A Smart Monitoring and Early Warning Method for Safe Operation of Subway Doors

Abstract

This invention belongs to the field of subway door monitoring and early warning technology. Specifically, it discloses an intelligent monitoring and early warning method for the safe operation of subway doors. By utilizing historical load records of the subway and using a statistical quantile method based on historical load distribution to divide the load status into three levels: low, medium, and high, and simultaneously associating differentiated early warning actions with each load level, the method determines the load level based on the current load status during actual subway operation. At the same time, it performs anomaly judgment by matching the operating parameters with the corresponding load level's limit threshold, thereby triggering the corresponding load level-related early warning action. This achieves targeted and flexible early warning for subway door operation, making the early warning operation more adaptable to the subway door's operating status. It can effectively reduce false alarms and missed alarms caused by fixed thresholds, ensuring that the early warning operation is both sensitive and stable.

Description

Technical Field

[0001] This invention belongs to the field of subway door monitoring and early warning technology, and specifically discloses an intelligent monitoring and early warning method for the safe operation of subway doors. Background Technology

[0002] As a critical safety component of the rail transit system, the operational status of subway doors directly impacts passenger safety. Any operational anomalies that are not addressed promptly may prevent the doors from opening or closing properly, affecting passenger boarding and alighting. In extreme cases, this could even lead to door jamming or accidental opening, threatening passenger lives. Therefore, real-time monitoring and early warning systems for subway doors are absolutely essential during subway operations.

[0003] Existing technologies also offer solutions. For example, Chinese patent CN107219837A discloses an intelligent system for monitoring and warning of subway platform screen door malfunctions. When a component or part of a subway platform screen door reaches the warning setting or a malfunction occurs, the platform operation monitoring module or the door control system monitoring module transmits the warning or malfunction information to the fault diagnosis module and the neural network fault warning module for classification and rating. The results are then fed back to the user through a display. This system can determine the fault type and fault location and can provide early warnings for foreseeable malfunctions.

[0004] Currently, subway door monitoring and early warning systems primarily rely on fixed thresholds for anomaly detection. This method fails to fully consider the dynamic characteristics of door opening and closing under different load conditions, which to some extent affects the reliability and efficiency of early warning systems. Specifically, during peak hours, frequent opening and closing of subway doors significantly increases the probability of anomalies. Using fixed thresholds for anomaly detection may lead to a higher risk of missed alarms because the thresholds may not be adequate for the high-frequency operation. For example, during peak hours, when doors are frequently opening and closing, fixed thresholds cannot effectively identify potential faults caused by mechanical fatigue, thus increasing the possibility of missed alarms.

[0005] During off-peak hours, subway doors open and close less frequently, reducing the probability of anomalies. However, because fixed thresholds are not adjusted according to the normal operating range under low load conditions, the false alarm rate may increase. For example, slight parameter fluctuations (such as a small increase in motor temperature) may trigger alarms under low load conditions, even though these fluctuations are normal under such conditions.

[0006] Furthermore, current subway door systems mostly use a uniform warning action, which cannot respond differently according to the load level. In particular, occasional anomalies under low load conditions may trigger unnecessary emergency shutdowns, which not only affect overall operational efficiency but also waste the human and material resources spent on maintenance shutdowns. Summary of the Invention

[0007] Therefore, one objective of this application is to provide an intelligent monitoring and early warning method for the safe operation of subway doors that can dynamically sense load status, adaptively adjust thresholds, and realize multi-level early warning, so as to improve the reliability and efficiency of subway door operation early warning and thus solve the problems mentioned in the background art.

[0008] The purpose of this invention can be achieved through the following technical solution: a smart monitoring and early warning method for the safe operation of subway doors, comprising the following steps: (1) defining the load status indicators as the number of times the door opens and closes and the passenger flow within a set unit time, thereby dividing the load status into three levels: low, medium and high based on the statistical quantile method of historical load distribution, and at the same time as associating early warning actions for each load level.

[0009] (2) Configure differentiated operating parameter limit thresholds for each load level based on the operating parameter fault performance characteristics in the historical fault records under different load levels. The operating parameter fault performance characteristics are the time sequence data of the operating parameters set in the time window before the fault occurs.

[0010] (3) Collect the door operation parameters in real time from the subway door control terminal interface, determine the load level according to the current load status indicators, and at the same time, make anomaly judgment by matching the collected operation parameters with the corresponding load level limit threshold.

[0011] (4) When an abnormal operation is detected, trigger the warning action associated with the load level.

[0012] (5) Periodically count the failure frequency of each load level and update the operating parameter limit threshold configuration accordingly.

