A rail transit information data cleaning method and system

Abstract

The present invention relates to the field of electrical digital data processing technology, and specifically to a rail transit information data cleaning method and system, the method comprising: determining the degree of abnormality of local data of the rail vibration sensor and the amplitude difference between adjacent local data based on the preset segmentation period data of the rail vibration sensor; determining the overall regularity characteristic factor of the rail vibration sensor based on the amplitude difference; determining the possibility of influence of rail node failure of the rail vibration sensor using the overall regularity characteristic factor of multiple adjacent rail vibration sensors; determining whether the local data is data to be cleaned using the degree of abnormality of local data and the possibility of influence of rail node failure. Through the rail transit information data cleaning method of the present invention, vibration data with serious abnormal interference can be targetedly excluded or corrected, ensuring that the system still analyzes the health status of the rail node itself, and improving the monitoring accuracy of the rail node.

Description

Technical Field

[0001] The present invention relates to the technical field of electronic digital data processing, and in particular to a rail transit information data cleaning method and system. Background Art

[0002] Rail transit information data refers to various data related to the rail transit system, including train location, speed, delays, passenger flow, station operation, etc. These data can be collected through various sensors, monitoring equipment, computer systems and other data sources.

[0003] Among them, rail transit vehicles include subways. The relevant information of this type of transportation includes data related to the status of rail equipment, such as recording the operating status and fault information of the equipment in the rail transit system (such as signal equipment, power equipment, and communication equipment), which includes the vibration data of each node track. These vibration data are collected by vibration sensors and can be used for equipment maintenance and troubleshooting to ensure the normal operation of the rail transit system.

[0004] When the aging of the track causes cracks or looseness, etc., resulting in abnormal conditions of the track nodes, it may cause a sudden change in vibration frequency or an abnormal frequency, or a sudden increase or decrease in the amplitude of the vibration. It is necessary to identify the abnormal vibration data of such track nodes separately for analysis. However, in the process of monitoring the track status, on the one hand, due to the life of the vibration sensor itself and the influence of external factors during the monitoring process, the vibration data obtained itself has certain interference fluctuations; on the other hand, since there are multiple track trains running on the track in sequence, and the speeds of different trains at the corresponding detection positions are different, the generated interaction forces have certain differences, resulting in certain interference fluctuations in the vibration data at the detection position; therefore, the abnormal interference fluctuations in the above two aspects will eventually reduce the accuracy of monitoring abnormal track nodes, so it is necessary to clean the abnormal interference data and retain the abnormal vibration data of the track node itself for analysis. Summary of the invention

[0005] In order to solve the technical problem that the monitoring accuracy of abnormal track nodes is reduced due to abnormal interference fluctuations, the purpose of the present invention is to provide a rail transit information data cleaning method and system, and the technical solution adopted is as follows:

[0006] The present invention provides a rail transit information data cleaning method, the method comprising:

[0007] Based on the preset segmented period data of the rail vibration sensor, determining the degree of abnormality of the local data of the rail vibration sensor and the amplitude difference between adjacent local data;

[0008] determining an overall regularity characteristic factor of the rail vibration sensor based on the amplitude difference;

[0009] Determine the possibility of influence of track node failure of the track vibration sensor by using the overall regularity characteristic factor of a plurality of adjacent track vibration sensors;

[0010] Whether the local data is data to be cleaned is determined by using the degree of abnormality of the local data and the possibility of impact of the track node failure.

[0011] Further, based on the preset segmentation period data of the rail vibration sensor, the step of determining the abnormality degree of the local data of the rail vibration sensor comprises:

[0012] Based on the preset segmentation cycle data of the rail vibration sensor, determine any target peak point and a peak group consisting of a plurality of corresponding peak points adjacent thereto;

[0013] Determining a target amplitude difference value between the target peak point and other peak points in the peak group;

[0014] The degree of abnormality of local data of the rail vibration sensor is determined by using the target amplitude difference value and the maximum amplitude difference value in the peak value group.

[0015] Further, the step of determining the degree of abnormality of local data of the rail vibration sensor by using the target amplitude difference value and the maximum amplitude difference value in the peak value group comprises:

[0016] Determine the local prominence of the local data corresponding to the target peak point by using the target amplitude difference value;

[0017] The degree of local data abnormality of the rail vibration sensor is calculated using the local protrusion degree, the target amplitude corresponding to the target peak point, and the maximum amplitude difference value in the peak group.

[0018] Further, the step of determining the amplitude difference between adjacent local data based on the preset segmentation period data of the rail vibration sensor includes:

[0019] Determine the first amplitude difference between each group of adjacent maximum values ​​based on the preset segmentation period data of the rail vibration sensor;

[0020] Based on the preset segmentation period data, determining the second amplitude difference between each group of adjacent minimum values;

[0021] Among them, two adjacent maximum values ​​or two adjacent minimum values ​​are a group.

