Each neuron undergoes a linear transformation using corresponding weights and biases, and then undergoes a nonlinear activation function. Considering the need to solve second-order partial derivatives, the Tanh activation function, which is infinitely differentiable, can be selected as the activation function. During model training, automatic differentiation (AD) technology can be used to calculate the derivative of the network output function with respect to the input variable. AD technology can avoid computational errors caused by grid-scale differential operations by decomposing complex analytical functions into a series of elementary operations, thereby improving computational accuracy.

[0072] In some embodiments, the PINN model uses the control equation of the hydrodynamic-water quality model as a physical constraint condition in the training process, and the loss function includes a data fitting term and a physical constraint term. The data fitting term is used to measure the deviation between the predicted concentration value and the observed concentration value of the observation data sampling point, and the physical constraint term is used to measure the fit between the predicted concentration value of the constraint sampling point and the physical law.

[0073] According to this embodiment, the PINN model introduces the governing equations of the hydrodynamic-water quality model as physical constraints during training. In some examples, the governing equations may include the one-dimensional Saint-Venant equations (the continuity equation and the momentum equation) describing water flow and the one-dimensional convection-diffusion equation describing solute transport.

[0074] The PINN model's loss function consists of a data fitting term and a physical constraint term. The data fitting term is calculated at the observation sampling points, and the model's prediction accuracy is evaluated by comparing the deviation between the predicted concentration value and the actual observed value (i.e., the collected concentration data). The physical constraint term is calculated at the preset constraint sampling points. At these points, actual concentration data is not collected. Instead, the model's predicted concentration values ​​at these points are substituted into the governing equations, and the residual value is calculated to assess the prediction's conformity to physical laws.

[0075] This design enables the PINN model to simultaneously learn the true concentration distribution characteristics and satisfy basic physical laws, improving the model's prediction accuracy and generalization capabilities. The division of labor between the two types of sampling points ensures that the model output is consistent with both actual observations and theoretical requirements.

[0076] In some examples, the data fitting term can be determined according to the following formula

[0077]

[0078] Among them, Θ is the PINN network parameter, x (i) is the spatial coordinate point of the observation data sampling point, is the number of observation data sampling points, For PINN network in x (i) The predicted concentration value at g(x (i) ) is in x (i) The concentration values ​​collected at It means to find the square of L2 norm.

[0079] is the time-averaged concentration value predicted by the neural network, g(x (i) ) is the actually observed instantaneous concentration value (including pulsation). Through the above data fitting term, the difference between the instantaneous concentration value and the time-averaged concentration value (i.e., the concentration pulsation) is treated as the observation error, which is beneficial to improving the inversion stability. The L2 norm can effectively measure the prediction deviation, which is convenient for optimization and derivation. Incorporating the data fitting term designed as above into the loss function can effectively learn the true concentration distribution characteristics.

[0080] In some examples, the physical constraint term L can be determined according to the following formula: Ω (Θ):

[0081]

[0082] Among them, N Ω is the number of sampling points under the constraint condition, x (i) is the spatial coordinate point of the constraint sampling point, v represents the physical parameter of the control equation used to establish the physical constraint, D(x (i) ; v) means x (i) Substitute the predicted concentration value at into the residual calculated by the control equation, It means to find the square of L2 norm.

[0083] According to the physical constraints designed above, the predicted concentration values ​​of the constraint sampling points are substituted into the control equation to calculate the residuals. The residuals represent the degree of conformity of the prediction results to the physical laws, and the L2 norm square is used to measure the size of the residuals, thereby ensuring that the prediction results follow the basic laws of the hydrodynamic-water quality model. In addition, the introduction of physical constraints through residual calculation can enhance the generalization ability of the model.

[0084] In some implementations, the distribution of constraint sampling points may be determined according to the following method:

[0085] A spatiotemporal concentration variation dataset is obtained by large eddy simulation (LES), wherein the dataset includes the flow velocity and concentration values ​​of each grid point in the flow field at different times;

[0086] Constraint sampling points are selected based on the spatiotemporal concentration variation dataset, wherein the constraint sampling points in areas with large flow velocity or concentration gradient variations are denser than those in areas with small flow velocity or concentration gradient variations.

