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.     

A standard deviation based firefly algorithm for multi-objective optimization of WEDM process during machining of Indian RAFM steel

Non-conventional machining processes always suffer due to their low productivity and high cost. However, a suitable machining process should improve its productivity without compromising product quality. This implies the necessity to use efficient multi-objective optimization algorithm in non-conventional machining processes. In this present paper, an effective standard deviation based multi-objective fire-fly algorithm is proposed to predict various process parameters for maximum productivity (without affecting product quality) during WEDM of Indian RAFM steel. The process parameters of WEDM considered for this study are: pulse current (I), pulse-on time (T _on), pulse-off time (T _off) and wire tension (WT).While, cutting speed (CS) and surface roughness (SR) were considered as machining performance parameters. Mathematical models relating the process and response parameters had been developed by linear regression analysis and standard deviation method was used to convert this multi objective into single objective by unifying the responses. The model was then implemented in firefly algorithm in order to optimize the process parameters. The computational results depict that the proposed method is well capable of giving optimal results in WEDM process and is fairly superior to the two most popular evolutionary algorithms (particle swarm optimization algorithm and differential evolution algorithm) available in the literature.

     

Zigzag machining surface roughness modelling using evolutionary approach

Milling is one of the common machining methods that cannot be abandoned especially for machining of metallic materials. The cutters with appropriate cutting parameters remove material from the workpiece. Surface roughness has the major influence on both obtaining dimensional accuracy and quality of the product. A number of cutter path strategies are employed to obtain the required surface quality. Zigzag machining is one of the mostly appealing cutting processes. Modeling of surface roughness with traditional methods often results in inadequate solutions and can be very costly in terms of the efforts and the time spent. In this research Genetic Programming (GP) has employed to predict a surface roughness model based on the experimental data. The model has produced an accuracy of 86.43%. In order to compare GP performance, Artificial Neural Network (ANN) and Adaptive Neuro Fuzzy Inference System (ANFIS) techniques were utilized. It was seen that the surface roughness model produced by GP not only outperforms but also enables to produce more explicit models than of the other techniques. The effective parameters can easily be investigated based on the appearances in the model and they can be used in prediction of surface roughness in zigzag machining process.     

An artificial immune system approach to CNC tool path generation

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.     

Learning Bayesian Network Classifiers: Searching in a Space of Partially Directed Acyclic Graphs

There is a commonly held opinion that the algorithms for learning unrestricted types of Bayesian networks, especially those based on the score+search paradigm, are not suitable for building competitive Bayesian network-based classifiers. Several specialized algorithms that carry out the search into different types of directed acyclic graph (DAG) topologies have since been developed, most of these being extensions (using augmenting arcs) or modifications of the Naive Bayes basic topology. In this paper, we present a new algorithm to induce classifiers based on Bayesian networks which obtains excellent results even when standard scoring functions are used. The method performs a simple local search in a space unlike unrestricted or augmented DAGs. Our search space consists of a type of partially directed acyclic graph (PDAG) which combines two concepts of DAG equivalence: classification equivalence and independence equivalence. The results of exhaustive experimentation indicate that the proposed method can compete with state-of-the-art algorithms for classification.Editors: Pedro Larrañaga, Jose A. Lozano, Jose M. Peña and Iñaki Inza     

Using focal point learning to improve human–machine tacit coordination

We consider an automated agent that needs to coordinate with a human partner when communication between them is not possible or is undesirable (tacit coordination games). Specifically, we examine situations where an agent and human attempt to coordinate their choices among several alternatives with equivalent utilities. We use machine learning algorithms to help the agent predict human choices in these tacit coordination domains. Experiments have shown that humans are often able to coordinate with one another in communication-free games, by using focal points, “prominent” solutions to coordination problems. We integrate focal point rules into the machine learning process, by transforming raw domain data into a new hypothesis space. We present extensive empirical results from three different tacit coordination domains. The Focal Point Learning approach results in classifiers with a 40–80% higher correct classification rate, and shorter training time, than when using regular classifiers, and a 35% higher correct classification rate than classical focal point techniques without learning. In addition, the integration of focal points into learning algorithms results in agents that are more robust to changes in the environment. We also present several results describing various biases that might arise in Focal Point based coordination.     

