Prediction and optimization of a ceramic casting process using a hierarchical hybrid system of neural networks and fuzzy logic

This paper is a case study that describes a hybrid system integrating fuzzy logic, neural networks and algorithmic optimization for use in the ceramics industry. A prediction module estimates two quality metrics of slip-cast pieces through the simultaneous execution of two neural networks. A process improvement algorithm optimizes controllable process settings using the neural network prediction module in the objective function. An expert system module contains a hierarchy of two fuzzy logic rule bases. The rule bases prescribe processing times customized to individual production lines given ambient conditions, mold characteristics and the neural network predictions. This paper demonstrates the applicability of newer computational techniques to a very traditional manufacturing process and the system has been implemented at a major US plant.     

Application of Hybrid Learning Neural Fuzzy Systems in Reliability Prediction

This study presents a hybrid learning neural fuzzy system for accurately predicting system reliability. Neural fuzzy system learning with and without supervision has been successfully applied in control systems and pattern recognition problems. This investigation modifies the hybrid learning fuzzy systems to accept time series data and therefore examines the feasibility of reliability prediction. Two neural network systems are developed for solving different reliability prediction problems. Additionally, a scaled conjugate gradient learning method is applied to accelerate the training in the supervised learning phase. Several existing approaches, including feed‐forward multilayer perceptron (MLP) networks, radial basis function (RBF) neural networks and Box–Jenkins autoregressive integrated moving average (ARIMA) models, are used to compare the performance of the reliability prediction. The numerical results demonstrate that the neural fuzzy systems have higher prediction accuracy than the other methods. Copyright © 2005 John Wiley & Sons, Ltd.     

基于模糊神经网络的电子产品包装防护综合评价方法

从可靠性、方便性、经济性、环保性等4个方面建立了电子产品包装防护综合评价指标体系,并采用模糊神经网络的方法对电子产品包装防护进行综合评价.实例分析表明,这种方法适用于电子产品包装防护综合评价.     

基于蚁群算法优化BP神经网络的港口吞吐量预测

利用蚁群算法优化反向传播神经网络的初始权值、阈值,建立预测模型,对港口货物吞吐量进行预测。蚁群算法具有全局搜索能力,分布式计算和鲁棒性强等特点,有利于加快反向传播神经网络的收敛速度,避免易陷入局部极值的问题,提高建模精度。在港口吞吐量预测中的应用表明:蚁群算法优化BP神经网络模型、模糊神经网络预测模型、RBF预测模型及BP预测模型的平均绝对百分比误差分别为2.826%、3.734%、4.990%和6.566%;同时,蚁群算法优化BP神经网络模型收敛速度最快。与传统BP神经网络、RBF网络及模糊神经网络相比,蚁群算法优化BP神经网络模型、模糊神经网络预测模型、RBF预测模型及BP预测模型的平均绝对百分比误差分别为2.826%、3.734%、4.990%和6.566%。     

计算智能技术在陶瓷材料优化设计中的应用

综述了计算智能在陶瓷材料优化设计中的应用现状,阐明了利用人工神经网络以及遗传算法预测陶瓷材料性能和组分优化的方法,介绍了人工神经网络、遗传算法与免疫算法和模拟退火算法相结合的高效计算智能方法以及模糊神经网络在材料设计中的应用,分析了陶瓷材料优化设计中存在的问题并提出了今后的研究方向。     

基于自适应模糊神经网络的发动机故障诊断

发动机是车辆的核心部件,及时有效地发现并排除故障,对降低维修费用,减少经济损失,增加发动机工作时的可靠性,避免事故发生具有重大的意义。以某型号发动机为研究对象,运用测试技术、信号处理、小波分析、神经网络和模糊控制理论,提出了自适应模糊神经网络发动机故障诊断。首先建立了发动机故障信号采集试验台,在试验台上人工模拟四种工况,通过加速度传感器采集正常工况和异常工况的振动信号。再利用小波理论对采集到的振动信号进行消噪处理,提高信噪比,并提取出故障信号的特征值,作为网络训练和测试的样本数据。用样本数据训练和检测自适应模糊神经网络,即对发动机故障进行模式识别。通过仿真分析,取得了很好的诊断效果;同时与传统的BP神经网络故障诊断方法进行对比,无论在诊断精度上还是学习速度上,模糊神经网络在故障诊断中更具有优势。     

