Turnout switch equipment mechanical fault diagnosis method based on complementary feature enhancement and consistency learning

Abstract

The invention discloses a turnout switch equipment mechanical fault diagnosis method based on complementary feature enhancement and consistency learning, and relates to the technical field of equipment safety assessment, and the method comprises the following steps: 1, collecting vibration signal data of turnout switch equipment; step 2, constructing a double-branch structure, and performing feature extraction through the double-branch structure; step 3, constructing a complementary feature enhancement module, fusing the extracted features through the complementary feature enhancement module to obtain fused features, and updating the extractor E1, the extractor E2 and the main diagnostor C through loss function minimization; step 4, constructing domain invariant features based on a domain adversarial learning framework; step 5, constructing an auxiliary diagnosis device Ca, jointly constructing the main diagnosis device C and the auxiliary diagnosis device Ca into a double diagnosis device, performing consistency learning through the double diagnosis device, and optimizing the E1 and the E2 again; and step 6, performing fault diagnosis through the main diagnostor C to obtain a diagnosis result.

Description

Technical Field

[0001] The present invention relates to the technical field of equipment safety assessment, and in particular to a mechanical fault diagnosis method for turnout equipment based on complementary feature enhancement and consistency learning. Background Art

[0002] As an indispensable and important part of train operation, the operating status of turnout switch equipment is directly related to the safety of train operation. Mechanical failure of turnout switch equipment often leads to unstable equipment operation and even serious accidents. Therefore, it is of great significance to perform efficient and accurate mechanical fault diagnosis of turnout switch equipment. With the development of intelligent methods based on deep learning, a lot of results have been achieved in the research of fault diagnosis of mechanical equipment.

[0003] The rapid development of deep learning in the field of computer vision has promoted the progress of intelligent fault diagnosis. Traditional deep learning methods assume that training data and test data follow the same distribution. However, in actual scenarios, when the operating conditions of the equipment change, it is very easy to cause changes in the data distribution, resulting in a decrease in the diagnostic performance of the trained diagnostic model. In addition, it is impractical to collect and annotate a large amount of fault data because the equipment is less likely to fail during natural operation. In the face of fault diagnosis under variable operating conditions, unsupervised domain adaptation technology has shown great potential. In the absence of labeled data in the target domain, unsupervised domain adaptation transfers the knowledge learned by the model from the source domain to the target domain, which is one of the important methods to solve the domain migration problem.

[0004] Most of the existing unsupervised domain adaptive fault diagnosis methods map the features of the source domain and the target domain to a high-dimensional space by maximizing the mean difference (MMD), and then calculate the distance between the two feature distributions. By minimizing the distance between the feature distributions, the migration from the source domain to the target domain can be achieved. Another commonly used method is to introduce adversarial learning methods to achieve domain adaptation through adversarial training. Its basic idea is based on the idea of ​​generative adversarial networks (GANs), introduce a domain discriminator into the model, and make the feature distributions of the source domain and the target domain as similar as possible through adversarial training of the domain discriminator and the feature generator. In this way, the migration from the source domain to the target domain can be achieved. However, most of these methods focus on aligning the feature distributions of the source domain and the target domain, ignoring the acquisition of rich fault information from the original signal. In addition, in order to meet the distribution alignment, these methods are prone to sacrifice some category-related information, thereby limiting the further improvement of diagnostic accuracy. Therefore, a mechanical fault diagnosis method for turnout equipment based on complementary feature enhancement and consistency learning is urgently needed to solve the problems existing in the existing technology. Summary of the invention

[0005] The purpose of the present invention is to provide a mechanical fault diagnosis method for turnout equipment based on complementary feature enhancement and consistency learning, so as to solve the problems of limited accuracy, poor robustness and poor reliability of existing diagnostic models in the prior art.

