Characteristics Prediction Method of Electro-hydraulic Servo Valve Based on Rough Set and Adaptive Neuro-fuzzy Inference System

Synthesis characteristics of the electro-hydraulic servo valve are key factors to determine eligibility of the hydraulic production. Testing all synthesis characteristics of the electro-hydraulic servo valve after assembling leads to high repair rate and reject rate, so accurate prediction for the synthesis characteristics in the industrial production is particular important in decreasing the repair rate and the reject rate of the product. However, the research in forecasting synthesis characteristics of the electro-hydraulic servo valve is rare. In this work, a hybrid prediction method was proposed based on rough set（RS） and adaptive neuro-fuzzy inference system（ANFIS） in order to predict synthesis characteristics of electro-hydraulic servo valve. Since the geometric factors affecting the synthesis characteristics of the electro-hydraulic servo valve are from workers＇ experience, the inputs of the prediction method are uncertain. RS-based attributes reduction was used as the preprocessor, and then the exact geometric factors affecting the synthesis characteristics of the electro-hydraulic servo valve were obtained. On the basis of the exact geometric factors, ANFIS was used to build the final prediction model. A typical electro-hydraulic servo valve production was used to demonstrate the proposed prediction method. The prediction results showed that the proposed prediction method was more applicable than the artificial neural networks（ANN） in predicting the synthesis characteristics of electro-hydraulic servo valve, and the proposed prediction method was a powerful tool to predict synthesis characteristics of the electro-hydraulic servo valve. Moreover, with the use of the advantages of RS and ANFIS, the highly effective forecasting framework in this study can also be applied to other problems involving synthesis characteristics forecasting.

On-line least squares support vector machine algorithm in gas prediction

Traditional coal mine safety prediction methods are off-line and do not have dynamic prediction functions.The Support Vector Machine(SVM) is a new machine learning algorithm that has excellent properties.The least squares support vector machine(LS-SVM) algorithm is an improved algorithm of SVM.But the common LS-SVM algorithm,used directly in safety predictions,has some problems.We have first studied gas prediction problems and the basic theory of LS-SVM.Given these problems,we have investigated the affect of the time factor about safety prediction and present an on-line prediction algorithm,based on LS-SVM.Finally,given our observed data,we used the on-line algorithm to predict gas emissions and used other related algorithm to compare its performance.The simulation results have verified the validity of the new algorithm.

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.

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.

Intent Inference Based Trajectory Prediction and Smooth for UAS in Low-Altitude Airspace with Geofence

In order to meet the higher accuracy requirement of trajectory prediction for Unmanned Aircraft System(UAS)in Unmanned Aircraft System Traffic Management(UTM),an Intent Based Trajectory Prediction and Smooth Based on Constrained State-dependent-transition Hybrid Estimation(CSDTHE-IBTPS)algorithm is proposed.Firstly,an intent inference method of UAS is constructed based on the information of ADS-B and geofence system.Moreover,a geofence layering algorithm is proposed.Secondly,the Flight Mode Change Points(FMCP)are used to define the relevant mode transition parameters and design the guard conditions,so as to generate the mode transition probability matrix and establish the continuous state-dependent-transition model.After that,the constrained Kalman filter(CKF)is applied to improve State-dependent-transition Hybrid Estimation(SDTHE)algorithm by applying equality constraint to the velocity of UAS in the straight phase and turning phase,respectively,and thus the constrained state-dependent-transition hybrid estimation(CSDTHE)algorithm is constructed.Finally,the results of intent inference and hybrid estimation are used to make trajectory prediction.Furthermore,each flight segment of trajectory is smoothed respectively by Rauch-Tung-Striebel(RTS)backward smooth method using the proposed CSDTHE-RTS algorithm,so as to obtain more accurate trajectory prediction results.The simulation shows that the proposed algorithm can reduce the errors of trajectory prediction and the time delay of intent inference.

Variational Inference Based Kernel Dynamic Bayesian Networks for Construction of Prediction Intervals for Industrial Time Series With Incomplete Input

Prediction intervals(PIs)for industrial time series can provide useful guidance for workers.Given that the failure of industrial sensors may cause the missing point in inputs,the existing kernel dynamic Bayesian networks(KDBN),serving as an effective method for PIs construction,suffer from high computational load using the stochastic algorithm for inference.This study proposes a variational inference method for the KDBN for the purpose of fast inference,which avoids the timeconsuming stochastic sampling.The proposed algorithm contains two stages.The first stage involves the inference of the missing inputs by using a local linearization based variational inference,and based on the computed posterior distributions over the missing inputs the second stage sees a Gaussian approximation for probability over the nodes in future time slices.To verify the effectiveness of the proposed method,a synthetic dataset and a practical dataset of generation flow of blast furnace gas(BFG)are employed with different ratios of missing inputs.The experimental results indicate that the proposed method can provide reliable PIs for the generation flow of BFG and it exhibits shorter computing time than the stochastic based one.

