Use BP Neural Network Set up the Corrosion Prediction Model of Low Temperature Parts of Atmospheric Pressure Device

Fan, Yu; Piao, Zai Dong; Chen, Bing; Lin, Hong Xian; Yang, Yang

doi:10.4028/www.scientific.net/amm.152-154.1138

Cited by 3 publications

(4 citation statements)

References 1 publication

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Table 1 is the monitoring data collected from the top of fractionation tower system of one petrochemical company [5]. Modeling and Error Evaluation Samples Samples quantity has great impact on accuracy of corrosion prediction model.…”

Section: Modeling Data Standardized Methodsmentioning

confidence: 99%

BP Neural Network Application Research in Petrochemical Tower System Corrosion Prediction

Fan

Lin

et al. 2014

AMM

Self Cite

View full text Add to dashboard Cite

This paper takes the monitoring data sample from the top of fractionation tower system of one petrochemical company and uses prediction model which is constructed by BP neural network to study the corrosion prediction of catalytic fractionation tower top system. It uses min-max and z-score standardized method to deal with the original data and compare the impacts. The result shows that the BP neural constructing prediction model can provide basis of corrosion control for refinery. It also shows that better accuracy can be achieved by using min-max standardized method and when the number of training data quantity is over 20, the prediction result is more accurate and stable.

show abstract

Section: Modeling Data Standardized Methodsmentioning

confidence: 99%

BP Neural Network Application Research in Petrochemical Tower System Corrosion Prediction

Fan

Lin

et al. 2014

AMM

Self Cite

View full text Add to dashboard Cite

show abstract

“…The generated HCl would react with H 2 S, leading to the "HCl−H 2 S−H 2 O" corrosion system at the low-temperature part of the overhead of the atmospheric and vacuum distillation unit. 7 During the secondary refining processes of crude oil, both HCl from the organic chlorine and NH 3 from organic nitride would react with hydrogen at a low temperature to form ammonium chloride, 8 which could cause serious blockage to the prehydrogenation system 9,10 and underdeposit corrosion. 11 At the same time, chloride ions tend to react with metal ions of the catalysts, causing irreversible poisoning of catalysts.…”

Section: Introductionmentioning

confidence: 99%

“…It was known that during the distillation process, the organic chloride would hydrolyze and convert into HCl spontaneously. The generated HCl would react with H 2 S, leading to the “HCl–H 2 S–H 2 O” corrosion system at the low-temperature part of the overhead of the atmospheric and vacuum distillation unit . During the secondary refining processes of crude oil, both HCl from the organic chlorine and NH 3 from organic nitride would react with hydrogen at a low temperature to form ammonium chloride, which could cause serious blockage to the prehydrogenation system , and underdeposit corrosion .…”

Section: Introductionmentioning

confidence: 99%

Zn-Modified Hβ Zeolites Used in the Adsorptive Removal of Organic Chloride from Model Naphtha

Zhang

et al. 2020

ACS Omega

View full text Add to dashboard Cite

Different metal ions were used to modify Hβ zeolite adsorbents by an impregnation method to remove organic chlorides from the model naphtha. The dechlorination performance of different ion-modified adsorbents was evaluated using a microcoulometer. The effects of calcination time and temperature, metal loading, adsorption time and temperature, and dosage of adsorbent were investigated by batch adsorption experiments. The modified adsorbents were characterized by X-ray diffraction (XRD), Brunauer− Emmett−Teller (BET), NH 3 -temperature-programmed desorption (TPD), scanning electron microscopy (SEM), infrared spectroscopy of pyridine adsorption (Py-IR), and X-ray photoelectron spectroscopy (XPS). After modification, the modified Zn/Hβ zeolite exhibited the best dechlorination performance among the other metal-loaded zeolites. The removal percentage of organic chloride of the Zn/Hβ adsorbent prepared at optimum preparation and adsorption conditions can reach 72.54%, compared with 34.07% of Hβ zeolite. The Zn/Hβ adsorbent also maintained good dechlorination performance after regeneration by calcination for five times. The characterization results revealed that the concentration of the B acid sites in the zeolite decreased with the introduction of the metals, whereas that of the L acid sites increased. Zn/Hβ zeolite had the lowest B/L ratio but the best dechlorination performance, which meant that the type and amount of acidic sites present in zeolites played a significant role in dechlorination performance and L acid was beneficial for chloride compound removal.

show abstract

“…And the information science approach as a nonlinear simulation technology, that is an artificial neural network (ANN) (Fan, He, & Lin, ; Hattori & Kito, ; Yang, Yu, & Guan, ) including Hopfield neural network, adaptive resonance technology, fuzzy neural network, and backpropagation (BP) neural network, is structured to study the relationship between a set of factors and the results. According to research of Wang et al (), BP neural network is most widely used in various evaluation fields (Chen, ; Ding & Jia, ; Fan, Piao, & Chen, ; Ju, Tade, & Zhu, ) for its good performance of self‐learning, self‐adapting, self‐organizing, and self‐reasoning (Maier, Jain, & Dandy, ; Miao, Zhao, & Gao, ; Palani, Liong, & Tkalich, ), which was proposed by Rumelhart, Hintont, and Williams (). Yang et al () applied BP neural network to the performance evaluation of environmental catalytic materials and pollutant purification research; Fan et al () applied BP neural network to the corrosion prediction research of petrochemical tower; Ju et al () applied BP neural network to the prediction of hydrogen content in coal resources, etc.…”

Section: Introductionmentioning

confidence: 99%

Research of extraction behavior of heavy metal Cd in tea based on backpropagation neural network

Guan

Yang

2020

Food Science & Nutrition

View full text Add to dashboard Cite

In order to meet the increasing demand for food and beverage safety and quality, this study focused on the application of a back propagation (BP) neural network to determine the leaching rate of heavy metal in tea to improve the scientific health of tea drinking. The evaluation index and target expectations have been determined based on the extraction experiment of heavy metal Cd in tea soaking, with 3 evaluation index values taken as input layer parameters and the heavy metal extraction rate taken as output layer parameter. Then, employ the sample data standardized by min‐max linearization method to train and test the network model and get the satisfactory results, which showed that the constructed BP neural network expressed a fast convergence speed and the systematic error was as low as 0.0003509. Additionally, there was no significance between Cd leaching rate of experimental results and neural network model results by reliability testing with a correlation coefficient was .9895. These results revealed that the network model established possessed an outstanding training accuracy and generalization performance, which effectively reflected the extraction rate of heavy metal in tea soaking and improved the safety of tea drinking.

show abstract

Use BP Neural Network Set up the Corrosion Prediction Model of Low Temperature Parts of Atmospheric Pressure Device

Cited by 3 publications

References 1 publication

BP Neural Network Application Research in Petrochemical Tower System Corrosion Prediction

BP Neural Network Application Research in Petrochemical Tower System Corrosion Prediction

Zn-Modified Hβ Zeolites Used in the Adsorptive Removal of Organic Chloride from Model Naphtha

Research of extraction behavior of heavy metal Cd in tea based on backpropagation neural network

Contact Info

Product

Resources

About