Search Results (87)

Industrial surface defect detection is crucial for quality control in manufacturing, yet remains challenging due to the small scale, low contrast, and texture variability of defects. While YOLOv8n offers high inference speed and efficiency, its accuracy is limited by insufficient feature representation and inadequate data diversity. This paper proposes a detection framework integrating Channel–Spatial Modulation Attention (CASM) and Small-Scale Grid Texture Shuffling Augmentation (SG-TSA) into YOLOv8n to improve detection performance without sacrificing efficiency. CASM introduces a parallel channel–spatial attention structure with adaptive fusion to better capture fine-grained defect features, while SG-TSA increases sample diversity by introducing realistic texture perturbations within defect regions. Experiments on the NEU-DET dataset show that our method improves mAP@0.5:0.95 by 3.01% and mAP@0.5 by 2.84% over baseline YOLOv8n. These results highlight the importance of architecture-specific optimization for lightweight detectors in industrial scenarios. Full article

To improve the machinability of 2343ESR mold steel and promote environmentally sustainable machining, this study systematically investigates its cutting performance in high-speed milling assisted by cryogenic minimum quantity lubrication (CMQL). A series of comparative high-speed milling experiments were conducted under dry cutting and CMQL conditions to elucidate the synergistic cooling and friction-reducing mechanisms of CMQL in the cutting zone. The effects of cutting parameters on key indicators including cutting forces, surface roughness, and tool life were investigated. Tool wear mechanisms were further analyzed and compared based on microscopic observations of workpiece surface damage and tool wear morphologies. The results show that, compared with dry cutting, CMQL reduces resultant cutting force by approximately 15.7–25.2% and surface roughness by about 14.6–29.9%. With the assistance of CMQL, the machined surface defects such as tearing, spalling and microcracks were effectively suppressed. In addition, adhesive wear and flank wear of the tool were significantly retarded, thereby achieving a significant improvement in tool life. These findings demonstrate that CMQL-assisted high-speed milling is a high-efficiency, high-quality and environmentally friendly machining technology with broad application potential for 2343ESR mold steel. Full article

This paper introduces an innovative automatic trajectory generation method for the robotic deburring of molded parts, effectively addressing challenges posed by burr defects and workpiece deformation common in casting and injection molding processes. Existing offline trajectory planning methods often struggle with substantial burr sizes and complex surface deformations, resulting in compromised machining quality due to over-adaptation. To overcome these issues, the proposed approach utilizes 3D vision techniques to achieve precise burr localization. A novel burr point cloud segmentation method based on feature analysis, combined with a tolerance-constrained non-rigid registration algorithm, accurately identifies burr regions and optimizes trajectory positioning within defined manufacturing tolerances. Furthermore, the method employs quantitative burr height distribution analysis to dynamically adjust robotic feed rates, significantly enhancing processing efficiency. Experimental validations demonstrated that the proposed method reduces the deburring time by up to 68% compared to conventional techniques, achieving an average trajectory deviation of only 0.79 mm. This study provides a robust, efficient, and precise solution for automating deburring operations in complex molded components, highlighting its substantial potential for industrial applications. Full article

316L stainless steel slender tubes with smooth inner surfaces play an important role in fields such as aerospace and medical testing. In order to solve the challenge of difficult machining of their inner surfaces, this paper introduces a novel rotary magnetorheological finishing (RMRF) method specifically designed for processing the inner surfaces of slender tubes. This method does not require frequent replacement of the polishing medium during the processing, which helps to simplify the processing technology. By combining the rotational motion of a magnetic field with the linear reciprocating movement of the workpiece, uniform material removal on the inner surfaces of 316L stainless steel tubes was achieved. Initially, a finite element model coupling the magnetic and flow fields was developed to investigate the flow behavior of the MPF under a rotating magnetic field, to examine the theoretical feasibility of the proposed polishing principle. Subsequently, experimental validation was performed using a custom-designed polishing apparatus. Through processing experiments, with surface quality designated as the index, the influences of key parameters such as the volume content and sizes of carbonyl iron particles and abrasive particles in the MPF were comprehensively evaluated, and the composition and ratio of the MPF were optimized. Based on the optimized formulation, the optimal processing time was established, reducing the inner surface roughness from an initial Sa of approximately 320 nm to 28 nm, and effectively eliminating the original defects. Full article

