Accurate capacity estimation is of great importance for the reliable state monitoring,timely maintenance,and second-life utilization of lithium-ion batteries.Despite numerous works on battery capacity estimation using...Accurate capacity estimation is of great importance for the reliable state monitoring,timely maintenance,and second-life utilization of lithium-ion batteries.Despite numerous works on battery capacity estimation using laboratory datasets,most of them are applied to battery cells and lack satisfactory fidelity when extended to real-world electric vehicle(EV)battery packs.The challenges intensify for large-sized EV battery packs,where unpredictable operating profiles and low-quality data acquisition hinder precise capacity estimation.To fill the gap,this study introduces a novel data-driven battery pack capacity estimation method grounded in field data.The proposed approach begins by determining labeled capacity through an innovative combination of the inverse ampere-hour integral,open circuit voltage-based,and resistance-based correction methods.Then,multiple health features are extracted from incremental capacity curves,voltage curves,equivalent circuit model parameters,and operating temperature to thoroughly characterize battery aging behavior.A feature selection procedure is performed to determine the optimal feature set based on the Pearson correlation coefficient.Moreover,a convolutional neural network and bidirectional gated recurrent unit,enhanced by an attention mechanism,are employed to estimate the battery pack capacity in real-world EV applications.Finally,the proposed method is validated with a field dataset from two EVs,covering approximately 35,000 kilometers.The results demonstrate that the proposed method exhibits better estimation performance with an error of less than 1.1%compared to existing methods.This work shows great potential for accurate large-sized EV battery pack capacity estimation based on field data,which provides significant insights into reliable labeled capacity calculation,effective features extraction,and machine learning-enabled health diagnosis.展开更多
In this paper the application of image enhancement techniques to potential field data is briefly described and two improved enhancement methods are introduced. One method is derived from the histogram equalization tec...In this paper the application of image enhancement techniques to potential field data is briefly described and two improved enhancement methods are introduced. One method is derived from the histogram equalization technique and automatically determines the color spectra of geophysical maps. Colors can be properly distributed and visual effects and resolution can be enhanced by the method. The other method is based on the modified Radon transform and gradient calculation and is used to detect and enhance linear features in gravity and magnetic images. The method facilites the detection of line segments in the transform domain. Tests with synthetic images and real data show the methods to be effective in feature enhancement.展开更多
Edge detection and enhancement techniques are commonly used in recognizing the edge of geologic bodies using potential field data. We present a new edge recognition technology based on the normalized vertical derivati...Edge detection and enhancement techniques are commonly used in recognizing the edge of geologic bodies using potential field data. We present a new edge recognition technology based on the normalized vertical derivative of the total horizontal derivative which has the functions of both edge detection and enhancement techniques. First, we calculate the total horizontal derivative （THDR） of the potential-field data and then compute the n-order vertical derivative （VDRn） of the THDR. For the n-order vertical derivative, the peak value of total horizontal derivative （PTHDR） is obtained using a threshold value greater than 0. This PTHDR can be used for edge detection. Second, the PTHDR value is divided by the total horizontal derivative and normalized by the maximum value. Finally, we used different kinds of numerical models to verify the effectiveness and reliability of the new edge recognition technology.展开更多
The present study aims to improve the efficiency of typical procedures used for post-processing flow field data by applying a neural-network technology.Assuming a problem of aircraft design as the workhorse,a regressi...The present study aims to improve the efficiency of typical procedures used for post-processing flow field data by applying a neural-network technology.Assuming a problem of aircraft design as the workhorse,a regression calculation model for processing the flow data of a FCN-VGG19 aircraft is elaborated based on VGGNet(Visual Geometry Group Net)and FCN(Fully Convolutional Network)techniques.As shown by the results,the model displays a strong fitting ability,and there is almost no over-fitting in training.Moreover,the model has good accuracy and convergence.For different input data and different grids,the model basically achieves convergence,showing good performances.It is shown that the proposed simulation regression model based on FCN has great potential in typical problems of computational fluid dynamics(CFD)and related data processing.展开更多
Predominantly the localization accuracy of the magnetic field-based localization approaches is severed by two limiting factors:Smartphone heterogeneity and smaller data lengths.The use of multifarioussmartphones cripp...Predominantly the localization accuracy of the magnetic field-based localization approaches is severed by two limiting factors:Smartphone heterogeneity and smaller data lengths.The use of multifarioussmartphones cripples the performance of such approaches owing to the variability of the magnetic field data.In the same vein,smaller lengths of magnetic field data decrease the localization accuracy substantially.The current study proposes the use of multiple neural networks like deep neural network(DNN),long short term memory network(LSTM),and gated recurrent unit network(GRN)to perform indoor localization based on the embedded magnetic sensor of the smartphone.A voting scheme is introduced that takes predictions from neural networks into consideration to estimate the current location of the user.Contrary to conventional magnetic field-based localization approaches that rely on the magnetic field data intensity,this study utilizes the normalized magnetic field data for this purpose.Training of neural networks is carried out using Galaxy S8 data while the testing is performed with three devices,i.e.,LG G7,Galaxy S8,and LG Q6.Experiments are performed during different times of the day to analyze the impact of time variability.Results indicate that the proposed approach minimizes the impact of smartphone variability and elevates the localization accuracy.Performance comparison with three approaches reveals that the proposed approach outperforms them in mean,50%,and 75%error even using a lesser amount of magnetic field data than those of other approaches.展开更多