[0022] Further, based on the amplitude difference, the step of determining the overall regularity characteristic factor of the rail vibration sensor comprises:

[0023] Determine a first difference of first amplitude differences between adjacent groups using the first amplitude difference;

[0024] Determine a second difference of second amplitude differences between adjacent groups using the second amplitude difference;

[0025] Using the first difference and the second difference respectively, determine the first amplitude change regularity and the second amplitude change regularity corresponding to each other;

[0026] Determine the mean of the amplitude differences corresponding to all the first amplitude differences and the second amplitude differences;

[0027] The overall regularity characteristic factor of the rail vibration sensor is calculated using the amplitude difference mean, the first amplitude change regularity and the second amplitude change regularity.

[0028] Furthermore, the step of determining the possibility of influence of the track node failure of the track vibration sensor by using the overall regularity characteristic factor of a plurality of adjacent track vibration sensors comprises:

[0029] determining a first difference in an overall regularity characteristic factor between the rail vibration sensor and a preceding adjacent rail vibration sensor in a preceding direction;

[0030] determining a second difference in the overall regularity characteristic factor between a plurality of adjacent rail vibration sensors in a direction behind the rail vibration sensor;

[0031] determining a third difference in overall regularity characteristic factors between a plurality of adjacent rail vibration sensors in a direction forward of the preceding adjacent rail vibration sensor;

[0032] Using the first difference, the second difference and the third difference, calculate the possibility of influence of the track node failure of the track vibration sensor;

[0033] The previous direction and the next direction are based on the direction of the train's travel.

[0034] Further, the step of calculating the possibility of the impact of the track node failure of the track vibration sensor by using the first difference, the second difference and the third difference includes:

[0035] The possibility of the impact of the track node failure of the track vibration sensor is calculated by using the accumulated value of the first difference, the accumulated value of the second difference, and the accumulated value of the third difference.

[0036] Optionally, the step of determining whether the local data is data to be cleaned by using the degree of abnormality of the local data and the possibility of impact of the track node failure includes:

[0037] Determining a ratio between the degree of abnormality of the local data and the likelihood of impact of the orbital node failure;

[0038] The normalized ratio is compared with a preset threshold to determine whether the local data is data to be cleaned.

[0039] Optionally, after the step of determining whether the local data is data to be cleaned by using the degree of abnormality of the local data and the possibility of impact of the track node failure, the method further includes:

[0040] The normalized ratio is used to correct the data to be cleaned to obtain cleaned data.

[0041] The present invention also provides a rail transit information data cleaning system, the system is used to implement the rail transit information data cleaning method as described in any one of the above items; the system comprises:

[0042] A data analysis module, used to determine the degree of abnormality of local data of the rail vibration sensor and the amplitude difference between adjacent local data based on preset segmentation period data of the rail vibration sensor;

[0043] an amplitude analysis module, for determining an overall regularity characteristic factor of the rail vibration sensor based on the amplitude difference;

[0044] A track analysis module, used to determine the possibility of track node failure influence of the track vibration sensor by using the overall regularity characteristic factors of a plurality of adjacent track vibration sensors;

[0045] The cleaning evaluation module is used to determine whether the local data is data to be cleaned by using the abnormality degree of the local data and the possibility of the impact of the track node failure.

[0046] The present invention has the following beneficial effects:

[0047] The present invention analyzes each local data (local vibration data) of the track vibration sensor in the preset segmentation period data, and then determines the local abnormality degree of each local vibration data. This operation avoids the interference caused by the sawtooth change characteristics of the vibration data itself and the factors of the vibration sensor to the abnormal vibration data judgment of the track node, thereby improving the accuracy of data cleaning; and by analyzing the overall data change law of the vibration data collected by the vibration sensor in the time series, and analyzing the difference in laws between it and other surrounding vibration sensors, and then determining the overall data regularity of the vibration sensor itself and the possibility of being affected by the fault of the track node. This operation avoids the misjudgment of the abnormal vibration data of the track node due to the interference fluctuations generated during the train travel process, thereby improving the accuracy of subsequent data cleaning. Combined with the degree of local data abnormality and the possibility of impact of track node failure, the degree of influence of the track node's own abnormality and abnormal interference from other factors is weighed, so as to comprehensively judge whether each local vibration data is vibration data seriously affected by abnormal interference fluctuations. This type of vibration data makes it impossible to normally identify and analyze the abnormalities generated by the track node itself, and then these vibration data with serious abnormal interference can be targetedly excluded or corrected to ensure that the system still analyzes the health status of the track node itself and improve the monitoring accuracy of the track node. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] In order to more clearly illustrate the technical solutions and advantages in the embodiments of the present invention or the prior art, the drawings required for use in the embodiments or the prior art descriptions are briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0049] Figure 1 A flow chart of the steps of a rail transit information data cleaning method provided by one embodiment of the present invention;

[0050] Figure 2 A detailed flow chart of step S1 in a rail transit information data cleaning method provided by one embodiment of the present invention;

[0051] Figure 3 A detailed flow chart of step S1 in a rail transit information data cleaning method provided by another embodiment of the present invention;

[0052] Figure 4 A detailed flow chart of step S3 in a rail transit information data cleaning method provided by one embodiment of the present invention;

[0053] Figure 5It is a structural diagram of the hardware operating environment of the rail transit information data cleaning device involved in the embodiment of the present invention;

[0054] Figure 6 It is a schematic diagram of the framework structure of the rail transit information data cleaning system involved in the embodiment of the present invention. DETAILED DESCRIPTION

[0055] In order to further explain the technical means and effects adopted by the present invention to achieve the predetermined invention purpose, the following is a detailed description of a rail transit information data cleaning method proposed by the present invention, its specific implementation method, structure, characteristics and effects, in combination with the accompanying drawings and preferred embodiments. In the following description, different "one embodiment" or "another embodiment" does not necessarily refer to the same embodiment. In addition, specific features, structures or characteristics in one or more embodiments may be combined in any suitable form.

