Explore the vast range of titles available.

Wear is an inevitable problem in abrasive belt grinding, and the material removal rate decreases with continuous wear of the abrasive belt. This indicates that the grinding control force is affected by two dynamic factors, namely the actual material removal and abrasive belt wear state. To obtain an accurate force-control model to achieve uniform material removal, a new method for online monitoring of abrasive belt material removal rates and their corresponding wear statuses is proposed herein using only the grinding sound signals. By performing material removal rate and abrasive belt wear experiments, the grinding sound signals during processing are obtained. The wear states of the abrasive belt are quantified using the newly defined gray-mean values of the topographical images of the belt into different levels. The grinding sound signals are quantitatively described via the statistical features of their sound wavelet signals. The statistical features related to material removal rates or belt wear states are selected on the basis of the Pearson correlation coefficients. The prediction models for material removal rate and wear levels of the abrasive based on the selected features are then established using the LightGBM learning algorithm. Experimental datasets are used to train and validate the established model. The test results show that the evaluation parameters of the prediction model of the material removal rate are all within 5%. Further, the accuracy of the wear levels of the abrasive belt can exceed 91%. Compared with other prediction models, the new LightGBM models exhibit superiority in terms of time factor without loss of accuracy of the model. It is thus proved that the proposed method can provide a good basis for monitoring the material removal rate and belt wear in the abrasive belt grinding process.

Although the aspects that affect the performance and the deterioration of abrasive belt grinding are known, wear prediction of abrasive belts in the robotic arm grinding process is still challenging. Massive wear of coarse grains on the belt surface has a serious impact on the integrity of the tool and it reduces the surface quality of the finished products. Conventional wear status monitoring strategies that use special tools result in the cessation of the manufacturing production process which sometimes takes a long time and is highly dependent on human capabilities. The erratic wear behavior of abrasive belts demands machining processes in the manufacturing industry to be equipped with intelligent decision-making methods. In this study, to maintain a uniform tool movement, an abrasive belt grinding is installed at the end-effector of a robotic arm to grind the surface of a mild steel workpiece. Simultaneously, accelerometers and force sensors are integrated into the system to record its vibration and forces in real-time. The vibration signal responses from the workpiece and the tool reflect the wear level of the grinding belt to monitor the tool’s condition. Intelligent monitoring of abrasive belt grinding conditions using several machine learning algorithms that include K-Nearest Neighbor (KNN), Support Vector Machine (SVM), Multi-Layer Perceptron (MLP), and Decision Tree (DT) are investigated. The machine learning models with the optimized hyperparameters that produce the highest average test accuracy were found using the DT, Random Forest (RF), and XGBoost. Meanwhile, the lowest latency was obtained by DT and RF. A decision-tree-based classifier could be a promising model to tackle the problem of abrasive belt grinding prediction. The application of various algorithms will be a major focus of our research team in future research activities, investigating how we apply the selected methods in real-world industrial environments.

As an important material, titanium alloy is widely used in the manufacture of aircraft engine parts, and its processed surface quality is critical to the performance of aircraft engines. Abrasive belt grinding (ABG) is a kind of elastic grinding, which plays a significant role in improving titanium alloys’ surface integrity. To validate the mathematical model’s effectiveness from the grinding parameters to the surface residual stress after grinding, firstly, according to the molecular dynamics theory and ABG process, a physical model of titanium alloy ABG molecular system is proposed, and the embedded atom method is chosen as the interatomic potential of titanium alloy. Secondly, combined with the mathematical expression model of residual stress, the surface residual stress is characterized, and the heat correction coefficient is proposed to modify the mathematical model. Finally, based on molecular dynamics, the simulation of grinding residual stress and the grinding experiment is carried out for titanium alloy thin-walled parts. The results of simulation and experiment show that the trend of simulation results is similar to the experiment results. The simulation model can better represent the change rule of ABG surface residual stress for the titanium alloy material, but the average error rate is up to 15.01% due to the systematic error between the two. After correction, the average error rate between the simulation values and experiment values of residual stress on the surface decreases to 4.44%; the effectiveness of the mathematical model is verified.

