Wind turbine condition monitoring based on SCADA data using normal behavior models. Part 2: Application examples

This paper is part two of a two part series. The originality of part one was the proposal of a novelty approach for wind turbine supervisory control and data acquisition (SCADA) data mining for condition monitoring purposes. The novelty concerned the usage of adaptive neuro-fuzzy interference system (ANFIS) models in this context and the application of a proposed procedure to a wide range of different SCADA signals. The applicability of the set up ANFIS models for anomaly detection was proven by the achieved performance of the models. In combination with the fuzzy interference system (FIS) proposed the prediction errors provide information about the condition of the monitored components.Part two presents application examples illustrating the efficiency of the proposed method. The work is based on continuously measured wind turbine SCADA data from 18 modern type pitch regulated wind turbines of the 2 MW class covering a period of 35 months. Several real life faults and issues in this data are analyzed and evaluated by the condition monitoring system (CMS) and the results presented. It is shown that SCADA data contain crucial information for wind turbine operators worth extracting. Using full signal reconstruction (FSRC) adaptive neuro-fuzzy interference system (ANFIS) normal behavior models (NBM) in combination with fuzzy logic (FL) a setup is developed for data mining of this information. A high degree of automation can be achieved. It is shown that FL rules established with a fault at one turbine can be applied to diagnose similar faults at other turbines automatically via the CMS proposed. A further focus in this paper lies in the process of rule optimization and adoption, allowing the expert to implement the gained knowledge in fault analysis. The fault types diagnosed here are: (1) a hydraulic oil leakage; (2) cooling system filter obstructions; (3) converter fan malfunctions; (4) anemometer offsets and (5) turbine controller malfunctions. Moreover, the graphical user interface (GUI) developed to access, analyze and visualize the data and results is presented.     

基于SCADA参量关联互信息自编码的风电机组故障检测方法

针对风力发电机组数据采集与监视控制系统(supervisory control and data acquisition,SCADA)监测参量间的耦合关联性,提出基于多参数耦合关联互信息编码的风电机组故障检测方法.该方法构建了SCADA数据的耦合关联矩阵,采用互信息变分自编码器对关联矩阵进行编码重构;将SCADA参量关联矩阵的重构误差作为机组健康评估指标,结合指数加权移动平均模型的迭代更新,对机组实时故障阈值进行自适应设置.两个风场的风电机组SCADA数据分析结果表明,所提方法充分利用了SCADA数据的耦合关联结构信息,能有效提高风电机组故障检测的准确性及对环境工况的鲁棒性.     

基于行为监控和数据挖掘的动态信任模型*

实体之间的信任关系发生在一定的上下文中,其信任值与影响信任值的多个行为属性之间的关系复杂而且多变,很难用一个一成不变的函数去描述。根据软件传感器监测到的历史行为数据和目标信任值,利用logistic回归分析方法和成对分类法对行为属性与信任值之间的关系模式进行自适应的数据挖掘与知识发现,不需要任何的先验知识和主观假设,从而有效解决了信任值计算的动态性和客观性等问题。实验结果表明,与已有模型相比,该模型的平均误差率和计算效率都有所提高,能够快速有效地分类出实体间的信任等级。     

基于AC-GAN数据重构的风电机组主轴承温度监测方法

为更好地识别风电机组主轴承运行状态,提出了一种基于辅助分类生成对抗网络(auxiliary classifier generative adversarial networks, AC-GAN)的数据重构算法对风电机组主轴承温度进行监测。首先,利用采集与监视控制系统(supervisory control and data acquisition, SCADA)时序数据建立基于轻型梯度增强学习器(light gradient boosting machine, LightGBM)的主轴承温度预测模型,并计算其残差特征。其次,利用统计过程控制(statistical process control, SPC)方法对主轴承温度异常残差在控制线范围内进行筛选,并利用AC-GAN算法对残差进行重构。最后,分别提取主轴承温度正常和异常的残差特征,建立基于自然梯度提升(natural gradient boosting, NGBoost)的主轴承状态监测模型。实验结果表明,该方法对主轴承运行状态判断准确度高达87.5%,能够有效地监测风电机组轴承类运行状态。     

On the assessment of multivariable controllers using closed loop data. Part I: Identification of system models

Controller performance assessment of SISO and MIMO systems requires effective and systematic identification of the associated system models based on closed-loop data. In this work, a new methodology for the identification of the process, controller and disturbance models is presented for the purpose of enabling the evaluation of the performance of MIMO control systems. The methodology is based on subspace identification algorithms for the identification of the controller, process and disturbance models from closed-loop data. However, identification of the process model is enhanced by the estimation of the associated interactor matrix via the Variable Regression Estimation technique, the existence of which is mathematically proved. The proposed identification methodology is applied to two 2 × 2 systems utilizing both step-response and PRBS closed-loop data.     

