[go: up one dir, main page]

CN119126778A - A method for detecting unmanned boat formation attack based on distributed fuzzy set membership filtering - Google Patents

A method for detecting unmanned boat formation attack based on distributed fuzzy set membership filtering Download PDF

Info

Publication number
CN119126778A
CN119126778A CN202411066296.7A CN202411066296A CN119126778A CN 119126778 A CN119126778 A CN 119126778A CN 202411066296 A CN202411066296 A CN 202411066296A CN 119126778 A CN119126778 A CN 119126778A
Authority
CN
China
Prior art keywords
unmanned boat
state
ellipsoid
unmanned ship
follower
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.)
Pending
Application number
CN202411066296.7A
Other languages
Chinese (zh)
Inventor
包生贵
刘畅
黄增鸿
吕伟俊
郭裕如
周宇媚
李梓甜
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Guangdong University of Technology
Original Assignee
Guangdong University of Technology
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Guangdong University of Technology filed Critical Guangdong University of Technology
Priority to CN202411066296.7A priority Critical patent/CN119126778A/en
Publication of CN119126778A publication Critical patent/CN119126778A/en
Pending legal-status Critical Current

Links

Classifications

    • G—PHYSICS
    • G05—CONTROLLING; REGULATING
    • G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
    • G05D1/00—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
    • G05D1/40—Control within particular dimensions
    • G05D1/43—Control of position or course in two dimensions
    • G—PHYSICS
    • G05—CONTROLLING; REGULATING
    • G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
    • G05D2109/00—Types of controlled vehicles
    • G05D2109/30—Water vehicles
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
    • Y02T90/00—Enabling technologies or technologies with a potential or indirect contribution to GHG emissions mitigation

Landscapes

  • Engineering & Computer Science (AREA)
  • Aviation & Aerospace Engineering (AREA)
  • Radar, Positioning & Navigation (AREA)
  • Remote Sensing (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Automation & Control Theory (AREA)
  • Control Of Position, Course, Altitude, Or Attitude Of Moving Bodies (AREA)

Abstract

The invention discloses a distributed fuzzy set operator filtering-based unmanned ship formation attack detection method which comprises the steps of obtaining a state ellipsoid set of an unmanned ship at the moment k, predicting the state of the unmanned ship by adopting set operator filtering to obtain a state prediction ellipsoid set of the unmanned ship at the moment k+1, judging the intersection of the state ellipsoid set of the unmanned ship at the moment k and the state prediction ellipsoid set of the unmanned ship at the moment k+1, updating the state prediction ellipsoid set of the unmanned ship at the moment k+1 by adopting set operator filtering to obtain a state update ellipsoid set of the unmanned ship at the moment k+1, and judging the intersection of the state prediction ellipsoid set of the unmanned ship at the moment k+1 and the state update ellipsoid set. The invention solves the problems that although various attack detection methods are applied to unmanned ship systems at present, the methods can not timely and comprehensively capture the changes when facing diversified attack means, thereby causing missed detection or false alarm.

