基于贝叶斯神经网络的船用惯导定位修正方法

船用惯性导航系统(inertial navigation system, INS)通常采用与全球卫星导航系统(global navigation satellite system, GNSS)组合导航的方式提高其长时间工作的定位精度。当GNSS失效时,其定位误差将随时间迅速发散。针对这一问题,设计了采用反向传播神经网络(back propagate neural network, BPNN)、根据INS原始输出数据拟合修正经纬度的定位修正方案,提出了基于Bayesian算法更新网络权重系数的方法,结合理论分析和试验研究确定了神经元个数与训练数据集的分配方案。实船试验结果表明,当GNSS失效时,在后续2 h,通过24 h历史数据训练得到的神经网络修正INS位置,相比INS独立工作时的定位误差,修正后误差均值下降了63%,误差最大值下降约50%,最小值下降至0。

基于线性结构模型的古塔刚度中心识别方法研究

基于动力测试的古塔结构状态评估是其预防性保护工作的重要一环。该文结合动力测试方法,提出了一种基于线性结构模型进行古塔刚度中心识别的方法。基于偏心结构动力学理论凝练了非同轴刚度偏心的古塔计算模型与特征方程;基于Bayesian理论线性结构识别模型的推导及Gibbs抽样开展了结构物理参数识别,并结合经典算例对识别结果进行了验证;将该方法应用到我国重点保护文物开元寺塔的刚度中心识别中。

Remaining Useful Life Prediction Method for Multi-Component System Considering Maintenance:Subsea Christmas Tree System as A Case Study

Maintenance is an important technical measure to maintain and restore the performance status of equipment and ensure the safety of the production process in industrial production,and is an indispensable part of prediction and health management.However,most of the existing remaining useful life(RUL)prediction methods assume that there is no maintenance or only perfect maintenance during the whole life cycle;thus,the predicted RUL value of the system is obviously lower than its actual operating value.The complex environment of the system further increases the difficulty of maintenance,and its maintenance nodes and maintenance degree are limited by the construction period and working conditions,which increases the difficulty of RUL prediction.An RUL prediction method for a multi-omponent system based on the Wiener process considering maintenance is proposed.The performance degradation model of components is established by a dynamic Bayesian network as the initial model,which solves the uncertainty of insufficient data problems.Based on the experience of experts,the degree of degradation is divided according to Poisson process simulation random failure,and different maintenance strategies are used to estimate a variety of condition maintenance factors.An example of a subsea tree system is given to verify the effectiveness of the proposed method.

Rock mass quality prediction on tunnel faces with incomplete multi-source dataset via tree-augmented naive Bayesian network

Rock mass quality serves as a vital index for predicting the stability and safety status of rock tunnel faces.In tunneling practice,the rock mass quality is often assessed via a combination of qualitative and quantitative parameters.However,due to the harsh on-site construction conditions,it is rather difficult to obtain some of the evaluation parameters which are essential for the rock mass quality prediction.In this study,a novel improved Swin Transformer is proposed to detect,segment,and quantify rock mass characteristic parameters such as water leakage,fractures,weak interlayers.The site experiment results demonstrate that the improved Swin Transformer achieves optimal segmentation results and achieving accuracies of 92%,81%,and 86%for water leakage,fractures,and weak interlayers,respectively.A multisource rock tunnel face characteristic(RTFC)dataset includes 11 parameters for predicting rock mass quality is established.Considering the limitations in predictive performance of incomplete evaluation parameters exist in this dataset,a novel tree-augmented naive Bayesian network(BN)is proposed to address the challenge of the incomplete dataset and achieved a prediction accuracy of 88%.In comparison with other commonly used Machine Learning models the proposed BN-based approach proved an improved performance on predicting the rock mass quality with the incomplete dataset.By utilizing the established BN,a further sensitivity analysis is conducted to quantitatively evaluate the importance of the various parameters,results indicate that the rock strength and fractures parameter exert the most significant influence on rock mass quality.

