Train running state safety monitoring method based on data analysis

Abstract

The invention relates to the field of train safety monitoring, in particular to a train running state safety monitoring method based on data analysis, which comprises the following steps: under an abnormal change analysis condition, determining a data analysis strategy of each change analysis system according to a trend change stability index and a change duration index; when loss characteristic analysis is carried out, determining an associated change proportion based on the similar change coefficient and the position correlation coefficient of each change analysis system, and determining whether to carry out change data processing on the loss analysis system according to the associated change proportion so as to determine key monitoring data; when data compression analysis is carried out, determining a compression analysis mode of each change analysis data of the compression analysis system according to the proportion of the related monitoring data so as to obtain key monitoring data; under the condition that analysis is completed, key monitoring data are sent to the user, and the effectiveness and timeliness of the abnormal monitoring result of the train door are improved.

Description

Technical Field

[0001] The present invention relates to the field of train safety monitoring, and in particular to a method for monitoring the safety of train running status based on data analysis. Background Art

[0002] The monitoring results of the subway operation status are of great reference value for ensuring the overall operational efficiency and operation and maintenance optimization quality of the subway. Among them, with the gradual popularization of subway transportation, the opening and closing operations of subway train doors have gradually increased. The reliability of the monitoring results of abnormal conditions of train doors has a great impact on the safety and efficiency of subway operation. However, the existing abnormal state monitoring of subway train doors is often only based on whether the data exists in the corresponding threshold range, and fails to consider the different abnormal factors corresponding to the changes in the relevant data of the train doors during actual operation. As a result, the effectiveness and timeliness of the abnormal monitoring results of the train doors are poor, and it is impossible to effectively prevent the operation risks of subway vehicles caused by abnormal door conditions. Therefore, how to determine a targeted data analysis process based on the changes in the relevant data of the train doors during actual operation to improve the effectiveness and reliability of the data extracted for analyzing the causes of the abnormalities is a problem that needs to be solved urgently by technical personnel in this field.

[0003] Chinese patent application publication number CN114692904A discloses a health management system for urban subway doors, comprising: a data acquisition module for collecting and processing door information for vehicles on various urban subway lines; a user login module for user authentication; a monitoring and management module for viewing door information for vehicles on various urban subway lines; an alarm management module for generating real-time alarm information for doors on all urban subway lines; an early warning management module for generating early warning information for doors on all urban subway lines; an operation and maintenance module for uploading, updating, and displaying subway door operation and maintenance information; and a configuration management module for system configuration management. However, the above solution has the following problems: it fails to determine a targeted data analysis process based on changes in various relevant data on train doors during actual operation, resulting in low validity and reliability of the data extracted for analyzing the causes of anomalies, and thus poor validity and timeliness of the abnormality monitoring results for train doors. Summary of the Invention

[0004] To this end, the present invention provides a train running status safety monitoring method based on data analysis to overcome the problem in the prior art that the targeted data analysis process is not determined in combination with the changes in various relevant data of the train doors during actual operation, resulting in low validity and reliability of the data extracted for analyzing the causes of abnormalities, and further resulting in poor validity and timeliness of the abnormality monitoring results of the train doors.

[0005] To achieve the above objectives, the present invention provides a method for monitoring train running status safety based on data analysis, comprising:

[0006] Under abnormal change analysis conditions, the data analysis strategy for each change analysis system is determined based on the trend change stability index and the change continuity index, which is to perform loss feature analysis or data compression analysis on the change analysis system;

[0007] When performing loss feature analysis, determine the proportion of related changes based on the similar change coefficient and position correlation coefficient of each change analysis system. Based on the proportion of related changes, determine whether to perform change data processing for the loss analysis system to determine key monitoring data.

[0008] When performing data compression analysis, the compression analysis method of each change analysis data of the compression analysis system is determined according to the proportion of relevant monitoring data to obtain key monitoring data. The compression analysis method is to set the data compression threshold for each monitoring data segment according to the stage overlap index, or to set the data compression threshold based on the proportion of relevant monitoring data;

[0009] Under the analysis completion condition, key monitoring data is sent to the user. The analysis completion condition is that there is a change in the analysis system to complete the loss feature analysis or data compression analysis.

[0010] Furthermore, under abnormal change analysis conditions, the trend change stability index and change continuity index of each change analysis system are tested;

[0011] For a single change analysis system,

[0012] The trend change stability index is determined according to the change index of each change analysis data of the change analysis system during the change assessment phase;

[0013] The change continuity index is determined according to the change direction of the change index obtained by the change analysis system each time during the change assessment phase;

[0014] The abnormal change analysis condition is that the target monitored train has a door system that needs to be analyzed for changes, and the door system that needs to be analyzed for changes is recorded as a change analysis system.

