Efficient serial and parallel implementations of the cutting angle global optimisation technique

We examine efficient computer implementation of one method of deterministic global optimisation, the cutting angle method. In this method the objective function is approximated from values below the function with a piecewise linear auxiliary function. The global minimum of the objective function is approximated from the sequence of minima of this auxiliary function. Computing the minima of the auxiliary function is a combinatorial problem, and we show that it can be effectively parallelised. We discuss the improvements made to the serial implementation of the cutting angle method, and ways of distributing computations across multiple processors on parallel and cluster computers.

On work in progress optimisation

In this paper, we investigate how to best optimise the level of work in progress (WIP) in a real world factory. Using a simulation model of the factory, we show that an optimum level of WIP can be attained. By systematically varying the maximum allowable level of WIP within different model runs, results show that the throughput reaches a high level very quickly and then tapers off. The production lead times, in contrast, begin at relatively low levels and increase after the optimum WIP level has been reached.

Global optimisation of neural networks using a deterministic hybrid approach

Selection of the topology of a neural network and correct parameters for the learning algorithm is a tedious task for designing an optimal artificial neural network, which is smaller, faster and with a better generalization performance. In this paper we introduce a recently developed cutting angle method (a deterministic technique) for global optimization of connection weights. Neural networks are initially trained using the cutting angle method and later the learning is fine-tuned (meta-learning) using conventional gradient descent or other optimization techniques. Experiments were carried out on three time series benchmarks and a comparison was done using evolutionary neural networks. Our preliminary experimentation results show that the proposed deterministic approach could provide near optimal results much faster than the evolutionary approach.

A medium-temperature solar thermal power system and its efficiency optimisation

This paper firstly expounds that the reheat-regenerative Rankine power cycle is a suitable cycle for the parabolic trough collector, a popular kind of collector in the power industry. In a thermal power cycle, the higher the temperature at which heat is supplied, the higher the efficiency of the cycle. On the other hand, for a given kind of collector at the same exiting temperature, the higher the temperature of the fluid entering the collector, the lower the efficiency of the collector. With the same exiting temperature of the solar field and the same temperature differences at the hottest end of the superheater/reheater and at the pinch points in the heat exchangers (e.g., the boiler) in the cycle, the efficiencies of the system are subject to the temperature of the fluid entering the collector or the saturation temperature at the boiler. This paper also investigates the optimal thermal and exergetic efficiencies for the combined system of the power cycle and collector. To make most advantage of the collector, the exiting fluid is supposed to be at the maximum temperature the collector can harvest. Hence, the thermal and exergetic efficiencies of the system are related to the saturation temperature at the boiler here.

Knowledge based optimisation techniques for sheet metal forming die design

A knowledge based optimism technique has been developed to predict solutions for quality issues found in an initial draw die design. Post processing of the initial design yields all the features applying forces, and major quality issues. Using the geometric relationship between the two, a knowledge-base is interrogated to determine the possible corrective actions. These actions are then passed through a fast semi-analytical model to determine the level of change required. Results from a 2D forming are presented to highlight the advantage of the new algorithms over current optimisation techniques.

Towards insightful algorithm selection for optimisation using meta-learning concepts

In this paper we propose a meta-learning inspired framework for analysing the performance of meta-heuristics for optimization problems, and developing insights into the relationships between search space characteristics of the problem instances and algorithm performance. Preliminary results based on several meta-heuristics for well-known instances of the Quadratic Assignment Problem are presented to illustrate the approach using both supervised and unsupervised learning methods.

Response surface optimisation of medium components for naringinase production from staphylococcus xylosus MAK 2

Response surface methodology was used to optimize the fermentation medium for enhancing naringinase production by Staphylococcus xylosus. The first step of this process involved the individual adjustment and optimization of various medium components at shake flask level. Sources of carbon (sucrose) and nitrogen (sodium nitrate), as well as an inducer (naringin) and pH levels were all found to be the important factors significantly affecting naringinase production. In the second step, a 22 full factorial central composite design was applied to determine the optimal levels of each of the significant variables. A second-order polynomial was derived by multiple regression analysis on the experimental data. Using this methodology, the optimum values for the critical components were obtained as follows: sucrose, 10.0%; sodium nitrate, 10.0%; pH 5.6; biomass concentration, 1.58%; and naringin, 0.50% (w/v), respectively. Under optimal conditions, the experimental naringinase production was 8.45 U/mL. The determination coefficients (R ²) were 0.9908 and 0.9950 for naringinase activity and biomass production, respectively, indicating an adequate degree of reliability in the model.

The optimisation of ultrasonic cleaning procedures for dairy fouled ultrafiltration membranes

Ultrafiltration (UF) of whey is a major membrane based process in the dairy industry. However, commercialization of this application has been limited by membrane fouling, which has a detrimental influence on the permeation rate. There are a number of different chemical and physical cleaning methods currently used for cleaning a fouled membrane. It has been suggested that the cleaning frequency and the severity of such cleaning procedures control the membrane lifetime. The development of an optimal cleaning strategy should therefore have a direct implication on the process economics. Recently, the use of ultrasound has attracted considerable interest as an alternative approach to the conventional methods. In the present study, we have studied the ultrasonic cleaning of polysulfone ultrafiltration membranes fouled with dairy whey solutions. The effects of a number of cleaning process parameters have been examined in the presence of ultrasound and results compared with the conventional operation. Experiments were conducted using a small single sheet membrane unit that was immersed totally within an ultrasonic bath. Results show that ultrasonic cleaning improves the cleaning efficiency under all experimental conditions. The ultrasonic effect is more significant in the absence of surfactant, but is less influenced by temperature and transmembrane pressure. Our results suggest that the ultrasonic energy acts primarily by increasing the turbulence within the cleaning solution.

Diver navigation system acoustic signal encoding/decoding optimisation

This thesis describes the optimisation of the encoding and decoding processes used to transmit and receive frequency coded data tones acoustically during the operation of an underwater diver navigation system. The aim was to reduce the time required to both generate these data tones for transmission as well as to decode these tones during reception. Encoding of the data tones is performed using a phase lock loop under the control of a microcontroller. A technique was developed which combined both hardware and software modifications to effectively halve the phase lock loop settling time, and therefore the time required to generate these tones. Decoding of these data tones is achieved using the Fast Fourier Transform. Alternative forms of the Discrete Fourier Transform were explored to find the most efficient in terms of execution time. Numerous software optimisations were then applied which led to a reduction in program execution time of 54 % with no penalty in program complexity or length. Testing of the system under identical real-life operating conditions showed no evidence of any system performance degradation as a result of these optimisations.