Belt grinding is commonly applied for precision manufacturing of difficult-to-machine materials like GH4169, owing to its satisfactory elastic grinding properties, high efficiency, and strong adaptability. Abrasive belt wear is a common occurrence during the grinding process; however, its mechanism and effect on machining quality, particularly its influence on residual stress (RS), remain unclear. In order to compensate for these shortcomings, by means of experimentation, this paper studies how the RS distribution of GH4169 plate is affected by abrasive belt wear during robotic belt grinding, and the influence mechanism is analyzed from the perspectives of grinding force and heat. Firstly, the whole life cycle of the abrasive belt is determined through a wear test, then a novel evaluating index based on relative material removal rate is proposed to quantitatively characterize the wear conditions of belt. Secondly, according to the new division criteria, abrasive belts at various wear stages are created, and then, comparative grinding experiments of the GH4169 plate are carried out. Finally, based on the experimentally measured data, this paper fully analyzes and discusses the surface and subsurface RS distribution differences of grinding traces. The experimental findings suggest that the effect of abrasive belt wear on the surface RS distribution is notable in the grinding direction, but not in the vertical direction of the grinding traces. Additionally, as the belt conditions deteriorate, the overall grinding force ratio decreases while the accumulation of grinding heat increases, which leads to the generation of surface residual tensile stress (RTS) in the grinding direction. Furthermore, as a result of the uneven heat diffusion, the surface RS along the vertical direction of the grinding traces is distributed in an approximately symmetrical manner, with higher RS values in the center and lower values on the sides. As for the subsurface RS distribution, on the whole, with the progression of belt wear, the values of the subsurface residual compressive stress (RCS) layer decrease.

Abstract Abrasive belt grinding is a commonly used machining technique for many key components, especially on aerospace equipment. The surface roughness results from a belt grinding process are essential for the fatigue performance of workpieces; however, little research was reported on the surface topography generation of abrasive belt grinding. This study proposed a modeling and simulation method for the surface topography of abrasive belt grinding considering its elastic contact. Abrasive grain cloud forming tool was established combining standard grains number with Gaussian distribution. Workpiece surface and tool trajectory were discretized based on Brinell theory, which considered the microscopic cutting effects. Besides, Hertz theory is used to calculate the elastic deformation of rubber contact wheel with the selection of active abrasive grains and redistribution of forces in contact area; as a result, the interaction between multiple abrasive grains and workpiece could be simulated. Moreover, to verify the proposed method, numerical simulations and abrasive belt grinding experiments were conducted and compared. The results show that the minimum profile gap and error can reach 0.003 mm and 1.03% in terms of material removal depth and surface profile, and the error calculation is deeply affected by the denominator (simulation results). The grinding surface texture simulated by the model agrees well with the experimental observations, and the average predicting error of surface roughness is 3.25%.

The high-quality grinding of the aviation blade components with the industry robot presents tremendous challenges because of the complexity of blade surface. The hybrid force/position anti-disturbance control strategy is developed base on fuzzy PID control to improve the quality of grinding aviation blades. Firstly, according to gravity compensation technology, the perception of contact force is discussed to solve the contact force between the blades and abrasive belt machine. Then, the hybrid force/position anti-disturbance control strategy is designed to ensure the stability of robot automatic grinding system. The speed gain loop and the dual fuzzy PID control are introduced to enhance the anti-disturbance ability of the control system. Meanwhile, the analysis of stability and steady-state error for force control loop are performed to prove the validation of the feasibility of control system. Eventually, the simulation and experiments are carried out on the robot automatic grinding system. The experimental results reveal that the proposed control strategy can achieve better control effect and grinding quality compared with the traditional PID control.

