Inertial navigation dynamic alignment method, system and program product
By constructing environmental feature vectors and using BP neural network model for error compensation, and calibrating navigation attitude and velocity parameters with dynamic forgetting factors and error compensation factors, the problem of positioning error increasing with time in inertial navigation systems is solved, and high-precision navigation of underwater vehicles is achieved.
Patent Information
- Application Number
- CN202510998938.5
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-07-21
- Publication Date
- 2025-08-15
- Estimated Expiration
- Not applicable · inactive patent
AI Technical Summary
The existing inertial navigation systems have the problem that positioning errors increase over time in underwater vehicles, making it difficult to achieve effective correction.
By collecting inertial navigation parameters and sensing detection parameters of underwater vehicles, building environmental feature vectors, using the BP neural network model for error compensation, and calibrating navigation attitude and velocity parameters with dynamic forgetting factors and error compensation factors.
Effectively eliminate the accumulated error of the inertial navigation system over time, improve the inertial navigation accuracy of underwater vehicles, and provide more accurate and reliable deep-sea navigation information.
Smart Images
Figure CN120489183A_ABST
Abstract
Description
Technical Field
[0001] The present invention belongs to the technical field of inertial navigation, and in particular relates to an inertial navigation dynamic alignment method, system and program product. Background Art
[0002] Deep-sea vehicles play a vital role in research related to the detection and modeling of marine environments, underwater detection and identification of marine targets, and positioning and transmission. Due to their specialized mission requirements, deep-sea submersion requires extended periods of time, placing high demands on underwater navigation technology. Inertial navigation systems (INSs) are autonomous navigation systems based on Newtonian mechanics. They utilize inertial measurement units (IMUs) to capture the vehicle's acceleration and angular velocity data and, combined with initial motion conditions, calculate velocity and attitude in real time. INSs can provide effective displacement and attitude information even in the absence of satellite positioning signals.
[0003] Existing inertial navigation systems all use dead reckoning navigation during use, that is, the position of the next point is calculated from the position of a known point based on the continuously measured heading angle and velocity of the vehicle, so that the current position of the moving body can be continuously measured. The gyroscope in the inertial navigation system is used to form a navigation coordinate system to stabilize the measuring axis of the accelerometer in the coordinate system and provide the heading and attitude angles. The accelerometer is used to measure the acceleration of the moving body, and the velocity is obtained by integrating it once over time. The velocity is then integrated over time to obtain the distance. However, since the navigation information of the pure inertial navigation system is generated through integration, its positioning error will increase over time. Therefore, how to timely and effectively align and correct the positioning error of the inertial navigation system of the underwater vehicle has become an urgent problem that needs to be solved. Summary of the Invention
[0004] The purpose of the present invention is to provide an inertial navigation dynamic alignment method, system and program product to solve the above problems existing in the prior art.
[0005] In order to achieve the above object, the present invention adopts the following technical solutions: In a first aspect, a method for dynamic alignment of inertial navigation is provided, comprising: Collecting inertial navigation parameters and sensor detection parameters of the underwater vehicle at the current moment, the inertial navigation parameters include angular velocity parameters and acceleration parameters, and the sensor detection parameters include water temperature parameters, water pressure parameters and depth detection parameters; determining a motion intensity of the underwater vehicle at a current moment based on the angular velocity parameter and the acceleration parameter, and determining a dynamic forgetting factor based on the motion intensity of the underwater vehicle at the current moment; The environmental feature vector is constructed using the water temperature parameter, water pressure parameter, depth detection parameter and time parameter of the underwater vehicle at the current moment; Input the environmental feature vector into the preset environmental error compensation model to perform error prediction and obtain the error compensation factor at the current moment; Calculate the current navigation attitude parameter and navigation speed parameter using the current angular velocity parameter and acceleration parameter; The dynamic forgetting factor and the error compensation factor are used to calibrate the navigation attitude parameters and navigation speed parameters at the current moment to obtain the aligned navigation attitude parameters and navigation speed parameters; The aligned navigation attitude parameters and navigation speed parameters are output to perform inertial navigation of the underwater vehicle.
