CN117669396B - Unmanned ship movement detection method and device, unmanned ship and storage medium - Google Patents
Unmanned ship movement detection method and device, unmanned ship and storage medium Download PDFInfo
- Publication number
- CN117669396B CN117669396B CN202410150095.9A CN202410150095A CN117669396B CN 117669396 B CN117669396 B CN 117669396B CN 202410150095 A CN202410150095 A CN 202410150095A CN 117669396 B CN117669396 B CN 117669396B
- Authority
- CN
- China
- Prior art keywords
- vector
- motion model
- ship
- acting force
- unmanned ship
- 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
- 238000001514 detection method Methods 0.000 title claims abstract description 45
- 239000013598 vector Substances 0.000 claims abstract description 163
- 238000000034 method Methods 0.000 claims abstract description 28
- 230000002159 abnormal effect Effects 0.000 claims abstract description 25
- 238000012549 training Methods 0.000 claims abstract description 21
- 239000011159 matrix material Substances 0.000 claims description 63
- 238000004590 computer program Methods 0.000 claims description 17
- 238000004364 calculation method Methods 0.000 claims description 12
- 238000006243 chemical reaction Methods 0.000 claims description 3
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 abstract description 5
- 230000006870 function Effects 0.000 description 6
- 238000010586 diagram Methods 0.000 description 5
- 230000004044 response Effects 0.000 description 4
- 238000012545 processing Methods 0.000 description 3
- 230000005856 abnormality Effects 0.000 description 2
- 238000013507 mapping Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000007619 statistical method Methods 0.000 description 2
- NAWXUBYGYWOOIX-SFHVURJKSA-N (2s)-2-[[4-[2-(2,4-diaminoquinazolin-6-yl)ethyl]benzoyl]amino]-4-methylidenepentanedioic acid Chemical compound C1=CC2=NC(N)=NC(N)=C2C=C1CCC1=CC=C(C(=O)N[C@@H](CC(=C)C(O)=O)C(O)=O)C=C1 NAWXUBYGYWOOIX-SFHVURJKSA-N 0.000 description 1
- 206010000117 Abnormal behaviour Diseases 0.000 description 1
- 230000004075 alteration Effects 0.000 description 1
- 238000003491 array Methods 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 230000003247 decreasing effect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 235000019800 disodium phosphate Nutrition 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000001960 triggered effect Effects 0.000 description 1
Landscapes
- Control Of Position, Course, Altitude, Or Attitude Of Moving Bodies (AREA)
Abstract
The invention discloses an unmanned ship movement detection method, an unmanned ship movement detection device, an unmanned ship and a storage medium, wherein the method comprises the following steps: receiving an accelerator value issued by the control module, and calculating longitudinal acting force, transverse acting force and torque of the unmanned ship according to the accelerator value; forming an input vector according to the longitudinal acting force, the transverse acting force and the torque, and inputting the input vector into a constructed ship motion model to obtain a predicted output vector, wherein the ship motion model is obtained by training an initial ship motion model by the sample longitudinal acting force, the sample transverse acting force and the sample torque which are acquired in advance; and determining a residual norm according to the observed output vector and the predicted output vector, and detecting whether the motion of the unmanned ship is abnormal according to the residual norm, wherein the observed output vector is determined by the acquired transverse speed, longitudinal speed and angular speed. The invention can accurately detect and analyze the motion state of the unmanned ship in real time, and ensure the unmanned ship to safely operate in a complex water area environment.
Description
Technical Field
The embodiment of the invention relates to the technical field of unmanned ships, in particular to an unmanned ship movement detection method and device, an unmanned ship and a storage medium.
Background
With the continuous progress of automation and artificial intelligence technology, unmanned ship autonomous navigation systems gradually become the focus of research and application, but unmanned ships can be influenced by wind and waves in the operation process, the environment of an operation water area is complex and changeable, and motion abnormality detection becomes a key link for ensuring the safety of unmanned ship autonomous navigation. In the prior art, a statistical method is generally adopted to analyze the historical motion state of the unmanned ship, so that whether the current motion state is abnormal or not is inferred, a detection mode based on statistics is simple and easy to realize, but applicable conditions are limited, sudden and nonlinear abnormal behaviors are difficult to capture, the detection accuracy of the statistical method is possibly reduced due to the influence of sensor noise and external environment, and safe operation of the unmanned ship in a complex water area environment cannot be ensured.
Disclosure of Invention
The embodiment of the invention provides a method and a device for detecting the movement of an unmanned ship, the unmanned ship and a storage medium, and aims to solve the problems of untimely and inaccurate movement detection when the unmanned ship operates in a complex water area environment.
In a first aspect, an embodiment of the present invention provides a method for detecting movement of an unmanned ship, including:
Receiving an accelerator value issued by the control module, and calculating the longitudinal acting force, the transverse acting force and the torque of the unmanned ship according to the accelerator value;
Forming an input vector according to the longitudinal acting force, the transverse acting force and the torque, and inputting the input vector into a constructed ship motion model to obtain a predicted output vector, wherein the ship motion model is obtained by training a self-defined three-degree-of-freedom initial ship motion model through a sample longitudinal acting force, a sample transverse acting force and a sample torque which are acquired in advance;
And determining a residual norm according to an observation output vector and the prediction output vector, and detecting whether the motion of the unmanned ship is abnormal according to the residual norm, wherein the observation output vector is determined by the acquired transverse speed, longitudinal speed and angular speed.
