CN118114071B - Drill bit drilling state monitoring system for cutting underground anchor cable - Google Patents

Abstract

The invention relates to the technical field of data processing, in particular to a drill bit drilling state monitoring system for cutting off an underground anchor cable, which comprises the following components: the data acquisition module is used for acquiring vibration data; the data analysis module is used for obtaining the running state expression degree of each vibration data according to the difference between the vibration data, the difference between the data numbers in different data segments and the distribution of the tangential slopes of all data points on the vibration curve of the drill bit; the weight correction coefficient calculation module is used for obtaining a weight correction coefficient of each marking moment according to the difference between the running state expression degrees of different vibration data; and the monitoring module is used for obtaining a prediction result of the vibration data according to the weight correction coefficient of each marking moment and monitoring the drilling state of the drill bit according to the prediction result. The method improves the accuracy of the prediction result and the accuracy of monitoring the drilling state of the drill bit for cutting the underground anchor cable.

Description

A drilling status monitoring system for drilling bits for cutting underground anchor cables

Technical Field

The invention relates to the technical field of data processing, and in particular to a drilling status monitoring system for a drill bit for cutting off an underground anchor cable.

Background technique

Drill bits for cutting off underground anchor cables are usually used in underground engineering and construction projects. The role and significance of drill bits for cutting off underground anchor cables are to maintain, repair, dismantle and rebuild underground engineering structures to ensure engineering safety and environmental protection. By effectively removing damaged or failed underground anchor cables, the stability and sustainability of underground projects can be ensured. Therefore, it is of great significance to monitor the drilling status of drill bits for cutting off underground anchor cables.

The vibration data of the drill bit is predicted by the exponentially weighted moving average algorithm, and the drilling status of the drill bit is monitored based on the predicted data; however, the conventional exponentially weighted moving average algorithm predicts data by using the time interval between the current data and the historical data as the data weight. During the drilling process of the drill bit, the environmental hardness at different positions may change randomly, and the interference ability of the collected historical data on the prediction is different. At this time, if the weight is only given according to the time series distance, it will cause deviations in the final prediction results, reducing the accuracy of monitoring the drilling status of the drill bit for removing the underground anchor cable.

Summary of the invention

The invention provides a drilling status monitoring system for a drill bit for cutting off an underground anchor cable, so as to solve the existing problems.

The present invention discloses a drill bit drilling status monitoring system for removing underground anchor cables, which adopts the following technical solutions:

An embodiment of the present invention provides a drilling status monitoring system for a drill bit for cutting an underground anchor cable, the system comprising the following modules:

A data acquisition module is used to obtain vibration data of the drill bit at several consecutive moments;

A data analysis module is used to group the vibration data of the drill bit at a number of consecutive moments into a sequence in time order, recorded as the vibration data sequence of the drill bit, perform curve fitting on all the vibration data in the vibration data sequence to obtain the vibration curve of the drill bit, obtain all extreme value points in the vibration curve, the extreme value points include maximum value points and minimum value points, and group the vibration data corresponding to two adjacent extreme value points and the vibration data between the two extreme value points into a data segment to obtain a number of data segments;

According to the difference between the vibration data corresponding to adjacent extreme value points, the difference between the number of data in the left and right adjacent data segments of each data segment, and the distribution of the tangent slope of all vibration data in each data segment on the vibration curve of the drill bit, the performance degree of the operating state of each vibration data is obtained;

A weight correction coefficient calculation module is used to combine the vibration data at each moment and the vibration data at several moments before each moment into the time series vibration data at each moment, and obtain the weight correction coefficient at each marked moment according to the distribution of the tangent slopes of all vibration data in the time series vibration data at each moment corresponding to the vibration curve of the drill bit and the difference between the operating state performance levels of all vibration data in the time series vibration data at different moments;

The monitoring module is used to correct the weight of the vibration data at each marked moment according to the weight correction coefficient of each marked moment, obtain the corrected weight of the vibration data at each marked moment, obtain the predicted result of the vibration data according to the corrected weight of the vibration data at each moment, and monitor the drilling status of the drill bit for cutting the underground anchor cable according to the predicted result of the vibration data.

