Method and device for cleaning a load spectrum of a rail transport equipment

Abstract

The present disclosure provides a cleaning method and device for a load spectrum of rail transit equipment. In the present disclosure, after obtaining a suspicious load spectrum from the load spectrum, the suspicious coordinates in the suspicious load spectrum are not directly cleaned. Instead, the first window information segment is extracted from the suspicious load spectrum and compared with a plurality of preset abnormal information segments to further determine whether there is abnormal information in the suspicious load spectrum. When any comparison result meets the preset abnormal condition, it indicates that there is abnormal information in the suspicious load spectrum, and the suspicious load spectrum in the load spectrum is cleaned. When any comparison result does not meet the preset abnormal condition, the suspicious load spectrum is retained in the load spectrum. The effective information in the load spectrum is avoided to be cleaned, and the cleaned load spectrum can more truly reflect the service working condition of the rail transit equipment.

Description

Technical Field

[0001] This disclosure relates to the field of rail transit technology, and more specifically, to a method and apparatus for cleaning the load spectrum of rail transit equipment. Background Technology

[0002] For rail transit equipment, the testing and acquisition of load dynamic signals plays a crucial role in load spectrum compilation. The reliability of the test signals determines the accuracy of the load spectrum. Data verification and preprocessing of the test signals form the basis for further analysis and statistical analysis of load data.

[0003] When running on the track, the transmission device of rail transit equipment is under complex service conditions of high speed and heavy load. Therefore, there are abnormal information caused by various factors, which directly affect the accuracy of subsequent load spectrum compilation. Load spectrum signals containing abnormal information will directly affect the accuracy of life calculation.

[0004] Currently, amplitude thresholding and gradient thresholding methods are commonly used to remove anomalous information. However, these methods often remove valid signals as well, and they treat anomalous information as an isolated, sudden event, failing to consider the influence of complex environmental factors. This results in the cleaned load spectrum not accurately reflecting the service conditions of the rail transit equipment.

[0005] Therefore, this disclosure provides a method for cleaning the load spectrum of rail transit equipment to solve one of the above-mentioned technical problems. Summary of the Invention

[0006] The purpose of this disclosure is to provide a method and apparatus for cleaning the load spectrum of rail transit equipment, which can solve at least one of the aforementioned technical problems. The specific solution is as follows:

[0007] According to a specific embodiment of this disclosure, in a first aspect, this disclosure provides a method for cleaning the load spectrum of rail transit equipment, comprising:

[0008] Obtain the load spectrum of any load parameter of rail transit equipment;

[0009] A suspicious load spectrum is obtained based on the load spectrum, wherein the suspicious load spectrum includes multiple suspicious coordinates;

[0010] Based on the aforementioned multiple suspicious coordinates, the core suspicious coordinates are determined;

[0011] Based on the core suspicious coordinates, extract the first pane information segment that meets the preset pane format information from the load spectrum;

[0012] The first pane information segment is projected onto multiple preset abnormal information segments for comparison to obtain multiple comparison results, wherein each preset abnormal information segment satisfies the preset pane format information.

[0013] When any comparison result meets the preset abnormal conditions, the suspicious load spectrum is removed from the load spectrum.

[0014] Optionally, determining the core suspicious coordinates based on the plurality of suspicious coordinates includes:

[0015] The first suspicious coordinate with the largest amplitude in the time point sequence of the load spectrum from the plurality of suspicious coordinates is identified as the core suspicious coordinate.

[0016] Optionally, the step of extracting the first pane information segment from the load spectrum based on the core suspicious coordinates and preset pane format information includes:

[0017] Project the core suspicious coordinates onto the horizontal axis of the first coordinate system where the core suspicious coordinates are located to obtain the first core coordinates of the first pane information segment;

[0018] Set the first core coordinate of the first pane information segment to a position on the pane width specified in the preset pane format information;

[0019] The first pane information segment is extracted from the load spectrum based on the pane length in the preset pane format information.

[0020] Optionally, the step of projecting the first pane information segment onto multiple preset abnormal information segments for comparison to obtain multiple comparison results includes:

[0021] Based on the mapping relationship between the first core coordinates of the first pane information segment and the second core coordinates of each preset abnormal information segment, the first pane information segment is projected onto the second coordinate system of each preset abnormal information segment to obtain the second pane information segment in the second coordinate system of the corresponding preset abnormal information segment.

