Mechanical equipment fault identification method and device and storage medium

Abstract

The invention belongs to the technical field of mechanical intelligent operation and maintenance, and discloses a mechanical equipment fault identification method and device and a storage medium in the technical field of mechanical equipment intelligent operation and maintenance, and the method comprises the steps: extracting a domain global feature of a vibration signal, extracting an intra-domain classification feature of the domain global feature through an intra-domain classification feature extractor, extracting inter-domain classification features of the vibration signals through the inter-domain feature extractor, performing numerical value addition operation on the inter-domain classification features and the intra-domain classification features to obtain recombination classification features, and inputting the inter-domain classification features, the intra-domain classification features and the recombination classification features into a fault classifier to obtain a fault type prediction probability; and obtaining a corresponding fault type ordinal number through the maximum value of the fault type prediction probability, thereby realizing identification of the fault type. According to the invention, the technical problem that the fault identification accuracy of the mechanical equipment is reduced due to the fact that a novel fault is wrongly identified as an existing fault type can be solved.

Description

Technical Field

[0001] The present invention belongs to the technical field of mechanical intelligent operation and maintenance, and in particular relates to a mechanical equipment fault identification method, device and storage medium. Background Art

[0002] With the tremendous development of modern mechanical systems, the demand for their prediction and health management is becoming increasingly urgent. During the operation of mechanical systems, the occurrence of mechanical failures will have a serious impact on the safety and efficiency of industrial production.

[0003] In the era of industrial big data, traditional inspection methods for mechanical equipment are time-consuming and labor-intensive, and can no longer meet the needs of accurate identification of mechanical equipment failures. Intelligent maintenance of machinery has become a research hotspot in recent years. Due to its outstanding automation capabilities, mechanical equipment fault diagnosis technology based on deep learning can better ensure the safety and reliability of mechanical equipment, especially rolling bearings, gears and other mechanical equipment parts under harsh operating conditions, during operation, providing a new feasible solution for mechanical equipment fault diagnosis.

[0004] However, deep learning-based mechanical equipment fault diagnosis technology is limited in two aspects in actual engineering applications. On the one hand, the operating conditions of mechanical equipment are changeable, and the mechanical equipment status data collected under different conditions have different distributions. The distribution difference poses a challenge to the extraction of mechanical equipment status features. On the other hand, the historical loss type data collected cannot cover all fault types. When the model is used for online identification, new faults encountered will be mistakenly identified as existing fault types. This reduces the accuracy of mechanical equipment fault identification through deep learning, and the safety and efficiency of mechanical equipment operation are difficult to guarantee.

[0005] Therefore, there is an urgent need for a mechanical equipment fault identification method, device and storage medium to solve the above technical problems. Summary of the invention

[0006] The purpose of the present invention is to overcome the deficiencies in the prior art and to provide a mechanical equipment fault identification method, device and storage medium, which can solve the technical problem that a new type of fault may be mistakenly identified as an existing fault type, thereby reducing the accuracy of mechanical equipment fault identification.

[0007] To achieve the above object, the present invention is implemented by adopting the following technical solutions:

[0008] In a first aspect, the present invention provides a method for identifying a mechanical equipment fault, comprising:

[0009] Obtain vibration signals from mechanical equipment;

[0010] Inputting the vibration signal into a pre-trained diagnostic model, wherein the diagnostic model includes a domain global feature extractor, an inter-domain feature extractor, an intra-domain classification feature extractor, and a fault classifier;

[0011] The domain global feature extractor is used to extract the domain global feature of the vibration signal, the intra-domain classification feature extractor is used to extract the intra-domain classification feature of the domain global feature, the inter-domain classification feature of the vibration signal is extracted by the inter-domain feature extractor, the inter-domain classification feature and the intra-domain classification feature are numerically added to obtain the recombined classification feature, and the inter-domain classification feature, the intra-domain classification feature and the recombined classification feature are input into the fault classifier to obtain the prediction probability of the fault type;

[0012] The corresponding fault type ordinal number is obtained through the maximum value of the fault type prediction probability, so as to realize the identification of the fault type.

