Search

Thin-walled parts (TWPs) are widely used in aerospace, and their service performance is significantly affected by the machining accuracy. Multi-pass machining is used to machine the poor stiffness TWPs. However, it is difficult to accurately predict the final machining accuracy due to surface topography error propagation and accumulation in multi-pass machining. Therefore, this paper proposes a multi-pass machining accuracy prediction method for TWPs based on dynamic factors (cutting force and stiffness). First, a flexible cutting force prediction model, which considers the axial errors determined by the initial surface topography and part deflection, is proposed. Second, a position-pass-dependent stiffness (PPDS) model is established considering the position dependence of stiffness and multi-pass machining material removal. Finally, combining the two models above, a multi-pass machining accuracy prediction method based on a genetic algorithm–back propagation (GA-BP) neural network is proposed. Experiments under various conditions are carried out to validate the proposed method. The machining accuracy (flatness as an example) is as high as 90.8% using the method in this paper, while it is only 73.9% when the accumulative error is neglected. The proposed method can significantly improve the performance of machining accuracy prediction by revealing the error propagation mechanism and the effect of dynamic factors between multi-pass machining. Furthermore, this also provides a theoretical basis for process parameter optimization and machining accuracy improvement in TWP machining. [ABSTRACT FROM AUTHOR]

Reducing manufacturing cost is the main goal of machine tool precision allocation under the condition of meeting precision design requirements. The previous studies generally took "ensuring machining errors completely within the allowable range of design precision" as constraint. Due to the strict constraint, the cost reduction effect is limited. This paper proposes a new method of precision allocation based on precision reliability. The probability that the machining errors are within the design precision allowable range is taken as the measurement index of precision reliability, and the optimization model constraint is relaxed to "that the machining errors are within the allowable range of design precision with predefined precision reliability", so as to obtain lower manufacturing cost under tolerable precision loss risk. The case study of a large-scale gear hobbing machine shows that this method can effectively reduce the manufacturing cost, and the precision allocation is more economical and reasonable. [ABSTRACT FROM AUTHOR]

To maintain a high-quality machining process, it is necessary to develop an online cutting temperature prediction model accurately. However, using the conventional cutting temperature modeling methods, it is difficult to capture the continuous and multivariate time-variant characteristic of cutting temperature. Recently, local learning and switching dynamics have been employed to identify the time-variant characteristic. However, it requires quantitative and precise analysis with certain switching patterns, which are hard to realize in the machining process. In this article, a self-adaptive local learning method integrated with dynamic convolutional neural networks (DCNN) is proposed. The moving window strategy and t-test analysis of performance maps are first to give the local domains. Then, a DCNN is designed to capture spatial cross-correlations and temporal autocorrelations in each local domain. Finally, the local models are ensemble using Bayesian ensemble learning. The effectiveness of the proposed method is demonstrated through different process information and tool conditions. [ABSTRACT FROM AUTHOR]

Tool condition monitoring (TCM) is vital to maintain the quality of workpieces during machining. Recently, data-driven methods based on multisensory data have been applied to TCM. The quality of extracted features is a key to realizing a successful data-driven TCM. However, the extracted features in the previous study are focused on the multicollinearity of multisensory data, which is incapable of identifying the informative and discriminative information in the long time period aspect. This article proposed a novel method for TCM using deep spatial-temporal feature extraction and lightweight feature fusion techniques. A key to the proposed method is the extraction of multicollinearity as spatial features (SPs), and the capture of long-range dependencies and nonlinear dynamics as temporal features (TFs), to fully characterize tool wear change using multisensory data. Then, a lightweight feature fusion method is used to fuse SPs, TFs, and statistical features for further removing redundant information employing the kernel-principal component analysis. Finally, support vector machines is used to predict the tool conditions using the fusion feature. Experiments on a milling machine and a gear hobbing machine are carried out to verify the effectiveness and generalization of the proposed method respectively. [ABSTRACT FROM AUTHOR]