On the versatility of radial basis function neural networks: A case study in the field of intrusion detection

Classifiers based on radial basis function neural networks have a number of useful properties that can be exploited in many practical applications. Using sample data, it is possible to adjust their parameters (weights), to optimize their structure, and to select appropriate input features (attributes). Moreover, interpretable rules can be extracted from a trained classifier and input samples can be identified that cannot be classified with a sufficient degree of “certainty”. These properties support an analysis of radial basis function classifiers and allow for an adaption to “novel” kinds of input samples in a real-world application. In this article, we outline these properties and show how they can be exploited in the field of intrusion detection (detection of network-based misuse). Intrusion detection plays an increasingly important role in securing computer networks. In this case study, we first compare the classification abilities of radial basis function classifiers, multilayer perceptrons, the neuro-fuzzy system NEFCLASS, decision trees, classifying fuzzy-k-means, support vector machines, Bayesian networks, and nearest neighbor classifiers. Then, we investigate the interpretability and understandability of the best paradigms found in the previous step. We show how structure optimization and feature selection for radial basis function classifiers can be done by means of evolutionary algorithms and compare this approach to decision trees optimized using certain pruning techniques. Finally, we demonstrate that radial basis function classifiers are basically able to detect novel attack types. The many advantageous properties of radial basis function classifiers could certainly be exploited in other application fields in a similar way.     

A comparison of machine learning methods for cutting parameters prediction in high speed turning process

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 \((F_{c})\), 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 \(F_{c}\) and Ra prediction, while ANN had the best performance in the case of T, but also the worst performance in the case of \(F_{c}\) 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.     

Optimization studies in high speed turning of Ti-6Al-4V

Surface roughness is a major concern to the present manufacturing sector without the wastage of material. Hence, in order to achieve good surface roughness and reduce production time, optimization is necessary. In this study optimization techniques based on swarm intelligence (SI) namely firefly algorithm (FA), particle swarm optimization (PSO) and a newly introduced metaheuristic algorithm namely bat algorithm (BA) has been implemented for optimizing machining parameters namely cutting speed, feed rate, depth of cut and tool flank wear and cutting tool vibrations in order to achieve minimum surface roughness. Two parameters R_a and R_t have been considered for evaluating the surface roughness. The performance of BA algorithm has been compared with FA algorithm and PSO, which is a commonly and widely used optimization algorithm in machining. The results conclude that BA produces better optimization, when compared to FA and PSO. Based on the literature review carried out, this work is a first attempt at using a metaheuristic algorithm namely BA in machining applications.     

A Generic Ensemble Approach to Estimate Multidimensional Likelihood in Bayesian Classifier Learning

In Bayesian classifier learning, estimating the joint probability distribution p( x ,y) or the likelihood p( x |y) directly from training data is considered to be difficult, especially in large multidimensional data sets. To circumvent this difficulty, existing Bayesian classifiers such as Naive Bayes, BayesNet, and AηDE have focused on estimating simplified surrogates of p( x ,y) from different forms of one‐dimensional likelihoods. Contrary to the perceived difficulty in multidimensional likelihood estimation, we present a simple generic ensemble approach to estimate multidimensional likelihood directly from data. The idea is to aggregate p_i( x |y) estimated from a random subsample of data . This article presents two ways to estimate multidimensional likelihoods using the proposed generic approach and introduces two new Bayesian classifiers called ENNBayes and MassBayes that estimate p_i( x |y) using a nearest‐neighbor density estimation and a probability estimation through feature space partitioning, respectively. Unlike the existing Bayesian classifiers, ENNBayes and MassBayes have constant training time and space complexities and they scale better than existing Bayesian classifiers in very large data sets. Our empirical evaluation shows that ENNBayes and MassBayes yield better predictive accuracy than the existing Bayesian classifiers in benchmark data sets.     