[0022] Extract multiple morphological feature coordinates from the second pane information segment in the second coordinate system where the preset abnormal information segment is located;

[0023] In each second coordinate system, the first ordinate of the corresponding morphological feature coordinate is obtained from the preset abnormal information segment based on the first abscissa of each morphological feature coordinate.

[0024] The distance value of the corresponding morphological feature coordinate is obtained based on the second ordinate of each morphological feature coordinate and the first ordinate of the corresponding morphological feature coordinate.

[0025] When the distance value of any morphological feature coordinate is less than or equal to a preset distance threshold, the morphological feature coordinate is determined to be a matching coordinate.

[0026] The comparison results of the corresponding second coordinate system are obtained based on all matching coordinates in each second coordinate system. The comparison results include the percentage of matching coordinates in the corresponding second coordinate system relative to the total number of morphological feature coordinates.

[0027] Optionally, the step of removing the suspicious load spectrum from the load spectrum when any comparison result meets a preset anomaly condition includes:

[0028] When the matching percentage of any second coordinate system is greater than a preset matching percentage threshold, the suspicious load spectrum is removed from the load spectrum.

[0029] According to a specific embodiment of this disclosure, in a second aspect, this disclosure provides a cleaning device for the load spectrum of rail transit equipment, comprising:

[0030] The first acquisition unit is used to acquire the load spectrum of any load parameter of the rail transit equipment.

[0031] The second acquisition unit is used to acquire a segment of suspicious load spectrum based on the load spectrum, wherein the suspicious load spectrum includes multiple suspicious coordinates;

[0032] The determining unit is used to determine the core suspicious coordinates based on the plurality of suspicious coordinates;

[0033] The extraction unit is used to extract a first pane information segment that meets the preset pane format information from the load spectrum based on the core suspicious coordinates;

[0034] The obtaining unit is used to project the first pane information segment to multiple preset abnormal information segments for comparison and obtain multiple comparison results, wherein each preset abnormal information segment satisfies the preset pane format information.

[0035] The clearing unit is used to remove the suspicious load spectrum from the load spectrum when any comparison result meets the preset abnormal conditions.

[0036] Optionally, the determining unit includes:

[0037] The first determining subunit is used to determine the first suspicious coordinate with the largest amplitude in the time point sequence of the load spectrum from the plurality of suspicious coordinates as the core suspicious coordinate.

[0038] Optionally, the extraction unit includes:

[0039] The first obtaining subunit is used to project the core suspicious coordinates onto the horizontal axis of the first coordinate system where the core suspicious coordinates are located, and obtain the first core coordinates of the first pane information segment;

[0040] The sub-unit is configured to set the first core coordinate of the first pane information segment at a position on the pane width specified in the preset pane format information.

[0041] The first extraction subunit is used to extract a first pane information segment from the load spectrum based on the pane length in the preset pane format information.

[0042] Optionally, the obtaining unit includes:

[0043] The projection subunit is used to project the first pane information segment onto the second coordinate system of each preset abnormal information segment according to the mapping relationship between the first core coordinate of the first pane information segment and the second core coordinate of each preset abnormal information segment, so as to obtain the second pane information segment in the second coordinate system of the corresponding preset abnormal information segment.

[0044] The second extraction subunit is used to extract multiple morphological feature coordinates from the second pane information segment in the second coordinate system where the preset abnormal information segment is located.

[0045] The sub-unit is used to obtain the first ordinate of the corresponding morphological feature coordinate from the preset abnormal information segment based on the first abscissa of each morphological feature coordinate in each second coordinate system.

[0046] The second obtaining subunit is used to obtain the distance value of the corresponding morphological feature coordinate based on the second ordinate of each morphological feature coordinate and the first ordinate of the corresponding morphological feature coordinate.

[0047] The second determining subunit is used to determine the morphological feature coordinate as the matching coordinate when the distance value of any morphological feature coordinate is less than or equal to a preset distance threshold.

[0048] The third obtaining subunit is used to obtain the comparison result of the corresponding second coordinate system based on all matching coordinates in each second coordinate system. The comparison result includes the percentage of matching coordinates in the corresponding second coordinate system relative to the total number of morphological feature coordinates.