[0006] In one possible design, determining the motion intensity of the underwater vehicle at the current moment based on the angular velocity parameter and the acceleration parameter includes: Substitute the angular velocity parameter and the acceleration parameter into the preset motion index formula to calculate and obtain the motion index. The motion index formula is:
[0007] Among them, S represents the motion index, ω represents the angular velocity parameter, A represents the acceleration parameter, α is the set angular velocity coefficient, and β is the set acceleration coefficient; The motion index is substituted into a preset motion intensity table for matching to determine the corresponding motion intensity. The motion intensity table includes several motion index intervals and the motion intensity corresponding to each motion index interval.
[0008] In one possible design, determining the dynamic forgetting factor based on the motion intensity of the underwater vehicle at the current moment includes: Substitute the current motion intensity of the underwater vehicle into the preset dynamic forgetting factor formula to calculate and obtain the corresponding dynamic forgetting factor. The dynamic forgetting factor formula is:
[0009] Among them, λ is the dynamic forgetting factor, λ m is the preset minimum value of the dynamic forgetting factor, Z is the intensity of exercise, and Z m It is the preset motion intensity threshold.
[0010] In one possible design, the construction of the environmental feature vector using the current water temperature parameter, water pressure parameter, depth detection parameter of the underwater vehicle and the current time parameter includes: The water temperature parameter T(i), water pressure parameter P(i), depth detection parameter D(i) of the underwater vehicle at the current moment and the time parameter t(i) at the current moment are summarized in sequence as the components of each environmental feature vector to obtain the environmental feature vector X=[T(i), P(i), D(i), t(i)].
[0011] In one possible design, before inputting the environmental feature vector into a preset environmental error compensation model for error prediction, the method further includes: A BP neural network model is constructed and trained using a preset error compensation training set to obtain an environmental error compensation model. The error compensation training set includes a number of environmental feature vector samples labeled with corresponding error compensation factor labels.
[0012] In one possible design, the calculation of the navigation attitude parameter and the navigation speed parameter at the current moment using the angular velocity parameter and the acceleration parameter at the current moment includes: Substitute the current angular velocity parameter into the preset navigation attitude parameter formula to calculate and obtain the current navigation attitude parameter. The navigation attitude parameter formula is:
[0013] Among them, θ t（i） Characterizes the navigation attitude parameter at the current moment, θ t（i-1） Characterizes the navigation attitude parameter of the previous moment, ω t（i） Represents the angular velocity parameter at the current moment, t represents the time parameter, t(i) represents the time parameter at the current moment, and t(i-1) represents the time parameter at the previous moment; Substitute the current acceleration parameter into the preset navigation speed parameter formula to calculate and obtain the current navigation speed parameter. The navigation speed parameter formula is:
[0014] Among them, V t（i） Characterizes the current navigation speed parameter, V t（i-1） Characterizes the sailing speed parameter at the previous moment, A t（i） Represents the acceleration parameter at the current moment, t represents the time parameter, t(i) represents the time parameter at the current moment, and t(i-1) represents the time parameter at the previous moment.
[0015] In one possible design, the use of the dynamic forgetting factor and the error compensation factor to calibrate the current navigation attitude parameters and navigation speed parameters to obtain aligned navigation attitude parameters and navigation speed parameters includes: The dynamic forgetting factor and error compensation factor are used to calibrate the navigation attitude parameters at the current moment to obtain the aligned navigation attitude parameters θ' t（i） =λμθ t（i） , where λ is the dynamic forgetting factor and μ is the error compensation factor; The dynamic forgetting factor and error compensation factor are used to calibrate the current navigation speed parameter to obtain the aligned navigation speed parameter V' t（i） =λμV t（i） , where λ is the dynamic forgetting factor and μ is the error compensation factor.
