In soft sensor field, just-in-time learning (JITL) is an effective approach tomodel nonlinear and time varying processes. However,most similarity criterions in JITL are computed in the input space onlywhile ignoring important output information,whichmay lead to inaccurate construction of relevant sample set. To solve this problem, we propose a novel supervised feature extraction method suitable for the regression problemcalled supervised local and non-local structure preserving projections (SLNSPP), in which both input and output information can be easily and effectively incorporated through a newly defined similarity index. The SLNSPP can not only retain the virtue of locality preserving projections but also prevent faraway points from nearing after projection, which endues SLNSPP with powerful discriminating ability. Such two good properties of SLNSPP are desirable for JITL as they are expected to enhance the accuracy of similar sample selection. Consequently, we present a SLNSPP-JITL framework for developing adaptive soft sensor, including a sparse learning strategy to limit the scale and update the frequency of database. Finally, two case studies are conducted with benchmark datasets to evaluate the performance of the proposed schemes. The results demonstrate the effectiveness of LNSPP and SLNSPP.

The p-xylene (PX) oxidation process is of great industrial importance because of the strong demand of the global polyester fiber. A steady-state model of the PX oxidation has been studied by many researchers. In our previous work, a novel industrial p-xylene oxidation reactor model using the free radical mechanism based kinetics has been developed. However, the disturbances such as production rate change, feed composition variability and reactor temperature changes widely exist in the industry process. In this paper, dynamic simulation of the PX oxidation reactorwas designed by Aspen Dynamics and used to develop an effective plantwide control structure, which was capable of effectively handling the disturbances in the load and the temperature of the reactor. Step responses of the control structure to the disturbances were shown and served as the foundation of the smooth operation and advanced control strategy of this process in our future work.

Control performance monitoring has attracted great attention in both academia and industry over the past two decades. However, most research efforts have been devoted to the performance monitoring of linear control systems, without considering the pervasive nonlinearities (e.g. valve stiction) present inmost industrial control systems. In thiswork, a novel probability distribution distance based index is proposed tomonitor the performance of non-linear control systems. The proposedmethod uses Hellinger distance to evaluate change of control system performance. Several simulation examples are given to illustrate the effectiveness of the proposed method.

Conventional principal component analysis (PCA) can obtain low-dimensional representations of original data space, but the selection of principal components (PCs) based on variance is subjective, which may lead to information loss and poormonitoring performance. To address dimension reduction and information preservation simultaneously, this paper proposes a novel PC selection scheme named full variable expression.On the basis of the proposed relevance of variables with each principal component, key principal components can be determined. All the key principal components serve as a low-dimensional representation of the entire original variables, preserving the information of original data spacewithout information loss.A squaredMahalanobis distance,which is introduced as themonitoring statistic, is calculated directly in the key principal component space for fault detection. To test the modeling and monitoring performance of the proposed method, a numerical example and the Tennessee Eastman benchmark are used.

Low pressure chemical vapor deposition (LPCVD) is one of themost important processes during semiconductor manufacturing. However, the spatial distribution of internal temperature and extremely few samples makes it hard to build a good-quality model of this batch process. Besides, due to the properties of this process, the reliability of the model must be taken into consideration when optimizing the MVs. In this work, an optimal design strategy based on the self-learning Gaussian processmodel (GPM)is proposed to control this kind of spatial batch process. The GPMis utilized as the internalmodel to predict the thicknesses of thin films on all spatial-distributed wafers using the limited data. Unlike the conventional model based design, the uncertainties of predictions provided by GPM are taken into consideration to guide the optimal design of manipulated variables so that the designing can be more prudent. Besides, the GPM is also actively enhanced using as little data as possible based on the predictive uncertainties. The effectiveness of the proposed strategy is successfully demonstrated in an LPCVD process.