[0015] Furthermore, if the change stability coefficient of a change analysis system is greater than a preset change stability coefficient, a loss characteristic analysis is performed on the change analysis system, including:

[0016] The change analysis system is recorded as the loss analysis system, and the associated change ratio of the loss analysis system is determined based on the similarity change coefficient and position correlation coefficient of each change analysis system within the associated evaluation range;

[0017] Determine whether to perform change data processing for the loss analysis system based on the proportion of related changes;

[0018] The change stability coefficient is determined based on the trend change stability index and the change continuity index.

[0019] Furthermore, for a single loss analysis system, the correlation change index of each change analysis system within the correlation evaluation range is determined based on the similarity change coefficient and the position correlation coefficient;

[0020] If the correlation change index of any change analysis system within the correlation evaluation range is greater than the preset correlation change index, then the change analysis system will be recorded as the correlated change system of the loss analysis system;

[0021] The similarity change coefficient is determined according to the number of overlapping monitoring data of each change analysis system and the stability coefficient difference value, and the position correlation coefficient is determined according to the air pressure interference index of each change analysis system.

[0022] Furthermore, if the associated change ratio of the loss analysis system is greater than the preset associated change ratio, change data processing is performed on the loss analysis system to determine key monitoring data of the loss analysis system;

[0023] When processing change data, the reference change trend index for each trend analysis stage is determined based on the overlapping monitoring data of the loss analysis system and its associated change system;

[0024] Based on the reference change trend index and matching evaluation coefficient of each trend analysis stage, the change trend matching degree of each monitoring data is determined, and the key monitoring data of the loss analysis system is determined according to the change trend matching degree.

[0025] Further, determining whether to adjust the matching evaluation coefficient corresponding to each trend analysis stage according to the change difference coefficient;

[0026] If the change difference coefficient in a trend analysis phase is greater than the preset change difference coefficient, the matching evaluation coefficient is adjusted downward according to the change difference coefficient;

[0027] The reduction value of the matching evaluation coefficient is positively correlated with the change difference coefficient.

[0028] Furthermore, if the change stability coefficient of a change analysis system is less than or equal to the preset change stability coefficient, data compression analysis is performed on the change analysis system, including:

[0029] The change analysis system is recorded as a compression analysis system. The compression analysis method of each change analysis data of the compression analysis system is determined according to the proportion of relevant monitoring data, so as to compress each change analysis data and obtain key monitoring data.

[0030] Furthermore, for any change analysis data of the compression analysis system, if the proportion of relevant monitoring data is greater than the preset proportion of relevant monitoring data, the monitoring stage of the change analysis data is divided, and the data compression threshold of each monitoring data segment is set according to the stage overlap index;

[0031] The data compression threshold is negatively correlated with the stage overlap index.

[0032] Further, determining whether to perform secondary adjustment on the data compression threshold of each monitoring data segment according to the reference change index;

[0033] For a single monitoring data segment, if the reference change index is greater than the preset reference change index, the data compression threshold is reduced and adjusted according to the reference change index;

[0034] The reduction value of the data compression threshold is positively correlated with the reference change index.

[0035] Furthermore, for any change analysis data of the compression analysis system, if the proportion of relevant monitoring data is less than or equal to the preset proportion of relevant monitoring data, a data compression threshold is determined based on the proportion of relevant monitoring data, and compression processing is performed on the change analysis data according to the data compression threshold;

[0036] The data compression threshold is negatively correlated with the proportion of relevant monitoring data.

[0037] Compared with the prior art, the beneficial effect of the present invention lies in that the technical solution of the present invention determines the data analysis strategy of each change analysis system based on the trend change stability index and the change continuity index to determine the key monitoring data of each change analysis system, so that the analysis process of the change analysis system is more in line with the actual working situation, and the validity of the data extracted by the change analysis system for analyzing the cause of the abnormality is guaranteed, thereby improving the validity and timeliness of the abnormal monitoring results of the train doors.

[0038] Furthermore, the present invention determines the change stability coefficient of each change analysis system based on the trend change stability index and the change continuity index, and then determines a targeted data analysis strategy based on the size relationship between the change stability coefficient and the preset value. The change stability coefficient is used to determine whether there are time-series changes in the data changes of the change analysis system, and then determines whether the changes in the monitoring data are related to the losses caused by train operation. The present invention improves the effectiveness of the data extracted by the change analysis system for analyzing the causes of abnormalities.

[0039] Furthermore, the present invention performs loss characteristic analysis on change analysis systems with larger change stability coefficients, determines the associated change systems of such change analysis systems through similar change coefficients and position correlation coefficients, and then determines whether to perform change data processing on such change analysis systems based on the proportion of associated changes. When the proportion of associated changes is large, it indicates that there are many other door systems in the change analysis system that can be used for collaborative analysis of door loss conditions, and performs collaborative analysis to determine reference change trend indexes at different trend analysis stages, and then further determines monitoring data of fitting curves that can be used to analyze the loss conditions of such change analysis systems. The present invention improves the effectiveness of abnormal monitoring results for train doors.

