The perfectly matched layer （PML） is a highly efficient absorbing boundary condition used for the numerical modeling of seismic wave equation. The article focuses on the application of this technique to finite-eleme...The perfectly matched layer （PML） is a highly efficient absorbing boundary condition used for the numerical modeling of seismic wave equation. The article focuses on the application of this technique to finite-element time-domain numerical modeling of elastic wave equation. However, the finite-element time-domain scheme is based on the second- order wave equation in displacement formulation. Thus, the first-order PML in velocity-stress formulation cannot be directly applied to this scheme. In this article, we derive the finite- element matrix equations of second-order PML in displacement formulation, and accomplish the implementation of PML in finite-element time-domain modeling of elastic wave equation. The PML has an approximate zero reflection coefficients for bulk and surface waves in the finite-element modeling of P-SV and SH wave propagation in the 2D homogeneous elastic media. The numerical experiments using a two-layer model with irregular topography validate the efficiency of PML in the modeling of seismic wave propagation in geological models with complex structures and heterogeneous media.展开更多
The mechanism of zirconium poisoning on the grain-refining efficiency of an Al-Ti-B based grain refiner was studied. The experiment was conducted by melting Al-5Ti-1B and Al-3Zr master alloys together. The edge-to-edg...The mechanism of zirconium poisoning on the grain-refining efficiency of an Al-Ti-B based grain refiner was studied. The experiment was conducted by melting Al-5Ti-1B and Al-3Zr master alloys together. The edge-to-edge matching model was used to investigate and compare the orientation relationships between the binary intermetallic compounds present in the Al-Ti-B-Zr system. The results show that the poisoning effect probably results from the combination of Al3 Zr with Al3 Ti and the decreased amount of Ti solute, for Al3 Ti particles have good crystallographic relationships with Al3 Zr. Totally six orientation relationships may present between them, while they play vital roles in grain refinement. TiB2 particles appear to remain unchanged because of a bit large misfit. Only one orientation relationship may present between them to prevent Al3 Zr phase from forming on the surface of TiB2, though TiB2 is agglomerated. The theoretical calculation agrees well with the experimental results. The edge-to-edge matching model is proved to be a useful tool for discovering the orientation relationships between phases.展开更多
To efficiently and fully utilize aircraft carrier resources,an optimization model is presented to deal with parameter matching between aircraft and carrier in the process of aircraft catapult launch.Based on carrier a...To efficiently and fully utilize aircraft carrier resources,an optimization model is presented to deal with parameter matching between aircraft and carrier in the process of aircraft catapult launch.Based on carrier aircraft longitudinal dynamic equations and theorem of kinetic energy in catapult launch course,the work characteristics of different forces are learned and a theory model of parameter matching is deduced.In view of the uncertainty of the model parameters of the theory model and the low matching accuracy of the approximate model,an optimization model of parameter matching is introduced in line with the structure of theory model and the approximate model and is generated by the proposed immune genetic algorithm.Compared with the original genetic algorithm and immune algorithm,the proposed algorithm has better calculation accuracy and convergence.The calculation results show that the optimization model occupies certain application value of engineering estimation from the comparison with the relevant literature data and has higher precision than the approximate models.The validity of the proposed approach is verified with numerical case study on a carrier based aircraft.展开更多