[0056] Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.

[0057] The specific scheme of a rail transit information data cleaning method provided by the present invention is described in detail below with reference to the accompanying drawings.

[0058] Embodiment 1:

[0059] For a rail transit information data cleaning method provided by the present invention, please refer to Figure 1 , which shows a flow chart of the steps of a rail transit information data cleaning method provided by an embodiment of the present invention.

[0060] The method comprises:

[0061] Step S1, based on preset segmentation period data of the rail vibration sensor, determining the abnormality degree of local data of the rail vibration sensor and the amplitude difference between adjacent local data;

[0062] Vibration sensors are usually installed at fixed distances on the tracks along the subway line to monitor the vibration data of each node on the track in real time. At the same time, the vibration data can be combined with the train number, the speed of the train during travel, and the position on the track, and these data can also be transmitted to the computer for subsequent analysis.

[0063] In this embodiment, the preset segmentation cycle data means that all vibration data can be segmented according to a certain time period, and the abnormal situation of the orbital node in each segmentation cycle time can be determined by analyzing each segmentation cycle data.

[0064] The preset segmentation period can be set as needed, for example, 10s. For the track section along the subway line to be inspected, each vibration sensor can be marked with a serial number according to the direction of train travel, and the vibration data of each vibration sensor within 10s (i.e., the preset segmentation period data) is continuously collected for analysis. This embodiment takes any vibration sensor as an example for analysis, and the following embodiments will refer to the current sensor or the vibration sensor.

[0065] Since the abnormal interference data (abnormal interference fluctuation) generated by the vibration sensor itself usually appears as local data fluctuation, it will cause irregular mutations in the vibration amplitude, while the vibration data of normal track nodes usually appears as continuous sawtooth electrical signals, and the amplitude of the electrical signal is usually relatively regular, that is, the amplitudes between adjacent multiple peaks or troughs are basically the same, or increase or decrease relatively smoothly;

[0066] Therefore, the degree of interference of the vibration sensor on the vibration data can be determined by judging the degree of abnormality of each local data (which can be considered as a data point collected by the vibration sensor) within the preset segmentation period. The degree of abnormality of the local data here can reflect the degree of irregularity or prominence of each local data compared with other local data around it.

[0067] For the acquired preset segmentation period data, each local data has an amplitude and a peak point, so the amplitude difference between adjacent local data can be further obtained therefrom, and the peak point is a maximum value or a minimum value.

[0068] In a preferred embodiment, please refer to Figure 2 , the step S1 comprises:

[0069] Step S10, determining a peak group consisting of any target peak point and a plurality of corresponding peak points adjacent thereto based on preset segmentation period data of the rail vibration sensor;

[0070] Step S11, determining a target amplitude difference value between the target peak point and other peak points in the peak group;

[0071] Step S12: Determine the degree of abnormality of local data of the rail vibration sensor by using the target amplitude difference value and the maximum amplitude difference value in the peak value group.

[0072] Specifically, the step S12 includes:

[0073] Determine the local prominence of the local data corresponding to the target peak point by using the target amplitude difference value;

[0074] The degree of local data abnormality of the rail vibration sensor is calculated using the local protrusion degree, the target amplitude corresponding to the target peak point, and the maximum amplitude difference value in the peak group.

[0075] According to the continuous change relationship of the preset segmentation period data collected in the time series, there is generally a small difference between adjacent vibration data, so a peak point corresponding to any collection time t is taken as the target peak point (here it can also be referred to as peak point t, t corresponds to the collection time, and the peak point at time t is unique), and multiple corresponding peak points are taken to the left or right side or both sides, for example, the number of adjacent multiple corresponding peak points D=5 (if peak point t is a maximum value, then other peak points are maximum values, otherwise they are all minimum values), thereby establishing a window (peak group);

[0076] Get the target amplitude of the data point corresponding to the target peak point , and obtain the difference between the amplitude corresponding to the target peak point and the amplitude corresponding to other peak points in the window, thus obtaining:

[0077] ;

[0078] In the formula, i represents the vibration sensor that needs to be verified, k represents other peak points in the window, Indicates the amplitude corresponding to other peak points; reaction The larger the value of the local prominence in the time series, the greater the local prominence, and the greater the abnormality of the corresponding t-th peak point (i.e., peak point t).

