Laser-directed energy deposition with wire (L-DED/W) offers high deposition and material utilization rates but often suffers from geometric inaccuracies and anisotropic mechanical properties due to unstable deposition dynamics and complex thermomechanical phenomena. To enable in situ monitoring and closed-loop control of final qualities such as geometry and hardness-which cannot be directly measured during deposition-this study employs the parameter-signature-quality (PSQ) framework. This work presents the first in situ multi-input multi-output (MIMO) closed-loop control of both deposition geometry and hardness in a directed energy deposition process. Building on the experimental foundation established in Part 1 of this study, a real-time MIMO control strategy is developed for the L-DED/W process. A long-short-term-memory (LSTM) network is used to model the nonlinear and dynamic relationships between process parameters (power and speed) and melt pool signatures, while hardness is classified using a combined set of process parameters and melt pool signatures within the PSQ framework. These models are integrated with a fuzzy logic controller to achieve closed-loop MIMO control, demonstrating effective regulation of melt pool geometry while maximizing the likelihood of achieving high hardness under process uncertainties. The results demonstrate the feasibility of in situ regulation of otherwise unmeasurable final qualities and highlight fuzzy logic control as a flexible and computationally efficient approach for multi-objective control in metal additive manufacturing.

Laser energy absorption plays an important role in determining process stability and energy efficiency in wire Directed Energy Deposition using a laser beam. However, the combined influence of wire geometry, beam positioning, and temperature-dependent optical properties on absorbed laser power remains insufficiently understood. This work presents an analytical framework for predicting the absorptance and absorbed power during the processing of Inconel 718. The model combines Monte Carlo ray tracing, Fresnel reflection theory, and a temperature-dependent Drude formulation in which the optical properties are related to electrical resistivity. A parametric investigation was conducted to evaluate the effects of wire-feeding angle, beam-wire offset, melt pool temperature, and wire temperature. The results showed that increasing the wire feeding angle altered the incidence-angle distribution of laser rays on the wire surface, resulting in non-monotonic variations in wire absorptance and absorbed power despite increasing beam interception. Furthermore, the interaction between wire and melt pool temperatures revealed three operating regimes governing the response of absorbed power to beam-wire offset. When the wire absorptance was lower than that of the melt pool, absorbed power increased with increasing offset, whereas the opposite trend occurred when the wire absorptance exceeded that of the melt pool. Between these regimes, a compensation condition was identified in which absorbed power remained nearly independent of beam-wire offset. This behavior occurred when the wire absorptance approached that of the melt pool, minimizing the influence of laser-energy redistribution between both surfaces. For the investigated geometry and optical assumptions, the compensation condition was associated with an approximately constant electrical-resistivity ratio and a constant relationship between the compensation wire temperature and melt pool temperature.

One challenge in laser beam welding is the variability in joint gaps encountered during autogenous welding of butt joints. This study therefore develops and evaluates an adaptive laser beam shaping technique that utilizes a deformable mirror. By integrating image processing and an adaptive Kalman filter, the proposed method provides real-time estimation of the gap width which varies from point to point along the joint. This capability allows for dynamic adjustments of the beam shape during processing through feed-forward control. Proof of concept was performed in welding sheet metal plates with stepwise changes in gap widths, up to 0.55 mm. The distortion of the welded parts and the topology of the weld seam were assessed both qualitatively and quantitatively using data from a laser line scanner. The data analysis revealed a reduction above 80% in workpiece residual distortion compared to conventional welding with a static circular beam shape. Additionally, welding quality at a 0.55 mm gap width met the laser welding standard (ISO 13919-1) level D. In contrast, approximately 10% of the measured points using a static circular beam did not meet the level D of this standard. The seamlessly integration of real-time gap measurement with adaptive beam shaping thus offers a promising solution to mitigate gap variability in laser beam welding of butt joints. This approach also highlights the broader potential of adaptive beam shaping in high-power metal processing. 

Laser welding processes are highly sensitive to the alignment of the laser beam with respect to the joint location. Even minor deviations—referred to as beam offsets can induce critical defects in the final weld. This issue is particularly pronounced in stake welding of hidden T-joints, where the joint interface is not accessible from the top surface, rendering conventional vision-based seam tracking methods ineffective. To address this challenge, this study proposes a computer vision-based system employing LED illumination to acquire real-time images of the melt pool for early detection of beam offsets. The underlying hypothesis is that variations in melt pool geometry are indicative of beam misalignment; however, this relationship is complex and non-linear, necessitating a data-driven approach. A convolutional neural network is developed and trained to classify melt pool images into categories representing correct alignment and beam offset conditions. Experimental validation is conducted using image datasets obtained from controlled laser welding trials. The proposed method demonstrates high classification accuracy and holds significant potential for in-process quality assurance and defect prevention in laser stake welding of T-joints.

Directed energy deposition using laser beam and wire feed is a critical technology in high-productivity metal additive manufacturing, enabling precise deposition and fabrication of components with high quality and deposition rates. The interaction between the laser beam and metal is highly temperature-sensitive, affecting metal transfer, melting, solidification, and phase transformations. Effective control of heat input is crucial for influencing the geometry, microstructure, and overall integrity of the fabricated parts.