[0087] According to this embodiment, a complete spatiotemporal concentration variation dataset can be first obtained through large eddy simulation (LES). This dataset records the concentration value and flow velocity information of each grid point in the calculation domain at different times, and can reflect the concentration distribution and flow characteristics in the flow field. Based on the dataset generated by LES, areas where physical quantities in the flow field change dramatically can be identified. Therefore, in areas where the flow velocity changes greatly or the concentration gradient is significant, denser constraint sampling points can be arranged to ensure that the prediction results of these key areas meet the physical constraints; and in areas where the physical quantities change slowly, the sampling point density can be appropriately reduced. This non-uniformly distributed sampling strategy helps to improve the prediction accuracy of the PINN model in complex flow fields.

[0088] In other examples, under complex flow conditions, the physical constraint term L Ω (Θ) can be obtained by substituting the predicted concentration values ​​at the constraint sampling points into the residuals calculated using large eddy simulation (LES). When the flow field is complex, it may be difficult to reliably calculate the physical constraints directly using the governing equations. In this case, large eddy simulation can be used to calculate the residuals as a measure of whether the predicted values ​​meet the physical laws. This can address the problem of insufficient governing equations in complex flow fields. LES can also more accurately simulate the physical characteristics of complex flow fields, ensuring the applicability of the PINN model under complex conditions.

[0089] In some embodiments, the outputs of the simple model and the PINN model may be combined according to the following formula:

[0090]

[0091] Among them, w simple +w PINN =1, is the final time-averaged concentration field output by the time-averaged concentration gradient fast inversion model, The calculation results of the simple model are: is the calculation result of PINN model, w simple for and w PINN is the weight coefficient.

[0092] In some embodiments, the number of sampling points can be increased. exist The weight ratio in, that is, increasing w PINN At the same time, w is reduced accordingly simple , thus achieving smooth switching and avoiding instability caused by sudden switching, while ensuring the inversion accuracy and continuity of the inversion results.

[0093] In some embodiments, the concentration gradient direction error and the concentration inversion error of the calculation result of the simple model can be calculated; if any one of the concentration gradient direction error and the concentration inversion error exceeds the corresponding preset threshold, then w is set simple =0,w PINN = 1. The concentration gradient directional error can be obtained by calculating the angle between the gradient direction obtained by the simplified model and the reference direction. The reference direction can be calculated from the measured data at adjacent moments. The concentration inversion error can be measured by calculating the root mean square error between the value calculated by the simplified model and the collected concentration data.

[0094] According to this embodiment, when any error exceeds a preset threshold, such as the concentration gradient directional error exceeding the concentration gradient directional error threshold and / or the concentration inversion error exceeding the concentration inversion error threshold, the simplified model's performance is considered to have significantly deteriorated. To prevent this from further affecting the results, the simplified model's weight coefficient can be set to zero, fully adopting the PINN model's output, which can further improve inversion performance.

[0095] Step 3: Determine the next desired navigation path based on the concentration gradient direction of the time-averaged concentration field obtained by inversion.

[0096] The concentration gradient direction can be calculated based on the time-averaged concentration field obtained through real-time inversion. This gradient direction can then be used to determine the desired navigation path, thereby guiding the unmanned vessel toward the direction of increasing concentration, gradually approaching the pollution source. Because the concentration field is time-averaged, this navigation method can avoid interference from instantaneous concentration fluctuations, improving the stability and reliability of source tracing.

[0097] In practical applications, other objectives can also be used to optimize the navigation path. For example, a more uniform sampling coverage of the target area can be considered to obtain more comprehensive concentration field data, improve the accuracy of the inversion results, and avoid misjudgments due to local high concentrations.

[0098] Step 4: Based on the expected navigation path and in combination with the motion characteristics of the unmanned boat and the water environment characteristics, the moving direction and speed of the unmanned boat are adjusted in real time.

[0099] The desired navigation path can be tracked by adjusting the moving direction and speed of the unmanned vessel.

[0100] In practical applications, the steering angle and acceleration can be adjusted appropriately based on the inertial characteristics of the unmanned vessel. Since unmanned vessels cannot suddenly change their motion state, their dynamic characteristics can be comprehensively considered when making turns or speed changes.

