| 基于QPSO的BP神经网络油田节能指标预测 |
| |
| 引用本文： | 尚福华,杨慧,张吉峰,马明梅,董桂苓.基于QPSO的BP神经网络油田节能指标预测[J].计算机系统应用,2013,22(6):95-97,185. |
| |
| 作者姓名： | 尚福华 杨慧 张吉峰 马明梅 董桂苓 |
| |
| 作者单位： | 东北石油大学计算机与信息技术学院, 大庆 163318;东北石油大学计算机与信息技术学院, 大庆 163318;大庆市钻探工程公司地质录井一公司, 大庆 163318;东北石油大学计算机与信息技术学院, 大庆 163318;大庆市第三采油厂信息中心, 大庆 163318 |
| |
| 基金项目： | 国家自然科学基金(61170132);国家重大专项(2011ZX05020-007);黑龙江省教育厅科学技术研究项目(12521055) |
| |
| 摘 要： | 针对BP神经网络易陷入局部极小问题以及收敛速度慢的问题, 引入量子粒子群优化算法和BP神经网络相结合的方法, 共享BP神经网络强大的灵活性和量子粒子群全局搜索能力强的优势, 通过改进QPSO的平均最优位置的计算方法, 实现基于BP神经网络和量子粒子群的油田节能指标预测. 以大庆某采油厂注水泵机组单耗数据为训练数据, 预测结果表明该方法能达到良好的预测效果, 具有可行性.
|
| 关 键 词： | BP神经网络 量子粒子群 指标预测 算法优化 滑动平均 |
| 收稿时间： | 2012/11/9 0:00:00 |
| 修稿时间： | 2012/12/23 0:00:00 |
Oilfield Energy Saving Index Prediction Based on QPSO and BP Neural Network |
| |
| SHANG Fu-Hu,YANG Hui,ZHANG Ji-Feng,MA Ming-Mei and DONG Gui-Ling.Oilfield Energy Saving Index Prediction Based on QPSO and BP Neural Network[J].Computer Systems& Applications,2013,22(6):95-97,185. |
| |
| Authors: | SHANG Fu-Hu YANG Hui ZHANG Ji-Feng MA Ming-Mei and DONG Gui-Ling |
| |
| Affiliation: | School of Computer and Information Technology, Northeast Petroleum University, Daqing 163318, China;School of Computer and Information Technology, Northeast Petroleum University, Daqing 163318, China;Daqing Drilling Engineering Geologic Logging Company, Daqing 163318, China;School of Computer and Information Technology, Northeast Petroleum University, Daqing 163318, China;Information Department, Daqing No.3 Oil Production, Daqing 163318, China |
| |
| Abstract: | According to the fact that BP neural network is easy to fall into local minimum and the slow convergence problems, the paper introduces QPSO and BP neural network combination method, which shares the advantage of BP neural network robust flexibility and the powerful global searching ability of QPSO, through improved the calculation method of average optimal position of QPSO to make the BP neural network and QPSO oilfield energy conservation index prediction success. Using the injection pump unit consumption data of Daqing Oilfield Company as training data, by training the new mehtod with the data of samples, the forecast results show that the proposed method can achieve good forecast effect and have feasibility. |
| |
| Keywords: | bp neural network quantum partical swarm index prediction algorithm optimization moving average |
|
| 点击此处可从《计算机系统应用》浏览原始摘要信息 |
|
点击此处可从《计算机系统应用》下载全文 |
|
