To integrate high positioning accuracy with enhanced machining stiffness in the manufacturing of near-netshaped aero-engine blades, this paper proposes a Large Language Model (LLM)-driven Evolutionary Fixture Design (LMEFD) framework for Rigid-Flexible Collaborative Fixtures (RFCF). Traditional fixture design methods rely heavily on the tacit experience of engineers, struggling with multi-objective optimization. Within the LMEFD, the LLM is integrated as a cognitive agent in the evolutionary loop, transforming unstructured engineering domain knowledge and expert experience into quantified design parameter optimization through semantic initialization, selection, crossover, and mutation operators. To mitigate the LLM's hallucination, the LMEFD establishes a self-reflection and repair mechanism to learn the constraints from the prompt history and generate valid designs without external correction. To evaluate the performance of design candidates, the LMEFD is equipped with access to external geometry and finite element solvers, which can model the fixture and provide physics-informed feedback. Through the LMEFD, fixture designers can guide the design optimization process via natural language intervention, translating semantic design logic into a high-accuracy and high-stiffness physical system. To validate the practical feasibility, a physical RFCF system is manufactured, and experimental results demonstrate that the LLM-designed RFCF effectively controls positioning errors, machining deformation, vibration, and the profile deviation of the machined blades. This research demonstrates the potential of LLMs in solving complex physical design problems in high-precision manufacturing.

Nickel-based superalloy GH4169 is widely used in aero-engine casings, but its high flow strength, strong work hardening, and low thermal conductivity make machining difficult and often lead to degraded surface integrity. The key question addressed here is how cryogenic minimum quantity lubrication (CMQL) can be utilized to control the processing-microstructure-surface integrity relationship during GH4169 machining. Controlled turning tests under dry, flood, MQL, and CMQL conditions were combined with SEM, TEM, EBSD, surface roughness, microhardness, residual stress, chip morphology, and tool-wear analyses. A GPU-parallelized smoothed particle hydrodynamics (SPH) thermo-mechanical cutting model was further employed to interpret the cooling-induced changes in temperature field and chip formation. The novelty of the study lies in linking directed tool-side cooling to chip segmentation, near-surface microstructural evolution, and service-relevant surface integrity metrics for GH4169, including a production-oriented casing-machining case. Under CMQL, the machined surface showed improved topography (peak-to-valley, PV = 1.612 mu m; Ra = 0.357 mu m), a limited hardened layer of similar to 110 mu m, and a compressive residual stress of similar to 55 MPa. Tool flank wear was reduced by similar to 48% compared with dry cutting. TEM and EBSD confirmed a thin nanocrystalline surface layer and a reduced machining-affected layer, while SPH simulations reproduced the observed temperature and chip-morphology trends. These results demonstrate CMQL as a process-design strategy for improving the surface integrity and machinability of GH4169 components.

The surface quality of the blade leading and trailing edges (LTE) impacts jet-engine performance. This study constructs a robotic abrasive cloth flap wheel (ACFW) polishing system and proposes a multivariate parameter decision-making method for the optimal polishing surface quality of the blade LTE. The robotic polishing system, including machine vision, offline programming, and constant force control, is first developed, and the blade polishing process, including blade clamping, on-machine measurement, position compensation, and polishing strategies, is then analyzed. Finally, a multivariate parameter decision-making method is proposed based on the surface roughness regression model (RM) and adaptive genetic algorithm-backpropagation (AGA-BP) network. The surface roughness RM, influencing factors, and the response curve are determined through a full factorial design (FFD) and the response surface methodology (RSM). Meanwhile, the AGA-BP network, which integrates the adaptive genetic algorithm (AGA) and backpropagation neural network (BPNN), is proposed to model and predict the roughness of the blade surface. Based on the optimal parameters, the surface roughness of the blade LTE will reach Ra = 0.142 mu m, which illustrates that the developed robotic polishing system is highly efficient and feasible. Furthermore, the mean error percentages of the RM, BPNN, and AGA-BP predictions are 17.946%, 9.633%, and 1.495%, respectively, for four random test datasets. The maximum error for the AGA-BP network is 1.995%, while the minimum is 0.758%. This network model can accurately predict surface roughness for the robotic polishing system of the Ti-6Al-4V blade LTE.

