Method and device for detecting failure of AC switch machine, computer device, readable storage medium and program product

Abstract

The application relates to a fault detection method and device of an alternating current switch machine, computer equipment, a readable storage medium and a program product. The method comprises the following steps: acquiring a to-be-detected feature sequence of the alternating current switch machine, wherein the to-be-detected feature sequence comprises current feature values of the alternating current switch machine in each current feature section, the current feature section is obtained by dividing a current curve of the alternating current switch machine based on time features and current change features; according to a Deng's correlation degree algorithm, in the feature sequence corresponding to each fault mode, a target feature sequence satisfying a preset correlation degree condition with the to-be-detected feature sequence is determined; and based on the fault mode corresponding to the target feature sequence, a fault detection result of the alternating current switch machine is output. The method can improve detection accuracy and detection efficiency.

Description

Technical Field

[0001] This application relates to the field of computer technology, and in particular to a fault detection method, apparatus, computer equipment, readable storage medium, and program product for an AC switch machine. Background Technology

[0002] Currently, AC switch machines are core equipment in rail transit signaling systems, and their operational status directly affects the safety and efficiency of railway transportation. Therefore, fault detection technology for AC switch machines is receiving increasing attention.

[0003] In related technologies, fault detection of AC switch machines typically relies on maintenance personnel making subjective judgments based on historical experience and the shape of the AC switch machine's current curve. If an abnormality is found, the AC switch machine is deemed to be faulty. However, the detection results of this method are easily affected by the skill level of the personnel, resulting in low accuracy and inefficiency. Summary of the Invention

[0004] Therefore, it is necessary to provide a fault detection method, apparatus, computer equipment, readable storage medium, and program product for AC switch machines that can improve detection accuracy and efficiency in response to the above-mentioned technical problems.

[0005] In a first aspect, this application provides a fault detection method for an AC switch machine, the method comprising:

[0006] A test feature sequence of an AC switch machine is obtained, wherein the test feature sequence contains the current feature values ​​of the AC switch machine in each current feature segment, and the current feature segment is obtained by dividing the current curve of the AC switch machine based on time features and current change features.

[0007] According to the Deng's correlation algorithm, in the feature sequences corresponding to each fault mode, the target feature sequence that satisfies the preset correlation condition with the feature sequence to be tested is determined;

[0008] Based on the fault mode corresponding to the target feature sequence, the fault detection result of the AC switch machine is output.

[0009] In one embodiment, determining the target feature sequence that satisfies the preset correlation condition with the feature sequence to be tested from the feature sequences corresponding to each fault mode according to the Dumbledore correlation algorithm includes:

[0010] The test feature sequence is normalized to obtain a normalized feature sequence;

[0011] According to the Dumbledore correlation algorithm, the Dumbledore correlation between the normalized feature sequence and the feature sequence corresponding to each fault mode is calculated.

[0012] The feature sequence corresponding to the maximum Dung correlation degree is determined as the target feature sequence.

[0013] In one embodiment, the method further includes:

[0014] For each current characteristic segment, multiple current characteristic parameter values ​​within the current characteristic segment are calculated to obtain candidate current characteristic values;

[0015] Based on the inter-class and intra-class dispersion of each candidate current feature value, an evaluation value for each candidate current feature value is determined, and the candidate current feature value with the largest evaluation value is taken as the current feature value corresponding to the current feature segment.

[0016] In one embodiment, the method further includes:

[0017] According to a preset sampling interval, the sample current sequence of the AC switch machine is collected, and the sample current sequence contains multiple sample current values ​​arranged in time sequence;

[0018] The turnout switching identification result is determined based on the sample current value;

[0019] The current curve of the AC switch machine is identified based on the section identification strategy corresponding to the turnout switching identification result to obtain the current characteristic section.

[0020] In one embodiment, the current characteristic section includes an unlocking zone, a switching zone, a locking zone, and a release zone; the step of identifying the current curve of the AC switch machine according to the section identification strategy corresponding to the turnout switching identification result to obtain the current characteristic section includes:

[0021] When the turnout conversion identification result indicates that the conversion is complete, based on the time-series backward calculation strategy, the segment with a range value greater than a first preset threshold is determined from the sample current sequence as a release zone;

[0022] The starting sampling point corresponding to the release zone is taken as the end point of the locking zone, and the locking zone is divided according to the preset number of sampling points corresponding to the locking zone.

[0023] Among the sample current values ​​before the locking zone, the first sampling point with a current value less than the second preset threshold is determined as a candidate starting point. If the current change in the preset segment after the candidate starting point meets the preset current transformation condition, the preset segment is divided into an unlocking zone, and the segment between the unlocking zone and the locking zone is divided into a conversion zone.

[0024] In one embodiment, the current characteristic section includes an unlocking zone and a switching zone; the step of identifying the current curve of the AC switch machine according to the section identification strategy corresponding to the turnout switching identification result to obtain the current characteristic section includes:

[0025] If the turnout conversion identification result indicates that the conversion is not completed, based on the time-series backward strategy, sampling points with sample current values ​​less than the turnout conversion threshold are determined from the sample current sequence as candidate starting points of the unlocking zone. If the current change in the preset section after the candidate starting point meets the preset current transformation condition, the preset section is divided into the unlocking zone.

