Compensation method for full-parallel AT power supply fault distance measurement data missing of electrified railway

Abstract

The invention relates to the technical field of information compensation of electrified railway fault distance measurement, in particular to an electrified railway full parallel AT power supply fault distance measurement data missing compensation method, which comprises the following steps of: fitting missing data based on a current balance equation and historical data, analyzing the difference between a missing data fitting value and non-missing data, and calculating the missing data; calculating the dynamic fitting confidence of each kiosk; constructing a fitting rationality factor based on a Bayesian network in combination with historical data, real-time data and dynamic fitting confidence; dynamically adjusting the fitting value of the kiosk missing current data according to the fitting rationality factor; fault distance measurement is performed through the dynamically adjusted fitting value and the non-missing current data, so that the distance measurement stability and reliability are improved, the method can adapt to various fault types and complex system topology structures, the problem that the distance measurement precision is influenced by fitting data deviation superposition in a multi-pavilion data missing scene is avoided, and the fault measurement accuracy is improved. And safe and stable operation of the electrified railway is ensured.

Description

Technical Field

[0001] The present application relates to the technical field of information compensation for fault distance measurement in electrified railways, and in particular to a method for compensating for missing data in fault distance measurement for fully parallel AT power supply in electrified railways. Background Art

[0002] With the development of high-speed railways, the speed of trains has increased and the traffic density has increased. The power supply system needs to have high capacity and high reliability. The full parallel AT power supply method is widely used due to its advantages such as high transmission power, low voltage loss and long power supply distance. However, its complex power supply structure also increases the failure rate. During the development process, researchers have proposed a variety of ranging principles, which basically meet the needs of the project, but are also affected by many factors. The significance of fault ranging technology is that it can quickly and accurately determine the fault type and calibrate the fault point location, so as to solve the fault in time, restore power supply, and ensure the safe and stable operation of electrified railways. It plays an important role in improving the efficiency and safety of railway transportation.

[0003] However, in the scenario where data from multiple kiosks are missing, the missing data from each kiosk will introduce certain deviations. The deviations in the scenario with multiple kiosks will be superimposed on each other, significantly amplifying the overall error and affecting the ranging accuracy. Summary of the invention

[0004] In order to solve the above technical problems, the present application provides a method for compensating for missing distance measurement data of full-parallel AT power supply faults on electrified railways to solve the existing problems.

[0005] The method for compensating for missing data of fault distance measurement in full parallel AT power supply of electrified railways of the present application adopts the following technical solution: An embodiment of the present application provides a method for compensating for missing data of fault ranging of fully parallel AT power supply on an electrified railway, the method comprising the following steps: Collect various current data on the same side of each booth in real time, including T-line current, F-line current and suction current; divide all current data into the most recently collected data and historical data according to the time of collection; Fitting the missing data of each kiosk with the non-missing data of each kiosk to obtain the fitting value of each missing data; calculating the dynamic fitting confidence of each kiosk based on the difference between the fitting value of missing data and the non-missing data in the most recently collected data of each kiosk, and the difference between the fitting values ​​of missing data between the kiosk; Based on the historical data of all the pavilions, a probability graphical model is constructed and trained; based on the most recently collected data of all the pavilions, combined with the trained probability graphical model, the posterior probability of each current of each pavilion, as well as the posterior joint probability and the prior joint probability of each pavilion are calculated; based on the posterior joint probability and the prior joint probability, combined with the dynamic fitting confidence of each pavilion, the fitting rationality factor of the missing data of each pavilion is calculated; Based on the fitting rationality factor and the posterior probability of each current in each pavilion, dynamically adjust the fitting value of the missing data of each pavilion to obtain the final fitting value of each missing data; Fault location is performed based on the final fitted values ​​of the missing data of each kiosk and the non-missing data.

[0006] In one embodiment, the method for obtaining the fitting value of each missing data is: For each pavilion, if the number of missing data in the three current data at any moment in the pavilion is 1, the value of the missing data at any moment is solved by the current balance equation as its fitting value; if two or more of the three current data at any moment in the pavilion are missing, the average of the same current data at all moments before any moment is used as the fitting value of the corresponding missing data at any moment.

