期刊文献+
共找到2篇文章
< 1 >
每页显示 20 50 100
Few-shot working condition recognition of a sucker-rod pumping system based on a 4-dimensional time-frequency signature and meta-learning convolutional shrinkage neural network 被引量:1
1
作者 Yun-Peng He Chuan-Zhi Zang +4 位作者 Peng Zeng Ming-Xin Wang Qing-Wei Dong Guang-Xi Wan Xiao-Ting Dong 《Petroleum Science》 SCIE EI CAS CSCD 2023年第2期1142-1154,共13页
The accurate and intelligent identification of the working conditions of a sucker-rod pumping system is necessary. As onshore oil extraction gradually enters its mid-to late-stage, the cost required to train a deep le... The accurate and intelligent identification of the working conditions of a sucker-rod pumping system is necessary. As onshore oil extraction gradually enters its mid-to late-stage, the cost required to train a deep learning working condition recognition model for pumping wells by obtaining enough new working condition samples is expensive. For the few-shot problem and large calculation issues of new working conditions of oil wells, a working condition recognition method for pumping unit wells based on a 4-dimensional time-frequency signature (4D-TFS) and meta-learning convolutional shrinkage neural network (ML-CSNN) is proposed. First, the measured pumping unit well workup data are converted into 4D-TFS data, and the initial feature extraction task is performed while compressing the data. Subsequently, a convolutional shrinkage neural network (CSNN) with a specific structure that can ablate low-frequency features is designed to extract working conditions features. Finally, a meta-learning fine-tuning framework for learning the network parameters that are susceptible to task changes is merged into the CSNN to solve the few-shot issue. The results of the experiments demonstrate that the trained ML-CSNN has good recognition accuracy and generalization ability for few-shot working condition recognition. More specifically, in the case of lower computational complexity, only few-shot samples are needed to fine-tune the network parameters, and the model can be quickly adapted to new classes of well conditions. 展开更多
关键词 Few-shot learning Indicator diagram META-LEARNING Soft thresholding Sucker-rod pumping system time–frequency signature Working condition recognition
下载PDF
Critical dispersion of chirped fiber Bragg grating for eliminating time delay signature of distributed feedback laser chaos
2
作者 王大铭 雷一航 +1 位作者 史鹏飞 李壮爱 《Chinese Physics B》 SCIE EI CAS CSCD 2023年第9期237-241,共5页
Optical chaos has attracted widespread attention owing to its complex dynamic behaviors.However,the time delay signature(TDS)caused by the external cavity mode reduces the complexity of optical chaos.We propose and nu... Optical chaos has attracted widespread attention owing to its complex dynamic behaviors.However,the time delay signature(TDS)caused by the external cavity mode reduces the complexity of optical chaos.We propose and numerically demonstrate the critical dispersion of chirped fiber Bragg grating(CFBG)for eliminating the TDS of laser chaos in this work.The critical dispersion,as a function of relaxation frequency and bandwidth of the optical spectrum,is found through extensive dynamics simulations.It is shown that the TDS can be eliminated when the dispersion of CFBG is above this critical dispersion.In addition,the influence of dispersive feedback light and output light from a laser is investigated.These results provide important quantitative guidance for designing chaotic semiconductor lasers without TDS. 展开更多
关键词 CHAOS semiconductor laser time delay signature chirped fiber Bragg grating(CFBG)
下载PDF
上一页 1 下一页 到第
使用帮助 返回顶部