基于更新样本智能识别算法的自适应集成建模

选择表征建模对象特性漂移的新样本对软测量模型进行自适应更新,能够降低模型复杂度和运行消耗,提高模型可解释性和预测精度.针对新样本近似线性依靠程度（Approximate linear dependence, ALD）和预测误差（Prediction error, PE）等指标只能片面反映建模对象的漂移程度,领域专家结合具体工业过程需要依据上述指标和自身积累经验进行更新样本的有效识别等问题,本文提出了基于更新样本智能识别算法的自适应集成建模策略.首先,基于历史数据离线建立基于改进随机向量泛函连接网络（Improved random vector functional-link networks, IRVFL）的选择性集成模型;然后,基于集成子模型对新样本进行预测输出后采用在线自适应加权算法（On-line adaptive weighting fusion, OLAWF）对集成子模型权重进行更新,实现在线测量阶段对建模对象特性变化的动态自适应;接着基于领域专家知识构建模糊推理模型对新样本相对ALD（Relative ALD, RALD）值和相对PE（Relative PE, RPE）值进行融合,实现更新样本智能识别,构建新的建模样本库;最后实现集成模型的在线自适应更新.采用合成数据仿真验证了所提算法的合理性和有效性.     

Online quality prediction for cobalt oxalate synthesis process using least squares support vector regression approach with dual updating

Online measurement of the average particle size is typically unavailable in industrial cobalt oxalate synthesis process, soft sensor prediction of the important quality variable is therefore required. Cobalt oxalate synthesis process is a complex multivariable and highly nonlinear process. In this paper, an effective soft sensor based on least squares support vector regression (LSSVR) with dual updating is developed for prediction the average particle size. In this soft sensor model, the methods of moving window LSSVR (MWLSSVR) updating and the model output offset updating is activated based on model performance assessment. Feasibility and efficiency of the proposed soft sensor are demonstrated through the application to an industrial cobalt oxalate synthesis process.     

时变过程在线辨识的即时递推核学习方法研究

为了及时跟踪非线性化工过程的时变特性, 提出即时递推核学习 (Kernel learning, KL)的在线辨识方法. 针对待预测的新样本点, 采用即时学习 (Just-in-time kernel learning, JITL)策略, 通过构造累积相似度因子, 选择与其相似的样本集建立核学习辨识模型. 为避免传统即时学习对每个待预测点都重新建模的繁琐, 利用两个临近时刻相似样本集的异同点, 采用递推方法有效添加新样本, 并删减旧模型的样本, 以快速建立新即时模型. 通过一时变连续搅拌釜式反应过程的在线辨识, 表明了所提出方法在保证计算效率的同时, 较传统递推核学习方法提高了辨识的准确程度, 能更好地辨识时变过程.     

Fast and reliable computational strategy for developing a rigorous model-driven soft sensor of dynamic molecular weight distribution

Key polymer properties are substantially directly related to the polymer molecular weight distribution (MWD). On-line monitoring and prediction of dynamic MWD profiles are highly important for on-line quality control of polymerization processes. In this study, a fast and reliable computational strategy for an equation-oriented model-based soft sensor for the high-density polyethylene grade transition process is developed. The simultaneous collocation approach is adopted to discretize the dynamic model. A novel moving finite element method is proposed to improve the on-line performance of the derived large-scale nonlinear equation systems. The sensitivity information of the nonlinear equation systems contributes to a convergence enhancement strategy for the sensor. The prediction accuracy and computational efficiency are demonstrated using industrial data. A potential application to extend the polymerization process with changeable flowsheet is also tested through simulation.     

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.     

