To determine the mechanistic basis of tolerance, we evaluated six candidate traits for tolerance to damage using F(2) interspecific hybrids in a willow hybrid system. A distinction was made between reproductive tolerance and biomass tolerance; reproductive tolerance was designated as a plant's proportional change in catkin production following damage, while biomass tolerance referred to a plant's proportional change in biomass (i.e., regrowth) following damage. F(2) hybrids were generated to increase variation and independence among candidate traits. Using three clonally identical individuals, pre-damage candidate traits for tolerance to damage (root:shoot ratio, total nonstructural carbohydrate, and total available protein) and post-damage candidate traits (relative root:shoot ratio, phenolic ratio, and specific leaf area ratio) were measured. The range of variation for these six candidate traits was broad. Biomass was significantly increased two years after 50% shoot length removal, and catkin production was not significantly reduced when damaged, suggesting that F(2) hybrids had great biomass tolerance and reproductive tolerance. Based on multiple regression methods, increased reproductive tolerance was associated with increased protein storage and decreased relative root:shoot ratio (reduced root allocation after damage). In addition, a positive relationship between biomass tolerance and condensed tannins was detected, and both traits were associated with increased reproductive tolerance. These four factors explained 57% of the variance in the reproductive tolerance of F(2) hybrids, but biomass tolerance explained the majority of the variance in reproductive tolerance. Changes in plant architecture in response to plant damage may be the underlying mechanism that explains biomass tolerance.
An emerging prognostic and health management (PHM) technology has recently attracted a great deal of attention from academies, industries, and governments. The need for higher equipment availability and lower maintenance cost is driving the development and integration of prognostic and health management systems. PHM models depend on the smart sensors and data generated from sensors. This paper proposed a machine learning-based methods for developing PHM models from sensor data to perform fault diagnostic for transformer systems in a smart grid. In particular, we apply the Cuckoo Search (CS) algorithm to optimize the Back-propagation (BP) neural network in order to build high performance fault diagnostics models. The models were developed using sensor data called dissolved gas data in oil of the power transformer. We validated the models using real sensor data collected from power transformers in China. The results demonstrate that the developed meta heuristic algorithm for optimizing the parameters of the neural network is effective and useful; and machine learning-based models significantly improved the performance and accuracy of fault diagnosis/detection for power transformer PHM.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.