Policy-based techniques for self-managing parallel applications

This paper presents an empirical investigation of policy-based self-management techniques for parallel applications executing in loosely-coupled environments. The dynamic and heterogeneous nature of these environments is discussed and the special considerations for parallel applications are identified. An adaptive strategy for the run-time deployment of tasks of parallel applications is presented. The strategy is based on embedding numerous policies which are informed by contextual and environmental inputs. The policies govern various aspects of behaviour, enhancing flexibility so that the goals of efficiency and performance are achieved despite high levels of environmental variability. A prototype self-managing parallel application is used as a vehicle to explore the feasibility and benefits of the strategy. In particular, several aspects of stability are investigated. The implementation and behaviour of three policies are discussed and sample results examined.

Development of an in-situ, non-destructive ultrasonic monitoring technique for solder pastes

This paper concerns the use of a non-destructive ultrasonic technique for characterising the rheological properties of solder paste and specifically, the use of through-mode microsecond ultrasonic pulses for evaluation of viscoelastic properties of paste materials at the molecular level. Ultrasonic techniques are a widely used and a reliable form of non-destructive testing of materials. This is because techniques such as ultrasounds while used for testing or monitoring material properties, has offered immense benefits in applications where access to the sample is restricted or when handling the sample for testing could interfere with the monitoring or analysis process. Very often, this would mean that the measurements taken are not a true representation of the behaviour of the material (due to externally incorporated changes into the material's physical state during the removal or testing process). Ultrasonic based techniques are being increasingly used for quality control and production monitoring functions which requires evaluation of the changes in material properties over wide range of industrial applications such as cement paste quality, plastic/polymer extrusion process, dough, and even sugar content in beverage drinks. In addition, ultrasound techniques are of great interest for their capacity to take rapid measurements in systems which are optically opaque. The viscometer and rheometer are two of the most widely used rheological instruments used in industry for monitoring the quality of solder pastes, during the production and packaging stage. One of the potential limitations of viscometer and rheometer based measurements is that the collection and preparation of the solder paste samples can irreversibly alter the structure and flow behaviour of the sample. Hence the measurement may not represent the actual quality of the whole production batch. Secondly, rheological measurements and the interpretation of rheological data is a very technical and time consuming process, which requires professionally trained R&D personnel. It is for these reasons that materials suppliers (who formulate and produce solder pastes) and solder paste consumers (especially, contract electronics manufacturers) are keen to see the development of simple, easy to use and accurate techniques for the theological characterisation of solder pastes. The results from the work show that the technique can be used by R&D personnel involved in paste formulation and manufacture to monitor the batch-to-batch quality and consistency.

In-situ non-destructive ultrasonic rheology technique for monitoring different lead-free solder pastes for surface mount applications

This paper investigates the application of a non-destructive ultrasonic technique for characterising the rheological properties of solder paste through the use of through-mode microsecond ultrasonic pulses for evaluation of viscoelastic properties of lead-free solder paste containing different types of flux. Ultrasonic techniques offer a robust and reliable form of non-destructive testing of materials where access to the sample is restricted or when sample handling can interfere with the monitoring or analysis process due to externally incorporated changes to the material’s physical state or accidental contamination during the removal or testing process. Ultrasonic based techniques are increasingly used for quality control and production monitoring functions which requires evaluation of changes in material properties for a wide range of industrial applications such as cement paste quality, plastic/polymer extrusion process, dough and even sugar content in beverage drinks. In addition, ultrasound techniques are of great interest for their capability to take rapid measurements in systems which are optically opaque. The conventional industry approach for characterising the rheological properties of suspensions during processing/packaging stage is mainly through the use of viscometer and some through the use of rheometer. One of the potential limitations of viscometer and rheometer based measurements is that the collection and preparation of the solder paste samples can irreversibly alter the structure and flow behaviour of the sample. Hence the measurement may not represent the actual quality of the whole production batch. Secondly, rheological measurements and the interpretation of rheological data is a very technical and time consuming process, which requires professionally trained R&D personnel. The ultrasound technique being proposed provides simple, yet accurate and easy to use solution for the in-situ rheological characterisation of solder pastes which will benefit the materials suppliers (who formulate and produce solder pastes) and solder paste consumers (especially, contract electronics manufacturers). The results from the work show that the technique can be used by R&D personnel involved in paste formulation and manufacture to monitor the batch-to-batch quality and consistency.

Development of numerical techniques for near-field aeroacoustic computations

This work is concerned with the development of a numerical scheme capable of producing accurate simulations of sound propagation in the presence of a mean flow field. The method is based on the concept of variable decomposition, which leads to two separate sets of equations. These equations are the linearised Euler equations and the Reynolds-averaged Navier–Stokes equations. This paper concentrates on the development of numerical schemes for the linearised Euler equations that leads to a computational aeroacoustics (CAA) code. The resulting CAA code is a non-diffusive, time- and space-staggered finite volume code for the acoustic perturbation, and it is validated against analytic results for pure 1D sound propagation and 2D benchmark problems involving sound scattering from a cylindrical obstacle. Predictions are also given for the case of prescribed source sound propagation in a laminar boundary layer as an illustration of the effects of mean convection. Copyright © 1999 John Wiley & Sons, Ltd.

