基于t-SNE-VNWOA的船舶柴油机故障诊断

文中提出一种基于t-SNE-VNWOA-LSSVM故障诊断模型,并进行了台架试验.试验设置了正常工况、供气不足、燃烧提前和单缸断油四种工况,将各种工况采集的缸盖振动信号进行快速傅里叶变换(FFT),提取了13个时域和频域特征,利用t分布邻域嵌入算法(t-SNE)对数据降维、可视化故障特征.结合鲸鱼优化算法(VNWOA)对分类器(LSSVM)初始参数δ2和γ寻优,搭建其故障识别模型,将遗传算法(GA)和粒子群算法(PSO)的寻优诊断结果与之对比.结果表明:基于t-SNE-VNWOA-LSSVM故障诊断模型精度高达96.57%,且具有良好的稳定性及诊断速度.

基于HMFDE和t-SNE的旋转机械故障诊断方法

针对旋转机械的故障特征提取较难,以及单一类型的特征无法全面反映故障特性的问题,提出了一种基于混合多尺度波动散布熵(HMFDE)、t分布-随机邻域嵌入(t-SNE)和郊狼优化算法(COA)优化极限学习机(ELM)的旋转机械故障诊断方法。首先,采用特征加权提出了混合多尺度波动散布熵方法,并将其用于提取旋转机械振动信号的故障特征;随后,采用t-SNE方法对混合故障特征进行了特征降维,挑选出了最能够反映故障特性的特征子集,构建了敏感特征样本;最后,采用郊狼优化算法对极限学习机的输入权重和隐含层阈值进行了优化,完成了旋转机械的故障识别和分类;以齿轮箱和滚动轴承故障数据集为对象,对基于HMFDE、t-SNE和COA-ELM的故障诊断方法进行了实验,验证了方法的有效性。研究结果表明:采用HMFDE-t-SNE-CAO-ELM故障诊断方法可以取得100%的故障识别准确率,该方法能够有效地诊断旋转机械的不同故障类型和损伤;相较于基于单一类型特征的故障诊断方法,其准确率分别可以提高0.68%、22.42%、29.18%(齿轮箱)和1.43%、8.23%、23.67%(滚动轴承),虽然牺牲了一定的计算效率,但准确率得到了明显的提高;相较于其他常规故障分类器,COA-ELM的故障识别准确率具有明显的优势。

基于CAE-TSNE的成品油管道运行工况识别

成品油管道运行工况变化频繁,难以精准判断管道运行状态,依靠现场人员进行识别监控易造成误判。本文为实现管道运行工况的准确识别,考虑管道的物理空间特性,分析整理各站运行参数(压力、流量、密度);考虑管道运行的时间序列特性,基于SCADA管道数据构造运行数据矩阵,以克服单一时刻的瞬态扰动。针对管道运行数据高维度、非线性的特点,利用卷积自编码器(CAE)强大的特征压缩及重构能力对管道数据做降噪处理;利用T分布邻域嵌入算法(T-SNE)对管道数据做降维聚类处理,最终建立了基于CAE-TSNE的管道运行工况识别模型。以某两条成品油管道为例,对比主流的非线性分类模型(ANN、DT、RF),结果表明基于CAE-TSNE的工况识别模型精度最高,对降噪后的运行数据识别准确率可达到99%以上,可用于指导现场管道的运行管理。

基于t⁃SNE降维方法的滚动轴承剩余寿命预测

由于实际工况下的轴承退化数据有限,无法获得足够的退化数据来训练神经网络,在深度学习网络中很难得到好的预测结果,所以提出一种新的结合机器学习和统计数据驱动的方法。首先对原始振动信号做特征提取,通过集合经验模态分解奇异值分解(Ensemble Empirical Mode Decompositiont Singular Value Decomposition,EEMD+SVD)得到数十维特征,加上剩余寿命预测常用的诸如峭度、均值等有效特征,利用决策树筛选出15维特征;将所筛选特征进行双指数拟合并通过t分布随机近邻嵌入(t⁃distributed Stochastic Neighbor Embedding,t⁃SNE)将退化信号降维成线性趋势。线性退化趋势在预测上相比于指数趋势有更好的泛化性,同时预测准确度相比于指数模型支持向量回归(Support Vector Regression,SVR)和深度信念网络(Deep Belief Network,DBN)都有较高的提升。

