CN116147617B - Fault positioning and recovering method for underwater SINS/DVL/PS tightly-integrated navigation system - Google Patents
Fault positioning and recovering method for underwater SINS/DVL/PS tightly-integrated navigation system Download PDFInfo
- Publication number
- CN116147617B CN116147617B CN202211709717.4A CN202211709717A CN116147617B CN 116147617 B CN116147617 B CN 116147617B CN 202211709717 A CN202211709717 A CN 202211709717A CN 116147617 B CN116147617 B CN 116147617B
- Authority
- CN
- China
- Prior art keywords
- navigation system
- fault
- lstm
- dvl
- sins
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 49
- 238000013528 artificial neural network Methods 0.000 claims abstract description 46
- 238000012549 training Methods 0.000 claims abstract description 41
- 238000003062 neural network model Methods 0.000 claims abstract description 18
- 238000011084 recovery Methods 0.000 claims abstract description 10
- 238000005259 measurement Methods 0.000 claims description 57
- 239000011159 matrix material Substances 0.000 claims description 27
- 230000015654 memory Effects 0.000 claims description 10
- 230000006870 function Effects 0.000 claims description 9
- 238000004422 calculation algorithm Methods 0.000 claims description 8
- 238000001914 filtration Methods 0.000 claims description 8
- 230000008569 process Effects 0.000 claims description 8
- 230000007246 mechanism Effects 0.000 claims description 6
- 238000013508 migration Methods 0.000 claims description 6
- 230000005012 migration Effects 0.000 claims description 6
- 210000002569 neuron Anatomy 0.000 claims description 6
- 230000007704 transition Effects 0.000 claims description 6
- 101000802640 Homo sapiens Lactosylceramide 4-alpha-galactosyltransferase Proteins 0.000 claims description 3
- 102100035838 Lactosylceramide 4-alpha-galactosyltransferase Human genes 0.000 claims description 3
- 230000004913 activation Effects 0.000 claims description 3
- 238000004364 calculation method Methods 0.000 claims description 3
- 238000002474 experimental method Methods 0.000 claims description 3
- 230000004927 fusion Effects 0.000 claims description 3
- 230000007787 long-term memory Effects 0.000 claims description 3
- 238000007500 overflow downdraw method Methods 0.000 claims description 3
- 238000003745 diagnosis Methods 0.000 description 6
- 238000001514 detection method Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000005295 random walk Methods 0.000 description 2
- 238000004088 simulation Methods 0.000 description 2
- ORILYTVJVMAKLC-UHFFFAOYSA-N Adamantane Natural products C1C(C2)CC3CC1CC2C3 ORILYTVJVMAKLC-UHFFFAOYSA-N 0.000 description 1
- 230000008034 disappearance Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 230000008092 positive effect Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 238000013526 transfer learning Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
- G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
- G01C21/10—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 by using measurements of speed or acceleration
- G01C21/12—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 by using measurements of speed or acceleration executed aboard the object being navigated; Dead reckoning
- G01C21/16—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 by using measurements of speed or acceleration executed aboard the object being navigated; Dead reckoning by integrating acceleration or speed, i.e. inertial navigation
- G01C21/165—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 by using measurements of speed or acceleration executed aboard the object being navigated; Dead reckoning by integrating acceleration or speed, i.e. inertial navigation combined with non-inertial navigation instruments
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
- G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
- G01C21/20—Instruments for performing navigational calculations
Landscapes
- Engineering & Computer Science (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Automation & Control Theory (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Navigation (AREA)
Abstract
The invention discloses a fault locating and recovering method for an underwater SINS/DVL/PS tightly combined navigation system, which comprises the following steps: s1, constructing a system virtual model with the same principle as that of target experimental equipment, and generating a virtual training set; s2, training an LSTM neural network by using a virtual training set to obtain a pre-training model LSTM-1; s3, collecting a small amount of SINS/DVL/PS tightly-integrated navigation system experimental data to obtain an experimental training set, and migrating LSTM-1 to an experimental application scene to obtain a final neural network model LSTM-2; s4, the LSTM-2 neural network enters a classification mode, and the LSTM-2 neural network model outputs the position of fault occurrence at the current moment according to real-time fault statistics; s5, according to the fault positioning result, corresponding fault recovery measures are automatically adopted. By adopting the fault locating and recovering method, common faults such as gradual faults and the like can be rapidly diagnosed and located under the condition of a small amount of experimental data, corresponding fault recovering strategies can be automatically carried out, and the reliability of the integrated navigation system is improved.
Description
Technical Field
The invention relates to the technical field of navigation system fault diagnosis, in particular to a fault positioning and recovering method for an underwater SINS/DVL/PS tightly combined navigation system.
Background
The navigation system with high precision and high reliability is a necessary condition for successfully completing tasks of an autonomous underwater vehicle, and a common underwater navigation system is a Strapdown Inertial Navigation System (SINS)/Doppler log (DVL)/Pressure Sensor (PS) combined navigation system. Under the interference of the underwater complex environment, the DVL and PS sensors possibly fail at any time due to the dependence on the environment information, so that the error divergence of the positioning result of the navigation system is caused, and the operation of the autonomous underwater vehicle is further influenced. Under the condition, a user needs a set of fault diagnosis technology for the underwater integrated navigation system, and the occurrence and disappearance of faults of the DVL and PS navigation sensors can be detected in real time.
