Interlocking equipment fault detection method and device
By using convolutional neural networks to extract features and screen fault factors from interlocking equipment log data, the problems of inaccurate detection and low efficiency caused by manual analysis are solved, and automated and accurate fault detection is achieved.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-11-24
- Publication Date
- 2026-04-03
Smart Images
Figure CN121786665A_ABST
Abstract
Description
Technical Field
[0001] This invention relates to the field of rail transit technology, and in particular to a method and apparatus for detecting faults in interlocking equipment. Background Technology
[0002] Interlocking equipment refers to the equipment that controls the switches, routes, and signals of a station and establishes interlocking relationships between them. In railway and rail transit systems, the normal operation of interlocking equipment plays a crucial role in ensuring the safety of train operation and shunting.
[0003] Currently, fault detection for most interlocking equipment relies mainly on manual analysis, which not only consumes a lot of time and energy, but is also easily affected by subjective human factors, resulting in incomplete and inaccurate fault detection. This is especially true when there are many interlocking devices and the operating environment is complex, where manual analysis is particularly inefficient and prone to errors. Summary of the Invention
[0004] This invention provides a method and apparatus for detecting faults in interlocking equipment, which solves the technical problems of inaccurate and inefficient fault detection of interlocking equipment in the prior art.
[0005] This invention provides a method for detecting faults in interlocking equipment, comprising the following steps: Obtain the first log data of the interlocking equipment; The first log data is classified to obtain the second log data; The second log data is input into a convolutional neural network for feature extraction to obtain the potential fault factors output by the convolutional neural network. Based on the potential failure factors, the failure category of the interlocking equipment is determined.
[0006] According to the present invention, a fault detection method for interlocking equipment is provided, wherein the convolutional neural network includes a convolutional layer, a pooling layer, and a fully connected layer; The convolutional layer is used to extract local features from the second log data; The pooling layer is used to reduce the dimensionality of the local features to obtain low-dimensional features; The fully connected layer is used to map the low-dimensional features to the fault category space to generate corresponding potential fault factors.
[0007] According to a fault detection method for interlocking equipment provided by the present invention, determining the fault category of the interlocking equipment based on the potential fault factors includes: Determine the correlation between each potential failure factor and the failure state of the interlocking equipment; Based on the correlation, a first weight is determined for each potential failure factor; The first potential failure factor with the highest weight is taken as the key failure factor; Based on the key fault factors, the fault category of the interlocking equipment is determined.
[0008] According to a fault detection method for interlocking equipment provided by the present invention, the step of determining the correlation between each potential fault factor and the fault state of the interlocking equipment includes: Determine the first time when the interlocking equipment malfunctions, the second time when each potential fault factor occurs, and the number of times each potential fault factor occurs at the second time; Based on the first time, determine a second weight for each potential failure factor that occurs at the second time; Based on the occurrence frequency and the second weight, the correlation between each potential fault factor and the fault state of the interlocking equipment is determined.
[0009] According to a fault detection method for interlocking equipment provided by the present invention, before inputting the second log data into a convolutional neural network for feature extraction and obtaining the potential fault factors output by the convolutional neural network, the method further includes: The second log data is preprocessed to obtain preprocessed second log data; The preprocessing includes one or more of the following processing methods: Remove invalid data from the second log data; Unify the timestamps of the second log data; Based on the log data structure, the overall content of the second log data is decomposed into time, device number, fault content code, and fault category code.
[0010] According to a fault detection method for interlocking equipment provided by the present invention, before determining the fault category of the interlocking equipment based on the potential fault factors, the method further includes: Based on the professional knowledge base of interlocking systems, determine the fault screening indicators; The potential fault factors are screened by the feature recursive elimination algorithm according to the fault screening index to obtain the screened potential fault factors.
[0011] The present invention also provides a fault detection device for interlocking equipment, comprising the following modules: The acquisition module is used to acquire the first log data of the interlocking equipment; The classification module is used to classify the first log data to obtain the second log data; The feature module is used to input the second log data into a convolutional neural network, perform feature extraction, and obtain the potential fault factors output by the convolutional neural network. The determination module is used to determine the fault category of the interlocking equipment based on the potential fault factors.
