Underground engineering projects such as deep tunnel excavation often encounter rockburst disasters accompanied by numerous microseismic events.Rapid interpretation of microseismic signals is crucial for the timely id...Underground engineering projects such as deep tunnel excavation often encounter rockburst disasters accompanied by numerous microseismic events.Rapid interpretation of microseismic signals is crucial for the timely identification of rockbursts.However,conventional processing encompasses multi-step workflows,including classification,denoising,picking,locating,and computational analysis,coupled with manual intervention,which collectively compromise the reliability of early warnings.To address these challenges,this study innovatively proposes the“microseismic stethoscope"-a multi-task machine learning and deep learning model designed for the automated processing of massive microseismic signals.This model efficiently extracts three key parameters that are necessary for recognizing rockburst disasters:rupture location,microseismic energy,and moment magnitude.Specifically,the model extracts raw waveform features from three dedicated sub-networks:a classifier for source zone classification,and two regressors for microseismic energy and moment magnitude estimation.This model demonstrates superior efficiency compared to traditional processing and semi-automated processing,reducing per-event processing time from 0.71 s to 0.49 s to merely 0.036 s.It concurrently achieves 98%accuracy in source zone classification,with microseismic energy and moment magnitude estimation errors of 0.13 and 0.05,respectively.This model has been well applied and validated in the Daxiagu Tunnel case in Sichuan,China.The application results indicate that the model is as accurate as traditional methods in determining source parameters,and thus can be used to identify potential geomechanical processes of rockburst disasters.By enhancing the signal processing reliability of microseismic events,the proposed model in this study presents a significant advancement in the identification of rockburst disasters.展开更多
The leaching process of magnesiothermic self-propagating product generated during the multistage deep reduction process was investigated.The influence of magnesiothermic self-propagating product particle size,HCl solu...The leaching process of magnesiothermic self-propagating product generated during the multistage deep reduction process was investigated.The influence of magnesiothermic self-propagating product particle size,HCl solution concentration,and leaching solution temperature on the leaching behavior of elements Al and V was investigated.Results demonstrate that the leaching rate of Al and V is increased with the rise in leaching solution temperature,the increase in HCl solution concentration,and the enlargement of magnesiothermic self-propagating product particle size.The leaching processes of Al and V are consistent with the chemical reaction control model.When the magnesiothermic self-propagation product with D_(50) of 59.4μm is selected as the raw material,the leaching temperature is 40℃,and 1 mol/L HCl solution is employed,after leaching for 180 min,the leaching rates of Al and V are 24.8%and 12.6%,respectively.The acid-leached product exhibits a porous structure with a specific surface area of 3.5633 m^(2)/g.展开更多
DeepSeek Chinese artificial intelligence(AI)open-source model,has gained a lot of attention due to its economical training and efficient inference.DeepSeek,a model trained on large-scale reinforcement learning without...DeepSeek Chinese artificial intelligence(AI)open-source model,has gained a lot of attention due to its economical training and efficient inference.DeepSeek,a model trained on large-scale reinforcement learning without supervised fine-tuning as a preliminary step,demonstrates remarkable reasoning capabilities of performing a wide range of tasks.DeepSeek is a prominent AI-driven chatbot that assists individuals in learning and enhances responses by generating insightful solutions to inquiries.Users possess divergent viewpoints regarding advanced models like DeepSeek,posting both their merits and shortcomings across several social media platforms.This research presents a new framework for predicting public sentiment to evaluate perceptions of DeepSeek.To transform the unstructured data into a suitable manner,we initially collect DeepSeek-related tweets from Twitter and subsequently implement various preprocessing methods.Subsequently,we annotated the tweets utilizing the Valence Aware Dictionary and sentiment Reasoning(VADER)methodology and the lexicon-driven TextBlob.Next,we classified the attitudes obtained from the purified data utilizing the proposed hybrid model.The proposed hybrid model consists of long-term,shortterm memory(LSTM)and bidirectional gated recurrent units(BiGRU).To strengthen it,we include multi-head attention,regularizer activation,and dropout units to enhance performance.Topic modeling employing KMeans clustering and Latent Dirichlet Allocation(LDA),was utilized to analyze public behavior concerning DeepSeek.The perceptions demonstrate that 82.5%of the people are positive,15.2%negative,and 2.3%neutral using TextBlob,and 82.8%positive,16.1%negative,and 1.2%neutral using the VADER analysis.The slight difference in results ensures that both analyses concur with their overall perceptions and may have distinct views of language peculiarities.The results indicate that the proposed model surpassed previous state-of-the-art approaches.展开更多
Accurate retrieval of casting 3D models is crucial for process reuse.Current methods primarily focus on shape similarity,neglecting process design features,which compromises reusability.In this study,a novel deep lear...Accurate retrieval of casting 3D models is crucial for process reuse.Current methods primarily focus on shape similarity,neglecting process design features,which compromises reusability.In this study,a novel deep learning retrieval method for process reuse was proposed,which integrates process design features into the retrieval of casting 3D models.This method leverages the comparative language-image pretraining(CLIP)model to extract shape features from the three views and sectional views of the casting model and combines them with process design features such as modulus,main wall thickness,symmetry,and length-to-height ratio to enhance process reusability.A database of 230 production casting models was established for model validation.Results indicate that incorporating process design features improves model accuracy by 6.09%,reaching 97.82%,and increases process similarity by 30.25%.The reusability of the process was further verified using the casting simulation software EasyCast.The results show that the process retrieved after integrating process design features produces the least shrinkage in the target model,demonstrating this method’s superior ability for process reuse.This approach does not require a large dataset for training and optimization,making it highly applicable to casting process design and related manufacturing processes.展开更多
The accurate identification and diagnosis of chemical process faults are crucial for ensuring the safe and stable operation of production plants.The current hot topic in industrial process fault diagnosis research is ...The accurate identification and diagnosis of chemical process faults are crucial for ensuring the safe and stable operation of production plants.The current hot topic in industrial process fault diagnosis research is data-driven methods.Most of the existing fault diagnosis methods focus on a single shallow or deep learning model.This paper proposes a novel hybrid fault diagnosis method to fully utilize various features to improve the accuracy of fault diagnosis.Furthermore,the method addresses the issue of incomplete data,which has been largely overlooked in the majority of existing research.Firstly,the variable data is effectively fitted using orthogonal non-negative matrix tri-factorization,and the missing data in the matrix is solved to construct a complete production condition relationship.Next,the support vector machine model and the deep residual contraction network model are trained in parallel to prediagnose process faults by mining linear and non-linear interaction features.Finally,a novel mapping relationship is established between the result and model levels using the multi-layer perceptron algorithm to complete the final diagnosis and evaluation of the fault.To demonstrate the effectiveness of the proposed method,we conducted extensive comparative experiments on the Tennessee Eastman dataset and the ethylene plant cracking unit dataset.The experimental results show that the method has advantages in different evaluation metrics.展开更多