Correlation between Combined Urinary Metal Exposure and Grip Strength under Three Statistical Models:A Cross-sectional Study in Rural Guangxi

Objective This study aimed to investigate the potential relationship between urinary metals copper(Cu),arsenic(As),strontium(Sr),barium(Ba),iron(Fe),lead(Pb)and manganese(Mn)and grip strength.Methods We used linear regression models,quantile g-computation and Bayesian kernel machine regression(BKMR)to assess the relationship between metals and grip strength.Results In the multimetal linear regression,Cu(β=−2.119),As(β=−1.318),Sr(β=−2.480),Ba(β=0.781),Fe(β=1.130)and Mn(β=−0.404)were significantly correlated with grip strength(P<0.05).The results of the quantile g-computation showed that the risk of occurrence of grip strength reduction was−1.007(95%confidence interval:−1.362,−0.652;P<0.001)when each quartile of the mixture of the seven metals was increased.Bayesian kernel function regression model analysis showed that mixtures of the seven metals had a negative overall effect on grip strength,with Cu,As and Sr being negatively associated with grip strength levels.In the total population,potential interactions were observed between As and Mn and between Cu and Mn(P_(interactions) of 0.003 and 0.018,respectively).Conclusion In summary,this study suggests that combined exposure to metal mixtures is negatively associated with grip strength.Cu,Sr and As were negatively correlated with grip strength levels,and there were potential interactions between As and Mn and between Cu and Mn.

System Reliability Analysis Method Based on T-S FTA and HE-BN

For high-reliability systems in military,aerospace,and railway fields,the challenges of reliability analysis lie in dealing with unclear failure mechanisms,complex fault relationships,lack of fault data,and uncertainty of fault states.To overcome these problems,this paper proposes a reliability analysismethod based on T-S fault tree analysis(T-S FTA)and Hyper-ellipsoidal Bayesian network(HE-BN).The method describes the connection between the various systemfault events by T-S fuzzy gates and translates them into a Bayesian network(BN)model.Combining the advantages of T-S fault tree modeling with the advantages of Bayesian network computation,a reliability modeling method is proposed that can fully reflect the fault characteristics of complex systems.Experts describe the degree of failure of the event in the form of interval numbers.The knowledge and experience of experts are fused with the D-S evidence theory to obtain the initial failure probability interval of the BN root node.Then,the Hyper-ellipsoidal model(HM)constrains the initial failure probability interval and constructs a HE-BN for the system.A reliability analysismethod is proposed to solve the problem of insufficient failure data and uncertainty in the degree of failure.The failure probability of the system is further calculated and the key components that affect the system’s reliability are identified.The proposedmethod accounts for the uncertainty and incompleteness of the failure data in complex multi-state systems and establishes an easily computable reliability model that fully reflects the characteristics of complex faults and accurately identifies system weaknesses.The feasibility and accuracy of the method are further verified by conducting case studies.

基于BN-AHP的UUV系统效能评估方法

提出了一种结合层次分析法(Analytic Hierarchy Process,AHP)和贝叶斯网络(Bayesian Networks,BN)的新型效能评估方法。首先,梳理提炼了UUV(Unmanned underwater vehicle,UUV)效能评估的五个维度;其次,利用AHP方法为每个维度建立了指标体系,并将其作为贝叶斯网络的节点输入,从而将不确定性因素纳入评估过程;随后,通过贝叶斯推理得出UUV效能评估值;最后,通过计算机仿真与传统AHP法,信息熵和人工神经网络法进行对比,实验结果表明,所提的方法相较于传统AHP方法和信息熵方法的评估结果更具收敛性和集中度,相较于人工神经网络方法可以在数据缺乏的情况下完成评估,同时在效能影响因子分析和方案优选方面更具区分度。

基于电网调度运行的智能防误方法研究

针对电网调度过程中,相关节点数据异常监测和防误不及时的问题,设计一个基于电网调度运行的智能防误系统。系统通过嵌入式技术,将精确字符集(BM)算法融入电网调度数据监测中,通过优化监测数据达到精确数据的目的;对于超过设定值的异常数据,利用支持向量机(SVM)—主成分分析(PCA)算法进行防误校核,实现电网调度智能防误。实验结果表明,该系统能通过故障线路电流出现明显的波动,更准确地诊断出故障元件;电网调度防误准确率稳定在96%左右,最高达97%,且变化趋势不大。

基于贝叶斯模型与VAR模型的蔬菜销量与定价预测

对商超蔬菜日销售数据进行数据透视筛选,利用同期平均法处理异常值和缺失值,生成年度日销售新数据.对单品蔬菜销量进行Shapiro-Wilks检验,发现不服从正态分布,但经相关性分析发现同类别不同蔬菜单品销量间存在显著相关性.构建同类蔬菜销量Bayesian模型,定量化表达单品间销量的关系,建立单品蔬菜销量的Bayesian模型刻画销量的主要影响因素,两个模型分析和预测结果与实际相符.构建VAR(2)模型,完成未来一周补货设计.以收益最大化为目标,在满足市场需求与销售空间限制下,建立优化模型,完成未来一天的补货量及定价设计,为商超蔬菜销售提供合理化建议.