Further, the operating state performance degree of each vibration data is obtained according to the difference between the vibration data corresponding to adjacent extreme value points, the difference between the number of data in the left and right adjacent data segments of each data segment, and the distribution of the tangent slope of all vibration data in each data segment corresponding to the vibration curve of the drill bit, including:

According to the difference between the vibration data corresponding to adjacent extreme value points, the normality of the vibration data corresponding to each extreme value point is obtained;

The straight line connecting the two extreme points of each data segment is recorded as the reference straight line;

According to the normality of the vibration data corresponding to each extreme point, the difference between the number of data in the left and right adjacent data segments of each data segment, the difference between the tangent slope of each vibration data in each data segment on the vibration curve of the drill bit and the reference straight line slope of each data segment, and the distribution of the tangent slope of all vibration data in each data segment on the vibration curve of the drill bit, the operating status performance degree of each vibration data is obtained.

Furthermore, obtaining the normality of the vibration data corresponding to each extreme point according to the difference between the vibration data corresponding to adjacent extreme points includes:

Wherein, each extreme point, A extreme points adjacent to the left of each extreme point, and A extreme points adjacent to the right of each extreme point constitute a local extreme point of each extreme point, wherein A is a preset first parameter;

Mark the time data of all vibration data starting from the first vibration data in the vibration data sequence, starting from the positive integer 1, and add 1 to the time data corresponding to each vibration data to mark it as a positive integer;

The product result of the vibration data corresponding to any local extreme point of each extreme point and the time data corresponding to any local extreme point of each extreme point is recorded as the first eigenvalue of any local extreme point of each extreme point. The absolute value of the difference between the first eigenvalue of the local extreme point adjacent to the left of any local extreme point of each extreme point and the first eigenvalue of any local extreme point of each extreme point is recorded as the second eigenvalue of any local extreme point of each extreme point. The absolute value of the difference between the first eigenvalue of the local extreme point adjacent to the right of any local extreme point of each extreme point and the first eigenvalue of any local extreme point of each extreme point is recorded as the second eigenvalue of any local extreme point of each extreme point. the third eigenvalue of a local extreme point, add 0.1 to the third eigenvalue of any local extreme point of each extreme point as the fourth eigenvalue of any local extreme point of each extreme point, record the ratio between the second eigenvalue and the fourth eigenvalue of any local extreme point of each extreme point as the first ratio of any local extreme point of each extreme point, record the mean of the first ratios of all local extreme points of each extreme point as the first mean of each extreme point, record the absolute value of the difference between 1 and the first mean of each extreme point as the first absolute value of each extreme point, perform negative correlation mapping on the first absolute value of each extreme point, and obtain the normality of the vibration data corresponding to each extreme point.

Furthermore, the normality of the vibration data corresponding to each extreme point, the difference between the number of data in the left and right adjacent data segments of each data segment, the difference between the tangent slope of each vibration data in each data segment on the vibration curve of the drill bit and the reference straight line slope of each data segment, and the distribution of the tangent slope of all vibration data in each data segment on the vibration curve of the drill bit, the specific calculation method is as follows:

In the formula, Indicates The normality of the vibration data corresponding to the first extreme point in a data segment, Indicates The normality of the vibration data corresponding to the second extreme point in the data segment, Indicates The number of data in a data segment, Indicates The number of data in a data segment, Indicates In the data segment The vibration data corresponds to the tangent slope on the vibration curve of the drill bit. Indicates The slope of the reference line for each data segment, Indicates The mean square error of the tangent slope of all vibration data in a data segment corresponding to the vibration curve of the drill bit, is the absolute value symbol, Indicates The first The degree to which the operating status of each vibration data is represented.

Furthermore, the vibration data at each moment and the vibration data at several moments before each moment are combined into the time series vibration data at each moment, and the weight correction coefficient at each marked moment is obtained according to the distribution of the tangent slopes of all vibration data in the time series vibration data at each moment corresponding to the vibration curve of the drill bit and the difference between the operating state performance levels of all vibration data in the time series vibration data at different moments, including:

The vibration data of each moment and the vibration data of B moments before each moment form the time series vibration data of each moment; the moment closest to the moment is recorded as the current moment, and all moments except the current moment are recorded as marked moments; wherein B is the preset second parameter;

According to the performance degree of the running state of all vibration data in the time series vibration data at each moment and the tangent slope of all vibration data in the time series vibration data at each moment corresponding to the vibration curve of the drill bit, the normal coefficient of the vibration data at each moment is obtained;

According to the difference between the performance degree of the running state of all vibration data in the time series vibration data at the target moment and the performance degree of the running state of all vibration data in the time series vibration data at each marked moment, the similarity feature of each marked moment is obtained;

According to the normal coefficient of the vibration data at the target moment, the normal coefficient of the vibration data at each marked moment and the similar characteristics of each marked moment, a weight correction coefficient of each marked moment is obtained.

