The xanthan fermentation data in the stationary phase was analyzed using the black box and the metabolic network models. The data consistency is checked through the elemental balance in the black box model. In the met...The xanthan fermentation data in the stationary phase was analyzed using the black box and the metabolic network models. The data consistency is checked through the elemental balance in the black box model. In the metabolic network model, the metabolic flux distribution in the cell is calculated using the metabolic flux analysis method, then the maintenance coefficients is calculated.展开更多
开发有效的风机电磁暂态模型是进行海上风电并网研究的基础。根据不同生产厂家所提供的直驱风机模型,提出了一种基于厂家黑盒模型的直驱风机电磁暂态建模方法。利用厂家所提供的模型测试数据解析风机的故障响应特性,推导了不同厂家在电...开发有效的风机电磁暂态模型是进行海上风电并网研究的基础。根据不同生产厂家所提供的直驱风机模型,提出了一种基于厂家黑盒模型的直驱风机电磁暂态建模方法。利用厂家所提供的模型测试数据解析风机的故障响应特性,推导了不同厂家在电压故障下有功和无功功率响应表达式,包括故障期间的穿越控制过程及不同过程间的暂态切换策略。提出了加权平均压降的风电场等值方法,采用自主研发的全电磁暂态仿真软件(power system model,PSModel)对我国广东某海上风电场进行全电磁暂态建模。根据稳态潮流及暂态特性结果验证了模型可通过系统测试,且有效实现了海上风电场的全电磁暂态建模,从而为该风场接入大电网后的安全稳定分析提供了研究基础。展开更多
Concept of black box, condition of modeling and control methods were introduced. Taking high purity silica brick as an example, the silica brick featured with high purity, low porosity, low true density and high stren...Concept of black box, condition of modeling and control methods were introduced. Taking high purity silica brick as an example, the silica brick featured with high purity, low porosity, low true density and high strength was developed through problem analysis, test design, modeling and optimization. Using information technology to upgrade refractories industry was discussed.展开更多
In this paper, Black Box approach is presented for behavioral modeling of a non linear power amplifier with memory effects. Large signal parameters of a Motorola LDMOS power amplifier driven by a WCDMA signal were ext...In this paper, Black Box approach is presented for behavioral modeling of a non linear power amplifier with memory effects. Large signal parameters of a Motorola LDMOS power amplifier driven by a WCDMA signal were extracted while taking into considerations the power amplifier’s bandwidth. The proposed model was validated based on the simulated data. Some validation results are presented both in the time and frequency domains, using WCDMA signal.展开更多
The multiplicity distribution (P(nch)) of charged particles produced in a high energy collision is a key quantity to understand the mechanism of multiparticle production. This paper describes the novel application of ...The multiplicity distribution (P(nch)) of charged particles produced in a high energy collision is a key quantity to understand the mechanism of multiparticle production. This paper describes the novel application of an artificial neural network (ANN) black-box modeling approach based on the cascade correlation (CC) algorithm formulated to calculate and predict multiplicity distribution of proton-proton (antiproton) (PP and PP ) inelastic interactions full phase space at a wide range of center-mass of energy . In addition, the formulated cascade correlation neural network (CCNN) model is used to empirically calculate the average multiplicity distribution nch> as a function of . The CCNN model was designed based on available experimental data for = 30.4 GeV, 44.5 GeV, 52.6 GeV, 62.2 GeV, 200 GeV, 300 GeV, 540 GeV, 900 GeV, 1000 GeV, 1800 GeV, and 7 TeV. Our obtained empirical results for P(nch), as well as nch> for (PP and PP) collisions are compared with the corresponding theoretical ones which obtained from other models. This comparison shows a good agreement with the available experimental data (up to 7 TeV) and other theoretical ones. At full large hadron collider (LHC) energy ( = 14 TeV) we have predicted P(nch) and nch> which also, show a good agreement with different theoretical models.展开更多