[0012] The present invention also provides an electronic device, including a memory, a processor, and a computer program stored in the memory and running on the processor, wherein the processor executes the computer program to implement the interlocking equipment fault detection method as described above.
[0013] The present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the interlocking equipment fault detection method as described above.
[0014] The present invention also provides a computer program product, including a computer program that, when executed by a processor, implements the interlocking equipment fault detection method as described above.
[0015] This invention provides a fault detection method for interlocking equipment. It acquires first log data from the interlocking equipment and classifies this data to obtain second log data, thereby improving data quality through standardized classification of the first log data. Then, the second log data is input into a convolutional neural network for feature extraction, obtaining potential fault factors output by the convolutional neural network. This allows for automated and efficient mining of relevant fault features through the convolutional neural network, reducing the risk of subjective misjudgment compared to traditional manual analysis and significantly improving the accuracy and efficiency of fault detection. Finally, based on the potential fault factors, the fault category of the interlocking equipment is determined, achieving accurate and efficient fault detection for complex interlocking equipment. Attached Figure Description
[0016] To more clearly illustrate the technical solutions in this invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of this invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.
[0017] Figure 1 This is a flowchart illustrating a fault detection method for interlocking equipment provided by the present invention.
[0018] Figure 2 This is a schematic diagram of the structure of an interlocking equipment fault detection device provided by the present invention.
[0019] Figure 3 This is a schematic diagram of the structure of the electronic device provided by the present invention. Detailed Implementation
[0020] To make the objectives, technical solutions, and advantages of this invention clearer, the technical solutions of this invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of this invention. All other embodiments obtained by those skilled in the art based on the embodiments of this invention without creative effort are within the scope of protection of this invention.
[0021] The following is combined with Figures 1 to 3 This invention describes a method and apparatus for detecting faults in interlocking equipment.
[0022] Figure 1 This is a flowchart illustrating a fault detection method for interlocking equipment provided by the present invention, as shown below. Figure 1 As shown, the method includes the following steps: Step 101: Obtain the first log data of the interlocking equipment; Specifically, raw operation log data is collected in real time through the device communication interface to obtain complete data as the primary log data, ensuring the comprehensiveness and accuracy of fault analysis.
[0023] Step 102: Classify the first log data to obtain the second log data; Specifically, based on the log content, the first log data can be divided into: system status representation, station status representation, basic equipment status information and other information, to obtain the standardized and classified second log data, thereby improving data quality and subsequent processing efficiency. This allows for the adoption of corresponding processing strategies (such as targeted feature extraction) for different types of data.
[0024] Step 103: Input the second log data into a convolutional neural network to extract features and obtain the potential fault factors output by the convolutional neural network; Specifically, after constructing a convolutional neural network for interlocking log data, the convolutional neural network can be pre-trained using historical interlocking log data and corresponding potential fault factors, so that the model can fully learn the spatiotemporal characteristics of the interlocking log data and improve model performance.
[0025] After pre-training, the second log data is input into the convolutional neural network for feature extraction. The potential fault factors output by the convolutional neural network are obtained, realizing automated feature mining of the second log data, avoiding the influence of human subjective factors, and improving accuracy and efficiency.
[0026] This invention constructs a convolutional neural network to automate data processing and feature extraction, efficiently identifying potential fault modes in equipment operation and accurately capturing the relationship between equipment status changes and faults. This not only enables real-time monitoring of equipment operation and rapid identification of potential fault factors, reducing reliance on manual analysis and significantly alleviating the workload of maintenance personnel, but also improves the accuracy and efficiency of subsequent fault diagnosis, enhances system stability, and ensures long-term stable operation of interlocking equipment.
[0027] Step 104: Determine the fault category of the interlocking equipment based on the potential fault factors.
[0028] Specifically, based on potential failure factors, the most likely failure category corresponding to the potential failure factors is determined. In addition, maintenance personnel can further analyze the severity of the failure and determine the corresponding maintenance recommendation report.
