Discharge estimation in converging and diverging compound open channels by using adaptive neuro-fuzzy inference system

Das, B. S.; Devi, Kamalini; Khuntia, Jnana Ranjan; Khatua, Kishanjit Kumar

doi:10.1139/cjce-2018-0038

Cited by 22 publications

(6 citation statements)

References 40 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As shown in this table, the discharge is inversely related to other parameters such as the f r and β. For finding the most effective parameters, other methods, such as the Gamma test can be used (Das et al 2020). This method also works based on the correlation coefficient.…”

Section: Modeling Strategiesmentioning

confidence: 99%

“…Using soft computing models the research to date has tended to focus on estimating discharge in compound channels with prismatic floodplains rather than non-prismatic floodplains. In other words, little research has been done on non-uniform sections (Pradhan & Khatua 2019b;Mohanta & Patra 2021) or compound open channels with non-prismatic floodplains (Das et al 2020). Hence, due to the importance of discharge estimation especially in flood conditions, in this study, in addition to estimating the total flow rate, discharge prediction is considered in the floodplain and the main channel.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Discharge modeling in compound channels with non-prismatic floodplains using GMDH and MARS models

et al. 2022

View full text Add to dashboard Cite

In this study, modeling of discharge was performed in compound open channels with non-prismatic floodplain (CCNPF) using soft computation models including Multivariate Adaptive Regression Splines (MARS) and Group Method of Data Handling (GMDH) and then their results were compared with the multilayer perceptron neural networks (MLPNN). In addition to the total discharge, the discharge separation between the floodplain and main channel was modeled and predicted. The parameters of relative roughness coefficient, the relative area of flow cross-section, relative hydraulic radius, bed slope, the relative width of water surface, relative depth, convergence or divergence angle, relative longitudinal distance as inputs, and discharge were considered as models output. The results demonstrated that the statistical indices of MARS, GMDH, and MLPNN models in the testing stage are R2 = 0.962(RMSE = 0.003), 0.930(RMSE = 0.004), and 0.933(RMSE = 0.004) respectively. Examination of statistical error indices o shows that all of the developed models have the appropriate accuracy to estimate the flow discharge in CCNPF. Examination of the structure of developed GMDH and MARS models demonstrated that the parameters of relative: roughness, area, hydraulic radius, flow aspect ratio, depth, and angle of convergence or divergence of floodplain have the greatest impact on modeling and estimation of discharge.

show abstract

Section: Modeling Strategiesmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Discharge modeling in compound channels with non-prismatic floodplains using GMDH and MARS models

et al. 2022

View full text Add to dashboard Cite

show abstract

“…The composition of the block body mainly includes information such as version number, previous block hash value, random number, timestamp, Merkle root, and block hash value [27]. Blockchain technology is extracted from Bitcoin.…”

Section: Blockchain Technologymentioning

confidence: 99%

Research on Supply Chain Financial Risk Assessment Based on Blockchain and Fuzzy Neural Networks

Wang

2021

Wireless Communications and Mobile Computing

View full text Add to dashboard Cite

With the development of supply chain finance, the credit risk of small- and medium-sized financing enterprises from the perspective of supply chain finance has arisen. Risk management is one of the key tasks of the credit business of banks and other financial institutions, which runs through all aspects of the credit business before, during, and after the loan. This article combines blockchain and fuzzy neural network algorithms to study the credit risk of SME financing from the perspective of supply chain finance. This article builds a supply chain financial system through blockchain technology and integrates supply chain financial information into blocks. The fuzzy neural network algorithm is used for financial data processing and risk assessment, effectively solving and improving the risk processing level of the supply chain. Through further simulation, the application effect of blockchain and machine learning algorithms in the supply chain financial system was verified.

show abstract

“…Later Yonesi et al (2013) worked on diverging compound channels with differential bed roughness for diverging angles 3.81°, 5.7°and 11.3°. Das et al (2020) use the soft computing technique to estimate the discharge in converging and diverging compound channels. Das et al (2017) and Devi et al (2021) developed the numerical and analytical model for prediction of depth averaged velocity and boundary shear distribution in prismatic and non-prismatic compound channels without incorporating any flow distribution calculation in the model.…”

Section: Introductionmentioning

confidence: 99%

Flow Distributions in a Compound Channel with Diverging Floodplains

Das

Devi

Khuntia³

et al. 2021

River Hydraulics

View full text Add to dashboard Cite

During flood, the flow distribution in main channel and floodplain is always an important factor for river engineer to model, accordingly, the measures can be taken in the floodplain area. Experiments on diverging compound channel show that the flow distribution in main channel and floodplains are found to be a function of four non-dimensional geometric and hydraulic parameters such as width ratio, relative flow depth, relative longitudinal distance and flow aspect ratio. This paper presents an empirical-non-linear-multivariable regression model by considering the aforementioned parameters to compute discharge distribution in diverging compound channels. The model is developed using discharge distribution data obtained from present laboratory experiments and with the published data of other researchers on diverging compound channels. The predictive strength of the developed regression model is validated using several major statistics. All deployed statistics have indicated that the developed model is highly significant. The outcome for all diverging compound channels resulted in minimum RMSE and MAPE values as 0.0092 and 4.35%, respectively, when the discharge is predicted using the developed multivariable regression model.

show abstract

Discharge estimation in converging and diverging compound open channels by using adaptive neuro-fuzzy inference system

Cited by 22 publications

References 40 publications

Discharge modeling in compound channels with non-prismatic floodplains using GMDH and MARS models

Discharge modeling in compound channels with non-prismatic floodplains using GMDH and MARS models

Research on Supply Chain Financial Risk Assessment Based on Blockchain and Fuzzy Neural Networks

Flow Distributions in a Compound Channel with Diverging Floodplains

Contact Info

Product

Resources

About