Further, the normal coefficient of the vibration data at each moment is obtained according to the performance degree of the running state of all vibration data in the time series vibration data at each moment and the tangent slope of all vibration data in the time series vibration data at each moment corresponding to the vibration curve of the drill bit, including:

The product of the mean of the tangent slopes of all vibration data in the time-series vibration data at each moment corresponding to the vibration curve of the drill bit and the mean of the operating status performance levels of all vibration data in the time-series vibration data at each moment is recorded as the first product value at each moment. The first product values at all moments are linearly normalized, and the normalized first product value at each moment is used as the normal coefficient of the vibration data at each moment.

Further, the similarity feature of each marked moment is obtained according to the difference between the performance degree of the running state of all vibration data in the time series vibration data at the target moment and the performance degree of the running state of all vibration data in the time series vibration data at each marked moment, including:

The absolute value of the difference between the degree of performance of the operating status of any vibration data in the time-series vibration data of each marking moment and the degree of performance of the operating status of any vibration data in the time-series vibration data of the target moment is recorded as the first value of any vibration data in the time-series vibration data of each marking moment, and the cumulative sum of the reciprocals of the first values of all vibration data in the time-series vibration data of each marking moment is recorded as the second value of each marking moment. The second values of all the marking moments are linearly normalized, and the normalized second value of each marking moment is used as the similarity feature of each marking moment.

Furthermore, the weight correction coefficient of each marked moment is obtained according to the normal coefficient of the vibration data at the target moment, the normal coefficient of the vibration data at each marked moment and the similarity feature of each marked moment, and the specific calculation method included is as follows:

In the formula, Indicates similar features of the marked moments, Indicates The normal coefficient of the vibration data at the marked time, Indicates the target time Normal coefficient of vibration data, Indicates the preset first threshold, Indicates the preset second threshold value, Indicates The weight correction factor for each marking moment.

Furthermore, the weight of the vibration data at each marking moment is corrected according to the weight correction coefficient at each marking moment to obtain the corrected weight of the vibration data at each marking moment, including the following specific steps:

The product of the weight correction coefficient of each marking moment and the inverse of the time interval between each marking moment and the target moment is recorded as the third value of each marking moment. The third values of all marking moments are linearly normalized, and the normalized third value of each marking moment is used as the weight of the vibration data after correction at each marking moment.

Furthermore, the prediction result of the vibration data is obtained according to the weight corrected by the vibration data at each moment, and the specific steps include the following:

According to the weights corrected by the vibration data at each marked moment, the vibration data at future moments are predicted by an exponentially weighted moving average algorithm to obtain the prediction results of the vibration data.

The beneficial effects of the technical solution of the present invention are as follows: the present invention obtains the degree of performance of the operating state of each vibration data according to the difference between the vibration data corresponding to adjacent extreme points, the difference between the number of data in the left and right adjacent data segments of each data segment, and the distribution of the tangent slope of all vibration data in each data segment on the vibration curve of the drill bit, thereby reducing the degree of environmental hardness interference at different positions; obtains the weight correction coefficient of each marked moment according to the distribution of the tangent slope of all vibration data in the time-series vibration data at each moment on the vibration curve of the drill bit, and the difference between the degree of performance of the operating state of all vibration data in the time-series vibration data at different moments, thereby improving the accuracy of the weight analysis of each vibration data; according to the weight correction coefficient of each marked moment, the weight of the vibration data at each marked moment is corrected to obtain the corrected weight of the vibration data at each marked moment, and according to the corrected weight of the vibration data at each moment, the prediction result of the vibration data is obtained, and the drilling state of the drill bit for cutting off the underground anchor cable is monitored according to the prediction result of the vibration data, thereby improving the accuracy of the prediction result and also improving the accuracy of the monitoring of the drilling state of the drill bit for cutting off the underground anchor cable.

BRIEF DESCRIPTION OF THE DRAWINGS

In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

FIG1 is a module flow chart of a drill bit drilling status monitoring system for removing underground anchor cables according to the present invention;

FIG. 2 is a flow chart of monitoring the drilling status of a drill bit for cutting an underground anchor cable.