In a second aspect, an embodiment of the present invention further provides an unmanned ship motion detection apparatus, including:
The receiving unit is used for receiving the throttle value issued by the control module and calculating the longitudinal acting force, the transverse acting force and the torque of the unmanned ship according to the throttle value;
The prediction unit is used for forming an input vector according to the longitudinal acting force, the transverse acting force and the torque, and inputting the input vector into a constructed ship motion model to obtain a predicted output vector, wherein the ship motion model is obtained by training a self-defined three-degree-of-freedom initial ship motion model through a pre-acquired sample longitudinal acting force, a sample transverse acting force and a sample torque;
and the detection unit is used for determining a residual norm according to an observation output vector and the prediction output vector, and detecting whether the motion of the unmanned ship is abnormal according to the residual norm, wherein the observation output vector is determined by the acquired transverse speed, longitudinal speed and angular speed.
In a third aspect, an embodiment of the present invention further provides an unmanned ship, where the unmanned ship includes a memory and a processor, where the memory stores a computer program, and the processor implements the method when executing the computer program.
In a fourth aspect, embodiments of the present invention also provide a computer readable storage medium storing a computer program which, when executed by a processor, implements the above method.
The embodiment of the invention provides an unmanned ship motion detection method and device, an unmanned ship and a storage medium. Wherein the method comprises the following steps: receiving an accelerator value issued by the control module, and calculating the longitudinal acting force, the transverse acting force and the torque of the unmanned ship according to the accelerator value; forming an input vector according to the longitudinal acting force, the transverse acting force and the torque, and inputting the input vector into a constructed ship motion model to obtain a predicted output vector, wherein the ship motion model is obtained by training a self-defined three-degree-of-freedom initial ship motion model through a sample longitudinal acting force, a sample transverse acting force and a sample torque which are acquired in advance; and determining a residual norm according to an observation output vector and the prediction output vector, and detecting whether the motion of the unmanned ship is abnormal according to the residual norm, wherein the observation output vector is determined by the acquired transverse speed, longitudinal speed and angular speed. According to the technical scheme, the longitudinal acting force, the transverse acting force and the torque of the unmanned ship are calculated according to the accelerator value, then the predicted output vector is obtained according to the longitudinal acting force, the transverse acting force, the torque and the constructed ship motion model, and whether the motion of the unmanned ship is abnormal or not is detected according to the observed output vector and the predicted output vector, so that the motion state of the unmanned ship can be accurately detected and analyzed in real time, and the safe operation of the unmanned ship in a complex water area environment is ensured.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for the description of the embodiments will be briefly described below, and it is obvious that the drawings in the following description are some embodiments of the present invention, and other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
Fig. 1 is a schematic flow chart of an unmanned ship motion detection method according to an embodiment of the present invention;
fig. 2 is a schematic sub-flowchart of an unmanned ship motion detection method according to an embodiment of the present invention;
FIG. 3 is a schematic view of a sub-flow of an unmanned ship motion detection method according to an embodiment of the present invention;
fig. 4 is a schematic sub-flowchart of an unmanned ship motion detection method according to an embodiment of the present invention;
FIG. 5 is a schematic view of a sub-flow of an unmanned ship motion detection method according to an embodiment of the present invention;
FIG. 6 is a flow chart of an unmanned ship motion detection method according to another embodiment of the present invention;
FIG. 7 is a schematic block diagram of an unmanned ship motion detection device provided by an embodiment of the invention;
Fig. 8 is a schematic block diagram of an unmanned ship according to an embodiment of the present invention.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and fully with reference to the accompanying drawings, in which it is evident that the embodiments described are some, but not all embodiments of the invention. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
It should be understood that the terms "comprises" and "comprising," when used in this specification and the appended claims, specify the presence of stated features, integers, steps, operations, elements, and/or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and/or groups thereof.
It is also to be understood that the terminology used in the description of the invention herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention. As used in this specification and the appended claims, the singular forms "a," "an," and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise.
It should be further understood that the term "and/or" as used in the present specification and the appended claims refers to any and all possible combinations of one or more of the associated listed items, and includes such combinations.
As used in this specification and the appended claims, the term "if" may be interpreted as "when..once" or "in response to a determination" or "in response to detection" depending on the context. Similarly, the phrase "if a determination" or "if a [ described condition or event ] is detected" may be interpreted in the context of meaning "upon determination" or "in response to determination" or "upon detection of a [ described condition or event ]" or "in response to detection of a [ described condition or event ]".
Referring to fig. 1, fig. 1 is a flow chart of an unmanned ship motion detection method according to an embodiment of the invention. The unmanned ship motion detection method will be described in detail. As shown in fig. 1, the method includes the following steps S100 to S300.
And S100, receiving the throttle value issued by the control module, and calculating the longitudinal acting force, the transverse acting force and the torque of the unmanned ship according to the throttle value.
In the embodiment of the invention, the unmanned ship receives the throttle value issued by the control module, and the longitudinal acting force of the propeller along the longitudinal direction of the unmanned ship, the transverse acting force along the transverse direction of the unmanned ship and the installation position of the propeller are obtained through the mathematical relationship between the propulsion force and the throttle valueAnd the mathematical relationship is obtained by fitting pre-acquired propulsion data of the propeller under different throttle values. It should be noted that, in the embodiment of the present invention, the unmanned ship further includes other modules in addition to the control module.