基于BP神经网络的引信贮存可靠性预计

根据引信贮存可靠性的特点和BP神经网络结构．建立了引信贮存可靠性预计的神经网络模型;结合库存引信可靠性的实测数据,应用BP神经网络的误差反向传播算法．对引信贮存可靠度进行了训练并预计出引信贮存可靠度下限值,并与极大似然估计的可靠度下限值进行了比较,结果相吻合．神经网络在引信贮存可靠性预计中的应用．对处理目前库存引信的决策具有重要意义．     

空调系统神经模糊控制器——结构和算法

提出了一种适用于空调系统控制的新型神经模糊控制器。这种神经模糊控制器将神经网络和模糊控制紧密结合，是一种以神经网络表示模糊控制规则的模糊控制系统，控制推理基于模糊推理的精确值法，神经网络采用后向传播（BP）学习算法。本文论述这种神经模糊控制器的结构和算法，其仿真和优化将另文论述。     

Fuzzy Reliability Analysis of the Washing System in a Paper Plant for Components with Different Membership Function

The washing system in paper plant is a complex engineering system that needs to develop effective maintenance programs for enhancing its performance via reliability analysis. The reliability analysis of these systems require precise numerical data which may be very difficult to obtain in desired crisp form due to uncertainty. In general, triangular fuzzy number are used to quantify data uncertainty and fuzzy arithmetic operations are employed which give vide range of prediction for each computed reliability index due to accumulating phenomenon of fuzziness. To reduce the range of prediction of system reliability and fasten the computation process, this paper presents \(T_\omega \) (weakest t-norm) based generalized fuzzy lambda–tau technique in which different fuzzy membership functions are used to quantify uncertainty while \(\alpha \)-cut and \(T_\omega \) based approximate fuzzy arithmetic operations are employed for computation. The advantage of this technique is that this technique uses different fuzzy numbers as input to quantify different types of uncertainties and gives fuzzy reliability indices of the system having shape preserving characteristic, fitter decision values with compressed range of prediction under vague environment which is better for strong decision making to improve system performance. To show the effectiveness of the presented approach, computed results have been compared with results obtained from four other existing approaches. Moreover, this paper uses extended Tanaka et al. (Komal in Ocean Eng 155:278–294, 2018b) approach to rank the critical components of the system. Sensitivity, long run reliability and availability analyses have also been conducted to analyse the impact of variation of different reliability indices and time respectively on system performance.     

基于遗传算法和灰色神经网络的电力机车产品需求预测方法

目的 应对快速多变的市场,提前预知市场发展,制定相应的排产计划,使企业在竞争中占据先发优势。方法 目前基于灰色神经网络的预测算法,准确地预测产品需求通常需要连续且大量的样本数据,对小数据非线性系统的预测结果精确度低、可靠性差,针对这一问题,提出一种耦合遗传算法的灰色神经网络预测方法,综合灰色模型和神经网络理论,构建了面向产品订单量需求预测的灰色神经网络模型;通过电力机车产品实例分析了模型的预测性能;为解决预测过程中模型早熟收敛的问题,利用遗传算法对训练网络的权重和阈值进行了迭代优化。结论 研究结果表明,优化后产品预测模型的精确性和鲁棒性得到提高,验证了所设计方法的可行性。     