[0013] Furthermore, the training process of the diagnostic model includes:

[0014] Perform non-overlap segmentation on the collected historical vibration signals according to a preset segmentation length to obtain state samples, calibrate the state samples according to the fault type and the collected working condition domain type, and obtain a labeled training data set;

[0015] Extracting domain global features of state samples in the labeled training data set by the domain global feature extractor, inputting the domain global features into the intra-domain classification feature extractor to extract intra-domain classification features of the state samples, and extracting inter-domain classification features of the state samples by the inter-domain feature extractor;

[0016] Performing a numerical addition operation on the inter-domain classification features and the intra-domain classification features of the state sample to obtain a recombinant classification feature of the state sample;

[0017] Inputting the inter-domain classification features, intra-domain classification features and reorganized classification features of the state sample into a fault classifier to obtain the predicted probability of the fault type of the state sample;

[0018] The fault classification cross entropy loss is calculated according to the fault type prediction probability of the state sample and the real fault type label calibrated by the state sample, the preference correction loss is calculated based on the fault type prediction probability, the fault classification cross entropy loss and the preference correction loss are minimized according to the back propagation and optimization algorithm, and the trained diagnosis model is determined according to the minimum fault classification cross entropy loss and the preference correction loss.

[0019] Furthermore, the diagnostic model further includes a working condition specific feature extractor and a domain classifier, and the training process of the diagnostic model further includes:

[0020] Inputting the domain global features of the state sample into the working condition specific feature extractor to extract working condition specific features, inputting the domain global features, working condition specific features and domain classification features of the state sample into the domain classifier to obtain the domain type prediction probability of the state sample;

[0021] The domain classification cross entropy loss is calculated according to the domain type prediction probability and the actual domain type label in the labeled training data set, the covariance loss is calculated according to the working condition specific features, the intra-domain classification features and the inter-domain classification features, the domain classification cross entropy loss and the covariance loss are minimized based on the back propagation and optimization algorithm, the optimal training results of the working condition specific feature extractor and the domain classifier are determined according to the minimum domain classification cross entropy loss and covariance loss, the optimal training results of the working condition specific feature extractor and the domain classifier are used as the final trained diagnostic model to complete the training.

[0022] Further, calculating the fault classification cross entropy loss according to the fault type prediction probability and the actual fault type label in the labeled training data set includes:

[0023] ,

[0024] ,

[0025] in, is the cross entropy loss for fault classification, represents the sample ordinal number, represents the total number of samples, Indicates The one-hot vector of the true domain type label of each state sample, Indicates The predicted probability of the fault type of the state sample is Indicates The state samples belong to The predicted probability of a fault type, K represents the total number of known fault types in the labeled training data set, Indicates a new fault type.

[0026] Further, calculating the preference correction loss based on the fault type prediction probability includes:

[0027] ,

[0028] in, is the preference correction loss, represents the sample ordinal number, represents the total number of samples, Indicates The state samples belong to The predicted probability of each failure type, Indicates The fault type ordinal number corresponding to the state sample, Indicates The predicted probability that a state sample belongs to a new fault type, Indicates a new fault type.

[0029] Further, calculating the domain classification cross entropy loss according to the domain type prediction probability and the real domain type label calibrated by the state sample includes:

[0030] ,

[0031] ,

[0032] in, is the domain classification cross entropy loss, represents the sample ordinal number, represents the total number of samples, where Indicates The one-hot vector of the true domain type label of each state sample, Indicates The domain type prediction probability of state samples, Indicates The state samples belong to The predicted probability of each domain type, M is the total number of domains;

[0033] Calculating the covariance loss based on the working condition specific features, the intra-domain classification features, and the inter-domain classification features includes:

[0034] ,

[0035] in, is the covariance loss, Indicates the specific characteristics of the working condition, represents the classification features within the domain, represents the inter-domain classification feature, represents the covariance matrix, represents the Euclidean norm.

[0036] Furthermore, the optimization algorithm includes one of an adaptive moment estimation algorithm, a stochastic gradient descent algorithm and a root mean square transfer algorithm.

