技术领域technical field
本发明属于工程勘探领域，具体涉及一种对地裂缝识别的有效方法。The invention belongs to the field of engineering exploration, and in particular relates to an effective method for identifying ground fissures.
背景技术Background technique
“地裂缝”地面裂缝的简称。是地表岩层、土体在自然因素(地壳活动、水的作用等)或人为因素(抽水、灌溉、开挖等)作用下，产生开裂，并在地面形成一定长度和宽度的裂缝的一种宏观地表破坏现象。地裂缝作为一种表生的地质灾害现象，在世界许多国家普遍存在，地裂缝造成地面及地下建筑物开裂，破坏路面，错断地下供水、输气管道，危及文物古迹安全，造成巨大经济损失，给居民生活带来很多不便，因此采取有效探测方法查明地裂缝的展布特征具有重要意义。由于地裂缝发育的隐蔽性和不确定性,故其探测难度较大,如果单纯采用钻探方法,由于单个钻孔仅可了解一个点的地层,不仅勘查周期长、费用高，而且布置的钻孔数量和勘查范围都有限，很难满足查清地裂缝整体空间分布特征的目的。相比之下，本方法具有方便、经济、快捷和成果直观的特点，在解决地裂缝的空间分布特征上有不可替代的优越性,因此利用该方法技术开展地裂缝的精细探测是一个较好的选择。"Ground fissure" short for ground fissure. It is a kind of macroscopic cracking that occurs on the surface rock layer and soil under the action of natural factors (crustal activity, water action, etc.) or human factors (pumping, irrigation, excavation, etc.), and forms cracks of a certain length and width on the ground. Surface damage. As a superficial geological disaster phenomenon, ground fissures are common in many countries in the world. Ground fissures cause ground and underground buildings to crack, damage road surfaces, disrupt underground water supply and gas pipelines, endanger the safety of cultural relics and historic sites, and cause huge economic losses. , which brings a lot of inconvenience to residents' lives, so it is of great significance to find out the distribution characteristics of ground fissures by effective detection methods. Due to the concealment and uncertainty of the development of ground fissures, it is difficult to detect them. If only the drilling method is used, since a single borehole can only understand the stratum at one point, not only the exploration period is long and the cost is high, but also the drill holes arranged The number and scope of exploration are limited, and it is difficult to meet the purpose of finding out the overall spatial distribution characteristics of ground fissures. In contrast, this method has the characteristics of convenience, economy, quickness and intuitive results, and has irreplaceable advantages in solving the spatial distribution characteristics of ground fissures. Therefore, using this method to carry out fine detection of ground fissures is a better method. s Choice.
发明内容Contents of the invention
在原始地震数据上做倾角滤波处理得到的地裂缝增强滤波倾角数据体。是用倾角控制对地震数据做倾角定向滤波，改善同相轴的横向连续性，减少处理时产生的随机扰动，应用包含有倾角和方位角信息的增强滤波倾角数据体能提高神经网络提取最佳地震属性的精确度。The ground fissure enhanced filter dip data volume obtained by dip filter processing on the original seismic data. It uses dip control to perform dip-oriented filtering on seismic data, improves the lateral continuity of the event, reduces random disturbances during processing, and uses enhanced filtering dip data that includes dip and azimuth information to improve the neural network to extract the best seismic attributes. the accuracy.
对所述利用滤波倾角数据体计算和确定单地震道或多地震道的属性集，包括振幅、相位、相干、相似、能量、频率、曲率等，其中基准时间、能量时窗、倾角变化、相似性等是重要属性。Calculate and determine the attribute set of a single seismic trace or multiple seismic traces using the filtered dip data volume, including amplitude, phase, coherence, similarity, energy, frequency, curvature, etc., wherein the reference time, energy time window, dip angle change, similarity Sex etc. are important attributes.
人为拾取气烟囱体和非气烟囱体训练样点集。是在增强滤波倾角数据体和相干、相似体上进行的，拾取过程中参考若干对地裂缝敏感的单属性体，以人为经验和区域地质情况为基 础，拾取气烟囱体和非气烟囱体两组训练样点集。The training sample set of gas chimney and non-gas chimney is artificially picked. It is carried out on the enhanced filtering dip data volume and coherent and similar volumes. During the picking process, a number of single-attribute volumes sensitive to ground fissures are referred to. Based on human experience and regional geological conditions, both gas chimney bodies and non-gas chimney set of training samples.