S200, forming an input vector according to the longitudinal acting force, the transverse acting force and the torque, and inputting the input vector into a constructed ship motion model to obtain a predicted output vector, wherein the ship motion model is obtained by training a self-defined three-degree-of-freedom initial ship motion model through a pre-acquired sample longitudinal acting force, a sample transverse acting force and a sample torque.
In the embodiment of the invention, the longitudinal acting force, the transverse acting force and the torque form the input vector, and the input vector is input into the constructed ship motion model to obtain the predicted output vector; and taking the longitudinal acting force, the transverse acting force and the torque of the unmanned ship which are acquired in advance as sample longitudinal acting force, sample transverse acting force and sample torque, and training the initial ship motion model with three degrees of freedom by utilizing the sample longitudinal acting force, the sample transverse acting force and the sample torque to obtain the ship motion model.
In the embodiment of the present invention, as shown in fig. 2, step S200 may specifically include steps S210 to S230:
S210, customizing an inertial mass matrix, a centripetal force and Coriolis force coefficient matrix, a resistance coefficient matrix and torque according to the pre-collected sample longitudinal acting force, sample transverse acting force, sample torque and the mass of the unmanned ship; s220, establishing the initial ship motion model with three degrees of freedom according to the self-defined inertial mass matrix, the centripetal force and coriolis force coefficient matrix, the resistance coefficient matrix and the torque; s230, training the initial ship motion model to obtain the ship motion model. Specifically, the transverse speed of the unmanned ship at the current moment is acquired through a sensor while the longitudinal acting force of the sample, the transverse acting force of the sample and the torque of the sample are acquired Longitudinal speed/>Angular velocity/>According to/>、/>、/>Mass/>, of the unmanned shipCustom inertial mass matrix/>Centripetal force and coriolis force coefficient matrix/>Resistance coefficient matrix/>Torque/>，/>、/>、/>/>Are respectively shown as a formula (1), a formula (2), a formula (3) and a formula (4), wherein/>，/>，，/>For the unmanned ship edge/>Moment of inertia in axial direction,/>、/>、/>、/>、/>AndIs an unknown hydrodynamic coefficient; according to custom/>、/>、/>/>Establishing the initial ship motion model with three degrees of freedom, wherein the initial ship motion model is expressed in the form of differential equation, and the differential equation is shown as a formula (5), wherein/>Representing the speed of an unmanned ship,/>、/>/>Respectively representing the transverse speed, the longitudinal speed and the angular speed of the unmanned ship; training the initial ship motion model with the established three degrees of freedom to obtain the converged ship motion model. In the embodiment of the present invention, the initial ship motion model needs to be trained to obtain the converged ship motion model, because there is a large uncertainty in the initial stage of establishing the initial ship motion model, and the detected motion abnormality of the unmanned ship is not accurate at this time, and the ship motion model needs to be applied to the unmanned ship after the initial ship motion model is converged. It should also be noted that, in the embodiment of the present invention, the initial ship motion model may be judged to reach the convergence state by making the loss function value tend to be stable or not significantly decreasing, where the loss function may be calculated according to the lateral velocity, the longitudinal velocity, and the angular velocity, specifically, the difference/>, between the lateral velocity predicted by the initial ship motion model and the lateral velocity actually observed is calculatedCalculating the difference/>, between the longitudinal speed predicted by the initial ship motion model and the longitudinal speed actually observedCalculating the difference/>, between the angular velocity predicted by the initial ship motion model and the actual observed angular velocityAccording to/>、/>/>Calculate the loss function/>，/>The calculation formula of (2) is shown as formula (6).
（1）
（2）
（3）
（4）
（5）
（6）
Further, as shown in fig. 3, step S230 may specifically include steps S231-S233: s231, representing the initial ship motion model as an initial state space ship motion model in a state space form, wherein the initial state space ship motion model comprises a state vector, a state matrix, an input vector and an input matrix; s232, determining a state space ship motion model according to the state vector, the state matrix, the input vector and the input matrix, wherein a parameter estimation vector in the state space ship motion model is determined by the state matrix and the input matrix; s233, estimating the parameter estimation vector by using a dynamic forgetting factor recursive least square method to obtain a vector estimation value at the current moment, and inputting the vector estimation value into the state space ship motion model to obtain the ship motion model. Specifically, in order to facilitate the construction and solution of the model, the initial ship motion model with three degrees of freedom established is expressed as an initial state space ship motion model in the form of a state space, the state equation of the initial state space ship motion model is shown as formula (7), wherein,Is a state vector,/>For inputting vectors,/>Is a state matrix,/>Is an input matrix; according to/>And/>Determining a mapping matrix/>, of a state vector and an input vector to an output vectorAccording to/>And/>Determining a parameter estimation vector/>According to/>And/>Obtaining the state space ship motion model, wherein an output equation of the state space ship motion model is shown in a formula (8); recursive least square method pair/>, using dynamic forgetting factorsEstimating to obtain a vector estimation value/>, of the current momentWill/>And inputting the state space ship motion model to obtain the ship motion model.
