Fault detection method, system and equipment of optical fiber gyroscope and storage medium

Abstract

The invention belongs to the technical field of fault detection, and discloses a fault detection method, system and device of an optical fiber gyroscope and a storage medium, the method comprises the following steps: obtaining historical operation parameters of the optical fiber gyroscope during normal operation, and preprocessing the historical operation parameters to obtain an operation parameter sample set; performing clustering processing on the operation parameter sample set based on a preset clustering algorithm to obtain a plurality of normal behavior clusters; acquiring real-time operation parameters of the optical fiber gyroscope, and performing anomaly analysis on the real-time operation parameters based on the normal behavior cluster to obtain an anomaly analysis result; based on the abnormal analysis result and a pre-constructed fault occurrence condition, judging whether the optical fiber gyroscope has a fault or not, and if so, generating fault early warning information; and carrying out visual display on the fault early warning information. According to the method, the fault condition of the optical fiber gyroscope in the operation process can be accurately and quickly found, the optical fiber gyroscope can be conveniently calibrated and served in the later period, and the reliability of the optical fiber gyroscope in the operation process is improved.

Description

Technical Field

[0001] This invention belongs to the field of fault detection technology, specifically relating to a fault detection method, system, device, and storage medium for a fiber optic gyroscope. Background Technology

[0002] A fiber optic gyroscope (FOG) is an inertial sensor based on optical principles used to measure and detect the rotation of an object. It utilizes the optical properties and interference effects of optical fibers to measure angular velocity. The main characteristics of a fiber optic gyroscope are its simple structure, small size, light weight, and the absence of rotating and frictional components, resulting in a long lifespan and a wide dynamic range. Furthermore, its instantaneous start-up and stability are also important features.

[0003] The working principle of a fiber optic gyroscope is based on the Sagnac effect. In a closed optical path, two beams of light emitted from the same source propagate relative to each other and converge at the same detection point, producing interference. When this closed optical path rotates, the optical path lengths of the two beams will differ, allowing the measurement of the rotational angular velocity.

[0004] In practical applications, fiber optic gyroscopes may experience different types of faults, such as hardware-related faults like contamination of optical components, fiber breakage, and laser source aging, as well as faults caused by factors like zero-point drift, temperature changes, random noise, and electromagnetic interference. These faults may exhibit different characteristics, making it difficult to universally apply fault detection algorithms and accurately and quickly detect faults in fiber optic gyroscopes. Summary of the Invention

[0005] The purpose of this invention is to provide a fault detection method, system, device, and storage medium for fiber optic gyroscopes, in order to solve the problem that different types of faults may occur in the practical application of fiber optic gyroscopes, and these faults may exhibit different characteristics, making it difficult to universally apply fault detection algorithms and to accurately and quickly detect faults in fiber optic gyroscopes.

[0006] To achieve the above objectives, the present invention adopts the following technical solution:

[0007] In a first aspect, the present invention provides a fault detection method for a fiber optic gyroscope, the method comprising:

[0008] The historical operating parameters of the fiber optic gyroscope during normal operation are obtained, and the historical operating parameters are preprocessed to obtain a sample set of operating parameters;

[0009] The sample set of running parameters is clustered based on a preset clustering algorithm to obtain several normal behavior clusters;

[0010] The real-time operating parameters of the fiber optic gyroscope are obtained, and anomaly analysis is performed on the real-time operating parameters based on the normal behavior cluster to obtain the anomaly analysis results.

[0011] Based on the anomaly analysis results and the pre-constructed fault occurrence conditions, it is determined whether the fiber optic gyroscope will malfunction; if so, a fault warning message is generated.

[0012] The fault warning information is displayed visually.

[0013] Preferably, the preprocessing includes at least: data cleaning, standardization, normalization, filtering, and dimensionality reduction.

[0014] Preferably, the preset clustering algorithm is the K-means clustering algorithm. Based on the preset clustering algorithm, the sample set of operating parameters is clustered to obtain several normal behavior clusters, including:

[0015] A cluster set is constructed based on the sample set of running parameters. The cluster set includes at least one sub-cluster. The sum of squared errors of the cluster set is calculated. The sub-cluster corresponding to the maximum sum of squared errors is selected from the cluster set as the cluster to be clustered.

