Key principal components with recursive local outlier factor for multimode chemical process monitoring

Owing to various manufacturing strategies and demands of markets, chemical processes often involve multiple operating modes. How to identify mode from multimode process data collected under both stable and transitional modes is an important issue. This paper proposes a novel mode identification algorithm-recursive local outlier factor (RLOF) based on the sequential information in the time scale and the density information in the spatial scale. In this algorithm, not only the number of modes does not need to be determined in advance, but also details of mode switching can be acquired. In addition, the principal components (PCs) chosen by the variance of overall dataset in principal component analysis (PCA) cannot guarantee that all variables express information as completely as possible. Using the defined cumulative percent expression (CPE), this study chooses key PCs (KPCs) according to each variable. Moreover, fault diagnosis is realized via the contribution of every variable to key PCs. Finally, the monitoring performance is evaluated under the Tennessee Eastman (TE) benchmark and the continuous stirred tank reactor (CSTR) process.     

基于粒子群优化算法的熔融指数预报

针对丙烯聚合生产控制中聚丙烯熔融指数在线测量的控制要求,以及过程变量间相关性高的特点,提出一种实用高精度的软测量方法,以弥补传统的实验室分析严重滞后所导致的生产控制瓶颈问题。采用主元分析,提取少量主元反映多个变量的综合信息,以降低预报模型的复杂度。并在此基础上建立基于径向基函数神经网络的统计预报模型,提出利用粒子群优化算法优化神经网络的结构与参数,以减少人为因素对建模的影响,得到最优预报结果。通过对工厂实际生产过程进行详细的预报检测,并进一步与国内外相关研究报道进行比较,结果表明,所提出的预报方法具有更强的可靠性和更高的准确性。     

基于广义主成分分析的重构故障子空间建模方法

在线故障诊断是工业过程中十分重要的问题.相比传统贡献图而言,基于重构的故障诊断受到特别关注.传统的主元分析方法没有考虑故障数据中同时包含正常工况信息和故障信息,因而提取出故障子空间对故障的描述准确性不足.为提高故障子空间的准确性,提出一种基于广义主成分分析的重构故障子空间建模方法.首先,同时考虑正常工况数据和故障数据,...     

Finger-vein pattern identification using principal component analysis and the neural network technique

This paper presents a personal identification system using finger-vein patterns with component analysis and neural network technology. In the proposed system, the finger-vein patterns are captured by a device that can transmit near infrared through the finger and record the patterns for signal analysis. The proposed biometric system for verification consists of a combination of feature extraction using principal component analysis (PCA) and pattern classification using back-propagation (BP) network and adaptive neuro-fuzzy inference system (ANFIS). Finger-vein features are first extracted by PCA method to reduce the computational burden and removes noise residing in the discarded dimensions. The features are then used in pattern classification and identification. To verify the effect of the proposed ANFIS in the pattern classification, the BP network is compared with the proposed system. The experimental results indicated the proposed system using ANFIS has better performance than the BP network for personal identification using the finger-vein patterns.     

基于差分分段PCA的多模态过程故障监测

多模态的故障监测是一个复杂的问题, 既需要考虑稳定模态下的故障监测, 也需要考虑不同模态间的过渡故障监测. 不同稳定模态下的数据具有不同的相关关系, 对每个稳定模态需要建立不同的稳定模态模型. 当稳定生产模态发生改变时, 生产过程进入过渡模态, 需要考虑过渡变量相关关系的变化. 本文通过对过渡数据差分, 得到变量相对变化信息. 利用主成分分析(Principal component analysis, PCA)分段对差分变量的相关特性进行分析, 提取相对变化的特征. 最后以实际连续退火机组生产线为背景, 用基于差分分段PCA的多模态方法对多模态过程进行故障监测, 发现算法很好地反映了实际过渡过程机理, 验证了算法的有效性.     