[0026] Based on the sample current value after the unlocking zone, it is determined whether the switching zone blocking condition is met. If the switching zone blocking condition is met, the sampling point after the unlocking zone is divided into the switching zone; if the switching zone blocking condition is not met, the preset section after the unlocking zone is divided into the switching zone.

[0027] Secondly, this application also provides a fault detection device for an AC switch machine, the device comprising:

[0028] The acquisition module is used to acquire the test feature sequence of the AC switch machine. The test feature sequence includes the current feature values ​​of the AC switch machine in each current feature segment. The current feature segment is obtained by dividing the current curve of the AC switch machine based on time features and current change features.

[0029] The first determining module is used to determine, according to the Deng's correlation algorithm, a target feature sequence that satisfies the preset correlation condition with the feature sequence to be tested from the feature sequences corresponding to each fault mode;

[0030] The output module is used to output the fault detection results of the AC switch machine based on the fault mode corresponding to the target feature sequence.

[0031] In one embodiment, the first determining module is specifically used for:

[0032] The test feature sequence is normalized to obtain a normalized feature sequence;

[0033] According to the Dumbledore correlation algorithm, the Dumbledore correlation between the normalized feature sequence and the feature sequence corresponding to each fault mode is calculated.

[0034] The feature sequence corresponding to the maximum Dung correlation degree is determined as the target feature sequence.

[0035] In one embodiment, the device further includes:

[0036] The calculation module is used to calculate multiple current characteristic parameter values ​​within each current characteristic segment to obtain candidate current characteristic values.

[0037] The second determining module is used to determine the evaluation value of each candidate current feature value based on the inter-class dispersion and intra-class dispersion of each candidate current feature value, and to take the candidate current feature value with the largest evaluation value as the current feature value corresponding to the current feature segment.

[0038] In one embodiment, the device further includes:

[0039] The acquisition module is used to acquire the sample current sequence of the AC switch machine according to a preset sampling interval. The sample current sequence contains multiple sample current values ​​arranged in time sequence.

[0040] The third determining module is used to determine the turnout switching identification result based on the sample current value;

[0041] The identification module is used to identify the current curve of the AC switch machine according to the section identification strategy corresponding to the turnout conversion identification result, and obtain the current characteristic section.

[0042] In one embodiment, the current characteristic segment includes an unlocking region, a switching region, a latching region, and a release region; the identification module is specifically used for:

[0043] When the turnout conversion identification result indicates that the conversion is complete, based on the time-series backward calculation strategy, the segment with a range value greater than a first preset threshold is determined from the sample current sequence as a release zone;

[0044] The starting sampling point corresponding to the release zone is taken as the end point of the locking zone, and the locking zone is divided according to the preset number of sampling points corresponding to the locking zone.

[0045] Among the sample current values ​​before the locking zone, the first sampling point with a current value less than the second preset threshold is determined as a candidate starting point. If the current change in the preset segment after the candidate starting point meets the preset current transformation condition, the preset segment is divided into an unlocking zone, and the segment between the unlocking zone and the locking zone is divided into a conversion zone.

[0046] In one embodiment, the current characteristic segment includes an unlocking region and a switching region; the identification module is specifically used for:

[0047] If the turnout conversion identification result indicates that the conversion is not completed, based on the time-series backward strategy, sampling points with sample current values ​​less than the turnout conversion threshold are determined from the sample current sequence as candidate starting points of the unlocking zone. If the current change in the preset section after the candidate starting point meets the preset current transformation condition, the preset section is divided into the unlocking zone.

[0048] Based on the sample current value after the unlocking zone, it is determined whether the switching zone blocking condition is met. If the switching zone blocking condition is met, the sampling point after the unlocking zone is divided into the switching zone; if the switching zone blocking condition is not met, the preset section after the unlocking zone is divided into the switching zone.

[0049] Thirdly, this application also provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the method steps of the first aspect described above.

[0050] Fourthly, this application also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the method steps of the first aspect described above.

[0051] Fifthly, this application also provides a computer program product, including a computer program that, when executed by a processor, implements the method steps of the first aspect described above.

