Method for learning to recognize a conforming weld bead

Abstract

Method for learning to recognize a conforming weld deposited along a weld path, the method being implemented by means of a welding installation comprising: - a welding head movable along the weld path and capable of depositing a weld bead in the weld path, - means for acquiring at least one data influencing at least one characteristic of the weld bead, - at least one means for measuring the position of the welding head, - a computer unit in which is implemented at least one computer program, capable of receiving and storing the at least one data acquired and associated with the measured position of the welding head.

Description

Title of the invention: Method for learning to recognize a conforming weld bead Technical field of the invention

[0001] The invention relates to the field of welding. In particular, the invention relates to the field of recognizing a conforming weld deposited along a weld path. Technical background

[0002] Tube welding, buttering or additive manufacturing are operations that can be carried out automatically using a welding head.

[0003] A weld path can, for example, be formed at a junction between two joined tubes or directly on a specific surface, such as at least part of an edge of a workpiece for the purpose of buttering. This weld path, circular or flat, is filled with molten metal.

[0004] In the case where it is desired to weld two tubes together, this filling is carried out in several passes, each pass corresponding to a 360° rotation around the components, for example metallic, of the welding electrode.

[0005] Each pass deposits molten metal corresponding to at least one weld bead. Thus, each pass deposits the weld beads and layers them one on top of the other.

[0006] When all the passes have been completed and the weld path is filled, the weld is finished.

[0007] Welds intended for certain sectors, such as nuclear or hydrocarbon transport, must comply with strict specifications.

[0008] As things stand, the weld is analyzed by non-destructive or destructive testing to detect any defects once the weld has been completed, i.e. when all the passes have been carried out and the weld path has been filled.

[0009] When a defect is detected, that is, when at least one bead constituting the weld is considered non-compliant, it is currently necessary to remove it and redo it. This corrective operation may require grinding the weld to a thickness corresponding to the location of the defect, and then making several passes to refill the weld path.

[0010] These correction operations are tedious and weigh down production.

[0011] There is therefore a need to optimize these correction operations and to be able to establish the conformity of each weld bead deposited after each pass before the weld is completed.

[0012] The invention thus aims to ensure the conformity of the weld bead deposited after each pass. Summary of the invention

[0013] To this end, a method for learning to recognize a conforming weld deposited along a weld path is proposed firstly, the method being implemented by means of a welding installation comprising: - a welding head that moves along the welding path and is capable of depositing a weld bead in the welding path, - means of acquiring at least one piece of data influencing at least one characteristic of the weld bead, - at least one means of measuring the position of the welding head, - a computer unit in which at least one computer program is implemented, capable of receiving and storing at least one piece of data acquired and associated with the measured position of the welding head, said process comprising: - an operation to move the welding head along the welding path, - an operation to deposit a weld bead in the weld path, - an operation to acquire at least one piece of data influencing at least one characteristic of the weld bead, this acquisition operation being carried out simultaneously with the operation of depositing a weld bead, - an operation to measure the position of the welding head, this measurement operation being carried out simultaneously with the operation of acquiring at least one data point, - an operation to store the acquired data associated with the measured positions of the welding head in the computer unit, the aforementioned steps being repeated so as to deposit several weld beads, the set of weld beads deposited corresponding to one weld, the process also including: - a weld inspection operation,

[0014] - a controlled weld evaluation operation so as to establish a weld conforms, Once the conforming weld has been established, the process further includes:

[0015] - an operation of inserting the acquired data into the computer unit and associated with the measured positions of the welding head representative of each weld bead deposited,

[0016] the learning process being characterized in that the preceding steps are repeated to deposit several conforming welds and to constitute a set of representative data of conforming welds, and in that it further includes a calibration operation of at least one computer program with the representative data set of conforming welds inserted into the computer unit to obtain a calibrated computer program, the calibrated computer program being configured to recognize a conforming weld.

