Adrian R.G. Harwood

Parallelisation of an interactive lattice-Boltzmann method on an Android-powered mobile device

The role of mobile devices in interactive engineering simulation is discussed.Two parallelisation frameworks for simulation on Android-based mobile devices are presented.Task-based parallelisation performs slightly better than thread-based parallelisation.Implementing the kernel natively improves performance by 20%. Engineering simulation is essential to modern engineering design, although it is often a computationally demanding activity which can require powerful computer systems to conduct a study. Traditionally the remit of large desktop workstations or off-site computational facilities, potential is now emerging for mobile computation, whereby the unique characteristics of portable devices are harnessed to provide a novel means of engineering simulation. Possible use cases include emergency service assistance, teaching environments, augmented reality or indeed any such case where large computational resources are unavailable and a system prediction is needed. This is particularly relevant if the required accuracy of a calculation is relatively low, such as cases where only an intuitive result is required. In such cases the computational resources offered by modern mobile devices may already be adequate. This paper proceeds to discuss further the possibilities that modern mobile devices might offer to engineering simulation and describes some initial developments in this direction. We focus on the development of an interactive fluid flow solver employing the lattice Boltzmann method, and investigate both task-based and thread-based parallel implementations. The latter is more traditional for high performance computing across many cores while the former, native to Android, is more simple to implement and returns a slightly higher performance. The performance of both saturates when the number of threads/tasks equal three on a quad-core device. Execution time is improved by a further 20% by implementing the kernel in C++ and cross-compiling using the Android NDK.

Flyover Noise Measurements and Predictions of Commercial Airplanes

A series of flyover noise measurements has been taken to gather data for noise prediction, analysis, and computer program validation. A selected database of measurements is presented for the Airbus A320-200, the Boeing B737-800, and the ATR72 (turboprop). The experimental setup, the microphone positions, the effect of background noise, and the atmospheric effects are presented. It is shown that landing measurements are generally coherent with one another, with consistent peaks in noise levels and uniform noise levels ±5  s from the overhead position. In contrast, at takeoff, there are considerable variations in peak noise level, which are attributed to different takeoff procedures and gross weights. Comparisons with noise predicted using ray tracing are shown. These comparisons indicate that it is possible to predict with some accuracy the noise peaks, the rise and fall of overall sound level, and the integral noise metrics (effective perceived noise level and LAmax).

Interactive flow simulation using Tegra-powered mobile devices

Abstract The ability to perform interactive CFD simulations on mobile devices allows the development of portable, affordable simulation tools that can have a significant impact in engineering design as well as teaching and learning. This work extends existing work in the area by developing and implementing a GPU-accelerated, interactive simulation framework suitable for mobile devices. The accuracy, throughput, memory usage and battery consumption of the application is established for a range of problem sizes. The current GPU implementation is found to be over 300 ×  more efficient in terms of combined throughput and power consumption than a comparable CPU implementation. The usability of the simulation is examined through a new ‘interactivity’ metric which identifies the ratio of simulated convection to real world convection of the same problem. This real-time ratio illustrates that large resolutions may increase throughput through parallelisation on the GPU but this only partially offsets the decrease in simulated flow rate due to the necessary shrinking of the time step in the solver with increasing resolution. Therefore, targeting higher throughput configurations of GPU-solvers offer little additional benefit for interactive applications due to ultimately simulations evolving at a too slow a rate to facilitate interaction. The trade-off between accuracy, speed and power consumption are explored with the choice of problem resolution ultimately being characterised by a desired accuracy, flow speed and endurance of a given simulation. With current rates of growth in mobile compute power expected to continue, real-time simulation is expected to be possible at higher resolutions with a reduced energy footprint in the near future.

Numerical Evaluation of the Compact Green’s Function for the Solution of Acoustic Flows

Due to the relatively tiny length scales involved, complex acoustic flows are not always suitable for traditional CFD codes. This paper develops a robust, semi-analytical numerical method for predicting sound fields based on the calculation of the compact Green’s function over a grid of source-observer positions. These calculations often involve singular functions, hence variations of the method are applied to several different 2D problems to investigate the impact of any singularities on the solution. The effect of grid point density and other parameters on execution time and accuracy are explored including the effects of approximating curved geometries using a number of straight lines. Comparison to known analytical solutions for the 2D problems is used to assess the accuracy of the method. For a typical application, we compute the far-field sound generated by a simple source in the vicinity of a compact, ‘2D’ fan blade in a duct. The current method demonstrates calculation of the compact Green’s function both accurately and robustly by avoiding the mapping from unbounded domains and the evaluation of potential models containing singularities. Both are seen as sources of error which have a widespread impact.Copyright

Scan to Pattern: How body scanning can help transform traditional methods of creating pattern blocks

Body scanning provides one of the most efficient tools for recording information of the human body to support the development of body worn products. Traditionally the construction of garment patterns uses manual measurements and during the construction process applies some proportions, to create a pattern block [1], [2]. Traditional methods of drafting pattern blocks (slopers) apply very limited data from the body compared to the areas they cover and subsequently often require post drafting adjustments to achieve a suitable fit. Most pattern books have guidance on adjustments to blocks to accommodate figure variations [3]–[5]. These methods of block construction are well established and understood and have been used to inspire new approaches and propose theories for pattern block development [2], [6]. With advances in body scanning it is now possible to generate more measurements allowing for the body to have greater context in the process of pattern construction. This research retains the established 2D drafting methods and looks to explore further measurements than those traditionally used to create pattern blocks, these resulting blocks could then better reflect the individual variations in potential wearer size, shape and proportion. As well as looking to determine suitable measurements from a Size Stream (SS14) body scanner to inform the development of pattern blocks, this research tests an established skirt draft [4] using scan measurements, against a newly developed skirt drafting method which utilises the measurement capabilities of body scanning. The developed patterns are each tested on five dress forms. As well as assessing the resulting patterns, recommendations are made regarding how body scanning can be used to better inform pattern construction methods. This includes a contribution toward the theories of pattern construction, which will allow greater exploitation of body scanning technologies in developing better fitting and functioning garments. This research shows one means by which body scanning technologies can help to bridge the gap between traditional techniques of creating pattern blocks and the promising opportunities presented by body scanning technologies.