Modeling and identification for soft sensor systems based on the separation of multi-dynamic and static characteristics

Data-driven soft sensor is an effective solution to provide rapid and reliable estimations for key quality variables online.The secondary variables affect the primary variable in considerably different speed,and soft sensor systems exhibit multi-dynamic characteristics.Thus,the first contribution is improving the model in the previous study with multi-time-constant.The characteristics-separation-based model will be identified in substep way,and the stochastic Newton recursive (SNR) algorithm is adopted.Considering the dual-rate characteristics of soft sensor systems,the proposed model cannot be identified directly.Thus,two auxiliary models are first proposed to offer the intersample estimations at each update period,based on which the improved algorithm (DAM-SNR) is derived.These two auxiliary models function in switching mechanism which has been illustrated in detail.This algorithm serves for the identification of the proposed model together with the SNR algorithm,and the identification procedure is then presented.Finally,the laboratorial case confirms the effectiveness of the proposed soft sensor model and the algorithms.     

基于梯度估计的直接自适应控制

A control method of direct adaptive control based on gradient estimation is proposed in this article. The dynamic system is embedded in a linear model set. Based on the embedding property of the dynamic system, an adaptive optimal control algorithm is proposed. The robust convergence of the proposed control algorithm has been proved and the static control error with the proposed method is also analyzed. The application results of the proposed method to the industrial polypropylene process have verified its feasibility and effectiveness.     

基于剪接系统的遗传算法RBF网络建模方法

A splicing system based genetic algorithm is proposed to optimize dynamical radial basis function （RBF） neural network, which is used to extract valuable process information from input output data. The novel RBF network training technique includes the network structure into the set of function centers by compromising between the conflicting requirements of reducing prediction error and simultaneously decreasing model complexity. The effectiveness of the proposed method is illustrated through the development of dynamic models as a benchmark discrete example and a continuous stirred tank reactor by comparing with several different RBF network training methods.     

基于FCMISVM的自适应软测量建模算法及其在PX吸附分离过程中的应用

To overcome the problem that soft sensor models cannot be updated with the process changes, a soft sensor modeling algorithm based on hybrid fuzzy c-means (FCM) algorithm and incremental support vector machines (ISVM) is proposed. This hybrid algorithm FCMISVM includes three parts: samples clustering based on FCM algorithm, learning algorithm based on ISVM, and heuristic sample displacement method. In the training process, the training samples are first clustered by the FCM algorithm, and then by training each clustering with the SVM algorithm, a sub-model is built to each clustering. In the predicting process, when an incremental sample that represents new operation information is introduced in the model, the fuzzy membership function of the sample to each clustering is first computed by the FCM algorithm. Then, a corresponding SVM sub-model of the clustering with the largest fuzzy membership function is used to predict and perform incremental learning so the model can be updated on-line. An old sample chosen by heuristic sample displacement method is then discarded from the sub-model to control the size of the working set. The proposed method is applied to predict the p-xylene (PX) purity in the adsorption separation process. Simulation results indicate that the proposed method actually increases the model’s adaptive abilities to various operation conditions and improves its generalization capability.     

一种基于状态估计的间歇过程模型实时更新预测控制策略简

Nonlinear model predictive control （NMPC） is an appealing control technique for improving the per- formance of batch processes, but its implementation in industry is not always possible due to its heavy on-line computation. To facilitate the implementation of NMPC in batch processes, we propose a real-time updated model predictive control method based on state estimation. The method includes two strategies： a multiple model building strategy and a real-time model updated strategy. The multiple model building strategy is to produce a series of sim- plified models to reduce the on-line computational complexity of NMPC. The real-time model updated strategy is to update the simplified models to keep the accuracy of the models describing dynamic process behavior. The method is validated with a typical batch reactor. Simulation studies show that the new method is efficient and robust with respect to model mismatch and changes in process parameters.     

利用状态空间模型和不敏卡尔曼滤波的分批补料发酵过程在线估计(英文)

On-line estimation of unmeasurable biological variables is important in fermentation processes, directly influencing the optimal control performance of the fermentation system as well as the quality and yield of the targeted product. In this study, a novel strategy for state estimation of fed-batch fermentation process is proposed. By combining a simple and reliable mechanistic dynamic model with the sample-based regressive measurement model, a state space model is developed. An improved algorithm, swarm energy conservation particle swarm optimization (SECPSO), is presented for the parameter identification in the mechanistic model, and the support vector machines (SVM) method is adopted to establish the nonlinear measurement model. The unscented Kalman filter (UKF) is designed for the state space model to reduce the disturbances of the noises in the fermentation process. The proposed on-line estimation method is demonstrated by the simulation experiments of a penicillin fed-batch fermentation process.     

A data-derived soft-sensor method for monitoring effluent total phosphorus

The effluent total phosphorus(ETP)is an important parameter to evaluate the performance of wastewater treatment process(WWTP).In this study,a novel method,using a data-derived soft-sensor method,is proposed to obtain the reliable values of ETP online.First,a partial least square(PLS)method is introduced to select the related secondary variables of ETP based on the experimental data.Second,a radial basis function neural network (RBFNN)is developed to identify the relationship between the related secondary variables and ETP.This RBFNN easily optimizes the model parameters to improve the generalization ability of the soft-sensor. Finally, a monitoring system, based on the above PLS and RBFNN, named PLS-RBFNN-based soft-sensor system, is developed and tested in a real WWTP.Experimental results show that the proposed monitoring system can obtain the values of ETP online and own better predicting performance than some existing methods.     

