CN113221327B - Deep blasting damage area shape prediction method based on ADABOOST integrated algorithm - Google Patents
Deep blasting damage area shape prediction method based on ADABOOST integrated algorithm Download PDFInfo
- Publication number
- CN113221327B CN113221327B CN202110399900.8A CN202110399900A CN113221327B CN 113221327 B CN113221327 B CN 113221327B CN 202110399900 A CN202110399900 A CN 202110399900A CN 113221327 B CN113221327 B CN 113221327B
- Authority
- CN
- China
- Prior art keywords
- data
- adaboost
- algorithm model
- method based
- prediction method
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2111/00—Details relating to CAD techniques
- G06F2111/10—Numerical modelling
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2119/00—Details relating to the type or aim of the analysis or the optimisation
- G06F2119/14—Force analysis or force optimisation, e.g. static or dynamic forces
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Abstract
The invention discloses a deep blasting damage area shape prediction method based on an ADABOOST integrated algorithm, which comprises the following steps: collecting laboratory simulation real scene record data for correlation analysis to find main influencing factors, and step two: cutting data, and step three: and (3) reprocessing the data, and step four: data segmentation, namely, step five: training data, step six: comparing the trained data with real data, and step seven: and (5) evaluating the result. The invention belongs to the technical field of engineering blasting of metal mining, provides a deep blasting damage area shape prediction method based on an ADABOOST integrated algorithm, effectively solves the problems that a large amount of development cost is required for performing blasting damage area shape prediction in the past, a large amount of funds are required for purchasing corresponding services, and the cost performance is low, reflects the practical reference value of the machine learning method applied to the engineering blasting field, has theoretical significance in the prediction result, and is a prediction method for reducing the development cost.
Description
Technical Field
The invention belongs to the technical field of engineering blasting in metal mining, and particularly relates to a deep blasting damage area shape prediction method based on an ADABOOST integrated algorithm.
Background
The energy is an important factor for human survival for a long time, because the demand of society for energy is expanded, and the resources of the earth shallow part are in increasingly rare stages, the exploitation work of some ore bodies gradually transits to the earth deep part, the exploitation work of mines at home and abroad sequentially enters into the deep resource exploitation state, the research of the blasting of the ore bodies at home and abroad is mostly in the analysis stage by using simulation software in the past, so that the numerical simulation can calculate the speed, the strain, the stress, the energy field and the like in the rock mass around the blasthole, the damage and the flowing state of the rock can be quantitatively described, and then the damage range can be predicted, and because the prior numerical analysis software or some computer programs need a large amount of development cost and a large amount of funds are needed to purchase corresponding services, the cost performance is lower.
Disclosure of Invention
Aiming at the situation, in order to overcome the defects of the prior art, the invention aims to provide a deep blasting damage area shape prediction method based on an ADABOOST integrated algorithm, which effectively solves the problems that a large amount of development cost is required for predicting the blasting damage area shape and a large amount of funds are required for purchasing corresponding services, and the cost performance is lower, and is a prediction method for reducing the development cost.
The technical scheme adopted by the invention is as follows: a deep blasting damage area shape prediction method based on an ADABOOST integrated algorithm comprises the following steps:
step one: collecting laboratory simulation real scene record data to obtain original data, performing correlation analysis on the original data, and finding out main influencing factors influencing the shape change of the blasting damage area, wherein the main influencing factors are main factors;
step two: splitting the original data to find data with comparative feasibility and obtain split data;
step three: carrying out missing value processing, abnormal value detection and normalization processing on the segmentation data to obtain reprocessed data;
step four: dividing the reprocessed data to obtain a training data set and a test data set;
step five: training an AdaBoost integrated algorithm model and a Logistic algorithm model by using a training data set to obtain a trained AdaBoost integrated algorithm model and a trained Logistic algorithm model;
step six: predicting the shape of an engineering blasting damage area by using a trained AdaBoost algorithm model and a trained Logistic algorithm model, and comparing the shape with real data in a test data set;
step seven: and comparing the trained AdaBoost algorithm model with the trained Logistic algorithm model according to the prediction success rate obtained by predicting the test data set.
