A data and knowledge-driven cutting parameter adaptive optimization method considering dynamic tool wear

Tool wear prediction is of significance to reduce energy consumption through cutting parameter optimization. However, the current studies ignore the effect of machine aging on the tool wear prediction model, and their cutting parameter optimization methods cannot cope with the dynamic change of tool wear in the machining process. Thus, a reinforcement learning-enabled integrated method of tool wear prediction and cutting parameter optimization is proposed for minimizing energy consumption and production time. Specifically, the multi-source heterogeneous data fusion-based (MHDF) tool wear prediction model considering machine aging is first proposed to obtain the tool wear of the cutting tool. Then, a Markov Decision Process is designed to model the cutting parameter optimization process, which can be utilized to determine the proper cutting parameters adapted to the dynamic change of tool wear. Finally, the proposed method is demonstrated by extensive comparative experiments, and the results show that: 1) The proposed tool wear prediction model eliminates the influence of machine aging on prediction accuracy and has better generalizability for the machining data under different machine aging conditions, and its testing accuracy reaches 96.09%. 2) The proposed optimization method can adapt to the dynamic change of tool wear and further reduce the energy consumption and production time by 6.72% and 8.60% compared to that of not considering tool wear. The computation time of the proposed method is reduced by an average of 71.80%.     

Digital twin-driven surface roughness prediction and process parameter adaptive optimization

In the process of parts machining, the real-time state of equipment such as tool wear will change dynamically with the cutting process, and then affect the surface roughness of parts. The traditional process parameter optimization method is difficult to take into account the uncertain factors in the machining process, and cannot meet the requirements of real-time and predictability of process parameter optimization in intelligent manufacturing. To solve this problem, a digital twin-driven surface roughness prediction and process parameter adaptive optimization method is proposed. Firstly, a digital twin containing machining elements is constructed to monitor the machining process in real-time and serve as a data source for process parameter optimization; Then IPSO-GRNN (Improved Particle Swarm Optimization-Generalized Regression Neural Networks) prediction model is constructed to realize tool wear prediction and surface roughness prediction based on data; Finally, when the surface roughness predicted based on the real-time data fails to meet the processing requirements, the digital twin system will warn and perform adaptive optimization of cutting parameters based on the currently predicted tool wear. Through the development of a process-optimized digital twin system and a large number of cutting tests, the effectiveness and advancement of the method proposed in this paper are verified. The organic combination of real-time monitoring, accurate prediction, and optimization decision-making in the machining process is realized which solves the problem of inconsistency between quality and efficiency of the machining process.     

Adaptive restoration of complex geometry parts through reverse engineering application

After a certain number of hours of running, no two mechanical components are completely the same due to normal wear or foreign object damage. A nominal CAD model from a component designer is different from its corresponding worn one and therefore cannot be directly used for tool path generation for build up and machining repair processes. This is the main reason that most repair process used for complex geometry parts, such as gas turbine blades, is currently carried out manually and is called the “Black Art”.This paper proposes a defects-free model-based repair strategy to generate correct tool paths for build up process and machining process adaptive to each worn component through the reverse engineering application. Based on 3D scanning data, a polygonal modelling approach is introduced in this paper to rapidly restore worn parts for direct use of welding, machining and inspection processes. With this nominal model, this paper presents the procedure to accurately define and extract repair error, repair volume and repair patch geometry for the tool path generation, which is adaptive to each individual part. The tool paths are transferred to a CNC machine for the repairing trials. Further research work is performed on repair geometry extraction algorithm and repair module development within the reverse engineering environment.     

Multilevel classification of milling tool wear with confidence estimation

An important problem during industrial machining operations is the detection and classification of tool wear. Past research in this area has demonstrated the effectiveness of various feature sets and binary classifiers. Here, the goal is to develop a classifier which makes use of the dynamic characteristics of tool wear in a metal milling application and which replaces the standard binary classification result with two outputs: a prediction of the wear level (quantized) and a gradient measure that is the posterior probability (or confidence) that the tool is worn given the observed feature sequence. The classifier tracks the dynamics of sensor data within a single cutting pass as well as the evolution of wear from sharp to dull. Different alternatives to parameter estimation with sparsely-labeled training data are proposed and evaluated. We achieve high accuracy across changing cutting conditions, even with a limited feature set drawn from a single sensor.     

