A Bayesian perspective on stochastic neurocontrol

Control design for stochastic uncertain nonlinear systems is traditionally based on minimizing the expected value of a suitably chosen loss function. Moreover, most control methods usually assume the certainty equivalence principle to simplify the problem and make it computationally tractable. We offer an improved probabilistic framework which is not constrained by these previous assumptions, and provides a more natural framework for incorporating and dealing with uncertainty. The focus of this paper is on developing this framework to obtain an optimal control law strategy using a fully probabilistic approach for information extraction from process data, which does not require detailed knowledge of system dynamics. Moreover, the proposed control method framework allows handling the problem of input-dependent noise. A basic paradigm is proposed and the resulting algorithm is discussed. The proposed probabilistic control method is for the general nonlinear class of discrete-time systems. It is demonstrated theoretically on the affine class. A nonlinear simulation example is also provided to validate theoretical development.

Construction project control in the UK:current practice, existing problems and recommendations for future improvement

The aim of this study is to address the main deficiencies with the prevailing project cost and time control practices for construction projects in the UK. A questionnaire survey was carried out with 250 top companies followed by in-depth interviews with 15 experienced practitioners from these companies in order to gain further insights of the identified problems, and their experience of good practice on how these problems can be tackled. On the basis of these interviews and syntheses with literature, a list of 65 good practice recommendations have been developed for the key project control tasks: planning, monitoring, reporting and analysing. The Delphi method was then used, with the participation of a panel of 8 practitioner experts, to evaluate these improvement recommendations and to establish their degree of relevance. After two rounds of Delphi, these recommendations are put forward as "critical", "important", or "helpful" measures for improving project control practice.

Description and training of neural network dynamics

Attractor properties of a popular discrete-time neural network model are illustrated through numerical simulations. The most complex dynamics is found to occur within particular ranges of parameters controlling the symmetry and magnitude of the weight matrix. A small network model is observed to produce fixed points, limit cycles, mode-locking, the Ruelle-Takens route to chaos, and the period-doubling route to chaos. Training algorithms for tuning this dynamical behaviour are discussed. Training can be an easy or difficult task, depending whether the problem requires the use of temporal information distributed over long time intervals. Such problems require training algorithms which can handle hidden nodes. The most prominent of these algorithms, back propagation through time, solves the temporal credit assignment problem in a way which can work only if the relevant information is distributed locally in time. The Moving Targets algorithm works for the more general case, but is computationally intensive, and prone to local minima.

The 'moving targets' training algorithm

A simple method for training the dynamical behavior of a neural network is derived. It is applicable to any training problem in discrete-time networks with arbitrary feedback. The algorithm resembles back-propagation in that an error function is minimized using a gradient-based method, but the optimization is carried out in the hidden part of state space either instead of, or in addition to weight space. Computational results are presented for some simple dynamical training problems, one of which requires response to a signal 100 time steps in the past.

The 'moving targets' training algorithm

A simple method for training the dynamical behavior of a neural network is derived. It is applicable to any training problem in discrete-time networks with arbitrary feedback. The method resembles back-propagation in that it is a least-squares, gradient-based optimization method, but the optimization is carried out in the hidden part of state space instead of weight space. A straightforward adaptation of this method to feedforward networks offers an alternative to training by conventional back-propagation. Computational results are presented for simple dynamical training problems, with varied success. The failures appear to arise when the method converges to a chaotic attractor. A patch-up for this problem is proposed. The patch-up involves a technique for implementing inequality constraints which may be of interest in its own right.

Point-wise confidence interval estimation by neural networks: A comparative study based on automotive engine calibration.

In developing neural network techniques for real world applications it is still very rare to see estimates of confidence placed on the neural network predictions. This is a major deficiency, especially in safety-critical systems. In this paper we explore three distinct methods of producing point-wise confidence intervals using neural networks. We compare and contrast Bayesian, Gaussian Process and Predictive error bars evaluated on real data. The problem domain is concerned with the calibration of a real automotive engine management system for both air-fuel ratio determination and on-line ignition timing. This problem requires real-time control and is a good candidate for exploring the use of confidence predictions due to its safety-critical nature.