[0049] Optionally, the clearing unit includes:

[0050] The clearing sub-unit is used to remove the suspicious load spectrum from the load spectrum when the matching percentage of any second coordinate system is greater than a preset matching percentage threshold.

[0051] Compared with the prior art, the above-described solutions of this disclosure have at least the following beneficial effects:

[0052] This disclosure provides a method and apparatus for cleaning the load spectrum of rail transit equipment. Since abnormal information does not appear in isolation but is caused by the superposition of a series of complex factors, and the influence of these factors is already latent in the load spectrum, this disclosure does not directly remove the suspicious coordinates after obtaining a segment of the suspicious load spectrum. Instead, it extracts a first pane of information from the suspicious load spectrum and compares it with multiple preset abnormal information segments to further determine whether abnormal information exists in the suspicious load spectrum. When any comparison result meets a preset abnormality condition, it indicates that abnormal information exists in the suspicious load spectrum, and the suspicious load spectrum is then removed. When no comparison result meets the preset abnormality condition, the suspicious load spectrum is retained in the load spectrum. This avoids removing valid information from the load spectrum, thus ensuring that the cleaned load spectrum more accurately reflects the service conditions of the rail transit equipment. Attached Figure Description

[0053] Figure 1 A flowchart is shown of a method for cleaning the load spectrum of rail transit equipment according to an embodiment of the present disclosure;

[0054] Figure 2 The load spectrum of the vibration curve according to an embodiment of the present disclosure is shown;

[0055] Figure 3 A unit block diagram of a load spectrum cleaning device for rail transit equipment according to an embodiment of the present disclosure is shown. Detailed Implementation

[0056] To make the objectives, technical solutions, and advantages of this disclosure clearer, the disclosure will be further described in detail below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of this disclosure, and not all of them. Based on the embodiments of this disclosure, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this disclosure.

[0057] The terminology used in the embodiments of this disclosure is for the purpose of describing particular embodiments only and is not intended to be limiting of this disclosure. The singular forms “a,” “the,” and “the” as used in the embodiments of this disclosure and the appended claims are also intended to include the plural forms, and “multiple” generally includes at least two unless the context clearly indicates otherwise.

[0058] It should be understood that the term "and / or" used in this article is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, or B existing alone. Additionally, the character " / " in this article generally indicates that the preceding and following related objects have an "or" relationship.

[0059] It should be understood that although the terms first, second, third, etc., may be used to describe embodiments of this disclosure, these descriptions should not be limited to these terms. These terms are only used to distinguish the descriptions. For example, first may also be referred to as second without departing from the scope of embodiments of this disclosure, and similarly, second may also be referred to as first.

[0060] Depending on the context, the words “if” or “suppose” as used here can be interpreted as “when” or “in response to determination” or “in response to detection.” Similarly, depending on the context, the phrases “if determination” or “if detection (of the stated condition or event)” can be interpreted as “when determination” or “in response to determination” or “when detection (of the stated condition or event)” or “in response to detection (of the stated condition or event).”

[0061] It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that an article or device that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such an article or device. Without further limitation, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the article or device that includes said element.

[0062] It should be noted that any symbols and / or numbers present in the specification that are not marked in the accompanying drawings are not reference numerals.

[0063] The optional embodiments of this disclosure are described in detail below with reference to the accompanying drawings.

[0064] Example 1

[0065] The present disclosure provides an embodiment of a method for cleaning the load spectrum of rail transit equipment.

[0066] The following is combined Figure 1 The embodiments of this disclosure will be described in detail.

[0067] Step S101: Obtain the load spectrum of any load parameter of the rail transit equipment.

[0068] A load spectrum is a description of the changes in load parameter values ​​of a load-bearing object under specified load parameters and within a specified range. The horizontal axis of the load spectrum represents a time point, and the horizontal axis represents the load parameter value at that test time point.

[0069] The load parameters of rail transit equipment include torque parameters and speed parameters.

[0070] Step S102: Obtain a suspicious load spectrum based on the load spectrum.

[0071] Anomalies in the load spectrum of rail transit equipment are caused by sudden changes in test data. These anomalies include: impulse noise caused by short-term channel errors or vibration shocks; sawtooth fluctuations in load spectrum data caused by channel noise and external environment; no test data during the test period; data truncation exceeding the limit; and completely false information during the test period.

