Search

Regenerative chatter in machining operations such as milling is a common process anomaly that limits productivity and part quality, which in turn lead to increased manufacturing costs. The industrial relevance of the problem has sparked many research efforts over the recent decades, with a growing interest in real-time chatter detection and suppression. Inspired by learning from human demonstration frameworks, this paper proposes a new approach to milling chatter detection via effective human–machine interaction, which facilitates knowledge transfer from an experienced machine tool operator to a "Digital Apprentice." The proposed chatter detection approach acquires chatter-specific knowledge through a learnable skill primitive (LSP) algorithm designed to establish a robust chatter detection threshold from few-shot real-time demonstrations by an experienced human operator. In this work, digital audio data were acquired from milling experiments through a microphone mounted inside the milling machine. During the training phase, data for the human operator's natural reaction to chatter were collected via a specially designed human–machine interface. The learned chatter detection thresholds were obtained via the LSP algorithm by temporally mapping the reaction time data to the audio signal. During the testing phase, experiments were conducted to validate the detection accuracy and detection speed of the learned chatter detection thresholds under different cutting conditions. The experimental validation results of the learned thresholds indicate an average chatter detection accuracy of 94.4%, with 55.6% of chatter cases detected before chatter marks are produced on a 4140 Steel workpiece, thus demonstrating the effectiveness of human–machine interaction in chatter detection. [ABSTRACT FROM AUTHOR]

Most mechanical part models in current industrial manufacturing are composed of multiple different machining features. However, the traditional rule-based feature recognition methods are only suitable for analyzing simple and specific features. Although the existing methods based on deep learning are no longer limited to recognizing particular features, they cannot recognize complex overlapping features. To solve the above issues, this paper proposed a machining feature recognition approach based on the hierarchical neural network to recognize the multiple features on point cloud models. Firstly, the 3D models were converted into point cloud samples to construct the dataset, so that the approach could be applied to different 3D model formats. Then a hierarchical neural network called PointNet++ for single feature recognition was constructed. For the multi-feature point cloud models, a feature segmentation method was proposed to divide a complex multi-feature model into single feature models for recognition. Finally, the approach was evaluated on the created test data sets. The test results show that the overlapping machining feature on point cloud models can be accurately recognized with low computational cost. [ABSTRACT FROM AUTHOR]

Gear machining precision prediction is a challenging research topic because there are many influencing factors in the process of gear machining in terms of stochastic disturbance and hidden variables. To address this issue, a method that can predict gear manufacturing errors based on parameter significance estimations and probability regression is proposed in this paper. First, an adaptive machining quality evaluative function is designed to preprocess the raw precision detection data. Then, the key precision indices are extracted using a correlation and significance estimation (CSES) based on the modified density peak clustering (DPC) algorithm. A grading function is also designed, which can describe the precision grading of machined gear workpieces. Then, the significance estimation and attribution reduction of gear manufacturing parameters are performed using rough set theory. Finally, an adaptive variational inference Gaussian mixture regression (AVIGMR) model for gear machining error prediction is developed. The experimental results show that the proposed method has decent predictive capability with most gear precision detection indices and achieves superior comprehensive performance compared to eleven other regression algorithms. [ABSTRACT FROM AUTHOR]

This paper develops a prognostic technique called the logical analysis of survival curves (LASC). This technique is used to learn the degradation process of any physical asset, and consequently to predict its failure time (T). It combines the reliability information that is obtained from a classical Kaplan–Meier non-parametric curve to that obtained from online measurements of multiple sensed signals of degradation. An analysis of these signals by the machine learning technique, logical analysis of data (LAD), is performed to exploit the instantaneous knowledge about the state of degradation of the asset studied. The experimental results of the predictions of failure times for cutting tools are reported. The results show that LASC prognostic results are better than the results obtained by well-known machine learning techniques. Other advantages of the proposed techniques are also discussed. [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]

Machining accuracy reliability is considered to be one of the most important indexes in the process of performance evaluation and optimization design of the machine tools. Geometric errors, thermal errors and tool wear are the main factors to affect the machining accuracy and so affect the machining accuracy reliability of machine tools. This paper proposed a geometric error budget method that simultaneously considers geometric errors, thermal errors and tool wear to improve the machining accuracy reliability of machine tools. Homogeneous transformation matrices, neural fuzzy control theory and a tool wear predictive approach were employed to develop a comprehensive error model, which shows the influence of the geometric, thermal errors and tool wear to the machining accuracy of a machine tool. Based on Rackwite-Fiessler and Advanced First Order and Second Moment, a reliability model and a sensitivity model were put forward, which can deal with the errors of a machine tool drawn from any distribution. Then, a geometric error budget method of multi-axis NC machine tool was developed and formed into a mathematical model. In such method, the minimum cost of machine tool was the optimization objective, the reliability of the machining accuracy was the constraint, and the sensitivity was to identify the geometric errors to be optimized. An example conducted on a five-axis NC machine tool was used to explain and validate the proposed method. [ABSTRACT FROM AUTHOR]

Cutting parameters are important components in the process of computer numerical control (CNC) machining, and reasonable choice of cutting parameters can significantly affect the energy efficiency. This paper presents a multi-objective parameter optimization method for energy efficiency in CNC milling process. Firstly, the energy consumption composition characteristics and temporal characteristics in CNC milling are analyzed, respectively. The energy model of CNC milling is then established, of which the correlation coefficient is obtained through nonlinear regression fitting. Then a multi-objective optimization model is proposed to take the highest energy efficiency and the minimum production time as the optimization objectives, which is solved based on Tabu search algorithm. Finally, a case study is conducted to validate the proposed multi-objective optimization model and the optimal parameter solutions of maximum energy efficiency and minimum production time is obtained. Moreover, the parametric influence on specific energy consumption and production time are explicitly analyzed. The experiment results show that cutting depth and width are the most influential parameters for specific energy consumption, and spindle speed ranks the first for the production time. [ABSTRACT FROM AUTHOR]