Introduction: improving manufacturing performance through technology diffusion, implementation and management

The role of technology management in achieving improved manufacturing performance has been receiving increased attention as enterprises are becoming more exposed to competition from around the world. In the modern market for manufactured goods the demand is now for more product variety, better quality, shorter delivery and greater flexibility, while the financial and environmental cost of resources has become an urgent concern to manufacturing managers. This issue of the International Journal of Technology Management addresses the question of how the diffusion, implementation and management of technology can improve the performance of manufacturing industries. The authors come from a large number of different countries and their contributions cover a wide range of topics within this general theme. Some papers are conceptual, others report on research carried out in a range of different industries including steel production, iron founding, electronics, robotics, machinery, precision engineering, metal working and motor manufacture. In some cases they describe situations in specific countries. Several are based on presentations made at the UK Operations Management Association's Sixth International Conference held at Aston University at which the conference theme was 'Achieving Competitive Edge: Getting Ahead Through Technology and People'. The first two papers deal with questions of advanced manufacturing technology implementation and management. Firstly Beatty describes a three year longitudinal field study carried out in ten Canadian manufacturing companies using CADICAM and CIM systems. Her findings relate to speed of implementation, choice of system type, the role of individuals in implementation, organization and job design. This is followed by a paper by Bessant in which he argues that a more a strategic approach should be taken towards the management of technology in the 1990s and beyond. Also considered in this paper are the capabilities necessary in order to deploy advanced manufacturing technology as a strategic resource and the way such capabilities might be developed within the firm. These two papers, which deal largely with the implementation of hardware, are supplemented by Samson and Sohal's contribution in which they argue that a much wider perspective should be adopted based on a new approach to manufacturing strategy formulation. Technology transfer is the topic of the following two papers. Pohlen again takes the case of advanced manufacturing technology and reports on his research which considers the factors contributing to successful realisation of AMT transfer. The paper by Lee then provides a more detailed account of technology transfer in the foundry industry. Using a case study based on a firm which has implemented a number of transferred innovations a model is illustrated in which the 'performance gap' can be identified and closed. The diffusion of technology is addressed in the next two papers. In the first of these, by Lowe and Sim, the managerial technologies of 'Just in Time' and 'Manufacturing Resource Planning' (or MRP 11) are examined. A study is described from which a number of factors are found to influence the adoption process including, rate of diffusion and size. Dahlin then considers the case of a specific item of hardware technology, the industrial robot. Her paper reviews the history of robot diffusion since the early 1960s and then tries to predict how the industry will develop in the future. The following two papers deal with the future of manufacturing in a more general sense. The future implementation of advanced manufacturing technology is the subject explored by de Haan and Peters who describe the results of their Dutch Delphi forecasting study conducted among a panel of experts including scientists, consultants, users and suppliers of AMT. Busby and Fan then consider a type of organisational model, 'the extended manufacturing enterprise', which would represent a distinct alternative pure market-led and command structures by exploiting the shared knowledge of suppliers and customers. The three country-based papers consider some strategic issues relating manufacturing technology. In a paper based on investigations conducted in China He, Liff and Steward report their findings from strategy analyses carried out in the steel and watch industries with a view to assessing technology needs and organizational change requirements. This is followed by Tang and Nam's paper which examines the case of machinery industry in Korea and its emerging importance as a key sector in the Korean economy. In his paper which focuses on Venezuela, Ernst then considers the particular problem of how this country can address the problem of falling oil revenues. He sees manufacturing as being an important contributor to Venezuela's future economy and proposes a means whereby government and private enterprise can co-operate in development of the manufacturing sector. The last six papers all deal with specific topics relating to the management manufacturing. Firstly Youssef looks at the question of manufacturing flexibility, introducing and testing a conceptual model that relates computer based technologies flexibility. Dangerfield's paper which follows is based on research conducted in the steel industry. He considers the question of scale and proposes a modelling approach determining the plant configuration necessary to meet market demand. Engstrom presents the results of a detailed investigation into the need for reorganising material flow where group assembly of products has been adopted. Sherwood, Guerrier and Dale then report the findings of a study into the effectiveness of Quality Circle implementation. Stillwagon and Burns, consider how manufacturing competitiveness can be improved individual firms by describing how the application of 'human performance engineering' can be used to motivate individual performance as well as to integrate organizational goals. Finally Sohal, Lewis and Samson describe, using a case study example, how just-in-time control can be applied within the context of computer numerically controlled flexible machining lines. The papers in this issue of the International Journal of Technology Management cover a wide range of topics relating to the general question of improving manufacturing performance through the dissemination, implementation and management of technology. Although they differ markedly in content and approach, they have the collective aim addressing the concepts, principles and practices which provide a better understanding the technology of manufacturing and assist in achieving and maintaining a competitive edge.