[0052] The aforementioned fault detection method, apparatus, computer equipment, readable storage medium, and program product for AC switch machines allow the electronic equipment to acquire the test feature sequence of the AC switch machine. This test feature sequence includes the current characteristic values ​​of the AC switch machine within each current characteristic segment, which is obtained by dividing the current curve of the AC switch machine based on time and current change characteristics. Then, the electronic equipment, using the Dumbledore correlation algorithm, determines the target feature sequence that satisfies a preset correlation condition with the test feature sequence from the feature sequences corresponding to each fault mode. Subsequently, the electronic equipment outputs the fault detection result of the AC switch machine based on the fault mode corresponding to the target feature sequence. Using this scheme, the current characteristic values ​​and test feature sequences of the AC switch machine within each current characteristic segment can be calculated. These test feature sequences accurately and comprehensively reflect the operating status of the AC switch machine. Furthermore, based on the correlation between the test feature sequence and the feature sequences corresponding to each fault mode, fault mode identification is performed, resulting in the fault detection result of the AC switch machine. This achieves automatic fault detection result identification, improving fault detection accuracy and efficiency. Attached Figure Description

[0053] To more clearly illustrate the technical solutions in the embodiments of this application or related technologies, the drawings used in the description of the embodiments of this application or related technologies will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0054] Figure 1 This is a flowchart illustrating a fault detection method for an AC switch machine in one embodiment;

[0055] Figure 2 This is a flowchart illustrating an example of a fault detection method for an AC switch machine in one embodiment;

[0056] Figure 3 This is a structural block diagram of a fault detection device for an AC switch machine in one embodiment;

[0057] Figure 4 This is an internal structural diagram of a computer device in one embodiment. Detailed Implementation

[0058] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0059] This application provides a fault detection method for an AC switch machine. This embodiment illustrates the method by applying it to a terminal. It is understood that this method can also be applied to a server, or to a system including both a terminal and a server, and is implemented through interaction between the terminal and the server. It is understood that this method can be applied to any terminal with data processing capabilities, and this application is not limited to this method.

[0060] The fault detection method for AC switch machines provided in this application will be described in detail below, with specific implementation details. For example... Figure 1 As shown, the method includes the following steps:

[0061] Step 102: Obtain the test feature sequence of the AC switch machine.

[0062] The test feature sequence includes the current characteristic values ​​of the AC switch machine in each current characteristic segment. The current characteristic segments are obtained by dividing the current curve of the AC switch machine based on time characteristics and current change characteristics.

[0063] In this embodiment, the terminal can collect the three-phase operating current data of the AC switch machine according to a preset sampling interval. For example, the three-phase operating current data of the AC switch machine can be collected at a sampling interval of 40ms and stored as a time-series current sequence. ,in Indicates the first The maximum value of the three-phase current in the next sample ( Then, the terminal can determine the current value within each current characteristic segment based on the acquired current sequence. Furthermore, based on the current values ​​within each current characteristic segment, it can calculate the current characteristic value of the AC switch machine within that current characteristic segment. The current characteristic values ​​within each current characteristic segment can constitute the measured characteristic sequence. The current characteristic segments are obtained by dividing the current curve of the AC switch machine based on time and current change characteristics. The current characteristic segments can include at least one of the following: unlocking zone, switching zone, locking zone, and release zone. The specific process of dividing the current characteristic segments will be explained in detail later.

[0064] Step 104: Based on the Deng's correlation algorithm, determine the target feature sequence that satisfies the preset correlation condition with the feature sequence to be tested in the feature sequences corresponding to each fault mode.

[0065] In this embodiment, the terminal may pre-store mapping relationships between various fault modes and feature sequences. The fault modes may include at least one or more of the following: normal transition mode, difficult startup fault mode, transition jamming fault mode, abnormal transition resistance fault mode, locking jamming fault mode, abnormal locking resistance fault mode, no buffer zone fault mode, and high buffer zone fault mode. The terminal can calculate the Dumbledore correlation between the target feature sequence and the target feature sequence according to the Dumbledore correlation algorithm, and use the feature sequence corresponding to the maximum correlation as the target feature sequence that satisfies the preset correlation condition.

[0066] Step 106: Based on the fault mode corresponding to the target feature sequence, output the fault detection results of the AC switch machine.

[0067] In this embodiment of the application, the terminal can determine the fault mode corresponding to the target feature sequence and output the identification information corresponding to the fault mode as the fault detection result of the AC switch machine.

[0068] Using the above scheme, the current characteristic value of the AC switch machine in each current characteristic section can be calculated, and the test characteristic sequence can accurately and comprehensively reflect the operation of the AC switch machine. Then, based on the correlation between the test characteristic sequence and the characteristic sequence corresponding to each fault mode, fault mode identification is performed, and the fault detection result of the AC switch machine is obtained. This realizes the automatic identification of fault detection results and improves the accuracy and efficiency of fault detection.

[0069] Optionally, based on the Dumbledore correlation algorithm, in the feature sequences corresponding to each fault mode, a target feature sequence that satisfies the preset correlation condition with the feature sequence to be tested is determined, including: normalizing the feature sequence to be tested to obtain a normalized feature sequence; calculating the Dumbledore correlation between the normalized feature sequence and the feature sequence corresponding to each fault mode according to the Dumbledore correlation algorithm; and determining the feature sequence corresponding to the maximum Dumbledore correlation as the target feature sequence.

[0070] In this embodiment, the terminal may pre-store the mapping relationship between various fault modes and feature sequences. The fault modes may include at least one or more of the following: normal transition mode, difficult start-up fault mode, transition jamming fault mode, abnormal transition resistance fault mode, locking jamming fault mode, abnormal locking resistance fault mode, no buffer zone fault mode, and high buffer zone fault mode. The feature parameters of each type of fault mode are normalized to ensure data comparability, as shown in Table 1.

