The TC18 near-β titanium alloy exhibits significant potential for aerospace applications owing to its superior fatigue resistance. However, achieving an optimal balance between strength and ductility remains a critical challenge that limits its widespread engineering application. In this study, in-situ rolling combined with a three-stage post heat treatment was employed to enhance the mechanical properties of TC18 alloy fabricated by laser-arc hybrid additive manufacturing. The fine grains with multilevel microstructure consisting of coarse basketweave primary α (αP), fine intersecting secondary α (αS), and discontinuous grain-boundary α (αGB) were successfully achieved through controlled hot deformation and thermal cycling, resulting in an excellent strength–ductility combination, with an ultimate tensile strength of 1095 MPa and an elongation of 14%. The refined grains and relatively high volume fraction of αP restricted the available space for αS precipitation, thereby enhancing deformation compatibility. Meanwhile, the uniform distribution of αS increased dislocation storage capacity and strain-hardening capability, demonstrating a strong capacity to improve ductility without compromising high strength.

The purpose of this paper is to establish the quantitative relationship between the wire and arc additive manufacturing (WAAM) process parameters and four objectives including the size, heat input, grain and performance. So as to lay a good initial shape and performance foundation for the subsequent in-situ rolling. The experimental matrix was designed based on the response surface methodology (RSM) and the multi-objective optimization was performed based on the forming efficiency and deformation uniformity. All of the final polynomial models showed that the F-ratio is greater than the corresponding F0.05 and the P-value is less than 0.0001 in the 95% confidence level significance test. The optimum initial states showed good reactions when set at w = 2.5 m/min, v = 187 mm/min, I = 178 A, T = 93 degrees C. Compared with the original high-efficiency deposition processes with higher overlapping rate and constant force, the optimized deposition processes with optimal offset and constant deformation can result in more uniform and refined grain structures, leading to a 5.9% increase in average tensile strength and a 37.8% enhanced in average elongation. These findings lay a solid foundation for optimizing the high-precision and high-performance hybrid additive manufacturing (HAM) process planning of titanium alloy forgings.

Wire Arc Additive Manufacturing (WAAM) is an advanced digital technology for three-dimensional solid manufacturing. In contrast to traditional subtractive and equal-material manufacturing methods, WAAM is founded on the "bottom-up" layered discrete free form of digital 3D models, offering innovative design and manufacturing flexibility. This technology is not limited by part shapes and can efficiently create complex structural components that are difficult to produce with traditional methods. To tackle challenges in process parameter selection and predicting forming outcomes in practical arc additive manufacturing, a precise and efficient mathematical method has been devised to forecast the morphology of single-pass forming. This method enables rapid and convenient process parameter selection for Wire Arc Additive Manufacturing and assists in quality control during forming processes. This article introduces a pure convolutional neural network (CNN) model along with a loss function. Based on a single-pass single-layer wire arc additive manufacturing experiment, the CNN algorithm uses process parameters as input to predict the model and develop a comprehensive prediction model for the cross-sectional profile of the weld bead. Furthermore, employing this pure CNN network model and loss function greatly aids in predicting the single-layer morphology of arc additive manufacturing. The results show that the method proposed in this article can accurately forecast the cross-sectional profiles of single-layer single-pass and multi-layer single-pass welding beads in arc additive manufacturing.

Surface defects that affect the quality of parts are a particularly significant issue in wire arc additive manufacturing processes (WAAM). Therefore, how to effectively control their surface quality has become a focus of researchers’ attention. However, due to limited computing power and storage space of terminal devices, it is difficult to deploy defect detection models. Therefore, We present a lightweight WAAM weld surface defect detection algorithm based on YOLOv8n, called high-alternative novel YOLO (HAN-YOLO). Specifically, a novel lightweight adaptive Inverted bottleneck (NLAIB) is designed to optimize lightweight network architectures while significantly improving inference speed and computational efficiency. Subsequently, a lightweight alternative alterable kernel convolution (AAKConv) is employed to improve detection accuracy while reducing model parameters and complexity. Furthermore, the High-Level Screening Feature Fusion Pyramid (HS-FPN) was integrated to achieve multi-scale object detection, enhancing the model’s feature selection and fusion capabilities. Finally, experiments on the 3440-WAAM weld surface defect dataset, NEU-DET dataset and Weld dataset are made to test the validity of HAN-YOLO. The experimental results show that, compared with YOLOv8n, the model parameters and GFLOPs of HAN-YOLO are reduced by 44.1

