Field generalization-based mechanical assembly fault prediction method and equipment
By performing domain generalization of mechanical equipment fault prediction model, using linear interpolation and orthogonal feature extraction technology, the problems of data acquisition and inter-domain offset of unknown target domain are solved, and the accuracy and generalization ability of fault prediction are improved. .
Patent Information
- Application Number
- CN202411208244.9
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-08-30
- Publication Date
- 2024-12-03
- Estimated Expiration
- 2044-08-30
AI Technical Summary
The existing fault prediction method based on domain adaptation and domain generalization has the problem of low prediction accuracy when processing unknown target domain data, mainly because the unknown target domain data cannot be obtained and the similarity of the source domain and target domain degradation characteristics cannot be fully considered. and difficulty in alleviating edge and conditional distribution offsets between different source domains simultaneously.
By linearly interpolation of intra-domain data and inter-domain data with similar labels in the training set, the common degradation features are extracted and the orthogonal degradation features are calculated, and the common feature extractor is trained and Orthogonal degradation feature extractor reduces the offset of features and labels and enhances the generalization ability of the model.
It improves the accuracy and generalization ability of the mechanical equipment fault prediction model, can more effectively represent the degraded characteristics of unknown target domains, reduces the offset between different source domains, and improves the prediction accuracy under unknown conditions.
Smart Images

Figure CN119066472A_ABST
Abstract
Description
Technical Field
[0001] The present invention belongs to the technical field related to fault prediction and health management, and more specifically, to a method and device for predicting mechanical equipment faults based on domain generalization. Background Art
[0002] The main goal of prognosis and health management (PHM) is to proactively detect potential failures and degradation trends by analyzing real-time monitoring data, thereby facilitating optimal maintenance decisions and preventing failures, which is essential for improving equipment safety, reliability, and preventing catastrophic failures. As an important component of PHM, failure prediction, that is, predicting when the equipment will fail next, is essential for timely equipment maintenance and wise resource allocation.
[0003] In recent years, advances in sensor technology have facilitated the collection of a large amount of equipment monitoring data, providing the necessary data foundation for intelligent data-driven fault prediction technology. Compared with traditional model-based fault prediction methods, data-driven methods do not need to consider the complex degradation mechanism of equipment, making them more suitable for deployment in complex systems. Generally, in the field of data-driven fault prediction methods, deep learning (DL)-based fault prediction methods have become a prominent competitor due to their significant advantages, such as excellent accuracy and fast response time, which has attracted considerable interest. However, due to the variability of workloads, environmental conditions, etc., mechanical equipment usually operates under different operating conditions (OC). The difference in data distribution caused by variable OC (commonly known as domain offset) significantly reduces the predictive ability of deep prediction models.
[0004] Domain adaptation (DA) techniques can effectively mitigate domain shift and have been used to solve cross-domain fault prediction tasks in the past few years. DA-based fault prediction methods learn cross-domain invariant degradation feature representations by aligning feature distributions between source and target domains. These methods not only show robust prediction performance on the source domain, but also exhibit strong generalization capabilities on the target task. However, these methods encounter some challenges when applied to practical cross-domain prediction tasks. First, it is crucial for DA-based fault prediction methods to obtain unlabeled degradation data from the target device, which can effectively promote the transfer of prediction knowledge. However, given that the prediction task usually involves new devices in industrial prediction scenarios, it is often tricky to obtain such data in advance. Therefore, existing DA-based fault prediction methods cannot fully handle online cross-domain fault prediction tasks. Second, most DA-based fault prediction methods only generalize the prediction knowledge from a single source domain to the target domain of interest. Therefore, when the OC of the target device changes, DA-based fault prediction methods are prone to overfitting on the original domain, resulting in inaccurate prediction results.
[0005] Domain generalization (DG) can extract robust transferable knowledge from multiple known source domains and effectively perform the target task of interest under unknown OC. Therefore, DG-based fault prediction methods have become a research hotspot. However, current DG-based fault prediction methods still have the following shortcomings: 1) These methods focus on extracting common degradation features from multiple known source domains to represent the degradation features of the unknown target domain, ignoring the differences between different source domains and the unknown target domain. When there are significant differences in the degradation patterns between some source domains and the unknown target domain, these common degradation features may not accurately reflect the degradation trend of the unknown target domain. Therefore, new methods are needed to adaptively integrate existing degradation features based on the similarity between the unknown target domain and the known source domain, thereby enhancing the generalization ability of the model to unknown target data. 2) In addition, these methods usually only consider marginal distribution shift when mitigating domain shift. However, the degradation data in fault prediction tasks have continuous and different labels. Mitigating only marginal distribution changes may lead to incorrect alignment of features with different labels, thereby hindering the model's ability to effectively learn the mapping relationship between features and labels. Therefore, it is also necessary to align features with different labels separately, that is, to alleviate the change of conditional distribution. Summary of the invention
[0006] In response to the above defects or improvement needs of the prior art, the present invention provides a mechanical equipment fault prediction method and device based on domain generalization, which aims to solve the problem of low prediction accuracy in fault prediction due to the inability to obtain unknown target domain data, not considering the similarity between the degradation characteristics of the source domain and the unknown target domain, and difficulty in simultaneously alleviating the edge and conditional distribution offsets between different source domains.