Further, a deep blasting damage area shape prediction method based on an ADABOOST integrated algorithm comprises the following specific steps:
step 1: the data used by the invention is data acquired by simulating real blasting by college students in mining universities of certain schools, and the data lumped together contains 87 data and 12 characteristics including test piece type, stress intensity, stress and pressure of a load 1, stress and pressure of a load 2, medicine height, hole depth and resistance line;
step 2: the most critical influence of stress intensity and load on the result of the model in the data characteristics is obtained through data analysis.
Further, a deep blasting damage area shape prediction method based on an ADABOOST integrated algorithm is provided, and the second step specifically comprises:
step 1: performing segmentation operation on the original data to obtain segmented data;
step 2: the cut data is analyzed to find data that can be compared with each other.
Further, a deep blasting damage area shape prediction method based on an ADABOOST integrated algorithm comprises the following steps:
step 1: filling partial missing values in the original data by using an interpolation average method to obtain the supplemented data;
step 2: detecting abnormal values of the data after the supplement, checking whether the abnormal values exist, and obtaining corrected data;
step 3: the correction data is normalized, and the calculation formula is Xi = (Xi-xmin)/(xmax-xmin)
Where Xi represents normalized data; xi represents an initial value, xmax represents a maximum value in the data, xmin represents a minimum value in the data.
Further, a deep blasting damage area shape prediction method based on an ADABOOST integrated algorithm comprises the following steps:
step 1: the dataset was then set to 8:2, and taking the first eighty percent of the segmented data as a training data set and the last twenty percent as a test data set.
Further, a deep blasting damage area shape prediction method based on an ADABOOST integrated algorithm comprises the following steps:
step 1: because the AdaBoost integration algorithm has good applicability and good effect on small sample data, a training data set is put into an AdaBoost integration algorithm model, and training times are set to be 5000;
step 2: the training data set is put into a Logistic algorithm model, and training times are set to be 5000.
Further, a deep blasting damage area shape prediction method based on an ADABOOST integrated algorithm is provided, wherein the sixth step specifically comprises:
step 1: introducing the test data set into a trained AdaBoost integrated algorithm model, and judging the reliability of the model according to the drawn ROC curve;
step 2: and introducing the test data set into a trained Logistic algorithm model, comparing a predicted result with a target on the test data set, and evaluating the prediction effect of the model.
Further, a deep blasting damage area shape prediction method based on an ADABOOST integrated algorithm comprises the following steps:
step 1: comparing the prediction data of the AdaBoost integrated algorithm model and the Logistic algorithm model with the test data to obtain a prediction success rate;
step 2: the prediction success rates of the AdaBoost integrated algorithm model and the Logistic algorithm model are respectively marked as Y1 and Y2, wherein Y1=0.83 and Y2=0.78, and the prediction effect of the AdaBoost integrated algorithm model is better.
After the technical scheme is adopted, the invention has the following beneficial effects: the method for machine learning is applied to the field of engineering blasting, has practical reference value, has theoretical significance on a predicted result, has good adaptability to the AdaBoost integrated algorithm model, simultaneously has good adaptability to the problems of small sample, high latitude, difficult linear mapping and the like, has low development cost, and can be widely applied.
Drawings
Fig. 1 is a step diagram of a deep blasting damaged area shape prediction method based on an ADABOOST integration algorithm.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely, and it is apparent that the described embodiments are only some embodiments of the present invention, but not all embodiments; all other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
Embodiment 1. A deep blasting damage area shape prediction method based on an ADABOOST integrated algorithm comprises the following steps:
step one: collecting laboratory simulation real scene record data to obtain original data, performing correlation analysis on the original data, and finding out main influencing factors influencing the shape change of the blasting damage area, wherein the main influencing factors are main factors;
step two: splitting the original data to find data with comparative feasibility and obtain split data;
step three: carrying out missing value processing, abnormal value detection and normalization processing on the segmentation data to obtain reprocessed data;
step four: dividing the reprocessed data to obtain a training data set and a test data set;
step five: training an AdaBoost integrated algorithm model and a Logistic algorithm model by using a training data set to obtain a trained AdaBoost integrated algorithm model and a trained Logistic algorithm model;
step six: predicting the shape of an engineering blasting damage area by using a trained AdaBoost algorithm model and a trained Logistic algorithm model, and comparing the shape with real data in a test data set;
step seven: and comparing the trained AdaBoost algorithm model with the trained Logistic algorithm model according to the prediction success rate obtained by predicting the test data set.
