Defect depth analysis method for contact network equipment

Abstract

The invention discloses an overhead line system equipment defect depth analysis method and system, a storage medium and equipment, and belongs to the technical field of overhead line systems, and the method comprises the steps: carrying out the standardized definition of data uploaded by a detection device according to the requirements, and obtaining first detection data; the first detection data comprises 1C detection data, 2C detection data, 3C detection data and 4C detection data; performing pole number alignment processing on the first detection data to obtain second detection data; analyzing and processing defects of the second detection data to obtain associated data; and confirming the defect based on the associated data, and generating defect description information. According to the contact network equipment defect depth analysis method and system, the storage medium and the equipment, multi-source detection data are uploaded in a standardized mode, original data and external defects are subjected to depth analysis through technologies such as waveform alignment and intelligent image recognition, and the defect analysis efficiency and accuracy can be improved.

Description

Technical Field

[0001] The present invention relates to the field of contact network technology, and in particular to a contact network equipment defect depth analysis method, system, storage medium and equipment. Background Art

[0002] With the rapid development of my country's high-speed railways, the importance of railway traction power supply systems has become increasingly prominent. As an important infrastructure for providing energy to high-speed trains, the stability and safety of the overhead contact network are of vital importance. Due to the complex structure and high-altitude layout of the overhead contact network, and the impact of large current shocks and pantograph vibrations during daily operation, the equipment is prone to defects, which restricts the reliability and quality of the railway power supply system and affects the high-quality development of the railway.

[0003] At present, the defect analysis method of contact network equipment is mainly based on the 6C data center as the core, and with the help of 6C standardized software, the 1C-4C detection device type data of each manufacturer is uploaded and parsed according to the format requirements of the China Railway Corporation, and then the contact network 6C comprehensive diagnosis and analysis software is used to confirm the 1C and 3C defect data, and perform data analysis, defect marking and other functions on the 2C and 4C original data.

[0004] However, the 1C, 2C, 3C and 4C original data analysis software in this method is independent, and it is impossible to perform horizontal correlation analysis to further confirm and analyze the causes of defects; the vertical comparative analysis mainly relies on manual work, and it is impossible to quickly retrieve comparative data, and the convenience, efficiency and accuracy of the analysis operation are poor; currently, the 1C detection waveform data is mainly manually superimposed to analyze the change trends of height, pull-out value, hard point, arcing, contact force, etc. In order to locate the parameter defects of 1C, it often takes about 20 minutes to search and retrieve relevant data, and then manually perform waveform superposition analysis; and the analysis of 2C, 3C and 4C data requires manual opening of two independent software for position alignment and positioning. Summary of the invention

[0005] To solve the above problems, the present invention provides a method, system, storage medium and device for in-depth analysis of defects in contact network equipment. By standardizing the uploading of multi-source detection data and using technologies such as waveform alignment and image intelligent recognition to conduct in-depth analysis of original data and external defects, the efficiency and accuracy of defect analysis can be improved.

[0006] The above objectives can be achieved through the following solutions:

[0007] A method for in-depth analysis of defects in contact network equipment, comprising: standardizing and defining data uploaded by a detection device as required to obtain first detection data; the first detection data includes 1C detection data, 2C detection data, 3C detection data and 4C detection data; performing pole number alignment processing on the first detection data to obtain second detection data; analyzing and processing defects in the second detection data to obtain associated data; confirming defects based on the associated data to generate defect description information.

[0008] Optionally, performing pole number alignment processing on the first detection data to obtain the second detection data includes: performing pole number alignment on the multiple 1C detection data based on waveform alignment technology to obtain 1C alignment data; performing pole number alignment on the multiple 2C detection data based on image intelligent recognition technology to obtain 2C alignment data; performing pole number alignment on the multiple 3C detection data based on image intelligent recognition technology to obtain 3C alignment data; performing pole number alignment on the multiple 4C detection data based on one-pole-one-grade data to obtain 4C alignment data; wherein the second detection data includes the 1C alignment data, the 2C alignment data, the 3C alignment data and the 4C alignment data.

