指示代词“本”与其他结构体的限制性研究

在现代汉语中,“本”是一个很重要的指示代词,它与名词、量词的组合有一定限制性。“本”后面的名词类型,单音节名词占大多数,双音节名词中限于一些表示时间段或表示职务、身份、机构的名词。“本”后面量词的使用类型通常是动量词和集合量词。在“本+量词+名词”结构中的量词具有限制性,一方面要考虑它是否匹配“本”所指代的名词,另一方面还要考虑它在语境中是不是具有内指含义以及是不是说话人所在时间点。

探讨固本通络方基于细菌脂多糖介导的肠B细胞激活对Gd-IgA1的影响

目的探讨固本通络方对IgA肾病小鼠肠道细菌脂多糖(LPS)和糖基化缺陷IgA1(Gd-IgA1)的干预及肾保护作用。方法将36只雄性小鼠分为正常对照组、模型组、固本通络方低剂量组、固本通络方中剂量组、固本通络方高剂量组、依立托仑组。实验采用ddY小鼠构建IgA肾病动物模型,将模型组和各药物组进行造模,中药干预各组分别予以固本通络方免煎颗粒低(13.2 g/kg)、中(26.4 g/kg)、高(52.8 g/kg)3种不同剂量药液灌胃给药,正常对照组和模型组小鼠给予0.9%氯化钠溶液灌胃(10 mL/kg),依立托仑组予以腹腔注射依立托仑药液,各药物组每天给予药物1次,连续8周。干预4周、8周后,测定各组24 h尿蛋白定量;8周测定血清及肠道黏膜LPS、IgA、GdIgA1水平,观察肾脏病理染色及右肾IgA沉积情况,实时荧光定量PCR检测Cosmc基因表达,Western blot法测定Cosmc蛋白表达及IgA肠道菌群特异性,流式细胞术检测肠道B淋巴细胞活化率及分泌IgA前体B淋巴细胞比率,对肠道黏膜组织LPS水平与B细胞活化率及IgA前体B细胞比率行相关性分析。结果固本通络方可降低24 h尿蛋白定量水平及血清肌酐水平(P<0.05)。HE染色发现,与模型组相比,固本通络方用药组肾小球系膜细胞、内皮细胞及基质增生显著减少,肾小球系膜区IgA沉积显著改善;血清及肠道黏膜LPS水平检测发现,与模型组比较,各中药干预组均能降低小鼠血清和肠道黏膜组织LPS、Gd-IgA1和IgA水平(P<0.05);降低B细胞活化率及IgA前体B细胞比率(P<0.05),qRT-PCR和Western blot结果显示固本通络方能够显著降低小鼠粪便培养中菌落蛋白表达水平,上调Cosmc蛋白和Cosmc基因表达水平(P<0.05)。LPS水平与B细胞活化率及IgA前体B细胞比率均呈正相关(P<0.05)。结论固本通络方能有效降低IgA肾病小鼠蛋白尿及血清肌酐水平,减轻肾脏病理损伤及肾小球系膜区IgA沉积,其作用可能和固本通络方降低IgA肾病小鼠血清及肠道LPS水平,降低B淋巴细胞活化率,Cosmc表达上调相关。

金龙固本合剂对哮喘模型大鼠气道重塑及肺组织ET1、TFF2、IL-13表达水平的影响

目的观察金龙固本合剂对哮喘气道重塑大鼠肺组织内皮素1(ET1)、三叶因子2(TFF2)及白细胞介素-13(IL-13)表达水平的影响,并探讨抑制气道重塑的机制。方法将50只雄性大鼠随机分为中药低剂量组(A)、中药高剂量组(B)、地塞米松组(C)、模型对照组(D)、空白对照组(E),共5组,每组10只。腹腔注射卵蛋白致敏液构建大鼠气道重塑模型,观察各组大鼠症状及肺组织病理学形态改变。Western blot法检测肺组织ET1,ELISA法检测各组大鼠支气管肺泡灌洗液(bronchoalveolar lavage fluid,BALF)上清液中TFF2含量,实时荧光定量Q-PCR法检测各组大鼠肺组织IL-13 mRNA表达情况。结果各组大鼠肺组织ET1蛋白相对表达水平:与模型对照组比较,中药低剂量组ET1蛋白表达稍降低,中药高剂量组和地塞米松组ET1蛋白表达呈下降趋势,但差异均无统计学意义。各组大鼠BALF上清液中TFF2含量:与模型对照组比较,中药高剂量组和地塞米松组大鼠BALF上清液中TFF2含量显著降低(P<0.01),中药低剂量组大鼠BALF上清液中TFF2含量呈一定下降趋势,但差异无统计学意义。各组大鼠肺组织IL-13相对表达水平:与模型对照组比较,中药高剂量组大鼠肺组织IL-13 mRNA表达水平显著降低(P<0.05),地塞米松组大鼠肺组织IL-13 mRNA表达水平显著降低(P<0.01),中药低剂量组大鼠肺组织IL-13mRNA表达水平呈明显下降趋势,差异无统计学意义。结论金龙固本合剂可以改善哮喘模型大鼠气道重塑状态,其机制可能与调节ET1、TFF2、IL-13蛋白表达水平有关,为中医药治疗哮喘气道重塑提供理论基础,证明金龙固本合剂治疗哮喘气道重塑具有多途径多靶点的作用,具有临床推广应用的价值。