[0079] At the same time, the larger the value of the t-th peak point itself in the window, the higher the possibility of its abnormality. Therefore, the degree of abnormality of the local data at any current moment can be obtained:

[0080] ;

[0081] ;

[0082] In the formula, Indicates the maximum value of the data difference in the current window (the maximum amplitude difference, obtained by subtracting the minimum amplitude from the maximum amplitude in the window). express The relative size within the window, the larger its value, the greater the abnormality of the tth data. Weighted, thus obtaining the degree of local data abnormality of any target peak point ;

[0083] It should be noted that the above local data abnormality Taking the maximum point of the peak point as an example, when the peak point is the minimum point, it is expressed as ,in Indicates the minimum data difference in the current window (minimum amplitude difference value). The larger it is, the more abnormal the t-th data is.

[0084] In another preferred embodiment, please refer to Figure 3 , the step S1 comprises:

[0085] Step S100, determining the first amplitude difference between each group of adjacent maximum values ​​based on the preset segmentation period data of the rail vibration sensor;

[0086] Step S110, determining the second amplitude difference between each group of adjacent minimum values ​​based on the preset segmentation period data;

[0087] Among them, two adjacent maximum values ​​or two adjacent minimum values ​​are a group.

[0088] According to prior knowledge, vibration data is usually transmitted from the train location to both sides along the track, and the signal gradually attenuates as the distance increases; when abnormal vibration is generated by a fault at a certain node on the track, the vibration data collected by some vibration sensors after the node and the vibration data collected by the vibration sensors before the node along the direction of vibration transmission will destroy the original vibration attenuation law; therefore, the track node where the vibration sensor that may have abnormal vibration is located can be determined based on the difference in vibration data between adjacent vibration sensors;

[0089] It should be noted that since the propagation of vibration data in solids takes time, and the transmission speed of vibration in solid media is related to the properties of the material itself, in order to avoid the error in the data collection process of the vibration sensor due to the influence of the propagation time, the vibration propagation speed and the distance between two adjacent vibration sensor nodes can be obtained according to the prior track design; thereby, the propagation time between two adjacent sensor nodes can be obtained;

[0090] According to the analysis, the train is in motion. As the train approaches, the vibration data collected by each vibration sensor is in the process of amplification, and its amplitude is gradually increasing.

[0091] Therefore, in this embodiment, the amplitude differences between all adjacent maximum value points or adjacent minimum value points in the preset segmentation period data corresponding to the vibration sensor i can be obtained. , where t represents the sampling time corresponding to any maximum or minimum point, and can also represent the peak point, the explanation here is the same as above;

[0092] At this time, according to the above logic, the train is in the process of moving. Therefore, for the vibration sensor, the closer it is to the train and the closer the sampling time is to the current collection time point, the amplitude difference between adjacent groups of maximum values ​​should be in the process of continuously increasing.

[0093] Next, according to the update direction of the sampling time, the larger the t value, the newer the sampling time and the closer it is to the current acquisition time point, thereby obtaining the amplitude difference between the two adjacent groups of maximum points. and The difference between them, where grouping refers to every two adjacent maximum values ​​or every two adjacent minimum values ​​as a group. Taking the maximum value as an example, the first amplitude difference between each group of adjacent maximum values ​​refers to the difference between the two corresponding amplitudes, that is, the amplitude difference of each group. Similarly, the second amplitude difference refers to the difference between the two adjacent amplitudes corresponding to each group of adjacent minimum values; and the amplitude difference and The difference between them refers to the difference obtained by subtracting the amplitude differences of two adjacent groups, that is, the first difference and the second difference mentioned in the next embodiment.

[0094] Step S2, determining an overall regularity characteristic factor of the rail vibration sensor based on the amplitude difference;

[0095] In combination with the above embodiment, specifically, the step S2 includes:

[0096] Determine a first difference of first amplitude differences between adjacent groups using the first amplitude difference;

[0097] Determine a second difference of second amplitude differences between adjacent groups using the second amplitude difference;

[0098] Using the first difference and the second difference respectively, determine the first amplitude change regularity and the second amplitude change regularity corresponding to each other;

[0099] Determine the mean of the amplitude differences corresponding to all the first amplitude differences and the second amplitude differences;

[0100] The overall regularity characteristic factor of the rail vibration sensor is calculated using the amplitude difference mean, the first amplitude change regularity and the second amplitude change regularity.

[0101] Following the previous embodiment, all maximum value point combinations are traversed to show the regularity of the first amplitude change of the vibration data collected by the vibration sensor:

[0102] ;

[0103] In the formula, N represents the number of all adjacent groups; by obtaining the difference between the amplitude differences of all adjacent maximum point combinations (adjacent groups) and the absolute value of the accumulated value, it can be expressed by the fraction ,Right now , the value range is between [-1,1]; the closer the value is to 1, the more obvious the regularity of the amplitude increase of the vibration data collected by the vibration sensor under the influence of the train movement is, indicating that the regularity of the vibration data is higher;

[0104] Similarly, according to the above method, the second amplitude change regularity corresponding to all minimum value point combinations is obtained ;

[0105] For the mean amplitude difference : By accumulating the amplitude differences corresponding to each group of maximum points and each group of minimum points, the mean amplitude difference of the vibration sensor is obtained This value is used to represent the amplitude characteristics of the current sensor during the detection process, and then compared with other vibration sensors.

