基于特征融合的抽油机井检泵周期预测

摘要/Abstract

摘要： 检泵周期是反映抽油机井工作情况的重要指标，准确预测检泵周期对提高油井产能和经济效益具有重要意义。针对油田检泵周期预测准确率低等问题，提出一种基于特征融合抽油机井检泵周期预测方法。该方法引入SVR提取油田数据的静态特征，利用卷积神经网络学习油田数据的动态特征，引入多模态压缩双线性池化对静态特征和动态特征进行融合，利用判别模型训练融合特征实现检泵周期的准确预测。实验结果验证了该模型的有效性和可行性。

关键词: 特征提取, 特征融合, 检泵周期预测, 支持向量回归, 卷积神经网络

Abstract: Pump detection period is an important index to reflect the working reliability of pumping wells. Accurate prediction of pump detection period is of great practical significance to improve oil well production efficiency and economic benefits. Aiming at the low accuracy of pump detection period prediction in oil field, a pump detection period prediction method based on feature fusion is proposed. This method introduces SVR to extract the static characteristics of oilfield data, reconstructs the characteristics of oilfield dynamic data, uses convolution neural network to learn the dynamic characteristics of oilfield data, introduces multi-modal compression bilinear pooling to fuse the static and dynamic characteristics, and uses discriminant model to train the fusion characteristics to realize the accurate prediction of pump detection cycle. The experimental results verify the effectiveness and feasibility of the model.

Key words: feature extraction, feature fusion, pump detection period predicting, support vector regression, convolutional neural network

张晓东, 王栩颖, 秦子轩. 基于特征融合的抽油机井检泵周期预测[J]. 计算机与现代化, 2022, 0(12): 60-66.

ZHANG Xiao-dong, WANG Xu-ying, QIN Zi-xuan. Pump Detection Period Predicting of Pump Well Based on Feature Fusion[J]. Computer and Modernization, 2022, 0(12): 60-66.