[0013] Combining all the above technical solutions, the positive effects of this invention are as follows: 1. This invention uses historical load records and adopts the statistical quantile method to divide the load status into three levels: low, medium, and high, and associates specific early warning actions with each level. In actual operation, anomaly judgment is made by comparing the operating parameters with the limit threshold of the corresponding load level, and the corresponding early warning action is triggered. This can improve the pertinence and flexibility of the early warning, making it adaptable to the actual operating status, effectively reducing false alarms and missed alarms caused by fixed thresholds, and ensuring that the early warning operation has both sensitivity and stability.

[0014] 2. This invention defines load status indicators as the number of times the door opens and closes and the passenger flow within a set unit of time, thereby achieving a multi-dimensional assessment of load status. This provides a more comprehensive reflection of the actual operating conditions and can provide multi-dimensional data support for load level classification, ensuring that the definition of load levels is more reasonable and accurate.

[0015] 3. After implementing differentiated early warning based on load level, this invention dynamically updates the operating parameter limit threshold configuration by periodically statistically analyzing the fault frequency of each load level. This significantly improves the adaptability and accuracy of the system, ensures that the threshold settings always match the actual operating conditions, effectively reduces the risk of false alarms and missed alarms, and enhances the stability and reliability of the system. Attached Figure Description

[0016] The present invention will be further described with reference to the accompanying drawings, but the embodiments in the drawings do not constitute any limitation on the present invention. For those skilled in the art, other drawings can be obtained based on the following drawings without creative effort.

[0017] Figure 1 This is a diagram illustrating the implementation steps of the method of the present invention.

[0018] Figure 2 This is a schematic diagram illustrating the application of the tertiary load system in this invention, corresponding to three load levels: low, medium, and high.

[0019] Figure 3 This is a flowchart illustrating the implementation process of determining typical values ​​for the number of door openings and closings and typical values ​​for passenger flow within a single day in this invention. Detailed Implementation

[0020] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. 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 are within the scope of protection of the present invention.

[0021] See Figure 1 As shown, the present invention proposes an intelligent monitoring and early warning method for the safe operation of subway doors, including the following steps: (1) Define the load status indicators as the number of times the door is opened and closed and the passenger flow in a set unit time. Based on the statistical quantile method of historical load distribution, the load status is divided into three levels: low, medium and high. At the same time, an early warning action is associated with each load level.

[0022] In the example implementation of the above scheme, the unit time can be specifically quantified as an hour.

[0023] It's important to understand that the load on a subway door refers to the operational demands borne by the door within a specific timeframe. Combining the warning mechanism with load status is crucial because the probability of subway door malfunctions is closely related to its load condition. Particularly under high load conditions, frequent opening and closing operations and large passenger flows lead to increased wear on mechanical components, higher motor temperatures, and longer system response times, thus increasing the risk of failure. Therefore, integrating the warning mechanism with actual load status more accurately reflects the true operating condition of the subway door, ensuring that warning response measures better meet actual needs and improving the accuracy and reliability of the warning system.

[0024] It's also important to understand that using the number of opening and closing operations and passenger flow as indicators of subway door load status is primarily based on the following considerations: From an operational perspective, the number of opening and closing operations directly reflects the frequency of subway door operation within a specific time period. Frequent opening and closing operations not only increase wear and tear on mechanical components but may also lead to problems such as increased motor temperature and prolonged system response time. Therefore, the number of opening and closing operations is one of the important indicators for measuring the load of subway doors.

[0025] Passenger flow directly affects the frequency of boarding and alighting, which in turn determines the number of times the doors open and close. For example, during peak hours when passengers are boarding and alighting in large numbers, the doors open and close frequently, significantly increasing the load.

[0026] From the perspective of data availability: the number of opening and closing times and passenger flow are data that can be easily and accurately collected using existing sensors. For example, infrared array sensors can count the number of passengers entering and exiting the carriages, while subway door control systems typically have built-in opening and closing counters that can directly display the number of openings and closings on the control terminal interface.

[0027] By combining the number of opening and closing times and passenger flow, the load status of subway doors can be comprehensively assessed from multiple dimensions. A single indicator (such as the number of opening and closing times or passenger flow alone) may not be able to fully reflect the actual load situation, while the combination of the two can provide a more accurate load assessment, providing multi-dimensional data support for load level classification and ensuring that the definition of load levels is more reasonable and accurate.

[0028] In a preferred embodiment of the above-described solution of the present invention, the load status is divided into three levels—low, medium, and high—based on the statistical quantile method of historical load distribution, as described below: Load records for each unit time of each day within a historical year are extracted from the subway operation database. These load records contain load status indicators, and the load status indicators from the historical load records for each year are integrated into a door opening / closing count dataset and a passenger flow dataset, respectively. This ensures that the dataset for each year contains records for all unit times within the complete daily cycle.

[0029] The aforementioned subway operation database is formed by integrating multiple data sources, such as the door control system and infrared array sensors, to record the number of door openings and closings and passenger flow in real time. The door control system provides the number of openings and closings per hour, while the infrared array sensors count the passenger flow per hour. After cleaning and preprocessing, this data is stored in the subway operation database as a load record.