Computational issues in the modelling of materials-based manufacturing processes

The manufacture of materials products involves the control of a range of interacting physical phenomena. The material to be used is synthesised and then manipulated into some component form. The structure and properties of the final component are influenced by both interactions of continuum-scale phenomena and those at an atomistic-scale level. Moreover, during the processing phase there are some properties that cannot be measured (typically the liquid-solid phase change). However, it seems there is a potential to derive properties and other features from atomistic-scale simulations that are of key importance at the continuum scale. Some of the issues that need to be resolved in this context focus upon computational techniques and software tools facilitating: (i) the multiphysics modeling at continuum scale; (ii) the interaction and appropriate degrees of coupling between the atomistic through microstructure to continuum scale; and (iii) the exploitation of high-performance parallel computing power delivering simulation results in a practical time period. This paper discusses some of the attempts to address each of the above issues, particularly in the context of materials processing for manufacture.

A case based reasoning system capturing fire modelling expertise

This paper describes the architecture of the case based reasoning (CBR) component of Smartfire, a fire field modelling tool for use by members of the Fire Safety Engineering community who are not expert in modelling techniques. The CBR system captures the qualitative reasoning of an experienced modeller in the assessment of room geometries so as to set up the important initial parameters of the problem. The system relies on two important reasoning principles obtained from the expert: 1) there is a natural hierarchical retrieval mechanism which may be employed; and 2) much of the reasoning on a qualitative level is linear in nature, although the computational solution of the problem is non-linear. The paper describes the qualitative representation of geometric room information on which the system is based, and the principles on which the CBR system operates.

A knowledge-based system to represent spatial reasoning for fire modelling

This paper describes the architecture of the knowledge based system (KBS) component of Smartfire, a fire field modelling tool for use by members of the fire safety engineering community who are not expert in modelling techniques. The KBS captures the qualitative reasoning of an experienced modeller in the assessment of room geometries, so as to set up the important initial parameters of the problem. Fire modelling expertise is an example of geometric and spatial reasoning, which raises representational problems. The approach taken in this project is a qualitative representation of geometric room information based on Forbus’ concept of a metric diagram. This takes the form of a coarse grid, partitioning the domain in each of the three spatial dimensions. Inference over the representation is performed using a case-based reasoning (CBR) component. The CBR component stores example partitions with key set-up parameters; this paper concentrates on the key parameter of grid cell distribution.

Examining the effect of exit separation on aircraft evacuation performance during 90-second certification trials using evacuation modelling techniques

This paper examines the influence of exit separation, exit availability and seating configuration on aircraft evacuation efficiency and evacuation time. The purpose of this analysis is to explore how these parameters influence the 60-foot exit separation requirement found in aircraft certification rules. The analysis makes use of the airEXODUS evacuation model and is based on a typical wide-body aircraft cabin section involving two pairs of Type-A exits located at either end of the section with a maximum permissible loading of 220 passengers located between the exits. The analysis reveals that there is a complex relationship between exit separation and evacuation efficiency. A main finding of this work is that for the cabin section examined, with a maximum passenger load of 220 and under certification conditions, exit separations up to 170ft will result in approximately constant total evacuation times and average personal evacuation times. This practical exit separation threshold is decreased to 114ft if another combination of exits is selected. While other factors must also be considered when determining maximum allowable exit separations, these results suggest it is not possible to mandate a maximum exit separation without taking into consideration exit type, exit availability and aircraft configuration.

The use of evacuation modelling techniques in the design of very large transport aircraft and blended wing body aircraft

Very Large Transport Aircraft (VLTA) pose considerable challenges to designers, operators and certification authorities. Questions concerning seating arrangement, nature and design of recreational space, the number, design and location of internal staircases, the number of cabin crew required and the nature of the cabin crew emergency procedures are just some of the issues that need to be addressed. Other more radical concepts such as blended wing body (BWB) design, involving one or two decks with possibly four or more aisles offer even greater challenges. Can the largest exits currently available cope with passenger flow arising from four or five aisles? Do we need to consider new concepts in exit design? Should the main aisles be made wider to accommodate more passengers? In this paper we demonstrate how computer based evacuation models can be used to investigate these issues through examination of staircase evacuation procedures for VLTA and aisle/exit configuration for BWB cabin layouts.

Examining the effect of exit separation on aircraft evacuation performance using evacuation modelling techniques: "Is the 60 foot rule relevant?"