基于JITL的电量预测高斯软测量建模研究

为了解决工业过程受本身结构特征、外界因素等影响而存在严重的非线性和时变性等问题,本文提出了一种基于输入输出综合性相似度指标的即时学习高斯过程软测量建模方法。在该方法中,将样本数据进行归一化处理,首先利用传统的基于距离和角度的相似度指标分别对样本输入输出变量进行相似度计算,进而对相似度进行综合,最后选择出最终的相关样本集,建立高斯过程回归软测量模型,将所提基于输入输出相似度指标的即时学习高斯工程软测量模型应用于城市日用电量数据的预测。研究结果表明,所提出的软测量建模方法可以实现对日用电量数据的高精度预测且预测结果具有较小的误差。因此可表明该方法可在电量预测中具有一定的应用可靠性,可以在电力市场预测分析中得到广泛的应用。     

基于多样性加权相似度的集成局部加权偏最小二乘软测量建模

针对传统即时学习软测量方法仅考虑单一的相似度函数,难以有效处理复杂工业过程中的非线性特性,从而导致模型预测性能受限的问题,提出了一种基于多样性加权相似度（DWS）的集成局部加权偏最小二乘（LWPLS）软测量建模方法.首先采用随机子空间法和高斯混合聚类,构建一组多样性的训练样本子集;然后通过偏最小二乘回归分析确定输入特征权值,从而定义一组多样性加权相似度函数.在线实施阶段,对于任意的查询样本,基于多样性的相似度指标,可建立一组多样性的LWPLS软测量模型,随后引入集成学习策略实现难测变量的融合预测.在数值例子和脱丁烷塔过程中的应用结果表明了该方法的有效性.     

在线鲁棒最小二乘支持向量机回归建模

鉴于工业过程的时变特性以及现场采集的数据通常具有非线性特性且包含离群点,利用最小二乘支持向量机回归（least squares support vector regression,LSSVR）建模易受离群点的影响.针对这一问题,结合鲁棒学习算法（robust learning algorithm,RLA）,本文提出了一种在线鲁棒最小二乘支持向量机回归建模方法.该方法首先利用LSSVR模型对过程输出进行预测,与真实输出相比较得到预测误差;然后利用RLA方法训练LSSVR模型的权值,建立鲁棒LSSVR模型;最后应用增量学习方法在线更新鲁棒LSSVR模型,从而得到在线鲁棒LSSVR模型.仿真研究验证了所提方法的有效性.     

助训练框架下的半监督软测量建模方法

为了充分利用工业过程中大量无标签样本信息,并减少过程的不确定因素对无标签样本质量的影响,提出一种助训练框架下的半监督孪生支持向量回归软测量建模方法。采用孪生支持向量回归机构建主学习器,对高置信度无标签样本添加伪标签;同时,基于K近邻算法构建辅学习器,最大化学习器在近邻样本集上的均方误差,经过此项指标筛选后的待处理样本集包含了更多的数据信息;主、辅学习器二者相辅相成,一定程度上提高了模型的泛化性;再利用所构建的助训练框架提高样本利用率后得到预测模型,实现对无标签样本信息的充分挖掘。通过对脱丁烷塔工业过程中的实际数据进行建模仿真,所得结果表明此模型具有良好的预测性能。     

基于改进KH-ANFIS 的海洋溶菌酶发酵过程软测量

针对海洋溶菌酶（Marine Lysozyme,ML）发酵过程菌体浓度在线检测难以实现,离线测量不能反映发酵过程当前变化等问题,提出了一种基于改进磷虾群—自适应模糊神经网络软测量（HLKH-ANFIS）建模方法。首先利用自适应莱维飞行策略对传统KH进行改进,从而提升算法的全局搜索能力;同时利用跳变技术（HOT）对KH算法位置更新公式进行改进,提高算法的局部寻优能力,然后利用改进的KH算法对自适应模糊神经网络反馈进行优化,改善其过度修正和计算量大的问题;最后建立基于HLKH-ANFIS的海洋溶菌酶发酵过程菌体浓度软测量预测模型,仿真分析表明：相较于KH-ANFIS预测模型,HLKH-ANFIS模型的误差较小,具有更好的预测能力,能够满足ML发酵关键参量的在线预测需要。     