[0040] Furthermore, in the process of determining the key monitoring data of the loss analysis system, the present invention determines the matching evaluation coefficient of each trend analysis stage through the operating load conditions of the target monitoring train, and determines whether compensation adjustment is needed for the matching evaluation coefficient based on the change difference coefficient, thereby ensuring the accuracy of the subsequent determination results of the key monitoring data, thereby improving the effectiveness of the abnormal monitoring results of the train doors.

[0041] Furthermore, the present invention performs data compression analysis on the change analysis system with a smaller change stability coefficient, determines the compression analysis method of each change analysis data by the proportion of relevant monitoring data, ensures that the process of compressing and processing each change analysis data is more in line with the actual data situation, and ensures that the reconstruction accuracy of the compressed data fits the criticality of the data while ensuring that the compression quality requirements are met. The present invention improves the effectiveness of the determination results of key data and the transmission execution efficiency, thereby improving the effectiveness and timeliness of the abnormal monitoring results of train doors. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] Figure 1 Schematic diagram of a train running status safety monitoring method based on data analysis according to the present invention;

[0043] Figure 2 This is a flow chart of the present invention for determining the data analysis strategy of each change analysis system based on the trend change stability index and the change continuity index;

[0044] Figure 3 This is a flow chart of the present invention for determining whether to perform change data processing on the loss analysis system based on the associated change ratio;

[0045] Figure 4 This is a flow chart of the present invention for determining whether to adjust the matching evaluation coefficient corresponding to each trend analysis stage according to the change difference coefficient. DETAILED DESCRIPTION

[0046] In order to make the objects and advantages of the present invention more clearly understood, the present invention is further described below in conjunction with embodiments; it should be understood that the specific embodiments described herein are merely used to explain the present invention and are not intended to limit the present invention.

[0047] The preferred embodiments of the present invention are described below with reference to the accompanying drawings. It should be understood by those skilled in the art that these embodiments are only used to explain the technical principles of the present invention and are not intended to limit the scope of protection of the present invention.

[0048] It should be noted that, in the description of the present invention, terms such as "up", "down", "left", "right", "inside", and "outside" indicating directions or positional relationships are based on the directions or positional relationships shown in the accompanying drawings. This is only for the convenience of description and does not indicate or imply that the device or element must have a specific orientation, be constructed and operated in a specific orientation. Therefore, it cannot be understood as a limitation on the present invention.

[0049] Furthermore, it should be noted that, in the description of the present invention, unless otherwise expressly specified or limited, the terms "mounted," "connected," and "connected" should be understood in a broad sense. For example, they may refer to fixed connections, detachable connections, or integral connections; mechanical connections or electrical connections; direct connections or indirect connections through an intermediate medium; and internal communication between two components. Those skilled in the art will understand the specific meanings of the above terms in the present invention based on specific circumstances.

[0050] See also Figures 1 to 4 As shown, the present invention provides a method for monitoring the safety of train running status based on data analysis, comprising:

[0051] Under abnormal change analysis conditions, the change feature analysis strategy of each change analysis system is periodically determined based on the trend change stability index and the change continuity index, which is to perform loss feature analysis or feature mining analysis on the change analysis system;

[0052] Under abnormal change analysis conditions, the data analysis strategy for each change analysis system is determined based on the trend change stability index and the change continuity index, which is to perform loss feature analysis or data compression analysis on the change analysis system;

[0053] When performing loss feature analysis, determine the proportion of related changes based on the similar change coefficient and position correlation coefficient of each change analysis system. Based on the proportion of related changes, determine whether to perform change data processing for the loss analysis system to determine key monitoring data.

[0054] When performing data compression analysis, the compression analysis method of each change analysis data of the compression analysis system is determined according to the proportion of relevant monitoring data to obtain key monitoring data. The compression analysis method is to set the data compression threshold for each monitoring data segment according to the stage overlap index, or to set the data compression threshold based on the proportion of relevant monitoring data;

[0055] Under the analysis completion condition, key monitoring data is sent to the user. The analysis completion condition is that there is a change in the analysis system to complete the loss feature analysis or data compression analysis.

[0056] Among them, the present invention is used to perform operation monitoring on the door system of a subway train, and the subway train for operation monitoring is recorded as a target monitoring train. In the present invention, each train door in the target monitoring train and components such as motors for controlling corresponding train door switches are collectively recorded as a door system. The monitoring data is data corresponding to different stages in the process of executing the door unlocking task and the door locking task. The monitoring data in the present invention includes but is not limited to: changes in the speed and acceleration of the door during the execution of the door unlocking task and the door locking task, the vibration frequency and amplitude of the door during the execution of the door unlocking task and the door locking task, and the voltage, current and temperature of the motor during the execution of the door unlocking task and the door locking task.

