Bearing performance degradation starting point detection method, device, equipment and storage medium
By extracting the characteristic and correlation calculation of the vibration signal of the bearing, the correlation coefficients that are continuously below the threshold are determined, which solves the problems of complex detection and unstable accuracy in the prior art, and realizes the accurate detection of the starting point of the bearing performance degradation and online detection.
Patent Information
- Application Number
- CN202411087883.4
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2024-08-09
- Publication Date
- 2024-11-15
- Estimated Expiration
- 2044-08-09
AI Technical Summary
The existing method for detecting the starting point of bearing performance degradation is complex and the accuracy is unstable, making it difficult to achieve online inspection, and is greatly affected by manual knowledge and experience.
By obtaining the vibration signals of the bearing at different moments, using a pre-trained automatic encoder model to extract features, calculate the correlation between the vibration characteristics at each moment and the next moment, and determine the correlation coefficient that is continuously lower than the preset threshold value first. , to determine the starting point of performance degradation and avoid time-frequency analysis and manual intervention.
The detection process of performance degradation start point is simplified, the detection accuracy is improved, the influence of random impact and interference noise is reduced, and the accurate determination of the bearing performance degradation start point is achieved.
Smart Images

Figure CN118641204B_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of electrical digital data processing, and in particular to a method, device, equipment and storage medium for detecting a starting point of performance degradation of a bearing. Background Art
[0002] As a common component in industrial production and life, bearings have been widely used in various industrial equipment. Once a bearing fails, it will seriously affect the operation of the equipment and bring immeasurable losses. Therefore, it is necessary to predict the remaining life of the bearing and replace the bearing parts in time to ensure the smooth operation of the equipment.
[0003] The starting point of bearing performance degradation refers to the starting point of bearing performance degradation. The starting point of bearing performance degradation is the premise of bearing remaining life prediction. If there is a deviation in the starting point of performance degradation, the remaining life prediction process of the bearing will contain interference noise, or key information will be lost. In other words, the accuracy of the starting point of bearing performance degradation will seriously affect the prediction accuracy of the remaining life of the bearing.
[0004] In the related technologies, most of them detect the performance degradation of the bearing by searching for representative features in the time domain, frequency domain and time-frequency domain of the bearing vibration signal, applying the first-order backward difference to the representative features selected from the three domains, and designing a growth window based on the 3σ rule. The above detection method often requires manual time-frequency analysis, manual extraction of time domain features, frequency domain features and time-frequency domain features, and determination of the performance degradation starting point from the performance degradation of the bearing based on certain signal processing knowledge. This makes the entire performance degradation starting point detection process more complicated, which is not conducive to actual online detection. In addition, the accuracy of the performance degradation starting point is affected by artificial knowledge and experience, and it is easy to have the problem of unstable accuracy of the performance degradation starting point. Summary of the invention
[0005] Embodiments of the present invention provide a method, device, equipment and storage medium for detecting a performance degradation starting point of a bearing, so as to solve the problem that the existing method for detecting a performance degradation starting point of a bearing is relatively complicated and the accuracy of the performance degradation starting point is unstable.
[0006] In a first aspect, an embodiment of the present invention provides a method for detecting a starting point of performance degradation of a bearing, comprising:
[0007] Respectively obtain vibration signals of the bearing to be tested at different times, and perform feature extraction on the vibration signals to obtain corresponding vibration features at different times;
[0008] Calculate the correlation between the vibration characteristics at each moment and the vibration characteristics at the next moment respectively, and obtain the correlation coefficient corresponding to each moment;
[0009] Determine, in chronological order, from the correlation coefficients corresponding to all moments, the first plurality of correlation coefficients that are continuously lower than a preset threshold;
[0010] The performance degradation starting point of the bearing to be tested is determined based on a time next to the time corresponding to the last correlation coefficient among the multiple correlation coefficients that is lower than a preset threshold.
[0011] In a possible implementation, before determining the performance degradation starting point of the bearing to be tested at the next moment after the moment corresponding to the last correlation coefficient among the multiple correlation coefficients that is lower than a preset threshold, the method further includes:
[0012] In chronological order, detecting whether there are multiple correlation coefficients continuously higher than the preset threshold after multiple correlation coefficients continuously lower than the preset threshold;
[0013] Determining the performance degradation starting point of the bearing to be tested based on the next moment of the moment corresponding to the last correlation coefficient among the multiple correlation coefficients that is lower than a preset threshold, comprises:
[0014] If after detecting multiple correlation coefficients that are continuously lower than the preset threshold, there are no multiple correlation coefficients that are continuously higher than the preset threshold, the next moment after the moment corresponding to the last correlation coefficient among the multiple correlation coefficients that are continuously lower than the preset threshold is determined as the starting point of the performance degradation of the bearing to be tested.
[0015] In a possible implementation manner, after detecting in chronological order whether there are multiple correlation coefficients that are continuously lower than the preset threshold, the method further includes:
[0016] If, after detecting multiple correlation coefficients that are continuously lower than the preset threshold, multiple correlation coefficients that are continuously higher than the preset threshold exist, a time corresponding to the last correlation coefficient that is higher than the preset threshold among the multiple correlation coefficients that are continuously higher than the preset threshold is determined as the reset time;
[0017] Based on the moments after the reset moment, all new moments are determined, and the step of determining the first multiple correlation coefficients that are continuously lower than the preset threshold from the correlation coefficients corresponding to all moments in chronological order is jumped to execute until the starting point of the performance degradation of the bearing to be tested is determined.
[0018] In a possible implementation, determining the time corresponding to the last correlation coefficient higher than the preset threshold among the multiple correlation coefficients continuously higher than the preset threshold as the reset time includes:
[0019] If after multiple correlation coefficients continuously lower than the preset threshold, there are multiple groups of correlation coefficients continuously higher than the preset threshold, the last group of the multiple groups of correlation coefficients continuously higher than the preset threshold is determined, and the moment corresponding to the last correlation coefficient in the last group of multiple correlation coefficients continuously higher than the preset threshold is determined as the reset moment.
[0020] In a possible implementation, after respectively calculating the correlation between the vibration feature at each moment and the vibration feature at the next moment to obtain the correlation coefficient corresponding to each moment, the method further includes:
[0021] Based on the correlation coefficients corresponding to all moments, an average value of the correlation coefficients is determined;
[0022] The preset threshold is obtained according to the average value of the correlation coefficient.
