CN103322416B - Pipeline weak leakage detecting device and detecting method based on fuzzy hyperbolic chaos model - Google Patents

Abstract

The invention discloses a pipeline weak leakage detecting device and a detecting method based on a fuzzy hyperbolic chaos model and belongs to the technical field of pipeline detection. Two-stage detection is used, the first-stage detection is abnormal signal detection based on a neural network to mark abnormal signals, and the second-stage detection detects the abnormal signals marked by the first-state detection. By the two-stage detection, the first-stage primary detection is fast, the second-stage detection detects the abnormal signals marked by the first-state detection, and leakage detection capability is increased. The two-stage detection can be implemented on a FPGA (field programmable gate array) hardware platform, and overall system response speed is increased. By the double coupling time-varying delay fuzzy hyperbolic chaos model of the second-stage detection, initial value sensitivity and noise immunity of the chaos system is utilized to increase identification capability of weak leakage signals submerged in noise so as to highlight chaos phenomenon, system requirements for signal to noise ratio is lowered, and weak leakage detection is achieved.

Description

Pipeline weak leak detecting device and based on fuzzy hyperbolic chaotic model detecting method

Technical field

The invention belongs to pipeline inspection technology field, be specifically related to pipeline weak leak detecting device and based on fuzzy hyperbolic chaotic model detecting method.

Background technique

Along with the growth with pipeline active time that increases of oil transport pipeline, the safe condition of pipeline transport allows of no optimist.The degree of aging of a lot of pipeline is relatively more serious, and has entered the leakage accident multiple phase; In addition, the phenomenon that petroleum resources stolen by artificial destruction pipeline is also quite serious, brings major safety risks.Therefore, pipeline leakage testing becomes the important process content of pipe safety production management.

At present, to the moment large discharge Leak testtion such as pipeline generation booster, there is preferably detection technique in real time, but lacked the effective detection to faint leakage signal.Here faint leakage comprises Small leak and gradual leakage two kinds of situations: Small leak refers to that the constant and leakage rate of unit time internal leakage is less than the leakage of current throughput rate 1%; Gradual leakage refers to that starting leakage amount is less than the leakage of current throughput rate 1%, and leakage rate in the unit time increases increasing along with leak time.Existing Leak testtion theory is that ducted interference is regarded as random noise, take noise-reduction method to be filtered by noise, but faint leakage information has also been filtered while filtering interference before faut detection, and causing cannot the faint leakage failure of testing pipes.At present, the discussion for pipeline weak leakage signal context of detection is also little.

Summary of the invention

For the defect that prior art exists, the object of this invention is to provide a kind of pipeline weak leak detecting device and based on fuzzy hyperbolic chaotic model detecting method, through hierarchical detection method, pipe leakage detected.

Technological scheme of the present invention is achieved in that a kind of pipeline weak leak detecting device, comprising:

Pressure sensor module: for gathering the pressure change signal of pipeline head and end, and export to Signal-regulated kinase after pressure signal is converted to electrical signal;

Signal-regulated kinase: carry out filtering, amplification for passing the electrical signal of coming to pressure transducer, and the electrical signal nursed one's health is exported to A/D modular converter;

A/D modular converter: for electrical signal is carried out analog-to-digital conversion, and the digital signal of generation is exported to the Leak testtion module in FPGA central processing unit module;

FPGA central processing unit module: for detecting pipeline leakage signal; FPGA central processing unit module comprises further:

Time-sequence control module: for generation of the work schedule of A/D modular converter;

Leak testtion module: adopt and detect faint leakage signal based on the abnormal signal detection of neuron network and the hierarchical detection pattern based on two coupling Time-varying time-delays fuzzy hyperbolic chaotic model, Leak testtion module comprises further:

Abnormal signal detection sub-module based on neuron network: for carrying out abnormal signal detection to real time data, and abnormal signal is marked;

Faint Leak testtion submodule based on two coupling Time-varying time-delays fuzzy hyperbolic chaotic model: for the abnormal signal of certification mark, judges whether these abnormal signals are leakage signals.

Described pressure sensor module connects FPGA through Signal-regulated kinase, A/D modular converter.

