Julian Morris

Newcastle University, School of Chemical Engineering and Advanced Materials, Emeritus

Followers

Following

Co-authors

Public Views

Address: Newcastle

less

Interests

Uploads

Papers by Julian Morris

Artificial Neural Networks: -A Panacea to Modelling Problems?

by Ming Tham and Julian Morris

Hype has played a significant role in the history of artificial neural network research. From the... more Hype has played a significant role in the history of artificial neural network research. From the initial recognition of the potential for networks to approximate non-linear functions some quite exaggerated claims have been an unwelcome accompaniment to research developments. Results from both simulation studies and real process applications indicated that even simple network architectures appeared to possess powerful non-linear process modelling capabilities that provided easy and quick practical solutions to complex problems Optimism grew and the pragmatic solution was borne. In contrast, the structure of a neural network based model was also being considered generic in the sense that little prior knowledge of the process was required. Unlike ARMAX and NARMAX approaches the methodology has been attributed the potential of accurately describing the behaviour of extremely complex systems. Claims that the technique offered a panacea to all modelling problems surfaced. This paper cons...

Knowledge Based Process Supervisory Control

by Ming Tham and Julian Morris

Artificial neural networks and their applications to power systems—a bibliographical survey

by Ming Tham and Julian Morris

Electric Power Systems Research, 1993

Artificial neural networks (ANNs), representing computational paradigms based on a biological met... more

On-line multivariable adaptive control of a binary distillation column

by Ming Tham and Julian Morris

The Canadian Journal of Chemical Engineering, 1991

An experimental evaluation of the simultaneous control of top and bottom product compositions of ... more An experimental evaluation of the simultaneous control of top and bottom product compositions of a binary distillation column utilizing multi-variable self-tuning control algorithms is presented. The study was carried out using an 8-tray, 22.86 cm diameter methanol-water pilot scale column with continuous capacitance analysis of top product composition and bottom composition analyzed on a 3 minute cycle, by a gas chromatograph. Column control is studied for +25 % step disturbances in feed flow rate. Terminal composition regulation using both 'positional' and 'incremental' forms of a generalized minimum variance self-tuning control algorithm is compared with that achieved using a conventional digital PIIPID multiloop control strategy.

Download

Qualitative modelling-an application to supervisory control of a distillation column

by Ming Tham and Julian Morris

Proceedings of the 1992 IEEE International Symposium on Intelligent Control, 1992

ABSTRACT The authors examine the design and implementation of a knowledge based system. They inve... more ABSTRACT The authors examine the design and implementation of a knowledge based system. They investigate certain aspects of the knowledge representation problem, concentrating particularly on the use of qualitative modeling in representing deep knowledge. A novel qualitative modeling framework that draws upon established ideas, as well as some of the basic concepts of control theory, is presented. Some of the capabilities of the method were explored by applying it within a supervisory system for a simulated distillation column. Details of the application and the results of demonstration runs are presented

Artificial neural network based control

by Ming Tham and Julian Morris

ABSTRACT In the chemical process industry although most systems possess non-linear characteristic... more ABSTRACT In the chemical process industry although most systems possess non-linear characteristics, control algorithms are synthesised based upon linear approximations. In some process situations, however, the use of a non-linear control strategy may impart operational advantages. In this contribution a new formulation of a non-linear predictive controller is proposed. The algorithm follows a model based approach where the nominal model for control algorithm synthesis is an artificial neural network. This type of model structure can be considered generic in the sense that little prior knowledge of the process is required. Unlike other commonly used black box approaches, a neural network based process model has the potential to describe more concisely the behaviour of complex process dynamics. Results are presented from application of the artificial neural network based controller to an exothermic chemical reactor and binary distillation column

