WO2020258712A1 - 一种焊缝成形控制装置及方法 - Google Patents
一种焊缝成形控制装置及方法 Download PDFInfo
- Publication number
- WO2020258712A1 WO2020258712A1 PCT/CN2019/121403 CN2019121403W WO2020258712A1 WO 2020258712 A1 WO2020258712 A1 WO 2020258712A1 CN 2019121403 W CN2019121403 W CN 2019121403W WO 2020258712 A1 WO2020258712 A1 WO 2020258712A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- welding
- molten pool
- structured light
- weld
- collapse
- Prior art date
Links
Images
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B23—MACHINE TOOLS; METAL-WORKING NOT OTHERWISE PROVIDED FOR
- B23K—SOLDERING OR UNSOLDERING; WELDING; CLADDING OR PLATING BY SOLDERING OR WELDING; CUTTING BY APPLYING HEAT LOCALLY, e.g. FLAME CUTTING; WORKING BY LASER BEAM
- B23K31/00—Processes relevant to this subclass, specially adapted for particular articles or purposes, but not covered by only one of the preceding main groups
- B23K31/02—Processes relevant to this subclass, specially adapted for particular articles or purposes, but not covered by only one of the preceding main groups relating to soldering or welding
Definitions
- This application relates to the technical field of welding quality control, and in particular to a welding seam forming control device and method based on the visual sensing of the front of the molten pool.
- Welding is an extremely important technology in metal processing and manufacturing, and it is also the only optional manufacturing method to ensure the structural tightness of cabins and pressure vessels. Stability, high efficiency, and high precision are the goals pursued by modern production. It is the inevitable trend of modern production to replace low-efficiency manual welding with robot automatic welding with good repeatability and high efficiency.
- automated robotic welding that relies on fixed welding specifications is difficult to cope with uneven weld penetration caused by changes in groove gaps, changes in heat dissipation conditions, and misaligned edges in the actual production process.
- the sensing methods for the penetration degree of the welding process include the following: direct measurement of the back melt width, traditional sensing technology, visual sensing technology, and multi-pass Sense technology.
- Direct measurement of the backside melt width is a very effective means to ensure the quality of penetration.
- it is often limited by the workpiece and tooling structure and the size of the space. It is difficult to fix the sensor on the back of the weld. At this time, it is necessary to collect the weld pool and weld
- the front information is used to infer the degree of penetration on the back.
- Traditional sensing technologies include methods such as ultrasonic detection, infrared temperature measurement, and molten pool oscillation detection.
- the ultrasonic detection method uses ultrasonic signals to calculate the solid-liquid interface position of the molten pool to obtain the penetration depth.
- the ultrasonic detection method can be applied to weld tracking and real-time detection of weld defects, but the effect of the temperature difference in the welding zone on the wave speed limits the accuracy of the method
- the cost of non-contact ultrasonic testing equipment is high.
- the infrared temperature measurement method is to estimate the penetration state based on the temperature of the welding zone, but the accuracy of infrared temperature measurement is affected by the fluctuation of the thermal emissivity and the surface state of the workpiece.
- the natural oscillation frequency of the molten pool reflects the size and degree of penetration of the molten pool.
- the oscillation frequency of the molten pool can be detected by detecting the fluctuation frequency of the arc voltage, the change of arc length or the periodic change of the specular reflection spot pattern on the surface of the molten pool. Therefore, the closed-loop control of penetration based on the oscillation frequency of the molten pool is completed, but the infrared temperature measurement method is only suitable for pulse welding with obvious oscillation in the molten pool, and the signal processing is difficult.
- Visual sensing technology establishes the mapping relationship between the geometric features, gray-scale features, and penetration degree of the molten pool image through the analysis of the molten pool image. The mapping relationship is not straightforward. Neural networks are usually used for modeling.
- Visual sensing technology can Obtaining very rich information, but due to complex modeling, large training data required, and the applicability of the model depends on the adequacy of the process test, it is still in the research stage. Multi-sensing technology combines images, voltage, current and other welding process signals to judge the penetration state. The operation mode is complicated and has similar modeling problems with visual sensing technology.
- the purpose of this application is to provide a welding seam forming control device and method based on the visual sensing of the front of the molten pool to solve the problem of uneven weld penetration in the prior art.
- the present application provides a welding seam forming control device based on visual sensing of the front of the molten pool, including a welding unit, a visual sensing unit, and a calculation control unit;
- the welding unit includes a welding torch, and the welding torch is used to perform a welding operation on a welding workpiece;
- the vision sensing unit includes a structured light source and a vision sensor.
- the structured light source and the vision sensor are respectively arranged on the left and right sides of the welding gun; the structured light source is used to emit a single-line structured light and pass through a single-line The structured light irradiates the molten pool; the vision sensor is used to collect the structured light spot image formed by the single-line structured light irradiating the surface of the molten pool and the surface of the welding workpiece, and output the structured light spot image;
- the calculation control unit includes a computer, the computer is connected to the vision sensor; the computer is used to receive the structured light spot image, and process the structured light spot image, obtain the current molten pool collapse feature quantity, and according to the current melting
- the deviation between the pool sag feature quantity and the expected value of the molten pool sag feature quantity adjusts the welding current of the welding gun.
- the welding unit further includes a welding power source, the welding torch is connected to the welding power source, and the welding power source is connected to the computer; the welding power source is used to output welding current to the welding torch, and the computer passes through The welding power source regulates the welding current of the welding gun.
- the welding unit further includes a cooling water tank for cooling the welding torch, the cooling water tank is provided with a water tank water inlet and a water tank water outlet, the welding torch is provided with a welding torch water inlet and a welding torch water outlet, the The water tank outlet is connected with the welding torch water inlet, the welding torch water outlet is connected with the water tank inlet; the cooling water tank is connected with the welding power source.
- the welding unit further includes a shielding gas storage tank connected to the welding power source, and the shielding gas storage tank provides shielding gas to the welding gun through the welding power source.
- a band-pass filter is installed on the vision sensor, and the band-pass filter allows structured light to pass through and filters out the interference of arc light in other wavebands.
- the structured light source, the vision sensor and the welding torch are respectively mounted on the mounting board, and the axes of the structured light source, the vision sensor and the welding torch are in the same plane.
- the welding workpiece is arranged directly below the welding gun, the structured light source and the vision sensor are respectively aligned with the welding workpiece, and the axis of the structured light source and the axis of the vision sensor are respectively opposite to each other It is symmetrical to the axis of the welding gun.
- the present application also provides a welding seam forming control method based on the front visual sensing of the molten pool.