[0037] In a second aspect, the present invention provides a mechanical equipment fault identification device, comprising:

[0038] Acquisition module, used to obtain vibration signals of mechanical equipment;

[0039] An input module, used for inputting the vibration signal into a pre-trained diagnostic model, wherein the diagnostic model includes a domain global feature extractor, an inter-domain feature extractor, an intra-domain classification feature extractor, and a fault classifier;

[0040] A prediction module, configured to extract a domain global feature of the vibration signal through the domain global feature extractor, extract an intra-domain classification feature of the domain global feature through the intra-domain classification feature extractor, extract an inter-domain classification feature of the vibration signal through the inter-domain feature extractor, perform a numerical addition operation on the inter-domain classification feature and the intra-domain classification feature to obtain a recombined classification feature, and input the inter-domain classification feature, the intra-domain classification feature and the recombined classification feature into a fault classifier to obtain a prediction probability of a fault type;

[0041] An identification module, used to obtain a corresponding fault type ordinal number according to the maximum value of the predicted probability of the fault type, so as to identify the fault type;

[0042] The multiple fault types of the vibration signal include fault types of training samples and new fault types, and the fault type ordinal number is greater than the total number of fault types of training samples.

[0043] In a third aspect, the present invention provides an electronic terminal, comprising a processor and a memory connected to the processor, wherein a computer program is stored in the memory, and when the computer program is executed by the processor, the steps of any of the above methods are performed.

[0044] In a fourth aspect, the present invention provides a computer-readable storage medium having a computer program stored thereon, which implements the steps of any of the above methods when executed by a processor.

[0045] Beneficial Effects

[0046] The present invention inputs the vibration signal to be identified into a pre-built diagnostic model. Since the fault classifier in the diagnostic model is configured with a plurality of identification numbers, the fault type of the training sample and the new fault type can be identified, and the fault type prediction probability corresponding to the multiple fault types is obtained. The multiple fault types include the fault type of the training sample and the new fault type, so that the new fault type can be identified, the accuracy of mechanical equipment fault identification is improved, and the safety and efficiency of mechanical equipment operation are guaranteed.

[0047] The fault classifier will have K+1 prediction probabilities for all training samples. However, since there are no new fault samples involved in the training, the classifier's prediction preference will be biased towards known fault samples. Therefore, by setting the preference correction loss, the classifier preference will be corrected to balance the fault classifier's prediction probabilities for known fault types and new fault types.

[0048] During the diagnosis model training phase, the domain classification loss is calculated by predicting the domain type probability to optimize the domain-related features, namely, the domain global features, working condition specific features, and intra-domain classification features. The covariance loss is calculated based on the working condition specific features, intra-domain classification features, and inter-domain classification features to further decouple the features and ensure the mutual exclusion of information between different features, which helps to achieve the reorganization of fault classification features and extract more generalized fault features. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] Figure 1 It is a flow chart of a mechanical equipment fault identification method provided in the first embodiment of the present invention;

[0050] Figure 2 It is a schematic diagram of the structure of a diagnostic model of a mechanical equipment fault identification method provided in the first embodiment of the present invention;

[0051] Figure 3 It is a schematic diagram of online identification of a vibration signal to be identified in a method for identifying mechanical equipment faults provided in Example 1 of the present invention. DETAILED DESCRIPTION

[0052] The technical solution of the present invention is described in detail below through the accompanying drawings and specific embodiments. It should be understood that the embodiments of the present application and the specific features in the embodiments are detailed descriptions of the technical solution of the present application, rather than limitations on the technical solution of the present application. In the absence of conflict, the embodiments of the present application and the technical features in the embodiments can be combined with each other.

[0053] The term "and / or" in this article is only a description of the association relationship of the associated objects, indicating that there can be three relationships. For example, A and / or B can mean: A exists alone, A and B exist at the same time, and B exists alone. In addition, the character " / " in this article generally indicates that the associated objects before and after are in an "or" relationship.

