Online heat flux estimation using artificial neural network as a digital filter approach

Najafi, Hamidreza; Woodbury, Keith A.

doi:10.1016/j.ijheatmasstransfer.2015.08.010

Cited by 44 publications

(10 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…As the baseflow cannot be directly observed, foreign researchers have proposed various baseflow splitting methods, such as the direct splitting method, water balance method, numerical simulation method and hydrological modeling method, based on the difference in confluence between the steep rise and fall of surface runoff and the slow rise and fall of subsurface runoff. Among them, the direct splitting method is highly subjective, workload and not suitable for long time-scale baseflow splitting; the water balance method has more parameters, complex formulas and difficult to optimize; the hydrological modeling method has clear physical meaning and high credibility, but requires more parameters and extremely complex operation; and the numerical simulation method is highly efficient, repeatable and widely used in current research (Hao et al 2019), mainly including the digital filtering method (Hamidreza & Keith 2015), the hydrograph separation program (HYSEP) (Gardner et al 2010) and the minimum smoothing method (Bastola et al 2018).…”

Section: Methodology Base Flow Segmentationmentioning

confidence: 99%

Method to identify composition and production phases of spring runoff in high-latitude mid-temperate regions: a case study in the Second Songhua River Basin, China

Yangzong

Yang

et al. 2021

Journal of Water and Climate Change

View full text Add to dashboard Cite

Simulation and forecast of runoff play an important role in the early warning and prevention of drought and flood disasters. To improve the accuracy of spring runoff simulations, it is important to identify spring runoff production patterns under the combined effect of snow and frozen soil. Based on the theory of the hydrological cycle, three important parameters, which include surface and subsurface runoff, precipitation and temperature, were selected for this study. The trend analysis, statistical analysis and Eckhardt's recursive numerical filtering method were used to qualitatively identify the production patterns of spring runoff, the start and end dates and stage periods of the production patterns. Based on the qualitative identification results, the contribution of each production runoff to the total annual runoff and the total annual spring runoff is quantitatively assessed. The results of the study show that the spring runoff production patterns in the Second Songhua River Basin can be divided into snowmelt runoff, frozen soil conditions of snowmelt–rainfall runoff and rainfall runoff under frozen soil conditions; the snowmelt production is from 21 March, the frozen soil conditions production is from 21 April and the frozen soil ablation is ended on 15 June; the phases of each production pattern are the shortest lasting 28, 20 and 18 days and the longest lasting 31, 26 and 24 days. This research is providing the basis for improving the principles of production runoff calculation in spring runoff simulation methods.

show abstract

Section: Methodology Base Flow Segmentationmentioning

confidence: 99%

Method to identify composition and production phases of spring runoff in high-latitude mid-temperate regions: a case study in the Second Songhua River Basin, China

Yangzong

Yang

et al. 2021

Journal of Water and Climate Change

View full text Add to dashboard Cite

show abstract

“…They proposed that a combination of both algorithms would improve the results. Najafi and Woodbury 176 used neural networks to estimate the heat flux at the surface of a material using temperature information, and then they also discussed their limitations and benefits.…”

Section: Parameter Estimationmentioning

confidence: 99%

Pyrolysis modeling, sensitivity analysis, and optimization techniques for combustible materials: A review

Nyazika

Jimenez

Samyn

et al. 2019

Journal of Fire Sciences

View full text Add to dashboard Cite

Over the past years, pyrolysis models have moved from thermal models to comprehensive models with great flexibility including multi-step decomposition reactions. However, the downside is the need for a complete set of input data such as the material properties and the parameters related to the decomposition kinetics. Some of the parameters are not directly measurable or are difficult to determine and they carry a certain degree of uncertainty at high temperatures especially for materials that can melt, shrink, or swell. One can obtain input parameters by searching through the literature; however, certain materials may have the same nomenclature but the material properties may vary depending on the manufacturer, thereby inducing uncertainties in the model. Modelers have resorted to the use of optimization techniques such as gradient-based and direct search methods to estimate input parameters from experimental bench-scale data. As an integral part of the model, a sensitivity study allows to identify the role of each input parameter on the outputs. This work presents an overview of pyrolysis modeling, sensitivity analysis, and optimization techniques used to predict the fire behavior of combustible solids when exposed to an external heat flux.

show abstract

“…Sadeghi-Goughari et al (2016) applied the artificial neural network (ANN) to identify the brain tumors parameters by intraoperative thermal imaging based on artificial tactile sensing. Najafi and Woodbury (2015) used the ANN as a digital filter approach to estimate the heat flux. Chanda et al (2017) estimated the principal thermal conductivities of layered honeycomb composites using the ANN and genetic algorithm.…”

Section: Introductionmentioning

confidence: 99%

Identification of pipe inner surface in heat conduction problems by deep learning and effective thermal conductivity transform

Chen¹,

et al. 2020

View full text Add to dashboard Cite

Purpose The purpose of this paper is to develop a transform method and a deep learning model to identify the inner surface shape based on the measurement temperature at the outer boundary of the pipe. Design/methodology/approach The training process is assisted by the finite element method (FEM) simulation which solves the direct problem for the data preparation. To avoid re-meshing the domain when the inner surface shape varies, a new transform method is proposed to transform the shape identification problem into the effective thermal conductivity identification problem. The deep learning model is established to set up the relationship between the measurement temperature and the effective thermal conductivity. Then the unknown geometry shape is acquired by the mapping between the inner shape and the effective thermal conductivity through the inverse transform method. Findings The new method is successfully applied to identify the internal boundary of a pipe with eccentric circle, ellipse and nephroid inner geometries. The results show that as the measurement points increased and the measurement error decreased, the results became more accurate. The position of the measurement point and mesh density of the FEM model have less effect on the results. Originality/value The deep learning model and the transform method are developed to identify the pipe inner surface shape. There is no need to re-mesh the domain during the computation progress. The results show that the proposed method is a fast and an accurate tool for identifying the pipe inner surface.

show abstract

Online heat flux estimation using artificial neural network as a digital filter approach

Cited by 44 publications

References 23 publications

Method to identify composition and production phases of spring runoff in high-latitude mid-temperate regions: a case study in the Second Songhua River Basin, China

Method to identify composition and production phases of spring runoff in high-latitude mid-temperate regions: a case study in the Second Songhua River Basin, China

Pyrolysis modeling, sensitivity analysis, and optimization techniques for combustible materials: A review

Identification of pipe inner surface in heat conduction problems by deep learning and effective thermal conductivity transform

Contact Info

Product

Resources

About