This paper describes an optimization procedure to modify the geometry of a mixed-flow turbocharger turbine for improved aerodynamic efficiency. The procedure integrates parameterization of the turbine blade geometry, genetic algorithm optimization, and 3D CFD analysis using a commercial solver. Using a known mixed-flow turbocharger turbine as the baseline, the main features of the blade geometry — the hub, shroud, camberline, leading and trailing edge profiles — were separately adjusted by the genetic algorithm in the direction of better efficiency. Apart from optimizing the subject turbine for the operating point in question, more usefully this permits each geometrical feature to be ranked by their contribution to the change in efficiency. Cases were also run in which the hub and shroud curves were simultaneously adjusted. Analysis of CFD results provides additional insight into the underlying reasons for efficiency changes by examination of the relevant flow field features. The hub and shroud profiles were observed to have the greatest impact on turbine performance, optimization of which leads to an increase of 1.3 percentage points of efficiency. This compares to only 0.2 percentage points improvement following optimization of the outlet geometry.

To improve consumer experience and overall retail management, physical retailers may adapt consumer behaviour management systems using artificial intelligence to imitate the capability of consumer behaviour tracking in online shopping into physical retail. The proposed consumer behaviour management system consists of two parts - face recognition and consumer tracking at an area of interest. Both will be combined to produce a summary of individual customer’s visits to the shop. This information can be used to improve consumers experience and optimize retailer’s management. The developed system can track consumers’ movement inside the shop and summarize their whereabouts according to areas of interest. The face classification system via FaceNet has around 56.67% accuracy with 27.89% mean confidence. The tracking performance shows a consistent performance with a total standard deviation of 4.36 seconds. With the consumers’ analysis graph, retailers may pinpoint which area that was always frequented by their customers and take suitable actions with that information

Channel selection is an improvement technique to optimize EEG-based BCI performance.In previous studies, many channel selection methods-mostly based on spatial information of signals-have been introduced. One of these channel selection techniques is the energy calculation method. In this paper, we introduce an energy optimization calculation method, called the energy extraction method. Energy extraction is an extension of the energy calculation method, and is divided into two steps. The first step is energy calculation and the second is energy selection. In the energy calculation step, l2-norm is used to calculate channel energy, while in the energy selection method we propose three techniques: "high value" (HV), "close to mean" (CM), and "automatic". All proposed framework schemes for energy extraction are applied in two types of datasets. Two classes of datasets i.e. motor movement (hand and foot movement) and motor imagery (imagination of left-and right-hand movement) were used. The system used a Common Spatial Pattern (CSP) method to extract EEG signal features and k-NN as a classification method to classify the signal features with k=3. Based on the test results, all schemes for the proposed energy extraction method yielded improved BCI performance of up to 58%. In summary, the energy extraction approach using the CM energy selection method was found to be the best channel selection technique.

No abstract

Designing a suitable controller for air-conditioning systems to reduce energy consumption and simultaneously meet the requirements of the system is very challenging. Important factors such as stability and performance of the designed controllers should be investigated to ensure the effectiveness of these controllers. In this article, the stability and performance of the fuzzy cognitive map (FCM) controller are investigated. The FCM method is used to control the direct expansion air conditioning system (DX A/C). The FCM controller has the ability to do online learning, and can achieve fast convergence thanks to its simple mathematical computation. The stability analysis of the controller was conducted using both fuzzy bidirectional associative memories (FBAMs) and the Lyapunov function. The performances of the controller were tested based on its ability for reference tracking and disturbance rejection. On the basis of the stability analysis using FBAMS and Lyapunov functions, the system is globally stable. The controller is able to track the set point faithfully, maintaining the temperature and humidity at the desired value. In order to simulate the disturbances, heat and moisture load changed to measure the ability of the controller to reject the disturbance. The results showed that the proposed controller can track the set point and has a good ability for disturbance rejection, making it an effective controller to be employed in the DX A/C system and suitable for a nonlinear robust control system. Nowadays, the use of different controllers on HVAC systems is considered as an important issue, with the aim of increasing the system performance, by reason of their high installation demand in buildings and their huge energy consumption.The direct expansion air-conditioning (DX A/C) system is considered as a subgroup of HVAC systems. The mentioned system has two types of units, window units and split units, which are frequently employed in small-to medium-sized buildings by reason of having a simple configuration, low cost maintenance, and higher energy efficiency [3,4].According to the authors of [2], energy efficacy and indoor thermal conditions are the main objectives one needs to take into account when designing HVAC or A/C systems. Because of the complicated features of HVAC and A/C systems, attaining the mathematical model of HVAC and air conditioning systems is intricate and difficult. Likewise, designing an appropriate controller becomes a big challenge [5,6]. HVAC system is a multiple-Input and multiple-output (MIMO) system, sometimes with coupled parameters [7]. Moreover, it is a complex nonlinear system, which makes deriving the exact mathematical model a challenging task [3]. Consequently, the control system must be able to deal simultaneously with cross-coupling effects, nonlinearity, and uncertainty of the system. The high energy consumption of these systems calls for an intelligent control system that can adjust the parameters according to the systems' demands, so that it could prevent energy loss and b...