[0072] The characteristics of anomalous information in the load spectrum of rail transit equipment include: high randomness, large amplitude, unclear periodicity, simultaneous occurrence in all channels, and varying degrees of impact. Anomalous information can affect the accuracy of subsequent processing; noisy load spectrum signals will directly affect the accuracy of lifespan calculations. Therefore, anomalous information appearing in the load spectrum must be removed.

[0073] The suspicious load spectrum includes multiple suspicious coordinates, and the time interval between two adjacent suspicious coordinates is less than or equal to a preset time interval threshold.

[0074] Multiple suspicious coordinates in the suspicious load spectrum are identified from the load spectrum using the amplitude threshold method, gradient threshold detection method, and / or statistical variance smoothing method. In this embodiment, suspicious coordinates acquired at similar times are grouped together for a unified determination of whether they constitute a cleaning target.

[0075] Step S103: Determine the core suspicious coordinates based on the multiple suspicious coordinates.

[0076] This disclosure embodiment utilizes panes to extract suspicious coordinates from the load spectrum.

[0077] The core suspicious coordinates are associated with location indication information, which is used to indicate the setting position of the pane in the load spectrum.

[0078] In some specific embodiments, determining the core suspicious coordinates based on the plurality of suspicious coordinates includes the following steps:

[0079] Step S103a: Determine the first suspicious coordinate with the largest amplitude in the time sequence of the load spectrum from the plurality of suspicious coordinates as the core suspicious coordinate.

[0080] The time point sequence of the load spectrum refers to the time point sequence of the load spectrum from smallest to largest x-axis.

[0081] When determining whether a suspicious coordinate is a matching coordinate, amplitude is an important indicator. This embodiment uses the suspicious coordinate with the largest amplitude as core information, and performs anomaly identification on the suspicious load spectrum around this coordinate. If multiple suspicious coordinates with the largest amplitude exist in the suspicious load spectrum, the first suspicious coordinate with the largest amplitude is determined as the core suspicious coordinate, avoiding the omission of important anomaly information.

[0082] The first suspicious coordinate with the largest amplitude is the suspicious coordinate with the smallest maximum amplitude at a given time point among multiple suspicious coordinates with the largest amplitude.

[0083] Step S104: Extract the first pane information segment that meets the preset pane format information from the load spectrum based on the core suspicious coordinates.

[0084] The preset pane format information includes: the position of the x-coordinate of the core coordinate related to the core suspicious coordinates on the pane width, the pane length, and the pane height. The pane height is determined based on the information type of the y-coordinate in the load spectrum so that effective information can be extracted from the load spectrum.

[0085] The first pane information segment that satisfies the preset pane format information can be understood as follows: the horizontal coordinate of the core coordinate related to the core suspicious coordinate in the first pane information segment is located at the position of the pane width set in the preset pane format information, and the length of the first pane information segment extracted from the load spectrum is equal to the pane length set in the preset pane format information.

[0086] In some specific embodiments, extracting the first pane information segment from the load spectrum based on the core suspicious coordinates and preset pane format information includes the following steps:

[0087] Step S104-1: Project the core suspicious coordinates onto the horizontal axis of the first coordinate system where the core suspicious coordinates are located to obtain the first core coordinates of the first pane information segment.

[0088] Step S104-2: Set the first core coordinate of the first pane information segment to the position of the pane width set in the preset pane format information.

[0089] Step S104-3: Extract the first pane information segment from the load spectrum based on the pane length in the preset pane format information.

[0090] For example, such as Figure 2As shown, the pane height in the preset pane format information is 45dB, and the pane is a rectangle. The core suspicious coordinate A1 is projected onto the horizontal axis of the first coordinate system to obtain the first core coordinate A2 of the first pane information segment. The position of the pane width is set at the center of the pane width, that is, the first core coordinate A2 in the first pane information segment D is located at the center of the pane width. The first pane information segment D is extracted within the range of 1 / 2 pane length on both sides of the first core coordinate A2. Of course, the position of the core coordinate in the pane in this embodiment is not limited to this.

[0091] Step S105: Project the first pane information segment to multiple preset abnormal information segments for comparison to obtain multiple comparison results.