Bayesian inference-based wear prediction method for plain bearings under stationary mixed-friction conditions

This study introduces a method to predict the remaining useful life(RUL)of plain bearings operating under stationary,wear-critical conditions.In this method,the transient wear data of a coupled elastohydrodynamic lubrication(mixed-EHL)and wear simulation approach is used to parametrize a statistical,linear degradation model.The method incorporates Bayesian inference to update the linear degradation model throughout the runtime and thereby consider the transient,system-dependent wear progression within the RUL prediction.A case study is used to show the suitability of the proposed method.The results show that the method can be applied to three distinct types of post-wearing-in behavior:wearing-in with subsequent hydrodynamic,stationary wear,and progressive wear operation.While hydrodynamic operation leads to an infinite lifetime,the method is successfully applied to predict RUL in cases with stationary and progressive wear.

Bayesian inference for ammunition demand based on Gompertz distribution

Aiming at the problem that the consumption data of new ammunition is less and the demand is difficult to predict,combined with the law of ammunition consumption under different damage grades,a Bayesian inference method for ammunition demand based on Gompertz distribution is proposed.The Bayesian inference model based on Gompertz distribution is constructed,and the system contribution degree is introduced to determine the weight of the multi-source information.In the case where the prior distribution is known and the distribution of the field data is unknown,the consistency test is performed on the prior information,and the consistency test problem is transformed into the goodness of the fit test problem.Then the Bayesian inference is solved by the Markov chain-Monte Carlo(MCMC)method,and the ammunition demand under different damage grades is gained.The example verifies the accuracy of this method and solves the problem of ammunition demand prediction in the case of insufficient samples.

On-line real-time path planning of mobile robots in dynamic uncertain environment

A new path planning method for mobile robots in globally unknown environment with moving obstacles is pre- sented. With an autoregressive (AR) model to predict the future positions of moving obstacles, and the predicted position taken as the next position of moving obstacles, a motion path in dynamic uncertain environment is planned by means of an on-line real-time path planning technique based on polar coordinates in which the desirable direction angle is taken into consideration as an optimization index. The effectiveness, feasibility, high stability, perfect performance of obstacle avoidance, real-time and optimization capability are demonstrated by simulation examples.

Modeling of Microstructure Evolution and Mechanical Properties of Steel Plates Produced by Thermo-Mechanical Control Process and Its On-line Application

An integrated metallurgical model was developed to predict microstructure evolution and mechanical properties of low-carbon steel plates produced by TMCP. The metallurgical phenomena occurring during TMCP and mechanical properties were predicted for different process parameters. In the later passes full recrystallization becomes difficult to occur and higher residual strain remains in austenite after rolling. For the reasonable temperature and cooling schedule, yield strength of 30 mm plain carbon steel plate can reach 310 MPa. The first on-line application of prediction and control of microstructure and properties (PCMP) in the medium plate production was achieved. The predictions of the system are in good agreement with measurements.

Estimation of convergence of a high-speed railway tunnel in weak rocks using an adaptive neuro-fuzzy inference system(ANFIS) approach

Estimation of tunnel diameter convergence is a very important issue for tunneling construction,especially when the new Austrian tunneling method（NATM） is adopted.For this purpose,a systematic convergence measurement is usually implemented to adjust the design during the whole construction,and consequently deadly hazards can be prevented.In this study,a new fuzzy model capable of predicting the diameter convergences of a high-speed railway tunnel was developed on the basis of adaptive neuro-fuzzy inference system（ANFIS） approach.The proposed model used more than 1 000 datasets collected from two different tunnels,i.e.Daguan tunnel No.2 and Yaojia tunnel No.1,which are part of a tunnel located in Hunan Province,China.Six Takagi-Sugeno fuzzy inference systems were constructed by using subtractive clustering method.The data obtained from Daguan tunnel No.2 were used for model training,while the data from Yaojia tunnel No.1 were employed to evaluate the performance of the model.The input parameters include surrounding rock masses（SRM） rating index,ground engineering conditions（GEC） rating index,tunnel overburden（H）,rock density（？）,distance between monitoring station and working face（D）,and elapsed time（T）.The model’s performance was assessed by the variance account for（VAF）,root mean square error（RMSE）,mean absolute percentage error（MAPE） as well as the coefficient of determination（R2） between measured and predicted data as recommended by many researchers.The results showed excellent prediction accuracy and it was suggested that the proposed model can be used to estimate the tunnel convergence and convergence velocity.