The monopile is the most common foundation to support offshore wind turbines.In the marine environment,local scour due to combined currents and waves is a significant issue that must be considered in the design of win...The monopile is the most common foundation to support offshore wind turbines.In the marine environment,local scour due to combined currents and waves is a significant issue that must be considered in the design of wind turbine foundations.In this paper,a full-scale numerical model was developed and validated based on field data from Rudong,China.The scour development around monopiles was investigated,and the effects of waves and the Reynolds number Re were analyzed.Several formulas for predicting the scour depth in the literature have been evaluated.It is found that waves can accelerate scour development even if the KC number is small(0.78<KC<1.57).The formula obtained from small-scale model tests may be unsafe or wasteful when it is applied in practical design due to the scale effect.A new equation for predicting the scour depth based on the average pile Reynolds number(Rea)is proposed and validated with field data.The equilibrium scour depth predicted using the proposed equation is evaluated and compared with those from nine equations in the literature.It is demonstrated that the values predicted from the proposed equation and from the S/M(Sheppard/Melville)equation are closer to the field data.展开更多
The genetic algorithm is useful for solving an inversion of complex nonlinear geophysical equations. The multi-point search of the genetic algorithm makes it easier to find a globally optimal solution and avoid fall...The genetic algorithm is useful for solving an inversion of complex nonlinear geophysical equations. The multi-point search of the genetic algorithm makes it easier to find a globally optimal solution and avoid falling into a local extremum. The search efficiency of the genetic algorithm is a key to producing successful solutions in a huge multi-parameter model space. The encoding mechanism of the genetic algorithm affects the searching processes in the evolution. Not all genetic operations perform perfectly in a search under either a binary or decimal encoding system. As such, a standard genetic algorithm (SGA) is sometimes unable to resolve an optimization problem such as a simple geophysical inversion. With the binary encoding system the operation of the crossover may produce more new individuals. The decimal encoding system, on the other hand, makes the mutation generate more new genes. This paper discusses approaches of exploiting the search potentials of genetic operations with different encoding systems and presents a hybrid-encoding mechanism for the genetic algorithm. This is referred to as the hybrid-encoding genetic algorithm (HEGA). The method is based on the routine in which the mutation operation is executed in decimal code and other operations in binary code. HEGA guarantees the birth of better genes by mutation processing with a high probability, so that it is beneficial for resolving the inversions of complicated problems. Synthetic and real-world examples demonstrate the advantages of using HEGA in the inversion of potential-field data.展开更多
The anisotropic properties of subsurface media cause waveform distortions in seismic wave propagation,resulting in a negative infl uence on seismic imaging.In addition,wavefields simulated by the conventional coupled ...The anisotropic properties of subsurface media cause waveform distortions in seismic wave propagation,resulting in a negative infl uence on seismic imaging.In addition,wavefields simulated by the conventional coupled pseudo-acoustic equation are not only aff ected by SV-wave artifacts but are also limited by anisotropic parameters.We propose a least-squares reverse time migration(LSRTM)method based on the pure q P-wave equation in vertically transverse isotropic media.A fi nite diff erence and fast Fourier transform method,which can improve the effi ciency of the numerical simulation compared to a pseudo-spectral method,is used to solve the pure q P-wave equation.We derive the corresponding demigration operator,migration operator,and gradient updating formula to implement the LSRTM.Numerical tests on the Hess model and field data confirm that the proposed method has a good correction eff ect for the travel time deviation caused by underground anisotropic media.Further,it signifi cantly suppresses the migration noise,balances the imaging amplitude,and improves the imaging resolution.展开更多
Recently, use of mobile communicational devices in field data collection is increasing such as smart phones and cellular phones due to emergence of embedded Global Position System GPS and Wi-Fi Internet access. Accura...Recently, use of mobile communicational devices in field data collection is increasing such as smart phones and cellular phones due to emergence of embedded Global Position System GPS and Wi-Fi Internet access. Accurate timely and handy field data collection is required for disaster management and emergency quick responses. In this article, we introduce web-based GIS system to collect the field data by personal mobile phone through Post Office Protocol POP3 mail server. The main objective of this work is to demonstrate real-time field data collection method to the students using their mobile phone to collect field data by timely and handy manners, either individual or group survey in local or global scale research.展开更多
