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．     

A supervised approach for automated surface defect detection in ceramic tile quality control

Surface defect detection is very important to guarantee the quality of ceramic tiles production. At present, this process is usually performed manually in the ceramic tile industry, which is low efficiency and time-consuming. For small surface defects detection of high-resolution ceramic tiles image, an intelligent detection method for surface defects of ceramic tiles based on an improved you only look once version 5 (YOLOv5) algorithm is presented. Firstly, the high-resolution ceramic tile images are cropped into slices, and the Bottleneck module in the YOLOv5s network is optimized by introducing depthwise convolution and replaced in the whole network. Then, feature extraction is performed using the improved Shufflenetv2 backbone, and an attention mechanism is added to the backbone network to improve the feature extraction ability. The path aggregation network (PAN) and Feature Pyramid Networks (FPN) neck are used to enhance the feature extraction, and finally, the YOLO head is used to identify and locate the ceramic tile defects. The multiple sliding windows detection method is proposed to detect the original ceramic tile image which is faster than the single sliding window detection method. The experimental results show that compared with the original YOLOv5s detection algorithm, the parameters of the model are reduced by 20.46 %, the floating point operations are reduced by 26.22 %, and the mean average precision (mAP) of the proposed method is 96.73 % in the ceramic tile image slice test set which has 1.93 % improvement in mAP than the original YOLOv5s. Compare with other object detection methods, the method proposed in this paper also has certain advantages. In the high-resolution ceramic tile images test set, the mAP of the proposed algorithm is 86.44 % by using the multiple sliding window detection method. The ceramic defect detection experiment has verified the feasibility of the method proposed in this paper.     

多特征融合的瓷砖表面缺陷检测算法研究

鉴于单一特征在瓷砖种类较多的情况下,存在对瓷砖表面缺陷内容表达不明显,导致复杂瓷砖识别率较低。针对这个问题,在词袋模型（BoF）框架的基础上,提出一种有效的多特征融合算法用于瓷砖缺陷检测。该算法采用改进后的SIFT和颜色矩融合特征作为瓷砖图像的区域特征描述;根据每种特征对瓷砖被分类的准确率大小,给提取到的两种区域特征分配各自的权重系数实现特征的加权融合;形成综合特征向量送入SVM分类器达到瓷砖缺陷分类的目的。通过不同类型的瓷砖样本进行实验表明,该算法识别率高,对复杂瓷砖能实现较好的分类。     

Activatable tiles for compact robust programmable molecular assembly and other applications

Algorithmic DNA self-assembly is capable of forming complex patterns and shapes, that have been shown theoretically, and experimentally. Its experimental demonstrations, although improving over recent years, have been limited by significant assembly errors. Since 2003 there have been several designs of error-resilient tile sets but all of these existing error-resilient tile systems assumed directional growth of the tiling assembly. This is a very strong assumption because experiments show that tile self-assembly does not necessarily behave in such a fashion, since they may also grow in the reverse of the intended direction. The assumption of directional growth of the tiling assembly also underlies the growth model in theoretical assembly models such as the TAM. What is needed is a means for enforce this directionality constraint, which will allow us to reduce assembly errors. In this paper we describe a protection/deprotection strategy to strictly enforce the direction of tiling assembly growth so that the assembly process is robust against errors. Initially, we start with (1) a single “activated” tile with output pads that can bind with other tiles, along with (2) a set of “deactivated” tiles, meaning that the tile’s output pads are protected and cannot bind with other tiles. After other tiles bind to a “deactivated” tile’s input pads, the tile transitions to an active state and its output pads are exposed, allowing further growth. When these are activated in a desired order, we can enforce a directional assembly at the same scale as the original one. Such a system can be built with minimal modifications of existing DNA tile nanostructures. We propose a new type of tiles called activatable tiles and its role in compact proofreading. Activatable tiles can be thought of as a particular case of the more recent signal tile assembly model, where signals transmit binding/unbinding instructions across tiles on binding to one or more input sites. We describe abstract and kinetic models of activatable tile assembly and show that the error rate can be decreased significantly with respect to Winfree’s original kinetic tile assembly model without considerable decrease in assembly growth speed. We prove that an activatable tile set is an instance of a compact, error-resilient and self-healing tile-set. We describe a DNA design of activatable tiles and a mechanism of deprotection using DNA polymerization and strand displacement. We also perform detailed stepwise simulations using a DNA Tile simulator Xgrow, and show that the activatable tiles mechanism can reduce error rates in self assembly. We conclude with a brief discussion on some applications of activatable tiles beyond computational tiling, both as (1) a novel system for concentration of molecules, and (2) a catalyst in sequentially triggered chemical reactions.     