Description

Unmanned ship formation attack detection method based on distributed fuzzy set member filtering
Technical Field
The invention relates to the technical field of unmanned ship formation attack detection, in particular to an unmanned ship formation attack detection method based on distributed fuzzy set member filtering.
Background
With the continuous development of science and technology, unmanned ships can perform exploration, cruising and other works in water, and have wide application in a plurality of fields such as military reconnaissance, environmental monitoring, marine resource exploration and rescue actions, and therefore, state estimation and attack detection are required to be performed on the unmanned ships to judge whether the unmanned ships can normally execute tasks. Currently, although various attack detection methods have been applied to unmanned boat systems, most of these methods focus on a single component or layer of the system, such as anomaly detection of sensor data alone or security verification of control signals. The local detection strategy is worry when facing diversified attack means, especially when an attacker adopts strategy to change an attack target, such as changing from a direct attack sensor to an interference communication link or a tamper control instruction, the existing detection method can not timely and comprehensively capture the changes, thereby causing missed detection or false alarm and further affecting the safe operation of the unmanned ship.
Disclosure of Invention
Aiming at the defects, the invention provides an unmanned ship formation attack detection method based on distributed fuzzy set member filtering, which aims to solve the problems that although various attack detection methods are applied to an unmanned ship system at present, the methods can not timely and comprehensively capture the changes when facing diversified attack means, thereby causing missed detection or false alarm and further affecting the safe operation of the unmanned ship.
To achieve the purpose, the invention adopts the following technical scheme:
An unmanned ship formation attack detection method based on distributed fuzzy set member filtering comprises the following steps:
s1, constructing a kinematic and dynamic model of the unmanned ship;
S2, converting a kinematic and dynamic model of the unmanned ship into a state equation of the unmanned ship;
Step S3, linearizing nonlinear terms in the state equation of the unmanned ship by adopting a T-S fuzzy linearization method to obtain a linearized state equation of the unmanned ship;
s4, acquiring a state ellipsoid set of the unmanned ship at the moment k;
S5, predicting the state of the unmanned ship by adopting a collector filtering according to a linearized state equation of the unmanned ship and a state ellipsoid set of the unmanned ship at the moment k to obtain a state prediction ellipsoid set of the unmanned ship at the moment k+1;
S6, performing intersection operation on a state ellipsoid set of the unmanned ship at the moment k and a state prediction ellipsoid set of the unmanned ship at the moment k+1 to obtain a first intersection, judging whether the first intersection is an empty set, if so, indicating that the unmanned ship is attacked, and replacing the state prediction ellipsoid set of the unmanned ship at the moment k+1;
step S7, updating a state prediction ellipsoid set of the unmanned ship at the time k+1 by adopting a member collecting filter to obtain a state update ellipsoid set of the unmanned ship at the time k+1;
And S8, performing intersection operation on the state prediction ellipsoid set of the unmanned ship at the moment k+1 and the state update ellipsoid set of the unmanned ship at the moment k+1 to obtain a second intersection, judging whether the second intersection is an empty set, if not, indicating that the unmanned ship is not attacked, and if so, indicating that the unmanned ship is attacked, and replacing the state prediction ellipsoid set of the unmanned ship at the moment k+1 with the state update ellipsoid set.
Preferably, in step S1, the kinematic and kinetic models of the unmanned boat are expressed as:
Wherein, Represents the position vector of the unmanned ship, x represents the transverse coordinate of the unmanned ship, t represents the longitudinal coordinate of the unmanned ship,Representing a yaw angle of the unmanned boat; mu= [ w, v, r ] T represents a state vector of the unmanned ship, w represents a longitudinal speed of the unmanned ship, v represents a transverse speed of the unmanned ship, and r represents a deflection angular speed of the unmanned ship; The method comprises the following steps of (a) representing a first derivative of mu, (omega) representing noise of an external environment, (u) representing input of a controller, (M) representing an inertial matrix consisting of unmanned ship mass and additional ship mass; representing a rotation matrix between the unmanned ship carrier coordinates and the geodetic coordinates, C (mu) representing a Coriolis centripetal force matrix, D (mu) representing a water surface damping matrix, M, C (μ) and D (μ) are expressed as:
wherein m x and m y respectively represent inertial parameters obtained by subtracting the additional mass from the self weight of the unmanned ship in the transverse direction and the longitudinal direction, m r represents inertial parameters obtained by subtracting the additional mass in the rotation direction from the moment of inertia, and d x、dy and d r respectively represent hydrodynamic damping coefficients of the unmanned ship in the transverse direction, the longitudinal direction and the rotation direction.
Preferably, in step S2, the kinematic and kinetic model of the unmanned aerial vehicle is converted into a state equation of the unmanned aerial vehicle, the state equation of the unmanned aerial vehicle including a leader unmanned aerial vehicle state equation and a follower unmanned aerial vehicle state equation, the leader unmanned aerial vehicle state equation being as follows:
Wherein, Representing the system state of the unmanned ship of the leader at the kth moment; representing a nonlinear state matrix of the leader unmanned ship;
The follower unmanned ship state equation is as follows:
Wherein i e { 1..the N }, N represents the number of follower unmanned boats, x i,k represents the system state of the i-th follower unmanned boat at the k-th moment, y i,k represents the measured value of the i-th follower unmanned boat at the k-th moment, a i,k represents the controller input of the i-th follower unmanned boat at the k-th moment, B i,k represents the system noise of the i-th follower unmanned boat at the k-th moment, c i,k represents the measured noise of the i-th follower unmanned boat at the k-th moment, and both B i、Ei and H i represent the system matrix of the i-th follower unmanned boat.
Preferably, in step S3, the T-S fuzzy linearization method is specifically as follows:
RULE li:IF Is that Is thatIs thatTHEN
Wherein, i i = {1,..d } represents the number of fuzzy rules, d represents the maximum number of fuzzy rules; representing a front variable in a fuzzy rule, namely a nonlinear variable in an unmanned ship state equation; representing fuzzy sets, q representing the number of fuzzy sets; And All represent the system matrix after fuzzy linearization;
The state equation of the linearized unmanned ship is specifically as follows:
Wherein, Normalized weight for each fuzzy rule, Δf i(xi,k) represents error after fuzzy linearization, and satisfies the following equation:
Δfi(ci,k)＝Ji,kΔi,kKi,kxi,k;
wherein J i,k and K i,k represent known matrices, delta i,k is unknown but bounded, and Delta i,k is 1.
Preferably, in step S4, the unmanned ship has a state ellipsoid set at time k ofWherein, The predicted value of the state of the ith follower unmanned ship at the kth moment is represented, and P i,k|k represents the shape matrix of the ellipsoid set where the state at the kth moment is located.
Preferably, in step S5, the following substeps are specifically included:
Step S51, according to a T-S fuzzy linearization method, obtaining a predicted value of the state of the ith follower unmanned aerial vehicle at the moment k+1, wherein the predicted value of the state of the ith follower unmanned aerial vehicle at the moment k+1 is specifically as follows:
Wherein, A predicted value representing the state of the ith follower unmanned ship at time k+1; a state predicted value of the ith follower unmanned ship at the moment k is represented;
Step S52, calculating the next prediction error of the collector filter according to the predicted value of the state of the ith follower unmanned aerial vehicle at the moment k+1 and the linearized state equation of the unmanned aerial vehicle Error of leader unmanned boat
Step S53, according to the state ellipsoid set of the unmanned ship at the moment kAnd a predicted value of the state of the ith follower unmanned ship at time k+1Calculating a first state prediction ellipsoid set by using matrix inequalityWherein, A shape matrix representing a first set of state prediction ellipsoids, the first set of state prediction ellipsoids comprising predicted state information of an ith follower unmanned ship at time k+1;
step S54, according to the error of the unmanned ship of the leader Defining a set of state ellipsoids asWherein U i,k represents a shape matrix of the set of state ellipsoids;
step S55, according to the state ellipsoid set And calculating a second state prediction ellipsoid set by using matrix inequalityThe second state prediction ellipsoid set comprises the prediction state information of the ith follower unmanned ship at the time k+1;
Step S56, a first state prediction ellipsoid set And a second set of state prediction ellipsoidsPerforming intersection operation, and calculating to obtain a minimum ellipsoid set containing intersection of two ellipsoids by using interior point algorithm of semi-definite programmingI.e. the state of the unmanned ship at time k+1 predicts an ellipsoid set.
Preferably, in step S7, the following substeps are specifically included:
Step S71, updating the state of the unmanned ship by using the measured value of the ith follower unmanned ship at the kth moment in the state equation of the follower unmanned ship, wherein the updating equation is as follows:
Wherein, The state predicted value of the ith follower unmanned ship at the time k+1 obtained through data updating is represented; Representing a state predicted value of the ith follower unmanned ship at the time k+1; Y i,k+1 represents the measured value of the ith follower unmanned ship at the k+1 time; Representing a predicted value obtained by predicting a measured value of the ith follower unmanned ship at the k+1 time;
step S72, calculating to obtain an update error according to the update equation and the linearized state equation of the unmanned ship
Step S73, defining another state ellipsoid set as according to the update error e i,k+1|k+1
Step S74, according to the state ellipsoid setAnd calculating to obtain a state update ellipsoid set of the unmanned ship at the time k+1 by utilizing matrix inequality
The technical scheme provided by the embodiment of the application can have the following beneficial effects:
In the scheme, the state of the unmanned ship is predicted and updated by adopting the crew filtering, attack detection is respectively carried out after the prediction and the updating, and particularly whether the unmanned ship is attacked is judged by whether the intersection of two ellipsoidal sets is an empty set or not. The two-step attack detection method for judging whether the unmanned ship is attacked according to whether the intersection of the two ellipsoids is empty or not can timely and comprehensively capture attacks no matter whether the unmanned ship is attacked by a sensor, a control input or other parts and when an attacker adopts a strategy transformation attack target, thereby ensuring the normal operation of the unmanned ship.
Drawings
FIG. 1 is a flow chart of steps of an unmanned ship formation attack detection method based on distributed fuzzy set member filtering.
Detailed Description
Embodiments of the present invention are described in detail below, examples of which are illustrated in the accompanying drawings, wherein like or similar reference numerals refer to like or similar elements or elements having like or similar functions throughout. The embodiments described below by referring to the drawings are exemplary only for explaining the present invention and are not to be construed as limiting the present invention.
An unmanned ship formation attack detection method based on distributed fuzzy set member filtering comprises the following steps:
s1, constructing a kinematic and dynamic model of the unmanned ship;
S2, converting a kinematic and dynamic model of the unmanned ship into a state equation of the unmanned ship;
Step S3, linearizing nonlinear terms in the state equation of the unmanned ship by adopting a T-S fuzzy linearization method to obtain a linearized state equation of the unmanned ship;
s4, acquiring a state ellipsoid set of the unmanned ship at the moment k;
S5, predicting the state of the unmanned ship by adopting a collector filtering according to a linearized state equation of the unmanned ship and a state ellipsoid set of the unmanned ship at the moment k to obtain a state prediction ellipsoid set of the unmanned ship at the moment k+1;
S6, performing intersection operation on a state ellipsoid set of the unmanned ship at the moment k and a state prediction ellipsoid set of the unmanned ship at the moment k+1 to obtain a first intersection, judging whether the first intersection is an empty set, if so, indicating that the unmanned ship is attacked, and replacing the state prediction ellipsoid set of the unmanned ship at the moment k+1;
step S7, updating a state prediction ellipsoid set of the unmanned ship at the time k+1 by adopting a member collecting filter to obtain a state update ellipsoid set of the unmanned ship at the time k+1;
And S8, performing intersection operation on the state prediction ellipsoid set of the unmanned ship at the moment k+1 and the state update ellipsoid set of the unmanned ship at the moment k+1 to obtain a second intersection, judging whether the second intersection is an empty set, if not, indicating that the unmanned ship is not attacked, and if so, indicating that the unmanned ship is attacked, and replacing the state prediction ellipsoid set of the unmanned ship at the moment k+1 with the state update ellipsoid set.
According to the unmanned ship formation attack detection method based on distributed fuzzy set member filtering, as shown in fig. 1, the first step is to construct a kinematic and dynamic model of the unmanned ship, and specifically, the continuous system discretization of the unmanned ship is facilitated through the construction of the kinematic and dynamic model of the unmanned ship. The second step is to convert the kinematic and dynamic model of the unmanned ship into the state equation of the unmanned ship, and specifically, the nonlinear terms in the state equation of the unmanned ship are subjected to linearization treatment. In this embodiment, for the unmanned ship formation of a leader-follower system, that is, there is one unmanned ship in the leading position and coordinated, and the other unmanned ships are controlled to perform the target activities, so the state equations of the unmanned ships include the state equation of the leader unmanned ship and the state equation of the follower unmanned ship. The third step is to conduct linearization processing on nonlinear items in the state equation of the unmanned ship by adopting a T-S fuzzy linearization method, so that the linearized state equation of the unmanned ship is obtained, specifically, the T-S fuzzy linearization method is an existing linearization method, and because nonlinear items exist in the state equation of the unmanned ship, the nonlinear items can be effectively processed by adopting the T-S fuzzy