Abrupt and gradual faults are common faults in navigation systems, wherein gradual faults are the faults which are the most difficult to diagnose, and aiming at the fault diagnosis problem of gradual faults of navigation sensors, students use the strong nonlinear fitting capability and classification capability of a neural network to study. The specific idea is to fit navigation data for fault diagnosis by using a neural network or divide the navigation data into fault categories directly by using the neural network, for example, in a patent document with the patent application number of CN202010380332.2 and the name of an INS/GPS combined navigation fault detection and diagnosis method based on an integrated neural network, the integrated neural network is used as a classification decision function to detect faults of a navigation system; as another example, in the patent document with the patent application number CN201910953487.8 and entitled "a fault diagnosis method of integrated navigation system based on SVR", a fault detection function is constructed by using the fitting capability of SVR, but the above method requires a large amount of navigation experimental data support to train a high-performance neural network model, and the above method does not have a fault positioning function inside a sensor.
Disclosure of Invention
The invention aims to provide a fault locating and recovering method for an underwater SINS/DVL/PS tightly combined navigation system, which can rapidly diagnose and locate common faults such as gradual faults and the like under a small amount of experimental data conditions, automatically carry out corresponding fault recovering strategies according to fault locating results and improve the reliability of the combined navigation system.
In order to achieve the above purpose, the present invention provides a fault locating and recovering method for an underwater SINS/DVL/PS tightly combined navigation system, comprising the following steps:
s1, constructing a set of SINS/DVL/PS tightly-combined navigation system virtual model with the same principle as that of target experimental equipment, and generating a virtual training set by using the virtual model;
s2, building an LSTM neural network, and training the LSTM neural network by utilizing a virtual training set to obtain a pre-training model LSTM-1;
s3, acquiring a small amount of SINS/DVL/PS tightly-integrated navigation system experimental data by using a real ship experiment, obtaining an experimental training set based on the real ship experimental data by using the same method as the step S1, and pre-training a model based on a migration learning mechanism: and migrating the LSTM-1 to an experimental application scene to obtain a final LSTM neural network model: LSTM-2;
s4, enabling the SINS/DVL/PS tightly-combined navigation system to enter a working process, enabling the LSTM-2 neural network to enter a classification mode, and enabling the LSTM-2 neural network model to output the fault occurrence position at the current moment according to real-time fault statistics;
s5, according to a fault positioning result output by the LSTM-2 neural network model, the SINS/DVL/PS tightly combined navigation system automatically takes corresponding fault recovery measures, and effective fusion of SINS/DVL/PS information is realized by using a Kalman filter.
Further, in the step S1, the method for setting the virtual model of the SINS/DVL/PS tightly combined navigation system includes:
acquiring a state equation and a measurement equation of the tightly combined navigation system, wherein the state equation is as follows: x (k) =phi (k, k-1) X (k-1) +w (k-1) derives from the error equation of the inertial navigation system, where X (k) is the state quantity of the navigation system at time k,wherein [ phi ] e ,φ n ,φ u ]For the attitude angle error of the navigation system in the northeast direction, [ δv ] e ,δv n ,δv u ]For speed error of navigation system in northeast direction, [ delta L, delta lambda, delta h]For position error of longitude and latitude altitude of navigation system, [ epsilon ] x ,ε y ,ε z ]Is the three-axis zero offset of the gyroscope, +.>For the triaxial zero offset of the accelerometer, δK is the scale factor error of the Doppler velocimeter, phi (K, K-1) represents the state transition matrix of the system from K-1 time to K time, the state transition matrix is obtained by the error equation of the inertial navigation system, and W is the system noise; measurement equation: z (k) =h (k) X (k) +v (k), the measurement in the measurement equation is constructed from the real measurement of the earth speed of the four beams of DVL, the depth measured by the PS sensor, and the corresponding values solved by the inertial navigation system: />Wherein Z is the measurement of the navigation system, +.>Representing the projected component of the velocity of the inertial navigation solution in the direction of the ith beam of the doppler sensor, HSINS representing the altitude measurement of the inertial navigation system, a +.>Representing the speed measurement result of the ith wave beam of the Doppler sensor, wherein HPS represents the height measurement result of the depth gauge, H (k) is a measurement matrix at k moment, and V is measurement noise;
the information fusion method applied by the SINS/DVL/PS tightly-integrated navigation system is a Kalman filtering algorithm, and comprises time updating and parameter updating, and is shown as the formula:
P(k,k-1)＝φ(k,k-1)P(k-1)φ(k,k-1) T +Q(k-1)
K(k)＝P(k,k-1)H(k) T (H(k)·P(k,k-1)H(k) T +R(k)) -1
P(k)＝(I-K(k)H(k))P(k,k-1)
wherein,update value for the state from moment k-1 to moment k,/>For the state estimation value at time K-1, P (K, K-1) is the updated value of the covariance matrix from time K-1 to time K, P (K) is the covariance matrix at time K, Q (K) is the system noise matrix at time K, R (K) is the system measurement noise matrix at time K, and K (K) is the gain matrix at time K.