[0007] In one embodiment, the process of obtaining the dynamic fitting confidence of each kiosk is as follows: Calculate the missing current fitting ratio of each pavilion based on the difference between the missing data fitting values ​​of each pavilion and other pavilions; The mean of all current data in the most recent data collected at the x-th station is recorded as the first mean; the fitted value of the p-th missing data in the most recent data collected at the x-th station is recorded as ,Will The difference between the first mean and ; The dynamic fitting confidence of the xth pavilion is recorded as , The expression is: , where is the Sigmoid function; is the number of missing data in the most recently collected data of the x-th station; is the missing current fitting ratio of the x-th pavilion.

[0008] In one embodiment, the missing current fitting ratio is expressed as: , where N is the number of pavilions; is the number of missing data in the most recently collected data of the nth station; The most recent data collected by the nth station The fitted values ​​for the missing data.

[0009] In one embodiment, the process of constructing and training the probabilistic graphical model is as follows: A Bayesian network model is constructed by taking various fault types as root nodes, various currents of each station as intermediate nodes, and the fitting values ​​of missing data of each station as leaf nodes; the Bayesian network model is trained through the historical data of all stations.

[0010] In one embodiment, the process of obtaining the posterior probability of each current of each booth, and the posterior joint probability and the prior joint probability of each booth is as follows: The most recently collected data of all the pavilions are used as the input of the trained Bayesian network model, and the posterior probability of each current in each pavilion is output respectively. The posterior probability and prior probability of the joint of all kinds of current data of each pavilion are calculated by the Bayesian formula, which are recorded as the posterior joint probability and prior joint probability of each pavilion respectively.

[0011] In one embodiment, the expression of the fitting rationality factor of each missing data is: , where is the fitting rationality factor for the xth missing data; is the dynamic fitting confidence of the x-th pavilion; is the posterior joint probability of the xth pavilion; is the prior joint probability of the xth pavilion; It is an exponential function with the natural constant e as its base.

[0012] In one embodiment, the process of obtaining the final fitting value of each missing data is as follows: For each pavilion, if the fitting rationality factor of the pavilion is greater than or equal to a preset first threshold, the fitting value of each missing data of the pavilion is used as the final fitting value; If the fitting rationality factor of the pavilion is greater than or equal to the preset second threshold and less than the preset first threshold, the posterior weight and the prior weight of the pavilion are calculated based on the posterior joint probability, the prior joint probability and the fitting rationality factor of the pavilion; based on the posterior weight and the prior weight, combined with the posterior probability and historical data of each current of each pavilion, the final fitting value of each missing data of the pavilion is obtained; If the fitting rationality factor of the current station is less than the preset second threshold, the missing data in the current station is still regarded as missing data, and the final fitting value of each missing data of the station whose fitting rationality factor is greater than or equal to the preset second threshold is used as the non-missing data of the corresponding station, and the fitting rationality factor of the current station is recalculated until the fitting rationality factor of the current station is greater than or equal to the second threshold, so as to obtain the final fitting value of the missing data.

[0013] In one embodiment, the expression for calculating the posterior weight and the prior weight of the kiosk is: In the formula, , are the posterior weight and prior weight of the x-th pavilion respectively; is the fitting rationality factor for the xth missing data; is the posterior joint probability of the xth pavilion; is the prior joint probability of the xth pavilion.

[0014] In one embodiment, based on the posterior weights and the prior weights, combined with the posterior probability and historical data of each current of each pavilion, the final fitting value of each missing data of the pavilion is obtained, specifically: Calculate the posterior expected value of each current in each pavilion through the posterior probability of each current in each pavilion; The mean value of all data of the cth current in the xth historical data of the pavilion is recorded as ; The corrected fitting value of the missing data of the cth current in the most recently collected data of the xth pavilion is recorded as , The expression is: , where is the posterior expected value of the cth current at the xth pavilion; The corrected fitting value of each current in each booth is used as the final fitting value of each missing data of each current in each booth.

