Compacted graphite cast iron (CGI) is widely utilized in critical components such as high-performance diesel engines, exhaust manifolds, and braking systems, where it is frequently subjected to severe wear under thermal cycling. To address these challenges, this study developed a novel Nb-containing, high-temperature-resistant CGI and systematically investigated the influence of Nb content (0, 0.046, 0.096, 0.14, and 0.22 wt%) on its microstructure, mechanical properties, and tribological behavior against SiC ball at different temperatures (25, 300, 550, and 800 degrees C). The results indicate that increasing the Nb content refines the graphite morphology, while the ferrite content and grain size exhibit a non-monotonic trend, initially decreasing before slightly increasing. The addition of 0.046 wt% Nb yielded significant mechanical improvements, enhancing hardness by 22% and increasing tensile strength by 40.86% at room temperature and 58.87% at 800 degrees C. Regarding wear mechanisms, the dominant mode shifted from a combination of abrasive, adhesive, and oxidative wear at room temperature to predominantly oxidative wear at elevated temperatures. At 800 degrees C, the mechanism evolved into severe oxidative wear coupled with delamination. Within the 25-550 degrees C range, CGI containing trace amounts of Nb exhibits optimal wear resistance, while CGI with high Nb content demonstrates the best wear resistance at 800 degrees C. Furthermore, a wear prediction model incorporating oxidation kinetics and dissipated energy was constructed, providing a theoretical basis for evaluating the wear behavior of CGI across a wide temperature range.

Compacted graphite cast iron (CGI) is an ideal material for high-performance automotive components, but its widespread application is limited by poor machinability. The machining characteristics of CGI are closely related to its microstructure and accompanied by significant tool wear, necessitating a deeper understanding of how tool wear state and microstructural features affect the machining process. This study developed a microscopic finite element model incorporating vermicular graphite and pearlite phases. Numerical simulations and experimental investigations were conducted on cutting processes using two coated tools (Al₂O₃/TiCN and TiAlN) at different wear stages. The effects of microstructure, coating properties, and tool wear on chip morphology, cutting force, temperature distribution, and wear mechanisms were systematically analyzed. Results show that the maximum temperature concentrates in the crater wear region under both coating conditions (approximately 462 °C for TiAlN and 464 °C for Al₂O₃/TiCN), with high-temperature zones expanding continuously as wear progresses, thereby intensifying edge damage and plastic deformation. Stress analysis reveals that Al₂O₃/TiCN coating exhibits higher stress standard deviation and mean tensile stress than TiAlN coating across different wear stages and spatial scales, making it more susceptible to crack initiation and propagation at the coating/substrate interface. Good agreement between simulation results and experimental data validates the effectiveness of the proposed microscopic finite element model for studying CGI machining with worn tools.

In order to improve the friction properties of compacted graphite cast iron (CGI), trace amounts of Nb have been used to tune the microstructure of CGI, and as-cast high strength CGI with different Nb contents (0.046-0.22wt %) have been newly developed. The microstructure under the influence of niobium and its tribological behavior under different sliding speeds and loads were investigated by systematic friction and characterization experiments, and wear mechanisms and contact stresses were discussed. The results show that the niobium content affects the solidification process, thus the matrix morphology and precipitated phases. Under the influence of Nb, the graphite and matrix morphology was refined, the pearlite content increased, and the tensile strength increased. Moreover, the lattice constant of a-Fe matrix increases, and the phase hardness is improved. However, a critical value exists for the amount of Nb added. The specimens were subjected to abrasive, adhesive, and oxidative wear at low speeds and loads. With increasing speed or load, the main wear mechanisms change to oxidative and abrasive wear. The three-body oxide abrasive generated by oxide layer crushing significantly affects the wear rate. At high speeds, Nb caused the wear of CGI first to decrease and then increase. While at high loads, the wear rate decreases with increasing Nb content due to larger normal and shear contact stresses at the friction interface. The present work contributes to the understanding of the tribological properties of Nb-CGI under different sliding conditions.

