Method and device for evaluating power supply safety state of high-speed railway

Abstract

The present invention discloses a method and device for evaluating the power supply safety state of high-speed railways. The method includes: obtaining the original record data of faults and accidents on high-speed railways; extracting the time features and spatial features at the time of faults and accidents from the original record data of faults and accidents; using a spatio-temporal clustering analysis method to divide the levels of faults and accidents according to the time features to obtain the time coefficients at the time of accidents and faults; using a spatio-temporal clustering analysis method to divide the levels of faults and accidents according to the spatial features to obtain the spatial coefficients at the time of accidents and faults; determining the power supply safety index of high-speed railways according to the time and spatial coefficients at the time of accidents and faults; and evaluating the safety state of the high-speed railway power supply system according to the safety index. The present invention can quantitatively evaluate the safety state of the high-speed railway power supply system based on fault and accident data, and has scientific guiding significance for improving the safety performance of the high-speed railway power supply system.

Description

Technical Field

[0001] The present invention relates to the technical field of safety assessment of high - speed railway power supply, and particularly to an assessment method and device for the safety state of high - speed railway power supply. Background Art

[0002] This section aims to provide background or context for the embodiments of the present invention described in the claims. The description herein is not admitted to be prior art merely because it is included in this section.

[0003] Currently, researchers at home and abroad have preliminarily established safety indices in the fields of highway, aviation, maritime and railway transportation based on safety - related data to manage and evaluate the safety state of equipment. In the field of traction power supply for railway transportation, although there are currently some indicators such as fault indices, quality indices and performance indices that can reflect the fault trend, quality situation and performance state of equipment, in the field of traction power supply, there is still a lack of a comprehensive safety index that comprehensively considers normal state, accident state and fault state for quantitatively assessing the state of the traction power supply system. Summary of the Invention

[0004] Embodiments of the present invention provide an assessment method for the safety state of high - speed railway power supply, which is used to quantitatively assess the safety state of the high - speed railway power supply system based on fault and accident data. The method includes:

[0005] Obtain the original record data of faults and accidents of the high - speed railway;

[0006] Extract the time features and space features when faults and accidents occur from the original record data of faults and accidents;

[0007] Use the spatio - temporal clustering analysis method to divide the levels of faults and accidents according to the time features to obtain the time coefficients when accidents and faults occur; use the spatio - temporal clustering analysis method to divide the levels of faults and accidents according to the space features to obtain the space coefficients when accidents and faults occur;

[0008] Determine the high - speed railway power supply safety index according to the time coefficients and space coefficients when accidents and faults occur;

[0009] Evaluate the safety state of the high - speed railway power supply system according to the high - speed railway power supply safety index.

[0010] Embodiments of the present invention also provide an assessment device for the safety state of high - speed railway power supply, which is used to quantitatively assess the safety state of the high - speed railway power supply system based on fault and accident data. The device includes:

[0011] An acquisition unit, configured to obtain the original record data of faults and accidents of the high - speed railway;

[0012] A feature extraction unit, configured to extract the time features and spatial features at the time of faults and accidents from the original fault and accident record data;

[0013] A clustering analysis unit, configured to use the spatio-temporal clustering analysis method to classify the levels of faults and accidents according to the time features to obtain the time coefficients at the time of accidents and faults; use the spatio-temporal clustering analysis method to classify the levels of faults and accidents according to the spatial features to obtain the spatial coefficients at the time of accidents and faults;

[0014] A safety index determination unit, configured to determine the high-speed railway power supply safety index according to the time coefficient and spatial coefficient at the time of accidents and faults;

[0015] An evaluation unit, configured to evaluate the safety status of the high-speed railway power supply system according to the high-speed railway power supply safety index.

[0016] An embodiment of the present invention further provides a computer device, including a memory, a processor, and a computer program stored on the memory and executable on the processor. When the processor executes the computer program, the above-mentioned method for evaluating the safety status of the high-speed railway power supply is implemented.

[0017] An embodiment of the present invention further provides a computer-readable storage medium, where the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the above-mentioned method for evaluating the safety status of the high-speed railway power supply is implemented.

[0018] An embodiment of the present invention further provides a computer program product, where the computer program product includes a computer program, and when the computer program is executed by a processor, the above-mentioned method for evaluating the safety status of the high-speed railway power supply is implemented.