[0057] In the present invention, each door system needs to complete the door unlocking task and the door locking task. For a single door system, the starting time of the process of executing the door unlocking task is the time when the door system receives the door opening command, and the ending time of the process of executing the door unlocking task is the time when the door system completes opening the train door. The starting time of the process of executing the door locking task is the time when the door system receives the door closing command, and the ending time of the process of executing the door locking task is the time when the door system completes closing the train door.

[0058] The present invention applies several operation monitoring records, and any operation monitoring record records the change index, change stability coefficient, associated change index, associated change ratio, change trend matching degree, change difference coefficient and related monitoring data ratio during at least one abnormal monitoring process of each door system of the target monitoring train, and each operation monitoring record corresponds to a qualified mark, which records whether the timeliness and accuracy of the monitoring results of the door system meet user requirements.

[0059] Specifically, under abnormal change analysis conditions, the trend change stability index and change continuity index of each change analysis system are tested;

[0060] For a single change analysis system,

[0061] The trend change stability index is determined according to the change index of each change analysis data of the change analysis system during the change assessment phase;

[0062] The change continuity index is determined according to the change direction of the change index obtained by the change analysis system each time during the change assessment phase;

[0063] The abnormal change analysis condition is that the target monitored train has a door system that needs to be analyzed for changes, and the door system that needs to be analyzed for changes is recorded as a change analysis system.

[0064] Various monitoring data of each door system when performing a door unlocking task or a door locking task of a train door are obtained, and it is determined whether each door system needs to be subjected to change analysis. For any monitoring data of a single door system, the change index = |the value of the monitoring data currently obtained - the value of the monitoring data most recently obtained at the current acquisition time| / the value of the monitoring data most recently obtained at the current acquisition time. If the change index of the monitoring data is greater than a preset change index, the monitoring data is recorded as change analysis data.

[0065] The value of the preset change index can be determined by the user according to the actual working scenario. For example, the user can set it according to the operation monitoring record. The higher the user's requirements for the timeliness and accuracy of the monitoring results of the vehicle door system, the smaller the value of the preset change index. A method for determining the value of the preset change index is provided. The minimum value of the change index of the change analysis data in the operation monitoring record that meets the user's requirements for the timeliness and accuracy of the monitoring results of the vehicle door system is recorded as the preset change index.

[0066] For a single door system, if any monitoring data of the door system is change analysis data, it is determined that the door system needs to be changed. If any door system of the target monitoring train needs to be changed, it is determined that the target monitoring train is under abnormal change analysis conditions. Under abnormal change analysis conditions, the trend change stability index and change continuity index of each change analysis system are detected. For any door system, the end time of the change evaluation phase is the time when the door system is determined to be a change analysis system. The duration of the change evaluation phase is positively correlated with the number of change analysis data of the change analysis system. The trend change stability index = 1 / the maximum value of the trend change index of each change analysis data in the change analysis system. The trend change index is determined based on the change index of the change analysis data obtained each time during the change evaluation phase. For a single change analysis data, the trend change index n is the number of door opening and closing tasks completed by the door system during the change assessment phase, qi is the change index of the change analysis data obtained when the door opening and closing task is completed for the i-th time during the change assessment phase, q0 is the average of the change indexes of the change analysis data obtained when the door opening and closing tasks are completed each time during the change assessment phase. If the door system completes a door unlocking task followed by a door locking task, it is counted as completing a door opening and closing task. The change continuity index is the average of the change direction matching degrees of each change analysis data in the change analysis system. For a single change analysis data, the change direction matching degree = the change direction matching degree of the change analysis data obtained during the change analysis phase. The number of times the change direction of the change index of the change analysis data is consistent with the stage change direction / the number of change indices of the change analysis data obtained during the change assessment stage. The stage change value is the difference between the value of the change analysis data obtained last time and the value of the change analysis data obtained first time during the change assessment stage. For a single determined change index, if the difference between the value of the change analysis data obtained later for determining the above change index and the value of the change analysis data obtained previously is greater than 0 or less than 0 at the same time, then it is determined that the change direction of the change index determined this time is consistent with the stage change direction.

[0067] Specifically, if the change stability coefficient of a change analysis system is greater than a preset change stability coefficient, a loss characteristic analysis is performed on the change analysis system, including:

[0068] The change analysis system is recorded as the loss analysis system, and the associated change ratio of the loss analysis system is determined based on the similarity change coefficient and position correlation coefficient of each change analysis system within the associated evaluation range;

[0069] Determine whether to perform change data processing for the loss analysis system based on the proportion of related changes;

[0070] The change stability coefficient is determined based on the trend change stability index and the change continuity index.

