A three-source heterogeneous signal fusion method and system for spring failure detection

Abstract

The application discloses a three-source heterogeneous signal fusion system and method for detecting clamp spring faults, and relates to the technical fields of mechanical state monitoring, fault diagnosis and signal processing. The method comprises the following steps: acquiring vibration signals, microphone sound signals and acoustic emission signals of a clamp spring in a running process, a vibration process, a loading process or a fault detection process; respectively pre-processing the vibration signals, the microphone sound signals and the acoustic emission signals to obtain corresponding pre-processed continuous signals and reference characteristic sequences; estimating time offset amounts and time aligning of the three types of heterogeneous signals based on the reference characteristic sequences; generating a synchronous slice index table according to a unified time axis, and synchronously slicing the three types of heterogeneous signals according to the synchronous slice index table; fusing the three types of characteristics according to the same sample identifier to form a fusion characteristic vector; and outputting a state recognition result, an abnormality detection result or a fault discrimination result of the clamp spring based on the fusion characteristic vector.

Description

Technical Field

[0001] This invention relates to the field of mechanical condition monitoring and signal processing technology, and in particular to a three-source heterogeneous signal fusion method and system for snap ring fault detection. Background Technology

[0002] Snap rings, as common fastening and limiting components in mechanical assembly, are widely used in shaft connections, slot positioning, and constraints on rotating parts. Under long-term operation, high speed, alternating loads, impact, or complex vibration environments, snap rings are prone to loosening, wear, localized cracks, abnormal pre-fracture development, and failure. Once a snap ring fails, it may lead to component detachment, connection instability, or equipment downtime, thereby affecting system safety and reliability.

[0003] Existing methods for detecting the condition of snap rings mostly employ a single signal source for analysis. For example, they may use vibration signals to monitor overall dynamic changes, acoustic signals to detect external acoustic anomalies, or acoustic emission signals to capture local transient damage. While a single signal source can reflect a certain aspect of the snap ring's condition, its characterization capabilities are limited: vibration signals are more suitable for describing the overall structural response and are not sensitive enough to minor early damage; microphone acoustic signals are easily affected by environmental noise; and while acoustic emission signals can sensitively characterize local friction, impact, and crack initiation, high-frequency signals are complex and lack stability. Summary of the Invention

[0004] The purpose of this invention is to provide a three-source heterogeneous signal fusion method and system for snap ring fault detection, which solves the problems of incomplete information from a single signal source, inconsistent timing of multiple heterogeneous signals, inconsistent slicing, and difficulty in effectively fusing features in existing snap ring fault detection methods.

[0005] To achieve the above objectives, the present invention is implemented through the following technical solution: This application provides a three-source heterogeneous signal fusion method for snap ring fault detection, including the following steps: S1. Acquire the vibration signal, microphone sound signal, and acoustic emission signal of the snap ring mounted on the rotating shaft under rotating conditions; S2. Convert the vibration signal, microphone sound signal and acoustic emission signal into standard three-source continuous signals, the three-source continuous signals including a time series and one or more amplitude series, and record the sampling rate and effective duration of each signal source; S3. Extract a unified effective time period from the three-source continuous signal data to obtain the corresponding vibration continuous signal, microphone continuous signal and acoustic emission continuous signal; S4. Preprocess the vibration continuous signal, microphone continuous signal and acoustic emission continuous signal respectively, and generate their respective reference feature sequences; S5. Estimate the time offset between the three source signals based on the reference feature sequence, and establish a unified time axis accordingly; S6. Generate a synchronous slice index table according to the unified time axis, and perform synchronous slicing on the vibration continuous signal, microphone continuous signal and acoustic emission continuous signal according to the synchronous slice index table to obtain vibration slice, microphone sound signal slice and acoustic emission slice; S7. Extract the features of the vibration slice, microphone sound signal slice and acoustic emission slice respectively to obtain vibration features, microphone features and acoustic emission features; S8. The vibration features, microphone features, and acoustic emission features are fused according to the same sample identifier to form a fused feature vector.