[0106] Combined with the amplitude difference mean calculated above, the overall regularity characteristic factor of the vibration sensor is obtained:

[0107] ;

[0108] In the formula, the regular mean corresponding to the maximum and minimum values ​​is obtained The larger the value is and the closer it is to 1, the stronger the regularity is and the lower the possibility of track failure is. This value is used to calculate the mean amplitude difference. Weighted, we get ; This value represents the overall regularity of the vibration data collected by the vibration sensor;

[0109] At this time, according to the analysis, when there is no abnormality in the orbital node, the amplitude will be reduced to a certain extent compared with the surrounding sensors during the process of vibration attenuation with the solid;

[0110] Therefore, for the i-th vibration sensor, the relevant vibration data corresponding to the same number of vibration sensors before and after it along the direction of train travel are obtained; based on the propagation time obtained above, the vibration data corresponding to each node when the same vibration wave arrives can be obtained, thereby avoiding accidental errors.

[0111] Step S3, using the overall regularity characteristic factors of a plurality of adjacent rail vibration sensors to determine the possibility of influence of rail node failure of the rail vibration sensor;

[0112] By analyzing the overall regularity characteristic factors of multiple adjacent track vibration sensors including the vibration sensor, the possibility of fault impact on the track node where the track vibration sensor is located can be more comprehensively analyzed. The greater the possibility of fault impact, the more likely the abnormal data is to be caused by a fault in the track node itself.

[0113] In a preferred embodiment, please refer to Figure 4 , the step S3 comprises:

[0114] Step S30, determining a first difference in overall regularity characteristic factor between the rail vibration sensor and a preceding adjacent rail vibration sensor in a preceding direction;

[0115] Step S31, determining a second difference in overall regularity characteristic factors between a plurality of adjacent rail vibration sensors in a direction behind the rail vibration sensor;

[0116] Step S32, determining a third difference in overall regularity characteristic factors between a plurality of adjacent rail vibration sensors in a direction forward of the preceding adjacent rail vibration sensor;

[0117] Step S33, using the first difference, the second difference and the third difference, calculating the possibility of influence of the track node failure of the track vibration sensor;

[0118] The previous direction and the next direction are based on the direction of the train's travel.

[0119] Specifically, the step S33 includes:

[0120] The possibility of the impact of the track node failure of the track vibration sensor is calculated by using the accumulated value of the first difference, the accumulated value of the second difference, and the accumulated value of the third difference.

[0121] According to the above logic, the amplitude between adjacent vibration sensors will decrease regularly. When there is a fault before a certain track node, the above regularity will be destroyed. If the data of adjacent sensors are directly differentially operated, it is easy to be affected by the error caused by the slight increase in the period when the vibration propagates in the medium. Therefore, the analysis is based on the overall regularity characteristic factor calculated above.

[0122] According to the analysis, when the existing faulty track node is between the current i-th sensor and the previous r sensors (the previous adjacent track vibration sensor), since it destroys the original vibration data characteristics, the greater the difference in the above-mentioned overall regularity characteristic factors; at the same time, since the vibration transmission characteristics of the solid medium itself do not change, the vibration data after the i sensor and before the r sensor continue the vibration characteristics of the previous vibration sensor, and the smaller the corresponding overall regularity characteristic factor differences are, the greater the possibility that the current vibration sensor i is affected by the fault;

[0123] The probability that the current vibration sensor i is affected by the track node failure is obtained as follows:

[0124] ;

[0125] In the formula, represents the absolute value of the overall regularity characteristic factor difference (first difference) between the current vibration sensor i and the previous adjacent vibration sensor r. The larger the value, the greater the possibility of node failure.

[0126] At this time, for the vibration sensor i and the ones after i sensors, and obtain the characteristic factor differences between adjacent sensors, thereby obtaining (accumulation of second differences), Indicates this Any vibration sensor among the sensors; similarly, obtain the sensor r before including sensor r The characteristic factor difference between adjacent sensors is obtained (cumulative third differences), Indicates this Any vibration sensor among the sensors; the smaller the difference between the above two (the second and third differences), the more it conforms to the vibration transmission law described in the logic, and the higher the authenticity of the above calculated fault impact possibility; therefore, the two are added and expressed using a fraction, and weighted with the above calculated first difference; thus, we get The larger the value, the greater the possibility that the current sensor i is affected by the fault. At the same time, the larger the value, the greater the abnormal amplitude of the vibration data fluctuation caused by the node failure. The lower the possibility that the monitored vibration data is abnormal due to other factors, and the smaller the overall cleaning amplitude should be.

[0127] Step S4, using the degree of abnormality of the local data and the possibility of impact of the track node failure, determine whether the local data is data to be cleaned.

[0128] Specifically, the step S4 includes:

[0129] Determining a ratio between the degree of abnormality of the local data and the likelihood of impact of the orbital node failure;

[0130] The normalized ratio is compared with a preset threshold to determine whether the local data is data to be cleaned.

