Adsorption cooling and desalination technologies have recently received more attention. Adsorption chillers, using eco-friendly refrigerants, provide promising abilities for low-grade waste heat recovery and utilization, especially renewable and waste heat of the near ambient temperature. However, due to the low coefficient of performance (COP) and cooling capacity (CC) of the chillers, they have not been widely commercialized. Although operating in combined heating and cooling (HC) systems, adsorption chillers allow more efficient conversion and management of low-grade sources of thermal energy, their operation is still not sufficiently recognized, and the improvement of their performance is still a challenging task. The paper introduces an artificial intelligence (AI) approach for the optimization study of a two-bed adsorption chiller operating in an existing combined HC system, driven by low-temperature heat from cogeneration. Artificial neural networks are employed to develop a model that allows estimating the behavior of the chiller. Two crucial energy efficiency and performance indicators of the adsorption chiller, i.e., CC and the COP, are examined during the study for different operating sceneries and a wide range of operating conditions. Thus this work provides useful guidance for the operating conditions of the adsorption chiller integrated into the HC system. For the considered range of input parameters, the highest CC and COP are equal to 12.7 and 0.65 kW, respectively. The developed model, based on the neurocomputing approach, constitutes an easy-to-use and powerful optimization tool for the adsorption chiller operating in the complex HC system.
2
Dostęp do pełnego tekstu na zewnętrznej witrynie WWW
Blasting is an intrinsic component of mining cycle of operation. However, it is usually associated with negative environmental efects such as blast-induced ground vibration (BIGV) which require accurate prediction and control. Therefore, in this study, Gaussian process regression (GPR) has been proposed for prediction of BIGV in terms of peak particle velocity (PPV), while grey-wolf optimization (GWO) algorithm has been used to optimize the blast-design parameters for the control of BIGV in Obajana limestone quarry, Nigeria. The blast-design parameters such as burden (B), spacing (S), hole depth (Hd), stemming length (T), and number of holes (nh) were obtained from the quarry. The distance from the blasting point to the measuring point (D) and the charge per delay (W) were measured and determined, respectively. The PPV was also measured for the number of blasting operations witnessed. These seven parameters were used as inputs to the proposed GPR model, while the PPV was the targeted output. The performance of the proposed model was evaluated using some statistical indices. The output of the GPR model was compared with ANN model and three empirical models, and the GPR model proved to be more accurate with the coefcient of determination (R2 ) of approximately 1 and variance accounted for VAF of about 100%, respectively. In addition, the GWO was also developed to select the optimum blasting parameters using the ANN model for the generation of objective function. The output of the GWO revealed that if the number of holes (nh) can be reduced by 45% and W by 8%, the PPV will be reduced by about 94%. Hence, the proposed models are both suitable for prediction of PPV and optimization of blast-design parameters.
3
Dostęp do pełnego tekstu na zewnętrznej witrynie WWW
In this paper we present OvaExpert, an intelligent system for ovarian tumor diagnosis. We give an overview of its features and main design assumptions. As a theoretical framework the system uses fuzzy set theory and other soft computing techniques. This makes it possible to handle uncertainty and incompleteness of the data, which is a unique feature of the developed system. The main advantage of OvaExpert is its modular architecture which allows seamless extension of system capabilities. Three diagnostic modules are described, along with examples. The first module is based on aggregation of existing prognostic models for ovarian tumor. The second presents the novel concept of an Interval-Valued Fuzzy Classifier which is able to operate under data incompleteness and uncertainty. The third approach draws from cardinality theory of fuzzy sets and IVFSs and leads to a bipolar result that supports or rejects certain diagnoses.
This paper presents two innovative evolutionary-neural systems based on feed-forward and recurrent neural networks used for quantitative analysis. These systems have been applied for approximation of phenol concentration. Their performance was compared against the conventional methods of artificial intelligence (artificial neural networks, fuzzy logic and genetic algorithms). The proposed systems are a combination of data preprocessing methods, genetic algorithms and the Levenberg–Marquardt (LM) algorithm used for learning feed forward and recurrent neural networks. The initial weights and biases of neural networks chosen by the use of a genetic algorithm are then tuned with an LM algorithm. The evaluation is made on the basis of accuracy and complexity criteria. The main advantage of proposed systems is the elimination of random selection of the network weights and biases, resulting in increased efficiency of the systems.
5
Dostęp do pełnego tekstu na zewnętrznej witrynie WWW
In this article application of Principal Component Analysis pre-processing, clustering, and automatic dependency modelling methods for extracting diagnostic knowledge was presented. These methods were implemented using neural networks and fuzzy logic. The case study were signals measured on 200 MW power plant turboset.
PL
W artykule przedstawiono zastosowania Analizy Czynników Głównych do wstępnego przetwarzania i grupowania oraz zastosowania metod automatycznego modelowania zależności dla pozyskiwania wiedzy diagnostycznej. Dokonano implementacji tych metod wykorzystując sztuczne sieci neuronowe i logikę rozmytą. Przykładowe efekty ich działania otrzymano analizując sygnały zbierane w trakcie eksploatacji bloku energetycznego 200 MW.
JavaScript jest wyłączony w Twojej przeglądarce internetowej. Włącz go, a następnie odśwież stronę, aby móc w pełni z niej korzystać.