In the era of Industry 4.0, robot motion planning faces unprecedented challenges in adapting those high-dimension dynamic working environments with rigorous real-time planning requirements. Traditional sampling-based planning algorithms can find solutions in high-dimensional spaces but often struggle with achieving the balance among computational efficiency, real-time adaptability, and solution optimality. To overcome these challenges and unlock the full potential of robotic automation in smart manufacturing, we propose bidirectional recurrent motion planning network (BRMPNet). As an imitation learning-based approach for robot motion planning, it leverages deep neural networks to learn the heuristics for approximate-optimal path planning. BRMPNet employs the refined PointNet++ network to incorporate raw point-cloud information from depth sensors and generates paths with a bidirectional strategy using long short-term memory (LSTM) network. It can also be integrated with traditional sampling-based planning algorithms, offering theoretical assurance of the probabilistic completeness for solutions. To validate the effectiveness of BRMPNet, we conduct a series of experiments, benchmarking its performance against the state-of-the-art motion planning algorithms. These experiments are specifically designed to simulate common operations encountered within generic robotic platforms in smart manufacturing such as mobile robots and multi-joint robotic arms. The results demonstrate BRMPNet’s superior performance on key metrics including solution quality and computational efficiency, suggesting the promising potential of learning-based planning in addressing complex motion planning challenges.
New insights are proposed regarding the α′-martensite transformation and strengthening mechanisms of austenitic stainless steel 316L fabricated using selective laser melting (SLM-ed 316L SS). This study investigates the effects of annealing on the microstructural evolution, mechanical properties, and corrosion resistance of SLM-ed 316L SS specimens. The exceptional ultimate tensile strength (807 MPa) and good elongation (24.6%) of SLM-ed 316L SS was achieved by SLM process and annealing treatment at 900 °C for 1 h, which was attributed to effective dislocation strengthening and grain boundary strengthening. During tensile deformation, annealed samples exhibited deformation twinning as a result of the migration from high-angle grain boundaries to low-angle grain boundaries, facilitating the α′-martensite transformation. Consequently, a deformation mechanism model is proposed. The contribution of dislocation strengthening (~61.4%) is the most important strengthening factor for SLM-ed 316L SS annealed 900 °C for 1 h, followed by grain boundary strengthening and solid solution strengthening. Furthermore, the corrosion resistance of SLM-ed 316L SS after annealing treatment is poor due to its limited re-passivation ability.
Owing to the hard brittle phase organization in their matrixes, brittle materials are prone to the formation of pits and cracks on machined surfaces under extreme grinding conditions, which severely affect the overall performance and service behavior of machined parts. Based on the electroplastic effect of pulsed currents during material deformation, this study investigates electroplastic-assisted grinding with different electrical parameters (current, frequency, and duty cycle). The results demonstrate that compared to conventional grinding, the pulsed current can significantly decrease the surface roughness (S a) of the workpiece and reduce surface pits and crack defects. The higher the pulsed current, the more pronounced the improvement in the surface quality of the workpiece. Compared to traditional grinding, when the pulsed current is 1 000 A, S a decreases by 46.4%, and surface pit and crack defects are eliminated. Under the same pulse-current amplitude and frequency conditions, the surface quality continues to improve as the duty cycle increases. When the duty cycle is 75%, S a reaches a minimum of 0.749 μm. However, the surface quality is insensitive to the pulsed-current frequency. By investigating the influence of pulsed electrical parameters on the surface quality of brittle material under grinding conditions, this study provides a theoretical basis and technical support for improving the machining quality of hard, brittle materials.
Silicon carbide fiber-reinforced silicon carbide composites are preferred materials for hot-end structural parts of aero-engines. However, their anisotropy, heterogeneity, and ultra-high hardness make them difficult to machine. In this paper, 2.5-dimensional braided SiCf/SiC composites were processed using a nanosecond pulsed laser. The temperature field distribution at the laser ablated spot is analyzed through finite element modeling (FEM), and the ablation behavior of the two main components, SiC fiber and SiC matrix, is explored. A plasma plume forms when the pulse energy is sufficiently high, which increases with growing energy. The varied ablation behavior of the components is investigated, including the removal rate, ablative morphology, and phase transition. The ablation thresholds of SiC matrix and SiC fiber are found to be 2.538 J/cm2 and 3.262 J/cm2, respectively.
To enhance the performance of aero-engines, honeycomb seals are commonly used between the stator and rotor to reduce leakage and improve mechanical efficiency. Because of the thin-walled and densely distributed honeycomb holes, machining defects are prone to occur during manufacturing. Electrochemical grinding (ECG) can minimize machining deformation because it is a hybrid process involving electrochemical dissolution and mechanical grinding. However, electrolysis will generate excessive corrosion on the honeycomb surface, which affects the sealing capability and operational performance. In this study, an ECG method using an electrolyte of 10% (mass fraction) NaCl is proposed to machine the inner cylindrical surface of the honeycomb seal, and an eco-friendly inhibitor, sodium dodecylbenzene sulfonate (SDBS), is introduced to the electrolyte to inhibit corrosion of the honeycomb structure. A theoretical relationship between the voltage and feed rate during ECG is proposed, and the excessive corrosion of the honeycomb single-foiled segment is used as a measurement of the impact of electrolysis. The corrosion inhibition efficiency of SDBS on the honeycomb material in 10% (mass fraction) NaCl solution is evaluated through electrochemical tests, and the suitable feed rate and optimal concentration of SDBS are determined through ECG experiments. Additionally, the corrosion inhibition effect of SDBS is validated through four groups of comparative experiments. The results indicate that the inhibition efficiency of SDBS increases with increasing concentration, reaching the maximum of 73.44%. The optimal SDBS mass fraction is determined to be 0.06%. The comparative experiments show that excessive corrosion is reduced by more than 40%. This establishes ECG as an effective and environmentally friendly processing method for honeycomb seals by incorporating SDBS into a 10% (mass fraction) NaCl solution.
