An intelligent control method for post-peak failure process of hard rock under true triaxial disturbance

Abstract

The invention relates to the technical field of rock mechanics testing machine control, and provides an intelligent control method for the post-breakup process of hard rock peaks under true triaxial plane disturbance. First, determine the influencing factors of PID control parameters, including disturbance force amplitude, disturbance force frequency, deformation control rate, and rock brittleness index; PID control parameters to form a training sample set; then, build and train a PID control parameter prediction model based on evolutionary neural network; finally, use the trained prediction model to predict the optimal PID control parameters of the rock to be tested to control its surface disturbance under surface disturbance The post-peak failure process of hard rock is analyzed, and the training sample set is updated according to the test results to further optimize the prediction model. The invention can dynamically optimize the PID control parameters and the PID control parameter prediction model, and improve the precision and efficiency of the PID control parameter prediction.

Description

technical field [0001] The invention relates to the technical field of rock mechanics testing machine control, in particular to an intelligent control method for the post-peak failure process of hard rock under true triaxial disturbance. Background technique [0002] Obtaining the total stress-strain curve of rock through rock mechanics test with rock mechanics testing machine is an effective method to understand rock mechanics characteristics. With the rock peak strength as the boundary, the total stress-strain curve of the rock can be divided into the pre-peak area and the post-peak area. Usually the post-peak properties of rocks are very important to the stability of rock engineering. However, because the hard rock behind the peak is in an extremely unstable state, which is obviously different from that before the peak, the requirements for control performance are also extremely high. At present, in the static rock mechanics test, by increasing the rigidity and improvin...

AI Technical Summary

Problems solved by technology

If the frequency changes from low frequency to high frequency, the response speed of the low frequency PID parameters cannot meet the needs of high frequency. If the frequency changes from high frequency to low frequency, the high frequency PID parameter response is too fast but the stability is also unable to Get the expected disturbance force value

Fixed PID parameters will cause a decrease in response speed or response stability, making it impossible to obtain the desired control effect

And because the surface disturbance will be applied to the sample at any node in the whole process of the true triaxial stress state, the disturbance force cannot achieve the expected effect and the change rate of the rock fracture process will be different from the expected one. The fixed response ability may also be Unable to meet the demand of changing rupture rate, resulting in out of control of the post-peak process, so that the post-peak stress-strain curves under different frequency surface disturbance conditions cannot be obtained

If you want to obtain a better response and post-peak stress-strain curve at different disturbance frequencies, you need to repeatedly debug each frequency to obtain the optimal PID parameters corresponding to each frequency. This is undoubtedly cumbersome and will consume a lot of time and energy. Simultaneous trial success rate cannot be guaranteed

And because the current PID parameter control is an empirical control parameter, it is impossible to know the exact functional relationship between the frequency characteristics and the PID parameters

Therefore, the traditional static PID parameter adjustment method becomes very cumbersome under surface disturbance conditions

Images