The system impedance instability,high-order harmonics,and frequency offset are main fault characteristics of wind power system.Moreover,the measurement angle of faulty phase is affected by rotation speed frequency com...The system impedance instability,high-order harmonics,and frequency offset are main fault characteristics of wind power system.Moreover,the measurement angle of faulty phase is affected by rotation speed frequency component,which causes traditional directional protections based on angle comparison between voltage and current to operate incorrectly.In this paper,a time-domain protection for connected to wind power plant based on model matching is proposed,which compares the calculated current and the measured current to identify internal faults and external faults.Under external faults,the calculated current and measured current waveform are quite similar because the protected transmission lines is equivalent to a lumped parameter model and the model itself is not damaged.However,the similarity of calculated current and measured current is quite low,due to destroyed integrity of model under internal faults.Additionally,Hausdorff distance is introduced to obtain the similarity of the calculated current and measured current.Since the proposed protection scheme is applied in time domain,it is independent from current frequency offsets of wind energy system,high-order harmonics,and system impedance variations.Comprehensive case studies are undertaken through Power Systems Computer Aided Design(PSCAD),while simulation results verify the accuracy and efficiency of the proposed approach in fault identification.展开更多
In order to reach a compromise between fast response control and torques matching control in double turboshaft engines,research on nonlinear model predictive control for turboshaft engines based on double engines torq...In order to reach a compromise between fast response control and torques matching control in double turboshaft engines,research on nonlinear model predictive control for turboshaft engines based on double engines torques matching is conducted.Meanwhile,a Nonlinear Model Predictive Control(NMPC)method is proposed,which combines the control index of the power turbine speed with torques matching of double engines creatively.In addition to the control index,the difference of output torques between each engine is also incorporated in the objective function as a penalty term to ensure constant speed control and short torques matching time.Simulation results demonstrate that relative to unilateral torques matching,the settling time of the bidirectional matching method can be reduced by nearly 30.8%.Nevertheless,compared with the bidirectional torques matching method under the cascade PID controller,the NMPC method can decrease the overshoot of the power turbine speed by 65%and reduce the matching time by 15.5%synchronously.Besides fast response control of turboshaft engines,fast torques matching control of double engines is accomplished as well.展开更多
Biomass is a key parameter in fermentation process, directly influencing the performance of the fermentation system as well as the quality and yield of the targeted product. Hybrid soft-sensor modeling is a good metho...Biomass is a key parameter in fermentation process, directly influencing the performance of the fermentation system as well as the quality and yield of the targeted product. Hybrid soft-sensor modeling is a good method for on-line estimation of biomass. Structure of hybrid soft-sensor model is a key to improve the estimating accuracy. In this paper, a forward heuristic breadth-first reasoning approach based on rule match is proposed for constructing structure of hybrid model. First, strategy of forward heuristic reasoning about facts is introduced, which can reason complex hybrid model structure in the event of few known facts. Second, rule match degree is defined to obtain higher esti- mating accuracy. The experiment results of Nosiheptide fermentation process show that the hybrid modeling process can estimate biomass with higher accuracy by adding transcendental knowledge and partial mechanism to the process.展开更多
Background: Binary as well as polytomous logistic models are widely used for estimating odds ratios when the exposure of prime interest assumes unordered multiple levels under matched pairs case-control design. In our...Background: Binary as well as polytomous logistic models are widely used for estimating odds ratios when the exposure of prime interest assumes unordered multiple levels under matched pairs case-control design. In our previous studies, we have shown that the use of a polytomous logistic model for estimating cumulative odds ratios when the outcome (response) variable is ordinal (in addition to being polytomous) under matched pairs case-control design. The cumulative odds ratios were estimated based on separate fitting of the model at each of the cutpoint level as compared to less than equal to that level. In this paper we propose an alternative method of estimating the cumulative odds ratios and reanalyze the Los Angeles Endometrial Cancer data in the context of dose levels of conjugated oestrogen exposure and development of endometrial cancer under the matched pair case-control design. Methods: In the present study, the cumulative logit model is fitted using a single multinomial logit model for the data. For this, the full maximum likelihood estimation procedure is adopted. A test for equality of the cumulative odds ratios across the exposure levels is proposed. Results: The analysis revealed that there is a strong evidence of risk for developing endometrial cancer due to oestrogen exposure above each of the three dose level as compared to less than equal to that level. The estimated values at the three cutpoint levels were found to be 6.17, 3.60 and 5.16 respectively. Conclusions: The odds of developing endometrial cancer are very high for the users of any amount of oestrogen, even if it is the least dose, as compared to the non-users.展开更多
