CN107330511A - Unmanned boat environment adjustment method based on OS ELM algorithms - Google Patents
Unmanned boat environment adjustment method based on OS ELM algorithms Download PDFInfo
- Publication number
- CN107330511A CN107330511A CN201710417176.0A CN201710417176A CN107330511A CN 107330511 A CN107330511 A CN 107330511A CN 201710417176 A CN201710417176 A CN 201710417176A CN 107330511 A CN107330511 A CN 107330511A
- Authority
- CN
- China
- Prior art keywords
- mrow
- msub
- msubsup
- unmanned boat
- msup
- 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
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/048—Activation functions
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- General Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Evolutionary Computation (AREA)
- Artificial Intelligence (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Health & Medical Sciences (AREA)
- Secondary Cells (AREA)
Abstract
The invention belongs to unmanned boat artificial intelligence field, the unmanned boat environment adjustment method based on OS ELM algorithms is specifically, is comprised the following steps：The experimental situation of unmanned boat is built, unmanned boat aeronautical data is gathered；According to unmanned boat aeronautical data, sample set is gone into；The sample set is handled using OS ELM algorithms, the coupled relation of environment and external environment in unmanned boat is obtained；Matched according to the data that the coupled relation and unmanned boat are gathered in real navigation, to adjust the interior environment and external environment of the unmanned boat in real navigation.It can both study the interior environment and external environment when unmanned boat is navigated by water simultaneously to the present invention, can complete computing in the case of Finite Samples again, and pace of learning is fast, operational precision is high.
Description
Technical field
The invention belongs to unmanned boat artificial intelligence field, the unmanned boat environment regulation specifically based on OS-ELM algorithms
Method.
Background technology
In recent years, application of the artificial intelligence technology in each field is more and more, but by application demand and technical merit
Limitation, the progress of domestic unmanned boat is slower, what most of unmanned boats were all developed as unmanned remote controlled ROV, control
Mode processed is also remote control mode mostly.It is therefore desirable to design one kind to accurately identify marine environment, surrounding objects and energy accurately
Judge the unmanned boat context aware systems of unmanned boat operational configuration, athletic posture, auxiliary unmanned boat is made decisions on one's own, by remote control
Formula develops into intellectual.
Present most of environment perception methods deploy to study just for external environment condition, but in actual applications simultaneously
Not always in this way, also needing to pay close attention to the dynamic property of hull itself while perceiving external environment condition constantly, the inner ring such as navigation posture
Border, internal and external environment, which is organically combined, could improve stability of hull and recognition accuracy.
But the data volume of internal and external environment detecting sensor reception is very big and need to quickly handle, but at the big data of correlation
The research of reason technology needs to be goed deep into.Small part document is had at present to study unmanned boat data processing algorithm, but processing
Data be largely single conclusion, and most of algorithms employ increase number of nodes, original realization are improved into, such as based on used
The operational configuration cognitive method of guiding systems, MEMS gyro Denoising Study based on wavelet analysis method etc..But if control cost,
When reducing number of nodes, operand can increase, and calculation error can increase, and the stability of unmanned boat cannot be guaranteed.
The content of the invention
The technical problem to be solved in the present invention is, overcomes the deficiencies in the prior art to be based on OS-ELM algorithms there is provided one kind
Unmanned boat environment adjustment method, its can both study simultaneously unmanned boat navigation when interior environment and external environment, again can be in sample
Computing is completed in the case that this is limited, and pace of learning is fast, operational precision is high.
A kind of unmanned boat environment adjustment method based on OS-ELM algorithms involved in the present invention, comprises the following steps：Structure
The experimental situation of unmanned boat is built, unmanned boat aeronautical data is gathered；According to unmanned boat aeronautical data, sample set is gone into；Using OS-
ELM algorithms are handled the sample set, obtain the coupled relation of environment and external environment in unmanned boat；Closed according to the coupling
System and the data that are gathered in real navigation of unmanned boat are matched, come adjust in real navigation the interior environment of unmanned boat with
External environment.
Further, the experimental situation for building unmanned boat, is specifically included：Internal environment sensing is installed on unmanned boat
Device and external environment condition sensor；The external environment condition sensor is connected with external environment condition host computer；The internal environment sensor
It is connected by experimental field bus with internal environment host computer；The internal environment host computer and external environment condition host computer respectively with
Server is connected.