基于改进混合概率主元分析模型的过程监控

基于混合概率主元分析（MPPCA）的监控方法,存在要求各子模型中主元个数相同、监控指标不一致、监控表格过多等缺陷．为此对MPPCA算法进行改进,分两步建立模型：首先求出混合高斯模型（GMM）,然后利用概率主元分析（PPCA）建立每个子模型的主元模型．改进方法中各子模型主元的选取兼顾了主元的解释宰及其变化趋势,并引进基于PPCA的监控方法,保证了监控指标的一致性,减少了过程监控图．     

Predicting the occurrence of adverse events using an adaptive neuro-fuzzy inference system (ANFIS) approach with the help of ANFIS input selection

This study presents an adaptive neuro-fuzzy inference system (ANFIS) approach performed to estimate the number of adverse events where the dependent variables are adverse events leading to four types of variables: number of people killed, wounded, hijacked and total number of adverse events. Fourteen infrastructure development projects were selected based on allocated budgets values at different time periods, population density, and previous month adverse event numbers selected as independent variables. Firstly, number of independent variables was reduced by using ANFIS input selection approach. Then, several ANFIS models were performed and investigated for Afghanistan and the whole country divided into seven regions for analysis purposes. Performances of models were assessed and compared based on the mean absolute errors. The difference between observed and estimated value was also calculated within \({\pm }1\) range with values around 90 %. We included multiple linear regression (MLR) model results to assess the predictive power of the ANFIS approach, in comparison to a traditional statistical approach. When the model accuracy was calculated according to the performance metrics, ANFIS showed greater predictive accuracy than MLR analysis, as indicated by experimental results. As a result of this study, we conclude that ANFIS is able to estimate the occurrence of adverse events according to economical infrastructure development project data.     

Knowledge discovery in steel bar rolling mills using scheduling data and automated inspection

There are various surface defects which occur during the hot rolling of steels. It is difficult to correctly identify and control these defects due to the different inspection techniques on different materials and sizes. Also, the statistical data analysis techniques typically used like the principal component analysis, factor analysis etc. require a lot of plant data and are computationally very intensive. Before a detailed analysis of the actual cause of the defects can be done, it is necessary to separate the defects as those coming from the continuous casting or the rolling mill. Once this is done, analysis on the individual components can then be completed to find the root cause. To accomplish both these analysis, Bayesian hierarchical modeling is done on the automated inspection of the bars to form a causal relationship of the defects to the process equipments. Variance reduction model is used at the top of the analysis and regression models are used in the next level.     

基于主元分析和小波变换的开工过程故障识别

针对蒸汽裂解实验装置的开工过程具有间歇操作,变量间相关性高的特点,传统的故障识别方法无法有效处理这种具有较强动态特性的实际工业生产过程.本文提出利用主元分析,用少量主元反映多个动态变量的综合信息,并利用正交小波变换的多尺度时频分析提取主元中表征工况变化的频带特征,对频带特征进行模式归纳分类,进而识别工况.实验结果证实了所提出方法的可行性和有效性.     

A new fault diagnosis method of multimode processes using Bayesian inference based Gaussian mixture contribution decomposition

This paper presents a novel Bayesian inference based Gaussian mixture contribution (BIGMC) method to isolate and diagnose the faulty variables in chemical processes with multiple operating modes. The statistical confidence intervals of traditional principal component analysis (PCA) based T² and SPE diagnostics rely upon the assumption that the operating data follow a multivariate Gaussian distribution approximately and therefore may not be able to determine the faulty variables in multimode non-Gaussian processes accurately. As an alternative solution, the proposed BIGMC method first identifies the multiple Gaussian modes corresponding to different operating conditions and then integrates the Mahalanobis distance based variable contributions across all the Gaussian clusters through Bayesian inference strategy. The derived BIGMC index is of probabilistic feature and includes all operation scenarios with posterior probabilities as weighting factors. The Tennessee Eastman process (TEP) is used to demonstrate the utility of the proposed BIGMC method for fault diagnosis of multimode processes. The comparison of the single-PCA and multi-PCA based contribution approaches shows that the BIGMC method can effectively identify the leading faulty variables with superior diagnosis capability.     