Robotic spraying of building exterior walls is an important pathway towards construction automation and intelligent development. However, unclear spraying mechanisms and improper matching of process parameters often result in inconsistent coating quality in natural stone paint applications. This study proposes a mechanism-oriented method to investigate the influence mechanism of process parameters by integrating statistical analysis and machine learning. On-site robotic spraying experiments were conducted to collect coating quality data under different combinations of sliding table speed (v), spraying distance (s), screw pump speed (n) and atomization pressure (pw). Macroscopic statistical analysis was used to quantitatively evaluate the main effects of process parameters on coating central thickness (d), thickness variance (sd) and effective spray width (w). Harmony search-optimized support vector regression (HS-SVR) models were then developed to predict coating quality indicators. Based on these models, interaction effect diagrams were constructed to analyse parameter coupling effects. The results show that v is the dominant factor influencing d, sd and w. Lower v and shorter s improve d and w, while higher v combined with lower n enhances sd. This study provides a theoretical basis for intelligent parameter configuration in robotic exterior wall spraying.

Improving machining benefit while maintaining stable quality and performance is a prerequisite for improving intelligent manufacturing and enterprise competitiveness. This paper attempts to explore the method of segmented optimization of process parameters to improve benefit (such as machining time and tool life) while maintaining quality and performance within a given range during the tool life cycle in batch machining. An intelligent parameter adjustment framework is proposed, which utilizes the historical machining data to construct the process parameter adjustment time series (i.e., process planning) in the tool life cycle, and by online adding data from new tool machining processes, the time series can be modified. The key technology of the framework is to determine the adjustment point and the corresponding process parameters. A segmented prediction model based on historical data is presented to predict the adjustment point during the new tool machining process of, and a double depth Q-network (DDQN) is utilized to obtain the optimized machining parameters at the adjustment point. Based on a milling experiment of TC18, the effectiveness of the proposed method is validated by the prediction and optimization of the first adjustment point. The adjustment point is predicted to be the 58th machining of the new tool, after adjusting the process parameters obtained through DDQN at the adjustment point, the quality and cutting force remain within the set threshold, cutting time decreases by 0.2% and tool life increases by 14.42%, which shows that the proposed methods achieve quality assurance and benefit enhancement during the machining process.

The core of improving the comprehensive efficiency of laser cutting is to reduce the cost of cutting head transfer and piercing cost. This paper proposes a method based on the endpoint cutting problem model to connect multiple contours into a whole by considering the constrained connecting bridge to realize the uninterrupted cutting of multiple contours in one piercing and to reduce the length of the connecting bridge, and on the basis of which a cutting path planning method integrating the connecting bridge-air path is proposed, thus reducing the comprehensive cutting cost effectively. This method first analyzes and establishes an uninterrupted cutting optimization model considering the constraints of the contour features; then discretizes the contours according to the constraints to calculate the shortest distance between the contours and takes it as the feasible space for the length of connecting bridges; subsequently, an improved adaptive genetic algorithm is used to obtain the optimized global shortest connecting bridge positions and combinations that meet the constraints with the objective of fetching the minimum spanning tree; finally, by using the connecting bridge cutting method for planning the cutting path of the outer contour and determining the cutting sequence, coupled with the planning of the inner contour of the air path cutting trajectory, to achieve the purpose of integrating the reduction of transfer cost and piercing cost. Simulation results confirm the effectiveness and practicality of the proposed method.

Accurate and efficient detection of spray-painted regions and boundary delineations on building gables is crucial for promoting automated construction processes. External wall spraying robots rely on robust environmental perception. However, existing semantic segmentation techniques frequently suffer from low detection accuracy and inadequate feature representation under real-time constraints. Traditional convolution-based deep methods also exhibit limitations in handling complex boundary delineations. To address these challenges, we propose an innovative framework called Channel-Spatial Attention Deeplabv3+ Based Network (CSADnet). CSADnet enhances context modeling and global feature representation through a channel-spatial attention mechanism, effectively overcoming the commonly observed low recognition rate in current methods. A cross-spatial feature fusion module further integrates local and global information, thus improving segmentation performance. To tackle the issue of imbalanced training data, we introduce a weighted cross-entropy loss function that stabilizes model convergence. Additionally, we adopt a Chebyshev distance-based boundary error evaluation metric for a more intuitive assessment of spraying boundary accuracy. Experimental results on a real-world building image data set demonstrate that CSADnet outperforms existing state-of-the-art approaches. Compared with the benchmark network, CSADnet achieves a 2.44% improvement in mean intersection over union and a 1.97% increase in mean pixel accuracy, and average and maximum boundary errors are reduced by 9.15% and 9.80%, respectively. These findings highlight the remarkable performance and innovative merits of CSADnet in construction robotics, paving the way for more efficient and high-precision gable painting operations.