[0006] To achieve the above object, the present invention provides a method for diagnosing mechanical faults of turnout equipment based on complementary feature enhancement and consistency learning, comprising the following steps:

[0007] Step 1: Collect vibration signal data of turnout equipment; manually annotate the data and divide the annotated data into source domain D s and the target domain D t ;

[0008] Step 2: Construct a dual-branch structure and perform feature extraction through the dual-branch structure, where the first branch focuses on capturing time series features through extractor E1 The second branch focuses on capturing frequency domain features through extractor E2

[0009] Step 3: Construct a complementary feature enhancement module to extract the time series features and frequency domain characteristics Fusion is performed to obtain the fused feature f i s , and update the extractors E1, E2 and the main diagnostic device C by minimizing the loss function to capture more comprehensive fault feature information;

[0010] Step 4: Construct domain-invariant features based on the domain adversarial learning framework;

[0011] Step 5: Build the auxiliary diagnostic device Ca, build the main diagnostic device C and the auxiliary diagnostic device Ca together as a dual diagnostic device, perform consistency learning through the dual diagnostic device, and optimize E1 and E2 again; through the mutual cooperation of the two diagnostic devices, enhance the robustness of the features and improve the generalization ability of the model for fault modes under different working conditions

[0012] Step 6: Perform fault diagnosis through the main diagnostic device C to obtain the diagnosis result.

[0013] Preferably, the source domain D with labels in step 1 s and the unlabeled target domain D t The specific representation is as follows:

[0014]

[0015] in, represents the source domain sample, represents the health status category label, n srepresents the number of source domain samples, M represents the number of health status categories; represents the target domain sample, n t represents the number of samples in the target domain. The source domain and the target domain have the same label space, which is represented by |Y s |=|Y t |=M.

[0016] Preferably, in step 3, the extracted time series features are enhanced by a complementary feature enhancement module. and frequency domain characteristics Fusion is performed to obtain the fused feature f i s The process is as follows:

[0017] S31. Calculate time series characteristics and frequency domain characteristics Intimacy A i , the calculation expression is as follows:

[0018]

[0019] S32. Calculate the features that E1 and E2 focus on together The calculation expression is as follows:

[0020]

[0021] S33. Calculate the complementary features of E1 and E2 The calculation expression is as follows:

[0022]

[0023] S34, obtain the fused feature f i s , the expression is as follows:

[0024]

[0025] In the formula, σ(·) represents Softmax, (·) T represents the matrix transpose, ψ(·), g(·), θ(·) both represent linear mapping functions, which are implemented using 1×1 convolution. FC represents a fully connected layer to integrate information. i It reflects the correlation between the features of the two branches, that is, the information that is of common concern, so 1-A i It indicates the difference between the features of the two branches, that is, the information that they do not pay attention to each other.

[0026] Preferably, through the loss function L ecThe expression for minimizing the updates to extractors E1, E2 and main diagnostics C is as follows:

[0027]

[0028] Where CE(·) represents the cross entropy loss function.

[0029] Preferably, in step 4, based on the domain adversarial learning framework, the expression of constructing the domain-invariant feature is as follows:

[0030] L D (D) = CE (D (f i m ),d i );

[0031] L adv (E1,E2)=CE(D(f i m ),d i );

[0032] Where CE(·) represents the cross entropy loss function, f i m Represents the characteristics of the source domain and the target domain, m = {s, t}, d i Represents the domain label, when x i When coming from the source domain, d i =1, when x i From the target domain i = 0, D represents the domain identifier, L D represents the domain classification loss, L adv represents the domain adversarial loss, and updates L alternately D and L adv , conduct adversarial training.

[0033] Preferably, in step 5, consistency learning is performed through a dual diagnostic device, and the expressions of E1 and E2 are optimized again as follows:

[0034]

[0035] In the formula, ||·|| 2 represents the MSE loss function, L con represents the consistency loss function, n b Indicates the batch size.

[0036] Preferably, the expression of the diagnosis result obtained by performing fault diagnosis by the main diagnostic device C in step 6 is as follows:

[0037] Accuracy=C(f i t );

[0038] In the formula, f i t express The target domain data features are obtained by extracting features through E1 and E2 and enhancing them through the complementary feature enhancement module.