[0131] Referring to the above embodiments, the degree of abnormality of the local data of any of the vibration sensors is calculated. and , and based on the calculated probability that the preset segmentation period of the vibration sensor i is affected by the fault Therefore, the local abnormality can be corrected according to the overall possibility of being affected by the fault, and then the necessity and magnitude of correction of any data point (i.e. local data) at any time can be obtained. :

[0132] ;

[0133] In the formula, through the inverse proportional relationship Use fractional expression to weight the abnormality of local data;

[0134] It should be noted that when the extreme point corresponding to t is the maximum value (that is, ), then , when the extreme point corresponding to t is the minimum value (that is, ), then ; The above two formulas are normalized using the norm function, thus obtaining ; The larger the value of the above two-part formula is, the higher the degree of abnormality of the local data is, and the overall data of the sensor is not affected by the fault node, and the vibration data fluctuation generated by it is more likely to show abnormal data;

[0135] The threshold can be set as needed, for example, 0.7. , it means that the abnormal interference level of local data is high, and it needs to be cleaned, otherwise no change will be made to the data.

[0136] In one embodiment, after step S4, the method further includes:

[0137] The normalized ratio is used to correct the data to be cleaned to obtain cleaned data.

[0138] According to the above steps, the data to be cleaned (vibration data with a high degree of abnormal interference) is cleaned, and the cleaned and corrected data is used as new reference data for analyzing the track nodes, thereby obtaining the local vibration data corresponding to any sampling time t of any vibration sensor after cleaning:

[0139] ;

[0140] here Represents the data to be cleaned corresponding to the sampling time t, traverses all vibration data collected by all vibration sensors, and completes all data cleaning based on the above steps.

[0141] The present invention analyzes each local data (local vibration data) of the track vibration sensor in the preset segmentation period data, and then determines the local abnormality degree of each local vibration data. This operation avoids the interference caused by the sawtooth change characteristics of the vibration data itself and the factors of the vibration sensor to the abnormal vibration data judgment of the track node, thereby improving the accuracy of data cleaning; and by analyzing the overall data change law of the vibration data collected by the vibration sensor in the time series, and analyzing the difference in laws between it and other surrounding vibration sensors, and then determining the overall data regularity of the vibration sensor itself and the possibility of being affected by the fault of the track node. This operation avoids the misjudgment of the abnormal vibration data of the track node due to the interference fluctuations generated during the train travel process, thereby improving the accuracy of subsequent data cleaning. Combined with the degree of local data abnormality and the possibility of impact of track node failure, the degree of influence of the track node's own abnormality and abnormal interference from other factors is weighed, so as to comprehensively judge whether each local vibration data is vibration data seriously affected by abnormal interference fluctuations. This type of vibration data makes it impossible to normally identify and analyze the abnormalities generated by the track node itself, and then these vibration data with serious abnormal interference can be targetedly excluded or corrected to ensure that the system still analyzes the health status of the track node itself and improve the monitoring accuracy of the track node.

[0142] Embodiment 2:

[0143] The embodiment of the present invention further provides a rail transit information data cleaning device. The rail transit information data cleaning device can be a data calculation and processing device such as a computer or a server.

[0144] like Figure 5 As shown, Figure 5 It is a structural diagram of the hardware operating environment of the rail transit information data cleaning device involved in the embodiment of the present invention.

[0145] like Figure 5As shown, the rail transit information data cleaning device may include: a processor 1001, such as a CPU, a network interface 1004, a user interface 1003, a memory 1005, and a communication bus 1002. Among them, the communication bus 1002 is used to realize the connection and communication between these components. The user interface 1003 may include a display (Display), an input unit such as a control panel, and the optional user interface 1003 may also include a standard wired interface and a wireless interface. The network interface 1004 may optionally include a standard wired interface and a wireless interface (such as a WIFI interface). The memory 1005 may be a high-speed RAM memory or a stable memory (non-volatile memory), such as a disk memory. The memory 1005 may also be a storage device independent of the aforementioned processor 1001. The memory 1005 as a computer storage medium may include a rail transit information data cleaning program.

[0146] Those skilled in the art will understand that Figure 5 The hardware structure shown in the figure does not constitute a limitation of the device, and may include more or less components than shown in the figure, or combine certain components, or arrange the components differently.

[0147] Continue to refer to Figure 5 , Figure 5 The memory 1005 as a computer-readable storage medium may include an operating system, a user interface module, a network communication module, and a rail transit information data cleaning program.

[0148] exist Figure 5 In the embodiment, the network communication module is mainly used to connect to the server and can communicate data with the server; and the processor 1001 can call the rail transit information data cleaning program stored in the memory 1005 and execute the steps in the above embodiments.

[0149] The hardware structure of the rail transit information data cleaning device described above is used to implement various embodiments of the rail transit information data cleaning method of the present invention.

