音频信号在气体钻井携岩状态监测中的应用研究

发布时间：2018-04-12 00:21

本文选题：气体钻井 + 大颗粒岩屑　；参考：《西南石油大学》2017年硕士论文

【摘要】：近年来,气体钻井作为一项应对复杂地质的高效钻井方式得到了越来越多的应用,但使用气体作为钻井循环介质易发生井壁坍塌、井底岩爆等状况,急需一种安全监测系统保障气体钻井的安全运行。当气体钻井发生异常状况时,排砂管内返出岩屑的流量会突然变化,大颗粒岩屑明显增多,及时、准确地监测大颗粒岩屑的流量变化,可为判断、预防井下事故的发生提供依据。本文在分析大颗粒岩屑撞击音频信号特征的基础上,开展了气体钻井返出大颗粒岩屑的监测方法研究。首先,根据对异常状况发生时岩屑大小的调研,设计了音频信号采集方案用于采集岩屑撞击声和干扰声;然后,根据短时能量的大小寻找声音段的起止点,分析声音段特征,选定以梅尔倒谱系数为主的混合参数组成模板库,利用人工神经网络算法排除干扰声音;最后,分析不同大小岩屑撞击声的状态特征,分别利用隐马尔科夫模型和能量法计算岩屑的大小,并在MATLAB平台上验证了方法的可用性。在理论研究的基础上,设计了排砂管线返屑状态的安全监测系统。系统硬件部分主要由PC机、外置声卡、音频信号线、拾音器、隔音材料组成;软件部分采用C#语言编写监控界面、SQLServer数据库存储监测信息。通过测试,系统能够达到实时性、准确性的要求。通过大量实验结果表明,采用声音处理技术排除干扰声,继而识别岩屑大小的二级判断方法,适用于排砂管线返屑状态的监测,可为气体钻井的安全运行提供有力保障,有较高的实用价值。
[Abstract]:In recent years, gas drilling has been used more and more as an efficient drilling method to deal with complicated geology.A safety monitoring system is urgently needed to ensure the safe operation of gas drilling.When abnormal condition occurs in gas drilling, the flow rate of the back cuttings in the sand discharge pipe will change suddenly, and the large granular cuttings will increase obviously. It can be judged that the flow rate of the large granular cuttings can be monitored in time and accurately.To prevent underground accidents from happening.Based on the analysis of the characteristics of the large particle cuttings impact audio signal, the monitoring method of the large grain cuttings from gas drilling is studied in this paper.First of all, according to the investigation of the debris size when the abnormal condition occurs, the audio signal acquisition scheme is designed to collect the cuttings impact sound and interference sound, and then, according to the size of the short time energy, the starting and ending points of the sound segment are found, and the characteristics of the sound segment are analyzed.The template library is composed of mixed parameters based on Mel cepstrum coefficient, and the interference sound is eliminated by artificial neural network algorithm. Finally, the state characteristics of cuttings impact sound of different sizes are analyzed.The size of cuttings is calculated by using hidden Markov model and energy method respectively, and the availability of the method is verified on MATLAB platform.On the basis of theoretical research, a safety monitoring system for the state of sand discharge pipeline is designed.The hardware part of the system is mainly composed of PC, external sound card, audio signal line, pick-up, soundproof material, and the software part uses C # language to compile the monitor interface and SQL Server database to store monitoring information.Through testing, the system can meet the requirements of real-time and accuracy.Through a large number of experimental results, it is shown that the two-stage judgment method of eliminating interference sound by sound processing technology and then identifying the size of cuttings is suitable for monitoring the sawback state of sand discharge pipeline, and can provide a strong guarantee for the safe operation of gas drilling.It has higher practical value.
【学位授予单位】：西南石油大学
【学位级别】：硕士
【学位授予年份】：2017
【分类号】：TE242

【相似文献】