This paper examines the influence of exit separation, exit availability and seating configuration on aircraft evacuation efficiency and evacuation time. The purpose of this analysis is to explore how these parameters influence the 60 foot exit separation requirement found in aircraft certification rules. The analysis makes use of the airEXODUS evacuation model and is based on a typical wide-body aircraft cabin section involving two pairs of Type-A exits located at either end of the section with a maximum permissible loading of 220 passengers located between the exits. The analysis reveals that there is a complex relationship between exit separation and evacuation efficiency. Indeed, other factors such as exit flow rate and exit availability are shown to exert a strong influence on critical exit separations. A main finding of this work is that for the cabin section examined under certification conditions, exit separations up to 170 feet will result in approximately constant total evacuation times and average personal evacuation times. This practical exit separation threshold is decreased to 114 feet if another combination of exits is selected. While other factors must also be considered when determining maximum allowable exit separations, these results suggest it is not possible to mandate a maximum exit separation without taking into consideration exit type, exit availability and aircraft configuration. This has implications when determining maximum allowable exit separations for wide and narrow body aircraft. It is also relevant when considering the maximum allowable separation between different exit types on a given aircraft configuration.

Computational modeling techniques for reliability of electronic components on printed circuit boards

This paper describes modeling technology and its use in providing data governing the assembly and subsequent reliability of electronic chip components on printed circuit boards (PCBs). Products, such as mobile phones, camcorders, intelligent displays, etc., are changing at a tremendous rate where newer technologies are being applied to satisfy the demands for smaller products with increased functionality. At ever decreasing dimensions, and increasing number of input/output connections, the design of these components, in terms of dimensions and materials used, is playing a key role in determining the reliability of the final assembly. Multiphysics modeling techniques are being adopted to predict a range of interacting physics-based phenomena associated with the manufacturing process. For example, heat transfer, solidification, marangoni fluid flow, void movement, and thermal-stress. The modeling techniques used are based on finite volume methods that are conservative and take advantage of being able to represent the physical domain using an unstructured mesh. These techniques are also used to provide data on thermal induced fatigue which is then mapped into product lifetime predictions.

The development of parallel implementation for a CFD based fire field model utilising conventional office based PCs

Parallel processing techniques have been used in the past to provide high performance computing resources for activities such as fire-field modelling. This has traditionally been achieved using specialized hardware and software, the expense of which would be difficult to justify for many fire engineering practices. In this article we demonstrate how typical office-based PCs attached to a Local Area Network has the potential to offer the benefits of parallel processing with minimal costs associated with the purchase of additional hardware or software. It was found that good speedups could be achieved on homogeneous networks of PCs, for example a problem composed of ~100,000 cells would run 9.3 times faster on a network of 12 800MHz PCs than on a single 800MHz PC. It was also found that a network of eight 3.2GHz Pentium 4 PCs would run 7.04 times faster than a single 3.2GHz Pentium computer. A dynamic load balancing scheme was also devised to allow the effective use of the software on heterogeneous PC networks. This scheme also ensured that the impact between the parallel processing task and other computer users on the network was minimized.

Case based adaptation using interpolation over nominal values

In this paper we propose a method for interpolation over a set of retrieved cases in the adaptation phase of the case-based reasoning cycle. The method has two advantages over traditional systems: the first is that it can predict “new” instances, not yet present in the case base; the second is that it can predict solutions not present in the retrieval set. The method is a generalisation of Shepard’s Interpolation method, formulated as the minimisation of an error function defined in terms of distance metrics in the solution and problem spaces. We term the retrieval algorithm the Generalised Shepard Nearest Neighbour (GSNN) method. A novel aspect of GSNN is that it provides a general method for interpolation over nominal solution domains. The method is illustrated in the paper with reference to the Irises classification problem. It is evaluated with reference to a simulated nominal value test problem, and to a benchmark case base from the travel domain. The algorithm is shown to out-perform conventional nearest neighbour methods on these problems. Finally, GSNN is shown to improve in efficiency when used in conjunction with a diverse retrieval algorithm.

Enhancing the usability of numerical models with case-based reasoning

Numerical models are important tools used in engineering fields to predict the behaviour and the impact of physical elements. There may be advantages to be gained by combining Case-Based Reasoning (CBR) techniques with numerical models. This paper considers how CBR can be used as a flexible query engine to improve the usability of numerical models. Particularly they can help to solve inverse and mixed problems, and to solve constraint problems. We discuss this idea with reference to the illustrative example of a pneumatic conveyor problem. The paper describes example problems faced by design engineers in this context and the issues that need to be considered in this approach. Solution of these problems require methods to handle constraints in both the retrieval phase and the adaptation phase of a typical CBR cycle. We show approaches to the solution of these problesm via a CBR tool.

Policy-centric integration and dynamic composition of autonomic computing techniques

This paper presents innovative work in the development of policy-based autonomic computing. The core of the work is a powerful and flexible policy-expression language AGILE, which facilitates run-time adaptable policy configuration of autonomic systems. AGILE also serves as an integrating platform for other self-management technologies including signal processing, automated trend analysis and utility functions. Each of these technologies has specific advantages and applicability to different types of dynamic adaptation. The AGILE platform enables seamless interoperability of the different technologies to each perform various aspects of self-management within a single application. The various technologies are implemented as object components. Self-management behaviour is specified using the policy language semantics to bind the various components together as required. Since the policy semantics support run-time re-configuration, the self-management architecture is dynamically composable. Additional benefits include the standardisation of the application programmer interface, terminology and semantics, and only a single point of embedding is required.