[0023] In a possible implementation, feature extraction is performed on the vibration signal to obtain vibration features at different times, including:
[0024] The vibration signal is subjected to feature extraction using a pre-trained autoencoder model, and vibration features at different moments are obtained accordingly; the pre-trained autoencoder model is used to extract the vibration features of the vibration signal.
[0025] In a possible implementation, respectively calculating the correlation between the vibration feature at each moment and the vibration feature at the next moment to obtain the correlation coefficient corresponding to each moment includes:
[0026] according to Calculate the correlation between the vibration characteristics at each moment and the vibration characteristics at the next moment respectively, and obtain the correlation coefficient corresponding to each moment;
[0027] in, express The correlation coefficient corresponding to the time, Indicates the amount of vibration information in the vibration feature, express The vibration characteristics of the moment Vibration information, express The average vibration information of the vibration characteristics at the moment, express The vibration characteristics of the moment Vibration information, express The average vibration information of the vibration characteristics at the moment.
[0028] In a second aspect, an embodiment of the present invention provides a device for detecting a starting point of performance degradation of a bearing, comprising:
[0029] An extraction module is used to obtain the vibration signals of the bearing to be tested at different times, and perform feature extraction on the vibration signals to obtain vibration features at different times;
[0030] A calculation module, used to calculate the correlation between the vibration characteristics at each moment and the vibration characteristics at the next moment, and obtain the correlation coefficient corresponding to each moment;
[0031] Detection module for:
[0032] Determine, in chronological order, from the correlation coefficients corresponding to all moments, the first plurality of correlation coefficients that are continuously lower than a preset threshold;
[0033] The performance degradation starting point of the bearing to be tested is determined based on a time next to the time corresponding to the last correlation coefficient among the multiple correlation coefficients that is lower than a preset threshold.
[0034] In a third aspect, an embodiment of the present invention provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the processor implements the steps of the method described in the first aspect or any possible implementation manner of the first aspect.
[0035] In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the method described in the first aspect or any possible implementation method of the first aspect are implemented.
[0036] The embodiment of the present invention provides a bearing performance degradation starting point detection method, device, equipment and storage medium. The vibration characteristics are obtained by extracting the characteristics of the vibration signals of the bearing to be tested at different times. Then, the correlation between the vibration characteristics at each moment and the vibration characteristics at the next moment is calculated to obtain the correlation coefficient corresponding to each moment. Then, the first multiple correlation coefficients that are continuously lower than the preset threshold are determined from the correlation coefficients corresponding to all moments in chronological order. Finally, the performance degradation starting point of the bearing to be tested is determined at the next moment corresponding to the last correlation coefficient lower than the preset threshold among the multiple correlation coefficients. Among them, the lower the correlation coefficient, the weaker the correlation between the vibration characteristics at two adjacent moments, which means that the performance of the bearing has changed. By determining the performance degradation starting point through the first multiple correlation coefficients that are continuously lower than the preset threshold, there is no need to perform time-frequency analysis on the vibration signal, which can not only effectively simplify the detection process of the performance degradation starting point, but also reduce the participation of artificial knowledge and experience. In addition, it can also effectively avoid the influence of random shocks and interference noise, and improve the detection accuracy of the performance degradation starting point. BRIEF DESCRIPTION OF THE DRAWINGS
[0037] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.
[0038] Figure 1 is a flow chart of a method for detecting a starting point of bearing performance degradation provided by an embodiment of the present invention;
[0039] Figure 2 is a schematic diagram of the structure of an automatic encoder model provided by an embodiment of the present invention;
[0040] Figure 3 is a flow chart of a method for detecting a starting point of bearing performance degradation provided by another embodiment of the present invention;
[0041] Figure 4 It is a schematic diagram of comparing the time domain amplitude of each vibration signal and the correlation coefficient corresponding to each moment under a slow failure condition provided by an embodiment of the present invention;
[0042] Figure 5 It is a schematic diagram comparing the time domain amplitude of each vibration signal and the correlation coefficient corresponding to each moment under a sudden failure condition provided by an embodiment of the present invention;
[0043] Figure 6 is a schematic structural diagram of a bearing performance degradation starting point detection device provided by an embodiment of the present invention;
[0044] Figure 7 It is a schematic diagram of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION
[0045] In the following description, specific details such as specific system structures, technologies, etc. are provided for the purpose of illustration rather than limitation, so as to provide a thorough understanding of the embodiments of the present invention. However, it should be clear to those skilled in the art that the present invention may be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to prevent unnecessary details from obstructing the description of the present invention.
[0046] In order to simplify the detection process of the starting point of performance degradation and avoid the detection accuracy being limited by artificial knowledge and experience, in the implementation of the present application, the correlation coefficient corresponding to each moment is obtained by calculating the correlation between the vibration characteristics at each moment and the vibration characteristics at the next moment; and from the correlation coefficients corresponding to all moments, the first multiple correlation coefficients that are continuously lower than the preset threshold are determined, and then based on the next moment corresponding to the moment corresponding to the last correlation coefficient of the multiple correlation coefficients that is lower than the preset threshold, the performance degradation starting point of the bearing to be tested is determined, wherein the lower the correlation coefficient, the greater the difference between the vibration characteristics corresponding to the moment and the next moment, which means that the performance of the bearing has changed. The embodiment of the present invention determines the starting point of performance degradation by using the first multiple correlation coefficients that are continuously lower than the preset threshold, which can not only simplify the detection process of the starting point of performance degradation, but also reduce the participation of artificial knowledge and experience, accurately determine the initial moment of bearing performance degradation, and improve the detection accuracy of the starting point of performance degradation.
[0047] In order to make the purpose, technical solutions and advantages of the present invention more clear, specific embodiments will be described below in conjunction with the accompanying drawings.
[0048] Figure 1 The implementation flow chart of the method for detecting the starting point of bearing performance degradation provided by the embodiment of the present invention is described in detail as follows:
[0049] Step 101, respectively obtain the vibration signals of the bearing to be tested at different times, and perform feature extraction on the vibration signals to obtain corresponding vibration features at different times.
[0050] In the embodiment of the present invention, a vibration sensor may be used to obtain vibration signals of the bearing to be tested at different times, and a deep learning model may be used to extract features of the vibration signals of the bearing to be tested at different times, for example, an autoencoder model.