Soft-sensors for process estimation and inferential control

by Ming Tham and Julian Morris

Journal of Process Control, 1991

This paper presents two adaptive estimators (software based sensors or 'soft-sensors') for inferr... more This paper presents two adaptive estimators (software based sensors or 'soft-sensors') for inferring process outputs that are subject to large measurement delays, from other (secondary) outputs which may be sampled more rapidly. In other words, these estimators utilize plant data sampled at different rates. The parameters of the estimators can be continuously estimated and updated on-line, thus enabling the tracking of slow variations in process characteristics. The estimators employ either an input-output or a state space process description as the starting points for algorithm synthesis. In contrast to mechanistic model-based estimators such as Kalman filters, the proposed adaptive techniques require minimal design effort. The key contribution of the paper is thus the formulation of applications independent, adaptive multi-rate algorithms, which can provide accurate estimates of infrequently measured process outputs, from other more rapidly sampled secondary outputs. Theoretical developments are supported by results of recent applications to a variety of industrial scale processes: estimation of biomass concentration in an industrial mycelial fermentation; top product composition of a large industrial distillation tower and melt flow index on an industrial polymerization reactor. Measurements from established instruments such as off-gas carbon dioxide in the fermenter; overheads temperature in the distillation column and hydrogen concentration in the reactor were used as the secondary variables for the respective processes. The range of the applications is an indication of the utility of the techniques. A significant improvement in overall process control performance is also possible when estimated plant outputs, rather than the infrequently obtained measurements, are used for feedback control. This is demonstrated by non-linear simulation studies.

Download

Multivariable and multirate self-tuning control: a distillation column case study

by Ming Tham and Julian Morris

IEE Proceedings D Control Theory and Applications, 1991

This paper is concerned with the evaluation of self-tuning control algorithms for the multivariab... more This paper is concerned with the evaluation of self-tuning control algorithms for the multivariable control of distillation columns. Effective distillation control remains a key concern of industry because of the high energy consumption associated with distillation processes. The results presented here are taken from a continuing programme of investigations aimed at improving distillation column control performance. The performance of several multivariable self-tuning strategies is evaluated by online application to a pilot-scale binary distillation column which is subjected to disturbances of f25% step changes in feed flow rate. The performance of the multivariable algorithms is compared with that achieved using conventional digital multiloop PI/PID control. The results have demonstrated that use of multivariable self-tuning control, in particular multirate-multivariable selftuning control, can provide better regulatory performance for feed flow rate disturbances than can be achieved using a multiloop PI/PID strategy. Paper 7632D (C8), received 8th August 1989 Dr. Tham and Prof. Morris are with the Department of Chemical and Process Engineering, University of Newcastle upon Tyne, Newcastle upon Tyne NE1 7RU, United Kingdom F. Vagi is with Shell

Download

Adaptive inferential control

by Ming Tham and Julian Morris

IEE Colloquium on Adaptive Controllers in Practice, 1996

A procedure for determining the topology of multilayer feedforward neural networks

by Ming Tham and Julian Morris

Neural Networks, 1994

Thts contrtbutton describes a procedure for determmmg the opttmal topology of a statw three-layer... more Thts contrtbutton describes a procedure for determmmg the opttmal topology of a statw three-layer neural network The method ts based on a canomcal decomposttion techmque that estabhshes a hnk between the number of neurons m each htdden layer and the dtmensions of the subspaces of the canomcal decomposmon. It ensures that the structure ts suffictently complex to characterise the process being modelled by the network, and also the untcity of the approxtmatton A practtcal procedure to tmplement this method is then outhned and applied to both stmulated and real process data Keywords--Neural network topology, Canonical form, Number of neurons.

Download

Artificial neural networks in process estimation and control

by Ming Tham and Julian Morris

Automatica, 1992

In this contribution, the suitability of the artificial neural network methodology for solving so... more In this contribution, the suitability of the artificial neural network methodology for solving some process engineering problems is discussed. First the concepts involved in the formulation of artificial neural networks are presented. Next the suitability of the technique to provide estimates of difficult to measure quality variables is demonstrated by application to industrial data. Measurements from established instruments are used as secondary variables for estimation of the "primary" quality variables. The advantage of using these estimates for feedback control is then demonstrated. The possibility of using neural network models directly within a model-based predictive control strategy is also considered, making use of an on-line optimization routine to determine the future inputs that will minimize the deviations between the desired and predicted outputs. Control is implemented in a receding horizon fashion. Application of the predictive controller to a nonlinear distillation system is used to indicate the potential of the neural network based control philosophy. *

Download

Extended Generalised Minimum Variance Multivariable Self-Tuning Control

by Ming Tham and Julian Morris

This paper examines the extension of a well known multivariable self-tuning algorithm to include ... more

Download

Artificial neural network based multivariable predictive control

by Ming Tham and Julian Morris

… Neural Networks, 1991 …, 1991

... to determine the sequence of controls: ui(t+io), io = 0. .... N $=l, ... NL Sfep VI Implement... more ... to determine the sequence of controls: ui(t+io), io = 0. .... N $=l, ... NL Sfep VI Implement ui ... as many systems are characterised by relatively large time constants and correspondingly large sample times this may not ... Simal&amp;amp;amp; Svs., 2.303-314 Wwg, 2.. MT Tham and AJ Morris (1991). ...

