Explore the vast range of titles available.

In this paper, a metaheuristic optimized multilayer feed‐forward artificial neural network (ANN) controller is proposed to extract the maximum power from available solar energy for a three-phase shunt active power filter (APF) grid connected photovoltaic (PV) system supplying an arc welding machine. Firstly, in order to improve the maximum power point (MPP) delivered by PV arrays and to overcome the drawbacks in the conventional MPPT method under irradiation variation, a hybrid MPPT controller is designed, in which the input parameters include the PV array voltage and current, and the output parameter is the duty cycle of the DC/DC boost converter. The proposed approach abbreviated as ANN-ACO MPPT controller is based on an ant colony optimization (ACO) algorithm which is useful to train the developed ANN and to evolve the connection weights and biases to get the optimal values of duty cycle converter corresponding to the MPP of a PV array. Secondly, aiming to meet the various grid requirements such as power quality improvement, distortion free signals etc., a three-phase shunt APF is utilized, and a direct power control algorithm is designed for distributing the solar energy between the DC-link capacitor, arc welding machine and the AC grid. Finally, the performance of proposed control system is confirmed by simulation tests on a 12.2 kW PV system. Both simulation and experimental results have demonstrated that the deigned ANN-ACO MPPT controller can provide a better MPP tracking with a faster speed and a high robustness with a minimal steady-state oscillation than those obtained with the conventional INC method. Also, with the use of a three-phase shunt APF, all the power fluctuations from the arc welding machine disturbances are damped out and the output active and reactive power become controllable.

WAAM has been proven a promising alternative to fabricate medium and large scale metal parts with a high depositing rate and automation level. However, the production quality may deteriorate due to the poor deposited layer surface quality. In this paper, a laser sensor based surface roughness measuring method was developed for WAAM. To improve the surface integrity of deposited layers by WAAM, different machine learning models, including ANFIS, ELM and SVR, were developed to predict the surface roughness. Furthermore, the ANFIS model was optimized by GA and PSO algorithms. Full factorial experiments were conducted to obtain the training data, and the K-fold Cross-validation strategy was applied to train and validate machine learning models. The comparison results indicate that GA–ANFIS has superiority in predicting surface roughness. The RMSE, R2, MAE and MAPE for GA–ANFIS were 0.0694, 0.93516, 0.0574, 14.15% respectively. This study could also provide inspiration and guidance for surface roughness modelling in multipass arc welding and cladding.

Due to its unique benefits over standard conventional “subtractive” manufacturing, additive manufacturing is attracting growing interest in academic and industrial sectors. Here, special emphasis is given to wire arc additive manufacturing (WAAM), a directed energy deposition process that employs arc welding tools and wire to build metallic components by deposition of weld material. The WAAM process has several advantages, e.g., low cost, rapid deposition rate, and suitability for large complex metallic components. However, many WAAM challenges such as large welding deformation, undesirable porosity, and components with high residual stress remain to be overcome. Multidisciplinary cross-fusion research involving manufacturing, material science, automation control, and artificial intelligence/machine learning (ML) are deployed to overcome the above-mentioned problems. ML enables improved product quality control, process optimization, and modeling of complex multiphysics systems in the WAAM process. This research utilizes a data-driven literature review process, a defined and deliberate approach to localizing, evaluating, and analyzing published studies in the literature. The most relevant studies in the literature are analyzed using keyword co-occurrence and cluster analysis. Numerous aspects of WAAM, including design for WAAM, material analytics/characterization, defect detection/monitoring, as well as process modeling and optimization, have been examined to identify state-of-the-art research in ML for WAAM. Finally, the challenges and opportunities for using ML in the WAAM process are identified and summarized.

In gas metal arc welding (GMAW) processes, including wire arc additive manufacturing (WAAM), machine learning (ML) is emerging as a powerful tool for monitoring both process and product anomalies. However, a significant challenge in real industrial environments is the reliance on large, balanced datasets for training supervised learning models. To address this issue, a shift toward unsupervised learning is gaining attention in this research field, offering the potential to work effectively with small and unbalanced datasets. However, different materials, sensors, and welding technologies have been used in the literature, making complex the comparison of the results. This work fills that gap by presenting a comprehensive comparison of both supervised and unsupervised learning methods. An experimental campaign was conducted on Invar 36 alloy—a material with limited WAAM research—where 15 wall structures were deposited with varying process parameters using the natural dip transfer process, aiming to identify the optimal parameters for this alloy. Data on welding current and voltage were captured, and during the qualification procedure, anomalies were detected, some of which led to product defects. Supervised, unsupervised, and semi-supervised ML approaches, along with a detailed frequency domain analysis of the collected signals, were applied to process the obtained unbalanced dataset. The results provide key insights: while supervised learning models can be applied to anomaly detection in small and unbalanced datasets, they are prone to overfitting, which limits their practical use due to the prevalence of normal cases over anomalies in the dataset, resulting in higher number of missed anomalies. In contrast, unsupervised models, with their lower generalization capability, tend to exhibit higher false alarm rates but better performance to identify anomalous data. This work not only compares in depth these data analytics methodologies but also offers guidance on selecting the appropriate ML algorithm based on specific industrial objectives and provides insights into the printability of Invar 36 for WAAM applications under natural dip transfer process.