Further, the method for generating the virtual training set in the step S1 is as follows:
according to the state equation, measurement equation and Kalman filtering algorithm of the SINS/DVL/PS tightly combined navigation system of experimental equipment, a set of SINS/DVL/PS tightly combined navigation system virtual model with the same principle is constructed, and at different moments, the SINS/DVL/PS tightly combined navigation system virtual model is respectively constructedAdding faults to each beam and depth meter of the Doppler velocimeter of the virtual model:H PS * ＝H PS +f, where x represents the added fault state, f represents the fault artificially added to a different location, the fault location comprising: a certain beam of the DVL, a plurality of beams of the DVL and a depth gauge, and recording the occurrence time and the occurrence position of faults;
the residual quantity at the moment k can be obtained by iteration of Kalman filtering:the normalized residual amount is r (k)' =a (k) -1/2 r (k), wherein A (k) is a variance matrix of time k residual errors, the normalized residual quantity is set as navigation statistics reflecting fault positions, a normalized residual sequence generated by a Kalman filter and with a fixed time length is stored as a sample, the fault position at the last time is stored as a label of the sample, and a virtual training set is generated.
Further, the LSTM neural network in the step S2 is composed of an input layer, a long-short-period memory layer, a full-connection layer, a softmax layer and an output layer; the long-term memory layer comprises 128 LSTM units, forgetting gates, input gates and output gates of the LSTM units control the flow of information in the network, and a specific calculation formula is as follows:
i t ＝σ(U i h t-1 +W i x t +b i )
f t ＝σ(U f h t-1 +W f x t +b f )
o t ＝σ(U o h t-1 +W o x t +b o )
c t ＝f t ⊙c t-1 +i t ⊙tanh(U c h t-1 +W c x t +b c )
h t ＝o t ⊙tanh(c t )
wherein the subscript t represents the time t, i, f and o represent an input gate, a forgetting gate and an output gate respectively, c, h are the states of neurons and the outputs of the neurons respectively, U, W and b are parameters obtained by training a network, tanh is an activation function, and sigma is a sigmoid function;
the specific mode of generating the pre-training model LSTM-1 is that the normalized residual sequence in the virtual training set generated in the step S1 is used as the input quantity of the LSTM neural network: x is X input ＝[r(k-l+1)',r(k-l+2)',...,r(k)']The fault location at the current time k is used as a label of the network: y is Y output And training the LSTM neural network to obtain a pre-training model LSTM-1, and storing the pre-training model for later use.
Further, the specific process of migrating the pre-training model to the experimental application scenario based on the migration learning mechanism in step S3 is as follows:
the method comprises the steps of reserving a pre-training model, namely, a long-period memory layer in an LSTM-1 neural network, resetting a full-connection layer of the LSTM-1, setting a small learning rate for the long-period memory layer, setting a large learning rate for the full-connection layer, and transferring the modified neural network to an experimental scene by using a small amount of experimental data, namely, taking a normalized residual sequence with a fixed length generated by the experimental data as input of the modified neural network, taking the fault position at the last moment as output of the neural network, and training the modified neural network to obtain a final LSTM-2 neural network model.
Further, in the step S4, in the operation engineering of the SINS/DVL/PS tightly-integrated navigation system, the classification mode operation process of the LSTM-2 neural network is as follows: calculating normalized residual statistics r (k)' generated by a Kalman filter, storing the statistics with a fixed time step l, and generating time sequence data X corresponding to k moment input ＝[r(k-l+1)',r(k-l+2)',...,r(k)']At this time, the trained LSTM-2 neural network model in the step S3 enters a classification mode, time series data is input into the model, and the model outputs a fault positioning result.
Further, the fault recovery measures in the step S5 are as follows: when the fault positioning result in the step S4 is no fault, continuing to fuse the navigation model information according to the default in the step S1; when it isThe obstacle positioning result is the inherent relation of four beam measurement according to the Doppler velocimeter when a certain beam of the Doppler velocimeter fails:the remaining three beam quantity measurements are used to replace the fault beam quantity, beam 1 being taken as an example: />The measurement equation for this case is as follows: />When a plurality of beams fail, the Doppler velocimeter is isolated, and the measurement equation of the situation is as follows: z= [ H ] SINS -H PS ]=hx+v, only the measurement information of the depth gauge is fused in the integrated navigation system; when the depth gauge fails, the depth gauge is isolated, and the measurement equation of the situation is as follows:only the measurement information of the Doppler velocimeter is fused in the integrated navigation system.
The fault locating and recovering method for the underwater SINS/DVL/PS tightly combined navigation system has the advantages and positive effects that:
1. compared with the traditional neural network algorithm, the intelligent fault positioning method based on the transfer learning and long-short-period memory neural network can learn the characteristics of time sequence data with longer time interval and shorter time interval at the same time, and is suitable for processing navigation data with time correlation.
2. According to the method, the normalized residual sequence is used as the input of the intelligent fault positioning module, the fault position is used as the output of the module, and the migration learning mechanism is introduced, so that the method can assist in training the model by utilizing virtual data which can be obtained infinitely under the condition that the sample size is insufficient for training the model alone, the model can successfully finish tasks, the problem that experimental data is difficult to obtain is solved, and the method has a certain engineering application value.