[0009] Optionally, the waveform alignment technology is used to perform pole number alignment on multiple 1C detection data to obtain 1C alignment data, including: establishing target template data according to preset requirements; based on an image template matching method and the target template data, roughly positioning the 1C detection data to obtain positioning data; based on a longest matching subsequence search method and the positioning data, roughly matching the 1C detection data to obtain rough matching data; based on a feature inflection point search method, accurately positioning and matching the rough matching data to obtain precise matching data; and according to the precise matching data, performing pole number alignment on multiple 1C detection data to obtain the 1C alignment data.

[0010] Optionally, the performing pole number alignment on the multiple 2C detection data based on the image intelligent recognition technology to obtain the 2C aligned data includes: segmenting the 2C detection data to obtain multiple 2C picture data; identifying the pole number of the 2C picture data by using the image intelligent recognition technology; performing pole number alignment on the multiple 2C detection data according to the pole number of the 2C picture data to obtain the 2C aligned data.

[0011] Optionally, the performing pole number alignment on the multiple 3C detection data based on the image intelligent recognition technology to obtain the 3C alignment data includes: segmenting the 3C detection data to obtain multiple 3C picture data; identifying kilometer mark information of the 3C picture data by using the image intelligent recognition technology; converting the kilometer mark information according to basic data to obtain the pole number corresponding to the 3C picture data; performing pole number alignment on the multiple 3C detection data according to the pole number of the 3C picture data to obtain the 3C alignment data.

[0012] Optionally, the performing pole number alignment on the multiple 4C detection data based on the one-pole-one-file data to obtain the 4C aligned data includes: pre-processing the missed pole or wrong pole data of the multiple 4C detection data to obtain 4C correction data; performing pole number alignment on the multiple 4C detection data according to the pole number of the 4C correction data to obtain the 4C aligned data.

[0013] Optionally, the analyzing and processing the defects of the second detection data to obtain the associated data includes: performing a vertical analysis on the defects of the second detection data to obtain first associated data; performing a horizontal analysis on the defects that cannot be confirmed by the second detection data to obtain second associated data; wherein the associated data includes the first associated data and the second associated data.

[0014] Based on the same inventive concept, the present invention also provides a contact network equipment defect in-depth analysis system, the system comprising: a data processing module, used to standardize and upload the data uploaded by the detection device as required to obtain first detection data; a pole number alignment module, used to process the first detection data, thereby achieving pole number alignment, and obtaining second detection data; a defect analysis module, used to analyze and process the defects of the second detection data to obtain associated data; a defect confirmation module, used to confirm the defects based on the associated data and generate defect description information.

[0015] Based on the same inventive concept, the present invention also provides a computer storage medium storing one or more programs, which can implement any of the aforementioned methods when the one or more programs are executed.

[0016] Based on the same inventive concept, the present invention also provides a device, including a processor, a communication interface, a memory and a communication bus; the processor, the communication interface and the memory communicate with each other through the communication bus; the processor is used to execute the program stored in the aforementioned computer-readable storage medium.

[0017] Compared with the prior art, the present invention has the following advantages:

[0018] 1. By standardizing the upload of multi-source inspection data, the 1C-4C inspection raw data is automatically aligned to provide a basis for subsequent horizontal correlation analysis and vertical comparative analysis, which can improve the precise positioning capability and rapid data retrieval capability of defect depth analysis.

[0019] 2. Use waveform alignment and image intelligent recognition technologies to conduct horizontal correlation analysis and vertical comparative analysis on external defects and 1C-4C detection raw data, realize correlation analysis in spatial latitude and comparative analysis in temporal latitude, thereby improving defect analysis efficiency and accuracy.

[0020] 2. Through the defect-related information such as one-pole-one-file, bow-net video, historical defects, ledger data, drawing data, original inspection data, etc., we assist in in-depth analysis and confirmation of defects and improve the accuracy of defect classification.

[0021] Other features and advantages of the present invention will be described in the following description, and partly become apparent from the description, or understood by practicing the present invention. The purpose and other advantages of the present invention can be realized and obtained by the structures pointed out in the description, claims and drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0023] Figure 1 It is a flow chart of a method for in-depth analysis of defects in contact network equipment according to an embodiment of the present invention.

