Flaw detection system for rail transit stainless steel seamless tube

Abstract

The invention provides a flaw detection system for a rail transit stainless steel seamless tube, which comprises a detection device and a parameter acquisition module connected with the detection device, the parameter acquisition module is used for acquiring a stainless steel seamless tube to be detected and initial parameters; the automatic conveying module is used for carrying out conveying, speed adjustment, stop control and anomaly detection on the seamless steel pipe to be detected; the multi-modal detection module is used for carrying out steel pipe defect detection to obtain multi-source detection original data; the mode recognition and feature extraction module is used for analyzing multi-source detection original data to obtain a defect feature set; the judgment and execution module is used for carrying out abnormity judgment on the defect feature set and executing sorting and man-machine interaction; and the data management module is used for carrying out statistical analysis and quality tracing on the defect feature set to obtain an analysis report. According to the invention, rapid and accurate detection of internal and surface defects of the rail transit stainless steel seamless tube is realized, detection data are effectively managed and analyzed, and reliable guarantee is provided for safe operation of rail transit.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of non-destructive testing, in particular to a flaw detection system for rail transit stainless seamless pipe. BACKGROUND

[0002] In the field of rail transit, stainless seamless pipe is widely used in key parts such as brake system, air conditioning system and electrical line protection. The quality of the stainless seamless pipe directly affects the safe operation of rail transit. Once the stainless seamless pipe has internal defects such as cracks, pores and slag inclusions, these defects may gradually expand under long-term high pressure, vibration and complex environmental conditions, eventually leading to pipe rupture, leakage and other serious failures, thereby endangering the safety of train operation and passenger life and property.

[0003] Currently, common flaw detection methods for stainless seamless pipe include ultrasonic flaw detection, eddy current flaw detection, magnetic powder flaw detection, etc. However, the existing flaw detection technology and system have many shortcomings. For example, traditional ultrasonic flaw detection has low sensitivity when detecting small defects, and is prone to missed detection; eddy current flaw detection is not accurate enough in judging the depth and shape of defects, and it is difficult to provide comprehensive defect information; magnetic powder flaw detection is only suitable for surface and near-surface defect detection, and is powerless for internal deep defects.

[0004] In addition, the existing flaw detection system often has low automation degree and requires a large amount of manual operation, which not only has low detection efficiency, but also has a large impact of human factors on the detection results, making it difficult to ensure the accuracy and consistency of the detection. At the same time, the management and analysis of detection data are also relatively backward, and real-time monitoring, storage, analysis and quality tracing of detection data cannot be realized, which is not conducive to quality control and optimization of the production process. SUMMARY

[0005] In order to overcome the shortcomings of the prior art, the purpose of the present application is to provide a flaw detection system for rail transit stainless seamless pipe, which realizes rapid and accurate detection of internal and surface defects of rail transit stainless seamless pipe, and effectively manages and analyzes detection data, providing reliable protection for the safe operation of rail transit.

[0006] To achieve the above purpose, the present application provides the following solution: a flaw detection system for rail transit stainless seamless pipe, characterized in that it comprises a detection device and a: parameter acquisition module for acquiring a stainless seamless steel pipe to be detected and acquiring initial parameters; an automatic conveying module for conveying, speed adjustment, stop control and abnormality detection of the seamless steel pipe to be detected based on a conveying device and a positioning device; A multi-modal detection module is configured to detect defects of the steel pipe by means of bore imaging, eddy current testing and metal magnetic memory testing, and obtain multi-source detection raw data; A pattern recognition and feature extraction module is configured to analyze and integrate abnormal shadows, defect types, defect positions, defect degrees, defect attributes and severity based on the multi-source detection raw data, and obtain a defect feature set; A decision and execution module is configured to perform abnormality determination, sorting and human-computer interaction on the defect feature set by using an industrial computer or a programmable logic controller; A data management module is configured to build a detection database, perform statistical analysis and quality traceability on the defect feature set, and obtain an analysis report; The parameter acquisition module, the automatic conveying module, the multi-modal detection module, the pattern recognition and feature extraction module, the decision and execution module and the data management module are connected with each other.

[0007] Optionally, the detection device comprises a feeding area, a detection area arranged on one side of the feeding area, and a discharging area arranged on one side of the detection area. The detection area comprises a laser range finder connected with the feeding area, a first positioning and guiding assembly arranged on one side of the laser range finder, a magnetic memory testing unit arranged on one side of the first positioning and guiding assembly, a second positioning and guiding assembly arranged on one side of the magnetic memory testing unit, and a photoelectric sensor and a phased array arranged on one side of the second positioning and guiding assembly; wherein the positioning and guiding assembly is composed of a positioning device and a conveying device.