3. The invention further increases the fault recovery module in the next step of the fault positioning module, adopts corresponding fault recovery measures according to the fault positioning result, and improves the fault tolerance performance of the system.
The technical scheme of the invention is further described in detail through the drawings and the embodiments.
Drawings
FIG. 1 is a flow chart of an embodiment of a fault locating and recovering method for an underwater SINS/DVL/PS tightly integrated navigation system of the present invention;
FIG. 2 is a block diagram of a navigation system with fault location and fault tolerance module for an embodiment of a fault location and recovery method for an underwater SINS/DVL/PS tightly integrated navigation system according to the present invention;
FIG. 3 is a velocity error plot of an embodiment of a fault locating and recovering method for an underwater SINS/DVL/PS tightly integrated navigation system according to the present invention.
Detailed Description
The technical scheme of the invention is further described below through the attached drawings and the embodiments.
Examples
Fig. 1 is a flowchart of an embodiment of a fault location and recovery method for an underwater SINS/DVL/PS tight integrated navigation system according to the present invention, and fig. 2 is a block diagram of a navigation system with a fault location and fault tolerance module according to an embodiment of a fault location and recovery method for an underwater SINS/DVL/PS tight integrated navigation system according to the present invention. As shown in the drawing, the liquid crystal display device,
a fault locating and recovering method for an underwater SINS/DVL/PS tightly-integrated navigation system comprises the following steps:
s1, constructing a set of SINS/DVL/PS tightly-combined navigation system virtual model with the same principle as that of target experimental equipment, artificially adding faults into the virtual model, and collecting a sample set as a virtual training set.
The SINS/DVL/PS tightly-integrated navigation system virtual model setting method comprises the following steps:
acquiring a state equation and a measurement equation of the tightly combined navigation system, wherein the state equation is as follows: x (k) =φ (k, k-1) X (k-1)+W (k-1) is derived from the error equation of the inertial navigation system, where X (k) is the state quantity of the navigation system at time k,wherein [ phi ] e ,φ n ,φ u ]For the attitude angle error of the navigation system in the northeast direction, [ δv ] e ,δv n ,δv u ]For speed error of navigation system in northeast direction, [ delta L, delta lambda, delta h]For position error of longitude and latitude altitude of navigation system, [ epsilon ] x ,ε y ,ε z ]Is the three-axis zero offset of the gyroscope, +.>For the triaxial zero offset of the accelerometer, δK is the scale factor error of the Doppler velocimeter, phi (K, K-1) represents the state transition matrix of the system from K-1 time to K time, the state transition matrix is obtained by the error equation of the inertial navigation system, and W is the system noise. Measurement equation: z (k) =h (k) X (k) +v (k), the measurement in the measurement equation is constructed from the real measurement of the earth speed of the four beams of DVL, the depth measured by the PS sensor, and the corresponding values solved by the inertial navigation system: />Wherein Z is the measurement of the navigation system, +.>Representing the projected component of the velocity of the inertial navigation solution in the direction of the ith beam of the Doppler sensor, H SINS Representing altitude measurements of an inertial navigation system, < >>Representing the speed measurement result of the ith wave beam of the Doppler sensor, H PS And representing the height measurement result of the depth gauge, wherein H (k) is a measurement matrix at k time, and V is measurement noise.
The information fusion method applied by the SINS/DVL/PS tightly-integrated navigation system is a Kalman filtering algorithm, and comprises time updating and parameter updating, and is shown as the formula:
P(k,k-1)＝φ(k,k-1)P(k-1)φ(k,k-1) T +Q(k-1)
K(k)＝P(k,k-1)H(k) T (H(k)·P(k,k-1)H(k) T +R(k)) -1
P(k)＝(I-K(k)H(k))P(k,k-1)
wherein,update value for the state from moment k-1 to moment k,/>For the state estimation value at time K-1, P (K, K-1) is the updated value of the covariance matrix from time K-1 to time K, P (K) is the covariance matrix at time K, Q (K) is the system noise matrix at time K, R (K) is the system measurement noise matrix at time K, and K (K) is the gain matrix at time K.
According to the equation, the designed ship simulation track is utilized to build a SINS/DVL/PS tightly combined navigation system virtual model by utilizing sensor data generated through simulation and a Kalman filter principle, and the real-time process quantity and the resolving result of the combined navigation system are calculated and generated.
And respectively adding faults to each beam and each depth meter of the Doppler velocimeter of the virtual model at different moments:H PS * ＝H PS +f, where x represents the added fault state, f represents the fault artificially added to a different location, the fault location comprising: a certain beam of the DVL, multiple beams of the DVL and depth gauges, and the time and location of the fault occurrence are recorded.
The residual quantity at the moment k can be obtained by iteration of Kalman filtering:the normalized residual amount is r (k)' =a (k) -1/2 r (k), where a (k) is the variance matrix of the time k residuals, the normalized residual quantity is set as the navigation statistic reflecting the fault location. And storing the normalized residual sequence generated by the Kalman filter for a fixed time length as one sample, and storing the fault position at the last moment as a label of the sample to generate a virtual training set. The sample set includes the input quantity X of the neural network input And tag Y output The input quantity of the neural network is designed as time-series data of length l consisting of normalized residual quantities: x is X input ＝[r(k-l+1)',r(k-l+2)',...,r(k)']The tag is designed as the fault location at the current time (time k): y is Y output 。
S2, building an LSTM neural network, and training the LSTM neural network by utilizing a virtual training set to obtain a pre-training model LSTM-1.