[0007] To achieve the above object, according to one aspect of the present invention, a mechanical assembly fault prediction method based on domain generalization is provided, and the prediction method comprises the following steps:
[0008] S1, linearly interpolate the intra-domain data and inter-domain data pairs with similar labels in the training set to obtain intra-domain and inter-domain enhanced data; wherein the training set includes a part of the full life cycle sensor data of multiple mechanical assemblies under different working conditions;
[0009] S2, using the public feature extractor F CF Extract the common degradation features of the original data and enhanced data in the training set, and then input the common degradation features of the enhanced data in the domain and the original data in the training set into multiple different orthogonal degradation feature extractors F ODFk∈{1,…,K} To obtain the orthogonal degraded features of each domain, and then calculate the covariance matrix between any two source domain orthogonal degraded features, and then calculate the L2 norm of the covariance matrix, which is the feature orthogonalization loss;
[0010] S3, based on the common degradation features, an orthogonal degradation feature weighted adaptive classifier is learned that can identify the source of the data, and then the classification loss is calculated; according to the classification results of the orthogonal degradation feature weighted adaptive classifier, multi-domain orthogonal degradation features are adaptively aggregated to accurately and effectively represent the degradation features of the test data;
[0011] S4, applies label consistency constraints and sample pairing strategies to the aggregated features, thereby promoting the aggregation of features with similar labels and the separation of features with different labels in the aggregate space, and then calculates the label consistency constraint loss and sample pairing loss; at the same time, learns a regressor for predicting the occurrence time of a fault based on the aggregated features and their corresponding labels, and then calculates the regression loss;
[0012] S5, based on feature orthogonalization loss, classification loss, label consistency constraint loss, sample pairing loss and regression loss, the common feature extractor F is trained simultaneously CF , multiple orthogonal degenerate feature extractors F ODFk∈{1,…,K} , orthogonal degradation feature weighted adaptive classifier C and regressor R, and use the trained mechanical fault prediction model to predict mechanical faults.
[0013] Furthermore, the Hungarian algorithm is used to pair the intra-domain data and inter-domain data with similar labels, and then the paired data are interpolated to generate intra-domain and inter-domain enhanced data.
[0014] Furthermore, the augmented data are interpolations of data pairs from the same and different source domains, respectively. These interpolations are calculated as follows:
[0015]
[0016]
[0017]
[0018]
[0019]
[0020] in represents the in-domain enhanced data generated by using the in-domain data from the k-th source domain, is the remaining time label for the next failure of the corresponding mechanical equipment. is its corresponding domain label; represents the inter-domain enhanced data generated by the inter-domain data pair consisting of the k-th source domain and the l-th source domain, is the remaining time label of the next failure of the corresponding mechanical equipment; γ is sampled from the beta distribution and is used to control the ratio between the two samples during the interpolation process.
[0021] Furthermore, given multiple source raw data and in-domain augmented data Feature orthogonalization is achieved by optimizing the covariance matrix between any two data to a zero matrix. The calculation formula of the orthogonalization loss is:
[0022]
[0023] Where Cov(·) represents the covariance of the matrix.
[0024] Furthermore, the output of the orthogonal degraded feature weighted adaptive classifier is the probability that each input data belongs to each source domain, and the input is the common degraded feature. The cross entropy loss between the probability distribution of the output of the orthogonal degraded feature weighted adaptive classifier and the true domain label is calculated, and the cross entropy loss is the classification loss; the input of the regressor is the aggregated feature, and the output is a value between 0 and 1; the true label is also a value between 0 and 1, and the square of the difference between the output of the regressor and the true label is the regression loss.
[0025] Furthermore, given the input data xk,i , whose aggregate feature z k,i It is expressed as:
[0026]
[0027] Among them, ω k,i represents the kth source domain The weight reflects the i-th input data x k,i With the kth source domain similarity; in addition, ω k,i >0, and
[0028] Furthermore, the label consistency constraint LCC is defined as the absolute difference between the similarity of a cross-domain data pair in its original space and the degree of difference between them in the aggregated feature space, as follows:
[0029]
[0030] In the formula, for any two data from different source domains and The similarity between them is defined as in and They respectively represent the remaining time labels for the next failure of the mechanical equipment corresponding to these data; and are the data from the kth source domain respectively. The corresponding aggregate features and data from the lth source domain The corresponding aggregation features; and are the in-domain augmented data of the kth source domain respectively. The corresponding aggregated features and the in-domain enhanced data of the lth source domain The corresponding aggregation features.
[0031] Further, according to The value of determines the degree of difference between the features of any two data from different source domains, where Represents the data of the kth source domain The labels and data of the lth source domain The difference between the labels of , and the Euclidean distance d(·) is used to measure the difference between the aggregated features; the label consistency constraint loss is:
[0032] The sample pairing loss is:
[0033]
[0034] Where nb is the batch size; represents the i-th data from the k-th source domain The corresponding aggregation features; represents the jth data from the lth source domain The corresponding aggregation features.
[0035] The present invention also provides a mechanical equipment fault prediction system based on domain generalization, the system includes a memory and a processor, the memory stores a computer program, and the processor executes the mechanical equipment fault prediction method based on domain generalization as described above when executing the computer program.
[0036] The present invention also provides a computer-readable storage medium, which stores machine-executable instructions. When the machine-executable instructions are called and executed by a processor, the machine-executable instructions prompt the processor to implement the mechanical equipment fault prediction method based on domain generalization as described above.