[0008] Optionally, the parameter acquisition module comprises: A parameter setting unit is configured to obtain a stainless steel seamless pipe to be detected, and input conveying positioning parameters and detection parameters on a human-computer interaction interface; wherein the conveying positioning parameters comprise start-stop threshold, speed curve and positioning accuracy, and the detection parameters comprise bore imaging scanning strategy, eddy current and probe distance, and metal magnetic memory scanning path and threshold; An equipment state confirmation unit is configured to perform equipment self-checking, initial state confirmation of the equipment and record basic information of the steel pipe, and output initial parameters.

[0009] Optionally, the automatic conveying module comprises: A start control unit is configured to send a workpiece presence signal by using a sensor at an entrance of the feeding area, and convey the stainless steel seamless pipe to be detected to the detection area at a preset initial speed; A speed adjusting unit is configured to determine whether the speed deviation of the stainless steel seamless pipe exceeds 5% by the position encoder and the displacement sensor, and if so, adjust the motor frequency of the conveying device, and determine whether the stainless steel seamless pipe deviates from the detection area by more than 0.5 mm, and if so, adjust the positioning motor of the positioning device. A stop control unit is configured to delay deceleration stop for 0.2-0.5 seconds after the tail end of the stainless steel seamless pipe leaves the sensor at the outlet of the unloading area, and monitor the speed of the stainless steel seamless pipe in real time, and if the speed is abnormal, trigger the emergency stop function and sound and light alarm.

[0010] Optionally, the conveying device is configured as a motor-driven conveying roller, and the positioning device is configured to monitor the position and posture of the steel pipe in real time by the photoelectric sensor and the position encoder to perform the steel pipe positioning and fixing operation.

[0011] Optionally, the multi-modal detection module comprises: A small hole imaging unit is configured to control the emission and receiving angle of the light source based on the photoelectric sensor and the phased array electronic scanning, form an optical image according to the straight-line propagation and defect shielding of the light, and determine whether there is a steel pipe defect through the optical image; An eddy current detection unit is configured to excite eddy current on the surface and near-surface of the stainless steel seamless pipe by using multi-frequency parallel alternating magnetic field, and determine whether there is a steel pipe defect through the change of the eddy current; A metal magnetic memory detection unit is configured to detect the stress concentration or early micro-defects of the steel pipe based on the magnetic memory effect under the geomagnetic field to locate the early damage of the steel pipe; A data processing unit is configured to acquire and integrate the detection signals of the small hole imaging unit, the eddy current detection unit and the metal magnetic memory detection unit by using a data acquisition card, and link the signal sampling frequency and the steel pipe conveying speed to obtain multi-source detection raw data; the multi-source detection raw data comprises optical image data, eddy current impedance data and magnetic memory leakage field data.

[0012] Optionally, the pattern recognition and feature extraction module comprises: An imaging processing unit is configured to compare the optical image and the standard defect-free image, identify abnormal shadows, and infer the defect type, defect position and defect degree according to the abnormal shadows; An eddy current processing unit is configured to perform waveform change analysis based on the eddy current impedance data to obtain a defect signal, filter and phase analyze the defect signal to exclude non-defect interference, and then perform abnormality judgment on the defect signal to obtain defect attributes; A magnetic memory processing unit is configured to perform curve anomaly analysis based on the magnetic memory leakage field data to locate zero points and gradient peaks, to obtain stress concentration or early defect position, and to evaluate defect or stress severity according to signal strength and gradient; A feature output unit is configured to integrate the abnormal shadow, the defect type, the defect position, the defect degree, the defect attribute and the severity to obtain a defect feature set.

[0013] Optionally, the determination and execution module comprises: An anomaly determination unit is configured to determine, based on an industrial computer or a programmable logic controller, whether the defect feature set exceeds a preset corresponding feature threshold, and if so, to trigger an audible and light alarm, and to record the defect type, position and severity to obtain record information; An execution sorting unit is configured to control the conveying speed and scanning rhythm synchronously through a conveying device to complete the determination and sorting of qualified and unqualified products; A human-computer interaction unit is configured to perform parameter setting, start-stop control, real-time display of detection results and running state, defect fault alarm and information pop-up through a human-computer interaction interface.

[0014] Optionally, the data management module comprises: A data storage unit is configured to adopt a distributed storage architecture to construct a detection database storing product and detection basic information, defect feature information, determination and execution results, and equipment and parameter information to obtain a structured data set; A statistical analysis unit is configured to perform statistical analysis, quality traceability and report output based on the defect feature set to obtain an analysis report including statistical report, trend chart and traceability chain.