Tool wear state recognition based on linear chain conditional random field model

Tool condition monitoring (TCM) system is paramount for guaranteeing the quality of workpiece and improving the efficiency of the machining process. To overcome the shortcomings of Hidden Markov Model (HMM) and improve the accuracy of tool wear recognition, a linear chain conditional random field (CRF) model is presented. As a global conditional probability model, the main characteristic of this method is that the estimation of the model parameters depends not only on the current feature vectors but also on the context information in the training data. Therefore, it can depict the interrelationship between the feature vectors and the tool wear states accurately. To test the effectiveness of the proposed method, acoustic emission data are collected under four kinds of tool wear state and seven statistical features are selected to realize the tool wear classification by using CRF and hidden Markov model (HMM) based pattern recognition method respectively. Moreover, k-fold cross validation method is utilized to estimate the generation error accurately. The analysis and comparison under different folds schemes show that the CRF model is more accurate for the classification of the tool wear state. Moreover, the stability and the training speed of the CRF classifier outperform the HMM model. This method casts some new lights on the tool wear monitoring especially in the real industrial environment.     

加工过程智能最优自适应控制的研究

对加工过程最优自适应控制进行了探讨,提出了基于GA的切削用量优化方法和基于多感知融合策略的刀具磨损检测技术,建立了一种新的加工过程智能最优自适应控制系统。     

A novel approach to CNC machining center processing parameters optimization considering energy-saving and low-cost

NC machining is currently a machining method widely used in mechanical manufacturing systems. Reasonable selection of process parameters can significantly reduce the processing cost and energy consumption. In order to realize the energy-saving and low-cost of CNC machining, the cutting parameters are optimized from the aspects of energy-saving and low-cost, and a process parameter optimization method of CNC machining center that takes into account both energy-saving and low -cost is proposed. The energy flow characteristics of the machining center processing system are analyzed, considering the actual constraints of machine tool performance and tool life in the machining process, a multi-objective optimization model with milling speed, feed per tooth and spindle speed as optimization variables is established, and a weight coefficient is introduced to facilitate the solution to convert it into a single objective optimization model. In order to ensure the accuracy of the model solution, a combinatorial optimization algorithm based on particle swarm optimization and NSGA-II is proposed to solve the model. Finally, take plane milling as an example to verify the feasibility of this method. The experimental results show that the multi-objective optimization model is feasible and effective, and it can effectively help operators to balance the energy consumption and processing cost at the same time, so as to achieve the goal of energy conservation and low-cost. In addition, the combinatorial optimization algorithm is compared with the NSGA-II, the results show that the combinatorial optimization algorithm has better performance in solving speed and optimization accuracy.     

Design of neural network-based estimator for tool wear modeling in hard turning

Hard turning with cubic boron nitride (CBN) tools has been proven to be more effective and efficient than traditional grinding operations in machining hardened steels. However, rapid tool wear is still one of the major hurdles affecting the wide implementation of hard turning in industry. Better prediction of the CBN tool wear progression helps to optimize cutting conditions and/or tool geometry to reduce tool wear, which further helps to make hard turning a viable technology. The objective of this study is to design a novel but simple neural network-based generalized optimal estimator for CBN tool wear prediction in hard turning. The proposed estimator is based on a fully forward connected neural network with cutting conditions and machining time as the inputs and tool flank wear as the output. Extended Kalman filter algorithm is utilized as the network training algorithm to speed up the learning convergence. Network neuron connection is optimized using a destructive optimization algorithm. Besides performance comparisons with the CBN tool wear measurements in hard turning, the proposed tool wear estimator is also evaluated against a multilayer perceptron neural network modeling approach and/or an analytical modeling approach, and it has been proven to be faster, more accurate, and more robust. Although this neural network-based estimator is designed for CBN tool wear modeling in this study, it is expected to be applicable to other tool wear modeling applications.     