The catalytic activity of cation exchange resins will be continuously reduced with its use time in a condensation reaction for bisphenol A (BPA). For online estimation of the catalytic activity, a catalytic deactivation model is studied for a production plant of BPA, state equation and observation equation are proposed based on the axial temperature distribution of the reactor and the acetone concentration at reactor entrance. A hybrid model of state equation is constructed for improving estimation precision. The unknown parameters in observation equation are calculated with sample data. The unscented Kalman filtering algorithm is then used for on-line estimation of the catalytic activity. The simulation results show that this hybrid model has higher estimation accuracy than the mechanism model and the model is effective for production process of BPA.

Complex processes often work with multiple operation regions, it is critical to develop effective monitoring approaches to ensure the safety of chemical processes. In this work, a discriminant local consistency Gaussianmixture model (DLCGMM) for multimode process monitoring is proposed for multimode process monitoring by integrating LCGMMwith modified local Fisher discriminant analysis (MLFDA).Different fromFisher discriminant analysis (FDA) that aims to discover the global optimal discriminant directions, MLFDA is capable of uncovering multimodality and local structure of the data by exploiting the posterior probabilities of observations within clusters calculated fromthe results of LCGMM. This may enableMLFDA to capturemoremeaningful discriminant information hidden in the high-dimensional multimode observations comparing to FDA. Contrary to most existing multimode process monitoring approaches, DLCGMMperforms LCGMMandMFLDA iteratively, and the optimal subspaces with multi-Gaussianity and the optimal discriminant projection vectors are simultaneously achieved in the framework of supervised and unsupervised learning. Furthermore, monitoring statistics are established on each cluster that represents a specific operation condition and two global Bayesian inference-based faultmonitoring indexes are established by combining with all themonitoring results of all clusters. The efficiency and effectiveness of the proposed method are evaluated through UCI datasets, a simulated multimode model and the Tennessee Eastman benchmark process.

Formeasurement of component content in the extraction and separation process of praseodymium/neodymium (Pr/Nd), a softmeasurement method was proposed based on modeling of ion color features,which is suitable for fast estimation of component content in production field. Feature analysis on images of the solution is conducted, which are captured from Pr/Nd extraction/separation field. H/S components in the HSI color space are selected as model inputs, so as to establish the least squares support vector machine (LSSVM) model for Nd (Pr) content, while the model parameters are determined with the GA algorithm. To improve the adaptability of the model, the adaptive iteration algorithmis used to correct parameters of the LSSVMmodel, on the basis of model correction strategy and new sample data. Using the field data collected from rare earth extraction production, predictive methods for component content and comparisons are given. The results indicate that the proposed method presents good adaptability and high prediction precision, so it is applicable to the fast detection of element content in the rare earth extraction.

Alarmflood is one of themain problems in the alarmsystems of industrial process. Alarmroot-cause analysis and alarmprioritization are good for alarmflood reduction. This paper proposes a systematic rationalization method for multivariate correlated alarms to realize the root cause analysis and alarm prioritization. An information fusion based interpretive structural model is constructed according to the data-driven partial correlation coefficient calculation and process knowledge modification. This hierarchical multi-layer model is helpful in abnormality propagation path identification and root-cause analysis. Revised Likert scale method is adopted to determine the alarmpriority and reduce the blindness of alarmhandling. As a case study, the Tennessee Eastman process is utilized to showthe effectiveness and validity of proposed approach. Alarmsystem performance comparison shows that our rationalization methodology can reduce the alarmflood to some extent and improve the performance.

The paper describes a closed-loop system identification procedure for hybrid continuous-time Box-Jenkins models and demonstrates howit can be used for IMC based PID controller tuning. An instrumental variable algorithmis used to identify hybrid continuous-time transfer function models of the Box-Jenkins formfromdiscretetime prefiltered data, where the process model is a continuous-time transfer function, while the noise is represented as a discrete-time ARMA process. A novel penalizedmaximum-likelihood approach is used for estimating the discrete-time ARMA process and a circulatory noise elimination identification method is employed to estimate process model. The input-output data of a process are affected by additive circulatory noise in a closedloop. The noise-free input-output data of the process are obtained using the proposed method by removing these circulatory noise components. The process model can be achieved by using instrumental variable estimation method with prefiltered noise-free input-output data. The performance of the proposed hybrid parameter estimation scheme is evaluated by the Monte Carlo simulation analysis. Simulation results illustrate the efficacy of the proposed procedure. The methodology has been successfully applied in tuning of IMCbased flowcontroller and a practical application demonstrates the applicability of the algorithm.

