Railway signal equipment operation data analysis method and system

Abstract

The invention discloses a method and system for analyzing operation data of railway signal equipment, and belongs to the technical field of railway signal equipment, and the method comprises the steps: obtaining the operation data of the railway signal equipment; preprocessing the operation data, wherein the preprocessing comprises missing value filling of the data; calculating a concentration trend and a dispersion degree of the preprocessed data, dividing the preprocessed data into a plurality of types, and fusing the preprocessed data of the same type; constructing a signal data set by using the fused data; calling the operation data of each railway signal device before the signal alarm state, and deeming the operation data of each railway signal device before the alarm state as alarm set data; performing similarity calculation and matching rate calculation on the real-time signal data set and the alarm set data; and screening the similarity and the matching rate through a threshold comparison method, and optimizing the operation state of the railway signal equipment.

Description

Technical Field

[0001] The present invention belongs to the technical field of railway signal equipment, and in particular relates to a method and system for analyzing operation data of railway signal equipment. Background Art

[0002] At present, my country's high-speed passenger dedicated line railway signal control system has built a relatively complete technical architecture, named China Railway Train Control System (CTCS system for short). The CTCS system covers a series of signal equipment such as computer interlocking equipment, train control center equipment, track circuit equipment, on-board train automatic protection equipment, signal centralized monitoring equipment, dispatching centralized equipment, EMU supervision system and temporary speed limit server. Specifically, computer interlocking equipment mainly assists in station signal control; train control center equipment is responsible for interval coding, lighting control, line direction control and transponder message control; track circuit equipment focuses on track coding and occupancy status inspection; dispatching centralized equipment is mainly responsible for dispatching command and issuing temporary speed limit orders; train automatic protection equipment is responsible for collecting ground signals and calculating protection curves to prevent trains from speeding. In view of the importance of driving safety, all kinds of signal equipment attach great importance to system safety and reliability design during the design and implementation stages, and their software and hardware have undergone long-term rigorous testing and verification.

[0003] The existing railway signal equipment alarm system mainly performs monitoring functions. When a parameter of the equipment is detected to exceed the preset threshold, an alarm is issued. However, due to the many factors that affect the stable operation of railway signal equipment, the existing alarm system does not yet have the ability to predict and handle faults. During real-time communication, if a railway signal equipment fails, on the one hand, it may cause the fault to deteriorate further and increase maintenance costs; on the other hand, in a high-density and high-frequency train operation environment, equipment failure will cause communication interruption, which may lead to safety accidents or cause economic losses. Summary of the invention

[0004] In order to solve the above technical problems, a method and system for analyzing the operation data of railway signal equipment are provided. The present invention improves the problem that the existing alarm system mentioned in the above background technology lacks the function of predicting and processing the faults of railway signal equipment. During the real-time communication process, if the railway signal equipment fails, the existing system has two major drawbacks: one is that it may aggravate the degree of failure of the railway signal equipment, thereby increasing the maintenance cost; the other is that in an environment with high train operation density and high frequency, the failure of the railway signal equipment will lead to communication interruption, which may cause safety accidents or cause economic losses. This technical solution aims to solve the above problems.

[0005] In order to achieve the above purpose, the technical solution adopted by the present invention is:

[0006] The first object of the present invention is to provide a method for analyzing railway signal equipment operation data, comprising:

[0007] Acquiring operation data of railway signal equipment, including computer interlocking equipment, train control center equipment, track circuit equipment, centralized dispatching equipment, centralized signal monitoring equipment, automatic train protection equipment and temporary speed limit server;

[0008] Preprocessing the running data, wherein the preprocessing includes filling missing values ​​of the data;

[0009] Calculate the central tendency and dispersion of preprocessed data, divide the preprocessed data into several categories, and merge the preprocessed data of the same category;

[0010] Use fused data to construct signal datasets;

[0011] Retrieving the operation data of each railway signal device before the signal alarm state occurs, and naming the operation data of each railway signal device before the alarm state as alarm aggregate data;

[0012] Calculate the similarity and matching rate between the real-time signal data set and the alarm collection data;

[0013] The similarity and matching rate are screened by a threshold comparison method, and the operating status of the railway signal equipment is optimized.

[0014] Preferably, the missing value filling comprises the following steps:

[0015]

[0016] Where D i is the filling data; i is the number of filling data; D j are different types of historical operation data; n is the number of different types of historical operation data.

