Signal equipment state identification method and device, equipment, medium and product

Abstract

The invention discloses a state identification method and device of signal equipment, equipment, a medium and a product. The state identification method of the signal equipment comprises the following steps: acquiring time sequence monitoring data of a to-be-monitored component in the railway signal equipment, and extracting data in a daily target time period from the time sequence monitoring data as time period data; determining a time period characteristic value in a daily target time period based on the time period data, and constructing a trend curve according to the time period characteristic values of the target time periods of multiple days; trend characteristics are extracted from the trend curve in a window sliding mode, and degradation trend analysis of the to-be-monitored component is carried out according to the trend characteristics; and determining the health state of the railway signal equipment based on the degradation trend analysis result. According to the technical scheme provided by the embodiment of the invention, the progressive degradation trend of the signal equipment is captured by constructing the trend curve to carry out degradation trend analysis, and the operation and maintenance perspectiveness of the railway signal equipment is improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of rail transit technology, and in particular to a signal device state recognition method, device, equipment, medium and product. BACKGROUND

[0002] Railway signal devices are the core infrastructure for ensuring train operation safety and improving transportation efficiency. These devices are exposed to complex natural and electrical environments for a long time, and are affected by multiple factors such as vibration, temperature change, environmental erosion, and electrical load. The internal components of the devices inevitably experience progressive performance degradation, i.e., "deterioration", over time. If such hidden deterioration trends are not detected in time, they may eventually cause sudden failures, affecting the order and safety of railway operation.

[0003] In the prior art, railway signal device fault diagnosis mainly relies on traditional alarm logic and analysis of basic data from centralized monitoring systems. Existing solutions trigger alarms when device parameters exceed a fixed threshold, for example, diagnosis of X4 disconnection and other faults.

[0004] Current railway signal device operation and maintenance mode highly depends on post-fault maintenance, with strong passive responsiveness but insufficient proactive prevention. As the requirements for device reliability and proactive operation and maintenance of railway transportation become increasingly urgent, it is important to identify the progressive deterioration trend of device components and shift from post-fault maintenance to trend early warning maintenance, in order to improve the proactive and effectiveness of railway signal device operation and maintenance. SUMMARY

[0005] The present application provides a signal device state recognition method, device, equipment, medium and product to solve the problem that railway signal device operation and maintenance relies on post-fault maintenance.

[0006] According to an aspect of the present application, a signal device state recognition method is provided, comprising: Obtaining time series monitoring data of a to-be-monitored component in a railway signal device, and extracting data in a daily target period as period data in the time series monitoring data; Determining a period characteristic value in the daily target period based on the period data, and constructing a trend curve according to period characteristic values of multiple daily target periods; Extracting a trend feature in the trend curve by a sliding window method, and performing deterioration trend analysis of the to-be-monitored component according to the trend feature; Determining the health status of the railway signal device based on the deterioration trend analysis result.

[0007] According to another aspect of the present application, a signal device state recognition device is provided, comprising: The monitoring data acquisition module is used to acquire the time-series monitoring data of the components to be monitored in the railway signaling equipment, and extract the data within the daily target time period from the time-series monitoring data as time period data; The trend curve construction module is used to determine the time period characteristic values ​​within the daily target time period based on the time period data, and to construct a trend curve based on the time period characteristic values ​​of the target time periods over multiple days. The degradation trend analysis module is used to extract trend features from the trend curve through a sliding window, and to perform degradation trend analysis on the component to be monitored based on the trend features. The health status determination module is used to determine the health status of the railway signaling equipment based on the deterioration trend analysis results.

[0008] According to another aspect of the present invention, an electronic device is provided, the electronic device comprising: At least one processor; and A memory communicatively connected to the at least one processor; wherein, The memory stores a computer program that can be executed by the at least one processor, the computer program being executed by the at least one processor to enable the at least one processor to perform the signal device state identification method according to any embodiment of the present invention.

[0009] According to another aspect of the present invention, a computer-readable storage medium is provided, the computer-readable storage medium storing computer instructions for causing a processor to execute and implement the state identification method of a signal device according to any embodiment of the present invention.

[0010] According to another aspect of the present invention, a computer program product is provided, including a computer program that, when executed by a processor, implements a state recognition method for a signal device according to any embodiment of the present disclosure.

[0011] The technical solution of this invention involves acquiring time-series monitoring data of components to be monitored in railway signaling equipment, extracting data within daily target time periods from the time-series monitoring data as time period data, determining time period characteristic values ​​within daily target time periods based on the time period data, constructing trend curves based on the time period characteristic values ​​of multiple target time periods, extracting trend features from the trend curves using a sliding window approach, and performing degradation trend analysis on the components to be monitored based on the trend features. Based on the degradation trend analysis results, the health status of the railway signaling equipment is determined. By collecting time-series monitoring data of each component in the railway signaling equipment and constructing trend curves for degradation trend analysis, the gradual degradation trend of the signaling equipment is captured, guiding maintenance personnel to locate potential fault points and improving operation and maintenance efficiency.

[0012] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of the present invention, nor is it intended to limit the scope of the invention. Other features of the invention will become readily apparent from the following description. Attached Figure Description

[0013] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are 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.