生产现场数据分析与刀具耐用度模型的建立

选择适当的刀具材料和合理的加工条件，是双轴数控立式车床实现火车车轮经济高效加工的关键之一，首要问题是建立加工条件下的刀具耐用度模型。本文根据车轮生产现场实际情况，首先提出一种多次端面快速刀具耐用度试验方法，通过适当安排试验因子和利用最小二乘法原理，推导出一系列数据处理公式；然后利用生产现场采集与处理数据，建立了多种涂层硬质合金加工火车车轮的刀具耐用度模型。最后，根据试验建立的刀具耐用度模型，对几种进口的涂层硬质合金刀具和两种国产硬质合金刀具的切削性能进行了比较。试验结果证明该方法具有贴合实际、准确可靠、经济实用、不影响生产等特点，为合理选择刀具和优化加工用量提供了理论依据。     

Tool wear monitoring using neuro-fuzzy techniques: a comparative study in a turning process

Tool wear detection is a key issue for tool condition monitoring. The maximization of useful tool life is frequently related with the optimization of machining processes. This paper presents two model-based approaches for tool wear monitoring on the basis of neuro-fuzzy techniques. The use of a neuro-fuzzy hybridization to design a tool wear monitoring system is aiming at exploiting the synergy of neural networks and fuzzy logic, by combining human reasoning with learning and connectionist structure. The turning process that is a well-known machining process is selected for this case study. A four-input (i.e., time, cutting forces, vibrations and acoustic emissions signals) single-output (tool wear rate) model is designed and implemented on the basis of three neuro-fuzzy approaches (inductive, transductive and evolving neuro-fuzzy systems). The tool wear model is then used for monitoring the turning process. The comparative study demonstrates that the transductive neuro-fuzzy model provides better error-based performance indices for detecting tool wear than the inductive neuro-fuzzy model and than the evolving neuro-fuzzy model.     

人工神经网络预测刀具磨损和切削力

刀具磨损和切削力预测与控制是切削加工过程中需要考虑的重要问题.本文介绍了利用人工神经网络模型预测刀具磨损和切削力的步骤并且针对产生误差的因素进行分析.首先将切削速度、切削深度、切削时间、主轴转速和不同频带的能量值通过归一化法处理,作为输入特征值,对改进的神经网络模型进行训练.然后利用训练完成的神经网络模型预测刀具磨损和切削力.结果表明:神经网络模型能够综合考虑加工过程中更多的影响因素,与经验公式结果对比,具有更高的预测精度.研究结果表明神经网络模型预测刀具磨损和切削力具有可行性和准确性,为刀具结构的优化及加工参数的选择提供了依据.     

Numerical analysis of the tool wear effect in the machining induced residual stresses

Machining is a dynamic process involving coupled phenomena: high strain and strain rate and high temperature. Prediction of machining induced residual stresses is an interesting objective at the manufacturing processes modelling field. Tool wear results in a change of tool geometry affecting thermo-mechanical phenomena and thus has a significant effect on residual stresses. The experimental study of the tool wear influence in residual stresses is difficult due to the need of controlling wear evolution during cutting. Also the involved phenomena make the analysis extremely difficult. On the other hand, Finite Element Analysis (FEA) is a powerful tool used to simulate cutting processes, allowing the analysis of different parameters influent on machining induced residual stresses.The aim of this work is to develop and to validate a numerical model to analyse the tool wear effect in machining induced residual stresses. Main advantages of the model presented in this work are, reduced mesh distortion, the possibility to simulate long length machined surface and time-efficiency. The model was validated with experimental tests carried out with controlled worn geometry generated by electro-discharge machining (EDM). The model was applied to predict machining induced residual stresses in AISI 316 L and reasonable agreement with experimental results were found.     