This study presents an intelligent machine developed for real-time quality monitoring during CNC turning, aimed at improving cutting efficiency and reducing production energy. A dynamometer integrated into the CNC machine captures decomposed cutting forces using the Daubechies wavelet transform. These force ratios are correlated with key workpiece dimensions: surface roughness, average roughness, straightness, and roundness. Two predictive models—nonlinear regression and a feed-forward neural network with Levenberg–Marquardt backpropagation—are employed to estimate these parameters under varying cutting conditions. Experimental results indicate that nonlinear regression models outperform neural networks in predictive accuracy. The proposed system offers effective in-process control of machining quality, contributing to shorter cycle times, lower defect rates, and more sustainable manufacturing practices. Full article

To address the challenges of automatic detection caused by the variation of surface normal vectors in automotive steering knuckles, an automatic detection method based on ultrasonic phased array technology is herein proposed. First, a point cloud model of the workpiece was constructed using ultrasonic distance measurement, and Gaussian-weighted principal component analysis was used to estimate the normal vectors of the point cloud. By utilizing the normal vectors, water layer thickness during detection, and the incident angle of the sound beam, the probe pose information corresponding to the detection point was precisely calculated, ensuring the stability of the sound beam incident angle during the detection process. At the same time, in the trajectory planning process, piecewise cubic Hermite interpolation was used to optimize the detection trajectory, ensuring continuity during probe movement. Finally, an automatic detection system was set up to test a steering knuckle specimen with surface circumferential cracks. The results show that the point cloud data of the steering knuckle specimen, obtained using phased array ultrasound, had a relative measurement error controlled within 1.4%, and the error between the calculated probe angle and the theoretical angle did not exceed 0.5°. The probe trajectory derived from these data effectively improved the B-scan image quality during the automatic detection of the steering knuckle and increased the defect signal amplitude by 5.6 dB, demonstrating the effectiveness of this method in the automatic detection of automotive steering knuckles. Full article

This study addresses the critical challenge of precise control over active abrasive particles in magnetorheological polishing (MRP) through innovative core–shell particle engineering. A sol–gel synthesized CIP@SiO₂ magnetic composite abrasive with controlled SiO₂ encapsulation (20 nm shell thickness) was developed using tetraethyl orthosilicate (TEOS) as the silicon precursor, demonstrating significant advantages in optical-grade fused silica finishing. Systematic polishing experiments reveal that the core–shell architecture achieves a remarkable 20.16% improvement in surface quality (Ra = 1.03 nm) compared to conventional CIP/SiO₂ mixed abrasives, with notably reduced surface defects despite a modest 8–12% decrease in material removal rate. Through synergistic analysis combining elastic microcontact mechanics modeling and molecular dynamics simulations, we establish that the SiO₂ shell mediates stress distribution at tool–workpiece interfaces, effectively suppressing deep subsurface damage while maintaining nano-scale material removal efficiency. The time-dependent performance analysis further demonstrates that extended polishing durations with CIP@SiO₂ composites progressively eliminate mid-spatial frequency errors without introducing new surface artifacts. These findings provide fundamental insights into designed abrasive architectures for precision finishing applications requiring sub-nanometer surface integrity control. Full article

Particle-reinforced Al-based matrix composites have great potential for application in aerospace, automotive manufacturing, and defense due to their high strength, hardness, and excellent wear and corrosion resistance. However, the presence of particles increases the processing difficulty, making it a typical difficult-to-machine material. In recent years, ultrasonic vibration-assisted machining has been quite popular in manufacturing this kind of material. This paper reviews the research advancements in ultrasonic vibration-assisted machining of particle-reinforced Al-based matrix composites, providing a comprehensive analysis of the effects of introducing an ultrasonic energy field on tool wear, chip morphology, cutting force, cutting temperature, and surface integrity. Ultrasonic vibration periodically alters the contact state between the tool and the workpiece, effectively reducing the tool wear rate and extending the tool life. Meanwhile, ultrasonic vibration facilitates the fracture and ejection of chips, enhancing chip morphology and reducing energy consumption during the cutting process. Additionally, ultrasonic vibration significantly decreases cutting force and cutting temperature, contributing to the stability of the cutting process and improving processing efficiency. Regarding surface integrity, ultrasonic vibration-assisted machining refines the machined surface’s microstructure, reducing surface defects and residual stress, thereby significantly enhancing the machining quality. In the future, we will conduct in-depth research on the effects of ultrasonic energy on material properties in terms of softening effect, thermal effect, and stress superposition, further revealing the mechanism of ultrasonic vibration-assisted processing of particle-reinforced aluminum-based composite materials. Full article