[0037] In general, compared with the prior art, the above technical solutions conceived by the present invention mainly have the following beneficial effects:
[0038] 1. During the training process, the present invention pairs batches of raw operating parameter measurement signals with similar labels in the same source domain and different source domains, and then performs intra-domain data and inter-domain data enhancement to increase the richness of the training data; using data pairs with similar labels for data enhancement can avoid generating enhanced data that does not match the actual degradation situation. In addition, intra-domain data enhancement can capture various degradation patterns inherent in each specific source data, ensuring that the prediction model can extract more representative degradation features of a specific domain, while inter-domain data enhancement reduces the overfitting of the mechanical fault prediction model on a specific source domain by utilizing data from different source domains, thereby improving the prediction accuracy.
[0039] 2. The present invention enhances the diversity of source domain degradation features through orthogonalization, instead of extracting common degradation features of multiple source domains. The application of feature orthogonalization operation reduces the redundant information between multi-source degradation features, and can comprehensively capture various degradation features presented in the original feature space of different source domains, so as to provide diversified feature support for unknown target data in the subsequent testing stage.
[0040] 3. By learning an orthogonal degradation feature weighted adaptive classifier C that can identify the source of data in the training stage, the multi-source orthogonal degradation features can be optimally fused by weight selection in the test stage, thereby accurately representing the degradation characteristics of unknown target data. In this way, the present invention can represent and learn the degradation characteristics of unknown targets based on the similarity between the unknown target data and the known source domain data, thereby enhancing the generalization ability of the model for unknown target data.
[0041] 4. The present invention can simultaneously reduce the marginal and conditional distribution differences between features in different source domains through semantically consistent orthogonalization, thereby promoting the learning of cross-domain invariant degradation knowledge, which helps to improve the generalization ability of the mechanical fault prediction model, and then improve the fault prediction accuracy of the mechanical fault prediction model on unknown target numbers. BRIEF DESCRIPTION OF THE DRAWINGS
[0042] Figure 1 It is a flow chart of a mechanical assembly fault prediction method based on domain generalization provided by the present invention;
[0043] Figure 2 (a), (b), (c), and (d) are schematic diagrams of fault prediction results for the entire life cycle data of bearing P1_1, schematic diagrams of fault prediction results for the entire life cycle data of bearing P1_2, schematic diagrams of fault prediction results for the entire life cycle data of bearing X1_1, and schematic diagrams of fault prediction results for the entire life cycle data of bearing X1_2, respectively;
[0044] Figure 3 (a), (b), (c), (d), (e), and (f) are respectively the edge distribution maps of multi-source orthogonal degradation features extracted using baseline in task 1, the edge distribution map of multi-source orthogonal degradation features extracted using EMODF-V1 in task 1, the edge distribution map of multi-source orthogonal degradation features extracted using EMODF in task 1, the edge distribution map of multi-source orthogonal degradation features extracted using baseline in task 7, the edge distribution map of multi-source orthogonal degradation features extracted using EMODF-V1 in task 7, and the edge distribution map of multi-source orthogonal degradation features extracted using EMODF in task 7;
[0045] Figure 4(a), (b), (c), (d), (e), and (f) are the conditional distribution graphs of multi-source orthogonal degradation features extracted using baseline in task 1, the conditional distribution graph of multi-source orthogonal degradation features extracted using EMODF-V1 in task 1, the conditional distribution graph of multi-source orthogonal degradation features extracted using EMODF in task 1, the conditional distribution graph of multi-source orthogonal degradation features extracted using baseline in task 7, the conditional distribution graph of multi-source orthogonal degradation features extracted using EMODF-V1 in task 7, and the conditional distribution graph of multi-source orthogonal degradation features extracted using EMODF in task 7, respectively;
[0046] Figure 5 (a) and (b) are schematic diagrams of the similarity between the test data and different source domains in Task 1, and schematic diagrams of the fault prediction results of the bearing P1_1 full life cycle data using the orthogonal degradation features of a single source domain and the adaptive fusion of multi-domain orthogonal degradation features in Task 1, respectively. DETAILED DESCRIPTION
[0047] In order to make the purpose, technical solutions and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention. In addition, the technical features involved in the various embodiments of the present invention described below can be combined with each other as long as they do not conflict with each other.
[0048] See also Figure 1 The present invention provides a mechanical assembly fault prediction method based on domain generalization, and the prediction method mainly includes the following steps:
[0049] S1, collects sensor data from multiple mechanical assemblies under different working conditions throughout their life cycle, and divides the collected data into training and test sets.
[0050] Among them, sampling is performed at certain time intervals and frequencies, so as to obtain measurement signal data of operating parameters of mechanical equipment throughout its life cycle.
[0051] S2, linearly interpolates the intra-domain data and inter-domain data pairs with similar labels in the training set to obtain intra-domain and inter-domain enhanced data.
[0052] Specifically, the Hungarian algorithm is used to pair the intra-domain data and inter-domain data with similar labels, and then the paired data are interpolated to generate intra-domain and inter-domain enhanced data.