The LSTM neural network consists of an input layer, a long-short-period memory layer, a full-connection layer, a softmax layer and an output layer; the long-term memory layer comprises 128 LSTM units, forgetting gates, input gates and output gates of the LSTM units control the flow of information in the network, and a specific calculation formula is as follows:
i t ＝σ(U i h t-1 +W i x t +b i )
f t ＝σ(U f h t-1 +W f x t +b f )
o t ＝σ(U o h t-1 +W o x t +b o )
c t ＝f t ⊙c t-1 +i t ⊙tanh(U c h t-1 +W c x t +b c )
h t ＝o t ⊙tanh(c t )
wherein the subscript t represents the time t, and i, f, and o represent the input gates, respectivelyForget about the gate and output gate, c h is the state of the neuron and the output of the neuron, U, W and b are parameters obtained by training the network, tanh is an activation function, and sigma is a sigmoid function;
the specific mode of generating the pre-training model LSTM-1 is that the normalized residual sequence in the virtual training set generated in the step S1 is used as the input quantity of the LSTM neural network: x is X input ＝[r(k-l+1)',r(k-l+2)',...,r(k)']The fault location at the current time (time k) serves as a label for the network: y is Y output Training the LSTM neural network by adopting an Adam optimization algorithm to obtain a pre-training model LSTM-1, and storing the pre-training model for standby.
S3, acquiring a small amount of SINS/DVL/PS tightly combined navigation system experimental data by using a real ship experiment, injecting faults into the experimental data by using the same method as the step S1, acquiring a sample set as an experimental training set, and designing the input quantity of the same network as follows: x is X input ＝[r(k-l+1)',r(k-l+2)',...,r(k)']The tag is designed to be the current time (the fault location at time k). The pre-training model is based on a migration learning mechanism: and migrating the LSTM-1 to an experimental application scene to obtain a final LSTM neural network model: LSTM-2.
The method comprises the steps of reserving a pre-training model, namely, a long-period memory layer in an LSTM-1 neural network, resetting a full-connection layer of the LSTM-1, setting a small learning rate (0.0001) for the long-period memory layer, setting a large learning rate (0.001) for the full-connection layer, migrating the modified neural network into an experimental scene by using a small amount of experimental data, namely, taking a normalized residual sequence with a fixed length and generated by the experimental data as input of the modified neural network, taking a fault position at the last moment as output of the neural network, training the modified neural network to obtain a final LSTM-2 neural network model, and storing the model for standby.
S4, enabling the SINS/DVL/PS tightly-combined navigation system to enter a working process, enabling the LSTM-2 neural network to enter a classification mode, and enabling the LSTM-2 neural network model to output the fault occurrence position at the current moment according to real-time fault statistics.
In the working engineering of SINS/DVL/PS tightly-integrated navigation system, the normalization generated by Kalman filter is calculatedThe residual statistics r (k)' are converted into fixed time steps l, and the statistics are stored to generate time series data X corresponding to the k moment input ＝[r(k-l+1)',r(k-l+2)',...,r(k)']At this time, the trained LSTM-2 neural network model in step S3 is used as a fault location determiner to enter a classification mode, and the time series data is input into the fault location determiner, and the determiner generates the fault location (or no fault) of the current navigation sensor.
S5, according to a fault positioning result output by the LSTM-2 neural network model, the SINS/DVL/PS tightly combined navigation system automatically takes corresponding fault recovery measures, and effective fusion of SINS/DVL/PS information is realized by using a Kalman filter.
When the fault positioning result in the step S4 is no fault, continuing to fuse the navigation model information according to the default in the step S1; when the fault positioning result is that a certain beam of the Doppler velocimeter fails, according to the inherent relation of measurement of four beams of the Doppler velocimeter:the remaining three beam quantity measurements are used to replace the fault beam quantity, beam 1 being taken as an example: />The measurement equation for this case is as follows:when a plurality of beams fail, the Doppler velocimeter is isolated, and the measurement equation of the situation is as follows: z= [ H ] SINS -H PS ]=hx+v, only the measurement information of the depth gauge is fused in the integrated navigation system; when the depth gauge fails, the depth gauge is isolated, and the measurement equation of the situation is as follows: />Only the measurement information of the Doppler velocimeter is fused in the integrated navigation system.
The present embodiment demonstrates the effectiveness of the algorithm in combination with experimentally collected navigation data instances. Experimental ginsengThe numbers are set as follows: setting zero offset of each axis gyroscope to be 0.2 degrees/h, setting the angle random walk to be 0.15 degrees/h, setting the zero offset of the accelerometer to be 500 mug, and setting the speed random walk to beThe random noise of the Doppler velocimeter is 0.01m/s, the scale factor is 0.1%, and the random noise of the pressure meter is 2m (the data of the Doppler velocimeter and the pressure meter are obtained by artificially adding noise to the reference data due to the limitation of objective experimental conditions). The experimental training set sample is sample data with the navigation time of 30s, and the test set sample is navigation data with the navigation time of 500 s. The four beams of the Doppler velocimeter are respectively applied with the growth speed of 0.5m/s at 101-129 s, 201-229 s, 301-329 s and 401-429 s 2 As can be seen from fig. 3, the fault locating and recovering module under small sample data reduces the influence of doppler velocimeter faults on the navigation system solution result.
