CN117444776B - Drill bit processing control method and device - Google Patents

Abstract

The application relates to a drill bit processing control method and device. The method comprises the following steps: detecting whether the current time step is a spot check time step or not; if the current time step is a spot check time step, detecting the size parameter of the drill bit in the processing process to obtain the drill bit size parameter of the current time step, and correcting the prediction model; if the current time step is a non-sampling time step, predicting the drill bit dimension parameter of the current time step according to the prediction model and the drill bit processing information of the last time step; generating a feed feedback compensation parameter of a processing grinding wheel corresponding to the drill according to the drill size parameter of the current time step and a preset drill standard parameter; and controlling the processing grinding wheel to process the drill bit according to the feeding feedback compensation parameters. By adopting the method, more accurate feedback compensation parameters can be generated, thereby being beneficial to improving the processing precision of the drill bit.

Description

Drill bit processing control method and device

Technical Field

The application relates to the technical field of precision machining, in particular to a method and a device for controlling machining of a drill bit.

Background

Along with the development of the drill bit processing technology, a drill bit processing control technology appears, the technology tracks the error between the bar processed by the drill bit and the standard value of the drill bit, the compensation parameter generated by fitting the error and the feedback compensation model is fed back to a controller for drill bit processing, and the controller controls a drill bit processing cutter according to the feedback compensation parameter.

In the conventional technology, the drill bit machining control technology generally adopts off-line compensation, the off-line compensation is used for putting a newly machined drill bit into automatic measuring equipment for measurement through an automatic system, and then machining parameters of a machine tool are adjusted according to a measuring result and a compensation model.

However, due to the complex physical environment of the drill bit machining process, grinding fluid, temperature, humidity, rotating speed, air pressure, material feeding difference and the like in the grinding process may affect the grinding process, and the off-line compensation mode is adopted to perform compensation only once during feeding of the drill bit bar, so that as the machining process proceeds, the compensation parameter may not match with the actual drill bit dimension parameter, resulting in low drill bit machining precision.

Disclosure of Invention

In view of the above, it is desirable to provide a drill processing control method and apparatus that can improve the accuracy of drill processing.

In a first aspect, the present application provides a method of controlling drill bit machining. The method comprises the following steps:

detecting whether the current time step is a spot check time step or not;

if the current time step is a spot check time step, performing size parameter detection on a drill bit in the processing process to obtain a drill bit size parameter of the current time step, and correcting a prediction model according to the drill bit size parameter obtained by the current time step detection and the drill bit size parameter obtained by the previous time step prediction, wherein the prediction model is used for predicting the drill bit size parameter;

If the current time step is a non-sampling time step, predicting the drill bit dimension parameter of the current time step according to the prediction model and the drill bit processing information of the previous time step;

generating a feed feedback compensation parameter of a processing grinding wheel corresponding to the drill according to the drill size parameter of the current time step and a preset drill standard parameter;

and controlling the processing grinding wheel to process the drill bit according to the feeding feedback compensation parameters.

In one embodiment, predicting the drill bit dimension parameter of the current time step according to the prediction model and the drill bit processing information of the previous time step includes:

Acquiring drill bit processing information of the last time step, wherein the drill bit processing information of the last time step comprises drill bit size parameters, grinding wheel abrasion loss and feed feedback compensation parameters of the last time step; and according to the drill bit size parameter, the abrasion loss of the grinding wheel, the feed feedback compensation parameter and the prediction model of the last time step.

In one embodiment, the bit machining information includes an amount of grinding wheel wear; acquiring drill bit processing information of a previous time step, including:

acquiring the abrasion loss of the grinding wheel of each sampling inspection time step; linearly fitting the abrasion loss of the grinding wheel of each sampling inspection time step and the time value corresponding to each sampling inspection time step to obtain abrasion prediction information of the grinding wheel; and generating the abrasion loss of the grinding wheel in the last time step according to the abrasion prediction information of the grinding wheel and the time value of the last time step.

In one embodiment, before the obtaining the bit processing information of the previous time step, the method includes:

acquiring historical wear data of a processing grinding wheel in the processing process of the drill bit; and linearly fitting the abrasion loss in the historical abrasion data and the on-machine time of the processing grinding wheel to obtain a grinding wheel abrasion prediction model, wherein the grinding wheel abrasion prediction model is used for predicting the abrasion loss of the grinding wheel.

In one embodiment, the generating the feed feedback compensation parameter of the machining grinding wheel corresponding to the drill according to the drill size parameter of the current time step and the preset drill standard parameter includes:

generating a tracking error according to the bit size parameter of the current time step and a preset bit standard parameter; and generating a feedback compensation parameter according to the tracking error.

In one embodiment, the generating the feedback compensation parameter according to the tracking error includes:

If the tracking error is greater than or equal to a preset proportional compensation threshold, fitting the tracking error and a preset PID proportional parameter to obtain a feedback compensation parameter; and if the tracking error is smaller than the proportional compensation threshold, setting a feedback compensation parameter to be a preset compensation value.

In one embodiment, the correcting the prediction model according to the drill bit size parameter detected in the current time step and the drill bit size parameter predicted in the previous time step includes:

calculating to obtain the actual abrasion loss of the processing grinding wheel in the current time step according to the drill size parameter obtained by the detection in the current time step and the conversion relation between the profile of the processing grinding wheel and the profile of the drill bar;

predicting the predicted abrasion loss of the grinding wheel processed in the current time step according to the grinding wheel prediction model and the moment value of the current time step;

And correcting the prediction model according to the actual abrasion loss of the processing grinding wheel in the current time step and the predicted abrasion loss of the processing grinding wheel in the current time step until the predicted value obtained through the prediction model is identical with the detection value.

In a second aspect, the application also provides a drill processing control device. The device comprises:

the judging module is used for detecting whether the current time step is a spot check time step or not;

the detection module is used for detecting the size parameters of the drill bit in the processing process to obtain the size parameters of the drill bit in the current time step when the current time step is the spot check time step;

The correction module is used for correcting the prediction model according to the drill bit size parameter obtained by the current time step detection and the drill bit size parameter obtained by the previous time step prediction, wherein the prediction model is used for predicting the drill bit size parameter;

the prediction module is used for predicting the drill bit dimension parameter of the current time step according to the prediction model and the drill bit processing information of the previous time step when the current time step is a non-sampling inspection time step;

The compensation parameter generation module is used for generating feed feedback compensation parameters of the processing grinding wheel corresponding to the drill according to the drill size parameters of the current time step and preset drill standard parameters;

And the control processing module is used for controlling the processing grinding wheel to process the drill bit according to the feed feedback compensation parameter.