有混合数据输入的自适应模糊神经推理系统

现有数据建模方法大多依赖于定量的数值信息,而对于数值与分类混合输入的数据建模问题往往根据分类变量组合建立多个子模型,当有多个分类变量输入时易出现子模型数据分布不均匀、训练耗时长等问题.针对上述问题,提出一种具有混合数据输入的自适应模糊神经推理系统模型,在自适应模糊推理系统的基础上,引入激励强度转移矩阵和结论影响矩阵,采用基于高氏距离的减法聚类辨识模型结构,通过混合学习算法训练模型参数,使数值与分类混合数据对模糊规则的前后件参数同时产生作用,共同影响模型输出.仿真实验分析了分类数据对模型规则后件的作用以及结构辨识算法对模糊规则数的影响,与其他几种混合数据建模方法对比表明本文所提出的模型具有较高的预测精度和计算效率.     

基于傅里叶变换的随机纹理瓷砖的高精度表面缺陷检测

针对经典缺陷检测算法不能很好地提取随机纹理瓷砖图像的缺陷的问题,提出一种基于傅里叶变换的随机纹理瓷砖表面缺陷高精度检测方法。在此基础上,完成了瓷砖表面缺陷检测硬件系统设计。对采集的瓷砖图像,首先利用傅里叶变换得到频率谱图像,然后研究截止频率参数对滤波的影响,设计最优化滤波器进行滤波,再通过傅里叶逆变换获得重构图像,达到抑制背景纹理信息,加强缺陷区域信息的目的,最后通过阈值化和形态学操作获得缺陷区域。实验结果表明: 本方法对不同的随机纹理瓷砖样本进行缺陷检测的准确率高,在瓷砖缺陷检测中具有较高的实用价值。     

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.     

一种改进DCGANs网络的磁瓦缺陷图像生成方法研究

基于机器视觉的磁瓦表面缺陷检测研究对于改进磁瓦生产工艺、提升磁瓦生产效率有着重要意义.但在研究过程中,存在磁瓦含缺陷样本收集困难、不同缺陷样本数不均匀、缺陷类型单一等问题.本文提出一种使用高斯混合模型的深度卷积生成对抗网络(Gaussian Mixture Model Deep Convolution Generative Adversarial Networks,GMM-DCGANs)生成含缺陷磁瓦图像的方法.在深度卷积生成对抗网络的基础上,将生成图像的输入噪声潜在空间复杂化为高斯混合模型,从而提高图像生成网络对有限数量且具有类间及类内多样性训练样本的学习能力.实验结果表明,GMMDCGANs网络可以生成质量更好、缺陷类型更加丰富的磁瓦缺陷图像,并且生成的图像满足缺陷检测及分类的要求.     

瓷砖图像的纹理特征分类研究

在已有的瓷砖图像分类系统中,仅靠颜色特征和简单的纹理边缘信息只能对无花纹的单色砖或简单花纹的瓷砖进行有效分类,对复杂图案的瓷砖存在识别率低的问题。针对此种情况,结合瓷砖图像的灰度共生矩阵和统计几何特征,将这些特征输入支持向量机进行特征分层分类。采用基于径向基核函数和[K]交叉验证法所得到的最优参数构造支持向量机,解决瓷砖纹理特征具有非线性的分类问题。用瓷砖生产线上采集的大量图像进行实验表明,该方法准确率高,分类效果好。     

基于PLC的瓷砖平整度在线检测系统研究

为实现瓷砖平整度的自动在线检测及分级,设计了基于PLC、组态软件和激光位移传感器的瓷砖平整度实时检测分级系统。系统由传送、检测和分级三部分组成。该检测系统采用光学三角法检测技术,通过编码器及PLC的高速计数器功能对移动中的待检测瓷砖的采样位置进行精确定位,使用激光位移传感器对瓷砖表面进行信息采集,经AD转换后在PLC内部按照特定的算法进行平整度运算,以PLC为核心实现瓷砖的分级处理和对设备的整体控制。实验表明该检测系统高效、稳定、可靠。瓷砖平整度检测精度为±0.1 mm,多次同方向检测精度为±0.05 mm,检测速度为每分钟40片,检测准确度可达到95%以上,适用于当前瓷砖生产过程的质量控制。     

Control of a ceramic tiles cooling process based on water spraying

The control of the surface temperature of ceramic tiles in a real industrial production line is developed. The process consists of a transportation band that carries the hot tiles through a water sprayer whose objective is to reduce its temperature. Two input signals can be modified: the velocity of the transportation band and the flow rate of the sprayer. In order to control the outlet surface temperature, the quantity of water deposited (and hence evaporated) per tile, that is a static function of the velocity and the flow rate, is used as the control input. The inlet temperature has a tile to tile fast pattern variation and a slow average change. First, the experimental identification of the process model is carried out. Then a feedback PI controller based on the measurement of the outlet temperature is then tested, showing a good average tracking, but a poor compensation of the fast variations. An adaptive feedforward control based on the measurement of the inlet and outlet temperatures is developed and also tested in the plant, showing a much better performance, but a higher cost. Finally, a disturbance observer based feedforward control is tested, showing an intermediate performance and cost.     