The invention discloses a deep blasting damage area shape prediction method based on an ADABOOST integrated algorithm, which specifically comprises the following steps:
step 1: the data used by the invention is data acquired by simulating real blasting by college students in mining universities of certain schools, and the data lumped together contains 87 data and 12 characteristics including test piece type, stress intensity, stress and pressure of a load 1, stress and pressure of a load 2, medicine height, hole depth and resistance line;
step 2: the most critical influence of stress intensity and load on the result of the model in the data characteristics is obtained through data analysis.
The invention discloses a deep blasting damage area shape prediction method based on an ADABOOST integrated algorithm, which comprises the following steps:
step 1: performing segmentation operation on the original data to obtain segmented data;
step 2: the cut data is analyzed to find data that can be compared with each other.
The invention discloses a deep blasting damage area shape prediction method based on an ADABOOST integrated algorithm, which comprises the following steps:
step 1: filling partial missing values in the original data by using an interpolation average method to obtain the supplemented data;
step 2: detecting abnormal values of the data after the supplement, checking whether the abnormal values exist, and obtaining corrected data;
step 3: the correction data is normalized, and the calculation formula is Xi = (Xi-xmin)/(xmax-xmin)
Where Xi represents normalized data; xi represents an initial value, xmax represents a maximum value in the data, xmin represents a minimum value in the data.
The invention discloses a deep blasting damage area shape prediction method based on an ADABOOST integrated algorithm, which comprises the following steps:
step 1: the dataset was then set to 8:2, and taking the first eighty percent of the segmented data as a training data set and the last twenty percent as a test data set.
The invention discloses a deep blasting damage area shape prediction method based on an ADABOOST integrated algorithm, which comprises the following steps:
step 1: putting the training data set into an AdaBoost integrated algorithm model, and setting the training times to be 5000;
step 2: the training data set is put into a Logistic algorithm model, and training times are set to be 5000.
The invention discloses a deep blasting damage area shape prediction method based on an ADABOOST integrated algorithm, which comprises the following steps:
step 1: introducing the test data set into a trained AdaBoost integrated algorithm model, and judging the reliability of the model according to the drawn ROC curve;
step 2: and introducing the test data set into a trained Logistic algorithm model, comparing a predicted result with a target on the test data set, and evaluating the prediction effect of the model.
The invention discloses a deep blasting damage area shape prediction method based on an ADABOOST integrated algorithm, which specifically comprises the following steps:
step 1: comparing the prediction data of the AdaBoost integrated algorithm model and the Logistic algorithm model with the test data to obtain a prediction success rate;
step 2: the prediction success rates of the AdaBoost integrated algorithm model and the Logistic algorithm model are respectively marked as Y1 and Y2, wherein Y1=0.83 and Y2=0.78, and the prediction effect of the AdaBoost integrated algorithm model is better.
It is noted that relational terms such as first and second, and the like are used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Moreover, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus.
Although embodiments of the present invention have been shown and described, it will be understood by those skilled in the art that various changes, modifications, substitutions and alterations can be made therein without departing from the principles and spirit of the invention, the scope of which is defined in the appended claims and their equivalents.
The invention and its embodiments have been described above without limitation, and the actual construction is not limited thereto. In summary, if one of ordinary skill in the art is informed by this disclosure, a structural manner and an embodiment similar to the technical solution should not be creatively devised without departing from the gist of the present invention.
Claims (8)
1. A deep blasting damage area shape prediction method based on an ADABOOST integrated algorithm is characterized by comprising the following steps:
step one: collecting laboratory simulation real scene record data to obtain original data, performing correlation analysis on the original data, and finding out influence factors influencing the shape change of the blasting damaged area;
step two: splitting the original data to find data with comparative feasibility and obtain split data;
step three: carrying out missing value processing, abnormal value detection and normalization processing on the segmentation data to obtain reprocessed data;
step four: dividing the reprocessed data to obtain a training data set and a test data set;
step five: training an AdaBoost integrated algorithm model and a Logistic algorithm model by using a training data set to obtain a trained AdaBoost integrated algorithm model and a trained Logistic algorithm model;
step six: predicting the shape of an engineering blasting damage area by using a trained AdaBoost algorithm model and a trained Logistic algorithm model, and comparing the shape with real data in a test data set;
step seven: and comparing the trained AdaBoost algorithm model with the trained Logistic algorithm model according to the prediction success rate obtained by predicting the test data set.
