期刊文献+
共找到551篇文章
< 1 2 28 >
每页显示 20 50 100
Digital modulation classification using multi-layer perceptron and time-frequency features
1
作者 Yuan Ye Mei Wenbo 《Journal of Systems Engineering and Electronics》 SCIE EI CSCD 2007年第2期249-254,共6页
Considering that real communication signals corrupted by noise are generally nonstationary, and timefrequency distributions are especially suitable for the analysis of nonstationary signals, time-frequency distributio... Considering that real communication signals corrupted by noise are generally nonstationary, and timefrequency distributions are especially suitable for the analysis of nonstationary signals, time-frequency distributions are introduced for the modulation classification of communication signals: The extracted time-frequency features have good classification information, and they are insensitive to signal to noise ratio (SNR) variation. According to good classification by the correct rate of a neural network classifier, a multilayer perceptron (MLP) classifier with better generalization, as well as, addition of time-frequency features set for classifying six different modulation types has been proposed. Computer simulations show that the MLP classifier outperforms the decision-theoretic classifier at low SNRs, and the classification experiments for real MPSK signals verify engineering significance of the MLP classifier. 展开更多
关键词 Digital modulation classification Time-frequency feature Time-frequency distribution multi-layer perceptron.
在线阅读 下载PDF
An improved model for predicting thermal contact resistance at multi-layered rock interface
2
作者 WEN Min-jie XIE Jia-hao +4 位作者 LI Li-chen TIAN Yi EL NAGGAR M.Hesham MEI Guo-xiong WU Wen-bing 《Journal of Central South University》 2025年第1期229-243,共15页
This study proposes a general imperfect thermal contact model to predict the thermal contact resistance at the interface among multi-layered composite structures.Based on the Green-Lindsay(GL)thermoelastic theory,semi... This study proposes a general imperfect thermal contact model to predict the thermal contact resistance at the interface among multi-layered composite structures.Based on the Green-Lindsay(GL)thermoelastic theory,semi analytical solutions of temperature increment and displacement of multi-layered composite structures are obtained by using the Laplace transform method,upon which the effects of thermal resistance coefficient,partition coefficient,thermal conductivity ratio and heat capacity ratio on the responses are studied.The results show that the generalized imperfect thermal contact model can realistically describe the imperfect thermal contact problem.Accordingly,it may degenerate into other thermal contact models by adjusting the thermal resistance coefficient and partition coefficient. 展开更多
关键词 multi-layered structures general thermal contact model thermal contact resistance GL thermoelastic theory Laplace transform
在线阅读 下载PDF
Experimental investigation on dynamic stab resistance of highperformance multi-layer textile materials
3
作者 Mulat Alubel Abtew François Boussu +1 位作者 Irina Cristian Bekinew Kitaw Dejene 《Defence Technology(防务技术)》 2025年第5期1-14,共14页
Stab-resistant textiles play a critical role in personal protection,necessitating a deeper understanding of how structural and layering factors influence their performance.The current study experimentally examines the... Stab-resistant textiles play a critical role in personal protection,necessitating a deeper understanding of how structural and layering factors influence their performance.The current study experimentally examines the effects of textile structure,layering,and ply orientation on the stab resistance of multi-layer textiles.Three 3D warp interlock(3DWI)structures({f1},{f2},{f3})and a 2D woven fabric({f4}),all made of high-performance p-aramid yarns,were engineered and manufactured.Multi-layer specimens were prepared and subjected to drop-weight stabbing tests following HOSBD standards.Stabbing performance metrics,including Depth of Trauma(DoT),Depth of Penetration(DoP),and trauma deformation(Ymax,Xmax),were investigated and analyzed.Statistical analyses(Two-and One-Way ANOVA)indicated that fabric type and layer number significantly impacted DoP(P<0.05),while ply orientation significantly affected DoP(P<0.05)but not DoT(P>0.05).Further detailed analysis revealed that 2D woven fabrics exhibited greater trauma deformation than 3D WIF structures.Increasing the number of layers reduced both DoP and DoT across all fabric structures,with f3 demonstrating the best performance in multi-layer configurations.Aligned ply orientations also enhanced stab resistance,underscoring the importance of alignment in dissipating impact energy. 展开更多