High-precision surface defect detection in manufacturing often relies on laser triangulation profilometric sensors for detailed surface measurements, providing detailed and accurate surface measurements over a line. Accurate motion between the sensor and workpiece, usually managed by robotic systems, is critical for maintaining optimal distance and orientation. This paper introduces a novel Reinforcement Learning (RL) approach to optimize inspection trajectories for profilometric sensors based on the boustrophedon scanning method. The RL model dynamically adjusts sensor position and tilt to ensure consistent profile distribution and high-quality scanning. We use a simulated environment replicating real-world conditions, including sensor noise and surface irregularities, to plan trajectories offline using CAD models. Key contributions include designing a state space, action space, and reward function tailored for profilometric sensor inspection. The Proximal Policy Optimization (PPO) algorithm trains the RL agent to optimize these trajectories effectively. Validation involves testing the model on various parts in simulation and performing real-world inspection with a UR3e robotic arm, demonstrating the approach’s practicality and effectiveness. Full article

High-entropy alloys (HEAs) possess multi-element composition and uniform structure, exhibiting superior microstructure and properties compared to traditional alloys. However, the multi-element composition of HEAs results in a complex internal composition configuration with exceptionally high hardness and strength, leading to various machining defects under cutting loading such as poor surface roughness, excessive machining temperature, and cutting tool wear. This study investigates the milling performance of FeCoNiCrMn_x HEAs with different elemental ratios subjected to various ultrasonic-assisted milling techniques, aiming to identify the better ultrasonic assisted technique and machining process parameters. The ultrasonic-assisted milling techniques include single-axis ultrasonic, dual-axis ultrasonic, and triple-axis ultrasonic. The side milling experiments were performed on three different elemental ratios of HEAs, e.g., FeCoNiCrMn_0.1, FeCoNiCrMn_0.5, and FeCoNiCrMn_1.0 workpieces. The study is divided into two phases. Each alloy workpiece undergoes side-milling experiments using two designated combinations of feed rate and radial cutting depth subjected to various ultrasonic-assisted milling techniques in the first phase. The purpose is to identify which ultrasonic-assisted milling technique may provide the better surface quality for different elemental ratios and to analyze the performance of various cutting condition combinations in terms of surface roughness and cutting tool wear. Based on the results of the first phase, the better ultrasonic-assisted milling technique is selected and an L₉ Taguchi orthogonal array is then employed for process parameter planning, by varying spindle speed, feed rate, and radial cutting depth to investigate the effects of different process parameter combinations on machining performance of HEAs with different elemental ratios. The results show that ultrasonic assistance significantly improves the cutting performance in aspects such as reduction of cutting force and cutting tool wear, and the surface quality of alloys with high Mn content. In the first phase experiment, as compared to milling without assistance, the surface roughness may be reduced up to approximately 17.86% by single-axis ultrasonic-assisted milling using the Set 1 process parameters for different elemental ratios, while it achieves up to approximately 34.4% in surface roughness and approximately 17.68% in cutting tool wear using the Set 2 process parameters. The results from the second phase of experiments reveal a more moderate fluctuation of surface roughness and an approximate reduction from 22.03% to 314.27%, with an approximate reduction from 3.64% to 54.45% in cutting force, and an approximate reduction from 0.58% to 94.77% in cutting tool wear for the higher Mn content alloy in contrast to the lower Mn content one. The integrity of the surface morphology is significantly improved as the elemental ratio, x, is increased to 1.0, resulting in a reduction in machined surface deformation and more consistent milling marks on the machined surface, which indicates a higher stable state of machining quality. Full article

Under high fluence and a high repetition rate, femtosecond laser drilling still produces defects due to heat accumulation. In order to suppress these defects, this study conducted research on water-assisted femtosecond laser drilling. This study focused on the impact of two different water-assisted methods, static-water-based and flowing-water-based approaches, on the quality of microholes made using layer-by-layer helical drilling with a femtosecond laser in thermal-barrier-coated superalloys. Furthermore, the effects of single-pulse laser energy on the hole entrance/exit diameter, taper angle, sidewall morphology, sidewall roughness, and sidewall oxygen content in the two water environments were compared and analyzed. Water-based-assisted laser drilling is an auxiliary method where the lower surface of the workpiece is placed in water while the upper surface remains in the air. On the other hand, the water flows horizontally in the flowing-water-based method. The experimental results demonstrate that both static- and flowing-water-based methods can significantly improve the quality of femtosecond laser drilling. Notably, the improvement effect was more pronounced with the flowing-water-based method. At a laser pulse energy of 50 μJ, the hole taper angle in the flowing-water environment was reduced by 38.80% compared with that in the air. With flowing-water-based assistance, the hole sidewall roughness was lower and the melt was less. Flowing water was better at carrying away the debris and heat generated by processing. The oxygen content of the hole sidewalls decreased significantly in both kinds of water-assisted environments. The experimental results provide a valuable reference for optimizing water-assisted femtosecond laser drilling. Full article