[0101] The course and speed can be adjusted according to the current water flow. The unmanned boat will be affected by the change of flow speed during movement, and the deviation caused by the water flow needs to be compensated in real time.

[0102] At the same time, sensors can be used to monitor the surrounding environment in real time, identify and avoid obstacles in the water, such as tree stumps and protruding stones, to ensure navigation safety.

[0103] The travel speed can also be reduced in areas with high concentration gradients. Areas with larger concentration gradients usually correspond to areas where pollutant diffusion is more significant, and the data in these areas are more critical for accurately locating pollution sources. Reducing the speed can obtain more sampling data points per unit distance, that is, collecting more concentration data, and the increase in sampling density helps the PINN model to more accurately invert the concentration field of the area, further providing more reliable gradient direction information to guide subsequent navigation. This speed control strategy improves the accuracy of tracing by obtaining more data in key areas. Those skilled in the art can judge whether the concentration gradient in a certain area has reached a high concentration gradient based on experience, real-time conditions and tasks.

[0104] The integrated control strategy based on the planned navigation path and comprehensive consideration of the unmanned ship's motion characteristics and environmental factors not only ensures the safety and reliability of navigation, but also improves the efficiency of sampling.

[0105] The concentration gradient-based autonomous navigation method for unmanned vessels in water environments proposed in this embodiment significantly improves the efficiency and reliability of source tracing. This embodiment uses a strategy that dynamically combines a simple model with the PINN model to quickly obtain preliminary estimates when sampled data is limited, avoiding delays in source tracing due to waiting for model convergence. As data increases, the method gradually transitions to the more accurate PINN model, achieving a seamless combination of rapid response and high accuracy.

[0106] The PINN model incorporates physical constraints into its design. By calculating residuals at constraint sampling points, the model ensures that predictions conform to hydrodynamic and water quality laws. Large eddy simulations are also used to optimize the distribution of constraint points, further improving prediction accuracy in complex flow fields. This physical constraint mechanism significantly enhances the model's generalization and predictive reliability.

[0107] In terms of navigation control, this embodiment determines the desired navigation path based on the concentration gradient and makes real-time adjustments based on the unmanned vessel's motion characteristics and the water environment. By employing strategies such as reducing speed and increasing sampling density in areas of high concentration gradients, this approach ensures both navigation safety and data collection efficiency. This multi-faceted navigation solution significantly improves the accuracy and efficiency of pollution source location.

[0108] Figure 2 A technical framework diagram according to an exemplary embodiment of the present disclosure is shown.

[0109] The blue module at the top of the figure shows the combination of the basic technical support modules - large eddy simulation (LES) and physical information neural network (PINN).

[0110] The middle section contains four main technical parts (marked with dotted boxes):

[0111] Highly sensitive water quality information collection system, including water quality sampling and detection functions;

[0112] Time-averaged concentration field inversion methods based on instantaneous measurement data, concentration field inversion under conditions where measurement points are available (e.g., using a simplified model), and rapid inversion correction methods as more monitoring point data is added (e.g., gradually switching to a PINN model). This involves planning the desired navigation path based on high-precision water quality concentration detection through a real-time monitoring-inversion communication model, resulting in direction and speed control.

[0113] The robot's autonomous navigation method based on concentration gradient integrates navigation planning and control, and autonomously plans a reasonable cruise route based on concentration gradient and inspection requirements. It also explores the accuracy of inspection traceability based on the OpenFOAM virtual simulation platform;

[0114] The scheme can be tested through indoor water pool experiments, autonomous navigation robot design and testing, and field water body testing.

[0115] like Figure 2 As shown at the bottom, the tested technical solutions can be applied to the intelligent monitoring and traceability of water environment.

[0116] The following combination Figure 3 The traceability line diagram shown is an example of the traceability process of an unmanned ship.

[0117] In the first step, the unmanned vessel is positioned at the starting point B and the monitoring system is activated. The concentration data at the current location is collected in real time through sensors, and after preliminary screening, the data is input into the time-averaged concentration gradient rapid inversion model.

[0118] In the second step, the inversion model dynamically adjusts the weight ratio of the simple model and the PINN model based on the current sampling data. In the initial sampling period, the interpolation results of the simple model are mainly relied on. As the data accumulates, the weight of the PINN model is gradually increased to obtain the time-averaged concentration field of the water body.

