Evaluation value calibration method of equipment intelligent early warning system

Abstract

The invention belongs to the technical field of equipment state early warning, and particularly relates to an evaluation value calibration method of an equipment intelligent early warning system based on an SVM regression model. The evaluation value calibration method of the equipment intelligent early warning system can remove deviation of an abnormal detecting point with respect to the evaluation values of other normal measuring points in real time sequentially through establishment of an equipment intelligent early warning model, influence relation curve fitting, identification of abnormal measuring points and calibration of interfered evaluation values, has good universality and can be grafted to other regression algorithms for performance optimization. When the evaluation value of an interfered measuring point of equipment is adjusted on line, no excessive delay effect is generated, and a real-time early warning capability of the model for the equipment is ensured; discrimination and analysis for abnormal measuring points can be carried out in real time, so that the real-time performance of judgment is ensured, and online state analysis for equipment data can be carried out; and evaluation values without interference of the normal measuring points can be output steadily. According to the evaluation value calibration method of the equipment intelligent early warning system, the reliability of the early warning model is higher, and the life cycle is long.

Description

(1) Technical field [0001] The invention belongs to the technical field of equipment state early warning, and in particular relates to an evaluation value calibration method of an equipment intelligent early warning system based on an SVM regression model. (2) Background technology [0002] As we all know, the operating status of important equipment has a great impact on factory production, such as key equipment such as boilers and generators in power plant units. The functional characteristics, appearance characteristics and electrical characteristics reflected in the operation process of the equipment under normal working conditions are different from those under abnormal conditions. Intelligent early warning of equipment means that when there are signs of abnormality in equipment components, an early warning signal is sent to equipment management personnel in advance to prevent abnormalities from becoming uncontrollable faults, ensure the safety of production personnel, a...

AI Technical Summary

Problems solved by technology

For example, in the paper "SVM Short-Term Load Forecasting Based on ARMA Error Correction and Adaptive Particle Swarm Optimization" (Power System Protection and Control, 2011, No. 14), the optimization limitation of the support vector machine regression model is that the ant colony algorithm and the particle swarm optimization algorithm can only For Kernel Bandwidth , error penalty factor Global optimization of two parameters; and the national patent "A Method and System for Prediction and Early Warning of Grain Situation Based on SVM" (application number 201410068731.X) mentions the use of preprocessed historical health multi-parameter sample data to establish support vector machines The regression prediction model realizes the real-time evaluation of the grain safety level parameters, but the key parameter optimization of the support vector machine can only adjust the regression evaluation value to a certain extent, and cannot fundamentally change the redundant relationship between the measurement points. An abnormality of one or more measuring points will still affect the evaluation value of other measuring points, thus reducing the accuracy and effectiveness of the equipment early warning system

Since abnormal measuring points affect the evaluation of normal measuring points by disturbing the complex nonlinear mapping relationship of normal measuring points, the optimization strategy cannot essentially eliminate the phenomenon of interference caused by abnormal measuring points

Images