In this paper, the methods developed by?[1] are used to analyze flowback data, which involves modeling flow both before and after the breakthrough of formation fluids. Despite the versatility of these techniques, achi...In this paper, the methods developed by?[1] are used to analyze flowback data, which involves modeling flow both before and after the breakthrough of formation fluids. Despite the versatility of these techniques, achieving an optimal combination of parameters is often difficult with a single deterministic analysis. Because of the uncertainty in key model parameters, this problem is an ideal candidate for uncertainty quantification and advanced assisted history-matching techniques, including Monte Carlo (MC) simulation and genetic algorithms (GAs) amongst others. MC simulation, for example, can be used for both the purpose of assisted history-matching and uncertainty quantification of key fracture parameters. In this work, several techniques are tested including both single-objective (SO) and multi-objective (MO) algorithms for history-matching and uncertainty quantification, using a light tight oil (LTO) field case. The results of this analysis suggest that many different algorithms can be used to achieve similar optimization results, making these viable methods for developing an optimal set of key uncertain fracture parameters. An indication of uncertainty can also be achieved, which assists in understanding the range of parameters which can be used to successfully match the flowback data.展开更多
科学基金在推动我国科学发展中发挥着重要作用。然而,当前基金管理中存在项目成果与立项内容不匹配的现象,亟须建立细粒度的匹配度评估机制,以完善科研项目评价体系。实现项目成果细粒度匹配的首要前提是项目关键要素抽取。已有研究实...科学基金在推动我国科学发展中发挥着重要作用。然而,当前基金管理中存在项目成果与立项内容不匹配的现象,亟须建立细粒度的匹配度评估机制,以完善科研项目评价体系。实现项目成果细粒度匹配的首要前提是项目关键要素抽取。已有研究实现了项目文本的句子级语步分类,但难以捕捉细粒度信息;面向论文的问题方法抽取通常局限于单一研究问题的识别,难以适配包含多子问题的科研项目。基于此,本文聚焦科研项目关键要素抽取任务,首先界定研究背景、研究问题、研究方法、研究目标和研究意义五类项目关键要素;在此基础上,提出一种基于大模型的项目要素自动抽取方法,分别运用零样本学习、单样本学习和微调三种策略,探索大模型在项目要素抽取任务中的适配能力。研究结果表明,微调策略下最优模型ROUGE-L(recall-oriented understudy for gisting evaluation-L)指标达到0.849,验证了微调模型在项目要素抽取任务上的实用性和有效性。本文抽取的项目要素能够直接服务于项目成果细粒度匹配场景,为后续下游任务的开展提供方法支持以及为科研项目管理的智能化提供支撑。展开更多
地图匹配是智能交通系统中的核心技术之一,旨在将GPS轨迹数据映射至城市路网上,消除定位误差并还原实际行驶路径。随着GPS轨迹数据量的爆炸性增长,传统的基于隐马尔可夫模型(HMM)的地图匹配方法因高计算成本和时序依赖性问题,难以满足...地图匹配是智能交通系统中的核心技术之一,旨在将GPS轨迹数据映射至城市路网上,消除定位误差并还原实际行驶路径。随着GPS轨迹数据量的爆炸性增长,传统的基于隐马尔可夫模型(HMM)的地图匹配方法因高计算成本和时序依赖性问题,难以满足实时处理要求。为此,提出了一种基于轨迹微分段模型的快速地图匹配方法(Micro-Segment Fast Matching,MSFM)。该方法基于滑动窗口机制,将轨迹分解为固定长度的微轨迹段,在分布式计算环境中利用向量化计算方法,在兼顾地图匹配准确性的条件下大幅度提升了计算效率。实验结果表明,在给定的分布式集群环境下,MSFM实现了约110000点/秒的地图匹配速度,比基准算法快约7倍,同时保持了95.86%的匹配准确率。MSFM方法通过改进轨迹数据的存储结构,在高效实时处理大规模轨迹数据方面具有显著的性能优势。展开更多
In 3D models retrieval, feature description and retrieval of non-rigid model face more complex problems due to the isometry transformation of itself. We introduce the hierarchical combination matching into the feature...In 3D models retrieval, feature description and retrieval of non-rigid model face more complex problems due to the isometry transformation of itself. We introduce the hierarchical combination matching into the feature comparison, and build a map between the divided regions of two models, and then achieve accurate feature matching based on patch-by-patch, which successfully introduces the spatial information into feature matching. Verified by experiment, the 3D model retrieval method proposed in this paper based on hierarchical combination matching can make sure more accurate feature matching, so as to enhance the precision of retrieval.展开更多
在一些修船企业建立的修船结算系统和电子价格库中,人工匹配结算编码步骤易出错且耗时长,直接影响结算效率。为解决该问题,提出一种基于多特征融合的修船结算编码智能匹配复合模型。采用来自变换器的双向编码器表示(Bidirectional Encod...在一些修船企业建立的修船结算系统和电子价格库中,人工匹配结算编码步骤易出错且耗时长,直接影响结算效率。为解决该问题,提出一种基于多特征融合的修船结算编码智能匹配复合模型。采用来自变换器的双向编码器表示(Bidirectional Encoder Representations from Transformers,BERT)模型将工程内容文本表示为词向量,采用卷积神经网络(Convolutional Neural Network,CNN)模型提取文本的局部特征,采用双向长短期记忆网络结合注意力机制(Bidirectional Long Short-Term Memory with Attention Mechanism,BiLSTM-Attention)模型提取上下文特征,得到对应的结算编码。试验结果表明,所提出的复合模型在整体准确率方面实现显著提升,充分证明该复合模型在处理复杂文本分类任务中的优势。展开更多