[0014] Figure 1 This is a flowchart of a signal device status identification method according to Embodiment 1 of the present invention; Figure 2 This is a flowchart of a signal device status identification method according to Embodiment 2 of the present invention; Figure 3 This is a schematic diagram of the structure of a status identification device for a signal device according to Embodiment 3 of the present invention; Figure 4 This is a schematic diagram of the structure of an electronic device that implements the signal device state recognition method of the present invention. Detailed Implementation

[0015] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0016] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0017] Example 1 Figure 1 This is a flowchart illustrating a method for identifying the state of signaling equipment according to Embodiment 1 of the present invention. This embodiment is applicable to situations where degradation analysis of components in railway signaling equipment is performed by constructing trend curves. This method can be executed by a state identification device for the signaling equipment, which can be implemented in both hardware and software and can be configured in various general-purpose computing devices. Figure 1 As shown, the method includes: S110. Obtain the time-series monitoring data of the components to be monitored in the railway signaling equipment, and extract the data within the daily target time period from the time-series monitoring data as time period data.

[0018] Railway signaling equipment is a technical device installed along railway lines and at stations to transmit control commands, indicate train operating conditions, and ensure train safety and efficiency. For example, railway signaling equipment includes hydraulic turnouts, ZPW2000 track circuits, and 25Hz track circuits.

[0019] Time-series monitoring data is a sequence of electrical parameters collected continuously in chronological order, reflecting the operating status of various components of railway signaling equipment. For example, time-series monitoring data includes analog data and digital data. Analog data includes continuous data values ​​such as voltage, current, and phase angle, while digital data includes state changes such as relay activation / deactivation or circuit breaker on / off states.

[0020] The target time period is a fixed time interval set daily for accurate trend analysis, such as 9:00-10:00 AM. The time period data is a subset of data belonging to the target time period extracted from the full-day time-series monitoring data.

[0021] In this embodiment of the invention, time-series monitoring data of the components to be monitored in railway signaling equipment are acquired. Specifically, for analog parameters, a centralized monitoring system can be configured with a fixed frequency, such as once per minute, to perform timed acquisition at equal intervals, ensuring that the data density meets the needs of subsequent analysis. For digital parameters, state-triggered acquisition is adopted, recording events only when the state changes, avoiding the recording of a large amount of repetitive state data and saving storage and processing resources.

[0022] Furthermore, based on the preset target time period definition, the original data points belonging to the target time period are filtered and extracted from the time series data stream of the whole day as time period data, so as to facilitate subsequent trend analysis.

[0023] In a specific example, the railway signaling equipment is a hydraulic turnout, and the associated components to be monitored include an automatic switch and a BHJ relay. The X1X3 voltage associated with the automatic switch and the BHJ voltage associated with the BHJ relay are collected according to a set sampling frequency. Then, the data from 9:00 to 10:00 is extracted from the X1X3 voltage throughout the day as the time period data.

[0024] S120. Determine the time period characteristic values ​​within the daily target time period based on the time period data, and construct a trend curve based on the time period characteristic values ​​of the target time periods over multiple days.

[0025] The time-period feature value is a characteristic value that represents the overall level of equipment parameters during a specific time period by aggregating and calculating all the raw data of the target time period within a day using a set algorithm.

[0026] A trend curve is a curve formed by connecting the time-period characteristic values ​​of the same target time period across different dates in chronological order. Unlike time series charts, the core feature of a trend curve is that it spans multiple dates and time periods. For example, a trend curve can be an hourly trend curve, such as one formed by connecting the time-period characteristic values ​​corresponding to the 9:00-10:00 time period each day of a month.

[0027] In this embodiment of the invention, based on the time period data within the daily target time period, the time period characteristic value of the target time period can be calculated directly by averaging. Furthermore, the time period characteristic values ​​of the same target time period over multiple consecutive days are connected in chronological order to form a trend curve. Specifically, with the date as the horizontal axis and the time period characteristic value as the vertical axis, a connecting line is drawn to form an hourly trend curve representing the long-term change trend within a fixed time period. For example, a voltage hourly trend curve for the 9:00-10:00 time period (X1X3) can be constructed daily.

[0028] S130. Extract trend features from the trend curve using a sliding window, and perform degradation trend analysis on the component to be monitored based on the trend features.

[0029] A sliding window defines a subsequence of fixed length on a time series, i.e., a trend curve. For example, the sliding window size is 7 days, and then this subsequence slides from beginning to end point by point, performing calculations and analysis at each window position.

[0030] Trend characteristics are quantitative indicators extracted by analyzing the local or overall shape of trend curves. They can characterize the changing patterns of characteristic values ​​over a period of time. For example, trend characteristics include the slope of change (reflecting the rate of deterioration) and the standard deviation of fluctuation (reflecting operational stability).

[0031] In this embodiment of the invention, a sliding window of length L, such as 7 days, is set on the generated trend curve. Each time the window slides, the slope (reflecting the average rate of change) and standard deviation (reflecting the dispersion of the data around the trend line) within the window are calculated as trend features. After sliding through the entire curve, a series of feature tuples characterizing the changes within different windows are obtained, such as (time interval, slope, standard deviation) as trend features.

[0032] Furthermore, the extracted trend features are compared with a pre-established degradation model library. The fuzzy comprehensive evaluation method is used to calculate the matching degree between the trend features and the standard features corresponding to each degradation model in the degradation model library. If the matching degree exceeds the high confidence threshold, the current trend is determined to conform to the degradation model.

