A Bayesian multi-model inference methodology for imprecise momentindependent global sensitivity analysis of rock structures

Traditional global sensitivity analysis(GSA)neglects the epistemic uncertainties associated with the probabilistic characteristics(i.e.type of distribution type and its parameters)of input rock properties emanating due to the small size of datasets while mapping the relative importance of properties to the model response.This paper proposes an augmented Bayesian multi-model inference(BMMI)coupled with GSA methodology(BMMI-GSA)to address this issue by estimating the imprecision in the momentindependent sensitivity indices of rock structures arising from the small size of input data.The methodology employs BMMI to quantify the epistemic uncertainties associated with model type and parameters of input properties.The estimated uncertainties are propagated in estimating imprecision in moment-independent Borgonovo’s indices by employing a reweighting approach on candidate probabilistic models.The proposed methodology is showcased for a rock slope prone to stress-controlled failure in the Himalayan region of India.The proposed methodology was superior to the conventional GSA(neglects all epistemic uncertainties)and Bayesian coupled GSA(B-GSA)(neglects model uncertainty)due to its capability to incorporate the uncertainties in both model type and parameters of properties.Imprecise Borgonovo’s indices estimated via proposed methodology provide the confidence intervals of the sensitivity indices instead of their fixed-point estimates,which makes the user more informed in the data collection efforts.Analyses performed with the varying sample sizes suggested that the uncertainties in sensitivity indices reduce significantly with the increasing sample sizes.The accurate importance ranking of properties was only possible via samples of large sizes.Further,the impact of the prior knowledge in terms of prior ranges and distributions was significant;hence,any related assumption should be made carefully.

Intention Estimation of Adversarial Spatial Target Based on Fuzzy Inference

Estimating the intention of space objects plays an important role in air-craft design,aviation safety,military and otherfields,and is an important refer-ence basis for air situation analysis and command decision-making.This paper studies an intention estimation method based on fuzzy theory,combining prob-ability to calculate the intention between two objects.This method takes a space object as the origin of coordinates,observes the target’s distance,speed,relative heading angle,altitude difference,steering trend and etc.,then introduces the spe-cific calculation methods of these parameters.Through calculation,values are input into the fuzzy inference model,andfinally the action intention of the target is obtained through the fuzzy rule table and historical weighted probability.Ver-ified by simulation experiment,the target intention inferred by this method is roughly the same as the actual behavior of the target,which proves that the meth-od for identifying the target intention is effective.

A Neuro T-Norm Fuzzy Logic Based System

In this study, we are first examining well-known approach to improve fuzzy reasoning model (FRM) by use of the genetic-based learning mechanism [1]. Later we propose our alternative way to build FRM, which has significant precision advantages and does not require any adjustment/learning. We put together neuro-fuzzy system (NFS) to connect the set of exemplar input feature vectors (FV) with associated output label (target), both represented by their membership functions (MF). Next unknown FV would be classified by getting upper value of current output MF. After that the fuzzy truths for all MF upper values are maximized and the label of the winner is considered as the class of the input FV. We use the knowledge in the exemplar-label pairs directly with no training. It sets up automatically and then classifies all input FV from the same population as the exemplar FVs. We show that our approach statistically is almost twice as accurate, as well-known genetic-based learning mechanism FRM.

A Novel Fuzzy Inference System-Based Endmember Extraction in Hyperspectral Images

Spectral unmixing helps to identify different components present in the spectral mixtures which occur in the uppermost layer of the area owing to the low spatial resolution of hyperspectral images.Most spectral unmixing methods are globally based and do not consider the spectral variability among its endmembers that occur due to illumination,atmospheric,and environmental conditions.Here,endmember bundle extraction plays a major role in overcoming the above-mentioned limitations leading to more accurate abundance fractions.Accordingly,a two-stage approach is proposed to extract endmembers through endmember bundles in hyperspectral images.The divide and conquer method is applied as the first step in subset images with only the non-redundant bands to extract endmembers using the Vertex Component Analysis(VCA)and N-FINDR algorithms.A fuzzy rule-based inference system utilizing spectral matching parameters is proposed in the second step to categorize endmembers.The endmember with the minimum error is chosen as the final endmember in each specific category.The proposed method is simple and automatically considers endmember variability in hyperspectral images.The efficiency of the proposed method is evaluated using two real hyperspectral datasets.The average spectral angle and abundance angle are used to analyze the performance measures.