[0019] In the embodiment of the present invention, compared with the prior art in which there is a lack of a comprehensive safety index that uniformly considers the normal state, accident state, and fault state for quantitatively evaluating the state of the traction power supply system, the evaluation solution for the safety status of the high-speed railway power supply is as follows: obtaining the original fault and accident record data of the high-speed railway; extracting the time features and spatial features at the time of faults and accidents from the original fault and accident record data; using the spatio-temporal clustering analysis method to classify the levels of faults and accidents according to the time features to obtain the time coefficients at the time of accidents and faults; using the spatio-temporal clustering analysis method to classify the levels of faults and accidents according to the spatial features to obtain the spatial coefficients at the time of accidents and faults; determining the high-speed railway power supply safety index according to the time and spatial coefficients at the time of accidents and faults; evaluating the safety status of the high-speed railway power supply system according to the safety index, so as to realize the quantitative evaluation of the safety status of the high-speed railway power supply system based on the fault and accident data, which has a scientific guiding significance for improving the safety performance of the high-speed railway power supply system. Brief Description of the Drawings

[0020] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required for the description of the embodiments or the prior art. Obviously, the drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can be obtained based on these drawings. In the drawings:

[0021] Figure 1 is a schematic diagram of the description of the accident data fields in the power supply specialty in the embodiment of the present invention;

[0022] Figure 2 is a schematic diagram of the description of the fault data fields in the power supply specialty in the embodiment of the present invention;

[0023] Figures 3a to 3c is a schematic diagram of the data preprocessing result in the embodiment of the present invention;

[0024] Figure 4 is a schematic diagram of the data feature extraction result in the embodiment of the present invention;

[0025] Figure 5 is a schematic diagram of the GVF curve used to determine the number of categories in the spatio-temporal clustering feature analysis in the embodiment of the present invention;

[0026] Figure 6 is a schematic diagram of the time feature clustering analysis in the embodiment of the present invention;

[0027] Figure 7 is a schematic diagram of the space feature clustering analysis in the embodiment of the present invention;

[0028] Figure 8 is a schematic diagram of the time feature clustering result statistics in the embodiment of the present invention;

[0029] Figure 9 is a schematic diagram of the space feature clustering result statistics in the embodiment of the present invention;

[0030] Figure 10 is a schematic diagram of the power supply safety index calculation result;

[0031] Figure 11 is a schematic flow diagram of the method for evaluating the power supply safety state of high-speed railways in the embodiment of the present invention;

[0032] Figure 12 is a schematic structural diagram of the device for evaluating the power supply safety state of high-speed railways in the embodiment of the present invention. Detailed Embodiments

[0033] To make the objectives, technical solutions and advantages of the embodiments of the present invention clearer and more understandable, the following further describes the embodiments of the present invention in detail with reference to the accompanying drawings. Herein, the illustrative embodiments of the present invention and their descriptions are used to explain the present invention, but not to limit the present invention.

[0034] The objective of the embodiments of the present invention is to provide an evaluation scheme for the power supply safety status of high-speed railways. This scheme is a calculation and evaluation scheme for the power supply safety index of high-speed railways based on the modeling of fault and accident data, which solves the problem of the lack of quantitative comprehensive evaluation means in the existing safety evaluation of high-speed railway power supply specialties. The following details the evaluation scheme for the power supply safety status of high-speed railways.

[0035] Figure 11 is a schematic flowchart of the evaluation method for the power supply safety status of high-speed railways in the embodiments of the present invention. As Figure 11 shown, the method includes the following steps:

[0036] Step 101: Obtain the original record data of faults and accidents of high-speed railways;

[0037] Step 102: Extract the time characteristics and spatial characteristics when the faults and accidents occur from the original record data of faults and accidents;

[0038] Step 103: Use the spatio-temporal clustering analysis method to divide the levels of faults and accidents according to the time characteristics to obtain the time coefficients when the accidents and faults occur; use the spatio-temporal clustering analysis method to divide the levels of faults and accidents according to the spatial characteristics to obtain the spatial coefficients when the accidents and faults occur;

[0039] Step 104: Determine the power supply safety index of high-speed railways according to the time coefficients and spatial coefficients when the accidents and faults occur;

[0040] Step 105: Evaluate the safety status of the high-speed railway power supply system according to the power supply safety index of high-speed railways.

[0041] The evaluation method for the power supply safety status of high-speed railways provided by the embodiments of the present invention, when working: obtains the original record data of faults and accidents of high-speed railways; extracts the time characteristics and spatial characteristics when the faults and accidents occur from the original record data of faults and accidents; uses the spatio-temporal clustering analysis method to divide the levels of faults and accidents according to the time characteristics to obtain the time coefficients when the accidents and faults occur; uses the spatio-temporal clustering analysis method to divide the levels of faults and accidents according to the spatial characteristics to obtain the spatial coefficients when the accidents and faults occur; determines the power supply safety index of high-speed railways according to the time and spatial coefficients when the accidents and faults occur; and evaluates the safety status of the high-speed railway power supply system according to this safety index.

[0042] In specific implementation, the evaluation method for the power supply safety state provided by the embodiments of the present invention can also be applied to the evaluation of the power supply safety state of ordinary railways.