[0017] A compliant weld is defined as a weld that meets predetermined criteria. For example, predetermined criteria may be defined by specifications or by one or more specific standards. Examples of predetermined criteria include the absence of certain defects such as spherical blowholes, blowhole pockets, aligned blowholes, metallic inclusions, joint defects, fusion gaps, bond gaps, and weld bead thicknesses that are too thin or too thick compared to a reference value.

[0018] By welding head, we mean a consumable electrode or a refractory electrode used with or without welding wire. For example, the welding head can be connected to a welding generator, which is conventionally a power supply generator.

[0019] It should be noted that at least one data influencing at least one characteristic of the weld bead can take the form of one or more values ​​that may be intrinsic to the elements implemented for the deposition of the weld bead and / or be representative of one or more measured, programmed and / or calculated parameters, and / or related to the environment.

[0020] For example, characteristics of the weld bead include its thickness, surface condition, volume, position in the weld path, mechanical properties or chemical composition.

[0021] It should be noted that the learning process does not include a step of inserting, into the computer unit, data representative of non-conforming welds, for example welds including a weld bead containing a defect.

[0022] Various additional features may be provided alone or in combination: - at least one piece of data is the voltage and / or current delivered by a welding generator connected to the welding head; - at least one piece of data is the speed of movement of the welding head; - at least one piece of data is the ambient temperature; - at least one piece of data is ambient humidity; - at least one piece of data is the wind speed; - at least one piece of data is the temperature of the weld bead; - at least one piece of data is the volumetric or mass flow rate of a protective gas designed to prevent the oxidation of molten metal by oxygen from the air; - at least one piece of data is the pressure of a protective gas intended to prevent the oxidation of the molten metal by oxygen from the air; - at least one piece of data is the temperature of a protective gas intended to prevent the oxidation of the molten metal by oxygen from the air; - at least one piece of data is the profile of the weld bead and / or the profile of the adjacent areas.

[0023] Secondly, an automated method for recognizing a conforming weld bead deposited or being deposited along a welding path is proposed, this method using the lessons learned from a prior learning method as previously described, the automated recognition method being implemented by means of a welding installation comprising: - a welding head that moves along the welding path and is capable of depositing a weld bead in the welding path, - means of acquiring at least one piece of data influencing at least one characteristic of the weld bead, - at least one means of measuring the position of the welding head, - a computer unit in which at least one computer program is implemented and in which the acquired data associated with the measured positions of the welding head are inserted, the computer program being calibrated by means of said learning process to ensure the conformity of the weld bead being deposited, said automated recognition process comprising: - an operation to move the welding head along the welding path, - an operation to deposit a weld bead in the weld path, - an operation to acquire at least one piece of data influencing at least one characteristic of the weld bead, this acquisition operation being carried out simultaneously with the operation of depositing a weld bead, - an operation to measure the position of the welding head, this measurement operation being carried out simultaneously with the operation of acquiring at least one data point, - an operation to detect a deviation of at least one acquired data point associated with its measured position relative to the representative data of conforming welds defined according to the calibrated computer program, when said deviation is detected, the automated recognition process further includes an alert operation for an operator.

[0024] It should be noted that the above automated learning and recognition processes can be implemented in the context of a weld removal between the less two components, for example metallic, defining the weld path or in the context of depositing a weld directly onto a specific surface and according to a predetermined direction defining the weld path, or for example during buttering or during the implementation of additive manufacturing.

[0025] Deviation detection refers to the detection of a data point, considered alone or in combination with others, acquired and associated with its measured position, that is sufficiently far from the representative data of welds qualified as compliant according to the definition of compliance defined by the calibrated computer program. This data point is then sufficiently far from the definition to be considered as being outside the coverage area of ​​the representative data of compliant welds defined according to the calibrated computer program. Detailed description of the invention

[0026] The following will describe a method for learning to recognize a conforming weld bead according to an example of an embodiment of the invention.

[0027] This learning method is described in the context of welding two metal tubes. However, it should be noted that this learning method can be suitable for welding between two metal components of different shapes and / or materials.