An Automatic Threshold Selection Using ALO for Healthcare Duplicate Record Detection with Reciprocal Neuro-Fuzzy Inference System

ESystems based on EHRs(Electronic health records)have been in use for many years and their amplified realizations have been felt recently.They still have been pioneering collections of massive volumes of health data.Duplicate detections involve discovering records referring to the same practical components,indicating tasks,which are generally dependent on several input parameters that experts yield.Record linkage specifies the issue of finding identical records across various data sources.The similarity existing between two records is characterized based on domain-based similarity functions over different features.De-duplication of one dataset or the linkage of multiple data sets has become a highly significant operation in the data processing stages of different data mining programmes.The objective is to match all the records associated with the same entity.Various measures have been in use for representing the quality and complexity about data linkage algorithms,and many other novel metrics have been introduced.An outline of the problem existing in themeasurement of data linkage and de-duplication quality and complexity is presented.This article focuses on the reprocessing of health data that is horizontally divided among data custodians,with the purpose of custodians giving similar features to sets of patients.The first step in this technique is about an automatic selection of training examples with superior quality from the compared record pairs and the second step involves training the reciprocal neuro-fuzzy inference system(RANFIS)classifier.Using the Optimal Threshold classifier,it is presumed that there is information about the original match status for all compared record pairs(i.e.,Ant Lion Optimization),and therefore an optimal threshold can be computed based on the respective RANFIS.Febrl,Clinical Decision(CD),and Cork Open Research Archive(CORA)data repository help analyze the proposed method with evaluated benchmarks with current techniques.

An Adaptive Neuro-Fuzzy Inference System to Improve Fractional Order Controller Performance

The design and analysis of a fractional order proportional integral deri-vate(FOPID)controller integrated with an adaptive neuro-fuzzy inference system(ANFIS)is proposed in this study.Afirst order plus delay time plant model has been used to validate the ANFIS combined FOPID control scheme.In the pro-posed adaptive control structure,the intelligent ANFIS was designed such that it will dynamically adjust the fractional order factors(λandµ)of the FOPID(also known as PIλDµ)controller to achieve better control performance.When the plant experiences uncertainties like external load disturbances or sudden changes in the input parameters,the stability and robustness of the system can be achieved effec-tively with the proposed control scheme.Also,a modified structure of the FOPID controller has been used in the present system to enhance the dynamic perfor-mance of the controller.An extensive MATLAB software simulation study was made to verify the usefulness of the proposed control scheme.The study has been carried out under different operating conditions such as external disturbances and sudden changes in input parameters.The results obtained using the ANFIS-FOPID control scheme are also compared to the classical fractional order PIλDµand conventional PID control schemes to validate the advantages of the control-lers.The simulation results confirm the effectiveness of the ANFIS combined FOPID controller for the chosen plant model.Also,the proposed control scheme outperformed traditional control methods in various performance metrics such as rise time,settling time and error criteria.

基于EMD-BiLSTM-ANFIS的负荷区间预测

考虑到新型电力负荷随机性增强,传统的准确预测方法已无法满足要求,提出一种EMD-BiLSTM-ANFIS(Empirical Mode Decomposition-Bi-directional Long Short-Term Memory-Adaptive Network-based Fuzzy Inference System)分位数预测负荷概率密度的方法,使用负荷预测区间取代点预测的准确数值,能为电力系统分析与决策提供更多数据,增强预测的可靠性。首先将原始负荷序列通过EMD(Empirical Mode Decomposition)分解成若干分量,并通过计算样本熵分为3类分量。然后将重构后的3类分量与由相关性筛选的外界因素特征采用BiLSTM、ANFIS模型进行训练和分位数回归(QR:Quantile Regression),并将分量的预测区间结果累加得到最终负荷的预测区间。最后利用核密度估计输出任意时刻用户负荷概率密度预测结果。通过与CNN-BiLSTM(Convolutional Neural Network-Bidirectional Long Short-Term Memory)、LSTM(Long Short-Term Memory)模型对比点预测及区间预测结果,证明了该方法的有效性。

