A device damage detection method and system based on gpr

Abstract

The invention discloses a GPR-based equipment damage detection method and system. The system includes a collection module, a standardization processing module, a first calculation module, a second calculation module, a confidence interval determination module and a detection judgment module. The method includes: performing numerical standardization on the collected time-domain response data to obtain actual measurement data; inputting the actual measurement data into the GPR prediction model for processing to obtain prediction data; calculating the average value of the mean square error between the prediction data and the actual measurement data; determining The confidence interval of the mean square error is obtained; the damage judgment of the equipment is carried out according to the confidence interval of the mean square error. By using the method and the system of the invention, the downtime can be shortened, the maintenance cost can be reduced, the safety of equipment operation can be improved, and the accuracy of equipment damage detection can be improved. As a GPR-based equipment damage detection method and system, the invention can be widely used in the field of equipment structure damage detection in the industrial field.

Description

technical field [0001] The invention relates to the technical field of GPR and equipment structure health detection in the industrial field, in particular to a GPR-based equipment damage detection method and system. Background technique [0002] Explanation of technical terms: [0003] GPR: Gaussian Process Regression, Gaussian process regression. [0004] Damage: Changes within the system that adversely affect the structure and performance of the system. [0005] The aging of industrial equipment has gradually become a problem that cannot be ignored in on-site production. If these equipment damages are ignored or cannot be detected, it may lead to immeasurable consequences. Therefore, real-time fault monitoring has become one of the urgent issues in the industrial field. Obviously, the method of equipment damage detection in industry has not been popularized so far. At present, most enterprises still adopt the maintenance method based on time, that is, equipment detectio...

AI Technical Summary

Problems solved by technology

If these equipment damages are ignored or cannot be detected, it may lead to immeasurable consequences. Therefore, real-time fault monitoring has become one of the urgent issues in the industrial field.

Obviously, the method of equipment damage detection in industry has not been popularized so far. At present, most enterprises still adopt the maintenance method based on time, that is, equipment detection and maintenance are carried out at intervals (often based on human experience), but this method is easy to cause damage. Waste of resources and increased man-hours

There are also some enterprises that do not adopt the fault detection strategy, that is, temporarily shut down the line for maintenance after the fault occurs. This method will greatly increase unnecessary working hours, increase the downtime and greatly increase the cost.

Although, for these traditional methods, experts have proposed some schemes that use autoregressive model (AR), moving average model (MA) and autoregressive moving average model (ARMA) to train data to achieve equipment damage detection, but these schemes In the implementation process, it is easy to be affected by nonlinear factors in the detection object, resulting in inaccurate models, thereby reducing the accuracy of equipment damage detection

Images