[0039] Therefore, the present invention adopts the above-mentioned turnout equipment mechanical fault diagnosis method based on complementary feature enhancement and consistency learning, which has the following beneficial effects:

[0040] (1) The present invention uses a dual-branch structure to extract features through complementary feature learning, and fuses the features of the two branches through a complementary feature enhancement module, thereby effectively capturing more comprehensive fault feature information and improving the accuracy of fault identification;

[0041] (2) The present invention integrates dual diagnostic devices for consistency learning based on the domain adversarial learning framework, which alleviates the distribution difference between the source domain and the target domain and realizes domain-invariant feature representation. In addition, this design not only improves the robustness of the features, but also improves the generalization ability of the model for fault modes under different working conditions, thereby enhancing the reliability of fault diagnosis.

[0042] (3) The method of the present invention can be widely applied to different types of turnout equipment, such as gears, bearings, etc., and has good versatility and adaptability. The implementation of this method can provide strong technical support for the health management of turnout equipment machinery, and help realize the intelligent and automated maintenance of the mechanical system of turnout equipment.

[0043] The technical solution of the present invention is further described in detail below through the accompanying drawings and embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] Figure 1 It is an overall flow chart of a mechanical fault diagnosis method of a turnout equipment based on complementary feature enhancement and consistency learning of the present invention;

[0045] Figure 2 Schematic diagram of a complementary feature enhancement module according to an embodiment of the present invention. DETAILED DESCRIPTION

[0046] The following detailed description of the embodiments of the present invention provided in the accompanying drawings is not intended to limit the scope of the invention claimed for protection, but merely represents selected embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0047] See also Figure 1-Figure 2 A mechanical fault diagnosis method for turnout equipment based on complementary feature enhancement and consistency learning comprises the following steps:

[0048] Step 1: Collect vibration signal data of turnout equipment; manually annotate the data and divide the annotated data into source domain D s and the target domain D t ; Among them, the labeled source domain D s and the unlabeled target domain D t The specific representation is as follows:

[0049]

[0050]

[0051] in, represents the source domain sample, Indicates the health status category label, n s represents the number of source domain samples, M represents the number of health status categories; represents the target domain sample, n t represents the number of samples in the target domain. The source domain and the target domain have the same label space, which is represented by |Y s |=|Y t |=M.

[0052] Step 2: Construct a dual-branch structure and perform feature extraction through the dual-branch structure, where the first branch focuses on capturing time series features through extractor E1 The second branch focuses on capturing frequency domain features through extractor E2

[0053] Step 3: Construct a complementary feature enhancement module to extract the time series features and frequency domain characteristics Fusion is performed to obtain the fused feature f i s , and update the extractors E1, E2 and the main diagnostic device C by minimizing the loss function to capture more comprehensive fault feature information; among them, the extracted time series features are enhanced by the complementary feature enhancement module and frequency domain characteristics Fusion is performed to obtain the fused feature f i s The process is as follows:

[0054] S31. Calculate time series characteristics and frequency domain characteristics Intimacy A i , the calculation expression is as follows:

[0055]

[0056] S32. Calculate the features that E1 and E2 focus on together The calculation expression is as follows:

[0057]

[0058] S33. Calculate the complementary features of E1 and E2 The calculation expression is as follows:

[0059]

[0060] S34, obtain the fused feature f i s , the expression is as follows:

[0061]

[0062] In the formula, σ(·) represents Softmax, (·) T represents the matrix transpose, ψ(·), g(·), θ(·) both represent linear mapping functions, which are implemented using 1×1 convolution. FC represents a fully connected layer to integrate information. i It reflects the correlation between the features of the two branches, that is, the information that is of common concern, so 1-A i It indicates the difference between the features of the two branches, that is, the information that they do not pay attention to each other.

[0063] Through the loss function L ec The expression for minimizing the updates to extractors E1, E2 and main diagnostics C is as follows:

[0064]

[0065] Where CE(·) represents the cross entropy loss function.