[0028] This process uses a welding installation.

[0029] The welding installation includes a welding head and a device for feeding the metal to be welded. For example, the head may be a consumable electrode connected to a welding generator, which is conventionally a power supply generator, and which creates an electric arc to melt the metal to be welded.

[0030] The installation includes a displacement device on which the welding head is mounted. The displacement device is adapted to allow the welding head to be moved.

[0031] The installation includes means for measuring the position of the welding head. The position of the welding head is understood to mean its coordinates in a given reference frame. The reference frame is represented by a mark on one of the two tubes to be welded.

[0032] The welding installation allows two tubes to be welded together. Initially, two tubes are placed side by side. The junction between these two tubes forms a circular weld path. To fix these tubes together, molten metal is deposited in the weld path.

[0033] Thus the installation is capable of depositing several weld beads in the weld path.

[0034] The installation includes means for acquiring data influencing a characteristic of the weld bead.

[0035] The installation includes a means for measuring the position of the welding head.

[0036] The installation includes a computer unit. At least one computer program is implemented in the computer unit. The computer unit is capable of receiving and storing data acquired by the acquisition means and associated with positions measured by a measuring means.

[0037] More precisely, the computer unit stores in real time the data acquired and associated with the positions of the welding head.

[0038] A data influencing a characteristic of the weld bead is systematically associated with the corresponding position of the welding head.

[0039] The learning phase consists of initiating an initial welding operation between two tubes. This initial welding operation comprises several passes to deposit multiple weld beads, thus filling the weld path with molten metal. Therefore, the first welding operation consists of performing a weld, referred to as a complete weld, between two metal tubes.

[0040] Thus, the learning process includes an operation of moving the welding head along the welding path. This operation is carried out by means of the movement device.

[0041] The method includes an operation of depositing a weld bead in the weld path. At least one weld bead is deposited per pass.

[0042] The operation of depositing a weld bead is carried out as the head moves along the weld path.

[0043] The method comprises an operation for measuring several data influencing at least one characteristic of the weld bead. The method simultaneously includes a measurement of the position of the welding head in the reference frame.

[0044] The method includes an operation of storing the acquired data associated with the measured positions of the welding head, this storage being carried out in the computer unit.

[0045] In other words, several data influencing at least one characteristic of the weld bead are measured and associated with the corresponding position of the welding electrode. Finally, this data is stored in the computer unit.

[0046] The preceding steps are repeated so as to deposit several weld beads, the set of weld beads deposited corresponding to one weld.

[0047] When the welding of the tubes is complete, that is, when the weld is finished or the weld path is filled with weld beads after several passes, a weld inspection operation, either destructive or non-destructive, is performed. Then, an evaluation of the inspected weld is carried out to establish that it is compliant. This operation can be performed manually. For example, radiography can be performed to obtain an image of the weld depth. Other techniques can be used.

[0048] The radiographs are analyzed by an operator who visually detects welding defects.

[0049] When the operator detects no welding defects, the inspected and evaluated weld is considered to be a compliant weld. In this case, the operator enters the acquired data, associated with the measured positions of the welding head representative of each deposited weld bead, into the computer unit.

[0050] The computer unit then associates with each weld bead contained in the conforming weld the data acquired and associated with the measured positions of the welding head.

[0051] The preceding steps are repeated to deposit several conforming welds and to constitute a set of data representative of the conforming welds.

[0052] Next, a calibration operation is performed on at least one computer program using the representative dataset of conforming welds inserted into the computer unit. The purpose of this calibration operation is to obtain a calibrated computer program, which is then configured to recognize a conforming weld.

[0053] In what follows, the data influencing at least one characteristic of the weld bead will be described in detail.

[0054] Advantageously, data influencing at least one characteristic of the weld bead are the voltage and current delivered by the welding generator. The current is measured across the generator terminals. The voltage is measured across the displacement device.

[0055] The intensity and voltage determine the quality of the weld. More precisely, the weld pool may fail to melt the surrounding metal or, conversely, may collapse.