The deep geologic processes between the Xing’an-Mongolian Orogenic Belt and the North China Craton in the Mesozoic are crucial to reveal the magmatic and tectonic evolution and their constraints on mineralization in ...The deep geologic processes between the Xing’an-Mongolian Orogenic Belt and the North China Craton in the Mesozoic are crucial to reveal the magmatic and tectonic evolution and their constraints on mineralization in the Jiapigou-Haigou collage zone.In this paper,We have presented the geochronology,geochemistry and Sr-Nd-Hf isotopic compositions of the Middle Jurassic granitic complexes in the Songjianghe area,Jilin Province.The granitic complexes can be categorized into four groups based on their geologic characteristics,with corresponding zircon U-Pb isotope ages of 177 Ma,172 Ma,169 Ma and 168-167 Ma,respectively.These granitoids exhibit calcalkaline to high-K calc-alkaline,metaluminous to weakly peraluminous Ⅰ-type characteristics,which show relative enrichment in LILEs(Rb,Sr,Ba)and depletion in HFSEs(Nb,Zr).Geochemical analyses reveal high initial^(87)Sr/^(86)Sr ratios of 0.70633-0.70740,coupled with lowεNd(t)values ranging from−10.65 to−13.23.The zircon analyses show similarly negativeεHf(t)values ranging from−16.9 to−3.2.The integrated elemental and Hf-Sr-Nd isotopic signatures demonstrate that the primitive magmas of the four group rocks were primarily derived from partial melting of thickened Archean lower crust,with the exception of the Group Ⅳ rocks,which exhibit significant evidence of crustal contamination.The residual mineral assemblages during the magma-forming process varied from amphibole to eclogite facies.These findings indicate that magmatism in the Songjianghe region likely resulted from the accretion and delamination of the Archean crust in the collage zone during the subduction of the Paleo-Pacific Plate beneath the Eurasian continent.展开更多
Deep learning now underpins many state-of-the-art systems for biomedical image and signal processing,enabling automated lesion detection,physiological monitoring,and therapy planning with accuracy that rivals expert p...Deep learning now underpins many state-of-the-art systems for biomedical image and signal processing,enabling automated lesion detection,physiological monitoring,and therapy planning with accuracy that rivals expert performance.This survey reviews the principal model families as convolutional,recurrent,generative,reinforcement,autoencoder,and transfer-learning approaches as emphasising how their architectural choices map to tasks such as segmentation,classification,reconstruction,and anomaly detection.A dedicated treatment of multimodal fusion networks shows how imaging features can be integrated with genomic profiles and clinical records to yield more robust,context-aware predictions.To support clinical adoption,we outline post-hoc explainability techniques(Grad-CAM,SHAP,LIME)and describe emerging intrinsically interpretable designs that expose decision logic to end users.Regulatory guidance from the U.S.FDA,the European Medicines Agency,and the EU AI Act is summarised,linking transparency and lifecycle-monitoring requirements to concrete development practices.Remaining challenges as data imbalance,computational cost,privacy constraints,and cross-domain generalization are discussed alongside promising solutions such as federated learning,uncertainty quantification,and lightweight 3-D architectures.The article therefore offers researchers,clinicians,and policymakers a concise,practice-oriented roadmap for deploying trustworthy deep-learning systems in healthcare.展开更多
Human Activity Recognition(HAR)is a novel area for computer vision.It has a great impact on healthcare,smart environments,and surveillance while is able to automatically detect human behavior.It plays a vital role in ...Human Activity Recognition(HAR)is a novel area for computer vision.It has a great impact on healthcare,smart environments,and surveillance while is able to automatically detect human behavior.It plays a vital role in many applications,such as smart home,healthcare,human computer interaction,sports analysis,and especially,intelligent surveillance.In this paper,we propose a robust and efficient HAR system by leveraging deep learning paradigms,including pre-trained models,CNN architectures,and their average-weighted fusion.However,due to the diversity of human actions and various environmental influences,as well as a lack of data and resources,achieving high recognition accuracy remain elusive.In this work,a weighted average ensemble technique is employed to fuse three deep learning models:EfficientNet,ResNet50,and a custom CNN.The results of this study indicate that using a weighted average ensemble strategy for developing more effective HAR models may be a promising idea for detection and classification of human activities.Experiments by using the benchmark dataset proved that the proposed weighted ensemble approach outperformed existing approaches in terms of accuracy and other key performance measures.The combined average-weighted ensemble of pre-trained and CNN models obtained an accuracy of 98%,compared to 97%,96%,and 95%for the customized CNN,EfficientNet,and ResNet50 models,respectively.展开更多
Recent advances in deep learning have significantly improved flood detection and segmentation from aerial and satellite imagery.However,conventional convolutional neural networks(CNNs)often struggle in complex flood s...Recent advances in deep learning have significantly improved flood detection and segmentation from aerial and satellite imagery.However,conventional convolutional neural networks(CNNs)often struggle in complex flood scenarios involving reflections,occlusions,or indistinct boundaries due to limited contextual modeling.To address these challenges,we propose a hybrid flood segmentation framework that integrates a Vision Transformer(ViT)encoder with a U-Net decoder,enhanced by a novel Flood-Aware Refinement Block(FARB).The FARB module improves boundary delineation and suppresses noise by combining residual smoothing with spatial-channel attention mechanisms.We evaluate our model on a UAV-acquired flood imagery dataset,demonstrating that the proposed ViTUNet+FARB architecture outperforms existing CNN and Transformer-based models in terms of accuracy and mean Intersection over Union(mIoU).Detailed ablation studies further validate the contribution of each component,confirming that the FARB design significantly enhances segmentation quality.To its better performance and computational efficiency,the proposed framework is well-suited for flood monitoring and disaster response applications,particularly in resource-constrained environments.展开更多
Covert timing channels(CTC)exploit network resources to establish hidden communication pathways,posing signi cant risks to data security and policy compliance.erefore,detecting such hidden and dangerous threats remain...Covert timing channels(CTC)exploit network resources to establish hidden communication pathways,posing signi cant risks to data security and policy compliance.erefore,detecting such hidden and dangerous threats remains one of the security challenges. is paper proposes LinguTimeX,a new framework that combines natural language processing with arti cial intelligence,along with explainable Arti cial Intelligence(AI)not only to detect CTC but also to provide insights into the decision process.LinguTimeX performs multidimensional feature extraction by fusing linguistic attributes with temporal network patterns to identify covert channels precisely.LinguTimeX demonstrates strong e ectiveness in detecting CTC across multiple languages;namely English,Arabic,and Chinese.Speci cally,the LSTM and RNN models achieved F1 scores of 90%on the English dataset,89%on the Arabic dataset,and 88%on the Chinese dataset,showcasing their superior performance and ability to generalize across multiple languages. is highlights their robustness in detecting CTCs within security systems,regardless of the language or cultural context of the data.In contrast,the DeepForest model produced F1-scores ranging from 86%to 87%across the same datasets,further con rming its e ectiveness in CTC detection.Although other algorithms also showed reasonable accuracy,the LSTM and RNN models consistently outperformed them in multilingual settings,suggesting that deep learning models might be better suited for this particular problem.展开更多
