The all traditional electrical resistance tomography (ERT) sensors have a static structure, which cannot satisfy the intelligent requirements for adaptive optimization to ERT sensors that is subject to flow pattern ch...The all traditional electrical resistance tomography (ERT) sensors have a static structure, which cannot satisfy the intelligent requirements for adaptive optimization to ERT sensors that is subject to flow pattern changes during the real-time detection of two-phase flow. In view of this problem, an adaptive ERT sensor with a dynamic structure is proposed. The electrodes of the ERT sensor are arranged in an array structure, the flow pattern recognition technique is introduced into the ERT sensor design and accordingly an ERT flow pattern recognition method based on signal sparsity is proposed. This method uses the sparse representation of the signal to express the sampling voltage of the ERT system as a sparse combination and find its sparse solution to achieve the classification of different flow patterns. With the introduction of flow identification information, the sensor has an intelligent function of adaptively and dynamically adapting the sensor structure according to the real-time flow pattern change. The experimental results show that the sensor can automatically identify four typical flow patterns: core flow, bubble flow, laminar flow and circulation flow with recognition rates of 91%, 93%, 90% and 88% respectively. For different flow patterns, the dynamically optimized sensor can significantly improve the quality of ERT image reconstruction.展开更多
Nonlinear resistivity inversion requires efficient artificial neural network(ANN)model for better inversion results.An evolutionary BP neural network(BPNN)approach based on differential evolution(DE)algorithm was pres...Nonlinear resistivity inversion requires efficient artificial neural network(ANN)model for better inversion results.An evolutionary BP neural network(BPNN)approach based on differential evolution(DE)algorithm was presented,which was able to improve global search ability for resistivity tomography 2-D nonlinear inversion.In the proposed method,Tent equation was applied to obtain automatic parameter settings in DE and the restricted parameter Fcrit was used to enhance the ability of converging to global optimum.An implementation of proposed DE-BPNN was given,the network had one hidden layer with 52 nodes and it was trained on 36 datasets and tested on another 4 synthetic datasets.Two abnormity models were used to verify the feasibility and effectiveness of the proposed method,the results show that the proposed DE-BP algorithm has better performance than BP,conventional DE-BP and other chaotic DE-BP methods in stability and accuracy,and higher imaging quality than least square inversion.展开更多
针对未知的污染场地,为了准确估计污染物运移模型的参数,提出一种基于多重数据同化集合平滑器(ensemble smoother with multiple data assimilation,ES-MDA)算法的地下水模型参数反演方法,通过融合由高密度电阻率(electrical resistance...针对未知的污染场地,为了准确估计污染物运移模型的参数,提出一种基于多重数据同化集合平滑器(ensemble smoother with multiple data assimilation,ES-MDA)算法的地下水模型参数反演方法,通过融合由高密度电阻率(electrical resistance tomography,ERT)法采集的ERT观测数据,实现对污染源源强和渗透系数场的联合反演。以此为基础设计3组数值算例,比较不同类型观测数据对反演精度的影响。研究结果表明:融合ERT数据的ES-MDA算法对模型参数的反演精度更高,并且将ERT数据和传统的质量浓度与水头观测数据相结合,能进一步优化反演结果。展开更多
基金Projects(51405381,51674188)supported by the National Natural Science Foundation of China
文摘The all traditional electrical resistance tomography (ERT) sensors have a static structure, which cannot satisfy the intelligent requirements for adaptive optimization to ERT sensors that is subject to flow pattern changes during the real-time detection of two-phase flow. In view of this problem, an adaptive ERT sensor with a dynamic structure is proposed. The electrodes of the ERT sensor are arranged in an array structure, the flow pattern recognition technique is introduced into the ERT sensor design and accordingly an ERT flow pattern recognition method based on signal sparsity is proposed. This method uses the sparse representation of the signal to express the sampling voltage of the ERT system as a sparse combination and find its sparse solution to achieve the classification of different flow patterns. With the introduction of flow identification information, the sensor has an intelligent function of adaptively and dynamically adapting the sensor structure according to the real-time flow pattern change. The experimental results show that the sensor can automatically identify four typical flow patterns: core flow, bubble flow, laminar flow and circulation flow with recognition rates of 91%, 93%, 90% and 88% respectively. For different flow patterns, the dynamically optimized sensor can significantly improve the quality of ERT image reconstruction.
基金Project(20120162110015)supported by the Research Fund for the Doctoral Program of Higher Education,ChinaProject(41004053)supported by the National Natural Science Foundation of ChinaProject(12c0241)supported by Scientific Research Fund of Hunan Provincial Education Department,China
文摘Nonlinear resistivity inversion requires efficient artificial neural network(ANN)model for better inversion results.An evolutionary BP neural network(BPNN)approach based on differential evolution(DE)algorithm was presented,which was able to improve global search ability for resistivity tomography 2-D nonlinear inversion.In the proposed method,Tent equation was applied to obtain automatic parameter settings in DE and the restricted parameter Fcrit was used to enhance the ability of converging to global optimum.An implementation of proposed DE-BPNN was given,the network had one hidden layer with 52 nodes and it was trained on 36 datasets and tested on another 4 synthetic datasets.Two abnormity models were used to verify the feasibility and effectiveness of the proposed method,the results show that the proposed DE-BP algorithm has better performance than BP,conventional DE-BP and other chaotic DE-BP methods in stability and accuracy,and higher imaging quality than least square inversion.
基金国家自然科学基金(the National Natural Science Foundation of Chinaunder Grant No.60572153)黑龙江省自然科学基金(the Natural Science Foundation of Helongjiang Province of Chinaunder Grant No.F200609)+2 种基金国家教育部重点科技项目(No.204043)黑龙江省重点科技攻关项目(No.GC05A510)哈尔滨市重点科技攻关项目(No.2005AA1CG035)。
文摘针对未知的污染场地,为了准确估计污染物运移模型的参数,提出一种基于多重数据同化集合平滑器(ensemble smoother with multiple data assimilation,ES-MDA)算法的地下水模型参数反演方法,通过融合由高密度电阻率(electrical resistance tomography,ERT)法采集的ERT观测数据,实现对污染源源强和渗透系数场的联合反演。以此为基础设计3组数值算例,比较不同类型观测数据对反演精度的影响。研究结果表明:融合ERT数据的ES-MDA算法对模型参数的反演精度更高,并且将ERT数据和传统的质量浓度与水头观测数据相结合,能进一步优化反演结果。