[0029] This invention provides a fault detection method for interlocking equipment. It acquires first log data from the interlocking equipment and classifies this data to obtain second log data, thereby improving data quality through standardized classification of the first log data. Then, the second log data is input into a convolutional neural network for feature extraction, obtaining potential fault factors output by the convolutional neural network. This allows for automated and efficient mining of relevant fault features through the convolutional neural network, reducing the risk of subjective misjudgment compared to traditional manual analysis and significantly improving the accuracy and efficiency of fault detection. Finally, based on the potential fault factors, the fault category of the interlocking equipment is determined, achieving accurate and efficient fault detection for complex interlocking equipment.
[0030] Furthermore, the convolutional neural network includes convolutional layers, pooling layers, and fully connected layers; The convolutional layer is used to extract local features from the second log data; The pooling layer is used to reduce the dimensionality of the local features to obtain low-dimensional features; The fully connected layer is used to map the low-dimensional features to the fault category space to generate corresponding potential fault factors.
[0031] Specifically, the convolutional neural network constructed in the embodiments of the present invention includes at least a convolutional layer, a pooling layer, and a fully connected layer.
[0032] Convolutional layers are used to extract local features from the second log data. Through the local awareness mechanism of the convolutional layers, local spatiotemporal features are captured, automatically identifying and extracting fault-related local features from the log data. These local features are typically related to abnormal patterns in system or device operation, providing important clues for fault diagnosis. For example, a 3×1 kernel convolutional layer can be used to extract local abnormal pattern-related features from the log sequence.
[0033] Pooling layers are used to reduce the dimensionality of local features, thereby reducing the amount of data computation and enhancing feature robustness.
[0034] Fully connected layers are used to map low-dimensional features to a fault category space to generate corresponding potential fault factors. For example, based on the various categories in the standard fault classification of railway signaling systems, a fault category space is formed, and then low-dimensional features are mapped to the fault category space to match the corresponding potential fault factors.
[0035] This invention utilizes the local perception mechanism of convolutional layers in convolutional neural networks to automatically identify and extract key local features related to faults in log data, effectively filtering out state variables with high fault correlation, thereby accurately capturing the relationship between equipment state changes and faults. Pooling layers are used for data dimensionality reduction, reducing the computational burden in subsequent fault analysis and improving the model's computational efficiency. Fully connected layers map low-dimensional features to the fault category space, enabling the model to more accurately identify potential fault factors, making the data more accurate and valuable, and improving the accuracy and efficiency of subsequent fault detection.
[0036] Further, determining the fault category of the interlocking equipment based on the potential fault factors includes: Determine the correlation between each potential failure factor and the failure state of the interlocking equipment; Based on the correlation, a first weight is determined for each potential failure factor; The first potential failure factor with the highest weight is taken as the key failure factor; Based on the key fault factors, the fault category of the interlocking equipment is determined.
[0037] Specifically, based on the degree of correlation between each potential fault factor and the corresponding interlocking equipment fault state, a first weight is assigned to each potential fault factor. Then, the potential fault factor with the highest first weight is taken as the key fault factor, and the fault category of the interlocking equipment is determined based on the key fault factor.
[0038] For example, if the power fluctuation factor has a high correlation with signal failure and the communication delay factor has a low correlation with signal failure, then the power fluctuation factor is assigned a higher first weight and the communication delay factor is assigned a lower first weight. If the power fluctuation factor has the highest first weight among all potential failure factors, then the power fluctuation factor can be identified as a critical failure factor, the failure category of the interlocking equipment is the power system failure corresponding to the power fluctuation factor, and the maintenance recommendation can be to check the power interface or power wiring, etc.
[0039] This invention, through quantitative analysis of the contribution of each characteristic factor, determines the first weight of each potential fault factor, thereby screening out key fault factors, improving the interpretability of fault detection, and making the fault detection results more reliable and accurate.
[0040] Furthermore, determining the correlation between each potential failure factor and the failure state of the interlocking equipment includes: Determine the first time when the interlocking equipment malfunctions, the second time when each potential fault factor occurs, and the number of times each potential fault factor occurs at the second time; Based on the first time, determine a second weight for each potential failure factor that occurs at the second time; Based on the occurrence frequency and the second weight, the correlation between each potential fault factor and the fault state of the interlocking equipment is determined.