A hybrid grid-GA-based LSSVR learning paradigm for crude oil price forecasting

In order to effectively model crude oil spot price with inherently high complexity, a hybrid learning paradigm integrating least squares support vector regression (LSSVR) with a hybrid optimization searching approach for the parameters selection in the LSSVR [consisting of grid method and genetic algorithm (GA)], i.e., a hybrid grid-GA-based LSSVR model, is proposed in this study. In the proposed hybrid learning paradigm, the grid method, a simple but efficient searching method, is first applied to roughly but rapidly determine the proper boundaries of the parameters in the LSSVR; then, the GA, an effective and powerful intelligent searching algorithm, is further implemented to select the most suitable parameters. For illustration and verification, the proposed learning paradigm is used to predict the crude oil spot prices of the West Texas Intermediate and the Brent markets. The empirical results demonstrate that the proposed hybrid grid-GA-based LSSVR learning paradigm can outperform its benchmarking models (including some popular forecasting techniques and similar LSSVRs with other parameter searching algorithms) in terms of both prediction accuracy and time-savings, indicating that it can be utilized as one effective forecasting tool for crude oil price with high volatility and irregularity.     

一种用于软测量建模的增量学习集成算法

针对软测量模型在实际应用中遇到的问题, 结合AdaBoost 集成学习思想, 提出适用于软测量回归的集成学习算法, 以提高传统软测量模型的精度. 为了克服模型更新技术对软测量实际应用的制约, 将增量学习机制加入软测量集成建模中, 使软测量模型具有在线实时更新的增量学习能力. 对浆纱过程使用新方法建立上浆率软测量模型, 并使用实际生产数据对模型进行检验, 检验结果表明, 该模型具有很好的预测精度, 并能够较好地实现在线更新.

     

Data supplement for a soft sensor using a new generative model based on a variational autoencoder and Wasserstein GAN

In industrial process control, measuring some variables is difficult for environmental or cost reasons. This necessitates employing a soft sensor to predict these variables by using the collected data from easily measured variables. The prediction accuracy and computational speed in the modeling procedure of soft sensors could be improved with adequate training samples. However, the rough environment of some industrial fields makes it difficult to acquire enough samples for soft sensor modeling. Generative adversarial networks (GANs) and the variational autoencoder (VAE) are two prominent methods that have been employed for learning generative models. In the current work, the VA-WGAN combining VAE with Wasserstein generative adversarial networks (WGAN) as a generative model is established to produce new samples for soft sensors by using the decoder of VAE as the generator in WGAN. An actual industrial soft sensor with insufficient data is used to verify the data generation capability of the proposed model. According to the experimental results, the samples obtained with the proposed model more closely resemble the true samples compared with the other four common generative models. Moreover, the insufficiency of the training data and the prediction precision of soft sensors could be improved via these constructed samples.     

Online dual updating with recursive PLS model and its application in predicting crystal size of purified terephthalic acid (PTA) process

To improve the performance of online prediction of existing soft sensor models, we propose a dual updating strategy, i.e., integrating the methods of recursive partial least square (RPLS) model updating and the model output offset updating. In online applications, each update is activated rotationally. In this strategy, a new recursive PLS method is developed and implemented by updating the mean and variance of the training samples using the data acquired from the process, while the offset updating method takes into account both the old overall offset and the new bias between the actual measurement and the model prediction. Since the dual updating strategy takes the advantages of the two updating methods, it is more effective than any individual updating method in adapting process changes. The high performance of the strategy is demonstrated by the application of an industrial purified terephthalic acid (PTA) purification process in which prediction of average crystal particle size was within 2.5% with regard to the relative root mean square error (RMSE). In addition, the dynamic PLS method was found inferior to any of the three methods mentioned above, at least for this particular industrial application. The present dual updating method may also be extended to other industrial applications using process models outside PLS.     