Adopt the realization of pipeline weak leak detecting device based on the detecting method of fuzzy hyperbolic chaotic model, comprise the following steps:

Step 1: gather the instantaneous pressure signal being arranged on the pressure transducer of pipe ends;

Step 2: choose certain time period, certain pipeline section, when normally running, the pipeline pressure data utilizing pipeline weak leak detecting device to collect form historical data;

Step 3: choose a part of data in the historical data from step 2, trains the neural network model detected abnormal signal with these off-line datas;

Step 4: choose another part data again from historical data, calculates smallest embedding dimension number d and the delay time T of these data;

The data represented in the form of vectors are converted to matrix form by step 5: carry out phase space reconfiguration to the historical data selected in step 4;

Step 6: utilize two coupling Time-varying time-delays fuzzy hyperbolic chaotic models that the matrix off-line training obtained in step 5 detects faint leakage signal;

Step 7: pipeline pressure real time data is sent into neural network model and detects in real time abnormal signal, the change according to real time data is constantly adjusted renewal by the variable weight of neural network model, the predicted value u of neural network model ₁and with u ₁corresponding actual value x ₁between difference E ₁with threshold value T ₁compare, if difference E ₁> threshold value T ₁, then detect abnormal signal, abnormal signal is marked, perform step 8, otherwise, then repeated execution of steps 7;

Step 8: the signal marked through step 7 is sent into and based on two coupling Time-varying time-delays fuzzy hyperbolic chaotic model, faint leakage is detected in real time, constantly renewal is adjusted by according to the change of the marking signal passed in step 7, the predicted value u of two coupling Time-varying time-delays fuzzy hyperbolic chaotic model based on the variable weight of two coupling Time-varying time-delays fuzzy hyperbolic chaotic model and coupling factor ₂and with u ₂corresponding actual value x ₂between difference E ₂with threshold value T ₂compare, if E ₂> threshold value T ₂, then faint leakage signal is detected.

The representation of the two coupling Time-varying time-delays fuzzy hyperbolic chaotic models described in step 6 is:

$\left\{\begin{array}{c}{X}_n=F\left(X_{n-1}\right)+\mathrm{\ϵ}(Y_n-\mathrm{hF}\left(X_{n-1}\right))\\ Y_n=F\left(Y_{n-1}\right)+\mathrm{\ϵ}(X_n-\mathrm{hF}\left(Y_{n-1}\right))\end{array}\right.$

Wherein, X _n, Y _nfor system variable, h is power gain, and ε is coupling factor, and when ε=0, the coupled relation of two systems disappears; When ε ≠ 0, follow according to Chaotic Synchronization Theory, select to make Y _n→ X _nthe ε set up is as coupling factor; Two F () functions are above the function expression of Time-varying time-delays fuzzy hyperbolic model, two system variable X _n, Y _ncan be tending towards rapidly synchronous under the impact of coupling.

The expression of F () function is as follows:

$\stackrel{\·}{x}=A\tanh \left(\mathrm{Kx}\right)+\mathrm{Bu}$

Wherein, A, B are normal matrix, and K is diagonal matrix.

Detecting step based on the faint Leak testtion module of two coupling Time-varying time-delays fuzzy hyperbolic chaotic model described in step 8 is as follows:

(1) selected threshold value T ₂: leakage signal error being less than comprise in the data of threshold value is more few better, and threshold value is now best threshold value, reduces rate of false alarm;

(2) the marking signal x passed in step 7 _ias the input of two coupling Time-varying time-delays fuzzy hyperbolic chaotic model, the prediction obtaining next step exports

(3) utilize in step 7 and pass the marking signal of coming in real time and train two coupling Time-varying time-delays fuzzy hyperbolic chaotic model in real time, the weights obtained are used for the weights of two coupling Time-varying time-delays fuzzy hyperbolic chaotic models that next step prediction of real-time update uses; Also coupling factor ε will be adjusted, because the change of weights causes X while weighed value adjusting _n, Y _nthe change of function expression, can make both no longer synchronous, so will adjust coupling factor, make X _n→ Y _n;

(4) the actual value x of subsequent time (the i-th+1 moment) _i+1with its predicted value predicated error as the foundation of faut detection, if E ₂<T ₂, then there is not faint leakage; Otherwise, then there is faint leakage.

(5) repeat (3)-(5), complete the detection to flag data.

