Search

The majority of existing image encryption algorithms use single chaotic systems, such as Logistic map or Lorentz system, to be the pseudo-random sequence generator. Actually, neither low nor high dimensional chaotic system can get rid of pseudo-randomness deterioration of chaotic sequence calculated by limited precision computer. Additionally, most of them use only one chaotic pseudo-random sequence throughout the encryption process. These are the more obvious deficiencies. In the current paper, a novel compound chaotic system is applied to color images domain to solve the mentioned problems. Dynamic parameter-control chaotic system can enhance the sequence’s randomness after digitalizing. Corresponding the different sequences generated by the novel chaotic system to each color channel of image is a helpful method to reduce the image’s statistical characteristics in the scrambling process. Finally, the effectiveness and security of the proposed encryption has been illustrated by the experimental, and at the meantime, excellent performance is also demonstrated.

Urban building energy analysis has attracted more attention as the population living in cities increases as does the associated energy consumption in urban environments. This paper proposes a systematic bottom-up method to conduct energy analysis and assess energy saving potentials by combining dynamic engineering-based energy models, machine learning models, and global sensitivity analysis within the GIS (Geographic Information System) environment for large-scale urban buildings. This method includes five steps: database construction of building parameters, automation of creating building models at the GIS environment, construction of machine learning models for building energy assessment, sensitivity analysis for choosing energy saving measures, and GIS visual evaluation of energy saving schemes. Campus buildings in Tianjin (China) are used as a case study to demonstrate the application of the method proposed in this research. The results indicate that the method proposed here can provide reliable and fast analysis to evaluate the energy performance of urban buildings and determine effective energy saving measures to reduce energy consumption of urban buildings. Moreover, the GIS-based analysis is very useful to both create energy models of buildings and display energy analysis results for urban buildings.

Machine learning techniques have attracted more attention as advanced data analytics in building energy analysis. However, most of previous studies are only focused on the prediction capability of machine learning algorithms to provide reliable energy estimation in buildings. Machine learning also has great potentials to identify energy patterns for urban buildings except for model prediction. Therefore, this paper explores energy characteristic of London domestic properties using ten machine learning algorithms from three aspects: tuning process of learning model; variable importance; spatial analysis of model discrepancy. The results indicate that the combination of these three aspects can provide insights on energy patterns for urban buildings. The tuning process of these models indicates that gas use models should have more terms in comparison with electricity in London and the interaction terms should be considered in both gas and electricity models. The rankings of important variables are very different for gas and electricity prediction in London residential buildings, which suggests that gas and electricity use are affected by different physical and social factors. Moreover, the importance levels for these key variables are markedly different for gas and electricity consumption. There are much more important variables for electricity use in comparison with gas use for the importance levels over 40. The areas with larger model discrepancies can be determined using the local spatial analysis based on these machine learning models. These identified areas have significantly different energy patterns for gas and electricity use. More research is required to understand these unusual patterns of energy use in these areas.

Energy performance of urban buildings is affected by a number of inherent uncertain factors, including weather conditions, internal heat gains, occupant behavior, and HVAC systems. These uncertain variables lead to variations of energy use in urban buildings. Therefore, this paper implements a two-dimensional Monte Carlo method to properly assess variations of energy performance of urban buildings by considering two types of uncertain factors (aleatory and epistemic). In this study, aleatory uncertainty refers to inherent randomness of input variables in building energy analysis; whereas, epistemic uncertainty refers to retrofit variations to improve energy efficiency for urban buildings. The results indicate that the two-dimensional Monte Carlo technique can consider two types of uncertain factors to quantify the variations of energy performance in urban buildings. It is also found that the aleatory uncertainty of energy performance is larger than the epistemic uncertainty of energy use in this study, which indicates that more attention should be paid on aleatory uncertainty to reduce its influence on energy use.

Variance-based sensitivity analysis in combination with machine-learning techniques has been increasingly applied in energy analysis of buildings in order to reduce computational cost of running a large number of energy models with sufficient accuracy. This paper compares the performance of two sensitivity analysis methods based on machine-learning models for building energy assessment: multivariate adaptive regression splines (MARS) and Cubist (CB). An office building located in Tianjin, China, is used as a case study with the EnergyPlus simulation program, to study the characteristics of these two sensitivity analysis methods. The results indicate that sufficient sample number is required to obtain reliable sensitivity analysis results in building energy assessment and subsequent HVAC system design and sizing. It is recommended to use at least two machine-learning models for variance-based sensitivity methods to allow the comparison of ranking results. The consistency of results from these learning methods should be thoroughly checked since the parameters in tuning these machine-learning models have significant influences on ranking results.

