A challenge facing the pharmaceutical and chemical industries is how to understand and identify differences in process behaviour where a product is manufactured at two different sites. Three approaches based on multi-...
详细信息
Selection of the number of latent variables in partial least squares (PLS) is an important issue in process modelling. In this paper, the Bayesian Information Criterion (BIC) is used to establish a rule for the determ...
详细信息
Selection of the number of latent variables in partial least squares (PLS) is an important issue in process modelling. In this paper, the Bayesian Information Criterion (BIC) is used to establish a rule for the determination of the number of latent variables. Unlike Wold's R criterion, where the number of latent variables is determined by the prediction error sum of squares, the philosophy of the BIC rule is based on model accuracy and model parsimony. A simulation study and a practical application are used to demonstrate that BIC is a competitive alternative to Wold's R criterion for latent variable selection in PLS.
A nonlinear multiscale multivariate statistical processcontrol method is proposed to address fault detection and diagnosis issues at different scales in nonlinear processes. A kernel principal component analysis (KPC...
详细信息
The detection of process changes using a partial least squares (PLS) based monitoring scheme can be achieved through the interrogation of two metrics, Hotelling's T 2 and the Q-statistic. The Q-statistic has been ...
详细信息
The detection of process changes using a partial least squares (PLS) based monitoring scheme can be achieved through the interrogation of two metrics, Hotelling's T 2 and the Q-statistic. The Q-statistic has been shown to be insensitive to small changes in the process model parameters. In this paper, a modified statistic based on the local approach is proposed to detect changes in the model parameters in a PLS based monitoring scheme. The performance of the Q-statistic is compared with the modified statistic through their application to fault detection in a continuous stirred tank reactor.
Optimisation of fed-batch processes can be described as a constrained nonlinear end-point dynamic optimisation problem. Although iterative dynamic programming (IDP) is feasible, it is usually very time-consuming and v...
详细信息
Optimisation of fed-batch processes can be described as a constrained nonlinear end-point dynamic optimisation problem. Although iterative dynamic programming (IDP) is feasible, it is usually very time-consuming and very difficult to apply to on-line optimisation because of solving the non-linear differential-algebraic equations of the process model in each iteration. The replacement of a rigorous mechanistic model by an equivalent neural network (NN) model takes the advantage of high speed processing, since simulation with a NN model involves only a few non-iterative algebraic calculations. To use IDP algorithm for NN model based on-line re-optimisation, a modified algorithm is proposed and is called as iterative dynamic programming for discrete-time system ( IDP/DTS ). The novel IDP/DTS algorithm can obtain a reduction of many times in computational time compared to the conventional IDP algorithm. In this paper, an effective optimisation and control scheme for on-line re-optimisation of fed-batch processes is proposed based on NN models and the novel IDP/DTS algorithm. The proposed scheme is illustrated using simulation studies of an ethanol fermentation process.
Projection to Latent Structures (PLS) is a linear regression technique for nondynamic problems where the data is noisy, highly correlated and where there are a limited number of observations. Methodologies have been p...
详细信息
Projection to Latent Structures (PLS) is a linear regression technique for nondynamic problems where the data is noisy, highly correlated and where there are a limited number of observations. Methodologies have been proposed to integrate the nonlinear features within a linear PLS framework resulting in a non-linear algorithm. PLS has also been extended to include dynamic processes. This paper presents a non-linear dynamic PLS algorithm which incorporates polynomial or neural network functions that are integrated within the PLS algorithm through weight updating of the inner/outer models. The modelling capabilities are assessed through comparisons on a pH neutralisation process.
With the increasing take-up of PAT 1 by the pharma- and bio- industries there is a critical need for robust spectral calibrations for processes which are subject to the variations in physical properties such as sample...
详细信息
With the increasing take-up of PAT 1 by the pharma- and bio- industries there is a critical need for robust spectral calibrations for processes which are subject to the variations in physical properties such as sample compactness, surface topology, etc. The variation in the optical path-length materializing from the physical differences between samples may result in multiplicative light scattering influencing spectra in a nonlinear manner leading to the poor calibration performance. A new approach “Optical Path Length Estimation and Correction” overcomes the limitations of existing light scattering correction methods.
With a view to ensuring the validity of multivariate calibration models in the presence of temperature variations, a new methodology, individual contribution standardization (ICS), is proposed to correct for temperatu...
详细信息
With a view to ensuring the validity of multivariate calibration models in the presence of temperature variations, a new methodology, individual contribution standardization (ICS), is proposed to correct for temperature-induced spectral variations. The methodology was applied to shortwave NIR spectral data sets recorded at different temperatures. The results showed that ICS can almost eliminate temperature effects resulting in calibration models that exhibit good predictive performance. Compared with other methods, such as continuous piecewise direct standardization, ICS has the advantages of easy implementation, simple selection of the calibration model and less restrictions on the training samples.
A neural network based batch to batch optimal control strategy is proposed in this paper. To overcome the difficulty in developing mechanistic models for batch processes, neural network models are developed from proce...
详细信息
A neural network based batch to batch optimal control strategy is proposed in this paper. To overcome the difficulty in developing mechanistic models for batch processes, neural network models are developed from process operational data. The developed neural network model can only approximate the batch process and model plant mismatches usually exist. Thus the optimal control policy calculated based on a neural network model may not be optimal when applied to the true process. Due to the repetitive nature of batch processes, it is possible to improve the operation of the next batch using the information of the current and previous batch runs. A batch to batch optimal control strategy based on the linearization of the neural network model is proposed in this paper. Applications to a simulated batch polymerisation reactor demonstrate that the proposed method can improve process performance from batch to batch in the presence of model plant mismatches and unknown disturbances.
暂无评论