[0092] This disclosure embodiment predefines multiple preset exception information segments, each of which conforms to preset pane format information. Each preset exception information segment is a first pane information segment historically identified as containing exception information. This disclosure embodiment uses the preset exception information segments as reference samples to identify whether the first pane information segment contains exception information.

[0093] The first pane information segment is projected onto multiple preset abnormal information segments for comparison. Since both the first pane information segment and the multiple preset abnormal information segments meet the preset pane format information, the comparability and effectiveness of the two information segments are guaranteed.

[0094] In some specific embodiments, the step of projecting the first pane information segment onto multiple preset abnormal information segments for comparison to obtain multiple comparison results includes the following steps:

[0095] Step S105-1: Based on the mapping relationship between the first core coordinates of the first pane information segment and the second core coordinates of each preset abnormal information segment, the first pane information segment is projected onto the second coordinate system of each preset abnormal information segment to obtain the second pane information segment in the second coordinate system of the corresponding preset abnormal information segment.

[0096] Since each preset anomaly information segment originates from the first pane information segment that has been historically confirmed to contain anomaly information, each preset anomaly information segment has a second core coordinate. The method for determining the second core coordinate is the same as the method for determining the first core coordinate of the first pane information segment.

[0097] This can be understood as projecting the first core coordinates of the first pane information segment onto the second core coordinates of each preset abnormal information segment to locate the information in the first pane information segment, and then projecting the other information in the first pane information segment onto the second coordinate system of each preset abnormal information segment.

[0098] Step S105-2: Extract multiple morphological feature coordinates from the second pane information segment in the second coordinate system where the preset abnormal information segment is located.

[0099] The morphological feature coordinates refer to the coordinates that can reflect the curve morphological features of the second pane information segment. For example, the second pane information segment is an irregularly vibrating waveform curve, in which the peak coordinates and trough coordinates of each vibration are morphological feature coordinates.

[0100] Step S105-3: In each second coordinate system, the first ordinate of the corresponding morphological feature coordinate is obtained from the preset abnormal information segment based on the first abscissa of each morphological feature coordinate.

[0101] For example, in the second coordinate system, if the first morphological feature coordinate is (X1, Y1), the first horizontal coordinate of the first morphological feature coordinate is X1, and the coordinate corresponding to the first morphological feature coordinate in the preset abnormal information segment is (X1, Y2), then the first vertical coordinate is Y2.

[0102] Step S105-4: Obtain the distance value of the corresponding morphological feature coordinate based on the second ordinate of each morphological feature coordinate and the first ordinate of the corresponding morphological feature coordinate.

[0103] The distance value refers to the absolute value of the difference between the second ordinate and the first ordinate. For example, continuing the example above, the distance value = |Y1 - Y2|.

[0104] Step S105-5: When the distance value of any morphological feature coordinate is less than or equal to a preset distance threshold, the morphological feature coordinate is determined to be a matching coordinate.

[0105] Steps S105-6: Obtain the comparison results of the corresponding second coordinate system based on the number of all matching coordinates and the number of all morphological feature coordinates in each second coordinate system. The comparison results include the percentage of matching coordinates in the corresponding second coordinate system relative to the total number of morphological feature coordinates.

[0106] For example, there are 5 second coordinate systems with a total of 100 morphological feature coordinates. If there are 86 matching coordinates in the first second coordinate system, the matching percentage of the first pane information segment with the first preset anomaly information segment in the first second coordinate system is 86%. If there are 16 matching coordinates in the second second coordinate system, the matching percentage of the first pane information segment with the second preset anomaly information segment in the second second coordinate system is 16%. If there are 32 matching coordinates in the third second coordinate system, the matching percentage of the first pane information segment with the third preset anomaly information segment in the third second coordinate system is 32%. If there are 23 matching coordinates in the fourth second coordinate system, the matching percentage of the first pane information segment with the fourth preset anomaly information segment in the fourth second coordinate system is 23%. If there are 10 matching coordinates in the fifth second coordinate system, the matching percentage of the first pane information segment with the fifth preset anomaly information segment in the fifth second coordinate system is 10%.

[0107] Step S106: When any comparison result meets the preset abnormal conditions, the suspicious load spectrum is removed from the load spectrum.

[0108] The embodiments disclosed herein do not merely remove an isolated anomalous information from the load spectrum, but rather remove suspicious load spectra containing anomalous information from the load spectrum.

