Improved Process Monitoring Using Nonlinear Principal Component Models

This paper presents two new approaches for use in complete process monitoring. The firstconcerns the identification of nonlinear principal component models. This involves the application of linear
principal component analysis (PCA), prior to the identification of a modified autoassociative neural network (AAN) as the required nonlinear PCA (NLPCA) model. The benefits are that (i) the number of the reduced set of linear principal components (PCs) is smaller than the number of recorded process variables, and (ii) the set of PCs is better conditioned as redundant information is removed. The result is a new set of input data for a modified neural representation, referred to as a T2T network. The T2T NLPCA model is then used for complete process monitoring, involving fault detection, identification and isolation. The second approach introduces a new variable reconstruction algorithm, developed from the T2T NLPCA model. Variable reconstruction can enhance the findings of the contribution charts still widely used in industry by reconstructing the outputs from faulty sensors to produce more accurate fault isolation. These ideas are illustrated using recorded industrial data relating to developing cracks in an industrial glass melter process. A comparison of linear and nonlinear models, together with the combined use of contribution charts and variable reconstruction, is presented.

A new Jacobian matrix for optimal learning of single-layer neural networks

This paper investigates the learning of a wide class of single-hidden-layer feedforward neural networks (SLFNs) with two sets of adjustable parameters, i.e., the nonlinear parameters in the hidden nodes and the linear output weights. The main objective is to both speed up the convergence of second-order learning algorithms such as Levenberg-Marquardt (LM), as well as to improve the network performance. This is achieved here by reducing the dimension of the solution space and by introducing a new Jacobian matrix. Unlike conventional supervised learning methods which optimize these two sets of parameters simultaneously, the linear output weights are first converted into dependent parameters, thereby removing the need for their explicit computation. Consequently, the neural network (NN) learning is performed over a solution space of reduced dimension. A new Jacobian matrix is then proposed for use with the popular second-order learning methods in order to achieve a more accurate approximation of the cost function. The efficacy of the proposed method is shown through an analysis of the computational complexity and by presenting simulation results from four different examples.

A novel continuous forward algorithm for RBF neural modelling

A continuous forward algorithm (CFA) is proposed for nonlinear modelling and identification using radial basis function (RBF) neural networks. The problem considered here is simultaneous network construction and parameter optimization, well-known to be a mixed integer hard one. The proposed algorithm performs these two tasks within an integrated analytic framework, and offers two important advantages. First, the model performance can be significantly improved through continuous parameter optimization. Secondly, the neural representation can be built without generating and storing all candidate regressors, leading to significantly reduced memory usage and computational complexity. Computational complexity analysis and simulation results confirm the effectiveness.

Improved reliability in diagnosing faults using multivariate statistics

This paper analyses multivariate statistical techniques for identifying and isolating abnormal process behaviour. These techniques include contribution charts and variable reconstructions that relate to the application of principal component analysis (PCA). The analysis reveals firstly that contribution charts produce variable contributions which are linearly dependent and may lead to an incorrect diagnosis, if the number of principal components retained is close to the number of recorded process variables. The analysis secondly yields that variable reconstruction affects the geometry of the PCA decomposition. The paper further introduces an improved variable reconstruction method for identifying multiple sensor and process faults and for isolating their influence upon the recorded process variables. It is shown that this can accommodate the effect of reconstruction, i.e. changes in the covariance matrix of the sensor readings and correctly re-defining the PCA-based monitoring statistics and their confidence limits. (c) 2006 Elsevier Ltd. All rights reserved.

Genetic algorithms for local controller network construction

Local Controller Networks (LCNs) provide nonlinear control by interpolating between a set of locally valid, subcontrollers covering the operating range of the plant. Constructing such networks typically requires knowledge of valid local models. This paper describes a new genetic learning approach to the construction of LCNs directly from the dynamic equations of the plant, or from modelling data. The advantage is that a priori knowledge about valid local models is not needed. In addition to allowing simultaneous optimisation of both the controller and validation function parameters, the approach aids transparency by ensuring that each local controller acts independently of the rest at its operating point. It thus is valuable for simultaneous design of the LCNs and identification of the operating regimes of an unknown plant. Application results from a highly nonlinear pH neutralisation process and its associated neural network representation are utilised to illustrate these issues.

Constructing networks of continuous-time velocity-based models

A conventional local model (LM) network consists of a set of affine local models blended together using appropriate weighting functions. Such networks have poor interpretability since the dynamics of the blended network are only weakly related to the underlying local models. In contrast, velocity-based LM networks employ strictly linear local models to provide a transparent framework for nonlinear modelling in which the global dynamics are a simple linear combination of the local model dynamics. A novel approach for constructing continuous-time velocity-based networks from plant data is presented. Key issues including continuous-time parameter estimation, correct realisation of the velocity-based local models and avoidance of the input derivative are all addressed. Application results are reported for the highly nonlinear simulated continuous stirred tank reactor process.

