改进TD3算法的机械臂三维路径规划方法

在军事航空领域中,复杂任务对机械臂路径规划提出了挑战。针对双延迟深度确定性策略梯度(TD3)算法学习效率低、样本利用率低的问题,提出了一种改进的TD3算法(Recurrent-TD3算法)。首先,将LSTM结合到策略网络与价值网络中,捕获航空控制任务中的时间序列信息,增强对时间序列变化的响应能力,使其能够在决策时考虑历史动作和状态,提高网络的表达能力;然后,将事后经验回放(HER)技术集成到TD3算法中,以解决任务中稀疏奖励难以学习的问题,通过将未达到目标的经验转化为达到新目标的经验,从而更有效地利用样本;最后,设计了一种基于包围盒的碰撞检测流程,以提高机械臂在军用航空任务中的安全性。实验表明,该算法相比于其他算法能够更快地找到一条无碰撞的路径,且平均路径长度最短。

小分子药物TD-198946促进大鼠骨髓间充质干细胞的成骨分化

背景:小分子药物TD-198946是一种能诱导干细胞形成软骨的高效软骨生成剂,但目前尚不清楚其对成骨分化的作用。目的:探讨小分子药物TD-198946促进大鼠骨髓间充质干细胞成骨分化的效果及其作用机制。方法:提取SD大鼠骨髓间充质干细胞,利用CCK-8法评估不同浓度TD-198946对骨髓间充质干细胞增殖的影响,确定TD-198946的最佳使用浓度;然后加入最适浓度TD-198946和成骨分化培养基对骨髓间充质干细胞进行成骨诱导;成骨诱导第3天用qRT-PCR检测碱性磷酸酶、Runt相关转录因子2、骨桥蛋白、骨钙蛋白、Ⅰ型胶原基因表达;成骨诱导第7天进行碱性磷酸酶染色,Western blot检测Runt相关转录因子2、Ⅰ型胶原、AKT、p-AKT、PI3K、p-PI3K蛋白表达;成骨诱导第21天进行茜素红染色。结果与结论:①CCK-8实验结果显示,100 nmol/L TD-198946能促进骨髓间充质干细胞增殖;②碱性磷酸酶染色及茜素红染色结果显示,TD-198946能促进大鼠骨髓间充质干细胞的成骨分化;③qRT-PCR结果显示,TD-198946可促进成骨相关基因碱性磷酸酶、Runt相关转录因子2、骨桥蛋白、骨钙蛋白、Ⅰ型胶原的表达;④Western blot结果显示,TD-198946可促进Runt相关转录因子2、Ⅰ型胶原以及p-PI3K、p-AKT蛋白表达。结果表明,小分子药物TD-198946可能通过激活PI3K/AKT信号通路,诱导大鼠骨髓间充质干细胞成骨分化。

DecMamba:Mamba Utilizing Series Decomposition for Multivariate Time Series Forecasting

Multivariate time series forecasting iswidely used in traffic planning,weather forecasting,and energy consumption.Series decomposition algorithms can help models better understand the underlying patterns of the original series to improve the forecasting accuracy of multivariate time series.However,the decomposition kernel of previous decomposition-based models is fixed,and these models have not considered the differences in frequency fluctuations between components.These problems make it difficult to analyze the intricate temporal variations of real-world time series.In this paper,we propose a series decomposition-based Mamba model,DecMamba,to obtain the intricate temporal dependencies and the dependencies among different variables of multivariate time series.A variable-level adaptive kernel combination search module is designed to interact with information on different trends and periods between variables.Two backbone structures are proposed to emphasize the differences in frequency fluctuations of seasonal and trend components.Mamba with superior performance is used instead of a Transformer in backbone structures to capture the dependencies among different variables.A new embedding block is designed to capture the temporal features better,especially for the high-frequency seasonal component whose semantic information is difficult to acquire.A gating mechanism is introduced to the decoder in the seasonal backbone to improve the prediction accuracy.A comparison with ten state-of-the-art models on seven real-world datasets demonstrates that DecMamba can better model the temporal dependencies and the dependencies among different variables,guaranteeing better prediction performance for multivariate time series.

