In order to study the hot melt extrusion process in fused deposition modeling (FDM), this study mainly explores the effects of printing temperature, heated block length, feeding speed on the exit morphology and mechanical properties of FDM printed Polylactic acid (PLA) samples. High-speed camera is used to capture the exit morphology of molten PLA just extruded to the nozzle. According to exit morphology, the outlet states of extruded molten material can be divided into four categories, namely, bubbled state, coherent state, expanding state, and unstable state. Tensile test results show that printing temperature, heated block length and printing speed have significant influence on tensile properties and fracture mode of FDM printed samples. When the heated block length is 15 mm and 30 mm, there is a ductile-brittle transition in fracture mode with the increase of printing speed. The printing process window under different heated block lengths and printing temperatures has been figured out and the distribution of printing process window under different printing speeds has been discussed. There is a maximum printing process window under the heated block length of 30 mm. This finding provides a frame work for performance prediction of FDM printed parts and theoretical guidance for expanding the scope of printing process window.
Duplex stainless steels are being used on applications that require, especially, high corrosion resistance and overall good mechanical properties, such as the naval and oil-gas exploration industry. The components employed in these industries are usually obtained by machining, however, these alloys have low machinability when compared to conventional stainless steels. In this work, a study of the wear developed when milling duplex stainless-steel, LDX 2101, is going to be presented and evaluated, employing four types of milling tools with different geometries and coatings, while studying the influence of feed rate and cutting length in the wear of these tools. Tools used have been provided with two and four flutes, as well as three different coatings, namely: TiAlN, TiAlSiN and AlCrN. The cutting behavior of these tools was analyzed; data relative to the cutting forces developed during the process were obtained; and roughness measurements of the machined surfaces were executed. The tools were then submitted to scanning electron microscope (SEM) analysis, enabling the identification of the wear mechanisms that tools were subjected to when machining this material, furthermore, the early stages of these mechanisms were also identified. All this work was done with the goal of relating the machining parameters and cutting force values obtained, identifying, and discussing the wear patterns that were observed in the coating and tools after the milling tests, providing further information on the machining of these alloys.
Keyhole tungsten inert gas (K-TIG) welding is capable of realizing single-sided welding and double-sided forming and has been widely used in medium and thick plate welding. In order to improve the accuracy of automatic weld identification and weld penetration prediction of robot in the process of large workpiece welding, a two-stage model is proposed in this paper, which can monitor the K-TIG welding penetration state in real time on the embedded system, called segmentation-LSTM model. The proposed system extracts 9 weld pool geometric features with segmentation network, and then extracts the weld gap using a traditional algorithm. Then these 10-dimensional features are input into the LSTM model to predict the penetration state, including under penetration, partial penetration, good penetration and over penetration. The recognition accuracy of the proposed system can reach 95.2%. In this system, to solve the difficulty of labeling data and lack of segmentation accuracy, an improved LabelMe capable of live-wire annotation tool and a novel loss function were proposed, respectively. The latter was also called focal dice loss, which enabled the network to achieve a performance of 0.933 mIoU on the testing set. Finally, an improved slimming strategy compresses the network, making the segmentation network achieve real-time on the embedded system (RK3399pro).
In order to study the hot melt extrusion process in fused deposition modeling (FDM), this study mainly explores the effects of printing temperature, heated block length, feeding speed on the exit morphology and mechanical properties of FDM printed Polylactic acid (PLA) samples. High-speed camera is used to capture the exit morphology of molten PLA just extruded to the nozzle. According to exit morphology, the outlet states of extruded molten material can be divided into four categories, namely, bubbled state, coherent state, expanding state, and unstable state. Tensile test results show that printing temperature, heated block length and printing speed have significant influence on tensile properties and fracture mode of FDM printed samples. When the heated block length is 15 mm and 30 mm, there is a ductile-brittle transition in fracture mode with the increase of printing speed. The printing process window under different heated block lengths and printing temperatures has been figured out and the distribution of printing process window under different printing speeds has been discussed. There is a maximum printing process window under the heated block length of 30 mm. This finding provides a frame work for performance prediction of FDM printed parts and theoretical guidance for expanding the scope of printing process window.
Duplex stainless steels are being used on applications that require, especially, high corrosion resistance and overall good mechanical properties, such as the naval and oil-gas exploration industry. The components employed in these industries are usually obtained by machining, however, these alloys have low machinability when compared to conventional stainless steels. In this work, a study of the wear developed when milling duplex stainless-steel, LDX 2101, is going to be presented and evaluated, employing four types of milling tools with different geometries and coatings, while studying the influence of feed rate and cutting length in the wear of these tools. Tools used have been provided with two and four flutes, as well as three different coatings, namely: TiAlN, TiAlSiN and AlCrN. The cutting behavior of these tools was analyzed; data relative to the cutting forces developed during the process were obtained; and roughness measurements of the machined surfaces were executed. The tools were then submitted to scanning electron microscope (SEM) analysis, enabling the identification of the wear mechanisms that tools were subjected to when machining this material, furthermore, the early stages of these mechanisms were also identified. All this work was done with the goal of relating the machining parameters and cutting force values obtained, identifying, and discussing the wear patterns that were observed in the coating and tools after the milling tests, providing further information on the machining of these alloys.