[0054] Non-overlap segmentation: Non-overlap segmentation of vibration signals usually means that during signal processing, the signal is segmented into multiple consecutive segments with no overlapping parts between each segment. It allows to obtain higher resolution in the frequency domain while reducing signal distortion caused by window functions;

[0055] In practical applications, the method to be chosen depends on the characteristics of the signal and the analysis objectives. If non-overlapping segmentation is required, the maximum overlap discrete wavelet transform (MODWT) can be considered. These methods can process signals of arbitrary length and avoid a series of problems caused by overlap.

[0056] Regarding how to "obtain the fault type prediction probability corresponding to multiple fault types through the fault classifier based on the intra-domain classification features and inter-domain classification features", those skilled in the art can understand that the "fault classifier" in this application can obtain the specific fault type corresponding to the data to be tested under its corresponding classification logic just like a conventional neural network model classifier after training according to the optimization training process proposed in this application; "inputting the domain global features, working condition specific features and intra-domain classification features into the domain classifier to obtain the domain type prediction probability of the state sample" is the same and will not be repeated.

[0057] Example 1

[0058] Figure 1 This is a flow chart of the mechanical equipment fault identification method in the first embodiment of the present invention. This flow chart only shows the logical sequence of the method described in this embodiment. In other possible embodiments of the present invention, different Figure 1 The steps shown or described are accomplished in the order shown.

[0059] The mechanical equipment fault identification method provided in this embodiment can be applied to a terminal and can be executed by a mechanical equipment fault identification device, which can be implemented by software and / or hardware, and can be integrated in a terminal, for example: any smart phone, tablet computer or computer device with communication function. Figure 1 and Figure 3 As shown, the method of this embodiment specifically includes the following steps:

[0060] Step 1: Obtain different types of vibration signals under historical working conditions and target working conditions of mechanical equipment.

[0061] Step 2: Input the vibration signal into a pre-trained diagnostic model, such as Figure 2 As shown, the diagnostic model includes a domain global feature extractor, an inter-domain feature extractor, an intra-domain classification feature extractor, a working condition specific feature extractor, a domain classifier and a fault classifier. Before the vibration signal is input into the pre-trained diagnostic model, the collected historical vibration signal can be non-overlappingly segmented according to a preset segmentation length to obtain a state sample, which is calibrated according to the fault type of the state sample and the acquisition working condition domain type to obtain an unlabeled test data set, and finally the unlabeled test data set including the vibration signal to be identified is input into the diagnostic model.

[0062] Step 3: extracting the domain global features of the vibration signal through the domain global feature extractor, extracting the domain intra-classification features of the domain global features through the domain intra-classification feature extractor, and extracting the inter-domain classification features of the vibration signal through the inter-domain feature extractor. Based on the intra-domain classification features and inter-domain classification features, it should be noted that, in the test phase, the input of the fault classifier is as follows: Figure 3 As shown, only the intra-domain classification features and inter-domain classification features are shown, and the fault type prediction probabilities corresponding to multiple fault types are obtained through the fault classifier;

[0063] Step 4: Obtain the corresponding fault type ordinal number through the maximum value of the predicted probability of the fault type, so as to identify the fault type;

[0064] The multiple fault types of the vibration signal include fault types of training samples and new fault types, and the fault type ordinal number is greater than the total number of fault types of training samples.

[0065] Specifically, the training process of the diagnostic model includes:

[0066] Perform non-overlap segmentation on the collected historical vibration signals according to a preset segmentation length to obtain state samples, calibrate the state samples according to the fault type and the collected working condition domain type, and obtain a labeled training data set;

[0067] Extracting domain global features of the state samples in the training data set by the domain global feature extractor, inputting the domain global features into the intra-domain classification feature extractor to extract the intra-domain classification features of the state samples, and extracting the inter-domain classification features of the state samples by the inter-domain feature extractor;

[0068] Performing a numerical addition operation on the inter-domain classification features and the intra-domain classification features of the state sample to obtain a recombinant classification feature of the state sample;

[0069] Inputting the inter-domain classification features, intra-domain classification features and reorganized classification features of the state sample into a fault classifier to obtain the predicted probability of the fault type of the state sample;

[0070] Calculating the fault classification cross entropy loss based on the predicted probability of the fault type and the actual fault type label in the labeled training data set includes:

[0071] ,

[0072] ,

[0073] in, is the cross entropy loss for fault classification, represents the sample ordinal number, represents the total number of samples, Indicates The one-hot vector of the true domain type label of each state sample, Indicates The predicted probability of the fault type of the state sample is Indicates The state samples belong to The predicted probability of a fault type, K represents the total number of known fault types in the labeled training data set, Indicates a new type of fault;

[0074] Calculating the preference correction loss based on the predicted probability of the fault type includes:

[0075] ,

[0076] in, is the preference correction loss, represents the sample ordinal number, represents the total number of samples, Indicates The state samples belong to The predicted probability of each failure type, Indicates The fault type ordinal number corresponding to the state sample, Indicates The predicted probability that a state sample belongs to a new fault type, Indicates a new fault type.

[0077] The fault classification cross entropy loss is calculated according to the fault type prediction probability of the state sample and the real fault type label calibrated by the state sample, the preference correction loss is calculated based on the fault type prediction probability, the fault classification cross entropy loss and the preference correction loss are minimized according to the back propagation and optimization algorithm, and the trained diagnosis model is determined according to the minimum fault classification cross entropy loss and preference correction loss.

[0078] Regarding preference correction loss: During the training process, the fault classifier will generate K+1 prediction probabilities for each training sample (corresponding to K known fault types and the K+1th new fault type, and the specific type of the new fault type is unknown). However, since no new fault samples are involved in the training process, the fault classifier's prediction preference will be biased towards known fault types (the prediction probability of K known fault types will be greater than the prediction probability of the K+1th new fault type). At this time, the classifier preference will be corrected according to the preference correction loss to balance the fault classifier's prediction probability for known faults and unknown faults.

[0079] Specifically, the training process of the diagnostic model also includes:

[0080] Inputting the domain global features of the state sample into the working condition specific feature extractor to extract working condition specific features, inputting the domain global features, working condition specific features and domain classification features of the state sample into the domain classifier to obtain the domain type prediction probability of the state sample;

[0081] Calculating the domain classification cross entropy loss based on the domain type prediction probability and the true domain type labels in the labeled training dataset includes:

[0082] ,

[0083] ,

[0084] in, is the domain classification cross entropy loss, represents the sample ordinal number, represents the total number of samples, where Indicates The one-hot vector of the true domain type label of each state sample, Indicates The domain type prediction probability of state samples, Indicates The state samples belong to The predicted probability of each domain type, M is the total number of domains;

[0085] Calculating the covariance loss based on the working condition specific features, the intra-domain classification features, and the inter-domain classification features includes:

[0086] ,

[0087] in, is the covariance loss, Indicates the specific characteristics of the working condition, represents the classification features within the domain, represents the inter-domain classification feature, represents the covariance matrix, represents the Euclidean norm;

[0088] Based on the back propagation and optimization algorithm, the domain classification cross entropy loss and covariance loss are minimized, the optimal training results of the working condition specific feature extractor and the domain classifier are determined according to the minimum domain classification cross entropy loss and covariance loss, and the optimal training results of the working condition specific feature extractor and the domain classifier are used as the final trained diagnostic model to complete the training.

[0089] It should be noted that the domain type prediction probability is calculated here in order to calculate the domain cross entropy loss. Its purpose is to optimize the working condition specific features, the domain classification features and the domain global features extracted by the domain global feature extractor. The covariance loss is calculated and minimized based on the domain global features, the domain classification features and the working condition specific features to achieve feature decoupling. Finally, the information contained in each feature is made mutually exclusive, so that each feature vector contains unique information.

[0090] The optimization algorithm adopts one of the adaptive moment estimation algorithm, the stochastic gradient descent algorithm and the root mean square transfer algorithm. The back propagation refers to finding the gradient of the calculated loss, and then the optimization algorithm updates the network parameters according to the obtained gradient. They all belong to the existing technology and will not be described here.