[0015] Optionally, the statistical analysis unit comprises: An imaging statistical analysis subunit is configured to analyze shadow defect type proportion, defect size distribution and defect position concentration for the optical image data to identify macro defect high incidence law; An eddy current flaw detection statistical analysis subunit is configured to analyze defect signal amplitude distribution, defect phase angle distribution and different frequency detection rate comparison for the eddy current impedance data to optimize frequency parameters and quantify near-surface defect detection law and severity; A metal magnetic memory statistical analysis subunit is configured to analyze stress concentration area magnetic field parameter distribution and stress concentration and subsequent cracking correlation for the magnetic memory leakage field data to identify stress concentration and early damage risk law; A quality traceability subunit is configured to associate the identification results of the imaging statistical analysis subunit, the eddy current flaw detection statistical analysis subunit and the metal magnetic memory statistical analysis subunit to production information and detection history, to perform quality traceability, and to output an analysis report including statistical reports, trend charts and traceability chains.

[0016] The present application discloses the following technical effects by providing a flaw detection system for rail transportation stainless steel seamless pipes: 1. High detection accuracy: The multi-modal detection module combines ultrasonic flaw detection, eddy current flaw detection and magnetic memory flaw detection, achieving comprehensive and high-precision detection of internal and surface defects of stainless steel seamless pipes, effectively improving detection accuracy and reliability, and reducing the probability of missed detection and false detection.

[0017] 2. High automation: The automatic conveying and positioning module and the intelligent control system work together to realize full automation of the detection process, greatly reducing manual operation, improving detection efficiency and reducing the influence of human factors on detection results.

[0018] 3. Perfect data management: Data storage and management can comprehensively and systematically store and analyze detection data, providing rich data support for production process quality control and optimization, and helping to achieve quality traceability and continuous improvement.

[0019] 4. Strong adaptability: The method can adapt to the detection needs of different specifications and models of rail transportation stainless steel seamless pipes, and can be flexibly applied to various production scenarios by adjusting detection parameters and equipment configuration.

[0020] The technical solutions of the present application will be further described in detail below with the help of the accompanying drawings and examples. BRIEF DESCRIPTION OF DRAWINGS

[0021] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the accompanying drawings needed to be used in the embodiments will be briefly introduced. Obviously, the accompanying drawings in the following description are only some embodiments of the present application, and other accompanying drawings can be obtained by those skilled in the art without creative labor.

[0022] Figure 1 The system architecture diagram provided for the embodiments of the present application; Figure 2 The front view of the detection device provided for the embodiments of the present application; Figure 3 The top view of the detection device provided for the embodiments of the present application; Figure 4 The side view of the detection device provided for the embodiments of the present application; Figure 5 A perspective view of a detection device provided for an embodiment of the present application is shown in the figure; Figure 6 A perspective view of a detection area provided for an embodiment of the present application is shown in the figure; Figure 7 A front view of a detection area provided for an embodiment of the present application is shown in the figure; Figure 8 A side view of a detection area provided for an embodiment of the present application is shown in the figure; Figure 9 A top view of a detection area provided for an embodiment of the present application is shown in the figure; Figure 10 A schematic view of a human-computer interaction interface provided for an embodiment of the present application is shown in the figure; Marked as follows: 1, feeding area; 2, detection area; 21, laser range finder, 22a, first positioning guide assembly; 22b, second positioning guide assembly; 23, magnetic memory flaw detection unit; 24, photoelectric sensor; 25, phased array; 3, discharging area. DETAILED DESCRIPTION

[0023] The technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor fall within the scope of protection of the present application.

[0024] In order to make the above-mentioned purposes, features and advantages of the present application more obvious and easy to understand, the present application will be further described in detail below with reference to the drawings and specific embodiments.

[0025] As shown in the figure, Figure 1 The present application provides a flaw detection system for rail transit stainless steel seamless pipes, characterized in that it comprises a detection device and a parameter acquisition module, an automatic conveying module, a multi-modal detection module, a pattern recognition and feature extraction module, a judgment and execution module and a data management module connected with the detection device.

[0026] As shown in the figure, Figures 2-5 The detection device comprises a feeding area 1, a detection area 2 arranged on one side of the feeding area 1, and a discharging area 3 arranged on one side of the detection area 2.

[0027] As shown in the figure, Figures 6-9As shown, the detection area 2 includes a laser range finder 21 connected with the feeding area 1, a first positioning guide assembly 22a arranged on one side of the laser range finder 21, a magnetic memory flaw detection unit 23 arranged on one side of the first positioning guide assembly 22a, a second positioning guide assembly 22b arranged on one side of the magnetic memory flaw detection unit 23, and a photoelectric sensor 24 and a phased array 25 arranged on one side of the second positioning guide assembly 22b.