[0051] In some embodiments, a pre-trained autoencoder model may be used to extract features from the vibration signal to obtain vibration features at different times. Figure 2 , the autoencoder model is a neural network consisting of an input layer, a hidden layer, and an output layer connected in sequence. It operates by receiving data, compressing and encoding the data, and then reconstructing the data from the encoded representation. The autoencoder model is designed to copy the input data, then analyze the data and output a copy of the data after reconstructing the data in an unsupervised manner, so the input layer and the output layer have exactly the same number of units. The trained autoencoder model is obtained by training the model until the loss is minimized. Through model training, the autoencoder model can learn the important features of the data.
[0052] See also Figure 2 , the autoencoder model consists of two parts: encoding part and decoding part. The encoding part includes: input layer and hidden layer. The input layer is used to receive input data, and the hidden layer is used to encode and compress the input data and output the data features corresponding to the input data. When the input data is When , the output of the encoding part, that is, the output of the hidden layer can be expressed as .
[0053] in, Represents input data The corresponding data features are represents the activation function of the encoding part, that is, the activation function of the hidden layer, and Represents the weights and biases corresponding to the encoding part.
[0054] The decoding part includes: hidden layer and output layer. The hidden layer is used to output data features. The output layer is used to decode the data features to obtain output data. When , the output of the decoding part, that is, the output of the output layer can be expressed as .
[0055] in, Representing data characteristics The corresponding output data is, represents the activation function of the decoding part, that is, the activation function of the output layer, and Represents the weights and biases corresponding to the decoding part.
[0056] The above model parameters , , and After gradient descent optimization, the reconstruction error between the output data of the output layer and the input data of the input layer is minimized, the optimal model parameters are obtained, and the model training is completed. Here, the reconstruction error can be expressed as: .
[0057] in, represents the reconstruction error between the output data and the input data, Indicates the number of batchsizes during model training. Indicates The output data corresponding to the input data is Indicates Input data.
[0058] Here, the autoencoder model is trained until the reconstruction error is minimized so that the output data is as close to the input data as possible. Through the above training process, the autoencoder model can learn the important features of the data. Here, as close as possible can be understood as within the error range.
[0059] In the embodiment of the present invention, a pre-trained autoencoder model is used to extract the vibration characteristics of the vibration signal.
[0060] When training the autoencoder model, a first dropout layer may be added between the input layer and the hidden layer, and a second dropout layer may be added between the hidden layer and the output layer. Here, the first dropout layer and the second dropout layer may randomly inactivate neurons in the autoencoder model to prevent the model from over-adapting to the training data, thereby improving the generalization ability of the model and preventing the model from overfitting.
[0061] Exemplarily, the structure of the autoencoder model can be 2560-256-2560. That is, the input layer contains 2560 nodes for receiving the vibration signal of the bearing to be tested, and the hidden layer contains 256 nodes for outputting the vibration characteristics. The number of nodes in the output layer is the same as the number of nodes in the input layer. The activation function of the hidden layer is the relu function, and the activation function of the output layer is the tanh function. The parameters of the first dropout layer and the second dropout layer are both 0.5, the batchsize number is 64, the epochs is 30, the loss function is the mean square error function, and the optimizer is the Adam optimizer.
[0062] Here, after the autoencoder model is trained, the first dropout layer and the second dropout layer are discarded to obtain a trained autoencoder model. The trained autoencoder model includes an input layer, a hidden layer, and an output layer.
[0063] In an embodiment of the present invention, the vibration signal of the bearing to be tested can be input into the input layer of a pre-trained autoencoder model, the input layer receives the vibration signal of the bearing to be tested, and transmits it to the hidden layer. The hidden layer compresses and encodes the vibration signal of the bearing to be tested to obtain the vibration characteristics of the vibration signal.
[0064] Step 102, respectively calculating the correlation between the vibration characteristics at each moment and the vibration characteristics at the next moment, and obtaining the correlation coefficient corresponding to each moment.
[0065] Based on the above automatic encoder model, the vibration features at different moments can be determined respectively. For the features at each moment, the correlation between the vibration features at that moment and the vibration features at the next moment is calculated to obtain the correlation coefficient corresponding to that moment.
[0066] In some embodiments, the The correlation between the vibration characteristics at each moment and the vibration characteristics at the next moment is calculated respectively, and the correlation coefficient corresponding to each moment is obtained.
[0067] in, express The correlation coefficient corresponding to the time, Indicates the amount of vibration information in the vibration feature, express The vibration characteristics of the moment Vibration information, express The average vibration information of the vibration characteristics at the moment, express The vibration characteristics of the moment Vibration information, express The average vibration information of the vibration characteristics at the moment.
[0068] Here, the vibration feature is in vector form. The vibration feature at each moment contains multiple vibration information. The multiple vibration information as elements in the vector together constitute the vibration feature in vector form. Among them, the average vibration information refers to the average value of each vibration information in the vibration feature at the same moment.
[0069] Step 103 , determining, in chronological order, from the correlation coefficients corresponding to all moments, a plurality of correlation coefficients that are first continuously lower than a preset threshold.
[0070] Here, the correlation coefficient corresponding to each moment is used to characterize the correlation between the vibration characteristics at that moment and the vibration characteristics at the next moment. The lower the correlation coefficient, the weaker the correlation between the vibration characteristics at that moment and the vibration characteristics at the next moment. This also means that the performance of the bearing has changed. Therefore, the embodiment of the present invention determines the correlation coefficient that is first lower than the preset threshold from the correlation coefficients corresponding to all moments, thereby determining the starting point of the performance degradation of the bearing.
[0071] In addition, considering that the vibration signal of the bearing mostly contains random shocks and interference noise. Random shocks and interference noise may reduce the correlation coefficient. However, random shocks and interference noise are mostly short-term interferences and will not appear continuously. Therefore, the embodiment of the present invention further determines the first multiple correlation coefficients that are continuously lower than the preset threshold from the correlation coefficients corresponding to all moments, which are used to determine the starting point of the performance degradation of the bearing.
[0072] Here, the number of correlation coefficients that are first continuously lower than the preset threshold can be represented by n. n is a positive integer. The specific value of n can be determined according to actual conditions. Accordingly, the above-mentioned determination of the first multiple correlation coefficients that are continuously lower than the preset threshold from the correlation coefficients corresponding to all moments in chronological order can be understood as: determining the first n correlation coefficients that are continuously lower than the preset threshold from the correlation coefficients corresponding to all moments in chronological order.