Synthetic polymers:A review of applications in drilling fluids

With the growth of deep drilling and the complexity of the well profile,the requirements for a more complete and efficient exploitation of productive formations increase,which increases the risk of various complications.Currently,reagents based on modified natural polymers(which are naturally occurring compounds)and synthetic polymers(SPs)which are polymeric compounds created industrially,are widely used to prevent emerging complications in the drilling process.However,compared to modified natural polymers,SPs form a family of high-molecular-weight compounds that are fully synthesized by undergoing chemical polymerization reactions.SPs provide substantial flexibility in their design.Moreover,their size and chemical composition can be adjusted to provide properties for nearly all the functional objectives of drilling fluids.They can be classified based on chemical ingredients,type of reaction,and their responses to heating.However,some of SPs,due to their structural characteristics,have a high cost,a poor temperature and salt resistance in drilling fluids,and degradation begins when the temperature reaches 130℃.These drawbacks prevent SP use in some medium and deep wells.Thus,this review addresses the historical development,the characteristics,manufacturing methods,classification,and the applications of SPs in drilling fluids.The contributions of SPs as additives to drilling fluids to enhance rheology,filtrate generation,carrying of cuttings,fluid lubricity,and clay/shale stability are explained in detail.The mechanisms,impacts,and advances achieved when SPs are added to drilling fluids are also described.The typical challenges encountered by SPs when deployed in drilling fluids and their advantages and drawbacks are also discussed.Economic issues also impact the applications of SPs in drilling fluids.Consequently,the cost of the most relevant SPs,and the monomers used in their synthesis,are assessed.Environmental impacts of SPs when deployed in drilling fluids,and their manufacturing processes are identified,together with advances in SP-treatment methods aimed at reducing those impacts.Recommendations for required future research addressing SP property and performance gaps are provided.

基于tSNE-LSTM算法的工业预测模型

随着工业生产的复杂性和规模的增加,准确的工业预测模型对于提高生产效率和降低成本至关重要。为此,提出一种基于tSNE-LSTM算法的工业预测模型来预测工业生产过程的温度。将t-SNE应用于数据降维和特征提取,然后使用LSTM进行序列建模和预测。该模型结合了t-SNE降维和LSTM循环神经网络的优势,能够有效地捕捉时间序列数据的非线性动态特征,并进行准确预测。在实际工业数据集上的实验验证结果表明,该模型在工业预测任务中具有较高的准确性和鲁棒性。

基于t-SNE的多参数岩体结构面分步聚类方法

结构面聚类是进行岩体稳定性评价的重要步骤。常用聚类方法多以产状作为分组依据,忽略了结构面物理特性指标对岩体稳定性的影响。针对分组依据单一化的不足,综合考虑结构面倾向、倾角、迹长、张开度、填充状态和粗糙度的影响,提出一种基于学生分布随机邻近嵌入(student-distributed stochastic neighbor embedding,简称t-SNE)的多参数岩体结构面分步聚类方法。首先,利用t-SNE算法对除产状外的结构面特征进行数据降维;进而利用模拟退火算法搜索K-means算法的全局最优初始值,并采用分步聚类思想完成聚类。研究表明:所提方法有效地解决了高维空间样本稀疏的问题,同时保留了数据的局部结构与全局结构。新方法相比于传统方法能对空间分布相似区内结构面的物理特性进行精确划分,分组精度更高,且在避免复杂权重值计算的条件下,能有效区分产状与物理特性参数对岩体稳定性的影响差异。最后,将所提方法应用于中国新疆某露天矿坡结构面实测数据分析中,所得分组结果合理可靠,进一步证明该方法在实际工程中的有效性。研究方法可为多参数岩体结构面的分步聚类提供参考。