[0056] Advantageously, one factor influencing at least one characteristic of the weld bead is the speed of movement of the welding electrode. This speed is measured by a sensor that continuously measures the speed of movement of the welding electrode.

[0057] The travel speed is an important factor in the deposition of the weld bead. A high travel speed causes significant mechanical stresses that can lead to cracking in the weld bead.

[0058] Advantageously, one factor influencing at least one characteristic of the weld bead is the ambient temperature. This temperature is provided by a sensor capable of measuring the ambient temperature.

[0059] Ambient temperature has an impact on weld quality. When the temperature is below a given temperature, weld defects may appear. appear.

[0060] Advantageously, one factor influencing at least one characteristic of the weld bead is ambient humidity. Ambient humidity is provided by a sensor capable of measuring it.

[0061] Ambient humidity has an impact on weld quality. Measuring humidity, along with measuring temperature, allows the dew point to be determined. The dew point is likely to affect weld quality.

[0062] Advantageously, a factor influencing at least one characteristic of the weld bead is the wind speed at the welding electrode. This speed is measured using a speed sensor.

[0063] Wind speed near the welding electrode can affect weld quality. In particular, it causes porosity, oxidation, and blowholes in the weld.

[0064] Advantageously, a factor influencing at least one characteristic of the weld bead is the weld bead temperature. This temperature is measured using a temperature sensor.

[0065] The temperature of the weld bead has an impact on the quality of the weld.

[0066] Advantageously, a factor influencing at least one characteristic of the weld bead is the volumetric or mass flow rate of a protective gas intended to prevent oxidation of the molten metal by oxygen from the air.

[0067] The flow rate of the shielding gas has an impact on the quality of the weld. In particular, it is the cause of porosity, oxidation and blowholes in the weld.

[0068] Advantageously, a factor influencing at least one characteristic of the weld bead is the pressure of the shielding gas.

[0069] The pressure of the shielding gas has an impact on the quality of the weld.

[0070] Advantageously, a factor influencing at least one characteristic of the weld bead is the temperature of the shielding gas.

[0071] The temperature of the shielding gas has an impact on the quality of the weld.

[0072] Advantageously, a factor influencing at least one characteristic of the weld bead is the weld bead profile and / or the profile of the adjacent areas. Adjacent areas are defined as areas located near the weld bead. These profiles are captured, for example, using a profilometer.

[0073] The profile provides useful information on the quality of the weld.

[0074] Other data influencing at least one characteristic of the weld bead could be recorded by means of any known element configured to capture at least one video stream or sound recording.

[0075] Once the learning phase is complete, it becomes possible to recognize weld beads conforming to an early stage of the welding operation. Indeed, With the computer unit having been enriched by the lessons learned from the learning process, and the computer program having been calibrated, it is possible to implement an automated recognition process for a conforming weld bead.

[0076] Thus, the invention relates to a method for automated recognition of a conforming weld bead. This method comprises an operation of moving the welding electrode along the weld path.

[0077] The method simultaneously comprises an operation to deposit a weld bead in the weld path. The method includes an operation to measure at least one data point influencing at least one characteristic of the weld bead and, simultaneously, an operation to measure the position of the welding electrode in the reference frame. The method includes an operation to detect a deviation of at least one acquired data point associated with its measured position from the representative data of conforming welds defined by the calibrated computer program. The detection operation is therefore carried out, in particular, using the calibrated computer program. When the deviation of at least one acquired data point associated with its measured position from the representative data of conforming welds is detected, the automated recognition method further includes an alert operation for an operator.

[0078] Thus the operator can suspend the welding operation at a juvenile stage, that is to say before the welding operation is completed and thus remove the thin thickness of characteristic weld at least in part from the non-conforming, or possibly non-conforming, weld bead, for which a deviation of at least one data acquired and associated with its measured position with respect to the data representative of conforming welds has been detected.