[0109] In some specific embodiments, the step of removing the suspicious load spectrum from the load spectrum when any comparison result meets a preset anomaly condition includes the following steps:

[0110] Step S106a: When the matching percentage of any second coordinate system is greater than the preset matching percentage threshold, the suspicious load spectrum is removed from the load spectrum.

[0111] When the matching percentage in any second coordinate system is greater than a preset matching percentage threshold, the first pane information segment matches a preset abnormal information segment in the corresponding second coordinate system, meaning there is abnormal information in the first pane information segment. For example, continuing the above example, with a preset matching percentage threshold of 75%, five matching percentages were generated in the five second coordinate systems: 86%, 16%, 32%, 23%, and 10%. 86% is greater than 75%, indicating that the first pane information segment matches the first preset abnormal information segment in the first second coordinate system. When the matching percentage in all second coordinate systems is less than or equal to the preset matching percentage threshold, it indicates that there is no abnormal information in the first pane information segment.

[0112] Because abnormal information does not appear in isolation, but is caused by the superposition of a series of complex factors in the preceding period, and the influence of these factors is already latent in the load spectrum, this embodiment of the present disclosure, after obtaining a segment of suspicious load spectrum from the load spectrum, does not directly remove the suspicious coordinates in the suspicious load spectrum. Instead, it extracts a first pane of information from the suspicious load spectrum and compares it with multiple preset abnormal information segments to further determine whether there is abnormal information in the suspicious load spectrum. When any comparison result meets the preset abnormality condition, it indicates that there is abnormal information in the suspicious load spectrum, and the suspicious load spectrum in the load spectrum is then removed. When no comparison result meets the preset abnormality condition, the suspicious load spectrum is retained in the load spectrum. This avoids removing valid information from the load spectrum, thereby ensuring that the cleaned load spectrum can more accurately reflect the service conditions of the rail transit equipment.

[0113] Example 2

[0114] This disclosure also provides apparatus embodiments that follow the above embodiments, for implementing the method steps described in the above embodiments. The interpretation of the same names is the same as that in the above embodiments, and they have the same technical effects as those in the above embodiments, so they will not be repeated here.

[0115] like Figure 3 As shown, this disclosure provides a load spectrum cleaning device 300 for rail transit equipment, comprising:

[0116] The first acquisition unit 301 is used to acquire the load spectrum of any load parameter of the rail transit equipment.

[0117] The second acquisition unit 302 is used to acquire a segment of suspicious load spectrum based on the load spectrum, wherein the suspicious load spectrum includes multiple suspicious coordinates;

[0118] Determining unit 303 is used to determine core suspicious coordinates based on the plurality of suspicious coordinates;

[0119] Extraction unit 304 is used to extract a first pane information segment that meets the preset pane format information from the load spectrum based on the core suspicious coordinates;

[0120] The obtaining unit 305 is used to project the first pane information segment to multiple preset abnormal information segments for comparison and obtain multiple comparison results, wherein each preset abnormal information segment satisfies the preset pane format information.

[0121] The clearing unit 306 is used to clear the suspicious load spectrum from the load spectrum when any comparison result meets the preset abnormal conditions.

[0122] Optionally, the determining unit 303 includes:

[0123] The first determining subunit is used to determine the first suspicious coordinate with the largest amplitude in the time point sequence of the load spectrum from the plurality of suspicious coordinates as the core suspicious coordinate.

[0124] Optionally, the extraction unit 304 includes:

[0125] The first obtaining subunit is used to project the core suspicious coordinates onto the horizontal axis of the first coordinate system where the core suspicious coordinates are located, and obtain the first core coordinates of the first pane information segment;

[0126] The sub-unit is configured to set the first core coordinate of the first pane information segment at a position on the pane width specified in the preset pane format information.

[0127] The first extraction subunit is used to extract a first pane information segment from the load spectrum based on the pane length in the preset pane format information.

[0128] Optionally, the obtaining unit 305 includes:

[0129] The projection subunit is used to project the first pane information segment onto the second coordinate system of each preset abnormal information segment according to the mapping relationship between the first core coordinate of the first pane information segment and the second core coordinate of each preset abnormal information segment, so as to obtain the second pane information segment in the second coordinate system of the corresponding preset abnormal information segment.