[0028] Wherein, the positioning guide assembly is composed of a positioning device and a conveying device: Conveying device: composed of a conveying roller driven by a motor, the conveying speed can be accurately adjusted according to the detection requirements. The conveying roller surface adopts special rubber material, which can not only ensure the stable conveying of stainless steel seamless pipe, but also avoid damaging the surface of the steel pipe.

[0029] Positioning device: a plurality of high-precision photoelectric sensors and position encoders are arranged on the conveying roller, which are used to monitor the position and attitude of the stainless steel seamless pipe in real time. When the steel pipe is conveyed to the detection position, the positioning device can quickly and accurately fix the steel pipe, ensuring the stability of the steel pipe during detection.

[0030] 1. Parameter acquisition module Used for acquiring the stainless steel seamless steel pipe to be detected and acquiring initial parameters. The parameter acquisition module includes: 1.1 Parameter setting unit Used for acquiring the stainless steel seamless steel pipe to be detected and inputting the conveying positioning parameters and detection parameters on the man-machine interaction interface; wherein, the conveying positioning parameters include start-stop threshold, speed curve and positioning accuracy, the detection parameters include small hole imaging scanning strategy, eddy current and probe distance, and metal magnetic memory scanning path and threshold, and the emission frequency of ultrasonic flaw detection can also be selected.

[0031] 1.2 Equipment state confirmation unit Used for equipment self-checking, equipment initial state confirmation and steel pipe basic information recording, and outputting initial parameters.

[0032] For example, the detection module is reset, the power system voltage / air pressure meets the standard, and the safety interlock is closed. Record the basic information such as steel pipe specifications, production batch, etc. for subsequent traceability.

[0033] 2. Automatic conveying module Used for conveying, speed adjustment, stop control and abnormal detection of the seamless steel pipe to be detected based on the conveying device and the positioning device. The automatic conveying module includes: 2.1 Start control unit The workpiece presence signal is sent by a sensor at the entrance of the feeding area, and the stainless steel seamless pipe to be detected is fed to the detection area at a preset initial speed, such as 0.5 m / s, for more than 50 ms, and the positioning deviation is less than or equal to ±1 mm.

[0034] 2.2 Speed adjustment unit The speed deviation of the stainless steel seamless pipe to be detected is judged by a position encoder and a displacement sensor. If the speed deviation exceeds 5%, the motor frequency of the feeding device is adjusted, and whether the stainless steel seamless pipe to be detected deviates from the detection area by more than 0.5 mm is judged. If yes, the positioning motor of the positioning device is adjusted.

[0035] The feeding device is a motor-driven feeding roller, and the roller surface is made of special rubber material to ensure smooth feeding without damaging the surface. The feeding speed can be accurately adjusted, such as a feeding speed of 0.1-3 m / s, a coarse positioning speed of 50-200 mm / s, and a fine positioning speed of 5-50 mm / s. The positioning accuracy is ±0.1 mm.

[0036] The positioning device monitors the position and posture of the steel pipe in real time through a photoelectric sensor and a position encoder to quickly fix the steel pipe after positioning and ensure the stability of detection.

[0037] 2.3 Stop control unit After the tail end of the stainless steel seamless pipe leaves the sensor at the exit of the discharging area, the speed is reduced and stopped after 0.2-0.5 seconds, and whether the speed of the stainless steel seamless pipe is abnormal (the defect amplitude is out of limit, and the speed deviation is greater than ±15%) is monitored in real time. If yes, the emergency stop function is triggered and an audible and visual alarm is sounded.

[0038] Cyclic operation: automatic reset after single piece to wait for the next entrance trigger, without manual intervention throughout the process.

[0039] 3. Multi-modal detection module The steel pipe defect detection is performed by means of small hole imaging, eddy current flaw detection, and metal magnetic memory flaw detection, and multi-source detection raw data is obtained. The multi-modal detection module comprises: 3.1 Small hole imaging unit The light source emission and receiving angle is controlled based on a photoelectric sensor and a phased array electronic scanning, and an optical image is formed according to the straight-line propagation of light and the defect shielding. Whether there is a steel pipe defect is judged by the optical image.

[0040] When there is no defect, the imaging surface is a uniform spot or a normal image matching the cross section; when there is a defect, a dark area (shadow) corresponding to the defect shape / position appears.

[0041] 3.2 Eddy current flaw detection unit The present application is used for exciting eddy current on the surface and near surface of the stainless steel seamless pipe by using multi-frequency parallel alternating magnetic field, and judging whether there is pipe defect by the change of the eddy current.

[0042] The defect changes the eddy current distribution and phase, resulting in abnormal coil impedance / induced voltage. Multi-frequency parallel is used to consider different depth and type defects, and facilitate quantitative analysis.