扶正固本方联合针刺对胃癌患者症状改善及抗氧化机制研究

目的分析扶正固本方联合针刺治疗胃癌的干预改善效果及对氧化应激水平的影响。方法纳入2022年9月—2023年6月医院收治的94例胃癌患者为研究对象,随机将其分为两组,47例对照组采用化疗治疗,47例观察组在此基础上予以扶正固本方联合针刺治疗,对比两组疗效差异、炎症因子水平、氧化应激水平、T细胞亚群指标水平变化情况等。结果观察组客观缓解率为40.43%(19/47),疾病控制率为93.62%(44/47),高于对照组的25.53%(12/47)、76.60%(36/47),组间比较差异有统计学意义(P<0.05);观察组谷胱甘肽过氧化酶(glutathione peroxidase,GSH-Px)、超氧化物歧化酶(superoxide dismutase,SOD)高于对照组,丙二醛(malondialdehyde,MDA)、血清活性氧(reactive oxygen species,ROS)水平低于对照组(P<0.05);观察组干扰素-γ(interferon gamma-γ,IFN-γ)、肿瘤坏死因子-α(tumor necrosis factor-α,TNF-α)高于对照组,白介素细胞-6(interleukin 6,IL-6)、白介素细胞-8(interleukin 8,IL-8)水平低于对照组、CD_(3)^(+)、CD_(4)^(+)/CD_(8)^(+)高于对照组,CD_(4)^(+)低于对照组(P<0.05)。结论对胃癌患者开展扶正固本方联合针刺治疗改善效果明确,有利于减轻机体炎症刺激反应,改善氧化应激水平,提高患者机体免疫功能,调节免疫失衡,对患者预后改善具有积极作用。

基于多任务学习的同行评审细粒度情感分析模型

学术论文同行评审能够直接反映审稿人对论文的主观评价,对审稿文本进行情感分析有利于挖掘审稿人对论文多维度的评价信息。现有的情感分析模型仅能挖掘专家单一的评审维度和相应的情感倾向,本文提出了一种基于多任务学习的同行评审细粒度情感分析模型。该模型在多任务学习框架下,通过在BERT-LCF模型的基础上增加BiLSTM-CRF模块,使其具备了同时完成属性词抽取和细粒度情感分析任务的能力。与传统的基于Pipeline模式的单任务细粒度情感分析模型相比,本模型在保证精度的情况下可以同时完成评审属性提取和情感分析任务。在这两项任务中,所提出模型的F1分数分别达到了89.01%和90.71%。对比实验证明,在多任务场景下,引入BiLSTM-CRF模块对评审文本属性词提取任务有一定的提升作用。

Unveiling the challenges encountered by newly graduated nurses during night shifts:A descriptive qualitative study

