CN102879475B - Identification system for fatigue damage state of 16 manganese steel bearing member based on PCA and TDF - Google Patents

Abstract

The invention discloses an identification system for a fatigue damage state of a 16 manganese steel bearing member based on PCA and TDF. The system is composed of a plurality of acoustic emission transducers (6), a plurality of preamplifiers (5), an acoustic emission meter (4) and a fatigue damage detection unit (1) of the 16 Mn steel bearing member, wherein the fatigue damage detection unit (1) of the 16 Mn steel bearing member comprises a filtering module (11), a first stage data fusion module (12) and a second stage data fusion module (13). The system employs a combination of principal component analysis and fatigue damage category, obtains damage degree marks of each transducer in a data space by performing neural network training in the data space, then performs local diagnosis on information of each acoustic emission transducer by using the damage degree marks, further constructs elementary probability values of the data fusion with the output results of the neural network, and finally carries out diagnosis for the fatigue damage state by using a combination relationship of the data fusion. The system can identify and diagnose the fatigue damage state in a fatigue process of the 16 manganese steel, and further provides basis for reliable operation of the16 manganese steel.

Description

Based on PCA and TDF, 16 manganese steel bearing members are carried out the recognition system of Fatigue Damage States

Technical field

The present invention relates to a kind of in-service 16Mn steel force-bearing part Fatigue Damage States during one's term of military service be known to method for distinguishing.More particularly, refer to and a kind ofly first adopt principal component analysis (PCA) (PCA) to build different data spaces according to its damage type to the data of acoustic emission transducer collection, the training of carrying out neural network in data space obtains the injury tolerance Sign module of each transducer in data space, then apply this module the acoustic emission data of in-service 16Mn steel force-bearing part Real-time Collection are carried out to two-stage data fusion (TDF), belong to which kind of Fatigue Damage States thereby identify in-service 16Mn steel force-bearing part.

Background technology

Bank equipment in the heavy mechanical equipment of harbour: as ship loader, ship unloaders, grab claw, often apply 16 manganese steel as crucial bearing member.Bank equipment in use for some time, as the faulted condition of 16 manganese steel of main bearing member to causing material impact the serviceable life of whole bank equipment.

16Mn steel (16 manganese steel) is a kind of low alloy steel growing up in conjunction with china natural resources situation, is widely used.16Mn steel construction is under arms after the regular hour; often can there are some failure accidents; and damage is the main cause that causes its inefficacy; to make effective identification to its faulted condition for this reason; in time, correctly evaluate the degree of injury of 16Mn steel force-bearing part, for its safe operation and life prediction provide foundation.

Acoustic emission (Acoustic Emission Technique), because having the advantages such as dynamic, real-time detection, has been widely used in the damage check of structure and member.Practice shows, material is in the different phase of fatigue process, can there are a series of different variations in its characteristics of Acoustic Emission, that is to say the fatigue damage stage that 16Mn steel force-bearing part is different, different acoustic emission signals will be had, and the transformation of faulted condition, often cause the variation of the multiple parameters of acoustic emission, simultaneously a certain parameter changes and can be caused by multiple faulted condition again, so be necessary to adopt the Data fusion technique of many acoustic emission transducers, make full use of many acoustic emission transducers data resource in different time and space, adopt computer technology to the many acoustic emission transducers observation data obtaining by time series, under certain criterion, analyze, comprehensively, domination and use, obtain the consistance of measurand is explained and described, and then realize corresponding decision-making and estimation, system is obtained than its each ingredient information more fully.Therefore the present invention introduces Data fusion technique in 16Mn steel force-bearing part faulted condition recognition system, sets up principal component analysis (PCA), and the diagnostic system that data fusion and artificial neural network combine is identified, diagnosed 16Mn steel force-bearing part faulted condition.

Principal component analysis (PCA) also claims principal component analysis.Principal component analysis (PCA) utilizes the thought of dimensionality reduction, multiple indexs is converted into the multivariate statistical method of several overall targets under the prerequisite of loss little information.Conventionally the index changing into is called to major component, wherein each major component is the linear combination of original variable, and uncorrelated mutually between each major component, makes major component have some more superior performance than original variable." principal component analysis (PCA) " quotes publishing house of the Renmin University of China in " multivariate statistical analysis " of the 2nd edition publication September in 2008, the content introduction of the 152nd page to the 154th page.

Neural network is an a kind of nonlinear system of the people's of simulation thinking.Radial basis function (RBF) neural network is that basis has local modulation in people's cortex and overlapping receptive field proposes, and is called again local receptive field neural network.It is a kind of three layers of feed-forward type network model that comprise input layer, hidden layer and output layer.Because RBF network structure is simple, and have the ability of approaching arbitrary continuation function with arbitrary accuracy, learning rate is fast, so be more and more widely used in every field.

Along with modern industry is day by day to extensive, high-level efficiency development, as the large-scale bank crane tool of the important Logistics Equipment in harbour, there is following feature:

(1) equipment is old, having a lot of goliaths is the sixties to the seventies of China's self design or from Eastern Europe import, also having minority is from second-hand equipment beautiful, the import of Deng state, considers by 20～25 years designed lives, and a lot of equipment has also entered be on active service later stage or extended active duty stage;

(2) task weight, along with production-scale expansion, and the hysteresis of crane renewal, the work of many cranes is increasingly heavy, and the situation of overload also happens occasionally;

(3) current damage detecting method is immature, the part sampling Detection that the methods such as ultrasound examination and magnetic detection are carried out crane, and blindness is large, it is long to be prone to the cycle undetected and that detect, and workload is large, somewhat expensive;

(4) early warning evaluating system imperfection, the analysis and distinguishing technology of application can't be made early warning accurately and safety assessment to the damage of crane bearing member at present.

Therefore, for guaranteeing that crane safety moves reliably, must detect bearing member, judge the Fatigue Damage States of bearing member, thereby carry out safety assessment.

Summary of the invention

In order to reduce bank equipment personnel injury, equipment loss and the economic loss that fracture causes that in use happen suddenly, the present invention proposes a kind of principal component analysis (PCA) that adopts, and the method that neural network and two-stage data fusion combine is identified the Fatigue Damage States of in-service 16Mn steel force-bearing part.First this fatigue state recognition system adopts principal component analysis (PCA) to build two data spaces to different damage data in training sample, the information that adopts neural net method to collect multi-Channel Acoustic transmitting transducer is carried out neural metwork training under two data spaces, obtains the injury tolerance Sign module for judging 16Mn steel force-bearing part different fatigue faulted condition; Then the neural network Output rusults of this module under two data spaces is carried out carrying out one-level data fusion after basic probability assignment, again multiple transducer one-level data fusion results are carried out to secondary data fusion, obtain data fusion module, and then data fusion module is embedded in the tired recognition system of 16Mn steel force-bearing part.Be embedded with data fusion module of the present invention in working order under, can identify in-service 16Mn steel force-bearing part different fatigue faulted condition, and the result identifying is made to early warning.