Gas-insulated switchgear(GIS)plays a critical role in ensuring the reliability of power systems,but partial discharge(PD)is a primary cause of failures within GIS equipment.Traditional PD diagnostic methods rely heavi...Gas-insulated switchgear(GIS)plays a critical role in ensuring the reliability of power systems,but partial discharge(PD)is a primary cause of failures within GIS equipment.Traditional PD diagnostic methods rely heavily on laboratory data,which differ signifi-cantly from that under the complex conditions of field data,leading to a marked drop in recognition accuracy when they are applied to field PD diagnosis.This study addresses the challenge by integrating field data into the training process,utilising a deep transfer learning approach that combines laboratory and field data to improve diagnostic accuracy for GIS PD.The research collected PD data from laboratory models representing five defect types and field data gathered from operational GIS equipment.A deep residual network(ResNet50)was pretrained using laboratory data and fine-tuned with field data through deep transfer learning to optimise the recognition of PD in field conditions.The results show that the proposed model achieves a significantly higher recognition accuracy(93.7%)for field data compared to traditional methods(60%-70%).The integration of deep transfer learning ensures that both low-dimensional general features from labora-tory data and high-dimensional specific features from field data are effectively utilised.This research significantly contributes to improving the diagnostic accuracy of PD in GIS under field conditions,providing a robust method for defect detection in operational equipment.展开更多
Edge detection is a commonly requested task in the interpretation of potential field data. Different methods have different results for varied depths and shapes of geological bodies. In this paper,we propose using the...Edge detection is a commonly requested task in the interpretation of potential field data. Different methods have different results for varied depths and shapes of geological bodies. In this paper,we propose using the combination of structure tensor and tilt angle to detect the edges of the sources,which can display the edges of shallow and deep bodies simultaneously. Through tests on synthetic potential field data,it is obvious that the proposed edge detection methods can display the sources edges more clearly and precisely,compared with other commonly used methods. The application on real potential field data shows similar result,obtaining the edges of layers and faults clearly. In addition,another advantage of the new method is its insensitivity to noise.展开更多
Edge location is an important information of the source,and can be obtained by the potential field data. Most edge detection methods of potential field data are the functions of horizontal and vertical derivatives.The...Edge location is an important information of the source,and can be obtained by the potential field data. Most edge detection methods of potential field data are the functions of horizontal and vertical derivatives.The authors provide a new strategy to establish edge detection filters that can improve the resolution to identify small bodies,which use the ratio functions of different-order derivatives to recognize the edges of the sources.The new filter is named as advanced derivative ratio( ADR) filter and balanced outputs can be produced for different forms of ADR filters. The ADR filters are tested on synthetic data and real potential field data. The advantage of the ADR filters is that they can detect the edges of the causative sources more precisely and clearly,and the model testing results show that the resolution of ADR filters is higher than other existing filters. The ADR filters were applied to real data,with more subtle details obtained.展开更多
The problems of the present management information system are introduced. A solution based on field-bus is proposed to overcome the problem. A issue how the old instruments is applied to the new system is discussed, a...The problems of the present management information system are introduced. A solution based on field-bus is proposed to overcome the problem. A issue how the old instruments is applied to the new system is discussed, and a rebuild method of the old instruments with LED or LCD to fit the solution is provided.展开更多
This study aims to improve knowledge of the structure of southwest Cameroon based on the analysis and interpretation of gravity data derived from the SGG-UGM-2 model. A residual anomaly map was first calculated from t...This study aims to improve knowledge of the structure of southwest Cameroon based on the analysis and interpretation of gravity data derived from the SGG-UGM-2 model. A residual anomaly map was first calculated from the Bouguer anomaly map, which is strongly affected by a regional gradient. The residual anomaly map generated provides information on the variation in subsurface density, but does not provide sufficient information, hence the interest in using filtering with the aim of highlighting the structures affecting the area of south-west Cameroon. Three interpretation methods were used: vertical gradient, horizontal gradient coupled with upward continuation and Euler deconvolution. The application of these treatments enabled us to map a large number of gravimetric lineaments materializing density discontinuities. These lineaments are organized along main preferential directions: NW-SE, NNE-SSW, ENE-WSW and secondary directions: NNW-SSE, NE-SW, NS and E-W. Euler solutions indicate depths of up to 7337 m. Thanks to the results of this research, significant information has been acquired, contributing to a deeper understanding of the structural composition of the study area. The resulting structural map vividly illustrates the major tectonic events that shaped the geological framework of the study area. It also serves as a guide for prospecting subsurface resources (water and hydrocarbons). .展开更多
The cross-sectional width of highways is a major factor that affects the construction cost of engineering projects.With the increasing demand for intensive highway construction,research on dedicated lanes or roadway f...The cross-sectional width of highways is a major factor that affects the construction cost of engineering projects.With the increasing demand for intensive highway construction,research on dedicated lanes or roadway for cars has attracted research attention.The lateral oscillation value of vehicle’s trajectory is the direct factor that affects the lane width;however,relevant research is relatively limited,and the characteristics are not yet clear.Therefore,this study utilized an integrated radar shorter video system(IRVS)to collect real high-precision trajectory data,obtaining 24697 datasets.Statistical methods were used to reveal the lateral oscillation value and determine the effective lane width of cars for safe driving.The research results are as follows.1.The lateral oscillation value of cars varies across different lanes.Vehicles on the inner two lanes tend to drift leftward,whereas those on the outermost lane tend to drift rightward.2.When the operating speed ranges from 80 km/h to 110 km/h,the lateral oscillation value presents a statistical rule,which obeys a normal distribution for the left and right margins,i.e.,D_(left)~N(0.87,0.15)and Dright~N(0.72,0.15).This lateral oscillation value is insensitive to fluctuations in the operating speed(80 km/h~110 km/h)from the standpoint of field data.3.The fitted expressions of effective lane width for cars were proposed,and the effective lane width at the 95th,90th,and 85th percentile is 3.2 m,3.0 m,and 2.8 m,respectively.These results can provide technical support for dedicated lane width for cars,and have practical significance for the intensive construction of road infrastructure in highly urbanized areas.展开更多
