Intra-class adaptation fault diagnosis method for bearing under variable working conditions

A fault diagnosis method for a rolling bearing under variable working conditions based on a convolutional neural network and transfer learning, comprising:

• Step 1:
• acquiring bearing vibration data in different health states under different working conditions, using the bearing vibration data in the different health states under each working condition as one domain, wherein data in different domains conforms to different distributions, and segmenting the data to form samples;
• Step 2:
• performing a fast Fourier transform (FFT) on samples in a source domain and samples in a target domain, and feeding labeled samples in the source domain and unlabeled samples in the target domain at the same time into a deep intra-class adaptation convolutional neural network model with initialized parameters in a training stage;
• Step 3:
• extracting low-level features of the samples by using improved ResNet-50 in the deep intra-class adaptation convolutional neural network model, performing, by a multi-scale feature extractor, further analysis based on the low-level features to obtain high-level features as an input of a classifier, and at the same time calculating a conditional distribution distance between the high-level features of the samples in the two domains;
• Step 4:
• combining the conditional distribution distance between the source domain and the target domain and classification loss of samples in the source domain to form a target function, optimizing the target function by using a stochastic gradient descent (SGD) method, and training the parameters of the model;
• Step 5:
• inputting a sample set of the target domain into a trained deep neural network diagnosis model, qualitatively and quantitatively determining a fault type and a fault size of each test sample by using an actual outputted label value, and performing comparison with labels that are marked in advance but do not participate in training, to obtain diagnosis accuracy,
• wherein Step 3 comprises:
• Step 3.1:
• modifying a structure of ResNet-50, and removing last two layers of the model:
• a global average pooling layer and a fully connected layer used for classification, wherein the deep intra-class adaptation convolutional neural network model extracts the low-level features of the samples by using the improved ResNet-50, and a process of an extraction is as follows:
• g(x)ƒ(x),
• wherein x represents a sample in a frequency domain after the FFT, ƒ(·) represents the modified ResNet-50, and g(x) represents the low-level features extracted from the samples by using the improved ResNet-50;
• Step 3.2:
• further analyzing, by a plurality of substructures of the multi-scale feature extractor, the low-level features at the same time to obtain the high-level features as an input of a softmax classifier, wherein a process of extracting the high-level features is represented as follows:
• g(x)=[g0(x),g1(x), . . . ,gn-1(x)],
• wherein gi(x) is an output of one substructure, i∈{0, 1, 2, . . . , n−1}, and n is a total quantity of substructures in the feature extractor;
• and a softmax function is represented as follows:
• q
• i
• =
• e
• Vi
• ∑
• i
• =
• 0
• C
• -
• 1
• e
• Vi
• ,
• wherein qi represents a probability that a sample belongs to a label i, C is a total quantity of label classes, and vi is a value of an ith position of an input of the softmax function;
• and
• Step 3.3:
• calculating the conditional distribution distance between the high-level features in the source domain and the target domain, wherein because labels of samples in the target domain are unknown in a training process, it seems impossible to match the conditional distribution distance between the source domain and the target domain, and predetermined results for samples in the target domain by a deep learning model in a training iteration process are used as pseudo labels to calculate the conditional distribution distance between the source domain and the target domain, and a formula for a conditional distribution distance between features extracted by one substructure of the multi-scale feature extractor is as follows:
• d
• H
• (
• X
• s
• ,
• X
• t
• )
• =
• 1
• C
• ⁢
• ∑
• c
• =
• 0
• C
• -
• 1
• 
• 1
• n
• s
• (
• c
• )
• ⁢
• ∑
• i
• =
• 0
• n
• s
• (
• c
• )
• -
• 1
• Φ
• ⁢
• (
• X
• i
• s
• ⁡
• (
• c
• )
• )
• -
• 1
• n
• t
• (
• c
• )
• ⁢
• ∑
• j
• =
• 0
• n
• t
• (
• c
• )
• -
• 1
• Φ
• ⁡
• (
• X
• j
• t
• ⁡
• (
• c
• )
• )
• 
• H
• 2
• ,
• wherein H represents the reproducing kernel Hilbert space, and Φ(·) represents a function of feature space mapping;
• xis(c) represents an ith sample in samples with a label of c in the source domain, ns(c) is equal to a quantity of all samples with the label of c in the source domain, xji(c) represents a jth sample in samples with a pseudo label of c in the target domain, and ns(c) is equal to a quantity of all samples with the pseudo label of c in the target domain;
• a foregoing expression is used for estimating a difference between intra-class condition distributions Ps(xs|ys=c) and Pt(xt|yt=c);
• a conditional distribution difference between the source domain and the target domain can be reduced by minimizing the foregoing expression;
• and because the high-level features are extracted by the plurality of substructures at the same time, a total conditional distribution distance is as follows:
• d
• ⁡
• (
• X
• s
• ,
• X
• t
• )
• =
• ∑
• i
• =
• 0
• n
• -
• 1
• d
• ⁢
• g
• i
• (
• X
• s
• )
• ,
• g
• i
• (
• X
• t
• )
• ,
• wherein gi(x) is the output of one substructure, i∈{0, 1, 2, . . . , n−1}, and n is the total quantity of substructures in the feature extractor;
• although pseudo labels rather than actual labels of samples in the target domain are used in the training process, as a quantity of iterations increases, a training loss keeps decreasing, and the pseudo labels keep approaching the actual labels, to maximize the accuracy of classifying samples in the target domain.