Prediction of mechanical properties for deep drawing steel by deep learning

At present,iron and steel enterprises mainly use“after spot test ward”to control final product quality.However,it is impossible to realize on-line quality predetermining for all products by this traditional approach,hence claims and returns often occur,resulting in major eco-nomic losses of enterprises.In order to realize the on-line quality predetermining for steel products during manufacturing process,the predic-tion models of mechanical properties based on deep learning have been proposed in this work.First,the mechanical properties of deep drawing steels were predicted by using LSTM(long short team memory),GRU(gated recurrent unit)network,and GPR(Gaussian process regression)model,and prediction accuracy and learning efficiency for different models were also discussed.Then,on-line re-learning methods for transfer learning models and model parameters were proposed.The experimental results show that not only the prediction accuracy of optimized trans-fer learning models has been improved,but also predetermining time was shortened to meet real time requirements of on-line property prede-termining.The industrial production data of interstitial-free(IF)steel was used to demonstrate that R2 value of GRU model in training stage reaches more than 0.99,and R2 value in testing stage is more than 0.96.

Building a Tax Predictive Model Based on the Cloud Neural Network

Tax is very important to the whole country, so a scientific tax predictive model is needed. This paper introduces the theory of the cloud model. On this basis, it presents a cloud neural network, and analyzes the main factors which influence the tax revenue. Then if proposes a tax predictive model based on the cloud neural network. The model combines the strongpoints of the cloud model and the neural network. The experiment and simulation results show the effectiveness of the algorithm in this paper.

Bayesian Posterior Predictive Probability Happiness

We propose to determine the underlying causal structure of the elements of happiness from a set of empirically obtained data based on Bayesian. We consider the proposal to study happiness as a multidimensional construct which converges four dimensions with two different Bayesian techniques, in the first we use the Bonferroni correction to estimate the mean multiple comparisons, on this basis it is that we use the function t and a z-test, in both cases the results do not vary, so it is decided to present only those shown by the t test. In the Bayesian Multiple Linear Regression, we prove that happiness can be explained through three dimensions. The technical numerical used is MCMC, of four samples. The results show that the sample has not atypical behavior too and that suitable modifications can be described through a test. Another interesting result obtained is that the predictive probability for the case of sense positive of life and personal fulfillment dimensions exhibit a non-uniform variation.

DiagData： A Tool for Generation of Fuzzy Inference System

In this paper, it described the architecture of a tool called DiagData. This tool aims to use a large amount of data and information in the field of plant disease diagnostic to generate a disease predictive system. In this approach, techniques of data mining are used to extract knowledge from existing data. The data is extracted in the form of rules that are used in the development of a predictive intelligent system. Currently, the specification of these rules is built by an expert or data mining. When data mining on a large database is used, the number of generated rules is very complex too. The main goal of this work is minimize the rule generation time. The proposed tool, called DiagData, extracts knowledge automatically or semi-automatically from a database and uses it to build an intelligent system for disease prediction. In this work, the decision tree learning algorithm was used to generate the rules. A toolbox called Fuzzygen was used to generate a prediction system from rules generated by decision tree algorithm. The language used to implement this software was Java. The DiagData has been used in diseases prediction and diagnosis systems and in the validation of economic and environmental indicators in agricultural production systems. The validation process involved measurements and comparisons of the time spent to enter the rules by an expert with the time used to insert the same rules with the proposed tool. Thus, the tool was successfully validated, providing a reduction of time.