The present invention is a kind of principal component analysis (PCA) that adopts, the technology that neural network and data fusion combine carries out to 16Mn steel force-bearing part the recognition system that Fatigue Damage States is identified, this system includes multiple acoustic emission transducers (6), multichannel prime amplifier (5), an Acoustic radiating instrument (4), it is characterized in that: also include a 16Mn steel force-bearing part fatigue damage detecting unit (1);

16Mn steel force-bearing part fatigue damage detecting unit (1) includes filtering module (11) and one-level data fusion module (12), secondary data Fusion Module (13), wherein, filtering module (11) has data filtering processing module (11A) and waveform filtering processing module (11B), one-level data fusion module (12) has the first data space (12A), the second data space (12B), the first injury tolerance Sign module (12C), the second injury tolerance Sign module (12D), D-S Evidence Combination Methods module (12E);

Acoustic emission transducer (6) and prime amplifier (5) are for supporting the use, the output terminal that is each acoustic emission transducer (6) is connected with the input end of a prime amplifier (5), the output terminal of each prime amplifier (5) is connected on the input information interface of Acoustic radiating instrument (4), and this input information interface is used for receiving multichannel demblee form amplification message 16Mn steel force-bearing part fatigue damage detecting unit (1) is embedded in the storer of Acoustic radiating instrument (4);

Acoustic emission transducer (6), for gathering in-service 16Mn steel force-bearing part at acquisition time T _xdemblee form information burst type information in section

Prime amplifier (5), for the demblee form information to receiving after amplifying 40dB, become demblee form amplification message

Acoustic radiating instrument (4) is for the demblee form amplification message to receiving after A/D conversion, become digital demblee form information export to 16Mn steel force-bearing part fatigue damage detecting unit (1);

Data filtering processing module (11A) in the filtering module (11) of 16Mn steel force-bearing part fatigue damage detecting unit (1) is to the digital demblee form information receiving carry out parametric filtering, filter after electromagnetic noise and neighbourhood noise, purify and obtain acoustic emission fatigue damage preliminary information then waveform filtering processing module (11B) is to acoustic emission fatigue damage preliminary information carry out waveform filtering, obtain acoustic emission fatigue damage information $f_{11B}^{T_X}=(e,A,C,R,D);$

Transducer is received to the fatigue damage information of 16Mn steel force-bearing part carry out acquisition time T _xaccumulated process in section, then normalization obtains normalization accumulation of fatigue damage information f _11B', by f _11B' obtain score matrix f separately at the first data space (12A) and the lower projection of the second data space (12B) respectively _12A=(t _a1, t _a2, t _a3, t _a4, t _a5) and f _12B=(t _b1, t _b2, t _b3, t _b4, t _b5), score matrix f _12A=(t _a1, t _a2, t _a3, t _a4, t _a5) obtain the neural network output f in the first data space through the first injury tolerance Sign module (12C) processing _12C=[f _{iD, a}(A ₁) f _{iD, a}(A ₂)], score matrix f _12B=(t _b1, t _b2, t _b3, t _b4, t _b5) process the neural network output f obtaining in the second data space through the second injury tolerance Sign module (12D) _12D=[f _{iD, b}(A ₁) f _{iD, b}(A ₂)]; By f _12Cand f _12Dcarry out the related coefficient assignment of each node, the f after assignment _12Cand f _12Dcarry out basic probability assignment, then carry out D-S Evidence Combination Methods module (12E) and process the data fusion result m that obtains single transducer _iD(B _j), then D-S Evidence Combination Methods module (12E) result of all transducers is carried out to secondary data fusion (13) obtain data fusion result m (C _j), this result is exported fatigue damage identifying information D to alarm unit (3) after resolve damage grade evaluation unit (2).

The present invention is a kind of according to acoustic emission information, adopt neural network, under the data space of principal component analysis (PCA) structure, faulted condition is carried out to part identification, then application data integration technology is carried out two-stage fusion to Neural Network Diagnosis result, identifying and diagnosing goes out the final Fatigue Damage States of 16Mn steel force-bearing part, and the advantage of this recognition system is:

(A) capture card in employing Acoustic radiating instrument is to using acoustic emission information (the energy e of the acoustic emission transducer on 16Mn steel force-bearing part after a while _s, measuring amplitude A _s, Ring-down count C _s, rise time R _s, duration D _s) gather, and input information using this relevant information as the recognition system of acoustic emission neural network, make the present invention in acoustic emission detection process, can be by Acoustic radiating instrument to acoustic emission transducer information, then according to the variation of acoustic emission information parameter and waveform, identifying is damage information, or noise information.

(B) adopt principal component analysis (PCA) to construct different data spaces according to tired damage mode type, under each data space, faulted condition is carried out to part identification by neural network, through two-stage data fusion output diagnostic result, the difference that takes full advantage of signal between different type of impairments is identified damage mode.

(C) can be comprehensive, arrange and use Monitoring Data multiple, polytype acoustic emission transducer, make full use of the information of each acoustic emission transducer, increased reliability and the accuracy of diagnostic result, improved the adaptive faculty of diagnostic system.

(D) the comprehensive identifying and diagnosing system that neural network and Data-Fusion theory combine, has certain fault-tolerant ability, can meet the requirement of steel construction complication system damage.

Brief description of the drawings

Fig. 1 is the structured flowchart of 16Mn steel force-bearing part fatigue damage recognition system of the present invention.

Fig. 2 is the structured flowchart of fatigue damage detecting unit in 16Mn steel force-bearing part fatigue damage recognition system of the present invention.

Embodiment

Below in conjunction with drawings and Examples, the present invention is described in further detail.

In Fatigue Damage States pattern, include: the stable expansion of fatigue crack faulted condition, fatigue crack unstable propagation faulted condition.In-service bearing member is generally worked under the stable expansion of fatigue crack faulted condition, when in fatigue crack unstable propagation faulted condition, this bearing member damage is more serious, user should carry out real-time emphasis detection, monitoring or replacing to bearing member, therefore bearing member is carried out to Fatigue Damage States and detect and can prevent and the generation of minimizing accident, the personnel's injury, equipment loss and the economic loss that cause to reduce burst fracture.

Shown in Fig. 1, Fig. 2, generally also claim sensor by multiple acoustic emission transducer 6(for the fatigue damage recognition system of 16Mn steel force-bearing part), multichannel prime amplifier 5, Acoustic radiating instrument 4,16Mn steel force-bearing part fatigue damage detecting unit 1, damage grade evaluation unit 2 and an alarm unit 3 form; Wherein, 16Mn steel force-bearing part fatigue damage detecting unit 1 includes filtering module 11 and one-level data fusion module 12, secondary data Fusion Module 13;

Wherein, filtering module 11 includes data filtering processing module 11A and waveform filtering processing module 11B;

Wherein, one-level data fusion module 12 includes the first data space 12A, the second data space 12B, the first injury tolerance Sign module 12C, the second injury tolerance Sign module 12D, D-S Evidence Combination Methods module 12E.

16Mn steel force-bearing part fatigue damage detecting unit 1 adopts Matlab language (version R2011b) exploitation.16Mn steel force-bearing part fatigue damage detecting unit 1 is embedded in the storer of Acoustic radiating instrument 4.

In the present invention, acoustic emission transducer 6 and prime amplifier 5 are for supporting the use, the output terminal that is each acoustic emission transducer 6 is connected with the input end of a prime amplifier 5, the output terminal of each prime amplifier 5 is connected on the input information interface of Acoustic radiating instrument 4, and this input information interface is used for receiving multichannel demblee form amplification message

In the present invention, Acoustic radiating instrument 4 is chosen the DiSP acoustic emission system that PAC company of the U.S. produces, acoustic emission transducer 6 is chosen CZ series or the WD series acoustic emission transducer that PAC company of the U.S. produces, and multichannel prime amplifier 5 is chosen the 2/4/6 type prime amplifier that PAC company of the U.S. produces.

In the present invention, utilize acoustic emission transducer 6 at acquisition time T _xwhile carrying out information acquisition in section, not only damage information is gathered, also noise (neighbourhood noise, electromagnetic noise, mechanical friction noise) is gathered (is e simultaneously _s, A _s, C _s, R _s, D _sin information, be comprise noisy), therefore, in the present invention, adopted data filtering and waveform filtering to gather obtain information carried out denoising.Its object of such denoising is to obtain required for the present invention for carrying out five parameters of fatigue damage monitoring: i.e. energy e _s, measuring amplitude A _s, Ring-down count C _s, rise time R _swith duration D _s.