Chatter commonly emerges during milling procedures, resulting in an array of problems such as defective workpiece surface and diminished machining efficiency. To control chatter, an active electromagnetic tool holder system is proposed, including the active structure with an electromagnetic actuator installed at the tool holder position and a time-delay output feedback chatter control method for low immersion milling. More specifically, a noncontact two-degree-of-freedom active magnetic bearing (AMB) actuator is developed and integrated with displacement sensors at the tool holder position, making the actuator and sensors closer to the cutting point. Under low immersion milling conditions, both the thin-walled workpieces and tool flexibility are considered in the controller design, as well as practical physical limitations including the bandwidth of the power amplifier and the output current constraints of the actuator. Numerical simulation and experiments under low immersion milling conditions are carried out. The results demonstrate that the proposed active electromagnetic tool holder system exhibits good control consequences on the chatter of thin-walled workpieces and tools under low immersion milling. Full article

Severe reflections on the surfaces of smooth objects can result in low dynamic range and uneven illumination in images, which negatively impacts downstream tasks such as defect detection and QR code recognition on images of smooth workpieces. Consequently, this paper proposes a novel approach to real-time high dynamic equalization imaging based on a fully convolutional network, termed Multi-exposure Image Fusion with Multi-dimensional Attention Mechanism and Training Storage Units (MEF-AT). Specifically, this paper innovatively proposes using training storage units, which utilize intermediate results during network training as auxiliary images, to remove uneven illumination and enhance image dynamic range effectively. Furthermore, by integrating a multi-dimensional attention mechanism into the backbone network, the model can more efficiently extract and utilize critical image information. Additionally, this paper introduces a Deep Guided Filter (DGF) with learnable parameters, which upsample the weight maps generated by the network, thus better adapting to complex industrial scenarios and producing higher quality fused images. An image evaluation metric assessing the lighting uniformity is introduced to thoroughly evaluate the proposed method’s performance. Given the lack of an MEF dataset for smooth workpieces, this paper collects a new dataset for multi-exposure fusion tasks on metallic workpieces. Our method takes less than 4 ms to run four 2K images on a GPU 3090. Both qualitative and quantitative experimental results demonstrate our method’s superior comprehensive performance in proprietary industrial and public datasets. Full article

Chemical mechanical planarization (CMP) is a technique used to efficiently prepare defect-free, flat surfaces of stainless steel (SS) foils and sheets that are implemented in various modern devices. CMP uses (electro)chemical reactions to structurally weaken the surface layers of a workpiece for easy removal by low-pressure mechanical abrasion. Using a model CMP system of 316/316L stainless steel (SS) in an acidic (pH = 3.63) slurry with alumina abrasives, citrate buffer (CB), and H₂O₂, we examine the tribo-electrochemical mechanisms of SS CMP that dictate the designs of functionally efficient and cost-effective CMP slurries. The use of CB as a pH-controlled complexing agent prevents defect-causing dissolution of SS and eliminates the need for using separate (often toxic) corrosion inhibitors in the slurry. A material removal rate of 8.6 nm min⁻¹ is obtained at a moderate down pressure of 0.014 MPa with a platen rotation speed of 95 RPM. Electrochemical techniques are strategically combined with mechanical abrasion of SS test samples to probe complex CMP mechanisms that are not readily accessible with electrochemical experiments alone. Corrosion-like reactions of salt-film formation at the SS surface act to enable the CMP process, where corrosion-induced wear plays a major role in material removal. Full article

In the process of aluminum alloy reflector mirror processing, the structural defects of aluminum alloys present bottlenecks restricting the development of aluminum alloy reflector mirror processing technologies. Therefore, this study proposes an aluminum alloy reflector mirror processing method involving ultrasonic rolling and single-point diamond turning. The core idea of this method is to use ultrasonic rolling to pretreat the surface of the workpiece to refine the grains and increase the hardness, then perform single-point diamond turning to improve the optical reflection performance. In this study, an ultrasonic rolling cutting experiment was carried out, and the influence of the material preparation method on the microstructure and hardness of the workpiece was analyzed. An ultrasonic rolling single-point diamond turning experiment was carried out, and the influence of the material preparation method on the reflection performance of single-point diamond turning was studied. Results showed that compared with single-point diamond turning after ordinary milling, the ultrasonic rolling single-point diamond turning method has certain advantages in improving the surface reflection performance, with an increase of 5.116%. The method proposed in this study can provide new ideas for the high-quality processing of aluminum alloy reflector mirrors. Full article