[0024] Figure 2 It is a flow chart of a method for detecting data pole number alignment according to an embodiment of the present invention.

[0025] Figure 3 It is a defect analysis flow diagram of a method for in-depth defect analysis of contact network equipment according to an embodiment of the present invention.

[0026] Figure 4 It is a framework diagram of a contact network equipment defect depth analysis system according to an embodiment of the present invention.

[0027] Figure 5 It is a structural schematic diagram of an electronic device according to an embodiment of the present invention. DETAILED DESCRIPTION

[0028] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0029] Reference Figure 1 An embodiment of the present invention proposes a method for in-depth analysis of defects in contact network equipment. By standardizing and uploading multi-source detection data, the original data and external defects are deeply analyzed using technologies such as waveform alignment and image intelligent recognition, which can improve the efficiency and accuracy of defect analysis.

[0030] The analysis method of this embodiment specifically includes:

[0031] The data uploaded by the detection device is standardized and defined as required to obtain first detection data; the first detection data includes 1C detection data, 2C detection data, 3C detection data and 4C detection data;

[0032] Exemplarily, as shown in Appendix 1, it can support data uploading by different detection devices of multiple manufacturers; the data uploaded by the detection devices can be standardized and defined in accordance with the requirements of the "Provisional Technical Conditions for the 6C System Integrated Data Processing Center" to obtain 1C detection data, 2C detection data, 3C detection data and 4C detection data.

[0033] 1. Detection device data type and source table (Appendix 1)

[0034]

[0035]

[0036] Performing a rod number alignment process on the first detection data to obtain second detection data;

[0037] Analyzing and processing defects of the second detection data to obtain associated data;

[0038] The defect is confirmed based on the associated data, and defect description information is generated.

[0039] Exemplarily, related data is received to assist in the final confirmation of the defect. When confirming the defect, the defect information can be modified, such as the line, station, type of line, track, kilometer mark and pole number information. At the same time, the defect is modified according to the national railway standardized description, and the defect description information is automatically generated. At the same time, 7 types of defects are added, such as equipment defects, bird nests, dangerous trees, external environment, adjacent construction records, special projects and others.

[0040] Optionally, performing rod number alignment processing on the first detection data to obtain second detection data includes:

[0041] Performing pole number alignment on the plurality of 1C detection data based on waveform alignment technology to obtain 1C alignment data;

[0042] Specifically, the location information of 1C detection data comes from vehicle speed sensors, electronic tags, GPS, etc. After a certain period of time, there will be a certain difference between the detected mileage and the actual mileage. The output detection data has poor repeatability for a long time; waveform alignment solves the problem that the geometric parameter waveforms of multiple 1C detection data detected by the same detection equipment cannot be aligned.

[0043] Performing pole number alignment on the plurality of 2C detection data based on image intelligent recognition technology to obtain 2C alignment data;

[0044] Specifically, based on the image intelligent recognition technology, the pole number recognition of 2C inspection data is realized, and then the pole number alignment function is realized, which provides great convenience for the query and comparison of historical data of the same line. For example, for the pole number images at the same location, the defects of the 2C inspection data can be compared and analyzed to confirm.

[0045] Performing pole number alignment on the plurality of 3C detection data based on image intelligent recognition technology to obtain 3C alignment data;

[0046] Performing pole number alignment on the plurality of 4C detection data based on one-pole-one-file data to obtain 4C alignment data;

[0047] The second detection data includes the 1C alignment data, the 2C alignment data, the 3C alignment data and the 4C alignment data.

[0048] Optionally, the step of performing pole number alignment on the plurality of 1C detection data based on the waveform alignment technology to obtain 1C alignment data includes:

[0049] Establish target template data according to preset requirements;

[0050] Specifically, the preset requirements can be to limit the clarity, completeness, accuracy and other factors of the 1C test data. The target template data is the highest quality or most representative 1C test data. The pole number can be understood as the identifier, index, etc. of the data. In multiple 1C test data, the pole number may be different due to various reasons, such as inconsistent naming rules, recording errors, etc. By establishing the target template data, it can be ensured that all data are identified according to a unified standard, thereby improving the consistency and comparability of the data.