Presentation and description of two classification methods using data fusion based on sensor management

The application of multi-sensor fusion, which aims at recognizing a state among a set of hypotheses for object classification, is of major interest with regard to the performance improvement brought by the sensor complementarity. Nevertheless, this needs to take into account the most accurate information and take advantage of the statistical learning of the previous measurements acquired by sensors. When previous learning is not representative of real measurements provided by the sensors, the classical probabilistic fusion methods lack performance. The Dempster–Shafer theory is then introduced to face this disadvantage by integrating further information which is the context of the sensor acquisitions. In this paper, we propose a model formalism for the sensor reliability in a context that leads to two methods of integration when all the hypotheses, associated to the objects of the scene acquired by sensors, are previously learned: the first one models the integration of this further information in the fusion rule as degrees of trust and the second models the sensor reliability directly as probability mass. These two methods are based on the theory of fuzzy events. Simulations of typical cases are developed in order to define the respective validity domains of these two methods. Afterwards, we are interested in the development of these two methods in the case where the previous learning is unavailable for an object and a global method of contextual information integration can be deduced.     

基于.NET Remoting的电能质量监控数据的发布

本文提出了基于.NET Remoting技术的电能质量监测数据发布模型。采用该模型有利于提高监测数据的传输效率,使电能质量网络化监测的系统扩展性、兼容性、可移植性更好。最后采用某系统的电能质量数据作为数据源进行测试,证明了该模型的可行性和实用性。     

Model variables identification of a gas turbine using a subspace approach based on input/output data measurements

This paper deals with a state model identification of a gas turbine used for gas transport, using a subspace approach of the state space model. This method provides a reliable and robust state representation of the model, taking advantage of its benefits in the control, monitoring, and supervision of this machine. The model for each variable is set so that the state matrices associated with the gas turbine model are determined from their real input/output data. The comparison of the obtained identification results with those of the actual turbine operation serves to validate the proposed model in this work. This numerical algorithm of the subspace identification method is full of information and more accurate in terms of residual modeling error, and expresses a very high level of confidence in the identified turbine system dynamics. Hence, the controllability and observability tests of turbine operation for different input/output variables allowed to validate the real-time operating stability of the turbine.     

An estimation of the optimum temporal resolution for monitoring vegetation condition on a nationwide scale using MODIS/Terra data

Monitoring vegetation condition is an important issue in the Mediterranean region, in terms of both securing food and preventing fires. The recent abundance of remotely sensed data, such as the daily availability of MODIS imagery, raises the issue of appropriate temporal sampling when monitoring vegetation: under‐sampling may not accurately describe the phenomenon under consideration, whilst over‐sampling would increase the cost of the project without additional benefit. The aim of this work is to estimate the optimum temporal resolution for vegetation monitoring on a nationwide scale using 250 m MODIS/Terra daily images and composites. Specific objectives include: (i) an investigation into the optimum temporal resolution for monitoring vegetation condition during the dry season on a nationwide scale using time‐series analysis of Normalized Difference Vegetation Index, NDVI, datasets, (ii) an investigation into whether this temporal resolution differs between the two major vegetation categories of natural and managed vegetation, and (iii) a quality assessment of multi‐temporal NDVI composites following the proposed optimum temporal resolution. A time‐series of daily NDVI data is developed for Greece using MODIS/Terra 250 m imagery. After smoothing to remove noise and cloud influence, it is subjected to temporal autocorrelation analysis, and its level of significance is the adopted objective function. In addition, NDVI composites are created at various temporal resolutions and compared using qualitative criteria. Results indicate that the proposed optimum temporal resolution is different for managed and natural vegetation. Finally, quality assessment of the multi‐temporal NDVI composites reveals that compositing at the proposed optimum temporal resolution could derive products that are useful for operational monitoring of vegetation.     

BTSR：一种基于行为可信的安全数据融合与路由算法

针对无线传感器网络数据融合与路由面临安全威胁,从传感器数据融合过程的空间相关性和时间相关性入手,对LEACH算法进行改进,考虑节点的行为可信因素,提出了一种基于行为可信的安全数据融合与路由算法-BTSR。该算法通过检验传感器本地采样值构成的时空相似度与传感器数据融合过程统计特征的符合程度,保证了数据融合路由的安全和可靠。仿真实验表明BTSR算法在安全概率、能量消耗、融合精度方面比LEACH算法更具优越性。     

Efficient data selection for speech recognition based on prior confidence estimation using speech and monophone models

This paper proposes an efficient speech data selection technique that can identify those data that will be well recognized. Conventional confidence measure techniques can also identify well-recognized speech data. However, those techniques require a lot of computation time for speech recognition processing to estimate confidence scores. Speech data with low confidence should not go through the time-consuming recognition process since they will yield erroneous spoken documents that will eventually be rejected. The proposed technique can select the speech data that will be acceptable for speech recognition applications. It rapidly selects speech data with high prior confidence based on acoustic likelihood values and using only speech and monophone models. Experiments show that the proposed confidence estimation technique is over 50 times faster than the conventional posterior confidence measure while providing equivalent data selection performance for speech recognition and spoken document retrieval.     

Tool wear condition monitoring based on a two-layer angle kernel extreme learning machine using sound sensor for milling process

Journal of Intelligent Manufacturing - Tool condition monitoring (TCM) in numerical control machines plays an essential role in ensuring high manufacturing quality. The TCM process is conducted...     

