基于残差U-Net和自注意力Transformer编码器的磁场预测方法

利用有限元方法对几何结构复杂的电机和变压器进行磁场分析,存在仿真时间长且无法复用的问题。因此,该文提出一种基于残差U-Net和自注意力Transformer编码器的磁场预测方法。首先建立永磁同步电机(PMSM)和非晶合金变压器(AMT)有限元模型,得到深度学习训练所需的数据集;然后将Transformer模块与U-Net模型结合,并引入短残差机制建立ResUnet-Transformer模型,通过预测图像的像素实现磁场预测;最后通过Targeted Dropout算法和动态学习率调整策略对模型进行优化,解决拟合问题并提高预测精度。计算实例证明,ResUnet-Transformer模型在PMSM和AMT数据集上测试集的平均绝对百分比误差(MAPE)均小于1%,且仅需500组样本。该文提出的磁场预测方法能减少实际工况和多工况下精细模拟和拓扑优化的时间和资源消耗,亦是虚拟传感器乃至数字孪生的关键实现方法之一。

基于MsTCN-Transformer模型的轴承剩余使用寿命预测研究

剩余使用寿命(remaining useful life, RUL)预测是PHM的核心问题之一,复杂的运行工况往往导致设备部件经历不同的故障退化过程,给RUL准确预测带来了巨大挑战。为此,提出了一种多尺度时间卷积网络(multi-scale temporal convolutional network, MsTCN)与Transformer(MsTCN-Transformer)融合模型用于变工况下滚动轴承RUL预测。该方法设计了一种新的多尺度膨胀因果卷积单元(multi-scale dilated causal convolution unit, MsDCCU),能够自适应地挖掘滚动轴承全寿命信号中固有的时序特征信息;然后构建了基于自注意力机制的Transformer网络模型,在克服预测序列记忆力退化的基础上,准确学习时序特征与轴承RUL之间的映射关系。此外,通过对轴承不同故障退化阶段所提取的时序特征可视化分析,验证了所提方法在变工况下所提取的时序特征泛化性较好。多种工况条件下滚动轴承RUL预测试验表明,所提方法能够较为准确地实现变工况下轴承的RUL预测,相比当前多种方法RUL预测结果准确性更高。

The transformation and concentration of environmental hazardous trace elements during coal combustion

Studied the content and distribution of 18 environmental hazardous trace elementsin the lignite, fatty coal, anthracite and its burnt products by combustion simulatingexpriment in the one-dismensinal boiler.The transformations and concentration of 18 traceelements during different coal combustion were discussed.The results show that there aresome content distribution of 18 hazardous trace elements in every burnt product, but thelaw of concentration and dispersion of every trace element during different coal combustionis very different.Experiment results indicate that the transformation and concentrationof trace elements during coal combustion are related to the element contents and occur-rencesof trace elements in raw coal, but are also affected by some man-made factorssuch as the combustion method of boiler, combustion temperature and atmosphere, thetype of precipitators and so on.

Transformer网络在大地电磁反演成像中的应用

传统大地电磁反演通常是基于确定性梯度的迭代求解,不仅需要大量时间计算雅可比矩阵,还依赖于初始模型的输入和正则化因子等参数的设置。近年来学者们不断引入机器学习方法以试图改善大地电磁反演,该方法不需要计算雅可比矩阵,不用输入初始模型,训练好的网络仅需几毫秒就可实现反演成像。这里利用Google团队提出的Transformer神经网络经典框架搭建大地电磁数据和模型之间的映射网络,以9240组正演数据为样本,对Transformer网络参数进行训练。采用南非开源大地电磁数据,实现了由视电阻率图像到电阻率模型的反演成像。研究表明:①经训练后的Transformer网络可以较准确的反映出异常体位置和大小;②网络实现了简单的矩阵并行化运算,大幅度提高训练的效率,且成像效率高于传统的反演。

ISOPARAMETRIC ELEMENT TRANSFORMATION FOR FINITE ANALYTIC METHOD

Finite analytic method (FAM) is widely used to calculate high Reynolds number flow. However, on complex geometric domain this method must employ boundary-fitted coordinate transformation, which is difficult for some flow regions. In this paper, the isoparametric element was incorporated into the FAM. The flow region was subdivided into a number of small arbitary quadrilaterals and each element was transformed into a square element by the shape functions of isoparametric element. Then, the partial differential equations on the square element can be solved by FAM. Because this transformation is solely local, it is more flexible and convenient than the transformation on the whole domain. To illustrate this transformation, the two-dimensional incompressible viscous flow passing tube bundles has been calculated by this method.