linearization method, and the T-S fuzzy linearization method has stronger robustness to noise, is easy to realize, has small calculation amount and is easier to use. The fourth step is to obtain a state ellipsoid set of the unmanned ship at the time k, in this embodiment, for the unmanned ship, the states such as position, speed and heading of the unmanned ship are affected by various factors in the actual running process, such as water flow, wind wave and sensor noise, and these factors all introduce uncertainty. The state of the unmanned ship at the moment k and the uncertainty thereof can be contained in one ellipsoid by acquiring the state ellipsoid set of the unmanned ship at the moment k, so that the current state of the unmanned ship can be more comprehensively known. Fifthly, predicting the state of the unmanned aerial vehicle by adopting crew filtering according to a linearized state equation of the unmanned aerial vehicle and a state ellipsoid set of the unmanned aerial vehicle at the moment k to obtain a state prediction ellipsoid set of the unmanned aerial vehicle at the moment k+1, in the embodiment, because the unmanned aerial vehicle formation is interfered by external noise when the unmanned aerial vehicle formation executes tasks on the water surface, and most of external noise cannot acquire statistical characteristics of the external noise, so that the scheme uses the crew filtering to estimate the state of the unmanned ship, the estimation comprises two steps, and the first step of estimation is to predict the state of the unmanned ship at the moment k+1 by using the ellipsoid set of the state of the unmanned ship at the moment k. the set membership filtering is an algorithm that performs state estimation in an uncertain environment. The sixth step is that intersection operation is carried out on a state ellipsoid set of the unmanned ship at the moment k and a state prediction ellipsoid set of the unmanned ship at the moment k+1 to obtain a first intersection, whether the first intersection is an empty set is judged, if yes, the unmanned ship is attacked, the state prediction ellipsoid set of the unmanned ship at the moment k+1 is replaced, if not, the unmanned ship is not attacked, in the embodiment, after the state of the unmanned ship is predicted, one attack detection needs to be carried out, specifically, whether the intersection of the state ellipsoid set of the unmanned ship at the moment k and the state prediction ellipsoid set of the unmanned ship at the moment k+1 is an empty set is judged, and whether the unmanned ship is attacked is judged. The seventh step is to update the state prediction ellipsoid set of the unmanned ship at the time k+1 by adopting the crew filtering to obtain the state update ellipsoid set of the unmanned ship at the time k+1, and in the embodiment, the second step of estimation is to update the state prediction value of the unmanned ship at the time k+1, so that the state prediction value is more accurate. The eighth step is that intersection operation is carried out on a state prediction ellipsoid set of the unmanned ship at the moment k+1 and a state update ellipsoid set of the unmanned ship at the moment k+1 to obtain a second intersection, whether the second intersection is an empty set is judged, if not, the unmanned ship is not attacked, if so, the unmanned ship is attacked, the state prediction ellipsoid set of the unmanned ship at the moment k+1 is replaced with the state update ellipsoid set, in the embodiment, after the state prediction value of the unmanned ship is updated, one attack detection is needed, and specifically, whether the unmanned ship is attacked is judged by judging whether the intersection of the state prediction ellipsoid set of the unmanned ship at the moment k+1 and the state update ellipsoid set of the unmanned ship at the moment k+1 is an empty set or not. Further, after the unmanned aerial vehicle is attacked, the state prediction ellipsoid set and the state update ellipsoid set obtained through the unmanned aerial vehicle state estimation may deviate seriously, so that the state prediction ellipsoid set and the state update ellipsoid set which deviate seriously at the moment need to be subjected to data replacement, the influence of network attack on the subsequent state estimation of the unmanned aerial vehicle is reduced, and the normal operation of the unmanned aerial vehicle is ensured.
In the scheme, the state of the unmanned ship is predicted and updated by adopting the crew filtering, attack detection is respectively carried out after the prediction and the updating, and particularly whether the unmanned ship is attacked is judged by whether the intersection of two ellipsoidal sets is an empty set or not. The two-step attack detection method for judging whether the unmanned ship is attacked according to whether the intersection of the two ellipsoids is empty or not can timely and comprehensively capture attacks no matter whether the unmanned ship is attacked by a sensor, a control input or other parts and when an attacker adopts a strategy transformation attack target, thereby ensuring the normal operation of the unmanned ship.
Preferably, in step S1, the kinematic and kinetic model of the unmanned boat is expressed as:
Wherein, Represents the position vector of the unmanned ship, x represents the transverse coordinate of the unmanned ship, y represents the longitudinal coordinate of the unmanned ship,Representing a yaw angle of the unmanned boat; mu= [ w, v, r ] T represents a state vector of the unmanned ship, w represents a longitudinal speed of the unmanned ship, v represents a transverse speed of the unmanned ship, and r represents a deflection angular speed of the unmanned ship; The method comprises the following steps of (a) representing a first derivative of mu, (omega) representing noise of an external environment, (u) representing input of a controller, (M) representing an inertial matrix consisting of unmanned ship mass and additional ship mass; representing a rotation matrix between the unmanned ship carrier coordinates and the geodetic coordinates, C (mu) representing a Coriolis centripetal force matrix, D (mu) representing a water surface damping matrix, M, C (μ) and D (μ) are expressed as:
wherein m x and m y respectively represent inertial parameters obtained by subtracting the additional mass from the self weight of the unmanned ship in the transverse direction and the longitudinal direction, m r represents inertial parameters obtained by subtracting the additional mass in the rotation direction from the moment of inertia, and d x、dy and d r respectively represent hydrodynamic damping coefficients of the unmanned ship in the transverse direction, the longitudinal direction and the rotation direction.
In the embodiment, the continuous system discretization of the unmanned ship is facilitated by establishing the kinematic and dynamic model of the unmanned ship, and the discrete system has the advantages of good stability, controllability and observability.
Preferably, in step S2, the kinematic and kinetic model of the unmanned aerial vehicle is converted into a state equation of the unmanned aerial vehicle, where the state equation of the unmanned aerial vehicle includes a leader unmanned aerial vehicle state equation and a follower unmanned aerial vehicle state equation, and the leader unmanned aerial vehicle state equation is as follows:
Wherein, Representing the system state of the unmanned ship of the leader at the kth moment; representing a nonlinear state matrix of the leader unmanned ship;
The follower unmanned ship state equation is as follows:
Wherein i e { 1..the N }, N represents the number of follower unmanned boats, x i,k represents the system state of the i-th follower unmanned boat at the k-th moment, y i,k represents the measured value of the i-th follower unmanned boat at the k-th moment, a i,k represents the controller input of the i-th follower unmanned boat at the k-th moment, B i,k represents the system noise of the i-th follower unmanned boat at the k-th moment, c i,k represents the measured noise of the i-th follower unmanned boat at the k-th moment, and both B i、Ei and H i represent the system matrix of the i-th follower unmanned boat.