[0051] Based on the image template matching method and the target template data, the IC detection data is roughly positioned to obtain positioning data;

[0052] Specifically, the image template matching method is used to preliminarily compare the detection image of the 1C detection data with the image of the target template data to determine the approximate position of the detection image of the 1C detection data in the target template data and obtain positioning data.

[0053] Exemplarily, the detection image of 1C detection data may contain elements such as tracks, sleepers, and signal equipment. Through the template matching algorithm, the area most similar to the detection image of 1C detection data can be found in the image of the target template data, thereby preliminarily locating the detection position and obtaining positioning data.

[0054] Based on the longest matching subsequence search method and the positioning data, the IC detection data is roughly matched to obtain rough matching data;

[0055] Specifically, based on the positioning data, the longest common subsequence (LCS) search method is further used to roughly match the 1C detection data with the target template data.

[0056] Exemplarily, the key information in the 1C detection data is compared with the corresponding information in the standard template data, such as the track length, signal equipment location, etc.; the longest common subsequence between the two is found through the LCS algorithm, and the rough matching data is obtained as the result of the rough matching.

[0057] Based on the characteristic inflection point search method, the rough matching data is accurately positioned and matched to obtain accurate matching data;

[0058] Specifically, based on the coarse matching data, the characteristic inflection point search method is used to accurately locate and match the 1C detection data; characteristic inflection points usually refer to significant change points in images or data, such as turning points of tracks, boundaries of signal equipment, etc.

[0059] Exemplarily, feature inflection points in a detection image of 1C detection data are compared with corresponding feature inflection points in an image of target template data, which may be turning points of a track, and the precise position of the detection image of 1C detection data in the image of target template data is determined. This process may be combined with image processing techniques and machine learning algorithms to improve the accuracy and robustness of the match.

[0060] The plurality of 1C detection data are aligned with each other in terms of pole numbers according to the precise matching data to obtain the 1C alignment data.

[0061] Exemplarily, the method of aligning pole numbers of multiple 1C detection data based on waveform alignment technology mainly uses the data alignment algorithm to take the target template data as the alignment target, and aligns and matches the previous 1C detection data with the target template data to achieve the purpose of data verification and positioning correction; establishes the target template data of the line based on the preferred 1C detection data, and roughly locates the detection data based on the image template matching method, so as to preliminarily locate the detection position in the image of the target template data, and then finds the optimal solution for image matching based on the longest matching subsequence search method, and roughly matches the 1C detection data with the target template data, and finally, based on the feature inflection point search method, accurately locates and matches the 1C detection data to achieve the data alignment effect.

[0062] Optionally, as attached Figure 2 As shown, the pole number alignment of the plurality of 2C detection data is performed based on the image intelligent recognition technology to obtain the 2C alignment data including:

[0063] Segmenting the 2C detection data to obtain a plurality of 2C picture data;

[0064] Exemplarily, the video data of the 2C detection data is divided into several pictures according to time intervals or key frames; each picture represents a moment in the video and contains all the information of the scene at that time; for example, the duration of the 2C detection data video is 1 minute and the frame rate is 30fps, then the video can be divided into 1800 pictures.

[0065] Using image intelligent recognition technology to identify the pole number of the 2C image data;

[0066] Exemplarily, the pole number information of each segmented image in the 2C image data is identified through an intelligent image recognition algorithm; the image recognition algorithm can be a convolutional neural network recognition, and the recognition process generally includes image preprocessing (such as denoising, contrast enhancement), feature extraction (such as edge detection, corner detection), character recognition and other steps.

[0067] The plurality of 2C detection data are aligned with the pole numbers according to the pole numbers of the 2C picture data to obtain the 2C aligned data.

[0068] Exemplarily, the identified pole number is matched with the existing 2C test data, and alignment of multiple 2C test data is achieved based on the uniqueness of the pole number; thereby facilitating the integration of 2C test data collected at different times, locations or with different test equipment to form a complete test record.