Comparative analysis of the DC performance of DG MOSFETs on highly-doped and near-intrinsic silicon layers

A comparison of dc characteristics of fully depleted double-gate (DG) MOSFETs with respect to low-power circuit applications and device scaling has been performed by two-dimensional device simulation. Three different DG MOSFET structures including a conventional N+ polysilicon gate device with highly doped Si layer, an asymmetrical P+/N+ polysilicon gate device with low doped Si layer and a midgap metal gate device with low doped Si layer have been analysed. It was found that DG MOSFET with mid-gap metal, gates yields the best dc parameters for given off-state drain leakage current and highest immunity to the variation of technology parameters (gate length, gate oxide thickness and Si layer thickness). It is also found that an asymmetrical P+/N+ polysilicon gate DG MOSFET design offers comparable dc characteristics, but better parameter immunity to technology tolerances than a conventional DG MOSFET. (C) 2004 Elsevier Ltd. All rights reserved.

An empirical study of green supply chain management practices amongst UK manufacturers

Purpose: The purpose of this paper is to examine the extent and nature of greening the supply chain (SC) in the UK manufacturing sector; and the factors that influence the breadth and depth of this activity.

Design/methodology/approach: Based on the findings from a sample of manufacturing organisations drawn from the membership of The Chartered Institute for Purchasing and Supply. Data are collected using a questionnaire, piloted and pre-tested before distribution with responses from 60 manufacturing companies.

Findings: On average manufacturers perceive the greatest pressure to improve environmental performance through legislation and internal drivers (IDs). The least influential pressures are related to societal drivers and SC pressures from individual customers. Green supply chain management (GSCM) practices amongst this “average” group of UK manufacturing organisations are focusing on internal, higher risk, descriptive activities, rather than proactive, external engagement processes. Environmental attitude (EA) is a key predictor of GSCM activity and those organisations that have a progressive attitude are also operationally very active. EA shows some relationship to legislative drivers but other factors are also influential. Operational activity may also be moderated by organisational contingencies such as risk, size, and nationality.

Research limitations/implications: The main limitation to this paper is the relatively small manufacturing sample.

Practical implications: This paper presents a series of constructs that identify GSCM operational activities companies to benchmark themselves against. It suggests which factors are driving these operational changes and how industry contingencies may be influential.

Originality/value: This paper explores what is driving environmental behaviour amongst an “average” sample of manufacturers, what specific management practices take place and the relationships between them.

Keywords: Manufacturing industries, Environmental management, Supply chain management, Sustainable development, United Kingdom
Paper type: Research paper

Plant-wide predictive control for a thermal power plant based on a physical plant model

A constrained non-linear, physical model-based, predictive control (NPMPC) strategy is developed for improved plant-wide control of a thermal power plant. The strategy makes use of successive linearisation and recursive state estimation using extended Kalman filtering to obtain a linear state-space model. The linear model and a quadratic programming routine are used to design a constrained long-range predictive controller One special feature is the careful selection of a specific set of plant model parameters for online estimation, to account for time-varying system characteristics resulting from major system disturbances and ageing. These parameters act as nonstationary stochastic states and help to provide sufficient degrees-of-freedom to obtain unbiased estimates of controlled outputs. A 14th order non-linear plant model, simulating the dominant characteristics of a 200 MW oil-fired pou er plant has been used to test the NPMPC algorithm. The control strategy gives impressive simulation results, during large system disturbances and extremely high rate of load changes, right across the operating range. These results compare favourably to those obtained with the state-space GPC method designed under similar conditions.

Sampled-data gain scheduling of continuous LTV plants

This paper discusses the design of gain- scheduled sampled-data controllers for continuous-time polytopic linear parameter-varying systems. The scheduling variables are assumed to available only at the sampling instants, and a bound on the time-variation of the scheduling parameters is also assumed to be known. The resultant gain-scheduled controllers improve the maximum achieveable delay bound over previous constant-gain ones in the literature.

Convergence and tracking analysis of a variable normalised LMF (XE-NLMF) algorithm

The least-mean-fourth (LMF) algorithm is known for its fast convergence and lower steady state error, especially in sub-Gaussian noise environments. Recent work on normalised versions of the LMF algorithm has further enhanced its stability and performance in both Gaussian and sub-Gaussian noise environments. For example, the recently developed normalised LMF (XE-NLMF) algorithm is normalised by the mixed signal and error powers, and weighted by a fixed mixed-power parameter. Unfortunately, this algorithm depends on the selection of this mixing parameter. In this work, a time-varying mixed-power parameter technique is introduced to overcome this dependency. A convergence analysis, transient analysis, and steady-state behaviour of the proposed algorithm are derived and verified through simulations. An enhancement in performance is obtained through the use of this technique in two different scenarios. Moreover, the tracking analysis of the proposed algorithm is carried out in the presence of two sources of nonstationarities: (1) carrier frequency offset between transmitter and receiver and (2) random variations in the environment. Close agreement between analysis and simulation results is obtained. The results show that, unlike in the stationary case, the steady-state excess mean-square error is not a monotonically increasing function of the step size. (c) 2007 Elsevier B.V. All rights reserved.