In the embodiment, the kinematic and dynamic models of the unmanned ship are converted into the leader unmanned ship state equation and the follower unmanned ship state equation, so that subsequent linearization processing of nonlinear terms in the leader unmanned ship state equation and the follower unmanned ship state equation is facilitated.
Preferably, in step S3, the T-S fuzzy linearization method is specifically as follows:
RULEli:IF Is that Is thatIs thatTHEN
Wherein, i i = {1,..d } represents the number of fuzzy rules, d represents the maximum number of fuzzy rules; representing a front variable in a fuzzy rule, namely a nonlinear variable in an unmanned ship state equation; representing fuzzy sets, q representing the number of fuzzy sets; And All represent the system matrix after fuzzy linearization;
The state equation of the linearized unmanned ship is specifically as follows:
Wherein, Normalized weight for each fuzzy rule, Δf i(xi,k) represents error after fuzzy linearization, and satisfies the following equation:
Δfi(xi,k)＝Ji,kΔi,kKi,kxi,k;
wherein J i,k and K i,k represent known matrices, delta i,k is unknown but bounded, and Delta i,k is 1.
In the embodiment, the nonlinear terms in the state equation of the unmanned ship of the leader and the state equation of the unmanned ship of the follower are linearized by a T-S fuzzy linearization method, so that the nonlinear terms approach to the original linear equation.
Preferably, in step S4, the unmanned ship has a state ellipsoid set at time k ofWherein, The predicted value of the state of the ith follower unmanned ship at the kth moment is represented, and P i,k|k represents the shape matrix of the ellipsoid set where the state at the kth moment is located.
In the embodiment, the state ellipsoid set of the unmanned ship at the time k is obtained, so that the subsequent attack detection in the state prediction stage is facilitated.
Preferably, in step S5, the method specifically comprises the following substeps:
Step S51, according to a T-S fuzzy linearization method, obtaining a predicted value of the state of the ith follower unmanned aerial vehicle at the moment k+1, wherein the predicted value of the state of the ith follower unmanned aerial vehicle at the moment k+1 is specifically as follows:
Wherein, A predicted value representing the state of the ith follower unmanned ship at time k+1; a state predicted value of the ith follower unmanned ship at the moment k is represented;
Step S52, calculating the next prediction error of the collector filter according to the predicted value of the state of the ith follower unmanned aerial vehicle at the moment k+1 and the linearized state equation of the unmanned aerial vehicle Error of leader unmanned boat
Step S53, according to the state ellipsoid set of the unmanned ship at the moment kAnd a predicted value of the state of the ith follower unmanned ship at time k+1Calculating a first state prediction ellipsoid set by using matrix inequalityWherein, A shape matrix representing a first set of state prediction ellipsoids, the first set of state prediction ellipsoids comprising predicted state information of an ith follower unmanned ship at time k+1;
step S54, according to the error of the unmanned ship of the leader Defining a set of state ellipsoids asWherein U i,k represents a shape matrix of the set of state ellipsoids;
step S55, according to the state ellipsoid set And calculating a second state prediction ellipsoid set by using matrix inequalityThe second state prediction ellipsoid set comprises the prediction state information of the ith follower unmanned ship at the time k+1;
Step S56, a first state prediction ellipsoid set And a second set of state prediction ellipsoidsPerforming intersection operation, and calculating to obtain a minimum ellipsoid set containing intersection of two ellipsoids by using interior point algorithm of semi-definite programmingI.e. the state of the unmanned ship at time k+1 predicts an ellipsoid set.
In this embodiment, the matrix inequality and the interior point algorithm of the semi-definite programming are both existing algorithms. For unmanned ship formation of a leader-follower system, the controller inputs a' i,k of the system are as follows, according to the control protocol of the leader-follower system:
Wherein, Is a conventional matrix; Representing a follower unmanned boat adjacent to the ith unmanned boat; Representing a state predicted value of the jth follower unmanned ship obtained through data updating at the kth moment; when the ith unmanned boat receives information of the jth unmanned boat, h ij =1, otherwise h ij =0. Because the whole follower unmanned ship system is controlled by the leader unmanned ship, when the ith follower unmanned ship receives the information of the leader unmanned ship at the k moment, lambda i is more than or equal to 0, otherwise lambda i =0. From the predicted value of the state of the ith follower unmanned ship at time k+1 and the controller input a' i,k of the leader-follower system, it can be seen that the state of the ith follower unmanned ship at time k+1 is related not only to itself but also to the leader unmanned ship, and thus, the error of the leader unmanned ship Defining a set of state ellipsoids asAnd calculating a second state prediction ellipsoid set by using matrix inequalityEllipsoid set due to first state predictionAnd a second set of state prediction ellipsoidsThe method comprises the step of predicting the state information of the ith follower unmanned ship at the moment k+1, so that the intersection of the information and the predicted state information can be obtained, and the state predicting ellipsoid set of the unmanned ship at the moment k+1 can be further obtained.
Preferably, in step S7, the method specifically includes the following substeps:
Step S71, updating the state of the unmanned ship by using the measured value of the ith follower unmanned ship at the kth moment in the state equation of the follower unmanned ship, wherein the updating equation is as follows:
Wherein, The state predicted value of the ith follower unmanned ship at the time k+1 obtained through data updating is represented; Representing a state predicted value of the ith follower unmanned ship at the time k+1; Y i,k+1 represents the measured value of the ith follower unmanned ship at the k+1 time; Representing a predicted value obtained by predicting a measured value of the ith follower unmanned ship at the k+1 time;
step S72, calculating to obtain an update error according to the update equation and the linearized state equation of the unmanned ship
Step S73, defining another state ellipsoid set as according to the update error e i,k+1|k+1
Step S74, according to the state ellipsoid setAnd calculating to obtain a state update ellipsoid set of the unmanned ship at the time k+1 by utilizing matrix inequality
In this embodiment, the state prediction ellipsoid set of the unmanned ship at time k+1 is updated, so that the state prediction ellipsoid set can be more accurate.
Furthermore, functional units in various embodiments of the present invention may be integrated into one processing module, or each unit may exist alone physically, or two or more units may be integrated into one module. The integrated modules may be implemented in hardware or in software functional modules. The integrated modules may also be stored in a computer readable storage medium if implemented in the form of software functional modules and sold or used as a stand-alone product.
While embodiments of the present invention have been shown and described above, it will be understood that the above embodiments are illustrative and not to be construed as limiting the invention, and that variations, modifications, alternatives and variations of the above embodiments may be made by those skilled in the art within the scope of the invention.