[0069] Optionally, as attached Figure 2 As shown, the pole number alignment of the plurality of 3C detection data is performed based on the image intelligent recognition technology to obtain the 3C alignment data, including:

[0070] Segmenting the 3C detection data to obtain a plurality of 3C picture data;

[0071] Exemplarily, the 3C detection data is divided into independent picture files according to time intervals, for example, one frame or multiple frames per second, to obtain 3C picture data; each picture represents a moment in the video and contains all the information of the scene at that time; for example, the length of the 3C detection data video is 1 minute and the frame rate is 40fps, then the video can be divided into 2400 pictures.

[0072] Using image intelligent recognition technology to identify the kilometer landmark information of the 3C image data;

[0073] Exemplarily, kilometer marker information is relevant information of a landmark used to identify a distance or location; using image intelligent recognition technology, such as a target detection algorithm (such as YOLO, Faster R-CNN, etc.), each picture is scanned to identify the kilometer markers and related information in the picture; for example, in the 3C picture data, the algorithm successfully identified the kilometer marker information of "K10+500", which means that the location is 10 kilometers and 500 meters away from the starting point.

[0074] Convert the kilometer mark information according to the basic data to obtain the pole number corresponding to the 3C image data;

[0075] Exemplarily, the kilometer landmark information and the basic information of each pole tower, such as the pole tower location, height, type and other information, can be combined to find the corresponding pole number by calculation or querying the database, thereby obtaining the pole number corresponding to the 3C image data; for example, it is known that there is a pole tower near "K10+500", and its record in the tower pole basic data is "pole number: 123, location: K10+490 to K10+510". By comparing the kilometer landmark information and the pole tower location range, it can be determined that the pole number corresponding to the kilometer landmark is 123.

[0076] The plurality of 3C detection data are aligned with each other in pole numbers according to the pole numbers of the 3C picture data to obtain the 3C aligned data.

[0077] Exemplarily, 3C image data with the same feature (here, the pole number) are sorted together to facilitate subsequent processing and analysis. For example, after processing all images, all images with the pole number 123 are filed into a folder named "Pole Number 123"; 3C detection data collected at different times, different devices or different angles are identified and segmented, and multiple 3C detection data can be correctly associated by comparing the pole number information in the collected 3C detection data; for example, a certain 3C detection data is collected, and after being processed by the above process, a picture group with the pole number 123 is obtained. By comparing the pole number information in the two groups of pictures (both are 123), the pole numbers of the two 3C detection data can be aligned.

[0078] Optionally, as attached Figure 2 As shown, the pole number alignment of the plurality of 4C detection data based on one pole one file data to obtain 4C alignment data includes:

[0079] Preprocessing the missing or misaligned bar data of the plurality of 4C detection data to obtain 4C correction data;

[0080] For example, for missing poles, the 4C inspection data can be compared to check whether the tower data is missing; for misaligned poles, the 4C inspection data can be analyzed to determine the tower number to which the data should be associated by comparing geographic location information, timestamps, data change trends of adjacent towers, and other methods; after preprocessing and correction by technical personnel, the system will receive an updated data set, namely the 4C correction data, in which each data point is accurately associated with the correct tower number.

[0081] The plurality of 4C detection data are aligned with the rod numbers according to the rod numbers of the 4C correction data to obtain the 4C alignment data.

[0082] For example, based on the corrected pole number, multiple 4C test data (which can be tests at different times and under different weather conditions) are aligned according to the pole tower number; so that each pole tower has a complete, chronologically arranged data set, which is convenient for subsequent analysis and comparison; on the basis of data alignment, the state change trend of each pole tower can be further analyzed, such as temperature changes, stress accumulation, etc., so as to timely discover potential safety hazards and provide a scientific basis for maintenance and inspection; for example, it is found that the data of the pole tower numbered 103 is missing (missing pole), and the data of the pole tower numbered 105 is mistakenly recorded under the pole tower numbered 104 (wrong pole), the technicians make corresponding corrections, and then align the corrected data according to the pole tower number, forming a complete and accurate data set for subsequent detailed analysis and maintenance decisions.