[0017] Preferably, the calculation of the central tendency and dispersion degree of the preprocessed data specifically comprises the following steps:

[0018] Calculate the data mean of the preprocessed data, and calculate the variance of the preprocessed data according to the variance formula;

[0019] Setting the variance as the central tendency of the preprocessed data and assigning a trend identification code to the central tendency;

[0020] Pairing each data in the preprocessed data with the remaining data in the preprocessed data to obtain at least one paired group;

[0021] Calculate the absolute value of the difference between two preprocessed data in each paired group of preprocessed data, and accumulate the absolute values ​​of the difference between two data in all paired groups to obtain a discrete value;

[0022] The discrete value is set as the discrete degree of the data, and a discrete identification code is assigned to the discrete degree.

[0023] Preferably, the calculation formula of the variance is as follows:

[0024]

[0025] Among them, D is the variance, q is the number of data, x i is the value of the data, and a is the average value of the data.

[0026] Preferably, said dividing the pre-processed data into several categories comprises the following steps:

[0027] Retrieve the historical data classification and discrimination standard 1 from the database, and obtain the range interval of the central tendency ratio and the range interval of the dispersion ratio in the classification and discrimination standard 1;

[0028] Calculate the first ratio of the central tendency of the data to the central tendency mean of the sample data;

[0029] Calculate the second ratio of the degree of dispersion of the data to the mean of the degree of dispersion of the sample data;

[0030] Compare whether the first ratio falls within the range of the central tendency ratio;

[0031] Compare whether the second ratio belongs to the range interval of the dispersion ratio;

[0032] If the first ratio belongs to the range of the central tendency ratio and the second ratio belongs to the range of the dispersion ratio, calling the classification in the classification discrimination group 1, setting the classification as the first classification, and classifying the data into the first classification;

[0033] If the first ratio does not belong to the range of the central tendency ratio or the second ratio does not belong to the range of the dispersion ratio, the remaining classification discrimination groups in the data type determination model are called;

[0034] Find the second historical data classification discrimination criterion in the remaining classification discrimination groups, and the second classification discrimination criterion satisfies that the first ratio of the data belongs to the range interval of the central tendency ratio of the classification discrimination group two and the second ratio of the data belongs to the range interval of the dispersion ratio of the classification discrimination group two, call the classification in the classification discrimination group two, set the classification to the second classification, and classify the data into the second classification.

[0035] Preferably, the fusing of the same type of pre-processed data specifically comprises the following steps:

[0036] Retrieve pre-processed data belonging to the first category and the second category;

[0037] Fusing the preprocessed data of the first classification to obtain first classification fused data;

[0038] The preprocessed data of the second classification is fused to obtain the second classification fused data.

[0039] Preferably, the formula for calculating the similarity is:

[0040]

[0041] In the formula, S i is the similarity between the real-time signal dataset and the i-th feature of the alarm set data, w ij is the jth feature index value of the i-th feature of the alarm set data, v ij is the jth feature index value of the ith feature of the alarm collection data, and p is the total number of ith feature index values.

[0042] Preferably, the calculation formula of the matching rate is:

[0043]

[0044] Where C is the degree of fit between the characteristic parameters of the real-time signal data set and the characteristic parameters of the alarm set data, α i is the weight value of the i-th feature parameter, and m is the total number of feature parameters.

[0045] A second object of the present invention is to provide a railway signal equipment operation data analysis system, comprising:

[0046] A data acquisition module, which acquires the operation data of railway signal equipment, wherein the railway signal equipment includes computer interlocking equipment, train control center equipment, track circuit equipment, dispatching centralized equipment, signal centralized monitoring equipment, train automatic protection equipment and temporary speed limit server;

[0047] A data preprocessing module, which preprocesses the operation data, wherein the preprocessing includes filling missing values ​​of the data;

[0048] Data fusion module, which calculates the central tendency and dispersion degree of preprocessed data, divides the preprocessed data into several categories, and fuses the preprocessed data of the same category;

[0049] The data set construction module uses the fused data to construct the signal data set;

[0050] The marking module retrieves the operation data of each railway signal device before the signal alarm state occurs, and names the operation data of each railway signal device before the alarm state as alarm set data;

[0051] The matching module calculates the similarity and matching rate between the real-time signal data set and the alarm set data;

[0052] The screening optimization module screens the similarity and matching rate through a threshold comparison method, and optimizes the operating status of the railway signal equipment.