Claims (7)

1.一种基于分布式模糊集员滤波的无人艇编队攻击检测方法，其特征在于：包括以下步骤：1. A method for detecting an attack of an unmanned boat formation based on distributed fuzzy set membership filtering, characterized in that it comprises the following steps: 步骤S1：构建无人艇的运动学和动力学模型；Step S1: construct the kinematic and dynamic models of the unmanned boat; 步骤S2：将无人艇的运动学和动力学模型转换为无人艇的状态方程；Step S2: converting the kinematic and dynamic models of the unmanned boat into the state equation of the unmanned boat; 步骤S3：采用T-S模糊线性化方法对无人艇的状态方程中的非线性项进行线性化处理，得到线性化的无人艇的状态方程；Step S3: linearize the nonlinear terms in the state equation of the unmanned boat using the T-S fuzzy linearization method to obtain a linearized state equation of the unmanned boat; 步骤S4：获取无人艇在k时刻的状态椭球集；Step S4: Obtain the state ellipsoid set of the unmanned boat at time k; 步骤S5：根据线性化的无人艇的状态方程以及无人艇在k时刻的状态椭球集，采用集员滤波对无人艇的状态进行预测，得到无人艇在k+1时刻的状态预测椭球集；Step S5: according to the linearized state equation of the unmanned boat and the state ellipsoid set of the unmanned boat at time k, the state of the unmanned boat is predicted by using set membership filtering to obtain the state prediction ellipsoid set of the unmanned boat at time k+1; 步骤S6：将无人艇在k时刻的状态椭球集与无人艇在k+1时刻的状态预测椭球集进行交集运算，得到第一交集，并判断第一交集是否为空集，若是，则说明无人艇受到攻击，并将无人艇在k+1时刻的状态预测椭球集进行替换；若否，则说明无人艇没有受到攻击；Step S6: performing an intersection operation on the state ellipsoid set of the unmanned boat at time k and the state prediction ellipsoid set of the unmanned boat at time k+1 to obtain a first intersection, and determining whether the first intersection is an empty set. If so, it means that the unmanned boat is attacked, and the state prediction ellipsoid set of the unmanned boat at time k+1 is replaced; if not, it means that the unmanned boat is not attacked; 步骤S7：采用集员滤波对无人艇在k+1时刻的状态预测椭球集进行更新，得到无人艇在k+1时刻的状态更新椭球集；Step S7: using set membership filtering to update the state prediction ellipsoid set of the unmanned boat at time k+1, and obtaining the state update ellipsoid set of the unmanned boat at time k+1; 步骤S8：将无人艇在k+1时刻的状态预测椭球集与无人艇在k+1时刻的状态更新椭球集进行交集运算，得到第二交集，并判断第二交集是否为空集，若否，则说明无人艇没有受到攻击；若是，则说明无人艇受到攻击，并将无人艇在k+1时刻的状态预测椭球集与状态更新椭球集进行替换。Step S8: Perform an intersection operation on the state prediction ellipsoid set of the unmanned boat at time k+1 and the state update ellipsoid set of the unmanned boat at time k+1 to obtain a second intersection, and determine whether the second intersection is an empty set. If not, it means that the unmanned boat is not attacked; if so, it means that the unmanned boat is attacked, and the state prediction ellipsoid set of the unmanned boat at time k+1 and the state update ellipsoid set are replaced. 2.根据权利要求1所述的一种基于分布式模糊集员滤波的无人艇编队攻击检测方法，其特征在于：在步骤S1中，无人艇的运动学和动力学模型表示为：2. The method for detecting an attack of an unmanned boat formation based on distributed fuzzy set membership filtering according to claim 1, characterized in that: in step S1, the kinematic and dynamic models of the unmanned boat are expressed as: 其中，表示无人艇的位置向量，x表示无人艇的横向坐标，y表示无人艇的纵向坐标，表示无人艇的偏航角；表示θ的一阶导数；μ＝[w，v，r]T表示无人艇的状态向量，w表示无人艇的纵向速度，v表示无人艇的横向速度，r表示无人艇的偏向角速度；表示μ的一阶导数；ω表示外界环境的噪声；u表示控制器的输入；M表示无人艇质量以及船体附加质量组成的惯性矩阵；表示无人艇载体坐标与大地坐标之间的旋转矩阵；C(μ)表示科里奥利向心力矩阵；D(μ)表示水面阻尼矩阵；M、C(μ)和D(μ)表示为：in, represents the position vector of the unmanned boat, x represents the lateral coordinate of the unmanned boat, y represents the longitudinal coordinate of the unmanned boat, Indicates the yaw angle of the unmanned boat; represents the first-order derivative of θ; μ = [w, v, r] T represents the state vector of the unmanned boat, w represents the longitudinal velocity of the unmanned boat, v represents the lateral velocity of the unmanned boat, and r represents the yaw angular velocity of the unmanned boat; represents the first-order derivative of μ; ω represents the noise of the external environment; u represents the input of the controller; M represents the inertia matrix composed of the mass of the unmanned boat and the additional mass of the hull; represents the rotation matrix between the unmanned vehicle carrier coordinates and the earth coordinates; C(μ) represents the Coriolis centripetal force matrix; D(μ) represents the water surface damping matrix; M, C(μ) and D(μ) are expressed as: 其中，mx和my分别表示无人艇在横向与纵向上自身重量减去附加质量得到的惯性参数；mr表示转动惯量减去旋转方向上的附加质量得到的惯性参数；dx、dy和dr分别表示无人艇在横向、纵向和旋转方向上的水动力阻尼系数。Among them, m x and my y represent the inertia parameters obtained by subtracting the additional mass from the self-weight of the unmanned boat in the lateral and longitudinal directions, respectively; m r represents the inertia parameter obtained by subtracting the additional mass in the rotation direction from the moment of inertia; d x , dy and d r represent the hydrodynamic damping coefficients of the unmanned boat in the lateral, longitudinal and rotational directions, respectively. 3.根据权利要求1所述的一种基于分布式模糊集员滤波的无人艇编队攻击检测方法，其特征在于：在步骤S2中，将无人艇的运动学和动力学模型转换为无人艇的状态方程，无人艇的状态方程包括领导者无人艇状态方程和跟随者无人艇状态方程，领导者无人艇状态方程如下：3. According to the method for detecting an attack of an unmanned boat formation based on distributed fuzzy set membership filtering in claim 1, it is characterized in that: in step S2, the kinematic and dynamic models of the unmanned boat are converted into the state equation of the unmanned boat, the state equation of the unmanned boat includes the state equation of the leader unmanned boat and the state equation of the follower unmanned boat, and the state equation of the leader unmanned boat is as follows: 其中，表示领导者无人艇在第k时刻的系统状态；表示领导者无人艇的非线性状态矩阵；in, represents the system state of the leader unmanned boat at the kth moment; represents the nonlinear state matrix of the leader unmanned vehicle; 跟随者无人艇状态方程如下：The state equation of the follower unmanned boat is as follows: 其中，i∈{1,...,N}，N表示跟随者无人艇的数量；xi,k表示第i个跟随者无人艇在第k时刻的系统状态；yi,k表示第i个跟随者无人艇在第k时刻的测量值；ai,k表示第i个跟随者无人艇在第k时刻的控制器输入；bi,k表示第i个跟随者无人艇在k时刻的系统噪声；ci,k表示第i个跟随者无人艇在k时刻的测量噪声；Bi、Ei和Hi均表示第i个跟随者无人艇的系统矩阵。Among them, i∈{1,...,N}, N represents the number of follower unmanned boats; x i,k represents the system state of the i-th follower unmanned boat at the k-th moment; y i,k represents the measurement value of the i-th follower unmanned boat at the k-th moment; a i,k represents the controller input of the i-th follower unmanned boat at the k-th moment; b i,k represents the system noise of the i-th follower unmanned boat at the k-th moment; c i,k represents the measurement noise of the i-th follower unmanned boat at the k-th moment; Bi , E i and Hi all represent the system matrix of the i-th follower unmanned boat. 4.