Monitoring defects of ceramic tiles using fuzzy subtractive clustering-based system identification method

In this paper, a subtractive clustering fuzzy identification method and a Sugeno-type fuzzy inference system are used to monitor tile defects in tile manufacturing process. The models for the tile defects are identified by using the firing mechanical resistance, water absorption, shrinkage, tile thickness, dry mechanical resistance and tiles temperature as input data, and using the concavity defect and surface defects as the output data. The process of model building is carried out by using subtractive clustering in both the input and output spaces. A minimum error model is developed through exhaustive search of clustering parameters. The fuzzy model obtained is capable of predicting the tile defects for a given set of inputs as mentioned above. The fuzzy model is verified experimentally using different sets of inputs. This study intends to examine and deal with the experimental results obtained during various stages of ceramic tile production during 90-day period. It is believed, that the results obtained from the present study could be considered in other ceramic tiles industries, which experienced similar forms of defects.     

利用减法聚类的自适应模糊神经网络客观评定织物起皱等级

本文提出一种基于减法聚类的自适应模糊神经网络，用于织物起皱等级评定。首先利用减法聚类方法确定模糊神经网络的结构，再结合模糊推理系统进行模式识别，并详细介绍其基本原理和学习算法，最后引入四种起皱特征参数对真实织物进行验证，实验表明该方法是有效、可行的。     

Development of Quantum-Based Adaptive Neuro-Fuzzy Networks

In this study, we are concerned with a method for constructing quantum-based adaptive neuro-fuzzy networks (QANFNs) with a Takagi–Sugeno–Kang (TSK) fuzzy type based on the fuzzy granulation from a given input–output data set. For this purpose, we developed a systematic approach in producing automatic fuzzy rules based on fuzzy subtractive quantum clustering. This clustering technique is not only an extension of ideas inherent to scale-space and support-vector clustering but also represents an effective prototype that exhibits certain characteristics of the target system to be modeled from the fuzzy subtractive method. Furthermore, we developed linear-regression QANFN (LR-QANFN) as an incremental model to deal with localized nonlinearities of the system, so that all modeling discrepancies can be compensated. After adopting the construction of the linear regression as the first global model, we refined it through a series of local fuzzy if–then rules in order to capture the remaining localized characteristics. The experimental results revealed that the proposed QANFN and LR-QANFN yielded a better performance in comparison with radial basis function networks and the linguistic model obtained in previous literature for an automobile mile-per-gallon prediction, Boston Housing data, and a coagulant dosing process in a water purification plant.      

Dynamic NC simulation of milling operations

To increase productivity in manufacturing, accurate cutting-simulation systems have increasingly been used to study the performance of machining processes. A new dynamic cutting-simulation system that can simulate the dynamic behaviour of the milling cutting force along the programmed NC toolpath is presented in the paper. The radial and axial depths of cut in the cutting process are extracted from a geometric cutting-simulation system on a workstation. Then, the radial and axial depths of cut and the other given cutting parameters are transmitted to a mechanistic model of the milling process from which the dynamic cutting force is obtained. There is good agreement between the simulated and measured cutting forces.     

基于减法聚类和自适应神经模糊推理系统的递阶模糊系统的设计

提出了一种设计递阶模糊系统的简易而有效的方法.在得到一个单级模糊系统的基础上,用灵敏度分析法对每一个输入变量的重要性进行排序,从而确定每一级子系统的输入变量.利用减法聚类和自适应神经 模糊推理系统逐级对子系统进行训练.所得到的递阶模糊系统可进一步得到简化.仿真实例证实了设计方法的有效性.     

Assessment of micro turning machine stiffness response and material characteristics by fuzzy rule based pattern matching of cutting force plots

In micro-nano systems technology (MNST), application of mechanical based machining operations such as micro turning, micro milling, micro EDM have shown promising trends to produce micro parts in batch scale. In order to ensure reproducibility better understanding on micro cutting process dynamics and sensitivity of machine stiffness and material characteristics becomes critical. In this paper, a methodology has been developed to assess machine stiffness and material dependent characteristics and demonstrated for micro turning operations conducted on DT-110 micro machining center. In this method, authors incorporate pattern matching algorithm to compare run data image of cutting force plots with that of reference plot. The reference plots of cutting forces v/s time were drawn from simulation run data computed from the micro turning process models. The run data plots of cutting force v/s time were drawn from the processed signal data obtained from the dynamometer during machining operation. The plots were fragmented into patterns and Euclidean distance computed between pair patterns of reference and measured cutting forces v/s time plot image represents the changes happened in machining conditions. This has been used to perform backward calculation to assess the machine stiffness response and material characteristic constants variations over machining time. In order to perform these comparative pattern error adjustments between reference and measured cutting force plots a fuzzy rule based algorithm has been developed.     