[0015] This application has at least the following beneficial effects: The present application collects various current data on the same side of each booth in real time, fits the missing data based on the current balance equation and historical data, analyzes the difference between the missing data fitting value and the non-missing data, calculates the dynamic fitting confidence of each booth, evaluates the reliability of the missing data fitting of the booth, and provides a basis for the subsequent fitting rationality judgment; through the dynamic fitting confidence of each booth, and based on the Bayesian network combined with historical data and real-time data, evaluates the rationality of the fitting value, and excludes the situation where the fitting result deviates greatly from the historical data; dynamically adjusts the fitting value of the missing current data of the booth according to the fitting rationality factor, directly incorporates the high-reliability fitting value into the ranging calculation, performs weighted average correction on the more reliable fitting value, starts iterative calculation for the unreliable fitting value, and readjusts the fitting value, which helps to improve the fault tolerance and accuracy of fault ranging; performs fault ranging through the dynamically adjusted fitting value and the non-missing current data, improves the stability and reliability of ranging, can adapt to a variety of fault types and complex system topology structures, avoids the superposition of fitting data deviations in the scenario where data from multiple booths is missing, and affects the ranging accuracy, and ensures the safe and stable operation of electrified railways. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the technical solutions and advantages in the embodiments of the present application 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 application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0017] Figure 1 A flow chart of a method for compensating for missing distance measurement data for full parallel AT power supply faults on electrified railways provided in this application; Figure 2 Schematic diagram of the process of obtaining the final fitting value of each missing data. DETAILED DESCRIPTION

[0018] In order to further explain the technical means and effects adopted by the present application to achieve the predetermined invention purpose, the following is a detailed description of the method for compensating for missing data of full parallel AT power supply fault ranging in electrified railways proposed in accordance with the present application, its specific implementation, structure, features and effects, in conjunction 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.

[0019] 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 application belongs.

[0020] The specific scheme of the method for compensating missing data of full-parallel AT power supply fault ranging in electrified railways provided by the present application is described in detail below with reference to the accompanying drawings.

[0021] An embodiment of the present application provides a method for compensating for missing distance measurement data of a fully parallel AT power supply fault on an electrified railway.

[0022] Specifically, the following method for compensating for missing data of fault distance measurement in full parallel AT power supply of electrified railway is provided. Figure 1 , the method comprises the following steps: Step S1, collect various current data on the same side of each booth in real time, including T-line current, F-line current and suction current; divide all current data into recently collected data and historical data according to the time of collection.

[0023] Assume that the electrified railway system contains N posts, and the xth post is denoted as .

[0024] High-precision current sensors and GPS modules are deployed in all booths. Various current data of each booth are captured in real time through current sensors. Since the circuit is divided into an upstream side and a downstream side in the full parallel AT power supply mode of the railway, the embodiment of the present application takes the downstream side as an example for analysis. The T-line current, F-line current, and suction current of the downstream side of each booth are collected through current sensors. The T line current is recorded as , the F line current is recorded as , the absorbed current is recorded as .

[0025] For data collection of the current sensor, preferably, in the embodiment of the present application, the data collection frequency is set to 1kHz. As other embodiments of the present application, the implementer can set the data collection frequency according to the actual situation.

[0026] Each kiosk uses the PPS (pulse per second) signal generated by the GPS module to align the local clock, ensuring that the timestamp error between different kiosks is less than or equal to To ensure timing consistency, the PPS signal of the GPS module and the PTP protocol (Precision Time Protocol) are used to achieve hardware-level clock synchronization. The clock synchronization method is a well-known technology, and the specific process will not be repeated here.

[0027] For the T-line current, F-line current and suction current data collected by each kiosk, a hierarchical storage strategy is implemented, specifically: the current data collected within 1 hour from the current time is taken as the most recently collected data and stored in the memory database to support real-time query; the current data collected from 1 hour to 1 month before is taken as the intermediate segment data and stored in the time series database; the current data collected more than 1 month ago is taken as historical data and archived to the distributed file system.

[0028] Step S2, fitting the missing data of each kiosk with the non-missing data of each kiosk to obtain the fitting value of each missing data; based on the difference between the fitting value of the missing data in the most recently collected data of each kiosk and the non-missing data, and the difference in the fitting value of the missing data between the kiosk, calculate the dynamic fitting confidence of each kiosk.

