Maximum-likelihood mixture factor analysis model and its application for process monitoring

In the present paper, a mixture form of the factor analysis model is developed under the maximum-likelihood framework. In this new model structure, different noise levels of process variables have been considered. Afterward, the developed mixture factor analysis model is utilized for process monitoring. To enhance the monitoring performance, a soft combination strategy is then proposed to integrate different local monitoring results into a single monitoring chart, which is based on the Bayesian inference method. To test the modeling and monitoring performance of the proposed mixture factor analysis method, a numerical example and the Tennessee Eastman (TE) benchmark case studies are provided.     

Challenges to Engineering Management in the Big Data Era

This paper presents a review of the challenges to engineering management in the Big Data Era as well as the Big Data applications. First, it outlines the definitions of big data, data science and intelligent knowledge and the history of big data. Second, the paper reviews the academic activities about big data in China. Then, it elaborates a number of challenging big data problems, including transforming semi-structured and non-structured data into"structured format" and explores the relationship of data heterogeneity, knowledge heterogeneity and decision heterogeneity. Furthermore, the paper reports various real-life applications of big data, such as financial and petroleum engineering and internet business.     

Type 2 Diabetes Risk Prediction Using Deep Convolutional Neural Network Based-Bayesian Optimization

Diabetes mellitus is a long-term condition characterized by hyperglycemia. It could lead to plenty of difficulties. According to rising morbidity in recent years, the world’s diabetic patients will exceed 642 million by 2040, implying that one out of every ten persons will be diabetic. There is no doubt that this startling figure requires immediate attention from industry and academia to promote innovation and growth in diabetes risk prediction to save individuals’ lives. Due to its rapid development, deep learning (DL) was used to predict numerous diseases. However, DL methods still suffer from their limited prediction performance due to the hyperparameters selection and parameters optimization. Therefore, the selection of hyper-parameters is critical in improving classification performance. This study presents Convolutional Neural Network (CNN) that has achieved remarkable results in many medical domains where the Bayesian optimization algorithm (BOA) has been employed for hyperparameters selection and parameters optimization. Two issues have been investigated and solved during the experiment to enhance the results. The first is the dataset class imbalance, which is solved using Synthetic Minority Oversampling Technique (SMOTE) technique. The second issue is the model's poor performance, which has been solved using the Bayesian optimization algorithm. The findings indicate that the Bayesian based-CNN model superbases all the state-of-the-art models in the literature with an accuracy of 89.36%, F1-score of 0.88.6, and Matthews Correlation Coefficient (MCC) of 0.88.6.     

工资智能决策支持系统SIDSS的知识表达与处理

由于工资政策基本上是基于语言描述的,没有固定的公式可言,因而很难用数学模型加以描述;而另一方面,如何将各省不同且繁杂的工资政策作为知识从程序中脱离出来也是一个要考虑的地方,所以将工资政策看作知识库中的知识,同时将这些工资政策转换为规则加以处理不失为一个较好的解决办法。本文详细讨论了在SIDSS中事件处理器和规则处理器等知识的表达与处理技术。     

模糊支撑半径变量贝叶斯网络多态系统故障概率分析

针对现有隶属函数描述系统及部件故障状态的不足,构建了一种含模糊支撑半径变量的隶属函数来描述部件故障状态,提出了一种基于模糊支撑半径变量的贝叶斯网络多态系统故障概率计算方法。在隶属函数的构造中,用变量代替精确值描述隶属函数模糊支撑半径,建立了含模糊支撑半径变量的隶属函数;并将其引入贝叶斯网络,利用桶消元法对多态系统叶节点故障概率进行分析,得到叶节点故障概率变化曲线。将所提出的方法与文献中基于模糊支撑半径为定值的隶属函数贝叶斯网络方法相比较,验证了方法的有效性。最后,将该方法应用到数控机床主轴系统故障分析实例中,对叶节点故障概率进行计算。结果表明,该方法能够有效解决多态系统故障状态隶属函数选择中的主观性问题。     

