Lessen Pressure Drop and Forecasting Thermal Performance in U-Tube Heat Exchanger Using Chimp Optimization and Deep Belief Neural Network

IF 1 Q4 OPTICS Optical Memory and Neural Networks Pub Date : 2023-12-22 DOI:10.3103/s1060992x23040033

Shailandra Kumar Prasad, Mrityunjay Kumar Sinha

{"title":"Lessen Pressure Drop and Forecasting Thermal Performance in U-Tube Heat Exchanger Using Chimp Optimization and Deep Belief Neural Network","authors":"Shailandra Kumar Prasad, Mrityunjay Kumar Sinha","doi":"10.3103/s1060992x23040033","DOIUrl":null,"url":null,"abstract":"<h3 data-test=\"abstract-sub-heading\">Abstract</h3><p>In the chemical, pharmaceutical, and petroleum industries, Shell and U-Tube Heat Exchangers (STHX) were extensively utilized. Baffles must be positioned at the right distance and angle to increase the heat exchangers' capacity to convey heat and, as a result, lower pressure in the shell. The rate of heat transfer in an STHX has been improved, and pressure drop has been reduced using a variety of models. But those methods are not provided satisfactory pressure drop reduction. In the proposed model, an optimal Unilateral Ladder-Type Helical Baffles (ULHB) design and intelligent performance prediction system based U-tube heat exchanger was designed to reduce the pressure drop as well as predict the heat exchanger performance. The shell and tubes were made up of steel and copper material, respectively. A baffle was placed above tubes to barrier the flow of cold water. The design of the baffle was accomplished by using Chimp Optimization Algorithm (ChOA) and is motivated by the hunting behaviour of chimpanzees. After designing the exchanger, its fluid analysis was verified, and the parameter values of the heat exchanger were collected to create a dataset. Based on that data, the intelligent performance prediction-system was designed. The controlling system analysed the given data to predict the performance of the heat exchanger. The suggested model has a pressure drop of 55 Pa, a heat transfer coefficient of 411 <i>U,</i> and 86% accuracy for the thermal performance prediction process. The proposed model provides better performance by improving heat transfer efficiency and significantly reduces pressure drop.</p>","PeriodicalId":721,"journal":{"name":"Optical Memory and Neural Networks","volume":null,"pages":null},"PeriodicalIF":1.0000,"publicationDate":"2023-12-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Optical Memory and Neural Networks","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.3103/s1060992x23040033","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q4","JCRName":"OPTICS","Score":null,"Total":0}

引用次数: 0

Abstract

In the chemical, pharmaceutical, and petroleum industries, Shell and U-Tube Heat Exchangers (STHX) were extensively utilized. Baffles must be positioned at the right distance and angle to increase the heat exchangers' capacity to convey heat and, as a result, lower pressure in the shell. The rate of heat transfer in an STHX has been improved, and pressure drop has been reduced using a variety of models. But those methods are not provided satisfactory pressure drop reduction. In the proposed model, an optimal Unilateral Ladder-Type Helical Baffles (ULHB) design and intelligent performance prediction system based U-tube heat exchanger was designed to reduce the pressure drop as well as predict the heat exchanger performance. The shell and tubes were made up of steel and copper material, respectively. A baffle was placed above tubes to barrier the flow of cold water. The design of the baffle was accomplished by using Chimp Optimization Algorithm (ChOA) and is motivated by the hunting behaviour of chimpanzees. After designing the exchanger, its fluid analysis was verified, and the parameter values of the heat exchanger were collected to create a dataset. Based on that data, the intelligent performance prediction-system was designed. The controlling system analysed the given data to predict the performance of the heat exchanger. The suggested model has a pressure drop of 55 Pa, a heat transfer coefficient of 411 U, and 86% accuracy for the thermal performance prediction process. The proposed model provides better performance by improving heat transfer efficiency and significantly reduces pressure drop.

Abstract Image

查看原文

微信好友朋友圈 QQ好友复制链接

本刊更多论文

利用 "黑猩猩优化 "和 "深度信念神经网络 "降低 U 型管式热交换器的压降并预测热性能

摘要在化学、制药和石油工业中，壳管和 U 型管热交换器（STHX）得到了广泛应用。挡板必须保持适当的距离和角度，以提高热交换器的传热能力，从而降低壳体内的压力。STHX 热交换器的传热速度得到了提高，压降也通过各种模型得到了降低。但这些方法并不能令人满意地降低压降。在所提出的模型中，设计了一种基于 U 型管换热器的最优单侧阶梯式螺旋挡板（ULHB）设计和智能性能预测系统，以降低压降并预测换热器的性能。壳体和管子分别由钢和铜材料制成。管子上方设有挡板，以阻挡冷水的流动。挡板的设计采用了黑猩猩优化算法（ChOA），其灵感来自黑猩猩的狩猎行为。设计完热交换器后，对其流体分析进行了验证，并收集了热交换器的参数值以创建数据集。根据这些数据，设计了智能性能预测系统。控制系统通过分析给定数据来预测热交换器的性能。建议的模型压降为 55 Pa，传热系数为 411 U，热性能预测准确率为 86%。所建议的模型通过提高传热效率和显著降低压降来提供更好的性能。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文去求助

来源期刊

Optical Memory and Neural Networks OPTICS-

CiteScore

1.50

自引率

11.10%

发文量

期刊介绍： The journal covers a wide range of issues in information optics such as optical memory, mechanisms for optical data recording and processing, photosensitive materials, optical, optoelectronic and holographic nanostructures, and many other related topics. Papers on memory systems using holographic and biological structures and concepts of brain operation are also included. The journal pays particular attention to research in the field of neural net systems that may lead to a new generation of computional technologies by endowing them with intelligence.