[0066] Step 4: Based on the domain adversarial learning framework, construct domain-invariant features; the specific expression is as follows:

[0067] L D (D) = CE (D (f i m ),d i );

[0068] L adv (E1,E2)=CE(D(f i m ),d i );

[0069] Where CE(·) represents the cross entropy loss function, f i mRepresents the characteristics of the source domain and the target domain, m = {s, t}, d i Represents the domain label, when x i When coming from the source domain, d i =1, when x i From the target domain i = 0, D represents the domain identifier, L D represents the domain classification loss, L adv represents the domain adversarial loss, and updates L alternately D and L adv , conduct adversarial training.

[0070] Step 5: Construct the auxiliary diagnostic device Ca, build the main diagnostic device C and the auxiliary diagnostic device Ca together as a dual diagnostic device, perform consistency learning through the dual diagnostic device, and optimize E1 and E2 again; through the mutual cooperation of the two diagnostic devices, enhance the robustness of the features and improve the generalization ability of the model for fault modes under different working conditions; among them, through the dual diagnostic device, perform consistency learning, and optimize E1 and E2 again. The expressions are as follows:

[0071]

[0072] In the formula, ||·|| 2 represents the MSE loss function, L con represents the consistency loss function, n b Indicates the batch size, that is, Batchsize.

[0073] Step 6: Perform fault diagnosis through the main diagnostic device C to obtain the diagnosis result; the specific calculation expression is as follows:

[0074] Accuracy=C(f i t );

[0075] In the formula, f i t express The target domain data features are obtained by extracting features through E1 and E2 and enhancing them through the complementary feature enhancement module.

[0076] Example

[0077] In order to verify the effectiveness of the proposed method, experiments were conducted on the CWRU bearing dataset. The effectiveness of the proposed method was verified on multiple diagnostic tasks to improve the fault identification accuracy and diagnostic efficiency of turnout equipment.

[0078] Rolling bearings are key mechanical components in turnout machines. The CWRU dataset is provided by Western Reserve University. The experimental platform operates at four different loads and speeds. The data in this experiment is acquired at a sampling frequency of 48KHZ, including 10 types of health states: healthy (NC), three different degrees of inner race faults (IF0, IF1, IF2), three different degrees of outer race faults (OF0, OF1, OF2) and three different degrees of rolling element faults (BF0, BF1, BF2). The detailed information of the dataset is shown in Table 1.

[0079] Table 1 Experimental data statistics

[0080]

[0081]

[0082] We compared the one-dimensional convolutional neural network CNN (Baseline), the deep domain adversarial network DANN, and the related alignment method CORAL. All methods used the same network structure and were compared in the same environment. According to the practice of existing studies, each experiment was conducted five times, and the average diagnostic accuracy and standard deviation were taken as the final results. Table 2 shows the accuracy of different methods on 12 diagnostic tasks (C 01 It can be seen that the proposed method has obvious advantages. 30 ), the worst model accuracy reached 73.34%±2.31%, while the method proposed in this paper achieved an accuracy of 89.24%±2.24% in this task. The results show that the method proposed in this paper is effective in the variable working condition fault diagnosis task.

[0083] Table 2 Comparison of diagnostic accuracy with other methods on the CWRU dataset (%)

[0084]

[0085] Therefore, the present invention adopts the above-mentioned mechanical fault diagnosis method of turnout equipment based on complementary feature enhancement and consistency learning. First, a dual-branch structure is used for feature extraction, and the features of the two branches are fused through a complementary feature enhancement module, effectively capturing more comprehensive fault feature information. Then, a complementary feature enhancement module is constructed, and the extracted features are fused through the complementary feature enhancement module, and domain-invariant features are constructed based on the domain adversarial learning framework; then, consistency learning is performed through a dual diagnostic device; finally, fault diagnosis is performed through the main diagnostic device to obtain a diagnostic result.

[0086] Finally, it should be noted that the above embodiments are only used to illustrate the technical solution of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that they can still modify or replace the technical solution of the present invention with equivalents, and these modifications or equivalent replacements cannot cause the modified technical solution to deviate from the spirit and scope of the technical solution of the present invention.