Objectives:Newly graduated nurses commence night shifts during a phase of heightened vulnerability to reality shock,exacerbating the challenges faced by these graduates.Therefore,this study aimed to identify the challenges experienced by newly graduated nurses when undertaking night shifts in order to help identify a strategy for supporting their adaptation to these shifts.Methods:Semi-structured personal interviews were used to collect data.Fifteen newly graduated nurses were selected to participate in the study by purposive sampling method from November 2021 to March 2022 in one of four general hospitals situated in the southwestern region of Japan.Semi-structured interviews were analyzed by using thematic analysis.Results:The analysis revealedfive central themes and nine subthemes:challenges in task efficiency(task organization challenges,challenges in time-constrained task performance),challenges in responding to patients’changing conditions(challenges in responding to patients’irregular conditions,challenges in responding to nighttime changes in patients’behaviors),challenges in independent practice(challenges in engaging in independent nursing practice,challenges in dealing with unexpected events),challenges in establishing collaborative relationships(challenges in working closely with other staff,challenges in establishing collaborative relationships during night shifts with limited resources),challenges in adapting to shift work(challenges in managing physical conditions for shift work).Conclusions:Newly graduated nurses often encounter challenges in performing their tasks during the transition period.When working night shifts,they face additional hurdles unique to nocturnal duties.Thefindings underscore the necessity for these graduates to develop night shift-specific readiness to effectively navigate the demands inherent in such work schedules.

Design and implementation of low-cost geomagnetic field monitoring equipment for high-density deployment

The observation of geomagnetic field variations is an important approach to studying earthquake precursors.Since 1987,the China Earthquake Administration has explored this seismomagnetic relationship.In particular,they studied local magnetic field anomalies over the Chinese mainland for earthquake prediction.Owing to the years of research on the seismomagnetic relationship,earthquake prediction experts have concluded that the compressive magnetic effect,tectonic magnetic effect,electric magnetic fluid effect,and other factors contribute to preearthquake magnetic anomalies.However,this involves a small magnitude of magnetic field changes.It is difficult to relate them to the abnormal changes of the extremely large magnetic field in regions with extreme earthquakes owing to the high cost of professional geomagnetic equipment,thereby limiting large-scale deployment.Moreover,it is difficult to obtain strong magnetic field changes before an earthquake.The Tianjin Earthquake Agency has developed low-cost geomagnetic field observation equipment through the Beijing–Tianjin–Hebei geomagnetic equipment test project.The new system was used to test the availability of equipment and determine the findings based on big data..

《广韵》206韵来源考

《广韵》206韵是怎么来的?历来聚讼纷纭,经分类详列各家的观点,再比较现有材料,得出结论如下:《广韵》是以开元本孙愐《唐韵》204韵,再加上敦煌本王仁昫《刊谬补缺切韵》上声五十一广与去声五十六严两韵而来的;《广韵》的韵数发展历程应为“193-204-206”,而非其他。

Ultrafast pulse wave velocity technique for evaluating changes of carotid artery elasticity in Hashimoto thyroiditis patients with euthyroidism

Objective To explore the value of ultrafast pulse wave velocity(UFPWV)technique for evaluating changes of carotid artery elasticity in Hashimoto thyroiditis(HT)patients with euthyroidism.Methods Conventional ultrasound and UFPWV for carotid artery were prospectively performed in 91 HT patients with euthyroidism(HT group)and 81 healthy subjects(control group).Clinical data and ultrasonic parameters were compared between groups.Spearman correlation analysis was performed to observe the correlations of carotid pulse wave velocity in end of systole(PWV-ES)with clinical indexes and other ultrasonic parameters in HT group.Multiple stepwise linear regression analysis was used to screen the independent impact factors of increased carotid PWV-ES in HT group.Results Significant differences of thyroid peroxidase antibody(TPOAb),thyroglobulin antibody(TgAb),total cholesterol(TC),low density lipoprotein and neutrophil-lymphocyte ratio(NLR)were found between groups(all P<0.05).The carotid PWV-ES in HT group was significantly higher than that in control group(P<0.05),while no significant difference of carotid artery intima-media thickness(CIMT)nor carotid pulse wave velocity in beginning of systole(PWV-BS)was found between groups(both P>0.05).Carotid PWV-ES in HT group was positively correlated with patients'age,body mass index,TPOAb,TC,triglyceride,NLR and CIMT(r=0.217—0.707,all P<0.05).Patients'age,TPOAb and NLR were all independent impact factors of increased carotid PWV-ES in HT patients with euthyroidism(all P<0.05).Conclusion UFPWV technique could be used to evaluate changes of carotid artery elasticity in HT patients with euthyroidism,among which PWV-ES was relatively sensitive.