In this study,an automated multimodal system for detecting,classifying,and dating fruit was developed using a two-stage YOLOv11 pipeline.In the first stage,the YOLOv11 detection model locates individual date fruits in...In this study,an automated multimodal system for detecting,classifying,and dating fruit was developed using a two-stage YOLOv11 pipeline.In the first stage,the YOLOv11 detection model locates individual date fruits in real time by drawing bounding boxes around them.These bounding boxes are subsequently passed to a YOLOv11 classification model,which analyzes cropped images and assigns class labels.An additional counting module automatically tallies the detected fruits,offering a near-instantaneous estimation of quantity.The experimental results suggest high precision and recall for detection,high classification accuracy(across 15 classes),and near-perfect counting in real time.This paper presents a multi-stage pipeline for date fruit detection,classification,and automated counting,employing YOLOv11-based models to achieve high accuracy while maintaining real-time throughput.The results demonstrated that the detection precision exceeded 90%,the classification accuracy approached 92%,and the counting module correlated closely with the manual tallies.These findings confirm the potential of reducing manual labour and enhancing operational efficiency in post-harvesting processes.Future studies will include dataset expansion,user-centric interfaces,and integration with harvesting robotics.展开更多
Underwater images frequently suffer from chromatic distortion,blurred details,and low contrast,posing significant challenges for enhancement.This paper introduces AquaTree,a novel underwater image enhancement(UIE)meth...Underwater images frequently suffer from chromatic distortion,blurred details,and low contrast,posing significant challenges for enhancement.This paper introduces AquaTree,a novel underwater image enhancement(UIE)method that reformulates the task as a Markov Decision Process(MDP)through the integration of Monte Carlo Tree Search(MCTS)and deep reinforcement learning(DRL).The framework employs an action space of 25 enhancement operators,strategically grouped for basic attribute adjustment,color component balance,correction,and deblurring.Exploration within MCTS is guided by a dual-branch convolutional network,enabling intelligent sequential operator selection.Our core contributions include:(1)a multimodal state representation combining CIELab color histograms with deep perceptual features,(2)a dual-objective reward mechanism optimizing chromatic fidelity and perceptual consistency,and(3)an alternating training strategy co-optimizing enhancement sequences and network parameters.We further propose two inference schemes:an MCTS-based approach prioritizing accuracy at higher computational cost,and an efficient network policy enabling real-time processing with minimal quality loss.Comprehensive evaluations on the UIEB Dataset and Color correction and haze removal comparisons on the U45 Dataset demonstrate AquaTree’s superiority,significantly outperforming nine state-of-the-art methods across five established underwater image quality metrics.展开更多
The Nanling region is an important nonferrous and rare metal metallogenic province in South China, in which most of the deposits are related to granitoids in genesis. It covers southern Hunan, southern Jiangxi, Guangx...The Nanling region is an important nonferrous and rare metal metallogenic province in South China, in which most of the deposits are related to granitoids in genesis. It covers southern Hunan, southern Jiangxi, Guangxi, Guangdong and Fujian provinces, with a total area of about 550,000 km2. This metallogenic province is well known in the world for its rich tungsten and tin resources. In the past 40-odd years, a vast amount of mineral exploration activities and studies of the geology of mineral deposits have been carried out and great achievements obtained in the province. This paper is focused on a discussion about the deep tectonic processes in the orogenic belt during the Mesozoic and their contribution to the superaccumulation of metals. Tectonically, this metallogenic province is composed of three units: (1) the marginal continental orogenic belt in the Southeastern Coast fold system in the Yanshanian; (2) the intercontinental orogenic belt in the collision suture belt between the Yangtze and Cathay-sian plates mainly in the Caledonian; and (3) the intracontinental orogenic belt induced by subduction of the ocean crust and delimination of the mantle lithosphere in the Yanshanian. It is suggested that superaccumulation of metals in this metallogenic province was caused by the existence of mantle rooted tectonics at the depth based on comprehensive studies of geophysical information of seismic, geothermal and magnetotelluric surveys in Nanling and its adjacent areas. The Xihuashan wolframite quartz vein deposit, the Shizhuyuan W, Sn, Mo, Bi greisen-skarn deposit and the Dachang tin-polymetallic deposit are three typical examples of the deep tectonic processes. However, this kind of deep tectonic processes only act as the 'engine' of the superaccumulation of metals, which means that they should have to correspond with the super-crust ore-controlling pattern of 'lines-rows-clusters' (L-R-C). This recog-nization is expected to play an important role in assessment of mineral resources in this province.展开更多
The Yinchuan basin,located on the western margin of the Ordos block,has the characteristics of an active continental rift.A NW-striking deep seismic reflection profile across the center of Yinchuan basin precisely rev...The Yinchuan basin,located on the western margin of the Ordos block,has the characteristics of an active continental rift.A NW-striking deep seismic reflection profile across the center of Yinchuan basin precisely revealed the fine structure of the crust.The images showed that the crust in the Yinchuan basin was characterized by vertical stratifications along a detachment located at a two-way travel time(TWT)of 8.0 s.The most outstanding feature of this seismic profile was the almost flat Mohorovicˇic′discontinuity(Moho)and a high-reflection zone in the lower crust.This sub-horizontal Moho conflicts with the general assumption of an uplifted Moho under sedimentary basins and continental rifts,and may indicate the action of different processes at depth during the evolution of sedimentary basins or rifts.We present a possible interpretation of these deep processes and the sub-horizontal Moho.The high-reflection zone,which consists of sheets of high-density,mantlederived materials,may have compensated for crustal thinning in the Yinchuan basin,leading to the formation of a sub-horizontal Moho.These high-density materials may have been emplaced by underplating with mantlesourced magma.展开更多
The collision between the Indian and Asian plates uplifted the Himalayan-Tibetan Plateau,thickening and expanding the crust.It is a scientific mystery of global concern as how the two continents collide and how the co...The collision between the Indian and Asian plates uplifted the Himalayan-Tibetan Plateau,thickening and expanding the crust.It is a scientific mystery of global concern as how the two continents collide and how the continent-continent collision deforms the continent.Deep seismic reflection profile detection is one of the most effective ways to unlock this scientific mystery.For more than 20 years using this technology,we have detected fine structures of the thick crust of the Tibetan plateau after overcoming technical bottlenecks to access the lower crust and Moho thus revealing the continental collision processes.This paper systematically summarizes the deep behaviors of the India-Asia collision and subduction beneath the Tibetan Plateau,from south to north,east to west and further into the hinterland of the plateau.The Indian crust undergoes underthrusting beneath the Himalayan orogenic belt on the southern margin of the plateau.Meanwhile,the lithosphere of the Alxa block in the Asian plate subducts southward beneath the Qilian Mountain in the north of the