This paper represents a template matching using statistical model and parametric template for multi-template. This algorithm consists of two phases: training and matching phases. In the training phase, the statistical...This paper represents a template matching using statistical model and parametric template for multi-template. This algorithm consists of two phases: training and matching phases. In the training phase, the statistical model created by principal component analysis method (PCA) can be used to synthesize multi-template. The advantage of PCA is to reduce the variances of multi-template. In the matching phase, the normalized cross correlation (NCC) is employed to find the candidates in inspection images. The relationship between image block and multi-template is built to use parametric template method. Results show that the proposed method is more efficient than the conventional template matching and parametric template. Furthermore, the proposed method is more robust than conventional template method.展开更多
基金sponsored by the National Natural Science Foundation of China Research(Grant No.41274138)the Science Foundation of China University of Petroleum(Beijing)(No.KYJJ2012-05-02)
文摘The perfectly matched layer （PML） is a highly efficient absorbing boundary condition used for the numerical modeling of seismic wave equation. The article focuses on the application of this technique to finite-element time-domain numerical modeling of elastic wave equation. However, the finite-element time-domain scheme is based on the second- order wave equation in displacement formulation. Thus, the first-order PML in velocity-stress formulation cannot be directly applied to this scheme. In this article, we derive the finite- element matrix equations of second-order PML in displacement formulation, and accomplish the implementation of PML in finite-element time-domain modeling of elastic wave equation. The PML has an approximate zero reflection coefficients for bulk and surface waves in the finite-element modeling of P-SV and SH wave propagation in the 2D homogeneous elastic media. The numerical experiments using a two-layer model with irregular topography validate the efficiency of PML in the modeling of seismic wave propagation in geological models with complex structures and heterogeneous media.
基金Project(2012CB619504) supported by the National Basic Research Program of China
文摘The mechanism of zirconium poisoning on the grain-refining efficiency of an Al-Ti-B based grain refiner was studied. The experiment was conducted by melting Al-5Ti-1B and Al-3Zr master alloys together. The edge-to-edge matching model was used to investigate and compare the orientation relationships between the binary intermetallic compounds present in the Al-Ti-B-Zr system. The results show that the poisoning effect probably results from the combination of Al3 Zr with Al3 Ti and the decreased amount of Ti solute, for Al3 Ti particles have good crystallographic relationships with Al3 Zr. Totally six orientation relationships may present between them, while they play vital roles in grain refinement. TiB2 particles appear to remain unchanged because of a bit large misfit. Only one orientation relationship may present between them to prevent Al3 Zr phase from forming on the surface of TiB2, though TiB2 is agglomerated. The theoretical calculation agrees well with the experimental results. The edge-to-edge matching model is proved to be a useful tool for discovering the orientation relationships between phases.
基金supported by the Excellence Foundation of BUAA for Ph D.and the National Natural Science Foundation of China(No.91641123).
文摘To efficiently and fully utilize aircraft carrier resources,an optimization model is presented to deal with parameter matching between aircraft and carrier in the process of aircraft catapult launch.Based on carrier aircraft longitudinal dynamic equations and theorem of kinetic energy in catapult launch course,the work characteristics of different forces are learned and a theory model of parameter matching is deduced.In view of the uncertainty of the model parameters of the theory model and the low matching accuracy of the approximate model,an optimization model of parameter matching is introduced in line with the structure of theory model and the approximate model and is generated by the proposed immune genetic algorithm.Compared with the original genetic algorithm and immune algorithm,the proposed algorithm has better calculation accuracy and convergence.The calculation results show that the optimization model occupies certain application value of engineering estimation from the comparison with the relevant literature data and has higher precision than the approximate models.The validity of the proposed approach is verified with numerical case study on a carrier based aircraft.
基金This paper is supported in part by the National Natural Science Foundations of China under Grant Nos.51977102 and 51807084.
