CN108983178A - A kind of Intelligent radar sea target detection system that agility is adaptive - Google Patents

Abstract

The invention discloses a kind of Intelligent radar sea target detection systems that agility is adaptive, including radar, database and host computer；Radar, database and host computer are sequentially connected, and radar is irradiated detected sea area, and by radar sea clutter data storage into database, and host computer models the sea clutter data in database and detects target；The host computer includes data preprocessing module, dynamic fuzzy neural network modeling module, differential evolution algorithm optimization module, module of target detection, model modification module and result display module.And propose a kind of Intelligent radar sea target detection method based on differential evolution algorithm optimization dynamic fuzzy neural network.The present invention provides a kind of radar marine target detection system and method for realizing that agility is adaptive.

Description

A kind of Intelligent radar sea target detection system that agility is adaptive

Technical field

The present invention relates to radar data process fields, particularly, are related to a kind of Intelligent radar sea mesh that agility is adaptive Mark detection system.

Background technique

Sea clutter, i.e. the radar raster-displaying echo from 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 in succession come inverting Wave Information, with The real time information about sea state, such as wave height, direction and the period of wave are obtained, thus further to marine small objects It is detected, this has a very important significance offshore activities.

Naval target detection technique has consequence, and providing accurate target decision is to the important of extra large radar work One of task.Radar automatic checkout system makes judgement under given detection threshold value according to decision rule, and strong sea clutter is past Toward the main interference for becoming 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 swims in the greasy dirt on sea, these may carry out potential crisis to navigation band； 2) 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 When to extra large observed object, faint Moving Target Return is usually buried in sea clutter, and signal to noise ratio is lower, and radar is not easy to detect Target, while a large amount of spikes of sea clutter also will cause serious false-alarm, produce bigger effect 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, but also be also the difficult point and hot spot of domestic and international naval target detection.

Summary of the invention

In order to overcome the shortcomings of that existing radar method for detecting targets at sea detection efficiency is not high, adaptive ability is poor, this Invention provides a kind of Intelligent radar sea target detection system that agility is adaptive.

The technical solution adopted by the present invention to solve the technical problems is: a kind of Intelligent radar sea mesh that agility is adaptive Mark detection system, including radar, database and host computer；The host computer includes data preprocessing module, dynamic fuzzy Neural net model establishing module, differential evolution algorithm optimization module, module of target detection, model modification module and mould as the result is shown Block, in which:

Data preprocessing module: pre-processing the radar sea clutter data of database input, complete using following process At:

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

(2) training sample is normalized, obtains normalization amplitude

Wherein, min x indicates the minimum value in training sample, and max x indicates the maximum value in training sample；

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

Wherein, D indicates reconstruct dimension, and D is natural number, and the value range of D < N, D are 50-70.

Dynamic fuzzy neural network modeling module: it to establish forecasting model, is completed using following process:

(1) network structure: p-th of training sample X is set_p=[x_p1,x_p2,…,x_pn], wherein n is the number of input variable.

The structure of dynamic fuzzy neural network is formed by 5 layers, and details are as follows:

1st layer is input layer, and each node respectively indicates the linguistic variable of an input.P-th of training sample known to then X_pThere is the linguistic variable x of n input_p1,x_p2,…,x_pn。

2nd layer is membership function layer, and each node respectively represents a membership function, which is with following height This function representation:

Wherein, μ_ijIt is x_piJ-th of membership function, c_ijIt is x_piJ-th of Gauss member function center, σ_jIt is x_pi's The width of j-th of Gauss member function, n are the numbers of input variable, and u is the quantity of membership function, also represent the total rule of system Then count.

3rd layer is T- norm layer, and each node respectively represents the part IF- in a possible fuzzy rule.Therefore, should Node layer reflects number of fuzzy rules；Meanwhile this layer of each node also represents a RBF unit, so number of fuzzy rules with RBF number of nodes is equal.J-th of rule R_jOutput be

Wherein,It is the center of j-th of RBF unit.