(1) acoustic emission transducer 6

Acoustic emission transducer 6 is for gathering the demblee form information S on in-service 16Mn steel force-bearing part _n.In the present invention, individual taking its sensing scope as 40cm～100cm/ for the number of acoustic emission transducer 6 required settings.The information that acoustic emission transducer 6 is collected adopts set form to be expressed as: demblee form information S _n={ e _s, A _s, C _s, R _s, D _s, e _srepresent energy, A _srepresent measuring amplitude, C _srepresent Ring-down count, R _srepresent rise time and D _srepresent the duration.

In the present invention, first acquisition time is designated as T ₁, second acquisition time be designated as T ₂..., last acquisition time T _x, for convenience of description, last acquisition time T _xalso referred to as any acquisition time T _x.

In the present invention, at acquisition time T _xthe demblee form information table that in section, acoustic emission transducer 6 collects is shown if first acquisition time T ₁the demblee form information obtaining is designated as in like manner can obtain, if second acquisition time T ₂the demblee form information obtaining is designated as $S_n^{T_2}=\{e_S,A_S,C_S,R_S,D_S\}.$

(2) prime amplifier 5

Prime amplifier 5 is for the demblee form information to receiving after amplifying 40dB, become demblee form amplification message

(3) Acoustic radiating instrument 4

Acoustic radiating instrument 4 is in the demblee form amplification message to receiving after A/D conversion, become digital demblee form information export to 16Mn steel force-bearing part fatigue damage detecting unit 1, in Acoustic radiating instrument 4, certainly have A/D converter.De _srepresentative digit formula energy, dA _srepresentative digit formula measuring amplitude, dC _srepresentative digit formula Ring-down count, dR _srepresentative digit formula rise time and dD _sthe representative digit formula duration.

(4) data filtering processing module 11A

In the present invention, data filtering processing module 11A is to the digital demblee form information receiving carry out parametric filtering, filter after electromagnetic noise and neighbourhood noise, purify and obtain fatigue damage preliminary information e ₀refer to digital energy de _senergy (being called for short parametric filtering energy) after parametric filtering, A ₀refer to digital measurement amplitude dA _smeasuring amplitude (being called for short parametric filtering amplitude) after parametric filtering, C ₀refer to digital Ring-down count dC _sring-down count (being called for short parametric filtering Ring-down count) after parametric filtering, R ₀refer to digital rise time dR _srise time (being called for short the parametric filtering rise time) after parametric filtering, D ₀refer to digital duration dD _sduration (being called for short the parametric filtering duration) after parametric filtering.

(5) waveform filtering processing module 11B

In the present invention, waveform filtering processing module 11B is to the fatigue damage preliminary information receiving carry out waveform filtering, obtain fatigue damage information e refers to parametric filtering energy e ₀through the filtered energy of waveform (being called for short waveform filtering energy), A refers to parametric filtering amplitude A ₀through the filtered amplitude of waveform (being called for short waveform filtered amplitude), C refers to parametric filtering Ring-down count C ₀through the filtered Ring-down count of waveform (referred to as waveform filtering Ring-down count), R refers to parametric filtering rise time R ₀through the filtered rise time of waveform (referred to as the waveform filtering rise time), D refers to parametric filtering duration D ₀through the filtered duration of waveform (being called for short the waveform filtering duration).

In the present invention, fatigue damage information first aspect is carried out RBF neural metwork training for the first injury tolerance Sign module 12C, obtains the first injury tolerance mark model; Second aspect is carried out RBF neural metwork training for the second injury tolerance Sign module 12D, obtains the second injury tolerance mark model; The third aspect is carried out projection process for the first data space 12A, obtains the first score matrix; Fourth aspect is carried out projection process for the second data space 12B, obtains the second score matrix.For fatigue damage information rBF neural metwork training to carry out before the first data space 12A and the second data space 12B.

(6) first data space 12A

The first data space 12A first aspect is to the fatigue damage information receiving carry out place acquisition time T _xaccumulated process in section, obtains accumulating rear fatigue damage information ${\mathrm{ACf}}_{11B}^{T_X}=(e,A,C,R,D);$

The first data space 12A second aspect is to accumulating rear fatigue damage information $\mathrm{AC}{f}_{11B}^{T_X}=(e,A,C,R,D)$ According to Normalized Relation ${f_{11B}}^{\′}=\frac{{\mathrm{ACf}}_{11B}^{T_X}-\stackrel{\‾}{{\mathrm{ACf}}_{11B}^{T_X}}}{{\mathrm{\σ}}_{{\mathrm{ACf}}_{11B}^{T_X}}}$ Process, obtain normalization accumulation of fatigue damage information f _11B'; The mean value of fatigue damage information represent the standard deviation of accumulation of fatigue damage information;

The first data space 12A third aspect is to normalization accumulation of fatigue damage information f _11B' according to the first projection relation f _12A=f _11B' × P _acarry out projection, obtain the first score matrix f _12A=(t _a1, t _a2, t _a3, t _a4, t _a5);

P _arepresent the eigenmatrix of the first data space;

F _12Arepresent to treat the score matrix of diagnostic sample in the first data space, a is the code of the first data space, t _a1, t _a2, t _a3, t _a4, t _a5represent to treat the score vector of diagnostic sample 5 dimensions in the first data space; t _a1represent to treat the score vector of diagnostic sample the 1st dimension in the first data space; t _a2represent to treat the score vector of diagnostic sample the 2nd dimension in the first data space; t _a3represent to treat the score vector of diagnostic sample the 3rd dimension in the first data space; t _a4represent to treat the score vector of diagnostic sample the 4th dimension in the first data space; t _a5represent to treat the score vector of diagnostic sample the 5th dimension in the first data space.

(7) second data space 12B

The second data space 12B first aspect is to the fatigue damage information receiving carry out place acquisition time T _xaccumulated process in section, obtains accumulating rear fatigue damage information ${\mathrm{ACf}}_{11B}^{T_X}=(e,A,C,R,D);$

The second data space 12B second aspect is to accumulating rear fatigue damage information ${\mathrm{ACf}}_{11B}^{T_X}=(e,A,C,R,D)$ According to Normalized Relation ${f_{11B}}^{\′}=\frac{{\mathrm{ACf}}_{11B}^{T_X}-\stackrel{\‾}{{\mathrm{ACf}}_{11B}^{T_X}}}{{\mathrm{\σ}}_{{\mathrm{ACf}}_{11B}^{T_X}}}$ Process, obtain normalization accumulation of fatigue damage information f _11B'; The mean value of fatigue damage information represent the standard deviation of accumulation of fatigue damage information;

The second data space 12B third aspect is to normalization accumulation of fatigue damage information f _11B' according to the second projection relation f _12B=f _11B' × P _bcarry out projection, obtain the second score matrix f _12B=(t _b1, t _b2, t _b3, t _b4, t _b5);

P _brepresent the eigenmatrix of the second data space;

F _12Brepresent to treat the score matrix of diagnostic sample in the second data space, b is the code of the second data space, t _b1, t _b2, t _b3, t _b4, t _b5represent to treat the score vector of diagnostic sample 5 dimensions in the second data space; t _b1represent to treat the score vector of diagnostic sample the 1st dimension in the second data space; t _b2represent to treat the score vector of diagnostic sample the 2nd dimension in the second data space; t _b3represent to treat the score vector of diagnostic sample the 3rd dimension in the second data space; t _b4represent to treat the score vector of diagnostic sample the 4th dimension in the second data space; t _b5represent to treat the score vector of diagnostic sample the 5th dimension in the second data space.

(8) first injury tolerance Sign module 12C

In the present invention, fatigue damage recognition system Main Function is that the fatigue crack that identifies 16Mn steel force-bearing part is stablized extension phase and fatigue crack unstable propagation stage, so damage data type has two classes in the present invention, i.e. crackle stability types ST and bursting type UT; Described crackle stability types ST refers to that fatigue crack stablizes the damage information of extension phase; Described bursting type UT refers to the damage information in fatigue crack unstable propagation stage.

