Operational time-series data modeling via LSTM network integrating principal component analysis based on human experience

Today’s information technologies involve increasingly intelligent systems, which come at the cost of increasingly complex equipment. Modern monitoring systems collect multi-measuring-point and long-term data which make equipment health prediction a “big data” problem. It is difficult to extract information from such condition monitoring data to accurately estimate or predict health statuses. Deep learning is a powerful tool for big data processing that is widely utilized in image and speech recognition applications, and can also provide effective predictions in industrial processes. This paper proposes the Long Short-term Memory Integrating Principal Component Analysis based on Human Experience (HEPCA-LSTM), which uses operational time-series data for equipment health prognostics. Principal component analysis based on human experience is first conducted to extract condition parameters from the condition monitoring system. The long short-term memory (LSTM) framework is then constructed to predict the target status. Finally, a dynamic update of the prediction model with incoming data is performed at a certain interval to prevent any model misalignment caused by the drifting of relevant variables. The proposed model is validated on a practical case and found to outperform other prediction methods. It utilizes a powerful deep learning analysis method, the LSTM, to fully process big condition monitoring series data; it effectively extracts the features involved with human experience and takes dynamic updates into consideration.     

构建媒体网络信息安全体系

通过对广州市电视台综合信息平台网络系统的应用现状及安全风险进行分析,提出基于网络层、系统层、用户层和安全策略管理全方位的网络信息安全体系.     

一种具有带孔补偿过滤器的γ剂量计的能响补偿计算

对在低能区有过高响应的γ辐射剂量计可采用带孔补偿过滤器进行能响补偿。本文介绍了对这类补偿过滤器选择最佳补偿参数(材料厚度和孔隙率)的近似求解方法;并对 CaSO:Tm 热释光剂量计用此方法作了实例计算。文中还计算了自制带有鼠笼结构的这类补偿过滤器的 CaSO:,Tm热释光剂量计对照射量的能量响应,与实测结果比较,各能量点响应的最大相差为10%。     

Indicators for inspection and maintenance planning of concrete structures

Based on an idea introduced by Benjamin and Cornell (1970. Probability, statistics and decision for civil engineers. New York: McGaw Hill) and previous works by the authors it is demonstrated how condition indicators may be formulated for the general purpose of quality control and for assessment and inspection planning in particular. The formulation facilitates quality control based on sampling of indirect information about the condition of the considered components. This allows for a Bayesian formulation of the indicators whereby the experience and expertise of the inspection personnel may be fully utilized and consistently updated as frequentistic information is collected. The approach is illustrated on an example considering a concrete structure subject to corrosion. It is shown how half-cell potential measurements may be utilized to update the probability of excessive repair after 50 years. Furthermore in the same example it is shown how the concept of condition indicators might be applied to develop a cost optimal maintenance strategy composed of preventive and corrective repair measures.     

Effect of sampling density on the measurement of stream condition indicators in two lowland Australian streams

There is widespread application of indicators to the assessment of environmental condition of streams. These indicators are intended for use by managers in making various comparative and absolute assessments and often have a role in resource allocation and performance assessment. Therefore, the problem of formally defining confidence in the results is important but difficult because the sampling strategies used are commonly based on a compromise between the requirements of statistical rigour and the pragmatic issues of access and resources. It is rare to see this compromise explicitly considered and consequently there is seldom quantification of the uncertainty that could affect the confidence a manager has in an indicator. In this paper, we present a method for quantitatively assessing the tradeoffs between sampling density and uncertainty in meeting various monitoring objectives. Assessments using judgement‐based representative reaches are shown to be unreliable; instead a sampling approach is recommended based on the random selection of measuring sites. A detailed dataset was collected along two streams in Victoria, Australia, and the effect of sampling density was assessed by subsampling from this dataset with precision related to the number of sites assessed per reach length and the intensity of the sampling at each site. The sampling scheme to achieve a given precision is shown to depend on the monitoring objective. In particular, three objectives were considered: (1) making a baseline assessment of current condition; (2) change detection; and (3) detection of a critical threshold in condition. Change detection is shown to be more demanding than assessing baseline condition with additional sampling effort required to achieve the same precision. Sampling to detect a critical threshold depends on nominating acceptable values of Type I and II error and the size of the effect to be detected. Copyright © 2006 John Wiley & Sons, Ltd.     

Two- or three-stage least squares?

Two elements enter the choice between 2 and 3SLS for full-system estimation: statistical efficiency and computational cost. 2SLS always has the computational edge, but 3SLS can be more efficient, a relative advantage that increases with the strength of the interrelations among the error terms. A measure of these interrelations is thus helpful in making the choice, and, when there are only two equations, this has suggested using a high pairwise error correlation as an indicator of when to use 3SLS. In larger systems of equations, however, these pairwise correlations can remain small even though more general interrelations give 3SLS the relative advantage. More general indicators are therefore needed, and this paper suggests three such and demonstrates their efficacy.Professor of Economics, Boston College, and Principal Research Associate, Center for Computational Research in Economics and Management Science, MIT. All computation was done on the TROLL system at MIT. My thanks go to Josh Charap for his able research assistance. This research was sponsored in part by the National Science Foundation under grant #IST-8420614.     

铁谱分析技术在燃油中非金属杂质监测方面应用的研究

通过对制谱时，谱片上磨屑沉积机理的重新分析，发现非金属磨屑在自身重力的作用下，仍可有规律地沉积在谱片上。据此特点成功地将柴油中的沙砾等杂质有规律地沉积到谱片上，并检测出了某型叉车柴油机喷油泵柱塞断裂的原因。     

Application of stochastic filtering for lifetime prediction

This paper introduces a stochastic filtering modeling approach for predicting the remaining lifetime of a component based on information on the stochastic degradation process and uncertain condition monitoring measurements. The model is illustrated by a case study, where the degradation is assumed to be a simplified fatigue crack growth process. The model accounts for uncertainties in both degradation process and condition measurements in a sound way. If completed with information on costs of monitoring, failure and replacement, such model could be used in optimizing both the condition monitoring intervals and, e.g. the replacement time for the component.     

State observability and condition observability for a class of interacting discrete event systems

This paper introduces the concepts of state observability and condition observability for condition systems, a class of systems composed of discrete state components which interact via discrete binary signals called conditions. Given a set of externally observed conditions, state observability implies that the state of the system can be determined from the observations, and condition observability implies that all unobserved input and output conditions of the system can be determined from the observations. In this paper, we present a class of systems which is state observable and condition observable. We present a method to synthesize an observer system to provide state and condition signal estimates for a single component subsystem.     

增力式夹具的设计与应用

增力式夹具结构紧凑，夹紧迅速可靠。它可以用较少的原动力获得较大的夹紧力，其增力倍数据实际须要同设计者调整。而且，若按机构自锁条件设计，该夹具夹紧之后，实现自锁。本文对该夹具结构做了介绍，并通过理论分析，指出增力系数和夹具自锁的设计条件。