A Multi-Objective Particle Swarm Optimization Algorithm Based on Decomposition and Multi-Selection Strategy

The multi-objective particle swarm optimization algorithm(MOPSO)is widely used to solve multi-objective optimization problems.In the article,amulti-objective particle swarm optimization algorithmbased on decomposition and multi-selection strategy is proposed to improve the search efficiency.First,two update strategies based on decomposition are used to update the evolving population and external archive,respectively.Second,a multiselection strategy is designed.The first strategy is for the subspace without a non-dominated solution.Among the neighbor particles,the particle with the smallest penalty-based boundary intersection value is selected as the global optimal solution and the particle far away fromthe search particle and the global optimal solution is selected as the personal optimal solution to enhance global search.The second strategy is for the subspace with a non-dominated solution.In the neighbor particles,two particles are randomly selected,one as the global optimal solution and the other as the personal optimal solution,to enhance local search.The third strategy is for Pareto optimal front(PF)discontinuity,which is identified by the cumulative number of iterations of the subspace without non-dominated solutions.In the subsequent iteration,a new probability distribution is used to select from the remaining subspaces to search.Third,an adaptive inertia weight update strategy based on the dominated degree is designed to further improve the search efficiency.Finally,the proposed algorithmis compared with fivemulti-objective particle swarm optimization algorithms and five multi-objective evolutionary algorithms on 22 test problems.The results show that the proposed algorithm has better performance.

基于改进TD3算法的智能通信干扰决策方法研究

本文对通信对抗中干扰决策方法展开研究,旨在解决人为手动干扰决策带来的对抗方式单一、极易被敌军发现、干扰效率不佳等问题。随着科技的发展,各种电子技术层出不穷,这就导致电子战争中的环境变得越来越复杂,为了应对这种复杂的环境,并达到预期的干扰效果,本文提出一种基于改进双延迟深度确定性策略梯度算法(TD3)的智能通信干扰决策方法,以解决通信干扰过程中的干扰决策问题。TD3算法不仅能够应对连续动作空间而且具有高稳定性的特点。另外,改进的TD3算法使学习的过程更加迅速,算法的结果也更加收敛。仿真结果表明,基于该算法的改进,通信干扰成功率比原算法提升了28%。

基于PE-CEEMD-SVD的Φ-OTDR信号降噪方法

为实现相位敏感光时域反射仪中相位信号的精确测量,提出了一种基于排列熵算法的互补集合经验模态分解联合奇异值分解的新型降噪方法(PE-CEEMD-SVD)。首先,对含有噪声的相位信号进行CEEMD分解,得到一系列频率不同的IMF分量;然后,将PE算法和相关系数机制相结合,保留较大相关的有用分量,对较小相关的噪声分量使用SVD算法进行二次降噪;最后将两次降噪后保留下来的有用分量进行重构。仿真和实验结果表明,相较于EMD、EEMD和CEEMD降噪方法,该方法可获得更高信噪比的信号,有利于相位信号的精确测量。

GEARBOX FAULTDIAGNOSIS BASED ON EMPIRICAL MODE DECOMPOSITION

Time synchronous averaging of vibration data is a fundament technique forgearbox diagnosis. Currently, this technique relies on hardware tachometer to give phase synchronousinformation. Empirical mode decomposition (EMD) is introduced to replace time synchronous averagingof gearbox vibration signal. With it, any complicated dataset can be decomposed into a finite andoften small number of intrinsic mode functions (IMF). The key problem is how to assure thatvibration signals deduced by gear defects could be sifted out by EMD. The characteristic vibrationsignals of gear defects are proved IMFs, which makes it possible to utilize EMD for the diagnosis ofgearbox faults. The method is validated by data from recordings of the vibration of a single-stagespiral bevel gearbox with fatigue pitting. The results show EMD is powerful to extractcharacteristic information from noisy vibration signals.

基于经验模态分解的单端BOTDA系统降噪方法研究

针对单端布里渊光时域分析(BOTDA)系统存在噪声大、信噪比较低等不足,提出一种基于经验模态分解的降噪方法。理论分析经验模态分解的降噪原理和少模光纤单端布里渊光时域分析传感原理,通过搭建的单端结构布里渊光时域分析温度传感系统,对经验模态分解的降噪效果进行对比分析。实验和仿真结果表明,经验模态分解算法对温度传感系统具有良好的降噪效果,降噪后信噪比提升了约3.06dB,温度测量精度提升了约0.98℃。