可信联邦学习进化优化算法综述

With the development of edge devices and cloud computing,the question of how to accomplish machine learning and optimization tasks in a privacy-preserving and secure way has attracted increased attention over the past decade.As a privacy-preserving distributed machine learning method,federated learning(FL)has become popular in the last few years.However,the data privacy issue also occurs when solving optimization problems,which has received little attention so far.This survey paper is concerned with privacy-preserving optimization,with a focus on privacy-preserving data-driven evolutionary optimization.It aims to provide a roadmap from secure privacy-preserving learning to secure privacy-preserving optimization by summarizing security mechanisms and privacy-preserving approaches that can be employed in machine learning and optimization.We provide a formal definition of security and privacy in learning,followed by a comprehensive review of FL schemes and cryptographic privacy-preserving techniques.Then,we present ideas on the emerging area of privacy-preserving optimization,ranging from privacy-preserving distributed optimization to privacy-preserving evolutionary optimization and privacy-preserving Bayesian optimization(BO).We further provide a thorough security analysis of BO and evolutionary optimization methods from the perspective of inferring attacks and active attacks.On the basis of the above,an in-depth discussion is given to analyze what FL and distributed optimization strategies can be used for the design of federated optimization and what additional requirements are needed for achieving these strategies.Finally,we conclude the survey by outlining open questions and remaining challenges in federated data-driven optimization.We hope this survey can provide insights into the relationship between FL and federated optimization and will promote research interest in secure federated optimization.

Stochastic seismic inversion and Bayesian facies classification applied to porosity modeling and igneous rock identification

We apply stochastic seismic inversion and Bayesian facies classification for porosity modeling and igneous rock identification in the presalt interval of the Santos Basin. This integration of seismic and well-derived information enhances reservoir characterization. Stochastic inversion and Bayesian classification are powerful tools because they permit addressing the uncertainties in the model. We used the ES-MDA algorithm to achieve the realizations equivalent to the percentiles P10, P50, and P90 of acoustic impedance, a novel method for acoustic inversion in presalt. The facies were divided into five: reservoir 1,reservoir 2, tight carbonates, clayey rocks, and igneous rocks. To deal with the overlaps in acoustic impedance values of facies, we included geological information using a priori probability, indicating that structural highs are reservoir-dominated. To illustrate our approach, we conducted porosity modeling using facies-related rock-physics models for rock-physics inversion in an area with a well drilled in a coquina bank and evaluated the thickness and extension of an igneous intrusion near the carbonate-salt interface. The modeled porosity and the classified seismic facies are in good agreement with the ones observed in the wells. Notably, the coquinas bank presents an improvement in the porosity towards the top. The a priori probability model was crucial for limiting the clayey rocks to the structural lows. In Well B, the hit rate of the igneous rock in the three scenarios is higher than 60%, showing an excellent thickness-prediction capability.

Adaptive optimisation of explosive reactive armour for protection against kinetic energy and shaped charge threats

We evaluate an adaptive optimisation methodology,Bayesian optimisation(BO),for designing a minimum weight explosive reactive armour(ERA)for protection against a surrogate medium calibre kinetic energy(KE)long rod projectile and surrogate shaped charge(SC)warhead.We perform the optimisation using a conventional BO methodology and compare it with a conventional trial-and-error approach from a human expert.A third approach,utilising a novel human-machine teaming framework for BO is also evaluated.Data for the optimisation is generated using numerical simulations that are demonstrated to provide reasonable qualitative agreement with reference experiments.The human-machine teaming methodology is shown to identify the optimum ERA design in the fewest number of evaluations,outperforming both the stand-alone human and stand-alone BO methodologies.From a design space of almost 1800 configurations the human-machine teaming approach identifies the minimum weight ERA design in 10 samples.

An efficient physics-guided Bayesian framework for predicting ground settlement profile during excavations in clay

Recently,the application of Bayesian updating to predict excavation-induced deformation has proven successful and improved prediction accuracy significantly.However,updating the ground settlement profile,which is crucial for determining potential damage to nearby infrastructures,has received limited attention.To address this,this paper proposes a physics-guided simplified model combined with a Bayesian updating framework to accurately predict the ground settlement profile.The advantage of this model is that it eliminates the need for complex finite element modeling and makes the updating framework user-friendly.Furthermore,the model is physically interpretable,which can provide valuable references for construction adjustments.The effectiveness of the proposed method is demonstrated through two field case studies,showing that it can yield satisfactory predictions for the settlement profile.