根据权利要求3所述的一种基于分布式模糊集员滤波的无人艇编队攻击检测方法，其特征在于：在步骤S3中，T-S模糊线性化方法具体如下：4. The method for detecting an attack of an unmanned boat formation based on distributed fuzzy set membership filtering according to claim 3 is characterized in that: in step S3, the T-S fuzzy linearization method is specifically as follows: RULE li：IF是是是THENRULE l i ：IF yes yes yes THEN 其中，li＝{1,...,d}表示模糊规则数，d表示模糊规则的最大数量； 表示模糊规则中的前件变量，即无人艇状态方程中的非线性变量； 表示模糊集，q表示模糊集的个数；和均表示模糊线性化后的系统矩阵；Where, l i ={1,...,d} represents the number of fuzzy rules, and d represents the maximum number of fuzzy rules; It represents the antecedent variable in the fuzzy rule, that is, the nonlinear variable in the state equation of the unmanned boat; represents a fuzzy set, q represents the number of fuzzy sets; and All represent the system matrix after fuzzy linearization; 线性化的无人艇的状态方程具体如下：The linearized state equation of the unmanned boat is as follows: 其中，表示每个模糊规则的正规化权重；Δfi(xi,k)表示模糊线性化后的误差，且满足如下式子：in, represents the normalized weight of each fuzzy rule; Δf i (xi ,k ) represents the error after fuzzy linearization and satisfies the following formula: Δfi(xi,k)＝Ji,kΔi,kKi,kxi,k；Δf i (x i,k )=J i,k Δ i,k K i,k x i,k ; 其中，Ji,k和Ki,k表示已知矩阵；Δi,k未知但有界，且||Δi,k||≤1。Where Ji ,k and Ki ,k represent known matrices; Δi ,k is unknown but bounded, and ||Δi ,k ||≤1. 5.根据权利要求4所述的一种基于分布式模糊集员滤波的无人艇编队攻击检测方法，其特征在于：在步骤S4中，无人艇在k时刻的状态椭球集为其中，表示第i个跟随者无人艇在第k时刻的状态预测值，Pi,k|k表示在第k时刻的状态所在椭球集的形状矩阵。5. The method for detecting an attack of an unmanned boat formation based on distributed fuzzy set membership filtering according to claim 4, characterized in that: in step S4, the state ellipsoid set of the unmanned boat at time k is in, represents the state prediction value of the i-th follower unmanned boat at the k-th moment, and Pi,k|k represents the shape matrix of the ellipsoid set where the state is located at the k-th moment. 6.根据权利要求5所述的一种基于分布式模糊集员滤波的无人艇编队攻击检测方法，其特征在于：在步骤S5中，具体包括以下子步骤：6. The method for detecting an attack of an unmanned boat formation based on distributed fuzzy set membership filtering according to claim 5 is characterized in that: in step S5, the method specifically comprises the following sub-steps: 步骤S51：根据T-S模糊线性化方法，获得第i个跟随者无人艇在k+1时刻的状态的预测值，其中，第i个跟随者无人艇在k+1时刻的状态的预测值具体如下：Step S51: According to the T-S fuzzy linearization method, the predicted value of the state of the i-th follower unmanned boat at the k+1 time is obtained, wherein the predicted value of the state of the i-th follower unmanned boat at the k+1 time is as follows: 其中，表示第i个跟随者无人艇在k+1时刻的状态的预测值；表示在第i个跟随者无人艇在k时刻的状态预测值；in, represents the predicted value of the state of the i-th follower unmanned boat at time k+1; represents the predicted state value of the i-th follower unmanned boat at time k; 步骤S52：根据第i个跟随者无人艇在k+1时刻的状态的预测值和线性化的无人艇的状态方程，计算得到集员滤波器的下一步预测误差 以及领导者无人艇的误差 Step S52: Calculate the next prediction error of the set membership filter based on the predicted value of the state of the i-th follower unmanned boat at time k+1 and the linearized state equation of the unmanned boat and the error of the leader's unmanned boat 步骤S53：根据无人艇在k时刻的状态椭球集以及第i个跟随者无人艇在k+1时刻的状态的预测值利用矩阵不等式计算得到第一状态预测椭球集其中，表示第一状态预测椭球集的形状矩阵，第一状态预测椭球集包含第i个跟随者无人艇在k+1时刻的预测状态信息；Step S53: Based on the state ellipsoid set of the unmanned boat at time k And the predicted value of the state of the i-th follower unmanned boat at time k+1 The first state prediction ellipsoid set is calculated using matrix inequality in, represents the shape matrix of the first state prediction ellipsoid set, which contains the predicted state information of the i-th follower unmanned boat at time k+1; 步骤S54：根据领导者无人艇的误差定义一状态椭球集为其中，Ui,k表示该状态椭球集的形状矩阵；Step S54: Based on the error of the leader unmanned boat Define a state ellipsoid set as Among them, U i,k represents the shape matrix of the state ellipsoid set; 步骤S55：根据状态椭球集并利用矩阵不等式计算得到第二状态预测椭球集其中，第二状态预测椭球集包含第i个跟随者无人艇在k+1时刻的预测状态信息；Step S55: According to the state ellipsoid set And use the matrix inequality to calculate the second state prediction ellipsoid set Among them, the second state prediction ellipsoid set contains the predicted state information of the i-th follower unmanned boat at time k+1; 步骤S56：将第一状态预测椭球集和第二状态预测椭球集进行交集运算，并通过半定规划的内点算法计算得到包含两椭球集交集的最小椭球集即无人艇在k+1时刻的状态预测椭球集。Step S56: Set the first state prediction ellipsoid set and the second state predicted ellipsoid set Perform intersection operation and calculate the minimum ellipsoid set containing the intersection of the two ellipsoid sets through the interior point algorithm of semidefinite programming That is, the state prediction ellipsoid set of the unmanned boat at time k+1. 7.根据权利要求6所述的一种基于分布式模糊集员滤波的无人艇编队攻击检测方法，其特征在于：在步骤S7中，具体包括以下子步骤：7. The method for detecting an attack of an unmanned boat formation based on distributed fuzzy set membership filtering according to claim 6 is characterized in that: in step S7, the method specifically comprises the following sub-steps: 步骤S71：利用跟随者无人艇状态方程中的第i个跟随者无人艇在第k时刻的测量值对无人艇状态进行更新，更新方程如下：Step S71: Update the state of the unmanned boat using the measurement value of the i-th follower unmanned boat at the k-th time in the state equation of the follower unmanned boat. The update equation is as follows: 其中，表示通过数据更新得到的第i个跟随者无人艇在k+1时刻的状态预测值；表示第i个跟随者无人艇在k+1时刻的状态预测值；表示参数矩阵；yi,k+1表示第i个跟随者无人艇在第k+1时刻的测量值；表示对第i个跟随者无人艇在第k+1时刻的测量值进行预测得到的预测值；in, represents the state prediction value of the i-th follower unmanned boat at time k+1 obtained through data update; represents the predicted state value of the i-th follower unmanned boat at time k+1; represents the parameter matrix; yi,k+1 represents the measurement value of the i-th follower unmanned boat at the k+1th time; represents the predicted value obtained by predicting the measured value of the i-th follower unmanned boat at the k+1th time; 步骤S72：根据更新方程以及线性化的无人艇的状态方程，计算得到更新误差 Step S72: Calculate the update error according to the update equation and the linearized state equation of the unmanned boat 步骤S73：根据更新误差ei,k+1|k+1，定义另一状态椭球集为 Step S73: Based on the update error e i,k+1|k+1 , define another state ellipsoid set as 步骤S74：根据状态椭球集并利用矩阵不等式计算得到无人艇在k+1时刻的状态更新椭球集 Step S74: According to the state ellipsoid set The matrix inequality is used to calculate the state update ellipsoid set of the unmanned boat at time k+1
CN202411066296.7A 2024-08-05 2024-08-05 A method for detecting unmanned boat formation attack based on distributed fuzzy set membership filtering Pending CN119126778A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202411066296.7A CN119126778A (en) 2024-08-05 2024-08-05 A method for detecting unmanned boat formation attack based on distributed fuzzy set membership filtering