[0041] Specifically, firstly, the first time when the interlocking equipment malfunctions, the second time when each potential fault factor occurs, and the number of times each potential fault factor occurs at the second time are determined; then, based on the first time, the second weight of each potential fault factor occurring at the second time is determined; finally, based on the number of occurrences and the second weight, the correlation between each potential fault factor and the fault state of the interlocking equipment is determined.
[0042] For example, if a communication interruption occurs between the interlocking equipment and the Automatic Train Supervision (ATS) extension, the time point of the interlocking equipment failure (the first time), such as 15:00, should be determined first, and then potential failure factors within a preset time period (such as 24 hours or 48 hours) should be investigated.
[0043] Within a preset time period, the closer the occurrence time (second time) of each potential fault factor is to the first time, the greater the second weight of the potential fault factor. For example, if, according to the records in the second log data, potential fault factor 1 (loss of status of control display machine A) occurs once at 12:00 and once at 13:00, and potential fault factor 2 (inconsistency between internal and external clock records of Computer-Based Interlocking (CI) leading to clock verification failure) occurs twice at 12:00, then since 13:00 is closer to 15:00, the second weight corresponding to the potential fault factor occurring at 13:00 is greater and can be set to 2, while the second weight corresponding to the potential fault factor occurring at 12:00 is smaller and can be set to 1.5.
[0044] In this embodiment of the invention, the correlation degree between each potential fault factor and the fault state of the interlocking equipment is determined based on the product of the frequency and the weight. The correlation degree of potential fault factor 1 is calculated as follows: 1 1.5+1 2=3.5; the correlation degree of potential failure factor 2 is calculated as 2. 1.5 = 3. If sorted by correlation from largest to smallest, potential failure factor 1 can be ranked first, and potential failure factor 2 can be ranked last.
[0045] This invention quantifies the correlation between each potential fault factor and the fault state of the interlocking equipment, thereby determining the magnitude of the correlation between each potential fault factor and the fault state of the interlocking equipment. This enables the scientific and accurate ranking of each potential fault factor, improving the accuracy of subsequent fault detection.
[0046] Furthermore, before inputting the second log data into a convolutional neural network for feature extraction to obtain the potential failure factor output by the convolutional neural network, the method further includes: The second log data is preprocessed to obtain preprocessed second log data; The preprocessing includes one or more of the following processing methods: Remove invalid data from the second log data; Unify the timestamps of the second log data; Based on the log data structure, the overall content of the second log data is decomposed into time, device number, fault content code, and fault category code.
[0047] Specifically, the second log data can be preprocessed before being input into the convolutional neural network to improve the quality of the input data.
[0048] For example, removing invalid data from the second log data includes: removing blank logs, debugging information, and non-critical information such as duplicate records; unifying the timestamps of the second log data includes: unifying the timeline corresponding to the data and clarifying the order of events; and decomposing the overall content of the second log data into time, device number, fault content code, and fault category code, etc., according to the log data structure.
[0049] This invention addresses the issue of log data heterogeneity through a standardized log preprocessing workflow, providing standardized data input for subsequent model detection, reducing the model processing burden, and thereby improving the efficiency and accuracy of fault detection results.
[0050] Furthermore, before determining the fault category of the interlocking equipment based on the potential fault factors, the method further includes: Based on the professional knowledge base of interlocking systems, determine the fault screening indicators; The potential fault factors are screened by the feature recursive elimination algorithm according to the fault screening index to obtain the screened potential fault factors.
[0051] Specifically, based on the interlocking system professional knowledge base, multiple fault screening indicators are determined to provide a basis for subsequent filtering and screening.
[0052] The feature recursive elimination algorithm filters potential fault factors based on fault screening indicators. Iteratively, iteratively eliminates features with lower importance from all potential fault factors and selects features with higher importance, thereby simplifying and optimizing features and improving the accuracy of subsequent fault category judgment.
[0053] This invention introduces a domain knowledge-guided feature selection mechanism, which achieves feature optimization selection through recursive elimination, retaining only potential fault factors with key functions as the basis for subsequent fault category determination of interlocking equipment, thereby improving the accuracy of fault detection of interlocking equipment.