Obtaining of two kinds of type of impairment RBF train samples: when in-service 16Mn steel force-bearing part is during only in the Crack Fatigue Stable Crack Growth stage, by fatigue damage information be designated as crackle stability types fatigue damage information when in-service 16Mn steel force-bearing part is during only in the Crack Fatigue instable growth of crack stage, by fatigue damage information be designated as bursting type fatigue damage information $f_{\mathrm{UT}}^{T_X}=(e,A,C,R,D).$

The first injury tolerance Sign module 12C first aspect is to the crackle stability types fatigue damage information receiving carry out place acquisition time T _xaccumulated process in section, obtains accumulating rear fatigue damage information ${\mathrm{ACf}}_{\mathrm{ST}}^{T_X}=(e,A,C,R,D);$

The first injury tolerance Sign module 12C second aspect is to accumulating rear fatigue damage information $\mathrm{AC}{f}_{\mathrm{ST}}^{T_X}=(e,A,C,R,D)$ According to Normalized Relation ${f_{\mathrm{ST}}}^{\′}=\frac{{\mathrm{ACf}}_{\mathrm{ST}}^{T_X}-\stackrel{\‾}{{\mathrm{ACf}}_{\mathrm{ST}}^{T_X}}}{{\mathrm{\σ}}_{{\mathrm{ACF}}_{\mathrm{ST}}^{T_X}}}$ Process, obtain crackle stability types normalization accumulation of fatigue damage information f _sT'; The mean value of crackle stability types accumulation of fatigue damage information represent the standard deviation of crackle stability types accumulation of fatigue damage information;

The first injury tolerance Sign module 12C third aspect is to crackle stability types normalization accumulation of fatigue damage information f _sT' carry out principal component analysis (PCA), obtain the eigenmatrix P of the first data space _a=(p _a1, p _a2, p _a3, p _a4, p _a5);

P _a1, p _a2, p _a3, p _a4, p _a5represent the proper vector of 5 dimensions in the first data space; p _a1the proper vector of the 1st dimension in the first data space; p _a2the proper vector of the 2nd dimension in the first data space; p _a3the proper vector of the 3rd dimension in the first data space; p _a4the proper vector of the 4th dimension in the first data space; p _a5the proper vector of the 5th dimension in the first data space;

In the present invention, when fatigue damage recognition system is stablized extension phase and fatigue crack unstable propagation stage at the fatigue crack of identification 16Mn steel force-bearing part, the eigenmatrix P of this first data space _aneed citation to carry out projection process to the first data space 12A.

The first injury tolerance Sign module 12C fourth aspect is to normalization accumulation of fatigue damage information f _sT' according to the 3rd projection relation Pf _12C=f _sT' × P _acarry out projection, obtain the 3rd score matrix Pf _12C=(Pt _a1, Pt _a2, Pt _a3, Pt _a4, Pt _a5);

Pt _a1, Pt _a2, Pt _a3, Pt _a4, Pt _a5represent the score vector of training sample 5 dimensions in the first data space of crackle stability types; Pt _a1represent the score vector of training sample the 1st dimension in the first data space of crackle stability types; Pt _a2represent the score vector of training sample the 2nd dimension in the first data space of crackle stability types; Pt _a3represent the score vector of training sample the 3rd dimension in the first data space of crackle stability types; Pt _a4represent the score vector of training sample the 4th dimension in the first data space of crackle stability types; Pt _a5represent the score vector of training sample the 5th dimension in the first data space of crackle stability types.

The first injury tolerance Sign module 12C the 5th aspect is by the 3rd score matrix Pf _12A=(Pt _a1, Pt _a2, Pt _a3, Pt _a4, Pt _a5) as the input layer information of RBF neural network, and set the output layer information of RBF neural network $O_{\mathrm{ID},\mathrm{tr}}=\left[\begin{array}{cc}1& 0\\ 0& 1\end{array}\right],$ Start RBF neural metwork training, obtain the first injury tolerance mark model M _a;

In the present invention, the output layer information of RBF neural network $O_{\mathrm{ID},\mathrm{tr}}=\left[\begin{array}{cc}1& 0\\ 0& 1\end{array}\right]$ In [1 0] represent training sample be the identity code that fatigue crack stablize extended mode, [0 1] expression training sample be the identity code of fatigue crack unstable propagation state.

The first injury tolerance Sign module 12C the 6th aspect adopts M _ato the first score matrix f _12A=(t _a1, t _a2, t _a3, t _a4, t _a5) process, obtain the first injury tolerance parameter f _12C=[f _{iD, a}(A ₁) f _{iD, a}(A ₂)].

In the present invention, the first injury tolerance Sign module 12C is to the f receiving _12A=(t _a1, t _a2, t _a3, t _a4, t _a5) carry out after the processing of RBF Learning Algorithm, obtain the first injury tolerance parameter f _12C=[f _{iD, a}(A ₁) f _{iD, a}(A ₂)]; Wherein f _{iD, a}(A ₁) represent the neural network output of diagnostic sample the 1st node in the first data space of the code transducer that is ID; f _{iD, a}(A ₂) represent the neural network output of diagnostic sample the 2nd node in the first data space of the code transducer that is ID; ID represents the code of acoustic emission transducer, and a is the code of the first data space.

(9) second injury tolerance Sign module 12D

The second injury tolerance Sign module 12D first aspect is to the bursting type fatigue damage information receiving carry out place acquisition time T _xaccumulated process in section, obtains accumulating rear fatigue damage information ${\mathrm{ACf}}_{\mathrm{UT}}^{T_X}=(e,A,C,R,D);$

The first injury tolerance Sign module 12D second aspect is to accumulating rear fatigue damage information ${\mathrm{ACf}}_{\mathrm{UT}}^{T_X}=(e,A,C,R,D)$ According to Normalized Relation ${f_{\mathrm{UT}}}^{\′}=\frac{{\mathrm{ACf}}_{\mathrm{UT}}^{T_X}-\stackrel{\‾}{{\mathrm{ACf}}_{\mathrm{UT}}^{T_X}}}{{\mathrm{\σ}}_{{\mathrm{ACf}}_{\mathrm{UT}}^{T_X}}}$ Process, obtain bursting type normalization accumulation of fatigue damage information f _uT'; The mean value of fatigue damage information represent the standard deviation of bursting type accumulation of fatigue damage information;

The second injury tolerance Sign module 12D third aspect is to bursting type normalization accumulation of fatigue damage information f _uT' carry out principal component analysis (PCA), obtain the eigenmatrix P of the second data space _b=(p _b1, p _b2, p _b3, p _b4, p _b5);

P _b1, p _b2, p _b3, p _b4, p _b5represent the proper vector of 5 dimensions in the second data space; p _b1the proper vector of the 1st dimension in the second data space; p _b2the proper vector of the 2nd dimension in the second data space; p _b3the proper vector of the 3rd dimension in the second data space; p _b4the proper vector of the 4th dimension in the second data space; p _b5the proper vector of the 5th dimension in the second data space;

In the present invention, when fatigue damage recognition system is stablized extension phase and fatigue crack unstable propagation stage at the fatigue crack of identification 16Mn steel force-bearing part, the eigenmatrix P of this second data space _bneed citation to carry out projection process to the second data space 12B.