关键词 2D/3D woven fabrics High-performance fibers Protective textiles multi-layer panels Impact ply orientation Dynamic stab resistance
在线阅读 下载PDF
Damage of multi-layer spaced metallic target plates impacted by radial layered PELE 被引量:10
4
作者 Chun Cheng Zhong-hua Du +4 位作者 Xi Chen Li-zhi Xu Cheng-xin Du Ji-long Han Xiao-dong Wang 《Defence Technology(防务技术)》 SCIE EI CAS CSCD 2020年第1期201-207,共7页
Three different kinds of PELE(the penetrator with lateral efficiency) were launched by ballistic artillery to impact the multi-layer spaced metal target plates.The lmpact velocities of the projectiles were measured by... Three different kinds of PELE(the penetrator with lateral efficiency) were launched by ballistic artillery to impact the multi-layer spaced metal target plates.The lmpact velocities of the projectiles were measured by the velocity measuring system.The damage degree and process of each laye r of target plate impacted by the three kinds of projectiles were analyzed.The experimental results show that all the three kinds of projectiles have the effect of expanding holes on the multi-layer spaced metal target plates.For the normal structure PELE(without layered) with tungsten alloy jacket and the radial layered PELE with tungsten alloy jacket,the diameters of holes on the seco nd layer of plates are 3.36 times and 3.76 times of the diameter of the projectile,re spectively.For radial layered PELE with W/Zr-based amorphous composite jacket,due to the large number of tungsten wires dispersed after the impact,the diameter of the holes on the four-layer spaced plates can reach 2.4 times,3.04 times,5.36 times and 2.68 times of the diameter of the projectile.Besides,the normal structure PELE with tungsten alloy jacket and the radial layered PELE whit tungsten alloy jacket formed a large number of fragments impact marks on the third target plate.Although the number of fragments penetrating the third target plate is not as large as that of the normal structure PELE,the area of dispersion of fragments impact craters on the third target plate is larger by the radial layered PELE.The radial layered PELE with W/Zr-based amorphous composite jacket released a lot of heat energy due to the impact of the matrix material,and formed a large area of ablation marks on the last three target plates. 展开更多
关键词 PELE(the PENETRATOR with lateral efficiency) multi-layer spaced metal TARGET PLATES Impact DAMAGE
在线阅读 下载PDF
Simulation of thermal field induced by concave spherical transducer in multi-layer media 被引量:5
5
作者 丁亚军 钱盛友 廖志远 《Journal of Central South University》 SCIE EI CAS 2013年第11期3166-3170,共5页
High intensity focused ultrasound(HIFU)therapy is an effective method in clinical treatment of tumors,in order to explore the bio-heat conduction mechanism of in multi-layer media by concave spherical transducer,tempe... High intensity focused ultrasound(HIFU)therapy is an effective method in clinical treatment of tumors,in order to explore the bio-heat conduction mechanism of in multi-layer media by concave spherical transducer,temperature field induced by this kind of transducer in multi-layer media will be simulated through solving Pennes equation with finite difference method,and the influence of initial sound pressure,absorption coefficient,and thickness of different layers of biological tissue as well as thermal conductivity parameter on sound focus and temperature distribution will be analyzed,respectively.The results show that the temperature in focus area increases faster while the initial sound pressure and thermal conductivity increase.The absorption coefficient is smaller,the ultrasound intensity in the focus area is bigger,and the size of the focus area is increasing.When the thicknesses of different layers of tissue change,the focus position changes slightly,but the sound intensity of the focus area will change obviously.The temperature in focus area will rise quickly before reaching a threshold,and then the temperature will keep in the threshold range. 展开更多
关键词 multi-layer media concave spherical transducer high intensity focused ultrasound thermal field
在线阅读 下载PDF
Numerical simulation analysis on multi-layer low-temperature heating method of asphalt pavement in hot in-place recycling 被引量:4
6
作者 MA Deng-cheng LAN Fen 《Journal of Central South University》 SCIE EI CAS CSCD 2020年第12期3793-3806,共14页