The work situation and class position of Brazilian engineers

This thesis analyses the work situation and class position of Brazilian engineers through a Marxist perspective. The research is based on two case studies, one focused on a large German steel company based in Brazil and the other on a large Brazilian energy corporation. The fieldwork involved 114 interviews, with engineers from different hierarchical positions in these two companies. Data was also gathered through interviews with representatives from the companies, the Council of Engineering, the Engineering Education System and the Engineers Trade Unions. The findings show that the engineering profession in Brazil has shifted from its initial condition as a liberal profession to an organizational profession, with the country's industrial deployment. Both companies consider all salaried workers as employees, including managers. Hence they are subject to the company's general personnel policies. The multinational company controls labour more rigidly than the national company, as well as reserving its top positions for its home country's executives. Although no deskilling process was found, engineers of both companies performed simple work, which required less engineering knowledge than they had learned from school. Engineers have little autonomy, authority and participation in decision making and are subject to direct supervision, performance evaluation, time control, overtime work, productivity and to poor working conditions in the multinational company. The majority of the engineers supervised other workers without being in a managerial position. They found that to move into management, was a good way to improve their autonomy, authority, prestige, salary, status, power and professional pride. Despite ideological divisions between capital and labour, most of the engineers were unionised and saw unions as the right way to deal with the employer.

Force sensing for measuring human body movement

The research developed in this thesis explores the sensing and inference of human movement in a dynamic way, as opposed to conventional measurement systems, that are only concerned with discrete evaluations of stimuli in sequential time. Typically, conventional approaches are used to infer the dynamic movement of the body; such as vision and motion tracking devices, with either a human diagnosis or complex image processing algorithm to classify the movement. This research is therefore the first of its kind to attempt and provide a movement classifying algorithm through the use of minimal sensing points, with the application for this novel system, to classify human movement during a golf swing. There are two main categories of force sensing. Firstly, array-type systems consisting of many sensing elements, and are the most commonly researched and commercially available. Secondly, reduced force sensing element systems (RFSES) also known as distributive systems have only been recently exploited in the academic world. The fundamental difference between these systems is that array systems handle the data captured from each sensor as unique outputs and suffer the effects of resolution. The effect of resolution, is the error in the load position measurement between sensing elements, as the output is quantized in terms of position. This can be compared to a reduced sensor element system that maximises that data received through the coupling of data from a distribution of sensing points to describe the output in discrete time. Also this can be extended to a coupling of transients in the time domain to describe an activity or dynamic movement. It is the RFSES that is to be examined and exploited in the commercial sector due to its advantages over array-based approaches such as reduced design, computational complexity and cost.