plateau,driving the northward overthrusting of the Qilian crust.Additionally,the Tarim and West Kunlun blocks undergo face-to-face collision in the northwestern margin of the plateau.In the easternmost part of the plateau,the Longriba fault,instead of the Longmen Shan fault zone,marks the western margin of the Yangtze block.It is also seismically evidenced that the Moho geometry in the plateaus hinterland appears thin and flat,indicating lithospheric collapse and extrusion.Multiple deep reflection profiles revealed the collisional behavior under the Yalung-Zangbo suture zone and longitudinal variation in subducting geometry of the Indian crust from west to the east.In the middle of the suture zone,it shows a decoupling between the upper and lower crusts of the Indian plate,where the upper crust undergoes a northward overthrusting while the lower one experiences a northward underthrusting.It is also seismically evidenced a down-and southward crustal duplexing of the subducting Indian crust thickening the northern Himalayas,leaving over a thinning subducting lower crust of the Indian slab.The subduction front of the Indian crust collides with the lower crust of the Asian plate at the mantle depth.A near-vertical collision boundary is seen between the Gangdese batholith and the Tethyan Himalayas,where the Gangdese batholith shows almost transparent weak reflections in the lower crust with localized bright spot reflection that indicates partial melting.Additionally,the near-flat Moho geometry implies an extensional tectonic environment of the southern margin of the Asian plate.展开更多
Major defects in forming of conical cups are wrinkles and rupture.Hydrodynamic deep drawing assisted by radial pressure（HDDRP） is a sheet hydroforming process for production of shell cups in one step.In this work,pr...Major defects in forming of conical cups are wrinkles and rupture.Hydrodynamic deep drawing assisted by radial pressure（HDDRP） is a sheet hydroforming process for production of shell cups in one step.In this work,process window diagrams（PWDs） for Al1050-O,pure copper and DIN 1623 St14 steel are obtained for HDDRP process.The PWD is determined to provide a quick assessment of part producibility for sheet hydroforming process.Finite element method is used for this purpose considering the process parameters including pressure path,and the blank material and its thickness.Numerical results are validated by experiments.It is shown that the sheets with less initial thickness and higher strength show better formability and uniformity of thickness distribution on final product.The results demonstrate that the obtained PWD can predict appropriate forming area and probability of rupture or wrinkling occurrence under different pressure loading paths.展开更多
The quantitative determination and evaluation of rock brittleness are crucial for the estimation of excavation efficiency and the improvement of hydraulic fracturing efficiency.Therefore,a“three-stage”triaxial loadi...The quantitative determination and evaluation of rock brittleness are crucial for the estimation of excavation efficiency and the improvement of hydraulic fracturing efficiency.Therefore,a“three-stage”triaxial loading and unloading stress path is designed and proposed.Subsequently,six brittleness indices are selected.In addition,the evolution characteristics of the six brittleness indices selected are characterized based on the bedding effect and the effect of confining pressure.Then,the entropy weight method(EWM)is introduced to assign weight to the six brittleness indices,and the comprehensive brittleness index Bcis defined and evaluated.Next,the new brittleness classification standard is determined,and the brittleness differences between the two stress paths are quantified.Finally,compared with the previous evaluation methods,the rationality of the proposed comprehensive brittleness index Bcis also verified.These results indicate that the proposed brittleness index Bccan reflect the brittle characteristics of deep bedded sandstone from the perspective of the whole life-cycle evolution process.Accordingly,the method proposed seems to offer reliable evaluations of the brittleness of deep bedded sandstone in deep engineering practices,although further validation is necessary.展开更多
Oscillation detection has been a hot research topic in industries due to the high incidence of oscillation loops and their negative impact on plant profitability.Although numerous automatic detection techniques have b...Oscillation detection has been a hot research topic in industries due to the high incidence of oscillation loops and their negative impact on plant profitability.Although numerous automatic detection techniques have been proposed,most of them can only address part of the practical difficulties.An oscillation is heuristically defined as a visually apparent periodic variation.However,manual visual inspection is labor-intensive and prone to missed detection.Convolutional neural networks(CNNs),inspired by animal visual systems,have been raised with powerful feature extraction capabilities.In this work,an exploration of the typical CNN models for visual oscillation detection is performed.Specifically,we tested MobileNet-V1,ShuffleNet-V2,Efficient Net-B0,and GhostNet models,and found that such a visual framework is well-suited for oscillation detection.The feasibility and validity of this framework are verified utilizing extensive numerical and industrial cases.Compared with state-of-theart oscillation detectors,the suggested framework is more straightforward and more robust to noise and mean-nonstationarity.In addition,this framework generalizes well and is capable of handling features that are not present in the training data,such as multiple oscillations and outliers.展开更多
Identification of abnormal conditions is essential in the chemical process.With the rapid development of artificial intelligence technology,deep learning has attracted a lot of attention as a promising fault identific...Identification of abnormal conditions is essential in the chemical process.With the rapid development of artificial intelligence technology,deep learning has attracted a lot of attention as a promising fault identification method in chemical process recently.In the high-dimensional data identification using deep neural networks,problems such as insufficient data and missing data,measurement noise,redundant variables,and high coupling of data are often encountered.To tackle these problems,a feature based deep belief networks(DBN)method is proposed in this paper.First,a generative adversarial network(GAN)is used to reconstruct the random and non-random missing data of chemical process.Second,the feature variables are selected by Spearman’s rank correlation coefficient(SRCC)from high-dimensional data to eliminate the noise and redundant variables and,as a consequence,compress data dimension of chemical process.Finally,the feature filtered data is deeply abstracted,learned and tuned by DBN for multi-case fault identification.The application in the Tennessee Eastman(TE)process demonstrates the fast convergence and high accuracy of this proposal in identifying abnormal conditions for chemical process,compared with the traditional fault identification algorithms.展开更多
The present paper describes the characteristics of Cenozoic basalt in the Bohaiwan basin and its implication of the control of deep process over the basin evolution. The large scale Eogene basalts lying on the basemen...The present paper describes the characteristics of Cenozoic basalt in the Bohaiwan basin and its implication of the control of deep process over the basin evolution. The large scale Eogene basalts lying on the basement of the Bohaiwan basin belong to alkaline series and subalkaline series. The basalt magma originates at a depth of 48-76 km and a temperature of 1 300-1 400 ℃ with the mantle partial melting degree of 8%-14%. In Eogene period, the rising of the top of asthenosphere from 100-140 km to 50-70 km led to the strong extension and thinning of the overlying lithosphere, which was stretched at an average rate of 0.41 cm/a and the β value from 1.9 to 2.3. At the same time, it triggered the great scale rifting in the earth crust, forming large rift basins.展开更多
基金supported by the National Natural Science Foundation of China(Grant Nos.42130719 and 42177173)the Doctoral Direct Train Project of Chongqing Natural Science Foundation(Grant No.CSTB2023NSCQ-BSX0029).