基于条码的生产现场质量管理系统研究与开发

针对离散制造企业生产现场质量管理高效和规范化的需求,研究了基于条码的生产现场质量管理方法．在分析生产现场质量管理的业务需求之后,给出了基础物料资源、零部件和业务单据等生产资源的编码方案．提出了基于条码的面向批量和单件管理的质量数据采集方案;并对基于条码的质量问题批次追踪和生产过程质量问题溯源方案展开研究;最后,设计开发了生产现场质量管理原型系统QQ—MIMS,并在航天某制造企业进行了初步应用．     

A Dynamic Risk Assessment Methodology for Maintenance Decision Support

The failure mode and effect analysis (FMEA) is a widely applied technique for prioritizing equipment failures in the maintenance decision‐making domain. Recent improvements on the FMEA have largely focussed on addressing the shortcomings of the conventional FMEA of which the risk priority number is incorporated as a measure for prioritizing failure modes. In this regard, considerable research effort has been directed towards addressing uncertainties associated with the risk priority number metrics, that is occurrence, severity and detection. Despite these improvements, assigning these metrics remains largely subjective and mostly relies on expert elicitations, more so in instances where empirical data are sparse. Moreover, the FMEA results remain static and are seldom updated with the availability of new failure information. In this paper, a dynamic risk assessment methodology is proposed and based on the hierarchical Bayes theory. In the methodology, posterior distribution functions are derived for risk metrics associated with equipment failure of which the posterior function combines both prior functions elicited from experts and observed evidences based on empirical data. Thereafter, the posterior functions are incorporated as input to a Monte Carlo simulation model from which the expected cost of failure is generated and failure modes prioritized on this basis. A decision scheme for selecting appropriate maintenance strategy is proposed, and its applicability is demonstrated in the case study of thermal power plant equipment failures. Copyright © 2016 John Wiley & Sons, Ltd.     

基于本体的教学知识库研究与应用

知识库是智能教学系统的基础。由于教学知识库的描述标准不统一,知识表示方法也不同,所以导致教学知识难以共享和互操作。将本体引入教学领域知识库建模过程,建立概念共享模型,提供概念语义空间,不仅可以解决智能教学系统中的知识共享和互操作问题,而且易于实现基于本体的语义检索系统,从而大大提高系统的查全率和查准率。     

基于知识协同微调的低资源知识图谱补全方法

知识图谱补全能让知识图谱变得更加完整.现有的知识图谱补全工作大多会假设知识图谱中的实体或关系有充足的三元组实例.然而,在通用领域,存在大量长尾三元组;在垂直领域,较难获得大量高质量的标注数据.本文针对这一问题,提出了一种基于知识协同微调的低资源知识图谱补全方法.本文通过已有的结构化知识来构造初始的知识图谱补全提示,并提出一种协同微调算法来学习最优的模板、标签和模型的参数.本文的方法同时利用了知识图谱中的显式结构化知识和语言模型中的隐式事实知识,且可以同时应用于链接预测和关系抽取两种任务.实验表明,本文的方法在3个知识图谱推理数据集和5个关系抽取数据集上都取得了目前最优的性能.     

粗糙集在销售决策系统中的应用

在销售决策支持系统中,存在着大量的信息和很多不确定的因素,这使得做出科学合理的决策变得很困难。粗糙集理论是处理不确定性知识与不完整数据的有效工具,因此可以根据粗糙集理论通过分析推理找出销售数据中存在的有用的知识。依据粗糙集理论实现了一种对销售决策表知识简化的方法,采用粗集理论处理大量销售信息,从中提取有用规则,通过分析和推理产生最小决策规则。通过实例分析,验证了粗糙集理论与销售决策支持系统相结合方法的可行性。该方法有效地解决了智能销售决策支持系统中决策规则的获取与理解等问题。