[0006] Furthermore, in the method of this application, step S2, the standardization process includes: uniformly converting the three types of original signals into a standard continuous signal format containing time columns and amplitude columns.

[0007] Furthermore, in the method of this application, step S3, the unified effective time period truncation includes: trimming the three continuous signals within the same preset time interval, and resetting the trimmed time axis to a relative time axis starting from zero.

[0008] Furthermore, in the method of this application, step S4, the preprocessing of the continuous vibration signal includes: mean removal processing and bandpass filtering, and further generating a root mean square sequence and / or envelope sequence as a reference feature sequence of the vibration signal.

[0009] Furthermore, in the method of this application, the vibration signal includes a multi-axis vibration signal acquired by two vibration sensors. The multi-axis vibration signal includes the X-axis, Y-axis and Z-axis signals of the first vibration sensor and the X-axis, Y-axis and Z-axis signals of the second vibration sensor. The vibration signals of each axis are preprocessed separately, and a unified vibration reference feature sequence is generated based on the sliding root mean square sequence of the vibration signals of each axis. Furthermore, in the method of this application, in step S4, Preprocessing of the microphone continuous signal includes: mean removal and bandpass filtering, and further generating a short-time energy sequence and / or envelope sequence as a reference feature sequence for the microphone acoustic signal; Preprocessing of the continuous acoustic emission signal includes mean removal, high-frequency bandpass filtering, and envelope extraction. The extracted envelope sequence is then used as a reference feature sequence for the acoustic emission signal.

[0010] Furthermore, in the method of this application, in step S5, the time offset estimation adopts the cross-correlation analysis method to calculate the correlation of the reference feature sequence to obtain the time offset of each signal source relative to the reference signal source. Before performing the cross-correlation analysis, the three types of reference feature sequences are resampled to a unified reference sampling rate.

[0011] Furthermore, in the method of this application, in step S6, the synchronization slice index table includes at least sample identifier sample_id, group identifier group_id, synchronization start time start_time_sync_s, synchronization end time end_time_sync_s, and sample label; the synchronization slice index table is generated within the common effective time interval of the three sources according to a preset window length and a preset step size, and the common effective time interval is determined jointly based on the effective duration of the three source signals, a unified time reference, and the start and end times that each signal source can cover.

[0012] Furthermore, in the method of this application, in step S7, six representative features are extracted for each type of signal source. The six representative features include root mean square value, peak value, peak-to-peak value, kurtosis, envelope energy or short-time energy, and spectral centroid or frequency band energy ratio.

[0013] A three-source heterogeneous signal fusion system for snap ring fault detection, characterized in that it includes: The three-source signal acquisition module is used to acquire vibration signals, microphone sound signals, and acoustic emission signals of the snap ring during operation, vibration, loading, or fault detection. The standardization processing module is used to standardize the three types of signals to obtain three-source continuous signal data in a unified format; The preprocessing module is used to perform unified effective time segmentation and preprocessing on the three-source continuous signal data, and generate their respective reference feature sequences; The time alignment module is used to estimate the time offset between the three source signals based on the reference feature sequence and to establish a unified time axis; The synchronization slicing module is used to generate a synchronization slicing index table based on the unified time axis, and to perform synchronization slicing on the three types of signals according to the synchronization slicing index table; The feature extraction module is used to extract features from vibration slices, microphone slices, and acoustic emission slices; The feature fusion module is used to fuse vibration features, microphone features, and acoustic emission features according to the same sample identifier to form a fused feature vector; The discrimination output module is used to output the status recognition result, anomaly detection result, or fault discrimination result of the snap ring based on the fused feature vector.