（7）
（8）
Further, as shown in fig. 4, step S233 may specifically include steps S2331-S2333: s2331, acquiring the input vector and the output vector at the current moment in the state space ship motion model, and calculating gain according to the input vector and the output vector; s2332, calculating the dynamic forgetting factor at the current moment according to the dynamic forgetting factor at the previous moment and the minimum dynamic forgetting factor; and S2333, updating the vector estimation value at the current moment according to the gain, the output vector, the dynamic forgetting factor at the current moment and the vector estimation value at the previous moment. Specifically, initializing the state vectorCovariance matrix/>The dynamic forgetting factor/>The parameter estimation vector/>The selection of a suitable initialization value is critical for successful convergence of the state space vessel motion model, generally/>The true initial state of the unmanned ship,/>, can be selectedMay be a larger diagonal matrix; /(I)A smaller value may be selected; after initializing the state vector, the covariance matrix, the dynamic forgetting factor and the parameter estimation vector, obtaining the input vector/>, at the current moment, in the state space ship motion modelAnd the output vector/>According to/>And/>Obtaining a mapping matrix from the state vector to the output vector at the current momentAnd calculate Kalman gain/>，/>The calculation formula of (2) is shown as formula (9), wherein/>Is thatCovariance matrix of time,/>Covariance matrix for measuring noise; updating the state vector to obtain the state vector/>, at the current momentUpdating the covariance matrix to obtain the covariance matrix/>, at the current momentThe calculation formula of the state vector at the current moment is shown as a formula (10), and the calculation formula of the covariance matrix at the current moment is shown as a formula (11); according to the dynamic forgetting factor/>Minimum dynamic forgetting factor/>Calculating the dynamic forgetting factor/>, at the current moment，/>The calculation formula of (2) is shown as formula (12), wherein/>To adjust parameters; according to/>、/>、/>And the vector estimate/>, of the previous instantUpdating the vector estimation value/>, of the current momentSaid/>The calculation formula of (2) is shown as formula (13).
（9）
（10）
（11）
（12）
（13）
S300, determining a residual norm according to an observation output vector and the prediction output vector, and detecting whether the motion of the unmanned ship is abnormal according to the residual norm, wherein the observation output vector is determined by the acquired transverse speed, longitudinal speed and angular speed.
In the embodiment of the invention, the longitudinal speed, the transverse speed and the angular speed of the unmanned ship are obtained through the sensor, and the observation output vector is obtained according to the longitudinal speed, the transverse speed and the angular speedPredicting the motion state of the unmanned ship by using the ship motion model to obtain the predicted output vector/>According to/>And determining a residual norm, and detecting whether the motion of the unmanned ship is abnormal according to the residual norm.
Further, as shown in fig. 5, step S300 may specifically include steps S310 to S350: s310, calculating the difference between the observed output vector and the predicted output vector to obtain a residual vector; s320, calculating the residual norm according to the residual vector through a preset norm formula; s330, judging whether the residual norm exceeds a preset residual norm threshold; s340, if the residual norm does not exceed the preset residual norm threshold, judging that the motion of the unmanned ship is not abnormal; and S350, if the residual norm exceeds the preset residual norm threshold, judging that the motion of the unmanned ship is abnormal. Specifically, the observed output vector is obtainedAnd the predicted output vector/>Thereafter, calculate/>And/>The difference results in a residual vector/>，/>The calculation of (2) is shown as a formula (14); according to/>Calculating the residual norm according to the preset norm formula, wherein the preset norm formula is shown as a formula (15); comparing the calculated residual norm with the preset residual norm threshold, wherein the preset residual norm threshold can be determined based on historical data, system characteristics or experience of a person skilled in the art; if the residual norm does not exceed the preset residual norm threshold, judging that the motion of the unmanned ship is not abnormal; and if the residual norm exceeds the preset residual norm threshold, indicating that the residual vector at the current moment deviates from a normal range, judging that the motion of the unmanned ship is abnormal.
（14）
（15）
Fig. 6 is a flow chart of a method for detecting movement of an unmanned ship according to another embodiment of the present invention, as shown in fig. 6, in this embodiment, the method includes steps S100-S400. That is, in the present embodiment, the method further includes step S400 after step S300 of the above embodiment.
And S400, if the movement of the unmanned ship is abnormal, triggering an alarm, and recording a detection result of the movement of the unmanned ship.
In the embodiment of the invention, if the movement of the unmanned ship is detected to be abnormal, a system alarm is triggered to inform related personnel, and the detection result of the movement of the unmanned ship is recorded, so that the related personnel can analyze and improve the system performance later.
As can be seen from the above, in the present embodiment, a ship motion model is first established, which is generally expressed as a state space equation; then, a recursive least square method is adopted to estimate a parameter estimation vector according to longitudinal acting force, transverse acting force and torque, a vector estimation value is updated recursively, a dynamic forgetting factor is introduced, and the weight of historical data is adjusted adaptively according to the importance of current observed data so as to adapt to the dynamic change of a system better; predicting the motion of the unmanned ship according to the ship motion model to obtain a predicted output vector, calculating a residual norm between the observed output vector and the predicted output vector, and if the residual norm at a certain moment exceeds a preset residual norm threshold value, considering that the motion of the unmanned ship is abnormal at the moment; when detecting that the motion of the unmanned ship is abnormal, triggering a system alarm to inform related personnel, and recording a detection result of the motion of the unmanned ship, so that the related personnel can analyze and improve system performance later.
Fig. 7 is a schematic block diagram of an unmanned ship motion detection apparatus 500 according to an embodiment of the present invention. As shown in fig. 7, the present invention also provides an unmanned ship motion detection apparatus 500 corresponding to the above unmanned ship motion detection method. The unmanned ship motion detection apparatus 500 includes a unit for performing the unmanned ship motion detection method described above, and may be configured in an unmanned ship. Specifically, referring to fig. 7, the unmanned ship motion detection apparatus 500 includes a receiving unit 501, a predicting unit 502, and a detecting unit 503.
