A method for cleaning wind power anomaly data by combining image processing with community detection algorithms

Current methodologies for cleaning wind power anomaly data exhibit limited capabilities in identifying abnormal data within extensive datasets and struggle to accommodate the considerable variability and intricacy of wind farm data.Consequently,a method for cleaning wind power anomaly data by combining image processing with community detection algorithms(CWPAD-IPCDA)is proposed.To precisely identify and initially clean anomalous data,wind power curve(WPC)images are converted into graph structures,which employ the Louvain community recognition algorithm and graph-theoretic methods for community detection and segmentation.Furthermore,the mathematical morphology operation(MMO)determines the main part of the initially cleaned wind power curve images and maps them back to the normal wind power points to complete the final cleaning.The CWPAD-IPCDA method was applied to clean datasets from 25 wind turbines(WTs)in two wind farms in northwest China to validate its feasibility.A comparison was conducted using density-based spatial clustering of applications with noise(DBSCAN)algorithm,an improved isolation forest algorithm,and an image-based(IB)algorithm.The experimental results demonstrate that the CWPAD-IPCDA method surpasses the other three algorithms,achieving an approximately 7.23%higher average data cleaning rate.The mean value of the sum of the squared errors(SSE)of the dataset after cleaning is approximately 6.887 lower than that of the other algorithms.Moreover,the mean of overall accuracy,as measured by the F1-score,exceeds that of the other methods by approximately 10.49%;this indicates that the CWPAD-IPCDA method is more conducive to improving the accuracy and reliability of wind power curve modeling and wind farm power forecasting.

Study on the operational safety of high-speed trains exposed to stochastic winds

The characteristic wind curve （CWC） was com- monly used in the previous work to evaluate the operational safety of the high-speed trains exposed to crosswinds. How- ever, the CWC only provide the dividing line between safety state and failure state of high-speed trains, which can not evaluate the risk of derailment of high-speed trains when ex- posed to natural winds. In the present paper, a more realistic approach taking into account the stochastic characteristics of natural winds is proposed, which can give a reasonable and effective assessment of the operational safety of high-speed trains under stochastic winds. In this approach, the longitudi- nal and lateral components of stochastic winds are simulated based on the Cooper theory and harmonic superposition. An algorithm is set up for calculating the unsteady aerody- namic forces （moments） of the high-speed trains exposed to stochastic winds. A multi-body dynamic model of the rail vehicle is established to compute the vehicle system dynamic response subjected to the unsteady aerodynamic forces （mo- ments） input. Then the statistical method is used to get the mean characteristic wind curve （MCWC） and spread range of the high-speed trains exposed to stochastic winds. It is found that the CWC provided by the previous analyticalmethod produces over-conservative limits. The methodol- ogy proposed in the present paper can provide more signif- icant reference for the safety operation of high-speed trains exposed to stochastic winds.

Operational Safety Assessment of a High-Speed Train Exposed to the Strong Gust Wind

The operational safety characteristics of trains exposed to a strong wind have caused great concern in recent years.In the present paper,the effect of the strong gust wind on a high-speed train is investigated.A typical gust wind model for any wind angle,named“Chinese hat gust wind model”,was first constructed,and an algorithm for computing the aerodynamic loads was elaborated accordingly.A vehicle system dynamic model was then set up in order to investigate the vehicle system dynamic characteristics.The assessment of the operational safety has been conducted by means of characteristic wind curves(CWC).As some of the parameters of the wind-train system were difficult to measure,we also investigated the impact of the uncertain system parameters on the CWC.Results indicate that,the descending order of the operational safety index of the vehicle for each wind angle is 90°-60°-120°-30°-150°,and the worst condition for the operational safety occurs when the wind angle reaches around 90°.According to our findings,the gust factor and aerodynamic side force coefficient have great impact on the critical wind speed.Thus,these two parameters require special attention when considering the operational safety of a railway vehicle subjected to strong gust wind.

An Algorithm for Practical Power Curve Estimation of Wind Turbines

Practical power curve estimation is necessary for evaluating the actual power output of a wind farm;since a power curve provided by the wind turbine manufacture will be different with the actual power curve following several years of operation.It can be estimated using the collected power output data including wind power generation and wind speed.This data is commonly ill-distributed due to a noticeable number of outliers,which impose a serious bias to the estimation models obtained from this data.It introduces an interesting challenge in estimation of a power curve.In this paper,an intelligent algorithm is proposed for estimating a power curve using the measured data while modeling and bias errors,imposed to the estimation model by the outliners,are minimized.More specifically,this algorithm is designed based on the Statistical Analysis Software(SAS)programming software package in order to facilitate analyzing and managing big datasets of wind speed and wind power generation.The effectiveness and practical application of the proposed algorithm is demonstrated using a real-world dataset.