[0071] Table 1

[0072]

[0073] After the terminal obtains the feature sequence to be tested, it can normalize the feature sequence to obtain a normalized feature sequence. Then, according to the Dumbledore correlation algorithm, the Dumbledore correlation between the normalized feature sequence and the feature sequence corresponding to each fault mode is calculated. The feature sequence with the highest Dumbledore correlation is then determined as the target feature sequence. The formula for calculating the Dumbledore correlation is as follows:

[0074]

[0075] in: For normalized feature sequences, ; The feature sequence corresponding to the fault mode, and similar. The feature difference (1≤k≤4, and is an integer). , These are the maximum and minimum values ​​among all differences; The resolution coefficient.

[0076] In the above scheme, Dumbledore correlation is used for feature sequence matching. Since Dumbledore correlation has good discriminative power, it can accurately match the target feature sequence, thereby improving the accuracy of fault type identification. Optionally, other correlation algorithms can also be used in this embodiment, such as gray absolute correlation, gray slope correlation, type B correlation, etc., and this embodiment is not limited thereto.

[0077] Optionally, the current characteristic values ​​corresponding to the current characteristic segments can be preset or obtained through screening. Accordingly, the method also includes: for each current characteristic segment, calculating multiple current characteristic parameter values ​​within the current characteristic segment to obtain candidate current characteristic values; determining the evaluation value of each candidate current characteristic value based on the inter-class dispersion and intra-class dispersion of each candidate current characteristic value, and taking the candidate current characteristic value with the largest evaluation value as the current characteristic value corresponding to the current characteristic segment.

[0078] In this embodiment, for each current characteristic segment, the terminal can calculate multiple current characteristic parameter values ​​within that segment to obtain candidate current characteristic values. Taking four current characteristic segments—unlocking, transition, locking, and release—as an example, each segment can extract parameter values ​​(i.e., candidate current characteristic values) of various time-domain characteristic parameters, such as inlet / outlet difference, maximum / minimum difference, steepness, and root mean square value. This forms a 48-dimensional feature set to comprehensively characterize the dynamic characteristics of the current curve. For each candidate current characteristic value, the inter-class and intra-class dispersion can be calculated, and their ratio can be calculated to obtain the Fisher evaluation value of the candidate current characteristic value. Specifically, the Fisher evaluation value... .in: For inter-class dispersion, This represents the intra-class scatter. The formula for calculating the inter-class scatter is as follows:

[0079]

[0080] The formula for calculating the intra-class dispersion is as follows:

[0081]

[0082] For each current characteristic segment, a candidate current characteristic value with the maximum evaluation value within that current characteristic segment can be selected as the current characteristic value corresponding to that current characteristic segment.

[0083] This application provides calculation formulas for various time-domain characteristic parameters for each segment. ( Calculate the following characteristic parameters (corresponding to the unlocking area, transition area, locking area, and release area, respectively):

[0084] (1) Import and export difference : Used to reflect the changes in current at the beginning and end of each section.

[0085]

[0086] (2) Maximum and minimum difference : Used to reflect the maximum change in current within each section.

[0087]

[0088] (3) Average value Used to reflect the central trend of current in each section.

[0089]

[0090] (4) Variance : Used to reflect the distribution of current around the mean.

[0091] (3-24)

[0092] (5) Root mean square value : Used to reflect the degree of fluctuation of the current relative to zero value in each section.

[0093]

[0094] (6) Difference sum Used to reflect the changing trend of current in each section.

[0095]

[0096] (7) Sum of squares of differences Used to reflect the absolute trend of current change within each section.

[0097]

[0098] (8) Steepness value It is used to detect current surge signals in different sections.

[0099]

[0100] (9) Peak factor : Used to reflect whether there is an impact signal in the current of each section.

[0101]

[0102] In one example, the current characteristic value corresponding to the unlocking area can be a steep value, which can effectively detect startup anomalies:

[0103]

[0104] in, The average current in the unlocking area. Let Variance be the variance.

[0105] In one example, the current characteristic value corresponding to the switching region can be the root mean square value, which is suitable for identifying switching jams or abnormal resistance:

[0106]

[0107] in, .

[0108] In one example, the current characteristic value corresponding to the latching region can be the difference between the maximum and minimum values, which can be used to detect abnormal resistance changes during the latching process:

[0109]

[0110] in, The current value within the locked zone.

[0111] In one example, the current characteristic value corresponding to the release region can be the average value, which is used to determine whether the release region is normal:

[0112]

[0113] in, The current value within the release zone.

[0114] It is understandable that the feature sequence to be tested .

[0115] Using the above scheme, feature optimization can be performed using the Fisher criterion to select the feature values ​​with the smallest intra-class dispersion and the largest inter-class dispersion. This allows for the selection of the most suitable feature values ​​for each segment to construct the test feature sequence, enabling the test feature sequence to better reflect the current change and thus improve the accuracy of feature extraction.