Beneficial effect of the present invention: (1) adopts hierarchical detection method to detect pipe leakage, the first order is detects based on the abnormal signal of neuron network, and marked by abnormal signal, the second level is only detected the abnormal signal that the first order marks; Detected by above-mentioned two-stage signal, the initial survey of the first order, achieve speed fast, the second level is detected the abnormal signal of the first order again, improves the detectability to leakage signal.And this hierarchical detection method realizes under the happy hardware platform of FPG, the multibus parallel processing mechanism utilizing FPG happy, improves entire system speed of response.(2) two coupling Time-varying time-delays fuzzy hyperbolic chaotic models of the second level, utilize the receptance of chaos system to initial value and the immunocompetence to noise, improve the recognition capability to the faint leakage signal be submerged in noise.(3) model of the second level, adopts the form of two coupling, can highlight chaos phenomenon, reduces system to the requirement of signal to noise ratio, thus realizes the detection to faint leakage.

Accompanying drawing explanation

Fig. 1 is one embodiment of the present invention pipeline weak leak detecting device structured flowchart;

Fig. 2 is the circuit theory diagrams of one embodiment of the present invention Signal-regulated kinase;

Fig. 3 is the interface circuit figure of one embodiment of the present invention pleasure/D conversion chip and FPG pleasure;

Fig. 4 is the middle Leak testtion modular structure block diagram arranged in one embodiment of the present invention FPG happy central processing unit module;

Fig. 5 is the interface circuit figure of happy M and the FPG pleasure of one embodiment of the present invention SDR;

Fig. 6 is that one embodiment of the present invention is based on fuzzy hyperbolic chaotic model detecting method flow chart;

Fig. 7 is the two coupling Time-varying time-delays fuzzy hyperbolic chaotic model structured flowcharts of one embodiment of the present invention based on fuzzy hyperbolic chaotic model.

Embodiment

Below in conjunction with accompanying drawing, embodiments of the present invention are described in further detail.

Pipeline weak leak detecting device structured flowchart is given, as shown in Figure 1 in present embodiment.This device comprises pressure sensor module, Signal-regulated kinase, A/D modular converter and FPGA central processing unit module, and wherein FPGA central processing unit module comprises time-sequence control module and Leak testtion module further.Wherein, the model of the model of pressure sensor module to be the model of PT500-502, A/D modular converter be ADS7844, FPGA central processing unit module is EP3C25Q240C8.

The pipe ends that pressure transducer is arranged on, pressure transducer gathers the instantaneous pressure data of pipeline, the input end of Signal-regulated kinase is exported to by output terminal, the output terminal of Signal-regulated kinase connects the input end of A/D modular converter, the output terminal of A/D modular converter connects the input end of FPGA central processing unit module, an output terminal of FPGA central processing module connects alarm unit, and another output terminal connects A/D modular converter.

Pressure signal is converted to voltage signal by pressure sensor module, because this pipeline leakage testing device is, the force value that collects is as research object, so the remolding sensitivity of pressure transducer is more important, but high-precision sensitivity also cannot the noise of filtering pressure signal itself again, as long as therefore select suitable sensor, too high sensitivity need not be pursued.

The circuit theory diagrams of Signal-regulated kinase as shown in Figure 2, this module realizes filtering and the amplification of signal, the output circuit filtering first after filtering of pressure transducer, then the inverting input of operational amplifier is connected to through the resistance R2 of a 10K, in-phase input end connects the reference voltage of 2.5V, one end of the output terminal contact resistance R3 of operational amplifier, one end of resistance R1 and one end of electric capacity C2, the other end of resistance R3 connects the input end of A/D conversion chip as the output terminal of Signal-regulated kinase, the other end of resistance R1 connected the inverting input calculating amplifier, the other end ground connection of electric capacity C2.In present embodiment, the model of operational amplifier is AD824.

The interface circuit figure of A/D conversion chip and FPGA as shown in Figure 3, voltage signal is converted to digital signal by A/D conversion chip, the output terminal that 6 of A/D conversion chip are different connects the self-defined I/O mouth of the happy time-sequence control module of FPG respectively, namely the DCLK end of A/D conversion chip connects the happy I/O.23 end of FPG, the CS end of A/D conversion chip connects I/O.24 end, the Din end of A/D conversion chip connects I/O.25 end, the Busy end of A/D conversion chip connects I/O.26 end, the Dout end of A/D conversion chip connects I/O.27 end, wherein, the model of A/D conversion chip is ADS7844, the model of FPGA is EP3C25Q240C8.