4th layer is normalization layer, and the node of this layer is known as N node.N number of nodes is equal with fuzzy rule number of nodes.J-th Node N_jOutput be

5th layer is output layer, and each node in this layer respectively indicates an output variable, which is all input letters Number superposition:

Wherein, y (X_p) it is the corresponding reality output of p-th of training sample, ω_kIt is the part THEN- or k-th of rule Connection weight.

ω_k=α_k0+α_k1x_p1+…+α_knx_pnK=1,2 ..., u (7)

Wherein, α_k0、α_k1、…、α_knIt is the consequent parameter of network.

Wushu (4), formula (5), formula (7) substitute into formula (6), then obtain:

(2) dynamic fuzzy neural network learning algorithm: for every group of observation data (X_p,t_p), wherein X_pIt is p-th of training Sample, t_pIt is the corresponding desired output of p-th of training sample, it is online to carry out system structure and parameter identification, implement step It is as follows:

(2.1) determination can accommodate the effective radius k on boundary_d, according to desired precision previously selected k_eIt is worth, according to rule Then importance and preset constant k_err。

(2.2) as the first group of observation data (X that arrive₁,t₁) when generate the first rule, and determine premise parameter and conclusion Parameter.

(2.3) since second group of observation data, often carry out one group of observation data, calculate d_min.If d_min>k_d, then into Enter step 4；Otherwise, into step 5.

d_min=argmin (d_p(j))=argmin (| | X_p-C_j| |) j=1,2 ..., u (9)

Wherein, X_pIt is p-th of training sample, C_jThe center of existing RBF unit, u be existing number of fuzzy rules or The quantity of RBF unit.

(2.4) calculate | | e_p||.If | | e_p||>k_e, then new rule is generated, otherwise adjust automatically well-regulated ginseng Number.

||e_p| |=| | t_p-y_p|| (10)

Wherein, t_pIt is the observation desired output of data of pth group, y_pIt is the observation actual output of data of pth group.

(2.5) calculate | | e_p||.If | | e_p||>k_e, then the Gaussian function width of rule is adjusted, then adjust consequent parameter, Otherwise the conclusion ginseng of adjust automatically rule.

(2.6) η is calculated_j, η_jIt is the importance of j-th strip rule.If η_j>k_err, then j-th strip rule is deleted, otherwise automatically Adjust the consequent parameter of rule.

(2.7) judge whether to terminate, if returning to step 3 without if, otherwise terminate entire learning process.

Differential evolution algorithm optimization module: for using differential evolution algorithm holding to dynamic fuzzy neural network module Receive the effective radius k on boundary_dValue, the previously selected k according to desired precision_eValue, the preset constant according to regular importance k_errValue optimizes, the specific steps are as follows:

(1) algorithm initialization initializes population in the solution space of problemIt is a Body X_i(k)=[x_i,1(k),x_i,2(k),…,x_i,D(k)], i=1,2 ..., N_pThe solution of characterization problems, D are the dimension of solution space, k Indicate the number of iterations, N_pFor population invariable number.Initialization population should cover entire search space as much as possible, and defined Individual is unanimously randomized in the search space of minimum and maximum bound of parameter limitation, setting minimum and maximum boundary difference For X_min={ x_min,1,…,x_min,DAnd X_max={ x_max,1,…,x_max,D}.In the number of iterations k=1, j-th of i-th of individual The initial value of component generates as the following formula:

x_i,j(0)=x_min,j+rand(0,1)·(x_max,j-x_min,j) (11)

Wherein rand (0,1) is equally distributed random number between 0 to 1.

(2) mutation operation.After being initialized to population, for each individual X_i(k) change can correspondingly be generated Incorgruous amount V_i(k)=[v_i,1(k),v_i,2(k),…,v_i,D(k)], individual X_i(k) object vector, the expression of mutation operation are also referred to as Formula is as follows:

V_i(k)=X_best(k)+F·(X_r1(k)-X_r2(k)),1≤r₁≠r₂≠i≤N_p (12)

Wherein, X_bestIt (k) is the individual vector in population in current kth time iteration with optimal adaptation angle value, ratio Factor F is the positive control parameter for scaling difference vector.