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202411066296.7A CN119126778A (en) 2024-08-05 2024-08-05 A method for detecting unmanned boat formation attack based on distributed fuzzy set membership filtering

Publications (1)

Publication Number Publication Date
CN119126778A true CN119126778A (en) 2024-12-13

Family

ID=93756406

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202411066296.7A Pending CN119126778A (en) 2024-08-05 2024-08-05 A method for detecting unmanned boat formation attack based on distributed fuzzy set membership filtering

Country Status (1)

Country Link
CN (1) CN119126778A (en)

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20140372026A1 (en) * 2011-09-14 2014-12-18 Trusted Positioning Inc. Method and apparatus for navigation with nonlinear models
US20210403182A1 (en) * 2020-06-28 2021-12-30 Mitsubishi Electric Research Laboratories, Inc. Fail-Safe Vehicle Rendezvous in Case of Total Control Failure
CN114296469A (en) * 2022-01-17 2022-04-08 上海大学 Reconfigurable fault-tolerant control method of unmanned ship based on double-parameter adaptive fault identification
CN116909283A (en) * 2023-07-26 2023-10-20 郑州大学 Cluster cooperative motion control method for escort task and electronic equipment
CN117368904A (en) * 2023-09-22 2024-01-09 辽宁工业大学 Target tracking method of offshore ship based on AIS and radar

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20140372026A1 (en) * 2011-09-14 2014-12-18 Trusted Positioning Inc. Method and apparatus for navigation with nonlinear models
US20210403182A1 (en) * 2020-06-28 2021-12-30 Mitsubishi Electric Research Laboratories, Inc. Fail-Safe Vehicle Rendezvous in Case of Total Control Failure
CN114296469A (en) * 2022-01-17 2022-04-08 上海大学 Reconfigurable fault-tolerant control method of unmanned ship based on double-parameter adaptive fault identification
CN116909283A (en) * 2023-07-26 2023-10-20 郑州大学 Cluster cooperative motion control method for escort task and electronic equipment
CN117368904A (en) * 2023-09-22 2024-01-09 辽宁工业大学 Target tracking method of offshore ship based on AIS and radar

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
MAHSHID RAHIMIFARD 等: "《Cyberattack Detection for a Class of Nonlinear Multiagent Systems Using Set-Membership Fuzzy Filtering》", 《IEEE SYSTEMS JOURNAL》, 13 February 2024 (2024-02-13), pages 1056 - 1068 *

Similar Documents

Publication Publication Date Title
CN115016496B (en) Path tracking method of unmanned surface vehicle based on deep reinforcement learning
Zhang et al. Neural network control of underactuated surface vehicles with prescribed trajectory tracking performance
Yan et al. Finite-time tracking control of autonomous underwater vehicle without velocity measurements
CN115079698A (en) Time-triggered control method for unmanned surface ship path tracking under spoofing attack mission
Bai et al. Multi-innovation gradient iterative locally weighted learning identification for a nonlinear ship maneuvering system
CN114047744A (en) Self-adaptive backstepping sliding mode multi-unmanned ship formation control method based on sampling communication
CN118584984B (en) Emergency auxiliary control method, system and product of underwater unmanned aircraft
CN118131609A (en) A self-triggered adaptive neural control method for unmanned surface ships in a network environment
Wang et al. Learning Nonlinear Dynamics of Ocean Surface Vessel With Multistep Constraints
CN112699536A (en) Self-adaptive target ship track prediction and locking method
CN119126778A (en) A method for detecting unmanned boat formation attack based on distributed fuzzy set membership filtering
CN117539239A (en) Unmanned ship track tracking controller structure based on meta-learning and control method
CN114834650B (en) A method and device for training satellite attitude control intelligent agent based on offline reinforcement learning
CN117891166A (en) An adaptive output feedback trajectory tracking control method for surface ships
CN116257054A (en) A non-periodic communication cooperative control system for unmanned ships
CN119758961B (en) A distributed fuzzy fault detection method for transmission-related multi-unmanned vessel systems
CN120844579B (en) A method for controlling the driving of steel pipe piles in a deep-water container terminal
CN121210882A (en) A Modeling Method for Underwater Robots Based on TPE Hyperparameter Optimization using LSTM
CN119179329B (en) Networked unmanned ship track tracking control method under replay attack
CN118550286B (en) Safety cooperative control method of multi-autonomous underwater robot system under asynchronous DoS attack
Huang et al. Nonlinear Predictive Trajectory Tracking Control of USV with Neural Network Model
CN119336052A (en) A ROV soft chi-square-dual-loop position-velocity condition control method for sea state interference
CN120508098A (en) High sea condition unmanned ship dynamic disturbance rejection control method based on body intelligence
Wang et al. Robust distributed guidance and control of multiple autonomous surface vehicles based on extended state observers and finite-set model predictive control
Wu et al. Secure Formation Control for Unmanned Surface Vehicles Against False Data Injection Attacks

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