[0029] In the scenario where data from multiple kiosks are missing, the missing data from each kiosk will introduce a certain amount of deviation. The deviations in the scenario with multiple kiosks will be superimposed on each other, significantly amplifying the overall error and affecting the ranging accuracy.

[0030] First, for each missing data in each pavilion, the missing data are fitted by the existing method according to the non-missing data of each pavilion, specifically: Yisuoting For example, through the current balance principle, the current balance equation can be established: , where Weisuoting The T line current, Weisuoting The F line current, Weisuoting The fitted value of each missing current data is obtained by using the non-missing data and the current balance equation: The number of missing data in the three current data collected is 1, that is, only one data is missing among the three current data. Then the missing data at this moment is solved by the current balance equation. For example, assuming that at this moment missing, and and is known, then it can be obtained by , get the missing value of the current value; if the pavilion at the same time If two or more of the three types of current data collected are unknown, the mean or standard deviation of the historical data can be used to fit the missing data. For example, if and If missing, the mean value of the suction current at all times before this moment is used as the fitting value of the suction current at this moment, and the mean value of the T line current at all times before this moment is used as the fitting value of the T line current at this moment. Thus, the fitting value of each missing data can be obtained by the above method, wherein the pavilion The fitted value of the pth missing data is recorded as .

[0031] Then, in order to analyze the reliability of the missing data fitting values ​​of each pavilion, For example, the latest collected data of the pavilion is obtained from the memory database, and the mean of all types of current data in the latest collected data of the pavilion is recorded as the first mean value; for each missing data of the pavilion, the difference between the fitting value of the missing data and the first current mean value is recorded as the first difference of the missing data; Furthermore, the dynamic fitting confidence of each pavilion is calculated, and the expression is: In the formula, is the dynamic fitting confidence of the x-th pavilion; is the Sigmoid function; is the number of missing data in the most recently collected data of the x-th station; is the first difference value of the p-th missing data in the most recently collected data of the x-th station; is the missing current fitting ratio of the xth pavilion; is the fitted value of the pth missing data in the most recently collected data of the xth pavilion; N is the number of pavilions; is the number of missing data in the most recently collected data of the nth station; The most recent data collected by the nth station The fitted values ​​for the missing data.

[0032] The deviation between the fitting value and the normal working condition is quantified. The larger the absolute value, the less reliable the fitting value. It represents the ratio of the sum of the missing current fitting values ​​of the xth pavilion to the sum of the missing current fitting values ​​of all pavilions. The numerator represents the actual contribution of the pavilion to the fault current. The larger the value, the higher the current intensity or the more missing data. The denominator represents the scale of the overall missing current of all pavilions, reflecting the severity and distribution range of the current fault. The larger the value, the higher the proportion of missing current in the pavilion, which may be located in a critical topological position, such as near a substation or a high-fault area.

[0033] It is used to quantify the fitting reliability of the missing data point of the x-th pavilion. The closer its value is to 1, the more reliable the fitting result of the missing data of the pavilion is. On the contrary, when its value is close to 0, it indicates that the fitting value of the missing data of the pavilion deviates from the normal working condition or the contribution ratio of the pavilion is low, and further correction is needed.

[0034] Step S3, constructing and training a probability graphical model based on the historical data of all the booths; calculating the posterior probability of each current in each booth, as well as the posterior joint probability and the prior joint probability of each booth, based on the recently collected data of all the booths, combined with the trained probability graphical model; calculating the fitting rationality factor of the missing data of each booth based on the posterior joint probability and the prior joint probability, combined with the dynamic fitting confidence of each booth.

[0035] When processing the missing data of the electrified railway system, we should not only pay attention to the reliability of data fitting, but also pay attention to the fit of the current missing data fitting relative to the historical data. However, due to the diversity of fault types and the complexity of system operating conditions, a single data fitting method is often difficult to fully reflect the actual scenario. Different fault types may lead to significant differences in current distribution patterns, and historical data may contain current characteristics under multiple conditions, which requires the fitting results to take into account both the rationality of current observation data and the consistency of historical data. In addition, changes in system topology, equipment aging, and external environmental factors may also affect the distribution of current data, further increasing the difficulty of fitting. Therefore, when evaluating the missing data fitting effect, it is necessary to comprehensively consider multiple factors to ensure that the fitting results can adapt to the current fault conditions and maintain a certain consistency with historical laws.