[0016] Find two center points for the cluster to be clustered. The two center points are the two data points with the largest distance between them in the cluster to be clustered. Each data point corresponds to a historical running parameter.

[0017] Based on the K-means clustering algorithm, the clusters to be clustered are locally clustered with two centroids as cluster centers to obtain two new clusters. The two new clusters are then added to the cluster set as new sub-clusters.

[0018] Recalculate the sum of squared errors of the clusters and reselect the clusters to be clustered until the number of subclusters in the clusters reaches the preset number;

[0019] Based on the K-means clustering algorithm, a preset number of centroids are used as initial centers to perform global clustering on the sample dataset, resulting in several normal behavior clusters and the cluster center corresponding to each normal behavior cluster.

[0020] Preferably, anomaly analysis is performed on real-time operating parameters based on normal behavior clusters to obtain anomaly analysis results, including:

[0021] Calculate the distance between the real-time operating parameters and the cluster centers of each normal behavior cluster to obtain the distance set corresponding to the real-time operating parameters;

[0022] Extract the minimum distance from the distance set, determine whether the minimum distance is greater than the preset distance, and if so, mark the real-time running parameter as abnormal, and use the abnormal real-time running parameter as the abnormal analysis result.

[0023] Preferably, determining whether the fiber optic gyroscope will malfunction based on the anomaly analysis results and pre-constructed fault occurrence conditions includes:

[0024] Based on the anomaly analysis results, the difference between the minimum distance corresponding to the real-time operating parameters of the anomaly and the preset distance is calculated to obtain the distance difference;

[0025] Determine whether the distance difference exceeds a preset distance difference threshold. If so, determine that the fiber optic gyroscope will malfunction. The condition for malfunction is that the distance difference between the minimum distance and the preset distance exceeds the preset distance difference threshold.

[0026] Preferably, when the distance difference does not exceed a preset distance difference threshold, the method further includes:

[0027] Obtain the timestamp corresponding to the real-time operating parameters of the anomaly, and store and record the distance difference and timestamp corresponding to the real-time operating parameters of the anomaly.

[0028] Acquire the distance difference and timestamp recorded during the preset operation time of the fiber optic gyroscope, and construct a distance difference sequence based on the recorded distance difference and timestamp;

[0029] If a predetermined number of distance differences in the distance difference sequence show a continuously increasing trend, it is determined that the fiber optic gyroscope will malfunction; the existence of a predetermined number of distance differences in the distance difference sequence showing a continuously increasing trend is used as the condition for the malfunction to occur.

[0030] Preferably, when there is no predetermined number of distance differences in the distance difference sequence that show a continuously increasing trend, the method further includes:

[0031] The time interval corresponding to each two adjacent distance differences in the statistical distance difference sequence is greater than a preset number;

[0032] Determine whether all time intervals of the distance difference sequence show a decreasing trend. If so, determine that the fiber optic gyroscope will malfunction. The condition for malfunction is that all time intervals of the distance difference sequence show a decreasing trend.

[0033] Secondly, the present invention provides a fault detection system for a fiber optic gyroscope, used to implement the above-mentioned fault detection method for a fiber optic gyroscope, the system comprising:

[0034] The parameter acquisition module is used to acquire historical operating parameters of the fiber optic gyroscope during normal operation, preprocess the historical operating parameters, and obtain a sample set of operating parameters.

[0035] The parameter clustering module is used to cluster the sample set of running parameters based on a preset clustering algorithm to obtain several normal behavior clusters;

[0036] The anomaly analysis module is used to acquire the real-time operating parameters of the fiber optic gyroscope, perform anomaly analysis on the real-time operating parameters based on the normal behavior cluster, and obtain the anomaly analysis results.

[0037] The fault analysis module is used to determine whether the fiber optic gyroscope will malfunction based on the anomaly analysis results and pre-built fault occurrence conditions; if so, it generates fault warning information.

[0038] The early warning display module is used to visualize fault early warning information.

[0039] Thirdly, the present invention provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the above-described fault detection method for a fiber optic gyroscope.

[0040] Fourthly, the present invention provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the above-described method for fault detection of a fiber optic gyroscope.