Investigation of a cross-layer link adaptation algorithm for IEEE 802.11n networks

Link adaptation is a critical component of IEEE 802.11 systems, which adapts transmission rates to dynamic wireless channel conditions. In this paper we investigate a general cross-layer link adaptation algorithm which jointly considers the physical layer link quality and random channel access at the MAC layer. An analytic model is proposed for the link adaptation algorithm. The underlying wireless channel is modeled with a multiple state discrete time Markov chain. Compared with the pure link quality based link adaptation algorithm, the proposed cross-layer algorithm can achieve considerable performance gains of up to 20%.

Stability of multi-agent systems

This work attempts to shed light to the fundamental concepts behind the stability of Multi-Agent Systems. We view the system as a discrete time Markov chain with a potentially unknown transitional probability distribution. The system will be considered to be stable when its state has converged to an equilibrium distribution. Faced with the non-trivial task of establishing the convergence to such a distribution, we propose a hypothesis testing approach according to which we test whether the convergence of a particular system metric has occurred. We describe some artificial multi-agent ecosystems that were developed and we present results based on these systems which confirm that this approach qualitatively agrees with our intuition.

Variational mean-field algorithm for efficient inference in large systems of stochastic differential equations

This work introduces a Gaussian variational mean-field approximation for inference in dynamical systems which can be modeled by ordinary stochastic differential equations. This new approach allows one to express the variational free energy as a functional of the marginal moments of the approximating Gaussian process. A restriction of the moment equations to piecewise polynomial functions, over time, dramatically reduces the complexity of approximate inference for stochastic differential equation models and makes it comparable to that of discrete time hidden Markov models. The algorithm is demonstrated on state and parameter estimation for nonlinear problems with up to 1000 dimensional state vectors and compares the results empirically with various well-known inference methodologies.

Using observation ageing to improve Markovian model learning in QoS engineering

Markovian models are widely used to analyse quality-of-service properties of both system designs and deployed systems. Thanks to the emergence of probabilistic model checkers, this analysis can be performed with high accuracy. However, its usefulness is heavily dependent on how well the model captures the actual behaviour of the analysed system. Our work addresses this problem for a class of Markovian models termed discrete-time Markov chains (DTMCs). We propose a new Bayesian technique for learning the state transition probabilities of DTMCs based on observations of the modelled system. Unlike existing approaches, our technique weighs observations based on their age, to account for the fact that older observations are less relevant than more recent ones. A case study from the area of bioinformatics workflows demonstrates the effectiveness of the technique in scenarios where the model parameters change over time.

Transition from time-continuous systems to discrete mappings

Detailed transport studies in plasmas require the solution of the time evolution of many different initial positions of test particles in the phase space of the systems to be investigated. To reduce this amount of numerical work, one would like to replace the integration of the time-continues system with a mapping.

A methodology for analysis and control of discrete event dynamic systems

The rapid developments in computer technology have resulted in a widespread use of discrete event dynamic systems (DEDSs). This type of system is complex because it exhibits properties such as concurrency, conflict and non-determinism. It is therefore important to model and analyse such systems before implementation to ensure safe, deadlock free and optimal operation. This thesis investigates current modelling techniques and describes Petri net theory in more detail. It reviews top down, bottom up and hybrid Petri net synthesis techniques that are used to model large systems and introduces on object oriented methodology to enable modelling of larger and more complex systems. Designs obtained by this methodology are modular, easy to understand and allow re-use of designs. Control is the next logical step in the design process. This thesis reviews recent developments in control DEDSs and investigates the use of Petri nets in the design of supervisory controllers. The scheduling of exclusive use of resources is investigated and an efficient Petri net based scheduling algorithm is designed and a re-configurable controller is proposed. To enable the analysis and control of large and complex DEDSs, an object oriented C++ software tool kit was developed and used to implement a Petri net analysis tool, Petri net scheduling and control algorithms. Finally, the methodology was applied to two industrial DEDSs: a prototype can sorting machine developed by Eurotherm Controls Ltd., and a semiconductor testing plant belonging to SGS Thomson Microelectronics Ltd.