Keyhole tungsten inert gas (K-TIG) welding is capable of realizing single-sided welding and double-sided forming and has been widely used in medium and thick plate welding. In order to improve the accuracy of automatic weld identification and weld penetration prediction of robot in the process of large workpiece welding, a two-stage model is proposed in this paper, which can monitor the K-TIG welding penetration state in real time on the embedded system, called segmentation-LSTM model. The proposed system extracts 9 weld pool geometric features with segmentation network, and then extracts the weld gap using a traditional algorithm. Then these 10-dimensional features are input into the LSTM model to predict the penetration state, including under penetration, partial penetration, good penetration and over penetration. The recognition accuracy of the proposed system can reach 95.2%. In this system, to solve the difficulty of labeling data and lack of segmentation accuracy, an improved LabelMe capable of live-wire annotation tool and a novel loss function were proposed, respectively. The latter was also called focal dice loss, which enabled the network to achieve a performance of 0.933 mIoU on the testing set. Finally, an improved slimming strategy compresses the network, making the segmentation network achieve real-time on the embedded system (RK3399pro).
In order to study the hot melt extrusion process in fused deposition modeling (FDM), this study mainly explores the effects of printing temperature, heated block length, feeding speed on the exit morphology and mechanical properties of FDM printed Polylactic acid (PLA) samples. High-speed camera is used to capture the exit morphology of molten PLA just extruded to the nozzle. According to exit morphology, the outlet states of extruded molten material can be divided into four categories, namely, bubbled state, coherent state, expanding state, and unstable state. Tensile test results show that printing temperature, heated block length and printing speed have significant influence on tensile properties and fracture mode of FDM printed samples. When the heated block length is 15 mm and 30 mm, there is a ductile-brittle transition in fracture mode with the increase of printing speed. The printing process window under different heated block lengths and printing temperatures has been figured out and the distribution of printing process window under different printing speeds has been discussed. There is a maximum printing process window under the heated block length of 30 mm. This finding provides a frame work for performance prediction of FDM printed parts and theoretical guidance for expanding the scope of printing process window.
Duplex stainless steels are being used on applications that require, especially, high corrosion resistance and overall good mechanical properties, such as the naval and oil-gas exploration industry. The components employed in these industries are usually obtained by machining, however, these alloys have low machinability when compared to conventional stainless steels. In this work, a study of the wear developed when milling duplex stainless-steel, LDX 2101, is going to be presented and evaluated, employing four types of milling tools with different geometries and coatings, while studying the influence of feed rate and cutting length in the wear of these tools. Tools used have been provided with two and four flutes, as well as three different coatings, namely: TiAlN, TiAlSiN and AlCrN. The cutting behavior of these tools was analyzed; data relative to the cutting forces developed during the process were obtained; and roughness measurements of the machined surfaces were executed. The tools were then submitted to scanning electron microscope (SEM) analysis, enabling the identification of the wear mechanisms that tools were subjected to when machining this material, furthermore, the early stages of these mechanisms were also identified. All this work was done with the goal of relating the machining parameters and cutting force values obtained, identifying, and discussing the wear patterns that were observed in the coating and tools after the milling tests, providing further information on the machining of these alloys.
Keyhole tungsten inert gas (K-TIG) welding is capable of realizing single-sided welding and double-sided forming and has been widely used in medium and thick plate welding. In order to improve the accuracy of automatic weld identification and weld penetration prediction of robot in the process of large workpiece welding, a two-stage model is proposed in this paper, which can monitor the K-TIG welding penetration state in real time on the embedded system, called segmentation-LSTM model. The proposed system extracts 9 weld pool geometric features with segmentation network, and then extracts the weld gap using a traditional algorithm. Then these 10-dimensional features are input into the LSTM model to predict the penetration state, including under penetration, partial penetration, good penetration and over penetration. The recognition accuracy of the proposed system can reach 95.2%. In this system, to solve the difficulty of labeling data and lack of segmentation accuracy, an improved LabelMe capable of live-wire annotation tool and a novel loss function were proposed, respectively. The latter was also called focal dice loss, which enabled the network to achieve a performance of 0.933 mIoU on the testing set. Finally, an improved slimming strategy compresses the network, making the segmentation network achieve real-time on the embedded system (RK3399pro).