In FPGA central processing unit module, Leak testtion modular structure block diagram as shown in Figure 4, and Leak testtion module is divided into following four modules: history data store module 2, real time data cache module 1, neural metwork training and abnormal signal testing module 3 and two Coupled Chaotic model training and faint Leak testtion module 4.History data store module 2 is made up of ROM in sheet; Real time data cache module 1 is made up of the outer SDRAM of sheet.

Neural metwork training and abnormal signal testing module 3 comprise as lower unit: logic control element 301, arithmetic element 302, weights regulon 304 and weight storage unit 303.Two Coupled Chaotic model training and faint Leak testtion module 4 comprise as lower unit: logic control element 401, arithmetic element 402, weights regulon 404, weight storage unit 403 and coupling factor regulon 405.Neural metwork training and abnormal signal testing module 3 are substantially identical with the workflow of two Coupled Chaotic model trainings and faint Leak testtion module 4: logic control element output signal comprises CLK clock, address signal, control signal.When control signal is 0, carry out the training of model, training completes, control signal becomes 1, carry out the real-time detection of signal, signal through arithmetic element prediction of output value, after predicted value compares with actual value, by weights regulon real-time update weights, the weights after renewal carry out the storage of new weights under the control of CLK clock and address signal; Unique difference is, two Coupled Chaotic model training and faint Leak testtion module add the adjustment of coupling factor while weights regulate, and the coupling factor after renewal stores under the control of CLK clock and address signal.Wherein, the model of the outer happy M of SDR of sheet is HY57V641620.The interface circuit figure of outer SDRAM and the FPGA of sheet as scheme attached shown in.The CLK end of the outer SDRAM of sheet connects the CLK0 end of FPGA, the BA0 end of the outer SDRAM of sheet connects the BA0 end of FPGA, the BA1 end of the outer SDRAM of sheet connects the BA1 of FPGA, the nCS end of the outer SDRAM of sheet connects the nCS end of FPGA, the nWE end of the outer SDRAM of sheet connects the nWE end of FPGA, the nCAS end of the outer SDRAM of sheet connects the nCAS end of FPGA, the nRAS end of the outer SDRAM of sheet connects the nCAS end of FPGA, the A11-A0 end of the outer SDRAM of sheet connects the ADDR11-ADDA0 end of FPGA, the DQ15-DQ0 end of the outer SDRAM of sheet connects the DATA15-DATA0 end of FPGA, the LDQM/UDQM end of the outer SDRAM of sheet connects the LDQM/UDQM end of FPGA.

In present embodiment, pipeline weak leak detecting device working procedure is as follows: pressure sensor module gathers the pressure change signal of pipeline head and end, and the electrical signal of conversion is exported to Signal-regulated kinase.Electrical signal carries out, after filtering, amplification, sending into A/D modular converter through Signal-regulated kinase; Under the control of the time-sequence control module in the happy central processing unit module of FPG, produce the work schedule of A/D modular converter, control A/D modular converter realizes mould/number (A/D) conversion, and the Leak testtion module sent in FPGA central processing unit module carries out faint leakage signal detection by the digital signal after conversion.Leak testtion module utilizes pipeline pressure time series to have (comprising the mixed signal of faint leakage signal, Chaos Variable and other random noises) feature of chaotic characteristic, first, set up neural network model and two coupling Time-varying time-delays fuzzy hyperbolic chaotic model, and utilize pipeline pressure historical data to train; Secondly, suitable threshold value is set, carries out detecting based on the abnormal signal of neuron network to pipeline pressure time series, mark abnormal signal; Finally, carry out detecting based on the faint leakage signal of two coupling Time-varying time-delays fuzzy hyperbolic chaotic model to the abnormal signal be labeled.

