基于CNN-LSTM-CS工业管道腐蚀率预测模型
作者:
基金项目:

国家自然科学基金(62206094); 湖州市公益性应用研究项目(2021GZ16); 湖州市特种设备检测研究院科研项目(2020-ZB-09)


Corrosion Rate Prediction Model for Industrial Pipelines Based on CNN-LSTM-CS
Author:
  • 摘要
  • | |
  • 访问统计
  • |
  • 参考文献 [22]
  • |
  • 相似文献 [20]
  • | | |
  • 文章评论
    摘要:

    针对传统工业管道腐蚀率预测模型存在特征提取依赖人工经验和泛化能力不足的问题, 本文将卷积神经网络(convolutional neural network, CNN)和长短期记忆网络(long short-term memory, LSTM)相结合, 提出了基于布谷鸟优化算法(cuckoo search, CS)的CNN-LSTM-CS网络模型, 实现对工业管道腐蚀率预测. 首先, 对采集的管道腐蚀数据集进行归一化预处理; 然后, 利用CNN网络提取影响管道腐蚀率因素的深层次特征信息, 并通过训练LSTM网络构建CNN-LSTM预测模型; 最后, 采用CS算法对预测模型进行参数优化, 减少预测误差, 实现腐蚀率的精准预测. 实验结果表明, 对比几种典型的腐蚀率预测方法, 本文提出的方法具有更高的预测精度, 为工业管道腐蚀率检测提供新的思路.

    Abstract:

    The traditional prediction models for the corrosion rates of industrial pipelines often have the problems of dependence of feature extraction on artificial experience and insufficient generalization ability. To address this issue, this study combines the convolutional neural network (CNN) with the long short-term memory (LSTM) network and proposes a network model based on the cuckoo search (CS) optimization algorithm, namely, the CNN-LSTM-CS model, to predict the corrosion rates of industrial pipelines. Specifically, the collected pipeline corrosion dataset is pre-processed by normalization. Then, the CNN is used to extract information on the deep features of factors affecting the corrosion rates of the pipelines, and a CNN-LSTM prediction model is constructed by training the LSTM network. Finally, the CS algorithm is used to optimize the parameters of the prediction model, thereby reducing the prediction error and predicting the corrosion rate accurately. The experimental results show that compared with several typical prediction methods for the corrosion rate, the method proposed has higher prediction accuracy and provides a new approach for predicting the corrosion rates of industrial pipelines.