Detailed ways

In order to further explain the technical means and effects adopted by the present invention to achieve the predetermined invention purpose, the following is a detailed description of the specific implementation method, structure, features and effects of a drill bit drilling status monitoring system for cutting underground anchor cables proposed by the present invention in combination with the accompanying drawings and preferred embodiments. In the following description, different "one embodiment" or "another embodiment" does not necessarily refer to the same embodiment. In addition, specific features, structures or characteristics in one or more embodiments may be combined in any suitable form.

Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.

The specific scheme of the drill bit drilling status monitoring system for removing underground anchor cables provided by the present invention is described in detail below with reference to the accompanying drawings.

Please refer to FIG. 1 , which shows a module flow chart of a drill bit drilling status monitoring system for removing underground anchor cables provided by an embodiment of the present invention. The system includes the following modules:

Module 101: Data acquisition module.

It should be noted that in order to analyze whether the working state of the drill bit for cutting the underground anchor cable is normal, the drilling state of the drill bit for cutting the underground anchor cable is monitored. Therefore, it is necessary to collect the vibration data of the drill bit and monitor the drilling state of the drill bit through the drill bit vibration data.

Specifically, a vibration sensor is installed on the drill bit to collect vibration data within 10 hours with a sampling interval of 0.1 seconds.

At this point, the vibration data of the drill bit at several consecutive moments are obtained.

Module 102: Data analysis module.

It should be noted that the normality of the drilling state of the drill bit is usually judged based on its vibration performance. For a drill bit in normal operation, since it rotates at high speed during the drilling process, the vibration data of the drill bit is relatively regular and periodic. When the drill bit fails, that is, the drill bit is worn due to long-term operation, the amplitude and periodicity of the monitored vibration data will change. In order to avoid safety hazards, the data collected by the drill bit is usually predicted to prevent safety problems caused by failures.

It should be further explained that, since the drill bit may come into contact with many harder objects during the drilling process, the harder the object the drill bit comes into contact with, the larger and more chaotic the amplitude of the drill bit vibration will be, which will interfere with the fault identification. Under normal circumstances, the amplitude of the drill bit vibration is smaller and more regular. Therefore, it is analyzed through the change in the amplitude of the drill bit vibration.

Specifically, the vibration data of the drill bit at several consecutive moments are organized into a sequence in chronological order, which is recorded as the vibration data sequence of the drill bit; a reference coordinate system is constructed with the time sequence as the horizontal axis and the vibration data as the vertical axis; curve fitting is performed according to the coordinates of the vibration data in the reference coordinate system; curve fitting is performed on all vibration data in the vibration data sequence using a quintic polynomial through the least squares method, and the fitted curve is recorded as the vibration curve of the drill bit, and all extreme points in the vibration curve are obtained, including maximum points and minimum points.

A first parameter A is preset, wherein this embodiment is described by taking A=5 as an example, and this embodiment is not specifically limited, wherein A can be determined according to the specific implementation situation. Each extreme point, the A extreme points adjacent to the left of each extreme point, and the A extreme points adjacent to the right of each extreme point constitute the local extreme point of each extreme point. Starting from the first vibration data in the vibration data sequence, all vibration data are marked with time data, starting from the positive integer 1, and the time data corresponding to each vibration data is marked as a positive integer by adding 1 in sequence.

According to the difference between the vibration data corresponding to the adjacent local extreme value points of each extreme value point, the normality of the vibration data corresponding to each extreme value point is obtained. As an embodiment, the specific calculation method is as follows:

In the formula, Indicates The extreme point The vibration data corresponding to the local extreme points, Indicates The extreme point The vibration data corresponding to the local extreme points, Indicates The extreme point The vibration data corresponding to the local extreme points, Indicates The extreme point The time data corresponding to the local extreme points, Indicates The extreme point The time data corresponding to the local extreme points, Indicates The extreme point The time data corresponding to the local extreme points, Indicates The number of local extreme points of extreme points, Indicates The normality of the vibration data corresponding to the extreme point, represents an exponential function with a natural constant as base, is the absolute value symbol. The denominator is added with 0.1 to prevent the denominator from being 0.

in, It represents the ratio of the difference between the vibration data corresponding to the adjacent local extreme points of each extreme point. When the ratio is smaller, it means that the change of the vibration data is more regular and the degree of interference is smaller, that is, it is more normal; when the ratio is larger, it means that the change of the vibration data is more chaotic and the degree of interference is greater, that is, it is more abnormal.

