A novel predictive model of mixed oil length of products pipeline driven by traditional model and data

2021 ◽  
Vol 205 ◽  
pp. 108787
Author(s):  
Lei Chen ◽  
Ziyun Yuan ◽  
JianXin Xu ◽  
Jingyang Gao ◽  
Yuhan Zhang ◽  
...  
Energies ◽  
2020 ◽  
Vol 13 (23) ◽  
pp. 6398
Author(s):  
Yi Wang ◽  
Baoying Wang ◽  
Yang Liu ◽  
Yongtu Liang

Long-distance pipelines transporting multiple product oils such as gasoline, diesel and jet fuel, are important facilities for transporting fossil energy. One major concern in operation is the energy consumption of the pipeline. Energy consumption should be made optimized tracking batches of oils and cutting mixed oil, which requires an accurate prediction of concentration curve. In engineering, the concentration curve is usually assumed to be symmetric, but it is actually asymmetric, which may lead to estimation errors. Thus, the asymmetric concentration of mixed oil should be studied. The formation mechanism of the asymmetry of concentration curve has not been clearly clarified. A new method is proposed to measure the asymmetry of the concentration curve. Quantitative analysis is carried out for each factor on the asymmetry distribution of concentration curve. Based on the convection–diffusion equation, a modified oil-mixing model considering near wall adsorption effect is established. The model shows a good agreement with the Jablonski empirical formula. The error, compared with the experimental results, is less than 5%. The main findings are: (1) deviation volume has a negative correlation with pipe diameter and mean velocity; (2) adsorption coefficient has a greater impact on the length ratio of front and tail oil than diffusion coefficient; (3) the influence of all factors considered on the total length of mixed oil, front oil, tail oil and trail oil are basically the same; (4) if the limit of adsorption concentration in adsorption layer is 1, the reasonable value of adsorption coefficient a and b should be around 0.4. The results reveal the mechanism of asymmetric concentration of product oils and can provide practical suggestions to deal with the mixed oil.


Word prediction is a technique which tries to suggest the users’ words after knowing the few input letters of the user. This predictive model also tries to generate the future words or next words of a sentence by observing earlier words of the sentence. In this research, two problems are combined, one is word prediction and the next is handling of ambiguous words. A word prediction model predicts the future words of a sentence by using n-gram based model. In general, predictive models use unigram, bigram or trigram models to predict the next words. In case of sentences consisting of ambiguous words, the predictive model by using only bigram or trigram cannot perform well to predict the next words. To enhance this prediction for ambiguous words, maximum of six previous input words are observed and try to predict almost the exact words after the ambiguous words in those particular contexts. Different level of experiments are done and the results are compared for modified or enhanced prediction model with the traditional prediction model, improvement on accuracy and failure rate are found in the enhanced model. The accuracy of the Traditional Model is 60.68% on the hand the accuracy of the Enhanced Model is 66.88%. The failure rate of the Traditional Model is 32.35% and the Enhanced Model is 29.17%


Author(s):  
Ziyun Yuan ◽  
Lei Chen ◽  
Weiming Shao ◽  
Zhiheng Zuo ◽  
Wan Zhang ◽  
...  

Author(s):  
Jing Gong ◽  
Qin Wang ◽  
Weidong Wang ◽  
Yi Guo

In order to improve the operational management of a products pipeline, we need to identify a suitable formula to calculate the volume of the contaminated product accurately when it arrives at the end point of the products pipeline. This paper presents a calculation method of mixing volume in a products pipeline. By combining the empirical formula of Austin-Palfrey with field data, we establish a new formula which meets the characteristics of the products pipeline. The flow characteristics and growth rules of mixed oil products are considered in the formula of Austin-Palfrey, but many influential factors are not taken into account, such as the structure and the terrain of the pipeline, the characteristics of mixed oil products in pumping stations and the distribution of the products along the pipeline. We obtain a group of coefficients from field data which are collected from a products pipeline. This new formula is proved by the validation of field data; it not only can improve the accuracy of the mixed oil products volume prediction, but also can be easily used for field application. This paper also discusses the relationship between mixing volume calculation and the terrain of products pipeline.


Sign in / Sign up

Export Citation Format

Share Document