Analysis of Progressively Type-Ⅱ Inverted Generalized Gamma Censored Data and Its Engineering Application

A novel inverted generalized gamma(IGG)distribution,proposed for data modelling with an upside-down bathtub hazard rate,is considered.In many real-world practical situations,when a researcher wants to conduct a comparative study of the life testing of items based on cost and duration of testing,censoring strategies are frequently used.From this point of view,in the presence of censored data compiled from the most well-known progressively Type-Ⅱ censoring technique,this study examines different parameters of the IGG distribution.From a classical point of view,the likelihood and product of spacing estimation methods are considered.Observed Fisher information and the deltamethod are used to obtain the approximate confidence intervals for any unknown parametric function of the suggestedmodel.In the Bayesian paradigm,the same traditional inferential approaches are used to estimate all unknown subjects.Markov-Chain with Monte-Carlo steps are considered to approximate all Bayes’findings.Extensive numerical comparisons are presented to examine the performance of the proposed methodologies using various criteria of accuracy.Further,using several optimality criteria,the optimumprogressive censoring design is suggested.To highlight how the proposed estimators can be used in practice and to verify the flexibility of the proposed model,we analyze the failure times of twenty mechanical components of a diesel engine.

A Function-Aware Mimic Defense Theory and Its Practice

In recent years,network attacks have been characterized by diversification and scale,which indicates a requirement for defense strategies to sacrifice generalizability for higher security.As the latest theoretical achievement in active defense,mimic defense demonstrates high robustness against complex attacks.This study proposes a Function-aware,Bayesian adjudication,and Adaptive updating Mimic Defense(FBAMD)theory for addressing the current problems of existing work including limited ability to resist unknown threats,imprecise heterogeneous metrics,and over-reliance on relatively-correct axiom.FBAMD incorporates three critical steps.Firstly,the common features of executors’vulnerabilities are obtained from the perspective of the functional implementation(i.e,input-output relationships extraction).Secondly,a new adjudication mechanism considering Bayes’theory is proposed by leveraging the advantages of both current results and historical confidence.Furthermore,posterior confidence can be updated regularly with prior adjudication information,which provides mimic system adaptability.The experimental analysis shows that FBAMD exhibits the best performance in the face of different types of attacks compared to the state-of-the-art over real-world datasets.This study presents a promising step toward the theo-retical innovation of mimic defense.

Accelerated design of high-performance Mg-Mn-based magnesium alloys based on novel bayesian optimization

Magnesium(Mg),being the lightest structural metal,holds immense potential for widespread applications in various fields.The development of high-performance and cost-effective Mg alloys is crucial to further advancing their commercial utilization.With the rapid advancement of machine learning(ML)technology in recent years,the“data-driven''approach for alloy design has provided new perspectives and opportunities for enhancing the performance of Mg alloys.This paper introduces a novel regression-based Bayesian optimization active learning model(RBOALM)for the development of high-performance Mg-Mn-based wrought alloys.RBOALM employs active learning to automatically explore optimal alloy compositions and process parameters within predefined ranges,facilitating the discovery of superior alloy combinations.This model further integrates pre-established regression models as surrogate functions in Bayesian optimization,significantly enhancing the precision of the design process.Leveraging RBOALM,several new high-performance alloys have been successfully designed and prepared.Notably,after mechanical property testing of the designed alloys,the Mg-2.1Zn-2.0Mn-0.5Sn-0.1Ca alloy demonstrates exceptional mechanical properties,including an ultimate tensile strength of 406 MPa,a yield strength of 287 MPa,and a 23%fracture elongation.Furthermore,the Mg-2.7Mn-0.5Al-0.1Ca alloy exhibits an ultimate tensile strength of 211 MPa,coupled with a remarkable 41%fracture elongation.

Parameter Estimation of a Valve-Controlled Cylinder System Model Based on Bench Test and Operating Data Fusion

The accurate estimation of parameters is the premise for establishing a high-fidelity simulation model of a valve-controlled cylinder system.Bench test data are easily obtained,but it is challenging to emulate actual loads in the research on parameter estimation of valve-controlled cylinder system.Despite the actual load information contained in the operating data of the control valve,its acquisition remains challenging.This paper proposes a method that fuses bench test and operating data for parameter estimation to address the aforementioned problems.The proposed method is based on Bayesian theory,and its core is a pool fusion of prior information from bench test and operating data.Firstly,a system model is established,and the parameters in the model are analysed.Secondly,the bench and operating data of the system are collected.Then,the model parameters and weight coefficients are estimated using the data fusion method.Finally,the estimated effects of the data fusion method,Bayesian method,and particle swarm optimisation(PSO)algorithm on system model parameters are compared.The research shows that the weight coefficient represents the contribution of different prior information to the parameter estimation result.The effect of parameter estimation based on the data fusion method is better than that of the Bayesian method and the PSO algorithm.Increasing load complexity leads to a decrease in model accuracy,highlighting the crucial role of the data fusion method in parameter estimation studies.