[0071] The present invention adopts a cyclic analysis and monitoring cycle, the duration of which can be determined by the user. The higher the user's requirements for the timeliness and accuracy of the monitoring results of the vehicle door system, the shorter the duration of the analysis and monitoring cycle. A duration of the analysis and monitoring cycle is provided, which is 10 days. At the end of each analysis and monitoring cycle, the change stability coefficient of each change analysis system is determined based on the trend change stability index and the change persistence index, and the change feature analysis strategy of each change analysis system is determined based on the change stability coefficient.

[0072] For a single change analysis system, the change stability coefficient = trend change stability index + change continuity index. The value of the preset change stability coefficient can be determined by the user according to the actual working scenario. For example, the user can set it according to the operation monitoring record and provide a preset change stability coefficient value. The operation monitoring record for loss characteristic analysis of the change analysis system is recorded as the analysis reference record, and the average value of the change stability coefficient of the change analysis system in the analysis reference record that meets the user's requirements for the timeliness and accuracy of the monitoring results of the vehicle door system is recorded as the preset change stability coefficient.

[0073] Specifically, for a single loss analysis system, the correlation change index of each change analysis system in the target monitoring train is determined based on the similarity change coefficient and the position correlation coefficient;

[0074] If there is any change analysis system whose associated change index is greater than the preset associated change index, then the change analysis system is recorded as the associated change system of the loss analysis system;

[0075] The similarity change coefficient is determined according to the number of overlapping monitoring data of each change analysis system and the stability coefficient difference value, and the position correlation coefficient is determined according to the air pressure interference index of each change analysis system.

[0076] Among them, when performing loss characteristic analysis on a single change analysis system, the change analysis system is recorded as the loss analysis system. For any change analysis system other than the loss analysis system in the target monitoring train, the associated change index is the product of the similarity change coefficient of the change analysis system and the position correlation index. The similarity change coefficient = ln(number of overlapping monitoring data / stability coefficient difference value), and the stability coefficient difference value is the absolute value of the difference between the change stability coefficients of the change analysis system and the target analysis system. For any target monitoring data, if the target monitoring data is used as the change analysis data of both the target analysis system and the change analysis system, the target monitoring data is recorded as the overlapping monitoring data. The position correlation index is the absolute value of the difference between the air pressure interference index of the change analysis system and the air pressure interference index of the loss analysis system. For a single change analysis system, the air pressure interference index = system interference distance / distance between the front and rear of the target monitoring train. The system interference distance is the minimum value of the distance between the change analysis system and the front and rear of the target inspection train.

[0077] For a single loss analysis system, the correlation change index of each change analysis system in the target monitoring train is determined based on the similarity change coefficient and the position correlation coefficient. If there is any change analysis system whose correlation change index is greater than the preset correlation change index, the change analysis system with the correlation change index greater than the preset correlation change index is recorded as the correlation change system of the loss analysis system. The value of the preset correlation change index can be determined by the user according to the actual working scenario. For example, the user can set it according to the operation monitoring record. The higher the user's requirements for the timeliness and accuracy of the monitoring results of the door system, the larger the value of the preset correlation change index. A method for determining the value of the preset correlation change index is provided, and the average value of the correlation change index of the correlation change system in the operation monitoring record that meets the user's requirements for the timeliness and accuracy of the monitoring results of the door system is recorded as the preset correlation change index.

[0078] Specifically, if the associated change ratio of the loss analysis system is greater than the preset associated change ratio, the change data of the loss analysis system is processed to determine the key monitoring data of the loss analysis system;

[0079] When processing change data, the reference change trend index for each trend analysis stage is determined based on the overlapping monitoring data of the loss analysis system and its associated change system;

[0080] Based on the reference change trend index and matching evaluation coefficient of each trend analysis stage, the change trend matching degree of each monitoring data is determined, and the key monitoring data of the loss analysis system is determined according to the change trend matching degree.

[0081] Among them, for a single loss analysis system, the associated change ratio = the number of associated change systems of the loss analysis system / the number of change analysis systems of the target monitoring train. The value of the preset associated change ratio can be determined by the user according to the actual work scenario. For example, the user can set it according to the operation monitoring record. The higher the user's requirements for the timeliness and accuracy of the monitoring results of the door system, the larger the value of the preset associated change ratio. A method for determining the value of the preset associated change ratio is provided, and the operation monitoring record for the change data processing of the loss analysis system is recorded as the associated reference record. The minimum value of the associated change ratio of the loss analysis system of the associated reference record that meets the user's requirements for the timeliness and accuracy of the monitoring results of the door system is recorded as the preset associated change ratio;

[0082] When performing change data processing on a single loss analysis system, the loss analysis system and its associated change systems are recorded as a change analysis set. The values ​​of the overlapping monitoring data of each door system in the change analysis set during each door unlocking task and door locking task completed in the associated change analysis phase are obtained. The end time of the associated change analysis phase is the time when the change data processing on the loss analysis system is determined. The duration of the associated change analysis phase can be determined by the user according to the actual work scenario. For example, the user can set it according to the operation monitoring record. The higher the user's requirements for the timeliness and accuracy of the monitoring results of the door system, the longer the duration of the associated change analysis phase is. A value for the duration of the associated change analysis phase is provided, and the value of the duration of the associated change analysis phase is 200 days.