[0053] A third object of the present invention is to provide a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the above-mentioned method for analyzing the operating data of railway signal equipment.

[0054] Compared with the prior art, the present invention has the following beneficial effects:

[0055] The present invention ensures the real-time and accuracy of the data by collecting the operating data of each railway signal device online in real time. During the data collection process, the operating data of the equipment is carefully checked to find and process the missing values ​​therein, thereby ensuring the integrity of the data. In this way, a complete and processing-worthy data set can be obtained, providing a solid foundation for subsequent data analysis and processing.

[0056] Next, the present invention classifies and processes these complete operation data, and merges similar data, thereby effectively reducing the memory usage of the same type of data. This process not only improves the efficiency of data processing, but also optimizes the use of data storage space. Through classification and fusion, the present invention can process and analyze data more quickly, thereby providing strong support for the maintenance and management of railway signal equipment.

[0057] In addition, the present invention also constructs a data set, which contains the operation data of each device before the signal alarm state occurs in history. In order to ensure the reference value of the data, these data specifically refer to the operation data within one hour before the alarm state occurs. If the time span is too large, the reference value of the data will be reduced, so it is necessary to strictly control the time range to ensure the accuracy and relevance of the data.

[0058] On this basis, the present invention compares and analyzes the real-time signal data set with the alarm set data, and by calculating the similarity and matching rate, can effectively predict the railway signal equipment that is about to fail. This prediction mechanism can send out alarm signals in time to remind maintenance personnel to carry out necessary inspections and repairs. In this way, the maintenance cost of railway signal equipment can be effectively reduced, while avoiding safety accidents caused by equipment failure, ensuring the safety and efficiency of railway transportation.

[0059] In general, the present invention meets the needs of railway staff for equipment operation status monitoring and fault warning through innovative data collection, processing and analysis methods, and provides strong technical support for the maintenance and management of railway signal equipment. BRIEF DESCRIPTION OF THE DRAWINGS

[0060] Figure 1 A flowchart of a preferred embodiment of the present invention;

[0061] Figure 2 A flowchart for calculating the central tendency and dispersion degree of preprocessed data in the present invention;

[0062] Figure 3 A flow chart of the method for dividing the pre-processed data into several groups of categories in the present invention;

[0063] Figure 4 The figure is a flow chart of the process of fusing the same pre-processed data in the present invention. DETAILED DESCRIPTION

[0064] The following description is used to disclose the present invention so that those skilled in the art can implement the present invention. The preferred embodiments described below are only examples, and those skilled in the art may think of other obvious variations.

[0065] Example 1

[0066] Please refer to Figure 1-Figure 4 As shown, a method for analyzing railway signal equipment operation data includes:

[0067] In order to ensure the efficient and safe operation of the railway signal system, it is first necessary to obtain key operating data from the railway signal equipment. These devices include but are not limited to computer interlocking equipment, train control center equipment, track circuit equipment, dispatching centralized equipment, signal centralized monitoring equipment, train automatic protection equipment and temporary speed limit server. These devices work together to ensure the smooth and safe operation of the train.

[0068] After obtaining the operating data of these devices, a series of preprocessing operations need to be performed on these data for further analysis and use. The preprocessing step mainly includes filling missing values ​​in the data to ensure the integrity and accuracy of the data. This step is crucial because it directly affects the reliability of subsequent analysis.

[0069] Next, the preprocessed data will be statistically analyzed to calculate its central tendency and dispersion. The central tendency usually includes the mean, median and mode of the data, while the dispersion involves statistical indicators such as standard deviation and variance. Through these statistical indicators, the data can be divided into different categories so that the data of the same category can be more deeply fused. Fusion processing can include operations such as normalization and standardization of data to ensure the comparability of data during the analysis process.

[0070] Based on the above fused data, a comprehensive signal data set will be constructed. This data set will contain the operating data of all relevant equipment, providing a solid foundation for subsequent analysis and decision-making. In addition, it is necessary to retrieve the operating data of each device before the signal alarm state occurs, and name this data separately as alarm collection data. This step helps to analyze and identify potential factors that may cause alarms.

[0071] In order to achieve real-time monitoring and early warning, the signal data set is collected in real time, and the similarity and matching rate are calculated between it and the alarm set data. Through calculation, the real-time data similar to the historical alarm data can be quickly identified, so that the alarm signal can be issued in time. This step is of great significance for preventing potential failures and accidents.

