A nonlinear quality-related fault detection approach based on modified kernel partial least squares

In this paper, a new nonlinear quality-related fault detection method is proposed based on kernel partial least squares (KPLS) model. To deal with the nonlinear characteristics among process variables, the proposed method maps these original variables into feature space in which the linear relationship between kernel matrix and output matrix is realized by means of KPLS. Then the kernel matrix is decomposed into two orthogonal parts by singular value decomposition (SVD) and the statistics for each part are determined appropriately for the purpose of quality-related fault detection. Compared with relevant existing nonlinear approaches, the proposed method has the advantages of simple diagnosis logic and stable performance. A widely used literature example and an industrial process are used for the performance evaluation for the proposed method.     

Prediction of quality responses in micro-EDM process using an adaptive neuro-fuzzy inference system (ANFIS) model

In the present trend of technological development, micro-machining is gaining popularity in the miniaturization of industrial products. In this work, a hybrid process of micro-wire electrical discharge grinding and micro-electrical discharge machining (EDM) is used in order to minimize inaccuracies due to clamping and damage during transfer of electrodes. The adaptive neuro-fuzzy inference system (ANFIS) and back propagation (BP)-based artificial neural network (ANN) models have been developed for the prediction of multiple quality responses in micro-EDM operations. Feed rate, capacitance, gap voltage, and threshold values were taken as the input parameters and metal removal rate, surface roughness and tool wear ratio as the output parameters. The results obtained from the ANFIS and the BP-based ANN models were compared with observed values. It is found that the predicted values of the responses are in good agreement with the experimental values and it is also observed that the ANFIS model outperforms BP-based ANN.     

基于AWLS-SVM的污水处理过程软测量建模

针对污水处理过程建模中样本数据可能存在的测量误差对模型性能的影响,提出一种自适应加权最小二乘支持向量机(AWLS-SVM)回归的软测量建模方法。该方法基于最小二乘支持向量机模型,根据样本拟合误差,并结合改进的指数分布赋权规则,自适应地为每个建模样本分配不同的权值,以降低随机误差对模型性能的影响;同时采用一种全局优化算法——混沌粒子群模拟退火(CPSO-SA)算法对最小二乘支持向量机的模型参数进行优化选择,以提高模型的泛化能力。仿真实验表明,AWLS-SVM模型的预测精度及鲁棒性能优于LS-SVM和WLS-SVM。最后,应用AWLS-SVM方法建立污水处理过程出水水质关键参数的软测量模型,获得了较好的效果。     

一种高速灌装自适应控制方法

针对灌装精度要求高的小剂量高速药液灌装机,现在仍广泛使用手动灌装控制方法、难以解决因灌药系统特性时变所带来的灌装误差较大的问题,设计了一种基于高速灌装模型的智能灌装控制器,以提高高速灌装系统的灌药精度。以此为基础,为了解决因系统非线性所带来的灌装特性变化问题,提出了一种通过最小二乘法在线构建灌装系统局部线性化模型,对灌药系统灵敏度进行在线分析的方法,并设计了能够克服时变及非线性影响的自适应智能灌装控制算法。分别对手动控制、智能控制和自适应智能控制方法进行了实时灌装控制实验,结果表明自适应智能控制效果最好,智能控制器和自适应智能控制器均能够较好地解决系统特性时变带来的影响,并且自适应智能控制器具有克服灌装特性非线性影响的能力。     

Sensitivity-based model-free adaptive displacement and velocity control algorithms for unknown single-input multi-output systems with recursive least squares

Journal of Mechanical Science and Technology - This study presents sensitivity-based adaptive model-free adaptive displacement and velocity control algorithms for unknown single-input multi-output...     

基于分块和偏最小二乘的非接触式手掌静脉生物特征识别

研究了一种适用于非接触式图像采集的手掌静脉识别的子空间方法,解决了传统接触式采集容易传染疾病,非接触采集使同类图像差别增大导致识别性能不佳的问题.先采用分块算法对图像进行快速降维,再用偏最小二乘算法提取掌脉图像中灰度值变异大,且类别信息相关性最大的若干方向组成分类子空间,然后依据图像在此空间中的位置进行分类识别.应用自建掌脉图库和中科院自动化研究所图库进行实验分析,实验结果表明:与传统掌脉识别方法相比,该方法能有效地提高正确识别率,降低误拒率.两个图库中,该算法选择分块大小为4×4时的正确识别率分别达到99.98％,99.34％;误识率分别达到0.02％,0.66％;误拒率分别达到0.13％,0.60％;识别时间分别在0.03 s,0.04s之内.适用于安防、考勤等场合,具有实用价值.     

偏最小二乘法方法在光谱定性分析中的应用研究

传统的光谱多元定性方法大都基于主成分分析(PCA),即首先将光谱进行PCA降维并选取特征变量后,再进行聚类或判别分析。近年来,用于光谱多元定量校正的偏最小二乘法(PLS)也被越来越多地用于定性分析中,并得到更优的结果。本文以实例介绍PLS方法在光谱模式识别以及建立定量模型适用性判据等方面的应用,其有望成为一种常用的光谱定性方法。     

Recursive least squares based sliding mode approach for position control of DC motors with self-tuning rule

Journal of Mechanical Science and Technology - In this paper, a self-tuning rule-based position control algorithm is proposed for DC motors with system parameter estimation using the recursive...     