At this point, the normality of the vibration data corresponding to each extreme point is obtained.

It should be noted that the normality of the vibration data corresponding to each extreme point can reflect the normality of the local vibration data of each extreme point. Whether the performance of each specific vibration data is normal needs to be analyzed based on the data in the local range of each vibration data.

Specifically, the vibration data corresponding to two adjacent extreme points and the vibration data between the two extreme points are combined into a data segment, and then several data segments are obtained; among which, the first data segment is composed of the vibration data of the drill bit at the first moment and the first extreme point, and the last data segment is composed of the vibration data of the drill bit at the last moment and the last extreme point.

Obtain the tangent slope of each vibration data in each data segment corresponding to the vibration curve of the drill bit; and record the straight line connecting the two extreme value points of each data segment as the reference straight line.

It should be further explained that when the drill bit is drilling normally and an abnormal situation occurs, the fluctuation range of the vibration data in each data segment is larger and more discrete. Therefore, the tangent slope of each vibration data in each data segment corresponding to the vibration curve of the drill bit is very different from the slope of the straight line between the two endpoints of each data segment, and the difference between the number of data in the left and right adjacent data segments of each data point is larger.

Specifically, according to the normality of the vibration data corresponding to each extreme point, the difference between the number of data in the left and right adjacent data segments of each data segment, and the difference between the tangent slope of each vibration data in each data segment on the vibration curve of the drill bit and the reference straight line slope of each data segment, the performance degree of the operating state of each vibration data is obtained. As an embodiment, the specific calculation method is:

In the formula, Indicates The normality of the vibration data corresponding to the first extreme point in a data segment, Indicates The normality of the vibration data corresponding to the second extreme point in the data segment, Indicates The number of data in a data segment, Indicates The number of data in a data segment, Indicates In the data segment The vibration data corresponds to the tangent slope on the vibration curve of the drill bit. Indicates The slope of the reference line for each data segment, Indicates The mean square error of the tangent slope of all vibration data in a data segment corresponding to the vibration curve of the drill bit, is the absolute value symbol, Indicates The first The degree to which the operating status of each vibration data is represented.

in, It indicates the difference between the number of data in the left and right adjacent data segments of each data segment. When the difference is larger, it means that the running status performance is worse, and the running status performance degree is smaller; when the difference is smaller, it means that the running status performance is better, and the running status performance degree is greater. It indicates the distribution difference of the tangent slope of each vibration data in each data segment corresponding to the vibration curve of the drill bit. When the difference is larger, it means that the operating status performance is worse, and the operating status performance degree is smaller; when the difference is smaller, it means that the operating status performance is better, and the operating status performance degree is greater. It is the mean of the normality of the vibration data corresponding to the two extreme points in each data segment. When the mean is smaller, it means that the operating status is worse, and the operating status performance is smaller; when the mean is larger, it means that the operating status is better, and the operating status performance is larger.

At this point, the degree of performance of the operating status of each vibration data is obtained.

Module 103: Weight correction coefficient calculation module.

It should be noted that, since the corresponding hardness is different at different positions, the vibration data of the drill bit in different time periods are different. Therefore, the normal coefficient of each vibration data is analyzed based on the partial data before each vibration data.

Specifically, a second parameter B is preset, wherein this embodiment is described by taking B=10 as an example, and this embodiment is not specifically limited, wherein B may be determined according to the specific implementation situation. The vibration data at each moment and the vibration data at B moments before each moment constitute the time series vibration data at each moment. The moment closest to this moment is recorded as the current moment, and the time series vibration data of the current moment is obtained. All moments except the current moment are recorded as marked moments.

It should be further explained that, when the difference between the operating status performance levels of all vibration data in different time periods is smaller, it means that the two time periods are more similar; when the difference between the operating status performance levels of all vibration data in different time periods is larger, it means that the two time periods are more dissimilar; therefore, the weight of each data in the exponentially weighted moving average algorithm is corrected by analyzing the difference between the time series vibration data at different times.