[0030] For the door opening / closing count dataset and passenger flow dataset of all years, data of the same unit time are extracted and the standard deviation is calculated. Based on this, the typical values ​​of door opening / closing count and passenger flow are determined for each unit time within a single day.

[0031] It's important to note that while the length of each day is fixed, passenger demand varies throughout the day, leading to corresponding changes in the operational demands on subway doors. To capture the daily load patterns across different time units within a single day, it's necessary to utilize load records for each time unit throughout historical years. This ensures data reliability and representativeness, avoiding biases and inaccuracies introduced by data from a single date. By extracting load records for each time unit over several years and calculating the standard deviation of door opening / closing times and passenger flow for each time unit across all years, we can reflect the fluctuations and determine typical values. This method accurately reflects load patterns across different time units within a single day, providing a solid data foundation for subsequent load level classification.

[0032] For further optimization and implementation of the above scheme, see [link to relevant documentation]. Figure 3 As shown, the typical values ​​of the number of door openings and closings and the typical values ​​of passenger flow for each unit time within a single day are determined as follows: The standard deviation of the number of door openings and closings and the standard deviation of passenger flow for each unit time within a single day are compared with the set critical values, where the standard deviation critical values ​​are preset and used to determine whether the data fluctuations are within an acceptable range.

[0033] If the standard deviation of the number of door openings and closings and the standard deviation of passenger flow in a certain unit of time do not exceed the critical value, it indicates that the data fluctuation in that unit of time is within an acceptable range, indicating that the operational demand is stable and there are no significant abnormal fluctuations. The average number of door openings and closings and the average passenger flow for all years corresponding to that unit of time are calculated as the typical value for that unit of time. Conversely, it indicates that the data fluctuation in that unit of time is large, and using the average as the typical value is not representative. In this case, the trimmed average is calculated for the dataset of all years corresponding to that unit of time as the typical value for that unit of time.

[0034] It's important to know that the trimmed mean, sometimes called the truncated mean, is a robust statistic used to reduce the impact of outliers on the calculation of the average. It achieves this by calculating the mean of the remaining data after removing a certain percentage of the maximum and minimum values ​​from the dataset. Compared to using the median, using the trimmed mean still utilizes most of the information from the original data, not just one or two middle values, thus providing a more robust and representative estimate of the central tendency.

[0035] In a specific example, assuming there are 100 data points in the dataset and the removal rate is 5%, first, all the values ​​in the dataset are sorted in ascending or descending order. Then, the 5% of extreme values ​​are removed, which means removing the lowest 5 values ​​and the highest 5 values, for a total of 10 data points. After removing the extreme values, the arithmetic mean is calculated using the remaining data points.

[0036] After sorting the typical values ​​of the number of door openings and closings and the typical values ​​of passenger flow in ascending order for each unit of time within a single day, the ternary quartile analysis method was applied to determine the first ternary quartile, the second ternary quartile, and the third ternary quartile for the number of door openings and closings and the passenger flow, respectively.

[0037] Based on the calculated third-order values, the load levels are classified as follows: Low load level: defined as the number of door openings and closings and passenger flow are both below their respective first third-order values, or one of them is below the first third-order value and the other is between its first and third third-order values, representing a low to one-third load level.

[0038] Medium load level: defined as a load level where both the number of door openings and passenger flow are between the first and third thirds of their respective tiers.

[0039] High load level: defined as the number of door openings or passenger flow exceeding their respective third third thirds, or one of them being lower than its first third third and the other higher than its third third third, representing a high load level pointing to the third third.

[0040] It should be noted that ternary analysis is a statistical method that divides a dataset into three equal parts. By determining the first ternary, the second ternary (i.e., the median), and the third ternary, the data distribution can be effectively divided.

[0041] In the specific implementation of the above operation, the steps of applying the ternary quantile analysis method are as follows: treat the number of switches and passenger flow in each unit of time as independent data points and arrange them in ascending order.

[0042] Calculate the quantile position: The first tertiary corresponds to the 25th percentile position in the permutation.

[0043] The second tertiary corresponds to the 50th percentile position in the permutation.

[0044] The third tertiary corresponds to the 75th percentile position in the permutation order.

[0045] In one example, suppose the number of times a door is opened and closed in ascending order over 24 time units in a day is: [10, 20, 30, 40, 50, 60, 70, 80, 90, 100, 110, 120, 130, 140, 150, 160, 170, 180, 190, 200, 210, 220, 230, 240]. The first tertiary corresponds to the 25th percentile position of the sorted order, which is the 6th value, approximately 60 times.

[0046] The second tertiary value corresponds to the 50% position in the permutation, which is the 12th value, approximately 120 times.

[0047] The third tertiary digit corresponds to the 75th percentile position in the permutation, which is the 18th value, approximately 180 times.