Therefore, the fault locating and recovering method for the underwater SINS/DVL/PS tightly combined navigation system can rapidly diagnose and locate common faults such as gradual faults and the like under a small amount of experimental data conditions, and automatically carries out corresponding fault recovering strategies according to fault locating results, thereby improving the reliability of the combined navigation system.
Finally, it should be noted that: the above embodiments are only for illustrating the technical solution of the present invention and not for limiting it, and although the present invention has been described in detail with reference to the preferred embodiments, it will be understood by those skilled in the art that: the technical scheme of the invention can be modified or replaced by the same, and the modified technical scheme cannot deviate from the spirit and scope of the technical scheme of the invention.
Claims (7)
1. The fault locating and recovering method for the underwater SINS/DVL/PS tightly-integrated navigation system is characterized by comprising the following steps:
s1, constructing a set of SINS/DVL/PS tightly-combined navigation system virtual model with the same principle as that of target experimental equipment, and generating a virtual training set by using the virtual model;
s2, building an LSTM neural network, and training the LSTM neural network by utilizing a virtual training set to obtain a pre-training model LSTM-1;
s3, acquiring a small amount of SINS/DVL/PS tightly-integrated navigation system experimental data by using a real ship experiment, obtaining an experimental training set based on the real ship experimental data by using the same method as the step S1, and pre-training a model based on a migration learning mechanism: and migrating the LSTM-1 to an experimental application scene to obtain a final LSTM neural network model: LSTM-2;
s4, enabling the SINS/DVL/PS tightly-combined navigation system to enter a working process, enabling the LSTM-2 neural network to enter a classification mode, and enabling the LSTM-2 neural network model to output the fault occurrence position at the current moment according to real-time fault statistics;
s5, according to a fault positioning result output by the LSTM-2 neural network model, the SINS/DVL/PS tightly combined navigation system automatically takes corresponding fault recovery measures, and effective fusion of SINS/DVL/PS information is realized by using a Kalman filter.
2. The fault locating and recovering method for the underwater SINS/DVL/PS compact navigation system according to claim 1, wherein the SINS/DVL/PS compact navigation system virtual model setting method in step S1 is as follows:
acquiring a state equation and a measurement equation of the tightly combined navigation system, wherein the state equation is as follows: x (k) =phi (k, k-1) X (k-1) +w (k-1) derives from the error equation of the inertial navigation system, where X (k) is the state quantity of the navigation system at time k,wherein [ phi ] e ,φ n ,φ u ]For the attitude angle error of the navigation system in the northeast direction, [ δv ] e ,δv n ,δv u ]For speed error of navigation system in northeast direction, [ delta L, delta lambda, delta h]For position error of longitude and latitude altitude of navigation system, [ epsilon ] x ,ε y ,ε z ]Is the three-axis zero offset of the gyroscope, +.>For the triaxial zero offset of the accelerometer, δK is the scale factor error of the Doppler velocimeter, phi (K, K-1) represents the state transition matrix of the system from K-1 time to K time, the state transition matrix is obtained by the error equation of the inertial navigation system, and W is the system noise; measurement equation: z (k) =h (k) X (k) +v (k), the measurement in the measurement equation is constructed from the real measurement of the earth speed of the four beams of DVL, the depth measured by the PS sensor, and the corresponding values solved by the inertial navigation system: />Wherein Z is the measurement of the navigation system, +.>Representing the projected component of the velocity of the inertial navigation solution in the direction of the ith beam of the Doppler sensor, H SINS Representing altitude measurements of an inertial navigation system, < >>Representing the speed measurement result of the ith wave beam of the Doppler sensor, H PS Representing the height measurement result of the depth gauge, wherein H (k) is a measurement matrix at k moment, and V is measurement noise;
the information fusion method applied by the SINS/DVL/PS tightly-integrated navigation system is a Kalman filtering algorithm, and comprises time updating and parameter updating, and is shown as the formula:
P(k,k-1)＝φ(k,k-1)P(k-1)φ(k,k-1) T +Q(k-1)
K(k)＝P(k,k-1)H(k) T (H(k)·P(k,k-1)H(k) T +R(k)) -1
P(k)＝(I-K(k)H(k))P(k,k-1)
wherein,update value for the state from moment k-1 to moment k,/>For the state estimation value at time K-1, P (K, K-1) is the updated value of the covariance matrix from time K-1 to time K, P (K) is the covariance matrix at time K, Q (K) is the system noise matrix at time K, R (K) is the system measurement noise matrix at time K, and K (K) is the gain matrix at time K.