[0072] Finally, for those devices with high similarity and matching rates, an alarm will be issued and their operating status will be optimized and adjusted. This may include adjusting equipment parameters, replacing parts, or taking other necessary maintenance measures. In this way, it can be ensured that railway signaling equipment is always in the best operating state, thereby ensuring the safety and efficiency of railway transportation.

[0073] Professionals in this technical field are well aware that in the real world, the railway signal system is a complex network that includes a variety of key equipment. These equipment include but are not limited to computer interlocking equipment, train control center equipment, track circuit equipment, dispatching centralized equipment, signal centralized monitoring equipment, train automatic protection equipment and temporary speed limit server. These equipment work together to ensure the normal operation of the railway signal system and the safe operation of trains.

[0074] In order to ensure that these devices can operate efficiently and stably, technicians will collect the operating data of these railway signal devices online. This data is crucial for the monitoring and maintenance of the equipment. However, in the actual collection process, data may be missing. In order to make this data valuable for processing, technicians will fill in the missing data to ensure the integrity of the data. In this way, the data set becomes more complete, providing a solid foundation for subsequent data analysis and processing.

[0075] Next, technicians will classify and fuse the data. Classification can group similar data into one category, thereby reducing data redundancy. Fusion further optimizes the data structure, making the same type of data occupy less memory, thereby improving the speed and efficiency of data processing. Through these steps, technicians can integrate the data into a more efficient data set.

[0076] In order to further improve the reliability of the railway signal system, technicians will retrieve the operation data of each device before the signal alarm state occurred in history. This data is usually for the data within one hour before the alarm state occurs. The data in this time period is selected because it has a high reference value. If the time difference is too large, the reference significance of the data will be greatly reduced.

[0077] By performing detailed similarity and matching rate calculations on real-time signal data sets and historical alarm collection data, technicians can effectively predict and accurately identify railway signal equipment that is about to fail. This process involves in-depth analysis and comparison of data to ensure that every potential failure point can be accurately captured. Once the system detects a potential failure risk, it will immediately send out an alarm signal so that technicians can respond quickly and take corresponding maintenance and optimization measures. This preventive maintenance can not only significantly reduce the maintenance cost of railway signal equipment and reduce economic losses caused by equipment failure, but also effectively avoid safety accidents caused by equipment failure, ensuring the safety and smoothness of railway transportation. In this way, the railway staff's needs for safety and efficiency are fully met, while also improving the overall operating efficiency and reliability of the railway system.

[0078] The preprocessing of running data specifically includes the following steps:

[0079]

[0080] Where D i is the filling data; i is the number of filling data; D j are different types of historical operation data; n is the number of different types of historical operation data.

[0081] In order to accurately analyze and understand the statistical characteristics of the preprocessed data, a series of detailed calculation steps are required. First, the mean value of the data in the preprocessed data set needs to be calculated, which is an important indicator to measure the trend of the data set. The mean value can be obtained by adding all the data values ​​and dividing by the total number of data. Next, the variance formula is used to calculate the variance of the data. The variance can reflect the degree of deviation between the data points and the mean value, thereby revealing the degree of dispersion of the data.

[0082] After the variance is calculated, it is used as an important indicator of the central trend of the preprocessed data set and is assigned a specific trend identification code. This identification code helps to quickly identify and reference relevant information about the central trend in subsequent data analysis.

[0083] In order to further analyze the discreteness of the data, it is necessary to pair each data value in the preprocessed data set with all other data values ​​in the complete data set. In this way, at least one pairing group can be generated, each pairing group contains two data values. Next, the absolute value of the difference between the two data values ​​in each pairing group is calculated. This step is to eliminate the positive and negative effects of the difference and ensure that only the size of the difference is focused on.

[0084] The absolute values ​​of the differences in all paired groups are added up to obtain a discrete value, which reflects the overall discreteness of the data set. Finally, this discrete value is used as an important indicator of the discreteness of the data and is assigned a discrete identification code. This identification code helps to quickly identify and reference relevant information about the discreteness during data analysis.

[0085] Through the above steps, not only the central tendency and dispersion of the preprocessed data are calculated, but also these statistical indicators are given identification codes that are easy to identify and reference, thus providing a solid foundation for subsequent data analysis and decision-making.