(3) crossover operation.For each pair of object vector X_i(k) and its accordingly make a variation vector V_i(k) crossover operation is carried out, To generate trial vector U_i(k)=[u_i,1(k),u_i,2(k),…,u_i,D(k)].The binomial interleaved scheme is carried out according to the following formula:

Wherein, CR is a customized crossing-over rate, and for value range usually between 0 to 1, it controls the multiplicity of population Property, and algorithm is avoided to fall into local optimum.If the value of certain parameters of newly-generated trial vector has been more than above and below corresponding Limit, then reinitialize it in predefined scope uniformly at random.Then, the fitness of all trial vectors is assessed Value.

(4) selection operation.The fitness of trial vector is compared by the operation with corresponding object vector, and selection is wherein Preferably solution.For minimization problem, the expression formula of selection operation is as follows:

Wherein, f (x) is fitness value.In the evolutionary process of every generation, each individual vector is as target individual one Secondary, algorithm retains defect individual by constantly iterating to calculate, and eliminates worst individual, and guiding search process is to globally optimal solution It approaches.

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

(1) D sea clutter echo-signal amplitude is acquired in sampling instant t obtain TX=[x_t-D+1,…,x_t], x_t-D+1It indicates The sea clutter echo-signal amplitude of t-D+1 sampling instant, x_tIndicate the sea clutter echo-signal amplitude of t sampling instant；

(2) it is normalized:

(3) the sea clutter predicted value that sampling instant (t+1) is calculated in Fuzzy Wavelet Network modeling module is substituted into.

(4) difference e for calculating sea clutter predicted value and radar return measured value calculates control limit Q_α:

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

(5) it carries out detection judgement: working as e²Difference is greater than control limit Q_αWhen, there are targets for the point, otherwise without target.

The adaptive radar marine target detection system of the agility, the host computer further include: model modification module is used To acquire data by the sampling time interval of setting, by obtained measured data compared with model prediction value, if relative error Greater than 10%, then training sample data are added in new data, update forecasting model.And result display module, to by target The testing result of detection module is shown in host computer.

Beneficial effects of the present invention are mainly manifested in: the present invention detects naval target, overcomes in existing Radar Sea The deficiency that object detection method detection efficiency is not high, adaptive ability is poor, the chaotic characteristic foundation for radar sea clutter are dynamic Morphotype pastes neural Network Model for Forecasting, differential evolution optimization algorithm is further introduced into, thus the agility under realizing sea clutter background Adaptive targets detection.

Detailed description of the invention

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.

Specific embodiment

The present invention is illustrated below according to attached drawing.

Referring to Fig.1, Fig. 2, a kind of Intelligent radar sea target detection system that agility is adaptive, including radar 1, database 2 and host computer 3, radar 1, database 2 and host computer 3 be sequentially connected, 1 pair of detected sea area of the radar is irradiated, and will To the database 2, the host computer 3 includes: radar sea clutter data storage

Data preprocessing module 4: pre-processing the radar sea clutter data of database input, complete using following process At:

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

(2) training sample is normalized, obtains normalization amplitude

Wherein, min x indicates the minimum value in training sample, and max x indicates the maximum value in training sample；

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

Wherein, D indicates reconstruct dimension, and D is natural number, and the value range of D < N, D are 50-70.

Dynamic fuzzy neural network modeling module 5: it to establish forecasting model, is completed using following process:

(1) network structure: p-th of training sample X is set_p=[x_p1,x_p2,…,x_pn], wherein n is the number of input variable.

The structure of dynamic fuzzy neural network is formed by 5 layers, and details are as follows:

1st layer is input layer, and each node respectively indicates the linguistic variable of an input.P-th of training sample known to then X_pThere is the linguistic variable x of n input_p1,x_p2,…,x_pn。

2nd layer is membership function layer, and each node respectively represents a membership function, which is with following height This function representation:

Wherein, μ_ijIt is x_piJ-th of membership function, c_ijIt is x_piJ-th of Gauss member function center, σ_jIt is x_pi's The width of j-th of Gauss member function, n are the numbers of input variable, and u is the quantity of membership function, also represent the total rule of system Then count.

