Explore the vast range of titles available.

Laser welding technology, recognized for its advantages such as its fast welding speed, high productivity, and energy concentration, is widely used in the industrial manufacturing field [...]

Welding monitoring technology based on machine vision has been widely researched in academic and industry, especially in the background of Industry 4.0, in that it can contribute to welding quality and productivity improvement. This paper outlines the technical points of welding status monitoring based on machine vision, including hardware and software. First of all, in the hardware part, the active and passive vision systems are briefly introduced, as well as the key steps in experimental deployment, such as the configuration of optical sensors and optical filters based on different detection objects. Secondly, some related image processing techniques in welding monitoring are also comprehensively reviewed. Additionally, the observed objects and their morphological characteristics of vision-based welding process monitoring are enumerated. On this basis, a series of intelligent models as well as optimization methods for recognition and classification in visual monitoring are considered in detail. Finally, potential research challenges and open research issues of welding visual monitoring are discussed to present an insight into future research opportunities. The main purpose of this paper is to provide a reference source for the researchers involved in intelligent robot welding.

In order to explore the relationship between the welding process and welded quality, a multiple sensor fusion system was built to obtain the photodiode and visible light information during the welding. Features of keyhole, plasma and spatters were extracted from five sensors, including two photodiode sensors, one spectrometer sensor, one ultraviolet and visible light sensing camera and one auxiliary illumination sensing camera, 15 features were analyzed by normalization and principle component analysis, and principle component numbers was chosen as input parameters of support vector machine classification, Three weld quality types were defined according to the weld seam width and weld depth. The overall accuracy of training data was 98%, and the overall accuracy of testing data was 91%, respectively. Experimental results showed that the estimation on welding status was accurate and effective, thus providing an experimental example of monitoring high-power disk laser welding quality.

The penetration status profoundly influences the dynamic behaviors of keyhole and molten pool during laser welding. This paper presents a three-dimensional numerical simulation model with a ray-tracing method, which is dedicated to investigating the different penetration statuses in laser welding of type 304 stainless steel. In the proposed model, the factors include melting, evaporation, solidification, the vapor-induced plume heat transfer, buoyancy force, Marangoni effect, surface tension, and recoil pressure. Unlike existing similar work, three types of penetration status are investigated, including non-penetration, insufficient penetration, and full penetration. The weld cross-section geometry of simulation results is in good agreement with the experimental results. The behaviors of keyhole and molten pool, energy absorbed by the weldment, and flow field in the molten pool are discussed in details. It is found that the penetration status affects the dynamics of keyhole and molten pool, the temperature field, the absorbed energy, and the flow field, which is greatly connected with weld bead formation and joint quality.

Real-time detection of welding defects in resistance spot welding is a complex challenge. Dynamic resistance (DR) reflects nugget growth and varies with defect types, serving as a key indicator. This study presents an online quality evaluation and defect classification method for Q235 low-carbon steel welding. Welding current and voltage were collected in real-time, and DR signals were processed employing a second-order Butterworth low-pass filter featuring zero-phase processing to enhance accuracy. Empirical mode decomposition (EMD) decomposed these signals into intrinsic mode functions (IMFs) and residuals, which were classified by a support vector machine (SVM). Experiments showed the EMD-SVM method outperforms traditional approaches, including backpropagation (BP) neural networks, SVM, wavelet packet decomposition (WPD)-BP, WPD-SVM, and EMD-BP, in identifying four welding states: normal, spatter, false, and edge welding. This method provides an efficient, robust solution for online defect detection in resistance spot welding.

The laser welding quality is determined by its welding statuses, and online welding statuses are depicted by the real-time signals captured from the welding process. A multiple-sensor system is designed to obtain information as comprehensive as possible for welding statuses monitoring. The multiple-sensor system includes an auxiliary illumination visual sensor system, an ultraviolet and visible band visual sensor system, a spectrometer and two photodiodes. The signals captured by different sensors are analyzed via signal or digital image processing algorithms, and distinct features are extracted from these signals to depict the online welding statuses. A deep learning framework based on stacked sparse autoencoder (SSAE) is established to model the relationship between the multi-sensor features and their corresponding welding statuses, and Genetic algorithm (GA) is applied to optimize the parameters of the SSAE framework (SSAE-GA). The proposed framework achieves higher accuracy and stronger robustness in monitoring welding status by comparing with the backpropagation neural network, support vector machine and random forest. Three new experiments with different welding parameters are implemented to validate the effectiveness and generalization of our proposed method. This study provides a novel and accurate method for high-power disk laser welding status monitoring.

