Pumped storage unit generator temperature early warning method and system

Abstract

The embodiment of the invention provides a pumped storage unit generator temperature early warning method and system, which are combined with the maximum information coefficient (MIC), can discover the nonlinear relationship between characteristics while ensuring low operand, and have good universality and fairness. An established Attention-TCN model has a self-adaptive function for the features, the Attention mechanism can dynamically allocate a weight for each sample in the training process, compared with a traditional method for determining the weight for the features, the method is more flexible and practical, the established model is more accurate in combination with the characteristics of few TCN parameters and good accuracy, and the probability of prediction error abnormity can be effectively reduced. Compared with a traditional method of taking an error maximum value, setting an alarm threshold value according to experience and the like, the method is more objective by analyzing skewness and kurtosis early warning of an error sequence, has good interpretability, gives consideration to sensitivity and reliability, is small in calculation amount, and guarantees the real-time performance of early warning.

Description

technical field [0001] Embodiments of the present invention relate to the technical field of generator state monitoring and fault diagnosis, and in particular to a method and system for early warning of generator temperature of a pumped storage unit. Background technique [0002] The pumped storage unit plays the role of peak shaving and valley filling, frequency modulation and phase modulation in the power grid, and can be used as an emergency backup power supply in an emergency. The generator is an important part of the pumped storage unit to realize the function of discharging water and generating electricity. Compared with the fault maintenance, the condition-based maintenance of the generator has the advantages of low maintenance cost and improved operation reliability. Condition monitoring and fault diagnosis are important contents of condition-based maintenance. Its main principle is: use sensors to collect on-site data, put them into neural network training or expert...

AI Technical Summary

Problems solved by technology

[0003] At present, the temperature early warning model using neural network usually uses linear correlation coefficient, k-nearest neighbor distance (K-Nearest Neighbor, KNN) and so on in feature selection, and such correlation criteria cannot accurately reflect nonlinear and non-functional correlations. relationship, or the calculation cost is high; in addition, the existing pumped-storage unit generator failure warning threshold usually selects the extreme value and variance during normal operation, which is greatly disturbed by human factors and cannot objectively reflect the actual threshold situation

Images