[0083] Optionally, the analyzing and processing the defects of the second detection data to obtain the associated data includes:

[0084] Performing a longitudinal analysis on the defects of the second detection data to obtain first correlation data;

[0085] Exemplarily, the system automatically superimposes and displays the two most recent historical waveform data by default, and identifies the areas where the conduction height, pull-out value, hard points, arcing, and contact force curves change significantly, to facilitate further assessment and confirmation of 1C defects, and to achieve longitudinal comparative analysis of 2C inspection data; the system queries 2C inspection data within 3 months by default, and two of the data can be manually selected for comparative analysis on the left and right screens to further assess and confirm 2C defects, and to achieve longitudinal comparative analysis of 4C inspection data; the system queries 4C inspection data within 12 months by default, and two of the data can be manually selected for comparative analysis on the left and right screens to further assess and confirm 4C defects.

[0086] Performing a horizontal analysis on the defects that cannot be confirmed by the second detection data to obtain second related information;

[0087] The associated data includes the first associated information and the second associated information.

[0088] Exemplarily, the system can quickly push the pole-to-pole information associated with this pillar position (pole number), the most recent defect information of other device types, the bow-net video, the defect data of this position within the past 12 months, drawings and materials, ledger information (flood control areas, tunnels, overpasses of power lines, fixed ice points, dirty areas, overpasses of bridges and culverts, limit gates, railway bridges, nearby construction ledgers, bird repellent devices, video devices, cable covers, electrified dedicated lines, 6C devices and high-speed rail limit locations), 1C detection data, 3C detection data, 2C detection data and 4C detection data, etc.; use threshold management, video assistance, repeated comparison, graphics, data association and fusion analysis and other methods to carry out local defect diagnosis and assessment of the contact network.

[0089] In summary, as attached Figure 3 As shown, the data uploaded by different detection devices are standardized and defined according to the requirements of the "Provisional Technical Conditions for the 6C System Integrated Data Processing Center" to obtain first detection data, which can be 1C detection data, 2C detection data, 3C detection data or 4C detection data; the 1C detection data, 2C detection data, 3C detection data or 4C detection data are subjected to pole number alignment processing to obtain second detection data; comparative analysis is performed based on the defects of the second detection module to obtain various information related to the defects and generate associated data; based on the associated data, the defects are finally confirmed with assistance.

[0090] Based on the same inventive concept, as attached Figure 4As shown, the present invention also provides a contact network equipment defect depth analysis system, the system comprising:

[0091] A data processing module, used to standardize and upload the data uploaded by the detection device according to requirements to obtain first detection data;

[0092] A rod number alignment module performs rod number alignment processing on the first detection data to obtain second detection data;

[0093] A defect analysis module, used for analyzing and processing defects of the second detection data to obtain related data;

[0094] The defect confirmation module is used to confirm the defect based on the associated data and generate defect description information.

[0095] Based on the above disclosed content, the present invention also provides an electronic device. Figure 5 As shown, the electronic device of an embodiment of the present invention includes at least one electrically connected processor and at least one storage medium, wherein the storage medium is electrically connected to the processor, wherein the storage medium stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the method as described above.

[0096] Based on the same inventive concept, the present invention also provides a storage medium, which stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to execute the method as described above.

[0097] It should be noted that the electrical connection between the above-mentioned units does not necessarily mean the connection between lines. An indirect connection method can be applied to the embodiments of the present invention as long as the purpose of the present invention is achieved.

[0098] The above is only an exemplary embodiment of the present invention and cannot be used to limit the scope of the present invention. That is, any equivalent changes and modifications made according to the teachings of the present invention are still within the scope of the present invention. After considering the disclosure of the specification and the truth of practice, it will be easy for those skilled in the art to think of other embodiments of the present invention. This application is intended to cover any variation, use or adaptive change of the present invention, which follows the general principles of the present invention and includes common knowledge or customary technical means in the technical field not recorded in the present invention.

Claims

1. A method for analyzing the defects of contact network equipment, characterized in that: The method comprises: The data uploaded by the detection device is standardized and defined as required to obtain first detection data; the first detection data includes 1C detection data, 2C detection data, 3C detection data and 4C detection data; Performing a rod number alignment process on the first detection data to obtain second detection data; Analyzing and processing defects of the second detection data to obtain associated data; The defect is confirmed based on the associated data, and defect description information is generated.