Support vector machines are arguably one of the most successful methods for data classification, but when using them in regression problems, literature suggests that their performance is no longer state-of-the-art. This paper compares performances of three machine learning methods for the prediction of independent output cutting parameters in a high speed turning process. Observed parameters were the surface roughness (Ra), cutting force (Fc), and tool lifetime (T). For the modelling, support vector regression (SVR), polynomial (quadratic) regression, and artificial neural network (ANN) were used. In this research, polynomial regression has outperformed SVR and ANN in the case of Fc and Ra prediction, while ANN had the best performance in the case of T, but also the worst performance in the case of Fc and Ra. The study has also shown that in SVR, the polynomial kernel has outperformed linear kernel and RBF kernel. In addition, there was no significant difference in performance between SVR and polynomial regression for prediction of all three output machining parameters. [ABSTRACT FROM AUTHOR]

Early cost estimation of machined parts is difficult as it requires detailed process information that is not usually available during product design. Parametric methods address this issue by estimating machining time from predictors related to design choices. One of them is complexity, defined as a function of dimensions and tolerances from an analogy with information theory. However, complexity has only a limited correlation with machining time unless restrictive assumptions are made on part types and machining processes. The objective of the paper is to improve the estimation of machining time by combining complexity with additional parameters. For this purpose, it is first shown that three factors that influence machining time (part size, area of machined features, work material) are not fully captured by complexity alone. Then an optimal set of predictors is selected by regression analysis of time estimates made on sample parts using an existing feature-based method. The proposed parametric model is shown to predict machining time with an average percentage error of 25% compared to the baseline method, over a wide range of part geometries and machining processes. Therefore, the model is accurate enough to support comparison of design alternatives as well as bidding and make-or-buy decisions. [ABSTRACT FROM AUTHOR]

This paper presents a new approximate analytical method for the performance evaluation of inhomogeneous assembly/disassembly (A/D) systems with machines subject to failures and finite buffers. Processing times of machines in these systems are deterministic but not identical. Times between failures and times to repair are both assumed to be exponentially distributed. The method developed in this paper provides a generalized approach for analyzing A/D systems. Unlike the previous work on this subject, generalized exponential distributions are adopted instead of exponential distributions to approximate the repair time distributions of the fictitious machines. As a result the proposed method can handle the situation where the orders of magnitude of machines' reliability parameters (mean times between failures and mean times to repair) are not at the same level. A new algorithm is also developed to improve the convergence reliability and efficiency of the method. Extensive numerical experiments and simulation have been carried out to illustrate that the method proposed for A/D systems is quite accurate and efficient. [ABSTRACT FROM AUTHOR]

The need to monitor tool wear is crucial, particularly in advanced manufacturing industries, as it aims to maximise the lifespan of the cutting tool whilst guaranteeing the quality of workpiece to be manufactured. Although there have been many studies conducted on monitoring the health of cutting tools under a specific cutting condition, the monitoring of tool wear across multi-cutting conditions still remains a challenging proposition. In addressing this, this paper presents a framework for monitoring the health of the cutting tool, operating under multi-cutting conditions. A predictive model, using advanced machine learning methods with multi-feature multi-model ensemble and dynamic smoothing scheme, is developed. The applicability of the framework is that it takes into account machining parameters, including depth of cut, cutting speed and feed rate, as inputs into the model, thus generating the key features for the predictions. Real data from the machining experiments were collected, investigated and analysed, with prediction results showing high agreement with the experiments in terms of the trends of the predictions as well as the accuracy of the averaged root mean squared error values. [ABSTRACT FROM AUTHOR]

The capability to generate complex geometrical features at tight tolerances and fine surface roughness is a key element in the implementation of Creep Feed grinding process in specialist applications such as the aerospace manufacturing environment. Based on the analysis of 3D cutting forces this paper proposes a novel method of predicting the profile deviations of tight geometrical features generated using Creep Feed grinding. In this application, there are several grinding passes made at varying depths providing an incremental geometrical change with the last cut generating the final complex feature. With repeatable results from co-ordinate measurements both the radial and tangential forces can be gauged versus the accuracy of the ground features. The tangential force was found more sensitive to the deviation of actual cut depth from the theoretical one. However, to make a more robust prediction on the profile deviation its values were considered as a function of both force components (proportional to force: power was also included). For multi process, one machining platforms hole making was also investigated in terms of monitoring the force to ensure the mean cylinder was kept within required tolerances and with minimal subsequent machining (due to these imposed accuracies this is also considered a complex feature). Genetic programming (GP), an evolutionary programming technique, has been used to compute the prediction rules of part profile deviations based on the extracted radial and tangential force correlated with the said chosen “gauging” methodology (for grinding process). GP was also used to correlate the force and flank wear (VB) for hole deviations. It was found that using this technique, complex rules can be achieved and used online to dynamically control the geometrical accuracy of ground and drilled hole features. The GP complex rules are based on the correlation between the measured forces and recorded deviation of the theoretical profile (both grinding and hole making). The mathematical rules are generated from Darwinian evolutionary strategy which provides the mapping between different output classes. GP works from crossover recombination of different rules and the best individual is evaluated in terms of the given ‘best fitness value so far’ which closes on an optimal solution. The best obtained GP terminal sets were realised in rule-based embedded coded systems which were finally implemented into a real-time Simulink simulation. This realisation gives a view of how such a control regime can be utilised within an industrial capacity. Neural networks were used for GP decision verification ensuring less sensitivity to possible outliers giving more robustness to the integrated system. [ABSTRACT FROM AUTHOR]