针对气烟囱区和非气烟囱区所提取的地震属性样点设计神经网络。它将随机分配属性数据到训练组和测试组，并且启动训练状态，对该网络结构进行反复的训练和调整,训练执行情况在训练期间可被追踪，并用两种指数来表示：正常均方根曲线和均方根错误率曲线，RMS错误率曲线表示训练组和测试组的总的错误，分别从1(最大错误)到0(最小错误)，两个曲线在训练期间都应走低，当测试曲线再次走高表示网络过度适配，训练应在这发生之前适可而止；典型的一个RMS值在0.8范围被认为是合理，0.8～0.6是好，0.6～0.4是很好，低于0.4就极好了；此外，网络节点中各属性在当前训练中的权重予以不同颜色表示：当在训练组上的表现达到最小错误时(曲线最低位置)，最优化结果的网络训练会停止，此时即可终止训练，该神经网络所预测的“气烟囱体”能够更清晰地反映地震数据体中的地裂缝展布。A neural network is designed for the seismic attribute sample points extracted from the gas chimney area and the non-gas chimney area. It will randomly assign attribute data to the training group and the test group, and start the training state, repeatedly train and adjust the network structure, the training execution can be tracked during the training, and expressed by two indices: normal root mean square Curve and root mean square error rate curve, RMS error rate curve represents the total error of the training group and the test group, respectively, from 1 (maximum error) to 0 (minimum error), both curves should go down during training, when the test A curve that goes higher again indicates that the network is overfitting, and training should stop before this happens; typically an RMS value in the range of 0.8 is considered reasonable, 0.8 to 0.6 is good, 0.6 to 0.4 is very good, and below 0.4 is excellent ;In addition, the weight of each attribute in the network node in the current training is represented by different colors: when the performance on the training group reaches the minimum error (the lowest position of the curve), the network training of the optimization result will stop, and it can be terminated at this time After training, the "gas chimney" predicted by the neural network can more clearly reflect the distribution of ground fissures in the seismic data volume.
将训练满意的神经网络推广到整个滤波倾角数据体得到气烟囱体并输出。是指将通过神经网络培训得到的最能反映地震异常体的最佳属性应用于整个地震数据体，得到气烟囱体。Extend the trained neural network to the entire filtered dip data body to obtain the gas chimney body and output it. It refers to applying the best attributes obtained through neural network training that can best reflect the seismic anomaly body to the entire seismic data body to obtain the gas chimney body.
显示和解释气烟囱体并识别地裂缝。是将气烟囱剖面与相干、相似性剖面对比可以看出，气烟囱剖面不仅突出了气烟囱体、断裂系统的垂向特征，同时又有效压制了主要由噪声和低波阻抗等引起的低相干但非气烟囱的特征，气烟囱剖面与地震剖面叠合显示，能够快速、准确地对陷落柱进行解释。Display and interpret gas chimney bodies and identify ground fissures. Comparing the gas chimney profile with the coherence and similarity profiles, it can be seen that the gas chimney profile not only highlights the vertical characteristics of the gas chimney body and fracture system, but also effectively suppresses the low coherence mainly caused by noise and low wave impedance. However, the characteristics of the non-gas chimney, the superimposed display of the gas chimney section and the seismic section, can quickly and accurately interpret the collapsed column.
附图说明Description of drawings
图1：为本发明的工作流程图。Fig. 1: is the work flowchart of the present invention.
图2：为气烟囱体剖面与常规地震剖面叠合显示图。Figure 2: Superimposed display of gas chimney section and conventional seismic section.
图3：为地震剖面显示图。Figure 3: Display diagram for seismic section.
具体实施方式detailed description
下面结合具体实施例对本发明的技术方案和技术效果进行详细地说明，但本发明的范围并不限制于以下具体实施例。The technical solutions and technical effects of the present invention will be described in detail below in conjunction with specific examples, but the scope of the present invention is not limited to the following specific examples.
