计算技术与自动化
計算技術與自動化
계산기술여자동화
COMPUTING TECHNOLOGY AND AUTOMATION
2015年
2期
114-116
,共3页
反馈动态神经网络%粒子群算法%异常井
反饋動態神經網絡%粒子群算法%異常井
반궤동태신경망락%입자군산법%이상정
feedback dynamic neural network%particle swarm algorithm%abnormal well
针对油田异常井诊断的问题，提出基于反馈动态神经网络的模型，该模型具有适应性强、学习效率高等特点。结合粒子群算法弥补其训练速度慢和容易陷入局部最小的缺点，给出模型及算法的优化原则和实现技术。最后根据实际问题，进行油田异常井诊断模型的具体应用，实验结果证明模型对于异常井诊断具有较高准确性及可行性。
針對油田異常井診斷的問題，提齣基于反饋動態神經網絡的模型，該模型具有適應性彊、學習效率高等特點。結閤粒子群算法瀰補其訓練速度慢和容易陷入跼部最小的缺點，給齣模型及算法的優化原則和實現技術。最後根據實際問題，進行油田異常井診斷模型的具體應用，實驗結果證明模型對于異常井診斷具有較高準確性及可行性。
침대유전이상정진단적문제，제출기우반궤동태신경망락적모형，해모형구유괄응성강、학습효솔고등특점。결합입자군산법미보기훈련속도만화용역함입국부최소적결점，급출모형급산법적우화원칙화실현기술。최후근거실제문제，진행유전이상정진단모형적구체응용，실험결과증명모형대우이상정진단구유교고준학성급가행성。
According to oilfield abnormal well,this paper proposed a dynamic feedback neural network model,which has the characteristics of strong adaptability and higher learning efficiency.Combined with the particle swarm algorithm to com-pensate for its slow training speed and falling easily into local minimum points,it gave the principle of optimization model and algorithm and implementation technology.Finally,according to the actual problem,this papers carried on the concrete application of diagnosis model for oilfield abnormal well,and the experimental results show that the model for abnormal well has higher diagnostic accuracy and feasibility.
