A method for compensating calibration coefficient error of inertial navigation system for guided projectiles

Abstract

The present invention provides a method for compensating scale coefficient errors of an inertial navigation system for guided projectiles, comprising the steps of collecting gyro and summing table outputs of the inertial navigation system for guided projectiles, preprocessing the gyro and summing table outputs to obtain inertial navigation angular velocity errors and acceleration errors; performing feature extraction based on the inertial navigation angular velocity errors and acceleration errors, setting model training inputs and model training outputs; performing model training using an RNN model based on the model training inputs and outputs to obtain a scale coefficient error training model; obtaining, based on the scale coefficient error training model, a real-time predicted output of an IMU scale coefficient error based on the gyro angular velocity and acceleration output by the inertial navigation system in real time, and completing scale coefficient error compensation for the inertial navigation system for guided projectiles based on the real-time predicted output of the IMU scale coefficient error. The present invention can solve the technical problem in the prior art of insufficient navigation measurement accuracy caused by using traditional scale coefficient error estimation methods.

Description

Technical Field

[0001] The present invention relates to the technical field of guided projectile navigation, and in particular to a method for compensating a calibration coefficient error of an inertial navigation system for a guided projectile. Background Art

[0002] Traditional artillery-launched ammunition strikes its target via free fall, resulting in a low hit rate, significant ammunition consumption, and a short range, resulting in a low cost-effectiveness ratio. Guided munitions offer advantages over conventional ammunition, including greater precision, longer range, and flexible deployment. Compared to missiles, guided munitions boast a large payload, rapid launch speed, and low operational costs. They can strike both point and surface targets, offering a wider range of applications and greater flexibility. This is particularly true as naval vessels are increasingly deployed to strike land targets, provide fire support for beach landings, and counter terrorist, maritime, and asymmetric threats. The use of guided munitions offers a higher cost-effectiveness ratio.

[0003] Guided munitions will play a crucial role in future high-tech warfare. Currently, countries around the world have successfully developed or are currently developing a variety of guided munitions using different guidance methods. From a guidance perspective, micro-inertial / GPS combined guidance systems offer broad application potential. The advantages of inertial navigation systems are autonomy and stealth. Micro-inertial navigation systems offer not only small size, light weight, ease of maintenance, and high reliability, but also direct access to a greater number of carrier linear and angular motion parameters and are less susceptible to external interference. However, MEMS devices suffer from poor measurement accuracy and are easily affected by the external environment. Scale factor errors are particularly significant under high-overload, high-dynamic, and high-rotation conditions, directly impacting navigation measurement accuracy. Therefore, to achieve precise guidance of guided projectiles, estimating and compensating for scale factor errors in inertial navigation systems is crucial.

[0004] Traditional scale factor error estimation methods use an error model based on mechanical motion characteristics to perform estimation and compensation. However, under high rotation and high overload conditions, these traditional error models struggle to accurately describe the dynamic process, leading to inaccurate error estimation and, in turn, affecting navigation accuracy. Therefore, a more accurate scale factor error estimation and compensation method suitable for guided projectiles is needed to improve navigation measurement accuracy. Summary of the Invention

[0005] The present invention aims to solve at least one of the technical problems existing in the prior art.

[0006] The present invention provides a method for compensating a scale coefficient error of an inertial navigation system for a guided projectile. The method comprises the following steps: collecting gyro and summing table outputs of the inertial navigation system for the guided projectile, and pre-processing the gyro and summing table outputs to obtain an inertial navigation angular velocity error and an acceleration error; performing feature extraction based on the inertial navigation angular velocity error and the acceleration error, and setting a model training input and a model training output; performing model training using an RNN model based on the model training input and the model training output to obtain a scale coefficient error training model; and based on the scale coefficient error training model, obtaining an IMU scale coefficient error predicted and output in real time according to the gyro angular velocity and acceleration output by the inertial navigation system in real time, and completing scale coefficient error compensation for the inertial navigation system for the guided projectile according to the predicted and output IMU scale coefficient error.