3. The fault locating and recovering method for underwater SINS/DVL/PS tightly-integrated navigation system according to claim 2, wherein the method for generating the virtual training set in step S1 is as follows:
according to a state equation, a measurement equation and a Kalman filtering algorithm of an SINS/DVL/PS tightly combined navigation system of experimental equipment, constructing a set of SINS/DVL/PS tightly combined navigation system virtual model with the same principle, and adding faults to each beam and depth meter of a Doppler velocimeter of the virtual model at different moments:H PS * ＝H PS +f, where x represents the added fault state, f represents the fault artificially added to a different location, the fault location comprising: a certain beam of the DVL, a plurality of beams of the DVL and a depth gauge, and recording the occurrence time and the occurrence position of faults;
the residual quantity at the moment k can be obtained by iteration of Kalman filtering:the normalized residual amount is r (k)' =a (k) -1/2 r (k), where A (k) is the variance matrix of the time k residualsSetting the normalized residual quantity as navigation statistics reflecting the fault position, storing a normalized residual sequence generated by a Kalman filter for a fixed time length as one sample, storing the fault position at the last moment as a label of the sample, and generating a virtual training set.
4. The fault locating and recovering method for underwater SINS/DVL/PS integrated navigation system according to claim 3, wherein the LSTM neural network in step S2 is composed of an input layer, a long-short-term memory layer, a full-connection layer, a softmax layer and an output layer; the long-term memory layer comprises 128 LSTM units, and forgetting gates, input gates and output gates of the LSTM units control the flow of information in the network, and a specific calculation formula is as follows:
i t ＝σ(U i h t-1 +W i x t +b i )
f t ＝σ(U f h t-1 +W f x t +b f )
o t ＝σ(U o h t-1 +W o x t +b o )
c t ＝f t ⊙c t-1 +i t ⊙tanh(U c h t-1 +W c x t +b c )
h t ＝o t ⊙tanh(c t )
wherein the subscript t represents the time t, i, f and o represent an input gate, a forgetting gate and an output gate respectively, c, h are the states of neurons and the outputs of the neurons respectively, U, W and b are parameters obtained by training a network, tanh is an activation function, and sigma is a sigmoid function;
the specific mode of generating the pre-training model LSTM-1 is that the normalized residual sequence in the virtual training set generated in the step S1 is used as the input quantity of the LSTM neural network: x is X input ＝[r(k-l+1)',r(k-l+2)',...,r(k)']The fault location at the current time k is used as a label of the network: y is Y output And training the LSTM neural network to obtain a pre-training model LSTM-1, and storing the pre-training model for later use.
5. The fault locating and recovering method for the underwater SINS/DVL/PS tightly-integrated navigation system according to claim 4, wherein the specific process of migrating the pre-training model to the experimental application scene based on the migration learning mechanism in the step S3 is as follows:
the method comprises the steps of reserving a pre-training model, namely, a long-period memory layer in an LSTM-1 neural network, resetting a full-connection layer of the LSTM-1, setting a small learning rate for the long-period memory layer, setting a large learning rate for the full-connection layer, and transferring the modified neural network to an experimental scene by using a small amount of experimental data, namely, taking a normalized residual sequence with a fixed length generated by the experimental data as input of the modified neural network, taking the fault position at the last moment as output of the neural network, and training the modified neural network to obtain a final LSTM-2 neural network model.
6. The fault locating and recovering method for underwater SINS/DVL/PS integrated navigation system according to claim 5, wherein in step S4, in the SINS/DVL/PS integrated navigation system working engineering, the classification mode working process of the LSTM-2 neural network is as follows: calculating normalized residual statistics r (k)' generated by a Kalman filter, storing the statistics with a fixed time step l, and generating time sequence data X corresponding to k moment input ＝[r(k-l+1)',r(k-l+2)',...,r(k)']At this time, the trained LSTM-2 neural network model in the step S3 enters a classification mode, time series data is input into the model, and the model outputs a fault positioning result.
7. The fault locating and recovering method for underwater SINS/DVL/PS tightly integrated navigation system according to claim 6, wherein the fault recovering measure in step S5 is: when the fault positioning result in the step S4 is no fault, continuing to fuse the navigation model information according to the default in the step S1; when the fault positioning result is that a certain beam of the Doppler velocimeter fails, according to the inherent relation of measurement of four beams of the Doppler velocimeter:replacing the fault beam quantity by using the rest three beam quantities; when a plurality of beams fail, the Doppler velocimeter is isolated, and the measurement equation of the situation is as follows: z= [ H ] SINS -H PS ]=hx+v, only the measurement information of the depth gauge is fused in the integrated navigation system; when the depth gauge fails, the depth gauge is isolated, and the measurement equation of the situation is as follows: />Only the measurement information of the Doppler velocimeter is fused in the integrated navigation system.
