CN104537416A - Fault diagnosis method based on HBF neural network observer - Google Patents

Abstract

The invention provides a fault diagnosis method based on an HBF neural network observer. The fault diagnosis method is used for conducting intelligent fault diagnosis. According to the method, an HBF neural network is adopted, the similarity between vectors can be signified through the Mahalanobis-like distance, the neuron number and the calculating speed are lowered, meanwhile, the neural network state observer is established, an abstracted non-linear system in engineering is observed, the system output prediction in the next step can be conducted through the output value of the state observer, and thus system fault diagnosis and detection can be achieved.

Description

A kind of method for diagnosing faults based on HBF Neural Network Observer

Technical field

The present invention designs neural network can only fault diagnosis and detection method, particularly relates to a kind of method for diagnosing faults based on HBF Neural Network Observer, belongs to mode identification technology.

Background technology

The development of fault diagnosis technology mainly experienced by the three phases such as Artificial Diagnosis, modern diagnosis and intelligent diagnostics.Be developed so far, method for diagnosing faults can be divided into the method based on analytic model, the method based on signal transacting and Knowledge based engineering method etc.Along with the development of science and technology, systems grow is complicated, simple dependence can not meet the reliability requirement of equipment based on the conventional fault diagnosis method of mathematical model, therefore Intelligent Fault Diagnosis Technique more and more obtains the great attention in each field, especially in control field, as the control annual meeting of the U.S., the control of IEEE and decision making meeting, International Federation of Automatic Control (IFAC) etc., all Intelligent Fault Diagnosis Technique is classified as important discussion special topic.Because it is more suitable for the development of modern science and technology, the Theories and methods in contemporary front line science also must penetrate in Intelligent Fault Diagnosis Technique, as neural network theory and particle filter etc.In recent years, all kinds of intelligent failure diagnosis method is obtained for and develops fast, such as, based on diagnostic techniquess such as neural network, neural network Adaptive Observer and support vector machine.Wherein neural network realizes Nonlinear Mapping relation complicated between fault and sign by study for the connection weight expressing fault diagnosis knowledge.

Owing to having some following advantage, in recent years, intelligent failure diagnosis method is subject to the favor of Fault diagnosis expert and scholar day by day.

(1) mathematical models of object is not needed.

(2) knowledge and experience of diagnostician can be effectively utilized, collect numerous expertise to the random diagnosing malfunction occurred.

(3) there is the inferential capability as diagnostician, automatically realize the mapping from failure symptom to failure cause.

(4) there is certain associative ability and antijamming capability, possess study mechanism, diagnostic knowledge can be obtained from the diagnosis example in past.

(5) to diagnostic result, there is interpretability.

Expert system, neural network, fuzzy theory, rough set theory, Data-Fusion theory, wavelet theory, fault tree and they each other with the main manifestations method that the fusion of they and out of Memory treatment technology is artificial intelligence means, in diagnostic field, they are paid attention to more and more widely.

(1) expert system diagnosis methods: primarily of part compositions such as knowledge base, database, inference machine, interpreter, failure symptom acquisition and man-machine interactions.Mainly on the basis of expert knowledge library, database, carry out fault diagnosis by the knowledge in inference machine comprehensive utilization knowledge base according to certain inference method.Expert system has had practical application in fields such as Aero-Space, chemical industry, nuclear industry, and brings huge social and economic benefits.

(2) Neural Network Diagnosis Method: because neural network has very strong non-linear mapping capability, can relation exactly between the failure symptom of Simulation of Complex equipment and failure cause, and there is parallel processing capability, self-learning capability and memory capability, because being successfully applied to fault diagnosis field.Fault diagnosis based on neural network has been applied to multiple field such as industry, national defence.

(3) fuzzy diagnosis method: fault diagnosis carrys out judgment device state by the relation between research fault and sign.Due to the complicacy of practical factor, be difficult between fault and sign represent by accurate mathematical model, simply can not represent with " having " and "None", and require to the possibility of generation of being out of order, abort situation and degree.Problems fuzzy logic can solve preferably.Fuzzy logic diagnostic method can overcome the difficulty brought due to the uncertainty of process itself, inexactness and noise etc., and calculating is simple, application is convenient, thus process complication system large dead time, time become and non-linear in, demonstrate its superiority.The application of fuzzy logic in fault diagnosis is combined with additive method, mostly as fuzzy neural network, fuzzy expert system etc.