The second injury tolerance Sign module 12D fourth aspect is to bursting type normalization accumulation of fatigue damage information f _uT' according to the 4th projection relation Pf _12D=f _uT' × P _bcarry out projection, obtain the 4th score matrix Pf _12D=(Pt _b1, Pt _b2, Pt _b3, Pt _b4, Pt _b5);

Pt _b1, Pt _b2, Pt _b3, Pt _b4, Pt _b5represent the score vector of training sample 5 dimensions in the second data space of bursting type; Pt _b1represent the score vector of training sample the 1st dimension in the second data space of bursting type; Pt _b2represent the score vector of training sample the 2nd dimension in the second data space of bursting type; Pt _b3represent the score vector of training sample the 3rd dimension in the second data space of bursting type; Pt _b4represent the score vector of training sample the 4th dimension in the second data space of bursting type; Pt _b5represent the score vector of training sample the 5th dimension in the second data space of bursting type.

The second injury tolerance Sign module 12D the 5th aspect is by the 4th score matrix Pf _12D=(Pt _b1, Pt _b2, Pt _b3, Pt _b4, Pt _b5) as the input layer information of RBF neural network, and set the output layer information of RBF neural network $O_{\mathrm{ID},\mathrm{tr}}=\left[\begin{array}{cc}1& 0\\ 0& 1\end{array}\right],$ Start RBF neural metwork training, obtain the first injury tolerance mark model M _b;

In the present invention, the output layer information of RBF neural network $O_{\mathrm{ID},\mathrm{tr}}=\left[\begin{array}{cc}1& 0\\ 0& 1\end{array}\right]$ In [1 0] represent training sample be the identity code that fatigue crack stablize extended mode, [0 1] expression training sample be the identity code of fatigue crack unstable propagation state.

The second injury tolerance Sign module 12D the 6th aspect adopts M _bto the second score matrix f _12B=(t _b1, t _b2, t _b3, t _b4, t _b5) process, obtain the second injury tolerance parameter f _12D=[f _{iD, b}(A ₁) f _{iD, b}(A ₂)].

In the present invention, the first injury tolerance Sign module 12C is to the f receiving _12B=(t _b1, t _b2, t _b3, t _b4, t _b5) carry out after the processing of RBF Learning Algorithm, obtain the second injury tolerance parameter f _12D=[f _{iD, b}(A ₁) f _{iD, b}(A ₂)]; Wherein f _{iD, b}(A ₁) represent the neural network output of diagnostic sample the 1st node in the second data space of the code transducer that is ID; f _{iD, b}(A ₂) represent the neural network output of diagnostic sample the 2nd node in the second data space of the code transducer that is ID;

ID represents the code of acoustic emission transducer, and b is the code of the second data space.

(10) D-S Evidence Combination Methods module 12E

In the present invention, D-S Evidence Combination Methods module 12E first aspect is to the f receiving _12C=[f _{iD, a}(A ₁) f _{iD, a}(A ₂)] and f _12D=[f _{iD, b}(A ₁) f _{iD, b}(A ₂)] according to node related coefficient $Q_{\mathrm{ID},i}\left(A_j\right)=\left[\begin{array}{cc}\frac{|f_{\mathrm{ID},a}\left(A_1\right)-1|}{|f_{\mathrm{ID},a}\left(A_1\right)-1|+|f_{\mathrm{ID},a}\left(A_2\right)-1|}& \frac{|f_{\mathrm{ID},a}\left(A_2\right)-1|}{\left|f_{\mathrm{ID},a}\left(A_1\right)\right|+|f_{\mathrm{ID},a}\left(A_2\right)-1|}\\ \frac{|f_{\mathrm{ID},b}\left(A_1\right)-1|}{|f_{\mathrm{ID},b}\left(A_1\right)-1|+|f_{\mathrm{ID},b}\left(A_2\right)-1|}& \frac{|f_{\mathrm{ID},b}\left(A_2\right)-1|}{|f_{\mathrm{ID},b}\left(A_1\right)-1|+|f_{\mathrm{ID},b}\left(A_2\right)-1|}\end{array}\right]$ Process, obtain treating diagnostic sample in the first data space and the second data space with the related coefficient Q of each node _{iD, i}(A _j);

Q _{iD, i}(A _j) represent the code transducer that is ID treat diagnostic sample code be in the data space of i (i=a, b) with the related coefficient of node j (j=1,2).

D-S Evidence Combination Methods module 12E second aspect is by basic probability assignment function $m_{\mathrm{ID},i}\left(A_j\right)=\frac{Q_{\mathrm{ID},i}\left(A_j\right)}{\underset{i=1}{\overset{N_c}{\mathrm{\Σ}}}{Q}_{\mathrm{ID},i}\left(A_j\right)+N_s\×(1-R_i)\×(1-{\mathrm{\α}}_i{\mathrm{\β}}_i)}$ Each node j (j=1,2) is carried out to basic probability assignment, obtain treating diagnostic sample in the first data space and the second data space with the basic probability assignment value m of each node _{iD, i}(A _j).

Wherein α _i=max{Q _{iD, i}(A _j) represent to treat diagnostic sample code be in the data space of i (i=a, b) with the maximum correlation coefficient of node; represent code be in the data space of i (i=a, b) with the apportioning cost of node related coefficient; represent that code is the safety factor of the data space of i (i=a, b); N in the present invention _cfor node number, N _sfor data space number, be 2; m _{iD, i}(A _j) represent that the code transducer that is ID receives treat diagnostic sample code be in the data space of i (i=a, b) with the basic probability assignment value of node j (j=1,2).

The D-S Evidence Combination Methods module 12E third aspect is used D-S evidence the first syntagmatic treat diagnostic sample and carry out data fusion with the basic probability assignment value of each node in two data spaces, obtain one-level data fusion value m _iD(B _j).

N _sfor data space number; m _iD(B _j) represent the one-level data fusion value of the code transducer that is ID at node j (j=1,2);

(11) second level data fusion module 13

In the present invention, secondary data merges 13 couples of data fusion result m that receive _iD(B _j) according to D-S evidence the second syntagmatic process, obtain secondary data fusion results m (C _j), C _jrepresent the node identification in secondary data Fusion Module.

N is the number of the acoustic emission transducer 6 of setting; M (C _j) represent in fatigue damage recognition system that all acoustic emission transducers 6 are with joint form, the secondary data fusion value of locating at node j (j=1,2).

(12) damage grade evaluation unit 2

In the present invention, damage grade evaluation unit 2 is to the secondary data fusion results m (C receiving _j) carry out ranking, obtain the residing Fatigue Damage States of in-service 16Mn steel force-bearing part.

Ranking condition: as node maximal value w=m (C ₁) time, Fatigue Damage States is: in-service 16Mn steel force-bearing part is under the stable expansion of fatigue crack faulted condition; As node maximal value w=m (C ₂) time, Fatigue Damage States is: in-service 16Mn steel force-bearing part is under fatigue crack unstable propagation faulted condition;

Described node maximal value w=max (m (C ₁), m (C ₂)), m (C ₁) represent that fatigue damage recognition system all transducers are in node 1(fatigue crack steady state (SS)) the secondary data fusion value located, m (C ₂) represent that fatigue damage recognition system all transducers are at node 2(fatigue crack instability status) the secondary data fusion value located.W represents the maximal value of all transducers of fatigue damage recognition system in the secondary data fusion value of two nodes.

(13) alarm unit 3

In the present invention, in alarm module 3, work as w=m (C ₁) time do not report to the police, as w=m (C ₂) time start alerting signal.Alarm unit 3 adopts as the prompt tone of the form such as loudspeaker, loudspeaker reports to the police and exports.

embodiment 1:to 40t(ton) bearing member of locomotive crane carries out acoustic emission detection.

Bearing member: cantilever is degree of stretching effectively: 5000mm, detects length 3000mm.

Bearing member 16Mn composition of steel used is as shown in table 1.

The 16Mn composition of steel that table 1 bearing member is used

Detection has with equipment: (A) two the narrow frequency acoustic emission transducer of R15 (CZ series of PAC company, response frequency is 100kHz～400kHz, centre frequency 150kHz) and two wideband transducers (the WD series of PAC company, response frequency is 20kHz～1MHz).