- the method adopts the above-mentioned welding seam forming control device, and the method includes:
- the vision sensor collects the structured light spot image formed by the single-line structured light irradiating the surface of the molten pool and the surface of the welding workpiece, and transmits the structured light spot image to the computer;
- the computer processes the structured light spot image, obtains the current molten pool collapse feature quantity, and adjusts the welding current of the welding gun according to the deviation between the current molten pool collapse feature quantity and the expected value of the molten pool collapse feature quantity.
- said obtaining the characteristic quantity of the current molten pool collapse specifically includes:
- Extract the centerline of the original image in the foreground area, and the extracted centerline is divided into a straight line segment formed by single-line structured light irradiated on the base material of the welding workpiece and a curved segment formed by single-line structured light irradiated on the concave surface of the molten pool;
- the obtaining of the foreground area specifically includes:
- ⁇ is a constant selected based on actual experience, and ⁇ takes a value within [0.01,0.06].
- said obtaining the expected value of the characteristic quantity of molten pool collapse specifically includes:
- the corresponding molten pool sinking feature quantity expected value is obtained.
- the welding seam forming control device and method provided in the present application perform welding operations on welding workpieces through a welding gun, a single-line structured light emitted by a structured light source to irradiate the molten pool, and a vision sensor to collect the single-line structured light to irradiate the surface and Weld the structured light spot image formed on the surface of the welding workpiece, and output the structured light spot image to the computer.
- the structured light spot image is processed by the computer to obtain the current molten pool collapse feature quantity, and according to the current molten pool collapse feature quantity and The deviation between the expected value of the molten pool collapse feature quantity adjusts the welding current of the welding gun.
- the application ensures that the characteristic quantity of the molten pool collapse is constant, thereby being able to obtain a uniform width of the back side of the weld, thereby achieving uniform weld penetration, with simple structure, low cost, and low implementation difficulty , Easy to use in production practice.
- the welding seam forming control device and method provided in the present application can realize effective control of the welding seam forming, and can be applied to unfilled direct current tungsten gas shielded welding of tightly butt joints, and realizes unfilled direct current tungsten with uniform penetration Extremely gas shielded welding seam, especially suitable for backing-free welding of large aluminum alloy structural parts in the aerospace manufacturing field.
- FIG. 1 is a schematic structural diagram of a welding seam forming control device based on visual sensing of the front of a molten pool according to an embodiment of the present application;
- FIG. 2 is a flowchart of a method for controlling weld formation based on visual sensing of the front of the molten pool according to an embodiment of the present application;
- FIG. 3 is a structured light spot image collected by a vision sensor in an embodiment of the present application.
- FIG. 4 is a binarized image obtained by performing threshold segmentation and morphological expansion operation on the region of interest of the image in an embodiment of the present application;
- FIG. 5 is a foreground area obtained by removing noise connected domains from a binarized image in an embodiment of the present application
- FIG. 6 is the result of centerline extraction of the original image in the foreground area in the embodiment of the present application.
- FIG. 7 is the result of fitting the straight line segment and the curve segment of the center line respectively in the embodiment of the present application.
- 1 welding gun; 2: welding workpiece; 3: structured light source; 4: vision sensor; 5: computer; 6: welding power supply; 7: cooling water tank; 8: shielding gas storage tank; 9: band-pass filter Piece; 10: Mounting board.
- an embodiment of the present application provides a welding seam forming control device based on visual sensing of the front of the molten pool, which includes a welding unit, a visual sensing unit, and a calculation control unit.
- the welding unit includes a welding torch 1, and the welding torch 1 is used to perform a welding operation on a welding workpiece 2.
- the vision sensing unit includes a structured light source 3 and a vision sensor 4, and the structured light source 3 and the vision sensor 4 are respectively arranged on the left and right sides of the welding gun 1.
- the structured light source 3 is used to emit single-line structured light and irradiate the molten pool through the single-line structured light.
- the vision sensor 4 is used to collect the structured light spot image formed by the single-line structured light irradiating the surface of the molten pool and the surface of the welding workpiece 2, and output the structured light spot image.
- the calculation control unit includes a computer 5 connected to the visual sensor 4.
- the computer 5 is used to receive the structured light spot image output by the visual sensor 4, and process the structured light spot image to obtain the current molten pool collapse feature quantity, and based on the current molten pool collapse feature quantity and the molten pool collapse
- the deviation between the expected value of the characteristic quantity adjusts the welding current of the welding gun 1.
- the welding seam forming control device based on the visual sensing of the front of the molten pool, by real-time adjustment of the welding current of the welding torch 1, ensures that the molten pool collapses characteristic quantity is constant, so that uniform welding can be obtained.
- the width of the back side of the seam thereby realizing the uniform penetration of the weld seam, has the advantages of simple structure, low cost, low implementation difficulty, and easy use in production practice.
- the welding seam forming control device described in the embodiments of the present application can realize effective control of the welding seam forming, and can be applied to the unfilled direct current tungsten gas shielded welding of tightly butt joints, and realizes the unfilled direct current with uniform penetration Tungsten gas shielded welding seam is especially suitable for backing-free welding of large aluminum alloy structural parts in the aerospace manufacturing field.
- the welding unit further includes a welding power source 6, the welding torch 1 is connected to the welding power source 6, and the welding power source 6 is used to output a welding current to the welding torch 1.
- the welding power source 6 is connected to the computer 5, and the computer 5 can adjust the welding current output by the welding power source 6 to the welding torch 1 in real time, thereby realizing real-time adjustment of the welding current of the welding torch 1.
- the welding unit further includes a cooling water tank 7, the cooling water tank 7 is provided with a water tank water inlet and a water tank water outlet, the welding gun 1 is provided with a welding gun water inlet and a welding gun water outlet, the The water outlet of the water tank is connected with the water inlet of the welding torch, and the water outlet of the welding torch is connected with the water inlet of the water tank, and the cooling water tank 7 is used to cool the welding torch 1.
- the cooling water tank 7 is connected to the welding power source 6, and the welding power source 6 can provide electrical energy for the operation of the cooling water tank 7.
- the welding unit further includes a shielding gas storage tank 8, which is connected to the welding power source 6, and the shielding gas storage tank 8 is connected to the welding power source 6 through the welding power source 6.
- the welding torch 1 provides shielding gas, so that direct current tungsten gas shielded welding is performed through the welding torch 1.
- a band-pass filter 9 is installed on the vision sensor 4, and the band-pass filter 9 can allow the single-line structured light emitted by the structured light source 3 to pass and illuminate On the surface of the molten pool, and filter out other wave band arc interference.
- a mounting board 10 is further included, and the structured light source 3, the visual sensor 4 and the welding gun 1 are respectively mounted on the mounting board 10.