The receiving unit 501 is configured to receive an accelerator value sent by the control module, and calculate a longitudinal acting force, a transverse acting force and a torque of the unmanned ship according to the accelerator value; the prediction unit 502 is configured to compose an input vector according to the longitudinal acting force, the transverse acting force and the torque, and input the input vector to a constructed ship motion model to obtain a predicted output vector, where the ship motion model is obtained by training a pre-acquired sample longitudinal acting force, sample transverse acting force and sample torque on a self-defined three-degree-of-freedom initial ship motion model; the detecting unit 503 is configured to determine a residual norm according to an observed output vector and the predicted output vector, and detect whether the motion of the unmanned ship is abnormal according to the residual norm, where the observed output vector is determined by the obtained lateral velocity, the obtained longitudinal velocity, and the obtained angular velocity.
In some embodiments, for example, the prediction unit 502 includes a customization unit, a model building unit, and a training unit.
The self-defining unit is used for self-defining an inertial mass matrix, a centripetal force and coriolis force coefficient matrix, a resistance coefficient matrix and a torque according to the pre-collected sample longitudinal acting force, sample transverse acting force, sample torque and the mass of the unmanned ship; the model building unit is used for building the initial ship motion model with three degrees of freedom according to the self-defined inertial mass matrix, the centripetal force and coriolis force coefficient matrix, the resistance coefficient matrix and the torque; the training unit is used for training the initial ship motion model to obtain the ship motion model.
In some embodiments, for example the present embodiment, the training unit includes a conversion unit, a determination unit, and an estimation unit.
The conversion unit is used for representing the initial ship motion model into an initial state space ship motion model in a state space form, wherein the initial state space ship motion model comprises a state vector, a state matrix, an input vector and an input matrix; the determining unit is used for determining a state space ship motion model according to the state vector, the state matrix, the input vector and the input matrix, wherein a parameter estimation vector in the state space ship motion model is determined by the state matrix and the input matrix; the estimation unit is used for estimating the parameter estimation vector by using a dynamic forgetting factor recursive least square method to obtain a vector estimation value at the current moment, and inputting the vector estimation value into the state space ship motion model to obtain the ship motion model.
In some embodiments, for example, the estimation unit includes an acquisition unit, a first calculation unit, and an update unit.
The acquisition unit is used for acquiring the input vector and the output vector at the current moment in the state space ship motion model, and calculating gain according to the input vector and the output vector; the first calculation unit is used for calculating the dynamic forgetting factor at the current moment according to the dynamic forgetting factor at the previous moment and the minimum dynamic forgetting factor; the updating unit is used for updating the vector estimation value at the current moment according to the gain, the output vector, the dynamic forgetting factor at the current moment and the vector estimation value at the previous moment.
In some embodiments, for example, in the present embodiment, the detecting unit 503 includes a second calculating unit, a third calculating unit, a judging unit, a first judging unit, and a second judging unit.
The second calculation unit is used for calculating the difference between the observed output vector and the predicted output vector to obtain a residual vector; the third calculation unit is used for calculating the residual norm according to the residual vector through a preset norm formula; the judging unit is used for judging whether the residual norm exceeds a preset residual norm threshold; the first judging unit is used for judging that the motion of the unmanned ship is not abnormal if the residual norm does not exceed the preset residual norm threshold; and the second judging unit is used for judging that the motion of the unmanned ship is abnormal if the residual norm exceeds the preset residual norm threshold.
In some embodiments, for example, the unmanned ship motion detection apparatus 500 further comprises a trigger unit.
And the triggering unit is used for triggering an alarm if the movement of the unmanned ship is abnormal and recording the detection result of the movement of the unmanned ship.
The unmanned ship movement detection apparatus described above may be implemented in the form of a computer program which can be run on an unmanned ship as shown in fig. 8.
Referring to fig. 8, fig. 8 is a schematic block diagram of an unmanned ship according to an embodiment of the present invention. The unmanned ship 600 is a device having a motion detection function.
Referring to fig. 8, the drone 600 includes a processor 602, memory, and a network interface 605 connected by a system bus 601, where the memory may include a non-volatile storage medium 603 and an internal memory 604.
The non-volatile storage medium 603 may store an operating system 6031 and a computer program 6032. The computer program 6032, when executed, causes the processor 602 to perform an unmanned ship motion detection method.
The processor 602 is used to provide computing and control capabilities to support the operation of the entire unmanned ship 600.
The internal memory 604 provides an environment for the execution of a computer program 6032 in the non-volatile storage medium 603, which computer program 6032, when executed by the processor 602, causes the processor 602 to perform a unmanned ship motion detection method.
The network interface 605 is used for network communication with other devices. It will be appreciated by those skilled in the art that the structure shown in fig. 8 is merely a block diagram of a portion of the structure associated with the present inventive arrangements and is not limiting of the drone 600 to which the present inventive arrangements are applied, and that a particular drone 600 may include more or fewer components than shown, or may incorporate certain components, or may have a different arrangement of components.
Wherein the processor 602 is configured to execute a computer program 6032 stored in a memory to implement any of the embodiments of the unmanned ship motion detection method described above.