[0091] The present embodiment is further described below with reference to the accompanying drawings and experimental cases:

[0092] 1. Experimental data

[0093] The data used in the experiment come from open source datasets and laboratory self-made datasets, as shown in Table 1. The open source dataset uses an accelerometer to collect vibration signals of artificially damaged bearings through a simulation test bench, with a sampling frequency of 25.6 kHz. This embodiment considers five bearing health states: normal state, inner ring fault, outer ring fault, roller fault, and composite fault of inner ring and outer ring faults, and their corresponding classification labels are 0, 1, 2, 3 and 4, respectively. At the same time, three working conditions with different speeds are simulated. 200 sample data are taken for each of the five bearing health states at three speeds of 4200 (r / min), 4500 (r / min), and 4800 (r / min), and set to different domains H1, H2 and H3. The laboratory self-made dataset uses an accelerometer installed on the bearing seat through a simulation test bench to capture vibration data at a sampling rate of 32768Hz. In this case, the six health states with labels are as follows: normal state, inner ring fault, outer ring fault, and three composite faults: inner ring and roller fault, inner ring and outer ring fault, outer ring and roller fault. Their corresponding class labels are 0, 1, 2, 3, 4, and 5. At the same time, four different working conditions are simulated. The speed and radial force under each working condition are different. Under each working condition, 200 sample data are taken for each of the six bearing health states, and set to different domains S1, S2, S3, and S4. Each state sample of the above two data sets contains 1024 data points.

[0094] Table 1 Open source datasets and laboratory self-made datasets

[0095]

[0096] 2. Method Validation

[0097] In order to verify the effectiveness of the proposed invention, the above two data sets are used to construct 8 tasks for experimental verification in this example. As shown in Table 2, the training set data and target working condition data of the eight tasks under the two data sets are constructed by matching different fault types and different working conditions. Task No. 1 is to use the open source data set to construct the task, and Task No. 2 is to use the laboratory self-made data set to construct the task. In this embodiment, multiple diagnostic tasks are set. The fault type that is not included in the training set label contained in the target working condition label of each diagnostic task is a new fault. For example, for task T1 in Table 2, the inner and outer ring faults represented by label 4 are new faults. In order to further verify the advancement of the invention, we use several other fault detection methods in the field to perform these tasks together with the invention for comparison, and use the H index to represent the fault diagnosis ability of the method. The H index is defined as the harmonic mean of the classification accuracy of the known fault class and the classification accuracy of the unknown fault class. It is an indicator commonly used in open set problems. It only shows a high value when both classification accuracies are good. The experimental results are shown in Table 3, where M1 is an adaptive open set domain generalization network model, M2 is a meta-learning model for joint domain class matching, M3 is an extreme value theory model based on a convolutional neural network, and M4 is the invented model based on empirical thresholds. Among the model-related parameters of the invention, the training cycle and batch size are set to 150 and 10 respectively, and the learning rate is set to 0.01.

[0098] Table 2 Task settings for the two datasets

[0099]

[0100] Table 3 Histochemical scores (H-score) and standard deviations of different methods

[0101]

[0102] Comparing the data in Table 3, we can draw the following conclusions: 1) On the open source datasets and laboratory homemade datasets, the average H index of M4 and the method proposed in the present invention is mostly higher than that of M1, M2 and M3. This shows the effectiveness of the invention and the advanced idea of ​​feature recombination and open set classifier preference correction in the diagnosis task containing unknown fault types; 2) The average H index of the present invention exceeds the M4 category by 18.3% and 8.1% on the open source datasets and laboratory homemade datasets, respectively, proving the superiority of the designed classification preference correction loss in learning decision boundaries; 3) The average H value of the present invention on the open source datasets and laboratory homemade datasets is 83.6% and 80.4%, respectively, and it performs well in all tasks. The results verify the superior classification ability of the present invention for known and unknown fault categories under unknown working conditions.