[0150] In addition, the present invention also provides a rail transit information data cleaning system, please refer to Figure 6 , the rail transit information data cleaning system comprises:

[0151] The data analysis module A10 is used to determine the abnormality degree of local data of the rail vibration sensor and the amplitude difference between adjacent local data based on the preset segmentation period data of the rail vibration sensor;

[0152] Amplitude analysis module A20, used to determine the overall regularity characteristic factor of the rail vibration sensor based on the amplitude difference;

[0153] A track analysis module A30, for determining the possibility of influence of track node failure of the track vibration sensor by using the overall regularity characteristic factors of a plurality of adjacent track vibration sensors;

[0154] The cleaning evaluation module A40 is used to determine whether the local data is data to be cleaned by using the abnormality degree of the local data and the possibility of the impact of the track node failure.

[0155] Furthermore, the data analysis module A10 is also used for:

[0156] Based on the preset segmentation cycle data of the rail vibration sensor, determine any target peak point and a peak group consisting of a plurality of corresponding peak points adjacent thereto;

[0157] Determining a target amplitude difference value between the target peak point and other peak points in the peak group;

[0158] The degree of abnormality of local data of the rail vibration sensor is determined by using the target amplitude difference value and the maximum amplitude difference value in the peak value group.

[0159] Furthermore, the data analysis module A10 is also used for:

[0160] Determine the local prominence of the local data corresponding to the target peak point by using the target amplitude difference value;

[0161] The degree of local data abnormality of the rail vibration sensor is calculated using the local protrusion degree, the target amplitude corresponding to the target peak point, and the maximum amplitude difference value in the peak group.

[0162] Furthermore, the data analysis module A10 is also used for:

[0163] Determine the first amplitude difference between each group of adjacent maximum values ​​based on the preset segmentation period data of the rail vibration sensor;

[0164] Based on the preset segmentation period data, determining the second amplitude difference between each group of adjacent minimum values;

[0165] Among them, two adjacent maximum values ​​or two adjacent minimum values ​​are a group.

[0166] Furthermore, the amplitude analysis module A20 is also used for:

[0167] Determine a first difference of first amplitude differences between adjacent groups using the first amplitude difference;

[0168] Determine a second difference of second amplitude differences between adjacent groups using the second amplitude difference;

[0169] Using the first difference and the second difference respectively, determine the first amplitude change regularity and the second amplitude change regularity corresponding to each other;

[0170] Determine the mean of the amplitude differences corresponding to all the first amplitude differences and the second amplitude differences;

[0171] The overall regularity characteristic factor of the rail vibration sensor is calculated using the amplitude difference mean, the first amplitude change regularity and the second amplitude change regularity.

[0172] Furthermore, the track analysis module A30 is also used for:

[0173] determining a first difference in an overall regularity characteristic factor between the rail vibration sensor and a preceding adjacent rail vibration sensor in a preceding direction;

[0174] determining a second difference in the overall regularity characteristic factor between a plurality of adjacent rail vibration sensors in a direction behind the rail vibration sensor;

[0175] determining a third difference in overall regularity characteristic factors between a plurality of adjacent rail vibration sensors in a direction forward of the preceding adjacent rail vibration sensor;

[0176] Using the first difference, the second difference and the third difference, calculate the possibility of influence of the track node failure of the track vibration sensor;

[0177] The previous direction and the next direction are based on the direction of the train's travel.

[0178] Furthermore, the track analysis module A30 is also used for:

[0179] The possibility of the impact of the track node failure of the track vibration sensor is calculated by using the accumulated value of the first difference, the accumulated value of the second difference, and the accumulated value of the third difference.

[0180] Furthermore, the cleaning assessment module A40 is also used for:

[0181] Determining a ratio between the degree of abnormality of the local data and the likelihood of impact of the orbital node failure;

[0182] The normalized ratio is compared with a preset threshold to determine whether the local data is data to be cleaned.

[0183] Furthermore, the cleaning assessment module A40 is also used for:

[0184] The normalized ratio is used to correct the data to be cleaned to obtain cleaned data.

[0185] The specific implementation of the rail transit information data cleaning system of the present invention is basically the same as the embodiments of the rail transit information data cleaning method described above, and will not be repeated here.

[0186] In addition, the present invention also provides a computer-readable storage medium. The computer-readable storage medium of the present invention stores a rail transit information data cleaning program, wherein when the rail transit information data cleaning program is executed by a processor, the steps of the rail transit information data cleaning method as described above are implemented.

[0187] Among them, the method implemented when the rail transit information data cleaning program is executed can refer to the various embodiments of the rail transit information data cleaning method of the present invention, and will not be repeated here.

[0188] It should be noted that the sequence of the above embodiments of the present invention is only for description and does not represent the advantages and disadvantages of the embodiments. The processes depicted in the accompanying drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0189] The various embodiments in this specification are described in a progressive manner, and the same or similar parts between the various embodiments can be referenced to each other, and each embodiment focuses on the differences from other embodiments.

[0190] It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Furthermore, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0191] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0192] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0193] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0194] Although preferred embodiments of the present invention have been described, additional changes and modifications may occur to these embodiments once those skilled in the art are aware of the basic inventive concepts.