(4) rough set diagnostic method: rough set theory is the method for thought based on indistinguishability and knowledge expression simplification, keeping under the prerequisite that classification capacity is constant, by Reduction of Knowledge, from data, inference logic rule is as the model of knowledge system.It has been given a definition ambiguity and probabilistic concept in the meaning of classification.Utilize rough set theory to carry out Fault Tree Diagnosis Decision table to system and carry out yojan process, the redundancy of the various fault signature inherence of interpre(ta)tive system, for system fault diagnosis provides new effective way.

(5) diagnosing information fusion fault method: information fusion technology utilizes multi-source information, to obtain the informix treatment technology of more objective, the more essential understanding to same thing or target.It refers to means collections such as utilizing multisensor and integrated various information source, multimedia and multi-format information, the information such as such as electric signal, temperature, image, electromagnetic radiation, thus generate complete, accurate, timely and effective integrated information, then carry out fault diagnosis according to certain judgment rule.Information fusion technology is widely used at present in military field.At present, data fusion method for diagnosing faults mainly contains Bayes reasoning, D-S evidential reasoning and neural Network Data Fusion etc.

In recent years, although intelligent trouble diagnosis algorithm progress is fast, a lot of intelligent method is suggested, and still there are some problems:

(1) knowledge base is huge.Current Intelligent Fault Diagnose Systems adopts production rule to represent the experimental knowledge of expert mostly, in order to the target making diagnostic system reach efficient, practical, a large amount of expertises must be needed to form huge knowledge base.The diagnostic system of main equipment, corresponding knowledge base is huger, and this gives the arrangement of knowledge base, calling of knowledge rule brings adverse effect.

(2) dark, shallow knowledge binding ability is poor.In concrete intelligent diagnosis system, when the ultimate principle and expertise that realize certain field combine, ability is poor.Some depth knowledge are good not in compatibility, are difficult to realize unification in same knowledge base.

(3) system update ability.The ability that system shows in automatic acquisition knowledge is also poor, although add the function of some Machine self-learning, is difficult to be in operation discovery and creating knowledge.Although neural network can alleviate this contradiction, require a large amount of training samples and be difficult to obtain, and along with the upgrading of diagnosis object, whole neural network theory wants re-training.

(4) fault sample is difficult to obtain.Along with the raising of automatization level and the develop rapidly of computing machine, for most of equipment, a large amount of normal data of reflection equipment running status easily obtain, and the acquisition of fault data is more difficult.

Summary of the invention

The object of the present invention is to provide a kind of method for diagnosing faults based on HBF Neural Network Observer, poor to solve generalization ability in traditional neural network method for diagnosing faults, the problems such as calculation of complex, reducing neuronal quantity and the complexity of network, providing new method for providing detection efficiency and degree of accuracy.

For achieving the above object, its process of HBF neural network failure detection method provided by the invention is as follows:

1) sample input and the sample of, choosing sample system export;

2), the sample of sample system input input hyper-base Function Neural Network observer is obtained estimating to export;

3), obtain estimating that exporting residual error is according to estimation output and actual output:

$e_y\left(t\right)=y\left(t\right)-\hat{y}\left(t\right)$

In formula, y (t) represents that sample exports, represent and estimate to export;

If estimation of error function is

In formula, U is weighting diagonal matrix; Its fault detect rule is:

Wherein, T is the threshold value of fault detect.

The process of described hyper-base Function Neural Network observer is as follows:

1), n is obtained _xthe input and output of individual fault of nonlinear system sample; Hidden layer neuron number J is selected according to input value output valve;

2), decision region is represented with " decision-making leaf " , it is expressed as:

Calculate sample input at decision domain network center its formula is:

c _ij＝(min(x _ij)+max(x _ij))/2 i＝1,...,n _x

Calculate decision domain kernel width, its formula is:

σ _ij＝(max(x _ij)-min(x _ij))/2 i＝1,...,n _x

3) all input amendment, are calculated at decision domain corresponding basis function values;

First Mahalanobis-like is adopted to calculate the distance of sample input and network center:

$\left|\right|x_i-c_j{\left|\right|}_{{\mathrm{\Σ}}_j}={(x_i-c_j)}^T{\mathrm{\Σ}}_j(x_i-c_j);$

In formula: Σ _jfor Positive Definite Square Matrices;

${\mathrm{\Σ}}_j=\mathrm{diag}(1/{\mathrm{\σ}}_1^2,1/{\mathrm{\σ}}_2^2,...,1/{\mathrm{\σ}}_{n_x}^2),j=\mathrm{1,2},...J,$

Then corresponding basis function is calculated as:

$h_j(x_i,c_j,{\mathrm{\Σ}}_j)=e^{-0.5{(x_i-c_j)}^T{\mathrm{\Σ}}_j(x_i-c_j)}$

If x ^μ, y ^μμ=1 ..., M is proper vector and the object vector of training sample set; Then error function is:

E(W)＝||HW-Y|| ²

Wherein, W is the weight matrix of output layer; H=(H _{μ j})=(h _j(x ^μ, c _j, σ _j)), H _{μ j}be μ input vector x ^μthe output of a corresponding jth basis function; Y=(Y _{μ j}), Y _{μ j}μ object vector y ^μa jth component;

5) output weight vector is solved

According to error minimize principle, solve output weight vector.For the error met the demands, solve weight vector by following formula

W＝H ⁺Y

Wherein H ⁺for the pseudoinverse of matrix H; For the error do not met the demands, by following formula adjustment weights, jump procedure 4);

W _k+1＝W _k+ΔW _k

$\mathrm{\Δ}{W}_k=-\mathrm{\η}\frac{\∂E}{\∂W}.$

The present invention compared with prior art advantage is:

It adopts HBF neural network failure detection method to detect fault of nonlinear system, there is stronger generalization ability, the method makes neuronal quantity less, reduce the complexity of conventional observation device method for designing, and to Nonlinear Dynamic nervous system fault, there is higher susceptibility, even if multivariate input does not increase too many complicacy yet, so be easy to expand in multi-input multi-output system, be conducive to real-time online application.

Accompanying drawing explanation

Fig. 1 is decision Tree algorithms process flow diagram;

Fig. 2 is HBF network algorithm process flow diagram;

Fig. 3 is HBF Neural Network Observer model.

Embodiment

For checking the present invention is based on the superiority of HBF neural network failure detection method, below in conjunction with example, the present invention is described in further detail.

Detection method based on HBF neural network is applied in fault of nonlinear system diagnoois and test by the present invention, verifies fault diagnosis of the present invention and detectability by state observation.

Obtain fault of nonlinear system sample data, sample data can obtain according to nonlinear state equation, selects suitable hidden layer neuron number K according to input and output.

Sample data is inputted, builds decision tree, and it to be tested, afterwards regularly computing center's vector sum width.Classifying rules if ... then form represents, each rule is all a path from root to leaf node, and leaf node represents concrete classification, and more than leaf node node and limit thereof represent the condition value of corresponding conditions.

If the result regularly calculated is satisfied, then Output rusults, otherwise repeats to build and check decision tree, until obtain qualified result (network center and kernel width).

Calculate input neuron and central nervous unit spacing:

$\left|\right|x_i-c_j{\left|\right|}_{{\mathrm{\Σ}}_j}={(x_i-c_j)}^T{\mathrm{\Σ}}_j(x_i-c_j);$ ${\mathrm{\Σ}}_j=\mathrm{diang}(1/{\mathrm{\σ}}_1^2,1/{\mathrm{\σ}}_2^2,\·\·\·,1/{\mathrm{\σ}}_{n_x}^2)$

In formula, c _j, σ _nxfor central nervous unit and the width of network.

Computational grid basis function: $h_j(x_i,c_j,{\mathrm{\Σ}}_j)=e^{-0.5{(x_i-c_j)}^T{\mathrm{\Σ}}_j(x_i-c_j)}$

Definition output error

Network concealed layer has K neuron, x ^μ, y ^μμ=1 ..., M is proper vector and the object vector of training fault sample collection respectively.The error function of network is

E(W)＝||HW-Y|| ²

Wherein, W is the weight matrix of output layer; H=(H _{μ j})=(h _j(x ^μ, c _j, σ _j)), H _{μ j}be μ input vector x ^μthe output of a corresponding jth basis function; Y=(Y _{μ j}), Y _{μ j}μ object vector y ^μa jth component.