[0014] Compared with the prior art, the present invention has at least the following beneficial effects: This application provides a three-source heterogeneous signal fusion method and system for snap ring fault detection. On the one hand, it can simultaneously utilize vibration signals, microphone sound signals, and acoustic emission signals to jointly characterize the snap ring state, improving information integrity. On the other hand, unlike general feature extraction and fusion methods, it extracts features from each source separately and directly concatenates them into a long vector. The core of the method described in this application lies in first unifying the three sources as standard continuous signals, then generating a reference feature sequence, calculating the time offset through normalized cross-correlation under a unified reference sampling rate, determining the common effective time interval, and generating a synchronization slice index table containing slice identifiers, synchronization start and end times, and start and end sampling points of the three sources. Finally, it uses this index table as a constraint for window slicing, feature extraction, and fusion discrimination. This ensures that the three source signals originate from the same physical event, solving problems such as different sampling rates, different start times, different effective time periods, and unstable signal quality among the signal sources, significantly improving the physical interpretability and robustness of the fusion discrimination.

[0015] Furthermore, the method of this application uses sensitive reference sequences for alignment, such as: a sliding root mean square sequence for vibration, a short-time energy sequence for microphones, and an envelope sequence for AE, rather than simply aligning the original waveform, which makes the alignment result closer to the real abnormal event.

[0016] Meanwhile, the method in this application first performs reliability-weighted cross-correlation time offset estimation, and then constructs consistency error using the offset closed-loop relationship between the three sources to correct abnormal offset estimation. It is not a simple pairwise alignment, but uses the closed-loop relationship between the three sources to correct the offset to improve stability. It is suitable for heterogeneous signal scenarios with inconsistent sampling rates, asynchronous start, and obvious local anomalies.

[0017] Furthermore, the fusion of three-source features can improve the accuracy and robustness of snap ring fault detection and status recognition. Attached Figure Description

[0018] Figure 1 This is a flowchart of a three-source heterogeneous signal fusion method for snap ring fault detection in an embodiment of this application; Figure 2 This is a diagram showing the original waveforms of the three-source signals in the embodiments of this application; Figure 3 This is a flowchart of the three-source signal preprocessing and reference feature sequence generation in an embodiment of this application; Figure 4 This is a schematic diagram of the three-source reference feature sequence in an embodiment of this application; Figure 5 This is a schematic diagram of time offset estimation in an embodiment of this application; Figure 6This is a flowchart illustrating the time offset estimation and unified time axis establishment in the embodiments of this application; Figure 7 This is a schematic diagram of synchronous slicing in an embodiment of this application; Figure 8 This is a schematic diagram of representative sensitive features in the embodiments of this application; Figure 9 This is a schematic diagram of the Euclidean distance method discrimination result in the embodiments of this application; Figure 10 This is a heatmap of the three-source fusion features in the embodiments of this application; Figure 11 This is a structural diagram of a three-source heterogeneous signal fusion system for snap ring fault detection in an embodiment of this application. Detailed Implementation

[0019] like Figure 1 As shown, this embodiment provides a three-source heterogeneous signal fusion method for snap ring fault detection, including the following steps: S1. Obtain the snap ring mounted on the rotating shaft under rotating conditions. Figure 2 The vibration signal VIB, microphone sound signal MIC, and acoustic emission signal AE are shown. The rotational speed in the rotating condition is a high-speed condition that is not lower than a preset speed threshold; the high-speed condition includes at least one of 27,500 rpm, 30,000 rpm and 32,500 rpm.

[0020] S2. The vibration signal, microphone sound signal and acoustic emission signal are uniformly formatted and converted into standard continuous signals. The standard continuous signal includes a time series and one or more amplitude series, and the sampling rate and effective duration of each signal source are recorded. In step S2, the standardization process includes converting the three types of original signals into a standard continuous signal format containing a time column (time_s) and an amplitude column (amplitude). In step S2, the time column of the standard continuous signal is time_s, and the one or more amplitude columns are used to record the sampling amplitude of the corresponding signal source; wherein, acoustic emission signals and microphone sound signals include single-channel amplitude columns, and vibration signals include one or more vibration channel amplitude columns.