A whole process damage constitutive model for layered sandstone under uniaxial compression based on Logistic function

Bedding structural planes significantly influence the mechanical properties and stability of engineering rock masses.This study conducts uniaxial compression tests on layered sandstone with various bedding angles(0°,15°,30°,45°,60°,75°and 90°)to explore the impact of bedding angle on the deformational mechanical response,failure mode,and damage evolution processes of rocks.It develops a damage model based on the Logistic equation derived from the modulus’s degradation considering the combined effect of the sandstone bedding dip angle and load.This model is employed to study the damage accumulation state and its evolution within the layered rock mass.This research also introduces a piecewise constitutive model that considers the initial compaction characteristics to simulate the whole deformation process of layered sandstone under uniaxial compression.The results revealed that as the bedding angle increases from 0°to 90°,the uniaxial compressive strength and elastic modulus of layered sandstone significantly decrease,slightly increase,and then decline again.The corresponding failure modes transition from splitting tensile failure to slipping shear failure and back to splitting tensile failure.As indicated by the modulus’s degradation,the damage characteristics can be categorized into four stages:initial no damage,damage initiation,damage acceleration,and damage deceleration termination.The theoretical damage model based on the Logistic equation effectively simulates and predicts the entire damage evolution process.Moreover,the theoretical constitutive model curves closely align with the actual stress−strain curves of layered sandstone under uniaxial compression.The introduced constitutive model is concise,with fewer parameters,a straightforward parameter determination process,and a clear physical interpretation.This study offers valuable insights into the theory of layered rock mechanics and holds implications for ensuring the safety of rock engineering.

The Use of Hand Stamps in the Manuscript Maps Drawn by East Asian Countries in the Eighteenth and Nineteenth Centuries

It was generally accepted that manuscript maps,as distinct from printed maps,exhibited no signs of printing and were entirely hand-drawn.Western scholars Christopher Terrell and Tony Campbell were the first to break this stereotype in 1987,followed by Catherine Delano-Smith and Chet Van Duzer who discovered a few Renaissance maps and two Qing dynasty maps that showed use of hand stamps.Inspired by these findings,this paper explores the stamped map signs in ten Chinese maps,three Japanese maps,and three Korean maps.By analyzing each map and each type of stamp,this paper provides more examples of this research,broadens the research horizons and geographical area,and demonstrates that use of stamps in manuscript maps was invented independently among people of different regions and civilizations as a result of human nature.

固本保真汤治疗气阴两虚型癌因性疲乏的临床研究

目的评价固本保真汤治疗气阴两虚型癌因性疲乏(cancer-related fatigue,CRF)临床疗效。方法将60例气阴两虚型CRF患者随机分为治疗组和对照组。对照组予基础治疗,指导患者合理作息、适当运动锻炼、心理指导等,必要时予以止痛、止呕、纠正水电解质紊乱等对症处理。治疗组在对照组的基础上给予固本保真汤治疗。比较两组治疗前后Piper疲乏量表、卡氏评分量表、中医证候积分和免疫指标变化情况,对疗效数据进行分析总结。结果①Piper疲乏量表比较:治疗组和对照组在第4周和第8周均出现显著改善(P<0.05),但治疗组优于对照组(P<0.05)。②卡氏评分量表比较:治疗组第4周评分变化无统计学意义,第8周时评分变化有统计学意义(P<0.05);对照组在第4周和第8周评分变化均无统计学意义(P>0.05)。③中医证候积分比较:治疗8周后治疗组的总有效率为86.67%(26/30),对照组的总有效率为26.67%(8/30),治疗组显著优于对照组,差异有统计学意义(P<0.05)。④免疫指标比较:治疗组CD_(3)^(+)、CD_(4)^(+)、CD_(8)^(+)、自然杀伤细胞(natural killer cell,NK)均有所升高,其中CD_(4)^(+)、CD_(8)^(+)的升高具有统计学意义(P<0.05)。对照组的CD_(8)^(+)较前升高具有统计学意义(P<0.05),余均无改善。提示治疗组的免疫指标改善优于对照组。结论固本保真汤在治疗气阴两虚型癌因性疲乏疗效确切,患者疲乏、体力状况均有良好改善作用,且安全性良好,值得临床推广和使用。

Novel damage constitutive models and new quantitative identification method for stress thresholds of rocks under uniaxial compression