Further, the use OS-ELM algorithms are handled the sample set, are specifically included：The sample set
It is transferred into server；The starting stage of sample completion OS-ELM algorithms in m% sample set is taken at random, obtains individual layer feedforward god
The expression formula of output weight matrix β through network, the m% is less than 50%；The sample set of (1-m%) is taken at random, with reference to individual layer
The recurrence formula of the output weight beta matrix of feedforward neural network, completes the study stage of OS-ELM algorithms, the list after improving
The output weight matrix β of layer feedforward neural network.
Yet further, sample completes the starting stage of OS-ELM algorithms, specific bag in the random sample set for taking m%
Include：Setting network Hidden nodes L；Sample the N ' (x of m% in the sample set N (x, t) are taken out at randomj, tj), j=1,2 ... n,
Wherein n>>L；It is random to take hidden node to input weights aiWith threshold values bi, i=1,2 ... L；Obtain hidden layer output function G (ai,bi,
X), so as to obtain the hidden layer output matrix H of neutral net0；Input variable r of equal value is obtained, so as to obtain the defeated of neutral net
Go out matrix R.
Also further, it is described to obtain hidden layer output function G (ai,bi, x), so that the hidden layer for obtaining neutral net is defeated
Go out matrix H0, specifically include：
The hidden layer output function G (ai,bi, calculation formula x) is：
G(ai,bi, x)=g (ai·x+bi) (1)
In formula (1), wherein g is activation primitive, is tried to achieve using Sigmoid functions；aiX represents hidden node input weights
Vectorial aiWith sample vector x inner product；The hidden node input weights aiWith threshold values biValue between [- 1,1]；
The hidden layer output matrix H of the neutral net0Calculation formula be：
In formula (2), g11……gmnRepresent hidden layer output function G (ai,bi, different values x).
Further, it is described to obtain input variable r of equal value, so as to obtain the output matrix R of network, specifically include：
The calculation formula of the input variable r of equal value is：
R=t (3)
The output matrix R of neutral net calculation formula is：
In formula (4), r1…rN0For input variable r of equal value different value.
Preferably, the output weight matrix β of individual layer feedforward neural network expression formula is：
H0β=R (5)
And then obtain equation below：
Preferably, the sample set for taking (1-m%) at random, with reference to the output weight beta matrix of individual layer feedforward neural network
Recurrence formula, complete OS-ELM algorithms the study stage, specifically include：Take out at random and sample is removed in the sample set N (x, t)
This N ' (xj, tj) remaining sample；Remaining described sample is used to update hidden layer output matrix H0With the output square of neutral net
Battle array R；With reference to the recurrence formula of the output weight beta matrix of individual layer feedforward neural network, until the whole values of remaining described sample are complete
Finish.
Preferably, the recurrence formula solution procedure is：
In formula (9),It can be obtained by Woodbury formula：
IfIt can obtain solving β recurrence formula：
Preferably, the coupled relation of environment and external environment is in the unmanned boat：
In formula (12) wherein, xiFor the external environment data in unmanned boat real navigation, tiIn in unmanned boat real navigation
Environmental data, βiFor output weight matrix.
The beneficial effects of the present invention are：
1. real-time processing environment is applied to using OS-ELM algorithms first and perceives measurement data, with information processing rate
It hurry up, the stable advantage of performance.2. unmanned boat external environment condition variable and internal environment variable are combined processing, depth analysis two
Relation between person's data, makes unmanned boat stronger to the adaptability of environment, dynamic property is more preferable.3. OS-ELM Algorithm Learnings are utilized
The characteristics of speed is fast, Generalization Capability is excellent, can be after multiplicity sampling be trained, you can utilize its powerful learning ability, right
Subsequent environments variable is predicted, and is greatly improved the stability of system and intelligent.
Brief description of the drawings
Below in conjunction with drawings and Examples, the invention will be further described, in accompanying drawing：
Fig. 1 is the flow chart of the embodiment of the present invention.
Embodiment
In order to which technical characteristic, purpose and effect to the present invention are more clearly understood from, now compare accompanying drawing and describe in detail
The embodiment of the present invention.
As shown in figure 1, the unmanned boat environment adjustment method of the present invention based on OS-ELM algorithms, including following step
Suddenly：
101st, the experimental situation of unmanned boat is built, unmanned boat aeronautical data is gathered.