基于IITD-WT的大地电磁噪声压制方法

矿集区采集的大地电磁信号极易受到各类噪声污染,导致其视电阻率-相位曲线在低频段出现紊乱现象或呈现出近源效应等。文中提出了一种优化固有时间尺度分解(Improved Intrinsic Time Decomposition,IITD)和小波阈值(Wavelet Threshold,WT)的大地电磁(Magnetotelluric,MT)去噪方法及应用。首先将含噪信号进行IITD分解得到若干阶旋转(Proper Rotation,PR)分量;然后对PR分量进行小波去噪,叠加小波系数重构得到MT去噪数据。通过计算机模拟出不同类型的强噪声,并对小波阈值法设置不同的分解层数、基函数对强噪声进行处理,总结出该算法面对不同噪声时的去噪性能。对模拟大尺度方波和三角波噪声去噪后,信噪比最高可达24dB和17dB,所提方法去噪性能显著。将所提方法应用至MT实测数据的降噪,结果显示该方法能够有效去除隐藏在MT数据中的强噪声。由去噪前后视电阻率曲线对比可知,相较于远参考法和原始曲线,所提方法获得的视电阻率曲线更为光滑、连续,低频段的数据质量明显改善。

Enhancing the Interaction of Carbon Nanotubes by Metal-Organic Decomposition with Improved Mechanical Strength and Ultra-Broadband EMI Shielding Performance

The remarkable properties of carbon nanotubes(CNTs)have led to promising applications in the field of electromagnetic inter-ference(EMI)shielding.However,for macroscopic CNT assemblies,such as CNT film,achieving high electrical and mechanical properties remains challenging,which heavily depends on the tube-tube interac-tions of CNTs.Herein,we develop a novel strategy based on metal-organic decomposition(MOD)to fabricate a flexible silver-carbon nanotube(Ag-CNT)film.The Ag particles are introduced in situ into the CNT film through annealing of MOD,leading to enhanced tube-tube interactions.As a result,the electrical conductivity of Ag-CNT film is up to 6.82×10^(5) S m^(-1),and the EMI shielding effectiveness of Ag-CNT film with a thickness of~7.8μm exceeds 66 dB in the ultra-broad frequency range(3-40 GHz).The tensile strength and Young’s modulus of Ag-CNT film increase from 30.09±3.14 to 76.06±6.20 MPa(~253%)and from 1.12±0.33 to 8.90±0.97 GPa(~795%),respectively.Moreover,the Ag-CNT film exhibits excellent near-field shield-ing performance,which can effectively block wireless transmission.This innovative approach provides an effective route to further apply macroscopic CNT assemblies to future portable and wearable electronic devices.

A Novel Tensor Decomposition-Based Efficient Detector for Low-Altitude Aerial Objects With Knowledge Distillation Scheme

Unmanned aerial vehicles(UAVs) have gained significant attention in practical applications, especially the low-altitude aerial(LAA) object detection imposes stringent requirements on recognition accuracy and computational resources. In this paper, the LAA images-oriented tensor decomposition and knowledge distillation-based network(TDKD-Net) is proposed,where the TT-format TD(tensor decomposition) and equalweighted response-based KD(knowledge distillation) methods are designed to minimize redundant parameters while ensuring comparable performance. Moreover, some robust network structures are developed, including the small object detection head and the dual-domain attention mechanism, which enable the model to leverage the learned knowledge from small-scale targets and selectively focus on salient features. Considering the imbalance of bounding box regression samples and the inaccuracy of regression geometric factors, the focal and efficient IoU(intersection of union) loss with optimal transport assignment(F-EIoU-OTA)mechanism is proposed to improve the detection accuracy. The proposed TDKD-Net is comprehensively evaluated through extensive experiments, and the results have demonstrated the effectiveness and superiority of the developed methods in comparison to other advanced detection algorithms, which also present high generalization and strong robustness. As a resource-efficient precise network, the complex detection of small and occluded LAA objects is also well addressed by TDKD-Net, which provides useful insights on handling imbalanced issues and realizing domain adaptation.

Formation and transformation of metastable LPSO building blocks clusters in Mg-Gd-Y-Zn-Zr alloys by spinodal decomposition and heterogeneous nucleation

To study the formation and transformation mechanism of long-period stacked ordered(LPSO)structures,a systematic atomic scale analysis was conducted for the structural evolution of long-period stacked ordered(LPSO)structures in the Mg-Gd-Y-Zn-Zr alloy annealed at 300℃~500℃.Various types of metastable LPSO building block clusters were found to exist in alloy structures at different temperatures,which precipitate during the solidification and homogenization process.The stability of Zn/Y clusters is explained by the first principles of density functional theory.The LPSO structure is distinguished by the arrangement of its different Zn/Y enriched LPSO structural units,which comprises local fcc stacking sequences upon a tightly packed plane.The presence of solute atoms causes local lattice distortion,thereby enabling the rearrangement of Mg atoms in the different configurations in the local lattice,and local HCP-FCC transitions occur between Mg and Zn atoms occupying the nearest neighbor positions.This finding indicates that LPSO structures can generate necessary Schockley partial dislocations on specific slip surfaces,providing direct evidence of the transition from 18R to 14H.Growth of the LPSO,devoid of any defects and non-coherent interfaces,was observed separately from other precipitated phases.As a result,the precipitation sequence of LPSO in the solidification stage was as follows:Zn/Ycluster+Mg layers→various metastable LPSO building block clusters→18R/24R LPSO;whereas the precipitation sequence of LPSO during homogenization treatment was observed to be as follows:18R LPSO→various metastable LPSO building block clusters→14H LPSO.Of these,14H LPSO was found to be the most thermodynamically stable structure.