Simultaneous hybrid modeling of a nosiheptide fermentation process using particle swarm optimization

Hybrid modeling approaches have recently been investigated as an attractive alternative to model fermentation processes. Normally, these approaches require estimation data to train the empirical model part of a hybrid model. This may result in decreasing the generalization ability of the derived hybrid model. Therefore, a simulta-neous hybrid modeling approach is presented in this paper. It transforms the training of the empirical model part into a dynamic system parameter identification problem, and thus al ows training the empirical model part with only measured data. An adaptive escaping particle swarm optimization (AEPSO) algorithm with escaping and adaptive inertia weight adjustment strategies is constructed to solve the resulting parameter identification problem, and thereby accomplish the training of the empirical model part. The uniform design method is used to determine the empirical model structure. The proposed simultaneous hybrid modeling approach has been used in a lab-scale nosiheptide batch fermentation process. The results show that it is effective and leads to a more consistent model with better generalization ability when compared to existing ones. The performance of AEPSO is also demonstrated.     

基于混合建模技术的复合肥养分含量MIMO软测量模型

In compound fertilizer production, several quality variables need to be monitored and controlled simultaneously. It is very diifficult to measure these variables on-line by existing instruments and sensors. So, soft-sensor technique becomes an indispensable method to implement real-time quality control. In this article, a new model of multi-inputs multi-outputs （MIMO） soft-sensor, which is constructed based on hybrid modeling technique, is proposed for these interactional variables. Data-driven modeling method and simplified first principle modelingmethod are combined in this model. Data-driven modeling method based on limited memory partial least squares（LM-PLS） al.gorithm is used to build soft-senor models for some secondary variables.then, the simplified first principle model is used to compute three primary variables on line. The proposed model has been used in practicalprocess; the results indicate that the proposed model is precise and efficient, and it is possible to realize on line quality control for compound fertilizer process.     

化工过程基于广义非线性状态观测器的不可测输入和不确定模型参数软仪表(英文)

Chemical processes are usually nonlinear singular systems. In this study, a soft sensor using nonlinear singular state observer is established for unknown inputs and uncertain model parameters in chemical processes, which are augmented as state variables. Based on the observability of the singular system, this paper presents a simplified observability criterion under certain conditions for unknown inputs and uncertain model parameters. When the observability is satisfied, the unknown inputs and the uncertain model parameters are estimated online by the soft sensor using augmented nonlinear singular state observer. The riser reactor of fluid catalytic cracking unit is used as an example for analysis and simulation. With the catalyst circulation rate as the only unknown input without model error, one temperature sensor at the riser reactor outlet will ensure the correct estimation for the catalyst cir- culation rate. However, when uncertain model parameters also exist, additional temperature sensors must be used to ensure correct estimation for unknown inputs and uncertain model parameters of chemical processes.     

化工过程软测量建模方法研究进展

软测量仪表是解决化工过程中质量变量难以实时测量的重要手段。软测量仪表的核心问题是软测量建模。阐述了软测量建模与辨识和非线性建模的关系:质量变量和易测变量的动态关系存在于增量之间,辨识模型依赖于增量数据,软测量建模则是依赖于实测变量数据来获取这个动态关系;非线性建模建立了变量间的静态关系,忽略了对象动态特性,而软测量建模要兼顾对动态特性的表征。随着人们对过程特性的认识加深,软测量建模方法不断发展,经历了从机理建模到数据驱动建模,从线性建模到非线性建模,从静态建模到动态建模的过程。详细讨论了软测量建模的发展过程,众多建模方法的优缺点及适用情况和现在建模的热点,最后对软测量建模方法进行了总体展望。     

人工神经网络软测量仪表延迟时间处理及动态特性研究

采用BP和RBF网络,开发了人工神经网络软测量仪表软件,实现了不可测变量的在线观测。讨论并解决了延迟时间的确定与处理、动态特性的拟合等主要难点问题。利用三层BP网络辨识出非线性对象的延迟时间;采用将输出量引入到多层静态神经网络的入口和对输入数据进行衰减加权的方法,完成对系统动态特性的表征,使所开发的神经网络软测量仪表更真实地反映了系统的静态和动态性能,准确性高且有更好的适应性。     

基于辅助变量KNN分析的软测量建模方法

提出一种基于辅助变量最近邻（KNN）分析的软测量建模方法,该方法将KNN算法应用于辅助变量分类,根据分类结果,应用核主成分分析（KPCA）和支持向量回归机（SVR）相结合进行软测量建模。KNN分析独立于后继回归模型,却又直接影响模型结构,KPCA作为中间层,在KNN分类结果指导下提取不同类别包含辅助变量高阶信息的特征主元,然后使用SVR建立特征主元和主导变量之间的回归模型。用该方法建立粗汽油干点软测量模型,结果表明KNN-KPCA-SVR（KKS）模型的预测精度和泛化能力优于线性PLS、RBF核函数SVR和KPCA-SVM模型。     