3rd layer is T- norm layer, and each node respectively represents the part IF- in a possible fuzzy rule.Therefore, should Node layer reflects number of fuzzy rules；Meanwhile this layer of each node also represents a RBF unit, so number of fuzzy rules with RBF number of nodes is equal.J-th of rule R_jOutput be

Wherein,It is the center of j-th of RBF unit.

4th layer is normalization layer, and the node of this layer is known as N node.N number of nodes is equal with fuzzy rule number of nodes.J-th Node N_jOutput be

5th layer is output layer, and each node in this layer respectively indicates an output variable, which is all input letters Number superposition:

Wherein, y (X_p) it is the corresponding reality output of p-th of training sample, ω_kIt is the part THEN- or k-th of rule Connection weight.

ω_k=α_k0+α_k1x_p1+…+α_knx_pnK=1,2 ..., u (7)

Wherein, α_k0、α_k1、…、α_knIt is the consequent parameter of network.

Wushu (4), formula (5), formula (7) substitute into formula (6), then obtain:

(2) dynamic fuzzy neural network learning algorithm: for every group of observation data (X_p,t_p), wherein X_pIt is p-th of training Sample, t_pIt is the corresponding desired output of p-th of training sample, it is online to carry out system structure and parameter identification, implement step It is as follows:

(2.1) determination can accommodate the effective radius k on boundary_d, according to desired precision previously selected k_eIt is worth, according to rule Then importance and preset constant k_err。

(2.2) as the first group of observation data (X that arrive₁,t₁) when generate the first rule, and determine premise parameter and conclusion Parameter.

(2.3) since second group of observation data, often carry out one group of observation data, calculate d_min.If d_min>k_d, then into Enter step 4；Otherwise, into step 5.

d_min=argmin (d_p(j))=argmin (| | X_p-C_j| |) j=1,2 ..., u (9)

Wherein, X_pIt is p-th of training sample, C_jThe center of existing RBF unit, u be existing number of fuzzy rules or The quantity of RBF unit.

(2.4) calculate | | e_p||.If | | e_p||>k_e, then new rule is generated, otherwise adjust automatically well-regulated ginseng Number.

||e_p| |=| | t_p-y_p|| (10)

Wherein, t_pIt is the observation desired output of data of pth group, y_pIt is the observation actual output of data of pth group.

(2.5) calculate | | e_p||.If | | e_p||>k_e, then the Gaussian function width of rule is adjusted, then adjust consequent parameter, Otherwise the conclusion ginseng of adjust automatically rule.

(2.6) η is calculated_j, η_jIt is the importance of j-th strip rule.If η_j>k_err, then j-th strip rule is deleted, otherwise automatically Adjust the consequent parameter of rule.

(2.7) judge whether to terminate, if returning to step 3 without if, otherwise terminate entire learning process.

Differential evolution algorithm optimization module 6: for using differential evolution algorithm to dynamic fuzzy neural network module can Accommodate the effective radius k on boundary_dValue, the previously selected k according to desired precision_eIt is worth, is preset normal according to regular importance Number k_errValue optimizes, the specific steps are as follows:

(1) algorithm initialization initializes population in the solution space of problemIt is a Body X_i(k)=[x_i,1(k),x_i,2(k),…,x_i,D(k)], i=1,2 ..., N_pThe solution of characterization problems, D are the dimension of solution space, k Indicate the number of iterations, N_pFor population invariable number.Initialization population should cover entire search space as much as possible, and defined Individual is unanimously randomized in the search space of minimum and maximum bound of parameter limitation, setting minimum and maximum boundary difference For X_min={ x_min,1,…,x_min,DAnd X_max={ x_max,1,…,x_max,D}.In the number of iterations k=1, j-th of i-th of individual The initial value of component generates as the following formula:

x_i,j(0)=x_min,j+rand(0,1)·(x_max,j-x_min,j) (11)

Wherein rand (0,1) is equally distributed random number between 0 to 1.