[0016] In a second aspect, an inertial navigation dynamic alignment system is provided, comprising a data acquisition unit, a dynamic determination unit, a vector construction unit, an error compensation unit, a parameter calculation unit, a parameter calibration unit, and an inertial navigation output unit, wherein: A data acquisition unit, configured to acquire inertial navigation parameters and sensor detection parameters of the underwater vehicle at the current moment, wherein the inertial navigation parameters include angular velocity parameters and acceleration parameters, and the sensor detection parameters include water temperature parameters, water pressure parameters, and depth detection parameters; a dynamic determination unit, configured to determine the motion intensity of the underwater vehicle at a current moment based on the angular velocity parameter and the acceleration parameter, and to determine a dynamic forgetting factor based on the motion intensity of the underwater vehicle at a current moment; A vector construction unit, configured to construct an environmental feature vector using the water temperature parameter, water pressure parameter, depth detection parameter, and time parameter of the underwater vehicle at the current moment; An error compensation unit is used to input the environmental feature vector into a preset environmental error compensation model to perform error prediction and obtain an error compensation factor at the current moment; A parameter calculation unit, configured to calculate a current navigation attitude parameter and a current navigation speed parameter using the current angular velocity parameter and the current acceleration parameter; A parameter calibration unit is used to calibrate the current navigation attitude parameters and navigation speed parameters using a dynamic forgetting factor and an error compensation factor to obtain aligned navigation attitude parameters and navigation speed parameters; The inertial navigation output unit is used to output the aligned navigation attitude parameters and navigation speed parameters for inertial navigation of the underwater vehicle.
[0017] In a third aspect, an inertial navigation dynamic alignment system is provided, comprising: a memory for storing instructions; A processor is used to read the instructions stored in the memory and execute the inertial navigation dynamic alignment method described in any one of the first aspects according to the instructions.
[0018] In a fourth aspect, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores instructions that, when executed on a computer, cause the computer to execute any one of the inertial navigation dynamic alignment methods described in the first aspect. Also provided is a computer program product that, when executed on a computer, executes any one of the inertial navigation dynamic alignment methods described in the first aspect.
[0019] Beneficial effects: The present invention collects the inertial navigation parameters and sensor detection parameters of the underwater vehicle in real time, then uses the sensor detection parameters to construct an environmental feature vector for error analysis, determines the error compensation factor, uses the inertial navigation parameters to perform motion intensity analysis to determine the dynamic forgetting factor, and uses the inertial navigation parameters to calculate the navigation attitude parameters and navigation speed parameters, and then uses the dynamic forgetting factor and the error compensation factor to calibrate the navigation attitude parameters and navigation speed parameters. Finally, the calibrated navigation attitude parameters and navigation speed parameters are used for deep-sea inertial navigation of the underwater vehicle, which can effectively improve the inertial navigation accuracy of the underwater vehicle. The present invention can eliminate the errors that gradually accumulate over time in traditional inertial navigation systems, realize dynamic inertial navigation parameter calibration, and integrate multi-source environmental detection data to provide more comprehensive environmental perception and decision support for dynamic inertial navigation calibration, and ultimately obtain more accurate and reliable deep-sea inertial navigation information. BRIEF DESCRIPTION OF THE DRAWINGS
[0020] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, 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. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.
[0021] Figure 1 Schematic diagram of the steps of the method in Example 1 of the present invention; Figure 2 Schematic diagram of the system structure in Example 2 of the present invention; Figure 3 This is a schematic diagram of the system structure in Example 3 of the present invention. DETAILED DESCRIPTION
[0022] It should be noted that the description of these embodiments is intended to help understand the present invention, but does not constitute a limitation of the present invention. The specific structural and functional details disclosed herein are merely intended to describe exemplary embodiments of the present invention. However, the present invention may be embodied in a variety of alternative forms, and should not be construed as being limited to the embodiments set forth herein.
[0023] It should be understood that, unless otherwise expressly specified or limited, the corresponding terms should be understood in a broad sense. For example, "connection" can refer to a fixed connection, a detachable connection, or an integral connection; it can refer to a direct connection, an indirect connection through an intermediate medium, or internal communication between two components. Those skilled in the art will understand the specific meanings of the above terms in the embodiments based on specific circumstances.
[0024] In the following description, certain details are provided to facilitate a thorough understanding of the example embodiments. However, one skilled in the art will appreciate that the example embodiments may be practiced without these specific details. For example, devices may be shown in block diagrams to avoid obscuring the examples with unnecessary detail. In other embodiments, well-known processes, structures, and techniques may be shown without unnecessary detail to avoid obscuring the embodiments.