Asphalt mixture pavement reheating is one of the important steps in hot in-place recycling(HIR).To improve the heating speed of asphalt pavement in HIR,based on the numerical analysis model of asphalt mixture heating ... Asphalt mixture pavement reheating is one of the important steps in hot in-place recycling(HIR).To improve the heating speed of asphalt pavement in HIR,based on the numerical analysis model of asphalt mixture heating process,a new multi-layer low-temperature heating method(MLHM)was proposed.Considering input heat flux,the thermal capacity and thermal resistance of asphalt mixture,the heat transfer model was established based on energy conservation law.By heating the asphalt mixture in layers,it changes the situation that the heat energy can only be input from the upper surface of the asphalt mixture pavement.Through the simulation of the heating method of asphalt mixture in the existing technology,the result shows that the existing heating methods lead to serious aging or charring of the asphalt mixture.By MLHM,the upper and the bottom of the asphalt mixture are heated at the same time,and the heating temperature is lower than other heat methods,which not only reduces the heating thickness and increases the heating area of the asphalt mixture pavement,but also improves the heating speed,saves the energy resource and ensures the heating quality.Especially,by MLHM,the heating uniformity is better and speed is faster. 展开更多
关键词 asphalt pavement hot in-place recycling heating speed heating uniformity multi-layer LOW-TEMPERATURE
在线阅读 下载PDF
Limit analysis of ultimate uplift capacity and failure mechanism ofshallow plate anchors in multi-layered soils 被引量:2
7
作者 LYU Cheng WANG Zhu-hong +1 位作者 ZENG Zheng-qiang ZHANG Xiao 《Journal of Central South University》 SCIE EI CAS CSCD 2022年第6期2049-2061,共13页
Considering the fact that in some complex cases,plate anchors are buried in multi-layered geotechnical materials,the ultimate dynamic analysis was performed to investigate the uplift capacity and failure mechanism of ... Considering the fact that in some complex cases,plate anchors are buried in multi-layered geotechnical materials,the ultimate dynamic analysis was performed to investigate the uplift capacity and failure mechanism of shallow strips and circular plate anchors in multi-layered soils.The nonlinear strength criterion and non-associated flow rule of geotechnical materials were introduced to investigate the influence of nonuniformity on the pullout performance and failure mechanism of shallow plate anchors.The expressions of the detaching curves or surfaces were obtained to reflect the failure mechanism,which can be used to figure out the ultimate uplift capacity and failure range.The results are generally in agreement with the numerical simulations and previous research.The effects of various parameters on the ultimate uplift capacity and failure mechanism of plate anchors in multi-layered soils were investigated,and it is found that the ultimate uplift capacity and failure range of shallow anchors increase with the increase of initial cohesion and dilatancy coefficient,but decrease with the unit weight,axial tensile stress and nonlinear coefficient. 展开更多
关键词 limit analysis dilatancy coefficient ultimate uplift capacity plate anchors multi-layered soils
在线阅读 下载PDF
New multi-layer data correlation algorithm for multi-passive-sensor location system 被引量:1
8
作者 Zhou Li Li Lingyun He You 《Journal of Systems Engineering and Electronics》 SCIE EI CSCD 2007年第4期667-672,共6页
Under the scenario of dense targets in clutter, a multi-layer optimal data correlation algorithm is proposed. This algorithm eliminates a large number of false location points from the assignment process by rough corr... Under the scenario of dense targets in clutter, a multi-layer optimal data correlation algorithm is proposed. This algorithm eliminates a large number of false location points from the assignment process by rough correlations before we calculate the correlation cost, so it avoids the operations for the target state estimate and the calculation of the correlation cost for the false correlation sets. In the meantime, with the elimination of these points in the rough correlation, the disturbance from the false correlations in the assignment process is decreased, so the data correlation accuracy is improved correspondingly. Complexity analyses of the new multi-layer optimal algorithm and the traditional optimal assignment algorithm are given. Simulation results show that the new algorithm is feasible and effective. 展开更多
关键词 multi-passive-sensor data correlation multi-layer correlation algorithm location system correlation cost
在线阅读 下载PDF
Blast wave characteristics of multi-layer composite charge:Theoretical analysis,numerical simulation,and experimental validation 被引量:1
9
作者 Jun-bao Li Wei-bing Li +2 位作者 Xiao-wen Hong Jia-xin Yu Jian-jun Zhu 《Defence Technology(防务技术)》 SCIE EI CAS CSCD 2023年第1期91-102,共12页
