• Nuclear Engineering and Technology
• /
• 제53권12호
• /
• pp.3944-3951
• /
• 2021

Several reasons such as no free lunch theorem indicate that there is not a universal Feature selection (FS) technique that outperforms other ones. Moreover, some approaches such as using synthetic dataset, in presence of large number of FS techniques, are very tedious and time consuming task. In this study to tackle the issue of dependency of estimation accuracy on the selected FS technique, a methodology based on the heterogeneous ensemble is proposed. The performance of the major learning algorithms of neural network (i.e. the FFNN-BR, the FFNN-LM) in combination with the diverse FS techniques (i.e. the NCA, the F-test, the Kendall's tau, the Pearson, the Spearman, and the Relief) and different combination techniques of the heterogeneous ensemble (i.e. the Min, the Median, the Arithmetic mean, and the Geometric mean) are considered. The target parameters/transients of Bushehr nuclear power plant (BNPP) are examined as the case study. The results show that the Min combination technique gives the more accurate estimation. Therefore, if the number of FS techniques is m and the number of learning algorithms is n, by the heterogeneous ensemble, the search space for acceptable estimation of the target parameters may be reduced from n × m to n × 1. The proposed methodology gives a simple and practical approach for more reliable and more accurate estimation of the target parameters compared to the methods such as the use of synthetic dataset or trial and error methods.

• Smart Structures and Systems
• /
• 제29권2호
• /
• pp.337-350
• /
• 2022

This paper focuses on predicting the post-heating mechanical properties of cementitious composites reinforced with multi-scale additives using the Artificial Neural Network (ANN) approach. A total of four different feed-forward ANN models are developed using 261 data sets collected from 18 published sources. The models are optimized using 12 input parameters selected based on a comprehensive literature review to predict the residual compressive strength, the residual flexural strengths, elastic modulus, and fracture energy of heat-damaged cementitious specimens. Furthermore, the ANN is employed to predict the impact of several variables including; the content of polypropylene (PP) microfibers and carbon nanotubes (CNTs) used in the concrete, mortar, or paste mix design, length of PP fibers, the average diameter of CNTs, and the average length of CNTs. The influence of the studied parameters is investigated at different heating levels ranged from 25℃ to 800℃. The results demonstrate that the developed ANN models have a strong potential for predicting the mechanical properties of the heated cementitious composites based on the mixing ingredients in addition to the heating conditions.

• Korean Chemical Engineering Research
• /
• 제61권2호
• /
• pp.328-339
• /
• 2023

Methanol steam reforming (MSR) is a promising method for hydrogen supplying as a critical step in hydrogen fuel cell commercialization in mobile applications. Modelling and understanding of the reactor behavior is an attractive research field to develop an efficient reformer. Three-layer feed-forward artificial neural network (ANN) and Box-Behnken design (BBD) were used to modelling of MSR process using the Cu-SiO₂ aerogel catalyst. Furthermore, impacts of the basic operational variables and their mutual interactions were studied. The results showed that the most affecting parameters were the reaction temperature (56%) and its quadratic term (20.5%). In addition, it was also found that the interaction between temperature and Steam/Methanol ratio is important on the MSR performance. These models precisely predict MSR performance and have great agreement with experimental results. However, on the basis of statistical criteria the ANN technique showed the greater modelling ability as compared with statistical BBD approach.

• 대한기계학회논문집A
• /
• 제31권1호
• /
• pp.26-35
• /
• 2007

The vehicle of urban transit is a complex system that consists of various electric, electronic, and mechanical equipments, and the maintenance cost of this complex and large-scale system generally occupies sixty percent of the LCC (Life Cycle Cost). For reasonable establishing of maintenance strategies, safety security and cost limitation must be considered at the same time. The concept of system reliability has been introduced and optimized as the key of reasonable maintenance strategies. For optimization, three preceding studies were accomplished; standardizing a maintenance classification, constructing RBD (Reliability Block Diagram) of VVVF (Variable Voltage Variable Frequency) urban transit, and developing a web based reliability evaluation system. Historical maintenance data in terms of reliability index can be derived from the web based reliability evaluation system. In this paper, we propose applying inverse problem analysis method and hybrid neuro-genetic algorithm to system reliability optimization for using historical maintenance data in database of web based system. Feed-forward multi-layer neural networks trained by back propagation are used to find out the relationship between several component reliability (input) and system reliability (output) of structural system. The inverse problem can be formulated by using neural network. One of the neural network training algorithms, the back propagation algorithm, can attain stable and quick convergence during training process. Genetic algorithm is used to find the minimum square error.