车辆主动悬架自适应变论域T-S模糊控制研究

针对传统变论域模糊控制存在过度依赖专家经验、伸缩因子参数不能自适应调整的问题,提出一种车辆主动悬架自适应变论域T-S模糊控制策略,从而提高车辆的行驶平顺性。结合神经网络和T-S模糊推理建立基于自适应神经模糊推理的一阶T-S模糊控制器,利用神经网络的自学习特性产生完善的模糊规则,进而在传统函数型伸缩因子的基础上,将系统误差和误差变化率作为动态参数引入伸缩因子中,实现伸缩因子参数的自适应调整,解决了传统函数型伸缩因子因参数确定难度大导致控制效果差的问题。通过随机工况下的仿真分析和基于相似理论的缩尺实验,对所提出算法的有效性和工况自适应性进行了验证。结果表明,所提出的自适应变论域T-S模糊控制策略具有较强的工况适应性,在不同车速、路面激励下均可有效提高车辆的平顺性并保证轮胎接地安全性。

APPLICATION STUDY ON ADAPTIVE NEURAL FUZZY INFERENCE MODEL IN COMPLEX SOCIAL-TECHNICAL SYSTEM

The adaptive neural fuzzy inference system （ANFIS） is used to make a ease study considering features of complex social-technical system with the target of increasing organizational efficiency of public scientific research institutions. An integrated ANFIS model is built and the effectiveness of the model is verified by means of investigation data and their processing results. The model merges the learning mechanism of neural network and the language inference ability of fuzzy system, and thereby remedies the defects of neural network and fuzzy logic system. Result of this case study shows that the model is suitable for complicated socio-technical systems and has bright application perspective to solve such problems of prediction, evaluation and policy-making in managerial fields.

基于量子衍生涡流算法和T⁃S模糊推理模型的储层岩性识别

鉴于梯度下降法易陷入局部极值、普通群智能优化算法易早熟收敛,提出一种基于量子衍生涡流算法(Quantum Vortex Search Algorithm,QVSA)和T⁃S模糊推理模型的岩性识别方法,QVSA具有操作简单、收敛速度快、寻优能力强等优点,有助于T⁃S模糊推理模型获得最优参数配置,从而实现储层岩性的准确识别。首先利用具有全局搜索能力的QVSA优化T⁃S模糊推理模型的各种参数;然后利用主成分分析方法降低获取的地震属性维度;再利用优化的T⁃S模糊推理模型识别储层岩性。实验结果表明,利用反映储层特征的8个地震属性识别储层岩性时,所提方法的识别正确率达到92%,比普通BP网络方法高5.1%,同时查准率、查全率、F1分数等指标也较BP网络方法提升明显。

基于D-S证据理论的岩爆预测方法研究

为了有效预测岩爆,提出基于D-S证据理论的岩爆预测方法.首先,选取与岩爆发生相关的6个指标因素作为证据体,并通过模糊物元框架和正态型隶属度函数构建证据体的基本概率分配.然后,利用K均值将证据体分类,并提出簇内证据用传统方式融合而簇间证据用权重方式融合的组合融合规则,以减轻高冲突证据融合的不利影响.最后,将模型应用在秦岭终南山公路隧道2号竖井工程,且与经验方法对比.为了分析预测过程的不确定性和估计岩爆发生概率,采用蒙特卡洛模拟进行抽样仿真,并通过Spearman秩相关系数衡量输入指标的全局敏感性.研究结果表明:输入指标在不同的岩爆案例的影响程度差异较大且方向不同;5个岩爆案例的发生概率在40.8%~70.1%之间.该模型表现出优异的预测分类性能,可为深埋地下工程岩爆预测提供参考.