文摘Underground engineering projects such as deep tunnel excavation often encounter rockburst disasters accompanied by numerous microseismic events.Rapid interpretation of microseismic signals is crucial for the timely identification of rockbursts.However,conventional processing encompasses multi-step workflows,including classification,denoising,picking,locating,and computational analysis,coupled with manual intervention,which collectively compromise the reliability of early warnings.To address these challenges,this study innovatively proposes the“microseismic stethoscope"-a multi-task machine learning and deep learning model designed for the automated processing of massive microseismic signals.This model efficiently extracts three key parameters that are necessary for recognizing rockburst disasters:rupture location,microseismic energy,and moment magnitude.Specifically,the model extracts raw waveform features from three dedicated sub-networks:a classifier for source zone classification,and two regressors for microseismic energy and moment magnitude estimation.This model demonstrates superior efficiency compared to traditional processing and semi-automated processing,reducing per-event processing time from 0.71 s to 0.49 s to merely 0.036 s.It concurrently achieves 98%accuracy in source zone classification,with microseismic energy and moment magnitude estimation errors of 0.13 and 0.05,respectively.This model has been well applied and validated in the Daxiagu Tunnel case in Sichuan,China.The application results indicate that the model is as accurate as traditional methods in determining source parameters,and thus can be used to identify potential geomechanical processes of rockburst disasters.By enhancing the signal processing reliability of microseismic events,the proposed model in this study presents a significant advancement in the identification of rockburst disasters.
基金Scientific and Technological Project of Nanyang(23KJGG017)Key Specialized Research&Development and Promotion Project(Scientific and Technological Project)of Henan Province(232102221022)+1 种基金College Students and Technology Innovation Fund Project of Nanyang Institute of Technology(2023139)Project of Doctoral Scientific Research Startup Fund of Nanyang Institute of Technology(NGBJ-2023-25)。
文摘The leaching process of magnesiothermic self-propagating product generated during the multistage deep reduction process was investigated.The influence of magnesiothermic self-propagating product particle size,HCl solution concentration,and leaching solution temperature on the leaching behavior of elements Al and V was investigated.Results demonstrate that the leaching rate of Al and V is increased with the rise in leaching solution temperature,the increase in HCl solution concentration,and the enlargement of magnesiothermic self-propagating product particle size.The leaching processes of Al and V are consistent with the chemical reaction control model.When the magnesiothermic self-propagation product with D_(50) of 59.4μm is selected as the raw material,the leaching temperature is 40℃,and 1 mol/L HCl solution is employed,after leaching for 180 min,the leaching rates of Al and V are 24.8%and 12.6%,respectively.The acid-leached product exhibits a porous structure with a specific surface area of 3.5633 m^(2)/g.
文摘DeepSeek Chinese artificial intelligence(AI)open-source model,has gained a lot of attention due to its economical training and efficient inference.DeepSeek,a model trained on large-scale reinforcement learning without supervised fine-tuning as a preliminary step,demonstrates remarkable reasoning capabilities of performing a wide range of tasks.DeepSeek is a prominent AI-driven chatbot that assists individuals in learning and enhances responses by generating insightful solutions to inquiries.Users possess divergent viewpoints regarding advanced models like DeepSeek,posting both their merits and shortcomings across several social media platforms.This research presents a new framework for predicting public sentiment to evaluate perceptions of DeepSeek.To transform the unstructured data into a suitable manner,we initially collect DeepSeek-related tweets from Twitter and subsequently implement various preprocessing methods.Subsequently,we annotated the tweets utilizing the Valence Aware Dictionary and sentiment Reasoning(VADER)methodology and the lexicon-driven TextBlob.Next,we classified the attitudes obtained from the purified data utilizing the proposed hybrid model.The proposed hybrid model consists of long-term,shortterm memory(LSTM)and bidirectional gated recurrent units(BiGRU).To strengthen it,we include multi-head attention,regularizer activation,and dropout units to enhance performance.Topic modeling employing KMeans clustering and Latent Dirichlet Allocation(LDA),was utilized to analyze public behavior concerning DeepSeek.The perceptions demonstrate that 82.5%of the people are positive,15.2%negative,and 2.3%neutral using TextBlob,and 82.8%positive,16.1%negative,and 1.2%neutral using the VADER analysis.The slight difference in results ensures that both analyses concur with their overall perceptions and may have distinct views of language peculiarities.The results indicate that the proposed model surpassed previous state-of-the-art approaches.
基金supported by the National Natural Science Foundation of China(Nos.52074246,52275390,52375394)the National Defense Basic Scientific Research Program of China(No.JCKY2020408B002)the Key R&D Program of Shanxi Province(No.202102050201011).
文摘Accurate retrieval of casting 3D models is crucial for process reuse.Current methods primarily focus on shape similarity,neglecting process design features,which compromises reusability.In this study,a novel deep learning retrieval method for process reuse was proposed,which integrates process design features into the retrieval of casting 3D models.This method leverages the comparative language-image pretraining(CLIP)model to extract shape features from the three views and sectional views of the casting model and combines them with process design features such as modulus,main wall thickness,symmetry,and length-to-height ratio to enhance process reusability.A database of 230 production casting models was established for model validation.Results indicate that incorporating process design features improves model accuracy by 6.09%,reaching 97.82%,and increases process similarity by 30.25%.The reusability of the process was further verified using the casting simulation software EasyCast.The results show that the process retrieved after integrating process design features produces the least shrinkage in the target model,demonstrating this method’s superior ability for process reuse.This approach does not require a large dataset for training and optimization,making it highly applicable to casting process design and related manufacturing processes.
文摘The accurate identification and diagnosis of chemical process faults are crucial for ensuring the safe and stable operation of production plants.The current hot topic in industrial process fault diagnosis research is data-driven methods.Most of the existing fault diagnosis methods focus on a single shallow or deep learning model.This paper proposes a novel hybrid fault diagnosis method to fully utilize various features to improve the accuracy of fault diagnosis.Furthermore,the method addresses the issue of incomplete data,which has been largely overlooked in the majority of existing research.Firstly,the variable data is effectively fitted using orthogonal non-negative matrix tri-factorization,and the missing data in the matrix is solved to construct a complete production condition relationship.Next,the support vector machine model and the deep residual contraction network model are trained in parallel to prediagnose process faults by mining linear and non-linear interaction features.Finally,a novel mapping relationship is established between the result and model levels using the multi-layer perceptron algorithm to complete the final diagnosis and evaluation of the fault.To demonstrate the effectiveness of the proposed method,we conducted extensive comparative experiments on the Tennessee Eastman dataset and the ethylene plant cracking unit dataset.The experimental results show that the method has advantages in different evaluation metrics.
