Multi-fidelity simulation modelling in optimization of a hybrid submarine propulsion system

Multi-objective Genetic Algorithms have become a popular choice to aid in optimising the size of the whole hybrid power train. Within these optimisation processes, other optimisation techniques for the control strategy are implemented. This optimisation within an optimisation requires many simulations to be run, so reducing the computational cost is highly desired. This paper presents an optimisation framework consisting of a series hybrid optimisation algorithm, in which a global search optimizes a submarine propulsion system using low-fidelity models and, in order to refine the results, a local search is used with high-fidelity models. The effectiveness of the Hybrid optimisation algorithm is demonstrated with the optimisation of a submarine propulsion system. © 2011 EPE Association - European Power Electr.

Pipe in Pipe PiP

PiP software is a powerful computational tool for calculating vibration from underground railways and for assessing the performance of vibration countermeasures. The software has a user-friendly interface and it uses the state-of-the-art techniques to perform quick calculations for the problem. The software employs a model of a slab track coupled to a circular tunnel embedded in the ground. The software calculates the Power Spectral Density (PSD) of the vertical displacement at any selected point in the soil. Excitation is assumed to be due to an infinitely-long train moving on a slab-track supported at the tunnel bed. The PSD is calculated for a roughness excitation of a unit value (i.e. "white noise"). The software also calculates the Insertion Gain (IG) which is the ratio between the PSD displacement after and before changing parameters of the track, tunnel or soil. Version 4 of the software accounts for important developments of the numerical model. The tunnel wall is modelled as a thick shell (using the elastic continuum theory) rather than a thin shell. More importantly, the numerical model accounts now for a tunnel embedded in a half space rather than a full space as done in the previous versions. The software can now be used to calculate vibration due to a number of typical PSD roughnesses for rails in good, average and bad conditions.

Bayesian classification of acoustical waveforms under environmental variability

We present in this paper a new multivariate probabilistic approach to Acoustic Pulse Recognition (APR) for tangible interface applications. This model uses Principle Component Analysis (PCA) in a probabilistic framework to classify tapping pulses with a high degree of variability. It was found that this model, achieves a higher robustness to pulse variability than simpler template matching methods, specifically when allowed to train on data containing high variability. © 2011 IEEE.

Parameter estimation for agenda-based user simulation

This paper presents an agenda-based user simulator which has been extended to be trainable on real data with the aim of more closely modelling the complex rational behaviour exhibited by real users. The train-able part is formed by a set of random decision points that may be encountered during the process of receiving a system act and responding with a user act. A sample-based method is presented for using real user data to estimate the parameters that control these decisions. Evaluation results are given both in terms of statistics of generated user behaviour and the quality of policies trained with different simulators. Compared to a handcrafted simulator, the trained system provides a much better fit to corpus data and evaluations suggest that this better fit should result in improved dialogue performance. © 2010 Association for Computational Linguistics.

Femtosecond superradiant emission in AlGaInAs quantum-well semiconductor laser structures.

Ultrashort superradiant pulse generation from a 1580 nm AlGaInAs multiple quantum-well (MQW) semiconductor structure has been experimentally demonstrated for the first time. Superradiance is confirmed by analyzing the evolution of the optical temporal waveforms and spectra. Superradiant trends and regimes are studied as a function of driving condition. An optical pulse train is obtained at 1580 nm wavelength, with pulse durations as short as 390 fs and pulse peak powers of 7.2 W.

Statistical parametric speech synthesis based on speaker and language factorization

An increasingly common scenario in building speech synthesis and recognition systems is training on inhomogeneous data. This paper proposes a new framework for estimating hidden Markov models on data containing both multiple speakers and multiple languages. The proposed framework, speaker and language factorization, attempts to factorize speaker-/language-specific characteristics in the data and then model them using separate transforms. Language-specific factors in the data are represented by transforms based on cluster mean interpolation with cluster-dependent decision trees. Acoustic variations caused by speaker characteristics are handled by transforms based on constrained maximum-likelihood linear regression. Experimental results on statistical parametric speech synthesis show that the proposed framework enables data from multiple speakers in different languages to be used to: train a synthesis system; synthesize speech in a language using speaker characteristics estimated in a different language; and adapt to a new language. © 2012 IEEE.

Passive suspensions incorporating inerters for railway vehicles

This paper investigates the possibility of improving the performance of railway vehicle suspensions by incorporating a newly developed mechanical device known as the inerter. A comparative study of several low-complexity passive suspension layouts is made. Improved performance for the lateral and vertical ride comfort, as well as lateral body movement when curving are demonstrated in comparison with the conventional suspension layout. The constraints imposed are to maintain the same level of other performance metrics. The calculations and optimisations are based on linearised plan-view and side-view high-speed train mathematical models. © 2012 Copyright Taylor and Francis Group, LLC.