- the axes of the structured light source 3, the vision sensor 3 and the welding gun 1 are on the same plane.
- the welding workpiece 2 is arranged directly below the welding torch 1, the structured light source 3 and the vision sensor 4 are respectively aligned with the welding workpiece 2, the axis of the structured light source 3 and the vision
- the axes of the sensors 4 are symmetrical with respect to the axis of the welding gun 1 respectively.
- the angle between the axis of the structured light source 3 and the axis of the welding torch 1 can be set to 70°.
- the axis of the vision sensor 4 is different from the axis of the welding torch 1. The angle between is also set to 70°.
- an embodiment of the present application also provides a welding seam forming control method, which adopts the welding seam forming control device in the foregoing embodiment, and the method specifically includes the following steps:
- the structured light source is turned on, and the single-line structured light emitted by the structured light source irradiates the surface of the molten pool and the surface of the welding workpiece, and the welding gun starts welding.
- the vision sensor collects the structured light spot image formed by the single-line structured light irradiating the surface of the molten pool and the surface of the welding workpiece, and transmits the structured light spot image to the computer.
- the computer processes the structured light spot image to obtain the current molten pool collapse feature quantity.
- the computer adjusts the welding current of the welding gun according to the deviation between the current molten pool collapse feature quantity and the expected value of the molten pool collapse feature quantity.
- Figure 3 shows the structured light spot image collected by the vision sensor.
- the box shown in A is the area of interest
- B is the structured light reflected on the surface of the welding workpiece on both sides of the weld
- D is the reflected light from the concave surface of the molten pool. Structured light.
- the welding seam forming control method described in the embodiments of the present application can adjust the welding current of the welding gun in real time, so as to ensure a constant molten pool collapse characteristic quantity, thereby obtaining a uniform backside width of the weld seam, and achieving uniform weld penetration.
- the welding seam forming control method described in the embodiments of the present application can realize effective control of the welding seam forming, and can be applied to unfilled direct current tungsten gas shielded welding of tightly butt joints to achieve uniform penetration of unfilled direct current Tungsten gas shielded welding seam is especially suitable for backing-free welding of large aluminum alloy structural parts in the aerospace manufacturing field.
- the acquisition of the characteristic quantity of the current molten pool collapse specifically includes the following steps:
- the centerline of the original image in the foreground area is extracted, and the extracted centerline is divided into a straight line segment formed by single-line structured light irradiated on the base material of the welding workpiece and a curved segment formed by single-line structured light irradiated on the concave surface of the molten pool.
- Figure 6 shows the result image obtained by extracting the center line of the original image in the foreground area, where G is the straight line formed by the single-line structured light irradiated on the base material of the welding workpiece, and F is the single-line structured light irradiated on the welding workpiece. Curved segment formed by the concave surface of the pool.
- the straight line equation is used to fit the straight line segment to obtain the straight line L
- the polynomial equation is used to fit the curve segment to obtain the curve C, as shown in Figure 7, and the area enclosed by the line L and the curve C is obtained, and this area is regarded as the lower part of the molten pool.
- Collapse area S the area of the shaded part in Figure 7 is the collapse area S of the molten pool.
- the acquisition of the foreground area specifically includes the following steps:
- the connected domains satisfying A/P 2 > ⁇ are removed, and the remaining connected domains after removal in the connected domains of the binary image are used as the foreground area.
- ⁇ is a constant selected based on actual experience. In one embodiment, ⁇ takes a value within [0.01, 0.06].
- the acquisition of the expected value of the characteristic quantity of molten pool collapse specifically includes the following steps:
- the corresponding molten pool sinking feature quantity expected value is obtained.
- mapping relationship between the feature quantity of molten pool collapse and the expected value of the width of the back side of the weld is obtained through modeling simulations and experiments on the welding process under different welding currents.
- the initial welding parameters of the welding gun include an initial welding current, which is obtained according to the material and thickness of the welding workpiece.
- the back of the weld with uniform penetration and uniform appearance means the front of the weld with the same degree of depression, so it is different from the traditional use
- the two-dimensional image information of the molten pool uses the collapse information of the molten pool to guide the welding process to obtain a weld with the same amount of collapse on the front side, thereby indirectly obtaining the back side of the weld with the same width, and then achieve uniform penetration.
- the welding seam forming control method described in the embodiments of the present application can provide an effective welding seam forming control method for the unfilled direct current tungsten gas shielded welding of close butt joints. Because of the use of structured light information of the weld pool, Compared with the traditional two-dimensional weld pool image, the image of the present application has a high signal-to-noise ratio, simple processing, and a direct relationship with the degree of penetration, so the control effect is more stable and good.
- the welding seam forming control device and method described in the embodiments of the present application ensure that the molten pool collapse feature quantity is constant by real-time adjustment of the welding current, thereby obtaining a uniform width of the weld back surface, thereby achieving The weld penetration is uniform and consistent.
- connection and “connected” should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral Ground connection; it can be a mechanical connection or an electrical connection; it can be directly connected or indirectly connected through an intermediate medium.
- connection should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral Ground connection; it can be a mechanical connection or an electrical connection; it can be directly connected or indirectly connected through an intermediate medium.