Solve output weight vector

According to error minimize principle, solve output weight vector.For the error met the demands, solve weight vector by following formula

W＝H ⁺Y

Wherein H ⁺for the pseudoinverse (or generalized inverse) of matrix H, obtained by svd (SVD).

Be used in fault-detecting-observer by the network trained, utilize the output valve of this network state observer, the system of carrying out next step exports forecast, thus the fault detect of just feasible system.

From above-mentioned steps, hyper-base Function Neural Network reduces the complexity of network calculations, there is stronger generalization ability, and realize approaching of complex nonlinear function with higher precision, reduce the complexity of conventional observation device method for designing, and to Nonlinear Dynamic nervous system fault, there is higher susceptibility, even if multivariate input does not increase too many complicacy yet, so be easy to expand in multi-input multi-output system, be conducive to real-time online application.

Claims (2)

1., based on a method for diagnosing faults for HBF Neural Network Observer, it carries out on the basis of sample system Mathematical Models, it is characterized in that: its process is as follows:

1) sample input and the sample of, choosing sample system export;

2), the sample of sample system input input hyper-base Function Neural Network observer is obtained estimating to export;

3), obtain estimating that exporting residual error is according to estimation output and actual output:

$e_y\left(t\right)=y\left(t\right)-\hat{y}\left(t\right)$

In formula, y (t) represents that sample exports, represent and estimate to export;

If estimation of error function is

In formula, U is weighting diagonal matrix; Its fault detect rule is:

Wherein, T is the threshold value of fault detect.

2. the method for diagnosing faults based on hyper-base Function Neural Network observer according to claim 1, is characterized in that: the process of described hyper-base Function Neural Network observer is as follows:

1), n is obtained _xthe input and output of individual fault of nonlinear system sample; Hidden layer neuron number J is selected according to input value output valve;

2), decision region is represented with " decision-making leaf " it is expressed as:

Calculate sample input at decision domain network center its formula is:

c _ij＝(min(x _ij)+max(x _ij))/2i＝1,...,n _x

Calculate decision domain kernel width, its formula is:

σ _ij＝(max(x _ij)-min(x _ij))/2i＝1,...,n _x

3) all input amendment, are calculated at decision domain corresponding basis function values;

First Mahalanobis-like is adopted to calculate the distance of sample input and network center:

${\left|\right|x_i-c_j\left|\right|}_{{\mathrm{\Σ}}_j}={(x_i-c_j)}^T{\mathrm{\Σ}}_j(x_i-c_j);$

In formula: Σ _jfor Positive Definite Square Matrices;

${\mathrm{\Σ}}_j=\mathrm{diag}(1/{\mathrm{\σ}}_1^2,1/{\mathrm{\σ}}_2^2,...,1/{\mathrm{\σ}}_{n_x}^2),j=\mathrm{1,2},...J,$

Then corresponding basis function is calculated as:

$h_j(x_i,c_j,{\mathrm{\Σ}}_j)=e^{-0.5{(x_i-c_j)}^T{\mathrm{\Σ}}_j(x_i-c_j)}$

4), output error is defined

If x ^μ, y ^μμ=1 ..., M is proper vector and the object vector of training sample set; Then error function is:

E(W)＝||HW-Y|| ²

Wherein, W is the weight matrix of output layer; H=(H _{μ j})=(h _j(x ^μ, c _j, σ _j)), H _{μ j}be μ input vector x ^μthe output of a corresponding jth basis function; Y=(Y _{μ j}), Y _{μ j}μ object vector y ^μa jth component;

5) output weight vector is solved

According to error minimize principle, solve output weight vector; For the error met the demands, solve weight vector by following formula

W＝H ⁺Y

Wherein H ⁺for the pseudoinverse of matrix H; For the error do not met the demands, by following formula adjustment weights, jump procedure 4);

W _k+1＝W _k+ΔW _k

$\mathrm{\Δ}{W}_k=-\mathrm{\η}\frac{\∂E}{\∂W}.$