The gas tungsten arc welding (GTAW) is a primary method for nuclear component fabrication and repair. Recent advancements in monitoring and automation technologies have made the shift toward fully automated arc welding more feasible, reducing the necessity for continuous human oversight. Two artificial intelligence-based networks were developed that utilize sensor-based feedback on a mechanized GTAW head. We present an image-based semantic segmentation convolutional neural network that identifies crucial features such as the weld pool, groove, wire, and electrode based on which geometric measurements are derived. A separate novel neural network predicts the weld bead geometry for multi-pass welds and inconsistent groove geometries. The application of both neural networks is a pre-requisite that enables the autonomous planning and execution of multi-pass welds to fill a groove.

Abstract Methodologies for the assessment of technology’s maturity are widely used in industry and research. Probably the best known are technology readiness levels (TRLs), initially pioneered by the National Aeronautics and Space Administration (NASA). At the beginning, only descriptively defined TRLs existed, but over time, automated assessment techniques in the form of questionnaires emerged in order to determine TRLs. Originally TRLs targeted equipment for space applications, but the demands on industrial relevant equipment are partly different in terms of, for example, overall costs, product quantities, or the presence of competitors. Therefore, we present a commonly valid assessment methodology with the aim of assessing laser-based equipment for industrial use, in general. The assessment is carried out with the help of a questionnaire, which allows for a user-friendly and easy accessible way to monitor the progress from the lab-proven state to the application-ready product throughout the complete development period. The assessment result is presented in a multidimensional metric in order to reveal the current specific strengths and weaknesses of the equipment development process, which can be used to direct the remaining development process of the equipment in the right direction.

Process observation in 3D printing of metals currently is one of the central challenges. Many companies strive to employ this additive manufacturing process in their production chains in order to gain competitive advantages through added flexibility in product design and embedded features. The new degrees of freedom are accompanied with the challenge to manufacture every detail of the product to the predefined specifications. Products with filigree internal structures for example require a perfect build to deliver the performance that was designed into these structures.Melting conditions determine properties such as grain structure and density of the finished part before it is sent to post processing steps. Monitoring of such melting conditions is still a challenge where the use of photodiodes, pyrometry and camera systems contribute to an overall picture that might identify errors or deviations during the build process. Additional considerations must be made to decide if these sensors are applied coaxially or from a lateral perspective. Furthermore, setting parameters of focal plane array (FPA) sensors are discussed and events that are seen in the machine vision image are compared against the pyrometry data.The resume of the experiments suggests the application of multiple sensors to the selective laser melting process (SLM) as they jointly contribute to an identification of events. These events need to be understood in order to establish cause effect relationships in the future.

Laser brazing is widely used for joining metal sheets in industrial applications, in particular in the automotive sector, where the requirements on surface quality are extremely high. Therefore, quality control and process observation cannot be omitted. This paper presents the current works of a camera based process control system. Hardware-based algorithms for estimation of machine parameters during the process are implemented on FPGA technology. In particular the process velocity is measured in real time which makes the system suitable for controlling tasks to react instantaneously on changes of the velocity.First experimental results on a controlled laser brazing process are presented. Additionally an evaluation of the accuracy of the hardware-based velocity measurement is given.

Laser material processes require constant energy input per unit length. Besides focal z-position, spot size, laser power and other process parameters, the relative travel speed (feed rate) of the laser spot on the work piece has the highest influence on the resulting energy input per unit length. In this paper a new metrology method is introduced, which enables users in industry and research to measure the real travel speed of the laser spot and the resulting contour of the trajectory.

Quality assurance in laser processing is often provided by post process inspections with machine vision solutions. When process stability gain is needed, one-dimensional signals like diodes or pyrometers which measure the emitted radiation of the laser process may be applied to closed-loop-control of e.g. the laser power. Such signals mostly provide short latency and good signal to noise ratio, but represent only mean values of the whole processing area or parts of it.On the other Hand secondary process radiation can provide information about the process stability, but may not always show the cause for process imperfections. To overcome the lack of spatial resolution in closed loop control, this paper explains how real-time computer vision improves existing processes and may even enable new laser processes. Furthermore an example machine vision algorithm is presented which measures kinematic properties of the process zone in real time. Such signals provide reliable information of the process state by recovering the influences which cause the process to leave its stable state.The shown system can be adapted to most laser processes (e.g. welding, brazing, cutting, selective laser melting, etc.). For complexity reasons most examples in this paper will be based on remote laser welding only.

Recently, near-infrared lasers show remarkable progress in terms of output power, long running stability and cost. The development of laser precision plastic welding technology utilizing these laser sources as one of main applications has been actively conducted all over the world. The authors studied and developed brand-new laser splicing technology as a new application of laser welding for thermoplastic film material fed at roll-to-roll handling process, which showed better bonding quality compared to the conventional splicing methods such as adhesive tape method, heat sealing method, and so on. In this report, basic laser splicing method for transparent thermoplastic films, correlation between laser processing condition and bonding condition, how to measure heating situation when laser irradiated, in-process controlling method, moreover high precision and photon absorber-free laser butt splicing technology which is state-of-the-art laser welding technology is described.