Landscapes
- Engineering & Computer Science (AREA)
- Mechanical Engineering (AREA)
- Arc Welding In General (AREA)
- Length Measuring Devices By Optical Means (AREA)
Abstract
一种基于熔池正面视觉传感的焊缝成形控制装置及方法，属于焊接质量控制技术领域。其采用结构光照射熔池的下凹表面，并利用视觉传感器（4）获取相应的结构光图像，通过图像处理获得熔池下塌特征量，对焊接电流进行实时调节以保持熔池下塌特征量恒定，从而能够获得均匀一致的焊缝背面宽度进而实现焊缝熔透均匀一致。其仅依靠熔池正面结构光信息实现了对焊缝成形的控制，可应用于紧密对接接头的不填丝直流钨极气体保护焊，尤其适用于航空航天制造领域大型铝合金结构件的无衬垫焊接。
Description
交叉引用
本申请引用于2019年06月28日提交的专利名称为“一种焊缝成形控制装置及方法”的第2019105796937号中国专利申请，其通过引用被全部并入本申请。
本申请涉及焊接质量控制技术领域，尤其涉及一种基于熔池正面视觉传感的焊缝成形控制装置及方法。
焊接是金属加工制造中极为重要的技术，也是确保舱体和压力容器等的结构密封性的唯一可选制造手段。稳定性、高效率、高精度是现代化生产追求的目标，以重复性好、效率高的机器人自动化焊接取代低效的人工焊接是现代化生产的必然趋势。但依赖固定焊接规范的机器人自动化焊接难以应对实际生产过程中坡口间隙变化、散热条件变化、错边等带来的焊缝不均匀熔透。
从国内外焊接质量实时检测与控制的研究与生产应用现状来看，焊接过程熔透程度的传感方法有以下几种：直接测量背面熔宽、传统传感技术、视觉传感技术、多传感技术。直接测量背面熔宽是保证熔透质量的十分有效的手段，但实际应用中常受限于工件和工装结构以及空间大小，难以在焊缝背面固定传感器，此时需要通过采集熔池及焊缝的正面信息来推断背面熔透程度。传统传感技术包括超声检测、红外测温、熔池振荡检测等方法。其中超声检测方法通过超声信号计算熔池固液界面位置得到熔深，超声检测方法可同时应用于焊缝跟踪和焊缝缺陷实时检测，但焊接区温度差异对波速的影响限制了该方法的准确性，非接触式超声检测设备成本高昂。红外测温方法是根据焊接区的温度来推测熔透状态，但红外测温的准确性受到热发射率波动和工件表面状态的影响。熔池的自然振荡频率反映了熔池的大小和熔透程度，通过检测弧压的波动频率、弧长的变化或者熔池表 面镜面反射光斑图案的周期性变化都可以检测出熔池的振荡频率，从而完成基于熔池振荡频率的熔透闭环控制，但红外测温方法仅适合于熔池存在明显振荡的脉冲焊，且信号处理难度大。视觉传感技术通过对熔池图像的分析，建立熔池图像几何特征、灰度特征和熔透程度的映射关系，该映射关系并不直接，通常采用神经网络进行建模，视觉传感技术能获取非常丰富的信息，但由于建模复杂、所需训练数据大、模型的适用性依赖于工艺试验的充分性，目前还处于研究阶段。多传感技术结合了图像、电压、电流等多种焊接过程信号来判断熔透状态，操作方式复杂，且与视觉传感技术有类似的建模问题。
发明内容
(一)要解决的技术问题
本申请的目的是提供一种基于熔池正面视觉传感的焊缝成形控制装置及方法，解决现有技术存在的焊缝熔透不均匀的问题。
(二)技术方案
为了解决上述技术问题，本申请提供了一种基于熔池正面视觉传感的焊缝成形控制装置，包括焊接单元、视觉传感单元和计算控制单元；
所述焊接单元包括焊枪，所述焊枪用于对焊接工件进行焊接操作；
所述视觉传感单元包括结构光光源和视觉传感器，所述结构光光源和所述视觉传感器分别设置于所述焊枪的左右两侧；所述结构光光源用于发出单线结构光，并通过单线结构光照射熔池；所述视觉传感器用于采集单线结构光照射在熔池表面和焊接工件表面所形成的结构光光斑图像，并将结构光光斑图像进行输出；
所述计算控制单元包括计算机，所述计算机与所述视觉传感器相连；所述计算机用于接收结构光光斑图像，并对结构光光斑图像进行处理，获取当前熔池下塌特征量，并根据当前熔池下塌特征量与熔池下塌特征量期望值之间的偏差调节所述焊枪的焊接电流。
进一步地，所述焊接单元还包括焊接电源，所述焊枪与所述焊接电源相连，所述焊接电源与所述计算机相连；所述焊接电源用于向所述焊枪输出焊接电流，所述计算机通过所述焊接电源调节所述焊枪的焊接电流。
进一步地，所述焊接单元还包括用于对所述焊枪进行冷却的冷却水箱， 所述冷却水箱设有水箱进水口和水箱出水口，所述焊枪设有焊枪进水口和焊枪出水口，所述水箱出水口与所述焊枪进水口相连，所述焊枪出水口与所述水箱进水口相连；所述冷却水箱与所述焊接电源相连。
进一步地，所述焊接单元还包括保护气储罐，所述保护气储罐与所述焊接电源相连，所述保护气储罐通过所述焊接电源向所述焊枪提供保护气。
进一步地，所述视觉传感器上安装有带通滤光片，所述带通滤光片允许结构光通过，并滤除其它波段的弧光干扰。
具体地，还包括安装板，所述结构光光源、视觉传感器和焊枪分别安装于所述安装板，所述结构光光源、视觉传感器和焊枪三者的轴线处于同一平面。
具体地，所述焊接工件设置在所述焊枪的正下方，所述结构光光源和所述视觉传感器分别对准所述焊接工件，所述结构光光源的轴线和所述视觉传感器的轴线分别相对于所述焊枪的轴线对称。
为了解决上述技术问题，本申请还提供了一种基于熔池正面视觉传感的焊缝成形控制方法，该方法采用上述的焊缝成形控制装置，该方法包括：
设定焊枪的初始焊接参数，获取熔池下塌特征量期望值；
打开结构光光源，通过单线结构光照射熔池，所述焊枪开始焊接；
视觉传感器采集单线结构光照射在熔池表面和焊接工件表面所形成的结构光光斑图像，并将结构光光斑图像传输至计算机；
所述计算机对结构光光斑图像进行处理，获取当前熔池下塌特征量，并根据当前熔池下塌特征量与熔池下塌特征量期望值之间的偏差来调节所述焊枪的焊接电流。
进一步地，所述的获取当前熔池下塌特征量，具体包括：
从结构光光斑图像中选取包含光斑的感兴趣区域作为后续图像处理的对象，对该感兴趣区域进行阈值分割和形态学膨胀运算，获取二值化图像，并将二值化图像连通域中的噪声连通域剔除，获取前景区域；
对前景区域内的原图像进行中心线提取，提取得到的中心线分为单线结构光照射在所述焊接工件母材上形成的直线段和单线结构光照射在熔池下凹表面形成的曲线段；
采用直线方程对直线段进行拟合获取直线L,采用多项式方程对曲线 段进行拟合获取曲线C，并获取直线L与曲线C围成的面积,将该面积作为熔池下塌面积S；
对熔池下塌面积S进行平方根运算，获取当前熔池下塌特征量
进一步地，所述的获取前景区域，具体包括：
设定二值化图像连通域的周长为P，面积为A；
将满足A/P
2>ε的连通域进行剔除，将二值化图像连通域中经过剔除后的剩余连通域作为前景区域；
其中，ε为根据实际经验选定的常数，ε在[0.01,0.06]内取值。
进一步地，所述的获取熔池下塌特征量期望值，具体包括：
根据对焊缝熔透程度的要求设定焊缝背面宽度期望值；
根据熔池下塌特征量与焊缝背面宽度期望值的映射关系获取对应的熔池下塌特征量期望值。
本申请的上述技术方案具有如下优点：
本申请提供的焊缝成形控制装置及方法，通过焊枪对焊接工件进行焊接操作，通过结构光光源来发出的单线结构光来照射熔池，通过视觉传感器来采集单线结构光照射在熔池表面和焊接工件表面所形成的结构光光斑图像，并将结构光光斑图像进行输出至计算机，在通过计算机对结构光光斑图像进行处理，获取当前熔池下塌特征量，并根据当前熔池下塌特征量与熔池下塌特征量期望值之间的偏差调节所述焊枪的焊接电流。本申请通过对焊接电流进行实时调节，确保了熔池下塌特征量恒定，从而能够获得均匀一致的焊缝背面宽度，进而实现了焊缝熔透均匀一致，具有结构简单、成本低廉、实施难度低、易用于生产实践的优点。