[0116] Optionally, the method further includes: collecting sample current sequences of the AC switch machine according to a preset sampling interval, wherein the sample current sequence contains multiple sample current values ​​arranged in time sequence; determining the turnout conversion identification result based on the sample current values; and identifying the current curve of the AC switch machine according to the section identification strategy corresponding to the turnout conversion identification result to obtain the current characteristic section.

[0117] In this embodiment, the terminal can collect the sample current sequence of the AC switch machine according to a preset sampling interval. The sample current sequence contains the sample current values ​​of multiple sampling points arranged in time sequence. Then, the maximum current value of the sample current value of each sampling point can be retained, and then the maximum current value of the last sampling point and the turnout switching threshold (e.g., The system determines the turnout switching identification result. Specifically, if the maximum current value is less than the turnout switching threshold, the switching is considered complete; if the maximum current value is greater than or equal to the turnout switching threshold, the switching is considered incomplete (e.g., switching jamming fault). For example, if the maximum three-phase current value at the last sampling point... If the turnout conversion is successful, the turnout conversion is considered complete; otherwise, the conversion is considered incomplete.

[0118] The terminal can identify the current curve of the AC switch machine according to the section identification strategy corresponding to the turnout conversion identification result, and obtain the current characteristic section. Specifically, if the conversion is completed, the terminal can dynamically adjust the segment boundary according to the preset sections corresponding to each current characteristic section (e.g., unlocking zone 0.5s, conversion zone 3.5s, locking zone 1s) and the current extreme value. If the conversion is not completed, the terminal can further determine whether there is a jamming fault. If there is a jamming fault, there is no locking zone or slow release zone, and it is divided into unlocking zone and conversion zone according to the division strategy; if there is no jamming fault, it is divided into unlocking zone, conversion zone and locking zone according to the division strategy.

[0119] It is understood that the above-mentioned current characteristic segmentation process can be performed during fault identification, in which case the sample current sequence consists of the current values ​​collected during fault detection. Alternatively, it can be performed before fault identification, and this application does not limit the specific steps. Using the above scheme, dynamic segmentation of current characteristic segments can be achieved. This segmentation method is based on the actual changes in current and is applicable to various switch machine models, exhibiting high adaptability.

[0120] Optionally, the current curve of the AC switch machine is identified according to the section identification strategy corresponding to the turnout conversion identification result to obtain the current characteristic section, including: when the turnout conversion identification result indicates that the conversion is completed, based on the time-series backward calculation strategy, the section with a range value greater than a first preset threshold is determined from the sample current sequence as the release zone; the starting sampling point corresponding to the release zone is taken as the end point of the locking zone, and the locking zone is divided according to the number of sampling points corresponding to the preset locking zone; among the sample current values ​​before the locking zone, the first sampling point with a current value less than a second preset threshold is determined as the candidate starting point; if the current change in the preset section after the candidate starting point meets the preset current transformation condition, the preset section is divided into the unlocking zone, and the section between the unlocking zone and the locking zone is divided into the conversion zone.

[0121] In this embodiment, when the turnout conversion identification result indicates that the conversion is complete, the current characteristic segment can be divided into an unlocking zone, a conversion zone, a locking zone, and a release zone according to the time sequence. Specifically, the terminal can determine the segment with a range value greater than a first preset threshold from the sample current sequence based on a time sequence backward deduction strategy, as the release zone. Then, the starting sampling point corresponding to the release zone is taken as the ending point of the locking zone, and the locking zone is divided according to the preset number of sampling points corresponding to the locking zone. Among the sample current values ​​of the sampling points before the starting point of the locking zone, the first sampling point with a current value less than a second preset threshold is determined as a candidate starting point. If the current change in the preset segment after the candidate starting point meets the preset current transformation condition, the preset segment is divided into an unlocking zone, and the segment between the unlocking zone and the locking zone is divided into a conversion zone.

[0122] For example, the acquired time-series current sequence ,in Indicates the first The maximum value of the three-phase current in the next sample ( When p=n, if If the turnout switching is complete, the range value can be determined by working backwards from p=n. The section is designated as the buffer zone. Then, the starting sampling point P corresponding to the buffer zone is taken as the end point of the locking zone, and the sampling point P-25 is taken as the start point of the locking zone and the end point of the transition zone. The query continues from this sampling point. Following the time sequence from front to back, the first matching point is found... sampling points At that time, based on sampling points As the starting point End point, judgment to Does there exist greater than ? The current value, and to Average current If this condition is met, then The sampling points are used as the end point of the unlocking area and the start point of the transition area, thus dividing the area into four segments. Optionally, if to There is no greater than 0 in The current value, or, to Average current Then The value is incremented by 1, and the judgment is repeated. This continues until the unlock zone and the conversion zone are determined.

[0123] Using the above scheme, the unlocking zone, conversion zone, locking zone and release zone can be dynamically divided after the conversion is completed. This enables dynamic segmentation of current characteristic sections. The segmentation method is based on the actual changes in current and is applicable to various switch machine models with high adaptability.