This paper presents a new systematic approach to the optimization of both design and manufacturing variables across a multi-step production process. The approach assumes a generic manufacturing process in which an initial near net shape (NNS) process is followed by a limited number of finishing operations. In this context the optimisation problem becomes a multi-variable problem in which the aim is to optimize by minimizing cost (or time) and improving technological performances (e.g. turning force). To enable such computation a methodology, named conditional design optimization (CoDeO) is proposed which allows the modelling and simultaneous optimization of process parameters and product design (geometric variables), using single or multi-criteria optimization strategies. After investigation of CoDeO's requirements, evolutionary algorithms, in particular Genetic Algorithms, are identified as the most suitable for overall NNS manufacturing chain optimization The CoDeO methodology is tested using an industrial case study that details a process chain composed of casting and machining processes. For the specific case study presented the optimized process resulted in cost savings of 22% (corresponding to equivalent machining time savings) and a 10% component weight reduction. [ABSTRACT FROM AUTHOR]

Carbon fiber reinforced polymer (CFRP) is an important composite material. It has many applications in aerospace and automotive fields. The little information available about the machining process of this material, specifically when routing process is considered, makes the process control quite difficult. In this paper, we propose a new process control technique and we apply it to the routing process for that important material. The measured machining conditions are used to evaluate the quality and the geometric profile of the machined part. The machining conditions, whether controllable or uncontrollable are used to control part accuracy and its quality. We present a pattern-based machine learning approach in order to detect the characteristic patterns, and use them to control the quality of a machined part at specific range. The approach is called logical analysis of data (LAD). LAD finds the characteristic patterns which lead to conforming products and those that lead to nonconforming products. As an example, LAD is used for online control of a simulated routing process of CFRP. We introduce the LAD technique, we apply it to the high speed routing of woven carbon fiber reinforced epoxy, and we compare the accuracy of LAD to that of an artificial neural network, since the latter is the most known machine learning technique. By using experimental results, we show how LAD is used to control the routing process by tuning autonomously the routing conditions. We conclude with a discussion of the potential use of LAD in manufacturing. [ABSTRACT FROM AUTHOR]

Simultaneous optimization of interrelated manufacturing processes viz. part sequencing and operation sequencing is required for the efficient allocation of production resources. Present paper addresses this problem with an integrated approach for Single Stage Multifunctional Machining System (SSMS), and identifies the best part sequence available in the part-mix. A mathematical model has been formulated to minimize the broad objectives of set-up cost and time simultaneously. The proposed approach has more realistic attributes as fixture related intricacies are also taken into account for model formulation. It has been solved by a new variant of particle swarm optimization (PSO) algorithm and named as Chaos embedded Taguchi particle swarm optimization (CE-TPSO) that draws its traits from chaotic systems, statistical design of experiments and time varying acceleration coefficients (TVAC). A simulated case study has been adopted from the literature and effectiveness of the proposed algorithm is proved. The results obtained with different variants of its own are compared along with the basic PSO and Genetic Algorithm (GA) to reveal the superiority of the proposed algorithm. [ABSTRACT FROM AUTHOR]

Reduced machining time and increased accuracy for a sculptured surface are both very important when producing complicated parts, so, the step-size and tool-path interval are essential components in high-speed and high-resolution machining. If they are too small, the machining time will increase, whereas if they are too large, rough surfaces will result. In particular, the machining time, which is a key factor in high-speed machining, is affected by the tool-path interval more than the step size. The present paper introduces a ‘system software’ developed to reduce machining time and increased accuracy for a sculptured surface with Non-Uniform Rational B-Spline (NURBS) patches. The system is mainly based on a new and a powerful artificial intelligence (AI) tool, called artificial immune systems ( AIS). It is implemented using C programming language on a PC. It can be used as stand alone system or as the integrated module of a CNC machine tool. With the use of AIS, the impact and power of AI techniques have been reflected on the performance of the tool path optimization system. The methodology of the developed tool path optimization system is illustrated with practical examples in this paper. [ABSTRACT FROM AUTHOR]

Induced by flexibility of the industrial robot, cutting tool or the workpiece, chatter in robotic machining process has detrimental effects on the surface quality, tool life and machining productivity. Consequently, accurate detection and timely suppression for such undesirable vibration is desperately needed to achieve high performance robotic machining. This paper presents a novel approach combining the notch filter and local maximum synchrosqueezing transform for the timely chatter identification in robotic drilling. The proposed approach is accomplished through the following steps. In the first step, the optimal matrix notch filter is designed to eliminate the interference of the spindle frequency and corresponding harmonic components to the measured acceleration signal. Subsequently, the high-resolution time–frequency information of the non-stationary filtered acceleration signal is acquired by employing local maximum synchrosqueezing transform (LMSST). On this basis, the filtered acceleration signal is divided into a finite number of equal-width frequency bands, and the corresponding sub-signal for each frequency band is obtained by summing the corresponding coefficient of the LMSST. Finally, to accurately depict the non-uniformity of energy distribution during the chatter incubation process, the statistical energy entropy is calculated and utilized as the indicator to detect chatter online. The effectiveness of the proposed approach is validated by a large number of robot drilling experiments with different cutting tools, workpiece materials and machining parameters. The results show that the presented local maximum synchrosqueezing-based approach can effectively recognize the chatter at an early stage during its incubation and development process. [ABSTRACT FROM AUTHOR]