[0048] See Figure 2 As shown, the first tertiary of the main body corresponds to the low load level, the second tertiary corresponds to the medium load level, and the third tertiary corresponds to the high load level. However, the division based on the main body may lead to data omissions or unclear classifications.

[0049] Therefore, the present invention optimizes the specific division of load levels based on the main body division: low load level is suitable for situations where the pressure in at least one dimension is low, and allows for situations where the pressure in a certain dimension is high but is still classified as low load level, thereby avoiding unnecessary warnings or resource allocation due to temporary peaks in a single dimension. Although this situation occurs less frequently, it helps to improve the system's response efficiency.

[0050] Medium load rating is suitable for situations where both load dimensions are at a moderate level. It can accurately identify the load status within the normal operating range and is suitable for most daily operation scenarios.

[0051] High load levels are applicable to situations where at least one dimension is under high pressure or extremely unbalanced (one dimension is extremely low while the other is extremely high). This definition can effectively identify high load states, especially in cases of extreme imbalance. Although such situations are relatively rare, timely identification and handling of these high-risk situations are crucial for ensuring the safety and stability of the system.

[0052] The above-mentioned optimized partitioning method based on ternary digits ensures that each data point can be clearly classified into one of the three load levels: low, medium, and high, avoiding data omissions or unclear classifications.

[0053] The above method not only comprehensively covers all data points, but also provides detailed and reasonable classifications based on different dimensions of pressure levels, improving the accuracy of the early warning mechanism and optimizing resource allocation.

[0054] As an operational example of the above scheme, the number of door openings and closings and the ternary digits of passenger flow are shown in Table 1.

[0055] Table 1: Tertiaries of Door Opening / Closing Frequency and Passenger Flow

[0056]

[0057] For a data point (door opening and closing times are 28, passenger flow is 300): the number of door opening and closing times is less than the first tertiary, and the passenger flow is between the first tertiary and the second tertiary.

[0058] According to the above load level classification rules, this data point belongs to the low load level.

[0059] For another data point (door opening and closing times: 47, passenger flow: 560): the door opening and closing times are between the second and third third quartiles, and the passenger flow is greater than the third third quartile.

[0060] According to the above load level classification rules, this data point belongs to the high load level.

[0061] In a preferred embodiment of the present invention, the warning actions associated with each load level are as follows: a low load level is associated with a blue warning, a blue static icon is displayed on the control terminal interface, the current operating parameters are recorded to the log file, and no maintenance work order is triggered.

[0062] It's important to understand that under low load levels, the operating parameters of subway doors (such as resistance and temperature) fluctuate within a small range, but occasional anomalies may occur due to momentary disturbances (such as foreign object obstruction). For example, if the low load resistance threshold is 15N, a single instantaneous value reaching 16N (a deviation of 6.7%) may be caused by sensor noise rather than a genuine fault. If this situation triggers a maintenance work order, it will lead to unnecessary waste of resources, including manpower scheduling, equipment inspection, and downtime losses, and the benefits of fault repair under low load may be lower than the costs. By logging anomalies under low load levels and retaining them for periodic analysis, frequent invalid work orders can be avoided. Maintenance personnel can periodically review the logs to investigate occasional anomalies, determine whether further investigation is needed, thereby optimizing resource utilization and improving maintenance efficiency.

[0063] The medium load level is associated with a yellow warning, which dynamically displays a flashing yellow icon on the control terminal interface and repeatedly pops up to show abnormal operating parameter information, including the name of the abnormal operating parameter, its real-time value, and the percentage of deviation. It also automatically generates a pre-maintenance work order and pushes it to the operation and maintenance system.

[0064] It's important to understand that a medium load level typically indicates that the subway door is under moderate operational demand but with some pressure. In this state, abnormal operating parameters may indicate an increased risk of potential malfunctions. Compared to low load levels, anomalies under medium load are more likely related to actual operating conditions (such as mechanical fatigue or temperature increases due to frequent opening and closing) rather than simply caused by transient interference or sensor noise. Therefore, dynamically displaying a yellow warning icon, showing abnormal parameter information in a pop-up window (such as name, real-time value, and percentage deviation), and automatically generating pre-maintenance work orders can promptly alert maintenance personnel to intervene in potential problems. This approach allows for preventative measures to be taken before a fault occurs, reducing the likelihood of a fault escalating into a serious problem.

[0065] A red alert is associated with a high load level, which displays a full-screen red warning interface on the control terminal, showing emergency fault indicators and fault location information, and forcibly locking the door to a safe state.

[0066] It's important to understand that high load typically indicates that subway doors are operating at high frequency or under extreme pressure. In such conditions, abnormal operating parameters can directly threaten passenger safety and system stability. Anomalies under high load (such as a surge in resistance or excessively high temperatures) are often closely related to mechanical fatigue, component wear, or sudden malfunctions, posing a high risk of escalating into serious accidents. Therefore, by providing full-screen warnings and forcibly locking the doors to a safe state, potentially dangerous actions can be immediately prevented, ensuring the safety of passengers and equipment. Simultaneously, clear fault location information facilitates rapid response and precise maintenance, minimizing the impact of faults on operations and ensuring the efficiency and safety of the subway system.