基于PSO-SVM的Φ-OTDR系统模式识别研究

针对相位敏感光时域反射仪(phase sensitive optical time domain reflectometer,Φ-OTDR)系统中误报率高的问题,提出一种多域特征提取与粒子群算法优化支持向量机(particle swarm optimization-support vector machine,PSO-SVM)相结合的模式识别算法。首先,对原始信号进行差分处理后提取时域特征,并利用小波包分解方法,通过验证不同分解层数下的事件分类准确率,设定最优分解层数为6层,提取差分信号的能量特征。然后以SVM分类器为基础,利用PSO算法优化SVM分类器参数,提高光纤振动信号识别准确率。最后利用Φ-OTDR事件数据集进行验证,实验结果表明,该模式识别算法达到了95.6%的振动事件分类准确率。

Reactive molecular dynamics insight into the thermal decomposition mechanism of 2,6-Bis(picrylamino)-3,5-dinitropyridine

2,6-bis(picrylamino)-3,5-dinitropyridine(PYX)has excellent thermostability,which makes its thermal decomposition mechanism receive much attention.In this paper,the mechanism of PYX thermal decomposition was investigated thoroughly by the ReaxFF-lg force field combined with DFT-B3LYP(6-311++G)method.The detailed decomposition mechanism,small-molecule product evolution,and cluster evolution of PYX were mainly analyzed.In the initial stage of decomposition,the intramolecular hydrogen transfer reaction and the formation of dimerized clusters are earlier than the denitration reaction.With the progress of the reaction,one side of the bitter amino group is removed from the pyridine ring,and then the pyridine ring is cleaved.The final products produced in the thermal decomposition process are CO_(2),H_(2)O,N_(2),and H_(2).Among them,H_(2)O has the earliest generation time,and the reaction rate constant(k_(3))is the largest.Many clusters are formed during the decomposition of PYX,and the formation,aggregation,and decomposition of these clusters are strongly affected by temperature.At low temperatures(2500 K-2750 K),many clusters are formed.At high temperatures(2750 K-3250 K),the clusters aggregate to form larger clusters.At 3500 K,the large clusters decompose and become small.In the late stage of the reaction,H and N in the clusters escaped almost entirely,but more O was trapped in the clusters,which affected the auto-oxidation process of PYX.PYX's initial decomposition activation energy(E_(a))was calculated to be 126.58 kJ/mol.This work contributes to a theoretical understanding of PYX's entire thermal decomposition process.

融合课程学习的TD3在上证50ETF期权上的动态对冲研究

如何进行动态对冲来管理头寸风险在期权交易中极为关键,然而在实际市场环境中并没有一个完美对冲的标准答案,因此寻求更好的对冲策略一直是投资领域的热门需求和研究的焦点.采用深度强化学习算法TD3,并结合课程学习的思想引导智能体采用从模拟到真实的学习方式实现动态对冲任务,降低学习难度并缓解期权数据不足的问题,构建了在上证50ETF期权上的动态对冲策略.结果表明深度强化学习算法的对冲效果远超传统对冲策略,验证了强化学习算法在期权对冲领域的有效性和优势.

Sparse Modal Decomposition Method Addressing Underdetermined Vortex-Induced Vibration Reconstruction Problem for Marine Risers

When investigating the vortex-induced vibration(VIV)of marine risers,extrapolating the dynamic response on the entire length based on limited sensor measurements is a crucial step in both laboratory experiments and fatigue monitoring of real risers.The problem is conventionally solved using the modal decomposition method,based on the principle that the response can be approximated by a weighted sum of limited vibration modes.However,the method is not valid when the problem is underdetermined,i.e.,the number of unknown mode weights is more than the number of known measurements.This study proposed a sparse modal decomposition method based on the compressed sensing theory and the Compressive Sampling Matching Pursuit(Co Sa MP)algorithm,exploiting the sparsity of VIV in the modal space.In the validation study based on high-order VIV experiment data,the proposed method successfully reconstructed the response using only seven acceleration measurements when the conventional methods failed.A primary advantage of the proposed method is that it offers a completely data-driven approach for the underdetermined VIV reconstruction problem,which is more favorable than existing model-dependent solutions for many practical applications such as riser structural health monitoring.