[0119] The third step is to calculate the concentration gradient direction based on the inverted time-averaged concentration field and determine the desired navigation path. The movement direction and speed are adjusted in real time based on the UAV's motion characteristics and the current water environment. During this process, the speed is reduced in areas of high concentration gradient to increase sampling density.

[0120] The fourth step is to continuously evaluate the concentration at the current location during sampling. If a local maximum is detected, it indicates proximity to the pollution source. Intensified sampling is then performed in this area to confirm the source's location. If the concentration at point B is the maximum value detected, point A can be inferred to be the likely location of the sewage outlet. Once confirmed, the patrol process is terminated, completing the source tracing mission.

[0121] The dynamic inversion and concentration gradient-based adaptive navigation strategy provided by the present disclosure can effectively improve the accuracy and efficiency of tracing.

[0122] The present disclosure also provides an autonomous navigation device for an unmanned vessel in a water environment based on a concentration gradient, comprising:

[0123] A real-time acquisition unit, used to collect concentration data in the water environment through sensors carried by unmanned vessels;

[0124] A model inversion unit is used to construct a time-averaged concentration gradient rapid inversion model, which includes a simple model that can be directly calculated based on the currently collected concentration data and a physical information neural network (PINN) model, and dynamically adjusts the weight ratio of the two models to process the collected concentration data to obtain the time-averaged concentration field of the water body;

[0125] A path determination unit is used to determine the next desired navigation path according to the concentration gradient direction of the time-averaged concentration field obtained by inversion;

[0126] The real-time navigation unit is used to adjust the moving direction and speed of the unmanned ship in real time based on the expected navigation path and in combination with the motion characteristics of the unmanned ship and the environmental characteristics.

[0127] For other details and advantages of this embodiment, please refer to the above description.

[0128] Figure 4 An electronic device provided for at least one embodiment of the present disclosure includes a memory and a processor, wherein the memory is used to store computer instructions that can be executed on the processor, and the processor is used to implement the concentration gradient-based water environment unmanned ship autonomous navigation method described in any embodiment or implementation method of the present disclosure when executing the computer instructions.

[0129] At least one embodiment of the present disclosure further provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the concentration gradient-based water environment unmanned ship autonomous navigation method described in any embodiment or implementation of the present disclosure.

[0130] Those skilled in the art will appreciate that one or more embodiments of this specification may be provided as a method, system, or computer program product. Thus, one or more embodiments of this specification may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware. Furthermore, one or more embodiments of this specification may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0131] The various embodiments in this specification are described in a progressive manner. Similar portions between the various embodiments can be referenced to each other. Each embodiment focuses on the differences between the other embodiments. In particular, the data processing device embodiment is generally similar to the method embodiment, so its description is relatively simple. For relevant portions, refer to the description of the method embodiment.

[0132] The foregoing description of this specification describes specific embodiments. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recited in the claims can be performed in an order different from that described in the embodiments and still achieve the desired results. Furthermore, the processes depicted in the accompanying drawings do not necessarily require the specific order shown or sequential order to achieve the desired results. In certain embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0133] Embodiments of the subject matter and functional operations described in this specification may be implemented in the following: digital electronic circuits, tangibly embodied computer software or firmware, computer hardware including the structures disclosed in this specification and their structural equivalents, or a combination of one or more of them. Embodiments of the subject matter described in this specification may be implemented as one or more computer programs, i.e., one or more modules of computer program instructions encoded on a tangible, non-transitory program carrier to be executed by a data processing device or to control the operation of the data processing device. Alternatively or additionally, the program instructions may be encoded on an artificially generated propagation signal, such as a machine-generated electrical, optical, or electromagnetic signal, which is generated to encode information and transmit it to a suitable receiver device for execution by the data processing device. The computer storage medium may be a machine-readable storage device, a machine-readable storage substrate, a random or serial access memory device, or a combination of one or more of them.

[0134] The processes and logic flows described in this specification can be performed by one or more programmable computers executing one or more computer programs to perform the corresponding functions by operating on input data and generating output. The processes and logic flows can also be performed by, and apparatus can be implemented as, special purpose logic circuitry, such as an FPGA (field programmable gate array) or an ASIC (application-specific integrated circuit).