Specifically, according to the performance degree of the running state of all vibration data in the time series vibration data at each moment and the tangent slope of all vibration data in the time series vibration data at each moment corresponding to the vibration curve of the drill bit, the normal coefficient of the vibration data at each moment is obtained. As an embodiment, the specific calculation method is:

In the formula, Indicates The mean value of the tangent slope of all vibration data in the time series vibration data at each moment on the vibration curve of the drill bit, Indicates The average value of the operating status performance of all vibration data in the time series vibration data at a moment, Indicates The normal coefficient of the vibration data at the moment, represents the linear normalization function.

Among them, the greater the mean value of the operating status performance degree of all vibration data in the time-series vibration data at each moment, and the greater the mean value of the tangent slope of all vibration data in the time-series vibration data at each moment corresponding to the vibration curve of the drill bit, the greater the normal coefficient of the vibration data at each moment.

At this point, the normal coefficient of the vibration data at each moment can be obtained.

According to the difference between the performance degree of the running state of all vibration data in the time series vibration data at the target moment and the performance degree of the running state of all vibration data in the time series vibration data at each marked moment, the similarity feature of each marked moment is obtained. As an embodiment, the specific calculation method is:

In the formula, Indicates The time series vibration data of the marked moment The degree of performance of the operating status of each vibration data, Indicates the time series vibration data at the target time. The degree of performance of the operating status of each vibration data, Indicates similar features of the marked moments, represents the linear normalization function, Indicates the number of data in the time series vibration data at each moment, is the absolute value symbol.

Among them, the greater the difference between the operating status performance levels of all vibration data in the time-series vibration data at the target moment and the operating status performance levels of all vibration data in the time-series vibration data at each marked moment, the greater the similarity characteristics of each marked moment, that is, the greater the possibility of being normal; conversely, the smaller the similarity characteristics of each marked moment, the smaller the possibility of being normal.

Preset first threshold and the second threshold , wherein this embodiment is based on and This is described by taking t as an example, and this embodiment is not specifically limited, wherein T can be determined according to specific implementation conditions.

According to the normal coefficient of the vibration data at the target moment, the normal coefficient of the vibration data at each marked moment and the similarity characteristics of each marked moment, the weight correction coefficient of each marked moment is obtained. As an embodiment, the specific calculation method is as follows:

In the formula, Indicates similar features of the marked moments, Indicates The normal coefficient of the vibration data at the marked time, Indicates the target time Normal coefficient of vibration data, Indicates the preset first threshold, Indicates the preset second threshold value, Indicates The weight correction factor for each marking moment.

Among them, when the similar features of each marking moment and the normal coefficient of the vibration data of each marking moment are larger, the weight of each marking moment should be larger, and the corresponding correction coefficient is also larger; when the similar features of each marking moment are smaller, the weight of each marking moment should be smaller, and the corresponding correction coefficient is also smaller.

At this point, the weight correction coefficient for each marking moment is obtained.

Module 104: Monitoring module.

According to the weight correction coefficient of each marking moment, the weight of the vibration data at each marking moment is corrected to obtain the corrected weight of the vibration data at each marking moment. As an embodiment, the specific calculation method is:

In the formula, Indicates The weight correction coefficient of the marking moment, Indicates The time interval between the marked moment and the target moment, Indicates The corrected weight of the vibration data at the marked moment, represents the linear normalization function.

Among them, when the weight correction coefficient of each marking moment is larger, the weight of the vibration data after correction of each marking moment is larger.

However, the weight of the vibration data at the target time is not corrected.

According to the weights corrected by the vibration data at each marked moment, the vibration data at future moments are predicted by the exponentially weighted moving average algorithm to obtain the prediction results of the vibration data. The drilling status of the drill bit for cutting the underground anchor cable is monitored according to the prediction results of the vibration data.

It should be noted that the The model is only used to represent negative correlation and constrain the output of the model to be in In the specific implementation, it can be replaced by other models with the same purpose. This embodiment is only based on The model is described as an example without any specific limitation. Refers to the input of the model. Among them, the drilling status monitoring flow chart of the drill bit for cutting the underground anchor cable is shown in Figure 2.

At this point, this embodiment is completed.

The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the principles of the present invention should be included in the protection scope of the present invention.