基金supported by the Natural Science Foundation of Jilin Province of China(grant no.20230101075JC)the National Natural Science Foundation of China(grant no.42072085).
文摘The deep geologic processes between the Xing’an-Mongolian Orogenic Belt and the North China Craton in the Mesozoic are crucial to reveal the magmatic and tectonic evolution and their constraints on mineralization in the Jiapigou-Haigou collage zone.In this paper,We have presented the geochronology,geochemistry and Sr-Nd-Hf isotopic compositions of the Middle Jurassic granitic complexes in the Songjianghe area,Jilin Province.The granitic complexes can be categorized into four groups based on their geologic characteristics,with corresponding zircon U-Pb isotope ages of 177 Ma,172 Ma,169 Ma and 168-167 Ma,respectively.These granitoids exhibit calcalkaline to high-K calc-alkaline,metaluminous to weakly peraluminous Ⅰ-type characteristics,which show relative enrichment in LILEs(Rb,Sr,Ba)and depletion in HFSEs(Nb,Zr).Geochemical analyses reveal high initial^(87)Sr/^(86)Sr ratios of 0.70633-0.70740,coupled with lowεNd(t)values ranging from−10.65 to−13.23.The zircon analyses show similarly negativeεHf(t)values ranging from−16.9 to−3.2.The integrated elemental and Hf-Sr-Nd isotopic signatures demonstrate that the primitive magmas of the four group rocks were primarily derived from partial melting of thickened Archean lower crust,with the exception of the Group Ⅳ rocks,which exhibit significant evidence of crustal contamination.The residual mineral assemblages during the magma-forming process varied from amphibole to eclogite facies.These findings indicate that magmatism in the Songjianghe region likely resulted from the accretion and delamination of the Archean crust in the collage zone during the subduction of the Paleo-Pacific Plate beneath the Eurasian continent.
基金supported by the Science Committee of the Ministry of Higher Education and Science of the Republic of Kazakhstan within the framework of grant AP23489899“Applying Deep Learning and Neuroimaging Methods for Brain Stroke Diagnosis”.
文摘Deep learning now underpins many state-of-the-art systems for biomedical image and signal processing,enabling automated lesion detection,physiological monitoring,and therapy planning with accuracy that rivals expert performance.This survey reviews the principal model families as convolutional,recurrent,generative,reinforcement,autoencoder,and transfer-learning approaches as emphasising how their architectural choices map to tasks such as segmentation,classification,reconstruction,and anomaly detection.A dedicated treatment of multimodal fusion networks shows how imaging features can be integrated with genomic profiles and clinical records to yield more robust,context-aware predictions.To support clinical adoption,we outline post-hoc explainability techniques(Grad-CAM,SHAP,LIME)and describe emerging intrinsically interpretable designs that expose decision logic to end users.Regulatory guidance from the U.S.FDA,the European Medicines Agency,and the EU AI Act is summarised,linking transparency and lifecycle-monitoring requirements to concrete development practices.Remaining challenges as data imbalance,computational cost,privacy constraints,and cross-domain generalization are discussed alongside promising solutions such as federated learning,uncertainty quantification,and lightweight 3-D architectures.The article therefore offers researchers,clinicians,and policymakers a concise,practice-oriented roadmap for deploying trustworthy deep-learning systems in healthcare.
基金supported by Princess Nourah bint Abdulrahman University Researchers Supporting Project number(PNURSP2026R765),Princess Nourah bint Abdulrahman University,Riyadh,Saudi Arabia.
文摘Human Activity Recognition(HAR)is a novel area for computer vision.It has a great impact on healthcare,smart environments,and surveillance while is able to automatically detect human behavior.It plays a vital role in many applications,such as smart home,healthcare,human computer interaction,sports analysis,and especially,intelligent surveillance.In this paper,we propose a robust and efficient HAR system by leveraging deep learning paradigms,including pre-trained models,CNN architectures,and their average-weighted fusion.However,due to the diversity of human actions and various environmental influences,as well as a lack of data and resources,achieving high recognition accuracy remain elusive.In this work,a weighted average ensemble technique is employed to fuse three deep learning models:EfficientNet,ResNet50,and a custom CNN.The results of this study indicate that using a weighted average ensemble strategy for developing more effective HAR models may be a promising idea for detection and classification of human activities.Experiments by using the benchmark dataset proved that the proposed weighted ensemble approach outperformed existing approaches in terms of accuracy and other key performance measures.The combined average-weighted ensemble of pre-trained and CNN models obtained an accuracy of 98%,compared to 97%,96%,and 95%for the customized CNN,EfficientNet,and ResNet50 models,respectively.
基金supported by the National Research Foundation of Korea(NRF)grant funded by theKorea government(MSIT)(No.RS-2024-00405278)partially supported by the Jeju Industry-University Convergence District Project for Promoting Industry-Campus Cooperationfunded by the Ministry of Trade,Industry and Energy(MOTIE,Korea)[Project Name:Jeju Industry-University Convergence District Project for Promoting Industry-Campus Cooperation/Project Number:P0029950].
文摘Recent advances in deep learning have significantly improved flood detection and segmentation from aerial and satellite imagery.However,conventional convolutional neural networks(CNNs)often struggle in complex flood scenarios involving reflections,occlusions,or indistinct boundaries due to limited contextual modeling.To address these challenges,we propose a hybrid flood segmentation framework that integrates a Vision Transformer(ViT)encoder with a U-Net decoder,enhanced by a novel Flood-Aware Refinement Block(FARB).The FARB module improves boundary delineation and suppresses noise by combining residual smoothing with spatial-channel attention mechanisms.We evaluate our model on a UAV-acquired flood imagery dataset,demonstrating that the proposed ViTUNet+FARB architecture outperforms existing CNN and Transformer-based models in terms of accuracy and mean Intersection over Union(mIoU).Detailed ablation studies further validate the contribution of each component,confirming that the FARB design significantly enhances segmentation quality.To its better performance and computational efficiency,the proposed framework is well-suited for flood monitoring and disaster response applications,particularly in resource-constrained environments.
基金This study is financed by the European Union-NextGenerationEU,through the National Recovery and Resilience Plan of the Republic of Bulgaria,Project No.BG-RRP-2.013-0001.