• Nuclear Engineering and Technology
• /
• 제53권10호
• /
• pp.3275-3285
• /
• 2021

A Nuclear Power Plant (NPP) is a complex dynamic system-of-systems with highly nonlinear behaviors. In order to control the plant operation under both normal and abnormal conditions, the different systems in NPPs (e.g., the reactor core components, primary and secondary coolant systems) are usually monitored continuously, resulting in very large amounts of data. This situation makes it possible to integrate relevant qualitative and quantitative knowledge with artificial intelligence techniques to provide faster and more accurate behavior predictions, leading to more rapid decisions, based on actual NPP operation data. Data-driven models (DDM) rely on artificial intelligence to learn autonomously based on patterns in data, and they represent alternatives to physics-based models that typically require significant computational resources and might not fully represent the actual operation conditions of an NPP. In this study, a feed-forward backpropagation artificial neural network (ANN) model was trained to simulate the interaction between the reactor core and the primary and secondary coolant systems in a pressurized water reactor. The transients used for model training included perturbations in reactivity, steam valve coefficient, reactor core inlet temperature, and steam generator inlet temperature. Uncertainties of the plant physical parameters and operating conditions were also incorporated in these transients. Eight training functions were adopted during the training stage to develop the most efficient network. The developed ANN model predictions were subsequently tested successfully considering different new transients. Overall, through prompt prediction of NPP behavior under different transients, the study aims at demonstrating the potential of artificial intelligence to empower rapid emergency response planning and risk mitigation strategies.

• Journal of Microbiology and Biotechnology
• /
• 제22권7호
• /
• pp.939-946
• /
• 2012

Antibiotic production with Streptomyces sindenensis MTCC 8122 was optimized under submerged fermentation conditions by artificial neural network (ANN) coupled with genetic algorithm (GA) and Nelder-Mead downhill simplex (NMDS). Feed forward back-propagation ANN was trained to establish the mathematical relationship among the medium components and length of incubation period for achieving maximum antibiotic yield. The optimization strategy involved growing the culture with varying concentrations of various medium components for different incubation periods. Under non-optimized condition, antibiotic production was found to be $95{\mu}g/ml$, which nearly doubled ($176{\mu}g/ml$) with the ANN-GA optimization. ANN-NMDS optimization was found to be more efficacious, and maximum antibiotic production ($197{\mu}g/ml$) was obtained by cultivating the cells with (g/l) fructose 2.7602, $MgSO_4$ 1.2369, $(NH_4)_2PO_4$ 0.2742, DL-threonine 3.069%, and soyabean meal 1.952%, for 9.8531 days of incubation, which was roughly 12% higher than the yield obtained by ANN coupled with GA under the same conditions.

• Advances in concrete construction
• /
• 제3권2호
• /
• pp.91-102
• /
• 2015

In this paper, the load-deflection analysis of the Carbon Fiber Reinforced Polymer (CFRP) strengthened Reinforced Concrete (RC) slab using Recurrent Neural Network (RNN) is investigated. Six reinforced concrete slabs having dimension $1800{\times}400{\times}120mm$ with similar steel bar of 2T10 and strengthened using different length and width of CFRP were tested and compared with similar samples without CFRP. The experimental load-deflection results were normalized and then uploaded in MATLAB software. Loading, CFRP length and width were as neurons in input layer and mid-span deflection was as neuron in output layer. The network was generated using feed-forward network and a internal nonlinear condition space model to memorize the input data while training process. From 122 load-deflection data, 111 data utilized for network generation and 11 data for the network testing. The results of model on the testing stage showed that the generated RNN predicted the load-deflection analysis of the slabs in acceptable technique with a correlation of determination of 0.99. The ratio between predicted deflection by RNN and experimental output was in the range of 0.99 to 1.11.