[0043] Compared with the prior art in which there is a lack of a comprehensive safety index that comprehensively considers normal states, accident states, and fault states for quantitatively evaluating the state of the traction power supply system, the evaluation method for the high-speed railway power supply safety state provided by the embodiments of the present invention can achieve quantitative evaluation of the safety state of the high-speed railway power supply system based on fault and accident data, which has scientific guiding significance for improving the safety performance of the high-speed railway power supply system. The following will be combined with Figures 1 to 10 to introduce the evaluation method for the high-speed railway power supply safety state in detail.

[0044] High-speed railway is one of the important ways of passenger transportation in our country. In recent years, with the rapid development of electrification technology, the traction power supply technology of high-speed railways in our country has been continuously improving. With the increasing annual operating mileage of high-speed railways, the complexity of the traction power supply system has gradually increased. Whether the traction power supply system can operate safely is an important guarantee for high-speed railway operation. Once an accident or fault occurs, it will cause power supply interruption, directly affect the train operation safety, interfere with the normal transportation order, and cause great economic losses and social impacts. Therefore, the safety of high-speed railway traction power supply is particularly important, and the safety performance of the high-speed railway traction power supply system should be continuously improved, and the safety state of the high-speed railway power supply system should be quantitatively evaluated.

[0045] At present, most of the fault data and accident data of high-speed railway traction power supply are recorded in the form of text descriptions. The accident data of high-speed railway power supply professionals are detailed descriptions of accidents recorded after the accidents occur, mainly including four parts: accident number, basic accident situation, accident responsible unit, and accident recognition letter. Among them, the basic accident situation includes the accident occurrence date, the railway bureau where the accident occurred, the jurisdiction of the affiliated supervision bureau, the high-speed railway line, the number of casualties, the train operation interruption time, the direct economic loss, and the accident level, etc. The high-speed railway traction power supply fault data mainly includes information such as fault number, basic fault situation, fault category and impact, and fault situation description. As an important carrier of fault and accident data, this kind of unstructured text data is mostly stored in Word and Excel, and it is very difficult to discover the potential great value in the text data.

[0046] Based on the accident and fault data of high-speed railway power supply professional equipment in our country, the embodiments of the present invention analyze the comprehensive impact of various factors in accidents and faults on power supply safety through data modeling, and then design a construction method for the high-speed railway power supply safety index for comprehensively evaluating the high-speed railway power supply safety state. The main steps are as follows:

[0047] (1) Data preprocessing

[0048] Since there are data quality problems such as missing values, different heterogeneous formats, calculation errors, annotation errors, input errors, etc. in the process of recording the original data of faults and accidents, it is first necessary to preprocess the collected original record data of faults and accidents. Most of these problems occur in the power outage time field caused by faults. After preprocessing and cleaning and confirming that the data content is accurate, it can be brought into the safety index model calculation process. That is, in one embodiment, the above method for evaluating the safety state of high-speed railway power supply may further include: preprocessing the original record data of faults and accidents on high-speed railways. For a detailed description of this preprocessing, see the following embodiments.

[0049] In specific implementation, the safety state of the high-speed railway power supply specialty is usually described by accident data and fault data, and these unstructured data are recorded and stored in text form. The accident data of the high-speed railway power supply specialty is a detailed description of the accident recorded after the accident occurs, mainly including four parts: accident number, basic situation of the accident, accident responsible unit, and accident recognition letter, as Figure 1 shown. The fault data of the high-speed railway power supply specialty mainly includes information such as fault number, basic situation of the fault, fault category and impact, and description of the fault situation, as Figure 2 shown.

[0050] In specific implementation, in the original text record data of faults and accidents, since the manual entry and filling method is used in the recording process, there are problems such as missing values, heterogeneous data formats generated by different personnel during entry, result errors caused by manual calculation, annotation errors, input errors, etc. Therefore, it is first necessary to preprocess the collected original record text data of faults and accidents.

[0051] In specific implementation, these data quality problems occur in the power outage time field caused by faults and accidents. For example, if there is no catenary power outage after a fault or accident occurs, the power outage time in these records is empty; in addition, the data formats recorded by different entry personnel are also different.

[0052] In specific implementation, to solve the above problems, in the data preprocessing process, first, missing value filling and automatic conversion of heterogeneous record formats are required. After missing value filling and heterogeneous format conversion, it is necessary to automatically verify the correctness of the data, that is, the total power outage time field. Finally, effective data after preprocessing and cleaning is obtained. The data preprocessing results are as Figures 3a to 3c shown. In Figure 3a : The left half is the original data, and the right half is the data after automatically filling in the missing values; in Figure 3b : The left half is the original data, and the right half is the data after automatically converting the format; in Figure 3cChinese: The left half is the original data, and the right half is the correct result data obtained after automatic calculation.