[0036] (1) Construct a Bayesian network model based on the current data of Suoting: The three fault types TR, FR and TF are used as the top-level input of the Bayesian network, that is, the three fault types are used as root nodes, the T-line current, F-line current and suction current of each station are used as intermediate nodes, and the fitting value of the missing data of each station is used as a leaf node to construct a Bayesian network model; Extract features based on all historical data of the pavilion and calculate conditional probability tables, and then use these conditional probability tables to train the Bayesian network model; the calculation of the conditional probability table and the training of the Bayesian network model are well-known technologies, and the specific process will not be repeated; The most recently collected data of all pavilions are used as the input of the trained Bayesian network model, and the posterior probabilities of the T-line current, F-line current and suction current of each pavilion are output respectively, and the posterior expected value of each current of the pavilion is calculated based on the posterior probability of each current of the pavilion; at the same time, the posterior probability and prior probability of the joint of all kinds of current data of each pavilion are calculated by the Bayesian formula, which are recorded as the posterior joint probability and prior joint probability of the pavilion respectively. The calculation of the posterior probability, prior probability and posterior expected value is a well-known technology, and the specific process will not be repeated.

[0037] (2) Based on the above analysis, taking the xth pavilion as an example, the fitting rationality factor of the missing data of each pavilion is calculated, and the expression is: In the formula, is the fitting rationality factor for the xth missing data; is the dynamic fitting confidence of the x-th pavilion; is the posterior joint probability of the xth pavilion; is the prior joint probability of the xth pavilion; It is an exponential function with the natural constant e as its base.

[0038] Evaluated the The reliability of the missing data fitting in the , the larger the value, the more reliable the missing values ​​of the fitting; It is based on the observed data, that is, the data in the memory database, and the posterior probability calculated by the Bayesian network model, indicating that under the current network topology and fault conditions, the The rationality of the fitting value of the missing current data. The larger the value, the more the fitting value matches the current observed data. It is a priori probability obtained based on historical data, that is, data archived in the distributed file system, indicating the The degree of matching between the fitting value of the missing current data and the historical pattern, the larger the value, the more consistent the fitting value is with the historical law; It is used to quantify the degree of improvement or decrease in the rationality of the fitting value under the current observation data relative to the historical pattern. The smaller the difference between its value and 1, the more similar the fitting value is to the historical pattern. At this time, it means that the fitting value can more accurately conform to the data rules of the past, has good generalization ability, and the fitting result is more stable and reliable.

[0039] To quantify the The overall reliability of the fitting value of the missing current data is that when the value of B is closer to 1, the rationality of the fitting value under the current observation data is highly consistent with the historical pattern, indicating that the fitting result is consistent not only with the current observation, but also with the historical law. The missing data fitting results are more reasonable.

[0040] Step S4: dynamically adjust the fitting value of the missing data of each pavilion based on the fitting rationality factor and the posterior probability of each current of each pavilion to obtain the final fitting value of each missing data.

[0041] When dealing with the challenge of missing data from multiple booths in the fully parallel AT power supply system of electrified railways, traditional methods are difficult to accurately locate faults due to the nonlinear superposition of current vector relationships and fuzzy contribution ratios. Especially in the scenario of multiple missing data, the error accumulation effect significantly reduces the ranging accuracy. Therefore, the fitting rationality factor is introduced as the core evaluation indicator. By comprehensively considering the fit between the current fitting data and the historical pattern, a high-tolerance and high-precision solution is provided for fault ranging in complex scenarios. Specifically: (1) Taking the xth Suoting as an example, the fitting rationality factor of the missing data of the xth Suoting is used as the weight factor, and the fitting value of the missing data of the xth Suoting is dynamically adjusted: Set the first threshold and the second threshold Preferably, in the embodiment of the present application, the first threshold Set to 0.8, the second threshold Set to 0.5; as other embodiments of the present application, the implementer can set the first threshold and the second threshold according to actual conditions.