According to the drill bit processing control method and device, if the current time step is the spot check time step, the size parameter detection is carried out on the drill bit in the processing process to obtain the drill bit size parameter of the current time step, and the prediction model is corrected according to the drill bit size parameter obtained by the detection of the current time step and the drill bit size parameter obtained by the prediction of the last time step, wherein the prediction model is used for predicting the drill bit size parameter; if the current time step is a non-sampling time step, predicting the drill bit dimension parameter of the current time step according to the prediction model and the drill bit processing information of the previous time step; generating a feed feedback compensation parameter of a processing grinding wheel corresponding to the drill according to the drill size parameter of the current time step and a preset drill standard parameter; and controlling the processing grinding wheel to process the drill bit according to the feeding feedback compensation parameters. In the processing process of the drill bit, the drill bit dimension parameter of the current time step can be obtained through spot check or prediction at each time step, so that the feed feedback compensation of the processing grinding wheel can be carried out according to the feedback compensation parameter generated by the tracking error between the real-time dimension parameter of the drill bit and the standard parameter of the drill bit, and the generated feedback compensation parameter is more accurate, thereby being beneficial to improving the processing precision of the drill bit.

Drawings

FIG. 1 is a flow chart of a method of controlling drill processing in one embodiment;

FIG. 2 is a flow chart of a bit dimension parameter prediction process according to one embodiment;

FIG. 3 is a diagram of a predictive feedback compensation model of a method of bit process control in one embodiment;

FIG. 4 is a block diagram of a drill processing control device according to one embodiment;

Fig. 5 is an internal structural diagram of a computer device in one embodiment.

Detailed Description

The present application will be described in further detail with reference to the drawings and examples, in order to make the objects, technical solutions and advantages of the present application more apparent. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the application.

In one embodiment, as shown in fig. 1, a drill bit processing control method is provided, where the method is applied to a terminal for illustration, it is understood that the method may also be applied to a server, and may also be applied to a system including the terminal and the server, and implemented through interaction between the terminal and the server. In this embodiment, the method includes the steps of:

Step 202, detecting whether the current time step is a spot check time step.

In the drill bit machining process, since the size detection of the drill bit needs a certain time, the machining efficiency of the drill bit is considered, the drill bit is generally subjected to spot check once in a period of time, the spot check time step refers to the time step of performing size detection on the drill bit, and the spot check time step can be set in advance according to actual requirements.

Step 204, if the current time step is a spot check time step, performing size parameter detection on the drill bit in the machining process to obtain a drill bit size parameter of the current time step, and correcting a prediction model according to the drill bit size parameter obtained by the current time step detection and the drill bit size parameter obtained by the previous time step prediction, wherein the prediction model is used for predicting the drill bit size parameter of the current time step according to the drill bit machining information of the previous time step.

The sampling inspection time step can be used for detecting a plurality of drill bits, so that the average value and the extremely poor detection value of the drill bits are obtained. The average value of the detection of a plurality of drills is used as the drill size parameter of the current time step, so that the generality of the detection value can be improved, the accuracy of the detection value can be improved, and more accurate feedback compensation parameters can be generated; the machining precision difference between the integrated machines can be judged according to the range of the plurality of drill bits, and if the difference is too large, technicians can debug the integrated machine with large error, wherein the integrated machine is machining equipment of the drill bits; the dimensional parameters of the drill bit include the diameter of the drill bit, core thickness, helix angle, etc. The prediction model can be obtained by training according to the drill bit processing history detection data and is used for predicting the drill bit dimension parameter of the current time step according to the drill bit processing information of the previous time step, and because the prediction model is obtained by training according to the history data, errors possibly exist in actual prediction, the accurate of the prediction model can be verified and corrected according to the drill bit dimension parameter obtained by the random inspection time step, so that the prediction accuracy of the prediction model is improved.

As an example, step 204 includes: if the current time step is the spot check time step, shooting the spot check drill bit to obtain a drill bit spot check photo; and carrying out image analysis processing on the spot check photo to obtain the drill bit size parameter of the current time step, and correcting the prediction model according to the drill bit size parameter obtained by detecting the current time step and the drill bit size parameter obtained by predicting the previous time step.

And step 206, if the current time step is a non-sampling time step, predicting the drill bit dimension parameter of the current time step according to the prediction model and the drill bit processing information of the previous time step.

If the current time step is a non-sampling time step, the drill bit size parameter of the current time step can be predicted through historical detection data, the drill bit processing information of the previous time step comprises the drill bit size parameter, the abrasion loss of the grinding wheel and the feed feedback compensation parameter of the previous time step, and the drill bit processing information of the previous time step is used as the input parameter of a prediction model in prediction, so that the drill bit size parameter of the current time step can be predicted.

As one example, a predictive model, which may be a random forest decision model, may be trained from drill bit machining history detection data.

As an example, step 206 includes: if the current time step is a non-sampling inspection time step, acquiring drill bit processing information and a drill bit size prediction model of the last time step; and the drill bit size parameter of the current time step is predicted by inputting the drill bit processing information of the previous time step into a drill bit size prediction model.

And step 208, according to the drill size parameter of the current time step and the preset drill standard parameter, generating a feed feedback compensation parameter of the processing grinding wheel corresponding to the drill.

The method comprises the steps of determining a preset drill standard parameter, wherein the preset drill standard parameter is used for representing the target size of drill machining, the difference between the drill size parameter of the current time step and the preset drill standard parameter represents the accuracy of drill machining, and the smaller the error between the drill size parameter of the current time step and the preset drill standard parameter is, the higher the accuracy of drill machining is, otherwise, the lower the accuracy of drill machining is; the feeding feedback compensation parameter is a parameter for controlling the drill bit machining grinding wheel to carry out feeding compensation, and because the compensation parameter is generated according to the error between the drill bit dimension parameter of the current time step and the preset drill bit standard parameter, the actual feeding amount of the machining grinding wheel is adjusted according to the compensation parameter, so that the drill bit dimension parameter after the actual machining is finished can be as close to the preset drill bit standard parameter as possible, and the machining precision can be improved.

As one example, step 208 includes: generating a tracking error according to the drill bit size parameter of the current time step and a preset drill bit standard parameter; and aggregating the preset feedback parameters and the tracking errors to obtain feed feedback compensation parameters of the processing grinding wheel corresponding to the drill bit, wherein the aggregation mode can be product solving or summation and the like, and the preset feedback parameters are feedback coefficients set in advance.

And 210, controlling the processing grinding wheel to process the drill bit according to the feed feedback compensation parameters.

The processing grinding wheel is a processing cutter of the drill bit, the drill bit is processed through grinding the drill bit, in the processing process of the drill bit, the bar stock of the drill bit is fixed, and the drill bit can be processed through adjusting the feeding parameters of the processing grinding wheel, wherein the feeding parameters can be the feeding amount, the feeding angle and the like.