To dealwith colored noise and unexpected load disturbance in identification of industrial processes with time delay, a bias-eliminated iterative least-squares (ILS) identification method is proposed in this paper to estimate the output error model parameters and time delay simultaneously. An extended observation vector is constructed to establish an ILS identification algorithm. Moreover, a variable forgetting factor is introduced to enhance the convergence rate of parameter estimation. For consistent estimation, an instrumental variable method is given to deal with the colored noise. The convergence and upper bound error of parameter estimation are analyzed. Two illustrative examples are used to show the effectiveness and merits of the proposed method.

This paper focuses on resolving the identification problemof a neuro-fuzzymodel (NFM) applied in batch processes. A hybrid learning algorithm is introduced to identify the proposed NFM with the idea of auxiliary error model and the identification principle based on the probability density function (PDF). The main contribution is that the NFM parameter updating approach is transformed into the shape control for the PDF ofmodeling error.More specifically, a virtual adaptive control systemis constructed with the aid of the auxiliary errormodel and then the PDF shape control idea is used to tune NFM parameters so that the PDF of modeling error is controlled to follow a targeted PDF, which is in Gaussian or uniform distribution. Examples are used to validate the applicability of the proposed method and comparisons are made with the minimum mean square error based approaches.

Strong mechanical vibration and acoustical signals of grinding process contain useful information related to load parameters in ball mills. It is a challenge to extract latent features and construct soft sensor model with high dimensional frequency spectra of these signals. This paper aims to develop a selective ensemble modeling approach based on nonlinear latent frequency spectral feature extraction for accurate measurement of material to ball volumeratio. Latent features are first extracted fromdifferent vibrations and acoustic spectral segments by kernel partial least squares. Algorithms of bootstrap and least squares support vector machines are employed to produce candidate sub-models using these latent features as inputs. Ensemble sub-models are selected based on genetic algorithm optimization toolbox. Partial least squares regression is used to combine these sub-models to eliminate collinearity among their prediction outputs. Results indicate that the proposedmodeling approach has better prediction performance than previous ones.

Interpretative structuralmodel (ISM) can transformamultivariate probleminto several sub-variable problems to analyze a complex industrial structure in a more efficient way by building a multi-level hierarchical structure model. To build an ISM of a production system, the partial correlation coefficient method is proposed to obtain the adjacency matrix,which can be transformed to ISM. According to estimation of correlation coefficient, the result can give actual variable correlations and eliminate effects of intermediate variables. Furthermore, this paper proposes an effective approach using ISMto analyze themain factors and basic mechanisms that affect the energy consumption in an ethylene production system. The case study shows that the proposed energy consumption analysis method is valid and efficient in improvement of energy efficiency in ethylene production.

With diversified requirements and varying manufacturing environments, the optimal production planning for a steelmill becomes more flexible and complicated. The flexibility provides operators with auxiliary requirements through an implementable integrated production planning. In this paper, a mixed-integer nonlinear programming (MINLP) model is proposed for the optimal planning that incorporates various manufacturing constraints and flexibility in a steel plate mill. Furthermore, two solution strategies are developed to overcome theweakness in solving the MINLP problem directly. The first one is to transformthe original MINLP formulation to an approximate mixed integer linear programming using a classic linearization method. The second one is to decompose the originalmodel using a branch-and-bound based iterative method. Computational experiments on various instances are presented in terms of the effectiveness and applicability. The result shows that the second method performs better in computational efforts and solution accuracy.