[0007] Further, according to Get the inertial navigation angular velocity error, where represents the gyro scale coefficient error, Indicates that the turntable is set to the speed Zω i , position Df k and temperature T j When , the angular velocity measured by the inertial navigation at time t; Indicates that the turntable is set to the speed Zω i , position Df k and temperature T j When t is the angular velocity reference value measured by the turntable, i = 1, 2, 3, ... m; k = 1, 2, 3, ... n; j = 1, 2, 3, ... p; m, n and p are all integers.

[0008] Further, according to Get the inertial acceleration error, where Indicates the error of the scale coefficient of the meter. Indicates that the turntable is set to the speed Zω i , position Df k and temperature T j When , the acceleration measured by the inertial navigation at time t; Indicates that the turntable is set to the speed Zω i , position Df k and temperature T j The acceleration reference value measured by the turntable at time t is i = 1, 2, 3, ...m; k = 1, 2, 3, ...n; j = 1, 2, 3, ...p; m, n and p are all integers.

[0009] Furthermore, set the model training input to Among them, X IN Input for model training, Indicates that the turntable is set to the speed Zω i , position Dfk and temperature T j When , the angular velocity measured by the inertial navigation at time t; Indicates that the turntable is set to the speed Zω i , position Df k and temperature T j When , the acceleration measured by the inertial navigation at time t; Indicates that the turntable is set to the speed Zω i , position Df k and temperature T j When t, the temperature value measured by the gyro at time t; Indicates that the turntable is set to the speed Zω i , position Df k and temperature T j When t, add the temperature value measured by the meter.

[0010] Furthermore, set the model training output to Among them, Y OUT is the model training output, represents the gyro scale coefficient error, Indicates the error of the scale factor.

[0011] Furthermore, the loss function of the scale factor error training model is Among them, Y OUT is the model output, Y pred is the predicted value during model training, a=m×n×p×t all , t all is the total measurement time, m, n, and p are the number of acquisitions of the rotation speed, position, and temperature of the turntable incubator, respectively.

[0012] Further, according to and Perform error compensation, where is the angular velocity at time t measured in real time by the inertial navigation system; is the acceleration at time t measured in real time by the inertial navigation system; is the angular velocity after compensation for the scale factor error; is the acceleration after compensation for the scale factor error, is the gyro scale coefficient error at time t obtained by the inertial navigation real-time measurement based on the scale coefficient error training model, is the scale coefficient error of the inertial navigation real-time measurement at time t obtained based on the scale coefficient error training model.

[0013] The technical solution of the present invention provides a method for compensating for scale coefficient errors in an inertial navigation system for guided artillery shells. The method preprocesses the collected gyroscope and summing table outputs of the inertial navigation system for guided artillery shells to obtain the inertial navigation angular velocity error and acceleration error, performs RNN (deep learning recurrent neural network) model training to obtain a scale coefficient error training model, and performs real-time online estimation and compensation of the scale coefficient error based on the scale coefficient error training model, effectively improving navigation measurement accuracy. Compared with the prior art, the technical solution of the present invention can solve the technical problem that traditional scale coefficient error estimation methods in the prior art cannot accurately describe the dynamic process of guided artillery shells, resulting in insufficient navigation measurement accuracy. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] The accompanying drawings are included to provide a further understanding of the embodiments of the present invention, constitute a part of the specification, illustrate the embodiments of the present invention, and together with the description, explain the principles of the present invention. Obviously, the drawings described below are only some embodiments of the present invention, and those skilled in the art can derive other drawings based on these drawings without inventive effort.

[0015] Figure 1 The figure shows a flow chart of a method for compensating calibration coefficient errors of an inertial navigation system for guided projectiles according to a specific embodiment of the present invention. DETAILED DESCRIPTION

[0016] It should be noted that, in the absence of conflict, the embodiments in this application and the features in the embodiments can be combined with each other. The technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. The following description of at least one exemplary embodiment is actually only illustrative and is in no way intended to limit the present invention and its application or use. Based on the embodiments in the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.

[0017] It should be noted that the terms used herein are only for describing specific embodiments and are not intended to limit the exemplary embodiments according to the present application. As used herein, unless the context clearly indicates otherwise, the singular form is also intended to include the plural form. In addition, it should be understood that when the terms "comprise" and / or "include" are used in this specification, they indicate the presence of features, steps, operations, devices, components and / or combinations thereof.