Contour offset approach to spiral toolpath generation with constant scallop height

Recently, the application of high-speed machining (HSM) is recognized as an economically viable manufacturing technology. Even though more HSM centers have increasingly been utilized, the conventional toolpath generation methods are usually employed in practice. But the conventional methods have inherent limitations for the HSM application.This paper presents a new toolpath generation algorithm for high-speed finish cutting process. In order to minimize the fluctuation of cutting load and the possibility of chipping on the cutting edge in HSM, a spiral topology toolpath that is to cut continuously with the minimum number of cutter retractions during the cutting operations is developed. This algorithm begins with the contour offset procedure along the boundary curve of the sculptured surface being machined. In the offset procedure, the offset distance is determined such that the scallop height maintains a constant roughness to ensure higher levels of efficiency and quality in high-speed finish machining. Then, the spiral path is generated as a kind of the diagonal curve between the offset curves. This path strategy is able to connect to a neighbor path without a cutter retraction. Therefore, the minimum tool retraction toolpath can be generated. And, it allows the sculptured surface incorporating both steeper and flatter areas to be high-speed machined. Based on these techniques, experimental results are given to verify the proposed approach.     

TAN Classifiers Based on Decomposable Distributions

In this paper we present several Bayesian algorithms for learning Tree Augmented Naive Bayes (TAN) models. We extend the results in Meila & Jaakkola (2000a) to TANs by proving that accepting a prior decomposable distribution over TAN’s, we can compute the exact Bayesian model averaging over TAN structures and parameters in polynomial time. Furthermore, we prove that the k-maximum a posteriori (MAP) TAN structures can also be computed in polynomial time. We use these results to correct minor errors in Meila & Jaakkola (2000a) and to construct several TAN based classifiers. We show that these classifiers provide consistently better predictions over Irvine datasets and artificially generated data than TAN based classifiers proposed in the literature.Editors: Pedro Larrañaga, Jose A. Lozano, Jose M. Peña and Iñaki Inza     

Feature-based rule induction in machining operation using rough set theory for quality assurance

There have been many studies, mainly by the use of statistical modeling techniques, as to predicting quality characteristics in machining operations where a large number of process variables need to be considered. In conventional metal removal processes, however, an exact prediction of surface roughness is not possible or very difficult to achieve, due to the stochastic nature of machining processes. In this paper, a novel approach is proposed to solve the quality assurance problem in predicting the acceptance of computer numerical control (CNC) machined parts, rather than focusing on the prediction of precise surface roughness values. One of the data mining techniques, called rough set theory, is applied to derive rules for the process variables that contribute to the surface roughness. The proposed rule-composing algorithm and rule-validation procedure have been tested with the historical data the company has collected over the years. The results indicate a higher accuracy over the statistical approaches in terms of predicting acceptance level of surface roughness.     

Bayesian forecaster using class-based optimization

Suppose that several forecasters exist for the problem in which class-wise accuracies of forecasting classifiers are important. For such a case, we propose to use a new Bayesian approach for deriving one unique forecaster out of the existing forecasters. Our Bayesian approach links the existing forecasting classifiers via class-based optimization by the aid of an evolutionary algorithm (EA). To show the usefulness of our Bayesian approach in practical situations, we have considered the case of the Korean stock market, where numerous lag-l forecasting classifiers exist for monitoring its status.     