In order to effectively conduct emotion recognition from spontaneous, non-prototypical and unsegmented speech so as to create a more natural human-machine interaction; a novel speech emotion recognition algorithm base...In order to effectively conduct emotion recognition from spontaneous, non-prototypical and unsegmented speech so as to create a more natural human-machine interaction; a novel speech emotion recognition algorithm based on the combination of the emotional data field （EDF） and the ant colony search （ACS） strategy, called the EDF-ACS algorithm, is proposed. More specifically, the inter- relationship among the turn-based acoustic feature vectors of different labels are established by using the potential function in the EDF. To perform the spontaneous speech emotion recognition, the artificial colony is used to mimic the turn- based acoustic feature vectors. Then, the canonical ACS strategy is used to investigate the movement direction of each artificial ant in the EDF, which is regarded as the emotional label of the corresponding turn-based acoustic feature vector. The proposed EDF-ACS algorithm is evaluated on the continueous audio）＇visual emotion challenge （AVEC） 2012 dataset, which contains the spontaneous, non-prototypical and unsegmented speech emotion data. The experimental results show that the proposed EDF-ACS algorithm outperforms the existing state-of-the-art algorithm in turn-based speech emotion recognition.展开更多
The quantification of the sheltering and exposure effects of non-uniform sediments has been widely achieved through hiding function models. Big challenge exists so far in the model parameter that is highly variable an...The quantification of the sheltering and exposure effects of non-uniform sediments has been widely achieved through hiding function models. Big challenge exists so far in the model parameter that is highly variable and differs greatly between laboratory flumes and field streams. This paper presents an improved surface-based hiding fimction. The force balance for particle inception was formulated and the allocation of the overall bed shear stress into each group of sediments was mimicked. The new hiding function was examined against and agrees well with the documented field and flume data. It was shown that the hiding fimction is closely related to the relative flow depth and the reference elevation in the velocity profile in addition to the bed material gradation. The power law of velocity profile that applies to both flume flows and natural streams can link the flume and field data together. The hiding function with b = 1/6 and b = 1/2 is applicable to natural streams and laboratory flumes, respectively. The value orb = 0.263 also works well for gravel bed rivers. The range of the reference elevation, namely z0 = 0.4Dm-1.4Dm, is recommended for either the flume or field data. The new hiding function contributes to addressing clearer physical meanings and a useful perspective for further improvement.展开更多
Enterprise applications utilize relational databases and structured business processes, requiring slow and expensive conversion of inputs and outputs, from business documents such as invoices, purchase orders, and rec...Enterprise applications utilize relational databases and structured business processes, requiring slow and expensive conversion of inputs and outputs, from business documents such as invoices, purchase orders, and receipts, into known templates and schemas before processing. We propose a new LLM Agent-based intelligent data extraction, transformation, and load (IntelligentETL) pipeline that not only ingests PDFs and detects inputs within it but also addresses the extraction of structured and unstructured data by developing tools that most efficiently and securely deal with respective data types. We study the efficiency of our proposed pipeline and compare it with enterprise solutions that also utilize LLMs. We establish the supremacy in timely and accurate data extraction and transformation capabilities of our approach for analyzing the data from varied sources based on nested and/or interlinked input constraints.展开更多
This paper emphasizes the importance of making field measurements for effective and realistic dependability evaluations.Two examples are given,both based on real data from IBM mainframes.The first evaluates the impact...This paper emphasizes the importance of making field measurements for effective and realistic dependability evaluations.Two examples are given,both based on real data from IBM mainframes.The first evaluates the impact of the operating environment on system failure characteristics and the second shows how an accurate model depicting this interaction can be extracted from real data.展开更多
Rice paddy mapping with optical remote sensing is challenging in Bangladesh due to the heterogeneous cropping pattern, fragmented field size and cloud </span><span style="font-family:Verdana;">co...Rice paddy mapping with optical remote sensing is challenging in Bangladesh due to the heterogeneous cropping pattern, fragmented field size and cloud </span><span style="font-family:Verdana;">cover during the growing period. The high-resolution Synthetic Aperture</span><span style="font-family:Verdana;"> Radar (SAR) sensor is the potential alternate to mapping rice area in Bangla</span><span style="font-family:Verdana;">desh. The L-band SAR sensor onboard Advanced Land Observing Satellit</span><span style="font-family:Verdana;">e (</span><span style="font-family:Verdana;">ALOS) acquires multi-polarization and multi-temporal images are </span><span style="font-family:Verdana;">a very useful tool for rice area mapping. In this study, we used ALOS-2 ScanSAR dual (HH</span></span><span style="font-family:""> </span><span style="font-family:Verdana;">+</span><span style="font-family:""> </span><span style="font-family:Verdana;">HV) polarized time series data in the study area. We used orthorectification and slope corrected backscatter (sigma-naught) images and median filtering (3 × 3) window for image