TdBrnn:An Approach to Learning Users’Intention to Legal Consultation with Normalized Tensor Decomposition and Bi-LSTM

With the development of Internet technology and the enhancement of people’s concept of the rule of law,online legal consultation has become an important means for the general public to conduct legal consultation.However,different people have different language expressions and legal professional backgrounds.This phenomenon may lead to the phenomenon of different descriptions of the same legal consultation.How to accurately understand the true intentions behind different users’legal consulting statements is an important issue that needs to be solved urgently in the field of legal consulting services.Traditional intent understanding algorithms rely heavily on the lexical and semantic information between the original data,and are not scalable,and often require taxing manual annotation work.This article proposes a new approach TdBrnn which is based on the normalized tensor decomposition method and Bi-LSTM to learn users’intention to legal consulting.First,we present the users’legal consulting statements as a tensor.And then we use the normalized tensor decomposition layer proposed by this article to extract the tensor elements and structural information of the original tensor which can best represent users’intention of legal consultation,namely the core tensor.The core tensor relies less on the lexical and semantic information of the original users’legal consulting statements data,it reduces the dimension of the original tensor,and greatly reduces the computational complexity of the subsequent Bi-LSTM algorithm.Furthermore,we use a large number of core tensors obtained by the tensor decomposition layer with users’legal consulting statements tensors as inputs to continuously train Bi-LSTM,and finally derive the users’legal consultation intention classification model which can comprehensively understand the user’s legal consultation intention.Experiments show that our method has faster convergence speed and higher accuracy than traditional recurrent neural networks.

基于TD3的恶意节点检测与鲁棒联邦聚合算法

针对联邦学习中的数据安全与隐私问题,提出了一种基于双延迟深度确定性策略梯度(Twin Delayed Deep Deterministic policy gradient,TD3)的恶意节点检测与鲁棒联邦聚合算法,旨在提高系统在面对恶意攻击时的鲁棒性。以标签翻转攻击和梯度上升攻击为例,展示了该算法对于恶意节点的有效识别与抵御能力,并对比分析了所提方法与传统的聚合算法,如FedAvg、Krum、MKrum等。试验结果表明,相较于传统算法,所提算法不仅能有效防御恶意攻击,同时能保持高效的学习效率和模型准确性,显著提升了模型的整体安全防御能力。

人工湿地对水体中TDS、Turb及FDOM的净化效果研究

以北京市野生动物救护中心的人工湿地为案例,评估人工湿地作为一种生态净化系统在不同环境条件下对水体中溶解性总固体(TDS)、浊度(Turb)和荧光溶解性有机质(FDOM)的去除效果。采用定位观测与对比分析方法,于2023年5月至7月期间,在北京市野生动物救护中心人工湿地选取不同的样点进行水样采集与监测,使用YSI6820多参数水质监测仪监测TDS、Turb及FDOM的浓度变化,并与2009年同期数据进行比较。研究结果表明:随着样点距离的增加,人工湿地对TDS、Turb和FDOM等污染物的去除率呈上升趋势,且同一样点不同月份之间的去除率存在差异;与2009年人工湿地浊度去除率对比分析可知,2023年浊度去除率显著提升;水体温度的升高能够提高人工湿地对TDS、Turb及FDOM的去除率。

基于TD-Mask R-CNN的机械装配体图像实例分割

在机械产品装配过程中,为了准确识别机械装配体零件信息以减少零件漏装、错装等现象,提出一种改进的机械装配体图像实例分割方法TD-Mask R-CNN。首先,在主干网络ResNet101中引入可变形卷积(deformable convolutional networks, DCN)以增加网络模型的泛化能力;其次,使用Transfiner结构作为掩码分支以提高机械零件边缘的分割精度;最后,在Transfiner结构中引入离散余弦变换(discrete cosine transform, DCT)模块以提升模型对机械装配体图像整体的分割能力。实验结果表明,提出的实例分割方法在合成深度图像数据集和真实彩色图像数据集上得到的掩码平均精度(average precision, AP)分别为87.7%和92.0%,与其他主流实例分割算法相比均有所提升。