One of the major challenges in pattern recognition problems is the feature extraction process which derives new features from existing features, or directly from raw data in order to reduce the cost of computation during the classification process, while improving classifier efficiency. Most current feature extraction techniques transform the original pattern vector into a new vector with increased discrimination capability but lower dimensionality. This is conducted within a predefined feature space, and thus, has limited searching power. Genetic programming (GP) can generate new features from the original dataset without prior knowledge of the probabilistic distribution. In this paper, a GP-based approach is developed for feature extraction from raw vibration data recorded from a rotating machine with six different conditions. The created features are then used as the inputs to a neural classifier for the identification of six bearing conditions. Experimental results demonstrate the ability of GP to discover autimatically the different bearing conditions using features expressed in the form of nonlinear functions. Furthermore, four sets of results--using GP extracted features with artificial neural networks (ANN) and support vector machines (SVM), as well as traditional features with ANN and SVM--have been obtained. This GP-based approach is used for bearing fault classification for the first time and exhibits superior searching power over other techniques. Additionaly, it significantly reduces the time for computation compared with genetic algorithm (GA), therefore, makes a more practical realization of the solution.

No abstract

No abstract

Abstract:Timber building has gained more and more attention worldwide due to it being a generic renewable material and having low environmental impact. It is widely accepted that the use of timber may be able to reduce the embodied energy of a building. However, the development of timber buildings in China is not as rapid as in some other countries. This may be because of the limitations of building regulations and technological development. Several new policies have been or are being implemented in China in order to encourage the use of timber in building construction and this could lead to a revolutionary change in the building industry in China. This paper is the first one to examine the feasibility of using Cross Laminated Timber (CLT) as an alternative solution to concrete by means of a cradle-to-grave life-cycle assessment in China. A seven-storey reference concrete building in Xi'an was selected as a case study in comparison with a redesigned CLT building. Two cities in China, in cold and severe cold regions (Xi'an and Harbin), were selected for this research. The assessment includes three different stages of the life span of a building: materialisation, operation, and end-of-life. The inventory data used in the materialisation stage was mostly local, in order to ensure that the assessment appropriately reflects the situation in China. Energy consumption in the operation stage was obtained from simulation by commercialised software IES TM , and different scenarios for recycling of timber material in the end-of-life are discussed in this paper. The results from this paper show that using CLT to replace conventional carbon intensive material would reduce energy consumption by more than 30% and reduce CO 2 emission by more than 40% in both cities. This paper supports, and has shown the potential of, CLT being used in cold regions with proper detailing to minimise environmental impact.

No abstract