As a typical deformation-strengthened alloy, Al-Mg alloys show great potential for hybrid manufacturing when integrated with the high deposition efficiency of wire arc additive manufacturing (WAAM), magnetic field (MF, 0.2T/0.4T), and in-situ hot rolling (HR, 4 kN). This study systematically evaluates the external morphology and internal quality of samples processed under different conditions. The Lorentz force generated by MF enhances molten pool stirring and reduces thermal gradients, effectively suppressing columnar grain growth and mitigating elemental segregation. Magnetic stirring also improves interlayer surface uniformity, minimizing post-processing requirements. HR lowers layer height and shortens pore floatation paths, thus reducing pore size and number. Simultaneously, plastic deformation enhances dislocation strengthening and refines grains. The compressive stress from HR offsets thermal tensile stress, reducing residual stress. Optimized conditions (0.2 MF+HR+WAAM) yielded superior mechanical properties: ultimate tensile strength (UTS) of 363 MPa, yield strength (YS) of 262 MPa, and elongation (EL) of 27.6 %, representing increases of 16.7 %, 19.1 %, and 37.3 % over conventional WAAM. This work provides an efficient, cost-effective strategy for fabricating highperformance Al-Mg components via additive manufacturing.

Considering the deformation-strengthening benefits of Al-Mg alloy and the high forming efficiency offered by wire and arc additive manufacturing (WAAM), the microstructure evolution and strengthening mechanism of hybrid interlayer hot rolling and wire arc additive manufacturing (HR-WAAM) samples have been systematically investigated in this study. The results indicate that interlayer hot rolling can effectively reduce the size and number of pores, which diminishes the stress concentration areas. Additionally, rolling deformation significantly enhances the effect of dislocation strengthening. Furthermore, a high density of dislocations can promote recrystallization to refine grain size, while also improving grain orientation, all of which contribute to better stress distribution. Due to these reasons, the strength and toughness of the alloy are notably improved. The average ultimate tensile strength (UTS), yield strength (YS), and elongation (EL) values achieved by HR-WAAM samples were 338 MPa, 276 MPa, and 20.9%, respectively. These values represent increases of 28.5%, 41.5%, and 38.4% compared to conventional WAAM samples. These findings are expected to provide an efficient and cost-effective method for additive manufacturing (AM) of deformation-strengthened aluminum alloys.

0Cr16Ni5Mo1 super martensitic stainless steel has excellent weldability and is an economical material with a high life cycle and low cost, but there are few researches and applications of this material in additive manufacturing. In order to realize the application of 0Cr16Ni5Mo1 large-area laser cladding technology, the multi-track lap cladding of the material was studied. In this work, a multi-physical finite element model of multi-layer multi-track laser cladding was established, taking into account thermodynamic processes such as phase transition, Marangoni convection, and buoyancy. The flow and heat transfer behavior of 0Cr16Ni5Mo1 in multi-layer multi-track laser cladding process and the characteristics of the molten pool are studied. The research focused on the flow heat transfer behavior and molten pool characteristics of 0Cr16Ni5Mo1 during multi-layer multi-track laser cladding. The discussed aspects include the evolution history of the temperature field within the molten pool, flow field characteristics, molten pool dimensions, and dilution ratio under various laser powers and overlap rates. The results show that with the increase of overlap rate, the morphology of molten pools in different clad tracks will also change, and the flow rate, dilution ratio, and length of molten pools in the second track are negatively correlated, while the temperature and height of molten pools are positively correlated. As the laser power increases, all the characteristic quantities are positively correlated with it.