[0018] Unless otherwise specifically stated, the relative arrangement of the parts and steps, numerical expressions and numerical values ​​set forth in these embodiments do not limit the scope of the present invention. At the same time, it should be understood that, for ease of description, the sizes of the various parts shown in the accompanying drawings are not drawn according to actual proportional relationships. The technology, methods and equipment known to those of ordinary skill in the relevant art may not be discussed in detail, but in appropriate cases, the technology, methods and equipment should be considered as a part of the specification. In all examples shown and discussed here, any specific value should be interpreted as being merely exemplary, rather than as a limitation. Therefore, other examples of the exemplary embodiments can have different values. It should be noted that similar numbers and letters represent similar items in the following drawings, and therefore, once an item is defined in an accompanying drawing, it does not need to be further discussed in subsequent drawings.

[0019] like Figure 1 As shown, according to a specific embodiment of the present invention, a method for compensating for a calibration coefficient error of an inertial navigation system for a guided projectile is provided. The method for compensating for a calibration coefficient error of an inertial navigation system for a guided projectile includes:

[0020] Collect the gyro and adder table outputs of the inertial navigation system used to guide artillery shells, and pre-process the gyro and adder table outputs to obtain the inertial navigation angular velocity error and acceleration error;

[0021] Extract features based on inertial navigation angular velocity error and acceleration error, and set model training input and output;

[0022] According to the model training input and model training output, the RNN model is used to train the model and obtain the scale coefficient error training model;

[0023] Based on the scale coefficient error training model, the real-time predicted output of the IMU scale coefficient error is obtained according to the gyro angular velocity and acceleration measured in real time by the inertial navigation system. The scale coefficient error compensation of the inertial navigation system for guided artillery shells is completed according to the real-time predicted output of the IMU scale coefficient error.

[0024] By applying this configuration, a method for compensating the scale coefficient error of an inertial navigation system for guided artillery shells is provided. The method preprocesses the collected gyroscope and summing table outputs of the inertial navigation system for guided artillery shells to obtain the inertial navigation angular velocity error and acceleration error, performs RNN model training to obtain a scale coefficient error training model, and performs real-time online estimation and compensation of the scale coefficient error based on the scale coefficient error training model, effectively improving the navigation measurement accuracy.

[0025] Furthermore, in the present invention, in order to realize the estimation of the scale coefficient error of the inertial navigation system for guided artillery shells, the gyro and summing table outputs of the inertial navigation system for guided artillery shells are first collected, and the gyro and summing table outputs are preprocessed to obtain the inertial navigation angular velocity error and acceleration error.

[0026] As a specific embodiment of the present invention, the rotation speed Zω of the turntable incubator is set i , position Df k and temperature T j , where i = 1, 2, 3, ... m; k = 1, 2, 3, ... n; j = 1, 2, 3, ... p; m, n and p are all integers; collect the angular velocity of the inertial navigation system at various speeds, positions and temperatures and acceleration in, Indicates the turntable speed Zω i , position Df k and temperature T j When , the angular velocity output by the inertial navigation is, Indicates the turntable speed Zω i , position Df k and temperature T j The acceleration output by the inertial navigation system when .

[0027] The inertial navigation angular velocity error and acceleration error are obtained according to the collected angular velocity and acceleration. Specifically, according to Get the inertial angular velocity error according to Get the inertial acceleration error, where represents the gyro scale coefficient error, Indicates the error of the scale factor of the added table; Indicates that the turntable is set to the speed Zω i , position Df k and temperature T j When , the angular velocity measured by the inertial navigation at time t; Indicates that the turntable is set to the speed Zω i , position Df k and temperature T j t is the angular velocity reference value measured by the turntable at time t; Indicates that the turntable is set to the speed Zω i , position Df k and temperature T j When , the acceleration measured by the inertial navigation at time t; Indicates that the turntable is set to the speed Zω i , position Df k and temperature T j The acceleration reference value measured by the turntable at time t.

