Abstract: High impedance fault (HIF) detection and location accuracy is provided. An HIF has random, irregular, and unsymmetrical characteristics, making such a fault difficult to detect in distribution grids via conventional relay measurements with relatively low resolution and accuracy. Embodiments disclosed herein provide a stochastic HIF monitoring and location scheme using high-resolution time-synchronized data in micro phasor measurement units (?-PMUs) for distribution network protection. In particular, a fault detection and location process is systematically designed based on feature selections, semi-supervised learning (SSL), and probabilistic learning.

Abstract: Effective feature set-based high impedance fault (HIF) detection is provided. Systems, methods and devices described herein present a systematic design of power feature extraction for HIF detection and classification. For example, power features associated with HIF events are extracted according to when a fault happens, how long it lasts, and the magnitude of the fault. Complementary power expert information is also integrated into feature pools. In another aspect, a ranking procedure is deployed in a feature pool for balancing information gain and complexity in order to avoid over-fitting of features. In aspects described herein, a logic-based HIF detector implements HIF feature extraction. To determine when an HIF occurs, the HIF detector calculates different quantities, such as active power and reactive power, based on a voltage and current time series, and uses the derivative of these quantities to tell when there is a potential change due to HIF.

Abstract: Reinforcement learning (RL)-based recloser control for distribution cables with degraded insulation level is provided. Utilities continuously observe cable failures on aged cables that have an unknown degraded basic insulation level (BIL). One of the root causes is the transient overvoltage (TOV) associated with circuit breaker reclosing. Since it is hard to model TOV due to its complexity, embodiments described herein provide a model-free stochastic control method for reclosers under the existence of uncertainty and noise. Concretely, to capture high-dimensional dynamics patterns, the recloser control problem is formulated herein by incorporating the temporal sequence reward mechanism into a deep Q-network (DQN). Meanwhile, physical understanding of the problem is embedded into the action probability allocation to develop an infeasible-action-space-elimination algorithm.

Abstract: High impedance fault (HIF) detection and location accuracy is provided. An HIF has random, irregular, and unsymmetrical characteristics, making such a fault difficult to detect in distribution grids via conventional relay measurements with relatively low resolution and accuracy. Embodiments disclosed herein provide a stochastic HIF monitoring and location scheme using high-resolution time-synchronized data in micro phasor measurement units (?-PMUs) for distribution network protection. In particular, a fault detection and location process is systematically designed based on feature selections, semi-supervised learning (SSL), and probabilistic learning.

Abstract: Effective feature set-based high impedance fault (HIF) detection is provided. Systems, methods and devices described herein present a systematic design of power feature extraction for HIF detection and classification. For example, power features associated with HIF events are extracted according to when a fault happens, how long it lasts, and the magnitude of the fault. Complementary power expert information is also integrated into feature pools. In another aspect, a ranking procedure is deployed in a feature pool for balancing information gain and complexity in order to avoid over-fitting of features. In aspects described herein, a logic-based HIF detector implements HIF feature extraction. To determine when an HIF occurs, the HIF detector calculates different quantities, such as active power and reactive power, based on a voltage and current time series, and uses the derivative of these quantities to tell when there is a potential change due to HIF.

Abstract: A process for dyeing ramie sliver, comprising: 1.) pretreatment: cooking the ramie sliver for 8-12 minutes in a cooking reagent in a bath ratio of 1:4-10, the cooking reagent is a 1-3 g/L aqueous solution of a penetrating agent; and 2.) dyeing: dyeing the cooked ramie sliver in an active dye in a bath ratio of 1:4-10. Also disclosed is a method for preparing ramie yarn. The ramie sliver dyed according to the present invention improves the properties of ramie fibers, such that the ramie fibers are less likely to break; and the ramie fibers are less likely to harden, avoiding poor drawing, needle breakage and missing stitches during carding and coalescing in post-procedures, thus achieving the purpose of smooth yarn spinning. Also disclosed is a method for preparing ramie colored-spun yarn.