[0073] Exemplarily, the number of the first correlation coefficients that are continuously lower than the preset threshold may be 4, that is, n = 4. That is, in chronological order, the first 4 correlation coefficients that are continuously lower than the preset threshold are determined from the correlation coefficients corresponding to all moments.
[0074] To facilitate understanding, a simple example is given below.
[0075] For example, the correlation coefficients corresponding to 10 moments are calculated respectively, and the correlation coefficients corresponding to each moment can be expressed as , , , , , , , , and .in, , , , , , and If both are lower than the preset threshold, , , and The first four correlation coefficients that are continuously lower than the preset threshold are determined.
[0076] like , , , , , , and If both are lower than the preset threshold, , , and The first multiple correlation coefficients below the preset threshold are determined. Here, and It may be an abnormal value below the preset threshold due to random impact and interference noise.
[0077] The embodiment of the present invention determines the first multiple correlation coefficients that are continuously lower than a preset threshold from the correlation coefficients corresponding to all moments, and then determines the starting point of the performance degradation of the bearing. This can effectively eliminate noise interference to accurately determine the starting point of the performance degradation of the bearing. At the same time, it can also effectively simplify the detection process of the starting point of the performance degradation, so as to facilitate real-time online detection of the bearing to be tested.
[0078] In some embodiments, after obtaining the correlation coefficient corresponding to each moment, the average value of the correlation coefficient can be determined based on the correlation coefficients corresponding to all moments; and the preset threshold value can be obtained according to the average value of the correlation coefficient.
[0079] That is to say, the preset threshold in the embodiment of the present invention can be determined according to the average value of the correlation coefficient corresponding to each moment. In some embodiments, the average value of the correlation coefficient corresponding to each moment can be directly determined as the preset threshold, or the preset threshold can be determined as any value close to the average value of the above correlation coefficient. Here, close can be understood as within the error range.
[0080] Step 104 : determining a performance degradation starting point of the bearing to be tested based on a time point next to a time point corresponding to a last correlation coefficient among the multiple correlation coefficients that is lower than a preset threshold.
[0081] During the operation of the bearing, random impacts or interference noises that occur during the normal operation stage may cause the correlation coefficient to decrease, thereby affecting the detection accuracy of the starting point of performance degradation. However, considering that random impacts and interference noises during the operation of the bearing cannot appear continuously, the embodiment of the present invention determines that the bearing performance begins to degrade only when multiple correlation coefficients are continuously lower than the preset threshold.
[0082] Furthermore, the embodiment of the present invention further determines the starting point of performance degradation of the bearing to be tested according to the next moment after the moment corresponding to the last correlation coefficient below the preset threshold among the multiple correlation coefficients that are continuously below the preset threshold.
[0083] For example, the correlation coefficients corresponding to each moment can be expressed as , , , , , , , , and .like , , and is the first four correlation coefficients that are continuously lower than the preset threshold. The next moment of the corresponding moment, that is, At the corresponding moment, the starting point of performance degradation of the bearing to be tested is determined.
[0084] In some embodiments, the starting point of performance degradation of the bearing to be tested can be determined directly at the next moment after the moment corresponding to the last correlation coefficient below the preset threshold among the multiple correlation coefficients that are continuously below the preset threshold. At the next moment after the corresponding moment, the starting point of performance degradation of the bearing to be tested is determined.
[0085] Compared with the prior art, the embodiment of the present invention extracts the characteristics of the vibration signals of the bearing to be tested at different moments to obtain the vibration characteristics, and then calculates the correlation between the vibration characteristics at each moment and the vibration characteristics at the next moment to obtain the correlation coefficient corresponding to each moment; then, in chronological order, from the correlation coefficients corresponding to all moments, the first multiple correlation coefficients that are continuously lower than the preset threshold are determined; finally, based on the next moment corresponding to the moment corresponding to the last correlation coefficient lower than the preset threshold among the multiple correlation coefficients, the performance degradation starting point of the bearing to be tested is determined. Among them, the lower the correlation coefficient, the weaker the correlation between the vibration characteristics of two adjacent moments, which means that the performance of the bearing has changed. By determining the starting point of performance degradation through the first multiple correlation coefficients that are continuously lower than the preset threshold, there is no need to perform time-frequency analysis on the vibration signal, which can not only effectively simplify the detection process of the starting point of performance degradation, but also reduce the participation of artificial knowledge and experience. In addition, it can also effectively avoid the influence of random shocks and interference noise, and improve the detection accuracy of the starting point of performance degradation.
[0086] The above method can be used to determine the initial point of bearing performance degradation. However, considering that the vibration signal of the bearing contains random impact and interference noise, the initial point of performance degradation is easily affected by random impact and interference noise. The embodiment of the present invention further tests the initial point of performance degradation to further improve the detection accuracy of the initial point of performance degradation. The specific test method is as follows:
[0087] In some embodiments, see Figure 3 , before the above step 104, it also includes:
[0088] Step 105 , detecting in chronological order whether there are multiple correlation coefficients that are continuously higher than the preset threshold after multiple correlation coefficients that are continuously lower than the preset threshold exist.
[0089] On this basis, step 104 can be expressed as step 1041. Step 1041 can include: if after detecting multiple correlation coefficients that are continuously lower than the preset threshold, there are no multiple correlation coefficients that are continuously higher than the preset threshold, then determine the next moment of the moment corresponding to the last correlation coefficient that is lower than the preset threshold among the multiple correlation coefficients that are continuously lower than the preset threshold as the performance degradation starting point of the bearing to be tested.
[0090] That is to say, after determining the first multiple correlation coefficients that are continuously lower than the preset threshold, continue to detect whether there are multiple correlation coefficients that are continuously higher than the preset threshold after the first multiple correlation coefficients that are continuously lower than the preset threshold. Only when there are no multiple correlation coefficients that are continuously higher than the preset threshold after the first multiple correlation coefficients that are continuously lower than the preset threshold, the next moment of the moment corresponding to the last correlation coefficient lower than the preset threshold among the first multiple correlation coefficients that are continuously lower than the preset threshold is determined as the performance degradation starting point of the bearing to be tested.