    参考文献
    [1] 罗涛, 高观玲, 田晓江, 等. 中低压燃气管网的腐蚀泄漏规律及关键影响因素. 腐蚀与防护, 2023, 44(4): 104–106, 118.
    [2] 吴硕. N公司天然气长输管道安全管理问题研究 [硕士学位论文]. 太原: 太原理工大学, 2022.
    [3] 肖荣鸽, 王栋, 王勤学. 基于ASO-BP神经网络的海底油气管道腐蚀速率预测. 化学工业与工程, 2022, 39(6): 109–116.
    [4] Li XH, Jia RC, Zhang RR, et al. A KPCA-BRANN based data-driven approach to model corrosion degradation of subsea oil pipelines. Reliability Engineering & System Safety, 2022, 219: 108231.
    [5] Seghier MEAB, Keshtegar B, Tee KF, et al. Prediction of maximum pitting corrosion depth in oil and gas pipelines. Engineering Failure Analysis, 2020, 112: 104505.
    [6] Peng SB, Zhang Z, Liu EB, et al. A new hybrid algorithm model for prediction of internal corrosion rate of multiphase pipeline. Journal of Natural Gas Science and Engineering, 2021, 85: 103716.
    [7] 黄港港, 周阳, 闫骁瑾, 等. 基于KPCA-CS-SVM的埋地管道外腐蚀速率预测研究. 热加工工艺, 2022, 51(16): 38–43.
    [8] 周阳, 王寿喜. 基于GRA-IFA-LSSVM模型的气田集输管道内腐蚀速率预测. 腐蚀与防护, 2022, 43(8): 86–93.
    [9] 郭永强, 李希, 周忠强, 等. 基于KPCA-ICS-ELM模型的油气水混输管道腐蚀速率预测分析. 热加工工艺, 2022, 51(16): 54–59, 63.
    [10] 马瑶, 智敏, 殷雁君, 等. CNN和Transformer在细粒度图像识别中的应用综述. 计算机工程与应用, 2022, 58(19): 53–63.
    [11] Magge A, Tutubalina E, Miftahutdinov Z, et al. DeepADEMiner: A deep learning pharmacovigilance pipeline for extraction and normalization of adverse drug event mentions on Twitter. Journal of the American Medical Informatics Association, 2021, 28(10): 2184–2192.
    [12] Kumar LA, Renuka DK, Rose SL, et al. Deep learning based assistive technology on audio visual speech recognition for hearing impaired. International Journal of Cognitive Computing in Engineering, 2022, 3: 24–30.
    [13] 胡中源, 薛羽, 查加杰. 演化循环神经网络研究综述. 计算机科学, 2023, 50(3): 254–265.
    [14] 许珠路, 王兴芬, 刘亚辉. 融合CNN-BiLSTM-Attention的集成学习价格预测. 计算机系统应用, 2023, 32(6): 32–41.
    [15] Karri M, Annavarapu CSR. A real-time embedded system to detect QRS-complex and arrhythmia classification using LSTM through hybridized features. Expert Systems with Applications, 2023, 214: 119221.
    [16] 贾彤华, 范磊, 程光旭, 等. 长短期记忆神经网络模型改进及其在循环冷却水管道腐蚀预测的应用. 石油化工设备, 2022, 51(4): 1–6.
    [17] 张雯莹, 代英宸, 张云龙. 基于LSTM的钢铁厂清循环系统浓缩倍数与腐蚀速率预测. 冶金动力, 2021(4): 61–64.
    [18] Wang Q, Ye M, Wei M, et al. Deep convolutional neural network based closed-loop SOC estimation for lithium-ion batteries in hierarchical scenarios. Energy, 2023, 263: 125718.
    [19] 吴则举, 焦翠娟, 陈亮. 基于改进Faster R-CNN的轮胎缺陷检测方法. 计算机应用, 2021, 41(7): 1939–1946.
    [20] 张达, 郭特, 丁瑞, 等. 具有多层次优化能力的EEG生成模型. 计算机系统应用, 2022, 31(8): 369–379.
    [21] Khadanga RK, Kumar A, Panda S. A modified grey wolf optimization with cuckoo search algorithm for load frequency controller design of hybrid power system. Applied Soft Computing, 2022, 124: 109011.
    [22] 张露潆. 基于改进布谷鸟算法的配送车辆路径优化方法. 吉林大学学报(信息科学版), 2023, 41(1): 118–123.
    引证文献
    网友评论
    网友评论
    分享到微博
    发 布
引用本文

王宏,冯佳俊,戴旗,施宇,梁宇航,张辉.基于CNN-LSTM-CS工业管道腐蚀率预测模型.计算机系统应用,2024,33(5):103-109

复制
分享
文章指标
  • 点击次数:440
  • 下载次数: 1329
  • HTML阅读次数: 760
  • 引用次数: 0
历史
  • 收稿日期:2023-10-30
  • 最后修改日期:2023-12-04
  • 在线发布日期: 2024-04-01
文章二维码
您是第11207641位访问者
版权所有:中国科学院软件研究所 京ICP备05046678号-3
地址:北京海淀区中关村南四街4号 中科院软件园区 7号楼305房间,邮政编码:100190
电话:010-62661041 传真: Email:csa (a) iscas.ac.cn
技术支持:北京勤云科技发展有限公司

京公网安备 11040202500063号