基于模糊神经网络与主成分分析的磨削表面粗糙度在线预测

基于声发射和振动信号提出了一种模糊神经网络和主成分分析的表面粗糙度预测方法,以提高磨削过程中工件表面粗糙度识别的准确性。首先,采集磨削程中声发射与振动信号,提取相关时域特征、频域特征和小波包特征参数,利用主成分分析对特征量进行降维优化;然后,构建表面粗糙度模糊神经网络预测模型,将信号特征量与表面粗糙度作为模糊神经网络的输入和输出;最后,对模型进行训练,并对表面粗糙度预测精度进行验证。实验结果表明:通过主成分分析(PCA)方法对声发射和振动信号特征量进行降维得到5个主成分,以此建立的模糊神经网络表面粗糙度预测模型的效果精度可达到91%以上,与局部线性嵌入和多维标度法降维方法相比,PCA方法降维后的特征所含信息更优,预测准确度更高。     

基于自适应RBF模糊神经网络的旋转柔性铰接梁的振动控制

由柔性关节连接中心刚体和挠性附件的刚柔耦合系统广泛应用于卫星太阳能帆板、空间机器人等领域中,在调姿或者外部扰动带来振动时,将影响系统的稳定性和指向精度,对带有铰接结构的柔性梁的影响更甚。设计并建立了带有柔性关节（谐波齿轮）的旋转柔性铰接梁实验平台,进行了基于压电传感器测量信号的振动频响特性分析,分别采用PD控制和自适应RBF模糊神经网络控制算法,进行了基于电机驱动的位置设定点弯曲振动的主动控制研究。实验比较结果验证设计的自适应RBF模糊神经网络控制算法能够快速抑制振动。

      

Interpretation and compensation of backlash error data in machine centers for intelligent predictive maintenance using ANNs

It is especially significant for a manufacturing company to select a proper maintenance policy because maintenance impacts not only on economy,reliability and availability but also on personnel safety.This article reports on research in the backlash error data interpretation and compensation for intelligent predictive maintenance in machine centers based on artificial neural networks(ANNs).The backlash error,measurement system and prediction methods are analyzed in detail.The result indicates that it is possible to predict and compensate for the backlash error in both forward and backward directions in machine centers.     

NAROAS: a neural network-based advanced operator support system for the assessment of systems reliability

We have developed and implemented a computerized reliability monitoring system for nuclear power plant applications, based on a neural network. The developed computer program is a new tool related to operator decision support systems, in case of component failures, for the determination of test and maintenance policies during normal operation or to follow an incident sequence in a nuclear power plant. The NAROAS (Neural Network Advanced Reliability Advisory System) computer system has been developed as a modularized integrated system in a C++ Builder environment, using a Hopfield neural network instead of fault trees, to follow and control the different system configurations, for interventions as quickly as possible at the plant. The observed results are comparable and similar to those of other computer system results. As shown, the application of this neural network contributes to the state of the art of risk monitoring systems by turning it easier to perform online reliability calculations in the context of probabilistic safety assessments of nuclear power plants.     

基于卷积神经网络的模糊车牌自动识别

目前,清晰的车牌识别算法已经成熟,但是对于人眼不能识别的模糊车牌,传统车牌识别算法的识别率较低或者根本无法识别。鉴于此,提出了一种基于卷积神经网络的车牌字符识别算法。制作了含9 720幅模糊字符样本集,用8 748幅样本对卷积神经网络进行训练,测试样本时,先对模糊车牌字符进行盲分割等预处理,再调用训练好的卷积神经网络对盲分割后的字符进行识别。实验结果表明:该算法对训练集的准确识别率约为99.17%,对测试集的准确识别率约为93.32%,这说明该算法对模糊车牌的识别具有鲁棒性,能应用于各种场景。     

Identification and Assessment of Factors Influencing Human Reliability in Maintenance Using Fuzzy Cognitive Maps

Human element forms an inevitable part of maintenance activity and gets affected by a variety of interacting factors, ranging from environmental, organizational, job factors, and so on to personal characteristics, which bring in inherent variability in its reliability. Assessment of impact of these factors is, therefore, critical for human reliability estimation in maintenance. In every probabilistic risk, safety or maintenance analysis, human reliability does act as an effective aspect to assess implications of various aspects of the human performance. But the main constraint with various human reliability analysis methods is in judging the important human performance influencing factors. Because of high degree of uncertainty and variability that characterizes the plant maintenance environment, it is proposed to use the soft computing technique of fuzzy cognitive maps in exploring the importance of performance shaping factors in maintenance scenario. For this purpose, the maintenance environment is modeled in terms of factors affecting human reliability using cognitive maps. The causal relationships among these factors are explored and simulations performed to quantify its effect on the human reliability. The applicability of the methodology is demonstrated through an example. Copyright © 2013 John Wiley & Sons, Ltd.     