Machine learning models have been widely used in building energy assessment to provide fast and reliable energy estimation. To validate these machine learning models, the cross-validation technique has been often used to estimate model accuracy. However, most cross-validation methods are used without repetition to have only one value that may have large variations due to different sampling seeds. Therefore, this paper applies repeated cross validation to provide reliable model accuracy with small variations. An office building with ten input variables is used as case study to demonstrate the performance of cross validation in building energy analysis. The results indicate that repeated cross validation can have stable results with sufficient sampling data available and medium fold number (ten in this case). At least 200 sampling number is required to obtain reliable model accuracy estimation. Ten times of cross validation is recommended to reduce the variations of model accuracy.

This study aimed to investigate the applicability of the solar heating system in different geographical regions with different meteorological conditions, of which parabolic trough solar collectors (PTCs) were operated with the absorption heat pumps (AHP) and oil/water heat exchanger (OWHE) at medium and low operating temperature respectively. The heat transfer model for PTCs was constructed with a lumped parameter method and validated by experimental results. The thermal performance of the system was evaluated by the index of primary energy ratio (PER). The results showed that on overcast days with low direct normal irradiance (DNI), the operation of the PTC + AHP/OWHE system was not cost-effective. On cloudy days with high DNI lasting for a short period (e.g. 2 h), the operation of the PTC + OWHE system was better than that of the PTC + AHP system as the latter needed more preheating energy before the system operation. While on sunny days with high DNI lasting for a longer period (e.g. 8 h), the PTC + AHP system was suggested to be operated as it owned higher PER values. Besides, the solar energy distributions in China could be divided into four categories, i.e. rich (S1), relatively rich (S2), available (S3) and absent (S4). In S1 region the PTC + AHP system was suggested to be operated. In S4 region the PTC + AHP/OWHE system was not suggested to be operated. While in S2 and S3 region, whether the operation of the PTC + AHP/OWHE system was suggested depending on the meteorological conditions. With these findings the developing strategy of the solar heating system in different geographical regions can be devised and the operating strategy on a specific day with different weather conditions can be developed, which is helpful to guide the application of solar energy and improve the energy structure in domestic heating.

Uncertainty analysis has become an active research area in the field of building energy analysis because most of parameters are inherently uncertain in buildings. Most of previous studies implement probabilistic-based uncertainty analysis, which requires detailed information to define probability for input factors. However, it is hard to obtain detailed information for these inputs, especially at the initial design stage of a building project. Therefore, this paper applies the non-probabilistic Dempster-Shafer theory of evidence approach for uncertainty analysis in an office building using the EnergyPlus program. The results indicate that the Dempster-Shafer theory can be very useful to provide pertinent and reliable results by taking into account the level of available information in the design stage of building projects for sustainable buildings. The reliable machine learning models can be constructed in order to reduce high computational cost of this non-probabilistic uncertainty analysis method.

Sensitivity analysis has been widely used in building energy assessment to provide reliable analysis of importance ranking for input variables in buildings. Most of previous studies used one single batch simulation models to obtain sensitivity indicators. To conduct robust analysis, this paper implements a sequential sensitivity analysis to assess the convergence of sensitivity indicators for two global sampling-based sensitivity analysis methods (standardized regression coefficients and meta-modelling Sobol) in an office building. The results indicate that this sequential method can be more effective and robust. In contrast, a single batch sensitivity method for building energy assessment may lead to non-convergence results due to smaller number of simulation models or over-convergence results due to larger number of simulation models. It is also found that the convergence rate for standardized regression methods are slower than that for the meta-modelling Sobol method.

Sustainable building design needs to consider uncertainty due to various sources, including weather condition, design uncertainty, and inherent random parameters, in order to maintain high performance. These different types of uncertainty requires more advanced computational methods. Therefore, this paper implements a second order probability approach to take into account two types of uncertainty: aleatory (inherent randomness) and epistemic (incomplete information). A retail building located in Tianjin (China) is used to demonstrate the application of this second order probability approach. The results indicate that this second order probability can deal with these two types of uncertainty in sustainable building design. This method can also provide insight on the dominance of design uncertainty or inherent aleatory uncertainty. Moreover, the variable importance method based on a locally weighted regression model is applied to determine the key variables influencing both aleatory and epistemic uncertainty of energy use for this retail building.