Adopt the realization of pipeline weak leak detecting device based on the detecting method of fuzzy hyperbolic chaotic model, its flow process as shown in Figure 6, comprises the following steps:

Step 1: gather the instantaneous pressure signal being arranged on the pressure transducer of pipe ends;

Step 2: choose certain time period, certain pipeline section, when normally running, the pipeline pressure data utilizing pipeline weak leak detecting device to collect form historical data, and the number of historical data is N;

Step 3: choose a n in the historical data from step 2 ₁data, n ₁<N, uses this n ₁the neural network model that individual data off-line training detects abnormal signal.

Step 4: choose n in the historical data from step 2 ₂individual data, n ₂for removing n in N ₁historical data afterwards, calculates this n ₂the smallest embedding dimension number d of individual data and delay time T, the smallest embedding dimension of different pieces of information collection is different with retard time.

Step 5: to the n in step 4 ₂individual data carry out phase space reconfiguration, n originally ₂individual data are with n ₂the vector form of × 1 represents, phase space reconfiguration is exactly convert original vector form to matrix form, and the ranks number of this matrix is relevant with the smallest embedding dimension number of trying to achieve in step 4 and retard time, and the line number of matrix equals n ₂-(d-1) τ, matrix column number equals smallest embedding dimension number d;

Step 6: utilize two coupling Time-varying time-delays fuzzy hyperbolic chaotic models that the matrix off-line training obtained in step 5 detects faint leakage signal, formula is as follows:

$\left\{\begin{array}{c}{X}_n=F\left(X_{n-1}\right)+\mathrm{\&epsiv;}(Y_n-\mathrm{hF}\left(X_{n-1}\right))\\ Y_n=F\left(Y_{n-1}\right)+\mathrm{\&epsiv;}(X_n-\mathrm{hF}\left(Y_{n-1}\right))\end{array}\right.$

Wherein, X _n, Y _nfor system variable, h is power gain, and ε is coupling factor, and when ε=0, the coupled relation of two systems disappears; When ε ≠ 0, follow according to Chaotic Synchronization Theory, select to make Y _n→ X _nthe ε set up is as coupling factor; Two F () functions are above the function expression of Time-varying time-delays fuzzy hyperbolic model, two system variable X _n, Y _ncan be tending towards rapidly synchronous under the impact of coupling.

The expression of F () function is as follows:

$\stackrel{\&CenterDot;}{x}=A\tanh \left(\mathrm{Kx}\right)+\mathrm{Bu}$

Wherein, A, B are normal matrix, and K is diagonal matrix.

As shown in Figure 7, two Time-varying time-delays fuzzy hyperbolic chaotic models form two coupling Time-varying time-delays fuzzy hyperbolic chaotic model, and the input of two models is respectively X _n-1, Y _n-1, export and be respectively F (X _n-1), F (Y _n-1), F (X _n-1) and F (Y _n-1) separately after the amplification of h times, regulate whether reach synchronous by coupling factor ε, the output after two Model coupling is respectively X _n, Y _n.

Step 7: pipeline pressure real time data is sent into neural network model and detects in real time abnormal signal, the change according to real time data is constantly adjusted renewal by the variable weight of neural network model, the predicted value u of neural network model ₁and with u ₁corresponding actual value x ₁between difference E ₁with threshold value T ₁compare, if difference E ₁> threshold value T ₁, then detect abnormal signal, abnormal signal is marked, otherwise, then repeated execution of steps 7;

Step 8: the signal marked through step 7 is sent into and based on two coupling Time-varying time-delays fuzzy hyperbolic chaotic model, faint leakage is detected in real time, constantly renewal is adjusted by according to the change of the marking signal passed in step 7, the predicted value u of two coupling Time-varying time-delays fuzzy hyperbolic chaotic model based on the variable weight of two coupling Time-varying time-delays fuzzy hyperbolic chaotic model and coupling factor ₂and with u ₂corresponding actual value x ₂between difference E ₂with threshold value T ₂compare, if E ₂> threshold value T ₂, then faint leakage signal is detected.Detailed process is as follows:

(1) selected threshold value T ₂: leakage signal error being less than comprise in the data of threshold value is more few better, and threshold value is now best threshold value, reduces rate of false alarm;

(2) the marking signal x passed in step 7 _ias the input of two coupling Time-varying time-delays fuzzy hyperbolic chaotic model, the prediction obtaining next step exports

(3) utilize in step 7 and pass the marking signal of coming in real time and train two coupling Time-varying time-delays fuzzy hyperbolic chaotic model in real time, the weights obtained are used for the weights of two coupling Time-varying time-delays fuzzy hyperbolic chaotic models that next step prediction of real-time update uses; Also coupling factor ε will be adjusted, because the change of weights causes X while weighed value adjusting _n, Y _nthe change of function expression, can make both no longer synchronous, so will adjust coupling factor, make X _n→ Y _n;

(4) the actual value x of subsequent time (the i-th+1 moment) _i+1with its predicted value predicated error as the foundation of faut detection, if E ₂<T ₂, then there is not faint leakage; Otherwise, then there is faint leakage.