[0124] Optionally, the current curve of the AC switch machine is identified according to the section identification strategy corresponding to the turnout conversion identification result to obtain the current characteristic section, including: when the turnout conversion identification result characterization is not completed, based on the time-series backward deduction strategy, the sampling points with sample current values ​​less than the turnout conversion threshold are determined from the sample current sequence as candidate starting points of the unlocking zone; if the current change in the preset section after the candidate starting point meets the preset current transformation condition, the preset section is divided into the unlocking zone; based on the sample current value after the unlocking zone, it is determined whether the conversion zone blocking condition is met; if the conversion zone blocking condition is met, the sampling points after the unlocking zone are divided into the conversion zone; if the conversion zone blocking condition is not met, the preset section after the unlocking zone is divided into the conversion zone.

[0125] In this embodiment, when the turnout conversion identification result indicates that the conversion is incomplete, the current characteristic section may include an unlocking zone and a conversion zone. Specifically, when the turnout conversion identification result indicates that the conversion is incomplete, the terminal can determine sampling points with sample current values ​​less than the turnout conversion threshold from the sample current sequence based on a time-series backward deduction strategy, as candidate starting points for the unlocking zone. Then, it further determines sampling points within a preset section after the candidate starting points, and determines whether the preset current transformation conditions are met based on the current values ​​of these sampling points. If met, the preset section is divided into an unlocking zone.

[0126] For example, the acquired time-series current sequence ,in Indicates the first The maximum value of the three-phase current in the next sample ( We can work backwards from p=n to determine... The sampling points are used as candidate starting points for the unlock area. Then, with sampling points As the starting point End point, judgment to Does there exist greater than ? The current value, and to Average current If this condition is met, then The sampling point is used as the end point of the unlocking area.

[0127] The terminal can further determine whether the switching zone blocking condition is met based on the sample current value after the unlocking zone. If the switching zone blocking condition is met, the sampling point after the unlocking zone is divided into the switching zone; if the switching zone blocking condition is not met, the preset section after the unlocking zone is divided into the switching zone.

[0128] For example, the end point of the unlocked area is p. Then the sampling point p can be calculated. With p The range between sampling points; if this range is greater than 0.2A, it indicates that the switching region blocking condition is met, and p... The last sampling point n is taken as the end point of the conversion region, serving as the starting point. If the range is less than or equal to 0.2A, then p... As the starting point of the transition region, p This marks the end of the transition region. At this point, p is the starting point of the locked region, and the last sampling point n is the ending point of the locked region.

[0129] Using the above scheme, the unlocking zone and the conversion zone can be dynamically divided even when the conversion is not completed. This allows for dynamic segmentation of current characteristic sections, which is based on the actual changes in current and is applicable to various switch machine models with high adaptability.

[0130] like Figure 2 As shown in the figure, this application provides an example of a method for section division of an AC switch machine, including the following steps:

[0131] Step 201: Collect the sample current sequence of the AC switch machine according to the preset sampling interval.

[0132] The sample current sequence contains multiple sample current values ​​arranged in time sequence.

[0133] Step 202: Determine the turnout switching identification result based on the sample current value.

[0134] If the turnout conversion identification result indicates that the conversion is complete, proceed to steps 203-206; if the turnout conversion identification result indicates that the conversion is not complete, proceed to steps 207-211.

[0135] Step 203: Based on the time-series backward inference strategy, determine the segment in the sample current sequence whose range value is greater than the first preset threshold as the release zone.

[0136] Step 204: Take the starting sampling point corresponding to the release zone as the end point of the locking zone, and divide the locking zone according to the preset number of sampling points corresponding to the locking zone.

[0137] Step 205: Among the sample current values ​​before the locking zone, determine the first sampling point whose current value is less than the second preset threshold as the candidate starting point.

[0138] Step 206: If the current change in the preset section after the candidate starting point meets the preset current transformation condition, then the preset section is divided into the unlocking zone, and the section between the unlocking zone and the locking zone is divided into the transformation zone.

[0139] Step 207: Based on the time-series backward strategy, determine the sampling points in the sample current sequence whose sample current values ​​are less than the turnout switching threshold, and use them as candidate starting points for the unlocking zone.

[0140] Step 208: If the current change in the preset section after the candidate starting point meets the preset current transformation condition, then the preset section is divided into the unlocking area.

[0141] Step 209: Based on the sample current value after the unlocking zone, determine whether the switching zone blocking condition is met.

[0142] If the switching zone blocking condition is met, proceed to step 210; otherwise, proceed to step 211.

[0143] Step 210: Divide the sampling points after the unlocked area into the conversion area.

[0144] Step 211: Divide the preset section after the unlocked area into the conversion area.

[0145] It should be understood that although the steps in the flowcharts of the above embodiments are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the above embodiments may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the steps or stages of other steps.

[0146] Based on the same inventive concept, this application also provides a fault detection device for an AC switch machine to implement the fault detection method for the AC switch machine described above. The solution provided by this device is similar to the solution described in the above method. Therefore, the specific limitations of one or more embodiments of the AC switch machine fault detection device provided below can be found in the limitations of the AC switch machine fault detection method described above, and will not be repeated here.