[0054] The following describes a fault detection device for interlocking equipment provided by the present invention. The fault detection device for interlocking equipment described below can be referred to in correspondence with the fault detection method for interlocking equipment described above.
[0055] Based on any of the above embodiments Figure 2 This is a schematic diagram of the structure of a fault detection device for interlocking equipment provided by the present invention, as shown below. Figure 2 As shown. This embodiment of the invention provides a fault detection device for interlocking equipment, including an acquisition module 201, a classification module 202, a feature module 203, and a determination module 204, wherein: The acquisition module 201 is used to acquire first log data of the interlocking device; the classification module 202 is used to classify the first log data to obtain second log data; the feature module 203 is used to input the second log data into a convolutional neural network to extract features and obtain the potential fault factors output by the convolutional neural network; the determination module 204 is used to determine the fault category of the interlocking device based on the potential fault factors.
[0056] This invention provides a fault detection device for interlocking equipment. It acquires first log data from the interlocking equipment and classifies this data to obtain second log data, thereby improving data quality through standardized classification of the first log data. Then, the second log data is input into a convolutional neural network for feature extraction, obtaining potential fault factors output by the convolutional neural network. This allows for automated and efficient mining of relevant fault features through the convolutional neural network, reducing the risk of subjective misjudgment compared to traditional manual analysis and significantly improving the accuracy and efficiency of fault detection. Finally, based on the potential fault factors, the fault category of the interlocking equipment is determined, achieving accurate and efficient fault detection for complex interlocking equipment.
[0057] Figure 3 An example is a schematic diagram of the physical structure of an electronic device, such as... Figure 3 As shown, the electronic device may include: a processor 310, a communications interface 320, a memory 330, and a communication bus 340, wherein the processor 310, the communications interface 320, and the memory 330 communicate with each other via the communication bus 340. The processor 310 can call logical instructions in the memory 330 to execute an interlocking equipment fault detection method, which includes: Obtain the first log data of the interlocking equipment; The first log data is classified to obtain the second log data; The second log data is input into a convolutional neural network for feature extraction to obtain the potential fault factors output by the convolutional neural network. Based on the potential failure factors, the failure category of the interlocking equipment is determined.
[0058] Furthermore, the logical instructions in the aforementioned memory 330 can be implemented as software functional units and, when sold or used as independent products, can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, essentially, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.
[0059] On the other hand, the present invention also provides a computer program product, the computer program product comprising a computer program that can be stored on a non-transitory computer-readable storage medium, wherein when the computer program is executed by a processor, the computer is able to execute the interlocking equipment fault detection method provided by the above methods, the method comprising: Obtain the first log data of the interlocking equipment; The first log data is classified to obtain the second log data; The second log data is input into a convolutional neural network for feature extraction to obtain the potential fault factors output by the convolutional neural network. Based on the potential failure factors, the failure category of the interlocking equipment is determined.
[0060] In another aspect, the present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, is implemented to perform the interlocking equipment fault detection method provided by the methods described above, the method comprising: Obtain the first log data of the interlocking equipment; The first log data is classified to obtain the second log data; The second log data is input into a convolutional neural network for feature extraction to obtain the potential fault factors output by the convolutional neural network. Based on the potential failure factors, the failure category of the interlocking equipment is determined.
[0061] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs. Those skilled in the art can understand and implement this without any creative effort.
[0062] Through the above description of the embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus necessary general-purpose hardware platforms, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solutions, in essence or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods described in the various embodiments or some parts of the embodiments.
[0063] It should be noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element. Furthermore, it should be noted that the scope of the methods and apparatuses in the embodiments of this application is not limited to performing functions in the order shown or discussed, but may also include performing functions substantially simultaneously or in the reverse order, depending on the functions involved. For example, the described methods may be performed in a different order than described, and various steps may be added, omitted, or combined. Additionally, features described with reference to certain examples may be combined in other examples.
[0064] It should also be noted that the terms "first," "second," etc., used in this invention are used to distinguish similar objects, and not to describe a specific order or sequence. It should be understood that such terms can be used interchangeably where appropriate so that embodiments of this application can be implemented in orders other than those illustrated or described herein, and the objects distinguished by "first" and "second" are generally of the same class, and the number of objects is not limited; for example, the first object can be one or more.