In-phase and out-of-phase spin pumping effects in Py/Ru/Pysynthetic antiferromagnetic structures

The spin pumping effect in magnetic heterostructures and multilayers is a highly effective method for the generationand transmission of spin currents. In the increasingly prominent synthetic antiferromagnetic structures, the two ferromagneticlayers demonstrate in-phase and out-of-phase states, corresponding to acoustic and optical precession modes. Withinthis context, our study explores the spin pumping effect in Py/Ru/Py synthetic antiferromagnetic structures across differentmodes. The heightened magnetic damping resulting from the spin pumping effect in the in-phase state initially decreaseswith increasing Py thickness before stabilizing. Conversely, in the out-of-phase state, the amplified damping exceeds thatof the in-phase state, suggesting a greater spin relaxation within this configuration, which demonstrates sensitivity to alterationsin static exchange interactions. These findings contribute to advancing the application of synthetic antiferromagneticstructures in magnonic devices.

Preparation of a high-performance synthetic pitch from aromatic hydrocarbons containing N/Cl

The preparation of a synthetic pitch from aromatic monomers could easily regulate structure orientation at the molecu-lar level,which would be useful in fabrication.An isotropic synthetic pitch was prepared by a chlorine-and/or nitrogen-induced sub-stitution polymerization reaction method using aromatic hydrocarbon precursors containing Cl and N,which for this study were chloromethyl naphthalene and quinoline.This method was verified by investigating the structural changes under different synthesis conditions,and the synthesis mechanism induced by aromatics containing Cl was also probed.The result shows that the pyridinic N in quinoline contains a lone pair of electrons,and is an effective active site to induce the polymerization reaction by coupling with aromatic hydrocarbons containing Cl.The reaction between such free radicals causes strong homopolymerization and oligomeriza-tion.A higher reaction temperature and longer reaction time significantly increased the degree of polymerization and thus increased the softening point of the pitch.A linear molecular structure was formed by the Cl substitution reaction,which produced a highly spinnable pitch with a softening point of 258.6℃,and carbon fibers with a tensile strength of 1163.82 MPa were obtained.This study provides a relatively simple and safe method for the preparation of high-quality spinnable pitch.

Synthetic Aperture Positioning: A Review

Obtaining precise position of interested emitters passively has wide applications in both civilian and military fields.Different from traditional parameter measurement and direct position determination(DPD)method,recently a new passive localization method based on synthetic aper-ture technique,named synthetic aperture positioning(SAP),has been proposed.The method com-pensates for the nonlinear phase produced by relative motion between the moving platform and the emitter,achieving coherent summation of intercepted signals.The SAP can obtain high-resolution and high-precision localization results at a low signal-to-noise ratio.This paper summarizes the research progress of SAP,including localization principles,spaceborne applications,and application scope analysis.Besides,the possible future outlook of SAP is considered.

New food sources and production systems:a comparison of international regulations and China’s advancements in novel foods with synthetic biology

The global shift towards sustainable food systems has sparked innovations in food sources and production systems,including cell-based meat,plant-based food products,precision fermentation,and 3D food printing.These advancements pose regulatory challenges and opportunities,with China emerging as a critical player in adopting and regulating new food technologies.This review explores the international landscape of new food sources and production systems(NFPS),focusing on China’s role and regulatory approaches compared to global practices.Through this comparative analysis,we aim to contribute to the ongoing dialogue on food safety regulation,offering insights and recommendations for policymakers,industry stakeholders,and researchers engaged in the global food system’s evolution.This comprehensive overview underscores the dynamic nature of regulatory frameworks governing NFPS,highlighting the international efforts to ensure food safety,consumer protection,and the sustainable evolution of the food industry.