文摘Covert timing channels(CTC)exploit network resources to establish hidden communication pathways,posing signi cant risks to data security and policy compliance.erefore,detecting such hidden and dangerous threats remains one of the security challenges. is paper proposes LinguTimeX,a new framework that combines natural language processing with arti cial intelligence,along with explainable Arti cial Intelligence(AI)not only to detect CTC but also to provide insights into the decision process.LinguTimeX performs multidimensional feature extraction by fusing linguistic attributes with temporal network patterns to identify covert channels precisely.LinguTimeX demonstrates strong e ectiveness in detecting CTC across multiple languages;namely English,Arabic,and Chinese.Speci cally,the LSTM and RNN models achieved F1 scores of 90%on the English dataset,89%on the Arabic dataset,and 88%on the Chinese dataset,showcasing their superior performance and ability to generalize across multiple languages. is highlights their robustness in detecting CTCs within security systems,regardless of the language or cultural context of the data.In contrast,the DeepForest model produced F1-scores ranging from 86%to 87%across the same datasets,further con rming its e ectiveness in CTC detection.Although other algorithms also showed reasonable accuracy,the LSTM and RNN models consistently outperformed them in multilingual settings,suggesting that deep learning models might be better suited for this particular problem.
基金supported by the Deanship of Scientific Research,Vice Presidency for Graduate Studies and Scientific Research,King Faisal University,Saudi Arabia,Grant No.KFU250098.
文摘In this study,an automated multimodal system for detecting,classifying,and dating fruit was developed using a two-stage YOLOv11 pipeline.In the first stage,the YOLOv11 detection model locates individual date fruits in real time by drawing bounding boxes around them.These bounding boxes are subsequently passed to a YOLOv11 classification model,which analyzes cropped images and assigns class labels.An additional counting module automatically tallies the detected fruits,offering a near-instantaneous estimation of quantity.The experimental results suggest high precision and recall for detection,high classification accuracy(across 15 classes),and near-perfect counting in real time.This paper presents a multi-stage pipeline for date fruit detection,classification,and automated counting,employing YOLOv11-based models to achieve high accuracy while maintaining real-time throughput.The results demonstrated that the detection precision exceeded 90%,the classification accuracy approached 92%,and the counting module correlated closely with the manual tallies.These findings confirm the potential of reducing manual labour and enhancing operational efficiency in post-harvesting processes.Future studies will include dataset expansion,user-centric interfaces,and integration with harvesting robotics.
基金supported by theHubei Provincial Technology Innovation Special Project and the Natural Science Foundation of Hubei Province under Grants 2023BEB024,2024AFC066,respectively.
文摘Underwater images frequently suffer from chromatic distortion,blurred details,and low contrast,posing significant challenges for enhancement.This paper introduces AquaTree,a novel underwater image enhancement(UIE)method that reformulates the task as a Markov Decision Process(MDP)through the integration of Monte Carlo Tree Search(MCTS)and deep reinforcement learning(DRL).The framework employs an action space of 25 enhancement operators,strategically grouped for basic attribute adjustment,color component balance,correction,and deblurring.Exploration within MCTS is guided by a dual-branch convolutional network,enabling intelligent sequential operator selection.Our core contributions include:(1)a multimodal state representation combining CIELab color histograms with deep perceptual features,(2)a dual-objective reward mechanism optimizing chromatic fidelity and perceptual consistency,and(3)an alternating training strategy co-optimizing enhancement sequences and network parameters.We further propose two inference schemes:an MCTS-based approach prioritizing accuracy at higher computational cost,and an efficient network policy enabling real-time processing with minimal quality loss.Comprehensive evaluations on the UIEB Dataset and Color correction and haze removal comparisons on the U45 Dataset demonstrate AquaTree’s superiority,significantly outperforming nine state-of-the-art methods across five established underwater image quality metrics.
文摘The Nanling region is an important nonferrous and rare metal metallogenic province in South China, in which most of the deposits are related to granitoids in genesis. It covers southern Hunan, southern Jiangxi, Guangxi, Guangdong and Fujian provinces, with a total area of about 550,000 km2. This metallogenic province is well known in the world for its rich tungsten and tin resources. In the past 40-odd years, a vast amount of mineral exploration activities and studies of the geology of mineral deposits have been carried out and great achievements obtained in the province. This paper is focused on a discussion about the deep tectonic processes in the orogenic belt during the Mesozoic and their contribution to the superaccumulation of metals. Tectonically, this metallogenic province is composed of three units: (1) the marginal continental orogenic belt in the Southeastern Coast fold system in the Yanshanian; (2) the intercontinental orogenic belt in the collision suture belt between the Yangtze and Cathay-sian plates mainly in the Caledonian; and (3) the intracontinental orogenic belt induced by subduction of the ocean crust and delimination of the mantle lithosphere in the Yanshanian. It is suggested that superaccumulation of metals in this metallogenic province was caused by the existence of mantle rooted tectonics at the depth based on comprehensive studies of geophysical information of seismic, geothermal and magnetotelluric surveys in Nanling and its adjacent areas. The Xihuashan wolframite quartz vein deposit, the Shizhuyuan W, Sn, Mo, Bi greisen-skarn deposit and the Dachang tin-polymetallic deposit are three typical examples of the deep tectonic processes. However, this kind of deep tectonic processes only act as the 'engine' of the superaccumulation of metals, which means that they should have to correspond with the super-crust ore-controlling pattern of 'lines-rows-clusters' (L-R-C). This recog-nization is expected to play an important role in assessment of mineral resources in this province.
基金This study was financed jointly by the Sino Probe Project of China(Sinoprobe-02-01)the National Natural Science Foundation of China(Nos.41430213,41274097,and 41404072)+1 种基金Geological Investigation Project of China Geological Survey(Nos.1212011220260 and 12120115027101)“Urban Active Fault Detection”of National Development and Reform Commission(No.20041138)
文摘The Yinchuan basin,located on the western margin of the Ordos block,has the characteristics of an active continental rift.A NW-striking deep seismic reflection profile across the center of Yinchuan basin precisely revealed the fine structure of the crust.The images showed that the crust in the Yinchuan basin was characterized by vertical stratifications along a detachment located at a two-way travel time(TWT)of 8.0 s.The most outstanding feature of this seismic profile was the almost flat Mohorovicˇic′discontinuity(Moho)and a high-reflection zone in the lower crust.This sub-horizontal Moho conflicts with the general assumption of an uplifted Moho under sedimentary basins and continental rifts,and may indicate the action of different processes at depth during the evolution of sedimentary basins or rifts.We present a possible interpretation of these deep processes and the sub-horizontal Moho.The high-reflection zone,which consists of sheets of high-density,mantlederived materials,may have compensated for crustal thinning in the Yinchuan basin,leading to the formation of a sub-horizontal Moho.These high-density materials may have been emplaced by underplating with mantlesourced magma.