Comparison of isotope-based linear and Bayesian mixing models in determining moisture recycling ratio

Stable water isotopes are natural tracers quantifying the contribution of moisture recycling to local precipitation,i.e.,the moisture recycling ratio,but various isotope-based models usually lead to different results,which affects the accuracy of local moisture recycling.In this study,a total of 18 stations from four typical areas in China were selected to compare the performance of isotope-based linear and Bayesian mixing models and to determine local moisture recycling ratio.Among the three vapor sources including advection,transpiration,and surface evaporation,the advection vapor usually played a dominant role,and the contribution of surface evaporation was less than that of transpiration.When the abnormal values were ignored,the arithmetic averages of differences between isotope-based linear and the Bayesian mixing models were 0.9%for transpiration,0.2%for surface evaporation,and–1.1%for advection,respectively,and the medians were 0.5%,0.2%,and–0.8%,respectively.The importance of transpiration was slightly less for most cases when the Bayesian mixing model was applied,and the contribution of advection was relatively larger.The Bayesian mixing model was found to perform better in determining an efficient solution since linear model sometimes resulted in negative contribution ratios.Sensitivity test with two isotope scenarios indicated that the Bayesian model had a relatively low sensitivity to the changes in isotope input,and it was important to accurately estimate the isotopes in precipitation vapor.Generally,the Bayesian mixing model should be recommended instead of a linear model.The findings are useful for understanding the performance of isotope-based linear and Bayesian mixing models under various climate backgrounds.

Enhancing Indoor User Localization:An Adaptive Bayesian Approach for Multi-Floor Environments

Indoor localization systems are crucial in addressing the limitations of traditional global positioning system(GPS)in indoor environments due to signal attenuation issues.As complex indoor spaces become more sophisticated,indoor localization systems become essential for improving user experience,safety,and operational efficiency.Indoor localization methods based on Wi-Fi fingerprints require a high-density location fingerprint database,but this can increase the computational burden in the online phase.Bayesian networks,which integrate prior knowledge or domain expertise,are an effective solution for accurately determining indoor user locations.These networks use probabilistic reasoning to model relationships among various localization parameters for indoor environments that are challenging to navigate.This article proposes an adaptive Bayesian model for multi-floor environments based on fingerprinting techniques to minimize errors in estimating user location.The proposed system is an off-the-shelf solution that uses existing Wi-Fi infrastructures to estimate user’s location.It operates in both online and offline phases.In the offline phase,a mobile device with Wi-Fi capability collects radio signals,while in the online phase,generating samples using Gibbs sampling based on the proposed Bayesian model and radio map to predict user’s location.Experimental results unequivocally showcase the superior performance of the proposed model when compared to other existing models and methods.The proposed model achieved an impressive lower average localization error,surpassing the accuracy of competing approaches.Notably,this noteworthy achievement was attained with minimal reliance on reference points,underscoring the efficiency and efficacy of the proposed model in accurately estimating user locations in indoor environments.

A Constrained Local Neighborhood Approach for Efficient Markov Blanket Discovery in Undirected Independent Graphs

When learning the structure of a Bayesian network,the search space expands significantly as the network size and the number of nodes increase,leading to a noticeable decrease in algorithm efficiency.Traditional constraint-based methods typically rely on the results of conditional independence tests.However,excessive reliance on these test results can lead to a series of problems,including increased computational complexity and inaccurate results,especially when dealing with large-scale networks where performance bottlenecks are particularly evident.To overcome these challenges,we propose a Markov blanket discovery algorithm based on constrained local neighborhoods for constructing undirected independence graphs.This method uses the Markov blanket discovery algorithm to refine the constraints in the initial search space,sets an appropriate constraint radius,thereby reducing the initial computational cost of the algorithm and effectively narrowing the initial solution range.Specifically,the method first determines the local neighborhood space to limit the search range,thereby reducing the number of possible graph structures that need to be considered.This process not only improves the accuracy of the search space constraints but also significantly reduces the number of conditional independence tests.By performing conditional independence tests within the local neighborhood of each node,the method avoids comprehensive tests across the entire network,greatly reducing computational complexity.At the same time,the setting of the constraint radius further improves computational efficiency while ensuring accuracy.Compared to other algorithms,this method can quickly and efficiently construct undirected independence graphs while maintaining high accuracy.Experimental simulation results show that,this method has significant advantages in obtaining the structure of undirected independence graphs,not only maintaining an accuracy of over 96%but also reducing the number of conditional independence tests by at least 50%.This significant performance improvement is due to the effective constraint on the search space and the fine control of computational costs.