Feature-filtered fuzzy clustering for condition monitoring of tool wear

Condition monitoring is of vital importance in order to assess the state of tool wear in unattended manufacturing. Various methods have been attempted, and it is considered that fuzzy clustering techniques may provide a realistic solution to the classification of tool wear states. Unlike fuzzy clustering methods used previously, which postulate cutting condition parameters as constants and define clustering centres subjectively, this paper presents a fuzzy clustering method based on filtered features for the monitoring of tool wear under different cutting conditions. The method uses partial factorial experimental design and regression analysis for the determination of coefficients of a filter, then calculates clustering centres for filtering the effect of various cutting conditions, and finally uses a developed mathematical model of membership functions for fuzzy classification. The validity and reliability of the method are experimentally illustrated using a CNC machining centre for milling.     

Advanced adaptive feed control for CNC machining

In computer numerical control (CNC) machining, the tool feed rate is crucial for determining the machining time. It also affects the degree of tool wear and the final product quality. In a mass production line, the feed rate guides the production cycle. On the other hand, in single-time machining, such as for molds and dies, the tool wear and product quality are influenced by the length of machining time. Accordingly, optimizing the CNC program in terms of the feed rate is critical and should account for various factors, such as the cutting depth, width, spindle speed, and cutting oil. Determining the optimal tool feed rate, however, can be challenging given the various machine tools, machining paths, and cutting conditions involved. It is important to balance the machining load by equalizing the tool's load, reducing the machining time during no-load segments, and controlling the feed rate during high load segments. In this study, an advanced adaptive control method was designed that adjusts the tool feed rate in real time during rough machining. By predicting both the current and future machining load based on the tool position and time stamp, the proposed method combines reference load control curves and cutting characteristics, unlike existing passive adaptive control methods. Four different feed control methods were tested including conventional and proposed adaptive feed control. The results of the comparative analysis was presented with respect to the average machining load and tool wear, the machining time, and the average tool feed speed. When the proposed adaptive control method was used, the production time was reduced up to 12.8% in the test machining while the tool life was increased.     

Artificial intelligence for automatic prediction of required surface roughness by monitoring wear on face mill teeth

Nowadays, face milling is one of the most widely used machining processes for the generation of flat surfaces. Following international standards, the quality of a machined surface is measured in terms of surface roughness, Ra, a parameter that will decrease with increased tool wear. So, cutting inserts of the milling tool have to be changed before a given surface quality threshold is exceeded. The use of artificial intelligence methods is suggested in this paper for real-time prediction of surface roughness deviations, depending on the main drive power, and taking tool wear, \(V_{B}\) into account. This method ensures comprehensive use of the potential of modern CNC machines that are able to monitor the main drive power, N, in real-time. It can likewise estimate the three parameters -maximum tool wear, machining time, and cutting power- that are required to generate a given surface roughness, thereby making the most efficient use of the cutting tool. A series of artificial intelligence methods are tested: random forest (RF), standard Multilayer perceptrons (MLP), Regression Trees, and radial-based functions. Random forest was shown to have the highest model accuracy, followed by regression trees, displaying higher accuracy than the standard MLP and the radial-basis function. Moreover, RF techniques are easily tuned and generate visual information for direct use by the process engineer, such as the linear relationships between process parameters and roughness, and thresholds for avoiding rapid tool wear. All of this information can be directly extracted from the tree structure or by drawing 3D charts plotting two process inputs and the predicted roughness depending on workshop requirements.     

微铣削刀具磨损状态监测方法研究

为提高金属微铣削过程中刀具磨损状态在线监测系统的预测效率与精度,提出一种基于线性判别分析与改进型BP神经网络模型识别刀具磨损的方法;该方法通过传感器与数据采集系统采集微铣削过程振动信号,提取其时域和频域特征并通过线性判别方法进行降维约简;将降维后的特征输入经灰狼优化改进的BP神经网络模型,从而实现微铣刀磨损状态特征的分类;结果表明,提出的微铣刀在线监测方法能够准确识别微铣刀的各种磨损状态;此外,和其它分类算法相比,提出的基于灰狼优化算法的BP神经网络模型在分类精度和计算效率方面具有综合优势;这对实际生产过程中微铣刀的磨损状态监测具有非常重要的实际意义.     