We report a method for achieving polarization smoothing of the large-aperture laser beam using a mechanical clamping device. A 450mm x 420mm x 43mm sized fused silica vacuum window was used as the implementation object for the polarization smoothing technique, and based on the narrow space constraints between this object and the high-power laser device, an implementation structure was designed that utilizes wedges to transmit and amplify loads. Under the action of the clamping structure, a gradient-varying planar stress field was generated within the optical aperture of the window, and the stress birefringence parameters of the material were altered, thereby realizing polarization modulation of the beam. Meanwhile, a near-field measurement device was designed for rapid offline measurement of the object's polarization modulation effect. The simulation and experimental results demonstrate that this method and structure can modulate a large-aperture linearly polarized beam into one with complex polarization state distribution, achieving a theoretical depolarization ratio of 40.8%. Moreover, this polarization smoothing method provides suppression of high-energy density speckle in the focal spot within the target area.

The uncertainty of the blade's position and attitude in robotic flexible polishing leads to poor accuracy and stability of force-position coupling, resulting in potential issues like over-polishing or under-polishing, significantly impacting the consistency of final polishing quality. The study proposes an online positioning method of thin-walled blade with small curvature for robotic flexible polishing. The novelty of proposed method lies in that it is based on optimal local geometric feature matching between the actual workpiece and CAD model to obtain the actual position and attitude of thin-walled blade with small curvature and limited measurement area, with a positioning accuracy of 0.3164 mm, thus achieving the adaptive optimization of robotic movement trajectory. Firstly, a mathematical model for the adaptive optimization of robotic movement trajectory based on the actual posture of workpiece is established. The theoretical principles of spatial point cloud mapping based on the forward kinematics model of serial-robot, spatial point cloud registration based on dense and sparse point clouds, workpiece posture analysis based on reverse derivation of point cloud transformation are secondly studied to achieve an accurate positioning of workpiece in the robotic workspace. The error sources of proposed positioning method are analyzed and a quantitative mathematical model is established to characterize the positioning accuracy of workpiece. The feasibility and reliability of proposed positioning method are finally validated through a typical experiment. The results demonstrate that the proposed method can achieve an accurate positioning of thin-walled blade with small curvature and limited measurement area and thereby ensuring the consistency of final polishing quality.

The effectiveness of film cooling in aero-engine turbine blades directly depends on the meticulously designed distribution of cooling holes. However, surface profile errors introduced by manufacturing processes create a discrepancy between the ideal design model and the actual blade geometry, making it impossible to fully implement the design layout in practice. In the case, drilling holes based on the theoretical coordinates leads to misplacement on the physical part and degraded cooling performance. To address this challenge, this study presents a design-intention-driven optimization method for the manufacturing process of turbine blade film cooling holes to enhance cooling performance. Unlike conventional methods that focus solely on geometric registration, the proposed method conducts a comprehensive analysis of blade clamping errors and surface profile errors. The methodology integrates thermo-fluid dynamic performance objectives directly into the manufacturing process control, bridging the gap between design and practical application. A performance-driven layout optimization is proposed to ensure the functional intent of the film cooling hole layout design is preserved. Machining experiments validate the method, demonstrating a reduction in positioning error of film cooling holes. Numerical simulations confirm that the optimized hole layout leads to an improvement in the overall cooling effectiveness compared to both conventional and simple geometric registration approaches.