This study investigates the correlation between the melt pool top surface boundary contour and the immediate solidification temperature, utilizing machine vision and radiation pyrometer measurements. The research highlights the significance of melt pool length as an indicator of temperature variations during deposition. System identification techniques were employed to develop a predictive model of the dynamic relationship between melt pool length and temperature, aimed at enhancing process control strategies. Our approach substitutes off-axis pyrometry with a cost-effective coaxial vision camera integrated into the laser head. By incorporating a vision camera without active illumination, the study offers a compact, omnidirectional solution. Comparative analysis of melt pool length and area measurements demonstrates the superiority of length-based correlations with temperature data.

This work addresses the challenges of heat-input control in directed energy deposition laser beam wire processes and suggests future research directions in various metal alloys, complex geometries, and advanced sensing and automatic control methodologies.

Robotized laser beam welding demands precise control, with accurate joint gap estimation essential for adaptive gap-bridging. Challenges such as smoke, surface irregularities, and spectral emissions hinder classification performance. This study applies deep learning models to enable real-time gap classification during autogenous butt joint welding using beam-shaping. Images captured from varying joint gaps allowed evaluation under dynamic conditions. Four models were trained and assessed, with the best model surpassing application accuracy requirements. The findings support the development of adaptive welding systems for consistent weld quality in noisy, fluctuating environments.

Effective thermal management is essential in metal additive manufacturing to ensure process stability and desirable material properties. Directed energy deposition using a laserbeam and wire (DED-LB/w) enables the production of large, high-performance components but remains sensitive to adverse thermal effects during multilayer deposition due to heat accumulation. While prior studies have investigated interlayer temperature control and substrate preheating in DED modalities, including laser-powder and arc-based systems, the influence of substrate preheating in DED-LB/w has not been thoroughly examined.

This study employs substrate preheating to simulate heat accumulation and assess its effects on melt pool geometry, wire–melt pool interaction, and the microstructural evolution of Alloy 718. Experimental results demonstrate that increased substrate temperatures lead to a gradual expansion of the melt pool, with a notable transition occurring beyond 400 ◦C. Microstructural analysis reveals that elevated preheat temperatures promote coarser secondary dendrite arm spacing and the development of wider columnar grains. Moreover, Nb-rich secondary phases, including the Laves phase, exhibit increased size but relatively unchanged area fractions. Observations from electrical conductance measurements and coaxial visual imaging show that preheat temperature significantly affects the process dynamics and microstructural evolution, providing a basis for advanced process control strategies.

This study presents a vision-based closed-loop tracking system designed specifcally for robotic laser beam welding of curved and closed square butt joints. The proposed system is compared against 11 existing solutions reported in the literature, which employ various sensor principles for the same application. The system employs a non-contact, non-intrusive machine vision approach, seamlessly integrated into the laser beam welding head to mitigate challenges associated with sensor forerun. Key features include an of-axis LED illumination, an optical flter, and a movable actuator, facilitating real-time image processing and closed-loop control during the welding process. Experimental validation was conducted on stainless-steel plates with complex closed square butt joints. The system achieved a mean absolute joint-to-beam ofset of 0.14 mm across four test cases, with a maximum ofset of 0.85 mm, demonstrating its robustness and precision. Comparative analysis underscores the proposed method’s advantages, showcasing its potential for industrial applications in laser beam welding of geometrically challenging joints.

Robotized laser beam welding is one important process in manufacturing, offering efficient welding while minimizing the heat input. Nonetheless, this method is sensitive to various deviations, including fixture problems, heat-induced distortions, and inaccuracies in tool handling. Such deviations can lead to significant defects like lack of fusion, particularly when welding square butt joints without gaps. Detecting these defects through visual inspection or non-destructive methods is challenging.

To address this, real-time monitoring and automatic intervention are necessary. One effective sensor for monitoring laser beam welding is the photodiode, which captures optical emissions from the process. Research has demonstrated correlations between these emissions and process stability. Photodiodes are costeffective and easily integrated into welding tools, making them ideal for industrial applications. However, the challenge lies in analyzing the output signals and defining thresholds for identifying deviations from normal conditions. Thus, there's a need for an automated method to set threshold values based on measured data. Machine learning offers a solution, particularly through supervised, unsupervised, or semi-supervised methods. Supervised machine learning requires labeled data, involving time-consuming experiments with nominal and deviating cases, making it less feasible for industrial setups.

This paper suggests using unsupervised learning for anomaly detection, relying solely on data from nominal welding cases for model training. In this approach, a model is trained using photodiode data from a single nominal weld case and subsequently tested on data collected during experiments involving laser beam offsets during welding. The results demonstrate the promise of this method for monitoring closed square butt-joint laser beam welding, even with limited training data from nominal cases. 

Laser Beam Welding (LBW) requires precise control to ensure high-quality welds. Accurate classification of joint gap widths and detection of tack welds are crucial for optimizing the process and enhancing product reliability.

This study investigates the application of Convolutional Neural Networks (CNNs) and Recurrent Neural Networks (RNNs) to classify instant joint gap widths and detect the presence of tack welds during welding. The goal is to facilitate adaptive joint gap bridging in robotized and autogenous butt joint welding. Sequences of images resembling a time series were captured during welding of prepared workpieces with varying joint gap widths along the joint line.

The results demonstrate that CNNs significantly outperform RNNs, achieving over 99 percent classification accuracy in both validation and test datasets, and 96 percent accuracy under conditions of substantial noise. These findings underscore the potential of CNNs in enhancing the precision and adaptability of welding automation. However, challenges remain in generalizing the CNN model to diverse and noisy operational environments.