[0135] Computers suitable for executing computer programs include, for example, general-purpose and / or special-purpose microprocessors, or any other type of central processing unit. Typically, the central processing unit will receive instructions and data from a read-only memory and / or random access memory. The basic components of a computer include a central processing unit for implementing or executing instructions and one or more memory devices for storing instructions and data. Typically, a computer will also include one or more mass storage devices for storing data, such as magnetic disks, magneto-optical disks, or optical disks, or the computer will be operably coupled to such mass storage devices to receive data from them or to transmit data to them, or both. However, a computer does not necessarily have such devices. In addition, a computer can be embedded in another device, such as a mobile phone, a personal digital assistant (PDA), a mobile audio or video player, a game console, a global positioning system (GPS) receiver, or a portable storage device such as a universal serial bus (USB) flash drive, to name a few.

[0136] Computer-readable media suitable for storing computer program instructions and data include all forms of non-volatile memory, media, and storage devices, including, for example, semiconductor memory devices (e.g., EPROM, EEPROM, and flash memory devices), magnetic disks (e.g., internal hard disks or removable disks), magneto-optical disks, and CD ROM and DVD-ROM disks. The processor and memory can be supplemented by, or incorporated in, special purpose logic circuitry.

[0137] Although this specification includes many specific implementation details, these should not be interpreted as limiting the scope of any invention or the scope of protection claimed, but are mainly used to describe the features of specific embodiments of specific inventions. Certain features described in multiple embodiments within this specification may also be implemented in combination in a single embodiment. On the other hand, the various features described in a single embodiment may also be implemented separately in multiple embodiments or in any suitable sub-combination. In addition, although features may work in certain combinations as described above and even initially claimed as such, one or more features from the claimed combination may be removed from the combination in some cases, and the claimed combination may point to a sub-combination or a variation of the sub-combination.

[0138] Similarly, although operations are depicted in a particular order in the accompanying drawings, this should not be understood as requiring that these operations be performed in the particular order shown or performed sequentially, or that all illustrated operations be performed to achieve the desired results. In some cases, multitasking and parallel processing may be advantageous. In addition, the separation of various system modules and components in the above-described embodiments should not be understood as requiring such separation in all embodiments, and it should be understood that the described program components and systems can generally be integrated together in a single software product, or packaged into multiple software products.

[0139] Thus, specific embodiments of the subject matter have been described. Other embodiments are within the scope of the following claims. In some cases, the actions recited in the claims can be performed in a different order and still achieve the desired results. Furthermore, the processes depicted in the accompanying drawings do not necessarily require the particular order shown or sequential sequence to achieve the desired results. In some implementations, multitasking and parallel processing may be advantageous.

[0140] The above description is merely a preferred embodiment of one or more embodiments of this specification and is not intended to limit one or more embodiments of this specification. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of one or more embodiments of this specification shall be included in the scope of protection of one or more embodiments of this specification.

Claims

1. A method for autonomous navigation of an unmanned vessel in a water environment based on concentration gradient, characterized in that: include: Collect concentration data in the water environment through sensors carried by unmanned vessels; A time-averaged concentration gradient rapid inversion model is constructed. The time-averaged concentration gradient rapid inversion model includes a simple model that can be directly calculated based on the currently collected concentration data and a physical information neural network PINN model, and the weight ratio of the two models is dynamically adjusted to process the collected concentration data to obtain the time-averaged concentration field of the water body. The PINN model uses the control equation of the hydrodynamic-water quality model as the physical constraint condition in the training process. The loss function includes a data fitting term and a physical constraint term. The data fitting term is used to measure the deviation between the predicted concentration value and the observed concentration value of the observation data sampling point, and the physical constraint term is used to measure the fit between the predicted concentration value of the constraint condition sampling point and the physical law. The data fitting term is determined according to the following formula : ， in, is the PINN network parameter, is the spatial coordinate point, is the number of observation data sampling points, For PINN network The predicted concentration value at For The concentration values ​​collected at Indicates the square of the L2 norm; and determines the physical constraint term according to the following formula : ， in, is the number of sampling points under the constraint condition, is the spatial coordinate point, represents the physical parameters of the governing equations used to establish physical constraints, Indicates that Substitute the predicted concentration value at into the residual calculated by the control equation, Indicates finding the square of the L2 norm; Determine the next desired navigation path based on the concentration gradient direction of the time-averaged concentration field obtained by inversion; Based on the expected navigation path, combined with the unmanned ship's motion characteristics and environmental characteristics, the moving direction and speed of the unmanned ship are adjusted in real time.