To explore the prediction accuracy of tool wear and achieve model parameter adaptive fine-tuning of a tool wear monitoring model used under different sensor combinations, this paper develops a tool wear state recognition model of deep forest (DF) with automatically select signal features and model parameter adaptive fine-tuning under variable sensor combinations, which can and improve the recognition accuracy and effectively reduce the model tuning work under different sensor combinations. In this paper, based on the autonomous feature selection ability of DF, DF is selected to establish an identification model for tool wear without additional feature selection operation, this was done to avoid the uncertainty of additional feature selection. Then, with the help of the characteristic that the number of layers of DF can be adaptively adjusted according to training data, DF is utilized to achieve model parameter adaptive fine-tuning of tool wear state recognition under variable sensor combinations. The sensors data of cutting force (F), vibration (V), acoustic emission (AE) and tool wear from Ti-5Al-5Mo-5V-1Cr-1Fe (TC18) milling were used for accuracy validation and analysis of feature selection ability of the developed model. Comparing with deep learning models from related literature and machine learning models with additional feature selection, DF obtains the highest prediction accuracy in F, V, F+V and F+V+AE with 92.65%, 88.24%, 97.06% and 97.06%. In addition, the developed recognition model has also achieved excellent recognition accuracy on the data of the numerical control machine tool health prediction competition published by the Prognostic and Health Management Society (PHM). These verifies the excellent prediction performance and feature selection ability of the developed model. This research provides effective guidance for the selection recognition models in the process of tool wear monitoring and expands the engineering application of DF.

Ti-5Al-5Mo-5V-1Cr-1Fe (TC18) is a difficult-to-machine material widely used in the aerospace field. To effectively promote intelligent machining technology for difficult-to-machine materials and obtain process parameters that meet requirements for processability in actual TC18 machining applications, this paper constructs a multiobjective optimization framework, with the goal or constraint of "Quality + Performance + Efficiency" in TC18 milling. The study employs support vector regression (SVR) optimized by the African Vulture Optimization Algorithm (AVOA) to predict tool force (Fh) and surface roughness (Ra), which are key indicators of machining performance and quality. AVOA-SVR was compared with SVR optimized by other algorithms. AVOA-SVR achieved the highest average R2 values (0.905 for Ra, 0.859 for Fh) and the lowest standard deviation, demonstrating its superior accuracy and stability. The influence of process parameters on Fh and Ra was analyzed to guide parameter selection for single-objective optimization. Additionally, the multiobjective AVOA (MOAVOA) was used to optimize three objectives as well as constrain two constraints. The results showed that MOAVOA effectively solves the multiobjective optimization problem in TC18 machining, outperforming commonly used algorithms.

To address the issues of workpiece distortion and excessive material melting caused by heat accumulation during laser cutting of thin-walled sheet metal components, this paper proposes a segmented optimization method for process parameters in sheet metal laser cutting considering thermal effects. The method focuses on predetermined perforation points and machining paths. Firstly, an innovative temperature prediction model Tpr,t is established for the nth perforation point during the cutting process, with a prediction error of less than 10%. Secondly, using the PSO-BP-constructed prediction model for laser cutting quality features and an empirical model for processing efficiency features, a multi-objective model for quality and efficiency is generated. The NSGA II algorithm is employed to solve the objective optimization model and obtain the Pareto front. Next, based on the predicted temperature at the perforation point using the model Tpr,t, the TOPSIS decision-making method is applied. Different weights for quality and efficiency are set during the cutting stages where the temperature is below the lower threshold and above the upper threshold. Various combinations of machining parameters are selected, and by switching the parameters during the cutting process, the thermal accumulation (i.e., temperature) during processing is controlled within a given range. Finally, the effectiveness of the proposed approach is verified through actual machining experiments.