[0021] S3. The three-source continuous signal data are truncated to a unified effective time period to eliminate invalid initial segments, pause segments, or background-irrelevant segments. This yields the corresponding continuous vibration signal, continuous microphone signal, and continuous acoustic emission signal. In step S3, the unified effective time period truncation includes: trimming the three continuous signals within the same preset time interval, and resetting the trimmed time axis to a relative time axis starting from zero.

[0022] S4, such as Figure 3 and 4 As shown, the vibration continuous signal, microphone continuous signal, and acoustic emission continuous signal are preprocessed respectively, and their respective reference feature sequences are generated; Step S4 involves preprocessing the continuous vibration signal, including mean removal and bandpass filtering, and further generating a root mean square sequence and / or envelope sequence as a reference feature sequence for the vibration signal. The vibration signal includes multi-axis vibration signals acquired by two vibration sensors, comprising the X, Y, and Z axis signals from the first vibration sensor and the X, Y, and Z axis signals from the second vibration sensor. Step S4 preprocesses the vibration signals for each axis separately and generates a unified vibration reference feature sequence based on the sliding root mean square sequences of the vibration signals for each axis.

[0023] In step S4, the preprocessing of the microphone continuous signal includes: mean removal and bandpass filtering, and further generating a short-time energy sequence and / or envelope sequence as a reference feature sequence of the microphone acoustic signal.

[0024] In step S4, the preprocessing of the acoustic emission continuous signal includes: mean removal, high-frequency bandpass filtering, and envelope extraction, and the extracted envelope sequence is used as the reference feature sequence of the acoustic emission signal.

[0025] In this embodiment, let the vibration, microphone, and acoustic emission signals be x, respectively. v (t), x m (t), x a (t).

[0026] Its mathematical expression is as follows: in: R v[n] : The vibration reference characteristic sequence value corresponding to the nth sampling point or the nth analysis time; K: Number of vibration channels; K: Vibration channel number; L: Length of the sliding window; J: The sampling point number within the sliding window; x v,k [nj]: The vibration amplitude of the k-th vibration channel at position nj; R m[n] : Short-time energy reference sequence value of microphone acoustic signal; x m [nj]: The amplitude of the microphone sound signal at location nj; R a[n] : The envelope reference sequence value of the acoustic emission signal; x a[n] : The amplitude of the acoustic emission signal at the nth sampling point; H{·}: Hilbert transform; S5. Estimate the time offset between the three source signals based on the reference feature sequence, and establish a unified time axis accordingly. Therefore, this application does not directly align the original signals, but aligns the reference feature sequence which is more sensitive to snap ring faults, thereby significantly improving the time consistency of multi-source signals at the fault feature level.

[0027] In step S5, the time offset estimation employs cross-correlation analysis to calculate the correlation of the reference feature sequences, thereby obtaining the time offset of each signal source relative to the reference signal source. Before performing the cross-correlation analysis, the three types of reference feature sequences are resampled to a unified reference sampling rate to address the issues of different sampling rates and time resolutions among the three signal sources.

[0028] Unified reference sampling rate resampling: Map the three types of reference feature sequences to a unified reference sampling rate f. r This allows for the comparison of three-source responses with different sampling rates and time resolutions on the same discrete-time reference. Its mathematical expression is as follows: in: R i : The reference characteristic sequence of the i-th type of signal source; : The reference feature sequence after resampling; p represents the discrete sampling point number under the uniform reference sampling rate; f r Unified reference sampling rate; i∈{v,m,a}: vibration signal, microphone sound signal, and acoustic emission signal.