Agricultural Text-to-Speech (TTS) has attracted increasingly more attention. The application of agricultural TTS and its problems are analyzed in this paper, and the traditional framework of the TTS system and its key technologies, i.e., text analysis, rhythm generation and speech synthesis are discussed. Furthermore, two advancements in agricultural TTS, the word segmentation of analytic language and the deep learning-based end-to-end TTS system, are detailed summarized. Based on the characteristics of agriculture, some appealing research directions are pointed out: how to improve the training speed and synthesis speed of the deep learning models is still the focus; the study on the approaches of weakly-supervised learning in TTS is in fancy; and research on the real-time and high-quality speech synthesis that can be deployed in mobile devices is a key point of agricultural TTS research.

Bayesian analysis has attracted more attention in calibrating building energy models since it can naturally account for uncertainty of input parameters. However, standard Bayesian analysis requires to compute likelihood functions to represent the probability of the observed data under a statistical energy model. This makes the implementation of standard Bayesian analysis difficult for calibrating dynamic building energy models. Therefore, this research proposes a new Bayesian method by combining the approximate Bayesian computation with machine learning techniques in calibrating building models without computing likelihood functions. The results indicate that this new Bayesian computation approach combined with the machine learning algorithms can provide fast and reliable calibration for building energy models created using the EnergyPlus program. The calibration metrics in terms of the coefficient variations of root mean square errors from this new Bayesian method are well below the threshold value (15%) recommended from the ASHRAE standard for monthly energy data. Moreover, the better calibration results can be obtained by using linear or nonlinear post-adjustment techniques to account for the differences between the simulated and observed energy data. The method proposed here can significantly extend the application of Bayesian analysis in calibrating building energy models under uncertainty due to its simplicity and fast computation. Furthermore, the new Bayesian approach combined with machine learning technique can also be used to calibrate the simulation-based models for various types of energy systems.

Direct liquid-immersion cooling of solar cells using dimethyl silicon oil is proposed as a heat dissipation solution for linear CPV (concentrating photovoltaic) systems. To reduce the liquid holdup, a narrow rectangular channel receiver was designed and its heat transfer performance was investigated experimentally at an energy flux ratio of 9.1 suns. Long-term stability of mono-crystalline concentrator silicon solar cells immersed in dimethyl silicon oil with viscosity of 2 mm 2 /s was monitored under real climate conditions. Experimental results show that the liquid-immersion cooling capacity in the designed receiver is favorable. The cell temperature can be controlled in the range of 20–31 °C at a 910 W/m 2 DNI (direct normal irradiance), 15 °C silicon oil inlet temperature and Re numbers (Reynolds) variation from 13,602 to 2720. The cell temperature distribution is quite uniform, and a general correlation of Nu number (Nusselt) was obtained. The electrical performance of the cells immersed in the silicon oil is stable and no obvious efficiency degradation was observed after immersed for 270 days.

This paper combines with building production energy and distributed energy system, putting forward the link of building hybrid energy system and distributed power generation system, which according to the characteristics of architecture space and internal demand of building hybrid energy system, through distributed the miniature, micro intelligent, cascaded utilization of energy in the user end, coordination with the various renewable energies as near as to meet the demand of users in multiple aspects of electricity, heating, cooling, domestic hot water, dehumidification, air etc, realizing the depth utilization of resources system, so that every construction project can base on its own resources, optimizing the best combination way, realizing optimum utility of energy and integrated system.

Distributed energy system (DES) has become the main development tendency of future power generation system. DES refers to a power generating system, cogeneration system and poly generation power system without bulk power transmission to remote areas, which can be in accordance with the energy requirements of user and which makes use of a series of system that can satisfy environmental protection and that is suitable for being in or close to the load center. If joint with the large electrical networks reasonability, it will improve the efficiency, quality and security of power supply greatly; reduce the environmental pollution and the pressure of the rising energy requirements to the power networks. This paper combines with the integrated solar building, the security need of urban energy, putting forward the construction of urban energy organic networks, which is designed to expand the means of networks energy, optimize integration energy system, guide urban development with the minimum ecological and resource cost, and to get the maximum benefit in a wide range of areas.

In view of computer technology widespread application in building where all kinds of information convergence, proposing the building numerical information integration, which aims at impelling the level conformity information of building, providing the advantageous support for intelligent building, the ecologically-safe building, and the energy efficiency of building, exploring the new direction of building development. As the high and new technology develops unceasingly, as information technology shows importantly, in the future, the application must establish above the gradient network, which also has the good artificial interaction ability and multi-dimensional information-handling capacity. As the exchange's medium of people and nature, building has the multi-dimensional information attribute, which inevitably requests the building information be digitization and integration.