预训练模型容易受到外部敌手实施的模型微调和模型剪枝等攻击,导致它的完整性被破坏。针对这一问题,提出一种针对黑盒模型的脆弱指纹框架FFWAS(Fragile Fingerprint With Adversarial Samples)。首先,提出一种无先验知识的模型复制框架,...预训练模型容易受到外部敌手实施的模型微调和模型剪枝等攻击,导致它的完整性被破坏。针对这一问题,提出一种针对黑盒模型的脆弱指纹框架FFWAS(Fragile Fingerprint With Adversarial Samples)。首先,提出一种无先验知识的模型复制框架,而FFWAS为每一位用户创建独立的模型副本;其次,利用黑盒方法在模型边界放置脆弱指纹触发集,若模型发生修改,边界发生变化,触发集将被错误分类;最后,用户借助模型副本上的脆弱指纹触发集对模型的完整性进行验证,若触发集的识别率低于预设阈值,则意味着模型完整性已被破坏。基于2种公开数据集MNIST和CIFAR-10对FFWAS的有效性和脆弱性进行实验分析,结果表明,在模型微调和剪枝攻击下,FFWAS的指纹识别率相较于完整模型均明显下降并低于设定阈值;与基于模型唯一性和脆弱签名的深度神经网络认证框架(DeepAuth)相比,FFWAS的触发集与原始样本在2个数据集上的相似性分别提高了约22%和16%,表明FFWAS具有更好的隐蔽性。展开更多
在黑盒场景下,使用模型功能窃取方法生成盗版模型已经对云端模型的安全性和知识产权保护构成严重威胁。针对扰动和软化标签(变温)等现有的模型窃取防御技术可能导致模型输出中置信度最大值的类别发生改变,进而影响原始任务中模型性能的...在黑盒场景下,使用模型功能窃取方法生成盗版模型已经对云端模型的安全性和知识产权保护构成严重威胁。针对扰动和软化标签(变温)等现有的模型窃取防御技术可能导致模型输出中置信度最大值的类别发生改变,进而影响原始任务中模型性能的问题,提出一种基于暗知识保护的模型功能窃取防御方法,称为DKP(defending against model stealing attacks based on Dark Knowledge Protection)。首先,利用待保护的云端模型对测试样本进行处理,以获得样本的初始置信度分布向量;然后,在模型输出层之后添加暗知识保护层,通过分区变温调节softmax机制对初始置信度分布向量进行扰动处理;最后,得到经过防御的置信度分布向量,从而降低模型信息泄露的风险。使用所提方法在4个公开数据集上取得了显著的防御效果,尤其在博客数据集上使盗版模型的准确率降低了17.4个百分点,相比之下对后验概率进行噪声扰动的方法仅能降低约2个百分点。实验结果表明,所提方法解决了现有扰动、软化标签等主动防御方法存在的问题,在不影响测试样本分类结果的前提下,通过扰动云端模型输出的类别概率分布特征,成功降低了盗版模型的准确率,实现了对云端模型机密性的可靠保障。展开更多
建立准确的静止无功发生器(static var generators,SVG)白盒电磁暂态仿真模型是分析电网电压稳定特性的前提。然而,由于SVG的控制器结构和参数保密,其建模大都基于典型控制结构和参数,模型的暂态输出特性与实际差异较大。针对上述问题,...建立准确的静止无功发生器(static var generators,SVG)白盒电磁暂态仿真模型是分析电网电压稳定特性的前提。然而,由于SVG的控制器结构和参数保密,其建模大都基于典型控制结构和参数,模型的暂态输出特性与实际差异较大。针对上述问题,提出了基于SVG厂家封装黑盒模型故障穿越(fault ride-through,FRT)演化特性的电磁暂态模型测辨方法。首先,分析了厂家黑盒模型的拓扑特征,通过多工况故障穿越响应测试,厘清了其故障穿越演化特性。然后,通过分析不同控制环节暂态切换过程对SVG故障穿越响应特性的影响和作用途径,提出了基于SVG故障穿越响应演化形态的控制器结构辨识方法。通过分析SVG不同控制环节参数对其故障穿越响应特性的分阶段作用原理,提出了基于故障穿越响应幅值的控制器参数分步辨识方法,形成了SVG的白盒化电磁暂态模型测辨方法体系。最后,将建立的不同型号白盒仿真模型与对应厂家黑盒模型进行了故障穿越响应特性对比分析,发现其误差远小于现行标准的允许误差,证明了提出方法的有效性和通用性。展开更多
基金Supported by the National Natural Science Foundation of China(No.29776035).
文摘The xanthan fermentation data in the stationary phase was analyzed using the black box and the metabolic network models. The data consistency is checked through the elemental balance in the black box model. In the metabolic network model, the metabolic flux distribution in the cell is calculated using the metabolic flux analysis method, then the maintenance coefficients is calculated.
文摘开发有效的风机电磁暂态模型是进行海上风电并网研究的基础。根据不同生产厂家所提供的直驱风机模型,提出了一种基于厂家黑盒模型的直驱风机电磁暂态建模方法。利用厂家所提供的模型测试数据解析风机的故障响应特性,推导了不同厂家在电压故障下有功和无功功率响应表达式,包括故障期间的穿越控制过程及不同过程间的暂态切换策略。提出了加权平均压降的风电场等值方法,采用自主研发的全电磁暂态仿真软件(power system model,PSModel)对我国广东某海上风电场进行全电磁暂态建模。根据稳态潮流及暂态特性结果验证了模型可通过系统测试,且有效实现了海上风电场的全电磁暂态建模,从而为该风场接入大电网后的安全稳定分析提供了研究基础。
基金This paper is funded by National 11th " Five-Year-Plan" Major Supporting Projects for Scientific and Technology. Its item name is "Green Manufacturing Processes and Equipment" with subject number of 2006BAF02A26.
文摘Concept of black box, condition of modeling and control methods were introduced. Taking high purity silica brick as an example, the silica brick featured with high purity, low porosity, low true density and high strength was developed through problem analysis, test design, modeling and optimization. Using information technology to upgrade refractories industry was discussed.