基于机器学习的钛合金弹性模量预测方法研究

目的 探索一种高效可行的预测方法以提高钛合金弹性模量的预测精度,采用第一性原理计算方法与机器学习相结合的方式建立高精度的预测模型。方法 通过数据挖掘获取材料数据库中钛合金的力学性质微观结构参数,结合第一性原理计算方法构建初始数据集,并对其进行预处理,包括噪音消除、归一化及标准化,以得到高质量的数据集。同时,采用随机森林特征重要性分析法对输入参数进行筛选,去除弱相关变量以降低预测模型的复杂度。在此基础上,构建随机森林模型、支持向量机模型、BP神经网络模型及优化后的GA-BP神经网络模型,综合对比各模型的回归能力,分析误差后选出最优的算法模型。结果 最终建立了钛合金弹性模量预测模型,其中随机森林模型、支持向量机模型、BP神经网络模型、GA-BP神经网络模型的预测相关系数R分别为0.836、0.943、0.917、0.986。结论 GA-BP模型对弹性模量的预测误差基本保持在5%～7%。遗传算法可以优化BP神经网络的权值和阈值,使预测精度大幅提升。说明通过该方法可以实现钛合金弹性模量的预测,大大节省研发和实验成本,加快高性能材料的筛选。     

基于小波神经网络辨识器的模糊神经自适应控制在VAV空调系统中的应用

针对空调温度控制的大惯性、大滞后、非线性等特点,提出采用基于小波神经网络辨识器的模糊神经自适应控制的中央空调房间温度控制器的设计方案。由于小波神经网络的非线性映射能力比一般神经网络要强,所以基于小波神经网络的辨识器可以获得很高的辨识精度。而且,模糊神经自适应控制器随着系统动态特性的改变可以在线改变其控制规则,从而进行客观准确的控制。与普通模糊控制方法相比较,仿真试验说明系统设计的有效性。     

于GA-BP模糊神经网络的商业银行信用风险评估

研究了商业银行信用风险评估的现状,针对单独应用BP神经网络评估信用风险时存在的缺陷,提出了基于遗传算法优化模糊BP神经网络的信用风险评估新模型.通过遗传算法训练模糊BP神经网络,克服网络建模中产生的局部极小的缺点,提高了风险评估的准确性.最后,利用Matlab软件对样本数据进行训练和测试,仿真结果表明所构造的评估模型预测误差非常小.     

A Fuzzy Neural Network for Fault Pattern Recognition

1　ＩｎｔｒｏｄｕｃｔｉｏｎＩｎｍａｔｈｅｍａｔｉｃｓ,ｆａｕｌｔｒｅｃｏｇｎｉｔｉｏｎｃａｎｂｅｓｕｍｍｅｄｕｐａｓａｍａｐｐｉｎｇｐｒｏｂｌｅｍｂｅｔｗｅｅｎｆａｕｌｔａｇｇｒｅ ｇａｔｅａｎｄｃｈａｒａｃｔｅｒａｇｇｒｅｇａｔｅ .Ｔｈｅｍａｐｐｉｎｇｂｅｔｗｅｅｎａｇｇｒｅｇａｔｅｓｉｓｃａｌｌｅｄａｍａｐｐｉｎｇｆｕｎｃｔｉｏｎ ;ｋｉｎｄｓｏｆｍａｐｐｉｎｇｆｕｎｃｔｉｏｎｓｃａｎｂｅｆｏｒｍｅｄｆｏｒｆａｕｌｔｐａｔｔｅｒｎｒｅｃｏｇｎｉｔｉｏｎ .Ｔｈｅｔｒａｄｉｔｉｏｎａｌｐａｔｔｅｒ…