Intelligent groove identification system for welding box type steel component

Abstract

The invention discloses an intelligent groove recognition system for box type steel member welding, relates to the technical field of groove recognition, and solves the technical problems that existing groove recognition for steel member welding has a blind area, is easily influenced by noise signals and is not high in recognition accuracy. Comprising the steps that in the groove machining process, a groove detection module is used for conducting magnetic powder or permeation nondestructive testing on a groove through an ultrasonic probe, and after the groove is detected to be qualified, size information of the groove is collected through the ultrasonic probe; the controller is used for comparing the size information with standard size information and constraint conditions stored in a database; if the comparison is consistent, generating a size qualified signal; when a size qualification signal is received, the camera module is triggered to collect image information of the groove, and the collected image information is transmitted to the defect recognition module for defect recognition; and the defect identification module is used for carrying out filtering gain adjustment on the preprocessed image information to reduce the signal-to-noise ratio, so that the accuracy of groove defect identification is improved.

Description

Technical Field

[0001] The invention relates to the technical field of groove recognition, in particular to an intelligent groove recognition system for welding box-type steel components. Background Art

[0002] Usually, when processing steel component products, the entire circumference of the steel pipe end is grooved on the outer surface. When constructing the pipeline, the steel pipes are first assembled and then butt-welded, that is, two steel pipes are butt-welded through the groove. The grooves used for welding steel components generally have very high requirements. Ultrasonic inspection, magnetic particle inspection, and penetration inspection are required during manufacturing. At the same time, due to factors such as equipment, environment, and human errors, there will be defects such as deformation, scratches, and fractures in the production of grooves that affect product performance;

[0003] Since the existing steel component welding groove wall thickness structure is irregular, the ultrasonic probe cannot fully contact the groove surface, resulting in a blind spot; and the current computer vision detection technology, when affected by noise signals, is prone to image blur, affecting the accuracy of groove recognition; based on the above shortcomings, the present invention proposes an intelligent groove recognition system for box-type steel component welding. Summary of the invention

[0004] The present invention aims to solve at least one of the technical problems existing in the prior art; to this end, the present invention proposes an intelligent groove recognition system for welding box-type steel components.

[0005] To achieve the above-mentioned object, the first aspect of the present invention provides a box-type steel member welding groove intelligent recognition system, comprising a model training module, a groove detection module, a controller, a database, a camera module and a defect recognition module;

[0006] The model training module is used to collect defective product images as sample training sets, train the LSTM neural network model, and obtain a defect recognition model M; wherein the defective product images are characterized by the presence of deformation, scratches, stains, fractures, and broken edges;

[0007] During the groove processing, the groove detection module is used to use an ultrasonic probe to perform magnetic powder or penetration nondestructive testing on the groove. After the test is qualified, the size information of the groove is collected through the ultrasonic probe;

[0008] The grooves include a first upper groove and a second upper groove arranged along the outer wall of the upper semicircle of the steel member pipe mouth, and a first lower groove and a second lower groove arranged along the outer wall of the lower semicircle of the steel member pipe mouth;

[0009] The groove detection module is used to upload the collected groove size information to the controller;

[0010] The controller is used to compare the size information with the standard size information and constraint conditions stored in the database; if the comparison is consistent, a size qualified signal is generated; otherwise, a size unqualified signal is generated;

[0011] When a size qualified signal is received, the camera module is triggered to collect image information of the groove, and the collected image information is transmitted to the defect recognition module for recognition;

[0012] The specific identification steps of the defect identification module are as follows:

[0013] Preprocess the received image information; adjust the filter gain of the preprocessed image information to reduce the signal-to-noise ratio and reduce image noise;

[0014] The adjusted image information is substituted into the defect recognition model M for groove defect recognition; when a defect is recognized, a defect signal and corresponding detection data are generated; the defect recognition module is used to send the defect signal and the corresponding detection data to the controller for display and storage.