Prediction and optimization of performance measures in electrical discharge machining using rapid prototyping tool electrodes

In this work, the performance of rapid prototyping (RP) based rapid tool is investigated during electrical discharge machining (EDM) of titanium as work piece using EDM 30 oil as dielectric medium. Selective laser sintering, a RP technique, is used to produce the tool electrode made of AlSi10Mg. The performance of rapid tool is compared with conventional solid copper and graphite tool electrodes. The machining performance measures considered in this study are material removal rate, tool wear rate and surface integrity of the machined surface measured in terms of average surface roughness (Ra), white layer thickness, surface crack density and micro-hardness on white layer. Since the machining process is a complex one, potentiality of application of a predictive tool such as least square support vector machine has been explored to provide guidelines for the practitioners to predict various machining performance measures before actual machining. The predictive model is said to be robust one as root mean square error in the range of 0.11–0.34 is obtained for various performance measures. A hybrid optimization technique known as desirability based grey relational analysis in combination with firefly algorithm is adopted for simultaneously optimizing the performance measures. It is observed that peak current and tool type are the significant parameters influencing all the performance measures.

     

Handling numeric attributes when comparing Bayesian network classifiers: does the discretization method matter?

Within the framework of Bayesian networks (BNs), most classifiers assume that the variables involved are of a discrete nature, but this assumption rarely holds in real problems. Despite the loss of information discretization entails, it is a direct easy-to-use mechanism that can offer some benefits: sometimes discretization improves the run time for certain algorithms; it provides a reduction in the value set and then a reduction in the noise which might be present in the data; in other cases, there are some Bayesian methods that can only deal with discrete variables. Hence, even though there are many ways to deal with continuous variables other than discretization, it is still commonly used. This paper presents a study of the impact of using different discretization strategies on a set of representative BN classifiers, with a significant sample consisting of 26 datasets. For this comparison, we have chosen Naive Bayes (NB) together with several other semi-Naive Bayes classifiers: Tree-Augmented Naive Bayes (TAN), k-Dependence Bayesian (KDB), Aggregating One-Dependence Estimators (AODE) and Hybrid AODE (HAODE). Also, we have included an augmented Bayesian network created by using a hill climbing algorithm (BNHC). With this comparison we analyse to what extent the type of discretization method affects classifier performance in terms of accuracy and bias-variance discretization. Our main conclusion is that even if a discretization method produces different results for a particular dataset, it does not really have an effect when classifiers are being compared. That is, given a set of datasets, accuracy values might vary but the classifier ranking is generally maintained. This is a very useful outcome, assuming that the type of discretization applied is not decisive future experiments can be d times faster, d being the number of discretization methods considered.     

Prediction of surface roughness during hard turning of AISI 4340 steel (69 HRC)

In this study, 39 sets of hard turning (HT) experimental trials were performed on a Mori-Seiki SL-25Y (4-axis) computer numerical controlled (CNC) lathe to study the effect of cutting parameters in influencing the machined surface roughness. In all the trials, AISI 4340 steel workpiece (hardened up to 69 HRC) was machined with a commercially available CBN insert (Warren Tooling Limited, UK) under dry conditions. The surface topography of the machined samples was examined by using a white light interferometer and a reconfirmation of measurement was done using a Form Talysurf. The machining outcome was used as an input to develop various regression models to predict the average machined surface roughness on this material. Three regression models – Multiple regression, Random forest, and Quantile regression were applied to the experimental outcomes. To the best of the authors’ knowledge, this paper is the first to apply random forest or quantile regression techniques to the machining domain. The performance of these models was compared to ascertain how feed, depth of cut, and spindle speed affect surface roughness and finally to obtain a mathematical equation correlating these variables. It was concluded that the random forest regression model is a superior choice over multiple regression models for prediction of surface roughness during machining of AISI 4340 steel (69 HRC).     

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.     

基于纹理分析的表面粗糙度等级识别

提出了一种利用图象纹理分析技术进行机械加工表面粗糙度检测的非接触检测方法,该方法首先根据统计方差对待测工件的表面粗糙度进行粗分类,然后,利用基于Ｇａｂｏｒ滤波器的纹理分类器,识别待测工件表面粗糙度等级。该新方法可简单、快速地实现表面粗糙度等级的自动识别,而且对图象旋转具有不变性,由于其纹理分类器的参数少,并且新方法成本低,参数标定方便,因而便于现场检测,如果与机床的控制系统相连,还可以实现加工的实