Manufacturing has experienced tremendous changes from industry 1.0 to industry 4.0 with the advancement of technology in fast-developing areas such as computing, image processing, automation, machine vision, machine learning along with big data and Internet of things. Machine tools in industry 4.0 shall have the ability to identify materials which they handle so that they can make and implement certain decisions on their own as needed. This paper aims to present a generalized methodology for automated material identification using machine vision and machine learning technologies to contribute to the cognitive abilities of machine tools as wells as material handling devices such as robots deployed in industry 4.0. A dataset of the surfaces of four materials (Aluminium, Copper, Medium density fibre board, and Mild steel) that need to be identified and classified is prepared and processed to extract red, green and blue color components of RGB color model. These color components are used as features while training the machine learning algorithm. Support vector machine is used as a classifier and other classification algorithms such as Decision trees, Random forests, Logistic regression, and k-Nearest Neighbor are also applied to the prepared data set. The capability of the proposed methodology to identify the different group of materials is verified with the images available in an open source database. The methodology presented has been validated by conducting four experiments for checking the classification accuracies of the classifier. Its robustness has also been checked for various camera orientations, illumination levels, and focal length of the lens. The results presented show that the proposed scheme can be implemented in an existing manufacturing setup without major modifications. [ABSTRACT FROM AUTHOR]

The demand for optimization of manufacturing processes rises as a reflection of the highly competitive market environment that requires shorter lead time and lower production costs. Although some approaches to milling process optimization have been developed based on analytical model using average cutting parameters, they are not available for complex workpieces when cutting parameters are time-varying and instantaneous cutting conditions need to be considered. In order to automate the optimization process and avoid costly machining tests, in this paper, an effective approach for parameters optimization of complex end milling process based on virtual machining is proposed. A computer-aided design (CAD)/computer-aided manufacturing (CAM) application is integrated for actual tool path generation and feedrate scheduling based on material removal rate. Then, a machining simulator based on octree and instantaneous force model is developed to evaluate feasibility of the given numerical control (NC) program, and the correctness of this simulator is verified by machining tests. The optimization process is controlled by the efficient global optimization method to find global optimal solution with fewer simulations and less computation time. During each iteration of the optimization process, NC programs are generated and evaluated automatically by the CAD/CAM application and the simulator, respectively. The effectiveness and efficiency of the proposed approach are proved by comparing the generated optimal solution (has reduced machining time and production cost) with the recommended cutting parameters from machining experts when machining an impeller. [ABSTRACT FROM AUTHOR]

Near-net-shaped jet engine blade machining process have better performance on both reducing material waste during production and improving work reliability in service, while precision machining of this blade is very challengeable and difficult due to its positioning difficulty and low stiffness. This paper propose that reasonable fixture and adaptive CNC machining technology can provide a systematic solution for the machining of near-net-shaped blade Tenon root, tip and Leading edges and Trailing edges (LTE). Firstly, process characteristics, difficulties and requirements of near-net-shaped blade are analyzed. Secondly, adaptive CNC machining process and its key technical principles are introduced and optimized, and proposes measuring bad points culling algorithm of simultaneously using distance relationship, angle relationship and radius relationship, and proposes camber line calculation algorithm of equidistant offset, and optimizes the iterative closest point (ICP) algorithm based on point-to-line ICP algorithm with six control points, and realizes the reconstruction of processing model. Finally, the feasibility of the proposed adaptive CNC machining process and the designed Polyetheretherketone (PEEK-GF30) material and multi-points support rigid-flexible coupling fixture are verified by a typical near-net-shaped blade LTE and Tenon root adaptive CNC machining process experiments. The results shows that the proposed process scheme of reasonable fixture and adaptive CNC machining process can solve two problems of near-net-shaped blade manufacturing of position difficulty and low stiffness. The designed fixture of PEEK-GF30 material and multi-point support rigid-flexible coupling, and the optimized adaptive CNC machining process algorithms can realize high-precision manufacturing of near-net-shaped jet engine blade. [ABSTRACT FROM AUTHOR]

This paper proposes an online evolutive procedure to optimize the Material Removal Rate in a turning process considering a stochastic constraint. The usual industrial approach in finishing operations is to change the tool insert at the end of each machining feature to avoid defective parts. Consequently, all parts are produced at highly conservative conditions (low levels of feed and speed), and therefore, at low productivity. In this work, a framework to estimate the stochastic constraint of tool wear during the production of a batch is proposed. A simulation campaign was carried out to evaluate the performances of the proposed procedure. The results showed that it was possible to improve the Material Removal Rate during the production of the batch and keeping the probability of defective parts under a desired level. [ABSTRACT FROM AUTHOR]

The aim of this paper is to process modelling of AWJM process on machining of green composites using fuzzy logic (FL). An integrated expert system comprising of Takagi–Sugeno–Kang (TSK) fuzzy model with subtractive clustering (SC) has been developed for prediction surface roughness in green AWJM. Initially, the data base is generated by performing the experiments on AWJM process using Taguchi (L 27) orthogonal array. Thereafter, SC is used to extracts the cluster information which are then utilized to construct the TSK model that best fit the data using minimum rules. The performance of TSK–FL model has been tested for its accuracy in prediction of surface roughness in AWJM process using artificially generated test cases. The result shows that, predictions through TSK–FL model are comparable with experimental results. The developed model can be used as systematic approach for prediction of surface roughness in green manufacturing processes. [ABSTRACT FROM AUTHOR]

Abstract This paper presents a tool axis vector approach for machining sculptured surfaces. Such an approach is well suited for highly twisted, rolled, or bent surfaces. The tool paths are generated for a 5-axis milling machine. The proposed approach is based on tilt angle, cutting direction, and a vector normal to the cutting surface. Gouging is avoided by checking the interference between the cutting tool and the part surface. The algorithm also finds maximum path intervals that generate maximum admissible cusp height within the specified tolerance limits. Such an approach minimizes the tool path and machining time. The paper presents an example to illustrate the details of the algorithm. [ABSTRACT FROM AUTHOR]