文摘The system impedance instability,high-order harmonics,and frequency offset are main fault characteristics of wind power system.Moreover,the measurement angle of faulty phase is affected by rotation speed frequency component,which causes traditional directional protections based on angle comparison between voltage and current to operate incorrectly.In this paper,a time-domain protection for connected to wind power plant based on model matching is proposed,which compares the calculated current and the measured current to identify internal faults and external faults.Under external faults,the calculated current and measured current waveform are quite similar because the protected transmission lines is equivalent to a lumped parameter model and the model itself is not damaged.However,the similarity of calculated current and measured current is quite low,due to destroyed integrity of model under internal faults.Additionally,Hausdorff distance is introduced to obtain the similarity of the calculated current and measured current.Since the proposed protection scheme is applied in time domain,it is independent from current frequency offsets of wind energy system,high-order harmonics,and system impedance variations.Comprehensive case studies are undertaken through Power Systems Computer Aided Design(PSCAD),while simulation results verify the accuracy and efficiency of the proposed approach in fault identification.
基金co-supported by the National Natural Science Foundation of China(No.51576096)Qing Lan and 333 Project and Research Funds for Central Universities(No.NF2018003).
文摘In order to reach a compromise between fast response control and torques matching control in double turboshaft engines,research on nonlinear model predictive control for turboshaft engines based on double engines torques matching is conducted.Meanwhile,a Nonlinear Model Predictive Control(NMPC)method is proposed,which combines the control index of the power turbine speed with torques matching of double engines creatively.In addition to the control index,the difference of output torques between each engine is also incorporated in the objective function as a penalty term to ensure constant speed control and short torques matching time.Simulation results demonstrate that relative to unilateral torques matching,the settling time of the bidirectional matching method can be reduced by nearly 30.8%.Nevertheless,compared with the bidirectional torques matching method under the cascade PID controller,the NMPC method can decrease the overshoot of the power turbine speed by 65%and reduce the matching time by 15.5%synchronously.Besides fast response control of turboshaft engines,fast torques matching control of double engines is accomplished as well.
基金Supported by the National Natural Science Foundation of China (20476007)
文摘Biomass is a key parameter in fermentation process, directly influencing the performance of the fermentation system as well as the quality and yield of the targeted product. Hybrid soft-sensor modeling is a good method for on-line estimation of biomass. Structure of hybrid soft-sensor model is a key to improve the estimating accuracy. In this paper, a forward heuristic breadth-first reasoning approach based on rule match is proposed for constructing structure of hybrid model. First, strategy of forward heuristic reasoning about facts is introduced, which can reason complex hybrid model structure in the event of few known facts. Second, rule match degree is defined to obtain higher esti- mating accuracy. The experiment results of Nosiheptide fermentation process show that the hybrid modeling process can estimate biomass with higher accuracy by adding transcendental knowledge and partial mechanism to the process.
文摘Background: Binary as well as polytomous logistic models are widely used for estimating odds ratios when the exposure of prime interest assumes unordered multiple levels under matched pairs case-control design. In our previous studies, we have shown that the use of a polytomous logistic model for estimating cumulative odds ratios when the outcome (response) variable is ordinal (in addition to being polytomous) under matched pairs case-control design. The cumulative odds ratios were estimated based on separate fitting of the model at each of the cutpoint level as compared to less than equal to that level. In this paper we propose an alternative method of estimating the cumulative odds ratios and reanalyze the Los Angeles Endometrial Cancer data in the context of dose levels of conjugated oestrogen exposure and development of endometrial cancer under the matched pair case-control design. Methods: In the present study, the cumulative logit model is fitted using a single multinomial logit model for the data. For this, the full maximum likelihood estimation procedure is adopted. A test for equality of the cumulative odds ratios across the exposure levels is proposed. Results: The analysis revealed that there is a strong evidence of risk for developing endometrial cancer due to oestrogen exposure above each of the three dose level as compared to less than equal to that level. The estimated values at the three cutpoint levels were found to be 6.17, 3.60 and 5.16 respectively. Conclusions: The odds of developing endometrial cancer are very high for the users of any amount of oestrogen, even if it is the least dose, as compared to the non-users.
文摘In this paper, the methods developed by?[1] are used to analyze flowback data, which involves modeling flow both before and after the breakthrough of formation fluids. Despite the versatility of these techniques, achieving an optimal combination of parameters is often difficult with a single deterministic analysis. Because of the uncertainty in key model parameters, this problem is an ideal candidate for uncertainty quantification and advanced assisted history-matching techniques, including Monte Carlo (MC) simulation and genetic algorithms (GAs) amongst others. MC simulation, for example, can be used for both the purpose of assisted history-matching and uncertainty quantification of key fracture parameters. In this work, several techniques are tested including both single-objective (SO) and multi-objective (MO) algorithms for history-matching and uncertainty quantification, using a light tight oil (LTO) field case. The results of this analysis suggest that many different algorithms can be used to achieve similar optimization results, making these viable methods for developing an optimal set of key uncertain fracture parameters. An indication of uncertainty can also be achieved, which assists in understanding the range of parameters which can be used to successfully match the flowback data.