Development of a systematic methodology of fuzzy logic modeling

This paper proposes a systematic methodology of fuzzy logic modeling for complex system modeling. It has a unified parameterized reasoning formulation, an improved fuzzy clustering algorithm, and an efficient strategy of selecting significant system inputs and their membership functions. The reasoning mechanism introduces 4 parameters whose variation provides a continuous range of inference operation. As a result, we are no longer restricted to standard extremes in any step of reasoning. The fuzzy model itself can then adjust the reasoning process by optimizing the inference parameters based on input-output data. The fuzzy rules are generated through fuzzy c-means (FCM) clustering. Major bottlenecks are addressed and analytical solutions are suggested. We also address the classification process to extend the derived fuzzy partition to the entire output space. In order to select suitable input variables among a finite number of candidates (unlike traditional approaches) we suggest a new strategy through which dominant input parameters are assigned in one step and no iteration process is required. Furthermore, a clustering technique called fuzzy fine clustering is introduced to assign the input membership functions. In order to evaluate the proposed methodology, two examples-a nonlinear function and a gas furnace dynamic procedure-are investigated in detail. The significant improvement of the model is concluded compared to other fuzzy modeling approaches     

Fuzzy model forecasting of offshore bar-shape profiles under high waves

This paper proposes a fuzzy model for predicting the complex changes of offshore beach topographies under high waves. The fuzzy model was developed through the integration of autoregressive exogenous input models, a Takagi–Sugeno fuzzy model, subtractive clustering algorithms, and a weighted least squares estimation technique. The height, the period of ocean wave signals, and the initial cross-shore bar shapes are used as input signals while the topographic features of the bar shape profiles are adopted as the output signals. To demonstrate the effectiveness of the proposed fuzzy model, a variety of laboratory experiments at 1/50th scale were conducted and compared to the CSHORE mathematical model. The experimental studies show that the proposed fuzzy model is effective in predicting the topographic features of beach profiles and performs better than the CSHORE model.     

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.      

Experimental and fuzzy modelling analysis on dynamic cutting force in micro milling

Prediction of cutting forces is very important for the design of cutting tools and for process planning. This paper presents a fuzzy modelling method of cutting forces based on subtractive clustering. The subtractive clustering combined with the least-square algorithm identifies the fuzzy prediction model directly from the information obtained from the sensors. In the micro-milling experimental case study, four sets of cutting force data are used to generate the learning systems. The systems are tested against each other to choose the best model. The obtained results prove that the proposed solution has the capability to model the cutting force in spite of uncertainties in the micromilling process.     

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.     

基于直方图聚类的颜色分级方法

文章提出了一种利用颜色特征对瓷砖进行在线颜色分级的新方法。针对瓷砖图像数据量大的特点,采用了颜色空间分裂和与初始条件无关的聚类算法相结合的量化方法来提取瓷砖图像颜色特征,这既可满足算法实时性要求又充分考虑到了颜色分级对特征的精确性要求。实验结果证明了该方法的有效性。     

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。     

A wavelet-based autoregressive fuzzy model for forecasting algal blooms

This paper proposes fuzzy models for forecasting the complex behavior of algal blooms. The models are developed through the integration of autoregressive models, the Takagi-Sugeno fuzzy model, and discrete wavelet transform algorithms. The premise parts of the proposed models are determined using the subtractive clustering technique and the consequent parts are optimized using weighted least squares. To train and validate the proposed fuzzy models, a large number of data sets were collected from Daecheong reservoir in Geum River in the Republic of Korea. The data include both water quality and hydrological variables. Total nitrogen, total phosphorous, dissolved oxygen, chemical oxygen demand, biochemical oxygen demand, pH, air temperature, water temperature and outflow water were evaluated as input signals while chlorophyll-a was used as an output. It is demonstrated from the simulation that the proposed fuzzy models are effective in forecasting algal blooms.     

Data-based multiple-model prediction of the production rate for hematite ore beneficiation process

The prediction of the production rate of the hematite ore beneficiation process is important to plant-wide optimization. This paper presents a data-based multi-model approach to predict the production rate with multiple operating modes. The inputs of the predictive model are the performance indices of each unit process, and the output is the global production index (the production rate) of the hematite ore beneficiation process. The multiple models are developed by integrating the fuzzy clustering algorithm and machine learning algorithm. A global model, Takagi–Sugeno–Kang fuzzy model, and multiple neural network model were compared using the data obtained from a practical industrial process, and the effectiveness of the proposed algorithm was proven.