[0043] 3.3 Metal magnetic memory detection unit The present application is used for detecting stress concentration or early micro-defect of the pipe based on the magnetic memory effect under the geomagnetic field, so as to locate the early damage of the pipe.

[0044] Based on the "magnetic memory effect" of irreversible orientation of metal magnetic domain under the geomagnetic field; without pre-magnetization, the magnetic sensitive sensor scans the normal component of the leakage magnetic field along the surface. The abnormal mutation such as zero point and gradient peak at the stress concentration or defect can quickly locate the early damage.

[0045] 3.4 Data processing unit The present application is used for acquiring and integrating the detection signals of the small hole imaging unit, the eddy current detection unit and the metal magnetic memory detection unit by using the data acquisition card, and linking the signal sampling frequency and the pipe conveying speed to obtain multi-source detection raw data; the multi-source detection raw data includes optical image data, eddy current impedance data and magnetic memory leakage magnetic field data.

[0046] 4. Pattern recognition and feature extraction module The present application is used for analyzing and integrating abnormal shadow, defect type, defect position, defect degree, defect attribute and severity based on the multi-source detection raw data to obtain a defect feature set. The pattern recognition and feature extraction module includes: 4.1 Imaging processing unit The present application is used for comparing the optical image and the standard defect-free image, identifying abnormal shadow, and inferring the defect type, defect position and defect degree according to the abnormal shadow.

[0047] Finding abnormality: comparing the current collected detection image and the standard defect-free image (such as the cross-sectional image of the intact pipe, the uniform light spot diagram), finding the different dark area (shadow), which is probably formed by the defect blocking the light.

[0048] Identifying type: judging the defect type according to the shape of the shadow, if the shadow is a long strip, it may be a crack, linear defect; if the shadow is blocky / pointy, it may be impurities, pores and other blocky defects.

[0049] Positioning + Severity Assessment: Look at the coordinates of the shadow in the image to determine the specific location of the defect on the steel pipe, such as 10 cm from the left end and 30° in the circumferential direction. Look at the size of the shadow, such as 5 mm long and 1 mm wide, and the clarity, the clearer the shadow, the more prominent the defect. According to the industry standards, assess the severity of the defect.

[0050] 4.2 Eddy Current Processing Unit For waveform change analysis based on the eddy current impedance data, obtain the defect signal, filter and phase analysis on the defect signal to exclude non-defect interference, and then make abnormal judgment on the defect signal to obtain the defect attribute. That is, a comprehensive judgment is made in combination with amplitude (size / deepness), position (axial / circumferential), and waveform (crack peak, inclusion wide wave).

[0051] 4.3 Magnetic Memory Processing Unit For curve anomaly analysis based on the magnetic memory leakage field data, locate the zero point and gradient peak to obtain the stress concentration or early defect position, and evaluate the severity of the defect or stress according to the signal strength and gradient. That is, look at the signal strength of the curve mutation point (the higher the peak, the more concentrated the stress / the more obvious the defect) and the gradient change (the steeper the curve inflection, the more prominent the problem), and then evaluate the severity of the defect / stress according to the standard.

[0052] 4.4 Feature Output Unit For integrating the abnormal shadow, the defect type, the defect position, the defect degree, the defect attribute, and the severity to obtain a defect feature set.

[0053] 5. Judgment and Execution Module For using an industrial computer or a programmable logic controller to make abnormal judgment on the defect feature set, execute sorting, and human-computer interaction. The judgment and execution module includes: 5.1 Abnormal Judgment Unit For automatically controlling the start and stop of the conveyor, speed adjustment, and detection process based on the industrial computer or programmable logic controller according to the preset program. Determine whether the defect feature set exceeds the corresponding feature threshold value, if so, trigger the sound and light alarm, and record the defect type, position, and severity to obtain the record information.

[0054] 5.2 Execution Sorting Unit For synchronously controlling the conveying speed and scanning rhythm through the conveying device to complete the judgment and sorting of qualified and unqualified products.

[0055] 5.3 Human-Computer Interaction Unit For example Figure 10As shown, for parameter setting, start-stop control, real-time display of detection results and running state, defect fault alarm and information pop-up through human-computer interaction interface.

[0056] 1) One of the page display examples: "Short tube mode" "Detection station starting" "Automatic detection" "vivo Y78" "2025 / 08 / 08 17:29"; "6000 unloading area city" "1950 detection area city" "6000 loading area city" "8950"; "Seamless steel pipe surface detection device" "Seamless steel pipe surface detection device-detection area".