processing. The unsupervised classification with the k-means++ algorithm is used for initial clustering (20 categories) of images over the study area. The GPS location of rice paddy field with cropping pattern over study area uses for classifying the different rice-growing season from the k-means clustering data. The result is compared with the moderate resolution imaging spectroradiometer (MODIS) based rice area and national statistical agricultural yearbook statistics. The results show that, based on the MODIS based rice map, the rice fields can be mapped with a conditional Kappa value of 0.68 and at user’s and producer’s accuracies of 86% and 90%, respectively. The large commission error primarily came from confusion between wet season Aus rice and others crop, Aus-Amon and Boro-Aus-Amon cropping pattern because of their similar backscatter amplitudes and temporal similarities in the rice growing season. The relatively high rice mapping accuracy in this study indicates that the ALOS/PALSAR-2 data could provide useful information in rice cropping management in subtropical regions such Bangladesh.展开更多
基金supported in part by the National Key Research and Development Program of China(No.2022YFB3305403)Project of basic research funds for central universities(2022CDJDX006)+1 种基金Talent Plan Project of Chongqing(No.cstc2021ycjhbgzxm0295)National Natural Science Foundation of China(No.52111530194)。
文摘Accurate capacity estimation is of great importance for the reliable state monitoring,timely maintenance,and second-life utilization of lithium-ion batteries.Despite numerous works on battery capacity estimation using laboratory datasets,most of them are applied to battery cells and lack satisfactory fidelity when extended to real-world electric vehicle(EV)battery packs.The challenges intensify for large-sized EV battery packs,where unpredictable operating profiles and low-quality data acquisition hinder precise capacity estimation.To fill the gap,this study introduces a novel data-driven battery pack capacity estimation method grounded in field data.The proposed approach begins by determining labeled capacity through an innovative combination of the inverse ampere-hour integral,open circuit voltage-based,and resistance-based correction methods.Then,multiple health features are extracted from incremental capacity curves,voltage curves,equivalent circuit model parameters,and operating temperature to thoroughly characterize battery aging behavior.A feature selection procedure is performed to determine the optimal feature set based on the Pearson correlation coefficient.Moreover,a convolutional neural network and bidirectional gated recurrent unit,enhanced by an attention mechanism,are employed to estimate the battery pack capacity in real-world EV applications.Finally,the proposed method is validated with a field dataset from two EVs,covering approximately 35,000 kilometers.The results demonstrate that the proposed method exhibits better estimation performance with an error of less than 1.1%compared to existing methods.This work shows great potential for accurate large-sized EV battery pack capacity estimation based on field data,which provides significant insights into reliable labeled capacity calculation,effective features extraction,and machine learning-enabled health diagnosis.
基金This work is supported by the research project (grant No. G20000467) of the Institute of Geology and Geophysics, CAS and bythe China Postdoctoral Science Foundation (No. 2004036083).
文摘In this paper the application of image enhancement techniques to potential field data is briefly described and two improved enhancement methods are introduced. One method is derived from the histogram equalization technique and automatically determines the color spectra of geophysical maps. Colors can be properly distributed and visual effects and resolution can be enhanced by the method. The other method is based on the modified Radon transform and gradient calculation and is used to detect and enhance linear features in gravity and magnetic images. The method facilites the detection of line segments in the transform domain. Tests with synthetic images and real data show the methods to be effective in feature enhancement.
基金supported by the National Science and Technology Major Projects (2008ZX05025)the Project of National Oil and Gas Resources Strategic Constituency Survey and Evaluation of the Ministry of Land and Resources,China (XQ-2007-05)
文摘Edge detection and enhancement techniques are commonly used in recognizing the edge of geologic bodies using potential field data. We present a new edge recognition technology based on the normalized vertical derivative of the total horizontal derivative which has the functions of both edge detection and enhancement techniques. First, we calculate the total horizontal derivative （THDR） of the potential-field data and then compute the n-order vertical derivative （VDRn） of the THDR. For the n-order vertical derivative, the peak value of total horizontal derivative （PTHDR） is obtained using a threshold value greater than 0. This PTHDR can be used for edge detection. Second, the PTHDR value is divided by the total horizontal derivative and normalized by the maximum value. Finally, we used different kinds of numerical models to verify the effectiveness and reliability of the new edge recognition technology.
文摘The present study aims to improve the efficiency of typical procedures used for post-processing flow field data by applying a neural-network technology.Assuming a problem of aircraft design as the workhorse,a regression calculation model for processing the flow data of a FCN-VGG19 aircraft is elaborated based on VGGNet(Visual Geometry Group Net)and FCN(Fully Convolutional Network)techniques.As shown by the results,the model displays a strong fitting ability,and there is almost no over-fitting in training.Moreover,the model has good accuracy and convergence.For different input data and different grids,the model basically achieves convergence,showing good performances.It is shown that the proposed simulation regression model based on FCN has great potential in typical problems of computational fluid dynamics(CFD)and related data processing.
基金supported by the MSIT(Ministry of Science and ICT),Korea,under the ITRC(Information Technology Research Center)support program(IITP-2019-2016-0-00313)supervised by the IITP(Institute for Information&communication Technology Promotion)+1 种基金supported by Basic Science Research Program through the National Research Foundation of Korea(NRF)funded by the Ministry of Science,ICT and Future Planning(2017R1E1A1A01074345).