Undesirable vibration and even chatter often occur during the unstable machining process of thin-walled parts. As an integral part of the machining system, machining fixtures play an important role in stable machining. This study proposes a novel flexible fixture system (FFS) with conformal flexible clamping, which combines curved shape retention and sufficient clamping force. The proposed FFS leverages bilateral flexible clamping forces to provide stiffness and damping, suppressing tangential vibrations at the clamping interface and transducing vibration control to the normal direction at machining points. A fixturing-machining dynamic model for conformal flexible clamping is then developed to systematically evaluate the impacts of the fixture parameters on the machining dynamics and chatter stability. Afterwards, the stability improvement mechanism of conformal flexible clamping is studied. By adjusting the clamping position and tangential stiffness, the tool-workpiecefixture system's dynamics can be optimized to suppress chatter and reduce forced vibrations. An FFS with integrated clamping position optimization is then designed with process flexibilities for adapting to complex workpiece shapes, workpiece-tool motion, and machining dynamics. A case study for thin-walled blade machining applications shows that chatter is suppressed, the vibration amplitude is reduced by 90.1 %, and the quality of the finished surface is improved. High damping performance, extensive adjustability for workpiecefixture system dynamics, and the flexibility to adjust fixture parameters throughout the machining process provide a high potential for stable machining of thin-walled parts.

The wear conditions of honeycomb sealing rings in aerospace engines are often complex. Traditional human operations based on sample paste exhibit poor adaptability and are inefficient. This paper proposes an automated detection method for the geometric features of wear marks on honeycomb sealing structures based on depth ratio features. Adaptive identification and quantification of cellular wear through point cloud data analysis. First, the point cloud data is cropped, followed by a least-squares fit iterative method to compute a reference line at a specified cross-section, which serves as a standard for computing the width and depth of wear marks while denoising the point cloud data. Subsequently, N-neighborhood sets and the depth ratio features within these sets are introduced, transforming the task of detecting wear marks' start and end points into a peak detection problem. An improved automatic multiscale-based peak detection (AMPD) algorithm with a masking mechanism is utilized to determine the extent of each wear mark. Finally, the geometric features are calculated for each wear mark. Experimental results demonstrate that the proposed method can robustly identify wear areas with varying depths and distributions, measurement time reduced by more than 90%, and fulfilling the requirements for identifying and measuring honeycomb wear marks.

The complexity of forming manufacturing and the error accumulation in multi-stage manufacturing processes lead to the contour deviation and the positioning error of turbine blade, resulting in the poor matching between the actual film cooling holes (FCHs) and the non-ideal blade surface, which is detrimental to the cooling effectiveness of FCHs. This paper studies a feature matching-based adaptive precision machining process for FCHs. This adaptive machining process consists of three parts: the digital detection, the model reconstruction and the precision machining. The digital detection is to digitally characterize the actual turbine blade by precise laser measurement. The model reconstruction includes the online positioning of actual turbine blade through geometric feature matching between the non-ideal workpiece and the design model as well as the adaptive reconstruction of FCHs on the deformed blade surface based on the design intent. The precision machining refers to the machining of FCHs based on the adaptively generated machining model. The novelty lies in that it is based on the design intent, rather than error propagation mechanisms or empirical methods, to establish a position mapping between the non-ideal workpiece and the design model. The proposed adaptive machining process is comprehensively evaluated by a typical case experiment and numerical simulation. Promising results have been achieved, indicating that the proposed adaptive machining process of FCHs has significant potential in industrial applications.

Polarization smoothing is one of the effective means to reduce laser plasma instability (LPI) in inertial confinement fusion (ICF). However, with the increase in laser power, there is currently a lack of stable singlebeam polarization smoothing methods suitable for engineering applications. In our previous work, we proposed a polarization smoothing idea based on stress birefringence of edge loading fused silica window, but two issues were left unresolved: determination of the optimal edge loads distribution and design of the loading structure within limited available space. In this article, a method for determining the optimal loads combining continuous load discretization processing and genetic algorithm is proposed. And guided by the optimized results, we propose a pre-tightening loading method based on the reaction force of deflection deformation of special-shaped beams. Enabling the loading structure to provide the optimal edge loads for the stressed optical window while being thin enough to allow the element to be installed into ICF final optics assembly. We conducted tests on the element in the ultraviolet (351 nm wavelength) section of a high-power laser system, with a laser energy of 2kJ/3 ns. The results showed that compared to the situation without polarization smoothing, the backscattered energy decreased by 50 similar to 60%, proving the effectiveness of this polarization smoothing scheme in reducing LPI.

