US 11,454,567 B2 · Fault diagnosis method of reciprocating machinery based on keyphasor-free complete-cycle signal

Abstract

The present disclosure relates to a fault diagnosis method of a reciprocating machinery based on a keyphasor-free complete-cycle signal. The method includes the following steps: 1) building a complete-cycle vibration signal image library; 2) training an image recognition model; 3) acquiring a complete-cycle data on a keyphasor-free basis; 4) building an automatic feature extraction model; and 5) inputting a hidden layer feature of an autoencoder into a support vector machine (SVM) classifier to obtain a diagnosis result. By using a deep cascade convolutional neural network (CNN), the present disclosure achieves the goal of complete-cycle data acquisition on a keyphasor-free basis, solves the problems that traditional intelligent fault diagnosis relies on a keyphasor signal and real-time diagnosis fails due to insufficient installation space. In addition, by using an autoencoder for automatic feature extraction, the present disclosure avoids manual feature selection, reduces labor costs.

A fault diagnosis method of a reciprocating machinery based on a keyphasor-free complete-cycle signal, wherein the method comprises the following steps:

step 1:
acquiring, by an online monitoring system of the reciprocating machinery, m groups of vibration acceleration data of a single cycle of a measuring point of a cylinder head in a normal state and an abnormal state respectively on a keyphasor basis to generate a normal data set Nm and an abnormal data set Am;
normalizing each group of data in the two data sets by using a z-score method to obtain a processed normal data set N′m and abnormal data set A′m;
generating images with a size of h1×h2 from the m groups of data in the normal data set N′m to acquire a normal data image set Pm;
step 2:
partitioning each image in the normal data image set Pm into sub-images with a size of
h
⁢
1
4
×
h
⁢
2
according to an order of the intake stroke, the compression stroke, the power stroke and the exhaust stroke;
labeling the sub-images to generate an intake stroke image set J={j1, j2, j3, . . . ,jm}, a compression stroke image set C={c1, c2,c3, . . . ,cm}, a power stroke image set F={f1, f2, f3, . . . , fm} and an exhaust stroke image set E={e1,e2,e3, . . . ,em};
dividing the four stroke image sets into a training set and a test set respectively to obtain a training image set Train_C={Jtrain, Ctrain, Ftrain, Etrain} and a test image set Test_C={Jtest, Ctest, Ftest, Etest}, wherein partitioning is based on locating the shock positions of the intake stroke, the compression stroke, the power stroke, and the exhaust stroke in the vibration acceleration data;
step 3:
building and training a two-class hybrid convolutional neural network (CNN) Net;
3.1:
representing categories of classification of the network Net by 0 and 1 respectively, wherein 0 indicates that an input data is not a complete-cycle data, and 1 indicates that the input data is a complete-cycle data;
composing the network Net by an intake stroke CNN CNN_J, a compression stroke CNN CNN_C a power stroke CNN CNN_E and an exhaust stroke CNN CNN_E;
adopting a mean cross-entropy loss function Mloss as follows:
M
l
⁢
o
⁢
s
⁢
s
=
1
k
⁢
∑
j
=
1
k
L
j
(
q
i
)
⁢
L
J
(
q
i
)
=
-
[
y
i
·
log
2
(
q
i
)
+
(
1
-
y
i
)
·
log
2
(
1
-
q
i
)
]
wherein, qi∈[0,1] represents a predicted value of a one-dimensional vector corresponding to an i-th category;
Lj(qi) represents a cross-entropy loss function for category i;
k represents a count of CNNs;
γi represents a true value of the i-th category;
j represents a j-th CNN;
3.2:
setting the four CNNs with the same network structure comprising an input layer, a convolution layer 1, a pooling layer 1, a convolution layer 2, a pooling layer 2, a fully connected layer 1 and a fully connected layer 2, wherein an input image in the input layer is a grayscale image of
h
⁢
1
4
×
h
⁢
2
;
output results of the convolution layer 1, the pooling layer 1, the convolution layer 2 and the pooling layer 2 are respectively processed by batch normalization, and output results of the fully connected layer 1 and the fully connected layer 2 are respectively processed by L2 regularization;
3.3:
denoting predicted probability values output by CNN_J, CNN_C, CNN_F and CNN_E as gJ,gC,gF,gE respectively, and taking a mean probability value g as a predicted probability value of the two-class hybrid CNN Net, wherein the mean probability value is calculated as follows:
g
=
g
J
+
g
C
+
g
F
+
g
E
4
inputting the training image set Train_C={Jtrain, Ctrain, Ftrain Etrain} into a built Net network model for training;
testing a trained network model by using the test set Test_C={Jtest, Ctest, Ftest, Etest} to obtain a final two-class hybrid CNN model which is denoted as T_Net;
calculating a test accuracy as follows:
Ac
⁢
c
=
Corr
T
⁢
e
⁢
s
⁢
t
-
⁢
m
×
1
⁢
0
⁢
0
⁢
%
wherein, Corr represents a count of correct identification;
Test_m represents a total count of test data;