[0033] S140. Based on the deterioration trend analysis results, determine the health status of railway signaling equipment.

[0034] In this embodiment of the invention, the health status of railway signaling equipment is determined based on the degradation trend analysis results in S130. Specifically, the health status can be determined jointly based on the time period characteristic values ​​in the trend curve, whether they match the degradation model, and the level of degradation mechanism associated with the degradation model.

[0035] For example, when all time-period feature values ​​are within the health boundary and no degradation model is matched, the health status of the railway signaling equipment is determined to be healthy; when the time-period feature values ​​exceed the health boundary but do not exceed the yellow warning boundary, and a degradation model is matched, with the degradation mechanism level corresponding to the degradation model being "slight degradation", the health status of the railway signaling equipment is determined to be sub-healthy; when the time-period feature values ​​exceed the yellow warning boundary, and a degradation model is matched, with the degradation mechanism level corresponding to the degradation model being "moderate / severe degradation", the health status of the railway signaling equipment is determined to be a fault warning.

[0036] The technical solution of this invention involves acquiring time-series monitoring data of components to be monitored in railway signaling equipment, extracting data within daily target time periods from the time-series monitoring data as time period data, determining time period characteristic values ​​within daily target time periods based on the time period data, constructing trend curves based on the time period characteristic values ​​of multiple target time periods, extracting trend features from the trend curves using a sliding window approach, and performing degradation trend analysis on the components to be monitored based on the trend features. Based on the degradation trend analysis results, the health status of the railway signaling equipment is determined. By collecting time-series monitoring data of each component in the railway signaling equipment and constructing trend curves for degradation trend analysis, the gradual degradation trend of the signaling equipment is captured, guiding maintenance personnel to locate potential fault points and improving operation and maintenance efficiency.

[0037] Example 2 Figure 2This is a flowchart of a signal device status identification method provided in Embodiment 2 of the present invention. This embodiment further refines the above embodiment, providing specific steps for determining time-period characteristic values ​​within a daily target time period based on the time-period data, constructing a trend curve based on the time-period characteristic values ​​of multiple target time periods, extracting trend features from the trend curve using a sliding window method, and performing degradation trend analysis of the monitored component based on the trend features. Figure 2 As shown, the method includes: S210. Obtain the time-series monitoring data of the components to be monitored in the railway signaling equipment, and extract the data within the daily target time period from the time-series monitoring data as time period data.

[0038] Optionally, acquiring time-series monitoring data of the components to be monitored in the railway signaling equipment, and extracting data within the daily target time period from the time-series monitoring data as time period data, including: For the analog parameters associated with the component to be monitored, time-series monitoring data of the analog parameters are collected according to the set acquisition frequency; For the switch parameters associated with the component to be monitored, when the switch state changes, the timing monitoring data of the switch parameters is collected; The time-series monitoring data undergoes a preprocessing operation to remove outliers.

[0039] In this optional embodiment, a specific method is provided for acquiring time-series monitoring data of components to be monitored in railway signaling equipment and extracting data within the target time period of each day from the time-series monitoring data as time period data: For the analog parameters associated with the components to be monitored, time-series monitoring data of the analog parameters are collected according to a set acquisition frequency, for example, once per minute, and timed acquisition is performed at equal intervals to ensure that the data density meets the needs of subsequent analysis.

[0040] For the switching parameters associated with the components under monitoring, time-series monitoring data of the switching parameters are collected when the switching state changes. Events are recorded only when the state changes, avoiding the recording of a large amount of duplicate state data and saving storage and processing resources. Furthermore, outlier removal preprocessing is performed on the time-series monitoring data.

[0041] Optionally, the preprocessing operation of outlier removal for the time-series monitoring data includes: Calculate the mean and standard deviation of the time-series monitoring data within a fixed time window; Based on the mean and standard deviation, the data range is determined, and data in the time-series monitoring data that exceed the data range are marked as suspected outliers. Extract a set number of target data points before and after the suspected outlier, and determine the trend of the target data points. If the suspected outlier is an isolated deviation point, remove the suspected outlier as an outlier.

[0042] In this optional embodiment, a specific method is provided for the preprocessing operation of outlier removal of the time-series monitoring data: calculating the mean and standard deviation of the time-series monitoring data within a fixed time window. Then, based on the mean and standard deviation, an outlier removal process is adopted. Criteria for determining the range of data values ,in, It is the mean of time-series monitoring data within a fixed window. It is the standard deviation of the time-series monitoring data within a fixed window.

[0043] Data exceeding the range of values ​​in the time-series monitoring data are marked as suspected outliers. Further, a set number of target data points are extracted before and after the suspected outlier; for example, five target data points constitute a local data segment. Linear fitting or simple difference calculations are performed on this local segment to determine the overall trend of the data, such as a slow upward, downward, or stable trend. Then, it is determined whether the suspected outlier deviates significantly from this local trend. If it does, the suspected outlier is identified as an isolated deviation point, considered to be caused by transient interference, and removed from the dataset as an outlier.

[0044] S220. Calculate the time period characteristic value of the target time period based on the time period data within the daily target time period.

[0045] In this embodiment of the invention, a time period feature value is calculated for the time period data within a daily target time period. Specifically, the average of multiple time period data within the daily target time period can be calculated as the time period feature value of the target time period.

[0046] S230. Connect the time period characteristic values ​​of the target period over multiple days to form a trend curve.