Fluorescent penetrant inspection (FPI) represents a novel approach that efficiently inspects minor defects on the blade surface. However, it presents several challenges, including being sensitive to the environment, relying heavily on experiential knowledge, difficulty quantifying defect characteristics, and a lack of traceability of results. This study proposes an artificial intelligence (AI)-based detection framework to detect minor defects on jet-engine blade surfaces through fluorescent penetrant. A FPI system and a high-precision automation control method are first constructed, and a comprehensive database of typical surface defects found in the blade manufacturing process is obtained through the detection system. The feature extraction and fusion structure of the You Only Look Once (YOLO) v8 algorithm is then redesigned for enhancing its multi-scale feature detection capability, enabling efficient detection of blade surface defects. Rather than using the traditional Task-Aligned Assigner (TAA) strategy for minor defects, a Normalized Gaussian Wasserstein Distance (NWD) label assignment is applied to enhance bounding box similarity measurement. Ablation and comparative experiments are finally conducted for validation. The experimental outcomes highlight the effectiveness of the intelligent defect detection system in capturing and detecting minor defects on blade surfaces, utilizing the proposed YOLOv8-RN. Specifically, the mean average precision (mAP) of YOLOv8-RN across all categories reaches 0.933 at an intersection over union (IoU) of 0.5 for four typical defects: crack, cold lap, inclusion, and cavity. Moreover, YOLOv8-RN demonstrates enhancements of 11.7

Full Poincar & eacute; beams have application value in various optical technologies due to their diverse polarization distribution forms. It will be of great significance for promoting the application research of this kind of beam if there is an individual element with a simple structure and easy fabrication that can conveniently generate full Poincar & eacute; beams of various aperture sizes. We propose a birefringent model of a single transmission waveplate that can convert the single polarization laser into a full Poincar & eacute; beam, perform optical calculations for it, and elucidate its polarization modulation law. Then, we analyze the stress conditions for realizing such a waveplate using stress engineering methods based on the principle of elastic-optic effect. An optical test of near-field polarization modulation was conducted to verify the correctness of the theoretical analysis of generating full Poincar & eacute; beams using stress-optic elements. Finally, we discuss the influence of typical structure and tightening parameters of stressed windows on the phase retardance distribution, providing a reference for engineering design.

This study aims to reduce titanium alloy blade surface roughness and enhance compressive residual stress (CRS) using the low-plasticity ultrasonic rolling strengthening process (URSP). Due to the URSP’s multifactorial complexity and characteristics of few and irregular test samples, this study proposes a Genetic Bayesian-Back Propagation neural network (GB-BP) for a few sample parameters optimization for low-plasticity URSP of the blade, which combines a back propagation (BP) neural network with genetic algorithm (GA) and Bayesian Optimization (BO). The proposed approach establishes a robust correlation between processing parameters, blade surface roughness, and CRS. Firstly, an orthogonal test with three factors, rolling depth, feeding speed, and rolling distance, is designed. The signal-to-noise ratio (S/N) analysis and mean value analysis identify rolling distance and depth as the primary factors influencing surface roughness and CRS. Furthermore, BP complement with BO is employed to predict blade surface roughness and CRS after URSP. Finally, GB-BP is proposed to predict parameters, and experimental validation demonstrates the superior predictive accuracy of the GB-BP network. Compared to traditional BP models, the mean error percentages for GB-BP prediction dropped by 51.286% for surface roughness and 69.818% for CRS. The root mean square error (RMSE) decreased by 51.864% for surface roughness and 71.982% for CRS. This network model can provide accurate parameters optimization for low-plasticity URSP of blades.