一种基于数据挖掘的模糊建模方法

为提高非线性系统模糊建模的速度和精确度,提出一种快速有效的基于数据挖掘的非线性系统模糊建模方法.该方法先采用改进的减法聚类结合模糊C-均值聚类进行结构辨识,在解决初始化问题的同时减少计算量,进而提高建模速度;然后利用带动态遗忘因子的递推最小二乘法进行后件参数辨识,减小动态误差,提高建模精度.将提出的方法应用于Box-J...     

Modelling and simulation of whirling process based on equivalent cutting volume

The thread whirling is an efficient and precise machining process for manufacturing of screws. The shaping motion of whirling is complex and difficult to model. In this paper, a novel model basing on equivalent cutting volume is proposed. The cutting force and the chip morphology are investigated to validate the model. The simulation of cutting force is in good agreement with the experimental results with error less than 16.5%. A chip with saw-toothed edges is obtained from simulation and for experimental verification. A case study on the effect of the tool edge geometry on cutting forces is also presented. The simulation results show that the tool edge geometry greatly influences the cutting forces. The tool with round edge is a good choice for reducing the cutting forces. The ratio of a_c/R_e holds the balance in selecting the parameter of cutting conditions. The model is applicable for the simulation of whirling process and can be used for parameter optimisation of the cutting tool edge.     

减法聚类-ANFIS在网络故障诊断的应用研究

提出了一种基于减法聚类-自适应模糊神经网络（ANFIS）的网络故障诊断建模方法。减法聚类算法生成初始模糊推理系统,ANFIS建立网络故障诊断原始模型,应用混合算法对模糊规则的参数进行训练并建立最终的模型。仿真实验表明基于减法聚类-ANFIS的建模方法是有效的;通过仿真结果比较,减法聚类-ANFIS的网络故障诊断能力及收敛速度均优于BP神经网络,更适合作为网络故障诊断模型。     

Eliciting transparent fuzzy model using differential evolution

In this paper a new technique for eliciting a fuzzy inference system (FIS) from data for nonlinear systems is proposed. The strategy is conducted in two phases: in the first one, subtractive clustering is applied in order to extract a set of fuzzy rules, in the second phase, the generated fuzzy rule base is refined and redundant rules are removed on the basis of an interpretability measure. Finally the centers and widths of the Membership Functions (MFs) are tuned by means differential evolution. Case studies are presented to illustrate the efficiency and accuracy of the proposed approach. The results obtained are compared and contrasted with those obtained from a conventionally neuro-fuzzy technique and the superiority of the proposed approach is highlighted.     

聚酯酯化率软测量技术研究

介绍了某聚酯生产过程酯化工艺建立的过程质量指标酯化率的软测量模型。提出一种利用减法聚类产生初始的T-S模糊模型,通过粗调与细调聚类半径优化模糊模型的方法。建模前选择或计算出辅助变量,对样本数据进行了误差剔除与归一化处理。仿真结果表明,该方法建模速度快,模型泛化性能良好,为酯化率的估计提供了一种有效方法。     

A hybrid genetic algorithm–adaptive network-based fuzzy inference system in prediction of wave parameters

An important issue in application of fuzzy inference systems (FISs) to a class of system identification problems such as prediction of wave parameters is to extract the structure and type of fuzzy if–then rules from an available input–output data set. In this paper, a hybrid genetic algorithm–adaptive network-based FIS (GA–ANFIS) model has been developed in which both clustering and rule base parameters are simultaneously optimized using GAs and artificial neural nets (ANNs). The parameters of a subtractive clustering method, by which the number and structure of fuzzy rules are controlled, are optimized by GAs within which ANFIS is called for tuning the parameters of rule base generated by GAs. The model has been applied in the prediction of wave parameters, i.e. wave significant height and peak spectral period, in a duration-limited condition in Lake Michigan. The data set of year 2001 has been used as training set and that of year 2004 as testing data. The results obtained by the proposed model are presented and analyzed. Results indicate that GA–ANFIS model is superior to ANFIS and Shore Protection Manual (SPM) methods in terms of their prediction accuracy.     