[0083] The associated change analysis phase of the associated change analysis phase is divided into several trend analysis phases of equal duration. The higher the user's requirements for the timeliness and accuracy of the monitoring results of the vehicle door system, the more trend analysis phases are divided. The reference data change index of each coincidence monitoring data of the loss analysis system and its associated change system in each trend analysis phase is tested. For a single coincidence monitoring data, the reference trend change index of any trend analysis phase is the average value of the trend change indexes of each vehicle door system in the change analysis set. For a single vehicle door system, the trend change index = (the value of the coincidence monitoring data first obtained in the trend analysis phase - the value of the coincidence monitoring data last obtained in the trend analysis phase) / the value of the coincidence monitoring data first obtained in the trend analysis phase;

[0084] For the single monitoring data of the loss analysis system, the value of the monitoring data is obtained when the door unlocking task and the door locking task are completed each time in the associated change analysis stage, and the change index to be evaluated in each trend analysis stage is detected. For a single trend analysis stage, the change index to be evaluated = (the value of the monitoring data obtained for the first time in the trend analysis stage - the value of the monitoring data obtained for the last time in the trend analysis stage) / the value of the monitoring data obtained for the first time in the trend analysis stage. The change trend matching degree is the sum of the products of the trend difference index of each trend analysis stage and the corresponding matching evaluation coefficient. For a single trend analysis stage, the trend difference index is the absolute value of the difference between the change index to be evaluated and the reference change trend index in the trend analysis stage. If the change trend matching degree of the monitoring data is greater than the preset change trend matching degree, the monitoring data is recorded as the key monitoring data of the loss analysis system, and curve fitting is performed on the loss situation of the loss analysis system based on the key monitoring data and the change analysis data. This is content that is easy for technicians in this field to understand and will not be elaborated here.

[0085] The value of the preset change trend matching degree can be determined by the user according to the actual working scenario. For example, the user can set it according to the operation monitoring record. The higher the user's requirements for the timeliness and accuracy of the monitoring results of the vehicle door system, the larger the value of the preset change trend matching degree. A method for transplanting the value of the preset change trend matching degree is provided, and the minimum value of the change trend matching degree of the key monitoring data of the associated reference record that meets the user's requirements for the timeliness and accuracy of the monitoring results of the vehicle door system is recorded as the preset change trend matching degree.

[0086] Specifically, whether to adjust the matching evaluation coefficient corresponding to each trend analysis stage is determined according to the change difference coefficient;

[0087] If the change difference coefficient in a trend analysis phase is greater than the preset change difference coefficient, the matching evaluation coefficient is adjusted downward according to the change difference coefficient;

[0088] The reduction value of the matching evaluation coefficient is positively correlated with the change difference coefficient.

[0089] Among them, for any trend analysis stage of a single loss analysis system, the initial matching evaluation coefficient is determined according to the operating load parameter of the target monitoring train in the trend analysis stage. The initial matching evaluation coefficient is positively correlated with the operating load parameter. The operating load parameter = ln (the travel distance of the target monitoring train in the trend analysis stage × the maximum travel speed of the target monitoring train in the trend analysis stage). The change difference coefficient is the standard deviation of the trend change index of each door system in the change analysis set in the trend analysis stage;

[0090] The value of the preset change difference coefficient can be determined by the user according to the actual working scenario. For example, the user can set it according to the operation monitoring record. The higher the user's requirements for the timeliness and accuracy of the monitoring results of the vehicle door system, the larger the value of the preset change difference coefficient. A method for determining the value of the preset change difference coefficient is provided. The operation monitoring record that is adjusted to reduce the matching evaluation coefficient according to the change difference coefficient is recorded as an adjustment reference record, and the average value of the change difference coefficient of each trend analysis stage of the adjustment reference record that meets the user's requirements for the timeliness and accuracy of the monitoring results of the vehicle door system is recorded as the preset change difference coefficient.

[0091] Specifically, if the change stability coefficient of a change analysis system is less than or equal to the preset change stability coefficient, data compression analysis is performed on the change analysis system, including:

[0092] The change analysis system is recorded as a compression analysis system. The compression analysis method of each change analysis data of the compression analysis system is determined according to the proportion of relevant monitoring data, so as to compress each change analysis data and obtain key monitoring data.