Prediction of scouring around an arch-shaped bed sill using Neuro-Fuzzy model

In this study, Adaptive Neuro-Fuzzy Inference System (ANFIS) has been used to model local scouring depth and pattern scouring around concave and convex arch shaped circular bed sills. The experimental part of this research study includes seven sets of laboratory test cases which were performed in an experimental flume under different flow conditions. A data set consists of 2754 data points of scouring depth were collected to use in the ANFIS model. The ratio of arch diameter, D, to flume width, W, is used as a non dimensional variables in all test cases. The results from ANFIS model were compared with the results of ANN model obtained by Homayoon et al. [24] and previously presented models. The results indicated that for D/W equal to 1 and 1.2, the ANFIS models produced a good performance for convex and concave bed sills. As a result, the ANFIS models can be used as an alternative to ANN for estimation of scour depth and scour pattern around a concave bed sill installed with a bridge pier.     

一种基于分级输入训练神经网络的非线性主元分析

基于输入训练神经网络的非线性主元分析（PCA）能够有效地提取过程变量的非线性主元,但是存在主元的个数不能通过网络训练确定,且各个主元重要程度在神经网络中无法区分等缺点，本文提出一种分级输入自调整神经网络,并进一步提出基于此网络的非线性PCA,通过多级输入自调整神经网络,将主元按顺序找出,且根据主元对过程数据的预测误差定量地确定出主元的个数,克服了上述缺点.     

基于振动频谱的磨机负荷在线软测量建模

针对磨机负荷(ML)软测量模型难以适应磨矿过程的时变特性,模型需要依据工况实时在线更新的问题,基于磨机简体振动频谱,通过递归主元分析(RPCA)和在线最小二乘支持向量回归机(LSSVR)的集成,提出了ML参数(料球比、矿浆浓度、充填率)在线软测量方法.首先,针对训练样本,采用主元分析(PCA)分别提取振动频谱在低、中、高频段的谱主元;然后以串行组合后的谱主元为输入,采用LSSVR方法构造ML参数离线软测量模型;最后,采用旧模型完成预测后,应用RPCA及在线LSSVR算法分别递归更新模型的输入和模型的回归参数,从而实现了ML软测量模型的在线更新.实验结果表明,该软测量方法与其它常规方法相比具有较高的精度和更好的预测性能.     

Predicting flow conditions over stepped chutes based on ANFIS

Chute flow may be either smooth or stepped. The flow conditions in stepped chutes have been classified into nappe, transition and skimming flows. In this paper, characteristics of flow conditions are presented systematically under a wide range of critical flow depth, step height and chute slope. The Adaptive Network Based Fuzzy Inference System (ANFIS) is used to predict flow conditions in stepped chutes using critical flow depth, step height and chute slope information. The proposed model performance is determined by threefold cross validation method. The evaluated classification accuracy of ANFIS model is 99.01%. The test results showed that the proposed ANFIS model can be used successfully for complex process control in hydraulic systems.     

Design and comparison of adaptive power system stabilizers based on neural fuzzy networks and genetic algorithms

This paper presents two different power system stabilizers (PSSs) which are designed making use of neural fuzzy network and genetic algorithms (GAs). In both cases, GAs tune a conventional PSS on different operating conditions and then, the relationship between these points and the PSS parameters is learned by the ANFIS. ANFIS will select the PSS parameters based on machine loading conditions. The first stabilizer is adjusted minimizing an objective function based on ITAE index, while second stabilizer is adjusted minimizing an objective function based on pole-placement technique. The proposed stabilizers have been tested by performing simulations of the overall nonlinear system. Preliminary experimental results are shown.     

Feature extraction and selection based on vibration spectrum with application to estimating the load parameters of ball mill in grinding process

Feature extraction and selection are important issues in soft sensing and complex nonlinear system modeling. In this paper, a new feature extraction and selection approach based on the vibration frequency spectrum is proposed to estimate the load parameters of wet ball mill in grinding process. This approach can simplify the modeling process. In this study, the vibration acceleration signals are first transformed into the frequency spectrum by fast Fourier transform (FFT). Then the candidate features are extracted and selected from the frequency spectrum, which include characteristic frequency sub-bands, spectral principal components, and features of local peaks. Mutual information, spectral segment clustering and kernel principal component analysis are used to obtain these candidate features. Finally, a combinatorial optimization method based on adaptive genetic algorithm selects the input sub-set and parameters of the soft sensor model simultaneously. This approach is successfully applied in a laboratory scale wet ball mill. The test results show that the proposed approach is effective for modeling the parameters of mill load.     