本申请提供的焊缝成形控制装置及方法，能够实现对焊缝成形的有效控制，可应用于紧密对接接头的不填丝直流钨极气体保护焊，实现熔透均匀一致的不填丝直流钨极气体保护焊焊缝，尤其适用于航空航天制造领域大型铝合金结构件的无衬垫焊接。
图1是本申请实施例基于熔池正面视觉传感的焊缝成形控制装置的结构示意图；
图2是本申请实施例基于熔池正面视觉传感的焊缝成形控制方法的流程图；
图3是本申请实施例中视觉传感器采集的结构光光斑图像；
图4是本申请实施例中对图像的感兴趣区域进行阈值分割以及形态学膨胀运算得到的二值化图像；
图5是本申请实施例中对二值化图像剔除噪声连通域得到的前景区域；
图6是本申请实施例中对前景区域内的原图像进行中心线提取得到的结果；
图7是本申请实施例中对进行中心线的直线段和曲线段分别拟合得到的结果。
图中：1：焊枪；2：焊接工件；3：结构光光源；4：视觉传感器；5：计算机；6：焊接电源；7：冷却水箱；8：保护气储罐；9：带通滤光片；10：安装板。
为使本申请实施例的目的、技术方案和优点更加清楚，下面将结合本申请实施例中的附图，对本申请实施例中的技术方案进行清楚、完整地描述，显然，所描述的实施例是本申请的一部分实施例，而不是全部的实施例。基于本申请中的实施例，本领域普通技术人员在没有做出创造性劳动的前提下所获得的所有其他实施例，都属于本申请保护的范围。
如图1所示，本申请实施例提供一种基于熔池正面视觉传感的焊缝成形控制装置，包括焊接单元、视觉传感单元和计算控制单元。
所述焊接单元包括焊枪1，所述焊枪1用于对焊接工件2进行焊接操作。
所述视觉传感单元包括结构光光源3和视觉传感器4，所述结构光光源3和所述视觉传感器4分别设置于所述焊枪1的左右两侧。其中，所述结构光光源3用于发出单线结构光，并通过单线结构光照射熔池。所述视觉传感器4用于采集单线结构光照射在熔池表面和焊接工件2表面所形成的结构光光斑图像，并将结构光光斑图像进行输出。
所述计算控制单元包括计算机5，所述计算机5与所述视觉传感器4相连。其中，所述计算机5用于接收所述视觉传感器4输出的结构光光斑 图像，并对结构光光斑图像进行处理，获取当前熔池下塌特征量，并根据当前熔池下塌特征量与熔池下塌特征量期望值之间的偏差调节所述焊枪1的焊接电流。
本申请实施例所述的基于熔池正面视觉传感的焊缝成形控制装置，通过对所述焊枪1的焊接电流进行实时调节，确保了熔池下塌特征量恒定，从而能够获得均匀一致的焊缝背面宽度，进而实现了焊缝熔透均匀一致，具有结构简单、成本低廉、实施难度低、易用于生产实践的优点。
本申请实施例所述的焊缝成形控制装置，能够实现对焊缝成形的有效控制，可应用于紧密对接接头的不填丝直流钨极气体保护焊，实现熔透均匀一致的不填丝直流钨极气体保护焊焊缝，尤其适用于航空航天制造领域大型铝合金结构件的无衬垫焊接。
在本申请的进一步实施例中，所述焊接单元还包括焊接电源6，所述焊枪1与所述焊接电源6相连，所述焊接电源6用于向所述焊枪1输出焊接电流。
所述焊接电源6与所述计算机5相连，所述计算机5能够实时调节所述焊接电源6向所述焊枪1输出的焊接电流，进而实现对所述焊枪1的焊接电流的实时调节。
在本申请的进一步实施例中，所述焊接单元还包括冷却水箱7，所述冷却水箱7设有水箱进水口和水箱出水口，所述焊枪1设有焊枪进水口和焊枪出水口，所述水箱出水口与所述焊枪进水口相连，所述焊枪出水口与所述水箱进水口相连，通过所述冷却水箱7用于对所述焊枪1进行冷却。
所述冷却水箱7与所述焊接电源6相连，所述焊接电源6能够为所述冷却水箱7的运行提供电能。
在本申请的进一步实施例中，所述焊接单元还包括保护气储罐8，所述保护气储罐8与所述焊接电源6相连，所述保护气储罐8通过所述焊接电源6向所述焊枪1提供保护气，从而通过所述焊枪1进行直流钨极气体保护焊。
在本申请的进一步实施例中，所述视觉传感器4上安装有带通滤光片9，通过设置所述带通滤光片9能够允许所述结构光光源3发出的单线结构光通过并照射于熔池表面，并滤除其它波段的弧光干扰。
在本申请的具体实施例中，还包括安装板10，所述结构光光源3、视觉传感器4和焊枪1分别安装于所述安装板10。
其中，所述结构光光源3、视觉传感器3和焊枪1三者的轴线处于同一平面。
其中，所述焊接工件2设置在所述焊枪1的正下方，所述结构光光源3和所述视觉传感器4分别对准所述焊接工件2，所述结构光光源3的轴线和所述视觉传感器4的轴线分别相对于所述焊枪1的轴线对称。这种结构设置方式，能够使得单线结构光在熔池表面的反射为镜面反射。
在一个实施例中，所述结构光光源3的轴线与所述焊枪1的轴线之间的夹角可以设置为70°，同理，所述视觉传感器4的轴线与所述焊枪1的轴线之间的夹角也设置为70°。
如图2所示，本申请实施例还提供了一种焊缝成形控制方法，该方法采用上述实施例中的焊缝成形控制装置，该方法具体包括如下步骤：
设定焊枪的初始焊接参数，获取熔池下塌特征量期望值。
打开结构光光源，所述结构光光源发出的单线结构光照射熔池表面和焊接工件表面，所述焊枪开始焊接。
视觉传感器采集单线结构光照射在熔池表面和焊接工件表面所形成的结构光光斑图像，并将结构光光斑图像传输至计算机。
所述计算机对结构光光斑图像进行处理，获取当前熔池下塌特征量。
所述计算机根据当前熔池下塌特征量与熔池下塌特征量期望值之间的偏差来调节所述焊枪的焊接电流。
如图3所示为视觉传感器采集的结构光光斑图像，其中A所示的方框为感兴趣区域，B为焊缝两侧的焊接工件表面反射的结构光，D为熔池下凹表面反射的结构光。
本申请实施例所述的焊缝成形控制方法，能够对焊枪的焊接电流进行实时调节，从而确保熔池下塌特征量恒定，进而获得均匀一致的焊缝背面宽度，实现焊缝熔透均匀一致。
本申请实施例所述的焊缝成形控制方法，能够实现对焊缝成形的有效控制，可应用于紧密对接接头的不填丝直流钨极气体保护焊，实现熔透均匀一致的不填丝直流钨极气体保护焊焊缝，尤其适用于航空航天制造领域 大型铝合金结构件的无衬垫焊接。
在本申请的进一步实施例中，所述的获取当前熔池下塌特征量，具体包括如下步骤：
从结构光光斑图像中选取包含光斑的感兴趣区域作为后续图像处理的对象，对该感兴趣区域进行阈值分割和形态学膨胀运算，获取二值化图像，并将二值化图像连通域中的噪声连通域剔除，获取前景区域。如图4所示为获得的二值化图像，其中E为噪声连通域。如图5所示为获取的前景区域。
对前景区域内的原图像进行中心线提取，提取得到的中心线分为单线结构光照射在所述焊接工件母材上形成的直线段和单线结构光照射在熔池下凹表面形成的曲线段。如图6所示为对前景区域内的原图像进行中心线提取得到的结果图像，其中G为单线结构光照射在所述焊接工件母材上形成的直线段，F为单线结构光照射在熔池下凹表面形成的曲线段。
采用直线方程对直线段进行拟合获取直线L,采用多项式方程对曲线段进行拟合获取曲线C，如图7所示，并获取直线L与曲线C围成的面积,将该面积作为熔池下塌面积S，图7中的阴影部分面积即为熔池下塌面积S。
对熔池下塌面积S进行平方根运算，获取当前熔池下塌特征量
在本申请的进一步实施例中，所述的获取前景区域，具体包括如下步骤：
设定二值化图像连通域的周长为P，面积为A。
将满足A/P
2>ε的连通域进行剔除，将二值化图像连通域中经过剔除后的剩余连通域作为前景区域。
其中，ε为根据实际经验选定的常数，在一个实施例中，ε在[0.01,0.06]内取值。
在本申请的进一步实施例中，所述的获取熔池下塌特征量期望值，具体包括如下步骤：
根据对焊缝熔透程度的要求设定焊缝背面宽度期望值；