文摘科学基金在推动我国科学发展中发挥着重要作用。然而,当前基金管理中存在项目成果与立项内容不匹配的现象,亟须建立细粒度的匹配度评估机制,以完善科研项目评价体系。实现项目成果细粒度匹配的首要前提是项目关键要素抽取。已有研究实现了项目文本的句子级语步分类,但难以捕捉细粒度信息;面向论文的问题方法抽取通常局限于单一研究问题的识别,难以适配包含多子问题的科研项目。基于此,本文聚焦科研项目关键要素抽取任务,首先界定研究背景、研究问题、研究方法、研究目标和研究意义五类项目关键要素;在此基础上,提出一种基于大模型的项目要素自动抽取方法,分别运用零样本学习、单样本学习和微调三种策略,探索大模型在项目要素抽取任务中的适配能力。研究结果表明,微调策略下最优模型ROUGE-L(recall-oriented understudy for gisting evaluation-L)指标达到0.849,验证了微调模型在项目要素抽取任务上的实用性和有效性。本文抽取的项目要素能够直接服务于项目成果细粒度匹配场景,为后续下游任务的开展提供方法支持以及为科研项目管理的智能化提供支撑。
文摘地图匹配是智能交通系统中的核心技术之一,旨在将GPS轨迹数据映射至城市路网上,消除定位误差并还原实际行驶路径。随着GPS轨迹数据量的爆炸性增长,传统的基于隐马尔可夫模型(HMM)的地图匹配方法因高计算成本和时序依赖性问题,难以满足实时处理要求。为此,提出了一种基于轨迹微分段模型的快速地图匹配方法(Micro-Segment Fast Matching,MSFM)。该方法基于滑动窗口机制,将轨迹分解为固定长度的微轨迹段,在分布式计算环境中利用向量化计算方法,在兼顾地图匹配准确性的条件下大幅度提升了计算效率。实验结果表明,在给定的分布式集群环境下,MSFM实现了约110000点/秒的地图匹配速度,比基准算法快约7倍,同时保持了95.86%的匹配准确率。MSFM方法通过改进轨迹数据的存储结构,在高效实时处理大规模轨迹数据方面具有显著的性能优势。
基金Supported by National Nature Science Foundation of China(61379106,61379082,61227802)Shandong Provincial Natural Science Foundation(ZR2013FM036,ZR2015FM011,ZR2015FM022)
文摘In 3D models retrieval, feature description and retrieval of non-rigid model face more complex problems due to the isometry transformation of itself. We introduce the hierarchical combination matching into the feature comparison, and build a map between the divided regions of two models, and then achieve accurate feature matching based on patch-by-patch, which successfully introduces the spatial information into feature matching. Verified by experiment, the 3D model retrieval method proposed in this paper based on hierarchical combination matching can make sure more accurate feature matching, so as to enhance the precision of retrieval.
文摘在一些修船企业建立的修船结算系统和电子价格库中,人工匹配结算编码步骤易出错且耗时长,直接影响结算效率。为解决该问题,提出一种基于多特征融合的修船结算编码智能匹配复合模型。采用来自变换器的双向编码器表示(Bidirectional Encoder Representations from Transformers,BERT)模型将工程内容文本表示为词向量,采用卷积神经网络(Convolutional Neural Network,CNN)模型提取文本的局部特征,采用双向长短期记忆网络结合注意力机制(Bidirectional Long Short-Term Memory with Attention Mechanism,BiLSTM-Attention)模型提取上下文特征,得到对应的结算编码。试验结果表明,所提出的复合模型在整体准确率方面实现显著提升,充分证明该复合模型在处理复杂文本分类任务中的优势。
文摘This paper represents a template matching using statistical model and parametric template for multi-template. This algorithm consists of two phases: training and matching phases. In the training phase, the statistical model created by principal component analysis method (PCA) can be used to synthesize multi-template. The advantage of PCA is to reduce the variances of multi-template. In the matching phase, the normalized cross correlation (NCC) is employed to find the candidates in inspection images. The relationship between image block and multi-template is built to use parametric template method. Results show that the proposed method is more efficient than the conventional template matching and parametric template. Furthermore, the proposed method is more robust than conventional template method.