Life-threatening constrictive pericarditis accompanied by synthetic cannabinoid use:A case report and literature review

Rationale:Synthetic cannabinoids are increasingly used as recreational drugs and have been associated with adverse cardiovascular effects.However,reports of synthetic cannabinoids accompanied by constrictive pericarditis are limited.Patient’s concern:A 28-year-old male with a history of synthetic cannabinoid(Bonzai)abuse presented with chest discomfort,dyspnea,and lower extremity edema.Investigations revealed reduced left ventricular ejection fraction,elevated inflammatory markers,low electrocardiogram voltages,and atrial fibrillation.Diagnosis:Chest spiral computerized tomography scan and chest X-ray demonstrated pericardial calcification.Cardiac magnetic resonance imaging and right heart catheterization were done to confirm the possibility of constrictive pericarditis.Based on the patient’s addiction history and exclusion of rheumatologic and infectious causes,it was supposed that constrictive pericarditis and cardiomyopathy may be accompanied by synthetic cannabinoid use.Interventions:The patient received standard medical therapy,including loop diuretics for cardiomyopathy and constrictive pericarditis.Catheter ablation was recommended for his rhythm control,and he was planned for close monitoring of clinical and echocardiographic response and evaluation of the need for surgical pericardiectomy in the future.Outcomes:After 6 months follow-up,echocardiographic exam revealed no significant improvement in ventricular function.However,due to the high surgical risk,the patient’s poor compliance,and the continuation of drug abuse,he was not a good candidate for surgery according to our heart team’s decision.Lessons:Synthetic cannabinoids can trigger constrictive pericarditis,and clinicians should consider them when evaluating patients with compatible symptoms and exposure history.Further research on the cardiovascular effects of synthetic cannabinoids is needed and public education on potential harms is warranted.

The occurrence,inheritance,and segregation of complex genomic structural variation in synthetic Brassica napus

"Synthetic"allopolyploids recreated by interspecific hybridization play an important role in providing novel genomic variation for crop improvement.Such synthetic allopolyploids often undergo rapid genomic structural variation(SV).However,how such SV arises,is inherited and fixed,and how it affects important traits,has rarely been comprehensively and quantitively studied in advanced generation synthetic lines.A better understanding of these processes will aid breeders in knowing how to best utilize synthetic allopolyploids in breeding programs.Here,we analyzed three genetic mapping populations(735 DH lines)derived from crosses between advanced synthetic and conventional Brassica napus(rapeseed)lines,using whole-genome sequencing to determine genome composition.We observed high tolerance of large structural variants,particularly toward the telomeres,and preferential selection for balanced homoeologous exchanges(duplication/deletion events between the A and C genomes resulting in retention of gene/chromosome dosage between homoeologous chromosome pairs),including stable events involving whole chromosomes("pseudoeuploidy").Given the experimental design(all three populations shared a common parent),we were able to observe that parental SV was regularly inherited,showed genetic hitchhiking effects on segregation,and was one of the major factors inducing adjacent novel and larger SV.Surprisingly,novel SV occurred at low frequencies with no significant impacts on observed fertility and yield-related traits in the advanced generation synthetic lines.However,incorporating genome-wide SV in linkage mapping explained significantly more genetic variance for traits.Our results provide a framework for detecting and understanding the occurrence and inheritance of genomic SV in breeding programs,and support the use of synthetic parents as an important source of novel trait variation.

High-Precision DOA Estimation Method Based on Synthetic Aperture Technique

The existing direction-of-arrival(DOA)estimation methods only utilize the current received signals,which are susceptible to noise.In this paper,a method for DOA estimation based on a motion platform is proposed to achieve high-precision DOA estimation by utilizing past and present signals.The concept of synthetic aperture is introduced to construct a linear DOA estima-tion model.A DOA fine-tuning method based on the linear model is proposed to eliminate the lin-ear DOA variation,achieving a non-coherent accumulation of DOA estimations.Moreover,the baseband modulation and the phase modulation caused by the range history are compensated to achieve the coherent accumulation of all the DOA estimations.Simulation results show that the proposed method can significantly improve the DOA estimated accuracy at low signal-to-noise ratios(SNR).