Internal environment sensor and external environment condition sensor are installed on unmanned boat；
The external environment condition sensor is connected with external environment condition host computer；
The internal environment sensor is connected by experimental field bus with internal environment host computer；
The internal environment host computer and external environment condition host computer are connected with server respectively.
102nd, according to unmanned boat aeronautical data, sample set is gone into.
103rd, the sample set is handled using OS-ELM algorithms, obtains the coupling of environment and external environment in unmanned boat
Relation；
The sample set is transferred into server.
The starting stage of sample completion OS-ELM algorithms in m% sample set is taken at random, obtains individual layer feedforward neural network
Output weight matrix β expression formula, the m% is less than 50%.
Setting network Hidden nodes L；
Sample the N ' (x of m% in the sample set N (x, t) are taken out at randomj, tj), j=1, wherein 2 ... n, n>>L；
It is random to take hidden node to input weights aiWith threshold values bi, i=1,2 ... L；
Obtain hidden layer output function G (ai,bi, x), so as to obtain the hidden layer output matrix H of neutral net0；
Input variable r of equal value is obtained, so as to obtain the output matrix R of neutral net.
It is described to obtain hidden layer output function G (ai,bi, x), so as to obtain the hidden layer output matrix H of neutral net0, tool
Body includes：
The hidden layer output function G (ai,bi, calculation formula x) is：
G(ai,bi, x)=g (ai·x+bi) (1)
In formula (1), wherein g is activation primitive, is tried to achieve using Sigmoid functions；aiX represents hidden node input weights
Vectorial aiWith sample vector x inner product；The hidden node input weights aiWith threshold values biValue between [- 1,1]；
The hidden layer output matrix H of the neutral net0Calculation formula be：
In formula (2), g11……gmnRepresent hidden layer output function G (ai,bi, different values x).
The calculation formula of the input variable r of equal value is：
R=t (3)
The output matrix R of neutral net calculation formula is：
In formula (4), r1…rN0For input variable r of equal value different value.
The output weight matrix β of individual layer feedforward neural network expression formula is：
H0β=R (5)
And then obtain equation below：
The sample set of (1-m%) is taken at random, with reference to the recurrence formula of the output weight beta matrix of individual layer feedforward neural network,
Complete the study stage of OS-ELM algorithms, the output weight matrix β of the individual layer feedforward neural network after improving.
Take out at random and sample N ' (x are removed in the sample set N (x, t)j, tj) remaining sample；
Remaining described sample is used to update hidden layer output matrix H0With the output matrix R of neutral net；
With reference to the recurrence formula of the output weight beta matrix of individual layer feedforward neural network, until remaining described sample all takes
Value is finished.
The recurrence formula solution procedure is：
In formula (8),It can be obtained by Woodbury formula：
IfIt can obtain solving β recurrence formula：
104th, the data gathered according to the coupled relation and unmanned boat in real navigation are matched, to adjust
The interior environment and external environment of unmanned boat in real navigation.
The coupled relation of environment and external environment is in the unmanned boat：
In formula (12) wherein, xiFor the external environment data in unmanned boat real navigation, tiIn in unmanned boat real navigation
Environmental data, βiFor output weight matrix.
Embodiments of the invention are described above in conjunction with accompanying drawing, but the invention is not limited in above-mentioned specific
Embodiment, above-mentioned embodiment is only schematical, rather than restricted, one of ordinary skill in the art
Under the enlightenment of the present invention, in the case of present inventive concept and scope of the claimed protection is not departed from, it can also make a lot
Form, these are belonged within the protection of the present invention.
Claims (10)
1. a kind of unmanned boat environment adjustment method based on OS-ELM algorithms, it is characterised in that comprise the following steps：
The experimental situation of unmanned boat is built, unmanned boat aeronautical data is gathered；
According to unmanned boat aeronautical data, sample set is gone into；
The sample set is handled using OS-ELM algorithms, the coupled relation of environment and external environment in unmanned boat is obtained；
Matched according to the data that the coupled relation and unmanned boat are gathered in real navigation, to adjust in real navigation
The interior environment and external environment of middle unmanned boat.
2. the unmanned boat environment adjustment method according to claim 1 based on OS-ELM algorithms, it is characterised in that the structure
The experimental situation of unmanned boat is built, is specifically included：
Internal environment sensor and external environment condition sensor are installed on unmanned boat；
The external environment condition sensor is connected with external environment condition host computer；
The internal environment sensor is connected by experimental field bus with internal environment host computer；
The internal environment host computer and external environment condition host computer are connected with server respectively.
3. the unmanned boat environment adjustment method according to claim 1 based on OS-ELM algorithms, it is characterised in that described to adopt
The sample set is handled with OS-ELM algorithms, specifically included：
The sample set is transferred into server；
The starting stage of sample completion OS-ELM algorithms in m% sample set is taken at random, obtains the defeated of individual layer feedforward neural network
Go out weight matrix β expression formula, the m% is less than 50%；
The sample set of (1-m%) is taken at random, with reference to the recurrence formula of the output weight beta matrix of individual layer feedforward neural network, is completed
The study stage of OS-ELM algorithms, the output weight matrix β of the individual layer feedforward neural network after improving.
4. the unmanned boat environment adjustment method according to claim 3 based on OS-ELM algorithms, it is characterised in that it is described with
Machine takes sample in m% sample set to complete the starting stage of OS-ELM algorithms, specifically includes：
Setting network Hidden nodes L；
Sample the N ' (x of m% in the sample set N (x, t) are taken out at randomj, tj), j=1, wherein 2 ... n, n>>L；
It is random to take hidden node to input weights aiWith threshold values bi, i=1,2 ... L；
Obtain hidden layer output function G (ai,bi, x), so as to obtain the hidden layer output matrix H of neutral net0；
Input variable r of equal value is obtained, so as to obtain the output matrix R of neutral net.
5. the unmanned boat environment adjustment method according to claim 4 based on OS-ELM algorithms, it is characterised in that described to ask
Go out hidden layer output function G (ai,bi, x), so as to obtain the hidden layer output matrix H of neutral net0, specifically include：
The hidden layer output function G (ai,bi, calculation formula x) is：
G(ai,bi, x)=g (ai·x+bi) (1)
In formula (1), wherein g is activation primitive, is tried to achieve using Sigmoid functions；aiX represents hidden node input weight vector
aiWith sample vector x inner product；The hidden node input weights aiWith threshold values biValue between [- 1,1]；
The hidden layer output matrix H of the neutral net0Calculation formula be：
In formula (2), g11……gmnRepresent hidden layer output function G (ai,bi, different values x).
6. the unmanned boat environment adjustment method according to claim 5 based on OS-ELM algorithms, it is characterised in that described to ask
Go out input variable r of equal value, so as to obtain the output matrix R of network, specifically include：
The calculation formula of the input variable r of equal value is：
R=t (3)
The output matrix R of neutral net calculation formula is：
<mrow>
<mi>R</mi>
<mo>=</mo>
<msub>
<mfenced open = "(" close = ")">
<mtable>
<mtr>
<mtd>
<msubsup>
<mi>r</mi>
<mn>1</mn>
<mi>T</mi>
</msubsup>
</mtd>
</mtr>
<mtr>
<mtd>
<mo>.</mo>
</mtd>
</mtr>
<mtr>
<mtd>
<mo>.</mo>
</mtd>
</mtr>
<mtr>
<mtd>
<mo>.</mo>
</mtd>
</mtr>
<mtr>
<mtd>
<msubsup>
<mi>r</mi>
<msub>
<mi>N</mi>
<mn>0</mn>
</msub>
<mi>T</mi>
</msubsup>
</mtd>
</mtr>
</mtable>
</mfenced>
<mrow>
<msub>
<mi>N</mi>
<mn>0</mn>
</msub>
<mo>&times;</mo>
<mi>m</mi>
</mrow>
</msub>
<mo>-</mo>
<mo>-</mo>
<mo>-</mo>
<mrow>
<mo>(</mo>
<mn>4</mn>
<mo>)</mo>
</mrow>
</mrow>
In formula (4), r1…rN0For input variable r of equal value different value.
7. the unmanned boat environment adjustment method according to claim 6 based on OS-ELM algorithms, it is characterised in that the list
The output weight matrix β expression formula of layer feedforward neural network is：
H0β=R (5)
And then obtain equation below：
<mrow>
<mi>&beta;</mi>
<mo>=</mo>
<msup>
<mrow>
<mo>(</mo>
<msubsup>
<mi>H</mi>
<mn>0</mn>
<mi>T</mi>
</msubsup>
<msub>
<mi>H</mi>
<mn>0</mn>
</msub>
<mo>)</mo>
</mrow>
<mrow>
<mo>-</mo>
<mn>1</mn>
</mrow>
</msup>
<msubsup>
<mi>H</mi>
<mn>0</mn>
<mi>T</mi>
</msubsup>
<mi>R</mi>
<mo>-</mo>
<mo>-</mo>
<mo>-</mo>
<mrow>
<mo>(</mo>
<mn>6</mn>
<mo>)</mo>
</mrow>
</mrow>
<mrow>
<mi>K</mi>
<mo>=</mo>
<msubsup>
<mi>H</mi>
<mn>0</mn>
<mi>T</mi>
</msubsup>
<msub>
<mi>H</mi>
<mn>0</mn>
</msub>
<mo>-</mo>
<mo>-</mo>
<mo>-</mo>
<mrow>
<mo>(</mo>
<mn>7</mn>
<mo>)</mo>
</mrow>
<mo>.</mo>
</mrow>
8. the unmanned boat environment adjustment method according to claim 7 based on OS-ELM algorithms, it is characterised in that it is described with
Machine takes the sample set of (1-m%), with reference to the recurrence formula of the output weight beta matrix of individual layer feedforward neural network, completes OS-ELM
In the study stage of algorithm, specifically include：
Take out at random and sample N ' (x are removed in the sample set N (x, t)j, tj) remaining sample；
Remaining described sample is used to update hidden layer output matrix H0With the output matrix R of neutral net；
With reference to the recurrence formula of the output weight beta matrix of individual layer feedforward neural network, until the whole values of remaining described sample are complete
Finish.
9. the unmanned boat environment adjustment method according to claim 8 based on OS-ELM algorithms, it is characterised in that described to pass
Apply-official formula solution procedure is：
<mrow>
<msub>
<mi>K</mi>
<mrow>
<mi>k</mi>
<mo>+</mo>
<mn>1</mn>
</mrow>
</msub>
<mo>=</mo>
<msub>
<mi>K</mi>
<mi>k</mi>
</msub>
<mo>+</mo>
<msubsup>
<mi>H</mi>
<mrow>
<mi>k</mi>
<mo>+</mo>
<mn>1</mn>
</mrow>
<mi>T</mi>
</msubsup>
<msub>
<mi>H</mi>
<mrow>
<mi>k</mi>
<mo>+</mo>
<mn>1</mn>
</mrow>
</msub>
<mo>-</mo>
<mo>-</mo>
<mo>-</mo>
<mrow>
<mo>(</mo>
<mn>8</mn>
<mo>)</mo>
</mrow>
</mrow>
<mrow>
<msup>
<mi>&beta;</mi>
<mrow>
<mo>(</mo>
<mi>k</mi>
<mo>+</mo>
<mn>1</mn>
<mo>)</mo>
</mrow>
</msup>
<mo>=</mo>
<msup>
<mi>&beta;</mi>
<mrow>
<mo>(</mo>
<mi>k</mi>
<mo>)</mo>
</mrow>
</msup>
<mo>+</mo>
<msubsup>
<mi>K</mi>
<mrow>
<mi>k</mi>
<mo>+</mo>
<mn>1</mn>
</mrow>
<mrow>
<mo>-</mo>
<mn>1</mn>
</mrow>
</msubsup>
<msubsup>
<mi>H</mi>
<mrow>
<mi>k</mi>
<mo>+</mo>
<mn>1</mn>
</mrow>
<mi>T</mi>
</msubsup>
<mrow>
<mo>(</mo>
<msub>
<mi>R</mi>
<mrow>
<mi>k</mi>
<mo>+</mo>
<mn>1</mn>
</mrow>
</msub>
<mo>-</mo>
<msub>
<mi>H</mi>
<mrow>
<mi>k</mi>
<mo>+</mo>
<mn>1</mn>
</mrow>
</msub>
<msup>
<mi>&beta;</mi>
<mrow>
<mo>(</mo>
<mi>k</mi>
<mo>)</mo>
</mrow>
</msup>
<mo>)</mo>
</mrow>
<mo>-</mo>
<mo>-</mo>
<mo>-</mo>
<mrow>
<mo>(</mo>
<mn>9</mn>
<mo>)</mo>
</mrow>
</mrow>
In formula (9),It can be obtained by Woodbury formula：
<mrow>
<mtable>
<mtr>
<mtd>
<mrow>
<msubsup>
<mi>K</mi>
<mrow>
<mi>k</mi>
<mo>+</mo>
<mn>1</mn>
</mrow>
<mrow>
<mo>-</mo>
<mn>1</mn>
</mrow>
</msubsup>
<mo>=</mo>
<msup>
<mrow>
<mo>(</mo>
<msub>
<mi>K</mi>
<mi>k</mi>
</msub>
<mo>+</mo>
<msubsup>
<mi>H</mi>
<mrow>
<mi>k</mi>
<mo>+</mo>
<mn>1</mn>
</mrow>
<mi>T</mi>
</msubsup>
<msub>
<mi>H</mi>
<mrow>
<mi>k</mi>
<mo>+</mo>
<mn>1</mn>
</mrow>
</msub>
<mo>)</mo>
</mrow>
<mrow>
<mo>-</mo>
<mn>1</mn>
</mrow>
</msup>
</mrow>
</mtd>
</mtr>
<mtr>
<mtd>
<mrow>
<mo>=</mo>
<msubsup>
<mi>K</mi>
<mi>k</mi>
<mrow>
<mo>-</mo>
<mn>1</mn>
</mrow>
</msubsup>
<mo>-</mo>
<msubsup>
<mi>K</mi>
<mi>k</mi>
<mrow>
<mo>-</mo>
<mn>1</mn>
</mrow>
</msubsup>
<msubsup>
<mi>H</mi>
<mrow>
<mi>k</mi>
<mo>+</mo>
<mn>1</mn>
</mrow>
<mi>T</mi>
</msubsup>
<msup>
<mrow>
<mo>(</mo>
<mi>I</mi>
<mo>+</mo>
<msub>
<mi>H</mi>
<mrow>
<mi>k</mi>
<mo>+</mo>
<mn>1</mn>
</mrow>
</msub>
<msubsup>
<mi>K</mi>
<mi>k</mi>
<mrow>
<mo>-</mo>
<mn>1</mn>
</mrow>
</msubsup>
<msubsup>
<mi>H</mi>
<mrow>
<mi>k</mi>
<mo>+</mo>
<mn>1</mn>
</mrow>
<mi>T</mi>
</msubsup>
<mo>)</mo>
</mrow>
<mrow>
<mo>-</mo>
<mn>1</mn>
</mrow>
</msup>
<mo>&times;</mo>
<msub>
<mi>H</mi>
<mrow>
<mi>k</mi>
<mo>+</mo>
<mn>1</mn>
</mrow>
</msub>
<msubsup>
<mi>K</mi>
<mi>k</mi>
<mrow>
<mo>-</mo>
<mn>1</mn>
</mrow>
</msubsup>
</mrow>
</mtd>
</mtr>
</mtable>
<mo>-</mo>
<mo>-</mo>
<mo>-</mo>
<mrow>
<mo>(</mo>
<mn>10</mn>
<mo>)</mo>
</mrow>
</mrow>
IfIt can obtain solving β recurrence formula：
<mrow>
<msub>
<mi>P</mi>
<mrow>
<mi>k</mi>
<mo>+</mo>
<mn>1</mn>
</mrow>
</msub>
<mo>=</mo>
<msub>
<mi>P</mi>
<mi>k</mi>
</msub>
<mo>-</mo>
<msub>
<mi>P</mi>
<mi>k</mi>
</msub>
<msubsup>
<mi>H</mi>
<mrow>
<mi>k</mi>
<mo>+</mo>
<mn>1</mn>
</mrow>
<mi>T</mi>
</msubsup>
<msup>
<mrow>
<mo>(</mo>
<mi>I</mi>
<mo>+</mo>
<msub>
<mi>H</mi>
<mrow>
<mi>k</mi>
<mo>+</mo>
<mn>1</mn>
</mrow>
</msub>
<msub>
<mi>P</mi>
<mi>k</mi>
</msub>
<msubsup>
<mi>H</mi>
<mrow>
<mi>k</mi>
<mo>+</mo>
<mn>1</mn>
</mrow>
<mi>T</mi>
</msubsup>
<mo>)</mo>
</mrow>
<mrow>
<mo>-</mo>
<mn>1</mn>
</mrow>
</msup>
<msub>
<mi>H</mi>
<mrow>
<mi>k</mi>
<mo>+</mo>
<mn>1</mn>
</mrow>
</msub>
<msub>
<mi>P</mi>
<mi>k</mi>
</msub>
<mo>-</mo>
<mo>-</mo>
<mo>-</mo>
<mrow>
<mo>(</mo>
<mn>11</mn>
<mo>)</mo>
</mrow>
</mrow>
<mrow>
<msup>
<mi>&beta;</mi>
<mrow>
<mo>(</mo>
<mi>k</mi>
<mo>+</mo>
<mn>1</mn>
<mo>)</mo>
</mrow>
</msup>
<mo>=</mo>
<msup>
<mi>&beta;</mi>
<mrow>
<mo>(</mo>
<mi>k</mi>
<mo>)</mo>
</mrow>
</msup>
<mo>+</mo>
<msub>
<mi>P</mi>
<mrow>
<mi>k</mi>
<mo>+</mo>
<mn>1</mn>
</mrow>
</msub>
<msubsup>
<mi>H</mi>
<mrow>
<mi>k</mi>
<mo>+</mo>
<mn>1</mn>
</mrow>
<mi>T</mi>
</msubsup>
<mrow>
<mo>(</mo>
<msub>
<mi>R</mi>
<mrow>
<mi>k</mi>
<mo>+</mo>
<mn>1</mn>
</mrow>
</msub>
<mo>-</mo>
<msub>
<mi>H</mi>
<mrow>
<mi>k</mi>
<mo>+</mo>
<mn>1</mn>
</mrow>
</msub>
<msup>
<mi>&beta;</mi>
<mrow>
<mo>(</mo>
<mi>k</mi>
<mo>)</mo>
</mrow>
</msup>
<mo>)</mo>
</mrow>
<mo>-</mo>
<mo>-</mo>
<mo>-</mo>
<mrow>
<mo>(</mo>
<mn>12</mn>
<mo>)</mo>
</mrow>
<mo>.</mo>
</mrow>
10. the unmanned boat environment adjustment method according to claim 9 based on OS-ELM algorithms, it is characterised in that