The near net shape forging of a preform fabricated using additive manufacturing (AM) technique has attracted significant attention due to its exceptional material utilization rate. However, the complexity of the parts hinders its further development. This study investigated the hot deformation behavior of TC4-DT titanium alloy fabricated by wire and arc additive manufacturing (WAAM) with in-situ forging. The isothermal compression samples underwent homogenizing treatment to eliminate layer bright lines before being subjected to deformation at temperatures ranging from 800 to 950 degrees C and strain rates ranging from 0.01 to 1 s-1 with the height reduction of 60%. Subsequently, the hot deformation constitutive equations and hot processing map were established to analyze the characteristics of hot deformation and microstructure evolution. The results demonstrate that the hyperbolic sine constitutive equation considering strain can accurately predict flow stress under arbitrary deformation conditions, with an average relative error of 7.23%. Furthermore, microstructure analysis under different deformation conditions validated the applicability of the hot processing map, which identified preferable and easily achievable in-situ hot forging regions at temperatures between 900 and 950 degrees C and strain rates between 0.05 and 1 s-1 with the strain exceeded 0.4. Finally, WAAM combined with optimized in-situ hot deformation processing enables the production of macrostructures consisting of fully equiaxed prior-beta grains while maintaining isotropy in mechanical properties, thereby providing a solid foundation for direct additive manufactured complex forgings featuring uniformly fine equiaxed grains and highly comprehensive properties.

GH4169D is an age-strengthened nickel-based superalloy designed according to the improved GH4169 superalloy, which has become a remarkable candidate material for aero engines' hot-end components. However, large columnar grains and obvious anisotropy of mechanical properties often occur in this superalloy, which is fabricated by conventional wire and arc additive manufacturing (WAAM). To solve these problems, hybrid arc and micro-rolling additive manufacturing (HARAM) has been proposed. HARAM operates by combining WAAM with the rolling process. Herein, GH4169D superalloy samples were fabricated by WAAM and HARAM. Further, microstructures and mechanical properties of the samples under different heat treatments were investigated. Results show that with micro-rolling applied, large columnar grains became finer. In addition, the tensile strength of HARAM-ed GH4169D was significantly improved compared with WAAM-ed GH4169D (48 MPa in the X direction and 90 MPa in the Z direction), and the anisotropy of mechanical properties of HARAM-ed GH4169D was effectively eliminated. Homogenization plus solution plus double aging heat treatment effectively eliminated Laves segregation phase and induced the recrystallization of HARAM-ed GH4169D, leading to more finer and uniform grains than those without heat treatment, thereby, making the comprehensive properties optimal (the tensile strength and elongation were 1366 MPa and 25.0% in the X direction and 1354 MPa and 24.6% in the Z direction, respectively).

The combination of wire and arc additive manufacturing (WAAM) and rolling offer the advantages of high efficiency, low cost, and fine grain, making it a viable option for the rapid production of aerospace thin-wall forgings using titanium alloy. However, the interplay between various factors such as temperature gradient, deformation force, and prior pass morphology directly influence the morphology and grain evolution before and after subsequent pass deformations, which lead to insufficient overall morphological accuracy and grain refinement uniformity. Building upon theoretical analysis, numerical simulation, and experimental verification, this study focuses on investigating the metal flow behavior and grain evolution mechanism during WAAM with in-situ rolling single-pass multi-layers. By establishing correlations between morphology, microstructure, temperature, stress-strain and deformation characteristics, the process optimization strategies of large width-height ratio, shallow melting depth and fixed width spread were proposed. These findings can provide theoretical support for the deformation machine design and the high-precision, uniformly fine grains additive manufacturing of thin-walled titanium alloy forgings.

In the present paper, the effects of macrostructure and microstructure on fatigue crack growth (FCG) behavior of wire and arc additive manufacturing (WAAM) and hybrid additive manufacturing with in-situ rolling (HAMR) were investigated in three sampling directions for Ti6Al4V ELI. The results demonstrate that WAAMed samples exhibit coarse columnar grains with zigzag boundaries, interlayer heat affected band (HAB), and basketweave microstructures. The fatigue crack growth rate (FCGR) is lowest in the Y-X direction while being similar between the X-Y and X-Z directions, indicating significant anisotropy. This difference can be attributed to changes in plastic region size and internal slip characteristics near the crack tip caused by variations in macrostructure and microstructure. After applying HAMR with quasi-beta heat treatment, interlayer HABs are eliminated, resulting in uniform equiaxed grains and colony microstructures. The FCGR curves in three directions significantly overlap without any observed anisotropy, which are lower than those obtained for traditionally forged materials. Therefore, the isotropic FCGR of plastic materials can be reduced by achieving a nearly flawless metallurgical quality and ensuring uniform equiaxed grain matching with the corresponding critical colony size and fine thickness lamellae. The findings suggest that the application of quasi-beta heat treatment in conjunction with HAMR offers a promising high-efficiency manufacturing technique for producing isotropic titanium alloy forgings characterized by exceptional damage tolerance.