排样图形匹配中的聚类算法应用研究

通过对排样问题的需要进行分析,选取了有效的聚类特征;通过对模糊C-均值算法和减法聚类算法的比较,选取减法聚类实现对排样图形的聚类;给出了针对排样问题的参数选取,文末给出了实例.     

T‐norms in subtractive clustering and backpropagation

The tuning of a fuzzy model is discussed in the context of choices made between different t‐norms. The effects of the choice is illustrated by looking at two fuzzy models initially generated, respectively, by grid partition and a novel variant of subtractive clustering. The new variant of subtractive clustering introduced in the paper is based on the standard method of subtractive clustering, where in this new method, the measure of similarity and thus also cluster shapes depend on a choice of t‐norm T. © 2010 Wiley Periodicals, Inc.     

Internal Model Control Based on a Neurofuzzy System for Network Applications. A Case Study on the High-Performance Drilling Process

This paper presents the design and implementation of a neurofuzzy system for modeling and control of a high-performance drilling process in a networked application. The neurofuzzy system considered in this work is an adaptive-network-based fuzzy inference system (ANFIS), where fuzzy rules are obtained from input/output data. The design of the control system is based on the internal model control paradigm. The results obtained are significant both in simulation as well as the real-time application of networked control of the cutting force during high-performance drilling processes.     

基于改进型模糊聚类的模糊系统建模方法

结合减法聚类和模糊C均值聚类,提出了一种改进型聚类算法,加快了收敛速度．利用改进后的算法对模糊系统输入或输出的样本集聚类,对聚类结果采用Trust-Region法拟合高斯型和S型函数,以实现模糊系统输入、输出空间的划分和隶属度函数参数的确定．结合MATLAB的模糊和曲线拟合工具箱,详述了如何在标准算法上进行改进和模糊系统建模．通过对IRIS标准数据聚类实验以及在解决机械加工误差复映问题上的应用,验证了改进后算法和建模方法的有效性．     

基于ANFIS的交通事件持续时间预测

针对高速公路交通事故引发交通堵塞的问题,提出一种基于减法聚类和自适应神经模糊推理系统的事件持续时间预测新方法。将该方法应用于交通事件持续时间预测,从I-880数据库中提取事件持续时间相关因素,使用非参数估计法进行显著性分析,将影响程度最大的因素作为模糊系统的输入样本,采用减法聚类对输入样本进行聚类,得到模糊规则数并建立初始模糊推理系统,使用BP反向传播算法和最小二乘估计算法的混合算法对该模糊系统进行训练并优化,建立最终模糊模型。仿真结果证明,该系统对交通事件持续时间预测具有较高检测率和较低误报率。     

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.     

Cutting tool wear estimation for turning

The experimental investigation on cutting tool wear and a model for tool wear estimation is reported in this paper. The changes in the values of cutting forces, vibrations and acoustic emissions with cutting tool wear are recoded and analyzed. On the basis of experimental results a model is developed for tool wear estimation in turning operations using Adaptive Neuro fuzzy Inference system (ANFIS). Acoustic emission (Ring down count), vibrations (acceleration) and cutting forces along with time have been used to formulate model. This model is capable of estimating the wear rate of the cutting tool. The wear estimation results obtained by the model are compared with the practical results and are presented. The model performed quite satisfactory results with the actual and predicted tool wear values. The model can also be used for estimating tool wear on-line but the accuracy of the model depends upon the proper training and section of data points.     

球头铣刀柔性铣削力建模与仿真

本文建立了球头铣刀柔性铣削力模型,研究了任意进给方向的球头铣刀铣削力模型,在模型建立过程中考虑了刀具偏心、刀具变形和刀具振动物理影响因素,推导出了综合物理因素影响下的瞬时切屑厚度表达式.在此基础上对球头铣刀瞬时铣削力进行仿真对比分析,验证了建立模型的正确性.