Multi-step ahead direct prediction for the machine condition prognosis using regression trees and neuro-fuzzy systems

This paper presents an approach to predict the operating conditions of machine based on classification and regression trees (CART) and adaptive neuro-fuzzy inference system (ANFIS) in association with direct prediction strategy for multi-step ahead prediction of time series techniques. In this study, the number of available observations and the number of predicted steps are initially determined by using false nearest neighbor method and auto mutual information technique, respectively. These values are subsequently utilized as inputs for prediction models to forecast the future values of the machines’ operating conditions. The performance of the proposed approach is then evaluated by using real trending data of low methane compressor. A comparative study of the predicted results obtained from CART and ANFIS models is also carried out to appraise the prediction capability of these models. The results show that the ANFIS prediction model can track the change in machine conditions and has the potential for using as a tool to machine fault prognosis.     

The prediction of ultimate pure bending moment of concrete-filled steel tubes by adaptive neuro-fuzzy inference system (ANFIS)

In this study, different modelling techniques such as multiple regression and adaptive neuro-fuzzy inference system (ANFIS) are used for predicting the ultimate pure bending of concrete-filled steel tubes (CFTs). The behaviour of CFT under pure bending is complex and highly nonlinear; therefore, forward modelling techniques can have considerable limitations in practical situations where fast and reliable solutions are required. Linear multiple regression (LMR), nonlinear multiple regression (NLMR) and ANFIS models were trained and checked using a large database that was constructed and populated from the literature. The database comprises 72 pure bending tests conducted on fabricated and cold-formed tubes filled with concrete. Out of 72 tests, 48 tests were conducted by the second author. Input variables for the models are the same with those used by existing codes and practices such as the tube thickness, tube outside diameter, steel yield strength, strength of concrete and shear span. A practical application example, showing the translation of constructed ANFIS model into design equations suitable for hand calculations, was provided. A sensitivity analysis was conducted on ANFIS and multiple regression models. It was found that the ANFIS model is more sensitive to change in input variables than LMR and NLMR models. Predictions from ANFIS models were compared with those obtained from LMR, NLMR, existing theory and a number of available codes and standards. The results indicate that the ANFIS model is capable of predicting the ultimate pure bending of CFT with a high degree of accuracy and outperforms other common methods.

     

Performance monitoring of a multi-product semi-batch process

Traditionally principal components analysis (PCA) has been viewed as a single-population method. In particular in multivariate statistical process control, PCA has been used to monitor single product production. An extension to principal components analysis is presented which enables the simultaneous monitoring of a number of product grades or recipes. The method is based upon the existence of a common eigenvector subspace for the sample variance–covariance matrices of the individual products. The pooled sample variance–covariance matrix of the individual products is then used to estimate the principal component loadings of the multi-group model. The methodology is applied to a semi-discrete industrial batch process manufacturing a number of recipes. The industrial application illustrates that the detection and diagnostic capabilities of the multi-group model are comparable to those achieved by developing a separate statistical representation for the individual products.     

PCA和PSO-ELM在高炉铁水硅含量中的预测仿真

炉温的实时预测技术对高炉运转具有重要意义。在高炉炼铁过程中,通常以铁水硅含量来表征高炉热状态。针对硅含量预测效率和精度不足的问题,提出主成分分析和粒子群改进的极限学习机相结合的方法对高炉铁水硅含量进行预测。由于影响铁水硅含量的因素众多,且各因素之间相互影响,通过主成分分析对影响硅含量的输入变量进行降维处理。利用粒子群算法来优化极限学习机的权值和阈值,并以均方根误差作为适应度函数建立预测模型。将提取出的主成分作为模型输入,铁水硅含量作为模型输出。最后比较了极限学习机算法和粒子群改进的极限学习机,实验结果表明改进后的预测模型提高了硅含量预测的准确度,上述方法可为高炉的生产操作提供参考。