该工区位于山西祁县，首先对所得到的地震偏移数据做倾角滤波处理得到地裂缝增强滤 波倾角数据体，人为拾取气烟囱和非气烟囱体训练样点，然后在两组拾取点集处提取多种地震属性并设计训练神经网络，提取的属性有：振幅、频率、相位、能量、相干、相似性和曲率，将训练满意的神经网络应用于整个地震数据体得到气烟囱体。最终通过地震数据和气烟囱体的叠合显示的方法，实现对该研究区地裂缝进行解释的目的。图2为气烟囱体剖面与常规地震剖面叠合显示图，图中指示的位置即为地裂缝预测位置。图3为最终解释的地裂缝成果，通过与实际揭露地裂缝资料对比发现，预测结果与实际结果完全吻合。The work area is located in Qixian County, Shanxi Province. Firstly, the obtained seismic migration data is dip-filtered to obtain the ground fissure-enhanced filtered dip data volume. The training sample points of gas chimney and non-gas chimney body are artificially picked, and then the two sets of picked point sets are Extract a variety of seismic attributes and design and train the neural network. The extracted attributes include: amplitude, frequency, phase, energy, coherence, similarity, and curvature. Apply the trained neural network to the entire seismic data volume to obtain the gas chimney. Finally, the purpose of interpreting the ground fissures in the study area is achieved by superimposing the seismic data and the chimney body. Figure 2 is a superimposed display of the gas chimney profile and the conventional seismic section, and the position indicated in the figure is the predicted position of the ground fissure. Figure 3 shows the results of the final interpretation of the ground fissures. By comparing with the actual ground fissure data, it is found that the predicted results are completely consistent with the actual results.
上述实施例并非是对本发明的限制，本领域相关的普通技术人员应该清楚，在不脱离本发明的基本构思和范围的情况内还可以有多重变形或替代，所有等同的技术方案也应该包含在本发明的保护范围内。本发明的专利保护范围以权力要求的限定为准。The above-mentioned embodiment is not a limitation to the present invention, and it should be clear to those skilled in the art that multiple modifications or substitutions can be made without departing from the basic idea and scope of the present invention, and all equivalent technical solutions should also be included in within the protection scope of the present invention. The scope of patent protection of the present invention is defined by the claims.
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710006085.8ACN106772606A (en) | 2017-01-05 | 2017-01-05 | A kind of new method that effective identification is carried out to ground fissure |
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710006085.8ACN106772606A (en) | 2017-01-05 | 2017-01-05 | A kind of new method that effective identification is carried out to ground fissure |
| Publication Number | Publication Date |
|---|---|
| CN106772606Atrue CN106772606A (en) | 2017-05-31 |
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710006085.8APendingCN106772606A (en) | 2017-01-05 | 2017-01-05 | A kind of new method that effective identification is carried out to ground fissure |
| Country | Link |
|---|---|
| CN (1) | CN106772606A (en) |
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108279435A (en)* | 2017-12-18 | 2018-07-13 | 中国石油天然气股份有限公司 | Method and device for determining fault section |
| CN109581485A (en)* | 2018-12-04 | 2019-04-05 | 成都捷科思石油天然气技术发展有限公司 | A method of carrying out automatic slit detection directly on pre-stack depth migration seismic data |
| CN110952978A (en)* | 2019-12-20 | 2020-04-03 | 西南石油大学 | Drilling leakage fracture width prediction method based on neural network data mining |
| CN111178320A (en)* | 2020-01-07 | 2020-05-19 | 中国矿业大学(北京) | Method for identifying geological anomalies and model training method and device |
| CN111626092A (en)* | 2020-03-26 | 2020-09-04 | 陕西陕北矿业韩家湾煤炭有限公司 | Unmanned aerial vehicle image ground crack identification and extraction method based on machine learning |
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20030200030A1 (en)* | 1998-09-11 | 2003-10-23 | Den Norske Stats Oljeselskap A.S. | Method of processing acquired seismic data |
| WO2011062807A1 (en)* | 2009-11-20 | 2011-05-26 | Exxonmobil Upstream Research Company | Method for geophysical and geological interpretation of seismic volumes in the domains of depth, time, and age |
| CN104614762A (en)* | 2014-12-17 | 2015-05-13 | 中国石油天然气股份有限公司 | Loose sandstone gas reservoir boundary determining method and device |
| CN105277979A (en)* | 2015-10-16 | 2016-01-27 | 中国石油天然气集团公司 | Seismic attribute optimization method and device |
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20030200030A1 (en)* | 1998-09-11 | 2003-10-23 | Den Norske Stats Oljeselskap A.S. | Method of processing acquired seismic data |
| WO2011062807A1 (en)* | 2009-11-20 | 2011-05-26 | Exxonmobil Upstream Research Company | Method for geophysical and geological interpretation of seismic volumes in the domains of depth, time, and age |