[0067] In a further preferred embodiment of the present invention, (2) a differentiated operating parameter limit threshold is configured for each load level based on the operating parameter fault performance characteristics in historical fault records under different load levels, wherein the operating parameter fault performance characteristics are time-series data of the operating parameters within a set time window before the fault occurs. For example, the set time window can be 5 minutes.

[0068] The specific configuration process is as follows: collect historical fault records of subway doors and their associated load status indicators, and classify each historical fault record into the corresponding load level according to the load level classification method.

[0069] The above-mentioned association between historical fault records and load status indicators is achieved by aligning the timestamp of the fault occurrence with the timestamp of the load record. This allows for the search for data with the same timestamp in the corresponding load record, thereby extracting the load status indicator at that moment for association.

[0070] All historical fault records are classified according to their corresponding load levels to form a historical fault record set for each load level.

[0071] Extract the cause parameters of each fault record from the historical fault record set corresponding to each load level, and classify fault records with the same cause parameters to form a fault record set corresponding to each cause parameter under each load level.

[0072] It should be added that the aforementioned contributing parameters refer to the key operating parameters that can cause subway door malfunctions. For example, subway door operating parameters include mechanical resistance and motor temperature. When a subway door fails to close due to excessive resistance, mechanical resistance is considered a contributing parameter.

[0073] The fault performance characteristics of each fault record are extracted from the fault record set corresponding to each trigger parameter under each load level. Based on this, the volatility of the trigger parameter in the time adjacent to the fault occurrence is calculated. The volatility can be calculated by quantifying the ratio of the change amplitude of the trigger parameter in the time adjacent before and after the fault occurrence to the time interval. Then, the trigger parameter value in the earlier time in the adjacent time corresponding to the maximum volatility is taken as the limiting threshold of the trigger parameter in the fault record.

[0074] This invention uses volatility to determine the limit threshold, which can effectively identify sharp changes that occur shortly before a failure occurs. These changes are often early signals that a failure is about to occur. This method reflects the trend of dynamic changes better than simple threshold setting.

[0075] Further selecting the earlier trigger parameter value from the adjacent timeframes corresponding to the maximum volatility as the limiting threshold for the trigger parameter in the fault record is because the maximum volatility usually occurs when a fault is about to occur or has just occurred. At this time, the trigger parameter value is often close to the limit that the system can withstand. By selecting the earlier trigger parameter value from the adjacent timeframes corresponding to the maximum volatility, the critical point where the system transitions from a normal operating state to a fault state can be captured. This selection helps to set more accurate early warning thresholds, enabling the system to issue timely alarms when approaching a critical state, thus avoiding the occurrence of faults or reducing the losses caused by faults.

[0076] The limit thresholds for each fault record corresponding to the cause parameter under each load level are compared, and the limit threshold with the highest frequency of occurrence is selected as the limit threshold for the cause parameter under the corresponding load level.

[0077] The above statistical analysis selects the most frequently occurring limit thresholds, ensuring that the chosen values ​​represent the most common critical points and reducing the possibility of false alarms and missed alarms. This statistical method helps improve the stability and reliability of the early warning system.

[0078] The method described above relies on historical fault data when configuring differentiated operating parameter limit thresholds for each load level, ensuring that the threshold settings are based on actual fault conditions rather than theoretical assumptions. This approach makes the limit thresholds more closely resemble actual operating conditions, significantly improving the accuracy and reliability of the early warning system. Furthermore, configuring limit thresholds using historical fault data allows for the identification of risks before potential faults occur, enabling preventative measures such as adjusting operating parameters or performing emergency repairs. This effectively reduces the probability of fault occurrence and enhances the overall stability and security of the system. This data-driven approach not only optimizes resource utilization but also strengthens the system's ability to cope with complex operating conditions.

[0079] (3) Collect the door operation parameters in real time from the subway door control terminal interface, determine the load level according to the current load status indicators, and at the same time, make anomaly judgment by matching the collected operation parameters with the corresponding load level limit threshold.

[0080] It should be noted that the control terminal of the subway door can be integrated into the control box. The operating parameters of the door will be displayed on the panel interface of the control box. These operating parameters include, but are not limited to, mechanical resistance, motor temperature, and motor current.

[0081] In the above-mentioned scheme, the anomaly determination process is as follows: the collected operating parameters are compared with the limit thresholds matched with the corresponding load levels. If the actual value of a certain operating parameter reaches or exceeds its limit threshold, the over-limit magnitude is calculated, and the over-limit duration is recorded.