During the CNC machining, the blades exhibit various surface defects, including diverse morphologies and dimensions. Deep learning-based intelligent detection algorithms for the blade production line aim to improve computational efficiency and accuracy while minimizing model dimensions. This study proposes an enhanced blade detection method predicated upon a real-time detection transformer (RT-DETR) to detect blade surface defects precisely and efficiently in the blade production line. A dataset of blade surface defects in the blade machining process is first constructed, focusing on four surface defect types: gash, scratch, bruise, and pockmark. Secondly, the backbone network segment is substituted with an improved and more lightweight ResNet18 to optimize defect detection efficiency. The original feature fusion approach in RT-DETR is replaced by a Hierarchical Scale-based Feature Pyramid Network (HS-FPN) to enhance the model’s capability of detecting blade surface defects across various scales. The Inner-GIoU loss function is employed in RT-DETR to expedite model convergence and improve the accuracy of detecting minor surface defects. The results illustrate that the approach developed in this study raises the detection accuracy (mAP@0.5) by 3.5

This study proposes a hybrid process method based on Cryogenic Minimum Quantity Lubrication and Ultrasonic Rolling Strengthening Process (CMQL-URSP) to improve the surface integrity and enhance the mechanical properties of blade surface. First, the principle of the CMQL-URSP hybrid process was described. Second, the TEM experiments were conducted to clarify the influence of the CMQL-URSP hybrid process on aircraft engine blades. Finally, the blade processing experiments were performed to demonstrate the effectiveness of the CMQL-URSP hybrid process on the blade surface micro-morphology, micro-hardness and residual stress. The results indicate that the CMQL-URSP hybrid process effectively overcomes the limitations inherent to the solitary application of URSP. The CMQL process inhibits work hardening, thereby allowing the URSP to achieve better low-plastic surface improvement. Grain refinement governed by the continuous dynamic recrystallization mechanism leads to the formation of nanocrystals, which significantly improves mechanical properties of blade surface. The CMQL-URSP hybrid process results in a reduction in surface roughness from Ra 2.644 μm to Ra 0.055 μm, an increase in surface residual compressive stress from 321 MPa to 657 MPa, and the formation of a reinforced layer with a depth of 3.7 mm on the blade, thereby enhancing the surface integrity of the blade.

A new mining dynamic cable configuration device has been designed with adjustable cable curvature, full-range guiding restriction, and an anti-dragging warning function to improve the intelligence level and multi-scenario applicability. The digital model of the dynamic cable configuration device is constructed, and a theoretical formula for interactions between its structure parameters, assembly parameters, and the cabling work state is deduced. Strength analysis and topology optimization reconstruction of the side plate of the dynamic cable configuration device are carried out by using Ansys. The intelligent cable retractable device has been successfully applied in engineering. These research results can provide a theoretical basis for cooperative regulation and intelligent upgrading of both mining dynamic cable configuration devices and intelligent cable retractable devices.

In laser-driven inertial confinement fusion (ICF) facilities, nonuniform laser irradiation can cause significant challenges, such as hydrodynamics instability and laser plasma instability, which hinder the success of fusion. This article presents a new idea for improving the uniformity of far-field laser irradiation through a method of single-beam polarization smoothing. The method involves modulating full Poincaré beams using stress-engineered optics made from fused silica. We designed a stress birefringence system and conducted opto-mechanical modeling and analysis on it. The article elaborates on the mechanism and principles of generating large-aperture full Poincaré beams by stress birefringence, as well as the mechanism of polarization smoothing by full Poincaré beams. Near-field polarization measurements were conducted to verify these mechanisms, and the effectiveness of this method in improving the uniformity of laser irradiation in the target area was evaluated through far-field optical tests.