• Bulletin of the Korean Chemical Society
• /
• 제26권12호
• /
• pp.2007-2016
• /
• 2005

An artificial neural network (ANN) is successfully presented for prediction acidity constant (pKa) of various benzoic acids and phenols with diverse chemical structures using a nonlinear quantitative structure-property relationship. A three-layered feed forward ANN with back-propagation of error was generated using six molecular descriptors appearing in the multi-parameter linear regression (MLR) model. The polarizability term $(\pi_1)$, most positive charge of acidic hydrogen atom $(q^+)$, molecular weight (MW), most negative charge of the acidic oxygen atom $(q^-)$, the hydrogen-bond accepting ability $(\epsilon_B)$ and partial charge weighted topological electronic (PCWTE) descriptors are inputs and its output is pKa. It was found that properly selected and trained neural network with 205 compounds could fairly represent dependence of the acidity constant on molecular descriptors. For evaluation of the predictive power of the generated ANN, an optimized network was applied for prediction pKa values of 37 compounds in the prediction set, which were not used in the optimization procedure. Squared correlation coefficient $(R^2)$ and root mean square error (RMSE) of 0.9147 and 0.9388 for prediction set by the MLR model should be compared with the values of 0.9939 and 0.2575 by the ANN model. These improvements are due to the fact that acidity constant of benzoic acids and phenols in water shows nonlinear correlations with the molecular descriptors.

• Computers and Concrete
• /
• 제19권1호
• /
• pp.59-68
• /
• 2017

This study focused on modeling the behavior of the compressive stress using the average strain and ultrasonic test results in concrete. Feed-forward backpropagation artificial neural network (ANN) models were used to compare four types of concrete mixtures with varying water cement ratio (WC), ordinary concrete (ORC) and concrete with short steel fiber-reinforcement (FRC). Sixteen (16) $150mm{\times}150mm{\times}150mm$ concrete cubes were used; each contained eighteen (18) data sets. Ultrasonic test with pitch-catch configuration was conducted at each loading state to record linear and nonlinear test response with multiple step loads. Statistical Spearman's rank correlation was used to reduce the input parameters. Different types of concrete produced similar top five input parameters that had high correlation to compressive stress: average strain (${\varepsilon}$), fundamental harmonic amplitude (A1), $2^{nd}$ harmonic amplitude (A2), $3^{rd}$ harmonic amplitude (A3), and peak to peak amplitude (PPA). Twenty-eight ANN models were trained, validated and tested. A model was chosen for each WC with the highest Pearson correlation coefficient (R) in testing, and the soundness of the behavior for the input parameters in relation to the compressive stress. The ANN model showed increasing WC produced delayed response to stress at initial stages, abruptly responding after 40%. This was due to the presence of more voids for high water cement ratio that activated Contact Acoustic Nonlinearity (CAN) at the latter stage of the loading path. FRC showed slow response to stress than ORC, indicating the resistance of short steel fiber that delayed stress increase against the loading path.

• 한국지능시스템학회논문지
• /
• 제1권1호
• /
• pp.9-25
• /
• 1991

This tutorial paper has been written for biologists, physicians or beginners in fuzzy sets theory and applications. This field is introduced in the framework of medical diagnosis problems. The paper describes and illustrates with practical examples, a general methodology of special interest in the processing of borderline cases, that allows a graded assignment of diagnoses to patients. A pattern of medical knowledge consists of a tableau with linguistic entries or of fuzzy propositions. Relationships between symptoms and diagnoses are interpreted as labels of fuzzy sets. It is shown how possibility measures (soft matching) can be used and combined to derive diagnoses after measurements on collected data. The concepts and methods are illustrated in a biomedical application on inflammatory protein variations. In the case of poor diagnostic classifications, it is introduced appropriate ponderations, acting on the characterizations of proteins, in order to decrease their relative influence. As a consequence, when pattern matching is achieved, the final ranking of inflammatory syndromes assigned to a given patient might change to better fit the actual classification. Defuzzification of results (i.e. diagnostic groups assigned to patients) is performed as a non fuzzy sets partition issued from a "separating power", and not as the center of gravity method commonly employed in fuzzy control. It is then introduced a model of fuzzy connectionist expert system, in which an artificial neural network is designed to build the knowledge base of an expert system, from training examples (this model can also be used for specifications of rules in fuzzy logic control). Two types of weights are associated with the connections: primary linguistic weights, interpreted as labels of fuzzy sets, and secondary numerical weights. Cell activation is computed through MIN-MAX fuzzy equations of the weights. Learning consists in finding the (numerical) weights and the network topology. This feed forward network is described and illustrated in the same biomedical domain as in the first part.