[0015] Furthermore, the filter gain is adjusted for the preprocessed image information, specifically including:

[0016] Convert the preprocessed image information into digital signals and filter the converted digital signals; the preprocessing includes sharpening, mathematical morphological transformation, binarization, edge extraction, and contour extraction;

[0017] Collect the periodic energy value of the corresponding digital signal according to the preset interval and mark it as KEi, and compare the periodic energy value KEi with the preset energy threshold; the preset energy threshold includes A1 and A2; wherein A1<A2;

[0018] When the periodic energy value KEi≤A1, let the energy deviation value KLi=A1-KEi;

[0019] When A1<periodic energy value KEi<A2, set the energy deviation value KLi=0;

[0020] When the periodic energy value KEi≥A2, let the energy deviation value KLi=KEi-A2;

[0021] In a preset time period, the energy deviation value KLi is integrated with respect to time to obtain a deviation reference index KZ; the deviation reference index KZ is compared with a preset reference threshold;

[0022] If the deviation from the reference index KZ is greater than a preset reference threshold, a regulation signal is generated;

[0023] When the adjustment signal is received, the gain of the digital signal is adjusted by controlling the programmable gain amplifier circuit, so that the periodic energy value of the digital signal is adjusted to between the preset energy thresholds A1 and A2.

[0024] Furthermore, the specific detection steps of the groove detection module are as follows:

[0025] During rough machining of steel components, allowances are left at the groove position; ultrasonic probes are used to inspect from the upper end face and side faces, with the ultrasonic probes completely in contact with the surface of the steel components during inspection;

[0026] Process the groove of the steel component to the state before welding, and cut off the remaining excess part at the groove position; perform magnetic particle or penetrant non-destructive testing at the groove position.

[0027] Furthermore, the dimensional information includes the angle between the first upward slope and the outer surface of the steel component, the angle between the second upward slope and the outer surface of the steel component, the angle between the first downward slope and the outer surface of the steel component, the angle between the second downward slope and the outer surface of the steel component, the length of the first upward slope, the length of the second upward slope, the length of the first downward slope and the length of the second downward slope.

[0028] Furthermore, the constraint conditions include: the angle between the first upslope and the outer surface of the steel component is smaller than the angle between the second upslope and the outer surface of the steel component; the angle between the first downslope and the outer surface of the steel component is smaller than the angle between the second downslope and the outer surface of the steel component; the length of the first upslope is greater than the length of the second upslope; the length of the first downslope is greater than the length of the second downslope.

[0029] Furthermore, the periodic energy value refers to a value obtained by accumulating and averaging the energy of a plurality of consecutive bits of received data.

[0030] Compared with the prior art, the present invention has the following beneficial effects:

[0031] In the present invention, during the groove processing process, the groove detection module is used to use an ultrasonic probe to perform magnetic powder or penetration non-destructive testing on the groove, thereby reducing the repair of the groove after welding and effectively reducing the manufacturing cost; after the detection is qualified, the size information of the groove is collected by the ultrasonic probe; the controller is used to compare the size information with the standard size information and constraint conditions stored in the database; if the comparison is consistent, a size qualification signal is generated; when the size qualification signal is received, the camera module is triggered to collect image information of the groove, and the collected image information is transmitted to the defect recognition module for recognition; the defect recognition module pre-processes the received image information; the filter gain of the pre-processed image information is adjusted to reduce the signal-to-noise ratio and reduce image noise, thereby improving the accuracy of groove defect recognition. BRIEF DESCRIPTION OF THE DRAWINGS

[0032] 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 only 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.

[0033] Figure 1 The present invention is a system block diagram of an intelligent groove recognition system for welding box-type steel components.

[0034] Figure 2 It is a schematic structural diagram of the groove for welding of box-shaped steel members in the present invention. DETAILED DESCRIPTION

[0035] The technical solution of the present invention will be clearly and completely described below in conjunction with the embodiments. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than 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.

[0036] See also Figure 1 to Figure 2 , the first aspect of the present invention provides a box-type steel member welding groove intelligent recognition system, including a model training module, a groove detection module, a controller, a database, a camera module and a defect recognition module;

[0037] The model training module is used to collect defective product images as sample training sets, train the LSTM neural network model, and obtain the defect recognition model M; wherein the defective product images show defects such as deformation, scratches, stains, fractures, and broken edges;

[0038] During the groove processing, the groove detection module is used to use an ultrasonic probe to perform magnetic powder or penetration non-destructive testing on the groove. The specific steps are as follows:

[0039] During rough machining of steel components, allowances are left at the groove position; ultrasonic probes are used to inspect from the upper end face and side faces, with the ultrasonic probes completely in contact with the surface of the steel components during inspection;

[0040] Process the groove of the steel component to the state before welding, and cut off the remaining part at the groove position;