Surface roughness, which has a significant influence on fatigue strength and wear resistance, is an important technical parameter. In practical machining, it is unstable and may be larger than the acceptable surface roughness due to unstable machining process. This will seriously deteriorate the surface performance of the workpieces. Therefore, an effective surface roughness stabilization method is of great significance to improve machining efficiency and reduce machining cost. In this paper, a surface roughness stabilization method is proposed and illustrated by taking five-axis machining as an example. A self-learning surface roughness prediction model based on Pigeon-Inspired Optimization and Support Vector Machine is firstly constructed and its prediction error is only 8.69% in the initial stage. This model has the self-learning ability that the prediction accuracy can be improved with the increase of training data. Furthermore, a machining parameters self-adaption adjustment method based on digital twin is proposed to make the machined surface quality stable. In this method, considering the feasibility of practical machining operation, the cutter posture (i.e. lead angle and tilt angle in five-axis machining) and spindle speed are selected as the adjustable parameters. When the predicted surface roughness doesn't meet the requirements, the Gradient Descent algorithm is applied to recalculate the new parameters for adjustment. According to the experimental results, the proposed method can stabilize surface roughness and improve the surface quality, which is vital for the precision manufacturing of complex workpiece. Meanwhile, it also greatly improves the intelligence level of manufacturing and production. [ABSTRACT FROM AUTHOR]

Characterizing and analyzing energy behaviors are significantly essential to improve energy efficiency for machining the workpieces in modern manufacturing enterprises. This paper proposes a flexible energy behaviors modeling method for machining the workpiece based on feature technology. Energy behaviors for machining the features of the workpiece are flexible, which are affected by the design parameters and the production scenarios of the workpiece. In the method, the multiple factors influencing the energy behaviors are decomposed into Design-related factors, Process-related factors and Machine-related factors. A timed hierarchical object-oriented Petri net (TOPN) methodology is exploited to model the flexible energy behaviors for machining the workpieces. Energy behaviors affected by Design-related factors and Process-related factors are modeled by the data dictionaries and the associated attributes, while energy behaviors related to Machine-related factors are simulated by the structure of the TOPN. The case studies show that the quantitative insight of flexible energy behaviors can be provided efficiently, which can benefit to forecast energy consumption and find some potentials for saving energy during machining the workpiece. [ABSTRACT FROM AUTHOR]

The relative position and orientation deviation between grinding wheel and workpiece caused by geometric errors affect the machining accuracy of five-axis CNC gear profile grinding machine tools directly. Therefore, geometric error modeling and compensation are presented according to homogeneous transformation and differential motion matrix based on the multi-body system theory for the accuracy enhancement of the machine tools. Firstly, the open kinematic chain and the ideal homogeneous transformation matrix from workpiece to grinding wheel are established according to the topological structure of the CFXZAY-type, five-axis gear profile grinding machine tools and the basic homogeneous transformation matrix between coordinate frames. Secondly, the homogenous transformation matrices of linear pairs and rotary pairs with geometric errors are calculated, and the relationships of the error propagation from workpiece to grinding wheel are acquired as well on the basis of 37 geometric error components analysis. The geometric error models including position and orientation errors of grinding wheel in workpiece coordinate system are obtained with matrix multiplication by using small-angle approximation and ignoring the second-order and high-order error terms. Then, the Jacobian is obtained by using transforming differential motion matrix of each motion axis to compensate the integrated error components of the grinding wheel, which can make the compensation effective and convenient with using the corresponding homogeneous transformation matrix. Finally, error measurement, error compensation, and machining experiments are carried out on a five-axis CNC gear profile grinding machine tool SKMC-1200W/10 to verify the applicability and effectiveness of the proposed error modeling, error compensation, and research approach. [ABSTRACT FROM AUTHOR]

Thermal deformation of large computer numerical control (CNC) gear profile grinding machine tools, which causes the position changes of grinding point between a grinding wheel and workpiece in X and Y directions, affects the machining accuracy significantly. In view of this situation, a theoretical model of thermal deformation based on the theories of thermal expansion of metallic materials, extensional axis of beam, non-uniform temperature distribution of Euler-Bernoulli beam, and Kirchhoff assumption of plane section is proposed according to the complex structure and machining process of the machine tools. To verify the accuracy and the reliability of the model, an experimental system and a platform for thermal deformation are established on a large CNC gear profile grinding machine tool, and the experimental data of temperature and displacement is measured and analyzed. Compared with theoretical value of displacement, the measurement data indicates that the relative errors are no more than 5 %. The proposed theoretical model and the adopted theories, technologies, and methods have great guidance significance and practical value to improve the accuracy of the machine tools effectively. [ABSTRACT FROM AUTHOR]