[0057] 2) The second example of page display: "Information display: automatic state" "Speed 0.69mm" "Current position 0mm" "Total length of detection 0mm"; "Laser marking mode" "Total number 68" "Short tube mode" "Clear"; "Number of unqualified products 3" "Pipe diameter 18mm" "Clear" "Automatic detection"; Menu: "Home / Feeding section / Detection section / Discharge section / Parameter setting / Information query"; "12 detection pages" "5 data storage and management modules"; Output: Form "execution and interface results" (sorting results, alarm records and visual information).

[0058] 6、Data management module For constructing a detection database, statistically analyzing and quality tracing the defect feature set, and obtaining an analysis report. The data management module comprises: 6.1 Data storage unit For constructing a detection database that stores product and detection basic information, defect feature information, judgment and execution results, and equipment and parameter information using a distributed storage architecture, and obtaining a structured data set.

[0059] 6.2 Statistical analysis unit For statistically analyzing, quality tracing and report output based on the defect feature set, and obtaining an analysis report including statistical report, trend chart and traceability chain. The statistical analysis unit comprises: 6.21 Imaging statistical analysis subunit For analyzing the proportion of shadow defect type, defect size distribution and defect position concentration for the optical image data, to identify the high incidence law of macroscopic defects, and guide raw material screening and forming process optimization.

[0060] Shadow defect type proportion: such as 30% of cracks and 50% of inclusions.

[0061] Defect size distribution: such as 80% of inclusion area <5 square millimeters.

[0062] Defect location concentration: such as wall thickness unevenness shadow is prone to occur at the tail of a large diameter steel pipe.

[0063] 6.22 Statistical analysis subunit of eddy current testing For the eddy current impedance data, the defect signal amplitude distribution, the defect phase angle distribution, and the comparison of detection rates at different frequencies are analyzed to optimize the frequency parameters, quantify the detection rules and severity of near-surface defects, and guide the grinding or rejection standards.

[0064] Defect signal amplitude distribution: such as 90% of crack signal amplitude >50 millivolts.

[0065] Defect phase angle distribution: such as surface layer defect phase angle concentrated in 20 to 40 degrees.

[0066] Comparison of detection rates at different frequencies: such as high frequency detection rate of surface cracks 95%, low frequency detection rate of near-surface inclusions 88%.

[0067] 6.23 Statistical analysis subunit of metal magnetic memory For the magnetic memory magnetic field data, the stress concentration area magnetic field parameter distribution and the correlation between stress concentration and subsequent cracking are analyzed to identify the stress concentration and early damage risk rules, evaluate the potential failure risk, and provide support for life prediction and maintenance cycle development.

[0068] Stress concentration area magnetic field parameter distribution: number of stress concentration area magnetic field zero points, gradient peak value distribution (such as 60% of the peak value concentrated in 30-50 A / m / mm), and classification according to service time / use environment (such as higher incidence of open air storage).

[0069] Correlation between stress concentration and subsequent cracking: such as tracking steel pipes with gradient peak value >60 A / m·mm and statistically analyzing the cracking probability in use.

[0070] 6.4 Quality traceability subunit For the identification results of the imaging statistical analysis subunit, the eddy current testing statistical analysis subunit, and the metal magnetic memory statistical analysis subunit, the production information and detection history are associated to perform quality traceability, and an analysis report including statistical reports, trend charts, and traceability chains is output.

[0071] In summary, the detection process of the present application is: Preparation before detection: First, according to the specifications of the rail transit stainless steel seamless pipe to be detected, set the corresponding detection parameters in the human-computer interaction interface of the intelligent control system, such as detection speed, ultrasonic wave emission frequency, eddy current detection frequency, etc. At the same time, check whether the connection of each module of the flaw detection system is normal, and whether the equipment is in the initial state.

[0072] Detection process: Place the stainless steel seamless pipe on the conveying roller of the automatic conveying and positioning module, and start the conveying device. The steel pipe is moved to the detection area under the drive of the conveying roller. When the steel pipe reaches the detection position, the positioning device quickly fixes the steel pipe according to the feedback signals of the photoelectric sensor and the position encoder. At this time, the multi-modal detection module starts to work, and the ultrasonic flaw detection unit, the eddy current flaw detection unit and the magnetic memory flaw detection unit simultaneously detect the steel pipe. During the detection process, the data acquisition and processing module collects the detection signals in real time and processes and analyzes them. The intelligent control system monitors and adjusts the entire detection process according to the preset program and parameters.

[0073] Detection result processing: After the detection is completed, the data acquisition and processing module transmits the analyzed defect information to the intelligent control system. The intelligent control system judges whether the steel pipe is qualified according to the type, position and size of the defect information. If the steel pipe is qualified, the conveying device will convey it to the qualified product area; if the steel pipe is unqualified, the intelligent control system will issue an alarm information through the human-computer interaction interface and display the detailed information of the defect. At the same time, the detection results and related data are stored in the database of the data storage and management module for subsequent query and analysis.