[0047] In this embodiment of the invention, after calculating the time-period characteristic values ​​for the daily target time period, a trend curve is constructed by connecting the time-period characteristic values ​​of the target time periods over multiple days, with the date as the horizontal axis and the hourly characteristic values ​​as the vertical axis. Constructing a trend curve allows for comparison of monitoring data for the same time period each day, avoiding interference from temperature differences (e.g., high-temperature noon versus low-temperature early morning) that could affect the comparison of monitoring data, thus accurately reflecting the daily degradation trend of the monitored components.

[0048] S240. Using a sliding window approach, calculate the slope and standard deviation of the characteristic values ​​for each time period within the trend curve as trend features.

[0049] In this embodiment of the invention, a sliding window approach is used to calculate the slope and standard deviation of the characteristic values ​​within each window period in the trend curve as trend features. Specifically, a first set duration, such as one month, is used as the analysis period, and a second set duration, such as seven days, is set as the sliding window. The slope and standard deviation of the trend curve within each sliding window are calculated as trend features. The slope can be obtained by fitting a straight line using the least squares method.

[0050] Each time the window is slid, a set of trend features including slope and standard deviation is output, representing the changing trend and fluctuation level of the sequence monitoring data within each time window.

[0051] In addition, for the main rail voltage of the ZPW2000 track circuit, an additional "interpolation change rate of adjacent sliding windows" is extracted. This involves calculating the difference between the maximum and minimum voltages in two adjacent sliding windows, and then calculating the rate of change of this difference within those two windows. If the rate of change of the voltage difference between the later and earlier sliding windows exceeds a set threshold, it is marked as an "accelerated degradation" feature. For the phase angle of 25H in the track circuit, the cumulative deviation from the standard value is extracted. If the cumulative deviation increases from 5° to 12° within a set time period (e.g., one month), it is marked as an "expanded deviation" feature.

[0052] S250. Compare the trend features with the preset standard features to obtain the feature matching degree.

[0053] The preset standard features are pre-established trend feature templates corresponding to specific degradation models. Each standard feature defines the numerical range of indicators such as slope and standard deviation when a certain degradation occurs. For example, the feature of "monthly gradual decrease of X1X3 voltage by 5V or more with increased fluctuation" for hydraulic turnouts matches "indicating progressive degradation model of circuit contact / insulation components"; the feature of "monthly gradual decrease of main rail voltage by 8% or more" for ZPW2000 track circuits matches "transmission link compensation capacitor aging model"; and the feature of "cumulative phase angle deviation of 10° or more" for 25Hz track circuits matches "protection box capacitor degradation model".

[0054] In this embodiment of the invention, the fuzzy comprehensive evaluation method is used to calculate the matching degree. Specifically, a fuzzy membership function is established for each index under each standard feature, such as slope and standard deviation. The membership function defines the degree to which different values ​​within the interval belong to "perfect match", "high match" and "general match" (the membership value is between 0 and 1).

[0055] Furthermore, the actual extracted slope and standard deviation are substituted into the membership function of the corresponding standard feature to calculate the membership value on each indicator. Finally, a weighted average is used to aggregate the membership values ​​of each indicator, and the result is the feature matching degree.

[0056] S260. When the feature matching degree is greater than the set matching degree threshold, determine the degradation model corresponding to the trend feature based on the mapping relationship between the standard feature and the degradation model.

[0057] In this embodiment of the invention, when the feature matching degree is greater than a set matching degree threshold, the degradation model corresponding to the trend feature is determined according to the mapping relationship between the standard feature and the degradation model, that is, the degradation model corresponding to the standard feature is directly determined as the degradation model matching the current trend feature.

[0058] In addition, if the feature matching degree between the trend feature and the preset standard feature is less than the matching degree threshold but greater than the degradation threshold, the corresponding degradation model is further determined based on the time-series monitoring data of other components to be monitored associated with the current railway signaling equipment. Specifically, the time-series monitoring data of other components to be monitored can be compared with the preset normal range. If they are not within the normal range, the degradation model corresponding to the current trend feature and the standard feature is determined to match.

[0059] In a specific example, taking "the monthly gradual decrease of X1X voltage to 5V and above with increased fluctuations as an example, if it does not reach 5V but reaches 4.5V", then a certain feature has a matching degree of ≥85% with the model, and is judged as "high confidence matching", and directly enters the mechanism tracing stage.

[0060] If the matching degree is between 60% and 85%, then other related parameters are combined. For example, when the voltage of hydraulic turnout X1X3 is abnormal, the voltage of BHJ is simultaneously compared to see if it is normal, further verification is performed to improve the matching accuracy. For instance, if the voltage of hydraulic turnout X1X3 is abnormal and the matching degree is between 60% and 85%, then it is further determined whether the voltage of BHJ is within the normal range. If not, then the trend feature is determined to be a "high confidence match" with the model, and the process directly proceeds to the mechanism tracing stage.

[0061] S270. Based on the degradation model, the degradation mechanism leading to the trend characteristics is determined by the Bayesian network inference algorithm, and the trend curve, degradation model and degradation mechanism are used as the degradation trend analysis results.