Dimensional and angular measurements using least squares and neural networks

In this study a machine vision approach is developed for dimensional and angular measurements of manufactured components comprising straight line segments. We aim at the measurements of distance between two parallel lines and angle between two intersecting lines using both least mean square (LMS) and artificial neural network (ANN) techniques. LMS models estimate the line parameters based on the sum of squared perpendicular distances, rather than the vertical distances, between the observed data points and the line. A set of 23 gauge blocks of varying sizes is used to evaluate the performance of the LMS line estimators. Experimental results show that the measurement errors of the LMS models are affected by the line length and orientation of digital images. ANN techniques are, therefore, used to adjust the measurement errors resulting from the LMS models. Two back-propagation neural networks are developed, one for measuring the distance between two parallel lines, and the other for measuring the angle between two intersecting lines. Experimental results show that the ANNs are very effective for correcting the measurement errors regardless of line lengths and orientations of digital images. A 90% improvement in measurement accuracy for the ANN compared to the LMS was achieved. By using the ANNs, the measurement accuracy and flexibility in manufacturing applications can be significantly improved.     

Nonlinear predictive control of a drying process using genetic algorithms

A nonlinear predictive control technique is developed to determine the optimal drying profile for a drying process. A complete nonlinear model of the baker's yeast drying process is used for predicting the future control actions. To minimize the difference between the model predictions and the desired trajectory throughout finite horizon, an objective function is described. The optimization problem is solved using a genetic algorithm due to the successful overconventional optimization techniques in the applications of the complex optimization problems. The control scheme comprises a drying process, a nonlinear prediction model, an optimizer, and a genetic search block. The nonlinear predictive control method proposed in this paper is applied to the baker's yeast drying process. The results show significant enhancement of the manufacturing quality, considerable decrease of the energy consumption and drying time, obtained by the proposed nonlinear predictive control.     

Management of the wind speed data using adaptive neuro-fuzzy methodology

In this paper, the accuracy of the Weibull model of wind speed is evaluated using an adaptive neuro-fuzzy inference system (ANFIS) based on wind data. The wind data comprises of wind speed measurements in the city of Nis in Serbia at different heights of 10 m, 30 m and 40 m for duration of one year. The ANFIS results are compared with the experimental results and Weibull model using root-mean-square error (RMSE), coefficient of determination, and Pearson coefficient. The effectiveness of the proposed unified strategy is verified based on the simulation results.     

基于局部加权偏最小二乘法的冷凝器污垢预测

提出了基于局部加权偏最小二乘回归算法的污垢预测算法,通过在训练集的污垢数据局部模型内对新测得的数据进行偏最小二乘回归分析,并应用自适应算法对模型参数、各模型之间的加权系数进行自动优化调整。算法能很好地解决新旧数据相互影响问题,以适应冷凝器水质及工况参数的动态变化,具有学习速度快、泛化能力强及鲁棒性强的特点。通过与各种工况下的污垢预测值比较,实验结果说明基于局部加权偏最小二乘回归学习算法的污垢模型预测精度比神经网络模型、渐近污垢模型有显著提高。     

Automated visual inspection for surface appearance defects of varistors using an adaptive neuro-fuzzy inference system

The purpose of this study is to develop an automated visual inspection system for analysis of the surface appearance of ring varistors based on an adaptive neuro-fuzzy inference system (ANFIS). Known image patterns of the six types of ring varistors are used in a training process to establish Sugeno FIS rules, and the input-output data are then set to train the ANFIS to tune the membership function. Feature extraction reduces image complexity using two-dimensional edge detection, calculated within divided rectangular region. The ANFIS combines the neural network adaptive capabilities and fuzzy logic qualitative to train a classification system for six different types of components. The performance of the ANFIS is evaluated in terms of training performance and classification accuracy. The results confirm that the proposed ANFIS is capable of classifying the six types of ring varistors with an accuracy of 98.67%. This paper has not been published elsewhere nor has it been submitted for publication elsewhere.     

应用于起重机稳钩控制的自适应神经模糊推理系统

提出一种基于自适应神经模糊推理系统（ANFIS）的控制方法应用于起重机的稳钩控制,该方法采用反向传播算法（BP）和最小二乘算法（LS）的混合算法对小车—吊重系统样本数据进行学习,调整各变量的隶属度函数,自动产生模糊规则。仿真结果表明,这种控制方法对小车—吊重系统的摇摆角度和小车位置的控制过程具有良好的动态性能和较强的鲁棒性能,说明了自适应神经模糊推理系统在起重机稳钩控制中的有效性。     

一种基于LS-SVM与PID复合的逆控制系统

针对逆系统中非线性逆模型辨识困难的问题,研究了基于最小二乘支持向量机(LS-SVM)的逆模型辨识及控制,并用微粒子群算法(PSO)优化LS-SVM的参数和核函数参数。提出了一种由LS-SVM的逆模型与PID结合的复合控制系统,由LS-SVM辨识非线性系统的逆模型作为前馈控制器,形成直接逆控制。同时,由PID控制器构成反馈控制,克服直接逆控制鲁棒性不强的缺陷。仿真研究结果表明LS-SVM的逆模型辨识能力强,该复合控制系统具有比基于最近邻聚类的RBF神经网络逆控制系统更优的动态跟踪性能,更好的抗干扰能力和鲁棒性。     

Multivariate fault isolation of batch processes via variable selection in partial least squares discriminant analysis

In recent years, multivariate statistical monitoring of batch processes has become a popular research topic, wherein multivariate fault isolation is an important step aiming at the identification of the faulty variables contributing most to the detected process abnormality. Although contribution plots have been commonly used in statistical fault isolation, such methods suffer from the smearing effect between correlated variables. In particular, in batch process monitoring, the high autocorrelations and cross-correlations that exist in variable trajectories make the smearing effect unavoidable. To address such a problem, a variable selection-based fault isolation method is proposed in this research, which transforms the fault isolation problem into a variable selection problem in partial least squares discriminant analysis and solves it by calculating a sparse partial least squares model. As different from the traditional methods, the proposed method emphasizes the relative importance of each process variable. Such information may help process engineers in conducting root-cause diagnosis.