The coupled relation of environment and external environment is in the unmanned boat：
<mrow>
<msub>
<mi>f</mi>
<mi>L</mi>
</msub>
<mrow>
<mo>(</mo>
<msub>
<mi>x</mi>
<mi>i</mi>
</msub>
<mo>)</mo>
</mrow>
<mo>=</mo>
<munderover>
<mo>&Sigma;</mo>
<mrow>
<mi>i</mi>
<mo>=</mo>
<mn>1</mn>
</mrow>
<mi>L</mi>
</munderover>
<msub>
<mi>&beta;</mi>
<mi>i</mi>
</msub>
<mi>G</mi>
<mrow>
<mo>(</mo>
<msub>
<mi>a</mi>
<mi>i</mi>
</msub>
<mo>,</mo>
<msub>
<mi>b</mi>
<mi>i</mi>
</msub>
<mo>,</mo>
<msub>
<mi>x</mi>
<mi>i</mi>
</msub>
<mo>)</mo>
</mrow>
<mo>=</mo>
<msub>
<mi>t</mi>
<mi>i</mi>
</msub>
<mo>,</mo>
<mi>i</mi>
<mo>=</mo>
<mn>1</mn>
<mo>,</mo>
<mo>...</mo>
<mo>,</mo>
<mi>L</mi>
<mo>-</mo>
<mo>-</mo>
<mo>-</mo>
<mrow>
<mo>(</mo>
<mn>13</mn>
<mo>)</mo>
</mrow>
</mrow>
2
In formula (12) wherein, xiFor the external environment data in unmanned boat real navigation, tiFor interior environment in unmanned boat real navigation
Data, βiFor output weight matrix.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710417176.0A CN107330511A (en) | 2017-06-06 | 2017-06-06 | Unmanned boat environment adjustment method based on OS ELM algorithms |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710417176.0A CN107330511A (en) | 2017-06-06 | 2017-06-06 | Unmanned boat environment adjustment method based on OS ELM algorithms |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN107330511A true CN107330511A (en) | 2017-11-07 |
Family
ID=60194150
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710417176.0A Pending CN107330511A (en) | 2017-06-06 | 2017-06-06 | Unmanned boat environment adjustment method based on OS ELM algorithms |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107330511A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109165684A (en) * | 2018-08-20 | 2019-01-08 | 集美大学 | A kind of unmanned boat sea major class target visual image-recognizing method |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106781371A (en) * | 2016-12-06 | 2017-05-31 | 北京臻迪科技股份有限公司 | A kind of communication system of unmanned boat under water |
-
2017
- 2017-06-06 CN CN201710417176.0A patent/CN107330511A/en active Pending
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106781371A (en) * | 2016-12-06 | 2017-05-31 | 北京臻迪科技股份有限公司 | A kind of communication system of unmanned boat under water |
Non-Patent Citations (2)
| Title |
|---|
| NAN-YING LIANG等: "A Fast and Accurate Online Sequential Learning Algorithm for Feedforward Networks", 《IEEE TRANSACTIONS ON NEURAL NETWORKS》 * |
| 吴恭兴等: "高速无人艇的运动建模及其视景仿真", 《大连海事大学学报》 * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109165684A (en) * | 2018-08-20 | 2019-01-08 | 集美大学 | A kind of unmanned boat sea major class target visual image-recognizing method |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Yan et al. | Robust adaptive sliding mode control of underactuated autonomous underwater vehicles with uncertain dynamics | |
| Wang et al. | Adaptive dynamic surface control for cooperative path following of marine surface vehicles with input saturation | |