The Laser as a production tool has gained significant shares in industrial applications today. Laser materials processing is therefore a well established technique, especially in applications like welding, cutting, or surface treatment – benefitting from laser typical features like high processing speed, low heat input into the material, and precise manufacturing technique of high quality. Hence, it is essential to know the quality state of manufactured products. For many application areas this is also formalized through ISO 9000 and other by law enforced regulations. Thus applied quality control is an essential tool in modern manufacturing and necessary in order to keep production results in deterministic boundaries.

Advanced laser sources enable manufacturers to produce weld seams of high quality at high process velocities. These processes require high degrees of precision and furthermore, process parameters have to be kept in close limits. The welding speed is one of the most important parameters among laser power which has to be held constantly in order to achieve a stable quality of the manufactured products. Only a constant energy input per unit length may ensure steady qualities of welded or brazed seams.Even by highly sophisticated handling systems, the influence of mass inertia cannot be fully suppressed when moving with high accelerations. Small deflection angles at the processing head cause large displacements at the Tool Center Point (TCP).In this paper new approaches to measure the real velocity at the TCP seamlessly are being published. A new image processing technique provides the ability, to measure welding velocities at high precision and high sampling rates directly on the work piece. By combining the values of the measured laser power at the processing head with the actual velocity, this technology enables the direct measurement of the energy input per unit length at real time. This new measurement method offers a high degree of quality gain and may even empower the end user to keep welding depths in small boundaries. Especially laser welding at long focal distances and setups with handling systems of mere precision (i.e. remote welding) will benefit from this measuring method.Advanced laser sources enable manufacturers to produce weld seams of high quality at high process velocities. These processes require high degrees of precision and furthermore, process parameters have to be kept in close limits. The welding speed is one of the most important parameters among laser power which has to be held constantly in order to achieve a stable quality of the manufactured products. Only a constant energy input per unit length may ensure steady qualities of welded or brazed seams.Even by highly sophisticated handling systems, the influence of mass inertia cannot be fully suppressed when moving with high accelerations. Small deflection angles at the processing head cause large displacements at the Tool Center Point (TCP).In this paper new approaches to measure the real velocity at the TCP seamlessly are being published. A new image processing technique provides the ability, to measure welding velocities at high precision and high sampling rates directly on the work piece. By combining the...

Laser brazing of zinc coated steel is a widely established manufacturing process in the automotive sector, where high quality requirements must be fulfilled. The strength, impermeablitiy and surface appearance of the joint are particularly important for judging its quality. The development of an on-line quality control system is highly desired by the industry. This paper presents recent works on the development of such a system, which consists of two cameras operating in different spectral ranges. For the evaluation of the system, seam imperfections are created artificially during experiments. Finally image processing algorithms for monitoring process parameters based the captured images are presented.

The laser brazing of steel (e.g. galvanized DC04) with copper solder (usually CuSi3) is already established in automotive manufacturing. Reasons for this are process advantages like a low working temperature and thus, a low thermal distortion. In addition, the quality of the joint with respect to surface appearance, joint strength and impermeability is fully ensured. The major challenge for a wide industrial spreading of laser brazing is the high sensitivity of the process. Slight disturbances of process variables such as an inaccurate wire feeder or misalignment of laser beam to seam cause imperfections such as pores, holes or one-side or even improper wetting. However, today it is still hardly possible to observe in-situ those failures reliably during laser brazing. Hence, the goal is the development and qualification of a new online quality control system for laser brazing. Therefore, in the first step the mechanisms of different joint imperfections are analyzed and evaluated. In the second step the joint failures that occurred during the process are captured and analyzed by using two cameras simultaneously. One camera uses human visible light wavelengths and the second captures the near-infrared spectral region. For the spatial-resolved in-situ-detection of different process and quality characteristics both camera modules are integrated coaxially into the laser beam path.

Main focus of this contribution is an investigation on process monitoring methods for transparent thermoplastic film laser beam welding. Target is to find feasible approaches to monitor and control the welding process in common industrial applications. The welding process is supported by an IR-absorber between the join partners. The presented work is focused on three different wavelength ranges: Starting from the visible wavelength through near infrared to mid infrared wavelength. In these areas two kinds of sensors are used. The sensors are imaging and integrating systems. The detectors for visible and near infrared are integrated into the beam path.

The laser welding of thermoplastics has been established in several industrial applications, but it has not yet been able to weld transparent thermoplastics without an IR-absorber. However, by the use of special optics in combination with a proper wavelength, absorber-free laser beam welding can be utilized in a large number of applications primarily in medical device technology or in high-tech products. The availability of high brilliance fiber lasers with new wavelengths makes these applications possible. The different wavelengths are achieved by doping the fibers with the laser-active elements ytterbium (1060 – 1080 nm), erbium (1530 – 1600 nm) or thulium (1800 – 2100 nm). Starting from 1200 nm the intrinsic absorption of several visually transparent polymers reaches a sufficient value to allow laser welding without any IR-absorber. To generate a heat source in the joining area, the intensity distribution and the wavelength of the laser must be aligned to the absorption characteristics of the polymer. The usage of special optics with high numerical aperture keeps the laser intensity on top of the material and below the melting threshold. Only in the welding area does the intensity reach the necessary value to determine the welding of the transparent components.