[0147] In one exemplary embodiment, such as Figure 3 As shown, a fault detection device for an AC switch machine is provided. The device includes: an acquisition module 310, a first determination module 320, and an output module 330.

[0148] The acquisition module 310 is used to acquire the test feature sequence of the AC switch machine. The test feature sequence includes the current feature values ​​of the AC switch machine in each current feature segment. The current feature segment is obtained by dividing the current curve of the AC switch machine based on time features and current change features.

[0149] The first determining module 320 is used to determine, according to the Deng's correlation algorithm, a target feature sequence that satisfies the preset correlation condition with the feature sequence to be tested from the feature sequences corresponding to each fault mode;

[0150] The output module 330 is used to output the fault detection result of the AC switch machine based on the fault mode corresponding to the target feature sequence.

[0151] In one embodiment, the first determining module 320 is specifically used for:

[0152] The test feature sequence is normalized to obtain a normalized feature sequence;

[0153] According to the Dumbledore correlation algorithm, the Dumbledore correlation between the normalized feature sequence and the feature sequence corresponding to each fault mode is calculated.

[0154] The feature sequence corresponding to the maximum Dung correlation degree is determined as the target feature sequence.

[0155] In one embodiment, the device further includes:

[0156] The calculation module is used to calculate multiple current characteristic parameter values ​​within each current characteristic segment to obtain candidate current characteristic values.

[0157] The second determining module is used to determine the evaluation value of each candidate current feature value based on the inter-class dispersion and intra-class dispersion of each candidate current feature value, and to take the candidate current feature value with the largest evaluation value as the current feature value corresponding to the current feature segment.

[0158] In one embodiment, the device further includes:

[0159] The acquisition module is used to acquire the sample current sequence of the AC switch machine according to a preset sampling interval. The sample current sequence contains multiple sample current values ​​arranged in time sequence.

[0160] The third determining module is used to determine the turnout switching identification result based on the sample current value;

[0161] The identification module is used to identify the current curve of the AC switch machine according to the section identification strategy corresponding to the turnout conversion identification result, and obtain the current characteristic section.

[0162] In one embodiment, the current characteristic segment includes an unlocking region, a switching region, a latching region, and a release region; the identification module is specifically used for:

[0163] When the turnout conversion identification result indicates that the conversion is complete, based on the time-series backward calculation strategy, the segment with a range value greater than a first preset threshold is determined from the sample current sequence as a release zone;

[0164] The starting sampling point corresponding to the release zone is taken as the end point of the locking zone, and the locking zone is divided according to the preset number of sampling points corresponding to the locking zone.

[0165] Among the sample current values ​​before the locking zone, the first sampling point with a current value less than the second preset threshold is determined as a candidate starting point. If the current change in the preset segment after the candidate starting point meets the preset current transformation condition, the preset segment is divided into an unlocking zone, and the segment between the unlocking zone and the locking zone is divided into a conversion zone.

[0166] In one embodiment, the current characteristic segment includes an unlocking region and a switching region; the identification module is specifically used for:

[0167] If the turnout conversion identification result indicates that the conversion is not completed, based on the time-series backward strategy, sampling points with sample current values ​​less than the turnout conversion threshold are determined from the sample current sequence as candidate starting points of the unlocking zone. If the current change in the preset section after the candidate starting point meets the preset current transformation condition, the preset section is divided into the unlocking zone.

[0168] Based on the sample current value after the unlocking zone, it is determined whether the switching zone blocking condition is met. If the switching zone blocking condition is met, the sampling point after the unlocking zone is divided into the switching zone; if the switching zone blocking condition is not met, the preset section after the unlocking zone is divided into the switching zone.

[0169] Each module in the aforementioned fault detection device for AC switch machines can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in the processor of a computer device in hardware form or independent of it, or stored in the memory of a computer device in software form, so that the processor can call and execute the corresponding operations of each module.

[0170] In one exemplary embodiment, a computer device is provided, which may be a terminal, and its internal structure diagram may be as follows: Figure 4 As shown, the computer device includes a processor, memory, input / output interfaces, a communication interface, a display unit, and an input device. The processor, memory, and input / output interfaces are connected via a system bus, and the communication interface, display unit, and input device are also connected to the system bus via the input / output interfaces. The processor provides computing and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage media. The input / output interfaces are used for exchanging information between the processor and external devices. The communication interface is used for wired or wireless communication with external terminals; wireless communication can be achieved through Wi-Fi, mobile cellular networks, Near Field Communication (NFC), or other technologies. When the computer program is executed by the processor, it implements a method for the operation and maintenance of substation equipment. The display unit is used to form a visually visible image and can be a display screen, a projection device, or a virtual reality imaging device. The display screen can be an LCD screen or an e-ink screen. The input device of the computer device can be a touch layer covering the display screen, or buttons, trackballs, or touchpads set on the casing of the computer device, or external keyboards, touchpads, or mice, etc.