[0093] Specifically, for any change analysis data of the compression analysis system, if the proportion of relevant monitoring data is greater than the preset proportion of relevant monitoring data, the monitoring stage of the change analysis data is divided, and the data compression threshold of each monitoring data segment is set according to the stage overlap index;

[0094] The data compression threshold is negatively correlated with the stage overlap index.

[0095] Specifically, determining whether to perform secondary adjustment on the data compression threshold of each monitoring data segment according to the reference change index;

[0096] For a single monitoring data segment, if the reference change index is greater than the preset reference change index, the data compression threshold is reduced and adjusted according to the reference change index;

[0097] The reduction value of the data compression threshold is positively correlated with the reference change index.

[0098] Among them, for any change analysis data of a single compression analysis system, the proportion of relevant monitoring data = the number of relevant monitoring data of the change analysis data / the number of monitoring data of the compression analysis system. The relevant monitoring data is other change analysis data whose monitoring phase overlaps with the monitoring phase of the change analysis data. For a single monitoring data, the starting time of the monitoring phase is the time when the acquisition of the monitoring data starts, and the ending time of the monitoring phase is the time when the acquisition of the monitoring data stops. The value of the preset proportion of relevant monitoring data can be determined by the user according to the actual working scenario. For example, the user can set it according to the operation monitoring record. The higher the user's requirements for the timeliness and accuracy of the monitoring results of the vehicle door system, the smaller the value of the preset proportion of relevant monitoring data. A method for determining the value of the preset proportion of relevant monitoring data is provided. The operation monitoring record for determining the data compression threshold based on the proportion of relevant monitoring data is recorded as a compression reference record. The maximum value of the proportion of relevant monitoring data in the compression reference record that meets the user's requirements for the timeliness and accuracy of the monitoring results of the vehicle door system is recorded as the preset proportion of relevant monitoring data.

[0099] For single change analysis data, the monitoring phase of the change analysis data is divided into several monitoring data segments of the same duration. For a single monitoring data segment, the phase overlap index is the number of relevant monitoring data existing in the monitoring data segment during the monitoring phase. The reference change index is the average value of the change indexes of the relevant monitoring data existing in the monitoring data segment during the monitoring phase. The change analysis data is compressed according to the data compression threshold of the monitoring data segment, and the compressed change analysis data is recorded as the key monitoring data. How to perform segmented compression on the change analysis data according to the data compression threshold of each monitoring data segment is easy to understand for those skilled in the art and will not be elaborated on here.

[0100] The value of the preset reference change index can be determined by the user according to the actual working scenario. For example, the user can set it according to the operation monitoring record. The higher the user's requirements for the timeliness and accuracy of the monitoring results of the vehicle door system, the smaller the value of the preset reference change index. A method for determining the value of the preset reference change index is provided. The operation monitoring record that is adjusted to reduce the data compression threshold according to the reference change index is recorded as a threshold adjustment record, and the minimum value of the reference change index in the threshold adjustment record that meets the user's requirements for the timeliness and accuracy of the monitoring results of the vehicle door system is recorded as the preset reference change index.

[0101] Specifically, for any change analysis data of the compression analysis system, if the proportion of relevant monitoring data is less than or equal to the preset proportion of relevant monitoring data, a data compression threshold is determined based on the proportion of relevant monitoring data, and compression processing is performed on the change analysis data according to the data compression threshold;

[0102] The data compression threshold is negatively correlated with the proportion of relevant monitoring data.

[0103] Among them, the determined data compression threshold is recorded as the global compression threshold, so as to perform compression processing on the change analysis data, and the change analysis data that has completed the compression processing is recorded as the key monitoring data. How to perform data compression according to the global compression threshold is easy to understand for technical personnel in this field and will not be elaborated here.

[0104] Thus far, the technical solutions of the present invention have been described in conjunction with the preferred embodiments shown in the accompanying drawings. However, it will be readily understood by those skilled in the art that the scope of protection of the present invention is obviously not limited to these specific embodiments. Without departing from the principles of the present invention, those skilled in the art may make equivalent changes or substitutions to the relevant technical features, and the technical solutions after such changes or substitutions will fall within the scope of protection of the present invention.

[0105] The foregoing description is merely a preferred embodiment of the present invention and is not intended to limit the present invention. Those skilled in the art will readily appreciate that the present invention is susceptible to various modifications and variations. Any modifications, equivalent substitutions, or improvements made within the spirit and principles of the present invention are intended to be within the scope of protection of the present invention.