(B) 2/4/6 type prime amplifier of four PAC companies.

(C) Acoustic radiating instrument is PAC company of U.S. full digital 16 passage DiSP acoustic emission systems.Threshold value 40dB when Acoustic radiating instrument detects, acoustic emission peak value definition time PDT is 300 μ s, and it is 600 μ s that limiting time HDT is clashed in acoustic emission, and it is 1000 μ s that blocking time HLT is clashed in acoustic emission.

At 16Mn steel force-bearing part at sampling time T _xfour acoustic emission information process fatigue damage recognition system identifications that transducer receives in section, fatigue damage detecting unit result is as shown in table 2.

The basic probability assignment result of the acoustic emission information that tetra-transducers of table 2A receive in fatigue damage detecting unit

Acoustic emission information one-level data fusion result in fatigue damage monitoring means that tetra-transducers of table 2B receive

Transducer	m ID(B 1)	m ID(B 2)	Uncertainty
				1	0.7344	0.1328	0.1328
2	0.9083	0.0427	0.0490
				3	0.9885	0.0051	0.0064
4	0.8338	0.0798	0.0864

Acoustic emission information secondary data fusion results in fatigue damage monitoring means that tetra-transducers of table 2C receive

	m(C 1)	m(C 2)	Uncertainty
				Secondary fusion results	0.9999	0.0001	0

In table 2C, fusion results is resolved through damage grade evaluation unit 2, and can obtain node maximal value is m (C ₁), so this 16Mn steel force-bearing part is stablized extension phase in fatigue crack, without warning.

As can be seen here, data fusion can reduce the local uncertainty merging of neural network, makes to diagnose the confidence level of decision-making to improve significantly.Meanwhile, improve the fault-tolerant ability of diagnostic system, and can meet the requirement of steel construction complication system damage.

The present invention adopts principal component analysis (PCA), the method that neural network and two-stage data fusion combine is identified 16Mn steel Fatigue Damage States, has set up 16Mn steel Fatigue Damage States identifying and diagnosing system: first with neural network model, each acoustic emission transducer information is carried out to local diagnosis under the different damage data space of principal component model structure; Then by the elementary probability value of the neural network Output rusults structure one-level data fusion module in same transducer, carry out one-level data fusion; Finally the one-level data fusion result of multiple sensors is carried out to secondary data fusion, then by damage identification module, Fatigue Damage States is diagnosed.Utilize this model, can the faulted condition in 16Mn steel fatigue process be identified, be diagnosed, and then provide foundation to its reliability service.

Claims (9)

1. one kind is carried out the recognition system of Fatigue Damage States to 16 manganese steel bearing members based on PCA and TDF, it is characterized in that: this system includes multiple acoustic emission transducers (6), multichannel prime amplifier (5), an Acoustic radiating instrument (4), it is characterized in that: also include a 16Mn steel force-bearing part fatigue damage detecting unit (1);

16Mn steel force-bearing part fatigue damage detecting unit (1) includes filtering module (11) and one-level data fusion module (12), secondary data Fusion Module (13), wherein, filtering module (11) has data filtering processing module (11A) and waveform filtering processing module (11B), one-level data fusion module (12) has the first data space (12A), the second data space (12B), the first injury tolerance Sign module (12C), the second injury tolerance Sign module (12D), D-S Evidence Combination Methods module (12E);

Acoustic emission transducer (6) and prime amplifier (5) are for supporting the use, the output terminal that is each acoustic emission transducer (6) is connected with the input end of a prime amplifier (5), the output terminal of each prime amplifier (5) is connected on the input information interface of Acoustic radiating instrument (4), and this input information interface is used for receiving multichannel demblee form amplification message 16Mn steel force-bearing part fatigue damage detecting unit (1) is embedded in the storer of Acoustic radiating instrument (4);

Acoustic emission transducer (6), for gathering in-service 16Mn steel force-bearing part at acquisition time T _xdemblee form information burst type information in section

Prime amplifier (5), for the demblee form information to receiving after amplifying 40dB, become demblee form amplification message

Acoustic radiating instrument (4) is for the demblee form amplification message to receiving after A/D conversion, become digital demblee form information export to 16Mn steel force-bearing part fatigue damage detecting unit (1); De _srepresentative digit formula energy, dA _srepresentative digit formula measuring amplitude, dC _srepresentative digit formula Ring-down count, dR _srepresentative digit formula rise time and dD _sthe representative digit formula duration; Data filtering processing module (11A) in the filtering module (11) of 16Mn steel force-bearing part fatigue damage detecting unit (1) is to the digital demblee form information receiving carry out parametric filtering, filter after electromagnetic noise and neighbourhood noise, purify and obtain acoustic emission fatigue damage preliminary information then waveform filtering processing module (11B) is to acoustic emission fatigue damage preliminary information carry out waveform filtering, obtain acoustic emission fatigue damage information e ₀refer to digital energy de _senergy after parametric filtering, A ₀refer to digital measurement amplitude dA _smeasuring amplitude after parametric filtering, C ₀refer to digital Ring-down count dC _sring-down count after parametric filtering, R ₀refer to digital rise time dR _srise time after parametric filtering, D ₀refer to digital duration dD _sduration after parametric filtering; E refers to parametric filtering energy e ₀through the filtered energy of waveform, A refers to parametric filtering amplitude A ₀through the filtered amplitude of waveform, C refers to parametric filtering Ring-down count C ₀through the filtered Ring-down count of waveform, R refers to parametric filtering rise time R ₀through the filtered rise time of waveform, D refers to parametric filtering duration D ₀through the filtered duration of waveform;

Transducer is received to the fatigue damage information of 16Mn steel force-bearing part carry out acquisition time T _xaccumulated process in section, then normalization obtains normalization accumulation of fatigue damage information f _11B', by f _11B' obtain score matrix f separately at the first data space (12A) and the lower projection of the second data space (12B) respectively _12A=(t _a1, t _a2, t _a3, t _a4, t _a5) and f _12B=(t _b1, t _b2, t _b3, t _b4, t _b5), score matrix f _12A=(t _a1, t _a2, t _a3, t _a4, t _a5) obtain the neural network output f in the first data space through the first injury tolerance Sign module (12C) processing _12C=[f _{iD, a}(A ₁) f _{iD, a}(A ₂)], f _{iD, a}(A ₁) represent the neural network output of diagnostic sample the 1st node in the first data space of the code transducer that is ID; f _{iD, a}(A ₂) represent the neural network output of diagnostic sample the 2nd node in the first data space of the code transducer that is ID; ID represents the code of acoustic emission transducer, and a is the code of the first data space; Score matrix f _12B=(t _b1, t _b2, t _b3, t _b4, t _b5) process the neural network output f obtaining in the second data space through the second injury tolerance Sign module (12D) _12D=[f _{iD, b}(A ₁) f _{iD, b}(A ₂)], f _{iD, b}(A ₁) represent the neural network output of diagnostic sample the 1st node in the second data space of the code transducer that is ID; f _{iD, b}(A ₂) represent the neural network output of diagnostic sample the 2nd node in the second data space of the code transducer that is ID; ID represents the code of acoustic emission transducer, and b is the code of the second data space; By f _12Cand f _12Dcarry out the related coefficient assignment of each node, the f after assignment _12Cand f _12Dcarry out basic probability assignment, then carry out D-S Evidence Combination Methods module (12E) and process the data fusion result m that obtains single transducer _iD(B _j), then D-S Evidence Combination Methods module (12E) result of all transducers is carried out to secondary data merge and obtain data fusion result m (C _j), this result is exported fatigue damage identifying information D to alarm unit (3) after resolve damage grade evaluation unit (2); f _12Arepresent to treat the score matrix of diagnostic sample in the first data space, a is the code of the first data space, t _a1, t _a2, t _a3, t _a4, t _a5represent to treat the score vector of diagnostic sample 5 dimensions in the first data space; t _a1represent to treat the score vector of diagnostic sample the 1st dimension in the first data space; t _a2represent to treat the score vector of diagnostic sample the 2nd dimension in the first data space; t _a3represent to treat the score vector of diagnostic sample the 3rd dimension in the first data space; t _a4represent to treat the score vector of diagnostic sample the 4th dimension in the first data space; t _a5represent to treat the score vector of diagnostic sample the 5th dimension in the first data space; f _12Brepresent to treat the score matrix of diagnostic sample in the second data space, b is the code of the second data space, t _b1, t _b2, t _b3, t _b4, t _b5represent to treat the score vector of diagnostic sample 5 dimensions in the second data space; t _b1represent to treat the score vector of diagnostic sample the 1st dimension in the second data space; t _b2represent to treat the score vector of diagnostic sample the 2nd dimension in the second data space; t _b3represent to treat the score vector of diagnostic sample the 3rd dimension in the second data space; t _b4represent to treat the score vector of diagnostic sample the 4th dimension in the second data space; t _b5represent to treat the score vector of diagnostic sample the 5th dimension in the second data space.