Applications Claiming Priority (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2022113006301 | 2022-10-24 | ||
| CN202211300630 | 2022-10-24 |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116147617A CN116147617A (en) | 2023-05-23 |
| CN116147617B true CN116147617B (en) | 2023-11-14 |
Family
ID=86338219
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211709717.4A Active CN116147617B (en) | 2022-10-24 | 2022-12-29 | Fault positioning and recovering method for underwater SINS/DVL/PS tightly-integrated navigation system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116147617B (en) |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102221363A (en) * | 2011-04-12 | 2011-10-19 | 东南大学 | Fault-tolerant combined method of strapdown inertial integrated navigation system for underwater vehicles |
| CN114563804A (en) * | 2021-12-27 | 2022-05-31 | 中国人民解放军空军工程大学 | Adaptive fault-tolerant method of GNSS/INS tightly-combined navigation system |
| CN114966762A (en) * | 2022-05-18 | 2022-08-30 | 中国人民解放军空军工程大学 | Fault detection method of GNSS/INS tightly-combined navigation system |
-
2022
- 2022-12-29 CN CN202211709717.4A patent/CN116147617B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102221363A (en) * | 2011-04-12 | 2011-10-19 | 东南大学 | Fault-tolerant combined method of strapdown inertial integrated navigation system for underwater vehicles |
| CN114563804A (en) * | 2021-12-27 | 2022-05-31 | 中国人民解放军空军工程大学 | Adaptive fault-tolerant method of GNSS/INS tightly-combined navigation system |
| CN114966762A (en) * | 2022-05-18 | 2022-08-30 | 中国人民解放军空军工程大学 | Fault detection method of GNSS/INS tightly-combined navigation system |
Non-Patent Citations (5)
| Title |
|---|
| A Hybrid Method for Dealing With DVL Faults of SINS/DVL Integrated Navigation System;J. Zhu, A. Li, F. Qin, L. Chang and L. Qian;IEEE Sensors Journal,;第22卷(第16期);15844 - 15854 * |
| A Novel Hybrid Method Based on Deep Learning for an Integrated Navigation System during DVL Signal Failure;Zhu Jiupeng;Li An;Qin Fangjun;Che Hao;Wang Jungang;Electronics;第11卷(第19期);1-19 * |
| An effective LS-SVM/AKF aided SINS/DVL integrated navigation system for underwater vehicles;Jin Sun & Fu Wang;Peer-to-Peer Networking and Applications;第15卷;1437–1451 * |
| Wanli Li,Mingjian Chen,Chao Zhang,Lundong Zhang,and Rui Chen.A Novel Neural Network-Based SINS/DVL Integrated Navigation Approach to Deal with DVL Malfunction for Underwater Vehicles.Mathematical Problems in Engineering.2020,第2020卷1-14. * |
| 基于RBF与OS-ELM神经网络的AUV传感器在线故障诊断;段杰，李辉，陈自立，龚时华，赵朝闻;水下无人系统学报;第26卷(第02期);157-165 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116147617A (en) | 2023-05-23 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Dai et al. | An INS/GNSS integrated navigation in GNSS denied environment using recurrent neural network | |
| Sushchenko et al. | Processing of redundant information in airborne electronic systems by means of neural networks | |
| CN110906933B (en) | AUV (autonomous Underwater vehicle) auxiliary navigation method based on deep neural network | |
| CN111707260B (en) | Positioning method based on frequency domain analysis and convolutional neural network | |
| Cohen et al. | BeamsNet: A data-driven approach enhancing Doppler velocity log measurements for autonomous underwater vehicle navigation | |
| Tan et al. | GA-SVR and pseudo-position-aided GPS/INS integration during GPS outage | |
| Zhang et al. | Multiple model AUV navigation methodology with adaptivity and robustness | |
| Srinivas et al. | Overview of architecture for GPS-INS integration | |
| Geragersian et al. | An INS/GNSS fusion architecture in GNSS denied environment using gated recurrent unit | |
| Al Bitar et al. | A novel approach for aiding unscented Kalman filter for bridging GNSS outages in integrated navigation systems | |
| Ansari-Rad et al. | Pseudo DVL reconstruction by an evolutionary TS-fuzzy algorithm for ocean vehicles | |
| CN115857529A (en) | Actuator fault reconstruction method of spacecraft attitude control system | |
| Yi-ting et al. | A fast gradual fault detection method for underwater integrated navigation systems | |
| Davari et al. | Real-time outlier detection applied to a Doppler velocity log sensor based on hybrid autoencoder and recurrent neural network | |
| Shi et al. | Tilt angle monitoring by using sparse residual LSTM network and grid search | |
| El Sabbagh et al. | Promoting navigation system efficiency during GPS outage via cascaded neural networks: A novel AI based approach | |
| Shaukat et al. | Underwater vehicle localization by hybridization of indirect Kalman filter and neural network | |
| CN116147617B (en) | Fault positioning and recovering method for underwater SINS/DVL/PS tightly-integrated navigation system | |
| CN115218927B (en) | Unmanned aerial vehicle IMU sensor fault detection method based on secondary Kalman filtering | |
| Nasserddine et al. | Artificial intelligence in navigation systems | |
| AbdulMajuid et al. | GPS-Denied Navigation Using Low-Cost Inertial Sensors and Recurrent Neural Networks | |
| Munafò et al. | Navigation of AUVs based on ocean fields variability | |
| CN114577204B (en) | Anti-interference self-alignment method and device for strapdown inertial navigation system based on neural network | |
| Nazaruddin et al. | Localization Method for Autonomous Car Using Virtual Sensing System | |
| US20220358365A1 (en) | Tightly coupled end-to-end multi-sensor fusion with integrated compensation |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |