CN107894584A - A kind of Intelligent radar sea target detection system and method based on mixing artificial bee colony algorithm - Google Patents

Abstract

The invention discloses a kind of Intelligent radar sea target detection system and method based on mixing artificial bee colony algorithm, system is sequentially connected by radar, database and host computer and formed, radar is irradiated to detected marine site, and radar sea clutter data storage to described database, described host computer are included into data preprocessing module, robust forecasting model modeling module, intelligent optimizing module, module of target detection, model modification module and result display module：Complex characteristics of the present invention for naval target detection, radar clutter data are reconstructed, and target data is detected, mixing artificial bee colony algorithm is introduced, a kind of on-line checking, intelligent high radar marine target detection system and method are realized so as to provide.

Description

It is a kind of based on mixing artificial bee colony algorithm Intelligent radar sea target detection system and Method

Technical field

The present invention relates to radar data process field, especially, is related to a kind of intelligence based on mixing artificial bee colony algorithm Radar marine target detection system and method.

Background technology

Sea clutter, that is, come from the radar raster-displaying echo on sea.In recent decades, with the depth recognized sea clutter Entering, the country such as Germany, Norway attempts to obtain radar wave image using radar observation sea clutter come inverting Wave Information in succession, with Obtain the real time information on sea state, wave height, direction and the cycle of such as wave, so as to further to marine small objects Detected, this is of great significance to offshore activities tool.

Naval target detection technique has consequence, there is provided accurate target decision is to the important of extra large radar work One of task.Radar automatic checkout system makes judgement according to decision rule under given detection threshold value, and strong sea clutter is past Toward the main interference for turning into weak target signal.Detection of the radar under marine environment will be directly influenced by how handling sea clutter Ability：1) ice of navigation by recognition buoy, small pieces, the greasy dirt on sea is swum in, these may carry out potential crisis to navigation band； 3) monitoring illegal fishing is an important task of environmental monitoring.

In traditional target detection, sea clutter is considered as that a kind of noise of interference navigation is removed.However, in radar During to extra large observed object, faint Moving Target Return is usually buried in sea clutter, and signal to noise ratio is relatively low, and radar is not easy to detect Target, while a large amount of spikes of sea clutter can also cause serious false-alarm, and considerable influence is produced to the detection performance of radar.For each For kind for sea police's ring and early warning radar, the main target of research is to improve the detectability of target under sea clutter background.Therefore, Not only there is important theory significance and practical significance, and be also the difficult point and focus of domestic and international naval target detection.

The content of the invention

In order to overcome the shortcomings of that existing radar method for detecting targets at sea can not realize on-line checking, intelligent poor, sheet Invention offer is a kind of to realize on-line checking, the intelligent strong Intelligent radar sea target detection based on mixing artificial bee colony algorithm System and method.

The technical solution adopted for the present invention to solve the technical problems is：

It is a kind of based on mixing artificial bee colony algorithm Intelligent radar sea target detection system, including radar, database with And host computer, radar, database and host computer are sequentially connected, the radar is irradiated to detected marine site, and by Radar Sea Clutter data is stored into described database, and described host computer includes：

Data preprocessing module, to carry out radar sea clutter data prediction, completed using following process：

(1) radar is irradiated to detected marine site, and by radar sea clutter data storage to described database；

(2) N number of radar sea clutter echo-signal amplitude x is gathered from database_iAs training sample, i=1 ..., N；

(3) training sample is normalized, obtains normalizing amplitude

Wherein, minx represents the minimum value in training sample, and maxx represents the maximum in training sample；

(4) training sample after normalization is reconstructed, respectively obtains input matrix X and corresponding output matrix Y：

Wherein, D represents reconstruct dimension, and D is natural number, and D ＜ N, D span are 50-70；

The robust forecasting model modeling module, to establish forecasting model, completed using following process：

X, Y that data preprocessing module is obtained substitute into following linear equation：

Wherein

Weight factor v_iCalculated by following formula：

WhereinIt is error variance ξ_iThe estimation of standard deviation, c₁,c₂For constant；

Solve to obtain function f (x) to be estimated：

Wherein, M is the number of supporting vector, 1_v=[1 ..., 1]^T,Subscript T representing matrixs turn Put,It is Lagrange multiplier, b^*It is amount of bias, K=exp (- | | x_i-x_j||/θ²), wherein i=1 ..., M, j=1 ..., M,With exp (- | | x-x_i||/θ²) be SVMs kernel function, x_jFor j-th of radar sea clutter Echo-signal amplitude, θ are nuclear parameters, and x represents input variable, and γ is penalty coefficient；

Intelligent optimizing module, nuclear parameter θ and penalty coefficient γ using mixing artificial bee colony algorithm to robust forecasting model Optimize, completed using following process：

Step 1：The parameter of initialization mixing artificial bee colony algorithm, if nectar source number P, greatest iteration number iter_max, initially search The minimum value and maximum L in rope space_dAnd U_d；The feasible solution of the positional representation problem in nectar source, because model has two parameter needs Optimization, so position p_iDimension for 2 dimension, as the following formula at random generation nectar source position p_i=(p_i1,p_i2), put primary iteration number Iter=0；

p_ij=L_d+rand()*(U_d-L_d) (i=1,2 ..., P, j=1,2)

Step 2：Employ honeybee EMBE_iNew explanation EMBE is produced with tabu search algorithm_i', and calculate its fitness value

Step 3：Compare EMBE_iAnd EMBE_i', if EMBE_i' it is better than EMBE_i, then EMBE is used_i' replace EMBE_i, and will employ Hire the parameter emlimit of honeybee_iReset；Otherwise, EMBE is kept_i' constant, by parameter emlimit_iAdd 1；

Step 4：Follow honeybee ONBE_iHoneybee EMBE is employed by roulette policy selection_pFollowed, and calculate its fitness Value.

Step 5：By ONBE_iWith employing honeybee EMBE_pIt is compared, if ONBE_iPreferably, then honeybee is employed with following honeybee to exchange Role, that is, use ONBE_iInstead of EMBE_p, and by parameter emlimit_pReset, parameter onlimit_iAdd 1；If EMBE_pIt is poor, then protect Hold it is original employ honeybee constant, and use EMBE_pInstead of ONBE_i, by parameter emlimit_pAdd 1, parameter onlimit_iAdd 1；

Step 6：The solution to be abandoned is determined whether, is replaced originally if it is present searching for a new explanation by search bee Solution；

Step 7：Record the optimal solution of this circulation；

Step 8：Iter=iter+1, judge whether to have been maxed out iterations, optimized parameter exported if meeting, Otherwise step 2 is gone to.

Wherein, nectar source number is 100, the minimum value and maximum 0 and 100 in initial ranging space, maximum iteration 100.

Module of target detection, to carry out target detection, completed using following process：

1) gather D sea clutter echo-signal amplitude in sampling instant t and obtain TX=[x_t-D+1,…,x_t], x_t-D+1Represent the The sea clutter echo-signal amplitude of t-D+1 sampling instants, x_tRepresent the sea clutter echo-signal amplitude of t sampling instants；

2) it is normalized；

3) substitute into the function f (x) to be estimated that robust forecasting model modeling module obtains and sampling instant (t+1) is calculated Sea clutter predicted value.

4) difference e of sea clutter predicted value and radar return measured value is calculated, calculates control limit Q_α：

Wherein, α is confidence level, θ₁,θ₂,θ₃,h₀It is intermediate variable, λ_j ⁱRepresent the i of j-th of characteristic value of covariance matrix Power, k are sample dimensions, C_αIt is the statistics that normal distribution confidence level is α；

5) detection judgement is carried out：Work as e²Difference is more than control limit Q_αWhen, there is target in the point, otherwise without target.

Model modification module, to by the sampling time interval of setting, gathered data, by obtained measured data and model Predicted value compares, if relative error is more than 10%, new data is added into training sample data, updates forecasting model.

Result display module, the testing result of module of target detection to be shown in host computer.

Mesh in Radar Sea used in a kind of Intelligent radar sea target detection system based on mixing artificial bee colony algorithm Detection method is marked, described method comprises the following steps：

1) N number of radar sea clutter echo-signal amplitude x is gathered from database_iAs training sample i=1 ..., N；

2) training sample is normalized, obtains normalizing amplitude

Wherein, minx represents the minimum value in training sample, and maxx represents the maximum in training sample；

3) training sample after normalization is reconstructed, respectively obtains input matrix X and corresponding output matrix Y：

Wherein, D represents reconstruct dimension, and D is natural number, and D ＜ N, D span are 50-70；

4) obtained X, Y are substituted into following linear equation：

Wherein

Weight factor v_iCalculated by following formula：

WhereinIt is error variance ξ_iThe estimation of standard deviation, c₁,c₂For constant；

Solve to obtain function f (x) to be estimated：

Wherein, M is the number of supporting vector, 1_v=[1 ..., 1]^T,K=exp (- | | x_i-x_j||/ θ²), the transposition of subscript T representing matrixs,It is Lagrange multiplier, wherein, i=1 ..., M, j=1 ..., M, b^*It is biasing Amount,With exp (- | | x-x_i||/θ²) be SVMs kernel function, x_jFor j-th of Radar Sea Clutter echo-signal amplitude, θ are nuclear parameters, and x represents input variable, and γ is penalty coefficient；

5) the nuclear parameter θ and penalty coefficient γ of step 4) are optimized with mixing artificial bee colony algorithm, using following mistake Journey is completed：

Step 1：The parameter of initialization mixing artificial bee colony algorithm, if nectar source number P, greatest iteration number iter_max, initially search The minimum value and maximum L in rope space_dAnd U_d；The feasible solution of the positional representation problem in nectar source, because model has two parameter needs Optimization, so position p_iDimension for 2 dimension, as the following formula at random generation nectar source position p_i=(p_i1,p_i2), put primary iteration number Iter=0；

p_ij=L_d+rand()*(U_d-L_d) (i=1,2 ..., P, j=1,2)

Step 2：Employ honeybee EMBE_iNew explanation EMBE is produced with tabu search algorithm_i', and calculate its fitness value

Step 3：Compare EMBE_iAnd EMBE_i', if EMBE_i' it is better than EMBE_i, then EMBE is used_i' replace EMBE_i, and will employ Hire the parameter emlimit of honeybee_iReset；Otherwise, EMBE is kept_i' constant, by parameter emlimit_iAdd 1；

Step 4：Follow honeybee ONBE_iHoneybee EMBE is employed by roulette policy selection_pFollowed, and calculate its fitness Value.

Step 5：By ONBE_iWith employing honeybee EMBE_pIt is compared, if ONBE_iPreferably, then honeybee is employed with following honeybee to exchange Role, that is, use ONBE_iInstead of EMBE_p, and by parameter emlimit_pReset, parameter onlimit_iAdd 1；If EMBE_pIt is poor, then protect Hold it is original employ honeybee constant, and use EMBE_pInstead of ONBE_i, by parameter emlimit_pAdd 1, parameter onlimit_iAdd 1；

Step 6：The solution to be abandoned is determined whether, is replaced originally if it is present searching for a new explanation by search bee Solution；

Step 7：Record the optimal solution of this circulation；

Step 8：Iter=iter+1, judge whether to have been maxed out iterations, optimized parameter exported if meeting, Otherwise step 2 is gone to.

Wherein, nectar source number is 100, the minimum value and maximum 0 and 100 in initial ranging space, maximum iteration 100.

6) gather D sea clutter echo-signal amplitude in sampling instant t and obtain TX=[x_t-D+1,…,x_t], x_t-D+1Represent the The sea clutter echo-signal amplitude of t-D+1 sampling instants, x_tRepresent the sea clutter echo-signal amplitude of t sampling instants；

7) it is normalized；

8) the sea clutter predicted value that sampling instant (t+1) is calculated in the function f (x) to be estimated that step 4) obtains is substituted into.

9) difference e of sea clutter predicted value and radar return measured value is calculated, calculates control limit Q_α：

Wherein, α is confidence level, θ₁,θ₂,θ₃,h₀It is intermediate variable, λ_j ⁱRepresent the i of j-th of characteristic value of covariance matrix Power, k are sample dimensions, C_αIt is the statistics that normal distribution confidence level is α；

10) detection judgement is carried out：Work as e²Difference is more than control limit Q_αWhen, there is target in the point, otherwise without target.

11) the sampling time interval gathered data of setting is pressed, by obtained measured data compared with model prediction value, if Relative error is more than 10%, then new data is added into training sample data, updates forecasting model.

Described method also includes：The testing result of module of target detection is shown in host computer in described step 10) Show.

The present invention technical concept be：The present invention is directed to the chaotic characteristic of radar sea clutter, and radar sea clutter data are entered Row reconstruct, and nonlinear fitting is carried out to the data after reconstruct, the forecasting model of radar sea clutter is established, calculates radar sea clutter Predicted value and measured value difference, when having the error in the presence of target to be noticeably greater than not have target, introduce mixing artificial bee colony Algorithm, so as to realize that the strong intelligent Target under sea clutter background detects.

Beneficial effects of the present invention are mainly manifested in：1st, can on-line checking naval target；2nd, detection method used only needs Less sample；3rd, it is intelligent it is strong, be affected by human factors it is small.

Brief description of the drawings

Fig. 1 is the hardware structure diagram of system proposed by the invention；

Fig. 2 is the functional block diagram of host computer proposed by the invention.

Embodiment

The invention will be further described below in conjunction with the accompanying drawings.The embodiment of the present invention is used for illustrating the present invention, without It is to limit the invention, in the protection domain of spirit and claims of the present invention, any is repaiied to what the present invention made Change and change, both fall within protection scope of the present invention.

Embodiment 1

Reference picture 1, Fig. 2, a kind of Intelligent radar sea target detection system based on mixing artificial bee colony algorithm, including thunder Up to 1, database 2 and host computer 3, radar 1, database 2 and host computer 3 are sequentially connected, and the radar 1 enters to detected marine site Row irradiation, and radar sea clutter data storage to described database 2, described host computer 3 are included：

Data preprocessing module 4, to carry out radar sea clutter data prediction, completed using following process：

(1) radar is irradiated to detected marine site, and by radar sea clutter data storage to described database；

(2) N number of radar sea clutter echo-signal amplitude x is gathered from database_iAs training sample, i=1 ..., N；

(3) training sample is normalized, obtains normalizing amplitude x_i：

Wherein, minx represents the minimum value in training sample, and maxx represents the maximum in training sample；

(4) training sample after normalization is reconstructed, respectively obtains input matrix X and corresponding output matrix Y：

Wherein, D represents reconstruct dimension, and D is natural number, and D ＜ N, D span are 50-70；

The robust forecasting model modeling module, to establish forecasting model, completed using following process：

X, Y that data preprocessing module is obtained substitute into following linear equation：

Wherein

Weight factor v_iCalculated by following formula：

WhereinIt is error variance ξ_iThe estimation of standard deviation, c₁,c₂For constant；

Solve to obtain function f (x) to be estimated：

Wherein, M is the number of supporting vector, 1_v=[1 ..., 1]^T,Subscript T representing matrixs turn Put,It is Lagrange multiplier, b^*It is amount of bias, K=exp (- | | x_i-x_j||/θ²), wherein i=1 ..., M, j=1 ..., M,With exp (- | | x-x_i||/θ²) be SVMs kernel function, x_jFor j-th of radar sea clutter Echo-signal amplitude, θ are nuclear parameters, and x represents input variable, and γ is penalty coefficient；

Intelligent optimizing module 6, to be to the nuclear parameter θ of robust forecasting model and punishment using mixing artificial bee colony algorithm Number γ is optimized, and is completed using following process：

Step 1：The parameter of initialization mixing artificial bee colony algorithm, if nectar source number P, greatest iteration number iter_max, initially search The minimum value and maximum L in rope space_dAnd U_d；The feasible solution of the positional representation problem in nectar source, because model has two parameter needs Optimization, so position p_iDimension for 2 dimension, as the following formula at random generation nectar source position p_i=(p_i1,p_i2), put primary iteration number Iter=0；

p_ij=L_d+rand()*(U_d-L_d) (i=1,2 ..., P, j=1,2)

Step 2：Employ honeybee EMBE_iNew explanation EMBE is produced with tabu search algorithm_i', and calculate its fitness value

Step 3：Compare EMBE_iAnd EMBE_i', if EMBE_i' it is better than EMBE_i, then EMBE is used_i' replace EMBE_i, and will employ Hire the parameter emlimit of honeybee_iReset；Otherwise, EMBE is kept_i' constant, by parameter emlimit_iAdd 1；

Step 4：Follow honeybee ONBE_iHoneybee EMBE is employed by roulette policy selection_pFollowed, and calculate its fitness Value.

Step 5：By ONBE_iWith employing honeybee EMBE_pIt is compared, if ONBE_iPreferably, then honeybee is employed with following honeybee to exchange Role, that is, use ONBE_iInstead of EMBE_p, and by parameter emlimit_pReset, parameter onlimit_iAdd 1；If EMBE_pIt is poor, then protect Hold it is original employ honeybee constant, and use EMBE_pInstead of ONBE_i, by parameter emlimit_pAdd 1, parameter onlimit_iAdd 1；

Step 6：The solution to be abandoned is determined whether, is replaced originally if it is present searching for a new explanation by search bee Solution；

Step 7：Record the optimal solution of this circulation；

Step 8：Iter=iter+1, judge whether to have been maxed out iterations, optimized parameter exported if meeting, Otherwise step 2 is gone to.

Wherein, nectar source number is 100, the minimum value and maximum 0 and 100 in initial ranging space, maximum iteration 100.

Module of target detection 7, to carry out target detection, completed using following process：

1) gather D sea clutter echo-signal amplitude in sampling instant t and obtain TX=[x_t-D+1,…,x_t], x_t-D+1Represent the The sea clutter echo-signal amplitude of t-D+1 sampling instants, x_tRepresent the sea clutter echo-signal amplitude of t sampling instants；

2) it is normalized；

3) substitute into the function f (x) that robust forecasting model modeling module obtains and obtain the sea clutter forecast of sampling instant (t+1) Value；

4) difference e of sea clutter predicted value and radar return measured value is calculated, calculates control limit Q_α：

Wherein, α is confidence level, θ₁,θ₂,θ₃,h₀It is intermediate variable, λ_j ⁱRepresent the i of j-th of characteristic value of covariance matrix Power, k are sample dimensions, C_αIt is the statistics that normal distribution confidence level is α；

5) detection judgement is carried out：Work as e²Difference is more than control limit Q_αWhen, there is target in the point, otherwise without target.

Model modification module 8, to by the sampling time interval gathered data of setting, by obtained measured data and model Predicted value compares, if relative error is more than 10%, new data is added into training sample data, updates forecasting model.

Result display module 9, the testing result of module of target detection to be shown in host computer.

The hardware components of the host computer 3 include：I/O elements, for the collection of data and the transmission of information；Data storage Device, data sample and operational factor needed for storage running etc.；The software program of functional module is realized in program storage, storage； Arithmetic unit, configuration processor, realize the function of specifying；Display module, show the parameter and testing result of setting.

Embodiment 2

Reference picture 1, Fig. 2, a kind of Intelligent radar sea target detection method based on mixing artificial bee colony algorithm are described Method comprises the following steps：

(1) radar is irradiated to detected marine site, and by radar sea clutter data storage to described database；

(2) N number of radar sea clutter echo-signal amplitude x is gathered from database_iAs training sample, i=1 ..., N；

(3) training sample is normalized, obtains normalizing amplitude

Wherein, minx represents the minimum value in training sample, and maxx represents the maximum in training sample；

(4) training sample after normalization is reconstructed, respectively obtains input matrix X and corresponding output matrix Y：

Wherein, D represents reconstruct dimension, and D is natural number, and D ＜ N, D span are 50-70；

(5) obtained X, Y are substituted into following linear equation：

Wherein

Weight factor v_iCalculated by following formula：

WhereinIt is error variance ξ_iThe estimation of standard deviation, c₁,c₂For constant；

Solve to obtain function f (x) to be estimated：

Wherein, M is the number of supporting vector, 1_v=[1 ..., 1]^T,Subscript T representing matrixs turn Put,It is Lagrange multiplier, b^*It is amount of bias, K=exp (- | | x_i-x_j||/θ²), wherein i=1 ..., M, j=1 ..., M,With exp (- | | x-x_i||/θ²) be SVMs kernel function, x_jFor j-th of radar sea clutter Echo-signal amplitude, θ are nuclear parameters, and x represents input variable, and γ is penalty coefficient；

(6) the nuclear parameter θ and penalty coefficient γ of step (5) are optimized with mixing artificial bee colony algorithm, using as follows Process is completed：

(6.1) parameter of initialization mixing artificial bee colony algorithm, if nectar source number P, greatest iteration number iter_max, initial ranging The minimum value and maximum L in space_dAnd U_d；The feasible solution of the positional representation problem in nectar source, because model has two parameters needs excellent Change, so position p_iDimension for 2 dimension, as the following formula at random generation nectar source position p_i=(p_i1,p_i2), put primary iteration number Iter=0；

p_ij=L_d+rand()*(U_d-L_d) (i=1,2 ..., P, j=1,2)

(6.2) honeybee EMBE is employed_iNew explanation EMBE is produced with tabu search algorithm_i', and calculate its fitness value

(6.3) EMBE is compared_iAnd EMBE_i', if EMBE_i' it is better than EMBE_i, then EMBE is used_i' replace EMBE_i, and will employ The parameter emlimit of honeybee_iReset；Otherwise, EMBE is kept_i' constant, by parameter emlimit_iAdd 1；

(6.4) honeybee ONBE is followed_iHoneybee EMBE is employed by roulette policy selection_pFollowed, and calculate its fitness Value.

(6.5) by ONBE_iWith employing honeybee EMBE_pIt is compared, if ONBE_iPreferably, then employ honeybee and follow honeybee to exchange angle Color, that is, use ONBE_iInstead of EMBE_p, and by parameter emlimit_pReset, parameter onlimit_iAdd 1；If EMBE_pIt is poor, then keep It is original to employ honeybee constant, and use EMBE_pInstead of ONBE_i, by parameter emlimit_pAdd 1, parameter onlimit_iAdd 1；

(6.6) solution to be abandoned is determined whether, is replaced originally if it is present searching for a new explanation by search bee Solution；

(6.7) optimal solution of this circulation is recorded；

(6.9) iter=iter+1, judge whether to have been maxed out iterations, optimized parameter exported if meeting, Otherwise step (6.2) is gone to.

Wherein, nectar source number is 100, the minimum value and maximum 0 and 100 in initial ranging space, maximum iteration 100.

(7) gather D sea clutter echo-signal amplitude in sampling instant t and obtain TX=[x_t-D+1,…,x_t], x_t-D+1Represent The sea clutter echo-signal amplitude of t-D+1 sampling instants, x_tRepresent the sea clutter echo-signal amplitude of t sampling instants；

(8) it is normalized；

(9) the sea clutter forecast that sampling instant (t+1) is calculated in the function f (x) to be estimated that step (5) obtains is substituted into Value.

(10) difference e of sea clutter predicted value and radar return measured value is calculated, calculates control limit Q_α：

Wherein, α is confidence level, θ₁,θ₂,θ₃,h₀It is intermediate variable, λ_j ⁱRepresent the i of j-th of characteristic value of covariance matrix Power, k are sample dimensions, C_αIt is the statistics that normal distribution confidence level is α；

(11) detection judgement is carried out：Work as e²Difference is more than control limit Q_αWhen, there is target in the point, otherwise without target.

(12) the sampling time interval gathered data of setting is pressed, by obtained measured data compared with model prediction value, such as Fruit relative error is more than 10%, then new data is added into training sample data, updates forecasting model.

From above example, the present invention establishes Intelligent radar sea target detection system and method, can be online Detect radar target；And detection method used only needs less sample；In addition, reduce the influence of human factor, intelligence Property high, strong robustness.

Claims (2)

1. it is a kind of based on mixing artificial bee colony algorithm Intelligent radar sea target detection system, including radar, database and Host computer, radar, database and host computer are sequentially connected, it is characterised in that：The radar is irradiated to detected marine site, and By radar sea clutter data storage to described database, described host computer includes data preprocessing module, robust forecast mould Type modeling module, intelligent optimizing module, module of target detection, model modification module and result display module：

The data preprocessing module, to carry out radar sea clutter data prediction, completed using following process：

(1) radar is irradiated to detected marine site, and by radar sea clutter data storage to described database；

(2) N number of radar sea clutter echo-signal amplitude x is gathered from database_iAs training sample, i=1 ..., N；

(3) training sample is normalized, obtains normalizing amplitude

<mrow> <msub> <mover> <mi>x</mi> <mo>&amp;OverBar;</mo> </mover> <mi>i</mi> </msub> <mo>=</mo> <mfrac> <mrow> <msub> <mi>x</mi> <mi>i</mi> </msub> <mo>-</mo> <mi>min</mi> <mi>x</mi> </mrow> <mrow> <mi>max</mi> <mi>x</mi> <mo>-</mo> <mi>min</mi> <mi>x</mi> </mrow> </mfrac> </mrow>

Wherein, minx represents the minimum value in training sample, and maxx represents the maximum in training sample；

(4) training sample after normalization is reconstructed, respectively obtains input matrix X and corresponding output matrix Y：

<mrow> <mi>Y</mi> <mo>=</mo> <mfenced open = "[" close = "]"> <mtable> <mtr> <mtd> <msub> <mover> <mi>x</mi> <mo>&amp;OverBar;</mo> </mover> <mrow> <mi>D</mi> <mo>+</mo> <mn>1</mn> </mrow> </msub> </mtd> </mtr> <mtr> <mtd> <msub> <mover> <mi>x</mi> <mo>&amp;OverBar;</mo> </mover> <mrow> <mi>D</mi> <mo>+</mo> <mn>2</mn> </mrow> </msub> </mtd> </mtr> <mtr> <mtd> <mo>.</mo> </mtd> </mtr> <mtr> <mtd> <mo>.</mo> </mtd> </mtr> <mtr> <mtd> <mo>.</mo> </mtd> </mtr> <mtr> <mtd> <msub> <mover> <mi>x</mi> <mo>&amp;OverBar;</mo> </mover> <mi>N</mi> </msub> </mtd> </mtr> </mtable> </mfenced> </mrow>

Wherein, D represents reconstruct dimension, and D is natural number, and D ＜ N, D span are 50-70；

The robust forecasting model modeling module, to establish forecasting model, completed using following process：

X, Y that data preprocessing module is obtained substitute into following linear equation：

<mrow> <mfenced open = "[" close = "]"> <mtable> <mtr> <mtd> <mn>0</mn> </mtd> <mtd> <msubsup> <mn>1</mn> <mi>v</mi> <mi>T</mi> </msubsup> </mtd> </mtr> <mtr> <mtd> <msub> <mn>1</mn> <mi>v</mi> </msub> </mtd> <mtd> <mrow> <mi>K</mi> <mo>+</mo> <msub> <mi>V</mi> <mi>&amp;gamma;</mi> </msub> </mrow> </mtd> </mtr> </mtable> </mfenced> <mfenced open = "[" close = "]"> <mtable> <mtr> <mtd> <msup> <mi>b</mi> <mo>*</mo> </msup> </mtd> </mtr> <mtr> <mtd> <msup> <mi>&amp;alpha;</mi> <mo>*</mo> </msup> </mtd> </mtr> </mtable> </mfenced> <mo>=</mo> <mfenced open = "[" close = "]"> <mtable> <mtr> <mtd> <mn>0</mn> </mtd> </mtr> <mtr> <mtd> <mi>Y</mi> </mtd> </mtr> </mtable> </mfenced> </mrow>

Wherein

Weight factor v_iCalculated by following formula：

WhereinIt is error variance ξ_iThe estimation of standard deviation, c₁,c₂For constant；

Solve to obtain function f (x) to be estimated：

<mrow> <mi>f</mi> <mrow> <mo>(</mo> <mi>x</mi> <mo>)</mo> </mrow> <mo>=</mo> <munderover> <mo>&amp;Sigma;</mo> <mrow> <mi>i</mi> <mo>=</mo> <mn>1</mn> </mrow> <mi>M</mi> </munderover> <msup> <msub> <mi>&amp;alpha;</mi> <mi>i</mi> </msub> <mo>*</mo> </msup> <mi>exp</mi> <mrow> <mo>(</mo> <mo>-</mo> <mo>|</mo> <mo>|</mo> <mi>x</mi> <mo>-</mo> <msub> <mi>x</mi> <mi>i</mi> </msub> <mo>|</mo> <mo>|</mo> <mo>/</mo> <msup> <mi>&amp;theta;</mi> <mn>2</mn> </msup> <mo>)</mo> </mrow> <mo>+</mo> <msup> <mi>b</mi> <mo>*</mo> </msup> </mrow>

Wherein, M is the number of supporting vector, 1_v=[1 ..., 1]^T,The transposition of subscript T representing matrixs,It is Lagrange multiplier, b^*It is amount of bias, K=exp (- | | x_i-x_j||/θ²), wherein i=1 ..., M, j=1 ..., M,With exp (- | | x-x_i||/θ²) be SVMs kernel function, x_jFor j-th of radar sea clutter Echo-signal amplitude, θ are nuclear parameters, and x represents input variable, and γ is penalty coefficient；

The intelligent optimizing module, to be to the nuclear parameter θ of robust forecasting model and punishment using mixing artificial bee colony algorithm Number γ is optimized, and is completed using following process：

(A) parameter of initialization mixing artificial bee colony algorithm, if nectar source number P, greatest iteration number iter_max, initial ranging space Minimum value and maximum L_dAnd U_d；The feasible solution of the positional representation problem in nectar source, because model has two parameters to need to optimize, institute With position p_iDimension for 2 dimension, as the following formula at random generation nectar source position p_i=(p_i1,p_i2), put primary iteration number iter= 0；

p_ij=L_d+rand()*(U_d-L_d) (i=1,2 ..., P, j=1,2)

(B) honeybee EMBE is employed_iNew explanation EMBE is produced with tabu search algorithm_i', and calculate its fitness value

(C) EMBE is compared_iAnd EMBE_i', if EMBE_i' it is better than EMBE_i, then EMBE is used_i' replace EMBE_i, and the ginseng that honeybee will be employed Number emlimit_iReset；Otherwise, EMBE is kept_i' constant, by parameter emlimit_iAdd 1；

(D) honeybee ONBE is followed_iHoneybee EMBE is employed by roulette policy selection_pFollowed, and calculate its fitness value.

(E) by ONBE_iWith employing honeybee EMBE_pIt is compared, if ONBE_iPreferably, then employ honeybee and follow honeybee to exchange role, i.e., Use ONBE_iInstead of EMBE_p, and by parameter emlimit_pReset, parameter onlimit_iAdd 1；If EMBE_pIt is poor, then keep original Employ honeybee constant, and use EMBE_pInstead of ONBE_i, by parameter emlimit_pAdd 1, parameter onlimit_iAdd 1；

(F) solution to be abandoned is determined whether, if it is present searching for a new explanation by search bee replaces original solution；

(G) optimal solution of this circulation is recorded；

(H) iter=iter+1, judge whether to have been maxed out iterations, export optimized parameter if meeting, otherwise turn To step (B).

Wherein, nectar source number is 100, the minimum value and maximum 0 and 100 in initial ranging space, maximum iteration 100.

The module of target detection, to carry out target detection, completed using following process：

(a) gather D sea clutter echo-signal amplitude in sampling instant t and obtain TX=[x_t-D+1,…,x_t], TX represents sea clutter From t-D+1 sampling instants to the signal amplitude matrix of t sampling instants；x_t-D+1Represent the sea clutter of t-D+1 sampling instants Echo-signal amplitude, x_tRepresent the sea clutter echo-signal amplitude of t sampling instants；

(b) it is normalized；

<mrow> <mover> <mrow> <mi>T</mi> <mi>X</mi> </mrow> <mo>&amp;OverBar;</mo> </mover> <mo>=</mo> <mfrac> <mrow> <mi>T</mi> <mi>X</mi> <mo>-</mo> <mi>min</mi> <mi>x</mi> </mrow> <mrow> <mi>max</mi> <mi>x</mi> <mo>-</mo> <mi>min</mi> <mi>x</mi> </mrow> </mfrac> </mrow>

(c) sea that sampling instant (t+1) is calculated in the function f (x) to be estimated that robust forecasting model modeling module obtains is substituted into Clutter predicted value.

(d) difference e of sea clutter predicted value and radar return measured value is calculated, calculates control limit Q_α：

<mrow> <msub> <mi>Q</mi> <mi>&amp;alpha;</mi> </msub> <mo>=</mo> <msub> <mi>&amp;theta;</mi> <mn>1</mn> </msub> <msup> <mrow> <mo>&amp;lsqb;</mo> <mfrac> <mrow> <msub> <mi>C</mi> <mi>&amp;alpha;</mi> </msub> <msub> <mi>h</mi> <mn>0</mn> </msub> <msqrt> <mrow> <mn>2</mn> <msub> <mi>&amp;theta;</mi> <mn>2</mn> </msub> </mrow> </msqrt> </mrow> <msub> <mi>&amp;theta;</mi> <mn>1</mn> </msub> </mfrac> <mo>+</mo> <mn>1</mn> <mo>+</mo> <mfrac> <mrow> <msub> <mi>&amp;theta;</mi> <mn>2</mn> </msub> <msub> <mi>h</mi> <mn>0</mn> </msub> <mrow> <mo>(</mo> <msub> <mi>h</mi> <mn>0</mn> </msub> <mo>-</mo> <mn>1</mn> <mo>)</mo> </mrow> </mrow> <msub> <mi>&amp;theta;</mi> <mn>2</mn> </msub> </mfrac> <mo>&amp;rsqb;</mo> </mrow> <mfrac> <mn>1</mn> <msub> <mi>h</mi> <mn>0</mn> </msub> </mfrac> </msup> </mrow>

<mrow> <msub> <mi>&amp;theta;</mi> <mi>i</mi> </msub> <mo>=</mo> <munderover> <mo>&amp;Sigma;</mo> <mrow> <mi>j</mi> <mo>=</mo> <mi>k</mi> <mo>+</mo> <mn>1</mn> </mrow> <mi>N</mi> </munderover> <msubsup> <mi>&amp;lambda;</mi> <mi>j</mi> <mi>i</mi> </msubsup> <mo>,</mo> <mi>i</mi> <mo>=</mo> <mn>1</mn> <mo>,</mo> <mn>2</mn> <mo>,</mo> <mn>3</mn> </mrow>

<mrow> <msub> <mi>h</mi> <mn>0</mn> </msub> <mo>=</mo> <mn>1</mn> <mo>-</mo> <mfrac> <mrow> <mn>2</mn> <msub> <mi>&amp;theta;</mi> <mn>1</mn> </msub> <msub> <mi>&amp;theta;</mi> <mn>3</mn> </msub> </mrow> <mrow> <mn>3</mn> <msubsup> <mi>&amp;theta;</mi> <mn>2</mn> <mn>2</mn> </msubsup> </mrow> </mfrac> </mrow>

Wherein, α is confidence level, θ₁,θ₂,θ₃,h₀It is intermediate variable, λ_j ⁱThe i powers of j-th of characteristic value of covariance matrix are represented, K is sample dimension, C_αIt is the statistics that normal distribution confidence level is α；

(e) detection judgement is carried out：Work as e²Difference is more than control limit Q_αWhen, there is target in the point, otherwise without target.