[0041] Beneficial effects:

[0042] This invention collects historical operating parameters of a fiber optic gyroscope during normal operation, and then uses a clustering algorithm to cluster the sample set of operating parameters to obtain normal behavior clusters of different categories. These normal behavior clusters are then used to determine whether real-time operating parameters will become abnormal. Finally, based on the fault occurrence conditions, it is determined whether the occurrence of an anomaly will lead to a fault. This method can accurately and quickly detect faults in the fiber optic gyroscope during operation, facilitating subsequent calibration and servicing of the fiber optic gyroscope and improving its reliability during operation. Attached Figure Description

[0043] The accompanying drawings are provided to further illustrate embodiments of the present invention and form part of the specification. They are used together with the following detailed description to explain the embodiments of the present invention, but do not constitute a limitation thereof. In the drawings:

[0044] Figure 1 This is a flowchart of a fault detection method for a fiber optic gyroscope provided in one embodiment of the present invention;

[0045] Figure 2 This is a block diagram of a fault detection system for a fiber optic gyroscope provided in one embodiment of the present invention. Detailed Implementation

[0046] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the present invention will be briefly introduced below in conjunction with the accompanying drawings and descriptions of the embodiments or the prior art. Obviously, the following description of the structure of the accompanying drawings is only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort. It should be noted that the description of these embodiments is for the purpose of helping to understand the present invention, but does not constitute a limitation of the present invention.

[0047] Example 1

[0048] Figure 1 This is a flowchart of a fault detection method for a fiber optic gyroscope provided in one embodiment of the present invention. Figure 1 As shown, this embodiment provides a fault detection method for a fiber optic gyroscope, the method comprising:

[0049] Step S10: Obtain the historical operating parameters of the fiber optic gyroscope during normal operation, preprocess the historical operating parameters, and obtain the operating parameter sample set.

[0050] In this embodiment, the preprocessing includes at least: data cleaning, standardization, normalization, filtering, and dimensionality reduction.

[0051] Data cleaning is used to remove invalid data, repair data inconsistencies, and improve data integrity. Data cleaning includes, but is not limited to, handling missing values, detecting and correcting outliers, handling duplicate values, and standardizing formats.

[0052] Missing value handling includes: directly deleting parameter columns with more than 20% consecutive missing values, and filling short-term missing values ​​in time series using linear interpolation or seasonal decomposition (STL);

[0053] Outlier detection and correction include: identifying outliers based on the 3σ criterion or IQR (interquartile range), such as removing data points that exceed the mean ± 3 times the standard deviation, and filtering unreasonable values ​​in combination with physical constraints (such as the gyroscope angular rate range ± 2000° / s).

[0054] Duplicate value processing includes: retaining the latest value or merging the mean for consecutive duplicate records (e.g., sampling interval <10ms) in high-frequency sampled data (e.g., 100Hz);

[0055] The format standardization includes converting parameters with different dimensions (such as temperature °C, voltage V, and angular velocity ° / s) into a unified unit system (SI units) and performing timestamp interpolation and alignment on multi-source data (such as temperature, voltage, and vibration), with the error controlled within ±1ms.

[0056] Standardization is used to eliminate differences in units of measurement and make the data conform to a specific distribution assumption (such as normal distribution), such as Z-Score standardization and Min-Max standardization.

[0057] Normalization is used to compress the dynamic range of data and enhance the robustness of the algorithm. Normalization can be performed using methods such as Allan variance analysis or nonlinear mapping normalization.

[0058] Among them, filtering is used to suppress high-frequency noise (such as mechanical vibration interference) and low-frequency drift (such as temperature drift), and filtering algorithms such as wavelet transform and median average filtering can be used.

[0059] Dimensionality reduction is used to eliminate redundant features, improve computational efficiency and model generalization ability, and can employ algorithms such as principal component analysis (PCA) and random forest.

[0060] Step S20: Cluster the sample set of running parameters based on the preset clustering algorithm to obtain several normal behavior clusters.

[0061] In this embodiment, the preset clustering algorithm is the K-means clustering algorithm. Therefore, the specific execution steps for clustering the sample set of running parameters based on the preset clustering algorithm to obtain several normal behavior clusters are as follows:

[0062] Step S201: Construct a cluster set based on the sample set of running parameters. The cluster set includes at least one sub-cluster. Calculate the sum of squared errors of the cluster set. Select the sub-cluster corresponding to the maximum sum of squared errors from the cluster set as the cluster to be clustered.