基于T-S模糊故障树的驱动电机冷却系统可靠性分析

车用驱动电机液压冷却系统存在故障机理不确定等问题。本文应用模糊数描述其故障概率和故障程度,建立驱动电机冷却系统的T-S模糊故障树模型,计算系统模糊可能性,分析各部件的概率重要度和关键重要度,找出影响系统可靠性的关键部件。

混合差分和多种群粒子群算法的T-S模糊模型辨识

为提高T-S模型的辨识精度,针对基本粒子群优化(particle swarm optimization,PSO)算法T-S模型全局优化辨识问题,提出混合差分和多种群粒子群算法的T-S模糊模型辨识方法,将T-S模型前件参数和后件参数整体编码进行全局优化辨识.为避免基本粒子群的早熟收敛和后期收敛速度慢的缺陷对T-S模型辨识精度和速度的影响,算法将种群分为若干个子群,每个子群根据粒子适应度值自适应调整惯性权重,平衡了算法的开发和探索能力,对子群最优粒子,进行差分操作以增强算法的全局搜索能力,采用全局最优粒子替代随机子群的最优粒子以加强子群间的信息交流,维持粒子多样性.典型非线性系统和混沌系统的仿真结果表明,采用混合差分和多种群粒子群算法辨识的T-S模型具有更高的辨识精度.

基于改进PSO优化的RBF火灾预测系统

针对系统预测火灾状态不准确,导致火情变大造成人民群众生命和财产损失的问题,本文提出了一种基于改进粒子群优化的径向基神经网络多传感器数据融合算法的火灾状态预测系统。以温度、烟雾浓度、一氧化碳浓度为输入,以无火、阴燃火、明火的概率为输出,为了避免输出产生偏差,模糊推理系统对神经网络系统的输出做补偿。由于粒子群算法存在容易陷入局部最优的缺陷,采用一种非线性动态自适应惯性权重的改进粒子群优化算法(IPSO)。仿真实验表明,改进后的系统,以明火为例的平均绝对百分比误差达到0.169、均方根误差达到0.0021、平均绝对误差达到0.031。

A precise tidal prediction mechanism based on the combination of harmonic analysis and adaptive network-based fuzzy inference system model

An efficient and accurate prediction of a precise tidal level in estuaries and coastal areas is indispensable for the management and decision-making of human activity in the field wok of marine engineering. The variation of the tidal level is a time-varying process. The time-varying factors including interference from the external environment that cause the change of tides are fairly complicated. Furthermore, tidal variations are affected not only by periodic movement of celestial bodies but also by time-varying interference from the external environment. Consequently, for the efficient and precise tidal level prediction, a neuro-fuzzy hybrid technology based on the combination of harmonic analysis and adaptive network-based fuzzy inference system（ANFIS）model is utilized to construct a precise tidal level prediction system, which takes both advantages of the harmonic analysis method and the ANFIS network. The proposed prediction model is composed of two modules： the astronomical tide module caused by celestial bodies’ movement and the non-astronomical tide module caused by various meteorological and other environmental factors. To generate a fuzzy inference system（FIS） structure,three approaches which include grid partition（GP）, fuzzy c-means（FCM） and sub-clustering（SC） are used in the ANFIS network constructing process. Furthermore, to obtain the optimal ANFIS based prediction model, large numbers of simulation experiments are implemented for each FIS generating approach. In this tidal prediction study, the optimal ANFIS model is used to predict the non-astronomical tide module, while the conventional harmonic analysis model is used to predict the astronomical tide module. The final prediction result is performed by combining the estimation outputs of the harmonious analysis model and the optimal ANFIS model. To demonstrate the applicability and capability of the proposed novel prediction model, measured tidal level samples of Fort Pulaski tidal station are selected as the testing database. Simulation and experimental results confirm that the proposed prediction approach can achieve precise predictions for the tidal level with high accuracy, satisfactory convergence and stability.