Bioprocess applications of model-based estimation techniques

by Ming Tham and Julian Morris

Journal of Chemical Technology & Biotechnology, 2007

Abstract: The last decade has seen the development of a number of approaches for estimating those... more

Towards improved penicillin fermentation via artificial neural networks

by Ming Tham and Julian Morris

Computers & Chemical Engineering, 1992

ABSTRACT Despite extensive research efforts in biosensor technology, effective supervision and co... more ABSTRACT Despite extensive research efforts in biosensor technology, effective supervision and control of bioprocess systems still remains a formidable task. However, the inference of important biological process variables from existing on-line measurements provides one means of easing the burden. Inferencing techniques are primarily based upon sound process models, which for non-linear bioprocess systems can be problematic to derive. The ability of artificial neural networks to learn essential process non-linearities from plant data may provide a means by which to assist in estimator development. This paper investigates this prospect by considering the construction of artificial network-based biomass and penicillin estimators for on-line application to an industrial fermentation. Results from on- line industrial site tests are presented.

An application of qualitative modelling in an intelligent process supervisory system

by Ming Tham and Julian Morris

Proceedings of IEEE International Conference on Control and Applications, 1993

ABSTRACT This paper describes the progress that has been made in this area. The ideas of qualitat... more ABSTRACT This paper describes the progress that has been made in this area. The ideas of qualitative systems theory are extended to qualitative transfer function (QTF) models, and are then used to analyse the properties of a detailed QTF model of a distillation process. It is shown that these analytical tools can prove extremely useful in developing such models. Results from examples showing how the qualitative model can be used in an intelligent supervisory system are also presented

A comparison of adaptive estimation with neural based techniques for bioprocess application

by Ming Tham and Julian Morris

American Control …, 1990

... a demaingeonment for reliable, stable and noise femeasurement Such consderatios often lead to... more

Process modelling for intelligent control

by Ming Tham and Julian Morris

Engineering Applications of Artificial Intelligence, 1992

ABSTRACT This contribution considers the problem of knowledge representation in intelligent contr... more ABSTRACT This contribution considers the problem of knowledge representation in intelligent control systems: the kind of knowledge that is required and how this may be encapsulated within an application framework. It is argued that rule-base techniques need to be supplemented by other methods in order to express certain pertinent aspects of the domain. After a brief discussion of qualitative modelling techniques, attention is focused upon numerical models and a relatively new qualitative modelling approach, Qualitative Transfer Functions.The effectiveness of the latter model forms as repositories of deep knowledge are evaluated by application to a simulated distillation plant. The results indicate that although numerical models can provide accurate input-output representations, the integrated framework offered by Qualitative Transfer Functions is capable of carrying more information relevant to decision-making systems.

Optimising control of fermentation processes

by Ming Tham, Chandrasekhar Kambhampati, and Julian Morris

Control Theory and …, 1992

... is well defined on a, (ii) There is at least one cluster point of the sequence {d} generated ... more ... is well defined on a, (ii) There is at least one cluster point of the sequence {d} generated by the algorithm ui+&amp;amp;#x27; E %!(vi). ... Nevertheless, simulation results, some of which are presented here, together with those presented in Willis and Tham [22], show that this condition need ...

Industrial applications of a new adaptive estimator for inferential control

by Ming Tham and Julian Morris

Two methods for inferring process outputs which can only be measured at infrequent intervals of t... more Two methods for inferring process outputs which can only be measured at infrequent intervals of time, from other more rapidly sampled secondary outputs, are presented. The estimators (or soft-sensors) use both a general input-output representation of the plant and a state space representation as starting points for synthesis of the algorithms. The developments are supported by results from some recent

Julian Morris

Uploads

Papers by Julian Morris

Log In