This article investigates the characteristics of shock wave overpressure generated by multi-layer composite charge under different detonation modes.Combining dimensional analysis and the explosion mechanism of the cha... This article investigates the characteristics of shock wave overpressure generated by multi-layer composite charge under different detonation modes.Combining dimensional analysis and the explosion mechanism of the charge,a peak overpressure prediction model for the composite charge under singlepoint detonation and simultaneous detonation was established.The effects of the charge structure and initiation method on the overpressure field characteristics were investigated in AUTODYN simulation.The accuracy of the prediction model and the reliability of the numerical simulation method were subsequently verified in a series of static explosion experiments.The results reveal that the mass of the inner charge was the key factor determining the peak overpressure of the composite charge under single-point detonation.The peak overpressure in the radial direction improved apparently with an increase in the aspect ratio of the charge.The overpressure curves in the axial direction exhibited a multi-peak phenomenon,and the secondary peak overpressure even exceeded the primary peak at distances of 30D and 40D(where D is the charge diameter).The difference in peak overpressure among azimuth angles of 0-90°gradually decreased with an increase in the propagation distance of the shock wave.The coupled effect of the detonation energy of the inner and outer charge under simultaneous detonation improved the overpressure in both radial and axial directions.The difference in peak overpressure obtained from model prediction and experimental measurements was less than 16.4%. 展开更多
关键词 Blast wave characteristics multi-layer composite charge Dimensional analysis AUTODYN mapping Model Explosion experiment
在线阅读 下载PDF
Application of response surface method for optimal transfer conditions of multi-layer ceramic capacitor alignment system
10
作者 PARK Su-seong KIM Jae-min +1 位作者 CHUNG Won-jee SHIN O-chul 《Journal of Central South University》 SCIE EI CAS 2011年第3期726-730,共5页
The multi-layer ceramic capacitor (MLCC) alignment system aims at the inter-process automation between the first and the second plastic processes.As a result of testing performance verification of MLCC alignment syste... The multi-layer ceramic capacitor (MLCC) alignment system aims at the inter-process automation between the first and the second plastic processes.As a result of testing performance verification of MLCC alignment system,the average alignment rates are 95% for 3216 chip,88.5% for 2012 chip and 90.8% for 3818 chip.The MLCC alignment system can be accepted for practical use because the average manual alignment is just 80%.In other words,the developed MLCC alignment system has been upgraded to a great extent,compared with manual alignment.Based on the successfully developed MLCC alignment system,the optimal transfer conditions have been explored by using RSM.The simulations using ADAMS has been performed according to the cube model of CCD.By using MiniTAB,the model of response surface has been established based on the simulation results.The optimal conditions resulted from the response optimization tool of MiniTAB has been verified by being assigned to the prototype of MLCC alignment system. 展开更多
关键词 multi-layer ceramic capacitor (MLCC) alignment system response surface method (RSM) MiniTAB ADAMS
在线阅读 下载PDF
简单Perceptron学习算法的收敛性
11
作者 冯建峰 《北京大学学报(自然科学版)》 CAS CSCD 北大核心 1995年第1期20-27,共8页
当输入是无穷集或区域时,通过构造一个上鞅,本文证明了简单Perceptron学习算法的收敛性。
关键词 上鞅 线性可分 收敛 随机过程
在线阅读 下载PDF
Building up Multi-Layered Perceptrons as Classifier System for Decision Support
12
作者 Cat Jun, Zhai Fan & Feng Shan (Inst. of Sys. Eng., Huazhong University of Science and Technology, Wuhan 430074, China) 《Journal of Systems Engineering and Electronics》 SCIE EI CSCD 1995年第2期32-39,共8页
This paper focuses on some application issues in m.multi-layered perceptrons researches. The following problem areas are discussed: (1) the classification capability of multi-layered perceptrons; (2) theself-configura... This paper focuses on some application issues in m.multi-layered perceptrons researches. The following problem areas are discussed: (1) the classification capability of multi-layered perceptrons; (2) theself-configuration algorithm for facilitating the design of the neural nets' structure;and,finally (3) the application of the fast BP algorithm to speed up the learning procedure. Some experimental results with respect to the application of multi-layered perceptrons as classifier systems in the comprehensive evaluation of Chinese large cities are presented. 展开更多
关键词 multi-layered perceptron Decision support system Classification ability SELF-CONFIGURATION Comprehensive evaluation.