[0091] Here, the number of correlation coefficients that are continuously higher than the preset threshold can be represented by n', where n' is a positive integer. The value of n' can be determined according to actual conditions. Accordingly, if after detecting multiple correlation coefficients that are continuously lower than the preset threshold, there are no multiple correlation coefficients that are continuously higher than the preset threshold, it can be understood that: if after detecting multiple correlation coefficients that are continuously lower than the preset threshold, there are no correlation coefficients that are continuously higher than the preset threshold, or the number of correlation coefficients that are continuously higher than the preset threshold is less than n'. At this time, the next moment corresponding to the moment when the last correlation coefficient among the multiple correlation coefficients that are continuously lower than the preset threshold is lower than the preset threshold is determined as the starting point of performance degradation of the bearing to be tested.
[0092] Exemplarily, the number of correlation coefficients that are continuously higher than the preset threshold may be greater than or equal to 4. That is, n'≥4. Taking n'=4 as an example, if after detecting multiple correlation coefficients that are continuously lower than the preset threshold, there are no n' correlation coefficients that are continuously higher than the preset threshold, it can be understood that: if after detecting multiple correlation coefficients that are continuously lower than the preset threshold, there are no correlation coefficients that are continuously higher than the preset threshold, or the number of correlation coefficients that are continuously higher than the preset threshold is less than 4. At this time, the next moment corresponding to the moment when the last correlation coefficient that is lower than the preset threshold among the multiple correlation coefficients that are continuously lower than the preset threshold is determined as the starting point of the performance degradation of the bearing to be tested.
[0093] It is understandable that during the bearing performance degradation process, the correlation coefficients corresponding to each moment are all lower than the preset threshold. However, due to the influence of random shocks or interference noise, abnormal values with correlations higher than the preset threshold may also appear during the bearing performance degradation process. In order to avoid the influence of random shocks or interference noise, the embodiment of the present invention determines the next moment of the moment corresponding to the last correlation coefficient below the preset threshold among the multiple correlation coefficients that are first continuously lower than the preset threshold as the starting point of the performance degradation of the bearing to be tested only when there are no correlation coefficients that are continuously higher than the preset threshold after the multiple correlation coefficients that are first continuously lower than the preset threshold, or when the number of correlation coefficients that are continuously higher than the preset threshold is less than 4.
[0094] For example, n=4, n'=4. The correlation coefficients corresponding to each moment can be expressed as , , , , , , , , and .like , , , , and are all below the preset threshold. , and are higher than the preset threshold. , , and It is the first four correlation coefficients that are continuously lower than the preset threshold. , and It may be an outlier caused by random shock or interference noise. At the next moment after the corresponding moment, the starting point of performance degradation of the bearing to be tested is determined.
[0095] According to the above method, the performance degradation starting point can be determined when there are no multiple correlation coefficients that are continuously higher than the preset threshold after the first multiple correlation coefficients that are continuously lower than the preset threshold. However, if there are multiple correlation coefficients that are continuously higher than the preset threshold after the first multiple correlation coefficients that are continuously lower than the preset threshold, it is determined that the multiple correlation coefficients that are continuously higher than the preset threshold are not abnormal values caused by random impact or interference noise, and the first multiple correlation coefficients that are continuously lower than the preset threshold may be misjudged and need to be re-tested.
[0096] In some embodiments, after the above step 105, the following steps may also be included:
[0097] Step 106, if after detecting multiple correlation coefficients that are continuously lower than the preset threshold, multiple correlation coefficients that are continuously higher than the preset threshold exist, then the time corresponding to the last correlation coefficient that is higher than the preset threshold among the multiple correlation coefficients that are continuously higher than the preset threshold is determined as the reset time;
[0098] Step 107, based on the moment after the reset moment, determine all new moments, and jump to execute the step of determining the first multiple correlation coefficients that are continuously lower than the preset threshold from the correlation coefficients corresponding to all moments in chronological order, until the starting point of performance degradation of the bearing to be tested is determined.
[0099] It is understandable that the performance degradation process of the bearing is irreversible, and during the performance degradation process of the bearing, the corresponding correlation coefficients at each moment are all lower than the preset threshold. If multiple correlation coefficients that are continuously lower than the preset threshold appear after multiple correlation coefficients that are continuously higher than the preset threshold, it means that the multiple correlation coefficients that are continuously lower than the preset threshold at first may be abnormal values caused by random impact or noise interference, and it is necessary to re-determine the multiple correlation coefficients that are continuously lower than the preset threshold to determine the starting point of performance degradation.
[0100] In the embodiment of the present invention, the time corresponding to the last correlation coefficient higher than the preset threshold among the multiple correlation coefficients continuously higher than the preset threshold is determined as the reset time. According to the time after the reset time, all new time periods are determined, and the first multiple correlation coefficients continuously lower than the preset threshold are determined from the corresponding correlation coefficients of all time periods to re-determine the performance degradation initial point.
[0101] Here, all moments after the reset moment may be determined as new all moments, and the performance degradation initial point may be re-determined according to the correlation coefficients corresponding to the new all moments.
[0102] Here, the above-mentioned if after detecting multiple correlation coefficients that are continuously lower than the preset threshold, there are multiple correlation coefficients that are continuously higher than the preset threshold, it can be understood that: if after detecting multiple correlation coefficients that are continuously lower than the preset threshold, there are at least n' correlation coefficients that are continuously higher than the preset threshold. At this time, the moment corresponding to the last correlation coefficient that is higher than the preset threshold among the at least n' correlation coefficients that are continuously higher than the preset threshold is determined as the reset moment.
[0103] Exemplarily, the number of correlation coefficients that are continuously higher than the preset threshold may be greater than or equal to 4. That is, n'≥4. Taking n'=4 as an example, if after detecting multiple correlation coefficients that are continuously lower than the preset threshold, there are n' correlation coefficients that are continuously higher than the preset threshold, it can be understood that: if after detecting multiple correlation coefficients that are continuously lower than the preset threshold, there are at least 4 correlation coefficients that are continuously higher than the preset threshold. At this time, the moment corresponding to the last correlation coefficient that is higher than the preset threshold among the at least 4 correlation coefficients that are continuously higher than the preset threshold is determined as the reset moment.