AN INVESTIGATION ON A NEW INTEGRAL TRANSFORM-BOUNDARY ELEMENT METHOD FOR ELASTODYNAMICS

The numerical methods of Fourier eigen transform FET and its inversion are discussed and applied to the boundary element method for elastodynamics. The program for solving elastodynamic problems with the boundary element method is developed and some examples are given. From the numerical results of the examples, we know the method can increase the computing speed 5 similar to 10 times and the accuracy is guaranteed.

Extensions to the Finite Element Technique for the Magneto-Thermal Analysis of Aged Oil Cooled-Insulated Power Transformers

It is well known that the hot spot temperature represents the most critical parameter identifying the power rating of a transformer. This paper investigates the effect of the degradation of core magnetic properties on temperature variation of aged oil-cooled transformers. Within this work, 2D accurate assessment of time average flux density distribution in an oil insulated-cooled 25 MVA transformer has been computed using finite-element analysis taking into account ageing and stress-induced non-uniform core permeability values. Knowing the core material specific loss and winding details, local core and winding losses are converted into heat. Based upon the ambient temperature outside the transformer tank and thermal heat transfer related factors, the detailed thermal modeling and analysis have then been carried out to determine temperature distribution everywhere. Analytical details and simulation results demonstrating effects of core magnetic properties degradation on hot spot temperatures of the transformer’s components are given in the paper.

Analysis of Thermal Behavior of High Frequency Transformers Using Finite Element Method

High frequency transformer is used in many applications among the Switch Mode Power Supply (SMPS), high voltage pulse power and etc can be mentioned. Regarding that the core of these transformers is often the ferrite core;their functions partly depend on this core characteristic. One of the characteristics of the ferrite core is thermal behavior that should be paid attention to because it affects the transformer function and causes heat generation. In this paper, a typical high frequency transformer with ferrite core is designed and simulated in ANSYS software. Temperature rise due to winding current (Joule-heat) is considered as heat generation source for thermal behavior analysis of the transformer. In this simulation, the temperature rise and heat distribution are studied and the effects of parameters such as flux density, winding loss value, using a fan to cool the winding and core and thermal conductivity are investigated.

Rolling Element Bearing Diagnostics by Combination of Envelope Analysis and Wavelet Transform

Rolling element-bearing diagnostics has been studied over the last thirty years, and envelope analysis is widely recognized as being the best approach for detection and diagnosis of rolling element bearing incipient failure. But one of the on-going difficulties with envelope technique is to determine the best frequency band to envelop. Here, wavelet transform technique is introduced into envelope analysis to solve the problem by capturing bearing defects-sensory scales (i.e. frequency bands). A modulated Gaussian function is chosen to be the analytical wavelet because it coincides well with bearing defect-induced vibration signal patterns. Vibration signals measured from railway bearing tests were studied by the proposed method. Cases of bearings with single and multiple defects on inner and outer race under different testing conditions are presented. Experimental results showed that the proposed method allowed a more accurate local description and separation of transient signal part, which were caused by impacts between defects and the mating surfaces in the bearing. The combination method provides an effective signal detection technique for rolling element-bearing diagnostics.