[0086] The formula for calculating variance is as follows:

[0087]

[0088] Among them, D is the variance, q is the number of data, x i is the value of the data, and a is the average value of the data.

[0089] In order to classify the preprocessed data into several groups, a series of detailed steps need to be followed. First, the historical data classification criteria 1 needs to be retrieved from the database. This step includes obtaining the range interval of the central tendency ratio and the range interval of the dispersion ratio in the classification criteria 1. Next, the first ratio of the central tendency of the data to the central tendency mean of the sample data, and the second ratio of the dispersion degree of the data to the dispersion degree mean of the sample data will be calculated.

[0090] After these calculations are completed, a comparison is made. First, the first ratio is compared to see if it falls within the range of the central tendency ratio. Second, the second ratio is compared to see if it falls within the range of the dispersion ratio. If the first ratio falls within the range of the central tendency ratio and the second ratio falls within the range of the dispersion ratio, then the classification in classification discriminant group one is called and the data is assigned to the first classification.

[0091] However, if the first ratio does not belong to the range interval of the central tendency ratio or the second ratio does not belong to the range interval of the dispersion ratio, the remaining classification discrimination groups in the data type determination model will be called. Among these remaining classification discrimination groups, it is necessary to find the historical data classification discrimination criterion 2. Classification discrimination criterion 2 must satisfy that the first ratio of the data belongs to the range interval of the central tendency ratio of classification discrimination group 2 and the second ratio of the data belongs to the range interval of the dispersion ratio of classification discrimination group 2. Once these conditions are met, the classification in classification discrimination group 2 will be called, the classification will be set to the second classification, and the data will be classified into the second classification. Through these steps, it can be ensured that the data is accurately classified, thus laying a solid foundation for further data analysis and processing.

[0092] In the process of data fusion, we first need to retrieve the pre-processed data belonging to the first and second categories. This process involves extracting the pre-processed data from the data storage system, which is usually classified and organized according to certain standards and rules. Next, we will perform further fusion operations on these pre-processed data.

[0093] Specifically, for the preprocessed data of the first classification, a series of fusion steps will be performed to generate the first classification fused data. This may include data integration, normalization, feature extraction and other operations to ensure that the data can maintain consistency and comparability during the fusion process. Similarly, for the preprocessed data of the second classification, similar fusion steps will be performed to generate the second classification fused data. These steps ensure that the fusion of data in different classifications can proceed smoothly and maintain the integrity and accuracy of the data.

[0094] During the fusion process, an important consideration is to keep the position of the original data unchanged. This means that before fusion, the initial position of the data has been determined and will not change during the fusion process. However, the position of the data group to be fused is undetermined before fusion. To solve this problem, it is necessary to calculate and select the smallest judgment sum, which is an indicator of data correlation. By calculating the judgment sum between different data groups, it is possible to determine which target data group has the strongest correlation with the data group to be fused.

[0095] Once the target data group with the strongest correlation with the data group to be fused is found, the two can be placed adjacent to each other. This setting method is based on the assumption that the data groups with the strongest correlation should be placed together when fused to better reflect the inherent connection between the data. Since the position of the target data group has been determined, the fusion position of the data group to be fused is also determined. This position determination not only ensures the accuracy of data fusion, but also improves the efficiency of data processing.

[0096] In general, through the above steps, the same pre-processed data can be effectively fused to generate fused data with higher value and better application prospects. This process requires not only precise calculation and analysis, but also a deep understanding of the inherent structure and relevance of the data. In this way, the quality and effect of data fusion can be ensured, providing a solid foundation for subsequent data analysis and application.

[0097] The formula for calculating the similarity between the real-time signal data set and the alarm collection data is:

[0098]

[0099] In the formula, S i is the similarity between the real-time signal dataset and the i-th feature of the alarm set data, w ij is the jth feature index value of the i-th feature of the alarm set data, v ij is the jth feature index value of the ith feature of the alarm collection data, and p is the total number of ith feature index values.

[0100] The formula for calculating the matching rate is:

[0101]

[0102] Where C is the degree of fit between the characteristic parameters of the real-time signal data set and the characteristic parameters of the alarm set data, α i is the weight value of the i-th feature parameter, and m is the total number of feature parameters.