[0104] For example, the correlation coefficients corresponding to each moment can be expressed as , , , , , , , , , , , , , and .like , , and are the first multiple correlation coefficients that are continuously lower than the preset threshold, and , , , and If both are higher than the preset threshold, The corresponding moment is determined as the reset moment, and the moment after the reset moment is determined as all new moments, and the step of determining the first multiple correlation coefficients that are continuously lower than the preset threshold from the correlation coefficients corresponding to all moments is continued, until after the first multiple correlation coefficients that are continuously lower than the preset threshold, there are no multiple correlation coefficients that are continuously higher than the preset threshold, and then the starting point of performance degradation is determined based on the first multiple correlation coefficients that are continuously lower than the preset threshold.
[0105] It is understandable that during the operation of the bearing, random impacts and interference noises may occur repeatedly from time to time. This means that after the first multiple correlation coefficients that are continuously lower than the preset threshold, there may be multiple groups of multiple correlation coefficients that are continuously higher than the preset threshold. At this time, the reset time can be determined according to the following method:
[0106] If after multiple correlation coefficients continuously lower than the preset threshold, there are multiple groups of correlation coefficients continuously higher than the preset threshold, the last group of the multiple groups of correlation coefficients continuously higher than the preset threshold is determined, and the moment corresponding to the last correlation coefficient in the last group of multiple correlation coefficients continuously higher than the preset threshold is determined as the reset moment.
[0107] Here, each group of multiple correlation coefficients that are continuously higher than the preset threshold value includes at least n' correlation coefficients that are continuously higher than the preset threshold value.
[0108] For example, the correlation coefficients corresponding to each moment can be expressed as , , , , , , , , , , , , , and .like , , and are the first multiple correlation coefficients that are continuously lower than the preset threshold, and , , , , , , , If both are higher than the preset threshold, The corresponding time is determined as the reset time.
[0109] According to the above method, the reset time can be determined. The embodiment of the present invention determines all the times after the reset time as new all the times, and re-determines the first multiple correlation coefficients that are continuously lower than the preset threshold from the correlation coefficients of the new all the times to re-determine the performance degradation starting point.
[0110] In addition, the embodiment of the present invention also provides the following experiment, which is used to determine the number n of correlation coefficients that are first continuously lower than a preset threshold, so as to reduce the error tolerance as much as possible, while ensuring that the fluctuation information of the vibration characteristics is judged in the shortest possible time. The value of n is determined by the following experiment, where the value of n' can be the same as the value of n.
[0111] Different values are taken for n respectively, and the above performance degradation starting point detection method is executed accordingly to determine the performance degradation starting points of different bearings. The performance degradation starting points of each bearing are shown in Table 1 below.
[0112] Table 1 Performance degradation starting point of each bearing when n is 3, 4, 5, 6
[0113]
[0114] It can be found from Table 1 that when n is 6, the starting point of performance degradation determined for bearing 1-1 is later than the starting point of performance degradation determined under other conditions. In the actual detection process, the earlier the starting point of performance degradation is discovered, the more conducive it is for people to prepare countermeasures in advance when the bearing fails. Therefore, the case of n=6 is excluded.
[0115] Next, n is set to 3, 4, and 5, and the performance degradation starting point detection is continued to obtain the following Table 2.
[0116] Table 2 Performance degradation starting point of each bearing when n is 3, 4, and 5
[0117]
[0118] When n is 3, the starting point of performance degradation determined by bearing 1-3 is later than the starting point of performance degradation determined under other conditions. When n is 5, the starting point of performance degradation determined by bearing 3-3 is later than the starting point of performance degradation determined under other conditions. Based on the principle that the earlier the starting point of performance degradation is discovered, the better, the cases of n=3 and 5 are excluded, and n is finally determined to be 4.
[0119] Finally, according to the case of n=4, the PHM2012 rolling bearing accelerated life test data set was used to determine 17 bearing performance degradation starting points according to the above bearing performance degradation starting point detection method, as shown in Table 3.
[0120] Table 3 Performance degradation starting point of each bearing under different working conditions when n is 4
[0121]
[0122] In addition, the embodiments of the present invention respectively use the above-mentioned performance degradation starting point detection method to detect the performance degradation starting point of the bearing under slow failure and the bearing under sudden failure. Figure 4 and Figure 5 Among them, the time domain amplitude change of the vibration signal at different times can be used to characterize the performance change of the bearing. Figure 4 and Figure 5 It can be seen that when the time domain amplitude of the vibration signal changes significantly, that is, the bearing performance changes, the correlation coefficient also decreases significantly. The performance degradation starting point determined by the above detection method can accurately determine the starting moment of bearing degradation. In other words, regardless of whether the bearing fails slowly or suddenly, the bearing performance degradation starting point detection method provided by the embodiment of the present invention can quickly and accurately determine the bearing performance degradation starting point.
[0123] It should be understood that the order of execution of the steps in the above embodiment does not necessarily mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiment of the present invention.
[0124] The following is an embodiment of the device of the present invention. For details not described in detail, reference may be made to the corresponding method embodiments described above.
[0125] Figure 6 The structure diagram of the bearing performance degradation starting point detection device provided by the embodiment of the present invention is shown. For the convenience of description, only the part related to the embodiment of the present invention is shown, which is described in detail as follows:
[0126] like Figure 6 As shown, the bearing performance degradation starting point detection device 6 includes: an extraction module 61 , a calculation module 62 and a detection module 63 .
[0127] An extraction module 61 is used to obtain vibration signals of the bearing to be tested at different times, and perform feature extraction on the vibration signals to obtain vibration features at different times;
[0128] A calculation module 62, used to calculate the correlation between the vibration characteristics at each moment and the vibration characteristics at the next moment, and obtain the correlation coefficient corresponding to each moment;
[0129] The detection module 63 is specifically used for:
[0130] Determine, in chronological order, from the correlation coefficients corresponding to all moments, the first plurality of correlation coefficients that are continuously lower than a preset threshold;
[0131] The performance degradation starting point of the bearing to be tested is determined based on a time next to the time corresponding to the last correlation coefficient among the multiple correlation coefficients that is lower than a preset threshold.