[0053] (2) Data feature extraction

[0054] After preprocessing the original data of accidents and faults, it is necessary to extract effective features such as spatial information after the occurrence of faults and accidents from the detailed text records to provide feature data support for subsequent spatio-temporal clustering analysis and calculation. The detailed implementation method of data feature extraction is described in the following paragraphs.

[0055] Specifically, when implementing, after obtaining the correct and effective data through preprocessing and cleaning, it is necessary to extract features from the data. For the unstructured fault and accident text data in the railway power supply specialty, the word segmentation pattern matching method is used to extract important features such as line number, starting station, terminal station, and interval multiple from the text description record data of a large number of fault situations, and extract important features such as the number of casualties, accident level, and accident cause from the text description record data of accident situations, so as to query the mileage from the line station mileage table and calculate the affected interval and impact degree when the fault and accident occur, providing effective feature data for subsequent spatio-temporal clustering analysis and data modeling work. The data feature extraction results are as Figure 4 shown.

[0056] (3) Spatio-temporal clustering analysis

[0057] For the fault and accident features after preprocessing and feature extraction, it is necessary to study the optimal number of clustering centers for time and space features, and use the spatio-temporal clustering analysis method to classify the levels of faults and accidents according to space and time respectively to obtain the time coefficient and space coefficient of the occurrence of accidents and faults. Calculate the high-speed railway power supply safety index according to the clustering classification results. The detailed implementation method of spatio-temporal clustering analysis is as follows.

[0058] Since the characteristic data such as power outage time and power outage distance caused by high-speed railway power supply faults and accidents are discrete in time and space and do not have general representative significance, it is necessary to perform clustering analysis on the discrete characteristic data such as power outage time and power outage distance caused by power supply faults and accidents. After obtaining accurate and effective power outage time and outage interval characteristic data through preprocessing and feature extraction of the original data of faults and accidents respectively, the spatio-temporal clustering analysis method is used to obtain the time coefficient and space coefficient. The spatio-temporal clustering analysis method is based on the K-means clustering algorithm

[12] , first initialize k clustering centers a 1 , a 2 , a 3 ,..., a k, then for the j-th clustering center, where j = 1, 2, 3, …, k, cluster analysis of the data x is achieved by iteratively solving formula (1).

[0059]

[0060] The value of the number of clusters k is determined using the Goodness of Variance Fit (GVF). The calculation method of GVF is as follows:

[0061]

[0062]

[0063]

[0064] In the formula: N is the total number of samples of the data x to be analyzed (evaluated), j is the number of data samples in the j-th class,

[0065] According to formulas (2)-(4), the GVF curve graphs corresponding to different values of k can be calculated and plotted, as Figure 5 shown. It is recommended to select the value of the optimal number of clusters k at the first curve inflection point where the GVF value is greater than 0.95. Because after this inflection point, when increasing the value of the number of clusters k, the change of the GVF curve is not obvious. For the characteristic data such as the power outage time and power outage distance caused by accidents and faults in the high-speed railway power supply specialty in China, the optimal value of the number of clusters is 6. The results of spatio-temporal clustering of the characteristic data of the power outage time and power outage section after the occurrence of faults and accidents using the above method are as Figure 6 and Figure 7 shown, and the statistical results of each clustering center and the number of samples are as Figure 8 and Figure 9 shown.

[0066] As can be seen from the above, in one embodiment, using the spatio-temporal clustering analysis method to classify the levels of faults and accidents according to time characteristics, the time coefficients when the accidents and faults occur are obtained; using the spatio-temporal clustering analysis method to classify the levels of faults and accidents according to space characteristics, the space coefficients when the accidents and faults occur can include:

[0067] Determine the optimal number of clustering centers using the goodness of variance fit;

[0068] With the optimal number of clustering centers, use the spatio-temporal clustering analysis method to classify the levels of faults and accidents according to time characteristics, and obtain the time coefficients when the accidents and faults occur;

[0069] Using the optimal number of clustering centers, the levels of faults and accidents are classified according to spatial characteristics by means of spatio-temporal clustering analysis to obtain the spatial coefficients at the time of accident and fault occurrence.

[0070] In specific implementation, using the optimal number of clustering centers, the time coefficient and spatial coefficient corresponding to the optimal number of clustering centers are respectively obtained as the optimal time coefficient and spatial coefficient. Based on the optimal time coefficient and spatial coefficient, the accuracy of determining the high-speed railway power supply safety index can be improved, and further the accuracy of high-speed railway safety state assessment can be improved.

[0071] (4) Completion of formula element composition in data modeling

[0072] To comprehensively and macroscopically analyze and evaluate the safety index of the high-speed railway traction power supply specialty, it is necessary to combine the normal state, accident state and fault state of the high-speed railway power supply specialty, and comprehensively calculate and conduct modeling analysis considering the state transition probability between different states.