Cloud manufacturing (CMfg) is a new service-oriented networked manufacturing paradigm inspired by cloud computing. It provides high-efficiency and intelligent manufacturing services by organizing isolated manufacturing resources in a collaborative manner. Since the proposition of this concept in 2010, relevant research has mainly focused on theoretical frameworks of the CMfg system. However, actual applications of the machining service, which is a key part in the CMfg service platform, are hardly ever studied. In order to explore a feasible machining service mode, prime granularities of machining services are analyzed based on the current state of the manufacturing industry. Then a novel part manufacturing service combined with working procedure manufacturing service (PMS + WPMS) prime collaboration mode is proposed, followed by research of machining resource integration methods. To facilitate prospective implementations, information models of machining services are constructed using Web ontology language (OWL). The prime collaboration mode is expanded to a complete CMfg machining service platform. Furthermore, a working procedure priority-based algorithm (WPPBA) is designed for resource selection in CMfg. Finally, simulation experiments based on actual manufacturing data are conducted, in which the test results demonstrate the feasibility of the proposed service mode and the effectiveness of WPPBA compared with genetic algorithm (GA) and particle swarm optimization (PSO). This research provides essential guidance for CMfg applications. [ABSTRACT FROM AUTHOR]

[Display omitted] • Four-terminal-architecture CEDTS is proposed for thermal error control. • Hyper-parameters of ILSTM network are optimized by ISOA. • Comprehensive machining error model is constructed according to HCT theory. • Data services, including clustering analysis, status monitoring, and data funsion, are provided. • GPU-based cloud computing layer is used to expedite executing process. Production lines are important for the high-accuracy and efficient machining of parts. The thermal error of key machining equipment in production lines has a significant effect on the geometric accuracy of machined parts. To improve the geometric accuracy of machined parts, the thermal error of key machining equipment in a production line should be controlled. Then the collection, storage, analysis, and calculation of the large-volume manufacturing data are essential. But the processing involving the large-volume manufacturing data is time-consuming and challenging, which leads to low executing efficiency. To solve the problem that the system is inefficient in the processing of the large-volume manufacturing data, a four-terminal-architecture cloud-edge-based digital twin system (CEDTS) is proposed with a reasonable functional division of four terminals, and thus the executing efficiency of CEDTS is expedited. Then the error mechanism is studied to prove the long-term memorizing behavior, and an improved seagull optimization algorithm (ISOA) is proposed based on the chaos thought to optimize the weights, thresholds, and the number of iterations of an improved long short term memory (ILSTM) network with the attention mechanism. The ISOA-ILSTM error model is embedded into the intelligent decision-making terminal of CEDTS to predict the thermal error. Moreover, a comprehensive machining error model is proposed and embedded into the intelligent decision-making terminal of CEDTS to control the thermal error. Finally, the effectiveness of CEDTS is verified on a production line. The results show that the reduction of the large-volume manufacturing data for the collection, storage, analysis, and calculation is significant. With the implementation of CEDTS, the fluctuation range of geometric errors of machined parts is reduced significantly. The executing time is reduced by more than half by CEDTS with the GPU acceleration. [ABSTRACT FROM AUTHOR]