As an example, step 210 includes: compensating the current feeding parameters of the processing grinding wheel according to the feeding feedback compensation parameters to obtain compensated feeding parameters; and controlling the processing grinding wheel to process the drill bit according to the compensated feed parameters.

In the above drill bit processing control method, if the current time step is a spot check time step, performing size parameter detection on the drill bit in the processing process to obtain the drill bit size parameter of the current time step, and correcting a prediction model according to the drill bit size parameter obtained by the current time step detection and the drill bit size parameter obtained by the previous time step prediction, wherein the prediction model is used for predicting the drill bit size parameter of the current time step according to the drill bit processing information of the previous time step; if the current time step is a non-sampling detection time step, predicting the drill bit dimension parameter of the current time step according to the prediction model and the drill bit processing information of the previous time step; generating a feed feedback compensation parameter of a processing grinding wheel corresponding to the drill according to the drill size parameter of the current time step and a preset drill standard parameter; according to the feeding feedback compensation parameters, controlling a processing grinding wheel to process the drill bit; because the drill bit dimension parameter of the current time step can be obtained through spot check or prediction in each time step, the feed feedback compensation can be carried out on the processing grinding wheel according to the feedback compensation parameter generated by the tracking error between the real-time dimension parameter of the drill bit and the standard parameter of the drill bit, the generated feedback compensation parameter is more accurate, thereby being beneficial to improving the processing precision of the drill bit, and the prediction model is corrected in the spot check time step, so that the precision of the prediction model can be improved, the prediction precision of the drill bit dimension parameter is improved, and the generation of more accurate feedback compensation parameter is facilitated, thereby improving the processing precision of the drill bit.

In one embodiment, as shown in FIG. 2, predicting the bit dimension parameter for the current time step based on the prediction model and the bit machining information for the previous time step includes:

step 302, obtaining drill bit processing information of the last time step, wherein the drill bit processing information of the last time step comprises drill bit size parameters, grinding wheel abrasion loss and feed feedback compensation parameters of the last time step.

The processing grinding wheel of the drill bit is correspondingly worn along with the processing of the drill bit, the wearing capacity of the processing grinding wheel can be obtained through the profile change of the processing grinding wheel, and the profile change of the processing grinding wheel can be obtained through the conversion of the profile of the cutting face of the bar stock of the drill bit.

As an example, the conversion relationship of the profile of the machining wheel to the profile of the drill bar may be as follows:

Wherein, Representing the distance between the two origins of the drill bit coordinate system and the grinding wheel coordinate system,Representing the corresponding rotation angle between the established drill bit coordinate system and the grinding wheel coordinate system,The rotation angle of the processing grinding wheel around the grinding wheel shaft is shown,As a bit profile data point,Representing the machining wheel data points.

As an example, step 302 includes: if the last time step is a spot check time step, obtaining a drill bit dimension parameter, a grinding wheel abrasion loss and a feed feedback compensation parameter of the last time step according to a drill bit detection result; if the last time step is a non-sampling time step, obtaining drill bit dimension parameters and feed feedback compensation parameters of the last time step according to the prediction result of the drill bit of the last time step, and predicting the abrasion loss of the grinding wheel of the last time step according to the abrasion prediction model of the grinding wheel.

As an example, the output result of the grinding wheel wear prediction model may be obtained by proportionally fusing a detected predicted wear amount, which may be obtained according to a corresponding relationship between the grinding wheel wear amount after the grinding wheel is on machine and time, and a historical predicted wear amount, which may be obtained according to a corresponding relationship between the grinding wheel wear amount after the grinding wheel is on machine and time.

As an example, a specific mathematical expression of the grinding wheel wear prediction model may be as follows:

Wherein, Representation ofThe abrasion loss of the grinding wheel is processed at any time,，Indicating that the predicted amount of wear is detected,Representing the amount of wear that has been predicted in the history,、The specific expression is as follows:

Wherein, Are all constants, according to the actual processing conditions, along with the accumulation of the time of the grinding wheel on machine,Linearly increasing in time from 0 to 1,The abrasion quantity of the processing grinding wheel can be accurately predicted by the aid of the abrasion prediction model of the grinding wheel, which is constructed by linearly decreasing from 1 to 0 according to time.

Step 304, predicting the drill bit size parameter of the current time step according to the drill bit size parameter, the abrasion loss of the grinding wheel, the feed feedback compensation parameter and the prediction model of the previous time step.

The prediction of the drill bit size parameter of the current time step can be generated through prediction by a trained prediction model.

As an example, a random forest decision model is built to predict dimensional changes, specifically built as follows: and constructing N decision trees, wherein the N decision trees participate in calculation together, and arithmetic average is carried out on calculation results of all the decision trees to obtain a final predicted value. And taking out data from the latest typical period detection data, and dividing three subsets of a training set, a verification set and a test set. Wherein the training set is used to train the decision tree, the validation set is used to adjust the decision tree to prevent overfitting, and the test set is used to ultimately validate the accuracy of the predictive model. The specific model construction process is input into size detection data X, grinding wheel abrasion W, feed compensation parameter K and time step T, the next size detection data Y is output, and the finally obtained prediction model is a black box regression function:。

As an example, step 304 includes: taking the drill bit size parameter, the abrasion loss of the grinding wheel, the feed feedback compensation parameter and the time step of the last time step as the input of a prediction model, and predicting the drill bit size parameter of the current time step.

Further, a first drill bit size parameter of the current time step is obtained through spot check, the drill bit size parameter, the abrasion loss of the grinding wheel, the feed feedback compensation parameter and the time step of the last time step are used as inputs of a prediction model, a second drill bit size parameter of the current time step is obtained through prediction, and if the error between the first drill bit size parameter and the second drill bit size parameter is smaller than or equal to a preset threshold value, the prediction model is reliable; if the error of the first drill bit size parameter and the second drill bit size parameter is larger than the preset threshold, the prediction error of the prediction model is too large, the prediction model is corrected at the moment, the accuracy of the prediction model for predicting the drill bit size parameter can be improved by correcting the prediction model, and when the accuracy of the prediction model meets the preset accuracy, the sampling frequency can be reduced, so that the drill bit machining efficiency is improved.

In the above embodiment, the processing information of the drill bit in the previous time step is obtained, where the processing information of the drill bit in the previous time step includes the size parameter of the drill bit in the previous time step, the abrasion loss of the grinding wheel, and the feeding feedback compensation parameter; and predicting the drill bit size parameter of the current time step according to the drill bit size parameter of the previous time step, the abrasion loss of the grinding wheel, the feed feedback compensation parameter and the prediction model. Considering the abrasion factor of the processing grinding wheel, the drill size parameter of the next time step is predicted through the drill size parameter of the last time step, the abrasion quantity of the grinding wheel and the feed feedback compensation parameter, and the predicted drill size parameter is more accurate.