在线阅读 下载PDF
A Hybrid Learning Method for Multilayer Perceptrons 被引量:1
13
作者 Zhon Meide Huang Wenhu Hong Jiarong (School of Astronautics) 《哈尔滨工业大学学报》 EI CAS CSCD 北大核心 1990年第3期52-61,共10页
A Newton learning method for a neural network of multilayer perceptrons is proposed in this paper. Furthermore, a hybrid learning method id legitimately developed in combination of the backpropagation method proposed ... A Newton learning method for a neural network of multilayer perceptrons is proposed in this paper. Furthermore, a hybrid learning method id legitimately developed in combination of the backpropagation method proposed by Rumelhart et al with the Newton learning method. Finally, the hybrid learning algorithm is compared with the backpropagation algorithm by some illustrations, and the results show that this hybrid leaming algorithm bas the characteristics of rapid convergence. 展开更多
关键词 计算机 多层感知机 牛顿线性方法 神经网络 增殖算法
在线阅读 下载PDF
Fast lossless color image compression method using perceptron
14
作者 JiaKebin ZhangYanhua ZhuangXinyue 《Journal of Systems Engineering and Electronics》 SCIE EI CSCD 2004年第2期190-196,共7页
The technique of lossless image compression plays an important role in image transmission and storage for high quality. At present, both the compression ratio and processing speed should be considered in a real-time m... The technique of lossless image compression plays an important role in image transmission and storage for high quality. At present, both the compression ratio and processing speed should be considered in a real-time multimedia system. A novel lossless compression algorithm is researched. A low complexity predictive model is proposed using the correlation of pixels and color components. In the meantime, perceptron in neural network is used to rectify the prediction values adaptively. It makes the prediction residuals smaller and in a small dynamic scope. Also a color space transform is used and good decorrelation is obtained in our algorithm. The compared experimental results have shown that our algorithm has a noticeably better performance than traditional algorithms. Compared to the new standard JPEG-LS, this predictive model reduces its computational complexity. And its speed is faster than the JPEG-LS with negligible performance sacrifice. 展开更多