根据熔池下塌特征量与焊缝背面宽度期望值的映射关系获取对应的熔池下塌特征量期望值。
其中，熔池下塌特征量与焊缝背面宽度期望值的映射关系，是通过对 不同焊接电流下的焊接过程进行建模仿真和实验获得。
在本申请的进一步实施例中，焊枪的初始焊接参数包括初始焊接电流，所述初始焊接电流根据焊接工件的材质、厚度来获取。
本申请实施例所述的焊缝成形控制方法所依据的原理是：
对于紧密对接工件的不填丝焊接过程而言，由于焊接前后金属体积基本不变，熔透均匀、形貌一致的焊缝背面意味着下凹程度一致的焊缝正面，因此不同于传统的利用熔池二维图像信息，本申请利用熔池的下塌信息来指导焊接过程，得到正面下塌量一致的焊缝，从而间接得到宽度一致的焊缝背面，继而实现熔透均匀一致。
本申请实施例所述的焊缝成形控制方法，能够为紧密对接接头的不填丝直流钨极气体保护焊提供一种有效的焊缝成形控制手段，由于利用焊接熔池的结构光信息，相比于传统的二维熔池图像而言，本申请的图像信噪比高、处理简单、与熔透程度的关系直接，因此控制效果更加稳定、良好。
综上所述，本申请实施例所述的焊缝成形控制装置及方法，通过对焊接电流进行实时调节，确保了熔池下塌特征量恒定，从而能够获得均匀一致的焊缝背面宽度，进而实现了焊缝熔透均匀一致。
在本申请的描述中，需要说明的是，除非另有明确的规定和限定，术语“相连”、“连接”应做广义理解，例如，可以是固定连接，也可以是可拆卸连接，或一体地连接；可以是机械连接，也可以是电连接；可以是直接相连，也可以通过中间媒介间接相连。对于本领域的普通技术人员而言，可以具体情况理解上述术语在本申请中的具体含义。
在本申请的描述中，除非另有说明，“若干”的含义是一个或多个；“多个”的含义是两个或两个以上；术语“上”、“下”、“左”、“右”、“内”、“外”等指示的方位或位置关系为基于附图所示的方位或位置关系，仅是为了便于描述本申请和简化描述，而不是指示或暗示所指的装置或元件必须具有特定的方位、以特定的方位构造和操作，因此不能理解为对本申请的限制。
最后应说明的是：以上实施例仅用以说明本申请的技术方案，而非对其限制；尽管参照前述实施例对本申请进行了详细的说明，本领域的普通技术人员应当理解：其依然可以对前述各实施例所记载的技术方案进行修改，或者对其中部分技术特征进行等同替换；而这些修改或者替换，并不 使相应技术方案的本质脱离本申请各实施例技术方案的精神和范围。
Claims (10)
- 一种基于熔池正面视觉传感的焊缝成形控制装置，其特征在于，包括焊接单元、视觉传感单元和计算控制单元；所述焊接单元包括焊枪，所述焊枪用于对焊接工件进行焊接操作；所述视觉传感单元包括结构光光源和视觉传感器，所述结构光光源和所述视觉传感器分别设置于所述焊枪的左右两侧；所述结构光光源用于发出单线结构光，并通过单线结构光照射熔池；所述视觉传感器用于采集单线结构光照射在熔池表面和焊接工件表面所形成的结构光光斑图像，并将结构光光斑图像进行输出；所述计算控制单元包括计算机，所述计算机与所述视觉传感器相连；所述计算机用于接收结构光光斑图像，并对结构光光斑图像进行处理，获取当前熔池下塌特征量，并根据当前熔池下塌特征量与熔池下塌特征量期望值之间的偏差调节所述焊枪的焊接电流。
- 根据权利要求1所述的基于熔池正面视觉传感的焊缝成形控制装置，其特征在于，所述焊接单元还包括焊接电源，所述焊枪与所述焊接电源相连，所述焊接电源与所述计算机相连；所述焊接电源用于向所述焊枪输出焊接电流，所述计算机通过所述焊接电源调节所述焊枪的焊接电流。
- 根据权利要求1所述的基于熔池正面视觉传感的焊缝成形控制装置，其特征在于，所述焊接单元还包括用于对所述焊枪进行冷却的冷却水箱，所述冷却水箱设有水箱进水口和水箱出水口，所述焊枪设有焊枪进水口和焊枪出水口，所述水箱出水口与所述焊枪进水口相连，所述焊枪出水口与所述水箱进水口相连；所述冷却水箱与所述焊接电源相连。
- 根据权利要求1所述的基于熔池正面视觉传感的焊缝成形控制装置，其特征在于，所述焊接单元还包括保护气储罐，所述保护气储罐与所述焊接电源相连，所述保护气储罐通过所述焊接电源向所述焊枪提供保护气。
- 根据权利要求1所述的基于熔池正面视觉传感的焊缝成形控制装置，其特征在于，所述视觉传感器上安装有带通滤光片，所述带通滤光片允许单线结构光通过。
- 根据权利要求1所述的基于熔池正面视觉传感的焊缝成形控制装 置，其特征在于，还包括安装板，所述结构光光源、视觉传感器和焊枪分别安装于所述安装板；所述结构光光源、视觉传感器和焊枪三者的轴线处于同一平面；所述结构光光源的轴线和所述视觉传感器的轴线分别相对于所述焊枪的轴线对称。
- 一种基于熔池正面视觉传感的焊缝成形控制方法，该方法采用如权利要求1-6任一项所述的基于熔池正面视觉传感的焊缝成形控制装置，其特征在于，该方法包括：设定焊枪的初始焊接参数，获取熔池下塌特征量期望值；打开结构光光源，通过单线结构光照射熔池，所述焊枪开始焊接；视觉传感器采集单线结构光照射在熔池表面和焊接工件表面所形成的结构光光斑图像，并将结构光光斑图像传输至计算机；所述计算机对结构光光斑图像进行处理，获取当前熔池下塌特征量，并根据当前熔池下塌特征量与熔池下塌特征量期望值之间的偏差来调节所述焊枪的焊接电流。
- 根据权利要求7所述的基于熔池正面视觉传感的焊缝成形控制方法，其特征在于，所述的获取当前熔池下塌特征量，具体包括：从结构光光斑图像中选取包含光斑的感兴趣区域作为后续图像处理的对象，对该感兴趣区域进行阈值分割和形态学膨胀运算，获取二值化图像，并将二值化图像连通域中的噪声连通域剔除，获取前景区域；对前景区域内的原图像进行中心线提取，提取得到的中心线分为单线结构光照射在所述焊接工件母材上形成的直线段和单线结构光照射在熔池下凹表面形成的曲线段；采用直线方程对直线段进行拟合获取直线L,采用多项式方程对曲线段进行拟合获取曲线C，并获取直线L与曲线C围成的面积,将该面积作为熔池下塌面积S；对熔池下塌面积S进行平方根运算，获取当前熔池下塌特征量
- 根据权利要求8所述的基于熔池正面视觉传感的焊缝成形控制方法，其特征在于，所述的获取前景区域，具体包括：设定二值化图像连通域的周长为P，面积为A；将满足A/P 2>ε的连通域进行剔除，将二值化图像连通域中经过剔除 后的剩余连通域作为前景区域；其中，ε为根据实际经验选定的常数，ε在[0.01,0.06]内取值。
- 根据权利要求7所述的基于熔池正面视觉传感的焊缝成形控制方法，其特征在于，所述的获取熔池下塌特征量期望值，具体包括：根据对焊缝熔透程度的要求设定焊缝背面宽度期望值；根据熔池下塌特征量与焊缝背面宽度期望值的映射关系获取对应的熔池下塌特征量期望值。
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| JP2020528447A JP6984988B1 (ja) | 2019-06-28 | 2019-11-28 | 溶接ビード成形制御装置及び方法 |
| US16/863,380 US11541483B2 (en) | 2019-06-28 | 2020-04-30 | Control device and method for formation of weld seam |
Applications Claiming Priority (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910579693.7 | 2019-06-28 | ||
| CN201910579693.7A CN110193679B (zh) | 2019-06-28 | 2019-06-28 | 一种基于熔池正面视觉传感的焊缝成形控制装置及方法 |