[0103] Example 2

[0104] Embodiment 2 of the present invention provides a mechanical equipment fault identification device, including:

[0105] Acquisition module, used to obtain vibration signals of mechanical equipment;

[0106] An input module, used for inputting the vibration signal into a pre-trained diagnostic model, wherein the diagnostic model includes a domain global feature extractor, an inter-domain feature extractor, an intra-domain classification feature extractor, and a fault classifier;

[0107] A prediction module, configured to extract a domain global feature of the vibration signal through the domain global feature extractor, extract an intra-domain classification feature of the domain global feature through the intra-domain classification feature extractor, extract an inter-domain classification feature of the vibration signal through the inter-domain feature extractor, and obtain a fault type prediction probability corresponding to a plurality of fault types through the fault classifier based on the intra-domain classification feature and the inter-domain classification feature;

[0108] An identification module, used to obtain a corresponding fault type ordinal number according to the maximum value of the predicted probability of the fault type, so as to identify the fault type;

[0109] The multiple fault types of the vibration signal include fault types of training samples and new fault types, and the fault type ordinal number is greater than the total number of fault types of training samples.

[0110] The mechanical equipment fault identification device provided in Example 2 of the present invention can execute the mechanical equipment fault identification method provided in Example 1 of the present invention, and has the corresponding functional modules and beneficial effects of the execution method.

[0111] Example 3

[0112] Embodiment 3 of the present invention further provides an electronic terminal, comprising a processor and a memory connected to the processor, wherein a computer program is stored in the memory, and the processor is configured to operate according to the instructions to execute the steps of the method described in Embodiment 1.

[0113] The electronic terminal provided in Example 3 of the present invention can execute the mechanical equipment fault identification method provided in Example 1 of the present invention, and has the corresponding functional modules and beneficial effects of the execution method.

[0114] Example 4

[0115] Embodiment 4 of the present invention further provides a computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, the steps of the method described in Embodiment 1 are implemented, and the computer program has functional modules and beneficial effects corresponding to the execution method.

[0116] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, devices, or computer program products. Therefore, the present application may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present application may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program codes.

[0117] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (apparatus), and computer program products according to the embodiments of the present application. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0118] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0119] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0120] The above is only a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the technical principles of the present invention. These improvements and modifications should also be regarded as the scope of protection of the present invention.

Claims

1. A method for identifying mechanical equipment faults, characterized in that: include: Obtain vibration signals from mechanical equipment; Inputting the vibration signal into a pre-trained diagnostic model, wherein the diagnostic model includes a domain global feature extractor, an inter-domain feature extractor, an intra-domain classification feature extractor, and a fault classifier; The domain global feature extractor is used to extract the domain global feature of the vibration signal, the intra-domain classification feature extractor is used to extract the intra-domain classification feature of the domain global feature, the inter-domain classification feature of the vibration signal is extracted by the inter-domain feature extractor, the inter-domain classification feature and the intra-domain classification feature are numerically added to obtain the recombined classification feature, and the inter-domain classification feature, the intra-domain classification feature and the recombined classification feature are input into the fault classifier to obtain the prediction probability of the fault type; The corresponding fault type ordinal number is obtained through the maximum value of the fault type prediction probability, so as to realize the identification of the fault type.

2. The mechanical equipment fault identification method according to claim 1, characterized in that: The training process of the diagnostic model includes: Perform non-overlap segmentation on the collected historical vibration signals according to a preset segmentation length to obtain state samples, calibrate the state samples according to the fault type and the collected working condition domain type, and obtain a labeled training data set; Extracting domain global features of state samples in the labeled training data set by the domain global feature extractor, inputting the domain global features into the intra-domain classification feature extractor to extract intra-domain classification features of the state samples, and extracting inter-domain classification features of the state samples by the inter-domain feature extractor; Performing a numerical addition operation on the inter-domain classification features and the intra-domain classification features of the state sample to obtain a recombinant classification feature of the state sample; Inputting the inter-domain classification features, intra-domain classification features and reorganized classification features of the state sample into a fault classifier to obtain the predicted probability of the fault type of the state sample; The fault classification cross entropy loss is calculated according to the fault type prediction probability of the state sample and the real fault type label calibrated by the state sample, the preference correction loss is calculated based on the fault type prediction probability, the fault classification cross entropy loss and the preference correction loss are minimized according to the back propagation and optimization algorithm, and the trained diagnosis model is determined according to the minimum fault classification cross entropy loss and the preference correction loss.