[0062] In this embodiment of the invention, based on the degradation model, the degradation mechanism leading to the trend characteristics is determined using a Bayesian network inference algorithm. Finally, the trend curve, degradation model, and degradation mechanism are used as the results of the degradation trend analysis. Specifically, based on the matched degradation model, potential fault points and degradation mechanisms are traced according to the correlation between components in the railway signaling equipment. For example, after the "degradation model of circuit contact components" for a hydraulic turnout is successfully matched, based on the correlation between "X1X3 voltage—automatic switch contact—cable core wire," and combined with the characteristic of "voltage fluctuations coinciding with train vibration periods" in the hourly trend curve, the degradation mechanism is traced back to "oxidation of automatic switch contacts + loosening of terminals."

[0063] Furthermore, for complex multi-factor degradation, a Bayesian network is pre-constructed for each degradation model. The root node in the network represents the degradation mechanism associated with the degradation model, such as capacitor aging or cable dampness, while the child nodes represent observable trend features. After determining the degradation model corresponding to the trend feature, the Bayesian network corresponding to the degradation model is invoked. The currently extracted trend feature is input into the response node of the Bayesian network, and the Bayesian inference algorithm is run. Based on the prior knowledge and conditional probabilities encoded in the network, the posterior probability of each degradation mechanism node under the current evidence is calculated. Finally, one or more degradation mechanisms are selected as the primary degradation mechanism output based on the posterior probability. Each degradation mechanism corresponds to a severity level. For example, "slight oxidation of the contact surface" and "initial decrease in insulation resistance" correspond to "slight degradation," while "capacitance decrease exceeding 20%" and "contact erosion leading to a significant increase in contact resistance" correspond to "moderate or severe degradation."

[0064] In a specific example, the voltage drop of the main rail of the ZPW2000 track circuit is accompanied by fluctuations in the voltage of the minor rail. The contribution of each factor is analyzed using a Bayesian network inference algorithm: By constructing a Bayesian network for "compensation capacitor aging (A), rail plug oxidation (B), and tuning unit parameter drift (C)," the prior probabilities trained by inputting historical fault data are used. For example, if the probability of A is 0.6, the probability of B is 0.3, and the probability of C is 0.1), the posterior probabilities are calculated by combining the current trend characteristics. If the posterior probabilities of A are 0.82, B is 0.15, and C is 0.03, then "compensation capacitor aging" is determined to be the main deterioration mechanism.

[0065] S280. Based on the deterioration trend analysis results, determine the health status of railway signaling equipment.

[0066] Optionally, based on the degradation trend analysis results, the health status of the railway signaling equipment is determined, including: If the time-period characteristic value in the trend curve is within the preset health parameter boundary range, and the trend characteristic does not match the deterioration model, then the railway signaling equipment is determined to be in a healthy state. If the time-period characteristic value in the trend curve is within the preset sub-health parameter boundary range, the trend feature matches the preset degradation model, and the corresponding degradation mechanism is slight degradation, then the railway signaling equipment is determined to be in a sub-healthy state. If the time-period characteristic value in the trend curve exceeds the preset fault parameter boundary, the trend feature matches the preset degradation model, and the corresponding degradation mechanism is moderate or above degradation, then the railway signaling equipment is determined to be in a fault warning state.

[0067] In this optional embodiment, a specific method is provided for determining the health status of the railway signaling equipment based on the deterioration trend analysis results: If the time-period characteristic value in the trend curve is within the preset health parameter boundary range, and the trend feature does not match a deterioration model, then the railway signaling equipment is determined to be in a healthy state. If the time-period characteristic value in the trend curve is within the preset sub-health parameter boundary range, and the trend feature matches a preset deterioration model, and the deterioration mechanism corresponding to the matched deterioration model is slight deterioration, then the railway signaling equipment is determined to be in a sub-healthy state. If the time-period characteristic value in the trend curve exceeds the preset fault parameter boundary, and the trend feature matches a preset deterioration model, and the deterioration mechanism corresponding to the matched deterioration model is moderate or above deterioration, then the railway signaling equipment is determined to be in a fault warning state. This achieves a triple verification mechanism of static boundary, dynamic model, and mechanism depth to jointly determine the equipment health status, avoiding false alarms and missed alarms.

[0068] In a specific example, for the AC voltage of hydraulic turnout X1X3, the healthy parameter boundary range is 100-110V (inclusive), the sub-healthy parameter boundary range is 95-100V (inclusive, excluding 100V), and the fault parameter boundary is less than 95V.

[0069] Optionally, after determining the health status of the railway signaling equipment based on the degradation trend analysis results, the method further includes: The compliance score of the parameters is determined based on the distance between the time period characteristic value in the trend curve and the preset boundary range of the health parameters; The trend stability score is determined based on the slope and standard deviation, as well as the pre-set range of slope and standard deviation. Based on the risk level of the aforementioned degradation mechanism, a mechanism risk score is determined, and the parameter compliance score, trend stability score, and mechanism risk score are weighted and summed to obtain the health score of the railway signaling equipment.

[0070] In this optional embodiment, specific steps are provided after determining the health status of the railway signaling equipment based on the deterioration trend analysis results: The parameter compliance score is determined according to the distance between the time-period characteristic value in the trend curve and the preset health parameter boundary range. The specific calculation formula is as follows: Where S1 is the parameter compliance score, M1 is the full parameter compliance score (e.g., 40 points), x is the mean of the characteristic values ​​for the current period, X is the ideal value, and d is the maximum permissible deviation between the ideal value and the fault boundary value.