2. recognition system of 16 manganese steel bearing members being carried out to Fatigue Damage States based on PCA and TDF according to claim 1, is characterized in that: data filtering processing module (11A) is to the digital demblee form information receiving carry out parametric filtering, filter after electromagnetic noise and neighbourhood noise, purify and obtain fatigue damage preliminary information $f_{11A}^{T_X}=(e_0,A_0,C_0,R_0,D_0).$

3. recognition system of 16 manganese steel bearing members being carried out to Fatigue Damage States based on PCA and TDF according to claim 1, is characterized in that: waveform filtering processing module (11B) is to the fatigue damage preliminary information receiving carry out waveform filtering, obtain fatigue damage information $f_{11B}^{T_X}=(e,A,C,R,D).$

4. recognition system of 16 manganese steel bearing members being carried out to Fatigue Damage States based on PCA and TDF according to claim 1, is characterized in that:

The first data space (12A) first aspect is to the fatigue damage information receiving carry out place acquisition time T _xaccumulated process in section, obtains accumulating rear fatigue damage information ${\mathrm{ACf}}_{11B}^{T_X}=(e,A,C,R,D);$

The first data space (12A) second aspect is to accumulating rear fatigue damage information ${\mathrm{ACf}}_{11B}^{T_X}=(e,A,C,R,D)$ According to Normalized Relation ${f_{11B}}^{\′}=\frac{{\mathrm{ACf}}_{11B}^{T_X}-\stackrel{\‾}{{\mathrm{ACf}}_{11B}^{T_X}}}{{\mathrm{\σ}}_{\mathrm{AC}{f}_{11B}^{T_X}}}$ Process, obtain normalization accumulation of fatigue damage information f _11B'; The mean value of fatigue damage information represent the standard deviation of accumulation of fatigue damage information;

The first data space (12A) third aspect is to normalization accumulation of fatigue damage information f _11B' according to the first projection relation f _12A=f _11B' × P _acarry out projection, obtain the first score matrix f _12A=(t _a1, t _a2, t _a3, t _a4, t _a5); P _arepresent the eigenmatrix of the first data space.

5. recognition system of 16 manganese steel bearing members being carried out to Fatigue Damage States based on PCA and TDF according to claim 1, is characterized in that:

The second data space (12B) first aspect is to the fatigue damage information receiving carry out place acquisition time T _xaccumulated process in section, obtains accumulating rear fatigue damage information ${\mathrm{ACf}}_{11B}^{T_X}=(e,A,C,R,D);$

The second data space (12B) second aspect is to accumulating rear fatigue damage information ${\mathrm{ACf}}_{11B}^{T_X}=(e,A,C,R,D)$ According to Normalized Relation ${f_{11B}}^{\′}=\frac{{\mathrm{ACf}}_{11B}^{T_X}-\stackrel{\‾}{{\mathrm{ACf}}_{11B}^{T_X}}}{{\mathrm{\σ}}_{\mathrm{AC}{f}_{11B}^{T_X}}}$ Process, obtain normalization accumulation of fatigue damage information f _11B'; The mean value of fatigue damage information represent the standard deviation of accumulation of fatigue damage information;

The second data space (12B) third aspect is to normalization accumulation of fatigue damage information f _11B' according to the second projection relation f _12B=f _11B' × P _bcarry out projection, obtain the second score matrix f _12B=(t _b1, t _b2, t _b3, t _b4, t _b5); P _brepresent the eigenmatrix of the second data space.

6. recognition system of 16 manganese steel bearing members being carried out to Fatigue Damage States based on PCA and TDF according to claim 1, is characterized in that:

The first injury tolerance Sign module (12C) first aspect is to the crackle stability types fatigue damage information receiving carry out place acquisition time T _xaccumulated process in section, obtains accumulating rear fatigue damage information ${\mathrm{ACf}}_{\mathrm{ST}}^{T_X}=(e,A,C,R,D);$

The first injury tolerance Sign module (12C) second aspect is to accumulating rear fatigue damage information ${\mathrm{ACf}}_{\mathrm{ST}}^{T_X}=(e,A,C,R,D)$ According to Normalized Relation ${f_{\mathrm{ST}}}^{\′}=\frac{{\mathrm{ACf}}_{\mathrm{ST}}^{T_X}-\stackrel{\‾}{{\mathrm{ACf}}_{\mathrm{ST}}^{T_X}}}{{\mathrm{\σ}}_{\mathrm{AC}{f}_{\mathrm{ST}}^{T_X}}}$ Process, obtain crackle stability types normalization accumulation of fatigue damage information f _sT'; The mean value of crackle stability types accumulation of fatigue damage information represent the standard deviation of crackle stability types accumulation of fatigue damage information;

First injury tolerance Sign module (12C) third aspect is to crackle stability types normalization accumulation of fatigue damage information f _sT' carry out principal component analysis (PCA), obtain the eigenmatrix P of the first data space _a=(p _a1, p _a2, p _a3, p _a4, p _a5); p _a1the proper vector of the 1st dimension in the first data space; p _a2the proper vector of the 2nd dimension in the first data space; p _a3the proper vector of the 3rd dimension in the first data space; p _a4the proper vector of the 4th dimension in the first data space; p _a5the proper vector of the 5th dimension in the first data space;

The first injury tolerance Sign module (12C) fourth aspect is to normalization accumulation of fatigue damage information f _sT' according to the 3rd projection relation Pf _12C=f _sT' × P _acarry out projection, obtain the 3rd score matrix Pf _12C=(Pt _a1, Pt _a2, Pt _a3, Pt _a4, Pt _a5); Pt _a1represent the score vector of training sample the 1st dimension in the first data space of crackle stability types; Pt _a2represent the score vector of training sample the 2nd dimension in the first data space of crackle stability types; Pt _a3represent the score vector of training sample the 3rd dimension in the first data space of crackle stability types; Pt _a4represent the score vector of training sample the 4th dimension in the first data space of crackle stability types; Pt _a5represent the score vector of training sample the 5th dimension in the first data space of crackle stability types;

The first injury tolerance Sign module (12C) the 5th aspect is by the 3rd score matrix Pf _12C=(Pt _a1, Pt _a2, Pt _a3, Pt _a4, Pt _a5) as the input layer information of RBF neural network, and set the output layer information of RBF neural network $O_{\mathrm{ID},\mathrm{tr}}=\left[\begin{array}{cc}1& 0\\ 0& 1\end{array}\right],$ Start RBF neural metwork training, obtain the first injury tolerance mark model M _a;

The output layer information of RBF neural network $O_{\mathrm{ID},\mathrm{tr}}=\left[\begin{array}{cc}1& 0\\ 0& 1\end{array}\right]$ In [1 0] represent training sample be the identity code that fatigue crack stablize extended mode, [0 1] expression training sample be the identity code of fatigue crack unstable propagation state;

The first injury tolerance Sign module (12C) the 6th aspect adopts M _ato the first score matrix f _12A=(t _a1, t _a2, t _a3, t _a4, t _a5) process, obtain the first injury tolerance parameter f _12C=[f _{iD, a}(A ₁) f _{iD, a}(A ₂)].