Micromilling has been extensively employed in different fields such as aerospace, energy, automobiles, and healthcare because of its efficiency, flexibility, and versatility in materials and structures. Recently, nanofluid minimum quantity lubrication (NMQL) has been proposed as a green and economical cooling and lubrication method to assist the micromilling process; however, its effect is limited because high-speed rotating tools disturb the surrounding air and impede the entrance of the nanofluid. Cold plasma can effectively enhance the wettability of lubricating droplets on the workpiece surface and promote the plastic fracture of materials. Therefore, the multifield coupling of cold plasma and NMQL may provide new insights to overcome this bottleneck. In this study, experiments on cold plasma + NMQL multifield coupling-assisted micromilling of a 7075-T6 aluminum alloy were conducted to analyze the three-dimensional (3D) surface roughness (S a), surface micromorphology, burrs of the workpiece, and milling force at different micromilling depths. The results indicated that, under cold plasma + NMQL, the workpiece surface micromorphology was smooth with fewer burrs. In comparison with dry, N2, cold plasma, and NMQL, the S a values at different cutting depths (5, 10, 15, 20 and 30 μm) were relatively smaller under cold plasma + NMQL with 0.035, 0.036, 0.041, 0.043 and 0.046 μm, which were respectively reduced by 38.9%, 45.7%, 45.9%, 47% and 48.9% when compared to the dry. The effect of cold plasma + NMQL multifield coupling-assisted micromilling on enhancing the workpiece surface quality was analyzed using mechanical analysis of tensile experiments, surface wettability, and X-ray photoelectron spectroscopy (XPS).
Ti2AlNb intermetallic alloys, which belong to the titanium aluminum (TiAl) family, are currently being extensively researched and promoted in the aerospace industry because of their exceptional properties, including low density, high-temperature strength, and excellent oxidation resistance. However, the excellent fracture toughness of the material leads to the formation of surface defects during machining, thereby affecting the quality of the machined surface. In this study, Ti2AlNb intermetallic alloys were subjected to side-milling trials to investigate the influence of tool coating and tool wear on both the machined surface quality and chip morphology. Specifically, the tool life, machined surface roughness, surface morphology, surface defects, and chip morphology were investigated in detail. The results indicated that the tool coating provided a protective effect, resulting in a threefold increase in the service life of the coated end mill compared to that of the uncoated one. A coated end mill yields a superior machined surface topography, as evidenced by reduced roughness and a more consistent morphology. Tool wear has a significant effect on the morphology of machined surfaces. The occurrence of material debris and feed marks became increasingly severe as the tool wore off. The chip morphology was not significantly affected by the tool coating. However, tool wear results in severe tearing along the chip edge, obvious plastic flow on the non-free surface, and a distinct lamellar structure on the free surface.
Electrical arc machining (EAM) is an efficient process for machining difficult-to-cut materials. However, limited research has been conducted on sloped surface machining within this context, constraining the further application for complex components. This study conducts bevel machining experiments, pointing out that the surface quality becomes unsatisfactory with the increasing bevel angle. The discharge condition is counted and analyzed, while the flow field and the removed particle movement of the discharge gap are simulated, demonstrating the primary factor contributing to the degradation of surface quality, namely the loss of flushing. This weakens both the plasma control effect and debris evacuation, leading to the poor discharge condition. To address this issue, the magnetic field is implemented in blasting erosion arc machining (BEAM). The application of a magnetic field effectively regulates the arc plasma, enhances debris expulsion, and significantly improves the discharge conditions, resulting in a smoother and more uniform sloped surface with a reduced recast layer thickness. This approach provides the possibility of applying BEAM to complex parts made of difficult-to-cut materials in aerospace and military industries.
Advances in artificial intelligence (AI) technology are propelling the rapid development of automotive intelligent cockpits. The active perception of driver emotions significantly impacts road traffic safety. Consequently, the development of driver emotion recognition technology is crucial for ensuring driving safety in the advanced driver assistance system (ADAS) of the automotive intelligent cockpit. The ongoing advancements in AI technology offer a compelling avenue for implementing proactive affective interaction technology. This study introduced the multimodal driver emotion recognition network (MDERNet), a dual-branch deep learning network that temporally fused driver facial expression features and driving behavior features for non-contact driver emotion recognition. The proposed model was validated on publicly available datasets such as CK+, RAVDESS, DEAP, and PPB-Emo, recognizing discrete and dimensional emotions. The results indicated that the proposed model demonstrated advanced recognition performance, and ablation experiments confirmed the significance of various model components. The proposed method serves as a fundamental reference for multimodal feature fusion in driver emotion recognition and contributes to the advancement of ADAS within automotive intelligent cockpits.
The health states of sensing devices have a long-reaching influence on many smart application scenarios, such as smart energy and intelligent manufacturing. This paper proposes an ensemble methodology of the health-state evaluation of sensing devices, based on artificial intelligence (AI) technologies, which firstly takes into the operational characteristics, then designs a method of scenario identification to extract the typical scenarios, and subsequently puts forth a specific health-state evaluation. This method could infer the causalities of faulty devices effectively, which provides the interpretable basis for the health-state evaluation and enhances the evaluation accuracy of the health states. The suggested method has the promising potential to support the efficiently fine management of sensing devices in smart age.