[0053] The collected full life cycle operating parameter measurement signal data under different working conditions are enhanced through intra-domain and inter-domain data. Intra-domain enhancement refers to the use of data from the same source domain for enhancement, which aims to capture the various degradation patterns inherent in each specific source data, ensuring that the mechanical fault prediction model can extract more representative degradation features for specific domains. At the same time, inter-domain data enhancement uses data from different source domains for data enhancement to reduce the overfitting of the mechanical fault prediction model on a specific source domain. By sharing data between different source domains, inter-domain enhancement can accurately obtain a generalized degradation feature representation from each source domain, thereby improving the generalization ability of the model when encountering unknown data. When performing intra-domain and inter-domain data enhancement, samples with similar labels are used for data enhancement, thereby avoiding the use of samples with too large label differences to generate enhanced samples that do not conform to the actual degradation pattern. The specific instructions are as follows:
[0054] Taking inter-domain data augmentation as an example, for two batches of data from different source domains and in, and Represent the batch data from the kth and lth source domains respectively; first calculate the label difference matrix between them, and use the Hungarian algorithm to optimize the label difference matrix to ensure that all data are uniquely paired and the sum of the label differences of all data pairs is minimized. The calculation formula of the label difference matrix between all samples of these two batches of data is:
[0055]
[0056] Among them, n bm =n bn =n b , n b is the batch size.
[0057] The steps to achieve maximum pairing using the Hungarian algorithm are:
[0058] Step 1: From L d Subtract the smallest number from each row of , and create a new matrix to contain the result;
[0059] Step 2: Subtract the smallest number in each column of the new matrix from that column, creating another matrix to contain the results.
[0060] Step 3: Check the possibility of the best allocation and try to cross out all the zeros in the matrix with the least number of lines; if the number of lines is greater than or equal to the number of rows in the matrix, go to step 6; otherwise, go to step 4;
[0061] Step 4: For the matrix elements not covered in step 3, subtract the smallest uncovered element value from all uncovered elements in the matrix elements; if there are elements repeatedly covered by lines in step 3, add the smallest uncovered element value to the repeatedly covered elements;
[0062] Step 5: Repeat steps 3 and 4 until the optimal matrix is obtained;
[0063] Step 6: Start assigning, starting with the row or column that has only one zero, match the items that have zero, use only one match per row and column, delete the rest of the cells.
[0064] For the paired inter-domain data pairs and domain data pairs in and They represent the i-th sample from the k-th source domain, the j-th sample from the k-th source domain, and the j-th sample from the l-th source domain respectively; and They represent the remaining time labels of the next failure of their corresponding mechanical equipment; d k and d l Represent their domain labels respectively.
[0065] The augmented data are interpolations of data pairs from the same and different source domains, respectively. These interpolations can be calculated as follows:
[0066]
[0067]
[0068]
[0069]
[0070]
[0071] in represents the in-domain enhanced data generated by using the in-domain data from the k-th source domain, is the remaining time label for the next failure of the corresponding mechanical equipment. is its corresponding domain label; represents the inter-domain enhanced data generated by the inter-domain data pair consisting of the k-th source domain and the l-th source domain, is the remaining time label of the next failure of the corresponding mechanical equipment. Given that the inter-domain augmented data is generated by data from different source domains, no domain label is assigned to the inter-domain augmented data. In addition, γ is sampled from the beta distribution to control the ratio between the two samples during the interpolation process.
[0072] S3, using the public feature extractor F CF Extract the common degradation features of the original data and enhanced data in the training set, and then input the common degradation features of the enhanced data in the domain and the original data in the training set into multiple different orthogonal degradation feature extractors To obtain the orthogonal degraded features of each domain, and then calculate the covariance matrix between any two source domain orthogonal degraded features, and then calculate the L2 norm of the covariance matrix, which is the feature orthogonalization loss.
[0073] Among them, the orthogonality method is used to reduce the similarity between orthogonal degradation features in different source domains, thereby reducing the redundancy of degradation information. At the same time, unrelated multi-domain orthogonal degradation features help enrich the diversity of degradation features, making it easier to effectively represent the degradation features of unknown targets in the subsequent testing phase, thereby improving the fault prediction accuracy of the model under unknown working conditions.
[0074] In order to provide diverse degradation feature support, we focus on enhancing the diversity of degradation features rather than extracting common degradation features. To this end, feature orthogonalization methods are applied to ensure that the aggregated features comprehensively capture the various degradation features presented in the original feature space. In other words, the goal is to alleviate the redundancy between multi-source degradation features and reduce the correlation between them. More formally, given multi-source raw data and in-domain augmented data Feature orthogonalization is achieved by optimizing the covariance matrix between any two data (original or in-domain augmented data) to a zero matrix. The orthogonalization loss can be calculated as:
[0075]
[0076] Where Cov(·) represents the covariance of the matrix. Uncorrelated multi-domain orthogonal degradation features help to enrich the diversity of degradation features, making it easier to effectively represent the degradation features of unknown targets in the subsequent testing phase, thereby improving the fault prediction accuracy of the model under unknown working conditions.
[0077] S4, based on the common degradation features, an orthogonal degradation feature weighted adaptive classifier is learned that can identify the source of the data, and then the classification loss is calculated; according to the classification results of the orthogonal degradation feature weighted adaptive classifier, multi-domain orthogonal degradation features are adaptively aggregated to accurately and effectively represent the degradation characteristics of the test data.
[0078] The output of the orthogonal degraded feature weighted adaptive classifier is the probability that each input data belongs to each source domain. The input is the common degraded feature. The cross entropy loss between the probability output by the orthogonal degraded feature weighted adaptive classifier and the true domain label is calculated. The cross entropy loss is the classification loss.
[0079] The input of the regressor is the aggregated feature, and the output is a value between 0 and 1; the true label is also a value between 0 and 1, and the square of the difference between the output of the regressor and the true label is the regression loss.