[0029] Reliability-weighted cross-correlation time skew estimation: Using the acoustic emission signal as a reference source, a reliability-weighted normalized cross-correlation is calculated for i∈{v,m}, and the time offset is determined based on the peak value of the cross-correlation. Its mathematical expression is as follows: in: The lag corresponding to the attainment of the maximum value. i: The signal source number to be aligned, which can be v or m; v represents the vibration signal, and m represents the microphone sound signal.

[0030] a: Reference signal source, representing acoustic emission signal.

[0031] w: Weighting identifier, indicating that reliability weights are introduced in the cross-correlation calculation.

[0032] Discrete hysteresis or offset points are used to represent the relative shift between two reference feature sequences.

[0033] p: Index of discrete-time sampling points.

[0034] wᵢ[p]: The reliability weight of the i-th signal source at the p-th sampling point. It can be determined based on local energy, signal-to-noise ratio, kurtosis, impulse intensity, or alignment confidence. The larger the value, the higher the reliability of the signal segment corresponding to the sampling point and the greater its contribution to the cross-correlation calculation.

[0035] : The value of the reference feature sequence after resampling from the i-th signal source at the p-th sampling point.

[0036] Acoustic emission reference feature sequence in offset The next The value at each sampling point.

[0037] : The mean of the reference feature sequence resampled from the i-th signal source.

[0038] : The mean of the acoustic emission reference feature sequence.

[0039] Estimate the time offsets between vibration-acoustic emission, microphone-acoustic emission, and vibration-microphone, respectively. in: Δtᵢ represents the time offset of the i-th signal source relative to the reference acoustic emission signal source.

[0040] fᵣ: Uniform reference sampling rate.

[0041] 1 / fᵣ: Uniform reference sampling period.

[0042] : Represents the reliability-weighted cross-correlation coefficient.

[0043] The formula means finding the number of lag points that maximizes the weighted cross-correlation coefficient and converting that number of lag points into the actual time offset.

[0044] Utilizing the offset closed-loop relationship between the three sources: Δt v,mThe time offset of the vibration signal relative to the microphone sound signal.

[0045] Δt v,a The time offset of the vibration signal relative to the acoustic emission signal.

[0046] Δt m,a The time offset of the microphone sound signal relative to the sound emission signal.

[0047] Constructing consistency error: e=|Δt v,m -(Δt v,a -Δt m,a )| If the three-source offset estimates are completely consistent, then the following should be satisfied: At this point, e is very small; if there is a discrepancy, e will become larger. This is used to correct for outlier estimates.

[0048] When the consistency error exceeds a preset threshold, the offset is reselected or corrected based on the cross-correlation peak value, alignment confidence, and closed-loop consistency constraints, such as... Figure 5 As shown, the corrected Δt is obtained. v * , Δt m * and Δt a * =0.

[0049] S6, such as Figure 6 and Figure 7 As shown, a synchronous slice index table is generated according to the unified time axis, and the vibration continuous signal, microphone continuous signal and acoustic emission continuous signal are synchronously sliced ​​according to the synchronous slice index table to obtain vibration slice, microphone sound signal slice and acoustic emission slice; In step S6, the synchronization slice index table includes at least sample identifier sample_id, group identifier group_id, synchronization start time start_time_sync_s, synchronization end time end_time_sync_s, and sample label.

[0050] In step S6, the synchronous slice index table is generated within the common effective time interval of the three sources according to the preset window length and preset step size.

[0051] The common effective time interval is determined based on the effective duration of the three source signals, the unified time reference, and the start and end times that each signal source can cover, so that the acoustic emission synchronization segment, vibration synchronization segment, and microphone synchronization segment under the same segment_id correspond to the same time window.

[0052] The specific mathematical expression is as follows: Establish a unified time axis based on the corrected time offset: t i syncd =t i -Δt i * in: t i : The original time axis of the i-th signal source.

[0053] t i sync : Synchronization time axis after correction of the i-th signal source.

[0054] Δt i * : The time offset of the i-th signal source after correction by the three-source consistency constraint.