[0041] Conduct magnetic particle or penetrant nondestructive testing at the groove position; avoid missed inspections due to poor contact of ultrasonic probes caused by irregular structures; reduce repairs after groove welding, effectively reducing manufacturing costs;

[0042] After the test is qualified, the size information of the groove is collected through the ultrasonic probe;

[0043] like Figure 2 As shown, the groove for welding the box-shaped steel member includes a first upper groove and a second upper groove arranged along the outer wall of the upper semicircle of the pipe mouth of the steel member, and a first lower groove and a second lower groove arranged along the outer wall of the lower semicircle of the pipe mouth of the steel member;

[0044] Therefore, the collected dimensional information includes the angle between the first upper bevel and the outer surface of the steel member, the angle between the second upper bevel and the outer surface of the steel member, the angle between the first lower bevel and the outer surface of the steel member, the angle between the second lower bevel and the outer surface of the steel member, the length of the first upper bevel, the length of the second upper bevel, the length of the first lower bevel and the length of the second lower bevel;

[0045] The groove detection module is used to upload the collected groove size information to the controller; the controller is used to compare the size information with the standard size information and constraint conditions stored in the database; if the comparison is consistent, a size qualified signal is generated; otherwise, a size unqualified signal is generated;

[0046] In this embodiment, the constraint conditions include: the angle between the first upslope and the outer surface of the steel member is smaller than the angle between the second upslope and the outer surface of the steel member; the angle between the first downslope and the outer surface of the steel member is smaller than the angle between the second downslope and the outer surface of the steel member; the length of the first upslope is greater than the length of the second upslope; the length of the first downslope is greater than the length of the second downslope;

[0047] In this embodiment, when a size qualified signal is received, the camera module is triggered to collect image information of the groove, and the collected image information is transmitted to the defect recognition module for recognition;

[0048] The specific identification steps of the defect identification module are as follows:

[0049] Preprocess the received image information; the preprocessing includes sharpening, mathematical morphological transformation, binarization, edge extraction, and contour extraction;

[0050] The filter gain of the pre-processed image information is adjusted to reduce the signal-to-noise ratio and image noise, thereby improving the accuracy of groove defect recognition; specifically including:

[0051] Convert the preprocessed image information into digital signals, and filter the converted digital signals;

[0052] The periodic energy value of the corresponding digital signal is collected according to the preset interval and marked as KEi. The periodic energy value refers to the value obtained by accumulating and averaging the energy of multiple consecutive bits of received data;

[0053] Compare the periodic energy value KEi with a preset energy threshold; the preset energy threshold includes A1 and A2; wherein A1<A2; when the periodic energy value KEi≤A1, set the energy deviation value KLi=A1-KEi;

[0054] When A1<periodic energy value KEi<A2, set the energy deviation value KLi=0;

[0055] When the periodic energy value KEi≥A2, let the energy deviation value KLi=KEi-A2;

[0056] In a preset time period, the energy deviation value KLi is integrated with respect to time to obtain a deviation reference index KZ; the deviation reference index KZ is compared with a preset reference threshold;

[0057] If the deviation from the reference index KZ is greater than a preset reference threshold, a regulation signal is generated;

[0058] When receiving the adjustment signal, the gain of the digital signal is adjusted by controlling the programmable gain amplifier circuit to adjust the periodic energy value of the digital signal to between the preset energy thresholds A1 and A2;

[0059] The adjusted image information is substituted into the defect recognition model M for groove defect recognition; when a defect is recognized, a defect signal and corresponding detection data are generated; the defect recognition module is used to send the defect signal and the corresponding detection data to the controller for display and storage.

[0060] In the description of this specification, the description with reference to the terms "one embodiment", "example", "specific example", etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representation of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described can be combined in any one or more embodiments or examples in a suitable manner.

[0061] The preferred embodiments of the present invention disclosed above are only used to help explain the present invention. The preferred embodiments do not describe all the details in detail, nor do they limit the invention to only specific implementation methods. Obviously, many modifications and changes can be made according to the content of this specification. This specification selects and specifically describes these embodiments in order to better explain the principles and practical applications of the present invention, so that those skilled in the art can understand and use the present invention well. The present invention is limited only by the claims and their full scope and equivalents.