Data-based adaptive online prediction model for plant-wide production indices

A data-based adaptive online prediction model is proposed for plant-wide production indices based on support vector regression, a general method which we customized specifically to model very large data sets that are generated dynamically and periodically. The proposed model can update its parameters online according to the statistical properties of the training samples. Further, in order to improve the prediction precision, each sample is weighted with a dynamic penalty factor that considers the effect of each sample on the prediction model accuracy. Moreover, a customized procedure is introduced to handle large training sets. After having been convincingly evaluated on benchmark data, effectiveness and performance of our approach for plant-wide production indices is demonstrated using industrial data from an operating ore dressing plant over a range of scale in training data set size. The higher accuracy and shorter computation times than existing methods suggest that it may prove advantageous in actual application to dynamic production processes.     

Uncertainty-aware soft sensor using Bayesian recurrent neural networks

Data-driven soft sensors have been widely used to measure key variables for industrial processes. Soft sensors using deep learning models have attracted considerable attention and shown superior predictive performance. However, if a soft sensor encounters an unexpected situation in inferring data or if noisy input data is used, the estimated value derived by a standard soft sensor using deep learning may at best be untrustworthy. This problem can be mitigated by expressing a degree of uncertainty about the trustworthiness of the estimated value produced by the soft sensor. To address this issue of uncertainty, we propose using an uncertainty-aware soft sensor that uses Bayesian recurrent neural networks (RNNs). The proposed soft sensor uses a RNN model as a backbone and is then trained using Bayesian techniques. The experimental results demonstrated that such an uncertainty-aware soft sensor increases the reliability of predictive uncertainty. In comparisons with a standard soft sensor, it shows a capability to use uncertainties for interval prediction without compromising predictive performance.     

Development and industrial application of soft sensors with on-line Bayesian model updating strategy

This paper deals with the issues associated with the development of data-driven models as well as model update strategy for soft sensor applications. A practical yet effective solution is proposed. Key process variables that are difficult to measure are commonly encountered in practice due to limitations of measurement techniques. Even with appropriate instruments, some measurements are only available through off-line laboratory analysis with typical sampling intervals of several hours. Soft sensors are inferential models that can provide continuous on-line prediction of hidden variables; such models are capable of combining real-time measurements with off-line lab data. Due to the prevalence of plant-model mismatch, it is important to update the model using the latest reference data. In this paper, parameters of data-driven models are estimated using particle filters under the framework of expectation–maximization (EM) algorithms. A Bayesian methodology for model calibration strategy is formulated. The proposed framework for soft sensor development is applied to an industrial process to provide on-line prediction of a quality variable.     

Streaming parallel variational Bayesian supervised factor analysis for adaptive soft sensor modeling with big process data

Time-varying and state shifting are two of the main process factors that cause poor prediction performance of soft sensors. Adaptive soft sensor is commonly an alternative practice to ensure high predictive accuracy. However, the large scale of process data often leads to inefficiency of model updating. In this paper, a streaming variational Bayesian supervised factor analysis (S-VBSFA) model is first proposed to capture the process time-varying and state shifting features through online updating of the posterior of model parameters. During the updating process, the symmetric Kullback–Leibler (SKL) divergence is utilized to determine priors of the next variation Bayesian inference. To improve the modeling efficiency for large-scale process data, the parallel computing strategy is further applied to the streaming model. As a result, the proposed streaming parallel VBSFA (SP-VBSFA) algorithm not only relieves the computing pressure of modeling big process data, but also improves the prediction accuracy and further reduces the tracking time delay for process variations. Two case studies demonstrate the superiority of the proposed method, compared to conventional methods.     

基于图像特征的锑浮选矿浆pH值预测控制

适宜的矿浆pH值是泡沫浮选高效生产的关键。针对浮选矿浆pH值无法在线检测和控制滞后的问题,提取pH关联泡沫表面敏感特征,建立了基于仿射传播聚类(AP)的多模型最小二乘支持向量机(LSSVM)软测量模型;提出一种基于差分进化(DE)的在线支持向量回归(OSVR)pH值预测控制方法,离线建立和在线校正pH值预测模型,采用DE优化方法求解预测控制决策变量实现pH值实时控制。金锑浮选工业数据表明所提出的控制策略稳定了矿浆pH值,减少了药剂消耗。