[0082] In the example of the above implementation method, the calculation of the over-limit range can be achieved by quantifying the deviation between the actual value of the operating parameter and the corresponding limit threshold. This difference reflects the degree to which the operating parameter exceeds the set safety range and is used to assess the severity of the over-limit.

[0083] Based on the monitoring results of the exceedance range and exceedance duration, the following conditions shall be used to determine whether the operation is abnormal: a) The exceedance range reaches or exceeds the preset warning range.

[0084] b) The time exceeding the limit reaches or exceeds the preset warning time.

[0085] An operational abnormality is determined when any of the above conditions are met.

[0086] The above-mentioned approach introduces two quantitative indicators: the magnitude of the exceedance and the duration of the exceedance. The magnitude of the exceedance reflects the severity of the parameter's deviation from the safe range, while the duration of the exceedance reflects the persistence of the deviation. By combining these two dimensions for comprehensive judgment, compared with the single threshold triggering method, it can effectively avoid misjudgment caused by instantaneous fluctuations or brief exceedances, improve the scientificity and accuracy of anomaly judgment, and ensure that the system only triggers anomaly alarms when intervention is truly needed.

[0087] In the improved implementation of the above method, the abnormal judgment of the collected operating parameters and the corresponding load level limit also includes the following: when the operating parameter is judged to be abnormal, the number of all the operating parameters judged to be abnormal is counted within a set time window (such as 5 minutes).

[0088] The correlation between these abnormal operating parameters can be assessed using correlation algorithms (such as Pearson correlation coefficient, Spearman rank correlation coefficient, etc.). Specifically, a correlation threshold (such as a correlation coefficient greater than 0.7) can be set to determine whether a significant correlation exists.

[0089] If there is a significant correlation, these abnormal operating parameters will be identified as related, and the identification information will be output synchronously when an early warning action is triggered.

[0090] It's important to understand that when multiple operating parameters become abnormal within a short period, correlation analysis can reveal the inherent connections and mutual influences between these abnormal parameters. Simultaneously outputting correlation indicators during early warning operations helps maintenance personnel quickly identify the root cause of the fault, rather than just the surface symptoms. For example, if mechanical resistance and motor current are simultaneously abnormal and significantly correlated, maintenance personnel can prioritize checking the status of the motor and transmission system, thereby developing a more targeted preventative maintenance plan, rationally allocating maintenance resources, avoiding unnecessary comprehensive inspections, and saving time and costs.

[0091] (4) When an abnormal operation is detected, trigger the warning action associated with the load level.

[0092] In the innovative implementation of the above scheme, when an abnormal operation is determined, the triggering of the early warning action associated with the load level also includes the following: after the early warning action is triggered, the monitoring screen of the relevant door is retrieved in real time and uploaded to the train control center simultaneously.

[0093] The monitoring footage provided firsthand visual information during the above operations, enabling the control center to react more quickly. For example, in an emergency, it can immediately determine whether emergency braking or other emergency measures are necessary to ensure passenger safety.

[0094] (5) Periodically count the failure frequency of each load level and update the operating parameter limit threshold configuration accordingly.

[0095] As an example of the above implementation, the periodicity can be weekly or monthly.

[0096] In a preferred embodiment of the present invention, the dynamic update of the operating parameter limit threshold configuration is implemented as follows: within each set period, the number of historical fault records for each load level is collected and the historical fault frequency for each load level is statistically analyzed.

[0097] Compare the failure frequency of each load level in the current period with the historical failure frequency of previous periods to identify whether the failure frequency has increased.

[0098] In the specific implementation of the above scheme, identifying whether the failure frequency has increased includes the following: statistical analysis of the mean and standard deviation of the historical failure frequency for each load level in previous periods.

[0099] The failure frequency of each load level in the current period is standardized by comparing it with the historical periodic average failure frequency of the corresponding load level, and a standardized score is calculated. The expression for the standardized score is as follows: In the formula The standardized score represents the degree of deviation of the current period's failure frequency from historical data. This indicates the failure frequency in the current cycle. , These represent the mean and standard deviation of the historical periodic failure frequency, respectively.

[0100] The standardized score is compared with a preset significance threshold. When the standardized score is greater than the significance threshold, it indicates that the failure frequency of the current cycle is significantly greater than the average failure frequency of the historical cycles, suggesting that there may be new risks or problems. In this case, the failure frequency is identified as increasing. Otherwise, it is considered that the failure frequency has not increased significantly.

[0101] It is important to note that the threshold for prominence can be determined based on actual needs and risk tolerance. For example, at high load levels, a lower threshold may be needed to detect potential problems earlier, while at low load levels, the threshold can be relaxed to reduce unnecessary alerts.