[0071] For example, the ideal voltage for hydraulic turnout X1X3 is 105V, the fault boundary is 95V, and the maximum permissible deviation is 10V. If the current value is 100V, and the deviation is 5V, then S1 = 40 × (1 - 5 / 10) = 20 minutes.

[0072] Furthermore, the trend stability score is determined based on the slope and standard deviation, as well as pre-defined ranges for slope and standard deviation. Specifically, multiple ranges of values ​​for the standard deviation and slope can be set, along with a corresponding score for each range. The currently calculated slope and standard deviation are then compared with the pre-defined ranges to determine the trend stability score. The slope can be the average of the slopes corresponding to multiple sliding windows within an analysis period, and the standard deviation is the maximum value among the standard deviations corresponding to multiple sliding windows within an analysis period.

[0073] For example, a standard deviation ≤ 1.5V and an absolute slope ≤ 0.05V / day earns 30 points; a standard deviation of 1.5-3V and an absolute slope of 0.05-0.1V / day earns 18 points; and a standard deviation > 3V and an absolute slope > 0.1V / day earns 6 points.

[0074] Furthermore, based on the risk level of the degradation mechanism, a mechanism risk score is determined. The parameter compliance score, trend stability score, and mechanism risk score are then weighted and summed to obtain the health score of the railway signaling equipment. Specifically, based on the risk level corresponding to the degradation mechanism, "minor degradation" receives 30 points, "moderate degradation" receives 15 points, and "severe degradation" receives 3 points. Finally, the parameter compliance score, trend stability score, and mechanism risk score are weighted and summed to obtain the health score of the railway signaling equipment. The weights of each score can be flexibly set according to actual needs.

[0075] The technical solution of this invention involves acquiring time-series monitoring data of components to be monitored in railway signaling equipment, extracting data within daily target time periods from the time-series monitoring data as time period data, determining time period characteristic values ​​within daily target time periods based on the time period data, constructing trend curves based on the time period characteristic values ​​of multiple target time periods, extracting trend features from the trend curves using a sliding window approach, and performing degradation trend analysis on the components to be monitored based on the trend features. Based on the degradation trend analysis results, the health status of the railway signaling equipment is determined. By collecting time-series monitoring data of each component in the railway signaling equipment and constructing trend curves for degradation trend analysis, the gradual degradation trend of the signaling equipment is captured, guiding maintenance personnel to locate potential fault points and improving operation and maintenance efficiency.

[0076] Example 3 Figure 3 This is a schematic diagram of the structure of a signal device status identification device provided in Embodiment 3 of the present invention. Figure 3 As shown, the device includes: The monitoring data acquisition module 310 is used to acquire the time-series monitoring data of the components to be monitored in the railway signaling equipment, and extract the data within the daily target time period from the time-series monitoring data as time period data; The trend curve construction module 320 is used to determine the time period characteristic value within the daily target time period based on the time period data, and to construct a trend curve based on the time period characteristic value of the target time period over multiple days. The degradation trend analysis module 330 is used to extract trend features from the trend curve through a sliding window and perform degradation trend analysis on the component to be monitored based on the trend features. The health status determination module 340 is used to determine the health status of the railway signaling equipment based on the deterioration trend analysis results.

[0077] The technical solution of this invention involves acquiring time-series monitoring data of components to be monitored in railway signaling equipment, extracting data within daily target time periods from the time-series monitoring data as time period data, determining time period characteristic values ​​within daily target time periods based on the time period data, constructing trend curves based on the time period characteristic values ​​of multiple target time periods, extracting trend features from the trend curves using a sliding window approach, and performing degradation trend analysis on the components to be monitored based on the trend features. Based on the degradation trend analysis results, the health status of the railway signaling equipment is determined. By collecting time-series monitoring data of each component in the railway signaling equipment and constructing trend curves for degradation trend analysis, the gradual degradation trend of the signaling equipment is captured, guiding maintenance personnel to locate potential fault points and improving operation and maintenance efficiency.

[0078] Optionally, the monitoring data acquisition module 310 includes: The first data acquisition unit is used to acquire time-series monitoring data of the analog parameters associated with the component to be monitored, according to a set acquisition frequency. The second data acquisition unit is used to acquire time-series monitoring data of the switch parameters associated with the component to be monitored when the switch state changes. The data preprocessing unit is used to perform outlier removal preprocessing on the time-series monitoring data.

[0079] Optional, the trend curve construction module 320 is specifically used for: Based on the time period data within the daily target time period, calculate the time period characteristic value of the target time period; The trend curve is formed by connecting the time-period characteristic values ​​of the target period over multiple days.

[0080] Optional, the degradation trend analysis module 330 includes: The trend feature calculation unit is used to calculate the slope and standard deviation of the time period feature values ​​within each window as trend features in the trend curve by means of a sliding window. The matching degree calculation unit is used to compare the trend features with preset standard features to obtain the feature matching degree; The degradation model determination unit is used to determine the degradation model corresponding to the trend feature based on the mapping relationship between the standard feature and the degradation model when the feature matching degree is greater than a set matching degree threshold. The degradation trend analysis unit is used to determine the degradation mechanism leading to the trend feature based on the degradation model using a Bayesian network inference algorithm, and to take the trend curve, degradation model and degradation mechanism as the degradation trend analysis result.