Claims (3)

1. A drilling status monitoring system for cutting underground anchor cables, characterized in that the system comprises the following modules: A data acquisition module is used to obtain vibration data of the drill bit at several consecutive moments; A data analysis module is used to group the vibration data of the drill bit at a number of consecutive moments into a sequence in time order, recorded as the vibration data sequence of the drill bit, perform curve fitting on all the vibration data in the vibration data sequence to obtain the vibration curve of the drill bit, obtain all extreme value points in the vibration curve, the extreme value points include maximum value points and minimum value points, and group the vibration data corresponding to two adjacent extreme value points and the vibration data between the two extreme value points into a data segment to obtain a number of data segments; According to the difference between the vibration data corresponding to adjacent extreme value points, the difference between the number of data in the left and right adjacent data segments of each data segment, and the distribution of the tangent slope of all vibration data in each data segment on the vibration curve of the drill bit, the performance degree of the operating state of each vibration data is obtained; A weight correction coefficient calculation module is used to combine the vibration data at each moment and the vibration data at several moments before each moment into the time series vibration data at each moment, and obtain the weight correction coefficient at each marked moment according to the distribution of the tangent slopes of all vibration data in the time series vibration data at each moment corresponding to the vibration curve of the drill bit and the difference between the operating state performance levels of all vibration data in the time series vibration data at different moments; A monitoring module, for correcting the weight of the vibration data at each marked moment according to the weight correction coefficient at each marked moment, obtaining the corrected weight of the vibration data at each marked moment, obtaining the prediction result of the vibration data according to the corrected weight of the vibration data at each moment, and monitoring the drilling state of the drill bit for cutting the underground anchor cable according to the prediction result of the vibration data; The operating state performance degree of each vibration data is obtained according to the difference between the vibration data corresponding to adjacent extreme value points, the difference between the number of data in the left and right adjacent data segments of each data segment, and the distribution of the tangent slope of all vibration data in each data segment on the vibration curve of the drill bit, including: According to the difference between the vibration data corresponding to adjacent extreme value points, the normality of the vibration data corresponding to each extreme value point is obtained; The straight line connecting the two extreme points of each data segment is recorded as the reference straight line; According to the normality of the vibration data corresponding to each extreme point, the difference between the number of data in the left and right adjacent data segments of each data segment, the difference between the tangent slope of each vibration data in each data segment on the vibration curve of the drill bit and the reference straight line slope of each data segment, and the distribution of the tangent slope of all vibration data in each data segment on the vibration curve of the drill bit, the operating state performance degree of each vibration data is obtained; The method of obtaining the normality of the vibration data corresponding to each extreme point according to the difference between the vibration data corresponding to adjacent extreme points includes: Wherein, each extreme point, A extreme points adjacent to the left of each extreme point, and A extreme points adjacent to the right of each extreme point constitute a local extreme point of each extreme point, wherein A is a preset first parameter; Mark the time data of all vibration data starting from the first vibration data in the vibration data sequence, starting from the positive integer 1, and add 1 to the time data corresponding to each vibration data to mark it as a positive integer; The product result of the vibration data corresponding to any local extreme point of each extreme point and the time data corresponding to any local extreme point of each extreme point is recorded as the first eigenvalue of any local extreme point of each extreme point. The absolute value of the difference between the first eigenvalue of the local extreme point adjacent to the left of any local extreme point of each extreme point and the first eigenvalue of any local extreme point of each extreme point is recorded as the second eigenvalue of any local extreme point of each extreme point. The absolute value of the difference between the first eigenvalue of the local extreme point adjacent to the right of any local extreme point of each extreme point and the first eigenvalue of any local extreme point of each extreme point is recorded as the second eigenvalue of any local extreme point of each extreme point. the third eigenvalue of a local extreme point, adding 0.1 to the third eigenvalue of any local extreme point of each extreme point is recorded as the fourth eigenvalue of any local extreme point of each extreme point, the ratio between the second eigenvalue and the fourth eigenvalue of any local extreme point of each extreme point is recorded as the first ratio of any local extreme point of each extreme point, the mean of the first ratios of all local extreme points of each extreme point is recorded as the first mean of each extreme point, the absolute value of the difference between 1 and the first mean of each extreme point is recorded as the first absolute value of each extreme point, and negative correlation mapping is performed on the first absolute value of each extreme point to obtain the normality of the vibration data corresponding to each extreme point; The specific calculation method for obtaining the degree of performance of the operating state of each vibration data is as follows: In the formula, Indicates The normality of the vibration data corresponding to the first extreme point in a data segment, Indicates The normality of the vibration