A synthetic diagnostics platform for microwave imaging diagnostics in tokamaks

Interpreting experimental diagnostics data in tokamaks,while considering non-ideal effects,is challenging due to the complexity of plasmas.To address this challenge,a general synthetic diagnostics(GSD)platform has been established that facilitates microwave imaging reflectometry and electron cyclotron emission imaging.This platform utilizes plasma profiles as input and incorporates the finite-difference time domain,ray tracing and the radiative transfer equation to calculate the propagation of plasma spontaneous radiation and the external electromagnetic field in plasmas.Benchmark tests for classical cases have been conducted to verify the accuracy of every core module in the GSD platform.Finally,2D imaging of a typical electron temperature distribution is reproduced by this platform and the results are consistent with the given real experimental data.This platform also has the potential to be extended to 3D electromagnetic field simulations and other microwave diagnostics such as cross-polarization scattering.

Predictive modeling for postoperative delirium in elderly patients with abdominal malignancies using synthetic minority oversampling technique

BACKGROUND Postoperative delirium,particularly prevalent in elderly patients after abdominal cancer surgery,presents significant challenges in clinical management.AIM To develop a synthetic minority oversampling technique(SMOTE)-based model for predicting postoperative delirium in elderly abdominal cancer patients.METHODS In this retrospective cohort study,we analyzed data from 611 elderly patients who underwent abdominal malignant tumor surgery at our hospital between September 2020 and October 2022.The incidence of postoperative delirium was recorded for 7 d post-surgery.Patients were divided into delirium and non-delirium groups based on the occurrence of postoperative delirium or not.A multivariate logistic regression model was used to identify risk factors and develop a predictive model for postoperative delirium.The SMOTE technique was applied to enhance the model by oversampling the delirium cases.The model’s predictive accuracy was then validated.RESULTS In our study involving 611 elderly patients with abdominal malignant tumors,multivariate logistic regression analysis identified significant risk factors for postoperative delirium.These included the Charlson comorbidity index,American Society of Anesthesiologists classification,history of cerebrovascular disease,surgical duration,perioperative blood transfusion,and postoperative pain score.The incidence rate of postoperative delirium in our study was 22.91%.The original predictive model(P1)exhibited an area under the receiver operating characteristic curve of 0.862.In comparison,the SMOTE-based logistic early warning model(P2),which utilized the SMOTE oversampling algorithm,showed a slightly lower but comparable area under the curve of 0.856,suggesting no significant difference in performance between the two predictive approaches.CONCLUSION This study confirms that the SMOTE-enhanced predictive model for postoperative delirium in elderly abdominal tumor patients shows performance equivalent to that of traditional methods,effectively addressing data imbalance.

Modulated-ISRJ rejection using online dictionary learning for synthetic aperture radar imagery

In electromagnetic countermeasures circumstances,synthetic aperture radar(SAR)imagery usually suffers from severe quality degradation from modulated interrupt sampling repeater jamming(MISRJ),which usually owes considerable coherence with the SAR transmission waveform together with periodical modulation patterns.This paper develops an MISRJ suppression algorithm for SAR imagery with online dictionary learning.In the algorithm,the jamming modulation temporal properties are exploited with extracting and sorting MISRJ slices using fast-time autocorrelation.Online dictionary learning is followed to separate real signals from jamming slices.Under the learned representation,time-varying MISRJs are suppressed effectively.Both simulated and real-measured SAR data are also used to confirm advantages in suppressing time-varying MISRJs over traditional methods.

