电力变压器是电力系统的关键设备,其运行状态与电网稳定性密切相关。变压器油中溶解气体分析(dissolve gas analysis,DGA)是判断其运行状态的重要方法,预测变压器未来时刻的油中溶解气体含量,可以辅助运维人员判断变压器未来的运行趋势...电力变压器是电力系统的关键设备,其运行状态与电网稳定性密切相关。变压器油中溶解气体分析(dissolve gas analysis,DGA)是判断其运行状态的重要方法,预测变压器未来时刻的油中溶解气体含量,可以辅助运维人员判断变压器未来的运行趋势,提前掌握运行状态确保稳定运行。然而,由于油中溶解气体的产生机制复杂且受到变压器特殊运行工况、严苛运行环境、复杂电磁环境等因素的影响,油中溶解气体时间序列将呈现非线性和非平稳性的特征,传统的基于回归拟合模型的预测方法很难挖掘时间序列的这些特征,从而导致预测准确性较低,无法用于对变压器运行状态和故障的预测和诊断。为了解决上述问题,该文利用经验小波变换将具有非线性和非平稳的油中溶解气体时间序列分解为多个复杂度较低的分量,使得预测模型更易挖掘其变化特征,随后,以径向基函数神经网络作为基学习器构建了梯度提升径向基,将径向基函数神经网络的最佳逼近、避免局部最小等优点与梯度提升机强大的监督学习能力相结合,实现对油中溶解气体分解分量潜在规律的深度挖掘,并最终实现对油中溶解气体数据的精准预测。基于现场在运变压器对所提方法进行验证,结果表明:对于单台变压器预测准确率可达98.30%,对于某区域电网内的全体变压器准确率可提升9.01%,且可以实现对变压器故障的准确预测。展开更多
Artificial lift plays an important role in petroleum industry to sustain production flowrate and to extend the lifespan of oil wells. One of the most popular artificial lift methods is Electric Submersible Pumps (ESP)...Artificial lift plays an important role in petroleum industry to sustain production flowrate and to extend the lifespan of oil wells. One of the most popular artificial lift methods is Electric Submersible Pumps (ESP) because it can produce high flowrate even for wells with great depth. Although ESPs are designed to work under extreme conditions such as corrosion, high temperatures and high pressure, their lifespan is much shorter than expected. ESP failures lead to production loss and increase the cost of replacement, because the cost of intervention work for ESP is much higher than for other artificial lift methods, especially for offshore wells. Therefore, the prediction of ESP failures is highly valuable in oil production and contribute</span></span></span><span style="font-family:Verdana;"><span style="font-family:Verdana;"><span style="font-family:Verdana;"><span style="font-family:Verdana;">s</span></span></span></span><span><span><span><span style="font-family:""><span style="font-family:Verdana;"> a lot to the design, construction and operation of oil wells. The contribution of this study is to use 3 machine learning algorithms, which are Decision Tree, Random Forest and Gradient Boosting Machine, to build predictive models for ESP lifespan while using both dynamic and static ESP parameters. The results of these </span><span style="font-family:Verdana;">models were compared to find out the most suitable model for </span></span></span></span></span><span style="font-family:Verdana;"><span style="font-family:Verdana;"><span style="font-family:Verdana;"><span style="font-family:Verdana;">the </span></span></span></span><span style="font-family:Verdana;"><span style="font-family:Verdana;"><span style="font-family:Verdana;"><span style="font-family:Verdana;">prediction of ESP life cycle. In addition, this study also evaluated the influence factor of various operating param</span></span></span></span><span style="font-family:Verdana;"><span style="font-family:Verdana;"><span style="font-family:Verdana;"><span 展开更多
文摘电力变压器是电力系统的关键设备,其运行状态与电网稳定性密切相关。变压器油中溶解气体分析(dissolve gas analysis,DGA)是判断其运行状态的重要方法,预测变压器未来时刻的油中溶解气体含量,可以辅助运维人员判断变压器未来的运行趋势,提前掌握运行状态确保稳定运行。然而,由于油中溶解气体的产生机制复杂且受到变压器特殊运行工况、严苛运行环境、复杂电磁环境等因素的影响,油中溶解气体时间序列将呈现非线性和非平稳性的特征,传统的基于回归拟合模型的预测方法很难挖掘时间序列的这些特征,从而导致预测准确性较低,无法用于对变压器运行状态和故障的预测和诊断。为了解决上述问题,该文利用经验小波变换将具有非线性和非平稳的油中溶解气体时间序列分解为多个复杂度较低的分量,使得预测模型更易挖掘其变化特征,随后,以径向基函数神经网络作为基学习器构建了梯度提升径向基,将径向基函数神经网络的最佳逼近、避免局部最小等优点与梯度提升机强大的监督学习能力相结合,实现对油中溶解气体分解分量潜在规律的深度挖掘,并最终实现对油中溶解气体数据的精准预测。基于现场在运变压器对所提方法进行验证,结果表明:对于单台变压器预测准确率可达98.30%,对于某区域电网内的全体变压器准确率可提升9.01%,且可以实现对变压器故障的准确预测。
文摘Artificial lift plays an important role in petroleum industry to sustain production flowrate and to extend the lifespan of oil wells. One of the most popular artificial lift methods is Electric Submersible Pumps (ESP) because it can produce high flowrate even for wells with great depth. Although ESPs are designed to work under extreme conditions such as corrosion, high temperatures and high pressure, their lifespan is much shorter than expected. ESP failures lead to production loss and increase the cost of replacement, because the cost of intervention work for ESP is much higher than for other artificial lift methods, especially for offshore wells. Therefore, the prediction of ESP failures is highly valuable in oil production and contribute</span></span></span><span style="font-family:Verdana;"><span style="font-family:Verdana;"><span style="font-family:Verdana;"><span style="font-family:Verdana;">s</span></span></span></span><span><span><span><span style="font-family:""><span style="font-family:Verdana;"> a lot to the design, construction and operation of oil wells. The contribution of this study is to use 3 machine learning algorithms, which are Decision Tree, Random Forest and Gradient Boosting Machine, to build predictive models for ESP lifespan while using both dynamic and static ESP parameters. The results of these </span><span style="font-family:Verdana;">models were compared to find out the most suitable model for </span></span></span></span></span><span style="font-family:Verdana;"><span style="font-family:Verdana;"><span style="font-family:Verdana;"><span style="font-family:Verdana;">the </span></span></span></span><span style="font-family:Verdana;"><span style="font-family:Verdana;"><span style="font-family:Verdana;"><span style="font-family:Verdana;">prediction of ESP life cycle. In addition, this study also evaluated the influence factor of various operating param</span></span></span></span><span style="font-family:Verdana;"><span style="font-family:Verdana;"><span style="font-family:Verdana;"><span