| Pan et al. | An efficient neural network approach to tracking control of an autonomous surface vehicle with unknown dynamics | |
| Wang et al. | Neural network based adaptive dynamic surface control for cooperative path following of marine surface vehicles via state and output feedback | |
| Kaiser et al. | Discovering conservation laws from data for control | |
| Wang et al. | Constructive multi-output extreme learning machine with application to large tanker motion dynamics identification | |
| Peng et al. | Neural adaptive steering of an unmanned surface vehicle with measurement noises | |
| Chu et al. | Observer-based adaptive neural network control for a class of remotely operated vehicles | |
| Yang et al. | Adaptive backstepping terminal sliding mode control method based on recurrent neural networks for autonomous underwater vehicle | |
| Xia et al. | Fuzzy neural network-based robust adaptive control for dynamic positioning of underwater vehicles with input dead-zone | |
| Guo et al. | Neural network-based nonlinear sliding-mode control for an AUV without velocity measurements | |
| Wang et al. | Adaptive neural control for cooperative path following of marine surface vehicles: state and output feedback | |
| Zhao et al. | Path planning for autonomous surface vessels based on improved artificial fish swarm algorithm: a further study | |
| Sun et al. | Distributed adaptive neural network constraint containment control for the benthic autonomous underwater vehicles | |
| CN106325064A (en) | Unmanned ship navigational speed and navigational direction control method | |
| CN114879657A (en) | Model-free fully-distributed unmanned ship collaborative time-varying formation control method based on satellite coordinate system | |
| CN109375642B (en) | Energy-saving control method for unmanned aerial vehicle | |
| Qiu et al. | Development of hybrid neural network and current forecasting model based dead reckoning method for accurate prediction of underwater glider position | |
| Liu et al. | Physics-informed identification of marine vehicle dynamics using hydrodynamic dictionary library-inspired adaptive regression | |
| Zhang et al. | Adaptive output feedback control for trajectory tracking of AUV in wave disturbance condition | |
| CN107330511A (en) | Unmanned boat environment adjustment method based on OS ELM algorithms | |
| Bai | Motion-dependent estimation of a spatial vector field with multiple vehicles | |
| Li et al. | Adaptive fixed-time fuzzy formation control for multiple AUV systems considering time-varying tracking error constraints and asymmetric actuator saturation | |
| Zhang et al. | Non-parametric dynamics modeling for unmanned surface vehicle using spectral metric multi-output Gaussian processes learning | |
| Chen et al. | Dynamic event-triggered observer-based control for autonomous underwater vehicles in the Trans-Atlantic Geotraverse hydrothermal field using rotation matrices |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20171107 |
|
| RJ01 | Rejection of invention patent application after publication |