文摘In this paper, Black Box approach is presented for behavioral modeling of a non linear power amplifier with memory effects. Large signal parameters of a Motorola LDMOS power amplifier driven by a WCDMA signal were extracted while taking into considerations the power amplifier’s bandwidth. The proposed model was validated based on the simulated data. Some validation results are presented both in the time and frequency domains, using WCDMA signal.
文摘The multiplicity distribution (P(nch)) of charged particles produced in a high energy collision is a key quantity to understand the mechanism of multiparticle production. This paper describes the novel application of an artificial neural network (ANN) black-box modeling approach based on the cascade correlation (CC) algorithm formulated to calculate and predict multiplicity distribution of proton-proton (antiproton) (PP and PP ) inelastic interactions full phase space at a wide range of center-mass of energy . In addition, the formulated cascade correlation neural network (CCNN) model is used to empirically calculate the average multiplicity distribution nch> as a function of . The CCNN model was designed based on available experimental data for = 30.4 GeV, 44.5 GeV, 52.6 GeV, 62.2 GeV, 200 GeV, 300 GeV, 540 GeV, 900 GeV, 1000 GeV, 1800 GeV, and 7 TeV. Our obtained empirical results for P(nch), as well as nch> for (PP and PP) collisions are compared with the corresponding theoretical ones which obtained from other models. This comparison shows a good agreement with the available experimental data (up to 7 TeV) and other theoretical ones. At full large hadron collider (LHC) energy ( = 14 TeV) we have predicted P(nch) and nch> which also, show a good agreement with different theoretical models.
文摘预训练模型容易受到外部敌手实施的模型微调和模型剪枝等攻击,导致它的完整性被破坏。针对这一问题,提出一种针对黑盒模型的脆弱指纹框架FFWAS(Fragile Fingerprint With Adversarial Samples)。首先,提出一种无先验知识的模型复制框架,而FFWAS为每一位用户创建独立的模型副本;其次,利用黑盒方法在模型边界放置脆弱指纹触发集,若模型发生修改,边界发生变化,触发集将被错误分类;最后,用户借助模型副本上的脆弱指纹触发集对模型的完整性进行验证,若触发集的识别率低于预设阈值,则意味着模型完整性已被破坏。基于2种公开数据集MNIST和CIFAR-10对FFWAS的有效性和脆弱性进行实验分析,结果表明,在模型微调和剪枝攻击下,FFWAS的指纹识别率相较于完整模型均明显下降并低于设定阈值;与基于模型唯一性和脆弱签名的深度神经网络认证框架(DeepAuth)相比,FFWAS的触发集与原始样本在2个数据集上的相似性分别提高了约22%和16%,表明FFWAS具有更好的隐蔽性。
文摘在黑盒场景下,使用模型功能窃取方法生成盗版模型已经对云端模型的安全性和知识产权保护构成严重威胁。针对扰动和软化标签(变温)等现有的模型窃取防御技术可能导致模型输出中置信度最大值的类别发生改变,进而影响原始任务中模型性能的问题,提出一种基于暗知识保护的模型功能窃取防御方法,称为DKP(defending against model stealing attacks based on Dark Knowledge Protection)。首先,利用待保护的云端模型对测试样本进行处理,以获得样本的初始置信度分布向量;然后,在模型输出层之后添加暗知识保护层,通过分区变温调节softmax机制对初始置信度分布向量进行扰动处理;最后,得到经过防御的置信度分布向量,从而降低模型信息泄露的风险。使用所提方法在4个公开数据集上取得了显著的防御效果,尤其在博客数据集上使盗版模型的准确率降低了17.4个百分点,相比之下对后验概率进行噪声扰动的方法仅能降低约2个百分点。实验结果表明,所提方法解决了现有扰动、软化标签等主动防御方法存在的问题,在不影响测试样本分类结果的前提下,通过扰动云端模型输出的类别概率分布特征,成功降低了盗版模型的准确率,实现了对云端模型机密性的可靠保障。
文摘建立准确的静止无功发生器(static var generators,SVG)白盒电磁暂态仿真模型是分析电网电压稳定特性的前提。然而,由于SVG的控制器结构和参数保密,其建模大都基于典型控制结构和参数,模型的暂态输出特性与实际差异较大。针对上述问题,提出了基于SVG厂家封装黑盒模型故障穿越(fault ride-through,FRT)演化特性的电磁暂态模型测辨方法。首先,分析了厂家黑盒模型的拓扑特征,通过多工况故障穿越响应测试,厘清了其故障穿越演化特性。然后,通过分析不同控制环节暂态切换过程对SVG故障穿越响应特性的影响和作用途径,提出了基于SVG故障穿越响应演化形态的控制器结构辨识方法。通过分析SVG不同控制环节参数对其故障穿越响应特性的分阶段作用原理,提出了基于故障穿越响应幅值的控制器参数分步辨识方法,形成了SVG的白盒化电磁暂态模型测辨方法体系。最后,将建立的不同型号白盒仿真模型与对应厂家黑盒模型进行了故障穿越响应特性对比分析,发现其误差远小于现行标准的允许误差,证明了提出方法的有效性和通用性。