Remote sensing monitoring of the suspended particle size in Hongze Lake based on GF-1 data

In remote sensing analyses of water colour, suspended particle size is an important optical parameter that also plays an important role in inland and coastal biogeochemical processes. Knowledge of the suspended particle size and its changes in month and area can be used to assess the contributions by suspended particulate matter to backscatter coefficient, particle sinking, and carbon sequestration under lake water. In this study, in situ samples collected in the summer and winter from Hongze Lake (HZL), 2016, were used to develop an empirical model to estimate the median diameter (D_V⁵⁰) of suspended particle sizes. The spatial distributions of D_V⁵⁰ were derived using 37 WFV (Wide Field Viewer) images of GF-1 (GaoFen-1), China, and the fluctuational diversification and the potential influencing factors were discussed. Several crucial findings can be drawn: (1) the empirical band ratio algorithm R_rs,green: R_rs,red was suitable for D_V⁵⁰ estimation with a coefficient of determination (R²) of approximately 0.7 for the modelling data. In addition, the validation data showed that the MAPE (mean absolute percentage error) is below 34%, the RMSE (root mean square error) is less than 4.2 μm, and the Mean ratio is close to 1; (2) the average median particle size shows an increasing trend from the northeast of the lake (NE) to Chengzi Lake (CZL) and the wetland (WL) in HZL from 2015 to 2016; (3) the D_V⁵⁰ of HZL is higher in summer than in the other seasons during the study period; (4) the fluctuation in hydrological factors, especially the monthly water discharge and flow, might be the driving force behind the seasonal variations in D_V⁵⁰ of HZL; and (5) channel transportation reduced D_V⁵⁰, and the reduced amplitude might be more than 22%.     

Missing data analyses: a hybrid multiple imputation algorithm using Gray System Theory and entropy based on clustering

Researchers and practitioners who use databases usually feel that it is cumbersome in knowledge discovery or application development due to the issue of missing data. Though some approaches can work with a certain rate of incomplete data, a large portion of them demands high data quality with completeness. Therefore, a great number of strategies have been designed to process missingness particularly in the way of imputation. Single imputation methods initially succeeded in predicting the missing values for specific types of distributions. Yet, the multiple imputation algorithms have maintained prevalent because of the further promotion of validity by minimizing the bias iteratively and less requirement on prior knowledge to the distributions. This article carefully reviews the state of the art and proposes a hybrid missing data completion method named Multiple Imputation using Gray-system-theory and Entropy based on Clustering (MIGEC). Firstly, the non-missing data instances are separated into several clusters. Then, the imputed value is obtained after multiple calculations by utilizing the information entropy of the proximal category for each incomplete instance in terms of the similarity metric based on Gray System Theory (GST). Experimental results on University of California Irvine (UCI) datasets illustrate the superiority of MIGEC to other current achievements on accuracy for either numeric or categorical attributes under different missing mechanisms. Further discussion on real aerospace datasets states MIGEC is also applicable for the specific area with both more precise inference and faster convergence than other multiple imputation methods in general.     

基于深度学习的融合流程多视角行为分析:预测业务流程监控

预测性业务流程监控（PBPM）是业务流程管理（BPM）中的一个重要研究领域,旨在准确预测未来的行为事件。目前,PBPM研究中广泛引用了深度学习方法,但大多数方法只考虑单一的事件-控制流视角,无法将属性-数据流视角与之结合进行流程预测。针对这一问题,提出了一种基于双层BERT神经网络和融合流程多视角行为分析方法（简称FMP框架）。首先,基于第一层BERT学习属性-数据流信息;接着,基于第二层BERT学习事件-行为控制流信息;最后,通过FMP框架融合数据流和控制流实现多维视角流程预测。在真实的事件日志中的实验结果表明,相比其他研究方法,基于FPM框架预测下一个事件的活动精度更高。这证明融合流程多视角的FMP框架能够更全面、更深层次地分析复杂的流程行为,并提高预测的性能。     

HJ-1B卫星遥感数据在重庆市城市热环境监测的应用分析

本文以MODIS反演大气透射率,以HJ-1B/CCD分类结果反演地表比辐射率,并基于单窗算法,利用HJ-1B/IRS4数据反演地表温度.在此基础上,提取研究区的热场变异指数来分析重庆热岛空间分布特征,并就NDVI与NDBI对热岛效应的影响进行了分析.其结果如下:1)重庆城市热岛大致位于中梁山、铜锣山之间,呈东北、西南走向分布;2)热岛中心不在市中心,而是集中在大渡口工业园区、江北机场这些能耗大、人口密集区域,热岛强度范围在5?C-10?C之间;3)接近长江、嘉陵江水域的建筑用地密集区域,其热岛效应并不明显;4)NDVI与热岛强度呈负相关关系,NDBI与热岛强度呈现较为明显的正相关关系,二者对热岛都有重要影响,而NDBI的影响更大.因此,利用HJ-1B数据监测城市热环境,能较好地揭示重庆城市热岛空间分布特征,为城市环境监测与改善提供参考.