[0132] In a possible implementation, the detection module 63 is further configured to:
[0133] In chronological order, detecting whether there are multiple correlation coefficients continuously higher than the preset threshold after multiple correlation coefficients continuously lower than the preset threshold;
[0134] Accordingly, the detection module 63 is specifically used for:
[0135] If after detecting multiple correlation coefficients that are continuously lower than the preset threshold, there are no multiple correlation coefficients that are continuously higher than the preset threshold, the next moment after the moment corresponding to the last correlation coefficient among the multiple correlation coefficients that are continuously lower than the preset threshold is determined as the starting point of the performance degradation of the bearing to be tested.
[0136] In a possible implementation, the detection module 63 is further configured to:
[0137] If, after detecting multiple correlation coefficients that are continuously lower than the preset threshold, multiple correlation coefficients that are continuously higher than the preset threshold exist, a time corresponding to the last correlation coefficient that is higher than the preset threshold among the multiple correlation coefficients that are continuously higher than the preset threshold is determined as the reset time;
[0138] Based on the moments after the reset moment, all new moments are determined, and the step of determining the first multiple correlation coefficients that are continuously lower than the preset threshold from the correlation coefficients corresponding to all moments in chronological order is jumped to execute until the starting point of the performance degradation of the bearing to be tested is determined.
[0139] In a possible implementation, the detection module 63 is specifically configured to:
[0140] If after multiple correlation coefficients continuously lower than the preset threshold, there are multiple groups of correlation coefficients continuously higher than the preset threshold, the last group of the multiple groups of correlation coefficients continuously higher than the preset threshold is determined, and the moment corresponding to the last correlation coefficient in the last group of multiple correlation coefficients continuously higher than the preset threshold is determined as the reset moment.
[0141] In a possible implementation, the calculation module 62 is further configured to:
[0142] Based on the correlation coefficients corresponding to all moments, an average value of the correlation coefficients is determined;
[0143] The preset threshold is obtained according to the average value of the correlation coefficient.
[0144] In a possible implementation, the extraction module 61 is specifically configured to:
[0145] The vibration signal is subjected to feature extraction using a pre-trained autoencoder model, and vibration features at different moments are obtained accordingly; the pre-trained autoencoder model is used to extract the vibration features of the vibration signal.
[0146] In a possible implementation, the calculation module 62 is specifically configured to:
[0147] according to Calculate the correlation between the vibration characteristics at each moment and the vibration characteristics at the next moment respectively, and obtain the correlation coefficient corresponding to each moment;
[0148] in, express The correlation coefficient corresponding to the time, Indicates the amount of vibration information in the vibration feature, express The vibration characteristics of the moment Vibration information, express The average vibration information of the vibration characteristics at the moment, express The vibration characteristics of the moment Vibration information, express The average vibration information of the vibration characteristics at the moment.
[0149] In the embodiment of the present invention, the extraction module 61 extracts the characteristics of the vibration signals of the bearing to be tested at different moments to obtain the vibration characteristics. Subsequently, the calculation module 62 calculates the correlation between the vibration characteristics at each moment and the vibration characteristics at the next moment to obtain the correlation coefficient corresponding to each moment. Then, the detection module 63 determines the first multiple correlation coefficients that are continuously lower than the preset threshold from the correlation coefficients corresponding to all moments in chronological order. And based on the next moment corresponding to the moment corresponding to the last correlation coefficient lower than the preset threshold among the multiple correlation coefficients, the performance degradation starting point of the bearing to be tested is determined. Among them, the lower the correlation coefficient, the weaker the correlation between the vibration characteristics of two adjacent moments, which means that the performance of the bearing has changed. The detection module 63 determines the performance degradation starting point by using the first multiple correlation coefficients that are continuously lower than the preset threshold, without the need for time-frequency analysis of the vibration signal. This can not only effectively simplify the detection process of the performance degradation starting point, but also reduce the participation of artificial knowledge and experience. In addition, it can also effectively avoid the influence of random shocks and interference noise, and improve the detection accuracy of the performance degradation starting point.
[0150] Figure 7 Schematic diagram of an electronic device provided by an embodiment of the present invention. Figure 7 As shown, the electronic device 7 of this embodiment includes: a processor 70, a memory 71, and a computer program 72 stored in the memory 71 and executable on the processor 70. When the processor 70 executes the computer program 72, the steps in the above-mentioned bearing performance degradation detection method embodiments are implemented, for example Figure 1 Alternatively, when the processor 70 executes the computer program 72, the functions of each module / unit in the above-mentioned device embodiments are realized, for example, Figure 6 The functions of modules 61 to 63 are shown.
[0151] Exemplarily, the computer program 72 may be divided into one or more modules / units, which are stored in the memory 71 and executed by the processor 70 to implement the present invention. The one or more modules / units may be a series of computer program instruction segments capable of implementing specific functions, which are used to describe the execution process of the computer program 72 in the electronic device 7. For example, the computer program 72 may be divided into Figure 6 Modules 61 to 63 are shown.
[0152] The electronic device 7 may be a computing device such as a desktop computer, a notebook, a PDA, or a cloud server. The electronic device 7 may include, but is not limited to, a processor 70 and a memory 71. Those skilled in the art will appreciate that Figure 7 It is only an example of the electronic device 7 and does not constitute a limitation of the electronic device 7. It may include more or fewer components than shown in the figure, or a combination of certain components, or different components. For example, the electronic device may also include input and output devices, network access devices, buses, etc.
[0153] The processor 70 may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor, etc.
[0154] The memory 71 may be an internal storage unit of the electronic device 7, such as a hard disk or memory of the electronic device 7. The memory 71 may also be an external storage device of the electronic device 7, such as a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, etc. equipped on the electronic device 7. Further, the memory 71 may also include both an internal storage unit and an external storage device of the electronic device 7. The memory 71 is used to store the computer program and other programs and data required by the electronic device. The memory 71 may also be used to temporarily store data that has been output or is to be output.
[0155] The technicians in the relevant field can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional units and modules is used as an example for illustration. In practical applications, the above-mentioned function allocation can be completed by different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiment can be integrated in a processing unit, or each unit can exist physically separately, or two or more units can be integrated in one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of software functional units. In addition, the specific names of the functional units and modules are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of this application. The specific working process of the units and modules in the above-mentioned system can refer to the corresponding process in the aforementioned method embodiment, which will not be repeated here.
[0156] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described or recorded in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.
[0157] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.
[0158] In the embodiments provided by the present invention, it should be understood that the disclosed devices / electronic devices and methods can be implemented in other ways. For example, the device / electronic device embodiments described above are only schematic. For example, the division of the modules or units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.