[0042] (2) When When The fitting values ​​of the missing data are highly reliable, so The fitted values ​​of each missing data are taken as the final fitted values ​​and included in the distance measurement calculation; (3) When When If there is a certain deviation in the fitting values ​​of the missing data, then it is combined with the posterior joint probability and the prior joint probability generated by the Bayesian network, and the current value is corrected by weighted average. The specific correction method is: First, according to the pavilion The posterior joint probability, the prior joint probability and the fitting rationality factor are calculated. The posterior weight of and prior weights , the expression is: The weight dynamically adjusts the contribution ratio of the posterior probability to the prior probability through the rationality factor. When higher, emphasizes current observation data The local characteristics of When it is lower, enhance historical data The global law constraints are implemented to suppress the fitting deviation caused by data missing or noise while retaining the real-time advantage, thereby improving the stability and physical consistency of the compensation results.

[0043] Furthermore, the mean of all the data of each current in the historical data of the x-th pavilion is used as the prior current estimation value of each current missing data of the pavilion. The fitting value of the missing data of each current is corrected by weighted average, and the specific correction formula is: , where is the corrected fitting value of the missing data of the cth current in the most recently collected data of the xth pavilion, is the posterior expected value of the cth current of the xth pavilion, is the prior current estimate of the cth current missing data for the xth pavilion.

[0044] The corrected fitting value of each current in each pavilion is used as the final fitting value of each missing data of each current in each pavilion, and is included in the distance measurement calculation.

[0045] Through weighted average correction, the high-confidence posterior estimate is integrated with the historical prior estimate, which not only avoids the error accumulation of a single data source, but also balances the real-time data with the long-term rules, so that the corrected current value can adapt to the current fault scenario and meet the system topology constraints, ultimately reducing the ranging error in multiple missing scenarios.

[0046] (4) When When the fitting rationality factor is less than the second threshold, the iterative calculation is started, and the fitting values ​​of the pavilions whose fitting rationality factors are less than the second threshold are deleted, that is, the missing data in the pavilions are still regarded as missing data, and the fitting rationality factor is greater than The final fitting value of each missing data of the pavilion is used as the known current data of the corresponding pavilion, and the calculation of steps S2-S4 is repeated and iterated until the fitting rationality factors of all pavilions are greater than the second threshold, and the final fitting value of the missing data is obtained.

[0047] This compensation method achieves high-precision fault ranging in multiple missing scenarios through the coordinated regulation of thresholds and fitting rationality factors. When the missing data fitting value is highly reliable, the fitting value is directly used to ensure real-time performance. When the missing data fitting value is relatively reliable, the Bayesian posterior probability and historical prior data are fused by weighted average to dynamically adjust the posterior weight and prior weight. The local characteristics of real-time data are used to adapt to the current fault type, and the noise interference is suppressed with the help of historical law constraints to ensure physical consistency. When the missing fitting value is unreliable, the low-confidence fitting value is iteratively deleted and recalculated to avoid error accumulation, which ultimately significantly improves the ranging accuracy and enhances the system's fault tolerance. It supports the simultaneous loss of multiple stations, takes into account both real-time performance and stability, and provides reliable protection for the safe operation of electrified railways.

[0048] Step S5, performing fault location measurement based on the final fitting value of the missing data of each kiosk and the non-missing data.

[0049] The final fitting value of each missing data in the most recently collected data is obtained by the above method, so as to fill in the missing values ​​of the current data of each pavilion. Further, based on the current data of all pavilions, the fault distance is measured in combination with the principle of the cross-line current ratio. This principle analyzes the electric quantity equations satisfied by various fault lines in the full parallel AT power supply traction network, and obtains the cross-line current ratio formula for fault distance measurement. In the event of a short circuit fault, the cross-line current of the uplink and downlink lines is measured, and the position of the fault point is calculated using the current ratio formula. This method can accurately determine the type of fault and calibrate the location of the fault point, which is crucial to ensure the safe and reliable operation of electrified railways. The cross-line current ratio principle is applicable to the situation where the cross-line is not untied under the uplink and downlink full parallel AT power supply mode, and can accurately calibrate TR, FR, TF faults, as well as line break faults and fault directions. Among them, fault distance measurement by the cross-line current ratio method is a well-known technology, and the specific process will not be repeated.