With stricter emissions regulations and higher engine performance demands, the high-quality processing of Compacted graphite cast iron (CGI) for the automotive industry has received more and more attention. Coated carbide tools are now widely used to cut CGI. The coating material is an essential factor affecting processing efficiency and cost. However, the processing adaptability and wear mechanism of tool coating materials to CGI has yet to be thoroughly studied. CGI milling experiments in this paper were carried out using different coated carbide tools. The effect of coating materials on milling forces, tool wear and surface roughness for coated tools under different cutting parameters were compared and evaluated. It is found that TiAlN/TiN coated tools have the best cutting force, tool wear, and surface roughness, followed by TiAlN/AlCrN coated tools. The analysis of the tool failure process shows that bonding and oxidation are the main wear mechanisms of TiAlN/TiN, TiAlN/AlCrN, and TiCN coated tools, while bonding is the primary wear mechanism of TiN/TiCN/Al2O3 and TiN/MT-TiCN/Al2O3 coated tools. The wear mechanism of the flank is groove and coating wear, and the wear process is removing the coating material on the tool surface and chipping the unprotected cutting edge. When comparing the tool durability, it was found that the tool life of TiAlN/TiN was extended by 17.4

Energy saving and consumption reduction is one of the current important research in the field of green and sustainable manufacturing. Products or components containing variable curvature contouring are widely used in the automotive, medical, aerospace, and mold industries, while there is a lack of methods to model the energy consumption ratio for variable curvature contouring and improve its energy efficiency. A method for modeling the specific energy consumption of variable curvature contouring and energy consumption optimization is proposed for this problem. Firstly, the components of energy consumption in processing of the CNC machine tool machining are analyzed, and the relationship between curvature characteristics and material removal rate is investigated from the geometric perspective. Secondly, orthogonal experiments with different curvatures of straight lines, convex arcs, and concave arcs are designed to collect energy consumption data. Based on the experimental data, the Dueling Deep Q-Network optimization support vector regression (Dueling DQN-SVR) was used to establish the specific energy consumption model considering the curvature. Finally, a multi-objective optimization model is constructed when considering specific energy consumption, efficiency, and quality, and the Pareto solution set is solved using a multi-objective Gray Wolf optimization algorithm (MOGWO). The Technique for Order Preference by Similarity to Ideal Solution (TOPSIS) method was used to select the optimal combination of machining parameters. The experimental results show that the accuracy of the established model is more than 95%. The method improved energy efficiency by more than 7.82% and efficiency by more than 1.128%. These research results are of great theoretical and practical significance for achieving energy-efficient variable curvature contour machining.

The machining trajectory of the irregular contour is usually discretized into straight lines and arcs, and process parameters selection affects the quality and efficiency of irregular sheet metal parts machining. To guide parameters selection of irregular sheet metal parts milling, a multi-objective optimization framework for efficiency and side machining quality is constructed. In the framework, to improve the modeling accuracy and reduce modeling cost, the theory-data coupled models of side roughness for straight line, convex arc and concave arc constructed, respectively. Aiming at the problems of single search method and susceptibility to local optima in the standard multi-objective seagull optimization algorithm (MOSOA), an improved MOSOA (MOSOAimprove) is proposed to solved the multi-objective optimization model of side quality and efficiency developed by the coupled model of side roughness and the empirical formula of the material removal rate. The effectiveness of coupled models and MOSOAimprove in multi-objective optimization of irregular sheet metal parts milling are verified by the actual machining.

Intelligent recognition of bulges, windows, and other features in building gable point cloud data is a prerequisite and critical step for the implementation of automated spray-painting in construction. Gable point cloud data exhibit characteristics such as large scenes, orthogonal structures, color degradation, and feature imbalance. Addressing these attributes, this paper proposes TransWallNet, a point cloud semantic segmentation model based on the attention mechanism. To alleviate the computational load from large scenes, the model employs random sampling. For the orthogonal nature of the gables, it innovatively utilizes Chebyshev distance to query neighbors, incorporating an attention mechanism to effectively aggregate local point cloud information. This allows for the reliance solely on positional information of point clouds to identify various features, addressing the issue of color feature reliance. The combination of local feature aggregation and a global attention module attends to both local point cloud details and their contextual relationships, accurately segmenting various gable elements. Compared to other leading methods, our approach achieved the highest macroaverage accuracy and macroaverage F1-score on a building facade data set, increasing by 9.81% and 4.55%, respectively, over other methods. This research provides high-quality environmental information and perception methods for the construction of gable spray-painting robots.

