首页|Researcher at University of Stuttgart Targets Support Vector Machines (Fault Det ection on Short-Haul or Highly Dynamic Flights Using Transient Flight Segments)
Researcher at University of Stuttgart Targets Support Vector Machines (Fault Det ection on Short-Haul or Highly Dynamic Flights Using Transient Flight Segments)
扫码查看
点击上方二维码区域，可以放大扫码查看
原文链接
NETL
NSTL
By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News-Researchers detail new data in . Accor ding to news reporting from Stuttgart, Germany, by NewsRx journalists, research stated, "A machine learning based approach is presented which allows to detect p ersistent engine faults after a single flight. It utilizes transient in-flight m easurements and atransient engine model." Our news journalists obtained a quote from the research from University of Stutt gart: "The time series of the residuals between the measured data and the data r esulting from performance synthesis is evaluated using moving windows containing at least one transient segment. A continuous wavelet transformation and a pre-t rained convolutional neural network are utilized on the residuals for feature ex traction. The fault detection is carried out via a one-class support vector mach ine, trained exclusively on nominal engine operation data. Therefore, the approa ch requires no a-priory knowledge of the effects of engine faults on the in-flig ht measurements. Under the assumption of persistent faults, all windows of a sin gle flight which contain at least one transient segment are considered in order to improve the reliability of the fault detection. This approach is validated us ing measured data of a small helicopter engine that replicates the dynamic fligh t of the corresponding model helicopter on a ground test bed. Consequently, step changes as well as complex variations of the shaft power output are considered. "
University of StuttgartStuttgartGerm anyEuropeEmerging TechnologiesMachine LearningSupport Vector MachinesV ector Machines
NETL
NSTL