Neuro-Fuzzy genetic system for selection of construction project managers

Choosing a project manager for a construction project—particularly, large projects—is a critical project decision. The selection process involves different criteria and should be in accordance with company policies and project specifications. Traditionally, potential candidates are interviewed and the most qualified are selected in compliance with company priorities and project conditions. Precise computing models that could take various candidates’ information into consideration and then pinpoint the most qualified person with a high degree of accuracy would be beneficial. On the basis of the opinions of experienced construction company managers, this paper, through presenting a fuzzy system, identifies the important criteria in selecting a project manager. The proposed fuzzy system is based on IF-THEN rules; a genetic algorithm improves the overall accuracy as well as the functions used by the fuzzy system to make initial estimates of the cluster centers for fuzzy c-means clustering. Moreover, a back-propagation neutral network method was used to train the system. The optimal measures of the inference parameters were identified by calculating the system’s output error and propagating this error within the system. After specifying the system parameters, the membership function parameters—which by means of clustering and projection were approximated—were tuned with the genetic algorithm. Results from this system in selecting project managers show its high capability in making high-quality personnel predictions

Graphone model interpolation and Arabic pronunciation generation

This paper extends n-gram graphone model pronunciation generation to use a mixture of such models. This technique is useful when pronunciation data is for a specific variant (or set of variants) of a language, such as for a dialect, and only a small amount of pronunciation dictionary training data for that specific variant is available. The performance of the interpolated n-gram graphone model is evaluated on Arabic phonetic pronunciation generation for words that can't be handled by the Buckwalter Morphological Analyser. The pronunciations produced are also used to train an Arabic broadcast audio speech recognition system. In both cases the interpolated graphone model leads to improved performance. Copyright © 2011 ISCA.

Fractal dimension, wavelet shrinkage and anomaly detection for mine hunting

An anomaly detection approach is considered for the mine hunting in sonar imagery problem. The authors exploit previous work that used dual-tree wavelets and fractal dimension to adaptively suppress sand ripples and a matched filter as an initial detector. Here, lacunarity inspired features are extracted from the remaining false positives, again using dual-tree wavelets. A one-class support vector machine is then used to learn a decision boundary, based only on these false positives. The approach exploits the large quantities of 'normal' natural background data available but avoids the difficult requirement of collecting examples of targets in order to train a classifier. © 2012 The Institution of Engineering and Technology.

Ultrashort pulse generation in diode laser devices

The generation of ultrashort optical pulses by semiconductor lasers has been extensively studied for many years. A number of methods, including gain-/Q-switching and different types of mode locking, have been exploited for the generation of picosecond and sub-picosecond pulses [1]. However, the shortest pulses produced by diode lasers are still much longer and weaker than those that are generated by advanced mode-locked solid-state laser systems [2]. On the other hand, an interesting class of devices based on superradiant emission from multiple contact diode laser structures has also been recently reported [3]. Superradiance (SR) is a transient quantum optics phenomenon based on the cooperative radiative recombination of a large number of oscillators, including atoms, molecules, e-h pairs, etc. SR in semiconductors can be used for the study of fundamental properties of e-h ensembles such as photon-mediated pairing, non-equilibrium e-h condensation, BSC-like coherent states and related phenomena. Due to the intrinsic parameters of semiconductor media, SR emission typically results in the generation of a high-power optical pulse or pulse train, where the pulse duration can be much less than 1 ps, under optimised bias conditions. Advantages of this technique over mode locking in semiconductor laser structures include potentially shorter pulsewidths and much larger peak powers. Moreover, the pulse repetition rate of mode-locked pulses is fixed by the cavity round trip time, whereas the repetition rate of SR pulses is controlled by the current bias and can be varied over a wide range. © 2012 IEEE.

Design and testing of a 250 kW medium-speed Brushless DFIG

This paper presents the design and testing of a 250 kW medium-speed Brushless Doubly-Fed Induction Generator (Brushless DFIG), and its associated power electronics and control systems. The experimental tests confirm the design, and show the system's steady-state and dynamic performance. The medium-speed Brushless DFIG in combination with a simplified two-stage gearbox promises a low-cost low-maintenance and reliable drive train for wind turbine applications.

Machine learning for predictive condensed-phase simulation

We show how machine learning techniques based on Bayesian inference can be used to reach new levels of realism in the computer simulation of molecular materials, focusing here on water. We train our machine-learning algorithm using accurate, correlated quantum chemistry, and predict energies and forces in molecular aggregates ranging from clusters to solid and liquid phases. The widely used electronic-structure methods based on density-functional theory (DFT) give poor accuracy for molecular materials like water, and we show how our techniques can be used to generate systematically improvable corrections to DFT. The resulting corrected DFT scheme gives remarkably accurate predictions for the relative energies of small water clusters and of different ice structures, and greatly improves the description of the structure and dynamics of liquid water.

N-best error simulation for training spoken dialogue systems

A recent trend in spoken dialogue research is the use of reinforcement learning to train dialogue systems in a simulated environment. Past researchers have shown that the types of errors that are simulated can have a significant effect on simulated dialogue performance. Since modern systems typically receive an N-best list of possible user utterances, it is important to be able to simulate a full N-best list of hypotheses. This paper presents a new method for simulating such errors based on logistic regression, as well as a new method for simulating the structure of N-best lists of semantics and their probabilities, based on the Dirichlet distribution. Off-line evaluations show that the new Dirichlet model results in a much closer match to the receiver operating characteristics (ROC) of the live data. Experiments also show that the logistic model gives confusions that are closer to the type of confusions observed in live situations. The hope is that these new error models will be able to improve the resulting performance of trained dialogue systems. © 2012 IEEE.

Policy optimisation of POMDP-based dialogue systems without state space compression

The partially observable Markov decision process (POMDP) has been proposed as a dialogue model that enables automatic improvement of the dialogue policy and robustness to speech understanding errors. It requires, however, a large number of dialogues to train the dialogue policy. Gaussian processes (GP) have recently been applied to POMDP dialogue management optimisation showing an ability to substantially increase the speed of learning. Here, we investigate this further using the Bayesian Update of Dialogue State dialogue manager. We show that it is possible to apply Gaussian processes directly to the belief state, removing the need for a parametric policy representation. In addition, the resulting policy learns significantly faster while maintaining operational performance. © 2012 IEEE.