ANN Based Data Integration for Multi-Path Ultrasonic Flowmeter

Zhao, Hongduo; Peng, Lihui; Takahashi, Tsuyoshi; Hayashi, Takuya; Shimizu, Katsuyuki; Yamamoto, Toshihiro

doi:10.1109/jsen.2013.2282466

Cited by 37 publications

(23 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Considering the two former methods have been studied in earlier researches [21,23,24], a comparison between them and ELM is made here and the piping configurations producing severe flow disturbances on a 0°in-stallation angle and 5D and 10D positions are adopted. A single hidden layer and a 6-15-1 network architecture are designed for both ANN and ELM method.…”

Section: Comparison Between Ann Svm and Elmmentioning

confidence: 99%

“…On the other hand, numerical simulation has been proved to have good agreement with experiments for UFMs [37,38] and widely adopted in many similar researches [12,13,23,24]. This paper will adopt numerical simulation to verify the proposed method aimed at focusing on minimizing the errors caused by integration methods.…”

Section: Introductionmentioning

confidence: 97%

“…It was in fact the same as ANN in principle but the detailed algorithm and results of determining flow rate were not given. An ANN method based on error backpropagation (BP) algorithm with a single hidden layer was designed for a 4-path UFM and errors within 70.3% are achieved under complex flow field downstream two elbows out-of-plane [23]. Then [24] applied support vector machine (SVM) which is based on VC dimension and structural risk minimization to reduce the errors existing in traditional weighted integration methods for UFMs, which showed high accuracy within 70.5% for flow rate determination under strongly distorted flow profiles.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Application of extreme learning machine to gas flow measurement with multipath acoustic transducers

Qin

Mao

et al. 2016

Flow Measurement and Instrumentation

View full text Add to dashboard Cite

Section: Comparison Between Ann Svm and Elmmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 97%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Application of extreme learning machine to gas flow measurement with multipath acoustic transducers

Qin

Mao

et al. 2016

Flow Measurement and Instrumentation

View full text Add to dashboard Cite

“…Velocity profile refers to the distribution of velocities in the axial direction in the cross-section of the circular pipe [1]. In natural gas industry, ultrasonic flowmeter is considered to be an important metering method for its accuracy, high repeatability, wide measurement range, simple operation, easy installation and other advantages [2][3][4][5].…”

Section: Introductionmentioning

confidence: 99%

A CFD simulation for the ultrasonic flow meter with a header

Liu

Tan²,

Peng

2017

Teh. vjesn.

View full text Add to dashboard Cite

Original scientific paper Ultrasonic flow meter has been used in natural gas metering for many years, however, the measurement accuracy of the ultrasonic flow meter is affected by the header, which leads to non-perfect fluid state in the flow meter. The objective of this research is to discuss the issues of dual-path ultrasonic flowmeter with a header. Computer fluid dynamic (CFD) method is used to simulate standard turbulent model. It is found that the flow state in the downstream is distorted by the header with secondary turbulence, swirl etc., and the velocity distribution of the gas is asymmetric; the farther the distance between the ultrasonic flow meter and the header, the smaller the distortion and the simulation error. When the downstream straight pipe length is greater than 27 − D (Diameter), the flow state will be steady. With the same diameter of the header, the shorter the meter header the greater the distortion of the gas in the downstream pipe. With the same length of the header, the smaller the diameter, the greater the distortion of the gas in the downstream. These results have a great guiding significance in the optimal design of the flow meter installation structure. Keywords: Pipe manifold; Ultrasonic flow meter; Measurement performance; Indication error CFD simulacija za ultrazvučni mjerač protoka sa zaglavljemIzvorni znanstveni članak Ultrazvučni mjerač protoka koristi se u mjerenju prirodnog plina dugi niz godina, međutim, na mjernu točnost ultrazvučnog mjerača protoka utječe zaglavlje, što dovodi do nespretnog fluidnog stanja u mjeraču protoka. Cilj ovog istraživanja je raspraviti pitanja dvostruke staze ultrazvučnih mjerača protoka sa zaglavljem. Dinamička metoda računalne tekućine (CFD) je korištena za simulaciju standardnog turbulentnog modela. Nađeno je da je stanje protoka u nizvodnom smjeru izobličeno zaglavljem sa sekundarnom turbulencijom, vrtloženjem itd., a brzina distribucije plina je asimetrična; što je dalje udaljenost između ultrazvučnog mjerača protoka i zaglavlja, to je manja iskrivljenost i simulacijska pogreška. Kada je nizvodno ravna duljina cijevi veća od 27 − D (promjer), stanje protoka će biti stabilno. S istim promjerom zaglavlja, što je kraći mjerač glave, to je veća deformacija plina u nizvodnoj cijevi. S istom duljinom zaglavlja, manji je promjer, ali je veća deformacija plina u nizvodnom smjeru. Ti rezultati imaju veliko značenje u optimalnom dizajnu instalacije mjerača protoka.

show abstract

“…3-layer feed-forward ANN with a strong nonlinear mapping and learning ability to measure the mean flow velocity on a cross section of a pipe from the flow velocities on the individual sound paths [18], which reduced the error significantly. However, the ANN-based method requires a sufficient number of training samples to produce an accurate estimation.…”

Section: Introductionmentioning

confidence: 99%

Support Vector Regression-Based Data Integration Method for Multipath Ultrasonic Flowmeter

Zhao

Peng

Takahashi³

et al. 2014

IEEE Trans. Instrum. Meas.

Self Cite

View full text Add to dashboard Cite

This paper presents a support vector regression (SVR)-based data integration method for a 4-path ultrasonic flowmeter, which is able to estimate accurately the mean cross-sectional flow velocity under complex flow profiles. While installed in the pipeline with complex configurations, such as single-elbow or out-plane double-elbow, the performance of multipath ultrasonic flowmeter will degenerate due to the strong nonlinear relationships between the flow velocities on different individual sound paths and the mean flow velocity on the cross section, particularly when the straight pipe length is not guaranteed. The presented SVR-based method is of an excellent nonlinear mapping and generalization ability. The cases while the Reynolds number in the range of 3.25 × 10 3 − 3.25 × 10 5 were simulated using computational fluid dynamics and the flow profiles located on the cross sections of 5 and 10 times pipe diameter downstream a single elbow and an out-plane doubleelbow were extracted to construct the data set for SVR training and test. It is found that the error of the estimated crosssectional mean flow velocity obtained by the SVR-based data integration method is within ±0.5% without the requirement of a flow conditioner, which is significantly better than the results from the traditional integration method with constant weights. The presented SVR-based data integration method is helpful to extend the limitation of straight pipe length for the installation of multipath ultrasonic flowmeter, which is attractive for the practical applications of multipath ultrasonic flowmeter.Index Terms-Computational fluid dynamics (CFD), flow measurement, flow profile, multipath ultrasonic flowmeter, support vector regression (SVR).

show abstract

ANN Based Data Integration for Multi-Path Ultrasonic Flowmeter

Cited by 37 publications

References 12 publications

Application of extreme learning machine to gas flow measurement with multipath acoustic transducers

Application of extreme learning machine to gas flow measurement with multipath acoustic transducers

A CFD simulation for the ultrasonic flow meter with a header

Support Vector Regression-Based Data Integration Method for Multipath Ultrasonic Flowmeter

Contact Info

Product

Resources

About