It should be appreciated that in embodiments of the present invention, the Processor 602 may be a central processing unit (Central Processing Unit, CPU), the Processor 602 may also be other general purpose processors, digital signal processors (DIGITAL SIGNAL processors, DSPs), application SPECIFIC INTEGRATED Circuits (ASICs), off-the-shelf Programmable gate arrays (Field-Programmable GATE ARRAY, FPGA) or other Programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, or the like. Wherein the general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.
Those skilled in the art will appreciate that all or part of the flow in a method embodying the above described embodiments may be accomplished by computer programs instructing the relevant hardware. The computer program may be stored in a storage medium that is a computer readable storage medium. The computer program is executed by at least one processor in the computer system to implement the flow steps of the embodiments of the method described above.
Accordingly, the present invention also provides a storage medium. The storage medium may be a computer readable storage medium. The storage medium stores a computer program. The computer program, when executed by a processor, causes the processor to perform any of the embodiments of the unmanned ship motion detection method described above.
The storage medium may be a U-disk, a removable hard disk, a Read-Only Memory (ROM), a magnetic disk, or an optical disk, or other various computer-readable storage media that can store program codes.
Those of ordinary skill in the art will appreciate that the elements and algorithm steps described in connection with the embodiments disclosed herein may be embodied in electronic hardware, in computer software, or in a combination of the two, and that the elements and steps of the examples have been generally described in terms of function in the foregoing description to clearly illustrate the interchangeability of hardware and software. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the solution. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present invention.
In the several embodiments provided by the present invention, it should be understood that the disclosed apparatus and method may be implemented in other manners. For example, the device embodiments described above are merely illustrative. For example, the division of each unit is only one logic function division, and there may be another division manner in actual implementation. For example, multiple units or components may be combined or may be integrated into another system, or some features may be omitted, or not performed.
The steps in the method of the embodiment of the invention can be sequentially adjusted, combined and deleted according to actual needs. The units in the device of the embodiment of the invention can be combined, divided and deleted according to actual needs. In addition, each functional unit in the embodiments of the present invention may be integrated in one processing unit, or each unit may exist alone physically, or two or more units may be integrated in one unit.
The integrated unit may be stored in a storage medium if implemented in the form of a software functional unit and sold or used as a stand-alone product. Based on such understanding, the technical solution of the present invention is essentially or partly contributing to the prior art or all or part of the technical solution may be embodied in the form of a software product stored in a storage medium comprising several instructions for causing an unmanned ship to perform all or part of the steps of the method according to the various embodiments of the present invention.
In the foregoing embodiments, the descriptions of the embodiments are focused on, and for those portions of one embodiment that are not described in detail, reference may be made to the related descriptions of other embodiments.
It will be apparent to those skilled in the art that various modifications and variations can be made to the present invention without departing from the spirit or scope of the invention. Thus, it is intended that the present invention also include such modifications and alterations insofar as they come within the scope of the appended claims or the equivalents thereof.
While the invention has been described with reference to certain preferred embodiments, it will be understood by those skilled in the art that various changes and substitutions of equivalents may be made and equivalents will be apparent to those skilled in the art without departing from the scope of the invention. Therefore, the protection scope of the invention is subject to the protection scope of the claims.
Claims (7)
1. An unmanned ship motion detection method, the unmanned ship comprising a control module, comprising:
Receiving an accelerator value issued by the control module, and calculating the longitudinal acting force, the transverse acting force and the torque of the unmanned ship according to the accelerator value;
Forming an input vector according to the longitudinal acting force, the transverse acting force and the torque, and inputting the input vector into a constructed ship motion model to obtain a predicted output vector, wherein the ship motion model is obtained by training a self-defined three-degree-of-freedom initial ship motion model through a sample longitudinal acting force, a sample transverse acting force and a sample torque which are acquired in advance;
Determining a residual norm according to an observation output vector and the prediction output vector, and detecting whether the motion of the unmanned ship is abnormal according to the residual norm, wherein the observation output vector is determined by the acquired transverse speed, longitudinal speed and angular speed;
the training of the initial ship motion model with three degrees of freedom by the pre-collected sample longitudinal acting force, sample transverse acting force and sample torque to obtain the ship motion model comprises the following steps:
The inertial mass matrix, the centripetal force and coriolis force coefficient matrix, the resistance coefficient matrix and the torque are customized according to the pre-collected sample longitudinal acting force, the sample transverse acting force, the sample torque and the mass of the unmanned ship;
establishing the initial ship motion model with three degrees of freedom according to the self-defined inertial mass matrix, the centripetal force and coriolis force coefficient matrix, the resistance coefficient matrix and the torque;
Training the initial ship motion model to obtain the ship motion model;
the training the initial ship motion model to obtain the ship motion model comprises the following steps:
Representing the initial ship motion model as an initial state space ship motion model in a state space form, wherein the initial state space ship motion model comprises a state vector, a state matrix, an input vector and an input matrix;
determining from the state vector, the state matrix, the input vector and the input matrix
A state space vessel motion model, wherein parameter estimation vectors in the state space vessel motion model are determined by the state matrix and the input matrix;
Estimating the parameter estimation vector by using a dynamic forgetting factor recursive least square method to obtain a vector estimation value at the current moment, and inputting the vector estimation value into the state space ship motion model to obtain the ship motion model;
The estimating the parameter estimation vector by using a dynamic forgetting factor recursive least square method to obtain a vector estimation value of the current moment comprises the following steps:
acquiring the input vector and the output vector at the current moment in the state space ship motion model, and calculating gain according to the input vector and the output vector;
Calculating the dynamic forgetting factor at the current moment according to the dynamic forgetting factor at the previous moment and the minimum dynamic forgetting factor;
And updating the vector estimation value at the current moment according to the gain, the output vector, the dynamic forgetting factor at the current moment and the vector estimation value at the previous moment.