[0073] Based on the above characteristic data and spatio-temporal clustering analysis results, the method for constructing a data model to calculate the high-speed railway power supply specialty safety index is as follows. In one embodiment, according to the time coefficient and spatial coefficient at the time of accident and fault occurrence, the high-speed railway power supply safety index is determined, including determining the high-speed railway power supply safety index according to the following formula:

[0074]

[0075] In the formula: F t : Time coefficient matrix of fault occurrence; C v : Victim degree coefficient matrix of accident occurrence; F s : Spatial coefficient matrix of fault occurrence; C n : Casualty number coefficient matrix of accident occurrence; F i : Influence coefficient matrix at the time of fault occurrence; C a : Accident type coefficient matrix of accident occurrence; F r : Cause coefficient matrix at the time of fault occurrence; C r : Accident cause coefficient matrix of accident occurrence; p i : State transition probability between normal state, fault state and accident state; m j : Number of occurrences of normal state / fault state / accident state, j = 0, 1, 2 respectively represent normal state / fault state / accident state, and x is the data to be evaluated.

[0076] As can be seen from the above, in one embodiment, the above method for evaluating the high-speed railway power supply safety state may further include: extracting the cause characteristics, type characteristics, number of victims characteristics and victim degree characteristics of faults and accidents at the time of fault and accident occurrence from the original record data of faults and accidents.

[0077] Determine the high - speed railway power supply safety index according to the time coefficient and space coefficient at the time of accidents and faults, including: construct a data model to calculate the high - speed railway power supply safety index according to the time coefficient, space coefficient, cause characteristic coefficient, type characteristic coefficient, number of victims characteristic coefficient and degree of damage characteristic coefficient at the time of accidents and faults.

[0078] In specific implementation, the evaluation method for the high - speed railway power supply safety state provided by the embodiments of the present invention is a high - speed railway power supply safety index evaluation method based on fault and accident data modeling. It extracts the cause characteristics, type characteristics, number of victims characteristics and degree of damage characteristics of faults and accidents at the time of faults and accidents from the original record data of faults and accidents. Subsequently, comprehensively according to the time coefficient, space coefficient, cause characteristic coefficient, type characteristic coefficient, number of victims characteristic coefficient and degree of damage characteristic coefficient at the time of accidents and faults, construct a data model to calculate the high - speed railway power supply safety index, further improving the accuracy of determining the high - speed railway power supply safety index, and thus further improving the accuracy of high - speed railway safety state evaluation.

[0079] As can be seen from the above, in one embodiment, determining the high - speed railway power supply safety index according to the time coefficient and space coefficient at the time of accidents and faults may include:

[0080] Determine the high - speed railway power supply safety index according to the time coefficient, space coefficient at the time of accidents and faults, and the state transition probabilities between the normal state, fault state and accident state.

[0081] In specific implementation, when determining the high - speed railway power supply safety index, the state transition probabilities between the normal state, fault state and accident state are comprehensively considered, further improving the accuracy of determining the high - speed railway power supply safety index, and thus further improving the accuracy of high - speed railway safety state evaluation.

[0082] The above formula elements are divided into three items: normal item, fault item and accident item. Since the number of accidents and faults in the high - speed railway power supply specialty occurs less than once a day on average, if the calculation time range is selected too small, the data sample size is small within a certain period of time and has no analytical significance. Therefore, the calculation is carried out with "month" as the time division unit, and the base period is selected as the month with the smallest safety state value for normalizing the calculation result of the safety index. To reflect the change trend of the overall safety index, it is necessary to finally compare the calculation result with the base period. The normalization method is as follows:

[0083]

[0084] In the formula: CRHSI 1 is the safety state value of different months, CRHSI 0The safety status value with [specific base period].

[0085] As can be seen from the above, in one embodiment, according to the high - speed railway power supply safety index, evaluating the safety status of the high - speed railway power supply system may include: evaluating the safety status of the high - speed railway power supply system with a month as the basic unit, which further improves the accuracy of determining the high - speed railway power supply safety index, and further improves the accuracy of the high - speed railway safety status evaluation.

[0086] In summary, the evaluation method of the high - speed railway power supply safety status provided by the embodiments of the present invention realizes:

[0087] (1) A method for cleaning and pre - processing the fault and accident data of the high - speed railway traction power supply specialty and extracting safety feature quantities. Selecting the fault cause, fault impact, fault time range, and fault space range as the safety feature quantities of faults; selecting the accident cause, accident type, number of victims, and degree of harm as the safety feature quantities of accidents.

[0088] (2) A method for evaluating the safety status by using the safety feature data to establish a high - speed railway power supply safety index model. It integrates all the fault and accident safety feature quantities, and considers the transition probabilities between the normal state, fault state, and accident state, and establishes a high - speed railway power supply safety index calculation model, and a method for evaluating the safety status of the high - speed railway power supply specialty with a month as the basic unit.

[0089] In the technical solution of this application, the acquisition, storage, use, processing, etc. of data all comply with the relevant regulations of national laws and regulations.

