Simulation and prediction of the thuringiensin abiotic degradation processes in aqueous solution by a radius basis function neural network model

IntroductionThe Algerian heritage of drinking water storage tank has almost 40,000 tanks and is mostly built of reinforced concrete. The average age of the national heritage of concrete tanks is about forty years. The feedback from nearly half a century of management has highlighted a great disparity in the behaviour of these structures, expressed by several pathologies [1]. The lack of maintenance of these tanks, directly exposed to natural threats (snow, earthquakes, winds), accelerates the ageing process. In consideration to this, in recent years, civil engineering activity is repositioning primarily in the life cycle of existing structures operation rather than in the design and construction of new structures. Therefore, we note a great interest in the scientific community to risk analysis. Many methods have been developed by several authors intended to structure managers in order to assess the structural performance, to make risk analysis or programming maintenance actions for hydraulic structures, harbour structures and buildings. We mainly cite the reliability approach, the approach using physical models and expertise approach.The reliability approach based on probabilistic analysis has its limitations when the data is in insufficient quantity and in poor quality. Probability calculations become quickly complicated or impossible and their validity becomes difficult to demonstrate. We are then in the presence of the concept of imprecise probabilities. The interested reader by further details can consult the reference [2]. This latter provides an overview on developments which involve imprecise probabilities for the solution of engineering problems. Evidence theory, probability bounds analysis with p-boxes, and fuzzy probabilities are discussed with emphasis on their key features and on their relationships to one another. In the case where the structure is badly known and where the available data are of poor quality, the deterministic method using physical models; which consists of a recalculation of the structure; is difficult to implement. So, the simplest way to assess the future development of damages is to examine the evolution laws of existing structures of same design that have similar mechanisms, based on the experience feedback. This method is known as the expert approach that will be discussed in this paper.

show abstract

“…This measurement considers the importance rather than the direction of forecast errors [29]. It is given by the following relation:…”

Section: Extrapolation Of the Function I V (T)mentioning

confidence: 99%

“…Exponential functions in their principles were used for modelling several phenomena such as the evaluation of rainfall in the field of hydrology [28], in biology [29], in economics and demography [30], in which the growth velocity is proportional to the size of the studied population.…”

Section: Approach By Exponential Modelmentioning

confidence: 99%

Development and validation of predictive model to describe the growth of concrete water tank vulnerability with time

Aliche

Hammoum

Bouzelha

et al. 2016

Period. Polytech. Civil Eng.

View full text Add to dashboard Cite

show abstract

Modeling of UV-Induced Photodegradation of Naphthalene in Marine Oily Wastewater by Artificial Neural Networks

Jing

Chen

Zhang

2014

Water Air Soil Pollut

View full text Add to dashboard Cite

Application of Modern Methods: Modeling of Sedimentary Soil ESP Content

Niknamian¹

2019

bioex

View full text Add to dashboard Cite

Knowing the exchangeable sodium percentage (ESP) variations and its values in sodic or saline-sodic soils is essential in order to estimate the amount of soil amendments and better land management. ESP calculated from cation exchange capacity (CEC), and since CEC measurement is difficult and time-consuming, ESP computation is costly and subject to error. Thus, presenting a method to estimate ESP indirectly, by an easily available index is much more efficient and economical. In this study, 296 soil samples collected and analyzed from Sistan plain, southeastern Iran. Soil ESP were predicted by using artificial neural networks, comprising radial basis functions (RBFN) and multilayer perceptron (MLP) and adaptive neuro-fuzzy inference systems (ANFIS), and results compared with stepwise linear regression method. Results indicated that the linear regression models performed poorly in order to estimate ESP (R2 ≤ 0.58 and root mean square error (RMSE) ≥ 4.31). Applying fewer inputs (electrical conductivity (EC) and pH), ANFIS showed better results (R2=0.80, RMSE=2.34), while increasing inputs (clay and organic carbon) decreased the accuracy (R2=0.82, RMSE=4.20). Using more inputs, RBFN resulted in better performance in comparison with other methods (R2=0.83, RMSE=2.85). Sensitivity analysis using the connection weight method demonstrated that EC, pH, clay percentage and bulk density are the most important variables in order to explain ESP variability in the region, respectively. Generally, considering the evaluation criteria and the number of used variables of models, ANFIS (with EC and pH as inputs) is the most appropriate method for estimating ESP in Sistan plain.

show abstract

Simulation and prediction of the thuringiensin abiotic degradation processes in aqueous solution by a radius basis function neural network model

Cited by 4 publications

References 25 publications

Development and validation of predictive model to describe the growth of concrete water tank vulnerability with time

Development and validation of predictive model to describe the growth of concrete water tank vulnerability with time

Modeling of UV-Induced Photodegradation of Naphthalene in Marine Oily Wastewater by Artificial Neural Networks

Application of Modern Methods: Modeling of Sedimentary Soil ESP Content

Contact Info

Product

Resources

About