[0074] Data management and analysis: The operator can query and analyze the detection data at any time through the data analysis software of the data storage and management module. For example, generate a defect statistical report to understand the frequency and distribution of different types of defects; draw a quality trend chart to observe the change trend of product quality. Through in-depth analysis of the detection data, the production enterprise can timely find out the problems existing in the production process, take corresponding improvement measures, and improve the product quality.

[0075] Therefore, the present application provides a flaw detection system for rail transit stainless steel seamless pipe, which realizes rapid and accurate detection of internal and surface defects of rail transit stainless steel seamless pipe, and effectively manages and analyzes the detection data, providing reliable guarantee for the safe operation of rail transit.

[0076] The various embodiments in the specification are described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts of each embodiment can be referred to each other.

[0077] The principles and implementation manners of the present application are described by using specific examples in the present application, and the above examples are only used to help understand the method of the present application and its core idea; meanwhile, for the general technical personnel in the art, the specific implementation manners and application ranges will be changed according to the idea of the present application. In conclusion, the content of the present specification should not be understood as the limitation of the present application.

Claims

1. A flaw detection system for seamless stainless steel pipes used in rail transit, characterized in that, Includes a detection device and components connected to the detection device: The parameter acquisition module is used to acquire the stainless steel seamless pipe to be inspected and to obtain the initial parameters; An automatic conveying module is used for conveying, speed regulation, stop control, and anomaly detection of seamless steel pipes to be inspected, based on a conveying device and a positioning device. The multimodal detection module is used to detect defects in steel pipes through pinhole imaging, eddy current testing, and metal magnetic memory testing, and to obtain multi-source raw detection data. The pattern recognition and feature extraction module is used to analyze and integrate abnormal shadows, defect types, defect locations, defect degrees, defect attributes, and severity based on the multi-source detection raw data to obtain a defect feature set; The judgment and execution module is used to perform anomaly judgment, sorting, and human-machine interaction on the defect feature set using an industrial computer or programmable logic controller; The data management module is used to build a detection database, perform statistical analysis and quality traceability on the defect feature set, and obtain an analysis report; The parameter acquisition module, the automatic delivery module, the multimodal detection module, the pattern recognition and feature extraction module, the judgment and execution module, and the data management module are interconnected.

2. The flaw detection system for seamless stainless steel tubes in rail transit according to claim 1, characterized in that, The detection device includes a feeding area, a detection area disposed on one side of the feeding area, and a discharging area disposed on one side of the detection area; The detection area includes a laser rangefinder connected to the feeding area, a first positioning guide component disposed on one side of the laser rangefinder, a magnetic memory flaw detection unit disposed on one side of the first positioning guide component, a second positioning guide component disposed on one side of the magnetic memory flaw detection unit, and a photoelectric sensor and a phased array disposed on one side of the second positioning guide component; wherein, the positioning guide component consists of a positioning device and a conveying device.

3. The flaw detection system for seamless stainless steel tubes in rail transit according to claim 2, characterized in that, The parameter acquisition module includes: The parameter setting unit is used to acquire the stainless steel seamless pipe to be inspected and input the conveying positioning parameters and detection parameters on the human-machine interface; wherein, the conveying positioning parameters include start and stop threshold, speed curve and positioning accuracy, and the detection parameters include pinhole imaging scanning strategy, eddy current and probe distance, and metal magnetic memory scanning path and threshold. The equipment status confirmation unit is used to perform equipment self-inspection, confirm the initial status of the equipment, record the basic information of the steel pipe, and output the initial parameters.

4. The flaw detection system for seamless stainless steel tubes in rail transit according to claim 3, characterized in that, The automatic conveying module includes: The start control unit is used to send a workpiece presence signal using the sensor at the entrance of the loading area, and to transport the stainless steel seamless pipe to be tested to the testing area at a preset initial speed. The speed adjustment unit is used to determine whether the speed deviation of the stainless steel seamless steel pipe to be tested exceeds 5% by using a position encoder and a displacement sensor. If so, the motor frequency of the conveying device is adjusted. The unit also determines whether the stainless steel seamless steel pipe to be tested deviates from the detection area by more than 0.5 mm. If so, the positioning motor of the positioning device is adjusted. The stop control unit is used to decelerate and stop the machine 0.2-0.5 seconds after the stainless steel seamless steel pipe leaves the sensor at the outlet of the unloading area, and to monitor in real time whether the stainless steel seamless steel pipe has an abnormal speed. If so, the emergency stop function is triggered and an audible and visual alarm is triggered.