[0025] Example 1: This embodiment provides an inertial navigation dynamic alignment method, which can be applied to corresponding deep-sea navigation systems, such as Figure 1 As shown, the method includes the following steps: S1. Collect inertial navigation parameters and sensor detection parameters of the underwater vehicle at the current moment, wherein the inertial navigation parameters include angular velocity parameters and acceleration parameters, and the sensor detection parameters include water temperature parameters, water pressure parameters, and depth detection parameters.
[0026] In a specific implementation, the current inertial navigation parameters can be collected from the underwater vehicle's inertial navigation system. The inertial navigation parameters include angular velocity parameters and acceleration parameters. The angular velocity parameters and acceleration parameters can be obtained by correcting the initial angular velocity and initial acceleration parameters output by the inertial navigation system after gyroscope bias correction and accelerometer bias correction. Simultaneously, the current sensor detection parameters can be collected from the underwater vehicle's corresponding sensors and detection equipment. The sensor detection parameters include water temperature parameters, water pressure parameters, and depth detection parameters. The water temperature parameter can be detected by a temperature sensor installed on the underwater vehicle, the water pressure parameter can be detected by a pressure sensor installed on the underwater vehicle, and the depth detection parameter can be detected by the underwater vehicle's sonar detection system.
[0027] S2. Determine the motion intensity of the underwater vehicle at the current moment based on the angular velocity parameter and the acceleration parameter, and determine a dynamic forgetting factor based on the motion intensity of the underwater vehicle at the current moment.
[0028] In specific implementation, the angular velocity parameter and the acceleration parameter can be substituted into a preset motion index formula to calculate and obtain the motion index. The motion index formula is:
[0029] Among them, S represents the motion index, ω represents the angular velocity parameter, A represents the acceleration parameter, α is the set angular velocity coefficient, and β is the set acceleration coefficient; The motion index is then substituted into a preset motion intensity table for matching to determine the corresponding motion intensity. The motion intensity table includes several motion index intervals and the motion intensity corresponding to each motion index interval.
[0030] Then, the motion intensity of the underwater vehicle at the current moment is substituted into the preset dynamic forgetting factor formula to calculate the corresponding dynamic forgetting factor. The dynamic forgetting factor formula is:
[0031] Among them, λ is the dynamic forgetting factor, λ m is the preset minimum value of the dynamic forgetting factor, Z is the intensity of exercise, and Z m It is the preset motion intensity threshold.
[0032] S3. Construct an environmental feature vector using the water temperature parameter, water pressure parameter, depth detection parameter of the underwater vehicle at the current moment and the time parameter at the current moment.
[0033] In the specific implementation, the water temperature parameter T(i), water pressure parameter P(i), depth detection parameter D(i) of the underwater vehicle at the current moment and the time parameter t(i) at the current moment are summarized in sequence as the components of each environmental feature vector to obtain the environmental feature vector X=[T(i), P(i), D(i), t(i)], where i represents the moment number of the current moment.
[0034] S4. Input the environmental feature vector into a preset environmental error compensation model to perform error prediction and obtain the error compensation factor at the current moment.
[0035] In practice, the system can pre-build a BP neural network model and train it using a preset error compensation training set to obtain an environmental error compensation model. The error compensation training set contains a number of environmental feature vector samples labeled with corresponding error compensation factors. The environmental feature vectors are then input into the preset environmental error compensation model for error prediction, resulting in the current error compensation factor.
[0036] S5. Calculate the navigation attitude parameter and navigation speed parameter at the current moment using the angular velocity parameter and acceleration parameter at the current moment.
[0037] In specific implementation, the angular velocity parameter at the current moment can be substituted into the preset navigation attitude parameter formula for calculation to obtain the navigation attitude parameter at the current moment. The navigation attitude parameter formula is:
[0038] Among them, θ t（i） Characterizes the navigation attitude parameter at the current moment, θ t（i-1） Characterizes the navigation attitude parameter of the previous moment, ω t（i） Represents the angular velocity parameter at the current moment, t represents the time parameter, t(i) represents the time parameter at the current moment, and t(i-1) represents the time parameter at the previous moment; At the same time, the acceleration parameter at the current moment is substituted into the preset navigation speed parameter formula to calculate the navigation speed parameter at the current moment. The navigation speed parameter formula is:
[0039] Among them, V t（i） Characterizes the current navigation speed parameter, V t（i-1） Characterizes the sailing speed parameter at the previous moment, A t（i） Represents the acceleration parameter at the current moment, t represents the time parameter, t(i) represents the time parameter at the current moment, and t(i-1) represents the time parameter at the previous moment.