[0063] Step S202: Find the two center points of the cluster to be clustered. The two center points are the two data points with the largest distance between them in the cluster to be clustered. Each data point corresponds to a historical running parameter.

[0064] Step S203: Based on the K-means clustering algorithm, perform local clustering on the clusters to be clustered with two centroids as cluster centers to obtain two new clusters, and add the two new clusters to the cluster set as new sub-clusters;

[0065] Step S204: Recalculate the sum of squared errors of the clusters and reselect the clusters to be clustered until the number of subclusters in the clusters reaches the preset number;

[0066] Step S205: Based on the K-means clustering algorithm, with a preset number of centroids as initial centers, perform global clustering on the sample dataset to obtain several normal behavior clusters and the cluster center corresponding to each normal behavior cluster.

[0067] Step S30: Obtain the real-time operating parameters of the fiber optic gyroscope, perform anomaly analysis on the real-time operating parameters based on the normal behavior cluster, and obtain the anomaly analysis results.

[0068] In this embodiment, the specific steps for performing anomaly analysis on real-time operating parameters based on normal behavior clusters to obtain the anomaly analysis results are as follows:

[0069] Step S301: Calculate the distance between the real-time operating parameters and the cluster centers of each normal behavior cluster to obtain the distance set corresponding to the real-time operating parameters;

[0070] Step S302: Extract the minimum distance from the distance set, determine whether the minimum distance is greater than the preset distance, and if so, mark the real-time running parameter as abnormal, and use the abnormal real-time running parameter as the abnormal analysis result.

[0071] Step S40: Based on the anomaly analysis results and the pre-constructed fault occurrence conditions, determine whether the fiber optic gyroscope will malfunction. If so, generate a fault warning message.

[0072] In this embodiment, the fault occurrence conditions include three conditions. When any one of these conditions is met, it indicates that the abnormal analysis result will lead to a fault. Therefore, the specific judgment methods for the three conditions are as follows:

[0073] Firstly, based on the anomaly analysis results and pre-constructed fault occurrence conditions, determine whether the fiber optic gyroscope will malfunction, including:

[0074] Step a10: Based on the anomaly analysis results, calculate the difference between the minimum distance corresponding to the real-time operating parameters of the anomaly and the preset distance to obtain the distance difference;

[0075] Step a20: Determine whether the distance difference exceeds the preset distance difference threshold. If so, determine that the fiber optic gyroscope will malfunction. The condition for malfunction is that the distance difference between the minimum distance and the preset distance exceeds the preset distance difference threshold. Therefore, the first condition is that the distance difference between the minimum distance and the preset distance exceeds the preset distance difference threshold.

[0076] Secondly, when the distance difference does not exceed a preset distance difference threshold, the method further includes:

[0077] Step b10: Obtain the timestamp corresponding to the real-time operating parameters of the anomaly, and store and record the distance difference and timestamp corresponding to the real-time operating parameters of the anomaly;

[0078] Step b20: Obtain the distance difference and timestamp recorded during the preset running time of the fiber optic gyroscope, and construct a distance difference sequence based on the recorded distance difference and timestamp;

[0079] Step b30: Determine whether there is a preset number of distance differences in the distance difference sequence that show a continuous increasing trend. If so, determine that the fiber optic gyroscope will malfunction. The presence of a preset number of distance differences in the distance difference sequence that show a continuous increasing trend is used as a malfunction condition. Therefore, the presence of a preset number of distance differences in the distance difference sequence that show a continuous increasing trend is the second condition.

[0080] Thirdly, when there is no predetermined number of distance differences in the distance difference sequence that show a continuously increasing trend, the method further includes:

[0081] Step c10: Count the time interval corresponding to each two adjacent distance differences in the distance difference sequence, wherein the number of time intervals in the distance difference sequence is greater than a preset number;

[0082] Step c20: Determine whether all time intervals of the distance difference sequence show a decreasing trend. If so, determine that the fiber optic gyroscope will malfunction. The condition for malfunction is that all time intervals of the distance difference sequence show a decreasing trend. Therefore, the condition for malfunction is that all time intervals of the distance difference sequence show a decreasing trend.