[0055] Common effective interval: in: T start The start time of the common effective time interval after the three source signals are synchronized.

[0056] T end : The end time of the common effective time interval after the three source signals are synchronized.

[0057] min(t i sync ): The earliest valid time for synchronizing the time axis of the i-th signal source.

[0058] max(t i sync ): The latest valid time for synchronizing the time axis of the i-th signal source.

[0059] Take the maximum value among all signal sources.

[0060] : Take the minimum value among all signal sources.

[0061] Synchronous window: start q =T start +qS end q =start q +W in: q: Synchronous slice window number, which can also correspond to the sample number.

[0062] start q: The start time of the q-th synchronized slice window.

[0063] end q : The end time of the q-th synchronized slice window.

[0064] S: Sliding step size.

[0065] W: Slice window length.

[0066] T start : The start time of the common valid time interval.

[0067] S7. Extract the features of the vibration slice, microphone sound signal slice and acoustic emission slice respectively to obtain vibration features, microphone features and acoustic emission features; For each type of signal source, six representative features are extracted. The six representative features (F1 to F6) include root mean square value, peak value, peak-to-peak value, kurtosis, envelope energy or short-time energy, and spectral centroid or frequency band energy percentage.

[0068] The root mean square value is used to reflect the overall energy intensity of the signal; The peak value is used to reflect the transient impact intensity; Peak-to-peak value is used to reflect the range of signal amplitude fluctuation; Kurtosis is used to reflect whether there are spikes, impulsive movements, or non-stationary abrupt changes in a signal. Envelope energy or short-time energy is used to reflect the accumulation and continuous enhancement of signal energy over time. VIB prioritizes envelope energy, MIC prioritizes short-time energy, and AE prioritizes envelope energy or high-frequency energy. The spectral centroid or frequency band energy percentage is used to reflect changes in frequency structure.

[0069] Among them, the characteristics of vibration signals are mainly used to characterize the overall dynamic response and amplitude disturbance of the snap ring; the characteristics of microphone acoustic signals are mainly used to characterize acoustic energy changes and abnormal noise response; and the characteristics of acoustic emission signals are mainly used to characterize local contact, friction, impact, or high-frequency transient events.

[0070] like Figure 8 As shown, different sample segments exhibit significant differences in F1 to F6, and the color distribution of the three source feature matrices differs, indicating that the state information captured by the three is complementary.

[0071] In one embodiment, such as Figure 9 As shown, representative sensitive features (the first feature F1 among acoustic emission features, vibration features, and microphone features) within the three sources were selected, and a Euclidean distance threshold was used for normal / damaged identification. The results show that when relying on only a few sensitive features and a single distance threshold, weakly damaged samples are easily misclassified as normal (accuracy rate 83.33%).

[0072] To improve the accuracy of the discrimination, this embodiment also includes the following steps: S8. The vibration features, microphone features, and acoustic emission features are fused according to the same sample identifier to form a fused feature vector; In step S8, the fusion is feature-level fusion, which involves splicing together the vibration features, microphone features, and acoustic emission features corresponding to the same sample identifier to form a fused feature vector.

[0073] In real-world applications, it's common to encounter situations where one source has significantly higher noise levels, a source has low reliability within a given time window, or a source may have a signal but not necessarily warrant equal weighting in the fusion process. To address this, this embodiment employs a weighted fusion of the three source features based on reliability. The weights are determined by alignment confidence or signal quality. This is not a simple feature concatenation but rather a weighted fusion based on alignment confidence or signal quality. The mathematical expression for this is as follows: F q =[β v F v,q ,β m F m,q ,β a F a,q ] in: in: F q : The three-source fusion feature vector corresponding to the q-th synchronous slice.

[0074] F v,q : Vibration signal feature vector of the qth synchronous slice.

[0075] F m,q : The microphone acoustic signal feature vector of the q-th synchronization slice.

[0076] F a,q : The acoustic emission signal feature vector of the q-th synchronization slice.

