[en] Recent research on deep learning control, a new control algorithm based on machine learning able to learn deep architectures, has shown excellent performance on robots and drones. With the development of intelligent control like deep learning and reinforcement learning, accuracy, real-time, adaptability, robustness and autonomy of control algorithm have been achieved by the intelligent controls. Traditional control methods have difficulties to achieve nice performance in complex situations. Deep learning offers powerful algorithms to real-time search near-optimal controllers of lunar landing spacecraft with nonlinear dynamics. In terms of lunar landing control system, deep architectures offer the possibility to get an approximate solution of co-state equation without time-consuming iterative process. Furthermore, real-time optimal thrust during lunar landing may be derived directly through deep neural networks. As a single infrastructure for machine learning in both production and research, TensorFlow is chosen for training the deep artificial neural networks in this paper. Numerical simulations demonstrate the effectiveness of deep neural networks. The results of deep neural networks based optimal control are contrasted with traditional optimal algorithm, whose main idea is to track the pre-designed optimal trajectory by ground station. This research provides an effective approach to cope with the lunar landing problem. (paper)

[en] Conventional circulation control technology presents problems in certain situations. Pulsed jet circulation control appears to be a feasible alternative to solve such problems, especially for the high-frequency pulsed jet (HFPJ). To acquire the aerodynamic characteristics of the HFPJ and reveal the mechanism behind it, numerical simulation is conducted using a verified computational fluid dynamics (CFD) method. The action mode of the pulsed jet characterized by equilibrium and oscillation is proposed according to the analysis of a dynamic procedure. Lift and drag characteristics are obtained, defining the critical frequency to demarcate high and low frequencies. An oscillation function is also established to illustrate the difference between the characteristics of the HFPJ and a low-frequency pulsed jet (LFPJ) by analyzing the simulation results. The pressure distribution and flow field in the simulation results explain the stall characteristic of the HFPJ. Series results indicate the HFPJ demonstrates superior lift augmentation and drag reduction compared to the LFPJ and steady jets. (paper)

[en] This paper uses Monte Carlo Analysis (MCA) for sensitivity analysis of the influence of sunlight shading and ventilation performance of classrooms in Taiwan on students’ cumulative overheating risk and average learning efficiency. The parameters influencing the sunlight shading and ventilation performance of classrooms include window orientation, window opening rate, ventilation rate, and external shading depth. EnergyPlus and local TMY3 weather data are used to simulate the hourly thermal environment conditions of 400 sample classrooms in two climatic regions (Taipei and Kaohsiung). The sensitivity of design parameters to the thermal risk of naturally ventilated classrooms and students’ learning efficiency is judged by using standardized regression coefficient, and the order of importance is window opening rate, ventilation rate, orientation, and external shading depth. (paper)

[en] A spectroscopy and visual investigation for turbulent swirling flames formed by four-circumferential swirling turbojet EV in comparison with a two-circumferential swirling air entries configuration burner using hyper spectral camera. The special design of the EV-burner guarantees flame stabilization at the burner exit by a recirculation of hot gases and entrained fresh reactance mixture. A recirculation zone (vortex breakdown) can be generated when a sufficient strong swirling flow exist. The main parameter of combustion diagnostics based on optical devices is the flame itself, whose spectrum is closely related to the process state, as a fingerprint of the instantaneous operational condition, in terms of energetic yield, fuel consumption and pollutants emissions. The hyperspectral imaging technique in the aspect of flame analysis to give a complete description for the flame zones behavior and distribution of reactions through the whole flame. The spectral peaks for issued flames have been studied to give complete vision for the effect of changing the equivalence ratio and different burner arrangement four and two circumferential swirling entries. (paper)

[en] Parallel Robot (PR) has shown its ability to be precise in its movement. Actuators move simultaneously to achieve the required target, on top of that its payload is much greater than what a serial robot can withstand. To determine workspace of the robot with known angles Forward kinematics has to be introduced which, bring a lot of difficulty as it requires the solution of multiple coupled nonlinear algebraic equations. Those equations bring multiple valid solutions. Those solutions could lead to different locations. As it is not going to make the pick and place for PR will be easier. This paper will discuss a numerical method that calculates the Forward Kinematics for PR. This method uses Artificial Neural Network which relay on training with a certain number of iterations. The set of data to be used in the training can be obtained from PR simulation. This method will serve to know workspace around PR as it will help it to pick the target object. (paper)