[0103] A railway signal equipment operation data analysis system, used to implement the analysis method in the first embodiment, comprising:

[0104] In this system, the data acquisition module is responsible for collecting the operating data of railway signal equipment. These railway signal equipment cover multiple key areas, including but not limited to computer interlocking equipment, train control center equipment, track circuit equipment, dispatching centralized equipment, signal centralized monitoring equipment, train automatic protection equipment and temporary speed limit server. The operating data of these equipment is crucial to ensure the safe and efficient operation of the railway system.

[0105] The data preprocessing module performs preliminary processing on the acquired operation data. The preprocessing step includes filling in missing values ​​in the data to ensure the accuracy and reliability of subsequent analysis. This link is a key step in the data processing process because it directly affects the quality of the data and the effectiveness of subsequent analysis.

[0106] The data fusion module performs further analysis based on the preprocessed data. It calculates the central tendency of the preprocessed data, such as the mean, median, etc., and the degree of dispersion, such as the standard deviation, variance, etc. In addition, the module also divides the preprocessed data into several categories and fuses the preprocessed data of the same category to facilitate subsequent data analysis and processing.

[0107] The dataset construction module uses the fused data to construct a signal dataset. This dataset is the basis for subsequent analysis and model training, and will provide important data support for the monitoring and early warning of the railway signal system.

[0108] The function of the marking module is to retrieve and mark the operating data of each railway signal device before the signal alarm state occurs. These data are specially marked as alarm collection data to facilitate subsequent analysis and processing. In this way, the system can better identify and predict potential alarm states.

[0109] The matching module is responsible for calculating the similarity and matching rate between the real-time signal data set and the alarm set data. Through this calculation, the system can identify the similarity between the current operation data and the historical alarm data, thereby predicting the potential alarm status.

[0110] The screening optimization module screens similarities and matching rates through threshold comparison to determine which data points are most likely to indicate an alarm state. In addition, the module also optimizes the operating status of railway signaling equipment, adjusting and improving the operating parameters of the equipment to improve the overall performance and reliability of the system.

[0111] A computer-readable storage medium stores a computer program, characterized in that when the program is executed by a processor, the above-mentioned analysis method of railway signal equipment operation data is implemented.

[0112] In summary, the present invention collects the operating data of each railway signal device online, fills the missing values ​​of the operating data of the device, so that the operating data is complete and has processing value. By classifying and fusing the data, the memory of data of the same type becomes smaller, and the data processing speed is improved. These data are formed into a set, and further, the operating data of each device before the signal alarm state occurs is retrieved. This operating data is for the data one hour before the alarm state, and the time difference cannot be large, otherwise it has no reference value. The real-time signal data set and the alarm set data are calculated for similarity and matching rate, and the railway signal equipment that is about to fail can be obtained, and an alarm is issued and optimized, thereby reducing the maintenance cost of the railway signal equipment, avoiding the occurrence of safety accidents, and meeting the needs of the staff.

[0113] The above shows and describes the basic principles, main features and advantages of the present invention. Those skilled in the art should understand that the present invention is not limited to the above embodiments. The above embodiments and descriptions only describe the principles of the present invention. The present invention may be subject to various changes and improvements without departing from the spirit and scope of the present invention. These changes and improvements fall within the scope of the present invention. The scope of protection claimed by the present invention is defined by the attached claims and their equivalents.

Claims

1. A method for analyzing railway signal equipment operation data, characterized in that: include: Acquiring operation data of railway signal equipment, including computer interlocking equipment, train control center equipment, track circuit equipment, centralized dispatching equipment, centralized signal monitoring equipment, automatic train protection equipment and temporary speed limit server; Preprocessing the running data, wherein the preprocessing includes filling missing values ​​of the data; Calculate the central tendency and dispersion of preprocessed data, divide the preprocessed data into several categories, and merge the preprocessed data of the same category; Use fused data to construct signal datasets; Retrieving the operation data of each railway signal device before the signal alarm state occurs, and naming the operation data of each railway signal device before the alarm state as alarm aggregate data; Calculate the similarity and matching rate between the real-time signal data set and the alarm collection data; The similarity and matching rate are screened by a threshold comparison method, and the operating status of the railway signal equipment is optimized.

2. The method for analyzing railway signal equipment operation data according to claim 1, characterized in that: The missing value filling comprises the following steps: Where D i is the filling data; i is the number of filling data; D j are different types of historical operation data; n is the number of different types of historical operation data.