[0195] The above description is only a preferred embodiment of the present invention, and does not limit the scope of the present invention. All equivalent structural changes made by using the contents of the present invention specification and drawings under the inventive concept of the present invention, or directly / indirectly applied in other related technical fields are included in the protection scope of the present invention.

Claims

1. A rail transit information data cleaning method, characterized in that: The method comprises: Based on the preset segmented period data of the rail vibration sensor, determining the degree of abnormality of the local data of the rail vibration sensor and the amplitude difference between adjacent local data; determining an overall regularity characteristic factor of the rail vibration sensor based on the amplitude difference; Determine the possibility of influence of track node failure of the track vibration sensor by using the overall regularity characteristic factor of a plurality of adjacent track vibration sensors; Determine whether the local data is data to be cleaned by using the degree of abnormality of the local data and the possibility of impact of the track node failure; The step of determining the degree of abnormality of local data of the rail vibration sensor based on preset segmented period data of the rail vibration sensor comprises: Based on the preset segmentation cycle data of the rail vibration sensor, determine any target peak point and a peak group consisting of a plurality of corresponding peak points adjacent thereto; Determining a target amplitude difference value between the target peak point and other peak points in the peak group; Determine the degree of abnormality of local data of the rail vibration sensor by using the target amplitude difference value and the maximum amplitude difference value in the peak value group; The step of determining the degree of abnormality of local data of the rail vibration sensor by using the target amplitude difference value and the maximum amplitude difference value in the peak value group comprises: Determine the local prominence of the local data corresponding to the target peak point by using the target amplitude difference value; The degree of abnormality of the local data of the rail vibration sensor is calculated by using the local protrusion degree, the target amplitude corresponding to the target peak point and the maximum amplitude difference value in the peak group; The step of determining the amplitude difference between adjacent local data based on the preset segmented period data of the rail vibration sensor comprises: Determine the first amplitude difference between each group of adjacent maximum values ​​based on the preset segmentation period data of the rail vibration sensor; Based on the preset segmentation period data, determining the second amplitude difference between each group of adjacent minimum values; Among them, two adjacent maximum values ​​or two adjacent minimum values ​​are grouped together; The step of determining the overall regularity characteristic factor of the rail vibration sensor based on the amplitude difference comprises: Determine a first difference of first amplitude differences between adjacent groups using the first amplitude difference; Determine a second difference of second amplitude differences between adjacent groups using the second amplitude difference; Using the first difference and the second difference respectively, determine the first amplitude change regularity and the second amplitude change regularity corresponding to each other; Determine the mean of the amplitude differences corresponding to all the first amplitude differences and the second amplitude differences; Using the amplitude difference mean, the first amplitude change regularity and the second amplitude change regularity, calculate and obtain an overall regularity characteristic factor of the rail vibration sensor; The step of determining the possibility of influence of track node failure of the track vibration sensors by using the overall regularity characteristic factors of a plurality of adjacent track vibration sensors comprises: determining a first difference in an overall regularity characteristic factor between the rail vibration sensor and a preceding adjacent rail vibration sensor in a preceding direction; determining a second difference in the overall regularity characteristic factor between a plurality of adjacent rail vibration sensors in a direction behind the rail vibration sensor; determining a third difference in overall regularity characteristic factors between a plurality of adjacent rail vibration sensors in a direction forward of the preceding adjacent rail vibration sensor; Using the first difference, the second difference and the third difference, calculate the possibility of influence of the track node failure of the track vibration sensor; Wherein, the previous direction and the next direction are based on the direction of travel of the train; The step of determining whether the local data is data to be cleaned by using the degree of abnormality of the local data and the possibility of impact of the track node failure includes: Determining a ratio between the degree of abnormality of the local data and the likelihood of impact of the orbital node failure; The normalized ratio is compared with a preset threshold to determine whether the local data is data to be cleaned.

2. The rail transit information data cleaning method according to claim 1, characterized in that: The step of calculating the possibility of the impact of the track node failure of the track vibration sensor by using the first difference, the second difference and the third difference comprises: The possibility of the impact of the track node failure of the track vibration sensor is calculated by using the accumulated value of the first difference, the accumulated value of the second difference, and the accumulated value of the third difference.

3. The rail transit information data cleaning method according to claim 1, characterized in that: After the step of determining whether the local data is data to be cleaned by using the degree of abnormality of the local data and the possibility of the impact of the track node failure, the method further includes: The normalized ratio is used to correct the data to be cleaned to obtain cleaned data.

4. A rail transit information data cleaning system, characterized in that: The system is used to implement the rail transit information data cleaning method according to any one of claims 1 to 3; the system comprises: A data analysis module, used to determine the degree of abnormality of local data of the rail vibration sensor and the amplitude difference between adjacent local data based on preset segmentation period data of the rail vibration sensor; an amplitude analysis module, for determining an overall regularity characteristic factor of the rail vibration sensor based on the amplitude difference; A track analysis module, used to determine the possibility of track node failure influence of the track vibration sensor by using the overall regularity characteristic factors of a plurality of adjacent track vibration sensors; The cleaning evaluation module is used to determine whether the local data is data to be cleaned by using the abnormality degree of the local data and the possibility of the impact of the track node failure.

Images