In one embodiment, the bit machining information includes an amount of grinding wheel wear; acquiring drill bit processing information of a previous time step, including:

acquiring the abrasion loss of the grinding wheel of each sampling inspection time step; linearly fitting the abrasion loss of the grinding wheel of each sampling inspection time step and the corresponding time value of each sampling inspection time step to obtain abrasion prediction information of the grinding wheel; and generating the abrasion loss of the grinding wheel in the last time step according to the abrasion prediction information of the grinding wheel and the time value of the last time step.

Specifically, the abrasion loss of the grinding wheel of each sampling inspection time step is obtained; the grinding wheel abrasion loss of each sampling inspection time step and the corresponding time value of each sampling inspection time step are fused to obtain an average value, so that an average abrasion rate is obtained; constructing a linear function related to time according to the average wear rate to obtain a grinding wheel wear prediction function; and generating the abrasion loss of the grinding wheel in the last time step according to the abrasion prediction function of the grinding wheel and the time value of the last time step.

As an example, the grinding wheel wear amount for each spot check time step may be the grinding wheel wear amount for each spot check time step at a preset interval from the current time step time.

In the embodiment, the linear relation between the abrasion loss of the grinding wheel and the on-machine time of the grinding wheel is constructed according to the abrasion loss of the grinding wheel at each sampling time, and the abrasion loss of the grinding wheel at the non-sampling time step can be obtained according to the linear relation and the time value of the non-sampling time step, so that the prediction efficiency and the accuracy of the abrasion loss prediction of the grinding wheel can be improved.

In one embodiment, prior to obtaining the bit processing information for the previous time step, the method comprises:

Acquiring historical wear data of a processing grinding wheel in the processing process of the drill bit; and linearly fitting the abrasion loss in the historical abrasion data and the on-machine time of the processing grinding wheel to obtain a grinding wheel abrasion prediction model, wherein the grinding wheel abrasion prediction model is used for predicting the abrasion loss of the grinding wheel.

Specifically, historical wear data of a processing grinding wheel in the processing process of the drill bit are obtained; the historical wear data and the on-machine time corresponding to the grinding wheel are fused to obtain an average value, and an average wear rate is obtained; and constructing a linear function related to time according to the average wear rate to obtain a grinding wheel wear prediction model, wherein the grinding wheel wear prediction model is used for predicting the grinding wheel wear.

In the above embodiment, the grinding wheel abrasion prediction model is constructed through the historical abrasion data of the processing grinding wheel in the drill processing process, and the abrasion quantity of the processing grinding wheel can be predicted through the grinding wheel abrasion prediction model when the current on-machine grinding wheel detection data is insufficient, so that the accurate grinding wheel abrasion quantity can be obtained.

In one embodiment, generating a feed feedback compensation parameter of a machining grinding wheel corresponding to a drill according to a drill size parameter of a current time step and a preset drill standard parameter includes:

Generating a tracking error according to the drill bit size parameter of the current time step and a preset drill bit standard parameter; and generating a feedback compensation parameter according to the tracking error.

The preset PID compensation parameter may be a compensation parameter with an optimal historical compensation effect.

Specifically, the bit size parameter of the current time step and the preset bit standard parameter are subjected to difference to generate tracking error; and fusing the tracking error and the preset PID compensation parameter to generate a feedback compensation parameter.

As an example, a specific mathematical expression of the feedback compensation parameter is as follows:

Wherein, Representing the feedback compensation parameter(s),Respectively representing proportional compensation parameters, integral compensation parameters and differential compensation parameters of the PID control algorithm,Represent the firstTracking error of time steps.

As an example, the integral compensation parameter of the PID control algorithmDifferential compensation parameterSet to 0.

In the embodiment, the processing of the drill bit can be controlled by the PID control algorithm to reach a stable control state more quickly, can be converged to the target value more quickly, can better inhibit the self-oscillation of the system, and improves the accuracy of the system; thereby being beneficial to improving the processing efficiency and the processing precision of the drill bit.

In one embodiment, generating the feedback compensation parameter from the tracking error includes:

if the tracking error is greater than or equal to the preset proportional compensation threshold, fitting the tracking error and the preset PID proportional parameter to obtain a feedback compensation parameter; and if the tracking error is smaller than the proportional compensation threshold, setting a preset compensation value as a feedback compensation parameter.

The proportional compensation threshold value can represent preset machining precision of drill bit machining, tracking error is larger than or equal to the proportional compensation threshold value, so that the predicted required machining progress is not met, at the moment, feedback compensation parameters are continuously generated to feed the machining grinding wheel for feedback compensation, if tracking error is smaller than the proportional compensation threshold value, the fact that the machining precision of the drill bit meets the preset precision requirement is indicated, at the moment, a preset compensation value can be used as the feedback compensation parameters, and the preset compensation value can be 0.

In this embodiment, whether feed feedback compensation is needed is determined according to the relationship between the tracking error and the proportional compensation threshold, so that unnecessary feedback compensation times can be reduced while machining precision is ensured, and only feed is compensated by proportional control, which is helpful for improving the machining efficiency of the drill bit.

In one embodiment, correcting the prediction model according to the drill bit size parameter detected in the current time step and the drill bit size parameter predicted in the previous time step includes:

According to the drill bit dimension parameter obtained by detecting the current time step and the conversion relation between the profile of the processing grinding wheel and the profile of the drill bit bar, calculating to obtain the actual abrasion loss of the processing grinding wheel of the current time step; predicting the predicted abrasion loss of the grinding wheel processed in the current time step according to the grinding wheel prediction model and the moment value of the current time step; and correcting the prediction model according to the actual abrasion loss of the processing grinding wheel in the current time step and the predicted abrasion loss of the processing grinding wheel in the current time step until the predicted value obtained through the prediction model is consistent with the detection value.

As an example, a specific mathematical expression for modifying the predictive model is as follows:

Wherein, Representing the modified predictive model and the model of the model,Indicating that a predictive model needs to be modified,A bit size parameter representing the current time step obtained by spot check,=/，The predicted wear amount of the grinding wheel is processed for the current time step,The actual wear of the grinding wheel is processed for the current time step.

And predicting the predicted value of the current spot check time step by using the corrected predicted model, continuously comparing the newly obtained predicted value with the detected value, and continuously iteratively adjusting the predicted model by using the formula if the difference between the predicted value and the current spot check value is still higher than a preset threshold value.

In this embodiment, the prediction model is corrected by the drill bit size parameter detected in the spot check time step and the drill bit size parameter predicted in the previous time step, and the prediction accuracy can be improved by using the corrected prediction model to predict later, so that the machining accuracy of the drill bit is improved.