2. The method according to claim 1, characterized in that The method further comprises: A spatiotemporal concentration variation dataset is obtained by large eddy simulation, wherein the spatiotemporal concentration variation dataset includes flow velocity and concentration values ​​of each grid point in the flow field at different times; Constraint sampling points for the PINN model are selected based on the spatiotemporal concentration variation dataset, wherein the constraint sampling points in areas with large changes in flow velocity or concentration gradient are denser than those in areas with small changes in flow velocity or concentration gradient.

3. The method according to claim 1, characterized in that Under complex flow field conditions, the physical constraint term is obtained by substituting the predicted concentration value of the constraint condition sampling point into the large eddy simulation calculation residual.

4. The method according to claim 1, wherein The time-averaged concentration gradient rapid inversion model combines the outputs of the simple model and the PINN model according to the following formula: ， in, , is the final time-averaged concentration field output by the time-averaged concentration gradient fast inversion model, The calculation results of the simple model are: is the calculation result of PINN model, and is the weight coefficient.

5. The method according to claim 4, characterized in that Dynamically adjusting the weight ratio of the two models includes: Increased with the number of sampling points exist The weight ratio in .

6. The method according to claim 4, characterized in that Dynamically adjusting the weight ratio of the two models includes: Calculate the concentration gradient direction error and concentration inversion error of the calculation results of the simple model; If either the concentration gradient direction error or the concentration inversion error exceeds the corresponding preset threshold, then set , .

7. The method according to claim 1, characterized in that Real-time adjustment of the moving direction and speed of the unmanned vessel includes: Use sensors to monitor the surrounding environment in real time and identify and avoid obstacles in the water; Adjust the steering angle and acceleration according to the unmanned vessel's own inertia characteristics; Adjust course and speed according to current water conditions; Reduce travel speed in areas of high concentration gradient to increase sampling density.

8. An autonomous navigation device for an unmanned vessel in a water environment based on a concentration gradient, characterized in that: include: A real-time acquisition unit, used to collect concentration data in the water environment through sensors carried by unmanned vessels; A model inversion unit is used to construct a time-averaged concentration gradient rapid inversion model, wherein the time-averaged concentration gradient rapid inversion model includes a simple model that can be directly calculated based on the currently collected concentration data and a physical information neural network PINN model, and dynamically adjusts the weight ratio of the two models to process the collected concentration data to obtain the time-averaged concentration field of the water body, wherein the PINN model uses the control equation of the hydrodynamic-water quality model as the physical constraint condition in the training process, and the loss function includes a data fitting term and a physical constraint term, wherein the data fitting term is used to measure the deviation between the predicted concentration value and the observed concentration value of the observation data sampling point, and the physical constraint term is used to measure the fit between the predicted concentration value of the constraint condition sampling point and the physical law. The data fitting term is determined according to the following formula : ， in, is the PINN network parameter, is the spatial coordinate point, is the number of observation data sampling points, For PINN network The predicted concentration value at For The concentration values ​​collected at Indicates the square of the L2 norm; and determines the physical constraint term according to the following formula : ， in, is the number of sampling points under the constraint condition, is the spatial coordinate point, represents the physical parameters of the governing equations used to establish physical constraints, Indicates that Substitute the predicted concentration value at into the residual calculated by the control equation, Indicates finding the square of the L2 norm; A path determination unit is used to determine the next desired navigation path according to the concentration gradient direction of the time-averaged concentration field obtained by inversion; The real-time navigation unit is used to adjust the moving direction and speed of the unmanned ship in real time based on the expected navigation path and in combination with the motion characteristics of the unmanned ship and the environmental characteristics.

9. An electronic device, characterized in that: The device includes a memory and a processor, wherein the memory is used to store computer instructions that can be executed on the processor, and the processor is used to implement the method according to any one of claims 1 to 7 when executing the computer instructions.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the method according to any one of claims 1 to 7 is implemented.

Images