[0040] S6. Use the dynamic forgetting factor and the error compensation factor to calibrate the navigation attitude parameters and navigation speed parameters at the current moment to obtain the aligned navigation attitude parameters and navigation speed parameters.
[0041] In specific implementation, after calculating the current navigation attitude parameters and navigation speed parameters, the dynamic forgetting factor and error compensation factor can be used to calibrate the current navigation attitude parameters to obtain the aligned navigation attitude parameters θ' t（i） =λμθ t（i） , where λ is the dynamic forgetting factor and μ is the error compensation factor. At the same time, the dynamic forgetting factor and the error compensation factor are used to calibrate the current navigation speed parameter to obtain the aligned navigation speed parameter V' t（i） =λμV t（i） , where λ is the dynamic forgetting factor and μ is the error compensation factor.
[0042] S7. Output the aligned navigation attitude parameters and navigation speed parameters to perform inertial navigation of the underwater vehicle.
[0043] In specific implementation, after obtaining the aligned navigation attitude parameters and navigation speed parameters, the aligned navigation attitude parameters and navigation speed parameters can be output for inertial navigation of the underwater vehicle to improve the inertial navigation accuracy of the underwater vehicle.
[0044] This method can eliminate the errors that gradually accumulate over time in traditional inertial navigation systems, realize dynamic inertial navigation parameter calibration, and integrate multi-source environmental detection data to provide more comprehensive environmental perception and decision support for dynamic inertial navigation calibration, ultimately obtaining more accurate and reliable deep-sea inertial navigation information.
[0045] Example 2: This embodiment provides an inertial navigation dynamic alignment system, such as Figure 2 As shown, it includes a data acquisition unit, a dynamic determination unit, a vector construction unit, an error compensation unit, a parameter calculation unit, a parameter calibration unit and an inertial navigation output unit, wherein: A data acquisition unit, configured to acquire inertial navigation parameters and sensor detection parameters of the underwater vehicle at the current moment, wherein the inertial navigation parameters include angular velocity parameters and acceleration parameters, and the sensor detection parameters include water temperature parameters, water pressure parameters, and depth detection parameters; a dynamic determination unit, configured to determine the motion intensity of the underwater vehicle at a current moment based on the angular velocity parameter and the acceleration parameter, and to determine a dynamic forgetting factor based on the motion intensity of the underwater vehicle at a current moment; A vector construction unit, configured to construct an environmental feature vector using the water temperature parameter, water pressure parameter, depth detection parameter, and time parameter of the underwater vehicle at the current moment; An error compensation unit is used to input the environmental feature vector into a preset environmental error compensation model to perform error prediction and obtain an error compensation factor at the current moment; A parameter calculation unit, configured to calculate a current navigation attitude parameter and a current navigation speed parameter using the current angular velocity parameter and the current acceleration parameter; A parameter calibration unit is used to calibrate the current navigation attitude parameters and navigation speed parameters using a dynamic forgetting factor and an error compensation factor to obtain aligned navigation attitude parameters and navigation speed parameters; The inertial navigation output unit is used to output the aligned navigation attitude parameters and navigation speed parameters for inertial navigation of the underwater vehicle.
[0046] Example 3: This embodiment provides an inertial navigation dynamic alignment system, such as Figure 3 As shown, at the hardware level, it includes: Data interface, used to establish data connection between the processor and the external data terminal; a memory for storing instructions; The processor is used to read the instructions stored in the memory and execute the inertial navigation dynamic alignment method in Example 1 according to the instructions.