[0077] β v : Vibration signal feature fusion weights.

[0078] β m : Weighting of microphone acoustic signal features.

[0079] β a : Weighting of acoustic emission signal features.

[0080] β i : Normalized fusion weights of the i-th signal source.

[0081] C i: The reliability evaluation value or alignment confidence of the i-th signal source.

[0082] C v : Reliability evaluation value of vibration signal.

[0083] C m : Reliability evaluation value of microphone acoustic signal.

[0084] C a : Reliability evaluation value of acoustic emission signal.

[0085] ε: A very small positive number used to prevent the denominator from being zero and to improve numerical stability.

[0086] Wherein, βi is calculated by normalization based on the reliability evaluation value or alignment confidence of the corresponding signal source. The larger Ci is, the higher the reliability of the i-th signal source in the current sample or the current time window, and the greater the contribution of its features to the fused feature vector.

[0087] Compared to the Euclidean distance method, the accuracy of Mahalanobis distance recognition with fused features is significantly improved.

[0088] Example 2 Based on Embodiment 1, this embodiment provides a three-source heterogeneous signal fusion system for snap ring fault detection, comprising: a three-source signal acquisition module for acquiring vibration signals, microphone sound signals, and acoustic emission signals of the snap ring during operation, vibration, loading, or fault detection; a standardization processing module for standardizing the three types of signals to obtain three-source continuous signal data in a unified format; a preprocessing module for uniformly extracting and preprocessing the three-source continuous signal data into a unified effective time period and generating their respective reference feature sequences; a time alignment module for estimating the time offset between the three-source signals based on the reference feature sequences and establishing a unified time axis; a synchronous slicing module for generating a synchronous slicing index table based on the unified time axis and synchronously slicing the three types of signals according to the synchronous slicing index table; a feature extraction module for extracting features from vibration slices, microphone slices, and acoustic emission slices; a feature fusion module for fusing vibration features, microphone features, and acoustic emission features according to the same sample identifier to form a fused feature vector; and a discrimination output module for outputting snap ring status identification results, anomaly detection results, or fault discrimination results based on the fused feature vector. In addition, the time alignment module uses cross-correlation analysis to estimate the time offset, and the synchronization slice index table generated by the synchronization slice module includes at least the sample identifier, group identifier, synchronization start time and synchronization end time.

Claims

1. A three-source heterogeneous signal fusion method for snap ring fault detection, characterized in that, Includes the following steps: S1. Acquire the three-source signals of the snap ring installed on the rotating shaft under rotation conditions. The three-source signals include vibration signal, microphone sound signal and acoustic emission signal. S2. Convert the vibration signal, microphone sound signal and acoustic emission signal into standard three-source continuous signals, the three-source continuous signals including a time series and one or more amplitude series, and record the sampling rate and effective duration of each signal source; S3. Extract a unified effective time period from the three-source continuous signal data to obtain the corresponding vibration continuous signal, microphone continuous signal and acoustic emission continuous signal; S4. Preprocess the vibration continuous signal, microphone continuous signal and acoustic emission continuous signal respectively, and generate their respective reference feature sequences; S5. Estimate the time offset between the three source signals based on the reference feature sequence, and establish a unified time axis accordingly; S6. Generate a synchronous slice index table according to the unified time axis, and perform synchronous slicing on the vibration continuous signal, microphone continuous signal and acoustic emission continuous signal according to the synchronous slice index table to obtain vibration slice, microphone sound signal slice and acoustic emission slice; S7. Extract the features of the vibration slice, microphone sound signal slice and acoustic emission slice respectively to obtain vibration features, microphone features and acoustic emission features; S8. The vibration features, microphone features, and acoustic emission features are fused according to the same sample identifier to form a fused feature vector.