关键词 lossless compression perceptron prediction model correlation.
在线阅读 下载PDF
水平井钻进中页岩小层结构元素录井智能实时识别
15
作者 夏国勇 彭仕轩 +5 位作者 陆林超 欧成华 权昊森 倪根生 邱前程 马韶光 《断块油气田》 北大核心 2025年第3期508-513,共6页
当前,水平井钻进中页岩小层结构需要依靠导向师利用元素录井曲线特征人工识别,常因页岩小层厚度小、导向师经验不足,井底位置判断失误,造成水平井出靶。为此,建立了页岩小层结构元素录井智能实时识别技术。该技术输入元素录井数据,利用... 当前,水平井钻进中页岩小层结构需要依靠导向师利用元素录井曲线特征人工识别,常因页岩小层厚度小、导向师经验不足,井底位置判断失误,造成水平井出靶。为此,建立了页岩小层结构元素录井智能实时识别技术。该技术输入元素录井数据,利用残差多层感知机算法,采用“1+u”个算法模型,依靠从页岩小层到小层结构的二级识别策略,实施水平井钻进中页岩小层结构元素录井的智能实时识别。此外,设计了以当前井元素数据为核心、迭代式更新计算的“一次训练,一次预测”工作流程,以适应不同地域、同一页岩小层元素特征间的差异性。应用该技术完成了川南泸州页岩气区的水平井钻进导向,证实了技术的可靠性、适用性、实时性,以及相较于人工分析的优越性。 展开更多
关键词 水平井 地质导向 元素录井 小层识别 残差多层感知机
在线阅读 下载PDF
基于HHO-MLP神经网络的变工况下齿轮箱故障诊断方法研究
16
作者 蒋章雷 郑威 +3 位作者 门大超 刘秀丽 查振栋 李子涵 《制造技术与机床》 北大核心 2025年第5期29-35,共7页
针对变工况下齿轮箱故障信号复杂多变导致故障诊断困难的问题,提出了一种基于哈里斯鹰优化器(Harris hawk optimizer,HHO)优化多层感知机(multi-layer perception,MLP)神经网络的故障诊断方法。首先,采用均方根-均值(root mean square-m... 针对变工况下齿轮箱故障信号复杂多变导致故障诊断困难的问题,提出了一种基于哈里斯鹰优化器(Harris hawk optimizer,HHO)优化多层感知机(multi-layer perception,MLP)神经网络的故障诊断方法。首先,采用均方根-均值(root mean square-mean,RMS-MEAN)方法对齿轮箱故障振动信号进行预处理,以降低随机变工况对不同振动信号的影响;其次,引入变工况修正因子k,利用HHO对MLP的超参数进行自动优化,增强振动信号中的周期性特征,构造变工况下最优的MLP网络结构;最后,将特征增强数据输入HHO-MLP中进行故障诊断。通过MCC5-THU齿轮箱故障数据集验证,该方法在变工况下对齿轮箱故障的诊断性能显著优于其他模型,故障分类的准确率可达97.5%,这说明了其在变工况下的有效性。 展开更多
关键词 齿轮箱 变工况 哈里斯鹰优化器 多层感知机 故障诊断
在线阅读 下载PDF
基于多层感知机-注意力模型的功耗预测算法
17
作者 敬超 全育涛 陈艳 《计算机应用》 北大核心 2025年第8期2646-2655,共10页
虽然异构计算系统的应用可以加快神经网络参数的处理,但系统功耗也随之剧增。良好的功耗预测方法是异构系统优化功耗和处理多类型工作负载的基础,基于此,通过改进多层感知机-注意力模型,提出一种面向CPU/GPU异构计算系统多类型工作负载... 虽然异构计算系统的应用可以加快神经网络参数的处理,但系统功耗也随之剧增。良好的功耗预测方法是异构系统优化功耗和处理多类型工作负载的基础,基于此,通过改进多层感知机-注意力模型,提出一种面向CPU/GPU异构计算系统多类型工作负载的功耗预测算法。首先,考虑服务器功耗与系统特征,建立一种基于特征的工作负载功耗模型;其次,针对现有的功耗预测算法不能解决系统特征与系统功耗之间的长程依赖的问题,提出一种改进的基于多层感知机-注意力模型的功耗预测算法Prophet,该算法改进多层感知机实现各个时刻的系统特征的提取,并使用注意力机制综合这些特征,从而有效解决系统特征与系统功耗之间的长程依赖问题;最后,在实际系统中开展相关实验,将所提算法分别与MLSTM_PM(Power consumption Model based on Multi-layer Long Short-Term Memory)和ENN_PM(Power consumption Model based on Elman Neural Network)等功耗预测算法对比。实验结果表明,Prophet具有较高的预测精准性,与MLSTM_PM算法相比,在工作负载blk、memtest和busspd上将平均相对误差(MRE)分别降低了1.22、1.01和0.93个百分点,并且具有较低的复杂度,表明了所提算法的有效性及可行性。 展开更多