In one embodiment, as shown in fig. 3, the detection data of the historical integrated machine K1 includes the abrasion loss of the grinding wheel at the historical sampling time step and the drill bit processing data at the historical sampling time step, the compensation value of the integrated machine is the feed feedback compensation parameter of the historical sampling time step, the time for changing the grinding wheel is the time for loading and unloading the historical processing grinding wheel, and the time period from the loading time to the unloading time is divided into one period; calculating the historical abrasion loss of the grinding wheel according to the drill bit processing data of the historical spot check time step, and training and generating a prediction model of the drill bit size by a random forest algorithm according to the drill bit processing data of the historical spot check time step, the historical abrasion loss of the grinding wheel and the feed feedback compensation parameters of the historical spot check time step, wherein the prediction model is used for predicting the size parameters of the drill bit in the non-spot check time step.

In the drill bit processing process, detecting whether the current time step is a sampling inspection time step or not; if the current time step is a spot check time step, performing size parameter detection on the drill bit in the machining process to obtain the drill bit size parameter of the current time step, and correcting a prediction model according to the drill bit size parameter obtained by the detection of the current time step and the drill bit size parameter obtained by the prediction of the previous time step, wherein the prediction model is used for predicting the drill bit size parameter of the current time step according to the drill bit machining information of the previous time step; if the current time step is a non-sampling time step, acquiring drill bit processing information of the last time step, wherein the drill bit processing information of the last time step comprises drill bit size parameters, grinding wheel abrasion loss and feed feedback compensation parameters of the last time step; predicting the drill bit size parameter of the current time step according to the drill bit size parameter, the grinding wheel abrasion loss, the feed feedback compensation parameter, the prediction model and the prediction model of the previous time step, wherein the grinding wheel abrasion loss can be predicted by the grinding wheel prediction model; because the drill bit dimension parameter of the current time step can be obtained through spot check or prediction in each time step, the feed feedback compensation of the processing grinding wheel can be carried out according to the feedback compensation parameter generated by the tracking error between the real-time dimension parameter of the drill bit and the standard parameter of the drill bit, and the generated feedback compensation parameter is more accurate, so that the processing precision of the drill bit is improved.

Further, generating a tracking error according to the bit size parameter of the current time step and a preset bit standard parameter; if the tracking error is greater than or equal to the proportional compensation threshold, fitting the tracking error and a preset PID proportional parameter to obtain a feedback compensation parameter; if the tracking error is smaller than the proportional compensation threshold, setting a feedback compensation parameter to be a preset compensation value; according to the feeding feedback compensation parameters, controlling a processing grinding wheel to process the drill bit; by determining whether feed feedback compensation is needed according to the relation between the tracking error and the proportional compensation threshold, unnecessary feedback compensation times can be reduced while machining precision is ensured, and feed is compensated only through proportional control, so that the machining efficiency of the drill bit is improved.

It should be understood that, although the steps in the flowcharts related to the embodiments described above are sequentially shown as indicated by arrows, these steps are not necessarily sequentially performed in the order indicated by the arrows. The steps are not strictly limited to the order of execution unless explicitly recited herein, and the steps may be executed in other orders. Moreover, at least some of the steps in the flowcharts described in the above embodiments may include a plurality of steps or a plurality of stages, which are not necessarily performed at the same time, but may be performed at different times, and the order of the steps or stages is not necessarily performed sequentially, but may be performed alternately or alternately with at least some of the other steps or stages.

Based on the same inventive concept, the embodiment of the application also provides a drill processing control device for realizing the drill processing control method. The implementation of the solution provided by the device is similar to that described in the above method, so the specific limitation of one or more embodiments of the drill processing control device provided below may refer to the limitation of the drill processing control method hereinabove, and will not be repeated herein.

In one embodiment, as shown in fig. 4, there is provided a drill processing control apparatus comprising: a determination module 402, a detection module 404, a correction module 406, a prediction module 408, a compensation parameter generation module 410, and a control process module 412, wherein:

a judging module 402, configured to detect whether the current time step is a spot check time step;

The detection module 404 is configured to detect a size parameter of the drill bit in the machining process when the current time step is a spot check time step, so as to obtain a size parameter of the drill bit in the current time step;

The correction module 406 is configured to correct a prediction model according to the drill bit size parameter detected in the current time step and the drill bit size parameter obtained in the previous time step, where the prediction model is used to predict the drill bit size parameter;

A prediction module 408, configured to predict a drill bit size parameter of the current time step according to the prediction model and drill bit processing information of a previous time step when the current time step is a non-sampling time step;

The compensation parameter generation module 410 is configured to generate a feed feedback compensation parameter of the processing grinding wheel corresponding to the drill according to the drill size parameter of the current time step and a preset drill standard parameter;

And the control processing module 412 is used for controlling the processing grinding wheel to process the drill bit according to the feed feedback compensation parameter.

In one embodiment, the prediction module 408 is further configured to:

Acquiring drill bit processing information of the last time step, wherein the drill bit processing information of the last time step comprises drill bit size parameters, grinding wheel abrasion loss and feed feedback compensation parameters of the last time step; and according to the drill bit size parameter, the abrasion loss of the grinding wheel, the feed feedback compensation parameter and the prediction model of the last time step.

In one embodiment, the bit machining information includes an amount of grinding wheel wear; the prediction module 408 is further configured to:

acquiring the abrasion loss of the grinding wheel of each sampling inspection time step; linearly fitting the abrasion loss of the grinding wheel of each sampling inspection time step and the time value corresponding to each sampling inspection time step to obtain abrasion prediction information of the grinding wheel; and generating the abrasion loss of the grinding wheel in the last time step according to the abrasion prediction information of the grinding wheel and the time value of the last time step.

In one embodiment, the drill bit machining control device further includes a grinding wheel wear prediction model generation module for:

acquiring historical wear data of a processing grinding wheel in the processing process of the drill bit; and linearly fitting the abrasion loss in the historical abrasion data and the on-machine time of the processing grinding wheel to obtain a grinding wheel abrasion prediction model, wherein the grinding wheel abrasion prediction model is used for predicting the abrasion loss of the grinding wheel.

In one embodiment, the compensation parameter generation module 410 is further configured to:

generating a tracking error according to the bit size parameter of the current time step and a preset bit standard parameter; and generating a feedback compensation parameter according to the tracking error.

In one embodiment, the compensation parameter generation module 410 is further configured to:

If the tracking error is greater than or equal to a preset proportional compensation threshold, fitting the tracking error and a preset PID proportional parameter to obtain a feedback compensation parameter; and if the tracking error is smaller than the proportional compensation threshold, setting a feedback compensation parameter to be a preset compensation value.