[0090] The embodiments of the present invention also provide an evaluation device for the high - speed railway power supply safety status, as described in the following embodiments. Since the principle of this device for solving problems is similar to that of the evaluation method of the high - speed railway power supply safety status, the implementation of this device can refer to the implementation of the evaluation method of the high - speed railway power supply safety status, and the repeated parts will not be described again.

[0091] Figure 12 It is a schematic structural diagram of the evaluation device for the high - speed railway power supply safety status in the embodiments of the present invention, as Figure 12 shown, the device includes:

[0092] An acquisition unit 01, configured to acquire the original record data of faults and accidents of the high - speed railway;

[0093] A feature extraction unit 02, configured to extract the time features and space features when faults and accidents occur from the original record data of faults and accidents;

[0094] The clustering analysis unit 03 is used to divide the levels of faults and accidents according to time characteristics by using the spatio-temporal clustering analysis method, and obtain the time coefficients when the accidents and faults occur; divide the levels of faults and accidents according to spatial characteristics by using the spatio-temporal clustering analysis method, and obtain the spatial coefficients when the accidents and faults occur.

[0095] The safety index determination unit 04 is used to determine the high-speed railway power supply safety index according to the time coefficient and spatial coefficient when the accident and fault occur.

[0096] The evaluation unit 05 is used to evaluate the safety state of the high-speed railway power supply system according to the high-speed railway power supply safety index.

[0097] In one embodiment, the clustering analysis unit is specifically used for:

[0098] Adopt the variance goodness of fit to determine the optimal number of clustering centers;

[0099] With the optimal number of clustering centers, divide the levels of faults and accidents according to time characteristics by using the spatio-temporal clustering analysis method, and obtain the time coefficients when the accidents and faults occur;

[0100] With the optimal number of clustering centers, divide the levels of faults and accidents according to spatial characteristics by using the spatio-temporal clustering analysis method, and obtain the spatial coefficients when the accidents and faults occur.

[0101] In one embodiment, the feature extraction unit is further used for: extracting the cause characteristics, type characteristics, number of victims characteristics and degree of damage characteristics of the faults and accidents when the faults and accidents occur from the original record data of the faults and accidents;

[0102] The safety index determination unit is specifically used for: constructing a data model to calculate the high-speed railway power supply safety index according to the time coefficient, spatial coefficient, cause characteristic coefficient, type characteristic coefficient, number of victims characteristic coefficient and degree of damage characteristic coefficient when the accident and fault occur.

[0103] In one embodiment, the safety index determination unit is specifically used for:

[0104] Determine the high-speed railway power supply safety index according to the time coefficient, spatial coefficient and state transition probability between the normal state, fault state and accident state when the accident and fault occur.

[0105] In one embodiment, the evaluation unit is specifically used to evaluate the safety state of the high-speed railway power supply system with a month as the basic unit.

[0106] In one embodiment, the evaluation device for the power supply safety state of the high-speed railway may further include a preprocessing unit configured to preprocess the original record data of faults and accidents of the high-speed railway.

[0107] In one embodiment, the safety index determination unit is specifically configured to determine the power supply safety index of the high-speed railway according to the following formula:

[0108]

[0109] In the formula: F t : Time coefficient matrix of faults occurred; C v : Degree of damage coefficient matrix of accidents occurred; F s : Space coefficient matrix of faults occurred; C n : Number of casualties coefficient matrix of accidents occurred; F i : Influence coefficient matrix when faults occur; C a : Accident type coefficient matrix of accidents occurred; F r : Cause coefficient matrix when faults occur; C r : Accident cause coefficient matrix of accidents occurred; p i : State transition probability between normal state, fault state and accident state; m j : Number of times of normal state / fault state / accident state occurred, where j = 0, 1, 2 represent normal state / fault state / accident state respectively.

[0110] An embodiment of the present invention further provides a computer device, including a memory, a processor, and a computer program stored on the memory and executable on the processor. When the processor executes the computer program, the above-mentioned evaluation method for the power supply safety state of the high-speed railway is implemented.

[0111] An embodiment of the present invention further provides a computer-readable storage medium, where the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the above-mentioned evaluation method for the power supply safety state of the high-speed railway is implemented.

[0112] An embodiment of the present invention further provides a computer program product, where the computer program product includes a computer program, and when the computer program is executed by a processor, the above-mentioned evaluation method for the power supply safety state of the high-speed railway is implemented.