基于神经网络的常压塔柴油凝点软测量的研究与应用

研究某炼油厂常压塔三线柴油凝点的软测量建模问题,分析过程变量对柴油凝点的影响。基于在线分析仪6min采样数据,利用前向网络和时延前向网络(TDNN)分别建立了三线柴油凝点的静态软测量模型和动态软测量模型,并结合在线分析仪对模型实现了在线修正。通过两种模型的仿真和在线实施效果,表明基于神经网络的软测量模型取得了较好的应用效果,而且动态模型的实施效果优于静态模型。     

A self-tuning control method for Wiener nonlinear systems and its application to process control problems

Many chemical processes can be modeled as Wiener models, which consist of a linear dynamic subsystem follow-ed by a static nonlinear block. In this paper, an effective discrete-time adaptive control method is proposed for Wiener nonlinear systems with uncertainties. The parameterization model is derived based on the inverse of the nonlinear function block. The adaptive control method is motivated by self-tuning control and is derived from a modified Clarke criterion function, which considers both tracking properties and control efforts. The un-certain parameters are updated by a recursive least squares algorithm and the control law exhibits an explicit form. The closed-loop system stability properties are discussed. To demonstrate the effectiveness of the obtained results, two groups of simulation examples including an application to composition control in a continuously stirred tank reactor (CSTR) system are studied.     

选择性集成LTDGPR模型的自适应软测量建模方法

随着时间的增加,传统时间差（TD）模型会出现性能显著下降的问题。为了提高TD模型的可靠性和预测精度,同时考虑过程的时滞特征,基于一种选择性集成策略,提出一种局部时间差高斯过程回归（LTDGPR）模型的自适应软测量建模方法。首先,提取出数据库中的时滞动态信息,对建模数据进行重构;然后,采取局部化策略对差分后的重构样本进行统计划分,得到LTDGPR模型集。对于新来的输入样本,选择部分泛化能力强的LTDGPR模型进行集成,估计出含一定时间差的主导变量动态偏移值;最后,基于TD模型思想对当前时刻主导变量值进行在线预测。通过脱丁烷塔过程的数据建模仿真研究,验证了所提方法的有效性和精度。     

基于广义状态观测器的催化裂化装置软仪表

与常规的输出校正软仪表不同,催化裂化装置软仪表的主导变量完全不可测,只能通过辅助变量进行在线校正,因此利用状态观测器构造催化裂化装置软仪表。催化裂化装置为指数1型广义非线性系统,理论分析证明,如果指数1型广义非线性系统在工作点线性化得到的广义线性变参数系统能检测,则可以通过线性化系统的在线极点配置来选取合适的状态观测器反馈增益阵,以确保广义状态观测器存在并在较大范围内是稳定的,从而保证软仪表对主导变量的在线估计值可以收敛于理论值。仿真结果表明,即使催化剂循环量为不可测输入变量,将其扩展为状态变量后,利用提升管反应器出口温度作为辅助变量进行在线校正,即可构成催化裂化装置软仪表完成对油品产率、催化剂循环量等不可测变量的在线估计,估计值能够稳定收敛到理论值并具有较好的动态性能。     

Application of online support vector regression for soft sensors

Soft sensors have been widely used in chemical plants to estimate process variables that are difficult to measure online. One of the crucial difficulties of soft sensors is that predictive accuracy drops due to changes in state of chemical plants. Characteristics of adaptive soft sensor models such as moving window models, just‐in‐time models and time difference models were previously discussed. The predictive accuracy of any traditional models decreases when sudden changes in processes occur. Therefore, a new soft sensor method based on online support vector regression (SVR) and the time variable was developed for constructing soft sensor models adaptive to rapid changes of relationships among process variables. A nonlinear SVR model with the time variable is updated with the most recent data. The proposed method was applied to simulation data and real industrial data, and achieved higher predictive accuracy than traditional ones even when time‐varying changes in process characteristics happen. © 2013 American Institute of Chemical Engineers AIChE J 60: 600–612, 2014     

Soft sensors model optimization and application for the refinery real-time prediction of toluene content

Industrial facilities nowadays show an increasing need for continuous measurements, monitoring and controlling many process variables. The on-line process analyzers, being the key indicators of process and product quality, are often unavailable or malfunction. This paper describes development of soft sensor models based on the real plant data that could replace an on-line analyzer when it is unavailable, or to monitor and diagnose an analyzer’s performance. Soft sensors for continuous toluene content estimation based on the real aromatic plant data are developed. The autoregressive model with exogenous inputs, output error, the nonlinear autoregressive model consisted of exogenous inputs and Hammerstein–Wiener models were developed. In case of complex real-plant processes a large number of model regressors and coefficients need to be optimized. To overcome an exhaustive trial-and-error procedure of optimal model regressor order determination, differential evolution optimization method is applied. In general, the proposed approach could be, of interest for the development of dynamic polynomial identification models. The performance of the models are validated on the real-plant data.