(2) mutation operation.After being initialized to population, for each individual X_i(k) change can correspondingly be generated Incorgruous amount V_i(k)=[v_i,1(k),v_i,2(k),…,v_i,D(k)], individual X_i(k) object vector, the expression of mutation operation are also referred to as Formula is as follows:

V_i(k)=X_best(k)+F·(X_r1(k)-X_r2(k)),1≤r₁≠r₂≠i≤N_p (12)

Wherein, X_bestIt (k) is the individual vector in population in current kth time iteration with optimal adaptation angle value, ratio Factor F is the positive control parameter for scaling difference vector.

(3) crossover operation.For each pair of object vector X_i(k) and its accordingly make a variation vector V_i(k) crossover operation is carried out, To generate trial vector U_i(k)=[u_i,1(k),u_i,2(k),…,u_i,D(k)].The binomial interleaved scheme is carried out according to the following formula:

Wherein, CR is a customized crossing-over rate, and for value range usually between 0 to 1, it controls the multiplicity of population Property, and algorithm is avoided to fall into local optimum.If the value of certain parameters of newly-generated trial vector has been more than above and below corresponding Limit, then reinitialize it in predefined scope uniformly at random.Then, the fitness of all trial vectors is assessed Value.

(4) selection operation.The fitness of trial vector is compared by the operation with corresponding object vector, and selection is wherein Preferably solution.For minimization problem, the expression formula of selection operation is as follows:

Wherein, f (x) is fitness value.In the evolutionary process of every generation, each individual vector is as target individual one Secondary, algorithm retains defect individual by constantly iterating to calculate, and eliminates worst individual, and guiding search process is to globally optimal solution It approaches.

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

(1) D sea clutter echo-signal amplitude is acquired in sampling instant t obtain TX=[x_t-D+1,…,x_t], x_t-D+1It indicates The sea clutter echo-signal amplitude of t-D+1 sampling instant, x_tIndicate the sea clutter echo-signal amplitude of t sampling instant；

(2) it is normalized:

(3) the sea clutter predicted value that sampling instant (t+1) is calculated in Fuzzy Wavelet Network modeling module is substituted into.

(4) difference e for calculating sea clutter predicted value and radar return measured value calculates control limit Q_α:

Wherein, α is confidence level, θ₁,θ₂,θ₃,h₀It is intermediate variable,Indicate i times of j-th of characteristic value of covariance matrix Side, k is sample dimension, C_αIt is the statistics that normal distribution confidence level is α；

(5) it carries out detection judgement: working as e²Difference is greater than control limit Q_αWhen, there are targets for the point, otherwise without target.

Model modification module 8 acquires data by the sampling time interval of setting, by obtained measured data and model prediction Value compares, if relative error is greater than 10%, training sample data is added in new data, update forecasting model.

Result display module 9 shows the testing result of module of target detection in host computer.

The hardware components of the host computer 3 include: I/O element, for the acquisition of data and the transmitting of information；Data storage Device, data sample and operating parameter etc. needed for storage operation；The software program of functional module is realized in program storage, storage； Arithmetic unit executes program, realizes specified function；Display module shows the parameter and testing result of setting.

The embodiment of the present invention is used to illustrate the present invention, rather than limits the invention, in spirit of the invention In scope of protection of the claims, to any modifications and changes that the present invention makes, protection scope of the present invention is both fallen within.

Claims (5)

1. a kind of radar marine target detection system that agility is adaptive, including radar, database and host computer；Radar, number It is sequentially connected according to library and host computer, radar is irradiated detected sea area, and by radar sea clutter data storage to database In, host computer models the sea clutter data in database and detects target；The host computer includes data prediction Module, dynamic fuzzy neural network modeling module, differential evolution algorithm optimization module, module of target detection, model modification module And result display module.

2. quick adaptive radar marine target detection system according to claim 1, which is characterized in that the data are pre- Processing module pre-processes the radar sea clutter data that database inputs, and is completed using following process:

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

(2) training sample is normalized, obtains normalization amplitude

Wherein, min x indicates the minimum value in training sample, and max x indicates the maximum value in training sample；

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

Wherein, D indicates reconstruct dimension, and D is natural number, and the value range of D < N, D are 50-70.