[0113] In the embodiments of the present invention, compared with the prior art in which there is a lack of a comprehensive safety index that comprehensively considers the normal state, accident state, and fault state for quantitatively evaluating the state of the traction power supply system, the evaluation scheme for the power supply safety state of high-speed railways is as follows: obtaining the original record data of faults and accidents on high-speed railways; extracting the time characteristics and spatial characteristics when the faults and accidents occur from the original record data of faults and accidents; using the spatio-temporal clustering analysis method to divide the levels of faults and accidents according to the time characteristics to obtain the time coefficients when the accidents and faults occur; using the spatio-temporal clustering analysis method to divide the levels of faults and accidents according to the spatial characteristics to obtain the spatial coefficients when the accidents and faults occur; determining the power supply safety index of the high-speed railway according to the time and spatial coefficients when the accidents and faults occur; and evaluating the safety state of the high-speed railway power supply system according to the safety index. It is possible to quantitatively evaluate the safety state of the high-speed railway power supply system based on the fault and accident data, which has scientific guiding significance for improving the safety performance of the high-speed railway power supply system.

[0114] Those skilled in the art should understand that the embodiments of the present invention can be provided as a method, a system, or a computer program product. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present invention can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk memories, CD-ROMs, optical memories, etc.) that contain computer-usable program code.

[0115] The present invention is described with reference to the flowcharts and / or block diagrams of methods, apparatuses (systems), and computer program products according to the embodiments of the present invention. It should be understood that each flow and / or block in the flowchart and / or block diagram, and the combination of flows and / or blocks in the flowchart and / or block diagram, can be realized by computer program instructions. These computer program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing devices to generate a machine, such that the instructions executed by the processor of the computer or other programmable data processing devices generate means for realizing the specified functions in Figure 1 one flow or multiple flows and / or blocks Figure 1 or means for realizing the specified functions in one block or multiple blocks.

[0116] These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing device to work in a specific manner, such that the instructions stored in the computer-readable memory generate a manufactured article including instruction means that realizes the specified functions in Figure 1 one flow or multiple flows and / or blocks Figure 1 or means for realizing the specified functions in one block or multiple blocks.

[0117] These computer program instructions can also be loaded onto a computer or other programmable data processing apparatus, so that a series of operation steps are executed on the computer or other programmable apparatus to produce a computer-implemented process, thereby providing instructions for implementing the steps of the function specified in one process or multiple processes and / or one block or multiple blocks in the flow Figure 1 one process or multiple processes and / or blocks Figure 1 or steps of the function specified in multiple blocks.

[0118] The specific embodiments described above further elaborate on the objectives, technical solutions, and beneficial effects of the present invention. It should be understood that the above are only specific embodiments of the present invention and are not used to limit the protection scope of the present invention. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principles of the present invention shall be included within the protection scope of the present invention.

Claims

1. An evaluation method for the power supply safety status of high - speed railways, characterized in that, it includes: Obtain the original record data of faults and accidents on high - speed railways; Extract the time characteristics and space characteristics at the time of faults and accidents from the original record data of faults and accidents; Use the spatio - temporal clustering analysis method to divide the levels of faults and accidents according to the time characteristics to obtain the time coefficients at the time of accidents and faults; use the spatio - temporal clustering analysis method to divide the levels of faults and accidents according to the space characteristics to obtain the space coefficients at the time of accidents and faults; Determine the power supply safety index of high - speed railways according to the time coefficients and space coefficients at the time of accidents and faults; Evaluate the safety status of the high - speed railway power supply system according to the power supply safety index of high - speed railways; Determine the power supply safety index of high - speed railways according to the time coefficients and space coefficients at the time of accidents and faults, including determining the power supply safety index of high - speed railways according to the following formula: Where: F t : Time coefficient matrix of failure occurrence; C v : Degree of injury coefficient matrix of accident occurrence; F s : Spatial coefficient matrix of failure occurrence; C n : Number of casualties coefficient matrix of accident occurrence; F i : Influence coefficient matrix at the time of failure occurrence; C a : Accident type coefficient matrix of accident occurrence; F r : Cause coefficient matrix at the time of failure occurrence; C r : Accident cause coefficient matrix of accident occurrence; p i : State transition probability between normal state, failure state and accident state; m j : Number of occurrences of normal state / failure state / accident state, where j = 0, 1, 2 represent normal state / failure state / accident state respectively.

2. The evaluation method for the power supply safety status of high - speed railways according to claim 1, characterized in that, Use the spatio - temporal clustering analysis method to divide the levels of faults and accidents according to the time characteristics to obtain the time coefficients at the time of accidents and faults; Use the spatio - temporal clustering analysis method to divide the levels of faults and accidents according to the space characteristics to obtain the space coefficients at the time of accidents and faults, including: Adopt the variance goodness - of - fit to determine the optimal number of clustering centers; With the optimal number of clustering centers, use the spatio - temporal clustering analysis method to divide the levels of faults and accidents according to the time characteristics to obtain the time coefficients at the time of accidents and faults; With the optimal number of clustering centers, use the spatio - temporal clustering analysis method to divide the levels of faults and accidents according to the space characteristics to obtain the space coefficients at the time of accidents and faults.