[en] As a basis for energy management in apartment blocks, this paper characterises heat use in a large housing cooperative in Norway, with in total 1,058 apartments. Heat measurements with hourly resolution are available from 20 heating substations. Average specific heat delivery is 139 kWh per heated floor area. A linear regression model is described, modelling specific heat delivered to the apartments. Models are also used for separating heat to domestic hot water (DHW) from the total heat delivery, with a modelled DHW heat delivery of 34 kWh/m². Daily heat load profiles are presented, for delivered heat during weekdays and holidays in the annual seasons. The study shows a potential for shifting heat loads in time on a neighbourhood level. (paper)

[en] In Canada, space heating accounts for the largest proportion of energy consumption in residential buildings. Therefore, accurately predicting the heating demand and interior temperature of a residential building plays a vital role in estimating the building’s total energy consumption with the consideration of thermal comfort. The prediction results obtained through different models could be used to develop predictive controllers to achieve peak shifting as well as to provide utility providers with valuable information for electric power distribution. Common methods to predict heating demand mainly include physical models and statistical methods. This study used two physical models (i.e. TRNSYS model and TRNSYS-CONTAM model) and one statistical model using supervised machine learning algorithm to predict the heating demand as well as the indoor temperature of a residential building, located in Quebec, Canada. Results show that TRNSYS-CONTAM model has higher accuracy than TRNSYS model no matter in terms of interior air temperature or heating demand prediction, while the statistical model shows better interior air temperature prediction result than physical models. (paper)

[en] Based on the characteristics of climatic conditions and intermittent energy use in the hot summer and cold winter regions, this paper takes a simplified residential building in Chongqing as an example, use DesignBuilder to simulate and explore the influence of passive methods on the indoor thermal environment and energy consumption of buildings. To make the cooling method used more in line with the actual situation of the residents, this research uses the passive cooling technology such as sunshades and ventilation, and combine them with the intermittent operated air conditioner to achieve a comfortable condition in the room. Under the thermal parameters of the building envelopes were set according to the current 65% energy-saving standards, the results show that the sunshade combined with the intermittent ventilation can extend the non-air-conditioning period of 2041 hours. The building energy consumption of the method combined intermittent air conditioner with sunshade and intermittent ventilation is 22.2 Kwh/m², which is 56.5% lower than the continuous air conditioner operation. (paper)

[en] This research is dedicated to the development of a multi criteria analysis method to optimize the sustainable architectural design of residential buildings. In this perspective, four axes have been chosen on the entire building life cycle: energy, ecology, health (including well-being) and economy. The building setting will be evaluated as its typology, its size, its construction method, the choice of the materials and of the systems implemented, since all these elements influence energy consumptions, environmental impacts, users’ health and financial costs. In order to be able to compare the four dimensions of this assessment, the developed methodology is based on the translation of energy consumption, environmental impacts and health impacts into energy costs, environmental costs and health costs, which makes them comparable to the building life cycle costs. According to users’ selection of the optimization axis and various optimization and design parameters, based on predefined options, this methodology will produce optimal solutions. Finally, this method will be useful for improving the sustainable performances of buildings, helping to create energy-efficient, ecological, healthy and affordable housing projects. (paper)

[en] Due to the Energy Performance of Building Directive 2010/31/UE (EPBD) recast, new and existing buildings have the aim to achieve the Zero Energy Buildings (ZEBs) requirements, in order to reduce the carbon emission and the energy building demand. Therefore, the building process cost is increasing, related to the applications of performant construction and efficiencies energy systems. In literature, several studies highlight the importance of innovative approaches in order to reduce the cost of the ZEB targets achievement, during the early stage design process. In this framework, Building Information Modeling (BIM) is a useful process that integrated building design since the first design stage, providing high-performance energy solutions and obtaining a single model reducing time and cost during the building design. In fact, in Italy, the regulatory obligations are progressively defined: with the Ministerial Decree 560 of 1 December 2017 (Baratono Decree), the time scale with which the obligation to use BIM will come into force has been established. The obligation started from 1 January 2019 for public tenders for an amount equal to or greater than 100 million euros, then there will be a gradual entry up to 2025 for public works contracts worth less than one million. The research proposes a new workflow that allows to performing energy analysis through the BIM and Building Energy Modeling (BEM) optimization interoperability, allowing to support the zero-energy building during the early stage design. (paper)