data corresponding to the second extreme point in the data segment, Indicates The number of data in a data segment, Indicates The number of data in a data segment, Indicates In the data segment The vibration data corresponds to the tangent slope on the vibration curve of the drill bit. Indicates The slope of the reference line for each data segment, Indicates The mean square error of the tangent slope of all vibration data in a data segment corresponding to the vibration curve of the drill bit, is the absolute value symbol, Indicates The first The degree of performance of the operating status of each vibration data; The vibration data at each moment and the vibration data at several moments before each moment are combined into the time series vibration data at each moment, and the weight correction coefficient at each marked moment is obtained according to the distribution of the tangent slopes of all vibration data in the time series vibration data at each moment corresponding to the vibration curve of the drill bit and the difference between the operating state performance levels of all vibration data in the time series vibration data at different moments, including: The vibration data of each moment and the vibration data of B moments before each moment form the time series vibration data of each moment; the moment closest to the moment is recorded as the current moment, and all moments except the current moment are recorded as marked moments; wherein B is the preset second parameter; According to the performance degree of the running state of all vibration data in the time series vibration data at each moment and the tangent slope of all vibration data in the time series vibration data at each moment corresponding to the vibration curve of the drill bit, the normal coefficient of the vibration data at each moment is obtained; According to the difference between the performance degree of the running state of all vibration data in the time series vibration data at the target moment and the performance degree of the running state of all vibration data in the time series vibration data at each marked moment, the similarity feature of each marked moment is obtained; According to the normal coefficient of the vibration data at the target moment, the normal coefficient of the vibration data at each marked moment and the similarity characteristics of each marked moment, a weight correction coefficient of each marked moment is obtained; The normal coefficient of the vibration data at each moment is obtained according to the performance degree of the running state of all the vibration data in the time series vibration data at each moment and the tangent slope of all the vibration data in the time series vibration data at each moment corresponding to the vibration curve of the drill bit, including: The product of the mean value of the tangent slope of all vibration data in the time series vibration data at each moment corresponding to the vibration curve of the drill bit and the mean value of the running state performance degree of all vibration data in the time series vibration data at each moment is recorded as the first product value at each moment, the first product values at all moments are linearly normalized, and the normalized first product value at each moment is used as the normal coefficient of the vibration data at each moment; The similarity feature of each marked moment is obtained based on the difference between the performance degree of the running state of all vibration data in the time series vibration data at the target moment and the performance degree of the running state of all vibration data in the time series vibration data at each marked moment, including: The absolute value of the difference between the degree of performance of the running state of any vibration data in the time-series vibration data at each marked moment and the degree of performance of the running state of any vibration data in the time-series vibration data at the target moment is recorded as the first value of any vibration data in the time-series vibration data at each marked moment, the cumulative sum of the reciprocals of the first values of all vibration data in the time-series vibration data at each marked moment is recorded as the second value of each marked moment, the second values of all marked moments are linearly normalized, and the normalized second value of each marked moment is used as the similarity feature of each marked moment; The weight correction coefficient of each marked moment is obtained according to the normal coefficient of the vibration data at the target moment, the normal coefficient of the vibration data at each marked moment and the similarity characteristics of each marked moment, and the specific calculation method included is as follows: In the formula, Indicates similar features of the marked moments, Indicates The normal coefficient of the vibration data at the marked time, Indicates the target time Normal coefficient of vibration data, Indicates the preset first threshold, Indicates the preset second threshold value, Indicates The weight correction factor for each marking moment. 2. According to claim 1, a drill bit drilling status monitoring system for removing underground anchor cables is characterized in that the weight of the vibration data at each marking moment is corrected according to the weight correction coefficient at each marking moment to obtain the corrected weight of the vibration data at each marking moment, and the specific steps included are as follows: The product of the weight correction coefficient of each marking moment and the inverse of the time interval between each marking moment and the target moment is recorded as the third value of each marking moment. The third values of all marking moments are linearly normalized, and the normalized third value of each marking moment is used as the weight of the vibration data after correction at each marking moment. 3. According to the drilling status monitoring system for cutting underground anchor cables of claim 1, it is characterized in that the prediction result of the vibration data is obtained according to the weight corrected by the vibration data at each moment, and the specific steps include the following: According to the weights corrected by the vibration data at each marked moment, the vibration data at future moments are predicted by an exponentially weighted moving average algorithm to obtain the prediction results of the vibration data.