In one embodiment, the detection module 404 is further configured to:

Acquiring drill bit processing information of the last time step, wherein the drill bit processing information of the last time step comprises drill bit size parameters, grinding wheel abrasion loss and feed feedback compensation parameters of the last time step; and predicting the drill bit size parameter of the current time step according to the drill bit size parameter of the last time step, the abrasion loss of the grinding wheel, the feed feedback compensation parameter and the prediction model.

In one embodiment, the correction module 406 is further configured to:

Calculating to obtain the actual abrasion loss of the processing grinding wheel in the current time step according to the drill size parameter obtained by the detection in the current time step and the conversion relation between the profile of the processing grinding wheel and the profile of the drill bar; predicting the predicted abrasion loss of the grinding wheel processed in the current time step according to the grinding wheel prediction model and the moment value of the current time step; and correcting the prediction model according to the actual abrasion loss of the processing grinding wheel in the current time step and the predicted abrasion loss of the processing grinding wheel in the current time step until the predicted value obtained through the prediction model is identical with the detection value.

The various modules in the drill bit machining control device described above may be implemented in whole or in part by software, hardware, and combinations thereof. The above modules may be embedded in hardware or may be independent of a processor in the computer device, or may be stored in software in a memory in the computer device, so that the processor may call and execute operations corresponding to the above modules.

In one embodiment, a computer device is provided, which may be a server, the internal structure of which may be as shown in fig. 5. The computer device includes a processor, a memory, and a network interface connected by a system bus. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, computer programs, and a database. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage media. The database of the computer device is used for storing drill bit history detection data. The network interface of the computer device is used for communicating with an external terminal through a network connection. The computer program is executed by a processor to implement a drill processing control method.

It will be appreciated by those skilled in the art that the structure shown in FIG. 5 is merely a block diagram of some of the structures associated with the present inventive arrangements and is not limiting of the computer device to which the present inventive arrangements may be applied, and that a particular computer device may include more or fewer components than shown, or may combine some of the components, or have a different arrangement of components.

In one embodiment, a computer device is provided comprising a memory and a processor, the memory having stored therein a computer program, the processor when executing the computer program performing the steps of:

Detecting whether the current time step is a spot check time step or not; if the current time step is a spot check time step, performing size parameter detection on a drill bit in the processing process to obtain a drill bit size parameter of the current time step, and correcting a prediction model according to the drill bit size parameter obtained by the current time step detection and the drill bit size parameter obtained by the previous time step prediction, wherein the prediction model is used for predicting the drill bit size parameter; if the current time step is a non-sampling time step, predicting the drill bit dimension parameter of the current time step according to the prediction model and the drill bit processing information of the previous time step; generating a feed feedback compensation parameter of a processing grinding wheel corresponding to the drill according to the drill size parameter of the current time step and a preset drill standard parameter; and controlling the processing grinding wheel to process the drill bit according to the feeding feedback compensation parameters.

In one embodiment, the processor when executing the computer program further performs the steps of:

Acquiring drill bit processing information of the last time step, wherein the drill bit processing information of the last time step comprises drill bit size parameters, grinding wheel abrasion loss and feed feedback compensation parameters of the last time step; and according to the drill bit size parameter, the abrasion loss of the grinding wheel, the feed feedback compensation parameter and the prediction model of the last time step.

In one embodiment, the processor when executing the computer program further performs the steps of:

acquiring the abrasion loss of the grinding wheel of each sampling inspection time step; linearly fitting the abrasion loss of the grinding wheel of each sampling inspection time step and the time value corresponding to each sampling inspection time step to obtain abrasion prediction information of the grinding wheel; and generating the abrasion loss of the grinding wheel in the last time step according to the abrasion prediction information of the grinding wheel and the time value of the last time step.

In one embodiment, the processor when executing the computer program further performs the steps of:

acquiring historical wear data of a processing grinding wheel in the processing process of the drill bit; and linearly fitting the abrasion loss in the historical abrasion data and the on-machine time of the processing grinding wheel to obtain a grinding wheel abrasion prediction model, wherein the grinding wheel abrasion prediction model is used for predicting the abrasion loss of the grinding wheel.

In one embodiment, the processor when executing the computer program further performs the steps of:

generating a tracking error according to the bit size parameter of the current time step and a preset bit standard parameter; and generating a feedback compensation parameter according to the tracking error.

In one embodiment, the processor when executing the computer program further performs the steps of:

If the tracking error is greater than or equal to a preset proportional compensation threshold, fitting the tracking error and a preset PID proportional parameter to obtain a feedback compensation parameter; and if the tracking error is smaller than the proportional compensation threshold, setting a feedback compensation parameter to be a preset compensation value.

In one embodiment, the processor when executing the computer program further performs the steps of:

Calculating to obtain the actual abrasion loss of the processing grinding wheel in the current time step according to the drill size parameter obtained by the detection in the current time step and the conversion relation between the profile of the processing grinding wheel and the profile of the drill bar; predicting the predicted abrasion loss of the grinding wheel processed in the current time step according to the grinding wheel prediction model and the moment value of the current time step; and correcting the prediction model according to the actual abrasion loss of the processing grinding wheel in the current time step and the predicted abrasion loss of the processing grinding wheel in the current time step until the predicted value obtained through the prediction model is identical with the detection value.

In one embodiment, a computer readable storage medium is provided having a computer program stored thereon, which when executed by a processor, performs the steps of:

Detecting whether the current time step is a spot check time step or not; if the current time step is a spot check time step, performing size parameter detection on a drill bit in the processing process to obtain a drill bit size parameter of the current time step, and correcting a prediction model according to the drill bit size parameter obtained by the current time step detection and the drill bit size parameter obtained by the previous time step prediction, wherein the prediction model is used for predicting the drill bit size parameter; if the current time step is a non-sampling time step, predicting the drill bit dimension parameter of the current time step according to the prediction model and the drill bit processing information of the previous time step; generating a feed feedback compensation parameter of a processing grinding wheel corresponding to the drill according to the drill size parameter of the current time step and a preset drill standard parameter; and controlling the processing grinding wheel to process the drill bit according to the feeding feedback compensation parameters.

In one embodiment, the computer program when executed by the processor further performs the steps of:

Acquiring drill bit processing information of the last time step, wherein the drill bit processing information of the last time step comprises drill bit size parameters, grinding wheel abrasion loss and feed feedback compensation parameters of the last time step; and according to the drill bit size parameter, the abrasion loss of the grinding wheel, the feed feedback compensation parameter and the prediction model of the last time step.