2. The method of claim 1, wherein the determining a residual norm from an observed output vector and the predicted output vector comprises:
calculating the difference between the observed output vector and the predicted output vector to obtain a residual vector;
And calculating the residual norm according to the residual vector through a preset norm formula.
3. The method of claim 1, wherein the detecting whether there is an anomaly in the unmanned ship's motion based on the residual norm comprises:
Judging whether the residual norm exceeds a preset residual norm threshold;
if the residual norm does not exceed the preset residual norm threshold, judging that the motion of the unmanned ship is not abnormal;
And if the residual norm exceeds the preset residual norm threshold, judging that the motion of the unmanned ship is abnormal.
4. The method of claim 1, wherein determining a residual norm from the observed output vector and the predicted output vector, and detecting whether there is an anomaly in the motion of the unmanned ship from the residual norm, wherein the observed output vector is determined from the acquired lateral velocity, longitudinal velocity, and angular velocity, further comprises:
and if the movement of the unmanned ship is abnormal, triggering an alarm, and recording a detection result of the movement of the unmanned ship.
5. An unmanned ship motion detection apparatus, the unmanned ship comprising a control module, comprising:
The receiving unit is used for receiving the throttle value issued by the control module and calculating the longitudinal acting force, the transverse acting force and the torque of the unmanned ship according to the throttle value;
The prediction unit is used for forming an input vector according to the longitudinal acting force, the transverse acting force and the torque, and inputting the input vector into a constructed ship motion model to obtain a predicted output vector, wherein the ship motion model is obtained by training a self-defined three-degree-of-freedom initial ship motion model through a pre-acquired sample longitudinal acting force, a sample transverse acting force and a sample torque;
the detection unit is used for determining a residual norm according to an observation output vector and the prediction output vector, and detecting whether the motion of the unmanned ship is abnormal according to the residual norm, wherein the observation output vector is determined by the acquired transverse speed, longitudinal speed and angular speed;
wherein the prediction unit includes:
The self-defining unit is used for self-defining an inertial mass matrix, a centripetal force and coriolis force coefficient matrix, a resistance coefficient matrix and a torque according to the pre-collected sample longitudinal acting force, sample transverse acting force, sample torque and the mass of the unmanned ship;
the model building unit is used for building the initial ship motion model with three degrees of freedom according to the self-defined inertial mass matrix, the centripetal force and coriolis force coefficient matrix, the resistance coefficient matrix and the torque;
The training unit is used for training the initial ship motion model to obtain the ship motion model;
Wherein the training unit comprises:
the conversion unit is used for representing the initial ship motion model into an initial state space ship motion model in a state space form, wherein the initial state space ship motion model comprises a state vector, a state matrix, an input vector and an input matrix;
A determining unit for determining a state space ship motion model according to the state vector, the state matrix, the input vector and the input matrix, wherein the state space ship motion model comprises
Is determined from the state matrix and the input matrix;
The estimation unit is used for estimating the parameter estimation vector by using a dynamic forgetting factor recursive least square method to obtain a vector estimation value at the current moment, and inputting the vector estimation value into the state space ship motion model to obtain the ship motion model;
Wherein the estimation unit includes:
The acquisition unit is used for acquiring the input vector and the output vector at the current moment in the state space ship motion model, and calculating gain according to the input vector and the output vector;
The first calculation unit is used for calculating the dynamic forgetting factor at the current moment according to the dynamic forgetting factor at the previous moment and the minimum dynamic forgetting factor;
and the updating unit is used for updating the vector estimation value at the current moment according to the gain, the output vector, the dynamic forgetting factor at the current moment and the vector estimation value at the previous moment.
6. An unmanned ship, comprising a memory and a processor, the memory having stored thereon a computer program, the processor implementing the method of any of claims 1-4 when executing the computer program.