The model modification module, to by the sampling time interval gathered data of setting, by obtained measured data and model Predicted value compares, if relative error is more than 10%, new data is added into training sample data, updates forecasting model.

The result display module, the testing result of module of target detection to be shown in host computer.

A kind of 2. radar of the Intelligent radar sea target detection system based on mixing artificial bee colony algorithm described in claim 1 Method for detecting targets at sea, it is characterised in that described method comprises the following steps：

(1) radar is irradiated to detected marine site, and by radar sea clutter data storage to described database；

(2) N number of radar sea clutter echo-signal amplitude x is gathered from database_iAs training sample, i=1 ..., N；

(3) training sample is normalized, obtains normalizing amplitude

<mrow> <msub> <mover> <mi>x</mi> <mo>&amp;OverBar;</mo> </mover> <mi>i</mi> </msub> <mo>=</mo> <mfrac> <mrow> <msub> <mi>x</mi> <mi>i</mi> </msub> <mo>-</mo> <mi>min</mi> <mi>x</mi> </mrow> <mrow> <mi>max</mi> <mi>x</mi> <mo>-</mo> <mi>min</mi> <mi>x</mi> </mrow> </mfrac> </mrow>

Wherein, minx represents the minimum value in training sample, and maxx represents the maximum in training sample；

(4) training sample after normalization is reconstructed, respectively obtains input matrix X and corresponding output matrix Y：

<mrow> <mi>Y</mi> <mo>=</mo> <mfenced open = "[" close = "]"> <mtable> <mtr> <mtd> <msub> <mover> <mi>x</mi> <mo>&amp;OverBar;</mo> </mover> <mrow> <mi>D</mi> <mo>+</mo> <mn>1</mn> </mrow> </msub> </mtd> </mtr> <mtr> <mtd> <msub> <mover> <mi>x</mi> <mo>&amp;OverBar;</mo> </mover> <mrow> <mi>D</mi> <mo>+</mo> <mn>2</mn> </mrow> </msub> </mtd> </mtr> <mtr> <mtd> <mo>.</mo> </mtd> </mtr> <mtr> <mtd> <mo>.</mo> </mtd> </mtr> <mtr> <mtd> <mo>.</mo> </mtd> </mtr> <mtr> <mtd> <msub> <mover> <mi>x</mi> <mo>&amp;OverBar;</mo> </mover> <mi>N</mi> </msub> </mtd> </mtr> </mtable> </mfenced> </mrow>

Wherein, D represents reconstruct dimension, and D is natural number, and D ＜ N, D span are 50-70；

(5) obtained X, Y are substituted into following linear equation：

<mrow> <mfenced open = "[" close = "]"> <mtable> <mtr> <mtd> <mn>0</mn> </mtd> <mtd> <msubsup> <mn>1</mn> <mi>v</mi> <mi>T</mi> </msubsup> </mtd> </mtr> <mtr> <mtd> <msub> <mn>1</mn> <mi>v</mi> </msub> </mtd> <mtd> <mrow> <mi>K</mi> <mo>+</mo> <msub> <mi>V</mi> <mi>&amp;gamma;</mi> </msub> </mrow> </mtd> </mtr> </mtable> </mfenced> <mfenced open = "[" close = "]"> <mtable> <mtr> <mtd> <msup> <mi>b</mi> <mo>*</mo> </msup> </mtd> </mtr> <mtr> <mtd> <msup> <mi>&amp;alpha;</mi> <mo>*</mo> </msup> </mtd> </mtr> </mtable> </mfenced> <mo>=</mo> <mfenced open = "[" close = "]"> <mtable> <mtr> <mtd> <mn>0</mn> </mtd> </mtr> <mtr> <mtd> <mi>Y</mi> </mtd> </mtr> </mtable> </mfenced> </mrow>

Wherein

Weight factor v_iCalculated by following formula：

WhereinIt is error variance ξ_iThe estimation of standard deviation, c₁,c₂For constant；

Solve to obtain function f (x) to be estimated：

<mrow> <mi>f</mi> <mrow> <mo>(</mo> <mi>x</mi> <mo>)</mo> </mrow> <mo>=</mo> <munderover> <mo>&amp;Sigma;</mo> <mrow> <mi>i</mi> <mo>=</mo> <mn>1</mn> </mrow> <mi>M</mi> </munderover> <msup> <msub> <mi>&amp;alpha;</mi> <mi>i</mi> </msub> <mo>*</mo> </msup> <mi>exp</mi> <mrow> <mo>(</mo> <mo>-</mo> <mo>|</mo> <mo>|</mo> <mi>x</mi> <mo>-</mo> <msub> <mi>x</mi> <mi>i</mi> </msub> <mo>|</mo> <mo>|</mo> <mo>/</mo> <msup> <mi>&amp;theta;</mi> <mn>2</mn> </msup> <mo>)</mo> </mrow> <mo>+</mo> <msup> <mi>b</mi> <mo>*</mo> </msup> </mrow>

Wherein, M is the number of supporting vector, 1_v=[1 ..., 1]^T,The transposition of subscript T representing matrixs,It is Lagrange multiplier, b^*It is amount of bias, K=exp (- | | x_i-x_j||/θ²), wherein i=1 ..., M, j=1 ..., M,With exp (- | | x-x_i||/θ²) be SVMs kernel function, x_jFor j-th of radar sea clutter Echo-signal amplitude, θ are nuclear parameters, and x represents input variable, and γ is penalty coefficient；

(6) the nuclear parameter θ and penalty coefficient γ of step (5) are optimized with mixing artificial bee colony algorithm, using following process Complete：

(6.1) parameter of initialization mixing artificial bee colony algorithm, if nectar source number P, greatest iteration number iter_max, initial ranging space Minimum value and maximum L_dAnd U_d；The feasible solution of the positional representation problem in nectar source, because model has two parameters to need to optimize, So position p_iDimension for 2 dimension, as the following formula at random generation nectar source position p_i=(p_i1,p_i2), put primary iteration number iter =0；

p_ij=L_d+rand()*(U_d-L_d) (i=1,2 ..., P, j=1,2)

(6.2) honeybee EMBE is employed_iNew explanation EMBE is produced with tabu search algorithm_i', and calculate its fitness value

(6.3) EMBE is compared_iAnd EMBE_i', if EMBE_i' it is better than EMBE_i, then EMBE is used_i' replace EMBE_i, and honeybee will be employed Parameter emlimit_iReset；Otherwise, EMBE is kept_i' constant, by parameter emlimit_iAdd 1；

(6.4) honeybee ONBE is followed_iHoneybee EMBE is employed by roulette policy selection_pFollowed, and calculate its fitness value.