(5) repeat (3)-(5), complete the detection to flag data.

Below in conjunction with concrete example, explanation is once done to above-mentioned detecting step:

The first step, 500 data composition historical datas when selected pipeline normally runs, suppose that the representation of this historical data is for (a ₁, a ₂, a ₃..., a ₅₀₀), these data are all pressure datas, and unit is MPa;

Second step, selects front 100 data as (a ₁, a ₂, a ₃..., a ₁₀₀) off-line training neural network model that abnormal signal is detected;

3rd step, calculates smallest embedding dimension number d and the delay time T of rear 400 data, and it is attached for adopting pseudo-nearest neighbour method to try to achieve d, and adopting autocorrelation analysis method to try to achieve τ is 4.Will with vector form (a ₁₀₁, a ₁₀₂, a ₁₀₃..., a ₅₀₀) phase space that the data reconstruction that represents becomes τ in the matrix form to represent, make (b ₁, b ₂, b ₃..., b ₄₀₀)=(a ₁₀₁, a ₁₀₂, a ₁₀₃..., a ₅₀₀), then matrix form is; V=(X ₁, X ₂..., X _t) ^t, t=484, this matrix is 484 × 5 matrixes.Wherein, X _i=(b _i, b _i+4, b _i+8, b _i+12, b _i+16), i=1,2,3 .., t.Further, this matrix V off-line training two coupling Time-varying time-delays fuzzy hyperbolic chaotic model is utilized;

4th step, by real time data x _isend into neural network model to detect in real time abnormal signal, find out abnormal signal y _j, by y _jsend into two coupling Time-varying time-delays fuzzy hyperbolic chaotic model and carry out leakage signal detection, if the leakage signal of being judged as, then report to the police, otherwise, continue the new real time data detecting input,

Although the foregoing describe the specific embodiment of the present invention, the those skilled in the art in related domain should be appreciated that these only illustrate, can make various changes or modifications, and do not deviate from principle of the present invention and essence to these mode of executions.Scope of the present invention is only defined by the appended claims.

Claims (4)

1. a pipeline weak leak detecting device, is characterized in that: comprising:

Pressure sensor module: for gathering the pressure change signal of pipeline head and end, and export to Signal-regulated kinase after pressure signal is converted to electrical signal;

Signal-regulated kinase: carry out filtering, amplification for passing the electrical signal of coming to pressure transducer, and the electrical signal nursed one's health is exported to A/D modular converter;

A/D modular converter: for electrical signal is carried out analog-to-digital conversion, and the digital signal of generation is exported to the Leak testtion module in FPGA central processing unit module;

FPGA central processing unit module: for detecting pipeline leakage signal; FPGA central processing unit module comprises further:

Time-sequence control module: for generation of the work schedule of A/D modular converter;

Leak testtion module: adopt and detect faint leakage signal based on the abnormal signal detection of neuron network and the hierarchical detection pattern based on two coupling Time-varying time-delays fuzzy hyperbolic chaotic model, Leak testtion module comprises further:

Abnormal signal detection sub-module based on neuron network: for carrying out abnormal signal detection to real time data, and abnormal signal is marked;

Faint Leak testtion submodule based on two coupling Time-varying time-delays fuzzy hyperbolic chaotic model: for the abnormal signal of certification mark, judges whether these abnormal signals are leakage signals;

The representation of described two coupling Time-varying time-delays fuzzy hyperbolic chaotic models is:

$\left\{\begin{array}{c}{X}_n=F\left(X_{n-1}\right)+\mathrm{\&epsiv;}(Y_n-\mathrm{hF}\left(X_{n-1}\right))\\ Y_n=F\left(Y_{n-1}\right)+\mathrm{\&epsiv;}(X_n-\mathrm{hF}\left(Y_{n-1}\right))\end{array}\right.$