Related Child Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| US16/863,380 Continuation US11541483B2 (en) | 2019-06-28 | 2020-04-30 | Control device and method for formation of weld seam |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| WO2020258712A1 true WO2020258712A1 (zh) | 2020-12-30 |
Family
ID=67755584
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| PCT/CN2019/121403 WO2020258712A1 (zh) | 2019-06-28 | 2019-11-28 | 一种焊缝成形控制装置及方法 |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN110193679B (zh) |
| WO (1) | WO2020258712A1 (zh) |
Families Citing this family (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110193679B (zh) * | 2019-06-28 | 2020-05-15 | 清华大学 | 一种基于熔池正面视觉传感的焊缝成形控制装置及方法 |
| JP6984988B1 (ja) | 2019-06-28 | 2021-12-22 | 清華大学Tsinghua University | 溶接ビード成形制御装置及び方法 |
| CN113029872B (zh) * | 2021-03-25 | 2022-12-20 | 兰州理工大学 | 一种实时测量焊接熔池液态金属表面张力的方法和系统 |
| CN114612457A (zh) * | 2022-03-21 | 2022-06-10 | 徐州华宝能源科技有限公司 | 一种基于计算机视觉的汽车零件激光焊接调节方法及系统 |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5481085A (en) * | 1994-09-09 | 1996-01-02 | University Of Kentucky Research Foundation | Apparatus and method for measuring 3-D weld pool shape |
| CN103506756A (zh) * | 2013-09-11 | 2014-01-15 | 上海交通大学 | 基于熔池图像视觉传感的激光搭接焊间隙检测系统及方法 |
| CN204221169U (zh) * | 2014-09-29 | 2015-03-25 | 天津滨孚企业管理咨询有限公司 | 基于ccd传感器的焊接参数图像采集系统 |
| KR101683044B1 (ko) * | 2015-11-24 | 2016-12-12 | 한국생산기술연구원 | 용융지 면적을 균일화하는 자동용접장치 |
| CN109202283A (zh) * | 2017-12-07 | 2019-01-15 | 中国航空制造技术研究院 | 一种t型接头双光束填丝焊接工艺调控装置及焊接方法 |
| CN110193679A (zh) * | 2019-06-28 | 2019-09-03 | 清华大学 | 一种焊缝成形控制装置及方法 |
Family Cites Families (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US4613743A (en) * | 1984-12-03 | 1986-09-23 | General Electric Company | Arc welding adaptive process control system |
| US4767911A (en) * | 1987-02-26 | 1988-08-30 | Rockwell International Corporation | Optical weld contour monitor for penetration control |
| US4733051A (en) * | 1987-08-25 | 1988-03-22 | Canadian Patents And Development Limited | Method and apparatus for controlling root pass weld penetration in open butt joints |
| GB8900738D0 (en) * | 1989-01-13 | 1989-03-08 | Central Electr Generat Board | Welding method and apparatus |
| US6084205A (en) * | 1997-03-14 | 2000-07-04 | Sandia Corporation | Method for enhanced control of welding processes |
| CN104014905A (zh) * | 2014-06-06 | 2014-09-03 | 哈尔滨工业大学 | Gtaw焊接过程中熔池三维形貌观测装置及方法 |
| CN105414710B (zh) * | 2015-12-29 | 2017-02-01 | 哈尔滨阿尔特机器人技术有限公司 | 主被动视觉焊接熔池复合传感装置及采用该装置实现的传感方法 |
| CN107127432B (zh) * | 2017-06-22 | 2019-10-18 | 西南交通大学 | 基于焊工调节的铝合金mig焊熔透控制系统与方法 |
| CN108226168A (zh) * | 2018-01-14 | 2018-06-29 | 湘潭大学 | 单目多功能主被动视觉传感装置及其传感方法 |
| CN108274095B (zh) * | 2018-01-18 | 2019-05-17 | 天津工业大学 | 基于正面熔池图像特征的非对称角焊缝焊接质量检测方法 |
| CN108856978B (zh) * | 2018-08-20 | 2020-08-07 | 南京理工大学 | 基于近红外双目视觉识别的角接接头熔透控制方法 |
-
2019
- 2019-06-28 CN CN201910579693.7A patent/CN110193679B/zh active Active
- 2019-11-28 WO PCT/CN2019/121403 patent/WO2020258712A1/zh active Application Filing
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5481085A (en) * | 1994-09-09 | 1996-01-02 | University Of Kentucky Research Foundation | Apparatus and method for measuring 3-D weld pool shape |