[0080] The orthogonal degradation feature weighted adaptive classifier C is used to evaluate the similarity between the test data and the source domain data, and then based on the obtained similarity, multi-domain orthogonal degradation features are adaptively aggregated to construct the degradation representation of the test data.
[0081] Considering the complexity and diversity of actual operating conditions, there may be differences in the degradation features between the unknown target domain and a single known source domain. However, as the number of available source domains increases, the unknown target domain may show similarities with one or more known source domains. Therefore, using ODFs from multiple known source domains has the potential to improve prediction accuracy. To this end, an ODF weighted adaptive classifier C is designed to optimally fuse multi-source ODFs by weight selection to obtain an aggregated unified feature representation. More formally, given the input data x k,i , whose aggregate feature z k,i It can be expressed as:
[0082]
[0083] Among them, ω k,i represents the kth source domain The weight reflects the i-th input data x k,i With the kth source domain In addition, ω k,i >0, and
[0084] The above feature aggregation process can be interpreted as a form of ensemble learning, where each feature extraction component is trained into a robust model that performs well on a specific source domain. Specifically, each feature extraction component consists of two components: a common feature extractor F CF and an orthogonal degradation feature extractor for each source domain The design of this feature extraction method is inspired by previous studies on deep transfer learning networks, where lower layers typically learn low-level and general features, while higher layers specialize in domain-specific features.
[0085] To obtain the weight ω for each source domain k,i, the designed ODF weighted adaptive classifier C takes the common degradation features as input and applies the Softmax function to convert its output into a probability distribution. In the model training stage, since each source data are accompanied by a domain label d k,i , so the similarity ω k,i Just set it up as follows:
[0086]
[0087] Therefore, the classification loss of C can be calculated as:
[0088]
[0089] Among them, L CE represents the cross entropy loss function.
[0090] When testing on the target machine, without access to the domain labels of unknown target data, the similarity of each target data to all source domains can be measured by the trained C as follows:
[0091]
[0092] Among them, ω j =[ω 1,j ,ω 2,j ,,…,ω K,j ] T . Similarly, ω k,j represents the similarity between the jth target data and the kth source domain. Then, the degradation characteristics of the target data can be expressed as:
[0093]
[0094] In this way, MODFE is able to represent and learn the degradation features of unknown targets based on the similarity between the unknown target data and the known source domain data. In addition, the aggregated degradation features are mapped to the remaining time value of the next failure of the mechanical equipment through the regressor R. Therefore, the prediction loss can be calculated as follows:
[0095]
[0096] Among them, L task represents the mean absolute error function which is widely used in fault prediction.
[0097] S5, applies label consistency constraints and sample pairing strategies to the aggregated features, thereby promoting the aggregation between features with similar labels and the separation between features with different labels in the aggregate space, and then calculates the label consistency constraint loss and sample pairing loss; at the same time, learns a regressor for predicting faults based on the aggregated features and their corresponding labels, and then calculates the regression loss.
[0098] according to The value of determines the degree of difference between the features of any two data from different source domains, and the Euclidean distance d(·) is used to measure the difference between the aggregated features; the label consistency constraint loss is:
[0099] The sample pairing loss is:
[0100]
[0101] Among them, considering the existence of marginal and conditional distribution shifts between orthogonal degraded features in different source domains, a semantic consistency regularization strategy is used to constrain the aggregated features before fault prediction. Specifically, the semantic consistency regularization strategy includes two parts: label consistency constraint and sample pairing strategy. The label consistency constraint forces the similarity between different features to be consistent with the similarity between their corresponding labels. The sample pairing strategy encourages features with close labels to be as similar as possible. Based on this, degraded features with close labels can be aggregated, and degraded features with different labels can be separated, so that the marginal and conditional distribution shifts between different domains can be reduced at the same time.
[0102] A semantic consistency regularization term is established to constrain the aggregated features. Specifically, the semantic consistency regularization term consists of two parts: label consistency constraints (LCC) and sample pairing strategy (SPS). LCC and SPS are designed to encourage data with similar labels to be close in the feature space, while data with inconsistent labels are far away from each other, so as to simultaneously mitigate marginal and conditional distribution shifts.
[0103] Label consistency constraint (LCC) is based on the basic principle that the similarity between data features depends on the similarity between data in the original space. Therefore, for any two data from different source domains, and The similarity between them is defined as in and They represent the remaining time labels of the next failure of the mechanical equipment corresponding to these data. As an explanation of the above similarity definition, if and With different labels, The value of will increase, indicating that the two data are not similar. and have the same label, then This shows and The goal is to The value of d(·) is used to determine the degree of difference between the features of any two data from different source domains. In this embodiment, the Euclidean distance d(·) is used to measure the difference between the aggregated features.
[0104] In summary, LCC is defined as the absolute difference between the similarity of a cross-domain data pair in its original space and the degree of difference between them in the aggregated feature space, as follows:
[0105]
[0106] Assume that two data samples form a cross-domain pair The feature values of are different, but their labels are the same. In this case, P k (X|Y)≠P l (X|Y). Based on L lcc , and will have the same eigenvalues, resulting in Therefore, in the aggregate space, since the differences between features are eliminated, P k (X|Y)=P l (X|Y). In another case, suppose and The features are the same, but have different labels, which means but if and are aligned in the aggregate feature space, which will lead to negative transfer. However, L lcc Will be based on and Limit the difference between labels and Therefore, when learning cross-domain invariant features, L lcc This can avoid the misalignment of some data by the deep model. lcc To a certain extent, it bridges the marginal and conditional distribution differences between multiple source domains in the aggregated feature space, thereby enhancing the generalization ability of the model.