[0081] Optional, the health status determination module 340 is specifically used for: If the time-period characteristic value in the trend curve is within the preset health parameter boundary range, and the trend characteristic does not match the deterioration model, then the railway signaling equipment is determined to be in a healthy state. If the time-period characteristic value in the trend curve is within the preset sub-health parameter boundary range, the trend feature matches the preset degradation model, and the corresponding degradation mechanism is slight degradation, then the railway signaling equipment is determined to be in a sub-healthy state. If the time-period characteristic value in the trend curve exceeds the preset fault parameter boundary, the trend feature matches the preset degradation model, and the corresponding degradation mechanism is moderate or above degradation, then the railway signaling equipment is determined to be in a fault warning state.

[0082] Optionally, the status identification device for the signal equipment also includes: The first score calculation module is used to determine the health status of the railway signaling equipment based on the deterioration trend analysis results, and then determine the parameter compliance score according to the distance between the time period characteristic value in the trend curve and the preset health parameter boundary range. The second score calculation module is used to determine the trend stability score based on the slope and standard deviation, as well as a pre-set range of slope and standard deviation. The health score determination module is used to determine the mechanism risk score based on the risk level of the degradation mechanism, and to perform a weighted summation of the parameter compliance score, trend stability score, and mechanism risk score to obtain the health score of the railway signaling equipment.

[0083] Optional, a data preprocessing unit, specifically used for: Calculate the mean and standard deviation of the time-series monitoring data within a fixed time window; Based on the mean and standard deviation, the data range is determined, and data in the time-series monitoring data that exceed the data range are marked as suspected outliers. Extract a set number of target data points before and after the suspected outlier, and determine the trend of the target data points. If the suspected outlier is an isolated deviation point, remove the suspected outlier as an outlier.

[0084] The signal device status identification device provided in the embodiments of the present invention can execute the signal device status identification method provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of executing the method.

[0085] In the technical solution of this invention, the information collected is information and data authorized by the user or fully authorized by all parties. The collection, storage, use, processing, transmission, provision, disclosure and application of related data all comply with the relevant laws, regulations and standards of relevant countries and regions, take necessary confidentiality measures, do not violate public order and good morals, and provide corresponding operation entry points for users to choose to authorize or refuse.

[0086] Example 4 According to embodiments of the present invention, the present invention also provides an electronic device, a readable storage medium, and a computer program product.

[0087] Figure 4A schematic diagram of an electronic device 10 that can be used to implement embodiments of the present invention is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, application processors, blade application processors, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices (such as helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the invention described and / or claimed herein.

[0088] like Figure 4 As shown, the electronic device 10 includes at least one processor 11 and a memory, such as a read-only memory (ROM) 12 or a random access memory (RAM) 13, communicatively connected to the at least one processor 11. The memory stores computer programs executable by the at least one processor. The processor 11 can perform various appropriate actions and processes based on the computer program stored in the ROM 12 or loaded from storage unit 18 into the RAM 13. The RAM 13 can also store various programs and data required for the operation of the electronic device 10. The processor 11, ROM 12, and RAM 13 are interconnected via a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0089] Multiple components in electronic device 10 are connected to I / O interface 15, including: input unit 16, such as keyboard, mouse, etc.; output unit 17, such as various types of displays, speakers, etc.; storage unit 18, such as disk, optical disk, etc.; and communication unit 19, such as network card, modem, wireless transceiver, etc. Communication unit 19 allows electronic device 10 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0090] Processor 11 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. Processor 11 performs the various methods and processes described above, such as the state recognition method for signal devices.

[0091] In some embodiments, the signal device state identification method may be implemented as a computer program tangibly contained in a computer-readable storage medium, such as storage unit 18. In some embodiments, part or all of the computer program may be loaded and / or installed on electronic device 10 via ROM 12 and / or communication unit 19. When the computer program is loaded into RAM 13 and executed by processor 11, one or more steps of the signal device state identification method described above may be performed. Alternatively, in other embodiments, processor 11 may be configured to perform the signal device state identification method by any other suitable means (e.g., by means of firmware).

[0092] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SoCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations may include: implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0093] Computer programs used to implement the methods of the present invention can be written in any combination of one or more programming languages. These computer programs can be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when executed by the processor, the computer programs cause the functions / operations specified in the flowcharts and / or block diagrams to be performed. The computer programs can be executed entirely on a machine, partially on a machine, as a standalone software package partially on a machine and partially on a remote machine, or entirely on a remote machine or application.

[0094] In the context of this invention, a computer-readable storage medium can be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, apparatus, or device. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination thereof. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0095] To provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the electronic device. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0096] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as data application processors), or computing systems that include middleware components (e.g., application application processors), or computing systems that include frontend components (e.g., user computers with graphical user interfaces or web browsers through which users can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., communication networks). Examples of communication networks include local area networks (LANs), wide area networks (WANs), blockchain networks, and the Internet.

[0097] A computing system can include clients and applications. Clients and applications are generally geographically separated and typically interact via a communication network. The client-application relationship is established by computer programs running on the respective computers and having a client-application relationship with each other. An application can be a cloud application, also known as a cloud computing application or cloud server, which is a hosting product within the cloud computing application ecosystem. It addresses the shortcomings of traditional physical servers and VPS applications, such as high management difficulty and weak business scalability.

[0098] It should be understood that the various forms of processes shown above can be used, with steps reordered, added, or deleted. For example, the steps described in this invention can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution of this invention can be achieved, and this is not limited herein.