参考文献［34］

［1］	吴小文. 油田油井检泵作业原因分析及治理对策［J］. 化学工程与装备, 2021(1):33-34.
［2］	周平,单长吉,刘丽丹. 抽油机井管杆偏磨检泵周期与其影响因素回归分析［J］. 东北电力大学学报, 2008,28(4):11-17.
［3］	任伟建,任欣元,王磊,等. 基于威布尔分布的油田机采井故障率研究［J］. 信息与控制, 2015,44(6):722-728.
［4］	张战敏. 抽油机井检泵周期可靠性预测模型与实际应用［J］. 价值工程, 2015,34(8):31-32.
［5］	赵廷峰,赵春艳,何帆,等. 抽油杆柱磨损分析与安全性评价［J］. 石油机械, 2017,45(8):65-70.
［6］	王旭东,李斌. 水平井抽油杆扶正器结构优化和疲劳寿命分析［J］. 西部探矿工程, 2016,28(12):30-31.
［7］	万夫,周兆明,张健,等. 基于在线检测数据优化连续油管疲劳寿命预测［J］. 钻采工艺, 2020,43(6):9-12.
［8］	赵岩龙,方正魁,邱子瑶,等. 基于长短时记忆网络的腐蚀工况下抽油杆剩余使用寿命预测［J］. 科学技术与工程, 2021,21(36):15429-15433.
［9］	侯延彬,陈炳均,高宪文. 基于GM-ELM的有杆泵抽油井故障诊断［J］. 东北大学学报(自然科学版), 2019,40(12):1673-1678.
［10］	ZHANG R, ZHANG W, SHEN S, et al. Evaluation of the correlations between laboratory measured material properties with field cracking performance for asphalt pavement［J］. Construction and Building Materials, 2021,301. DOI:10.1016/j.conbuildmat.2021.124126.
［11］	CHEN Y, XU P, CHU Y, et al. Short-term electrical load forecasting using the Support Vector Regression (SVR) model to calculate the demand response baseline for office buildings［J］. Applied Energy, 2017,195:659-670.
［12］	DENDI S V R, CHANNAPPAYYA S S. No-reference video quality assessment using natural spatiotemporal scene statistics［J］. IEEE Transactions on Image Processing, 2020,29:5612-5624.
［13］	DHIMAN H S, DEB D, GUERRERO J M. Hybrid machine intelligent SVR variants for wind forecasting and ramp events［J］.Renewable and Sustainable Energy Reviews, 2019,108:369-379.
［14］	FEIZIZADEH B, ROODPOSHTI M S, BLASCHKE T, et al. Comparing GIS-based support vector machine kernel functions for landslide susceptibility mapping［J］. Arabian Journal of Geosciences, 2017,10(5). DOI:10.1007/s12517-017-2918-z.
［15］	XIONG J, LIANG Q, WAN J, et al. The order statistics correlation coefficient and PPMCC fuse non-dimension in fault diagnosis of rotating petrochemical unit［J］. IEEE Sensors Journal, 2018,18(11):4704-4714.
［16］	XIE C, KUMAR A. Finger vein identification using Convolutional Neural Network and supervised discrete hashing［J］. Pattern Recognition Letters, 2019,119:148-156.
［17］	JUNG S, LEE J, CHO H, et al. Compton background elimination for in vivo x-ray fluorescence imaging of gold nanoparticles using convolutional neural network［J］. IEEE Transactions on Nuclear Science, 2020,67(11):2311-2320.〖HJ0.6mm〗
［18］	ZHANG Y, LEE T S, LI M, et al. Convolutional neural network models of V1 responses to complex patterns［J］. Journal of Computational Neuroscience, 2019,46(1):33-54.
［19］	LU Z, JIANG X, KOT A. Deep coupled ResNet for low-resolution face recognition［J］. IEEE Signal Processing Letters, 2018,25(4):526-530.
［20］	BALTRUSCHAT I M, NICKISCH H, GRASS M, et al. Comparison of deep learning approaches for multi-label chest x-ray classification［J］. Scientific Reports, 2019,9(1). DOI:10.1038/s41598-019-42294-8.
［21］	LU Z, BAI Y, CHEN Y, et al. The classification of gliomas based on a Pyramid dilated convolution resnet model［J］. Pattern Recognition Letters, 2020,133:173-179.
［22］	LEE J, SHRIDHAR K, HAYASHI, et al. ProbAct: A probabilistic activation function for deep neural networks ［J］.arXiv preprint arXiv:1905.10761, 2019.
［23］	ARIAV I, COHEN I. An end-to-end multimodal voice activity detection using waveNet encoder and residual networks［J］. IEEE Journal of Selected Topics in Signal Processing, 2019,13(2):265-274.
［24］	NOWAKOWSKA E, KORONACKI J, LIPOVETSKY S. Clusterability assessment for Gaussian mixture models［J］. Applied Mathematics and Computation, 2015,256(C):591-601.
［25］	LORAH J, WOMACK A. Value of sample size for computation of the Bayesian Information Criterion (BIC) in multlevel modeling［J］. Behavior Research Methods, 2019, 51(1):440-450.
［26］	YANG M, LAI C, LIN C. A robust EM clustering algorithm for Gaussian mixture models［J］. Pattern Recognition, 2012,45(11):3950-3961.
［27］	LEI X, FANG Z. GBDTCDA: Predicting circRNA-disease associations based on gradient boosting decision tree with multiple biological data fusion［J］. International Journal of Biological Sciences, 2019,15(13):2911-2924.
［28］	GUO F, LIU Z, HU W, et al. Gain prediction and compensation for subarray antenna with assembling errors based on improved XGBoost and transfer learning［J］. IET Microwaves, Antennas & Propagation, 2020,14(6). DOI:10.1049/iet-map.2019.0182.
［29］	MA J, CHENG J C P, XU Z, et al. Identification of the most influential areas for air pollution control using XGBoost and Grid Importance Rank［J］. Journal of Cleaner Production,2020,274. DOI:10.1016/j.jclepro.2020.122835.
［30］	ZHANG Z, HUANG Y, QIN R, et al. XGBoost-based on-line prediction of seam tensile strength for Al-Li alloy in laser welding: Experiment study and modelling［J］. Journal of Manufacturing Processes, 2021,64:30-44.
［31］	NANDINI N, SHENGPING Y, ENRIQUE G. Impact of mechanical circulatory support on post-transplant stroke risk［J］.The International Journal of Artificial Organs, 2021,44(10):675-680.
［32］	WANG Z, ZHAN Z, KWONG S, et al. Adaptive granularity learning distributed particle swarm optimization for large-scale optimization［J］. IEEE Transactions on Cybernetics, 2020. DOI:10.1109/TCYB.2020.2977956.
［33］	CHIRI H, ABASCAL A J, CASTANEDO S, et al. Mid-long term oil spill forecast based on logistic regression modelling of met-ocean forcings［J］. Marine Pollution Bulletin, 2019,146:962-976.
［34］	王鑫,吴际,刘超,等. 基于LSTM循环神经网络的故障时间序列预测［J］. 北京航空航天大学学报, 2018,44(4):772-784.

