Research on aero-engine fault diagnosis based on integrated neural network

2.1. Data processing module

This module is based on the original data to specific filtering, feature selection and selection of a series of operations, the diagnostic network provides the feature vector for each for $X_i\left(i=\mathrm{1,2},...,m\right)$. By using this module, the filtering link can be started directly in the interface, and the data noise can be removed by filtering, so that the necessary data can be prepared automatically to the subsystem to ensure the operation of the diagnosis work. In addition to filtering, sample pretreatment can also be started through the interface to select the features of the selected parameters and prepare data for the training of the neural network [5].

2.2. Characteristic information allocation unit

The feature information distribution unit performs the task of assigning feature information to each diagnostic subnetwork. The distribution of feature information is determined by the structure of each diagnostic sub-network. The feature information allocated by each sub-network can be based on either a single parameter or multiple parameters. In the process of diagnosis, in order to achieve the optimal diagnosis results, feature information can be flexibly allocated according to training requirements, structure settings and expected results [6].

2.3. Diagnostic subnetwork

As the core of the whole diagnostic system, the diagnostic network consists of $M$ sub-networks responsible for diagnostic reasoning. Like rule-based expert system, diagnostic network includes two design parts: reasoning engine and knowledge base. It is only for diagnostic network. The reasoning mechanism adopted by inference engine has replaced the original reasoning based on symbolic rules by numerical calculation based on network structure, and the formation of knowledge base is also replaced by the learning and training of neural network [7].

If the diagnostic sub-network is allocated feature information based on multiple parameters, then assuming that the diagnostic confidence of n diagnostic parameters in the diagnostic sub-network for the same fault mode is $t_i\left(i=\mathrm{1,2},3,...,n\right)$, the diagnostic confidence of the diagnostic sub-network for the same fault mode is $T$:

At the same time, the diagnostic input of the diagnostic sub-network based on multiple parameters can connect the eigenvectors $e_i\left(i=\mathrm{1,2},...,n\right)$ of all diagnostic parameters and form a new eigenvector $E$, $E=\left(e_1,e_2,...,e_n\right)$. Usually, the three-layer network is used as the structure of each diagnosis sub-network, that is, the dimension of diagnostic input eigenvector is used as the number of input nodes, and the number of fault modes is used as the number of output nodes. In addition, the number of middle layer (hidden layer) nodes should be selected according to the training error requirement and the size of training sample set.

2.4. Decision fusion network

The principle of decision fusion network is to fuse the diagnostic conclusions of each diagnostic sub-network and make decisions.

Assuming that the integrated neural network diagnosis system diagnoses $n$-type faults, each sub-network diagnoses $n$-type faults based on its own characteristic information at the same time. The output $R_i$ of subnetwork $N{N}_i$ is called fault mode vector:

The diagnostic results of each subnetwork for n-type faults are as follows [8]:

In the formula, $X_i\in R^{Ni}$ is the diagnostic input eigenvector of function subnetwork $N{N}_i$; $f_i\left(\right)$ is the mapping of the $i$th subnetwork for the design of decision fusion network, which integrates the same nodes of each diagnostic subnetwork, that is, the diagnosis results of the same fault mode are fused by each diagnostic subnetwork, and finally a node is formed as the output of decision fusion network the final diagnosis result. If the diagnostic confidence of the $i$th diagnostic subnetwork for $n$-type faults is $C_i=\left(C_{i1},C_{i2},...,C_{in}\right)$, then the fault mode matrix $\mathbf{R}$ and the confidence weight matrix $\mathbf{C}$ formed by the parallel combination of the m diagnostic subnetworks are respectively:

The output of decision fusion network is:

In the formula, $\mathrm{d}\mathrm{i}\mathrm{a}\mathrm{g}$ represents the diagonal element. The diagnostic probability of the $i$th fault is:

In the formula, ${\sum }_{i=1}^m{c}_{ij}=$ 1, which is normalized, represents the contribution of each diagnostic subnetwork to fault diagnosis. It can be seen that the algebraic sum method can well reflect the role and influence of various factors in this synthesis.

3.1. Information preprocessing

The CFM56-3 Aero-engine is one of the world’s most classic engines, accounting for 55 % of the B737 aircraft. B737 aircraft has been widely used because it meets the needs of the market more closely in terms of range and efficiency. According to the actual application of CFM56-3 Aero-engine, this paper studies the integrated neural network diagnosis technology of Aero-engine Based on the fusion of lubricating oil information and vibration information. It is difficult to analyze and process the diagnostic data because of the difference in both numerical value and dimension. Therefore, before the fusion diagnosis, the original symptoms need to be preprocessed. The specific method is to compare the original data with the standard threshold values of various diagnostic methods. The definition in the normal range is 0, and vice versa is 1, so that the original symptoms data can be converted to 0 and 1.