2. The three-source heterogeneous signal fusion method for snap ring fault detection according to claim 1, characterized in that, In step S2, the standardization process includes: converting the three types of original signals into a standard continuous signal format containing time columns and amplitude columns, wherein the one or more amplitude columns are used to record the sampling amplitude of the corresponding signal source; wherein, the acoustic emission signal and the microphone sound signal include a single-channel amplitude column, and the vibration signal includes one or more vibration channel amplitude columns.

3. The three-source heterogeneous signal fusion method for snap ring fault detection according to claim 1, characterized in that, In step S3, the unified effective time period truncation includes: trimming the three continuous signals within the same preset time interval, and resetting the trimmed time axis to a relative time axis starting from zero.

4. The three-source heterogeneous signal fusion method for snap ring fault detection according to claim 1, characterized in that, In step S4, the preprocessing of the continuous vibration signal includes: mean removal and bandpass filtering, and further generating a root mean square sequence and / or envelope sequence as a reference feature sequence of the vibration signal; Preprocessing of the microphone continuous signal includes: mean removal and bandpass filtering, and further generating a short-time energy sequence and / or envelope sequence as a reference feature sequence for the microphone acoustic signal; Preprocessing of the continuous acoustic emission signal includes mean removal, high-frequency bandpass filtering, and envelope extraction. The extracted envelope sequence is then used as a reference feature sequence for the acoustic emission signal.

5. The three-source heterogeneous signal fusion method for snap ring fault detection according to claim 1, characterized in that, in, The vibration signal includes multi-axis vibration signals acquired by two vibration sensors. The multi-axis vibration signal includes the X-axis, Y-axis and Z-axis signals of the first vibration sensor and the X-axis, Y-axis and Z-axis signals of the second vibration sensor. In step S4, the vibration signals of each axis are preprocessed respectively, and a unified vibration reference feature sequence is generated based on the sliding root mean square sequence of the vibration signals of each axis.

6. The three-source heterogeneous signal fusion method for snap ring fault detection according to claim 1, characterized in that, In step S5, the time offset estimation adopts the cross-correlation analysis method to calculate the correlation of the reference feature sequence to obtain the time offset of each signal source relative to the reference signal source. Before performing cross-correlation analysis, the three types of reference feature sequences are resampled to a uniform reference sampling rate.

7. The three-source heterogeneous signal fusion method for snap ring fault detection according to claim 1, characterized in that, In step S6, the synchronization slice index table includes at least sample identifier, group identifier, synchronization start time, synchronization end time, and sample label; the synchronization slice index table is generated within the common effective time interval of the three sources according to a preset window length and a preset step size. The common effective time interval is determined based on the effective duration of the three source signals, a unified time reference, and the start and end times that each signal source can cover.

8. The three-source heterogeneous signal fusion method for snap ring fault detection according to claim 1, characterized in that, Representative features are extracted for each type of signal source. These representative features include root mean square value, peak value, peak-to-peak value, kurtosis, envelope energy or short-time energy, and spectral centroid or frequency band energy percentage.

9. A three-source heterogeneous signal fusion system for snap ring fault detection, characterized in that, include: The three-source signal acquisition module is used to acquire vibration signals, microphone sound signals, and acoustic emission signals of the snap ring during operation, vibration, loading, or fault detection. The standardization processing module is used to standardize the three types of signals to obtain three-source continuous signal data in a unified format; The preprocessing module is used to perform unified effective time segmentation and preprocessing on the three-source continuous signal data, and generate their respective reference feature sequences; The time alignment module is used to estimate the time offset between the three source signals based on the reference feature sequence and to establish a unified time axis; The synchronization slicing module is used to generate a synchronization slicing index table based on the unified time axis, and to perform synchronization slicing on the three types of signals according to the synchronization slicing index table; The feature extraction module is used to extract features from vibration slices, microphone slices, and acoustic emission slices; The feature fusion module is used to fuse vibration features, microphone features, and acoustic emission features according to the same sample identifier to form a fused feature vector.

Images