7. A computer readable storage medium, characterized in that the storage medium stores a computer program which, when executed by a processor, implements the method according to any of claims 1-4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410150095.9A CN117669396B (en) | 2024-02-02 | 2024-02-02 | Unmanned ship movement detection method and device, unmanned ship and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410150095.9A CN117669396B (en) | 2024-02-02 | 2024-02-02 | Unmanned ship movement detection method and device, unmanned ship and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117669396A CN117669396A (en) | 2024-03-08 |
| CN117669396B true CN117669396B (en) | 2024-05-24 |
Family
ID=90069916
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410150095.9A Active CN117669396B (en) | 2024-02-02 | 2024-02-02 | Unmanned ship movement detection method and device, unmanned ship and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117669396B (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US9248898B1 (en) * | 2013-03-06 | 2016-02-02 | Brunswick Corporation | Systems and methods for controlling speed of a marine vessel |
| CN111123967A (en) * | 2020-01-02 | 2020-05-08 | 南京航空航天大学 | Fixed-wing unmanned aerial vehicle carrier landing control method based on adaptive dynamic inversion |
| CN114995133A (en) * | 2022-05-26 | 2022-09-02 | 武汉理工大学 | Hybrid logic dynamic model-based ship longitudinal queue hybrid predictive control method |
| CN115469553A (en) * | 2022-11-02 | 2022-12-13 | 中国船舶集团有限公司第七〇七研究所 | Ship motion state reconstruction method, device, equipment and storage medium |
| CN116702095A (en) * | 2023-06-01 | 2023-09-05 | 大连海事大学 | Modularized marine ship motion attitude real-time forecasting method |
| WO2023236247A1 (en) * | 2022-06-07 | 2023-12-14 | 东南大学 | Adaptive robust estimation method and system for unmanned surface vessel parameters |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20230356771A1 (en) * | 2022-05-09 | 2023-11-09 | Lubna Khasawneh | Electric power steering lumped parameters estimation using vector tyhpe recursive least squares method with variable forgetting factor |
-
2024
- 2024-02-02 CN CN202410150095.9A patent/CN117669396B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US9248898B1 (en) * | 2013-03-06 | 2016-02-02 | Brunswick Corporation | Systems and methods for controlling speed of a marine vessel |
| CN111123967A (en) * | 2020-01-02 | 2020-05-08 | 南京航空航天大学 | Fixed-wing unmanned aerial vehicle carrier landing control method based on adaptive dynamic inversion |
| CN114995133A (en) * | 2022-05-26 | 2022-09-02 | 武汉理工大学 | Hybrid logic dynamic model-based ship longitudinal queue hybrid predictive control method |
| WO2023236247A1 (en) * | 2022-06-07 | 2023-12-14 | 东南大学 | Adaptive robust estimation method and system for unmanned surface vessel parameters |
| CN115469553A (en) * | 2022-11-02 | 2022-12-13 | 中国船舶集团有限公司第七〇七研究所 | Ship motion state reconstruction method, device, equipment and storage medium |
| CN116702095A (en) * | 2023-06-01 | 2023-09-05 | 大连海事大学 | Modularized marine ship motion attitude real-time forecasting method |
Non-Patent Citations (4)
| Title |
|---|
| Lu, YF (Lu, Yanfei)等.Prognosis of Bearing Degradation Using Gradient Variable Forgetting Factor RLS Combined With Time Series Model.IEEE Access.2018,全文. * |
| 孙功武 ; 谢基榕 ; 王俊轩 ; .基于动态遗忘因子递推最小二乘算法的船舶航向模型辨识.计算机应用.2018,(03),全文. * |
| 杨宇君 ; .卡尔曼滤波在船舶跟踪预测中的研究应用.舰船科学技术.2016,(22),全文. * |
| 沈智鹏 ; 姜仲昊 ; .风帆助航船舶运动模型.交通运输工程学报.2015,(05),全文. * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117669396A (en) | 2024-03-08 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Zhao et al. | Particle filter for fault diagnosis and robust navigation of underwater robot | |
| KR101934368B1 (en) | Autonomous navigation ship controlling apparatus using ensemble artificial neural network combination and method therefor | |
| Shakhtarin et al. | Modification of the nonlinear kalman filter in a correction scheme of aircraft navigation systems | |
| JP5089281B2 (en) | State estimation device and state estimation method | |
| CN108983774B (en) | Single-jet-pump-propelled unmanned surface vehicle self-adaptive course control method based on fuzzy state observer | |
| CN110799949A (en) | Method, apparatus, and computer-readable storage medium having instructions for eliminating redundancy of two or more redundant modules | |
| Blanke et al. | Fault tolerant position-mooring control for offshore vessels | |
| JP6929488B2 (en) | Model predictive control device, model predictive control program, model predictive control system and model predictive control method | |
| CN112432644A (en) | Unmanned ship integrated navigation method based on robust adaptive unscented Kalman filtering | |
| KR101234797B1 (en) | Robot and method for localization of the robot using calculated covariance | |
| CN113984054A (en) | Improved Sage-Husa self-adaptive fusion filtering method based on information anomaly detection and multi-source information fusion equipment | |
| CN117669396B (en) | Unmanned ship movement detection method and device, unmanned ship and storage medium | |
| Zhang et al. | Navigation multisensor fault diagnosis approach for an unmanned surface vessel adopted particle-filter method | |
| US11231694B2 (en) | Information processing device, information processing method, and non-transitory recording medium | |
| US20220269232A1 (en) | Method for computer-implemented determination of a drag coefficient of a wind turbine | |
| CN112987741A (en) | Uncertain interference-oriented ship course intelligent control method | |
| CN111273671A (en) | Non-periodic communication remote observer of intelligent ship | |
| CN114741659B (en) | Adaptive model on-line reconstruction robust filtering method, device and system | |
| KR102412066B1 (en) | State determination method and device, robot, storage medium and computer program | |
| Samar et al. | Embedded estimation of fault parameters in an unmanned aerial vehicle | |
| CN117951817A (en) | Unmanned ship dynamics model identification method, unmanned ship dynamics model identification device, unmanned ship dynamics model identification equipment and unmanned ship dynamics model identification medium | |
| JP3960286B2 (en) | Adaptive controller, adaptive control method, and adaptive control program | |
| Kerhascoët et al. | Speedometer fault detection and GNSS fusion using Kalman filters | |
| CN117367410B (en) | State estimation method, unmanned underwater vehicle and computer readable storage medium | |
| CN117590441B (en) | Integrity protection level calculation method and related equipment |
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 |