[0050] The schematic diagram of the process of obtaining the final fitting value of each missing data is as follows Figure 2 shown.

[0051] In summary, the embodiment of the present application collects various current data on the same side of each pavilion in real time, fits the missing data based on the current balance equation and historical data, analyzes the difference between the missing data fitting value and the non-missing data, calculates the dynamic fitting confidence of each pavilion, evaluates the reliability of the missing data fitting of the pavilion, and provides a basis for the subsequent fitting rationality judgment; through the dynamic fitting confidence of each pavilion, and based on the Bayesian network combined with historical data and real-time data, the rationality of the fitting value is evaluated, and the situation where the fitting result deviates greatly from the historical data is excluded; according to the fitting rationality factor, the fitting value of the missing current data of the pavilion is dynamically adjusted, the fitting value with high reliability is directly included in the ranging calculation, the weighted average correction is performed for the more reliable fitting value, and the iterative calculation is started for the unreliable fitting value, and the fitting value is readjusted, which helps to improve the fault tolerance and accuracy of the fault ranging; the fault ranging is performed by the dynamically adjusted fitting value and the non-missing current data, the stability and reliability of the ranging are improved, and it can adapt to a variety of fault types and complex system topology structures, avoiding the superposition of fitting data deviations in the scenario where multiple pavilions are missing data, affecting the ranging accuracy, and ensuring the safe and stable operation of the electrified railway.

[0052] It should be noted that the above-mentioned sequence of the embodiments of the present application is only for description and does not represent the advantages and disadvantages of the embodiments. The above-mentioned specific embodiments of the present application are described. In addition, 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.

[0053] The various embodiments in the present application 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.

[0054] The embodiments described above are only used to illustrate the technical solutions of the present application, rather than to limit them. Modifications to the technical solutions recorded in the aforementioned embodiments, or equivalent replacement of some of the technical features therein, do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present application, and should all be included in the protection scope of the present application.

Claims

1. A method for compensating for missing data of fault distance measurement in full parallel AT power supply of electrified railway, characterized in that: The method comprises the following steps: Collect various current data on the same side of each booth in real time, including T-line current, F-line current and suction current; divide all current data into the most recently collected data and historical data according to the time of collection; Fitting the missing data of each kiosk with the non-missing data of each kiosk to obtain the fitting value of each missing data; calculating the dynamic fitting confidence of each kiosk based on the difference between the fitting value of missing data and the non-missing data in the most recently collected data of each kiosk, and the difference between the fitting values ​​of missing data between the kiosk; Based on the historical data of all the pavilions, a probability graphical model is constructed and trained; based on the most recently collected data of all the pavilions, combined with the trained probability graphical model, the posterior probability of each current of each pavilion, as well as the posterior joint probability and the prior joint probability of each pavilion are calculated; based on the posterior joint probability and the prior joint probability, combined with the dynamic fitting confidence of each pavilion, the fitting rationality factor of the missing data of each pavilion is calculated; Based on the fitting rationality factor and the posterior probability of each current in each pavilion, dynamically adjust the fitting value of the missing data of each pavilion to obtain the final fitting value of each missing data; Fault location is performed based on the final fitted values ​​of the missing data of each kiosk and the non-missing data.

2. The method for compensating for missing data of fault ranging in full parallel AT power supply of electrified railway according to claim 1, characterized in that: The method for obtaining the fitting value of each missing data is: For each pavilion, if the number of missing data in the three current data at any time of the pavilion is 1, the value of the missing data at any time is solved by the current balance equation as its fitting value; If two or more of the three current data at any moment are missing, the mean of the same current data at all moments before the said moment is used as the fitting value of the missing data corresponding to the said moment.

3. The method for compensating for missing data of fault ranging in full parallel AT power supply of electrified railway according to claim 1, characterized in that: The acquisition process of the dynamic fitting confidence of each pavilion is as follows: Calculate the missing current fitting ratio of each pavilion based on the difference between the missing data fitting values ​​of each pavilion and other pavilions; The mean of all current data in the most recent data collected at the x-th station is recorded as the first mean; the fitted value of the p-th missing data in the most recent data collected at the x-th station is recorded as ,Will The difference between the first mean and ; The dynamic fitting confidence of the xth pavilion is recorded as , The expression is: , where is the Sigmoid function; is the number of missing data in the most recently collected data of the x-th station; is the missing current fitting ratio of the x-th pavilion.