[0171] Those skilled in the art will understand that Figure 4 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0172] In one exemplary embodiment, a computer device is provided, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the above-described method steps.

[0173] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon, which, when executed by a processor, implements the above-described method steps.

[0174] In one embodiment, a computer program product is provided, including a computer program that, when executed by a processor, implements the above-described method steps.

[0175] It should be noted that the user information (including but not limited to user device identifiers, user personal information, etc.) and data (including but not limited to data used for analysis, data stored, data displayed, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of the relevant data must comply with relevant regulations.

[0176] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile memory and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM). The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, artificial intelligence (AI) processors, etc., and are not limited to these.

[0177] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this application.

[0178] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of this patent application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this application should be determined by the appended claims.

Claims

1. A fault detection method for an AC switch machine, characterized in that, The method includes: A test feature sequence of an AC switch machine is obtained, wherein the test feature sequence contains the current feature values ​​of the AC switch machine in each current feature segment, and the current feature segment is obtained by dividing the current curve of the AC switch machine based on time features and current change features. According to the Deng's correlation algorithm, in the feature sequences corresponding to each fault mode, the target feature sequence that satisfies the preset correlation condition with the feature sequence to be tested is determined; Based on the fault mode corresponding to the target feature sequence, the fault detection result of the AC switch machine is output.

2. The method according to claim 1, characterized in that, The step of determining the target feature sequence that satisfies the preset correlation condition with the feature sequence to be tested from the feature sequences corresponding to each fault mode according to the Deng correlation algorithm includes: The test feature sequence is normalized to obtain a normalized feature sequence; According to the Dumbledore correlation algorithm, the Dumbledore correlation between the normalized feature sequence and the feature sequence corresponding to each fault mode is calculated. The feature sequence corresponding to the maximum Dung correlation degree is determined as the target feature sequence.

3. The method according to claim 1, characterized in that, The method further includes: For each current characteristic segment, multiple current characteristic parameter values ​​within the current characteristic segment are calculated to obtain candidate current characteristic values; Based on the inter-class and intra-class dispersion of each candidate current feature value, an evaluation value for each candidate current feature value is determined, and the candidate current feature value with the largest evaluation value is taken as the current feature value corresponding to the current feature segment.

4. The method according to claim 1, characterized in that, The method further includes: According to a preset sampling interval, the sample current sequence of the AC switch machine is collected, and the sample current sequence contains multiple sample current values ​​arranged in time sequence; The turnout switching identification result is determined based on the sample current value; The current curve of the AC switch machine is identified based on the section identification strategy corresponding to the turnout switching identification result to obtain the current characteristic section.

5. The method according to claim 4, characterized in that, The current characteristic section includes an unlocking zone, a switching zone, a locking zone, and a release zone; the current curve of the AC switch machine is identified according to the section identification strategy corresponding to the turnout switching identification result to obtain the current characteristic section, including: When the turnout conversion identification result indicates that the conversion is complete, based on the time-series backward calculation strategy, the segment with a range value greater than a first preset threshold is determined from the sample current sequence as a release zone; The starting sampling point corresponding to the release zone is taken as the end point of the locking zone, and the locking zone is divided according to the preset number of sampling points corresponding to the locking zone. Among the sample current values ​​before the locking zone, the first sampling point with a current value less than the second preset threshold is determined as a candidate starting point. If the current change in the preset segment after the candidate starting point meets the preset current transformation condition, the preset segment is divided into an unlocking zone, and the segment between the unlocking zone and the locking zone is divided into a conversion zone.

6. The method according to claim 4, characterized in that, The current characteristic section includes an unlocking zone and a switching zone; the process of identifying the current curve of the AC switch machine according to the section identification strategy corresponding to the turnout switching identification result to obtain the current characteristic section includes: If the turnout conversion identification result indicates that the conversion is not completed, based on the time-series backward strategy, sampling points with sample current values ​​less than the turnout conversion threshold are determined from the sample current sequence as candidate starting points of the unlocking zone. If the current change in the preset section after the candidate starting point meets the preset current transformation condition, the preset section is divided into the unlocking zone. Based on the sample current value after the unlocking zone, it is determined whether the switching zone blocking condition is met. If the switching zone blocking condition is met, the sampling point after the unlocking zone is divided into the switching zone; if the switching zone blocking condition is not met, the preset section after the unlocking zone is divided into the switching zone.

7. A fault detection device for an AC switch machine, characterized in that, The device includes: The acquisition module is used to acquire the test feature sequence of the AC switch machine. The test feature sequence includes the current feature values ​​of the AC switch machine in each current feature segment. The current feature segment is obtained by dividing the current curve of the AC switch machine based on time features and current change features. The first determining module is used to determine, according to the Deng's correlation algorithm, a target feature sequence that satisfies the preset correlation condition with the feature sequence to be tested from the feature sequences corresponding to each fault mode; The output module is used to output the fault detection results of the AC switch machine based on the fault mode corresponding to the target feature sequence.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 6.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 6.

10. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 6.

Images