[0107] In order to avoid that some small number of sample features with close labels from different source domains cannot be well clustered together, the sample pairing strategy (SPS) is used to compare samples with similar labels in different source domains. SPS helps to tightly cluster samples with similar labels in the aggregated feature space, similar to local clustering in classification tasks. SPS uses the Hungarian algorithm to maximize the pairing of samples from different source domains in a random process and make the features of labeled samples as close as possible. For successfully paired cross-domain sample pairs SPS calculates the Euclidean distance between their features The SPS loss in batch processing is defined as follows:
[0108]
[0109] S6, based on feature orthogonalization loss, classification loss, label consistency constraint loss, sample pairing loss and regression loss, the common feature extractor F is trained simultaneously CF , multiple orthogonal degenerate feature extractors The orthogonal degradation feature weighted adaptive classifier C and regressor R use the trained mechanical fault prediction model to predict mechanical faults.
[0110] The mechanical failure prediction model includes a common feature extractor F CF , multiple orthogonal degenerate feature extractors Orthogonal degenerate feature weighted adaptive classifier C and regressor R.
[0111] Combine all the above loss functions to simultaneously train the common feature extractor F CF , multiple orthogonal degenerate feature extractors Orthogonal degenerate feature weighted adaptive classifier C and regressor R. The total loss is:
[0112] L=L r +k t (L ort +αL c +βL lcc +γL sps ),
[0113] in, are time-varying coefficients; q and q m Denote the qth iteration and the maximum number of iterations respectively. The trained model is deployed on the test data to perform fault prediction; the true value of the fault prediction time is the percentage of the remaining time for the next failure of the mechanical equipment to the entire life cycle time. The true fault prediction time label for the tth sampling point is:
[0114]
[0115] Among them, T t and T0 represent the order t of the sampling points and the total number of sampling points in the whole life cycle, respectively.
[0116] The following takes the bearing as a specific object, and further describes the method for predicting mechanical equipment faults based on domain generalization of the present invention in detail in combination with specific examples. The specific steps are as follows:
[0117] (1) Extract the measurement signal data of the full life cycle operating parameters of the bearing, and use the accelerated degradation test bearing dataset of the IEEE PHM 2012 Challenge and the XJTU-SY bearing dataset for training and testing respectively. Both datasets contain two orthogonally installed accelerometers. The sampling frequency of the accelerometer in the first dataset is 25.6kHz, the single sampling time is 0.1s, and the sampling interval is 10s. Therefore, 2560 sampling points can be obtained for each sensor each time. The sampling frequency of the accelerometer in the second dataset is 25.6kHz, the single sampling time is 1.28s, and the sampling interval is 1min. Therefore, 32768 sampling points can be obtained for each sensor each time. The specific details of the two bearing datasets and the designed multi-source domain generalized fault prediction tasks are shown in Tables 1 and 2, respectively.
[0118] Table 1 PHM 2012 and XJTU-SY bearing datasets
[0119]
[0120]
[0121] Table 2 Multi-source domain generalized fault prediction tasks
[0122]
[0123] (2) The Hungarian algorithm is used to pair batches of full-life cycle operation parameter measurement signal data from the same source domain and batches of full-life cycle operation parameter measurement signal data from different source domains during the training process. Intra-domain data pairs and cross-domain data pairs with similar labels are used to perform intra-domain data and inter-domain data augmentation to expand the diversity of training data. The number of out-of-domain augmented samples generated is consistent with the batch size, and the number of in-domain augmented samples generated is half of the batch size.
[0124] (3) Construct a common feature extractor model and an orthogonal degradation feature extractor model. The network structures of the common feature extractor and the orthogonal degradation feature extractor are shown in Table 3. The common feature extractor with shared parameters and the orthogonal degradation feature extractor with unshared parameters are used to extract the degradation features of the data. Then, these features are orthogonalized to reduce redundant degradation information. Specifically, the orthogonalization loss is calculated, which is the L2 norm of the covariance matrix between any two source domain degradation features.
[0125] (4) Construct a weighted adaptive classifier and regressor. In the training phase, the orthogonal degradation feature weighted adaptive classifier is used to classify the data of each source domain, that is, to accurately determine the source of each data. The classification cross entropy loss is calculated based on the classification results output by the orthogonal degradation feature weighted adaptive classifier and the true domain label of the data; then the similarity between the training data and each source domain is determined, and the multi-source orthogonal degradation features are aggregated by weight selection. The aggregated features are input into the regressor for fault prediction. The regression loss is calculated by the predicted value output by the regressor and the true label of the data. In the testing phase, the well-trained weighted adaptive classifier can identify the similarity between the unknown target data and the multi-source domain data, and then adaptively integrate the multi-source orthogonal degradation features based on the obtained similarity, thereby effectively representing the degradation characteristics of the unknown target data.
[0126] (5) Constrain the aggregated features of different source domains, that is, semantically constrain the aggregated features through label consistency constraints and sample pairing strategies. Specifically, in the aggregated feature space, the degraded features of different source domains with similar labels are brought closer, and the degraded features of different source domains with different labels are separated, thereby effectively reducing the marginal and conditional distribution differences between multi-domain degraded features, and calculating the label consistency loss and the loss of the sample pairing strategy.
