Browsing by Author "Zhang, Lijun"

Now showing 1 - 2 of 2
  • Publication
    Publication
    Ice Detection Model of Wind Turbine Blades Based on Random Forest Classifier
    (Energies, 2018-09-25) Zhang, Lijun; Liu, Kai; Wang, Yufeng; Omariba, Zachary
    When wind turbine blades are icing, the output power of a wind turbine tends to reduce, thus informing the selection of two basic variables of wind speed and power. Then other features, such as the degree of power deviation from the power curve fitted by normal sample data, are extracted to build the model based on the random forest classifier with the confusion matrix for result assessment. The model indicates that it has high accuracy and good generalization ability verified with the data from the China Industrial Big Data Innovation Competition. This study looks at ice detection on wind turbine blades using supervisory control and data acquisition (SCADA) data and thereafter a model based on the random forest classifier is proposed. Compared with other classification models, the model based on the random forest classifier is more accurate and more efficient in terms of computing capabilities, making it more suitable for the practical application on ice detection.
  • Publication
    Publication
    Remaining useful life prediction of electric vehicle lithium-ion battery based on particle filter method
    (IEEE, 2018-05-28) Omariba, Zachary Bosire; Zhang, Lijun; Sun, Dongbai
    Lithium-ion batteries are popular today as their applications spans from portable electronics, electric vehicles, military, and aerospace applications. These batteries form a core component of these systems making them critical to the systems functional capability. Remaining useful life prediction is essential therefore as failure to which can lead to reduced performance, and or even catastrophic failure. The remaining useful life estimates are obtained by evaluating successive probability distributions of degrading states. If battery capacity is less than the failure threshold it poses a major danger to electric vehicles. This is because the battery capacity is an important indicator to monitor state of health (SOH), and its value can be less than the failure threshold due to degradation. This paper makes use of NASA's battery dataset to form the observed data sequence for prediction of remaining useful life. Afterwards a particle filter (PF) algorithm is used to perform the prediction of remaining useful life.