5. A flaw detection system for seamless stainless steel tubes in rail transit according to claim 4, characterized in that, The conveying device is configured as a motor-driven conveying roller conveyor, and the positioning device monitors the position and attitude of the steel pipe in real time through photoelectric sensors and position encoders to perform the steel pipe positioning and fixing operation.

6. A flaw detection system for seamless stainless steel tubes in rail transit according to claim 5, characterized in that, The multimodal detection module includes: The pinhole imaging unit is used to control the emission and reception angles of the light source based on photoelectric sensors and phased array electronic scanning, and to form an optical image based on the rectilinear propagation of light and defect occlusion, and to determine whether there is a defect in the steel pipe through the optical image. Eddy current testing unit is used to generate eddy currents on the surface and near the surface of the stainless steel seamless pipe using a multi-frequency parallel alternating magnetic field, and to determine whether there are defects in the pipe by the changes in the eddy currents. The metal magnetic memory flaw detection unit is used to detect stress concentration or early micro-defects in steel pipes based on the magnetic memory effect under the geomagnetic field, so as to locate early damage to the steel pipes. The data processing unit is used to acquire and integrate the detection signals of the pinhole imaging unit, the eddy current flaw detection unit, and the metal magnetic memory flaw detection unit using a data acquisition card, and to link the signal sampling frequency and the steel pipe conveying speed to obtain multi-source detection raw data; the multi-source detection raw data includes optical image data, eddy current impedance data, and magnetic memory leakage field data.

7. A flaw detection system for seamless stainless steel tubes in rail transit according to claim 6, characterized in that, The pattern recognition and feature extraction module includes: An imaging processing unit is used to compare optical images with standard defect-free images, identify abnormal shadows, and infer the defect type, defect location, and defect severity based on the abnormal shadows. The eddy current processing unit is used to perform waveform change analysis based on the eddy current impedance data to obtain the defect signal, filter and perform phase analysis on the defect signal to eliminate non-defect interference, and then perform anomaly judgment on the defect signal to obtain the defect attribute. The magnetic memory processing unit is used to perform curve anomaly analysis based on the magnetic memory leakage field data to locate the zero point and gradient peak, obtain the location of stress concentration or early defects, and assess the severity of defects or stress based on signal strength and gradient. The feature output unit is used to integrate the abnormal shadow, the defect type, the defect location, the defect degree, the defect attribute, and the severity to obtain a defect feature set.

8. A flaw detection system for seamless stainless steel tubes in rail transit according to claim 7, characterized in that, The determination and execution module includes: An anomaly determination unit is used to determine, based on an industrial computer or programmable logic controller, whether the set of defect features exceeds a preset corresponding feature threshold. If so, an audible and visual alarm is triggered, and the defect type, location, and severity are recorded to obtain the recorded information. The sorting unit is used to synchronously control the conveying speed and scanning rhythm through the conveying device to complete the judgment and sorting of qualified and unqualified items; The human-machine interaction unit is used to set parameters, control start and stop, display test results and operating status in real time, alarm for defects and faults, and display information pop-ups through the human-machine interaction interface.

9. A flaw detection system for seamless stainless steel tubes in rail transit according to claim 8, characterized in that, The data management module includes: The data storage unit is used to construct a detection database that uses a distributed storage architecture to store basic product and detection information, defect feature information, judgment and execution results, and equipment and parameter information, thereby obtaining a structured dataset. The statistical analysis unit is used to perform statistical analysis, quality traceability, and report output based on the defect feature set, and to obtain an analysis report including statistical reports, trend charts, and traceability chains.

10. A flaw detection system for seamless stainless steel tubes in rail transit according to claim 9, characterized in that, The statistical analysis unit includes: The imaging statistical analysis subunit is used to analyze the proportion of shadow defect types, defect size distribution, and defect location concentration of the optical image data in order to identify the high incidence pattern of macroscopic defects. The eddy current testing statistical analysis subunit is used to analyze the defect signal amplitude distribution, defect phase angle distribution, and detection rate comparison at different frequencies based on the eddy current impedance data, so as to optimize frequency parameters and quantify the detection pattern and severity of near-surface defects. The metal magnetic memory statistical analysis subunit is used to analyze the distribution of magnetic field parameters in the stress concentration area and the correlation between stress concentration and subsequent cracking based on the magnetic memory leakage magnetic field data, so as to identify the pattern of stress concentration and early damage risk. The quality traceability subunit is used to associate the identification results of the imaging statistical analysis subunit, the eddy current flaw detection statistical analysis subunit, and the metal magnetic memory statistical analysis subunit with production information and inspection history to perform quality traceability and output an analysis report including statistical reports, trend charts, and traceability chains.

Images