[0127] (6) Combine all the losses calculated above to simultaneously train the common feature extractor F CF , multiple orthogonal degenerate feature extractors Orthogonal degenerate feature weighted adaptive classifier C and regressor R. In the process of back propagation, the optimization algorithm is Adam. The specific hyperparameters in the model training process are shown in Table 4. After the model training is completed, the test data set is input for testing. First, use F CF to obtain the common degradation features of the test data. The common degradation features are then fed into , to obtain multi-source orthogonal degradation features. The common degradation features are also input into the parallel C to determine the similarity between the test data and the multi-source data. Based on the obtained similarity, the multi-source orthogonal degradation features are adaptively aggregated to accurately obtain the degradation representation of the unknown target data. Finally, the aggregated degradation features are input into R, which outputs the remaining time prediction value of the next failure of the mechanical equipment of the test data.
[0128] Table 3: EMODF network structure
[0129]
[0130]
[0131] (7) Visualization of prediction results. Take tasks 1, 2, 7, and 8 as examples, that is, the test bearings are P1_1, P1_2, X1_1, and X1_2. Mean absolute error (MAE), root mean square error (RMSE), and score are used to analyze the experimental results. Their calculation methods are described as follows:
[0132]
[0133]
[0134]
[0135]
[0136]
[0137] in, With y i Represent the predicted value and the true value respectively; i Indicates the percentage error. The smaller the MAE and RMSE, the better the model prediction performance. The larger the Score, the better the model prediction performance. The fault prediction results are as follows: Figure 2 As shown in Table 5, the MAE, RMSE and Score values of all tasks are given. Figure 2 As can be seen from Table 5, the method proposed in this embodiment performs well in solving the fault prediction problem in cross-domain scenarios with unknown target domain data, which verifies the effectiveness of the present invention.
[0138] Table 5: Fault prediction results of MODEF on all tasks
[0139]
[0140] Table 6: Fault prediction results of different methods on Task 1 and Task 7
[0141]
[0142]
[0143] In order to further verify the effectiveness of the proposed method in simultaneously alleviating the differences between the edge and conditional distributions of different source domains, the multi-source ODF extracted by different methods is visualized using t-distributed random neighbor embedding technology. Specifically, Figure 3 and Figure 4 The results of mapping multi-source ODFs to one-dimensional and two-dimensional spaces are shown respectively. These figures illustrate the marginal and conditional distributions of multi-source ODFs using different methods on Task 1 and Task 7. The compared methods include: (1) baseline, (2) MODFE-V1, similar to MODFE, but with the label consistency constraint and sample pairing strategy replaced by maximum mean discrepancy (MMD), and (3) MODFE. The prediction results of these methods on Task 1 and Task 7 are shown in Table 6. Figure 3 and Figure 4 It can be seen from the above that the present invention can simultaneously alleviate the differences between the edge and conditional distributions of different source domains. Figure 3 , Figure 4 As can be seen from Table 6, simultaneously alleviating marginal and conditional variations between multiple existing domains and learning general predictive knowledge is a promising approach to improve the generalization ability of prognostic models.
[0144] In order to further verify the effectiveness of the method proposed in the present invention to adaptively fuse multi-domain orthogonal degradation features based on the similarity between the test data and multi-source data to represent the degradation features of the test data, Task 1 is selected to illustrate the advantages of the above-mentioned similarity-based aggregation features. Figure 5 The similarity between the test data and the source domain data and the prediction results of the remaining time for the next failure of the mechanical equipment are shown. Figure 5 It can be seen that the aggregated multi-domain orthogonal degradation features based on similarity adaptation can better represent the degradation features of the unknown target domain. By adaptively selecting the degradation features of the source domain data that are closer to the target data, the generalization ability of the model can be improved.
[0145] In order to further verify the superiority of the present invention in fault prediction results, the present invention is compared with some related methods, including multi-scale convolutional neural network (MSCNN) based on deep learning, double convolutional neural network (DCNN), Mixup based on domain generalization, representation self-challenging (RSC) and adversarial out-domain augmentation (AOA). It can be found from Table 7 that compared with MSCNN, DCNN, Mixup, RSC and AOA, the present invention achieves the best prediction performance, which verifies the effectiveness of the EMODF model established by the present invention.
[0146] Table 7: Comparison experiment of average prediction results of EMODF and related methods on all tasks
[0147]
[0148] The present invention also provides a mechanical equipment fault prediction system based on domain generalization, the system includes a memory and a processor, the memory stores a computer program, and the processor executes the mechanical equipment fault prediction method based on domain generalization as described above when executing the computer program.
[0149] The present invention also provides a computer-readable storage medium, which stores machine-executable instructions. When the machine-executable instructions are called and executed by a processor, the machine-executable instructions prompt the processor to implement the mechanical equipment fault prediction method based on domain generalization as described above.
[0150] It will be easily understood by those skilled in the art that the above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present invention should be included in the protection scope of the present invention.