[0159] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
[0160] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.
[0161] If the integrated module / unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the present invention implements all or part of the processes in the above-mentioned embodiment method, and can also be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium. When the computer program is executed by the processor, the steps of the above-mentioned performance degradation starting point detection method embodiments of each bearing can be implemented. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. The computer-readable medium may include: any entity or device that can carry the computer program code, recording medium, U disk, mobile hard disk, disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electric carrier signal, telecommunication signal and software distribution medium. The embodiments described above are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. Such modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention, and should all be included in the protection scope of the present invention.
Claims
1. A method for detecting the starting point of bearing performance degradation, characterized in that: include: Respectively obtain vibration signals of the bearing to be tested at different times, and perform feature extraction on the vibration signals to obtain corresponding vibration features at different times; The correlation between the vibration characteristics at each moment and the vibration characteristics at the next moment is calculated respectively to obtain the correlation coefficient corresponding to each moment; the correlation coefficient corresponding to each moment is used to characterize the correlation between the vibration characteristics at this moment and the vibration characteristics at the next moment; Determine, in chronological order, from the correlation coefficients corresponding to all moments, the first plurality of correlation coefficients that are continuously lower than a preset threshold; The performance degradation starting point of the bearing to be tested is determined based on a time next to the time corresponding to the last correlation coefficient among the multiple correlation coefficients that is lower than a preset threshold.
2. The method for detecting the starting point of bearing performance degradation according to claim 1, characterized in that: Before determining the performance degradation starting point of the bearing to be tested at the next moment after the moment corresponding to the last correlation coefficient among the multiple correlation coefficients that is lower than the preset threshold, the method further includes: In chronological order, detecting whether there are multiple correlation coefficients continuously higher than the preset threshold after multiple correlation coefficients continuously lower than the preset threshold; Determining the performance degradation starting point of the bearing to be tested based on the next moment of the moment corresponding to the last correlation coefficient among the multiple correlation coefficients that is lower than a preset threshold, comprises: If after detecting multiple correlation coefficients that are continuously lower than the preset threshold, there are no multiple correlation coefficients that are continuously higher than the preset threshold, the next moment after the moment corresponding to the last correlation coefficient among the multiple correlation coefficients that are continuously lower than the preset threshold is determined as the starting point of the performance degradation of the bearing to be tested.
3. The method for detecting the starting point of bearing performance degradation according to claim 2, characterized in that: After detecting, in chronological order, a plurality of correlation coefficients that are continuously lower than the preset threshold, whether there are a plurality of correlation coefficients that are continuously higher than the preset threshold, the method further includes: If, after detecting multiple correlation coefficients that are continuously lower than the preset threshold, multiple correlation coefficients that are continuously higher than the preset threshold exist, a time corresponding to the last correlation coefficient that is higher than the preset threshold among the multiple correlation coefficients that are continuously higher than the preset threshold is determined as the reset time; Based on the moments after the reset moment, all new moments are determined, and the step of determining the first multiple correlation coefficients that are continuously lower than the preset threshold from the correlation coefficients corresponding to all moments in chronological order is jumped to execute until the starting point of the performance degradation of the bearing to be tested is determined.
4. The method for detecting the starting point of bearing performance degradation according to claim 3, characterized in that: Determining a time corresponding to a last correlation coefficient higher than the preset threshold among a plurality of correlation coefficients continuously higher than the preset threshold as a reset time, comprising: If after multiple correlation coefficients continuously lower than the preset threshold, there are multiple groups of correlation coefficients continuously higher than the preset threshold, the last group of the multiple groups of correlation coefficients continuously higher than the preset threshold is determined, and the moment corresponding to the last correlation coefficient in the last group of multiple correlation coefficients continuously higher than the preset threshold is determined as the reset moment.
5. The method for detecting the starting point of bearing performance degradation according to any one of claims 1 to 3, characterized in that: After respectively calculating the correlation between the vibration characteristics at each moment and the vibration characteristics at the next moment to obtain the correlation coefficient corresponding to each moment, the method further includes: Based on the correlation coefficients corresponding to all moments, an average value of the correlation coefficients is determined; The preset threshold is obtained according to the average value of the correlation coefficient.
6. The method for detecting the starting point of bearing performance degradation according to any one of claims 1 to 3, characterized in that: Feature extraction is performed on the vibration signal to obtain vibration features at different times, including: The vibration signal is feature extracted using a pre-trained autoencoder model to obtain vibration features at different times; the pre-trained autoencoder model is used to extract the vibration features of the vibration signal.
7. The method for detecting the starting point of bearing performance degradation according to any one of claims 1 to 3, characterized in that: The step of respectively calculating the correlation between the vibration characteristics at each moment and the vibration characteristics at the next moment to obtain the correlation coefficient corresponding to each moment includes: according to Calculate the correlation between the vibration characteristics at each moment and the vibration characteristics at the next moment respectively, and obtain the correlation coefficient corresponding to each moment; in, express The correlation coefficient corresponding to the time, Indicates the amount of vibration information in the vibration feature, express The vibration characteristics of the moment Vibration information, express The average vibration information of the vibration characteristics at the moment, express The vibration characteristics of the moment Vibration information, express The average vibration information of the vibration characteristics at that moment.
8. A device for detecting the starting point of bearing performance degradation, characterized in that: include: An extraction module is used to obtain the vibration signals of the bearing to be tested at different times, and perform feature extraction on the vibration signals to obtain vibration features at different times; A calculation module is used to calculate the correlation between the vibration characteristics at each moment and the vibration characteristics at the next moment, and obtain the correlation coefficient corresponding to each moment; the correlation coefficient corresponding to each moment is used to characterize the correlation between the vibration characteristics at this moment and the vibration characteristics at the next moment; Detection module for: Determine, in chronological order, from the correlation coefficients corresponding to all moments, the first plurality of correlation coefficients that are continuously lower than a preset threshold; The performance degradation starting point of the bearing to be tested is determined based on a time next to the time corresponding to the last correlation coefficient among the multiple correlation coefficients that is lower than a preset threshold.
9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the steps of the method for detecting the starting point of performance degradation of a bearing as described in any one of claims 1 to 7 are implemented.
10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the steps of the method for detecting the starting point of performance degradation of a bearing as described in any one of claims 1 to 7 are implemented.