Experimental investigation and adaptive neural fuzzy inference system prediction of copper recovery from flotation tailings by acid leaching in a batch agitated tank

The potential of copper recovery from flotation tailings was experimentally investigated using a laboratory-mixing tank. The experiments were performed with solid weight percentages of 30 wt%, 35 wt%, 40 wt% and 45 wt% in water. The measurements revealed that adding sulfuric acid all at once to the tank rapidly increased the efficiency of the leaching process, which was attributed to the rapid change in the acid concentration. The rate of iron dissolution from tailings was less than when the acid was added gradually. The sample with 40 wt% solid is recommended as an appropriate feed for the recovery of copper. The adaptive neural fuzzy system(ANFIS) was also used to predict the copper recovery from flotation tailings. The back-propagation algorithm and least squares method were applied for the training of ANFIS. The validation data was also applied to evaluate the performance of these models. Simulation results revealed that the testing results from these models were in good agreement with the experimental data.

随机工况下基于改进ANFIS的锂电池容量衰减实时估计

锂电池容量的衰减会影响其安全性和稳定性,准确的容量估计能够帮助用户进行更好的决策。目前,广泛使用的黑盒数据驱动模型因其不可解释性很难被应用于安全相关的领域中,并且大多方法都基于固定工况进行特征提取,对具有随机性的实际工况不具有普适性。因此,本文构建了一种基于随机工况数据的改进自适应模糊神将网络推理系统(ANFIS)。首先分析了容量衰减的影响因素,据此从电池监测数据中提取和筛选健康特征;其次系统内部利用激活机制简化系统结构,并引入衰减系数更好地拟合电池单体特性;然后通过自适应粒子滤波算法优化模糊聚类中心;最后使用NASA随机工况数据集验证了该系统的有效性,其容量估计RMSE为3.73%。与其他方法相比,本文提出的方法结果精度更高且具有一定的可解释性。

Fuzzy inference systems with no any rule base and linearly parameter growth

A class of new fuzzy inference systems New-FISs is presented.Compared with the standard fuzzy system, New-FIS is still a universal approximator and has no fuzzy rule base and linearly parameter growth. Thus, it effectively overcomes the second "curse of dimensionality":there is an exponential growth in the number of parameters of a fuzzy system as the number of input variables,resulting in surprisingly reduced computational complexity and being especially suitable for applications,where the complexity is of the first importance with respect to the approximation accuracy.

Bottleneck Prediction Method Based on Improved Adaptive Network-based Fuzzy Inference System (ANFIS) in Semiconductor Manufacturing System

Semiconductor manufacturing (SM) system is one of the most complicated hybrid processes involved continuously variable dynamical systems and discrete event dynamical systems. The optimization and scheduling of semiconductor fabrication has long been a hot research direction in automation. Bottleneck is the key factor to a SM system, which seriously influences the throughput rate, cycle time, time-delivery rate, etc. Efficient prediction for the bottleneck of a SM system provides the best support for the consequent scheduling. Because categorical data (product types, releasing strategies) and numerical data (work in process, processing time, utilization rate, buffer length, etc.) have significant effect on bottleneck, an improved adaptive network-based fuzzy inference system (ANFIS) was adopted in this study to predict bottleneck since conventional neural network-based methods accommodate only numerical inputs. In this improved ANFIS, the contribution of categorical inputs to firing strength is reflected through a transformation matrix. In order to tackle high-dimensional inputs, reduce the number of fuzzy rules and obtain high prediction accuracy, a fuzzy c-means method combining binary tree linear division method was applied to identify the initial structure of fuzzy inference system. According to the experimental results, the main-bottleneck and sub-bottleneck of SM system can be predicted accurately with the proposed method.

Safety diagnosis on coal mine production system based on fuzzy logic inference

According to the randomness and uncertainty of information in the safety diagnosis of coal mine production system (CMPS), a novel safety diagnosis method was proposed by applying fuzzy logic inference method, which consists of safety diagnosis fuzzifier, defuzzifier, fuzzy rules base and inference engine. Through the safety diagnosis on coal mine roadway rail transportation system, the result shows that the unsafe probability is about 0.5 influenced by no speed reduction and over quick turnout on roadway, which is the most possible reason leading to the accident of roadway rail transportation system.