文摘Predominantly the localization accuracy of the magnetic field-based localization approaches is severed by two limiting factors:Smartphone heterogeneity and smaller data lengths.The use of multifarioussmartphones cripples the performance of such approaches owing to the variability of the magnetic field data.In the same vein,smaller lengths of magnetic field data decrease the localization accuracy substantially.The current study proposes the use of multiple neural networks like deep neural network(DNN),long short term memory network(LSTM),and gated recurrent unit network(GRN)to perform indoor localization based on the embedded magnetic sensor of the smartphone.A voting scheme is introduced that takes predictions from neural networks into consideration to estimate the current location of the user.Contrary to conventional magnetic field-based localization approaches that rely on the magnetic field data intensity,this study utilizes the normalized magnetic field data for this purpose.Training of neural networks is carried out using Galaxy S8 data while the testing is performed with three devices,i.e.,LG G7,Galaxy S8,and LG Q6.Experiments are performed during different times of the day to analyze the impact of time variability.Results indicate that the proposed approach minimizes the impact of smartphone variability and elevates the localization accuracy.Performance comparison with three approaches reveals that the proposed approach outperforms them in mean,50%,and 75%error even using a lesser amount of magnetic field data than those of other approaches.
基金financially supported by the National Natural Science Foundation of China (Grant No.52378329)。
文摘The monopile is the most common foundation to support offshore wind turbines.In the marine environment,local scour due to combined currents and waves is a significant issue that must be considered in the design of wind turbine foundations.In this paper,a full-scale numerical model was developed and validated based on field data from Rudong,China.The scour development around monopiles was investigated,and the effects of waves and the Reynolds number Re were analyzed.Several formulas for predicting the scour depth in the literature have been evaluated.It is found that waves can accelerate scour development even if the KC number is small(0.78<KC<1.57).The formula obtained from small-scale model tests may be unsafe or wasteful when it is applied in practical design due to the scale effect.A new equation for predicting the scour depth based on the average pile Reynolds number(Rea)is proposed and validated with field data.The equilibrium scour depth predicted using the proposed equation is evaluated and compared with those from nine equations in the literature.It is demonstrated that the values predicted from the proposed equation and from the S/M(Sheppard/Melville)equation are closer to the field data.
文摘The genetic algorithm is useful for solving an inversion of complex nonlinear geophysical equations. The multi-point search of the genetic algorithm makes it easier to find a globally optimal solution and avoid falling into a local extremum. The search efficiency of the genetic algorithm is a key to producing successful solutions in a huge multi-parameter model space. The encoding mechanism of the genetic algorithm affects the searching processes in the evolution. Not all genetic operations perform perfectly in a search under either a binary or decimal encoding system. As such, a standard genetic algorithm (SGA) is sometimes unable to resolve an optimization problem such as a simple geophysical inversion. With the binary encoding system the operation of the crossover may produce more new individuals. The decimal encoding system, on the other hand, makes the mutation generate more new genes. This paper discusses approaches of exploiting the search potentials of genetic operations with different encoding systems and presents a hybrid-encoding mechanism for the genetic algorithm. This is referred to as the hybrid-encoding genetic algorithm (HEGA). The method is based on the routine in which the mutation operation is executed in decimal code and other operations in binary code. HEGA guarantees the birth of better genes by mutation processing with a high probability, so that it is beneficial for resolving the inversions of complicated problems. Synthetic and real-world examples demonstrate the advantages of using HEGA in the inversion of potential-field data.
基金financially supported by the National Key R&D Program of China (No. 2019YFC0605503)the Major Scientific and Technological Projects of CNPC (No. ZD2019-183-003)the National Natural Science Foundation of China (No. 41922028,41874149)。
文摘The anisotropic properties of subsurface media cause waveform distortions in seismic wave propagation,resulting in a negative infl uence on seismic imaging.In addition,wavefields simulated by the conventional coupled pseudo-acoustic equation are not only aff ected by SV-wave artifacts but are also limited by anisotropic parameters.We propose a least-squares reverse time migration(LSRTM)method based on the pure q P-wave equation in vertically transverse isotropic media.A fi nite diff erence and fast Fourier transform method,which can improve the effi ciency of the numerical simulation compared to a pseudo-spectral method,is used to solve the pure q P-wave equation.We derive the corresponding demigration operator,migration operator,and gradient updating formula to implement the LSRTM.Numerical tests on the Hess model and field data confirm that the proposed method has a good correction eff ect for the travel time deviation caused by underground anisotropic media.Further,it signifi cantly suppresses the migration noise,balances the imaging amplitude,and improves the imaging resolution.
文摘Recently, use of mobile communicational devices in field data collection is increasing such as smart phones and cellular phones due to emergence of embedded Global Position System GPS and Wi-Fi Internet access. Accurate timely and handy field data collection is required for disaster management and emergency quick responses. In this article, we introduce web-based GIS system to collect the field data by personal mobile phone through Post Office Protocol POP3 mail server. The main objective of this work is to demonstrate real-time field data collection method to the students using their mobile phone to collect field data by timely and handy manners, either individual or group survey in local or global scale research.
基金Key Program of Joint Funds of the National Natural Science Foundation of China,Grant/Award Number:U22B20118。
文摘Gas-insulated switchgear(GIS)plays a critical role in ensuring the reliability of power systems,but partial discharge(PD)is a primary cause of failures within GIS equipment.Traditional PD diagnostic methods rely heavily on laboratory data,which differ signifi-cantly from that under the complex conditions of field data,leading to a marked drop in recognition accuracy when they are applied to field PD diagnosis.This study addresses the challenge by integrating field data into the training process,utilising a deep transfer learning approach that combines laboratory and field data to improve diagnostic accuracy for GIS PD.The research collected PD data from laboratory models representing five defect types and field data gathered from operational GIS equipment.A deep residual network(ResNet50)was pretrained using laboratory data and fine-tuned with field data through deep transfer learning to optimise the recognition of PD in field conditions.The results show that the proposed model achieves a significantly higher recognition accuracy(93.7%)for field data compared to traditional methods(60%-70%).The integration of deep transfer learning ensures that both low-dimensional general features from labora-tory data and high-dimensional specific features from field data are effectively utilised.This research significantly contributes to improving the diagnostic accuracy of PD in GIS under field conditions,providing a robust method for defect detection in operational equipment.