step 4:
acquiring a complete-cycle data of the reciprocating machinery on a keyphasor-free basis;
4.1:
selecting a measuring point of the cylinder head of the reciprocating machinery, and continuously acquiring normal vibration acceleration data Sn={s1, s2, s3, . . . , sn} and abnormal vibration acceleration data Ab_Sn′={ab_s1, ab_s2, ab_s3, . . . , ab_sn′} of two or more cycles on a keyphasor-free basis, wherein n and n′ respectively represent a count of sampling points;
4.2:
determining, according to a sampling frequency Fs of the monitoring system and a working speed range [Rmin, Rmax] of a unit, a range of sampling point count [Wmin, Wmax] of a complete cycle as follows:
W
min
=
1
⁢
2
⁢
0
R
max
·
F
s
⁢
W
max
=
1
⁢
2
⁢
0
R
min
·
F
s
setting a series of window lengths
Wv={Wmin,Wmin+d,Wmin+2d, . . . ,Wmin+αd},α=0,1,2, . . . , that is, a total of α+1 window lengths, according to [Wmin,Wmax], wherein d represents a gradient of length change;
Wmin+αd≤Wmax, and 10<d≤Wmin;
4.3:
performing sliding cut-off on data Sn, in window Wmin with a step Step to obtain a cut-off result Sn1;
traversing data Sn through the window to obtain a cut-off data set Cut1={Sn11,Sn12, . . . };
normalizing data in Cut1 by the z-score method to obtain a data set Cut1′;
generating images with a size of h1×h2 from each group of data in Cut1′ respectively;
partitioning each generated image from left to right into sub-images with a size of
h
⁢
1
4
×
h
⁢
2
,
wherein a partitioning result of each image is denoted as Sn1_P={img1,img2,img3,img4};
calculating the image set of each window in turn to obtain image sets
Cut1_P={Sn11_P,Sn12_P, . . . },Cut2_P={Sn21_P,Sn22_P, . . . }, . . . ,Cut(α+1)_P={Sn(α+1)1_P,Sn(a+1)2_P, . . . };
4.4:
sequentially selecting and inputting a first part of images in image set Cut1_P into T_Net for initial classification;
continuing to classify a remaining image if the selected images comprise a complete-cycle image, wherein a data point corresponding to a complete-cycle image recognized by the classification of T_Net is a complete-cycle data, which is denoted as zqi′;
stopping classification of the remaining image in Cut1_P and switching to a next window, if the selected images do not comprise a complete-cycle image;
calculating a count of images initially classified as follows:
Count
=
W
⁢
in
Step
wherein, Win represents a window in Wv;
4.5:
processing the image sets obtained by all windows according to the method in step 4.4 to finally obtain a normal complete-cycle data set T_zq={zq1, zq2, zq3, . . . , zqi′},i′=1,2,3, through keyphasor-free cut-off;
performing cut-off on abnormal data Ab_Sn′ by steps 4.2 to 4.5 to obtain cut-off cycle data ab_zqi′, and finally obtaining an abnormal complete-cycle data set Ab_zq={ab_zq1, ab_zq2, ab_zq3, . . . , ab_zqi′,} through keyphasor-free cut-off;
step 5:
building an automatic feature extraction model, that is, an autoencoder model, wherein the automatic feature extraction model provides a plurality of hidden layers of a keyphasor-free vibration signal;
dividing the normal data Nm and abnormal data Am of the vibration acceleration of the cylinder head acquired on a keyphasor basis into a training set Train and a test set Test, and labeling “normal” and “abnormal” respectively;
building an autoencoder comprising an input layer, a hidden layer 1, a hidden layer 2, a hidden layer 3, a hidden layer 4 and an output layer;
training an initial autoencoder model by the training set Train, and testing the model by the test set Test to obtain an autoencoder-based feature extraction model;
step 6:
labeling the complete-cycle data sets T_zq and Ab_zq obtained in step 4 as “normal” and “abnormal”, and then dividing the complete-cycle data sets into a training set and a test set respectively according to the same ratio;
inputting the training set into the autoencoder model obtained in step 5;
taking an intermediate hidden layer feature obtained by the autoencoder as an input into a support vector machine (SVM) model to train a two-class SVM model, which outputs “1” indicating normal or “0” indicating abnormal;
step 7:
classifying normal and abnormal keyphasor-free complete-cycle signals of the reciprocating machinery by the two-class SVM model after training to perform fault diagnosis on a keyphasor-free complete-cycle signal of a reciprocating machinery;
and
Step 8:
gathering the keyphasor-free vibration signal of the reciprocating machinery, and determining fault of the reciprocating machinery based on the abnormal output of the trained two-class SVM model, wherein the complete-cycle data is acquired by performing cut-off steps of 4.2 to 4.5 on the gathered keyphasor-free vibration signal, and wherein the acquired complete-cycle data is input into the trained two-class SVM model.

223 more elements

Fault diagnosis method of reciprocating machinery based on keyphasor-free complete-cycle signal

Life of this patent

Fault diagnosis method of reciprocating machinery based on keyphasor-free complete-cycle signal

Life of this patent

Abstract

Claims1