Claims

1. A mechanical fault diagnosis method for turnout equipment based on complementary feature enhancement and consistency learning, characterized in that: The following steps are involved: Step 1, collecting vibration signal data of turnout switching equipment; The labeled data is divided into source domain D s and the target domain D t ; Step 2: Construct a dual-branch structure and perform feature extraction through the dual-branch structure, where the first branch focuses on capturing time series features through extractor E1 The second branch focuses on capturing frequency domain features through extractor E2 Step 3: Construct a complementary feature enhancement module to extract the time series features and frequency domain characteristics Fusion is performed to obtain the fused feature f i s , and update the extractors E1, E2 and the main diagnostic device C by minimizing the loss function; Step 4: Construct domain-invariant features based on the domain adversarial learning framework; Step 5: Build an auxiliary diagnostic device Ca, build the main diagnostic device C and the auxiliary diagnostic device Ca together into a dual diagnostic device, perform consistency learning through the dual diagnostic device, and optimize E1 and E2 again; Step 6: Perform fault diagnosis through the main diagnostic device C to obtain the diagnosis result.

2. A mechanical fault diagnosis method for turnout equipment based on complementary feature enhancement and consistency learning according to claim 1, characterized in that: The labeled source domain D in step 1 s and the unlabeled target domain D t The specific representation is as follows: in, represents the source domain sample, represents the health status category label, n s represents the number of source domain samples, M represents the number of health status categories; represents the target domain sample, n t represents the number of samples in the target domain. The source domain and the target domain have the same label space, which is represented by |Y s |=|Y t |=M.

3. A method for mechanical fault diagnosis of turnout equipment based on complementary feature enhancement and consistency learning according to claim 2, characterized in that: In step 3, the extracted time series features are enhanced by the complementary feature enhancement module and frequency domain characteristics Fusion is performed to obtain the fused feature f i s The process is as follows: S31. Calculate time series characteristics and frequency domain characteristics Intimacy A i , the calculation expression is as follows: S32. Calculate the features that E1 and E2 focus on together The calculation expression is as follows: S33. Calculate the complementary features of E1 and E2 The calculation expression is as follows: S34, obtain the fused feature f i s , the expression is as follows: In the formula, σ(·) represents Softmax, (·) T represents the matrix transpose, ψ(·), g(·) and θ(·) both represent linear mapping functions, which are implemented using 1×1 convolution. FC represents a fully connected layer to integrate information.

4. A mechanical fault diagnosis method for turnout equipment based on complementary feature enhancement and consistency learning according to claim 3, characterized in that: Through the loss function L ec The expression for minimizing the updates to extractors E1, E2 and main diagnostics C is as follows: L ec (E1,E2,C)=CE(C(f i s ),y i s ); Where CE(·) represents the cross entropy loss function.

5. A method for mechanical fault diagnosis of turnout equipment based on complementary feature enhancement and consistency learning according to claim 4, characterized in that: In step 4, based on the domain adversarial learning framework, the expression for constructing domain-invariant features is as follows: L D (D)=CE(D(f i m ),d i ); L adv (E1,E2)=CE(D(f i m ),d i ); In the formula, CE(·) represents the cross entropy loss function, f i m Represents the characteristics of the source domain and the target domain, m = {s, t}, d i Represents the domain label, when x i When coming from the source domain, d i =1, when x i From the target domain i = 0, D represents the domain identifier, L D represents the domain classification loss, L adv represents the domain adversarial loss, and updates L alternately D and L adv , conduct adversarial training.

6. A method for mechanical fault diagnosis of turnout equipment based on complementary feature enhancement and consistency learning according to claim 5, characterized in that: In step 5, consistency learning is performed through the dual diagnostic device, and the expressions of E1 and E2 are optimized again as follows: In the formula, ||·|| 2 represents the MSE loss function, L con represents the consistency loss function, n b Indicates the batch size.

7. A method for diagnosing mechanical faults of turnout equipment based on complementary feature enhancement and consistency learning according to claim 6, characterized in that: In step 6, the diagnosis result obtained by the main diagnostic device C is expressed as follows: Accuracy=C(f i t ); In the formula, f i t express The target domain data features are obtained by extracting features through E1 and E2 and enhancing them through the complementary feature enhancement module.

Images