The wear state of an abrasive belt is one of the important factors affecting the grinding precision of belt grinding processes. At present, there are two problems associated with the monitoring method of the wear condition of abrasive belts: (1) there are no uniform wear criteria to classify the wear condition of abrasive belts, and the segmentation threshold of the wear condition is affected by the change in the grinding parameters; and (2) an abrasive belt wear model based on indirect sensor monitoring of signals is affected by the change in the grinding parameters of abrasive belts; therefore, it is only suitable for abrasive belt wear monitoring under specific grinding parameters. This paper introduces a method of belt wear state monitoring based on machine vision and image processing. Surface images of an abrasive belt during its entire life are captured using a noncontact electron microscope. Three image features related to the wear state are selected: first-order distance of color component R, entropy of the horizontal subgraph, and vertical subgraph of the texture feature. Moreover, the wear state is classified into three categories based on the selected features. Using the selected features and the random forest classification algorithm, an abrasive belt wear state classifier is established. The performance of the classifier is verified and evaluated using a data subset of different images. The results show that the proposed method has high recognition accuracy for belt wear state, which can reach 99% in the accelerated wear stage. The proposed method solves the problem of the dependence and sensitivity of the monitoring model on the variation in the grinding parameters in the process of abrasive belt wear monitoring, and it improves the adaptability and versatility of the monitoring method.

Abrasive belt condition (BC) monitoring is significant for achieving profile finishing precision and quality in grinding of difficult-to-machine materials like Inconel 718. While indirect signal-based BC monitoring methods are ineffective when varying grinding parameters, existing image-based direct monitoring methods currently suffer from a lack of: (i) a unified and quantitative definition of the belt condition; (ii) in situ tool-surface image capture and relevant feature extraction; and (iii) continuous monitoring of the entire belt conditions. This paper proposes a partitioned BC monitoring method that is adaptable to ever-changing grinding conditions. Based on the belt surface analysis, a unified BC coefficient is quantitatively defined by using two critical BC-dependent features, the average area and number of worn flats of abrasive grains per unit area. The belt surface image is in-situ captured from moving belts and is preprocessed to eliminate image defects in a unified form, then the entire belt is partitioned, and finally the image features are extracted by Gabor filter and K-means clustering. The proposed robust method which has a maximum relative repeatability error of 9.33%, and less computation was validated by the experimental results. This study provides an adaptable and efficient way for continuously monitoring the conditions of the entire belt and the grinding area.

Titanium alloys have become an indispensable material for all walks of life because of their excellent strength and corrosion resistance. However, grinding titanium alloy is exceedingly challenging due to its pronounced material characteristics. Therefore, it is crucial to create a theoretical roughness prediction model, serving to modify the machining parameters in real time. To forecast the surface roughness of titanium alloy grinding, an improved radial basis function neural network model based on particle swarm optimization combined with the grey wolf optimization method (GWO-PSO-RBF) was developed in this study. The results demonstrate that the improved neural network developed in this research outperforms the classical models in terms of all prediction parameters, with a model-fitting R2 value of 0.919.

Pyramid-structured abrasive belts are characterized by their regular microgeometry and self-sharpening, layer-by-layer wear. The coupling of this wear evolution with material removal behavior may significantly influence the surface residual stress during grinding. In this study, pyramid belts at various wear stages were utilized to perform constant-load and constant-speed plane grinding of Mn13 high-manganese steel plates on a force-controlled robotic platform. Surface residual stress distributions in different directions were measured using X-ray diffraction, and their consistency was evaluated through repeated trials and statistical indices. The results indicate that the ground surfaces predominantly exhibit tensile stress, whereas compressive stress or a transition toward compression tends to occur at the entry and exit regions of the grinding path. In the transverse direction, σ x displays a symmetric distribution that diminishes in the final wear stage, while σ y evolves from initial compression to tensile stress with increasing magnitude. As belt wear progresses, the removal mode transitions from cutting to plowing and friction, resulting in σ x gradually shifting toward compression and σ y toward tensile. Consistency analysis reveals that the Relative Uniformity Index (RUI) remains stable across wear stages, with lower values observed in the transverse direction compared to those along the grinding path. This stability is closely related to the layer-by-layer wear and self-sharpening characteristics of the pyramid belts. Together, these results provide a systematic link between pyramid-belt wear evolution, material removal mode and three-dimensional residual stress distribution, offering a basis for controlling surface integrity in robotic belt finishing.