The short segment discretization algorithm for complex curves is one of the critical factors in improving the quality and efficiency of economical CNC machine tools. However, traditional single constraint methods such as equal error and equal chord length algorithms cannot achieve the requirements of both quality and efficiency, and intelligent methods with high algorithmic complexity are unsuitable for traditional machining. To this end, a simple and effective method for generating short segment trajectories called area-chord error double constraint is presented in this paper. The area enclosed by the trace of the short line segment and the original curve is defined as area error, and the semicircle with chord length as the diameter is defined as constrained area. By controlling the ratio of the area error to the constrained area, short line segment separation with variable chord length and error can be achieved according to the curvature characteristics. The influence mechanism of short line segmentation on curves is investigated and the contour accuracy prediction model is established through 70 irregular curves from simple to complex. The experimental results show that this method can retain more geometric features of the original curve on the premise of fewer feature points so as to achieve both processing precision and efficiency.

The continuous short line segment processing method in CNC machining has the defect of frequent fluctuation of feedrate, which affects the quality and efficiency. For this problem, the local and global methods are common solutions. The local method is to insert transition curves at the corners to obtain a smooth toolpath, but this method does not essentially reduce the number of accelerations and decelerations, and it is difficult to insert transition curves between tiny straight sections. Although the global method can obtain smooth tool trajectories, the parametric interpolation method is not suitable for middle- and low-end CNC machine tools. The article proposes an adaptive tool path generation method with the original part contour as the research object and discretizes the NURBS curves into smooth trajectories consisting of large segments of straight lines and circular arcs. The article mimics the crawling characteristics of snakes and designs a double-headed snake algorithm based on the least squares method to implement this process. First, given the start and end points of the curve, two snakeheads search for the maximum linear and circular segments that satisfy the error constraint in the curve direction. The winner will then be selected as the candidate track segment through a competition mechanism. Finally, all trajectory segments are connected to obtain a smooth tool path. Experiments show that the toolpath data of the method in this paper are reduced by 75.56% compared with commercial CAM software when the contour error threshold is the same, and the contour error is reduced by more than one order of magnitude when the number of toolpath segments is equal. In addition, the method in this paper can obtain a smoother machining surface and more stable cutting force, thus achieving a win‒win situation of quality and efficiency.

为实现刀具磨损的准确预测,对加工过程的换刀和参数优化提供指导,提出一种基于最大信息系数(MIC)和改进的Bagging集成高斯过程回归(Bagging-GPR)的刀具磨损预测方法,建立切削力信号与刀具磨损间的非线性映射关系.采集加工的切削力信号,运用时域、小波包分解和经验模态分解提取切削力信号特征,并利用MIC分析特征与刀具磨损的相关度来实现特征选择,避免预测模型的"维数灾难".为提高预测模型的精度,考虑高斯子模型内部核函数的差异性及准确性,利用 Bagging 对高斯核函数进行随机组合,作为各子模型的核函数,构建改进的Bagging-GPR模型实现刀具磨损值预测,并基于铣削实验数据验证了所提方法的有效性和优异性.

For the process path problem of sheet metal cutting parts including bridge connection, a cutting path optimization method for sheet metal parts based on the traveling salesman problem model was proposed, and the location of bridge connection under this method was determined. Then, for the sheet metal layout diagram, the contour was split into processing graphic elements of N i sub-contour segments based on graphic element features, and the cutting path was planned with the goal of traversing all sub-contour segments. Furthermore, the cutting path including bridge connection positioning points was obtained by the improved ant colony algorithm, and the overall bridge connection positions were determined based on the bridge connection positioning points. Finally, the simulation verification of the well-arranged sheet metal cutting parts was tested, and the traditional generalized traveling salesman problem cutting method with bridge connection was compared with the related literature methods. The results show that this method can effectively reduce the cutting empty path and the number of starts and stops during the cutting process, which improving the processing efficiency.