Design of an optimal damper to minimize the vibration of machine tool structures subject to random excitation

The vibration of machine tools during machining adversely affects machining accuracy and tool life, and therefore must be minimized. The cutting forces for stable turning are generally known to be random, and hence excite all the resonance modes. Of all these modes, those that generate relative motions between a cutting tool and a workpiece are of concern.This paper presents a new approach for designing an optimal damper to minimize the relative vibration between the cutting tool and workpiece during stable machining. An approximate normal mode method is employed to calculate the response of a machine tool system with nonproportional damping subject to random excitation. The major advantage of this method is that it reduces the amount of computation greatly for higher-order systems when responses have to be calculated repeatedly in the process of optimization. An optimal design procedure is presented based on a representative lumped parameter model that can be constructed by using existing experimental or analytical techniques. The two-step optimization procedure based on the modified pattern search and univariate search effectively leads the numerical solution to the global minimun irrespectively of initial values even under the existence of many local minima.     

Pocketing toolpath computation using an optimization method

This paper proposes a new method of pocketing toolpath computation based on an optimization problem with constraints. Generally, the calculated toolpath has to minimize the machining time and respect a maximal effort on the tool during machining. Using this point of view, the toolpath can be considered as the result of an optimization in which the objective is to minimize the travel time and the constraints are to check the forces applied to the tool. Thus a method based on this account and using an optimization algorithm is proposed to compute toolpaths for pocket milling. After a review of pocketing toolpath computation methods, the framework of the optimization problem is defined. A modeling of the problem is then proposed and a solving method is presented. Finally, applications and experiments on machine tools are studied to illustrate the advantages of this method.     

虚拟加工中工件毛坯模型的建立

为解决虚拟加工中工件毛坯模型的识别问题,提出对规则形状工件毛坯采用OpenGL建模、对复杂形状工件毛坯采用美国初始图形交换规范（Initial Graphics Exchange Specification,IGES）文件进行模型数据转换的方法.该方法利用CAD软件为工件毛坯进行三维造型,生成IGES文件,然后在虚拟加工环境下读取IGES文件并生成工件毛坯模型,从而实现工件毛坯模型在新环境中的建立.经过建立具体的工件毛坯模型,验证相关理论的正确性,为在虚拟加工环境下工件毛坯模型的建立提供可行的依据.     

Modelling of the cutting tool stresses in machining of Inconel 718 using artificial neural networks

This study covers two main subjects: (i) The experimental and theoretical analysis: the cutting forces and indirectly cutting tool stresses, affecting the cutting tool life during machining in metal cutting, are one of very important parameters to be necessarily known to select the economical cutting conditions and to mount the workpiece on machine tools securely. In this paper, the cutting tool stresses (normal, shear and von Mises) in machining of nickel-based super alloy Inconel 718 have been investigated in respect of the variations in the cutting parameters (cutting speed, feed rate and depth of cut). The cutting forces were measured by a series of experimental measurements and the stress distributions on the cutting tool were analysed by means of the finite element method (FEM) using ANSYS software. ANSYS stress results showed that in point of the cutting tool wear, especially from von Mises stress distributions, the ceramic cutting insert may be possible worn at the distance equal to the depth of cut on the base cutting edge of the cutting tool. Thence, this wear mode will be almost such as the notch wear, and the flank wear on the base cutting edge and grooves in relief face. In terms of the cost of the process of machining, the cutting speed and the feed rate values must be chosen between 225 and 400 m/min, and 0.1 and 0.125 mm/rev, respectively. (ii) The mathematical modelling analysis: the use of artificial neural network (ANN) has been proposed to determine the cutting tool stresses in machining of Inconel 718 as analytic formulas based on working parameters. The best fitting set was obtained with ten neurons in the hidden-layer using back propagation algorithm. After training, it was found the R² values are closely 1.