With ever-increasing understanding of environmental and societal concerns, the focus of manufacturing industries, worldwide, is fast changing from mere profit-making to ensuring sustainability. The companies are striving hard to make their manufacturing processes more environment-friendly, in addition to being cost effective and time- and resource-efficient. The paper presents an experimental investigation and an application of fuzzy modeling for trade-off among energy consumption, tool life, and productivity of a metal cutting (machining) process. A total of 54 grooving experiments are performed under various pre-determined combinations of the workpiece material hardness, cutting speed, cutting feed, and width of cut. The respective measurements are taken for tool damage, energy consumed, and cutting and feed forces. A fuzzy rule-based system is developed that consists of two modules: optimization and prediction. The former suggests the most suitable settings for the cutting parameters that would lead to accomplishment of various combinations of the objectives related to energy consumption, tool life, and machining productivity. The prediction module works out the predicted values of all the responses based on the finalized values of the four input parameters. [ABSTRACT FROM AUTHOR]

The efficient use of digital manufacturing data is a key leverage point of the factories of the future. Automatic analysis tools are required to provide smart and comprehensible information from large process databases collected on shopfloor machines-tools. In this paper, an original and dedicated approach is proposed for the data mining of HSM (High Speed Machining) flexible productions. It relies on an unsupervised learning (by statistical modelling of machining vibrations) for the classification of machining critical events and their aggregation. Moreover, a contextual clustering is suggested for a better data selection, and a visualization of machining KPI for decision aiding. It results in new leverages for decision making and process improvement; through automatic detection of the main faulty programs, tools or machine conditions. This analysis has been performed over two spindle lifespans (18 months) of industrial HSM production in aeronautics and results are presented, which assess the proposed approach. [ABSTRACT FROM AUTHOR]

Nowadays, monitoring systems are essential tools for manufacturing processes. As the main objective in machining processes is to produce high-quality products with reduced time, many efforts are being made to find new indirect methods that does not require to interrupt the process and does not have an excessively cost. Motivated by this premise, results of investigation on the relationship between audible sound emitted during process and the machining parameters are reported in this paper. Through experiments with the AISI 52100 hardened steel, this work shows that such a correlation does exist, presenting strong evidences that principal components scores, extracted from the power spectra of audible sound, are correlated with different machining parameters, such as material removal rate, cutting speed and depth of cut, as well as with different surface roughness levels, which makes it a promising feature for real-time process quality monitoring systems. [ABSTRACT FROM AUTHOR]

Feed rate effect on scallop height in complex surface milling by torus-end mill is rarely studied. In a previous paper, an analytical predictive model of scallop height based on transverse step over distance has been established. However, this model doesn't take feed rate effect into consideration. In the present work an analytical expression of scallop height, including feed rate effect, is detailed in order to quantify feed rate effect and thus to estimate more precisely the surface quality. Then, an experimental validation is conducted, comparing the presented model predictions with experimental results. Actually, the share of the scallop height due to feed effect is highly dependent on the machining configuration. However, most of time, the feed effect on total scallop height values is far from being negligible. [ABSTRACT FROM AUTHOR]

Currently, machine tool selection, cutting tool selection and machining conditions determination are not usually performed at the same time but progressively, which may lead to suboptimal or trade-off solutions. Targeting this issue, this paper proposes a big data analytics based optimisation method for enriched Distributed Process Planning by considering machine tool selection, cutting tool selection and machining conditions determination simultaneously. Within the context, the machining resources are represented by data attributes, i.e. workpiece, machining requirement, machine tool, cutting tool, machine conditions, machining process and machining result. Consequently, the problem of machining optimisation can be treated as a statistic problem and solved by a hybrid algorithm. Regarding the algorithm, artificial neural networks based models are trained by machining data and used as optimisation objectives, whereas analytical hierarchy process is adopted to decide the weights of the multi-objective optimisation; and evolutionary algorithm or swarm intelligence is proposed to perform the optimisation. Finally, the results of a simplified proof-of-concept case study are reported to validate the proposed approach, where a Deep Belief Network model was trained by a set of hypothetic data and used to calculate the fitness of a genetic algorithm. [ABSTRACT FROM AUTHOR]

A tool condition monitoring (TCM) system is vital for the intelligent machining process. However, literature has mostly ignored the interaction effect between product quality and tool degradation and has devoted less attention to the criterion of integrated diagnostics and prognostics to cutting tools. In this paper, we aim to bridge the gap and make an attempt to propose a novel integrated tool condition monitoring system based on the relationship between product quality and tool degradation. First, a cost efficient experimentation concerning high-speed CNC milling machining was implemented. Subsequently, a comprehensive correlation investigation was performed; revealing strong positive relationship exists between product quality and tool degradation. Mapping this relationship, an integrated TCM system pertaining to diagnostics and prognostics was proposed. Herein, the diagnostic reliability was enhanced by researching on the use of a multi-level categorization of degradation. The prognostic competence was enhanced by formulating it explicitly for the tools critical zone as a function of tool life. The system is integrated in a manner that, whenever the degradation curve of the tool reaches the critical zone, prognostics module is triggered, and remaining useful life is assessed instantaneously. To enhance the performance of this system, it is modeled employing support vector machine with optimal training technique. The proposed system was validated based on the experimental data. An extensive performance investigation showed that the proposed system provides a robust problem-solving framework for the intelligent machining process. [ABSTRACT FROM AUTHOR]