基金Supported by projects of National Key Research and Development Plan(Nos.2017YFC0601606,2017YFC0602203)National Science and Technology Major Project(No.2016ZX05027-002-03)+1 种基金National Natural Science Foundation of China(Nos.41604098,41404089)State Key Program of National Natural Science of China(No.41430322)
文摘Edge detection is a commonly requested task in the interpretation of potential field data. Different methods have different results for varied depths and shapes of geological bodies. In this paper,we propose using the combination of structure tensor and tilt angle to detect the edges of the sources,which can display the edges of shallow and deep bodies simultaneously. Through tests on synthetic potential field data,it is obvious that the proposed edge detection methods can display the sources edges more clearly and precisely,compared with other commonly used methods. The application on real potential field data shows similar result,obtaining the edges of layers and faults clearly. In addition,another advantage of the new method is its insensitivity to noise.
基金Supported by Projects of National Key R&D Program of China(Nos.2017YFC0602203,2017YFC0601606)National Science and Technology Major Project(No.2016ZX05027-002-03)+1 种基金National Natural Science Foundation of China(Nos.41604098,41404089)State Key Program of National Natural Science of China(No.41430322)
文摘Edge location is an important information of the source,and can be obtained by the potential field data. Most edge detection methods of potential field data are the functions of horizontal and vertical derivatives.The authors provide a new strategy to establish edge detection filters that can improve the resolution to identify small bodies,which use the ratio functions of different-order derivatives to recognize the edges of the sources.The new filter is named as advanced derivative ratio( ADR) filter and balanced outputs can be produced for different forms of ADR filters. The ADR filters are tested on synthetic data and real potential field data. The advantage of the ADR filters is that they can detect the edges of the causative sources more precisely and clearly,and the model testing results show that the resolution of ADR filters is higher than other existing filters. The ADR filters were applied to real data,with more subtle details obtained.
文摘The problems of the present management information system are introduced. A solution based on field-bus is proposed to overcome the problem. A issue how the old instruments is applied to the new system is discussed, and a rebuild method of the old instruments with LED or LCD to fit the solution is provided.
文摘This study aims to improve knowledge of the structure of southwest Cameroon based on the analysis and interpretation of gravity data derived from the SGG-UGM-2 model. A residual anomaly map was first calculated from the Bouguer anomaly map, which is strongly affected by a regional gradient. The residual anomaly map generated provides information on the variation in subsurface density, but does not provide sufficient information, hence the interest in using filtering with the aim of highlighting the structures affecting the area of south-west Cameroon. Three interpretation methods were used: vertical gradient, horizontal gradient coupled with upward continuation and Euler deconvolution. The application of these treatments enabled us to map a large number of gravimetric lineaments materializing density discontinuities. These lineaments are organized along main preferential directions: NW-SE, NNE-SSW, ENE-WSW and secondary directions: NNW-SSE, NE-SW, NS and E-W. Euler solutions indicate depths of up to 7337 m. Thanks to the results of this research, significant information has been acquired, contributing to a deeper understanding of the structural composition of the study area. The resulting structural map vividly illustrates the major tectonic events that shaped the geological framework of the study area. It also serves as a guide for prospecting subsurface resources (water and hydrocarbons). .
基金supported by the National Key R&D Program of China(Nos.2017YFC0803907,2017YFC0803900,and 2014BAG05B02).
文摘The cross-sectional width of highways is a major factor that affects the construction cost of engineering projects.With the increasing demand for intensive highway construction,research on dedicated lanes or roadway for cars has attracted research attention.The lateral oscillation value of vehicle’s trajectory is the direct factor that affects the lane width;however,relevant research is relatively limited,and the characteristics are not yet clear.Therefore,this study utilized an integrated radar shorter video system(IRVS)to collect real high-precision trajectory data,obtaining 24697 datasets.Statistical methods were used to reveal the lateral oscillation value and determine the effective lane width of cars for safe driving.The research results are as follows.1.The lateral oscillation value of cars varies across different lanes.Vehicles on the inner two lanes tend to drift leftward,whereas those on the outermost lane tend to drift rightward.2.When the operating speed ranges from 80 km/h to 110 km/h,the lateral oscillation value presents a statistical rule,which obeys a normal distribution for the left and right margins,i.e.,D_(left)~N(0.87,0.15)and Dright~N(0.72,0.15).This lateral oscillation value is insensitive to fluctuations in the operating speed(80 km/h~110 km/h)from the standpoint of field data.3.The fitted expressions of effective lane width for cars were proposed,and the effective lane width at the 95th,90th,and 85th percentile is 3.2 m,3.0 m,and 2.8 m,respectively.These results can provide technical support for dedicated lane width for cars,and have practical significance for the intensive construction of road infrastructure in highly urbanized areas.