Exploration on Teaching Reform of Synthetic Biology Course Based on the New Engineering Concept

Synthetic biology is a new frontier of life science,which aims to design,transform and even synthesize organisms with engineering design concept.Doing a good job in the teaching of"synthetic biology"is of great significance to the cultivation and reserve of biotechnology professionals in China,and also has an important impact on students' employment competitiveness.Under the background of"new engineering",the course reform of"synthetic biology"was carried out in terms of the construction of teaching staff,teaching methods,students' participation and the innovation of course content,and specific reform suggestions were put forward,hoping to effectively promote the sustainable development of"synthetic biology"and effectively improve the quality of education.

CO_(2)capture costs of chemical looping combustion of biomass:A comparison of natural and synthetic oxygen carrier

Chemical looping combustion has the potential to be an efficient and low-cost technology capable of contributing to the reduction of the atmospheric concentration of CO_(2) in order to reach the 1.5/2°C goal and mitigate climate change.In this process,a metal oxide is used as oxygen carrier in a dual fluidized bed to generate clean CO_(2) via combustion of biomass.Most commonly,natural ores or synthetic materials are used as oxygen carrier whereas both must meet special requirements for the conversion of solid fuels.Synthetic oxygen carriers are characterized by higher reactivity at the expense of higher costs versus the lower-cost natural ores.To determine the viability of both possibilities,a techno-economic comparison of a synthetic material based on manganese,iron,and copper to the natural ore ilmenite was conducted.The synthetic oxygen carrier was characterized and tested in a pilot plant,where high combustion efficiencies up to 98.4%and carbon capture rates up to 98.5%were reached.The techno-economic assessment resulted in CO_(2) capture costs of 75 and 40€/tCO_(2) for the synthetic and natural ore route respectively,whereas a sensitivity analysis showed the high impact of production costs and attrition rates of the synthetic material.The synthetic oxygen carrier could break even with the natural ore in case of lower production costs and attrition rates,which could be reached by adapting the production process and recycling material.By comparison to state-of-the-art technologies,it is demonstrated that both routes are viable and the capture cost of CO_(2) could be reduced by implementing the chemical looping combustion technology.

A synthetic differencein-differences model for the influence of CR Express on Chongqing's economy

Purpose-The China-Europe Railway Express(CR Express)in Chongqing has operated regularly and undergone large-scale development.Its impact on Chongqing's economic growth has become increasingly evident,necessitating further research in this field.Design/methodology/approach-This study employs the opening of CR Express as a quasi-natural experiment,designating Chongqing,which inaugurated the CR Express in 2011,as the treatment group.13 provinces and cities that had not yet opened the CR Express until 2017 were selected as the control group.Utilizing panel data from 14 provinces across China spanning from 2006 to 2017,the synthetic control method(SCM)is employed to synthetically construct Chongqing.To quantify the difference in economic development levels between Chongqing with the operation of the CR express and Chongqing without its operation.Key metrics such as gross domestic product(GDP),per capita GDP,total retail sales of consumer goods,import and export value and the proportions of the secondary and tertiary industries are employed to measure urban economic development capabilities.Chongqing is designated as the experimental group,and a double-difference model is constructed to regress the operation of the CR Express against economic development capabilities.Robustness tests are conducted to validate the analytical results.Findings-The results indicate that,compared to provinces without the operation of the CR Express,the initiation of the CR Express in Chongqing significantly enhances the economic development level of the city.The opening of the CR Express exhibits a pronounced positive impact on Chongqing's economic development,and these findings remain robust and effective even after parallel trend tests and placebo tests.Originalitylvalue-The study represents an expansion of the theoretical framework.In contrast to previous studies that relied on a single indicator such as GDP,this study selects six indicators from the dimensions of economy,trade and industry to measure regional economic development capabilities.Furthermore,employing the grey relational analysis method,the study screens these indicators,thereby providing a theoretical basis for the selection of indicators for measuring regional economic development capabilities.