Finite Element CAD Experiments on the Effect of Magnetic Loss in Power Transformers with Laminated Cores

The paper describes a simulated experiment that focuses on the numeric computation of magnetic loss in the laminated core of a single-phase power transformer. The students’ laboratory work is part of the library of experiments of the Electrical Machines virtual laboratory and makes use of the two-dimensional open-access electromagnetic field analysis software Finite Element Method Magnetics. The idea of the simulated exercise is to demonstrate how the magnetic loss caused by time-varying excitations affects the magnetic permeability, μ, of the laminated core and the terminal quantities of the energizing winding. A parametric analysis employing different values for the electrical conductivity and maximum hysteresis-induced angle of the laminated material yields five different field problems with increasing magnetic loss. Electric circuits characterized by the (I-V) operating point and reflected impedance of the energizing winding provide the information required to compute the changes in real power ΔP, reactive power ΔQ and magnetically stored energy ΔWm between successive problems characterized by increasing magnetic loss. The concept of reflected impedance helps to explain the physical meaning of the changes in power dissipation and energy storage in the laminated core.

数据要素嵌入、双元创新与制造业转型升级

数据作为全新的生产要素成为制造业转型升级的重要引擎,双元创新是助推数据要素有效嵌入实体经济的关键动力。基于双元创新视角,剖析数据要素嵌入赋能制造业转型升级的理论机制,运用2008—2020年中国A股制造业上市企业数据进行实证检验。结果显示:数据要素嵌入能够有效赋能制造业转型升级,该结论在一系列稳健性检验后依然成立;双元创新在数据要素嵌入赋能制造业转型升级中发挥着中介作用,且更多地通过探索式创新促进制造业转型升级,利用式创新的中介效应尚不显著;进一步分析发现,数据要素嵌入赋能制造业转型升级的影响效应在企业内部微观特征和外部宏观环境层面存在异质性。因此,建议应有效推进数据要素市场化配置改革,营造数据要素赋能外部环境;持续提升企业探索式创新动力,激发数据要素赋能制造业转型升级的活力;积极引导企业数字化转型,推动数据要素与传统要素的深度融合。

多要素驱动下的福建制造业转型升级实证研究

制造业是福建省经济发展的基石和区域竞争力的基础,民营企业成为福建省制造业转型升级的主力军,互联网技术为传统制造业转型升级注入了强有力支撑。文章基于2000-2020年福建省面板数据,运用VAR模型实证多要素对制造业转型升级的效应。研究显示,科学研究与实验发展的总投入不足、基础研究不够重视导致技术对制造业升级没有直接效应,有效利用互联网技术、培养高素质技术技能人才、加速民营资本流动能有效促进制造业高质量发展。

数据要素市场化、数字化转型与企业绿色创新

数据要素作为数字经济时代的关键生产要素,是推动企业绿色创新发展的新引擎。本文基于2013—2021年沪深A股上市公司数据,采用双重差分模型和中介效应模型探讨数据要素市场化通过数字化转型影响企业绿色创新的内在机理。研究发现,数据要素市场化能够促进企业绿色创新,数字化转型在二者之间发挥中介效应。异质性分析显示,数字化转型的中介效应主要体现在高数字基础设施水平组和高动态能力组。进一步研究发现,底层技术在数据要素市场化与企业绿色创新之间发挥的中介效应高于实践应用;数字化转型在数据要素市场化与激进型绿色创新之间发挥的中介效应高于其在数据要素市场化与增量型绿色创新之间发挥的中介效应。

“数据要素×”背景下文化产业数字化转型的理论逻辑、现实问题与对策

为了探讨数据要素对文化产业的经济意义,促进文化产业高质量数字化转型,论述了文化产业数字化转型的理论逻辑、现实问题和对策。研究发现,数字化转型有利于整合文化产业数据,促进要素匹配;强化数字技术应用,提高生产效率;提升文化生产水平,拓展生产边界;促进影视文旅融合,实现跨界联动;促进商务模式创新,丰富商业策略;促进文化消费环境升级、文化传播效能升级和文化产业治理升级。研究表明,针对数据要素收集与管理、文化元素的保护和创造、数字化的普及和推广等现实问题,政府应改进数据要素治理,维护文化数字化秩序;创新文化数字化成果运用,激发文化元素活力;培育数字化环境,拓展文化产业发展空间;培养文化数字化人才,打牢数字文化产业根基,促进中国文化产业向数字化方向高质量转型。