Claims

1. A method for monitoring train running status safety based on data analysis, characterized in that: include: Under abnormal change analysis conditions, the data analysis strategy for each change analysis system is determined based on the trend change stability index and the change continuity index, which is to perform loss feature analysis or data compression analysis on the change analysis system. When performing loss feature analysis, determine the proportion of related changes based on the similar change coefficient and position correlation coefficient of each change analysis system. Based on the proportion of related changes, determine whether to perform change data processing for the loss analysis system to determine key monitoring data. When performing data compression analysis, the compression analysis method of each change analysis data of the compression analysis system is determined according to the proportion of relevant monitoring data to obtain key monitoring data. The compression analysis method is to set the data compression threshold for each monitoring data segment according to the stage overlap index, or to set the data compression threshold based on the proportion of relevant monitoring data; Under the analysis completion condition, key monitoring data is sent to the user. The analysis completion condition is that there is a change in the analysis system to complete the loss feature analysis or data compression analysis.

2. The method for monitoring train running status safety based on data analysis according to claim 1, characterized in that: Under abnormal change analysis conditions, the trend change stability index and change continuity index of each change analysis system are tested; For a single change analysis system, The trend change stability index is determined according to the change index of each change analysis data of the change analysis system during the change assessment phase; The change continuity index is determined according to the change direction of the change index obtained by the change analysis system each time during the change assessment phase; The abnormal change analysis condition is that the target monitored train has a door system that needs to be analyzed for changes, and the door system that needs to be analyzed for changes is recorded as a change analysis system.

3. The method for monitoring train running status safety based on data analysis according to claim 2, characterized in that: If the change stability coefficient of a change analysis system is greater than the preset change stability coefficient, a loss characteristic analysis is performed on the change analysis system, including: The change analysis system is recorded as the loss analysis system, and the associated change ratio of the loss analysis system is determined based on the similarity change coefficient and position correlation coefficient of each change analysis system within the associated evaluation range; Determine whether to perform change data processing for the loss analysis system based on the proportion of related changes; The change stability coefficient is determined based on the trend change stability index and the change continuity index.

4. The method for monitoring train running status safety based on data analysis according to claim 3 is characterized in that: For a single loss analysis system, determine the correlation change index of each change analysis system within the correlation assessment range based on the similarity change coefficient and position correlation coefficient; If the correlation change index of any change analysis system within the correlation evaluation range is greater than the preset correlation change index, then the change analysis system will be recorded as the correlated change system of the loss analysis system; The similarity change coefficient is determined according to the number of overlapping monitoring data of each change analysis system and the stability coefficient difference value, and the position correlation coefficient is determined according to the air pressure interference index of each change analysis system.

5. The method for monitoring train running status safety based on data analysis according to claim 4 is characterized in that: If the associated change ratio of the loss analysis system is greater than the preset associated change ratio, the change data of the loss analysis system is processed to determine the key monitoring data of the loss analysis system; When processing change data, the reference change trend index for each trend analysis stage is determined based on the overlapping monitoring data of the loss analysis system and its associated change system; Based on the reference change trend index and matching evaluation coefficient of each trend analysis stage, the change trend matching degree of each monitoring data is determined, and the key monitoring data of the loss analysis system is determined according to the change trend matching degree.

6. The method for monitoring train running status safety based on data analysis according to claim 5, characterized in that: Determine whether to adjust the matching evaluation coefficient corresponding to each trend analysis stage according to the change difference coefficient; If the change difference coefficient in a trend analysis phase is greater than the preset change difference coefficient, the matching evaluation coefficient is adjusted downward according to the change difference coefficient; The reduction value of the matching evaluation coefficient is positively correlated with the change difference coefficient.

7. The method for monitoring train running status safety based on data analysis according to claim 6, characterized in that: If the change stability coefficient of a change analysis system is less than or equal to the preset change stability coefficient, data compression analysis is performed on the change analysis system, including: The change analysis system is recorded as a compression analysis system. The compression analysis method of each change analysis data of the compression analysis system is determined according to the proportion of relevant monitoring data, so as to compress each change analysis data and obtain key monitoring data.

8. The method for monitoring train running status safety based on data analysis according to claim 6, characterized in that: For any change analysis data of the compression analysis system, if the proportion of related monitoring data is greater than the preset proportion of related monitoring data, the monitoring stage of the change analysis data will be divided, and the data compression threshold of each monitoring data segment will be set according to the stage overlap index; The data compression threshold is negatively correlated with the stage overlap index.

9. The method for monitoring train running status safety based on data analysis according to claim 8, characterized in that: Determining whether to perform secondary adjustment on the data compression threshold of each monitoring data segment according to the reference change index; For a single monitoring data segment, if the reference change index is greater than the preset reference change index, the data compression threshold is reduced and adjusted according to the reference change index; The reduction value of the data compression threshold is positively correlated with the reference change index.

10. The method for monitoring train running status safety based on data analysis according to claim 9, characterized in that: For any change analysis data of the compression analysis system, if the proportion of relevant monitoring data is less than or equal to the preset proportion of relevant monitoring data, a data compression threshold is determined based on the proportion of relevant monitoring data, and compression processing is performed on the change analysis data according to the data compression threshold; The data compression threshold is negatively correlated with the proportion of relevant monitoring data.

Images