[0102] The above method identifies whether the failure frequency has increased by calculating the mean and standard deviation of historical cycle failure frequencies and then using a standardized approach that compares the current cycle's failure frequency with historical failure frequencies. This method utilizes basic statistical principles, making the identification results more scientific and accurate. The standardized score quantifies the deviation of the current cycle's failure frequency from historical data, providing an objective benchmark. Compared to relying solely on experience or intuitive judgment, the standardized score avoids subjective bias caused by human factors, ensuring the fairness and reliability of the identification results.

[0103] As a data example to identify whether the failure frequency has increased, suppose the failure frequency of a certain subway door in the past multiple cycles and the current cycle under various load levels is shown in Table 2.

[0104] Table 2: Failure Frequency Data for Each Load Level

[0105]

[0106] The standardized score calculated at the low load level is 1.33 < 2, indicating that the failure frequency does not increase significantly at the low load level.

[0107] The standardized score calculated at the medium load level is 1 < 1.5, indicating that the failure frequency does not increase significantly at the medium load level.

[0108] The standardized score calculated under high load level is 1.67>1, indicating that the failure frequency increases under high load level.

[0109] If the failure frequency of a certain load level does not increase, it indicates that the failure frequency has decreased or remained stable. In this case, the current operating parameter limit threshold is maintained. Otherwise, the failure records of the corresponding load level in the current period are collected, and the operating parameter limit threshold is recalculated and updated using the failure performance characteristics of the operating parameters in the failure records.

[0110] Given the dynamic changes in the operating status of subway door systems and the potential wear and aging of equipment over time, their performance will change accordingly. By periodically assessing the failure frequency and adjusting the operating parameter limit thresholds, it is possible to ensure that the system adapts to these changes in a timely manner, maintains efficient and stable early warning operation, and thus guarantees the reliability and safety of the system.

[0111] The above formulas are all dimensionless calculations. The formulas are derived from software simulations based on a large amount of collected data to obtain the most recent real-world results. The preset parameters in the formulas are set by those skilled in the art according to the actual situation.

[0112] The above embodiments can be implemented, in whole or in part, by software, hardware, firmware, or any other combination thereof. When implemented using software, the above embodiments can be implemented, in whole or in part, in the form of a computer program product.

[0113] Those skilled in the art will recognize that the modules and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0114] In addition, the functional modules in the various embodiments of this application can be integrated into one processing module, or each module can exist physically separately, or two or more modules can be integrated into one module.

[0115] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the technical scope disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

[0116] Finally, the above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the protection scope of the present invention.

Claims

1. A method for intelligent monitoring and early warning of safe operation of subway doors, characterized in that, Includes the following steps: (1) The load status indicators are defined as the number of times the door opens and closes and the passenger flow in a set unit time. Based on the statistical quantile method of historical load distribution, the load status is divided into three levels: low, medium and high. At the same time, a warning action is associated with each load level. (2) Configure differentiated operating parameter limit thresholds for each load level based on the operating parameter fault performance characteristics in the historical fault records under different load levels, wherein the operating parameter fault performance characteristics are the time-series data of the operating parameters set in a time window before the fault occurs; (3) Collect the door operation parameters in real time from the subway door control terminal interface, determine the load level according to the current load status indicators, and at the same time, make anomaly judgment by matching the collected operation parameters with the corresponding load level limit threshold. (4) When an operational anomaly is detected, trigger an early warning action associated with the load level; (5) Periodically count the failure frequency of each load level and update the operating parameter limit threshold configuration accordingly; The process for configuring differentiated operating parameter limit thresholds for each load level is as follows: Collect historical fault records of subway doors and their associated load status indicators, and classify each historical fault record into the corresponding load level according to the load level classification method; classify all historical fault records according to their corresponding load levels to form historical fault record sets corresponding to each load level; extract the causative parameters of each fault record from the historical fault record set corresponding to each load level, and classify fault records with the same causative parameters to form fault record sets corresponding to each causative parameter under each load level; extract the fault performance characteristics of the causative parameters of each fault record from the fault record sets corresponding to each causative parameter under each load level, and calculate the volatility of the causative parameters in the time adjacent to the fault occurrence, and then take the causative parameter value of the earlier time in the adjacent time corresponding to the maximum volatility as the limit threshold of the causative parameter in the fault record; compare the limit thresholds of each fault record corresponding to the causative parameters under each load level, and select the limit threshold with the highest frequency of occurrence as the limit threshold of the causative parameter under the corresponding load level.