2. A method for analyzing defects in contact network equipment according to claim 1, characterized in that: The performing the rod number alignment process on the first detection data to obtain the second detection data comprises: Performing pole number alignment on the plurality of 1C detection data based on waveform alignment technology to obtain 1C alignment data; Performing pole number alignment on the plurality of 2C detection data based on image intelligent recognition technology to obtain 2C alignment data; Performing pole number alignment on the plurality of 3C detection data based on image intelligent recognition technology to obtain 3C alignment data; Performing pole number alignment on the plurality of 4C detection data based on one-pole-one-file data to obtain 4C alignment data; The second detection data includes the 1C alignment data, the 2C alignment data, the 3C alignment data and the 4C alignment data.

3. A method for analyzing the defects of a contact network device according to claim 2, characterized in that: The performing of pole number alignment on the plurality of 1C detection data based on the waveform alignment technology to obtain 1C alignment data comprises: Establish target template data according to preset requirements; Based on the image template matching method and the target template data, the IC detection data is roughly positioned to obtain positioning data; Based on the longest matching subsequence search method and the positioning data, the IC detection data is roughly matched to obtain rough matching data; Based on the characteristic inflection point search method, the rough matching data is accurately positioned and matched to obtain accurate matching data; The plurality of 1C detection data are aligned with each other in terms of pole numbers according to the precise matching data to obtain the 1C alignment data.

4. A method for analyzing the defects of a contact network equipment according to claim 2, characterized in that: The performing of pole number alignment on the plurality of 2C detection data based on the image intelligent recognition technology to obtain 2C alignment data comprises: Segmenting the 2C detection data to obtain a plurality of 2C picture data; Using image intelligent recognition technology to identify the pole number of the 2C image data; The plurality of 2C detection data are aligned with the pole numbers according to the pole numbers of the 2C picture data to obtain the 2C aligned data.

5. A method for analyzing the defects in depth of contact network equipment according to claim 2, characterized in that: The performing pole number alignment on the plurality of 3C detection data based on the image intelligent recognition technology to obtain 3C alignment data comprises: Segmenting the 3C detection data to obtain a plurality of 3C picture data; Using image intelligent recognition technology to identify the kilometer landmark information of the 3C image data; Convert the kilometer mark information according to the basic data to obtain the pole number corresponding to the 3C image data; The plurality of 3C detection data are aligned with each other in pole numbers according to the pole numbers of the 3C picture data to obtain the 3C aligned data.

6. A method for analyzing the defects of a contact network equipment according to claim 2, characterized in that: The performing pole number alignment on the plurality of 4C detection data based on one pole one file data to obtain 4C alignment data comprises: Preprocessing the missing or misaligned bar data of the plurality of 4C detection data to obtain 4C correction data; The plurality of 4C detection data are aligned with the rod numbers according to the rod numbers of the 4C correction data to obtain the 4C alignment data.

7. A method for analyzing the defects in depth of contact network equipment according to claim 1, characterized in that: The analyzing and processing the defects of the second detection data to obtain the associated data includes: Performing a longitudinal analysis on the defects of the second detection data to obtain first correlation data; Performing a horizontal analysis on the defects that cannot be confirmed by the second detection data to obtain second related information; The associated data includes the first associated information and the second associated information.

8. A contact network equipment defect depth analysis system, characterized in that: The system comprises: A data processing module, used to standardize and upload the data uploaded by the detection device according to requirements to obtain first detection data; A rod number alignment module, used for processing the first detection data, thereby achieving rod number alignment and obtaining second detection data; A defect analysis module, used for analyzing and processing defects of the second detection data to obtain related data; The defect confirmation module is used to confirm the defect based on the associated data and generate defect description information.

9. A computer storage medium, characterized in that One or more programs are stored, and when the one or more programs are executed, a method for in-depth analysis of defects in contact network equipment as described in any one of claims 1 to 7 can be implemented.

10. A device, characterized in that: The system comprises a processor, a communication interface, a memory and a communication bus; the memory stores at least one program in a computer storage medium as claimed in claim 9 which can be loaded and executed by the processor.

Images