[0099] The specific embodiments described above do not constitute a limitation on the scope of protection of this invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this invention should be included within the scope of protection of this invention.

Claims

1. A method for identifying the status of a signal device, characterized in that, include: Acquire time-series monitoring data of the components to be monitored in the railway signaling equipment, and extract data within the daily target time period from the time-series monitoring data as time period data; Based on the time period data, determine the time period characteristic values ​​within the daily target time period, and construct a trend curve based on the time period characteristic values ​​of the target period over multiple days; Trend features are extracted from the trend curve using a sliding window, and degradation trend analysis of the components to be monitored is performed based on these trend features. Based on the deterioration trend analysis results, the health status of the railway signaling equipment is determined.

2. The method according to claim 1, characterized in that, Acquire time-series monitoring data of the components to be monitored in railway signaling equipment, and extract data within a daily target time period from the time-series monitoring data as time period data, including: For the analog parameters associated with the component to be monitored, time-series monitoring data of the analog parameters are collected according to the set acquisition frequency; For the switch parameters associated with the component to be monitored, when the switch state changes, the timing monitoring data of the switch parameters is collected; The time-series monitoring data undergoes a preprocessing operation to remove outliers.

3. The method according to claim 1, characterized in that, Based on the time period data, determine the time period characteristic values ​​within the daily target time period, and construct a trend curve based on the time period characteristic values ​​of the target time periods over multiple days, including: Based on the time period data within the daily target time period, calculate the time period characteristic value of the target time period; The trend curve is formed by connecting the time-period characteristic values ​​of the target period over multiple days.

4. The method according to claim 1, characterized in that, Trend features are extracted from the trend curve using a sliding window approach, and based on these features, degradation trend analysis of the component to be monitored is performed, including: By using a sliding window approach, the slope and standard deviation of the time period characteristic values ​​within each window are calculated as trend features in the trend curve; The trend features are compared with preset standard features to obtain the feature matching degree; If the feature matching degree is greater than a set matching degree threshold, the degradation model corresponding to the trend feature is determined according to the mapping relationship between the standard feature and the degradation model. Based on the degradation model, the degradation mechanism leading to the trend characteristics is determined by a Bayesian network inference algorithm, and the trend curve, degradation model, and degradation mechanism are used as the degradation trend analysis results.

5. The method according to claim 4, characterized in that, Based on the degradation trend analysis results, the health status of the railway signaling equipment is determined, including: If the time-period characteristic value in the trend curve is within the preset health parameter boundary range, and the trend characteristic does not match the deterioration model, then the railway signaling equipment is determined to be in a healthy state. If the time-period characteristic value in the trend curve is within the preset sub-health parameter boundary range, the trend feature matches the preset degradation model, and the corresponding degradation mechanism is slight degradation, then the railway signaling equipment is determined to be in a sub-healthy state. If the time-period characteristic value in the trend curve exceeds the preset fault parameter boundary, the trend feature matches the preset degradation model, and the corresponding degradation mechanism is moderate or above degradation, then the railway signaling equipment is determined to be in a fault warning state.

6. The method according to claim 4, characterized in that, After determining the health status of the railway signaling equipment based on the deterioration trend analysis results, the process further includes: The compliance score of the parameters is determined based on the distance between the time period characteristic value in the trend curve and the preset health parameter boundary range; The trend stability score is determined based on the slope and standard deviation, as well as the pre-set range of slope and standard deviation. Based on the risk level of the aforementioned degradation mechanism, a mechanism risk score is determined, and the parameter compliance score, trend stability score, and mechanism risk score are weighted and summed to obtain the health score of the railway signaling equipment.

7. The method according to claim 2, characterized in that, The preprocessing operation for outlier removal of the time-series monitoring data includes: Calculate the mean and standard deviation of the time-series monitoring data within a fixed time window; Based on the mean and standard deviation, the data range is determined, and data in the time-series monitoring data that exceed the data range are marked as suspected outliers. Extract a set number of target data points before and after the suspected outlier, and determine the trend of the target data points. If the suspected outlier is an isolated deviation point, remove the suspected outlier as an outlier.

8. A status identification device for a signaling device, characterized in that, include: The monitoring data acquisition module is used to acquire the time-series monitoring data of the components to be monitored in the railway signaling equipment, and extract the data within the daily target time period from the time-series monitoring data as time period data; The trend curve construction module is used to determine the time period characteristic values ​​within the daily target time period based on the time period data, and to construct a trend curve based on the time period characteristic values ​​of the target time periods over multiple days. The degradation trend analysis module is used to extract trend features from the trend curve through a sliding window, and to perform degradation trend analysis on the component to be monitored based on the trend features. The health status determination module is used to determine the health status of the railway signaling equipment based on the deterioration trend analysis results.

9. An electronic device, characterized in that, The electronic device includes: At least one processor; and A memory communicatively connected to the at least one processor; wherein, The memory stores a computer program that can be executed by the at least one processor, the computer program being executed by the at least one processor to enable the at least one processor to perform the state identification method of the signal device according to any one of claims 1-7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions that, when executed by a processor, implement the state identification method for the signal device according to any one of claims 1-7.

11. A computer program product, characterized in that, The computer program product includes a computer program that, when executed by a processor, implements the state identification method for a signal device according to any one of claims 1-7.

Images