To achieve superior damage tolerance and fatigue properties, it is desirable for the microstructure of Ti-6Al-4V ELI (Extra Low Interstitial) titanium alloy to consist of equiaxed grains with a homogeneous lamellar structure. However, traditional forging and single additive manufacturing techniques require extreme processes such as quasi beta heat treatment and hot isostatic pressing. In this paper, a hybrid directed energy deposition method that integrates in -situ rolling with simple annealing is proposed to simultaneously achieve these microstructures. The results indicate that the initial microstructures produced by hybrid directed energy deposition consist of fine equiaxed prior-beta grains, inconspicuous interpass bright bands, randomly oriented lamellar structure and numerous small substructures at the TEM scale. Due to the plastic deformation caused by in -situ rolling, the primary beta grains underwent significant refinement with a reduction in grain diameter from over 2000 mu m to 113.8 mu m. Besides, the unique microstructures and thickness of alpha laths are influenced by coarsening and dissolution mechanisms that are controlled by diffusion during phase transformation. Furthermore, a uniform microstructure without bright bands and excellent comprehensive properties can be achieved through heating at 880 degrees C for 2 h and natural cooling. These findings validate that hybrid directed energy deposition coupled with simple annealing present a novel and cost-effective approach for the direct manufacturing of uniform titanium alloy forgings.

Wire and arc additive manufacturing (WAAM) has gradually been applied in industrial applications in recent years due to its low cost, high deposition rate, and high material utilization rate. Anomalies in the WAAM process, such as inclusion, porosity, and lack of fusion, can have unpredictable effects on the quality of the final product. While some studies have investigated anomaly detection methods in the WAAM process, they mainly rely on supervised learning methods that require extensive manual labeling, with less attention paid to unsupervised models. Furthermore, most studies focus on significant anomalies that are rare in actual production, limiting their practical application. This paper proposes a two-stage unsupervised defect detection framework based on online melt pool video data. By considering the motion characteristics of the manufacturing process, a revised threshold method is used to detect anomalies during the WAAM process. Combining machine contextual information, the physical spatial location of defects is further identified and displayed through a human-machine interactive interface. The dataset used in this study is derived from real printing processes of WAAM parts. Compared with baseline methods, the proposed approach significantly improves recall and achieves an F1-score of 86.3% on the test set.

对ZL114A铝合金进行电弧-激光自由熔积和电弧-激光微铸锻复合增材成形实验,探究工艺条件对该铝合金的冶金缺陷、显微组织、力学性能和断口 SEM形貌的影响机理.结果表明:电弧-激光微铸锻增材成形工艺能明显抑制成形过程中气孔的产生,显微组织更加细小、均匀,共晶硅在晶间弥散分布;与电弧-激光自由熔积工艺相比,熔积扫描方向、熔积增高方向的拉伸强度、塑性、布氏硬度均提高;两种工艺的试样拉伸断口形貌均为细小的等轴韧窝,但电弧-激光微铸锻工艺的拉伸断面微型气孔缺陷更少.

Al-Si alloy is one of the most important and commonly used materials in the manufacture of lightweight components for automobiles. However, Its application is limited by low-strength properties, which are usually caused by micropores and columnar grains of the as-deposited WAAM alloy. To effectively address these issues, a special method of inter-layer micro rolling was used to fabricate the additively manufactured Al–4.7Si alloy in this paper. The strengthening mechanism of micro-rolling on this alloy was systematically studied by analyzing microstructure and properties. The experimental results showed that the number of micropores was substantially reduced, and the growth of columnar grains was significantly interrupted by inter-layer micro rolling, which had a clear effect on improving the mechanical properties of 4043 Al-Si alloy. The average ultimate tensile strength (UTS) and yield strength (YS) of the micro-rolled sample with 4 kN load achieved 159 MPa and 72 MPa, respectively, which were 18.6% and 38.5% higher than that without rolling, and elongation (EL) increased from 12.3% to 16.2%. This study is expected to provide an experimental and theoretical basis for improving the mechanical properties of additively manufactured aluminum alloys.