3. The mechanical equipment fault identification method according to claim 2, characterized in that: The diagnostic model further includes a condition-specific feature extractor and a domain classifier, and the training process of the diagnostic model further includes: Inputting the domain global features of the state sample into the working condition specific feature extractor to extract working condition specific features, inputting the domain global features, working condition specific features and domain classification features of the state sample into the domain classifier to obtain the domain type prediction probability of the state sample; The domain classification cross entropy loss is calculated according to the domain type prediction probability and the real domain type label calibrated by the state sample, the covariance loss is calculated according to the working condition specific features, the intra-domain classification features and the inter-domain classification features, the domain classification cross entropy loss and the covariance loss are minimized based on the back propagation and optimization algorithm, the optimal training results of the working condition specific feature extractor and the domain classifier are determined according to the minimum domain classification cross entropy loss and the covariance loss, and the optimal training results of the working condition specific feature extractor and the domain classifier are used as the working condition specific feature extractor and the domain classifier of the finally trained diagnostic model.

4. The mechanical equipment fault identification method according to claim 2, characterized in that: The fault classification cross entropy loss is calculated according to the predicted probability of the fault type of the state sample and the real fault type label of the state sample, including: ， ， in, is the cross entropy loss for fault classification, represents the sample ordinal number, represents the total number of samples, Indicates The one-hot vector of the true domain type label of each state sample, Indicates The predicted probability of the fault type of the state sample is Indicates The state samples belong to The predicted probability of each failure type, K represents the total number of known fault types in the labeled training dataset, Indicates a new fault type.

5. The mechanical equipment fault identification method according to claim 2, characterized in that: Calculating the preference correction loss based on the predicted probability of the fault type includes: ， in, is the preference correction loss, represents the sample ordinal number, represents the total number of samples, Indicates The state samples belong to The predicted probability of each failure type, Indicates The fault type ordinal number corresponding to the state sample, Indicates The predicted probability that a state sample belongs to a new fault type, Indicates a new fault type.

6. The mechanical equipment fault identification method according to claim 3, characterized in that: Calculating the domain classification cross entropy loss based on the domain type prediction probability and the true domain type label of the state sample includes: ， ， in, is the domain classification cross entropy loss, represents the sample ordinal number, represents the total number of samples, where Indicates The one-hot vector of the true domain type label of each state sample, Indicates The domain type prediction probability of state samples, Indicates The state samples belong to The predicted probability of each domain type, M is the total number of domains; Calculating the covariance loss based on the working condition specific features, the intra-domain classification features, and the inter-domain classification features includes: ， in, is the covariance loss, Indicates the specific characteristics of the working condition, represents the classification features within the domain, represents the inter-domain classification feature, represents the covariance matrix, represents the Euclidean norm.

7. The mechanical equipment fault identification method according to claim 2, characterized in that: The optimization algorithm includes one of an adaptive moment estimation algorithm, a stochastic gradient descent algorithm and a root mean square transfer algorithm.

8. A mechanical equipment fault identification device, characterized in that: include: Acquisition module, used to obtain vibration signals of mechanical equipment; An input module, used for inputting the vibration signal into a pre-trained diagnostic model, wherein the diagnostic model includes a domain global feature extractor, an inter-domain feature extractor, an intra-domain classification feature extractor, and a fault classifier; A prediction module, configured to extract a domain global feature of the vibration signal through the domain global feature extractor, extract an intra-domain classification feature of the domain global feature through the intra-domain classification feature extractor, extract an inter-domain classification feature of the vibration signal through the inter-domain feature extractor, perform a numerical addition operation on the inter-domain classification feature and the intra-domain classification feature to obtain a recombined classification feature, and input the inter-domain classification feature, the intra-domain classification feature and the recombined classification feature into a fault classifier to obtain a prediction probability of a fault type; An identification module, used to obtain a corresponding fault type ordinal number through the maximum value of the predicted probability of the fault type, so as to identify the fault type; The multiple fault types of the vibration signal include fault types of training samples and new fault types, and the fault type ordinal number is greater than the total number of fault types of training samples.

9. An electronic terminal, characterized in that: The method comprises a processor and a memory connected to the processor, wherein a computer program is stored in the memory, and when the computer program is executed by the processor, the steps of the method according to any one of claims 1 to 7 are executed.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

Images