4. The method for compensating for missing data of fault ranging in full parallel AT power supply of electrified railway according to claim 3, characterized in that: The expression of the missing current fitting ratio is: , where N is the number of pavilions; is the number of missing data in the most recently collected data of the nth station; The most recent data collected by the nth station The fitted values ​​for the missing data.

5. The method for compensating for missing data of fault ranging in full parallel AT power supply of electrified railway according to claim 1, characterized in that: The process of constructing and training the probabilistic graphical model is as follows: A Bayesian network model is constructed by taking various fault types as root nodes, various currents of each station as intermediate nodes, and the fitting values ​​of missing data of each station as leaf nodes; the Bayesian network model is trained through the historical data of all stations.

6. The method for compensating for missing data of fault ranging in full parallel AT power supply of electrified railway according to claim 1, characterized in that: The process of obtaining the posterior probability of each current of each booth, and the posterior joint probability and the prior joint probability of each booth is as follows: The most recently collected data of all the pavilions are used as the input of the trained Bayesian network model, and the posterior probability of each current in each pavilion is output respectively. The posterior probability and prior probability of the joint of all kinds of current data of each pavilion are calculated by the Bayesian formula, which are recorded as the posterior joint probability and prior joint probability of each pavilion respectively.

7. The method for compensating for missing data of fault ranging in full parallel AT power supply of electrified railway according to claim 1, characterized in that: The expression of the fitting rationality factor of the missing data of each pavilion is: , where is the fitting rationality factor for the xth missing data; is the dynamic fitting confidence of the x-th pavilion; is the posterior joint probability of the xth pavilion; is the prior joint probability of the xth pavilion; It is an exponential function with the natural constant e as its base.

8. The method for compensating for missing data of fault ranging in full parallel AT power supply of electrified railway according to claim 1, characterized in that: The process of obtaining the final fitting value of each missing data is as follows: For each pavilion, if the fitting rationality factor of the pavilion is greater than or equal to a preset first threshold, the fitting value of each missing data of the pavilion is used as the final fitting value; If the fitting rationality factor of the pavilion is greater than or equal to the preset second threshold and less than the preset first threshold, the posterior weight and the prior weight of the pavilion are calculated based on the posterior joint probability, the prior joint probability and the fitting rationality factor of the pavilion; based on the posterior weight and the prior weight, combined with the posterior probability and historical data of each current of each pavilion, the final fitting value of each missing data of the pavilion is obtained; If the fitting rationality factor of the current station is less than the preset second threshold, the missing data in the current station is still regarded as missing data, and the final fitting value of each missing data of the station whose fitting rationality factor is greater than or equal to the preset second threshold is used as the non-missing data of the corresponding station, and the fitting rationality factor of the current station is recalculated until the fitting rationality factor of the current station is greater than or equal to the second threshold, so as to obtain the final fitting value of the missing data.

9. The method for compensating for missing data of fault ranging in full parallel AT power supply of electrified railway as claimed in claim 8, characterized in that: The expressions of the posterior weight and the prior weight of the calculation are: In the formula, , are the posterior weight and prior weight of the x-th pavilion respectively; is the fitting rationality factor for the xth missing data; is the posterior joint probability of the xth pavilion; is the prior joint probability of the xth pavilion.

10. The method for compensating for missing data of fault ranging in full parallel AT power supply of electrified railway according to claim 9, characterized in that: Based on the posterior weights and the prior weights, combined with the posterior probability and historical data of each current of each pavilion, the final fitting value of each missing data of the pavilion is obtained, specifically: Calculate the posterior expected value of each current in each pavilion through the posterior probability of each current in each pavilion; The mean value of all data of the cth current in the xth historical data of the pavilion is recorded as ; The corrected fitting value of the missing data of the cth current in the most recently collected data of the xth pavilion is recorded as , The expression is: , where is the posterior expected value of the cth current at the xth pavilion; The corrected fitting value of each current in each booth is used as the final fitting value of each missing data of each current in each booth.

Images