An analysis of common reinforcement methods of machine parts and theoretical bases for the selection of their chemical composition were carried out. Prospects for using flux-cored arc welding (FCAW) to restore and increase the wear resistance of machine parts in industries such as metallurgy, agricultural, wood processing, and oil industry were presented. It is noted that conventional series electrodes made of tungsten carbide are expensive, which limits their widespread use in some industries. The scope of this work includes the development of the chemical composition of tungsten-free hardfacing alloys based on the Fe-Mo-B-C system and hardfacing technology and the investigation of the microstructure and the mechanical properties of the developed hardfacing alloys. The composition of the hardfacing alloys was developed by extending the Fe-Mo-B-C system with Ti and Mn. The determination of wear resistance under abrasion and impact-abrasion wear test conditions and the hardness measurement by means of indentation and SEM analysis of the microstructures was completed. The results obtained show that the use of pure metal powders as starting components for electrodes based on the Fe-Mo-B-C system leads to the formation of a wear-resistant phase Fe(Mo,B)2 during FCAW. The addition of Ti and Mn results in a significant increase in abrasion and impact-abrasion wear resistance by 1.2 and 1.3 times, respectively.

Even though arc welding is widely utilized to join metallic parts with high reliability, the prediction and control of welding quality is challenging owing to difficulties in the prediction of weld penetration depth and the backside bead. In this study, an effective method for predicting weld penetration based on deep learning was proposed to control the welding quality in-process. The topside weld pool image was closely related to the welding quality and penetration depth and was also an accurate indicator of the state of welding over time. A prediction model for penetration depth using a topside weld pool image was constructed. Semantic segmentation based on a residual neural network was then performed on the acquired weld pool image. Consequently, an accurate weld pool shape was extracted. In addition, a penetration regression model was constructed based on a back-propagation neural network. Finally, the penetration depth (corresponding to the weld pool shape) was extracted via segmentation. The segmentation and regression models were combined to create a penetration prediction model. Considering a gas tungsten arc welding (GTAW) process, the predictions obtained from the proposed method were evaluated experimentally. In the validation process, the developed model quantitatively predicted the penetration depth in tungsten gas arc welding. The mean absolute error was 0.0596 mm with an R2 value of 0.9974. The model developed in this study can be utilized to predict weld depth penetration and in-processing time using surface images of the weld pool.

With arc welding machines, welding is only performed at optimum operating points. Determination of optimum operating points is important so as for welding machines which will be produced in future to be developed in a manner to operate in such parts. In this study, an Artificial Neutral Networks method was used in order to determine the optimum operating points of Electric Arc welding machine. For this purpose, a measurement system used to get the current measurements during the welding operation. A welding process includes some stages like initial case; transient case and operation case respectively. So as to use ANN model, a data set was established via time series. ANN is trained with 90% of data set and tested with 10% thereof. At the end of the test, a prediction of 97.49% was made according to the regression value. And according to the MSE value, it was understood that a successful prediction was made with an error of 0.00353075 values.

Wire arc additive manufacturing (WAAM) is an additive manufacturing process for building large-sized metal components using gas metal arc welding technology. Detecting defects during deposition is critical for halting production of low-quality components, thereby reducing waste and associated costs, and allowing timely process adjustments. This necessitates the integration of online anomaly detection systems in modern WAAM systems. While most existing methods rely on high-frequency data acquisition, this research explores the feasibility of using low-cost and low-frequency acquisition systems for anomaly detection, leveraging the advancements in Industry 4.0 and IoT protocols like MQTT. This study presents an IoT-driven intelligent system for WAAM, where data is collected at a low frequency of 10 Hz and processed using unsupervised machine learning techniques to develop an anomaly detection service. The methodology involves using a data-driven model to forecast WAAM process variables and detect anomalies through a Gaussian mixture model based on estimation errors between model estimation and real values collected from the process. The results obtained from various models were compared, specifically polynomial autoregression with exogenous variables (polyARX), autoregressive neural network with exogenous variables (ARXNN), and long short-term memory (LSTM). The proposed system demonstrated high performance in anomaly detection, achieving an F2-score of 90.4% with the LSTM model and 86.28% with the ARXNN model when used to forecast the WAAM process. These results are comparable to performance reached with supervised machine learning algorithms or with results reached by previous studies which employ high-frequency data. Furthermore, the results show that low-frequency data, when processed with complex ML techniques, can reduce the chance of missing anomalies by 40% compared to traditional statistical methods, thanks to a higher recall. Finally, the implementation of the system using containerisation technologies like Docker was discussed, and post-deployment results confirmed the findings. Additionally, a graphical user interface was developed for operator interaction, utilising emerging IoT technologies such as Grafana and SQL databases, which represent additional parts of the IoT-driven intelligent WAAM system proposed in this work.

A 2219 aluminum alloy was manufactured by ultrasonic impact arc additive welding, and well-formed multilayer and multipass deposition parts were obtained. The residual stresses on the top and substrate of 2219 aluminum alloy samples deposited by the conventional arc and ultrasonic impingement arc were measured by ultrasonic stress testing equipment. Through experiments, the following conclusions were reached: the residual stress of those specimens subjected to ultrasonic impact is lower than that of the specimens without ultrasonic impact, and the residual stress of the arcing and quenching positions is the most obvious reduction. The deformation of the substrate treated by ultrasonic impact treatment is less than that of the sample without ultrasonic impact treatment.

Three different AgZnO contact materials with varying In2O3 contents were prepared using internal oxidation. The electrical life, welding force, arc energy, and arc ignition time of these three materials under AC220 V and 20 A resistive load conditions were tested using simulated electrical performance testing equipment. The test results and the arc erosion morphology on the contact surface after the test were analyzed. Research has found that when the In2O3 content is 0-3%, as the In2O3 content increases, the arc energy and arc time of the contact material gradually decrease, and the anti-welding performance gradually increases. Although it may cause changes in the physical properties of the material, it greatly helps the anti-welding performance of the material, thus reducing its impact on the material’s performance. The addition of In2O3 is beneficial for suppressing material transfer and splashing. When the amount of In2O3 added is 3%, the surface burn morphology and other electrical performance parameters of the material are better.