Wherein, X _n, Y _nfor system variable, h is power gain, and ε is coupling factor, and when ε=0, the coupled relation of two systems disappears; When ε ≠ 0, follow according to Chaotic Synchronization Theory, select to make Y _n→ X _nthe ε set up is as coupling factor; Two F () functions are above the function expression of Time-varying time-delays fuzzy hyperbolic model, two system variable X _n, Y _ncan be tending towards rapidly synchronous under the impact of coupling;

The expression of F () function is as follows:

$\stackrel{\&CenterDot;}{x}=A\tanh \left(\mathrm{Kx}\right)+\mathrm{Bu}$

Wherein, A, B are normal matrix, and K is diagonal matrix.

2. pipeline weak leak detecting device according to claim 1, is characterized in that: described pressure sensor module connects FPGA through Signal-regulated kinase, A/D modular converter.

3. adopt pipeline weak leak detecting device according to claim 1 realization based on the detecting method of fuzzy hyperbolic chaotic model, it is characterized in that: comprise the following steps:

Step 1: gather the instantaneous pressure signal being arranged on the pressure transducer of pipe ends;

Step 2: choose certain time period, certain pipeline section, when normally running, the pipeline pressure data utilizing pipeline weak leak detecting device to collect form historical data;

Step 3: choose a part of data in the historical data from step 2, trains the neural network model detected abnormal signal with these off-line datas;

Step 4: choose another part data again from historical data, calculates smallest embedding dimension number d and the delay time T of these data;

The data represented in the form of vectors are converted to matrix form by step 5: carry out phase space reconfiguration to the historical data selected in step 4;

Step 6: utilize two coupling Time-varying time-delays fuzzy hyperbolic chaotic models that the matrix off-line training obtained in step 5 detects faint leakage signal;

Step 7: pipeline pressure real time data is sent into neural network model and detects in real time abnormal signal, the change according to real time data is constantly adjusted renewal by the variable weight of neural network model, the predicted value u of neural network model ₁and with u ₁corresponding actual value _x1between difference E ₁with threshold value T ₁compare, if difference E ₁> threshold value T ₁, then detect abnormal signal, abnormal signal is marked, perform step 8, otherwise, then repeated execution of steps 7;

Step 8: the signal marked through step 7 is sent into and based on two coupling Time-varying time-delays fuzzy hyperbolic chaotic model, faint leakage is detected in real time, constantly renewal is adjusted by according to the change of the marking signal passed in step 7, the predicted value u of two coupling Time-varying time-delays fuzzy hyperbolic chaotic model based on the variable weight of two coupling Time-varying time-delays fuzzy hyperbolic chaotic model and coupling factor ₂and with u ₂corresponding actual value x ₂between difference E ₂with threshold value T ₂compare, if E ₂> threshold value T ₂, then faint leakage signal is detected.

4. the detecting method based on fuzzy hyperbolic chaotic model according to claim 3, is characterized in that: the detecting step based on the faint Leak testtion module of two coupling Time-varying time-delays fuzzy hyperbolic chaotic model described in step 8 is as follows:

(1) selected threshold value T ₂: leakage signal error being less than comprise in the data of threshold value is more few better, and threshold value is now best threshold value, reduces rate of false alarm;

(2) the marking signal x passed in step 7 _ias the input of two coupling Time-varying time-delays fuzzy hyperbolic chaotic model, the prediction obtaining next step exports

(3) utilize in step 7 and pass the marking signal of coming in real time and train two coupling Time-varying time-delays fuzzy hyperbolic chaotic model in real time, the weights obtained are used for the weights of two coupling Time-varying time-delays fuzzy hyperbolic chaotic models that next step prediction of real-time update uses; Also coupling factor ε will be adjusted, because the change of weights causes X while weighed value adjusting _n, Y _nthe change of function expression, can make both no longer synchronous, so will adjust coupling factor, make X _n→ Y _n;

(4) the actual value x of subsequent time _i+1with its predicted value predicated error as the foundation of faut detection, if E ₂< T ₂, then there is not faint leakage; Otherwise, then there is faint leakage;

(5) repeat (3)-(5), complete the detection to flag data.