Machining state monitoring is an important subject for intelligent manufacturing. Feature construction is accepted to be the most critical procedure for a signal-based monitoring system and has attracted a lot of research interest. The traditional manual constructing way is skill intensive and the performance cannot be guaranteed. This paper presented an automatic feature construction method which can reveal the inherent relationship between the input vibration signals and the output machining states, including idling moving, stable cutting and chatter, using a reasonable and mathematical way. Firstly a large signal set is carefully prepared by a series of machining experiments followed by some necessary preprocessing. And then, a deep belief network is trained on the signal set to automatically construct features using the two step training procedure, namely unsupervised greedily layer-wise pertaining and supervised fine-tuning. The automatically extracted features can exactly reveal the connection between the vibration signal and the machining states. Using the automatic extracted features, even a linear classifier can easily achieve nearly 100% modeling accuracy and wonderful generalization performance, besides good repeatability precision on a large well prepared signal set. For the actual online application, voting strategy is introduced to smooth the predicted states and make the final state identification to ensure the detection reliability by taking consideration of the machining history. Experiments proved the proposed method to be efficient in protecting the workpiece from serious chatter damage. [ABSTRACT FROM AUTHOR]

Determination of optimal cutting parameters is one of the most essential tasks in process planning of sculptured parts to reduce machining cost and increase surface quality. This paper presents a multi-objective optimization approach, based on neural network, to optimize the cutting parameters in sculptured parts machining. An optimization mathematical model is first presented with spindle speed, feed rate, depth of cut and path spacing as the process parameters and machining time, energy consumption and surface roughness as objectives. Then a Back propagation neural network (BPNN) model is developed to predict cutting parameter, and experiments are designed to train and test the validation of developed BPNN model. Finally, an application case is given and its results demonstrate the ability of our method through comparing with the traditional approach. [ABSTRACT FROM AUTHOR]

In the recent years, there has been an increasing interest in presenting a comprehensive modeling technique to predict machining performances in different processes. As well, this paper proposes a new hybrid technique anchored in adaptive network-based fuzzy inference system (ANFIS) and modified genetic algorithm (MGA) to model the relationship between machining parameters and multi performances. MGA which employs a new type of population is effectively applied as the training algorithm to optimize the modeling parameters, finding appropriate fuzzy rules and membership function in the model. In the proposed MGA, a list of parameters is randomly considered as a solution and a collection of experiences 'in optimizing the solution' is utilized as population. To show the effectiveness of the presented model, it is applied to wire electrical discharge machining (WEDM) process for predicting material removal rate and surface roughness. The prediction results are compared with the most common prediction modeling techniques based on ANN and ANFIS-GA. The statistical evaluation results reveal that the ANFIS-MGA considerably enhances accuracy of the optimal solution and coverage rate. [ABSTRACT FROM AUTHOR]

This paper, an extension of our previous research, deals with the problem of jointly optimizing maintenance, production and inventory costs considering subcontracting and product returns. The manufacturing system, which fails randomly, has to satisfy a random product demand during a finite planning horizon under a required service level. The portion of products returned by the customers that are still in saleable condition are collected in the principle store from which customer demand is filled, while the portion that are non-conformal are collected in a second store and then remanufactured by a subcontractor. This study is validated by a real industrial case presented in this paper. [ABSTRACT FROM AUTHOR]

Aimed at satisfying the development demands of modern manufacturing for high quality spiral bevel gears, it is thought to be urgent and crucial to improve their machining efficiency and quality. The continuous maturing and fusion of information and network technologies open a new route for the manufacture of spiral bevel gears. With the consideration of requirements for the fast growth of such industry, this paper proposes a network-based manufacturing model for spiral bevel gears by combining the technologies of gear manufacturing with network, information and management. Firstly, the application integration framework and network communication architecture for spiral bevel gears network-based manufacture is built. On that basis, the business model of integrated platform for spiral bevel gears network-based manufacture is established. Subsequently, the information integration framework of network-based manufacturing processes is set up. Finally, through the network-based manufacturing application experiment and effect analysis, the feasibility of the proposed model, as well as the effectiveness on improving the processing efficiency and quality of such gears is verified. [ABSTRACT FROM AUTHOR]

The present paper focuses on machining (turning) aspects of CFRP (epoxy) composites by using single point HSS cutting tool. The optimal setting i.e. the most favourable combination of process parameters (such as spindle speed, feed rate, depth of cut and fibre orientation angle) has been derived in view of multiple and conflicting requirements of machining performance yields viz. material removal rate, surface roughness, SR $$(\hbox {R}_{\mathrm{a}})$$ (of the turned product) and cutting force. This study initially derives mathematical models (objective functions) by using statistics of nonlinear regression for correlating various process parameters with respect to the output responses. In the next phase, the study utilizes a recently developed advanced optimization algorithm teaching-learning based optimization (TLBO) in order to determine the optimal machining condition for achieving satisfactory machining performances. Application potential of TLBO algorithm has been compared to that of genetic algorithm (GA). It has been observed that exploration of TLBO appears more fruitful in contrast to GA in the context of this case experimental research focused on machining of CFRP composites. [ABSTRACT FROM AUTHOR]

The objective of this research is to develop a framework named Wise-ShopFloor and the enabling technologies for collaborative manufacturing in a decentralized environment. Particularly, this paper presents our latest development on Web-based and sensor-driven remote machining. Once a product design is given, its process plan and NC codes are generated by using a distributed process planning (DPP) system. The NC codes are then used for remote machining via a standard Web browser and a Java GUI interface running inside the browser. In this paper, the focus is given to the concept, architecture and a prototype implementation of the enabling technology. A case study of a test part machining on a 5-axis milling machine is also completed for testing and validation. It is expected that the developed technology can be applied to design verification via remote machining as well as real part production in a distributed manufacturing environment. [ABSTRACT FROM AUTHOR]