This paper presents a nonlinear model predictive control (NMPC) approach based on support vector machine (SVM) and genetic algorithm (GA) for multiple-input multiple-output (MIMO) nonlinear systems. Individual SVM is used to approximate each output of the controlled plant. Then the model is used in MPC control scheme to predict the outputs of the controlled plant. The optimal control sequence is calculated using GA with elite preserve strategy. Simulation results of a typical MIMO nonlinear system show that this method has a good ability of set points tracking and disturbance rejection.

In this paper, a two-layer hierarchical structure of optimization and control for polypropylene grade transition was raised to overcome process uncertain disturbances that led to the large deviation between the open-loop reference trajectory and the actual process. In the upper layer, the variant time scale based control vector parametric methods (VTS-CVP) was used for dynamic optimization of transition reference trajectory, while nonlinear model predictive controller (NMPC) based on closed-loop subspace and piece-wise linear (SSARX-PWL) model in the lower layer was tracking to the reference trajectory from the upper layer for overcoming high-frequency disturbances. Besides, mechanism about trajectory deviation detection and optimal trajectory updating onlinewere introduced to ensure a smooth transition for the entire process. The proposed method was validated with the real data from an industrial double-loop propylene polymerization reaction process with developed dynamic mechanismmathematicalmodel.

Comparing with continuous production process, unsteady operation process, such as startup and shutdown, tends to abnormal situations due to a large number of operations of operators and dynamic state changes involved. To guarantee a safe operation, process hazard analysis (PHA) is very important to proactively identify the potential safety problems. In the chemical process industry, hazard and operability (HAZOP) analysis is the mostwidely used method. In this paper, based on proposed qualitative simulation and inferencemethod, an automatic HAZOP analysis method for unsteady operation processes is proposed. Mass transfer and relationships among process variables are expressed by Petri net-directed graphmodel based fuzzy logic. Operating procedure is expressed according to a formal expression. Possible operation deviations from normal operating procedure are identified by using a group of guidewords. Hazards are identified automatically by qualitative simulation and inference when wrong operation process is performed. The method is validated by a rectification column system.

The control objective of the forced-circulation evaporation process of alumina production is not only to avoid large fluctuations of the level, but also to ensure the product density to track its setpoint quickly. Due to the existence of strong coupling between the level loop and the product density loop, and high nonlinearities in the process, the conventional control strategy cannot achieve satisfactory control performance, and thus the production demand cannot bemet. In this paper, an intelligent decoupling PID controller including conventional PID controllers, a decoupling compensator and a neural feedforward compensator is proposed. The parameters of such controller are determined by generalized predictive control law. Real-time experiment results show that the proposed method can decouple the loops effectively and thus improve the evaporation efficiency.

The computation burden in themodel-based predictive control algorithmis heavywhen solving QR optimization with a limited sampling step, especially for a complicated system with large dimension. A fast algorithm is proposed in this paper to solve this problem, inwhich real-time values are modulated to bit streams to simplify the multiplication. In addition, manipulated variables in the prediction horizon are deduced to the current control horizon approximately by a recursive relation to decrease the dimension of QR optimization. The simulation results demonstrate the feasibility of this fast algorithm for MIMO systems.

Smallmodular reactors (SMRs) are beneficial in providing electricity power safely and viable for specific applications such as seawater desalination and heat production. Due to its inherent safety feature, the modular high temperature gas-cooled reactor (MHTGR) is considered as one of the best candidates for SMR-based nuclear power plants. Since its dynamics presents high nonlinearity and parameter uncertainty, it is necessary to develop adaptive power-level control, which is beneficial to safe, stable, and efficient operation of MHTGR and is easy to be implemented. In this paper, based on the physically-based control design approach, an adaptive outputfeedback power-level control is proposed for MHTGRs. This control can guarantee globally bounded closedloop stability and has a simple form.Numerical simulation results showthe correctness of the theoretical analysis and satisfactory regulation performance of this control.