Claims
1. A mechanical assembly fault prediction method based on domain generalization, characterized by: The prediction method includes the following steps: S1, linearly interpolate the intra-domain data and inter-domain data pairs with similar labels in the training set to obtain intra-domain and inter-domain enhanced data; wherein the training set includes a part of the full life cycle sensor data of multiple mechanical assemblies under different working conditions; S2, using the public feature extractor F CF Extract the common degradation features of the original data and enhanced data in the training set, and then input the common degradation features of the enhanced data in the domain and the original data in the training set into multiple different orthogonal degradation feature extractors F ODFk∈{1,…,K} To obtain the orthogonal degraded features of each domain, and then calculate the covariance matrix between any two source domain orthogonal degraded features, and then calculate the L2 norm of the covariance matrix, which is the feature orthogonalization loss; S3, based on the common degradation features, learn an orthogonal degradation feature weighted adaptive classifier that can identify the source of the data, and then calculate the classification loss; according to the classification results of the orthogonal degradation feature weighted adaptive classifier, adaptively aggregate multi-domain orthogonal degradation features; S4, applies label consistency constraints and sample pairing strategies to the aggregated features, thereby promoting the aggregation of features with similar labels and the separation of features with different labels in the aggregate space, and then calculates the label consistency constraint loss and sample pairing loss; at the same time, learns a regressor for predicting the occurrence time of a fault based on the aggregated features and their corresponding labels, and then calculates the regression loss; S5, based on feature orthogonalization loss, classification loss, label consistency constraint loss, sample pairing loss and regression loss, the common feature extractor F is trained simultaneously CF , multiple orthogonal degenerate feature extractors F ODFk∈{1,…,K} , orthogonal degradation feature weighted adaptive classifier C and regressor R, and use the trained mechanical fault prediction model to predict mechanical faults.
2. The mechanical assembly fault prediction method based on domain generalization according to claim 1, characterized in that: The Hungarian algorithm is used to pair the intra-domain data and inter-domain data with similar labels, and then the paired data are interpolated to generate intra-domain and inter-domain enhanced data.
3. The mechanical assembly fault prediction method based on domain generalization according to claim 1, characterized in that: The augmented data are interpolations of data pairs from the same and different source domains, respectively, and these interpolations are calculated as follows: in represents the in-domain enhanced data generated by using the in-domain data from the k-th source domain, is the remaining time label for the next failure of the corresponding mechanical equipment. is its corresponding domain label; represents the inter-domain enhanced data generated by the inter-domain data pair consisting of the k-th source domain and the l-th source domain, is the remaining time label of the next failure of the corresponding mechanical equipment; γ is sampled from the beta distribution and is used to control the ratio between the two samples during the interpolation process.
4. The mechanical assembly fault prediction method based on domain generalization as claimed in claim 3, characterized in that: Given multiple source raw data and in-domain augmented data Feature orthogonalization is achieved by optimizing the covariance matrix between any two data to a zero matrix. The calculation formula of the orthogonalization loss is: Where Cov(·) represents the covariance of the matrix.
5. The mechanical assembly fault prediction method based on domain generalization according to claim 1, characterized in that: The output of the orthogonal degraded feature weighted adaptive classifier is the probability that each input data belongs to each source domain. The input is the common degraded feature. The cross entropy loss between the probability of the output of the orthogonal degraded feature weighted adaptive classifier and the true domain label is calculated. The cross entropy loss is the classification loss. The input of the regressor is the aggregated feature, and the output is a value between 0 and 1. The true label is also a value between 0 and 1. The square of the difference between the output of the regressor and the true label is the regression loss.
6. The mechanical assembly fault prediction method based on domain generalization according to claim 1, characterized in that: Given input data x k,i , whose aggregate feature z k,i It is expressed as: Among them, ω k,i represents the kth source domain The weight reflects the i-th input data x k,i With the kth source domain similarity; in addition, ω k,i >0, and 7. The mechanical assembly fault prediction method based on domain generalization according to claim 1, characterized in that: The label consistency constraint LCC is defined as the absolute difference between the similarity of a cross-domain data pair in its original space and the degree of difference in the aggregated feature space, as follows: In the formula, for any two data from different source domains and The similarity between them is defined as in and They respectively represent the remaining time labels for the next failure of the mechanical equipment corresponding to these data; and are the data from the kth source domain respectively. The corresponding aggregate features and data from the lth source domain The corresponding aggregation features; and are the in-domain augmented data of the kth source domain. The corresponding aggregated features and the in-domain enhanced data of the lth source domain The corresponding aggregation features.
8. The mechanical assembly fault prediction method based on domain generalization according to claim 7, characterized in that: according to The value of determines the degree of difference between the features of any two data from different source domains, where Represents the data of the kth source domain The labels and data of the lth source domain The difference between the labels of , and the Euclidean distance d(·) is used to measure the difference between the aggregated features; the label consistency constraint loss is: The sample pairing loss is: Where n b is the batch size; represents the i-th data from the k-th source domain The corresponding aggregation features; represents the jth data from the lth source domain The corresponding aggregation features.
9. A mechanical equipment fault prediction system based on domain generalization, characterized by: The system includes a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the method for predicting mechanical equipment faults based on domain generalization according to any one of claims 1 to 8 is executed.
10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores machine-executable instructions. When the machine-executable instructions are called and executed by a processor, the machine-executable instructions prompt the processor to implement the mechanical equipment fault prediction method based on domain generalization as described in any one of claims 1-8.
Citation Information
Patent Citations
New fault diagnosis method for rotating machinery based on deep confrontation convolutional neural network
CN114358124A
Bearing fault type prediction method and system based on multi-source domain transfer learning
CN116304820A
Mechanical fault diagnosis method, device and equipment under unavailable target working condition data
CN116756483A
