Event-based autonomous identification method for power grid monitoring alarm information

Abstract

The invention discloses an event-based autonomous identification method for power grid monitoring alarm information. The event-based autonomous identification method comprises the following steps: the step 1, collecting required basic data; the step 2, sorting feature information related to power grid change, and building an event rule base; the step 3, judging the alarm information by using a rule to form an event preliminary classification result and converting the event preliminary classification result into a vector; the step 4, performing data preprocessing on the original monitoring alarm information, generating a feature vector, and building a training sample set by combining the feature vector with the vector of the preliminary classification result; the step 5, training and learning the training sample set by adopting a convolutional neural network classification model; and the step 6, obtaining an accurate identification result of the monitoring event by using the trained convolutional neural network model. According to the method, autonomous identification of power grid alarm events and business events can be realized, the screen monitoring pressure of monitoring business personnel is effectively reduced, and the work efficiency of daily monitoring and accident exception handling is improved.

Description

technical field [0001] The invention relates to an event-based autonomous identification method for grid monitoring and alarm information, which classifies and prewarns the grid alarm information, and belongs to the technical field of electric power systems. Background technique [0002] The existing power grid monitoring service relies on the monitoring method of responding to alarm information one by one, and needs to distinguish, analyze and give feedback on each piece of information one by one. With the continuous expansion of the scale of the power grid and the continuous improvement of the level of intelligence of the power grid, the number of substations, power grid equipment and alarm information that are connected to the control agency for centralized monitoring continues to increase, and it is prone to equipment failure or abnormal misjudgment and misjudgment, which can no longer adapt to the current situation. Under the current situation, there are higher requirem...

AI Technical Summary

Problems solved by technology

[0005] Purpose of the invention: The present invention aims at the geometric growth trend of the current power grid equipment failure alarm information. The existing technical means still have low efficiency in real-time processing of monitoring alarm signals in terms of real-time analysis and disposal of monitoring services, and monitoring event analysis and disposal specifications Insufficient security, prone to misjudgment and misjudgment of equipment failure or abnormality, and failure to realize monitoring event identification for multi-service scenarios, provide an event-based autonomous identification method for power grid monitoring business

Images