文摘The collision between the Indian and Asian plates uplifted the Himalayan-Tibetan Plateau,thickening and expanding the crust.It is a scientific mystery of global concern as how the two continents collide and how the continent-continent collision deforms the continent.Deep seismic reflection profile detection is one of the most effective ways to unlock this scientific mystery.For more than 20 years using this technology,we have detected fine structures of the thick crust of the Tibetan plateau after overcoming technical bottlenecks to access the lower crust and Moho thus revealing the continental collision processes.This paper systematically summarizes the deep behaviors of the India-Asia collision and subduction beneath the Tibetan Plateau,from south to north,east to west and further into the hinterland of the plateau.The Indian crust undergoes underthrusting beneath the Himalayan orogenic belt on the southern margin of the plateau.Meanwhile,the lithosphere of the Alxa block in the Asian plate subducts southward beneath the Qilian Mountain in the north of the plateau,driving the northward overthrusting of the Qilian crust.Additionally,the Tarim and West Kunlun blocks undergo face-to-face collision in the northwestern margin of the plateau.In the easternmost part of the plateau,the Longriba fault,instead of the Longmen Shan fault zone,marks the western margin of the Yangtze block.It is also seismically evidenced that the Moho geometry in the plateaus hinterland appears thin and flat,indicating lithospheric collapse and extrusion.Multiple deep reflection profiles revealed the collisional behavior under the Yalung-Zangbo suture zone and longitudinal variation in subducting geometry of the Indian crust from west to the east.In the middle of the suture zone,it shows a decoupling between the upper and lower crusts of the Indian plate,where the upper crust undergoes a northward overthrusting while the lower one experiences a northward underthrusting.It is also seismically evidenced a down-and southward crustal duplexing of the subducting Indian crust thickening the northern Himalayas,leaving over a thinning subducting lower crust of the Indian slab.The subduction front of the Indian crust collides with the lower crust of the Asian plate at the mantle depth.A near-vertical collision boundary is seen between the Gangdese batholith and the Tethyan Himalayas,where the Gangdese batholith shows almost transparent weak reflections in the lower crust with localized bright spot reflection that indicates partial melting.Additionally,the near-flat Moho geometry implies an extensional tectonic environment of the southern margin of the Asian plate.
文摘Major defects in forming of conical cups are wrinkles and rupture.Hydrodynamic deep drawing assisted by radial pressure（HDDRP） is a sheet hydroforming process for production of shell cups in one step.In this work,process window diagrams（PWDs） for Al1050-O,pure copper and DIN 1623 St14 steel are obtained for HDDRP process.The PWD is determined to provide a quick assessment of part producibility for sheet hydroforming process.Finite element method is used for this purpose considering the process parameters including pressure path,and the blank material and its thickness.Numerical results are validated by experiments.It is shown that the sheets with less initial thickness and higher strength show better formability and uniformity of thickness distribution on final product.The results demonstrate that the obtained PWD can predict appropriate forming area and probability of rupture or wrinkling occurrence under different pressure loading paths.
基金supported by the National Natural Science Foundation of China(Nos.52034009 and 51974319)the Yue Qi Distinguished Scholar Project(No.2020JCB01)。
文摘The quantitative determination and evaluation of rock brittleness are crucial for the estimation of excavation efficiency and the improvement of hydraulic fracturing efficiency.Therefore,a“three-stage”triaxial loading and unloading stress path is designed and proposed.Subsequently,six brittleness indices are selected.In addition,the evolution characteristics of the six brittleness indices selected are characterized based on the bedding effect and the effect of confining pressure.Then,the entropy weight method(EWM)is introduced to assign weight to the six brittleness indices,and the comprehensive brittleness index Bcis defined and evaluated.Next,the new brittleness classification standard is determined,and the brittleness differences between the two stress paths are quantified.Finally,compared with the previous evaluation methods,the rationality of the proposed comprehensive brittleness index Bcis also verified.These results indicate that the proposed brittleness index Bccan reflect the brittle characteristics of deep bedded sandstone from the perspective of the whole life-cycle evolution process.Accordingly,the method proposed seems to offer reliable evaluations of the brittleness of deep bedded sandstone in deep engineering practices,although further validation is necessary.
基金the National Natural Science Foundation of China(62003298,62163036)the Major Project of Science and Technology of Yunnan Province(202202AD080005,202202AH080009)the Yunnan University Professional Degree Graduate Practice Innovation Fund Project(ZC-22222770)。
文摘Oscillation detection has been a hot research topic in industries due to the high incidence of oscillation loops and their negative impact on plant profitability.Although numerous automatic detection techniques have been proposed,most of them can only address part of the practical difficulties.An oscillation is heuristically defined as a visually apparent periodic variation.However,manual visual inspection is labor-intensive and prone to missed detection.Convolutional neural networks(CNNs),inspired by animal visual systems,have been raised with powerful feature extraction capabilities.In this work,an exploration of the typical CNN models for visual oscillation detection is performed.Specifically,we tested MobileNet-V1,ShuffleNet-V2,Efficient Net-B0,and GhostNet models,and found that such a visual framework is well-suited for oscillation detection.The feasibility and validity of this framework are verified utilizing extensive numerical and industrial cases.Compared with state-of-theart oscillation detectors,the suggested framework is more straightforward and more robust to noise and mean-nonstationarity.In addition,this framework generalizes well and is capable of handling features that are not present in the training data,such as multiple oscillations and outliers.
基金Financial support for carrying out this work was provided by the Shandong Provincial Key Research and Development Program(2018YFJH0802)。
文摘Identification of abnormal conditions is essential in the chemical process.With the rapid development of artificial intelligence technology,deep learning has attracted a lot of attention as a promising fault identification method in chemical process recently.In the high-dimensional data identification using deep neural networks,problems such as insufficient data and missing data,measurement noise,redundant variables,and high coupling of data are often encountered.To tackle these problems,a feature based deep belief networks(DBN)method is proposed in this paper.First,a generative adversarial network(GAN)is used to reconstruct the random and non-random missing data of chemical process.Second,the feature variables are selected by Spearman’s rank correlation coefficient(SRCC)from high-dimensional data to eliminate the noise and redundant variables and,as a consequence,compress data dimension of chemical process.Finally,the feature filtered data is deeply abstracted,learned and tuned by DBN for multi-case fault identification.The application in the Tennessee Eastman(TE)process demonstrates the fast convergence and high accuracy of this proposal in identifying abnormal conditions for chemical process,compared with the traditional fault identification algorithms.
文摘The present paper describes the characteristics of Cenozoic basalt in the Bohaiwan basin and its implication of the control of deep process over the basin evolution. The large scale Eogene basalts lying on the basement of the Bohaiwan basin belong to alkaline series and subalkaline series. The basalt magma originates at a depth of 48-76 km and a temperature of 1 300-1 400 ℃ with the mantle partial melting degree of 8%-14%. In Eogene period, the rising of the top of asthenosphere from 100-140 km to 50-70 km led to the strong extension and thinning of the overlying lithosphere, which was stretched at an average rate of 0.41 cm/a and the β value from 1.9 to 2.3. At the same time, it triggered the great scale rifting in the earth crust, forming large rift basins.