Claims

Demands

1. A method for learning to recognize a conforming weld deposited along a weld path, the method being implemented using a welding installation comprising: - a welding head that moves along the welding path and is capable of depositing a weld bead in the welding path, - means of acquiring at least one piece of data influencing at least one characteristic of the weld bead, - at least one means for measuring the position of the welding head, - a computer unit in which at least one computer program is implemented, capable of receiving and storing at least one piece of data acquired and associated with the measured position of the welding head, said method comprising: - an operation to move the welding head along the welding path, - an operation to deposit a weld bead in the weld path, - an operation to acquire at least one piece of data influencing at least one characteristic of the weld bead, this acquisition operation being carried out simultaneously with the operation of depositing a weld bead, - an operation to measure the position of the welding head, this measurement operation being carried out simultaneously with the operation of acquiring at least one data point, - an operation to store the acquired data associated with the measured positions of the welding head in the computer unit, the aforementioned preceding steps being repeated so as to deposit several weld beads, the set of weld beads deposited corresponding to one weld, the process further comprising: - a weld inspection operation, - a controlled weld evaluation operation to establish a compliant weld, Once the conforming weld has been established, the process further includes: - an operation to insert, into the computer unit, the acquired data associated with the measured positions of the welding head represented sensations of each weld bead deposited, the learning process being characterized in that the preceding steps are repeated to deposit several conforming welds and to constitute a set of data representative of the conforming welds, and - in that it further comprises a calibration operation of at least one computer program with the set of data representative of the conforming welds inserted into the computer unit to obtain a calibrated computer program, the calibrated computer program being configured to recognize a conforming weld.

2. Method according to the preceding claim wherein, at least one data point is the voltage and / or current delivered by a welding generator connected to the welding electrode.

3. A method according to any one of the preceding claims wherein at least one data point is the speed of movement of the welding electrode.

4. A method according to any one of the preceding claims wherein, at least one input is the ambient temperature.

5. A method according to any one of the preceding claims wherein, at least one input is ambient humidity.

6. A method according to any one of the preceding claims, wherein at least one input is wind speed.

7. A method according to any one of the preceding claims wherein, at least one data point is the temperature of the weld bead.

8. A method according to any one of the preceding claims, wherein at least one data point is the volumetric or mass flow rate of a protective gas intended to prevent oxidation of the molten metal by oxygen from the air.

9. A method according to any one of the preceding claims, wherein at least one parameter is the pressure of a protective gas intended to prevent oxidation of the molten metal by oxygen of 1 * Q1T*

10. 1 dll. A method according to any one of the preceding claims, wherein at least one datum is the temperature of a protective gas intended to prevent oxidation of the molten metal by oxygen of 1 * Q1T*

11. 1 dll. Method according to any one of the preceding claims in of which, at least one piece of data is the profile of the cordon and / or the profile of the adjacent areas.

12. An automated method for recognizing a conforming weld bead deposited or being deposited along a weld path, this method utilizing the teachings of a prior learning method according to any one of the preceding claims, the automated recognition method being implemented by means of a welding installation comprising: - a welding head that moves along the welding path and is capable of depositing a weld bead in the welding path, - means of acquiring at least one piece of data influencing at least one characteristic of the weld bead, - at least one means for measuring the position of the welding head, - a computer unit in which at least one computer program is implemented and in which the acquired data associated with the measured positions of the welding head are inserted, the computer program being calibrated by means of said learning process to ensure the conformity of the weld bead being deposited, said automated recognition process comprising: - an operation to move the welding head along the welding path, - an operation to deposit a weld bead in the weld path, - an operation to acquire at least one piece of data influencing at least one characteristic of the weld bead, this acquisition operation being carried out simultaneously with the operation of depositing a weld bead, - an operation to measure the position of the welding head, this measurement operation being carried out simultaneously with the operation of acquiring at least one data point, - an operation to detect a deviation of at least one acquired data point associated with its measured position relative to the representative data of conforming welds defined by the calibrated computer program, when said deviation is detected, the automated recognition process further includes an alert operation for an operator.