Claims

1. An intelligent groove recognition system for welding box-type steel components, characterized in that: It includes model training module, groove detection module, controller, database, camera module and defect recognition module; The model training module is used to collect defective product images as sample training sets, train the LSTM neural network model, and obtain a defect recognition model M; wherein the defective product images are characterized by the presence of deformation, scratches, stains, fractures, and broken edges; During the groove processing, the groove detection module is used to use an ultrasonic probe to perform magnetic powder or penetration nondestructive testing on the groove. After the test is qualified, the size information of the groove is collected through the ultrasonic probe; The grooves include a first upper groove and a second upper groove arranged along the outer wall of the upper semicircle of the steel member pipe mouth, and a first lower groove and a second lower groove arranged along the outer wall of the lower semicircle of the steel member pipe mouth; The groove detection module is used to upload the collected groove size information to the controller; The controller is used to compare the size information with the standard size information and constraint conditions stored in the database; if the comparison is consistent, a size qualified signal is generated; otherwise, a size unqualified signal is generated; When a size qualified signal is received, the camera module is triggered to collect image information of the groove, and the collected image information is transmitted to the defect recognition module for recognition; The specific identification steps of the defect identification module are as follows: Preprocess the received image information; adjust the filter gain of the preprocessed image information to reduce the signal-to-noise ratio and reduce image noise; The adjusted image information is substituted into the defect recognition model M for groove defect recognition; when a defect is recognized, a defect signal and corresponding detection data are generated; the defect recognition module is used to send the defect signal and the corresponding detection data to the controller for display and storage.

2. The intelligent groove identification system for welding of box-shaped steel members according to claim 1 is characterized in that: The filter gain is adjusted for the preprocessed image information, specifically including: Convert the preprocessed image information into digital signals and filter the converted digital signals; the preprocessing includes sharpening, mathematical morphological transformation, binarization, edge extraction, and contour extraction; Collect the periodic energy value of the corresponding digital signal according to the preset interval and mark it as KEi, and compare the periodic energy value KEi with the preset energy threshold; the preset energy threshold includes A1 and A2; wherein A1<A2; When the periodic energy value KEi≤A1, let the energy deviation value KLi=A1-KEi; When A1<periodic energy value KEi<A2, set the energy deviation value KLi=0; When the periodic energy value KEi≥A2, let the energy deviation value KLi=KEi-A2; In a preset time period, the energy deviation value KLi is integrated with respect to time to obtain a deviation reference index KZ; the deviation reference index KZ is compared with a preset reference threshold; If the deviation from the reference index KZ is greater than a preset reference threshold, a regulation signal is generated; When the adjustment signal is received, the gain of the digital signal is adjusted by controlling the programmable gain amplifier circuit, so that the periodic energy value of the digital signal is adjusted to between the preset energy thresholds A1 and A2.

3. The intelligent groove identification system for welding box-shaped steel members according to claim 1 is characterized in that: The specific detection steps of the groove detection module are as follows: During rough machining of steel components, allowances are left at the groove position; ultrasonic probes are used to inspect from the upper end face and side faces, with the ultrasonic probes completely in contact with the surface of the steel components during inspection; Process the groove of the steel component to the state before welding, and cut off the remaining excess part at the groove position; perform magnetic particle or penetrant non-destructive testing at the groove position.

4. The intelligent groove identification system for welding of box-shaped steel members according to claim 1 is characterized in that: The dimensional information includes the angle between the first upward slope and the outer surface of the steel component, the angle between the second upward slope and the outer surface of the steel component, the angle between the first downward slope and the outer surface of the steel component, the angle between the second downward slope and the outer surface of the steel component, the length of the first upward slope, the length of the second upward slope, the length of the first downward slope and the length of the second downward slope.

5. The intelligent groove identification system for welding box-shaped steel members according to claim 4 is characterized in that: The constraint conditions include: the angle between the first upslope and the outer surface of the steel member is smaller than the angle between the second upslope and the outer surface of the steel member; the angle between the first downslope and the outer surface of the steel member is smaller than the angle between the second downslope and the outer surface of the steel member; the length of the first upslope is greater than the length of the second upslope; the length of the first downslope is greater than the length of the second downslope.

6. The intelligent groove identification system for welding box-shaped steel members according to claim 2 is characterized in that: The periodic energy value refers to a value obtained by accumulating and averaging the energy of a plurality of consecutive bits of received data.

Images