[0083] Step S50: Visualize the fault warning information.

[0084] This invention collects historical operating parameters of a fiber optic gyroscope during normal operation, and then uses a clustering algorithm to cluster the sample set of operating parameters to obtain normal behavior clusters of different categories. These normal behavior clusters are then used to determine whether real-time operating parameters will become abnormal. Finally, based on the fault occurrence conditions, it is determined whether the occurrence of an anomaly will lead to a fault. This method can accurately and quickly detect faults in the fiber optic gyroscope during operation, facilitating subsequent calibration and servicing of the fiber optic gyroscope and improving its reliability during operation.

[0085] Example 2

[0086] Figure 2 This is a block diagram of a fault detection system for a fiber optic gyroscope provided in one embodiment of the present invention. Figure 2 As shown, this embodiment provides a fault detection system for a fiber optic gyroscope, used to implement the fault detection method for the fiber optic gyroscope in Embodiment 1. The system includes:

[0087] The parameter acquisition module is used to acquire historical operating parameters of the fiber optic gyroscope during normal operation, preprocess the historical operating parameters, and obtain a sample set of operating parameters.

[0088] The parameter clustering module is used to cluster the sample set of running parameters based on a preset clustering algorithm to obtain several normal behavior clusters;

[0089] The anomaly analysis module is used to acquire the real-time operating parameters of the fiber optic gyroscope, perform anomaly analysis on the real-time operating parameters based on the normal behavior cluster, and obtain the anomaly analysis results.

[0090] The fault analysis module is used to determine whether the fiber optic gyroscope will malfunction based on the anomaly analysis results and pre-built fault occurrence conditions; if so, it generates fault warning information.

[0091] The early warning display module is used to visualize fault early warning information.

[0092] This embodiment also provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it implements the fault detection method for the fiber optic gyroscope in Embodiment 1.

[0093] This embodiment also provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the fault detection method for the fiber optic gyroscope in Embodiment 1.

[0094] This invention collects historical operating parameters of a fiber optic gyroscope during normal operation, and then uses a clustering algorithm to cluster the sample set of operating parameters to obtain normal behavior clusters of different categories. These normal behavior clusters are then used to determine whether real-time operating parameters will become abnormal. Finally, based on the fault occurrence conditions, it is determined whether the occurrence of an anomaly will lead to a fault. This method can accurately and quickly detect faults in the fiber optic gyroscope during operation, facilitating subsequent calibration and servicing of the fiber optic gyroscope and improving its reliability during operation.

[0095] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0096] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart... Figure 1 One or more processes and / or boxes Figure 1 A system that specifies functions in one or more boxes.

[0097] The above are merely embodiments of this application and are not intended to limit the scope of this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the scope of the claims of this application.

Claims

1. A fault detection method for a fiber optic gyroscope, characterized in that, The method includes: The historical operating parameters of the fiber optic gyroscope during normal operation are obtained, and the historical operating parameters are preprocessed to obtain a sample set of operating parameters; The sample set of running parameters is clustered based on a preset clustering algorithm to obtain several normal behavior clusters; The real-time operating parameters of the fiber optic gyroscope are obtained, and anomaly analysis is performed on the real-time operating parameters based on the normal behavior cluster to obtain the anomaly analysis results. Based on the anomaly analysis results and the pre-constructed fault occurrence conditions, it is determined whether the fiber optic gyroscope will malfunction; if so, a fault warning message is generated. The fault warning information is displayed visually.

2. The fault detection method for a fiber optic gyroscope according to claim 1, characterized in that, The preprocessing includes at least: data cleaning, standardization, normalization, filtering, and dimensionality reduction.