2. The intelligent monitoring and early warning method for safe operation of subway doors as described in claim 1, characterized in that: The statistical quantile method based on historical load distribution is used to classify load status into three levels: low, medium, and high. See the following process: Load records for each unit of time of each day within the historical years are extracted from the subway operation database, and the load status indicators in the historical load records within each year are integrated into a door opening and closing count dataset and a passenger flow dataset, respectively. For the door opening and closing times dataset and passenger flow dataset of all years, data of the same unit time are extracted and the standard deviation is calculated. Based on this, the typical values ​​of door opening and closing times and passenger flow are determined for each unit time within a single day. After sorting the typical values ​​of the number of door openings and passenger flow in ascending order for each unit of time within a single day, the ternary quartile analysis method was applied to determine the first ternary quartile, the second ternary quartile, and the third ternary quartile for the number of door openings and passenger flow, respectively. Based on the tertiary values ​​calculated above, the load levels are classified as follows: Low load level: defined as both the number of door openings and passenger flow are below their respective first thirds, or one of them is below the first third and the other is between its first and third thirds, representing a low to third-third load level; Medium load level: defined as a load level where both the number of door openings and passenger flow are between the first and third thirds of their respective values; High load level: defined as the number of door openings or passenger flow exceeding their respective third third thirds, or one of them being lower than its first third third and the other higher than its third third third, representing a high load level pointing to the third third.

3. The intelligent monitoring and early warning method for safe operation of subway doors as described in claim 2, characterized in that: The process for determining typical values ​​for the number of door openings and closings and typical values ​​for passenger flow at different times within a single day is as follows: Compare the standard deviation of the number of door openings and closings and the standard deviation of passenger flow in each unit of time within a single day with the set critical values; If the standard deviation of the number of door openings and closings and the standard deviation of passenger flow in a certain unit of time do not exceed the critical value, the mean of the number of door openings and closings and the mean of passenger flow in all years corresponding to that unit of time are calculated as the typical value of that unit of time. Otherwise, the trimmed mean is calculated for the dataset of all years corresponding to that unit of time as the typical value of that unit of time.

4. The intelligent monitoring and early warning method for safe operation of subway doors as described in claim 1, characterized in that: The associated early warning actions for each load level are as follows: Low load level is associated with a blue alert, which displays a static blue icon on the control terminal interface, records the current running parameters to the log file, and does not trigger an operation and maintenance work order; The yellow warning associated with the medium load level dynamically displays a flashing yellow icon on the control terminal interface and repeatedly pops up abnormal operating parameter information, automatically generating a pre-maintenance work order and pushing it to the operation and maintenance system; A red alert is associated with a high load level, which displays a full-screen red warning interface on the control terminal, showing emergency fault indicators and fault location information, and forcibly locking the door to a safe state.

5. The intelligent monitoring and early warning method for safe operation of subway doors as described in claim 1, characterized in that: The process of combining the collected operating parameters with the corresponding load level matching threshold for anomaly determination is as follows: The collected operating parameters are compared with the limit thresholds matched with the corresponding load levels. If the actual value of a certain operating parameter reaches or exceeds its limit threshold, the over-limit magnitude is calculated and the over-limit duration is recorded. Based on the monitoring results of the exceeding range and the exceeding duration, the following conditions are used to determine whether the operation is abnormal: a) The exceedance range reaches or exceeds the preset warning range; b) The duration of exceeding the limit reaches or exceeds the preset warning duration; An operational abnormality is determined when any of the above conditions are met.

6. The intelligent monitoring and early warning method for safe operation of subway doors as described in claim 5, characterized in that: The method of combining the collected operating parameters with the corresponding load level matching threshold for anomaly determination also includes the following: Once a running parameter is determined to be abnormal, the number of all running parameters determined to be abnormal is counted within a set time window. The algorithm is used to assess whether there is a significant correlation between abnormal operating parameters. If a significant correlation exists, these abnormal operating parameters are identified, and the identification information is output synchronously when an early warning action is triggered.

7. The intelligent monitoring and early warning method for safe operation of subway doors as described in claim 1, characterized in that: The triggering of the warning action associated with the load level when an operational anomaly is determined also includes the following: After the warning action is triggered, the monitoring screen of the relevant door is retrieved in real time and uploaded to the train control center simultaneously.

8. The intelligent monitoring and early warning method for safe operation of subway doors as described in claim 1, characterized in that: The configuration of the dynamic update operation parameter limit threshold is implemented as follows: Collect the number of historical fault records for each load level within each set period and count the historical fault frequency for each load level. Compare the failure frequency of each load level in the current period with the historical failure frequency of previous periods to identify whether the failure frequency has increased. If the failure frequency of a certain load level is not increased, the current operating parameter limit threshold is maintained; otherwise, the failure records of the corresponding load level in the current period are collected, and the operating parameter limit threshold is recalculated and updated using the failure performance characteristics of the operating parameters in the failure records.

9. The intelligent monitoring and early warning method for safe operation of subway doors as described in claim 8, characterized in that: Whether the frequency of fault identification has increased includes the following: Statistical analysis of the mean and standard deviation of historical failure frequencies for each load level in previous periods; The failure frequency of each load level in the current cycle is standardized and compared with the historical cycle failure frequency average of the corresponding load level, and the standardization score is calculated. The standardized score is compared with a preset significance threshold. When the standardized score is greater than the significance threshold, the frequency of faults is identified as increasing; otherwise, the frequency of faults is considered not to have increased significantly.

Images