[0028] Furthermore, in the present invention, after pre-processing the gyro and the table output to obtain the inertial navigation angular velocity error and the acceleration error, feature extraction is performed based on the inertial navigation angular velocity error and the acceleration error, and the model training input and output are set.

[0029] As a specific embodiment of the present invention, the model training input is set to The model output is Among them, X IN Y is the model training input, OUT is the model training output, Indicates that the turntable is set to the speed Zω i , position Df k and temperature T j When t, the temperature value measured by the gyro at time t; Indicates that the turntable is set to the speed Zω i , position Df k and temperature T j When t, add the temperature value measured by the meter.

[0030] Furthermore, in the present invention, after completing the setting of the model training input and output, the RNN model is used to perform model training according to the model training input and output to obtain the scale coefficient error training model.

[0031] As a specific embodiment of the present invention, the loss function of the scale factor error training model is set to Among them, Y pred is the predicted value during model training, a=m×n×p×t all , t all To measure the total time.

[0032] This embodiment uses a squared loss function. Furthermore, the number of epochs for model training can be set. After the number of epochs is met, the scale factor error training model is obtained as F(r1, r2, r3…rs), where r1, r2, r3…rs are the parameters obtained from the training, and s is an integer.

[0033] Furthermore, in the present invention, after completing the model training, based on the scale coefficient error training model, the real-time predicted output IMU scale coefficient error is obtained according to the gyro angular velocity and acceleration measured and output by the inertial navigation system in real time, and the scale coefficient error compensation of the inertial navigation system for guided artillery shells is completed according to the real-time predicted output IMU scale coefficient error.

[0034] As a specific embodiment of the present invention, the trained scale factor error training model F(r1, r2, r3…rs) is imported into the inertial navigation application software for application, and the gyro angular velocity and acceleration output by the inertial navigation system in real time are used as the input value of the scale factor error training model, and the real-time prediction output is in, is the gyro scale coefficient error of the inertial navigation real-time measurement at time t, is the scale coefficient error of the inertial navigation real-time measurement at time t.

[0035] Further, according to the real-time prediction output Y pred To compensate for the error, specifically, and Perform error compensation, where is the angular velocity at time t measured in real time by the inertial navigation system; is the acceleration at time t measured in real time by the inertial navigation system; is the angular velocity after compensation for the scale factor error; is the acceleration after compensation for the scale factor error.

[0036] The scale coefficient error compensation method for the inertial navigation system for guided artillery shells of the present invention adopts a deep learning intelligent algorithm to collect gyro-addition table outputs at different speeds and temperatures. Based on all the collected data, model training is performed to obtain a scale coefficient error training model, thereby realizing real-time online estimation and compensation of the scale coefficient error, effectively improving the navigation measurement accuracy.

[0037] In order to have a further understanding of the present invention, the following Figure 1 The calibration coefficient error compensation method of the inertial navigation system for guided projectiles of the present invention is described in detail.

[0038] like Figure 1 As shown, according to a specific embodiment of the present invention, a method for compensating the calibration coefficient error of an inertial navigation system for guided projectiles is provided, which specifically includes the following steps.

[0039] Step 1: Set the rotation speed Zω of the turntable incubator i , position Df k and temperature T j ;

[0040] Collect the angular velocity of the inertial navigation system at various speeds, positions and temperatures and acceleration

[0041] according to Get the inertial angular velocity error according to Get the inertial navigation acceleration error.

[0042] Step 2: Extract features based on inertial angular velocity error and acceleration error, and set the model training input to The model training output is

[0043] Step 3: Use the RNN model to train the model based on the model training input and output, and set the loss function of the RNN model to Get the scale coefficient error training model F(r1, r2, r3…rs).

[0044] Step 4: Import the trained scale coefficient error training model F(r1, r2, r3…rs) into the inertial navigation application software for application, and use the gyro angular velocity and acceleration measured and output by the inertial navigation system in real time as the model input value, and predict the output in real time.

[0045] according to and Perform error compensation.