According to the actual situation, the oil analysis mainly relies on spectral information because of the fewer ferrographic data of an Aero-engine. The concentrations of Fe, Cu, Mg, Al, Cr, Ni, Mo, Ti and Ag were selected as the original data for spectral diagnosis. After pretreatment, the diagnostic rules of spectral data are as follows: 1) Fe element concentration exceeding the standard ($S_{S1}$); 2) Cu element concentration exceeding the standard ($S_{S2}$); 3) Mg element concentration exceeding the standard ($S_{S3}$); 4) Al element concentration exceeding the standard ($S_{S4}$); 5) Cr element concentration exceeding the standard ($S_{S5}$); 6) Ni element concentration exceeding the standard ($S_{S6}$); 7) Mo element concentration exceeding the standard ($S_{S7}$); 8) Ti element concentration exceeding the standard ($S_{S8}$); Element concentration exceeded the standard ($S_{S9}$).

At present, there are many vibration parameters applied in engine condition monitoring, and the object and occasion of application will have a greater impact on the diagnostic effect of various parameters. In order to obtain the time domain characteristic parameters of engine vibration signal, this paper extracts the time domain signal based on the noise reduction of the vibration signal, and carries on the time domain statistical analysis. The data of excessive peak value ($S_{C1}$) and excessive root mean square value ($S_{C2}$) are selected as vibration data.

3.2. Integrated neural network diagnosis

The diagnostic system based on integrated neural network includes spectral information sub-network and vibration information sub-network. After pretreatment of various original symptoms, the Boolean value is obtained and used as the input of the sub-network. The output of each sub-network is the final failure mode. Taking engine rotor failure as an example, the failure modes are determined as follows: 1) normal system ($F_1$); 2) bearing fatigue failure ($F_2$); 3) bearing wear failure ($F_3$); 4) gear gluing or scratch ($F_4$); 5) gear overload fatigue ($F_5$).

Fuzzy comprehensive decision-making method is used to make a comprehensive decision on the diagnostic results of each sub-network, so as to consult each sub-diagnostic network. Through the above diagnosis results of each sub-network, matrix $\mathbf{R}$ can be formed, and the final comprehensive decision results can be obtained by multiplying matrix $\mathbf{R}$ and weight matrix $\mathbf{C}$.

A Fuzzy Comprehensive Decision Model for:

In the matrix $\mathbf{R}$, $F_{S1}$, $F_{S2}$, $F_{S3}$, $F_{S4}$ and $F_{S5}$ are the diagnostic results of spectral information subnetwork, while $F_{C1}$, $F_{C2}$, $F_{C3}$, $F_{C4}$ and $F_{C5}$ are the diagnostic results of vibration information subnetwork. Weight matrix $\mathbf{C}$ mainly measures the contribution of various diagnostic methods to different fault diagnosis.

According to the actual use of a certain type of engine and expert experience, the weights are determined as follows.

1) For “normal system ($F_1$)”, the contribution of the two diagnostic methods is the same, that is, $C_{11}$ and $C_{12}$ are 0.5.

2) For “Bearing Fatigue Failure ($F_2$)”, because vibration information has high reliability for the diagnosis of fatigue failure, it mainly relies on vibration information for diagnosis, so the weights of the two diagnostic methods are as follows: the weight $C_{21}$ of spectral information is 0.3, and the weight $C_{22}$ of vibration information is 0.7.

3) For bearing wear failure ($F_3$), because the metal debris worn on the bearing surface is usually non-ferromagnetic particles and needs to be detected by spectroscopy, the weights of the two diagnostic methods are as follows: the weights of spectral information $C_{31}$ are 0.7, and the weights of vibration information $C_{32}$ are 0.3.

4) For “gear gluing or scratching ($F_4$)”, because the spectrum can analyze the metal composition and content of gear wear. Vibration information contributes little to such faults, so the weights of the two diagnostic methods are: the weight $C_{41}$ of spectral information is 0.9, and the weight $C_{42}$ of vibration information is 0.1.

5) For “gear overload fatigue ($F_5$)”, with fault 3, vibration information accounts for the largest proportion in this kind of fault diagnosis, so the weights of the two diagnostic methods are: spectral information weight $C_{51}$ is 0.3, vibration information weight $C_{52}$ is 0.7.

In summary, the weight matrix $\mathbf{C}$ is:

Vector $\mathbf{F}=\left(F_1,F_2,F_3,F_4,F_5\right)$ comprehensive decision results, is the final diagnosis results.