Environmental concern requires manufacturers to extend the domain of their control and responsibility across the product's life cycle. Much of the research has concentrated on assessment of environmental performance through the application of the Life Cycle Assessment (LCA) framework that provides a technical methodology to help identification of environmental impacts of product systems. However, the current LCA framework does not incorporate dynamic and diverse characteristics of manufacturing processes. As a result, the LCA's referential data will largely deviate from the real ones to an extent that the purpose of LCA is not meaningful. In other words, the current and fixed referential data-based method is not suitable to specify the impact categories related to manufacturing processes. From the perspective of decision making related with environmental impact during manufacturing, the current LCA method carried out in the off-line is hard to apply. As a result, performance index, such as greenability, a major performance index for environment conscious manufacturing cannot be implemented in the real practice. This paper presents the development of a framework (called process-oriented LCA) to realize environmental conscious manufacturing incorporating both greenability and productivity. To show the applicability and validity of this framework, experiments and analysis have been conducted and a prototype system has been implemented for a turning machining process. [ABSTRACT FROM AUTHOR]

Variation source identification for machining process is a key issue in closed-loop quality control, and critical for quality and productivity improvement. Meanwhile, it is a challenging engineering problem, especially for deep hole boring process of cutting-hard workpiece due to its complexity and instability. In this paper, a systematic method of variation source identification for deep hole boring process based on multi-source information fusion using Dempster-Shafter (D-S) evidence theory is proposed. A logic framework for variation source identification is presented to address how this issue can be formulated in the frame of evidence theory, in terms of evidence acquisition, variation source frame of discernment, mass functions and the rules for evidence combination and decision-making. First, run charts are applied to detect the non-random variation of quality measurements of one workpiece, which are acquired at equidistant positions along the axis direction of the hole. And the unnatural run chart patterns are detected by using fuzzy support vector machine and regarded as information cues for variation source identification. Then, the frame of discernment which consists of potential variation source in case of every specific unnatural pattern is constructed. The mass functions that represent the degree of belief supported by the unnatural patterns regarding the possible causes are determined by using judgment matrixes, and treated as pieces of evidences of variation source identification. Afterwards, all of the evidences are combined by using D-S fusion rules. The rules for making reliable diagnostic decisions are also addressed. Finally, a case study is put forward to demonstrate the feasibility and effectiveness of the proposed methodology. The results indicate that the proposed method can resolve the conflicts among the evidences and improve the accuracy of variation source identification for deep hole boring process. [ABSTRACT FROM AUTHOR]

This paper proposes an experimental investigation and optimization of various machining parameters for the die-sinking electrical discharge machining (EDM) process using a multi-objective particle swarm (MOPSO) algorithm. A Box-Behnken design of response surface methodology has been adopted to estimate the effect of machining parameters on the responses. The responses used in the analysis are material removal rate, electrode wear ratio, surface roughness and radial overcut. The machining parameters considered in the study are open circuit voltage, discharge current, pulse-on-time, duty factor, flushing pressure and tool material. Fifty four experimental runs are conducted using Inconel 718 super alloy as work piece material and the influence of parameters on each response is analysed. It is observed that tool material, discharge current and pulse-on-time have significant effect on machinability characteristics of Inconel 718. Finally, a novel MOPSO algorithm has been proposed for simultaneous optimization of multiple responses. Mutation operator, predominantly used in genetic algorithm, has been introduced in the MOPSO algorithm to avoid premature convergence. The Pareto-optimal solutions obtained through MOPSO have been ranked by the composite scores obtained through maximum deviation theory to avoid subjectiveness and impreciseness in the decision making. The analysis offers useful information for controlling the machining parameters to improve the accuracy of the EDMed components. [ABSTRACT FROM AUTHOR]

Feature recognition (FR) is one of the main tasks involved in computer-aided design, computer aided process planning, and computer-aided manufacturing systems. Conventional FR methods have topology, voxel, and pixel as model input data, which are rule-based, body decomposition-based, and neural network-based, respectively. However, FR methods are mostly applied to identify geometric features and are rarely manufacturing oriented. Recognizable feature types depend on the establishment of a feature database, which can easily lead to complex FR errors or omissions. This study proposes a novel recognition method for the general machining feature of 2.5-axis, one of the basic and commonly encountered feature types in manufacture industries. A novel ray fading algorithm is proposed to calculate the feature machining direction, and the type of 2.5-axis machining features is determined by both machining direction and topology. Features with machining directions can effectively assist the intelligent process planning to reduce the clamping changes and can potentially lead to significant time reduction for part machining. [ABSTRACT FROM AUTHOR]

Cutting tool condition is crucial in metal cutting. In-process tool failures significantly influences the surface roughness, power consumption, and process endurance. Industries are interested in supervisory systems that anticipate the health of the tool. A methodology that utilizes the information to predict problems and to avoid failures must be embraced. In recent years, several machine learning-based predictive modelling strategies for estimating tool wear have been emerged. However, due to intricate tool wear mechanisms, doing so with limited datasets confronts difficulties under varying operating conditions. This article proposes the use of transfer learning technology to detect tool wear, especially flank wear under distinct cutting environments (dry, flood, MQL and cryogenic). In this study, the state of the cutting tool was determined using the pre-trained networks like AlexNet, VGG-16, ResNet, MobileNet, and Inception-V3. The best-performing network was recommended for tool condition monitoring, considering the effects of hyperparameters such as batch size, learning rate, solver, and train-test split ratio. In light of this, the recommended methodology may prove to be highly helpful for classifying and suggesting the suitable cutting conditions, especially under limited data situation. The transfer learning model with Inception-V3 is extremely useful for intelligent machining applications. [ABSTRACT FROM AUTHOR]