The thermal error is a dominant factor that seriously hinders the high-accuracy machining of complex parts. The weak robustness and low predictive accuracy have always been barriers to the wide use of data-based models. To improve the robustness, the transfer learning-based error control method is proposed in this study. The error mechanism modeling is conducted to demonstrate the memory behavior of thermal errors, and the applicability of a long short-term memory network (LSTMN) for the error prediction is proven. Then an improved least mean square (ILMS) is proposed to filter the high-frequency noises and remove singular values. A pre-activated residual block is designed, and is embedded into the deep residual LSTMN (DRLSTMN). The differential spotted hyenas optimization algorithm (DSHOA) is proposed based on the chaos initialization strategy, differential mutation operator, and nonlinear control factor to optimize the hyper-parameters of DRLSTMN. Then the ILMS-DSHOA-DRLSTMN error prediction model is proposed for machine tool #1. The transfer learning model is established for machine tool #2 based on ILMS-DSHOA-DRLSTMN to enhance the robustness. The predictive abilities of the transfer learning models of ILMS-DSHOA-DRLSTMN, ILMS-DRLSTMN, ILMS-DSHOA-LSTMN, ILMS-back propagation network (ILMS-BP), ILMS-multiple linear regression analysis (ILMS-MLRA), ILMS-least squared support vector machine (ILMS-LSSVM), ILMS-CNNs-LSTM (ILMS-CL), and ILMS-deep calibration (ILMS-DC) are 98.37%, 97.95%, 97.60%, 94.51%, 95.41%, 96.02%, 96.43%, and 96.06%, respectively. Finally, the actual machining experiments were performed. When the thermal error is controlled with the transfer learning model, the fluctuation ranges for the geometric errors for D1 and D2 are [− 4 μ m , 4 μ m ] and [− 3 μ m , 3 μ m ], respectively. [Display omitted] • Mechanism- and data-models are combined to improve accuracy. • New variable step is designed to propose ILMS. • DSHOA is proposed to optimize hyper-parameters of DRLSTMN network. • ILMS-DSHOA-DRLSTMN is proposed to improve predictive accuracy. • Transfer learning model is trained to improve robustness. [ABSTRACT FROM AUTHOR]

• Based on geometric analysis and machining dynamics analysis, interference- and chatter-free cutter postures are identified and used to construct posture accessibility and stability diagram (PASD). • A novel surface roughness prediction model based on the maximum cutter deformation force (CDF) is proposed. • A new cutter posture optimization algorithm is proposed to avoid interference and chatter while achieving better surface roughness. • The proposed method can not only extend service life of cutter and machine tool but also obtain workpiece with better surface quality, which is of great significance for five-axis machining. Five-axis CNC machining of sculptured surfaces plays a significant role in aerospace industry, such as blisk machining. The key issue involved is the determination of cutter posture in tool path planning. As the interference will cause the cutter to intrude the workpiece or machine tool and then seriously damage the cutter or machine tool, cutter posture must be well planned to avoid interference. Meanwhile, as the machined surface quality will be deteriorated inevitably when chatter arises, chatter must be eliminated as well. In this paper, posture accessibility and stability diagram (PASD) is firstly constructed by identifying interference- and chatter-free cutter postures based on geometric analysis and machining dynamic analysis. Furthermore, as surface roughness is an important characteristic to evaluate the surface properties of workpieces and should be generally minimized, its prediction model is also established for optimization. As is well known, surface roughness is mainly affected by cutter deflection due to inevitable cutter deformation force (CDF). By analyzing the relationship between surface roughness and maximum CDF, a novel surface roughness prediction model is proposed from a new viewpoint, i.e., the maximum CDF. Compared with the traditional prediction models considering only geometry, the proposed prediction model is much more straightforward, and the prediction results are more accurate (the average prediction error is only about 9.0%). This study reveals that the cutter posture has a great effect on surface roughness, which implies that surface roughness can be optimized from a new perspective (cutter posture). Finally, based on the proposed PASD and surface roughness prediction model, a new cutter posture optimization algorithm is proposed to minimize surface roughness. The algorithm considers both geometrical and dynamical constraints (interference and chatter) simultaneously, and it is verified by machining experiments under different cutter postures. According to the validation experiments, the proposed algorithm can effectively avoid the interference and chatter while minimizing the surface roughness (the optimized Ra is only 0.3589 μm compared to normal one 0.5476 μm). To the authors' best knowledge, it is the first time to optimize cutter posture by considering the following three aspects simultaneously: avoiding interference, eliminating chatter and reducing surface roughness. It will greatly improve the machined surface properties, while optimizing the utilization of the machine tool and cutter (extending their service life by avoiding various potential damages). This also will provide a new perspective that optimizes the machining process of complex and precise parts from cutter posture, which is of great significance to aviation and aerospace industries. Image, graphical abstract [ABSTRACT FROM AUTHOR]