Improving Energy Efficiency in Buildings Using Machine Intelligence

Abstract

Abstract. Improving the detection of thermal insulation in buildings -which includes the development of models for heating and ventilation processes and fabric gain -could significantly increase building energy efficiency and substantially contribute to reductions in energy consumption and in the carbon footprints of domestic heating systems. Thermal insulation standards are now contractual obligations in new buildings, although poor energy efficiency is often a defining characteristic of buildings built before the introduction of those standards. Lighting, occupancy, set point temperature profiles, air conditioning and ventilation services all increase the complexity of measuring insulation efficiency. The identification of thermal insulation failure can help to reduce energy consumption in heating systems. Conventional methods can be greatly improved through the application of hybridized machine learning techniques to detect thermal insulation failures when a building is in operation. A three-step procedure is proposed in this paper that begins by considering the local building and heating system regulations as well as the specific features of the climate zone. Firstly, the dynamic thermal performance of different variables is specifically modelled, for each building type and climate zone. Secondly, Cooperative Maximum-Likelihood Hebbian Learning is used to extract the relevant features. Finally, neural projections and identification techniques are applied, in order to detect fluctuations in room temperatures and, in consequence, thermal insulation failures. The reliability of the proposed method is validated in three winter zone C cities in Spain. Although a great deal of further research remains to be done in this field, the proposed system is expected to outperform conventional methods described in Spanish building codes that are used to calculate energetic profiles in domestic and residential buildings.

Learning and training techniques in fuzzy control for energy efficiency in buildings

“…If the ARX model is used as the regression vector θ, the model structure is called NNARX (Neural Network for ARX model). Extensive use is made of NNARX (Neural Network ARX), and likewise of NNFIR (Neural Network Finite Impulse Response), NNARMAX (Neural Network Autoregressive Moving Average with external input), and NNOE (Neural Network Output Error) [30,34,36,37].…”

“…The results from subsequent studies [34,37,38] that used a procedure for detecting thermal insulation failures in buildings in operation provide a clue for solving the two above-mentioned drawbacks: the use of CMLHL to find the most relevant variables for estimating in-room temperature evolution. Using these ideas, the four-step procedure detailed in previous section has been improved.…”

“…Nevertheless, a new post-processing step is introduced using CMLHL as a dimensionality reduction technique to choose the most relevant features in order to determine the indoor temperature. Finally, the Simulated Annealing step for training a polynomial model was replaced with an ANN model, as proposed in [34,37,38]. The differences between the two methods are depicted in Figure 1.…”

Meta-heuristic improvements applied for steel sheet incremental cold shaping

“…Over recent years, there has been a significant increase in the use of artificial intelligence and soft computing (SOCO) methods to solve real world problems. Many different SOCO applications have been reported: the use of exploratory projection pursuit (EPS) and ARMAX for modelling the manufacture of steel components [3]; EPS and neural networks (NN) for determining the operating conditions in face milling operations [15] and in pneumatic drilling processes [17]; genetic algorithms and programming for trading rule extraction [4] and low quality data in lighting control systems [21]; feature selection and association rule discovery in high dimensional spaces [20] or NNs and principal component analysis and EPS in building energy efficiency [18,19].…”