3. The method for analyzing railway signal equipment operation data according to claim 2, characterized in that: The calculation of the central tendency and dispersion degree of the preprocessed data specifically includes the following steps: Calculate the data mean of the preprocessed data, and calculate the variance of the preprocessed data according to the variance formula; Setting the variance as the central tendency of the preprocessed data and assigning a trend identification code to the central tendency; Pairing each data in the preprocessed data with the remaining data in the preprocessed data to obtain at least one paired group; Calculate the absolute value of the difference between two preprocessed data in each paired group of preprocessed data, and accumulate the absolute values ​​of the difference between two data in all paired groups to obtain a discrete value; The discrete value is set as the discrete degree of the data, and a discrete identification code is assigned to the discrete degree.

4. The method for analyzing railway signal equipment operation data according to claim 3, characterized in that: The calculation formula of the variance is as follows: Among them, D is the variance, q is the number of data, x i is the value of the data, and a is the average value of the data.

5. The method for analyzing railway signal equipment operation data according to claim 4, characterized in that: The method of dividing the pre-processed data into several categories comprises the following steps: Retrieve the historical data classification and discrimination standard 1 from the database, and obtain the range interval of the central tendency ratio and the range interval of the dispersion ratio in the classification and discrimination standard 1; Calculate the first ratio of the central tendency of the data to the central tendency mean of the sample data; Calculate the second ratio of the degree of dispersion of the data to the mean of the degree of dispersion of the sample data; Compare whether the first ratio falls within the range of the central tendency ratio; Compare whether the second ratio belongs to the range interval of the dispersion ratio; If the first ratio belongs to the range of the central tendency ratio and the second ratio belongs to the range of the dispersion ratio, calling the classification in the classification discrimination group 1, setting the classification as the first classification, and classifying the data into the first classification; If the first ratio does not belong to the range of the central tendency ratio or the second ratio does not belong to the range of the dispersion ratio, the remaining classification discrimination groups in the data type determination model are called; Find the second historical data classification discrimination criterion in the remaining classification discrimination groups, and the second classification discrimination criterion satisfies that the first ratio of the data belongs to the range interval of the central tendency ratio of the classification discrimination group two and the second ratio of the data belongs to the range interval of the dispersion ratio of the classification discrimination group two, call the classification in the classification discrimination group two, set the classification to the second classification, and classify the data into the second classification.

6. The method for analyzing railway signal equipment operation data according to claim 5, characterized in that: The fusion of the same type of pre-processed data specifically includes the following steps: Retrieve pre-processed data belonging to the first category and the second category; Fusing the preprocessed data of the first classification to obtain first classification fused data; The preprocessed data of the second classification is fused to obtain the second classification fused data.

7. The method for analyzing railway signal equipment operation data according to claim 6, characterized in that: The formula for calculating the similarity is: In the formula, S i is the similarity between the real-time signal dataset and the i-th feature of the alarm set data, w ij is the jth feature index value of the i-th feature of the alarm set data, v ij is the jth feature index value of the ith feature of the alarm collection data, and p is the total number of ith feature index values.

8. The method for analyzing railway signal equipment operation data according to claim 7, characterized in that: The calculation formula of the matching rate is: Where C is the degree of fit between the characteristic parameters of the real-time signal data set and the characteristic parameters of the alarm set data, α i is the weight value of the i-th feature parameter, and m is the total number of feature parameters.

9. A railway signal equipment operation data analysis system, characterized in that: include: A data acquisition module, which acquires the operation data of railway signal equipment, wherein the railway signal equipment includes computer interlocking equipment, train control center equipment, track circuit equipment, dispatching centralized equipment, signal centralized monitoring equipment, train automatic protection equipment and temporary speed limit server; A data preprocessing module, which preprocesses the operation data, wherein the preprocessing includes filling missing values ​​of the data; Data fusion module, which calculates the central tendency and dispersion degree of preprocessed data, divides the preprocessed data into several categories, and fuses the preprocessed data of the same category; The data set construction module uses the fused data to construct the signal data set; The marking module retrieves the operation data of each railway signal device before the signal alarm state occurs, and names the operation data of each railway signal device before the alarm state as alarm set data; The matching module calculates the similarity and matching rate between the real-time signal data set and the alarm set data; The screening optimization module screens the similarity and matching rate through a threshold comparison method, and optimizes the operating status of the railway signal equipment.

10. A computer-readable storage medium storing a computer program, characterized in that: When the program is executed by a processor, the method for analyzing railway signal equipment operation data as described in any one of claims 1 to 8 is implemented.

Images