This works presents a methodology, along with its software implementation called "Design 2 Cost", for evaluating the manufacturing cost and complexity of a part built by a subtractive (e.g. milling) or additive (e.g. laser metal deposition, Selective laser melting, wire-arc additive manufacturing) process. The overall manufacturing complexity is calculated as a weighted average of morphological and material criteria, which are defined either locally or globally. The local morphological criteria are calculated over the leaf nodes of an octree representation of the part using a raycasting technique. This allows to efficiently probe the local geometry of the part and compare it with manufacturing constraints emanating from the manufacturing process and its associated effector. This algorithm yields a cartography of the local complexity criteria that helps visualizing the problematic regions for the processes under consideration. The software is accompanied by a database that feeds the required material and process properties needed for the calculation of the manufacturing complexity and cost. The proposed methodology therefore permits a technical and economic comparison of manufacturing processes for a given geometry and material, as well as a comparison of various part geometries and materials for a given manufacturing process. [ABSTRACT FROM AUTHOR]

An energy-efficient intelligent manufacturing system could significantly save energy compared to traditional intelligent manufacturing systems that do not consider energy issues. Intelligent energy estimation of machining processes is the foundation of the energy-efficient intelligent manufacturing system. This paper proposes a method for machining activity extraction and energy attributes inheritance to support the intelligent energy estimation of machining processes. Fifteen machining activities and their energy attributes are defined according to their operating and energy consumption characteristics. Activities and energy attributes are extracted mainly from NC program supplemented with blank dimensional information. An effective extraction method of activities and energy attributes is the basis for the intelligent energy calculating of machining process. Based on an investigation on the extraction procedure of activities and energy attributes, energy attributes inheritance method is further discussed. Four types of energy attribute inheritance rules are summarized according to the different inheritance characteristics. Based on these four types of inheritance rules, the energy attributes can be transmitted from activity to Therblig as effective inputs of Therblig-based energy model of machining processes. The proposed methodology is finally demonstrated through two machining cases. [ABSTRACT FROM AUTHOR]

Excessive deformations and chatter vibrations are two main obstacles frequently encountered in turning of long slender workpieces. So far, there is seldom reported research using optimization techniques to cope with those difficulties. This paper introduces a new method for optimizing the machining parameters and the sequence of cutting passes in turning of a slender rod to control the deformation and chatter. The mathematical model is formulated, in which the deformation and chatter constraints are intensively derived. The optimization problem is solved in two phases. The first phase is to determine the minimum production time for an individual cutting pass for the predefined depths of cut. A hybrid solver combining a genetic algorithm and sequential quadratic programming technique is adopted to accomplish this step. In the second phase, a dynamic programming technique is employed to achieve the optimal sequential subdivision of the total depth of cut. A simulation experiment illustrates the methodology in detail. The inclusion relation of the solutions and the effect of the defined series for depth of cut are discussed. This proposed method has been proved effective and of generality in comparison with the previous works. [ABSTRACT FROM AUTHOR]

Thin-walled parts such as blades are widely used in aerospace field, and their machining quality directly affects the service performance of core components. Due to obvious time-varying nonlinear effect and complex machining system, it is a great challenge to realize accurate and fast prediction of machining errors of such parts. To solve the above problems, an engineering knowledge based sparse Bayesian learning approach is proposed to realize in-situ prediction of machining errors of thin-walled blades. Firstly, an engineering knowledge based strategy is proposed to improve the generalization ability of the model by integrating multi-source engineering knowledge, including machining information, physical information and online monitoring information. Then, principal component analysis method is utilized for the dimensional reduction of features. Sparse Bayesian learning approach is developed for model training, which significantly reduce the complexity of the regression model. Finally, the superiority and effectiveness of the proposed approach have been proven in blade milling experiments. Experimental results show that the average deviation of the proposed in-situ prediction model is about 11 μm, and the model complexity is reduced by 66%. [ABSTRACT FROM AUTHOR]

To ensure the machining processes stability of multistage machining processes (MMPs) and improve the quality of machining processes, a real-time quality monitoring and predicting model based on error propagation networks for MMPs is proposed in this paper. As there are some complicated interactions among different stages in MMPs, a machining error propagation network (MEPN) is proposed and its complexity is discussed to analyze the correlation among different stages in MMPs. Based on these, a real-time quality-monitoring model based on process variation trajectory chart is proposed to monitor the key machining stages extracted by MEPN. Due to the complexity of the correlation in MEPN, it is important and necessary to explore the variation propagation mechanism in MEPN. As for this issue, a machining error propagation model of machining form feature nodes in MEPN is established with the neuron model, which is solved with back-propagation neural network. The mapping relationship among machining errors of quality attributes is described through this node model. Furthermore, a novel equipment synthetic failure probability exponent of machining status nodes in MEPN is established to synthesize equipment's parameters by using logistic regression to quantitatively analyze the potential-failure and forecast the equipment degradation trend. At last, the machining process of a connecting rod is used to verify the proposed method. [ABSTRACT FROM AUTHOR]

This paper proposes a spatial three degrees of freedom (DOF) parallel kinematic machine enhanced by a passive leg and a web-based remote control system. First, the geometric model of the parallel kinematic machine is addressed. In the mechanism, a fourth kinematic link-a passive link connecting the base center to the moving platform center-is introduced. Each of the three parallel limbs is actuated by one prismatic joint, respectively. The additional link has three passive DOF, namely two rotations around x and y axes and one translation along z axis. With the existence of this link, the unwanted motion of the tool (located in the moving platform) is constrained. The fourth link also enhances the global stiffness of the structure and distributes the torque from machining. With the kinematic model, a web-based remote control approach is applied. The concept of the web-based remote manipulation approach is introduced and the principles behind the method are explored in detail. Finally, a remote manipulation is demonstrated to the proposed structure using web-based remote control concept. [ABSTRACT FROM AUTHOR]