3. quick adaptive radar marine target detection system according to claim 1, which is characterized in that the dynamic analog Neural net model establishing module is pasted, to establish forecasting model, is completed using following process:

(1) network structure: p-th of training sample X is set_p=[x_p1,x_p2,…,x_pn], wherein n is the number of input variable.

The structure of dynamic fuzzy neural network is formed by 5 layers, and details are as follows:

1st layer is input layer, and each node respectively indicates the linguistic variable of an input.P-th of training sample X known to then_pThere is n The linguistic variable x of a input_p1,x_p2,…,x_pn。

2nd layer is membership function layer, and each node respectively represents a membership function, which is with following Gaussian function What number indicated:

Wherein, μ_ijIt is x_piJ-th of membership function, c_ijIt is x_piJ-th of Gauss member function center, σ_jIt is x_piJ-th The width of Gauss member function, n are the numbers of input variable, and u is the quantity of membership function, also represent the total regular number of system.

3rd layer is T- norm layer, and each node respectively represents the part IF- in a possible fuzzy rule.Therefore, the layer section Point reflects number of fuzzy rules；Meanwhile this layer of each node also represents a RBF unit, so number of fuzzy rules and RBF are saved It counts equal.J-th of rule R_jOutput be

Wherein,It is the center of j-th of RBF unit.

4th layer is normalization layer, and the node of this layer is known as N node.N number of nodes is equal with fuzzy rule number of nodes.J-th of node N_jOutput be

5th layer is output layer, and each node in this layer respectively indicates an output variable, which is all input signals Superposition:

Wherein, y (X_p) it is the corresponding reality output of p-th of training sample, ω_kIt is the connection of the part THEN- or k-th of rule Power.

ω_k=α_k0+α_k1x_p1+…+α_knx_pnK=1,2 ..., u (7)

Wherein, α_k0、α_k1、…、α_knIt is the consequent parameter of network.

Wushu (4), formula (5), formula (7) substitute into formula (6), then obtain:

(2) dynamic fuzzy neural network learning algorithm: for every group of observation data (X_p,t_p), wherein X_pIt is p-th of trained sample This, t_pIt is the corresponding desired output of p-th of training sample, online to carry out system structure and parameter identification, specific implementation step is such as Under:

(2.1) determination can accommodate the effective radius k on boundary_d, according to desired precision previously selected k_eIt is worth, according to rule weight The property wanted and preset constant k_err。

(2.2) as the first group of observation data (X that arrive₁,t₁) when generate the first rule, and determine premise parameter and consequent parameter.

(2.3) since second group of observation data, often carry out one group of observation data, calculate d_min.If d_min>k_d, then enter the 4th Step；Otherwise, into step 5.

d_min=arg min (d_p(j))=arg min (| | X_p-C_j| |) j=1,2 ..., u (9)

Wherein, X_pIt is p-th of training sample, C_jIt is the center of existing RBF unit, u is existing number of fuzzy rules or RBF The quantity of unit.

(2.4) calculate | | e_p||.If | | e_p||>k_e, then new rule is generated, otherwise adjust automatically well-regulated parameter.

||e_p| |=| | t_p-y_p|| (10)

Wherein, t_pIt is the observation desired output of data of pth group, y_pIt is the observation actual output of data of pth group.

(2.5) calculate | | e_p||.If | | e_p||>k_e, then the Gaussian function width of rule is adjusted, then adjust consequent parameter, otherwise The conclusion of adjust automatically rule is joined.

(2.6) η is calculated_j, η_jIt is the importance of j-th strip rule.If η_j>k_err, then j-th strip rule is deleted, otherwise adjust automatically The consequent parameter of rule.

(2.7) judge whether to terminate, if returning to step 3 without if, otherwise terminate entire learning process.