| CN103506756A (zh) * | 2013-09-11 | 2014-01-15 | 上海交通大学 | 基于熔池图像视觉传感的激光搭接焊间隙检测系统及方法 |
| CN204221169U (zh) * | 2014-09-29 | 2015-03-25 | 天津滨孚企业管理咨询有限公司 | 基于ccd传感器的焊接参数图像采集系统 |
| KR101683044B1 (ko) * | 2015-11-24 | 2016-12-12 | 한국생산기술연구원 | 용융지 면적을 균일화하는 자동용접장치 |
| CN109202283A (zh) * | 2017-12-07 | 2019-01-15 | 中国航空制造技术研究院 | 一种t型接头双光束填丝焊接工艺调控装置及焊接方法 |
| CN110193679A (zh) * | 2019-06-28 | 2019-09-03 | 清华大学 | 一种焊缝成形控制装置及方法 |
Non-Patent Citations (1)
| Title |
|---|
| ZHANG, YUMING: "Non-official translation: Research on Front Vision Adaptive Control of TIG Welding Fusion", DOCTORAL DISSERTATIONS FOR THE DEGREE OF ENGINEERING OF HARBIN ENGINEERING UNIVERSITY, 31 December 1990 (1990-12-31), DOI: 9160304 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110193679A (zh) | 2019-09-03 |
| CN110193679B (zh) | 2020-05-15 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| WO2020258712A1 (zh) | 一种焊缝成形控制装置及方法 | |
| CN104942404B (zh) | 双波长双目视觉焊缝跟踪方法及跟踪系统 | |
| CN108274095B (zh) | 基于正面熔池图像特征的非对称角焊缝焊接质量检测方法 | |
| CN107081503A (zh) | 一种弧焊质量的红外无损检测装置及其红外无损检测方法 | |
| Xu et al. | Visual sensing technologies in robotic welding: Recent research developments and future interests | |
| CN108672893B (zh) | 一种非对称角焊缝熔透形态及熔深的控制方法 | |
| CN104977305A (zh) | 一种基于红外视觉的焊接质量分析装置及分析方法 | |
| CN107931802B (zh) | 基于中红外温度传感的电弧焊焊缝质量在线检测方法 | |
| CN109702293B (zh) | 一种基于视觉检测的焊接熔透质量实时控制方法 | |
| CN108489986A (zh) | 一种增材制造在线检测及修复方法 | |
| Shi et al. | Laser-vision-based measurement and analysis of weld pool oscillation frequency in GTAW-P | |
| CN206567687U (zh) | 一种脉冲激光激振tig熔池检测振荡频率的熔透控制装置 | |
| CN106425025A (zh) | 一种激光位移传感器的角焊缝自动焊接控制方法及装置 | |
| CN115032944A (zh) | 基于机器视觉的激光焊接控制方法 | |
| ZHANG et al. | Visual sensing of weld pool in variable polarity TIG welding of aluminium alloy | |
| US11541483B2 (en) | Control device and method for formation of weld seam | |
| CN102519387A (zh) | 一种电子束焊接熔池形状参数的视觉检测方法 | |
| Peng et al. | Closed-loop control of medium-thickness plate arc welding based on weld-face vision sensing | |
| Wang et al. | Weld pool surface fluctuations sensing in pulsed GMAW | |
| Hong et al. | Real-time quality monitoring of ultrathin sheets edge welding based on microvision sensing and SOCIFS-SVM | |
| Shi et al. | Weld pool oscillation frequency in pulsed gas tungsten arc welding with varying weld penetration | |
| CN116664508A (zh) | 一种焊缝表面质量检测方法及计算机可读存储介质 | |
| Lertrusdachakul et al. | Vision-based control of wire extension in GMA welding | |
| Zhang et al. | A study on seam tracking in robotic GMA welding process | |
| Guo et al. | Correlation between fusion hole morphology and weld penetration in TIG welding |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| ENP | Entry into the national phase |
Ref document number: 2020528447 Country of ref document: JP Kind code of ref document: A |
|
| 121 | Ep: the epo has been informed by wipo that ep was designated in this application |
Ref document number: 19935302 Country of ref document: EP Kind code of ref document: A1 |
|
| NENP | Non-entry into the national phase |
Ref country code: DE |
|
| 122 | Ep: pct application non-entry in european phase |
Ref document number: 19935302 Country of ref document: EP Kind code of ref document: A1 |