[0047] Optionally, the system further includes an internal bus, through which the processor, memory, and data interface can be interconnected. The internal bus may be a PCIe (Peripheral Component Interconnect Eexpress) bus, which may be divided into an address bus, a data bus, a control bus, etc. The memory may include, but is not limited to, random access memory (RAM), read-only memory (ROM), flash memory, first-in first-out (FIFO), and / or first-in last-out (FILO). The processor may be a general-purpose processor, including a central processing unit (CPU) or a network processor (NP); it may also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components.
[0048] Example 4: This embodiment provides a computer-readable storage medium having instructions stored thereon. When the instructions are executed on a computer, the computer is caused to execute the inertial navigation dynamic alignment method of Embodiment 1. The computer-readable storage medium refers to a data storage medium, which may include, but is not limited to, a floppy disk, an optical disk, a hard disk, a flash memory, a USB flash drive, and / or a memory stick. The computer may be a general-purpose computer, a dedicated computer, a computer network, or other programmable device.
[0049] This embodiment further provides a computer program product, which, when executed on a computer, executes the inertial navigation dynamic alignment method of embodiment 1. The computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices.
[0050] Finally, it should be noted that the above description is only a preferred embodiment of the present invention and is not intended to limit the scope of protection of the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention shall be included in the scope of protection of the present invention.
Claims
1. A dynamic alignment method for inertial navigation, characterized in that: include: Collecting inertial navigation parameters and sensor detection parameters of the underwater vehicle at the current moment, the inertial navigation parameters include angular velocity parameters and acceleration parameters, and the sensor detection parameters include water temperature parameters, water pressure parameters and depth detection parameters; determining a motion intensity of the underwater vehicle at a current moment based on the angular velocity parameter and the acceleration parameter, and determining a dynamic forgetting factor based on the motion intensity of the underwater vehicle at the current moment; The environmental feature vector is constructed using the water temperature parameter, water pressure parameter, depth detection parameter and time parameter of the underwater vehicle at the current moment; Input the environmental feature vector into the preset environmental error compensation model to perform error prediction and obtain the error compensation factor at the current moment; Calculate the current navigation attitude parameter and navigation speed parameter using the current angular velocity parameter and acceleration parameter; The dynamic forgetting factor and the error compensation factor are used to calibrate the navigation attitude parameters and navigation speed parameters at the current moment to obtain the aligned navigation attitude parameters and navigation speed parameters; The aligned navigation attitude parameters and navigation speed parameters are output to perform inertial navigation of the underwater vehicle.
2. The inertial navigation dynamic alignment method according to claim 1, characterized in that: The determining of the motion intensity of the underwater vehicle at the current moment based on the angular velocity parameter and the acceleration parameter includes: Substitute the angular velocity parameter and the acceleration parameter into the preset motion index formula to calculate and obtain the motion index. The motion index formula is: Among them, S represents the motion index, ω represents the angular velocity parameter, A represents the acceleration parameter, α is the set angular velocity coefficient, and β is the set acceleration coefficient; The motion index is substituted into a preset motion intensity table for matching to determine the corresponding motion intensity. The motion intensity table includes several motion index intervals and the motion intensity corresponding to each motion index interval.
3. The inertial navigation dynamic alignment method according to claim 1, characterized in that: The determining of the dynamic forgetting factor based on the motion intensity of the underwater vehicle at the current moment includes: Substitute the current motion intensity of the underwater vehicle into the preset dynamic forgetting factor formula to calculate and obtain the corresponding dynamic forgetting factor. The dynamic forgetting factor formula is: Among them, λ is the dynamic forgetting factor, λ m is the preset minimum value of the dynamic forgetting factor, Z is the intensity of exercise, and Z m It is the preset motion intensity threshold.
4. The inertial navigation dynamic alignment method according to claim 1, characterized in that: The method of constructing an environmental feature vector using the water temperature parameter, water pressure parameter, depth detection parameter, and time parameter of the underwater vehicle at the current moment includes: The water temperature parameter T(i), water pressure parameter P(i), depth detection parameter D(i) of the underwater vehicle at the current moment and the time parameter t(i) at the current moment are summarized in sequence as the components of each environmental feature vector to obtain the environmental feature vector X=[T(i), P(i), D(i), t(i)].