基于混合有限元法的油浸式变压器稳态流-热耦合场并行计算方法

针对油浸式变压器2维流-热耦合仿真计算效率低的问题,提出了基于混合有限元法的并行计算方法。首先,在Visual Studio 2019中采用C++语言实现无量纲最小二乘有限元法以及迎风有限元法的串行计算方法。然后,基于图形处理器(graphic processing unit,GPU)实现流体场的并行计算,针对单分区分匝模型对比分析了不同GPU卡在不同网格条件下的并行计算效率,分析结果表明数据规模越大,GPU卡流处理器越多并行效果越好。其次,基于Intel MKL(Intel math kernel library)函数库结合共享存储并行编程(open multi-processing,OpenMP)实现了2维温度场的并行计算,并对比分析了不同网格数量对并行效率的影响。最后,在此基础上提出了根据不同仿真条件的混合并行计算方法,并应用到大型油浸式变压器绕组模型的2维温升热点分析中。结果表明,相较于串行程序,混合有限元并行计算方法的加速比达到了69.5,实验测试结果进一步验证了并行计算结果的准确性,研究成果为大型油浸式变压器流-热耦合问题的快速计算奠定了基础。

“三改联动”下高中压内缸适应灵活运行改造探讨

为实现“双碳”目标和构建新型电力系统,高中压内缸如何适应灵活性运行成为现役煤电高中压合缸机组“三改联动”时重点关注内容之一。文章通过对高中压内缸结构要素组合、典型结构方案、结合电厂实际运行情况和相应结构有限元分析,得出高中压进汽部分分开的内缸结构作为适应灵活性运行优选结构,并对现役机组高中压内缸改造方案进行探讨。

同位素技术示踪水环境生源要素氮的来源及循环过程研究进展

氮作为生态系统中的关键生源要素,对于水环境质量和生态系统平衡至关重要。文章综述了同位素技术示踪水环境生源要素氮的来源及循环过程的研究进展。介绍了水环境中氮的主要来源(自然和人为)及时空变化特点,强调自然因素(如降雨)和人为活动(如污水和农业施肥)对水环境中氮分布的影响;详细阐述了同位素技术识别水环境中氮来源的发展历程(单同位素、双同位素和多同位素联合溯源阶段);讨论了同位素技术在辨别水环境中氮循环过程(硝化、反硝化、矿化和同化作用)中的应用;指出当前研究的不足,主要表现在同位素分馏效应、测试成本高、未实测污染源端元值、多种同位素耦合溯源机制不清晰,未来研究需提高同位素溯源技术并整合多类技术与数据,尤其与机器学习结合潜力大。

变压器长圆形绕组振动仿真与机械故障诊断研究

针对目前配电变压器长圆形绕组的故障诊断研究较少的问题,本文提出一种基于灰狼优化(GWO)算法的变压器长圆形绕组机械故障诊断的方法。首先,建立长圆形绕组的辐向和轴向振动数学模型;其次,建立变压器电磁—机械耦合有限元模型,计算长圆形绕组在正常、松动以及翘曲状态下的振动分布,选取R点作为特征值提取点;最后,对变压器样机进行正常、松动以及翘曲3种状态试验,获取R点的小波包能量特征,采用GWO算法优化支持向量机(SVM)参数对变压器长圆形绕组机械故障诊断,最终优化后的诊断综合准确率达到90%。

城市低碳转型背景下绿色交通内涵解析与发展路径

发展绿色交通是贯彻落实生态文明思想和国家绿色发展战略、实现“双碳”目标、促进城市交通系统可持续发展、引导城市低碳转型的关键举措。针对当前绿色交通实践工作主要聚焦于交通工具或交通设施的局限性,提出绿色交通的内涵是基于以人为本、高质量和可持续发展理念,以追求低能耗、低排放为核心目标,同时满足交通与城市发展协调、交通运输效率和效益改善以及人民群众出行品质提升的发展新范式。基于全生命周期、全要素系统发展路径,从交通运输节能降碳、高品质服务人的需求和塑造低耗城市空间形态3个方面提出发展绿色交通的措施建议,助力城市加快实现“双碳”目标。