In one embodiment, the computer program when executed by the processor further performs the steps of:

acquiring the abrasion loss of the grinding wheel of each sampling inspection time step; linearly fitting the abrasion loss of the grinding wheel of each sampling inspection time step and the time value corresponding to each sampling inspection time step to obtain abrasion prediction information of the grinding wheel; and generating the abrasion loss of the grinding wheel in the last time step according to the abrasion prediction information of the grinding wheel and the time value of the last time step.

In one embodiment, the computer program when executed by the processor further performs the steps of:

acquiring historical wear data of a processing grinding wheel in the processing process of the drill bit; and linearly fitting the abrasion loss in the historical abrasion data and the on-machine time of the processing grinding wheel to obtain a grinding wheel abrasion prediction model, wherein the grinding wheel abrasion prediction model is used for predicting the abrasion loss of the grinding wheel.

In one embodiment, the computer program when executed by the processor further performs the steps of:

generating a tracking error according to the bit size parameter of the current time step and a preset bit standard parameter; and generating a feedback compensation parameter according to the tracking error.

In one embodiment, the computer program when executed by the processor further performs the steps of:

If the tracking error is greater than or equal to a preset proportional compensation threshold, fitting the tracking error and a preset PID proportional parameter to obtain a feedback compensation parameter; and if the tracking error is smaller than the proportional compensation threshold, setting a feedback compensation parameter to be a preset compensation value.

In one embodiment, the computer program when executed by the processor further performs the steps of:

Calculating to obtain the actual abrasion loss of the processing grinding wheel in the current time step according to the drill size parameter obtained by the detection in the current time step and the conversion relation between the profile of the processing grinding wheel and the profile of the drill bar; predicting the predicted abrasion loss of the grinding wheel processed in the current time step according to the grinding wheel prediction model and the moment value of the current time step; and correcting the prediction model according to the actual abrasion loss of the processing grinding wheel in the current time step and the predicted abrasion loss of the processing grinding wheel in the current time step until the predicted value obtained through the prediction model is identical with the detection value.

In one embodiment, a computer program product is provided comprising a computer program which, when executed by a processor, performs the steps of:

Detecting whether the current time step is a spot check time step or not; if the current time step is a spot check time step, performing size parameter detection on a drill bit in the processing process to obtain a drill bit size parameter of the current time step, and correcting a prediction model according to the drill bit size parameter obtained by the current time step detection and the drill bit size parameter obtained by the previous time step prediction, wherein the prediction model is used for predicting the drill bit size parameter; if the current time step is a non-sampling time step, predicting the drill bit dimension parameter of the current time step according to the prediction model and the drill bit processing information of the previous time step; generating a feed feedback compensation parameter of a processing grinding wheel corresponding to the drill according to the drill size parameter of the current time step and a preset drill standard parameter; and controlling the processing grinding wheel to process the drill bit according to the feeding feedback compensation parameters.

In one embodiment, the computer program when executed by the processor further performs the steps of:

Acquiring drill bit processing information of the last time step, wherein the drill bit processing information of the last time step comprises drill bit size parameters, grinding wheel abrasion loss and feed feedback compensation parameters of the last time step; and according to the drill bit size parameter, the abrasion loss of the grinding wheel, the feed feedback compensation parameter and the prediction model of the last time step.

In one embodiment, the computer program when executed by the processor further performs the steps of:

acquiring the abrasion loss of the grinding wheel of each sampling inspection time step; linearly fitting the abrasion loss of the grinding wheel of each sampling inspection time step and the time value corresponding to each sampling inspection time step to obtain abrasion prediction information of the grinding wheel; and generating the abrasion loss of the grinding wheel in the last time step according to the abrasion prediction information of the grinding wheel and the time value of the last time step.

In one embodiment, the computer program when executed by the processor further performs the steps of:

acquiring historical wear data of a processing grinding wheel in the processing process of the drill bit; and linearly fitting the abrasion loss in the historical abrasion data and the on-machine time of the processing grinding wheel to obtain a grinding wheel abrasion prediction model, wherein the grinding wheel abrasion prediction model is used for predicting the abrasion loss of the grinding wheel.

In one embodiment, the computer program when executed by the processor further performs the steps of:

generating a tracking error according to the bit size parameter of the current time step and a preset bit standard parameter; and generating a feedback compensation parameter according to the tracking error.

In one embodiment, the computer program when executed by the processor further performs the steps of:

If the tracking error is greater than or equal to a preset proportional compensation threshold, fitting the tracking error and a preset PID proportional parameter to obtain a feedback compensation parameter; and if the tracking error is smaller than the proportional compensation threshold, setting a feedback compensation parameter to be a preset compensation value.

In one embodiment, the computer program when executed by the processor further performs the steps of:

Calculating to obtain the actual abrasion loss of the processing grinding wheel in the current time step according to the drill size parameter obtained by the detection in the current time step and the conversion relation between the profile of the processing grinding wheel and the profile of the drill bar; predicting the predicted abrasion loss of the grinding wheel processed in the current time step according to the grinding wheel prediction model and the moment value of the current time step; and correcting the prediction model according to the actual abrasion loss of the processing grinding wheel in the current time step and the predicted abrasion loss of the processing grinding wheel in the current time step until the predicted value obtained through the prediction model is identical with the detection value.

Those skilled in the art will appreciate that implementing all or part of the above described methods may be accomplished by way of a computer program stored on a non-transitory computer readable storage medium, which when executed, may comprise the steps of the embodiments of the methods described above. Any reference to memory, database, or other medium used in embodiments provided herein may include at least one of non-volatile and volatile memory. The nonvolatile Memory may include Read-Only Memory (ROM), magnetic tape, floppy disk, flash Memory, optical Memory, high density embedded nonvolatile Memory, resistive random access Memory (ReRAM), magneto-resistive random access Memory (Magnetoresistive Random Access Memory, MRAM), ferroelectric Memory (Ferroelectric Random Access Memory, FRAM), phase change Memory (PHASE CHANGE Memory, PCM), graphene Memory, and the like. Volatile memory can include random access memory (Random Access Memory, RAM) or external cache memory, and the like. By way of illustration, and not limitation, RAM can be in various forms such as static random access memory (Static Random Access Memory, SRAM) or dynamic random access memory (Dynamic Random Access Memory, DRAM), etc. The databases referred to in the embodiments provided herein may include at least one of a relational database and a non-relational database. The non-relational database may include, but is not limited to, a blockchain-based distributed database, and the like. The processor referred to in the embodiments provided in the present application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic unit, a data processing logic unit based on quantum computing, or the like, but is not limited thereto.

The technical features of the above embodiments may be arbitrarily combined, and all possible combinations of the technical features in the above embodiments are not described for brevity of description, however, as long as there is no contradiction between the combinations of the technical features, they should be considered as the scope of the description.