7. recognition system of 16 manganese steel bearing members being carried out to Fatigue Damage States based on PCA and TDF according to claim 1, is characterized in that:

The second injury tolerance Sign module (12D) first aspect is to the bursting type fatigue damage information receiving carry out place acquisition time T _xaccumulated process in section, obtains accumulating rear fatigue damage information ${\mathrm{ACf}}_{\mathrm{UT}}^{T_X}=(e,A,C,R,D);$

The first injury tolerance Sign module (12D) second aspect is to accumulating rear fatigue damage information ${\mathrm{ACf}}_{\mathrm{UT}}^{T_X}=(e,A,C,R,D)$ According to Normalized Relation ${f_{\mathrm{UT}}}^{\′}=\frac{{\mathrm{ACf}}_{\mathrm{UT}}^{T_X}-\stackrel{\‾}{{\mathrm{ACf}}_{\mathrm{UT}}^{T_X}}}{{\mathrm{\σ}}_{\mathrm{AC}{f}_{\mathrm{UT}}^{T_X}}}$ Process, obtain bursting type normalization accumulation of fatigue damage information f _uT'; The mean value of fatigue damage information represent the standard deviation of bursting type accumulation of fatigue damage information;

Second injury tolerance Sign module (12D) third aspect is to bursting type normalization accumulation of fatigue damage information f _uT' carry out principal component analysis (PCA), obtain the eigenmatrix P of the second data space _b=(p _b1, p _b2, p _b3, p _b4, p _b5); p _b1the proper vector of the 1st dimension in the second data space; p _b2the proper vector of the 2nd dimension in the second data space; p _b3the proper vector of the 3rd dimension in the second data space; p _b4the proper vector of the 4th dimension in the second data space; p _b5the proper vector of the 5th dimension in the second data space;

The second injury tolerance Sign module (12D) fourth aspect is to bursting type normalization accumulation of fatigue damage information f _uT' according to the 4th projection relation Pf _12D=f _uT' × P _bcarry out projection, obtain the 4th score matrix Pf _12D=(Pt _b1, Pt _b2, Pt _b3, Pt _b4, Pt _b5); Pt _b1represent the score vector of training sample the 1st dimension in the second data space of bursting type; Pt _b2represent the score vector of training sample the 2nd dimension in the second data space of bursting type; Pt _b3represent the score vector of training sample the 3rd dimension in the second data space of bursting type; Pt _b4represent the score vector of training sample the 4th dimension in the second data space of bursting type; Pt _b5represent the score vector of training sample the 5th dimension in the second data space of bursting type;

The second injury tolerance Sign module (12D) the 5th aspect is by the 4th score matrix Pf _12D=(Pt _b1, Pt _b2, Pt _b3, Pt _b4, Pt _b5) as the input layer information of RBF neural network, and set the output layer information of RBF neural network $O_{\mathrm{ID},\mathrm{tr}}=\left[\begin{array}{cc}1& 0\\ 0& 1\end{array}\right],$ Start RBF neural metwork training, obtain the first injury tolerance mark model M _b;

The output layer information of RBF neural network $O_{\mathrm{ID},\mathrm{tr}}=\left[\begin{array}{cc}1& 0\\ 0& 1\end{array}\right]$ In [1 0] represent training sample be the identity code that fatigue crack stablize extended mode, [0 1] expression training sample be the identity code of fatigue crack unstable propagation state;

The second injury tolerance Sign module (12D) the 6th aspect adopts M _bto the second score matrix f _12B=(t _b1, t _b2, t _b3, t _b4, t _b5) process, obtain the second injury tolerance parameter f _12D=[f _{iD, b}(A ₁) f _{iD, b}(A ₂)].

8. recognition system of 16 manganese steel bearing members being carried out to Fatigue Damage States based on PCA and TDF according to claim 1, is characterized in that:

D-S Evidence Combination Methods module (12E) first aspect is to the f receiving _12C=[f _{iD, a}(A ₁) f _{iD, a}(A ₂)] and f _12D=[f _{iD, b}(A ₁) f _{iD, b}(A ₂)] according to node related coefficient $Q_{\mathrm{ID},i}\left(A_j\right)=\left[\begin{array}{cc}\frac{|f_{\mathrm{ID},a}\left(A_1\right)-1|}{|f_{\mathrm{ID},a}\left(A_1\right)-1|+|f_{\mathrm{ID},a}\left(A_2\right)-1|}& \frac{|f_{\mathrm{ID},a}\left(A_2\right)-1|}{|f_{\mathrm{ID},a}\left(A_1\right)-1|+|f_{\mathrm{ID},a}\left(A_2\right)-1|}\\ \frac{|f_{\mathrm{ID},b}\left(A_1\right)-1|}{|f_{\mathrm{ID},b}\left(A_1\right)-1|+|f_{\mathrm{ID},b}\left(A_2\right)-1|}& \frac{|f_{\mathrm{ID},b}\left(A_2\right)-1|}{|f_{\mathrm{ID},b}\left(A_1\right)-1|+|f_{\mathrm{ID},b}\left(A_2\right)-1|}\end{array}\right]$ Process, obtain treating diagnostic sample in the first data space and the second data space with the related coefficient Q of each node _{iD, i}(A _j);

D-S Evidence Combination Methods module (12E) second aspect is by basic probability assignment function $m_{\mathrm{ID},i}\left(A_j\right)=\frac{Q_{\mathrm{ID},i}\left(A_j\right)}{\underset{j=1}{\overset{N_c}{\mathrm{\Σ}}}{Q}_{\mathrm{ID},i}\left(A_j\right)+N_s\×(1-R_i)\×(1-{\mathrm{\α}}_i{\mathrm{\β}}_i)}$ Each node j (j=1,2) is carried out to basic probability assignment, obtain treating diagnostic sample in the first data space and the second data space with the basic probability assignment value m of each node _{iD, i}(A _j);

D-S Evidence Combination Methods module (12E) third aspect is used D-S evidence the first syntagmatic treat diagnostic sample and carry out data fusion with the basic probability assignment value of each node in two data spaces, obtain one-level data fusion value m _iD(B _j);

Wherein α _i=max{Q _{iD, i}(A _j) represent to treat diagnostic sample code be in the data space of i (i=a, b) with the maximum correlation coefficient of node; represent code be in the data space of i (i=a, b) with the apportioning cost of node related coefficient; represent that code is the safety factor of the data space of i (i=a, b); N _cfor node number, N _sfor data space number, be 2; m _{iD, i}(A _j) represent that the code transducer that is ID receives treat diagnostic sample code be in the data space of i (i=a, b) with the basic probability assignment value of node j (j=1,2); m _iD(B _j) represent the one-level data fusion value of the code transducer that is ID at node j (j=1,2).

9. recognition system of 16 manganese steel bearing members being carried out to Fatigue Damage States based on PCA and TDF according to claim 1, is characterized in that: secondary data merges (13) to the data fusion result m receiving _iD(B _j) according to D-S evidence the second syntagmatic process, obtain secondary data fusion results m (C _j), C _jrepresent the node identification in secondary data Fusion Module.