Search

Demand control ventilation is employed to save energy by adjusting airflow rate according to the ventilation load of a building. This paper investigates a method for occupancy estimation by using a dynamic neural network model based on carbon dioxide concentration in an occupied zone. The method can be applied to most commercial and residential buildings where human effluents to be ventilated. An indoor simulation program CONTAMW is used to generate indoor CO2 data corresponding to various occupancy schedules and airflow patterns to train neural network models. Coefficients of variation are obtained depending on the complexities of the physical parameters as well as the system parameters of neural networks, such as the numbers of hidden neurons and tapped delay lines. We intend to identify the uncertainties caused by the model parameters themselves, by excluding uncertainties in input data inherent in measurement. Our results show estimation accuracy is highly influenced by the frequency of occupancy variation but not significantly influenced by fluctuation in the airflow rate. Furthermore, we discuss the applicability and validity of the present method based on passive environmental conditions for estimating occupancy in a room from the viewpoint of demand control ventilation applications. [ABSTRACT FROM AUTHOR]

This paper proposes a neural network (NN)-based approach to solve the forward kinematics of a 3-RRR spherical parallel mechanism designed for a haptic device. The proposed algorithm aims to remarkably speed up computation to meet the requirement of highfrequency rendering for haptic display. To achieve high accuracy, the workspace of the haptic device is divided into smaller subspaces. The proposed algorithm contains NNs of two different precision levels: a rough estimation NN to identify the index of the subspace and several precise estimation networks with expected accuracy to calculate the forward kinematics. For continuous motion, the algorithm structure is further simplified to save internal memory and increase computing speed, which are critical for a haptic device control system running on an embedded platform. Compared with the mostly used Newton-Raphson method, the proposed algorithm and its simplified version greatly increase the calculation speed by about four times and 10 times, respectively, while achieving the same accuracy level. The proposed approach is of great significance for solving the forward kinematics of parallel mechanism used as haptic devices when high update frequency is needed but hardware resources are limited. [ABSTRACT FROM AUTHOR]

The conceptual design selection, which aims at choosing the best or most desirable design scheme among several candidates for the subsequent detailed design stage, oftentimes requires a set of tools to conduct design evaluation. Using computational intelligence techniques, such as fuzzy logic, neural network, genetic algorithm, and physical programming, several design evaluation methods are put forth in this paper to realize the conceptual design selection under different scenarios. Depending on whether an evaluation criterion can be quantified or not, the linear physical programming (LPP) model and the RAOGA-based fuzzy neural network (FNN) model can be utilized to evaluate design alternatives in conceptual design stage. Furthermore, on the basis of Vanegas and Labib's work, a multi-level conceptual design evaluation model based on the new fuzzy weighted average (NFWA) and the fuzzy compromise decision-making method is developed to solve the design evaluation problem consisting of many hierarchical criteria. The effectiveness of the proposed methods is demonstrated via several illustrative examples. [ABSTRACT FROM AUTHOR]

A method based on the theory of deep learning and feature extraction and a fault diagnosis model of a rolling bearing based on deep belief network are proposed in this study considering the complex, nonlinear, and non-stationary vibration signal of the rolling bearing. To some extent, the method avoids the complex structure of deep neural network and can be easily trained. Experimental results show that the recognition rate of the method reaches 100 %. The method can identify various types of faults accurately and has good fault diagnosis capability, which can provide the convenience for maintenance. [ABSTRACT FROM AUTHOR]

This study proposes a novel intelligent fault diagnosis method for rotating machinery using ant colony optimization (ACO) and possibility theory. The non-dimensional symptom parameters (NSPs) in the frequency domain are defined to reflect the features of the vibration signals measured in each state. A sensitive evaluation method for selecting good symptom parameters using principal component analysis (PCA) is proposed for detecting and distinguishing faults in rotating machinery. By using ACO clustering algorithm, the synthesizing symptom parameters (SSP) for condition diagnosis are obtained. A fuzzy diagnosis method using sequential inference and possibility theory is also proposed, by which the conditions of the machinery can be identified sequentially. Lastly, the proposed method is compared with a conventional neural networks (NN) method. Practical examples of diagnosis for a V-belt driving equipment used in a centrifugal fan are provided to verify the effectiveness of the proposed method. The results verify that the faults that often occur in V-belt driving equipment, such as a pulley defect state, a belt defect state and a belt looseness state, are effectively identified by the proposed method, while these faults are difficult to detect using conventional NN. [ABSTRACT FROM AUTHOR]

A model was proposed for optimization of stereolithography (SLA) process parameters to achieve the minimum shrinkage of H-shaped parts. A neural network was designed to correlate the input parameters to dimensional error of the parts manufactured by SLA. For this purpose, the data of a previous study from the literature was used that investigated the effect of three important parameters (layer thickness, hatch overcure and hatch spacing) of the SLA process by measuring the H-shaped parts manufactured by SLA 250. Then, the neural network model was imported into two optimization algorithms (genetic algorithm and simulated annealing) and the optimal values were determined. Results showed that the combination of neural network and optimization algorithms could determine the optimal input parameters for the minimum shrinkage with good accuracy. [ABSTRACT FROM AUTHOR]