[1]	刘缨杰, 兰海, 魏宪. 基于卷积与稀疏编码的半监督学习方法[J]. 计算机与现代化, 2022, 0(11): 9-16.
[2]	王长军, 彭成, 李勇. 复杂环境下的多特征融合船舶目标检测算法[J]. 计算机与现代化, 2022, 0(11): 81-88.
[3]	尹初, 赵启林, 芮挺, 袁辉, 王剑. 基于自适应锚框的裂缝目标检测算法研究[J]. 计算机与现代化, 2022, 0(11): 95-101.
[4]	李春生, 冯阳宵, 富宇, 张可佳, 吴润桐. 基于均值聚类的员工行为分析方法[J]. 计算机与现代化, 2022, 0(09): 19-24.
[5]	王梦, 张鸿鑫, 刘庆华, 张东. 基于改进YOLOv5的幽门螺杆菌免疫印迹图像识别[J]. 计算机与现代化, 2022, 0(09): 78-84.
[6]	王盼红, 朱昌明. 融合CNN与交互特征的多标签图像分类方法[J]. 计算机与现代化, 2022, 0(09): 85-92.
[7]	刘立婷, 欧毓毅. 融合注意力机制与并行混合网络的DGA域名检测[J]. 计算机与现代化, 2022, 0(09): 119-126.
[8]	曾奕斌, 葛红. 基于语义融合和多重相似性学习的跨模态检索[J]. 计算机与现代化, 2022, 0(08): 50-56.
[9]	李燕, 卢峥松, 李青云, 杨世海, 张小龙. 基于轻量级结构重参数化网络的口罩检测算法[J]. 计算机与现代化, 2022, 0(07): 40-46.
[10]	张龄允, 韩莹, 张凯, 卢海鹏, 丁昱杰. 基于深度学习的短时交通流预测模型[J]. 计算机与现代化, 2022, 0(07): 54-60.
[11]	贺雨霞, 曹国. 基于改进注意力网络的转炉炼钢状态判别[J]. 计算机与现代化, 2022, 0(07): 97-102.
[12]	陈钢. 融合RoBERTa和特征提取的政务热线工单分类[J]. 计算机与现代化, 2022, 0(06): 21-26.
[13]	何丽雯, 张锐驰. 基于深度学习的驾驶员分心行为识别[J]. 计算机与现代化, 2022, 0(06): 67-74.
[14]	徐亚军, 郭恩豪, 陈林, 司成可. 数据驱动的RF信号深度调制识别方法[J]. 计算机与现代化, 2022, 0(06): 80-86.
[15]	谭金林, 范文童, 刘亚虎, 梁志锋, 王梁, 刘斌, 黄斌. 基于软硬件协同加速框架的遥感图像目标检测[J]. 计算机与现代化, 2022, 0(06): 109-115.