The foregoing examples illustrate only a few embodiments of the application and are described in detail herein without thereby limiting the scope of the application. It should be noted that it will be apparent to those skilled in the art that several variations and modifications can be made without departing from the spirit of the application, which are all within the scope of the application. Accordingly, the scope of the application should be assessed as that of the appended claims.

Claims (10)

1.A method of drill bit machining control, the method comprising:

detecting whether the current time step is a spot check time step or not;

if the current time step is a spot check time step, detecting a size parameter of a drill bit in the machining process to obtain the drill bit size parameter of the current time step, and calculating to obtain the actual abrasion loss of the machining grinding wheel of the current time step according to the drill bit size parameter detected by the current time step and the conversion relation between the contour of the machining grinding wheel and the contour of the drill bit bar; predicting the predicted abrasion loss of the grinding wheel processed in the current time step according to the grinding wheel prediction model and the moment value of the current time step; correcting a prediction model according to the actual abrasion loss of the current time step machining abrasion wheel and the predicted abrasion loss of the current time step machining abrasion wheel until a predicted value obtained through the prediction model is identical with a detection value, wherein the prediction model is used for predicting drill bit dimension parameters;

If the current time step is a non-sampling time step, acquiring bit processing information of the last time step, wherein the bit processing information of the last time step comprises bit size parameters, grinding wheel abrasion loss and feed feedback compensation parameters of the last time step; predicting the drill bit size parameter of the current time step according to the drill bit size parameter of the previous time step, the abrasion loss of the grinding wheel, the feed feedback compensation parameter and the prediction model; the method for acquiring the abrasion loss of the grinding wheel in the drill bit processing information in the last time step comprises the following steps of: acquiring the abrasion loss of the grinding wheel of each sampling inspection time step; linearly fitting the abrasion loss of the grinding wheel of each sampling inspection time step and the time value corresponding to each sampling inspection time step to obtain abrasion prediction information of the grinding wheel; generating the abrasion loss of the grinding wheel in the last time step according to the abrasion prediction information of the grinding wheel and the time value of the last time step;

Generating a tracking error according to the bit size parameter of the current time step and a preset bit standard parameter;

If the tracking error is greater than or equal to a preset proportional compensation threshold, fitting the tracking error and a preset PID proportional parameter to obtain a feed feedback compensation parameter;

If the tracking error is smaller than the preset proportional compensation threshold, setting a preset compensation value as a feed feedback compensation parameter;

and controlling the processing grinding wheel to process the drill bit according to the feeding feedback compensation parameters.

2. The method of claim 1, wherein the step of performing dimension parameter detection on the drill bit during the machining process to obtain the drill bit dimension parameter of the current time step comprises:

Detecting a plurality of drill bits in the processing process to obtain the detection mean value and extremely poor of the drill bits;

taking the detection average value of a plurality of drill bits as the drill bit dimension parameter of the current time step.

3. The method of claim 1, wherein the drill bit dimension parameters include a diameter, a core thickness, and a helix angle of the drill bit.

4. The method of claim 1, comprising, prior to said obtaining bit processing information for a previous time step:

Acquiring historical wear data of a processing grinding wheel in the processing process of the drill bit;

and linearly fitting the abrasion loss in the historical abrasion data and the on-machine time of the processing grinding wheel to obtain a grinding wheel abrasion prediction model, wherein the grinding wheel abrasion prediction model is used for predicting the abrasion loss of the grinding wheel.

5. A drill processing control apparatus for performing the drill processing control method according to any one of claims 1 to 4, the apparatus comprising:

the judging module is used for detecting whether the current time step is a spot check time step or not;

the detection module is used for detecting the size parameters of the drill bit in the processing process to obtain the size parameters of the drill bit in the current time step when the current time step is the spot check time step;

The correction module is used for calculating the actual abrasion loss of the processing grinding wheel in the current time step according to the drill size parameter obtained by the detection in the current time step and the conversion relation between the profile of the processing grinding wheel and the profile of the drill bar; predicting the predicted abrasion loss of the grinding wheel processed in the current time step according to the grinding wheel prediction model and the moment value of the current time step; correcting a prediction model according to the actual abrasion loss of the current time step machining abrasion wheel and the predicted abrasion loss of the current time step machining abrasion wheel until a predicted value obtained through the prediction model is identical with a detection value, wherein the prediction model is used for predicting drill bit dimension parameters;

The prediction module is used for acquiring drill bit processing information of the last time step when the current time step is a non-sampling inspection time step, wherein the drill bit processing information of the last time step comprises drill bit size parameters, grinding wheel abrasion loss and feed feedback compensation parameters of the last time step; predicting the drill bit size parameter of the current time step according to the drill bit size parameter of the previous time step, the abrasion loss of the grinding wheel, the feed feedback compensation parameter and the prediction model; the method for acquiring the abrasion loss of the grinding wheel in the drill bit processing information in the last time step comprises the following steps of: acquiring the abrasion loss of the grinding wheel of each sampling inspection time step; linearly fitting the abrasion loss of the grinding wheel of each sampling inspection time step and the time value corresponding to each sampling inspection time step to obtain abrasion prediction information of the grinding wheel; generating the abrasion loss of the grinding wheel in the last time step according to the abrasion prediction information of the grinding wheel and the time value of the last time step;

The compensation parameter generation module is used for generating tracking errors according to the drill bit size parameters of the current time step and preset drill bit standard parameters; if the tracking error is greater than or equal to a preset proportional compensation threshold, fitting the tracking error and a preset PID proportional parameter to obtain a feed feedback compensation parameter; if the tracking error is smaller than the preset proportional compensation threshold, setting a preset compensation value as a feed feedback compensation parameter;

And the control processing module is used for controlling the processing grinding wheel to process the drill bit according to the feed feedback compensation parameter.

6. The apparatus of claim 5, wherein the drill bit dimension parameters include a diameter, a core thickness, and a helix angle of the drill bit.

7. The apparatus of claim 5, further comprising a grinding wheel wear prediction model generation module configured to: acquiring historical wear data of a processing grinding wheel in the processing process of the drill bit; and linearly fitting the abrasion loss in the historical abrasion data and the on-machine time of the processing grinding wheel to obtain a grinding wheel abrasion prediction model, wherein the grinding wheel abrasion prediction model is used for predicting the abrasion loss of the grinding wheel.

8. A computer device comprising a memory and a processor, the memory storing a computer program, characterized in that the processor implements the steps of the method of any of claims 1 to 4 when the computer program is executed.

9. A computer readable storage medium, on which a computer program is stored, characterized in that the computer program, when being executed by a processor, implements the steps of the method of any of claims 1 to 4.

10. A computer program product comprising a computer program, characterized in that the computer program, when executed by a processor, implements the steps of the method of any of claims 1 to 4.