3. The fault detection method for a fiber optic gyroscope according to claim 1, characterized in that, The preset clustering algorithm is the K-means clustering algorithm. Based on the preset clustering algorithm, the sample set of running parameters is clustered to obtain several normal behavior clusters, including: A cluster set is constructed based on the sample set of running parameters. The cluster set includes at least one sub-cluster. The sum of squared errors of the cluster set is calculated. The sub-cluster corresponding to the maximum sum of squared errors is selected from the cluster set as the cluster to be clustered. Find two center points for the cluster to be clustered. The two center points are the two data points with the largest distance between them in the cluster to be clustered. Each data point corresponds to a historical running parameter. Based on the K-means clustering algorithm, the clusters to be clustered are locally clustered with two centroids as cluster centers to obtain two new clusters. The two new clusters are then added to the cluster set as new sub-clusters. Recalculate the sum of squared errors of the clusters and reselect the clusters to be clustered until the number of subclusters in the clusters reaches the preset number; Based on the K-means clustering algorithm, a preset number of centroids are used as initial centers to perform global clustering on the sample dataset, resulting in several normal behavior clusters and the cluster center corresponding to each normal behavior cluster.

4. The fault detection method for a fiber optic gyroscope according to claim 3, characterized in that, Anomaly analysis is performed on real-time operating parameters based on normal behavior clusters, and the anomaly analysis results are obtained, including: Calculate the distance between the real-time operating parameters and the cluster centers of each normal behavior cluster to obtain the distance set corresponding to the real-time operating parameters; Extract the minimum distance from the distance set, determine whether the minimum distance is greater than the preset distance, and if so, mark the real-time running parameter as abnormal, and use the abnormal real-time running parameter as the abnormal analysis result.

5. The fault detection method for a fiber optic gyroscope according to claim 4, characterized in that, Based on the anomaly analysis results and pre-constructed fault occurrence conditions, determine whether the fiber optic gyroscope will malfunction, including: Based on the anomaly analysis results, the difference between the minimum distance corresponding to the real-time operating parameters of the anomaly and the preset distance is calculated to obtain the distance difference; Determine whether the distance difference exceeds a preset distance difference threshold. If so, determine that the fiber optic gyroscope will malfunction. The condition for malfunction is that the distance difference between the minimum distance and the preset distance exceeds the preset distance difference threshold.

6. The fault detection method for a fiber optic gyroscope according to claim 5, characterized in that, When the distance difference does not exceed a preset distance difference threshold, the method further includes: Obtain the timestamp corresponding to the real-time operating parameters of the anomaly, and store and record the distance difference and timestamp corresponding to the real-time operating parameters of the anomaly. Acquire the distance difference and timestamp recorded during the preset operation time of the fiber optic gyroscope, and construct a distance difference sequence based on the recorded distance difference and timestamp; If a predetermined number of distance differences in the distance difference sequence show a continuously increasing trend, it is determined that the fiber optic gyroscope will malfunction; the existence of a predetermined number of distance differences in the distance difference sequence showing a continuously increasing trend is used as the condition for the malfunction to occur.

7. The fault detection method for a fiber optic gyroscope according to claim 6, characterized in that, When there is no predetermined number of distance differences in the distance difference sequence that show a continuously increasing trend, the method further includes: The time interval corresponding to each two adjacent distance differences in the statistical distance difference sequence is greater than a preset number; Determine whether all time intervals of the distance difference sequence show a decreasing trend. If so, determine that the fiber optic gyroscope will malfunction. The condition for malfunction is that all time intervals of the distance difference sequence show a decreasing trend.

8. A fault detection system for a fiber optic gyroscope, used to implement the fault detection method for the fiber optic gyroscope according to any one of claims 1-7, characterized in that, The system includes: The parameter acquisition module is used to acquire historical operating parameters of the fiber optic gyroscope during normal operation, preprocess the historical operating parameters, and obtain a sample set of operating parameters. The parameter clustering module is used to cluster the sample set of running parameters based on a preset clustering algorithm to obtain several normal behavior clusters; The anomaly analysis module is used to acquire the real-time operating parameters of the fiber optic gyroscope, perform anomaly analysis on the real-time operating parameters based on the normal behavior cluster, and obtain the anomaly analysis results. The fault analysis module is used to determine whether the fiber optic gyroscope will malfunction based on the anomaly analysis results and pre-built fault occurrence conditions; if so, it generates fault warning information. The early warning display module is used to visualize fault early warning information.

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, it implements the fault detection method for the fiber optic gyroscope according to any one of claims 1-7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When executed by the processor, the program implements the fault detection method for the fiber optic gyroscope as described in any one of claims 1-7.

Images