Purpose Wire and arc additive manufacturing (WAAM) is a widely used advanced manufacturing technology. If the surface defects occurred during welding process cannot be detected and repaired in time, it will form the internal defects. To address this problem, this study aims to develop an in situ monitoring system for the welding process with a high-dynamic range imaging (HDR) melt pool camera. Design/methodology/approach An improved you only look once version 3 (YOLOv3) model was proposed for online surface defects detection and classification. In this paper, improvements were mainly made in the bounding box clustering algorithm, bounding box loss function, classification loss function and network structure. Findings The results showed that the improved model outperforms the Faster regions with convolutional neural network features, single shot multibox detector, RetinaNet and YOLOv3 models with mAP value of 98.0% and a recognition rate of 59 frames per second. And it was indicated that the improved YOLOv3 model satisfied the requirements of real-time monitoring well in both efficiency and accuracy. Originality/value Experimental results show that the improved YOLOv3 model can solve the problem of poor performance of traditional defect detection models and other deep learning models. And the proposed model can meet the requirements of WAAM quality monitoring.

To overcome the disadvantages of inhomogeneous microstructures and poor mechanical properties of additively manufactured Ti-6Al-4V alloys, a novel technique of hybrid deposition and synchronous micro-rolling is proposed. The micro-rolling leads to equiaxed prior β grains, thin discontinuous intergranular α, and equiaxed primary α, in contrast to the coarse columnar prior β grains without the application of micro-rolling. The recrystallization by micro-rolling results in discontinuous intergranular α via the mechanism of strain and interface-induced grain boundary migration. The evolution of α globularization, driven by a solute concentration gradient, starts from the sub-boundary until the formation of equiaxed primary α. Simultaneous strengthening and toughening are achieved, which means an increase in yield strength, ultimate tensile strength, fracture elongation, and work hardening rate. The formation of α recrystallization leads to more fine grain boundaries to strengthen the yield strength, and the improvement of ductility is due to the better-coordinated deformation ability of discontinuous intergranular α and equiaxed primary α. As a result, the fracture mode in micro-rolling changes from intergranular type to transgranular type.

The corrosion resistance of nickel-aluminum bronze (NAB) by electron beam powder bed fusion (EB-PBF) from different-size feeding particles is investigated in neutral 3.5 wt% NaCl solutions. Uniformly-distributed precipitates are observed in the samples at the microscale. The beta' phase that suffered from corrosion preferentially in conventional as-casting NAB is not observed in the EB-PBF NAB. Typically, the corrosion resistance of EB-PBF NAB built from middle-size particles is improved by 1.35 times that of as-casting NAB. This results from a collective effect of high relative density and uniformly-distributed precipitates, which mitigates selective phase corrosion and promotes the formation of corrosion products with uniform thickness.

Wire and arc additive manufacturing (WAAM) is an emerging manufacturing technology that is widely used in different manufacturing industries. To achieve fully automated production, WAAM requires a dependable, efficient, and automatic defect detection system. Although machine learning is dominant in the object detection domain, classic algorithms have defect detection difficulty in WAAM due to complex defect types and noisy detection environments. This paper presents a deep learning-based novel automatic defect detection solution, you only look once (YOLO)-attention, based on YOLOv4, which achieves both fast and accurate defect detection for WAAM. YOLO-attention makes improvements on three existing object detection models: the channel-wise attention mechanism, multiple spatial pyramid pooling, and exponential moving average. The evaluation on the WAAM defect dataset shows that our model obtains a 94.5 mean average precision (mAP) with at least 42 frames per second. This method has been applied to additive manufacturing of single-pass, multi-pass deposition and parts. It demonstrates its feasibility in practical industrial applications and has potential as a vision-based methodology that can be implemented in real-time defect detection systems.