基于多尺度窗口生成器網絡的抽油機噪聲壓制

摘要：在老油田的勘探開發中，抽油機噪聲形成強干擾，嚴重降低了地震資料的信噪比。為此，提出了一種基于多尺度窗口生成器網絡進行抽油機噪聲壓制的方法。構建的網絡主要由雙層編碼器—解碼器組成，結合不同層的特征信息可獲得準確的去噪結果；在不同層采用不同尺寸的窗口進行特征提取，可以有效地擴大神經網絡的感知范圍，并從抽油機噪聲中提取更多有用的特征。為了防止網絡的退化，編碼器和解碼器的每個塊中都分別使用了殘差連接。編碼器殘差塊部分采用了卷積核數量中間大、兩端小的反瓶頸設計，可以提取地震數據更多的特征；解碼器使用了編碼器五分之一的卷積層數，加快了模型訓練以及地震數據重建的速度。通過這種方式構建的網絡可以有效地利用多尺度語義信息壓制地震數據中的抽油機噪聲。模擬數據和實際數據實驗結果均表明，與DnCNN、GAN和MLGNet相比，所提方法能夠獲得高質量的去噪結果，并最大程度地保留有效數據。關鍵詞：地震資料，噪聲壓制，多尺度窗口，生成器，信噪比

中圖分類號：P631文獻標識碼：A DOI：10.13810/j.cnki.issn.1000?7210.2024.04.004

Noise suppression of pumping unit based on multi?scalewindow generator network

MA Yifan1，WEN Wu1，XUE Yajuan2，WEN Xiaotao3，XU Hong1

（1.School of Computer Science，Chengdu University of Information Technology，Chengdu，Sichuan 610225，China；2.Schoolof Communication Engineering，Chengdu University of Information Technology，Chengdu，Sichuan 610225，China；3.School of Geophysics，Chengdu University of Technology，Chengdu，Sichuan 610225，China）

Abstract：The noise of the pumping unit strongly interferes with the exploration and development of old oil fields and seriously reduces the signal?to?noise ratio of seismic data.Therefore，a pumping unit noise suppres?sion method based on a multi?scale window generator network is proposed.The constructed network is mainly composed of a double?layer encoder?decoder structure，and accurate denoising results can be obtained by com?bining characteristic information of different layers.The utilization of different?sized windows in different layers for feature extraction can effectively expand the sensing range of the neural network and extract more useful fea?tures from the pumping unit noise.To prevent the degradation of the network，residual connections are used re?spectively in each block of the encoder and decoder.The residual block of the encoder adopts the anti?bottle?neck design with a large amount of convolution kernels in the middle and small at both ends to extract more fea?tures of seismic data.The decoder uses one?fifth of the convolutional layers of the encoder，speeding up model training and seismic data reconstruction.The network constructed in this way can effectively suppress pumping unit noise in seismic data by using multi?scale semantic information.Both simulated data and real data experi?mental results show that compared with DnCNN，GAN，and M LGNet，the proposed method can obtain high?quality denoising results and retain valid data to the greatest extent.

Keywords：seismic data，noise suppression，multi?scale window，generator，signal?to?noise ratio

馬一凡，文武，薛雅娟，等.基于多尺度窗口生成器網絡的抽油機噪聲壓制［J］.石油地球物理勘探，2024，59（4）：684-691.

MA Yifan，WEN Wu，XUE Yajuan，et al.Noise suppression of pumping unit based on multi-scale window generator network［J］.Oil Geophysical Prospecting，2024，59（4）：684-691.

0引言

在地震資料采集過程中，噪聲會降低地震數據的質量，因此壓制噪聲很關鍵[1?3]。在老油田的勘探開發過程中，地震資料采集經常受到抽油機噪聲的干擾。抽油機噪聲的頻帶很窄，能量主要集中在個別頻率[4]，且其頻帶范圍完全與有效信號重疊，導致抽油機噪聲的壓制十分困難。……