[0065] In this application's embodiments, "determine B based on A" means that factor A must be considered when determining B. It is not limited to "B can be determined based solely on A," but should also include: "determine B based on A and C," "determine B based on A, C, and E," "determine C based on A, and further determine B based on C," etc. Additionally, it can include using A as a condition for determining B, for example, "when A meets the first condition, determine B using the first method"; another example, "when A meets the second condition, determine B," etc.; another example, "when A meets the third condition, determine B based on the first parameter," etc. Of course, it can also be a condition where A is a factor in determining B, for example, "when A meets the first condition, determine C using the first method, and further determine B based on C," etc.
[0066] In this invention, the term "multiple" refers to two or more, and other quantifiers are similar.
[0067] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.
Claims
1. A method for detecting faults in interlocking equipment, characterized in that, include: Obtain the first log data of the interlocking equipment; The first log data is classified to obtain the second log data; The second log data is input into a convolutional neural network for feature extraction to obtain the potential fault factors output by the convolutional neural network. Based on the potential failure factors, the failure category of the interlocking equipment is determined.
2. The method for detecting faults in interlocking equipment according to claim 1, characterized in that, The convolutional neural network includes convolutional layers, pooling layers, and fully connected layers; The convolutional layer is used to extract local features from the second log data; The pooling layer is used to reduce the dimensionality of the local features to obtain low-dimensional features; The fully connected layer is used to map the low-dimensional features to the fault category space to generate corresponding potential fault factors.
3. The method for detecting interlocking equipment faults according to claim 1, characterized in that, Determining the fault category of the interlocking equipment based on the potential fault factors includes: Determine the correlation between each potential failure factor and the failure state of the interlocking equipment; Based on the correlation, a first weight is determined for each potential failure factor; The first potential failure factor with the highest weight is taken as the key failure factor; Based on the key failure factors, the failure category of the interlocking equipment is determined.
4. The interlocking equipment fault detection method according to claim 3, characterized in that, Determining the correlation between each potential fault factor and the fault state of the interlocking equipment includes: Determine the first time when the interlocking equipment malfunctions, the second time when each potential fault factor occurs, and the number of times each potential fault factor occurs at the second time; Based on the first time, determine a second weight for each potential failure factor that occurs at the second time; Based on the occurrence frequency and the second weight, the correlation between each potential fault factor and the fault state of the interlocking equipment is determined.
5. The method for detecting faults in interlocking equipment according to claim 1, characterized in that, Before inputting the second log data into a convolutional neural network for feature extraction to obtain the potential failure factor output by the convolutional neural network, the method further includes: The second log data is preprocessed to obtain preprocessed second log data; The preprocessing includes one or more of the following processing methods: Remove invalid data from the second log data; Unify the timestamps of the second log data; Based on the log data structure, the overall content of the second log data is decomposed into time, device number, fault content code, and fault category code.
6. The interlocking equipment fault detection method according to claim 1, characterized in that, Before determining the fault category of the interlocking equipment based on the potential fault factors, the method further includes: Based on the professional knowledge base of interlocking systems, determine the fault screening indicators; The potential fault factors are screened by the feature recursive elimination algorithm according to the fault screening index to obtain the screened potential fault factors.
7. A fault detection device for interlocking equipment, characterized in that, include: The acquisition module is used to acquire the first log data of the interlocking equipment; The classification module is used to classify the first log data to obtain the second log data; The feature module is used to input the second log data into a convolutional neural network, perform feature extraction, and obtain the potential fault factors output by the convolutional neural network. The determination module is used to determine the fault category of the interlocking equipment based on the potential fault factors.
8. An electronic device comprising a memory, a processor, and a computer program stored in the memory and running on the processor, characterized in that, When the processor executes the computer program, it implements the interlocking equipment fault detection method as described in any one of claims 1 to 6.
9. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the interlocking equipment fault detection method as described in any one of claims 1 to 6.
10. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by the processor, it implements the interlocking equipment fault detection method as described in any one of claims 1 to 6.