[0130] The second extraction subunit is used to extract multiple morphological feature coordinates from the second pane information segment in the second coordinate system where the preset abnormal information segment is located.

[0131] The sub-unit is used to obtain the first ordinate of the corresponding morphological feature coordinate from the preset abnormal information segment based on the first abscissa of each morphological feature coordinate in each second coordinate system.

[0132] The second obtaining subunit is used to obtain the distance value of the corresponding morphological feature coordinate based on the second ordinate of each morphological feature coordinate and the first ordinate of the corresponding morphological feature coordinate.

[0133] The second determining subunit is used to determine the morphological feature coordinate as the matching coordinate when the distance value of any morphological feature coordinate is less than or equal to a preset distance threshold.

[0134] The third obtaining subunit is used to obtain the comparison result of the corresponding second coordinate system based on all matching coordinates in each second coordinate system. The comparison result includes the percentage of matching coordinates in the corresponding second coordinate system relative to the total number of morphological feature coordinates.

[0135] Optionally, the clearing unit 306 includes:

[0136] The clearing sub-unit is used to remove the suspicious load spectrum from the load spectrum when the matching percentage of any second coordinate system is greater than a preset matching percentage threshold.

[0137] Because abnormal information does not appear in isolation, but is caused by the superposition of a series of complex factors in the preceding period, and the influence of these factors is already latent in the load spectrum, this embodiment of the present disclosure, after obtaining a segment of suspicious load spectrum from the load spectrum, does not directly remove the suspicious coordinates in the suspicious load spectrum. Instead, it extracts a first pane of information from the suspicious load spectrum and compares it with multiple preset abnormal information segments to further determine whether there is abnormal information in the suspicious load spectrum. When any comparison result meets the preset abnormality condition, it indicates that there is abnormal information in the suspicious load spectrum, and the suspicious load spectrum in the load spectrum is then removed. When no comparison result meets the preset abnormality condition, the suspicious load spectrum is retained in the load spectrum. This avoids removing valid information from the load spectrum, thereby ensuring that the cleaned load spectrum can more accurately reflect the service conditions of the rail transit equipment.

[0138] Finally, it should be noted that the various embodiments in this specification are described in a progressive manner, with each embodiment focusing on its differences from other embodiments. Similar or identical parts between embodiments can be referred to interchangeably. For the systems or apparatus disclosed in the embodiments, since they correspond to the methods disclosed in the embodiments, the descriptions are relatively simple, and relevant parts can be referred to the method section.

[0139] The above embodiments are only used to illustrate the technical solutions of this disclosure, and are not intended to limit it. Although this disclosure has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this disclosure.

Claims

1. A method for cleaning the load spectrum of rail transit equipment, characterized in that, include: Obtain the load spectrum of any load parameter of rail transit equipment; A suspicious load spectrum is obtained based on the load spectrum, wherein the suspicious load spectrum includes multiple suspicious coordinates; Based on the multiple suspicious coordinates, the core suspicious coordinates are determined; Based on the core suspicious coordinates, extract the first pane information segment that meets the preset pane format information from the load spectrum; The first pane information segment is projected onto multiple preset abnormal information segments for comparison to obtain multiple comparison results, wherein each preset abnormal information segment satisfies the preset pane format information. When any comparison result meets a preset anomaly condition, the suspicious load spectrum is removed from the load spectrum. The determination of core suspicious coordinates based on the multiple suspicious coordinates includes: The first suspicious coordinate with the largest amplitude in the time sequence of the load spectrum from the plurality of suspicious coordinates is identified as the core suspicious coordinate. The extraction of the first pane information segment from the load spectrum based on the core suspicious coordinates and preset pane format information includes: Project the core suspicious coordinates onto the horizontal axis of the first coordinate system where the core suspicious coordinates are located to obtain the first core coordinates of the first pane information segment; Set the first core coordinate of the first pane information segment to the position on the pane width set in the preset pane format information; The first pane information segment is extracted from the load spectrum based on the pane length in the preset pane format information.