5. The inertial navigation dynamic alignment method according to claim 1, characterized in that: Before inputting the environmental feature vector into a preset environmental error compensation model for error prediction, the method further includes: A BP neural network model is constructed and trained using a preset error compensation training set to obtain an environmental error compensation model. The error compensation training set includes a number of environmental feature vector samples labeled with corresponding error compensation factor labels.
6. The inertial navigation dynamic alignment method according to claim 1, characterized in that: The method of calculating the navigation attitude parameter and the navigation speed parameter at the current moment by using the angular velocity parameter and the acceleration parameter at the current moment includes: Substitute the current angular velocity parameter into the preset navigation attitude parameter formula to calculate and obtain the current navigation attitude parameter. The navigation attitude parameter formula is: Among them, θ t（i） Characterizes the navigation attitude parameter at the current moment, θ t（i-1） Characterizes the navigation attitude parameter of the previous moment, ω t（i） Represents the angular velocity parameter at the current moment, t represents the time parameter, t(i) represents the time parameter at the current moment, and t(i-1) represents the time parameter at the previous moment; Substitute the current acceleration parameter into the preset navigation speed parameter formula to calculate and obtain the current navigation speed parameter. The navigation speed parameter formula is: Among them, V t（i） Characterizes the current navigation speed parameter, V t（i-1） Characterizes the sailing speed parameter at the previous moment, A t（i） Represents the acceleration parameter at the current moment, t represents the time parameter, t(i) represents the time parameter at the current moment, and t(i-1) represents the time parameter at the previous moment.
7. The inertial navigation dynamic alignment method according to claim 6, characterized in that: The method of calibrating the navigation attitude parameters and navigation speed parameters at the current moment by using the dynamic forgetting factor and the error compensation factor to obtain the aligned navigation attitude parameters and navigation speed parameters includes: The dynamic forgetting factor and error compensation factor are used to calibrate the navigation attitude parameters at the current moment to obtain the aligned navigation attitude parameters θ' t（i） =λμθ t（i） , where λ is the dynamic forgetting factor and μ is the error compensation factor; The dynamic forgetting factor and error compensation factor are used to calibrate the current navigation speed parameter to obtain the aligned navigation speed parameter V' t（i） =λμV t（i） , where λ is the dynamic forgetting factor and μ is the error compensation factor.
8. An inertial navigation dynamic alignment system, characterized in that: It includes a data acquisition unit, a dynamic determination unit, a vector construction unit, an error compensation unit, a parameter calculation unit, a parameter calibration unit and an inertial navigation output unit, wherein: A data acquisition unit, configured to acquire inertial navigation parameters and sensor detection parameters of the underwater vehicle at the current moment, wherein the inertial navigation parameters include angular velocity parameters and acceleration parameters, and the sensor detection parameters include water temperature parameters, water pressure parameters, and depth detection parameters; a dynamic determination unit, configured to determine the motion intensity of the underwater vehicle at a current moment based on the angular velocity parameter and the acceleration parameter, and to determine a dynamic forgetting factor based on the motion intensity of the underwater vehicle at a current moment; A vector construction unit, configured to construct an environmental feature vector using the water temperature parameter, water pressure parameter, depth detection parameter, and time parameter of the underwater vehicle at the current moment; An error compensation unit is used to input the environmental feature vector into a preset environmental error compensation model to perform error prediction and obtain an error compensation factor at the current moment; A parameter calculation unit, configured to calculate a current navigation attitude parameter and a current navigation speed parameter using the current angular velocity parameter and the current acceleration parameter; A parameter calibration unit is used to calibrate the current navigation attitude parameters and navigation speed parameters using a dynamic forgetting factor and an error compensation factor to obtain aligned navigation attitude parameters and navigation speed parameters; The inertial navigation output unit is used to output the aligned navigation attitude parameters and navigation speed parameters for inertial navigation of the underwater vehicle.
9. An inertial navigation dynamic alignment system, characterized in that: include: a memory for storing instructions; A processor is used to read the instructions stored in the memory and execute the inertial navigation dynamic alignment method according to any one of claims 1 to 7 according to the instructions.
10. A computer program product, characterized in that When the computer program product is run on a computer, the inertial navigation dynamic alignment method according to any one of claims 1 to 7 is executed.