Four key stress thresholds exist in the compression process of rocks,i.e.,crack closure stress(σ_(cc)),crack initiation stress(σ_(ci)),crack damage stress(σ_(cd))and compressive strength(σ_(c)).The quantitative identifications of the first three stress thresholds are of great significance for characterizing the microcrack growth and damage evolution of rocks under compression.In this paper,a new method based on damage constitutive model is proposed to quantitatively measure the stress thresholds of rocks.Firstly,two different damage constitutive models were constructed based on acoustic emission(AE)counts and Weibull distribution function considering the compaction stages of the rock and the bearing capacity of the damage element.Then,the accumulative AE counts method(ACLM),AE count rate method(CRM)and constitutive model method(CMM)were introduced to determine the stress thresholds of rocks.Finally,the stress thresholds of 9 different rocks were identified by ACLM,CRM,and CMM.The results show that the theoretical stress−strain curves obtained from the two damage constitutive models are in good agreement with that of the experimental data,and the differences between the two damage constitutive models mainly come from the evolutionary differences of the damage variables.The results of the stress thresholds identified by the CMM are in good agreement with those identified by the AE methods,i.e.,ACLM and CRM.Therefore,the proposed CMM can be used to determine the stress thresholds of rocks.

A Study on Short Text Matching Method Based on KS-BERT Algorithm

To improve the accuracy of short text matching,a short text matching method with knowledge and structure enhancement for BERT(KS-BERT)was proposed in this study.This method first introduced external knowledge to the input text,and then sent the expanded text to both the context encoder BERT and the structure encoder GAT to capture the contextual relationship features and structural features of the input text.Finally,the match was determined based on the fusion result of the two features.Experiment results based on the public datasets BQ_corpus and LCQMC showed that KS-BERT outperforms advanced models such as ERNIE 2.0.This Study showed that knowledge enhancement and structure enhancement are two effective ways to improve BERT in short text matching.In BQ_corpus,ACC was improved by 0.2%and 0.3%,respectively,while in LCQMC,ACC was improved by 0.4%and 0.9%,respectively.

Dynamic evaluation of digital and green development policies based on text mining of the PMC framework

Aiming to identify policy topics and their evolutionary logic that enhance the digital and green development(dual development)of traditional manufacturing enterprises,address weaknesses in current policies,and provide resources for refining dual development policies,a total of 15954 dual development-related policies issued by national and various departmental authorities in China from January 2000 to August 2023 were analyzed.Based on topic modeling techniques and the policy modeling consistency(PMC)framework,the evolution of policy topics was visualized,and a dynamic assessment of the policies was conducted.The results show that the digital and green development policy framework is progressively refined,and the governance philosophy shifts from a“regulatory government”paradigm to a“service-oriented government”.The support pattern evolves from“dispersed matching”to“integrated symbiosis”.However,there are still significant deficiencies in departmental cooperation,balanced measures,coordinated links,and multi-stakeholder participation.Future policy improvements should,therefore,focus on guiding multi-stakeholder participation,enhancing public demand orientation,and addressing the entire value chain.These steps aim to create an open and shared digital industry ecosystem to promote the coordinated dual development of traditional manufacturing enterprises.

Data-driven methods for predicting the representative temperature of bridge cable based on limited measured data

Cable-stayed bridges have been widely used in high-speed railway infrastructure.The accurate determination of cable’s representative temperatures is vital during the intricate processes of design,construction,and maintenance of cable-stayed bridges.However,the representative temperatures of stayed cables are not specified in the existing design codes.To address this issue,this study investigates the distribution of the cable temperature and determinates its representative temperature.First,an experimental investigation,spanning over a period of one year,was carried out near the bridge site to obtain the temperature data.According to the statistical analysis of the measured data,it reveals that the temperature distribution is generally uniform along the cable cross-section without significant temperature gradient.Then,based on the limited data,the Monte Carlo,the gradient boosted regression trees(GBRT),and univariate linear regression(ULR)methods are employed to predict the cable’s representative temperature throughout the service life.These methods effectively overcome the limitations of insufficient monitoring data and accurately predict the representative temperature of the cables.However,each method has its own advantages and limitations in terms of applicability and accuracy.A comprehensive evaluation of the performance of these methods is conducted,and practical recommendations are provided for their application.The proposed methods and representative temperatures provide a good basis for the operation and maintenance of in-service long-span cable-stayed bridges.