[0046] In summary, the present invention provides a method for compensating for a scale coefficient error of an inertial navigation system for a guided artillery projectile. The method preprocesses the collected gyroscope and addition table outputs of the inertial navigation system for a guided artillery projectile to obtain an inertial navigation angular velocity error and an acceleration error, performs RNN model training to obtain a scale coefficient error training model, and performs real-time online estimation and compensation of the scale coefficient error based on the scale coefficient error training model, thereby effectively improving navigation measurement accuracy.

[0047] The foregoing description is merely a preferred embodiment of the present invention and is not intended to limit the present invention. Those skilled in the art will readily appreciate that various modifications and variations of the present invention are possible. Any modifications, equivalent substitutions, or improvements made within the spirit and principles of the present invention are intended to be within the scope of protection of the present invention.

Claims

1. A method for compensating calibration coefficient error of an inertial navigation system for guided projectiles, characterized in that: The method for compensating the calibration coefficient error of the inertial navigation system for guided projectiles comprises: Gyro and table outputs of the inertial navigation system for guided projectiles are collected, and the gyro and table outputs are preprocessed to obtain inertial navigation angular velocity error and acceleration error; specifically according to Get the inertial navigation angular velocity error, where represents the gyro scale coefficient error, Indicates that the turntable is set to the speed Zω i , position Df k and temperature T j When , the angular velocity measured by the inertial navigation at time t; Indicates that the turntable is set to the speed Zω i , position Df k and temperature T j The angular velocity reference value measured by the turntable at time t, i = 1, 2, 3, ... m; k = 1, 2, 3, ... n; j = 1, 2, 3, ... p; m, n and p are all integers, and m, n, p are the number of samples collected of the rotation speed, position and temperature of the turntable incubator respectively; Perform feature extraction based on the inertial navigation angular velocity error and acceleration error, and set model training input and model training output; Perform model training using an RNN model according to the model training input and the model training output to obtain a scale coefficient error training model; Based on the scale coefficient error training model, the real-time predicted output IMU scale coefficient error is obtained according to the gyro angular velocity and acceleration measured and output by the inertial navigation system in real time. The scale coefficient error compensation of the inertial navigation system for guided artillery shells is completed according to the real-time predicted output IMU scale coefficient error. and Perform error compensation, where is the angular velocity at time t measured in real time by the inertial navigation system; is the acceleration at time t measured in real time by the inertial navigation system; is the angular velocity after compensation for the scale factor error; is the acceleration after compensation for the scale factor error, is the gyro scale coefficient error of the inertial navigation real-time measurement at time t obtained based on the scale coefficient error training model, It is the scale coefficient error of the inertial navigation real-time measurement at time t obtained based on the scale coefficient error training model.

2. The method for compensating the calibration coefficient error of an inertial navigation system for guided projectiles according to claim 1, wherein: according to Get the inertial acceleration error, where Indicates the error of the scale coefficient of the meter. Indicates that the turntable is set to the speed Zω i , position Df k and temperature T j When , the acceleration measured by the inertial navigation at time t; Indicates that the turntable is set to the speed Zω i , position Df k and temperature T j The acceleration reference value measured by the turntable at time t.

3. The method for compensating the calibration coefficient error of an inertial navigation system for guided projectiles according to claim 1, wherein: Set the model training input to Among them, X IN Provide input for model training; Indicates that the turntable is set to the speed Zω i , position Df k and temperature T j When , the acceleration measured by the inertial navigation at time t; Indicates that the turntable is set to the speed Zω i , position Df k and temperature T j When t, the temperature value measured by the gyro at time t; Indicates that the turntable is set to the speed Zω i , position Df k and temperature T j When t, add the temperature value measured by the meter.

4. The method for compensating the calibration coefficient error of an inertial navigation system for guided projectiles according to claim 1, wherein: Set the model training output to Among them, Y OUT is the model training output, represents the gyro scale coefficient error, Indicates the error of the scale factor.

5. The method for compensating the calibration coefficient error of an inertial navigation system for guided projectiles according to claim 1, wherein: The loss function of the scale factor error training model is Among them, Y OUT is the model output, Y pred is the predicted value during model training, a=m×n×p×t all , t all To measure the total time.

Images