3. The evaluation method for the power supply safety status of high - speed railways according to claim 1, characterized in that, It further includes: Extract the cause characteristics, type characteristics, number of victims characteristics and degree of damage characteristics of faults and accidents at the time of faults and accidents from the original record data of faults and accidents; Determine the power supply safety index of high - speed railways according to the time coefficients and space coefficients at the time of accidents and faults, including: construct a data model to calculate the power supply safety index of high - speed railways according to the time coefficients, space coefficients, cause characteristic coefficients, type characteristic coefficients, number of victims characteristic coefficients and degree of damage characteristic coefficients at the time of accidents and faults.

4. The evaluation method for the power supply safety status of high - speed railways according to claim 1, characterized in that, Determine the power supply safety index of high - speed railways according to the time coefficients and space coefficients at the time of accidents and faults, including: Determine the power supply safety index of high - speed railways according to the time coefficients, space coefficients, and state transition probabilities between the normal state, fault state and accident state at the time of accidents and faults.

5. The evaluation method for the power supply safety status of high - speed railways according to claim 1, characterized in that, Evaluate the safety status of the high - speed railway power supply system according to the power supply safety index of high - speed railways, including: evaluate the safety status of the high - speed railway power supply system with a month as the basic unit.

6. The evaluation method for the power supply safety state of high-speed railways as described in claim 1, characterized in that, it further includes: preprocessing the original record data of faults and accidents on high-speed railways.

7. An evaluation device for the power supply safety state of high-speed railways, characterized in that, it includes: an acquisition unit for acquiring the original record data of faults and accidents on high-speed railways; a feature extraction unit for extracting the time features and space features at the time of faults and accidents from the original record data of faults and accidents; a clustering analysis unit for using the spatio-temporal clustering analysis method to classify the levels of faults and accidents according to the time features to obtain the time coefficients at the time of accidents and faults; using the spatio-temporal clustering analysis method to classify the levels of faults and accidents according to the space features to obtain the space coefficients at the time of accidents and faults; a safety index determination unit for determining the power supply safety index of high-speed railways according to the time coefficients and space coefficients at the time of accidents and faults; an evaluation unit for evaluating the safety state of the power supply system of high-speed railways according to the power supply safety index of high-speed railways; Determining the power supply safety index of high-speed railways according to the time coefficients and space coefficients at the time of accidents and faults, including determining the power supply safety index of high-speed railways according to the following formula: Where: F t : Time coefficient matrix of failure occurrence; C v : Victim degree coefficient matrix of accident occurrence; F s : Spatial coefficient matrix of failure occurrence; C n : Casualty number coefficient matrix of accident occurrence; F i : Influence coefficient matrix at the time of failure occurrence; C a : Accident type coefficient matrix of accident occurrence; F r : Cause coefficient matrix at the time of failure occurrence; C r : Accident cause coefficient matrix of accident occurrence; p i : State transition probability between normal state, failure state and accident state; m j : Number of occurrences of normal state / failure state / accident state, where j = 0, 1, 2 represent normal state / failure state / accident state respectively.

8. The evaluation device for the power supply safety state of high-speed railways as described in claim 7, characterized in that, the clustering analysis unit specifically is used for: using the variance goodness of fit to determine the optimal number of clustering centers; using the spatio-temporal clustering analysis method to classify the levels of faults and accidents according to the time features with the optimal number of clustering centers to obtain the time coefficients at the time of accidents and faults; using the spatio-temporal clustering analysis method to classify the levels of faults and accidents according to the space features with the optimal number of clustering centers to obtain the space coefficients at the time of accidents and faults.

9. The evaluation device for the power supply safety state of high-speed railways as described in claim 7, characterized in that, the feature extraction unit is further used for: extracting the cause features, type features, number of victims features and degree of damage features of faults and accidents at the time of faults and accidents from the original record data of faults and accidents; the safety index determination unit specifically is used for: constructing a data model to calculate the power supply safety index of high-speed railways according to the time coefficients, space coefficients, cause feature coefficients, type feature coefficients, number of victims feature coefficients and degree of damage feature coefficients at the time of accidents and faults.

10. The evaluation device for the power supply safety state of high-speed railways as described in claim 7, characterized in that, the safety index determination unit specifically is used for: determining the power supply safety index of high-speed railways according to the time coefficients, space coefficients at the time of accidents and faults, and the state transition probabilities between the normal state, fault state and accident state.

11. A computer device, including a memory, a processor, and a computer program stored on the memory and executable on the processor, characterized in that, when the processor executes the computer program, it implements the method described in any one of claims 1 to 6.

12. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the method according to any one of claims 1 to 6 is implemented.

13. A computer program product, characterized in that the computer program product includes a computer program, and when the computer program is executed by a processor, the method according to any one of claims 1 to 6 is implemented.

Images