The extension direction of welding defects is random and uncontrollable, while magneto-optical imaging detection has a good imaging effect on defects perpendicular to the magnetic field direction. At present, magneto-optical detection methods may fail to detect small weld defects parallel to the direction of the magnetic field. To overcome this problem, a non-destructive testing method based on magneto-optical imaging under a vertical combined magnetic field (VCMF) is proposed. The paper first establishes a simulation model to compare and analyze the magnetic leakage characteristics of cross grooves under a constant magnetic field (CMF), an alternating magnetic field (AMF), a rotating magnetic field (RMF), a parallel combined magnetic field (PCMF), and VCMF excitation, proving that detection does not easily fail under VCMF. Secondly, by changing the size of the CMF in the VCMF simulation model, it was found that, as the CMF intensity increases, a new maximum value will appear on the side of the defect contour close to the sample area. This maximum value increases with the increase of the CMF intensity, which can lead to misjudgment of the defect contour, that is, false contours. Finally, magneto-optical imaging was used to verify the imaging effect of weld defects under VCMFs. The results indicate that more comprehensive defect information can be detected under VCMFs. When the maximum value of the excitation current of the AMF is at least 12 times the excitation current of the CMF, there will be no false contour defects.

Metal–polymer hybrid structures have been widely used in research into their lightweight automotive applications, because of their excellent comprehensive properties. As an efficient technology for automatic connection of dissimilar materials, laser joining has great application potential and development value in the field of lightweight automotive design. However, due to the physical and chemical differences between metals and polymers, the formation quality of the hybrid joint is seriously affected by defects, low bonding strength, and poor morphology. Meanwhile, it is difficult to meet the demands for lightweight automobiles by considering only bonding strength as the target for forming quality. Therefore, the technological characteristics of metal–polymer hybrid structures for use in lightweight automotive applications are analyzed, the advantages and problems of laser-joining technology are discussed, and the characterization indexes and regulation measures of forming quality in laser joining are summarized. This paper which provides reference and guidance for reliable forming, intelligent development, and lightweight application of laser joining for polymer–metal hybrid structures.

Laser welding experiments involving amorphous thermoplastic polymer (PMMA) and 304 austenitic stainless steel plates were conducted to explore the influence of laser welding process parameters on plastic–metal joints. A high-speed camera was applied to record the dynamics of the molten pool and the formation of bubbles to reveal the bonding mechanisms of the hybrid joints. The influence of process parameters on the joints was analyzed using temperature measurements performed with thermocouples. The microstructure morphology of joints was observed using SEM. The mechanical characterization of the hybrid joints was carried out to understand the effect of the welding conditions on the weld morphology, flaws and shear stress. Different interface temperatures resulted in two types of bubbles and led to different weld morphology characteristics. A stable hybrid joint with the best shear stress was produced with a laser line energy of 20.16 J/mm2, a temperature of 305 °C and small bubbles. The shear stress of the effective joint under the maximum mechanical resistance was 4.17 MPa. The chemical bonds (M-O, M-C) and mechanical anchoring that formed on the steel’s surface contributed to the joint bonding. Range analysis provided guidance for identifying the impact of individual factors in the shear stress for the laser welding of plastic–metal.

The dynamic characteristics of rubber isolation pad (abbreviated as RIP) after service under the high temperature thermal oxygen aging and the variable preloads have preload dependence and thermal oxygen aging dependence, which is a crucial problem for matching the vibration isolation system of air conditioner compressor to reveal the dynamic characteristic mechanism of the RIP with different preloads and thermal oxygen aging conditions. The Peck model is first introduced to characterize the thermal oxygen aging factor, the fractional derivative Kelvin-Voigt thermal oxygen aging-perturbation model (FDKVTPM) and the Coulomb frictional thermal oxygen aging-perturbation model (CFTPM) are established to describe the frequency dependence and the amplitude dependence, respectively. The thermal oxygen aging-dynamic characteristic model of the RIP is built by considering the influence of variable preloads, the model parameters under different preloads are further identified, the validity of the model was examined by the experimental data. The concepts of the stiffness transition point (STP) and the stiffness transition frequency (STF) are innovatively proposed to better describe softening effect of the RIP under variable preload and variable amplitude working conditions. The results show that the static stiffness of RIP increases by 20.7%, the dynamic stiffness increases by 9.3%, and the loss factor decreases by 35% after thermal oxygen aging under different preload conditions, which can lay a theoretical foundation for in-depth study of the stiffness matching and optimization of air conditioner compressor with the RIP.