Design of Fine Life Cycle Prediction System for Failure of Medical Equipment

The inquiry process of traditional medical equipment maintenance management is complex,which has a negative impact on the efficiency and accuracy of medical equipment maintenance management and results in a significant amount of wasted time and resources.To properly predict the failure of medical equipment,a method for failure life cycle prediction of medical equipment was developed.The system is divided into four modules:the whole life cycle management module constructs the life cycle data set of medical devices from the three parts of the management in the early stage,the middle stage,and the later stage;the status detection module monitors the main operation data of the medical device components through the normal value of the relevant sensitive data in the whole life cycle management module;and the main function of the fault diagnosis module is based on the normal value of the relevant sensitive data in the whole life cycle management module.The inference machine diagnoses the operation data of the equipment;the fault prediction module constructs a fine prediction system based on the least square support vector machine algorithm and uses the AFS-ABC algorithm to optimize the model to obtain the optimal model with the regularized parameters and width parameters;the optimal model is then used to predict the failure of medical equipment.Comparative experiments are designed to determine whether or not the design system is effective.The results demonstrate that the suggested system accurately predicts the breakdown of ECG diagnostic equipment and incubators and has a high level of support and dependability.The design system has the minimum prediction error and the quickest program execution time compared to the comparison system.Hence,the design system is able to accurately predict the numerous causes and types of medical device failure.

Application of four machine-learning methods to predict short-horizon wind energy

Renewable energy has garnered attention due to the need for sustainable energy sources.Wind power has emerged as an alternative that has contributed to the transition towards cleaner energy.As the importance of wind energy grows,it can be crucial to provide forecasts that optimize its performance potential.Artificial intelligence(AI)methods have risen in prominence due to how well they can handle complicated systems while enhancing the accuracy of prediction.This study explored the area of AI to predict wind-energy production at a wind farm in Yalova,Turkey,using four different AI approaches:support vector machines(SVMs),decision trees,adaptive neuro-fuzzy inference systems(ANFIS)and artificial neural networks(ANNs).Wind speed and direction were considered as essential input parameters,with wind energy as the target parameter,and models are thoroughly evaluated using metrics such as the mean absolute percentage error(MAPE),coefficient of determination(R~2),and mean absolute error(MAE).The findings accentuate the superior performance of the SVM,which delivered the lowest MAPE(2.42%),the highest R~2(0.95),and the lowest MAE(71.21%)compared with actual values,while ANFIS was less effective in this context.The main aim of this comparative analysis was to rank the models to move to the next step in improving the least efficient methods by combining them with optimization algorithms,such as metaheuristic algorithms.

一种基于线性模糊信息粒的时间序列预测算法

[目的]由于经济、金融、环境和生态等多个领域中时间序列数据规模的持续增长,对其进行预测变得日益复杂,为了提高大规模时间序列的长期预测效率,探索构建模糊信息粒的创新方法,以准确反映数据集大小和趋势信息.[方法]首先,根据模糊拓展原理,研究各种模糊信息粒,包括区间型、三角型和高斯型模糊信息粒的距离定义.随后,结合时间序列片段的中心线段和离散程度信息,引入一类新颖的模糊信息粒.这些粒子可以有效捕捉指定时间范围内时间序列的趋势信息和离散程度,进一步地提出高斯型模糊信息粒距离的函数表达式和几何解释.为了将这些粒子用于时间序列预测,设计一类模糊推理预测系统,该系统可以利用历史数据构造模糊信息粒,并从高斯型模糊信息粒序列中提取模糊推理规则.[结果]高斯型模糊信息粒距离的函数表达式具有简洁的数学表示,可以合理地反映两个高斯模糊信息粒的中心线和离散程度的差异.模糊推理预测系统可以从高斯型模糊信息粒序列中提取有效的规则,实现时间序列的长期预测.实验结果表明,结合线性高斯模糊信息粒与模糊推理系统的预测方法在均方根误差和平均绝对百分比误差方面优于其他数值预测算法和其他模糊信息粒推理方法,包括自回归模型、自回归神经网络和回归向量机等.[结论]结合线性模糊信息粒和模糊推理系统的方法可以提高时间序列长期预测的效率.基于对数据集特征的合理抽象提出了一种新颖的线性模糊信息粒,并简洁地推导出了它们的距离定义.时间序列预测的成功表明,通过巧妙地设计信息粒,能够准确捕捉数据集中的关键特征,从而提高其他数据挖掘任务的效率,例如更快的计算速度和更准确的结果.

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。

基于主动推理的人机交互信任建构

人机交互信任问题日渐受到学界的广泛关注,不同学者基于各自立论旨趣,尝试对人机交互信任机制加以多面相的审思与建构。随着预测加工理论的兴起,相关探论更是得到了来自于计算神经科学向度的理论预设与方法论支撑。在此视域下,作为其基本理论构件之一的主动推理为人机交互信任机制的探索提供了一种整合性认知架构。由此,基于将人际互动推展至人-机共同构成的异质系统的适用性分析,以主动推理逻辑框架对人机交互信任样态与特征加以阐释,对于建构一种新的人机交互信任的实践路径无疑具有重要的意义。