4. quick adaptive radar marine target detection system according to claim 1, which is characterized in that the difference into Change algorithm optimization module, for accommodate boundary effectively half using differential evolution algorithm to dynamic fuzzy neural network module Diameter k_dValue, the previously selected k according to desired precision_eValue, the preset constant k according to regular importance_errValue optimizes, Specific step is as follows:

(1) algorithm initialization carries out initialization X={ X to population in the solution space of problem₁,X₂,…,X_Np, individual X_i(k) =[x_i,1(k),x_i,2(k),…,x_i,D(k)], i=1,2 ..., N_pThe solution of characterization problems, D are the dimension of solution space, and k expression changes Generation number, N_pFor population invariable number.Initialization population should cover entire search space as much as possible, and defined minimum and Individual is unanimously randomized in the search space of maximum bound of parameter limitation, setting minimum and maximum boundary is respectively X_min ={ x_min,1,…,x_min,DAnd X_max={ x_max,1,…,x_max,D}.In the number of iterations k=1, j-th of component of i-th of individual Initial value generate as the following formula:

x_i,j(0)=x_min,j+rand(0,1)·(x_max,j-x_min,j) (11)

Wherein rand (0,1) is equally distributed random number between 0 to 1.

(2) mutation operation.After being initialized to population, for each individual X_i(k) a variation vector can correspondingly be generated V_i(k)=[v_i,1(k),v_i,2(k),…,v_i,D(k)], individual X_i(k) it is also referred to as object vector, the expression formula of mutation operation is as follows:

V_i(k)=X_best(k)+F·(X_r1(k)-X_r2(k)),1≤r₁≠r₂≠i≤N_p (12)

Wherein, X_bestIt (k) is the individual vector in population in current kth time iteration with optimal adaptation angle value, scale factor F It is the positive control parameter for scaling difference vector.

(3) crossover operation.For each pair of object vector X_i(k) and its accordingly make a variation vector V_i(k) crossover operation is carried out, with life At trial vector U_i(k)=[u_i,1(k),u_i,2(k),…,u_i,D(k)].The binomial interleaved scheme is carried out according to the following formula:

Wherein, CR is a customized crossing-over rate, and for value range usually between 0 to 1, it controls the diversity of population, And algorithm is avoided to fall into local optimum.If the value of certain parameters of newly-generated trial vector has been more than corresponding bound, Then it is reinitialized uniformly at random in predefined scope.Then, the fitness value of all trial vectors is assessed.

(4) selection operation.The fitness of trial vector is compared by the operation with corresponding object vector, is selected wherein more preferable Solution.For minimization problem, the expression formula of selection operation is as follows:

Wherein, f (x) is fitness value.In the evolutionary process of every generation, each individual vector is primary as target individual, calculates Method retains defect individual, eliminates worst individual, guiding search process is approached to globally optimal solution by constantly iterating to calculate.

5. quick adaptive radar marine target detection system according to claim 1, which is characterized in that the target inspection Module is surveyed, to carry out target detection, is completed using following process:

(1) D sea clutter echo-signal amplitude is acquired in sampling instant t obtain TX=[x_t-D+1,…,x_t], x_t-D+1Indicate t-D The sea clutter echo-signal amplitude of+1 sampling instant, x_tIndicate the sea clutter echo-signal amplitude of t sampling instant；

(2) it is normalized:

(3) the sea clutter predicted value that sampling instant (t+1) is calculated in Fuzzy Wavelet Network modeling module is substituted into.

(4) difference e for calculating sea clutter predicted value and radar return measured value calculates control limit Q_α:

Wherein, α is confidence level, θ₁,θ₂,θ₃,h₀It is intermediate variable,Indicate the i power of j-th of characteristic value of covariance matrix, k It is sample dimension, C_αIt is the statistics that normal distribution confidence level is α；

(5) it carries out detection judgement: working as e²Difference is greater than control limit Q_αWhen, there are targets for the point, otherwise without target.

The adaptive radar marine target detection system of the agility, the host computer further include: model modification module, to press The sampling time interval of setting acquires data, by obtained measured data compared with model prediction value, if relative error is greater than 10%, then training sample data are added in new data, update forecasting model.And result display module, to by target detection The testing result of module is shown in host computer.