(6.5) by ONBE_iWith employing honeybee EMBE_pIt is compared, if ONBE_iPreferably, then employ honeybee and follow honeybee to exchange role, Use ONBE_iInstead of EMBE_p, and by parameter emlimit_pReset, parameter onlimit_iAdd 1；If EMBE_pIt is poor, then keep former Employ honeybee constant, and use EMBE_pInstead of ONBE_i, by parameter emlimit_pAdd 1, parameter onlimit_iAdd 1；

(6.6) solution to be abandoned is determined whether, if it is present searching for a new explanation by search bee replaces original solution；

(6.7) optimal solution of this circulation is recorded；

(6.9) iter=iter+1, judge whether to have been maxed out iterations, export optimized parameter if meeting, otherwise Go to step (6.2).

Wherein, nectar source number is 100, the minimum value and maximum 0 and 100 in initial ranging space, maximum iteration 100.

(7) gather D sea clutter echo-signal amplitude in sampling instant t and obtain TX=[x_t-D+1,…,x_t], x_t-D+1Represent t-D The sea clutter echo-signal amplitude of+1 sampling instant, x_tRepresent the sea clutter echo-signal amplitude of t sampling instants；

(8) it is normalized；

<mrow> <mover> <mrow> <mi>T</mi> <mi>X</mi> </mrow> <mo>&amp;OverBar;</mo> </mover> <mo>=</mo> <mfrac> <mrow> <mi>T</mi> <mi>X</mi> <mo>-</mo> <mi>min</mi> <mi>x</mi> </mrow> <mrow> <mi>max</mi> <mi>x</mi> <mo>-</mo> <mi>min</mi> <mi>x</mi> </mrow> </mfrac> </mrow>

(9) the sea clutter predicted value that sampling instant (t+1) is calculated in the function f (x) to be estimated that step (5) obtains is substituted into.

(10) difference e of sea clutter predicted value and radar return measured value is calculated, calculates control limit Q_α：

<mrow> <msub> <mi>Q</mi> <mi>&amp;alpha;</mi> </msub> <mo>=</mo> <msub> <mi>&amp;theta;</mi> <mn>1</mn> </msub> <msup> <mrow> <mo>&amp;lsqb;</mo> <mfrac> <mrow> <msub> <mi>C</mi> <mi>&amp;alpha;</mi> </msub> <msub> <mi>h</mi> <mn>0</mn> </msub> <msqrt> <mrow> <mn>2</mn> <msub> <mi>&amp;theta;</mi> <mn>2</mn> </msub> </mrow> </msqrt> </mrow> <msub> <mi>&amp;theta;</mi> <mn>1</mn> </msub> </mfrac> <mo>+</mo> <mn>1</mn> <mo>+</mo> <mfrac> <mrow> <msub> <mi>&amp;theta;</mi> <mn>2</mn> </msub> <msub> <mi>h</mi> <mn>0</mn> </msub> <mrow> <mo>(</mo> <msub> <mi>h</mi> <mn>0</mn> </msub> <mo>-</mo> <mn>1</mn> <mo>)</mo> </mrow> </mrow> <msub> <mi>&amp;theta;</mi> <mn>2</mn> </msub> </mfrac> <mo>&amp;rsqb;</mo> </mrow> <mfrac> <mn>1</mn> <msub> <mi>h</mi> <mn>0</mn> </msub> </mfrac> </msup> </mrow>

<mrow> <msub> <mi>&amp;theta;</mi> <mi>i</mi> </msub> <mo>=</mo> <munderover> <mo>&amp;Sigma;</mo> <mrow> <mi>j</mi> <mo>=</mo> <mi>k</mi> <mo>+</mo> <mn>1</mn> </mrow> <mi>N</mi> </munderover> <msubsup> <mi>&amp;lambda;</mi> <mi>j</mi> <mi>i</mi> </msubsup> <mo>,</mo> <mi>i</mi> <mo>=</mo> <mn>1</mn> <mo>,</mo> <mn>2</mn> <mo>,</mo> <mn>3</mn> </mrow>

<mrow> <msub> <mi>h</mi> <mn>0</mn> </msub> <mo>=</mo> <mn>1</mn> <mo>-</mo> <mfrac> <mrow> <mn>2</mn> <msub> <mi>&amp;theta;</mi> <mn>1</mn> </msub> <msub> <mi>&amp;theta;</mi> <mn>3</mn> </msub> </mrow> <mrow> <mn>3</mn> <msubsup> <mi>&amp;theta;</mi> <mn>2</mn> <mn>2</mn> </msubsup> </mrow> </mfrac> </mrow>

Wherein, α is confidence level, θ₁,θ₂,θ₃,h₀It is intermediate variable, λ_j ⁱThe i powers of j-th of characteristic value of covariance matrix are represented, K is sample dimension, C_αIt is the statistics that normal distribution confidence level is α；

(11) detection judgement is carried out：Work as e²Difference is more than control limit Q_αWhen, there is target in the point, otherwise without target.

(12) by the sampling time interval gathered data of setting, by obtained measured data compared with model prediction value, if phase 10% is more than to error, then new data is added into training sample data, updates forecasting model.