2. The method according to claim 1, characterized in that, The step of projecting the first pane information segment onto multiple preset abnormal information segments for comparison to obtain multiple comparison results includes: Based on the mapping relationship between the first core coordinates of the first pane information segment and the second core coordinates of each preset abnormal information segment, the first pane information segment is projected onto the second coordinate system of each preset abnormal information segment to obtain the second pane information segment in the second coordinate system of the corresponding preset abnormal information segment. Extract multiple morphological feature coordinates from the second pane information segment in the second coordinate system where the preset abnormal information segment is located; In each second coordinate system, the first ordinate of the corresponding morphological feature coordinate is obtained from the preset abnormal information segment based on the first abscissa of each morphological feature coordinate. The distance value of the corresponding morphological feature coordinate is obtained based on the second ordinate of each morphological feature coordinate and the first ordinate of the corresponding morphological feature coordinate. When the distance value of any morphological feature coordinate is less than or equal to a preset distance threshold, the morphological feature coordinate is determined to be a matching coordinate. The comparison results of the corresponding second coordinate system are obtained based on all matching coordinates in each second coordinate system. The comparison results include the percentage of matching coordinates in the corresponding second coordinate system relative to the total number of morphological feature coordinates.

3. The method according to claim 2, characterized in that, When any comparison result meets a preset anomaly condition, the suspicious load spectrum is removed from the load spectrum, including: When the matching percentage of any second coordinate system is greater than a preset matching percentage threshold, the suspicious load spectrum is removed from the load spectrum.

4. A cleaning device for the load spectrum of rail transit equipment, characterized in that, include: The first acquisition unit is used to acquire the load spectrum of any load parameter of the rail transit equipment. The second acquisition unit is used to acquire a segment of suspicious load spectrum based on the load spectrum, wherein the suspicious load spectrum includes multiple suspicious coordinates; The determining unit is used to determine the core suspicious coordinates based on the plurality of suspicious coordinates; The extraction unit is used to extract a first pane information segment that meets the preset pane format information from the load spectrum based on the core suspicious coordinates; The obtaining unit is used to project the first pane information segment to multiple preset abnormal information segments for comparison and obtain multiple comparison results, wherein each preset abnormal information segment satisfies the preset pane format information. The clearing unit is used to remove the suspicious load spectrum from the load spectrum when any comparison result meets a preset abnormality condition. The determining unit includes: The first determining subunit is used to determine the first suspicious coordinate with the largest amplitude in the time point sequence of the load spectrum from the plurality of suspicious coordinates as the core suspicious coordinate. The extraction unit includes: The first obtaining subunit is used to project the core suspicious coordinates onto the horizontal axis of the first coordinate system where the core suspicious coordinates are located, and obtain the first core coordinates of the first pane information segment; The sub-unit is configured to set the first core coordinate of the first pane information segment at a position on the pane width specified in the preset pane format information. The first extraction subunit is used to extract a first pane information segment from the load spectrum based on the pane length in the preset pane format information.

5. The apparatus according to claim 4, characterized in that, The obtaining unit includes: The projection subunit is used to project the first pane information segment onto the second coordinate system of each preset abnormal information segment according to the mapping relationship between the first core coordinate of the first pane information segment and the second core coordinate of each preset abnormal information segment, so as to obtain the second pane information segment in the second coordinate system of the corresponding preset abnormal information segment. The second extraction subunit is used to extract multiple morphological feature coordinates from the second pane information segment in the second coordinate system where the preset abnormal information segment is located. The sub-unit is used to obtain the first ordinate of the corresponding morphological feature coordinate from the preset abnormal information segment based on the first abscissa of each morphological feature coordinate in each second coordinate system. The second obtaining subunit is used to obtain the distance value of the corresponding morphological feature coordinate based on the second ordinate of each morphological feature coordinate and the first ordinate of the corresponding morphological feature coordinate. The second determining subunit is used to determine the morphological feature coordinate as the matching coordinate when the distance value of any morphological feature coordinate is less than or equal to a preset distance threshold. The third obtaining subunit is used to obtain the comparison result of the corresponding second coordinate system based on all matching coordinates in each second coordinate system. The comparison result includes the percentage of matching coordinates in the corresponding second coordinate system relative to the total number of morphological feature coordinates.

6. The apparatus according to claim 5, characterized in that, The clearing unit includes: The clearing sub-unit is used to remove the suspicious load spectrum from the load spectrum when the matching percentage of any second coordinate system is greater than a preset matching percentage threshold.

Images