关键词 异构计算系统 负载特征 多层感知机 注意力机制 功耗预测
在线阅读 下载PDF
基于启发式交叉策略优化的K-Means聚类算法
18
作者 张立娜 张兴瑞 +2 位作者 马丽 于合龙 宋欣怡 《吉林大学学报(理学版)》 北大核心 2025年第6期1663-1672,共10页
针对传统K-Means算法对初始质心敏感、易陷入局部最优以及未能充分挖掘聚类结果潜在语义特征的问题,提出一种基于启发式交叉策略优化的K-Means聚类算法.首先,该算法通过密度驱动的启发式交叉初始化策略,筛选高密度区域的代表性父代点,... 针对传统K-Means算法对初始质心敏感、易陷入局部最优以及未能充分挖掘聚类结果潜在语义特征的问题,提出一种基于启发式交叉策略优化的K-Means聚类算法.首先,该算法通过密度驱动的启发式交叉初始化策略,筛选高密度区域的代表性父代点,并引入交叉系数动态生成多样性初始质心,以降低随机初始化导致的聚类结果波动性;其次,在聚类迭代过程中,结合父代点信息与簇内均值更新规则,通过交叉操作动态调整质心位置,解决了传统算法因局部最优导致的簇间重叠问题;最后,将优化后的聚类结果输入多层感知机,利用其非线性映射能力挖掘潜在特征,实现了聚类结果与深层语义特征的深度融合.实验结果表明,该算法的轮廓系数、Davies-Bouldin指数和调整Rand指数分别达0.634,1.398,0.621,显著优于其他改进算法,有效提升了算法的聚类准确性、稳定性和可解释性. 展开更多
关键词 启发式交叉策略 K-MEANS聚类算法 多层感知机 特征融合
在线阅读 下载PDF
河南省滑坡灾害易发性制图研究:多种机器学习模型的对比 被引量:6
19
作者 曹文庚 潘登 +3 位作者 徐郅杰 张文培 任宇 南天 《地质科技通报》 北大核心 2025年第1期101-111,共11页
河南省具有复杂的地貌类型,面临着频繁发生滑坡灾害的挑战,因此进行高效准确的滑坡易发性制图对于地方政府和居民具有重要意义。但是,在滑坡易发性制图研究中,如何选取适合河南省滑坡灾害数据集的机器学习模型、提高评价精度的对比研究... 河南省具有复杂的地貌类型,面临着频繁发生滑坡灾害的挑战,因此进行高效准确的滑坡易发性制图对于地方政府和居民具有重要意义。但是,在滑坡易发性制图研究中,如何选取适合河南省滑坡灾害数据集的机器学习模型、提高评价精度的对比研究仍需进一步开展。以河南省为研究区,收集滑坡数据并编录成滑坡灾害数据库。通过递归特征消除法筛选出对滑坡相对影响最高的11个因子(坡度、高程、平面曲率、剖面曲率、土地覆盖、岩性、土壤类型、降水量、道路密度、河流密度、断裂带密度)整合成空间数据集,训练多层感知机(MLP)神经网络、随机森林(RF)、极端梯度提升(XGBoost)和支持向量机(SVM)模型并使用接收者受试特征曲线下面积(AUC)评估各个模型性能,制作高精度滑坡易发性分区图。研究结果表明,多层感知机模型对河南省滑坡灾害数据集适配性最强,AUC达到0.95。相较于支持向量机、极端梯度提升和随机森林模型,MLP模型预测的滑坡灾害高易发区的面积占比最小,能更精确地识别潜在滑坡灾害高风险区域。预测的极高和高易发区主要分布在豫西山地、丘陵地区,地形因素对河南省滑坡灾害发育具有主导作用。研究成果可为大尺度区域开展高精度滑坡灾害易发性评价提供参考。 展开更多
关键词 滑坡 多层感知机 机器学习 易发性制图 河南省
在线阅读 下载PDF
基于迁移多层感知机的挤压铸件性能预测研究
20
作者 邓建新 农张华 +1 位作者 尹政 戴博林 《广西大学学报(自然科学版)》 北大核心 2025年第2期370-383,共14页
为了基于更少的试验样本数据来更准确地预测铸件性能,提出基于已有数据和迁移多层感知机的挤压铸件性能预测方法。首先基于预测的铸件性能,从材料、工艺参数、铸件性能等方面设计数据迁移规则,筛选出最适合迁移的历史铸件数据,在此基础... 为了基于更少的试验样本数据来更准确地预测铸件性能,提出基于已有数据和迁移多层感知机的挤压铸件性能预测方法。首先基于预测的铸件性能,从材料、工艺参数、铸件性能等方面设计数据迁移规则,筛选出最适合迁移的历史铸件数据,在此基础上建立工艺参数与性能间的贝叶斯优化的预训练多层感知机模型,然后引入少量目标铸件试验数据,通过冻结-微调隐藏层参数的迁移策略,最终建立面向新铸件的性能预测模型。应用实例表明,迁移模型的平均预测误差相对基模型最大可降低80.46%。与现有基于单一铸件数据的预测模型相比,所提方法运用历史案例,实现了工艺参数与铸件性能间的知识迁移,进一步降低了对训练样本的需求,从而减少新铸件的试验次数和成本。 展开更多
关键词 挤压铸件 性能预测 迁移学习 多层感知机 贝叶斯优化 少样本学习
在线阅读 下载PDF
上一页 1 2 28 下一页 到第
使用帮助 返回顶部