基金The National Natural Science Foundation of China(No.61231002,61273266,61571106)the Foundation of the Department of Science and Technology of Guizhou Province(No.[2015]7637)
文摘In order to effectively conduct emotion recognition from spontaneous, non-prototypical and unsegmented speech so as to create a more natural human-machine interaction; a novel speech emotion recognition algorithm based on the combination of the emotional data field （EDF） and the ant colony search （ACS） strategy, called the EDF-ACS algorithm, is proposed. More specifically, the inter- relationship among the turn-based acoustic feature vectors of different labels are established by using the potential function in the EDF. To perform the spontaneous speech emotion recognition, the artificial colony is used to mimic the turn- based acoustic feature vectors. Then, the canonical ACS strategy is used to investigate the movement direction of each artificial ant in the EDF, which is regarded as the emotional label of the corresponding turn-based acoustic feature vector. The proposed EDF-ACS algorithm is evaluated on the continueous audio）＇visual emotion challenge （AVEC） 2012 dataset, which contains the spontaneous, non-prototypical and unsegmented speech emotion data. The experimental results show that the proposed EDF-ACS algorithm outperforms the existing state-of-the-art algorithm in turn-based speech emotion recognition.
基金the Beijing Municipal Science&Technology Project(Grant No.Z141100003614052)the National Natural Science Foundation of China(Grants No.51525901&51379100)as well as by China Ministry of Science and Technology(Grant No.2011CB409901)
文摘The quantification of the sheltering and exposure effects of non-uniform sediments has been widely achieved through hiding function models. Big challenge exists so far in the model parameter that is highly variable and differs greatly between laboratory flumes and field streams. This paper presents an improved surface-based hiding fimction. The force balance for particle inception was formulated and the allocation of the overall bed shear stress into each group of sediments was mimicked. The new hiding function was examined against and agrees well with the documented field and flume data. It was shown that the hiding fimction is closely related to the relative flow depth and the reference elevation in the velocity profile in addition to the bed material gradation. The power law of velocity profile that applies to both flume flows and natural streams can link the flume and field data together. The hiding function with b = 1/6 and b = 1/2 is applicable to natural streams and laboratory flumes, respectively. The value orb = 0.263 also works well for gravel bed rivers. The range of the reference elevation, namely z0 = 0.4Dm-1.4Dm, is recommended for either the flume or field data. The new hiding function contributes to addressing clearer physical meanings and a useful perspective for further improvement.
文摘Enterprise applications utilize relational databases and structured business processes, requiring slow and expensive conversion of inputs and outputs, from business documents such as invoices, purchase orders, and receipts, into known templates and schemas before processing. We propose a new LLM Agent-based intelligent data extraction, transformation, and load (IntelligentETL) pipeline that not only ingests PDFs and detects inputs within it but also addresses the extraction of structured and unstructured data by developing tools that most efficiently and securely deal with respective data types. We study the efficiency of our proposed pipeline and compare it with enterprise solutions that also utilize LLMs. We establish the supremacy in timely and accurate data extraction and transformation capabilities of our approach for analyzing the data from varied sources based on nested and/or interlinked input constraints.
文摘This paper emphasizes the importance of making field measurements for effective and realistic dependability evaluations.Two examples are given,both based on real data from IBM mainframes.The first evaluates the impact of the operating environment on system failure characteristics and the second shows how an accurate model depicting this interaction can be extracted from real data.
文摘Rice paddy mapping with optical remote sensing is challenging in Bangladesh due to the heterogeneous cropping pattern, fragmented field size and cloud </span><span style="font-family:Verdana;">cover during the growing period. The high-resolution Synthetic Aperture</span><span style="font-family:Verdana;"> Radar (SAR) sensor is the potential alternate to mapping rice area in Bangla</span><span style="font-family:Verdana;">desh. The L-band SAR sensor onboard Advanced Land Observing Satellit</span><span style="font-family:Verdana;">e (</span><span style="font-family:Verdana;">ALOS) acquires multi-polarization and multi-temporal images are </span><span style="font-family:Verdana;">a very useful tool for rice area mapping. In this study, we used ALOS-2 ScanSAR dual (HH</span></span><span style="font-family:""> </span><span style="font-family:Verdana;">+</span><span style="font-family:""> </span><span style="font-family:Verdana;">HV) polarized time series data in the study area. We used orthorectification and slope corrected backscatter (sigma-naught) images and median filtering (3 × 3) window for image processing. The unsupervised classification with the k-means++ algorithm is used for initial clustering (20 categories) of images over the study area. The GPS location of rice paddy field with cropping pattern over study area uses for classifying the different rice-growing season from the k-means clustering data. The result is compared with the moderate resolution imaging spectroradiometer (MODIS) based rice area and national statistical agricultural yearbook statistics. The results show that, based on the MODIS based rice map, the rice fields can be mapped with a conditional Kappa value of 0.68 and at user’s and producer’s accuracies of 86% and 90%, respectively. The large commission error primarily came from confusion between wet season Aus rice and others crop, Aus-Amon and Boro-Aus-Amon cropping pattern because of their similar backscatter amplitudes and temporal similarities in the rice growing season. The relatively high rice mapping accuracy in this study indicates that the ALOS/PALSAR-2 data could provide useful information in rice cropping management in subtropical regions such Bangladesh.