| CN104614762A (en)* | 2014-12-17 | 2015-05-13 | 中国石油天然气股份有限公司 | Loose sandstone gas reservoir boundary determining method and device |
| CN105277979A (en)* | 2015-10-16 | 2016-01-27 | 中国石油天然气集团公司 | Seismic attribute optimization method and device |
| Title |
|---|
| 刘伟 等: ""基于倾角数据体的神经网络气烟囱识别"", 《石油地球物理勘探》* |
| 易远元 等: "《海洋深水钻井浅层地质灾害识别技术及案例分析》", 30 June 2012, 石油工业出版社* |
| 杨瑞召 等: ""倾角导向体控制的气烟囱识别技术及其在海拉尔盆地贝尔凹陷中的应用"", 《现代地质》* |
| 高磊 等: ""渤海A油田气烟囱识别及其研究意义"", 《物探与化探》* |
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108279435A (en)* | 2017-12-18 | 2018-07-13 | 中国石油天然气股份有限公司 | Method and device for determining fault section |
| CN108279435B (en)* | 2017-12-18 | 2020-02-14 | 中国石油天然气股份有限公司 | Method and device for determining fault section |
| CN109581485A (en)* | 2018-12-04 | 2019-04-05 | 成都捷科思石油天然气技术发展有限公司 | A method of carrying out automatic slit detection directly on pre-stack depth migration seismic data |
| CN110952978A (en)* | 2019-12-20 | 2020-04-03 | 西南石油大学 | Drilling leakage fracture width prediction method based on neural network data mining |
| CN111178320A (en)* | 2020-01-07 | 2020-05-19 | 中国矿业大学(北京) | Method for identifying geological anomalies and model training method and device |
| CN111178320B (en)* | 2020-01-07 | 2020-11-17 | 中国矿业大学(北京) | Geological abnormal body recognition method and model training method and device thereof |
| CN111626092A (en)* | 2020-03-26 | 2020-09-04 | 陕西陕北矿业韩家湾煤炭有限公司 | Unmanned aerial vehicle image ground crack identification and extraction method based on machine learning |
| CN111626092B (en)* | 2020-03-26 | 2023-04-07 | 陕西陕北矿业韩家湾煤炭有限公司 | A method for ground fissure recognition and extraction based on machine learning from UAV images |
| Publication | Publication Date | Title |
|---|---|---|
| CN106772606A (en) | A kind of new method that effective identification is carried out to ground fissure | |
| CN104879103B (en) | Layered water injection effect analysis method | |
| CN104977617B (en) | Reservoir Fracture recognition methods and imaging logging Reservoir Fracture recognition methods | |
| WO2011077223A2 (en) | System and method for microseismic analysis | |
| CN105334534A (en) | Low order fault interpretation method based on construction mode guidance | |
| CN105319585B (en) | A kind of method hidden using thin-layers interference amplitude recovery identification of hydrocarbon | |
| CN105735978A (en) | Well spacing method for carbonate interlayer karst reservoir | |
| CN105005080A (en) | Method for identifying stratigraphic trap pinch-out line by using amplitude ratio attribute | |
| Qian et al. | Evaluation of hydraulic fracturing in coal seam using ground microseismic monitoring and source location | |
| Wang et al. | Geology Quality: Case Study of Improving Multistage Fracturing and Completion with Quantitative Geology Considerations | |
| CN112748476B (en) | Injection fluid front edge identification method based on stress field and microseism joint inversion | |
| CN106501851B (en) | A kind of optimum methods of seismic attributes and device | |
| CN111379548B (en) | Method, device and equipment for determining well track and storage medium | |
| CN110646847A (en) | Method for identifying low-order fault breakpoint position based on well logging data of close well pattern area | |
| CN112489208A (en) | Crack sheet extraction method based on ant algorithm and three-dimensional geological model construction method | |
| CN104714247A (en) | Pre-stack and post-stack linkage attribute interpretation method | |
| Bai et al. | Evaluating the Sealing Effectiveness of a Caprock‐Fault System for CO2‐EOR Storage: A Case Study of the Shengli Oilfield | |
| CN114033352B (en) | Method and equipment for estimating density of well Zhou Liefeng | |
| CN106646663B (en) | The method that quantitatively characterizing causes oil gas cap rock risk of leakage due to faulting | |
| NL2029807B1 (en) | New method for effectively recognizing ground fissure | |
| CN115932967B (en) | A Crack Recognition Method Based on Ant Body Algorithm | |
| CN119066827B (en) | A method and device for evaluating the conversion of carbonate buried hill oil reservoir into gas storage | |
| CN104714248A (en) | Formation overlap-denudation line recognition method based on iteration earthquake DNA detection | |
| Putra et al. | Open up a new insight to explore bypassed oil in stratigraphic flank area reservoir | |
| CN119066827A (en) | A method and device for evaluating the reconstruction of carbonate buried hill oil reservoir into gas storage |
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | Application publication date:20170531 | |
| RJ01 | Rejection of invention patent application after publication |