Ground response and failure mechanism of gob-side entry by roof cutting with hard main roof

This study is the result of long-term efforts of the authors’team to assess ground response of gob-side entry by roof cutting(GSERC)with hard main roof,aiming at scientific control for GSERC deformation.A comprehensive field measurement program was conducted to determine entry deformation,roof fracture zone,and anchor bolt(cable)loading.The results indicate that GSERC deformation presents asymmetric characteristics.The maximum convergence near roof cutting side is 458 mm during the primary use process and 1120 mm during the secondary reuse process.The entry deformation is closely associated with the primary development stage,primary use stage,and secondary reuse stage.The key block movement of roof cutting structure,a complex stress environment,and a mismatch in the supporting design scheme are the failure mechanism of GSERC.A controlling ideology for mining states,including regional and stage divisions,was proposed.Both dynamic and permanent support schemes have been implemented in the field.Engineering practice results indicate that the new support scheme can efficiently ensure long-term entry safety and could be a reliable approach for other engineering practices.

On the beginning of the Japanese Upper Paleolithic:A review of recent archaeological and anthropological evidence

The beginning of the Japanese Upper Paleolithic has mainly been examined using two major models:the Middle Paleolithic evolutionary model within the archipelago and the continental Upper Paleolithic diffusion/migration model.However,recent archeological data from Japan and nearby countries are challenging such simple models.This paper critically reviews previous chronology of the Japanese Paleolithic,including possible Lower and Middle Paleolithic(LP/MP),and attempts to show an alternative model of the beginning of the Japanese Upper Paleolithic.This paper suggests several possible specimens of LP/MP and recommends further geoarchaeological investigation to understand the reliability and cultural relationship between possible LP/MP specimens and the Early Upper Paleolithic(EUP).The start of the Japanese EUP is presently characterized by a flake industry with trapezoids and denticulates around 39-37 kaBP cal on Paleo-Honshu Island,which has partial resemblance with contemporary assemblages in China and the Korean Peninsula,although trapezoids are endemic only to the Japanese EUP and may have derived from the ancestral lithic tradition.Blade technology appeared earliest on Central Paleo-Honshu Island,about 1000 years later than the earliest flake technology.Although blade technology may have originated from the elongated flake technology of the previous period,the sudden simultaneous emergence implies that it diffused from the Korean Peninsula.This paper proposes that blade technology from the Korean Peninsula arrived on the northeastern Paleo-Honshu Island,including the Japan Sea coastal region of western Honshu,rather than the southwest,where flake technology long prospered,due to differences in ecological settings and adaptation strategies between the two regions.

Region-Aware Fashion Contrastive Learning for Unified Attribute Recognition and Composed Retrieval

Clothing attribute recognition has become an essential technology,which enables users to automatically identify the characteristics of clothes and search for clothing images with similar attributes.However,existing methods cannot recognize newly added attributes and may fail to capture region-level visual features.To address the aforementioned issues,a region-aware fashion contrastive language-image pre-training(RaF-CLIP)model was proposed.This model aligned cropped and segmented images with category and multiple fine-grained attribute texts,achieving the matching of fashion region and corresponding texts through contrastive learning.Clothing retrieval found suitable clothing based on the user-specified clothing categories and attributes,and to further improve the accuracy of retrieval,an attribute-guided composed network(AGCN)as an additional component on RaF-CLIP was introduced,specifically designed for composed image retrieval.This task aimed to modify the reference image based on textual expressions to retrieve the expected target.By adopting a transformer-based bidirectional attention and gating mechanism,it realized the fusion and selection of image features and attribute text features.Experimental results show that the proposed model achieves a mean precision of 0.6633 for attribute recognition tasks and a recall@10(recall@k is defined as the percentage of correct samples appearing in the top k retrieval results)of 39.18 for composed image retrieval task,satisfying user needs for freely searching for clothing through images and texts.

Prediction of Hot Deformation Behavior of 7Mo Super Austenitic Stainless Steel Based on Back Propagation Neural Network

The hot compression tests of 7Mo super austenitic stainless(SASS)were conducted to obtain flow curves at the temperature of 1000-1200℃and strain rate of 0.001 s^(-1)to 1 s^(-1).To predict the non-linear hot deformation behaviors of the steel,back propagation-artificial neural network(BP-ANN)with 16×8×8 hidden layer neurons was proposed.The predictability of the ANN model is evaluated according to the distribution of mean absolute error(MAE)and relative error.The relative error of 85%data for the BP-ANN model is among±5%while only 42.5%data predicted by the Arrhenius constitutive equation is in this range.Especially,at high strain rate and low temperature,the MAE of the ANN model is 2.49%,which has decreases for 18.78%,compared with conventional Arrhenius constitutive equation.