2. The method for predicting the shape of a deep blasting failure zone based on an ADABOOST integration algorithm according to claim 1, wherein the step one specifically comprises:
step 1: the data used are data acquired by simulating real blasting by college students in mining industry of a certain school, wherein the data are lumped and contain 87 data and 12 characteristics, and the data comprise a test piece type, stress intensity, stress and pressure of a load 1, stress and pressure of a load 2, medicine height, hole depth and resistance line;
step 2: and (5) obtaining the key characteristics of the influence of the stress intensity and the load on the result of the model in the data characteristics through data analysis.
3. The method for predicting the shape of a deep blasting failure zone based on an ADABOOST integrated algorithm according to claim 1, wherein the step two is specifically:
step 1: performing segmentation operation on the original data to obtain segmented data;
step 2: the cut data is analyzed to find data that can be compared with each other.
4. The deep blasting failure zone shape prediction method based on the ADABOOST integrated algorithm according to claim 1, wherein the third step is specifically as follows:
step 1: filling partial missing values in the original data by using an interpolation average method to obtain the supplemented data;
step 2: detecting abnormal values of the data after the supplement, checking whether the abnormal values exist, and obtaining corrected data;
step 3: the correction data is normalized, and the calculation formula is Xi = (Xi-xmin)/(xmax-xmin)
Where Xi represents normalized data; xi represents an initial value, xmax represents a maximum value in the data, xmin represents a minimum value in the data.
5. The deep blasting damage area shape prediction method based on the ADABOOST integrated algorithm according to claim 1, wherein the step four is specifically:
step 1: the dataset was then set to 8:2, and taking the first eighty percent of the segmented data as a training data set and the last twenty percent as a test data set.
6. The deep blasting failure zone shape prediction method based on the ADABOOST integrated algorithm according to claim 1, wherein the fifth step is specifically as follows:
step 1: because the AdaBoost integration algorithm has good applicability and good effect on small sample data, a training data set is put into an AdaBoost integration algorithm model, and training times are set to be 5000;
step 2: the training data set is put into a Logistic algorithm model, and training times are set to be 5000.
7. The deep blasting failure zone shape prediction method based on the ADABOOST integration algorithm according to claim 1, wherein the sixth step is specifically:
step 1: introducing the test data set into a trained AdaBoost integrated algorithm model, and judging the reliability of the model according to the drawn ROC curve;
step 2: and introducing the test data set into a trained Logistic algorithm model, comparing a predicted result with a target on the test data set, and evaluating the prediction effect of the model.
8. The deep blasting failure zone shape prediction method based on the ADABOOST integrated algorithm according to claim 1, wherein the step seven is specifically:
step 1: comparing the prediction data of the AdaBoost integrated algorithm model and the Logistic algorithm model with the test data to obtain a prediction success rate;
step 2: the prediction success rates of the AdaBoost integrated algorithm model and the Logistic algorithm model are respectively marked as Y1 and Y2, wherein Y1=0.83 and Y2=0.78, and the prediction effect of the AdaBoost integrated algorithm model is better.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110399900.8A CN113221327B (en) | 2021-04-14 | 2021-04-14 | Deep blasting damage area shape prediction method based on ADABOOST integrated algorithm |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110399900.8A CN113221327B (en) | 2021-04-14 | 2021-04-14 | Deep blasting damage area shape prediction method based on ADABOOST integrated algorithm |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113221327A CN113221327A (en) | 2021-08-06 |
| CN113221327B true CN113221327B (en) | 2023-09-01 |
Family
ID=77087279
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110399900.8A Active CN113221327B (en) | 2021-04-14 | 2021-04-14 | Deep blasting damage area shape prediction method based on ADABOOST integrated algorithm |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113221327B (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104183236A (en) * | 2014-09-04 | 2014-12-03 | 北京语言大学 | Method and system for measuring discrimination of perception parameters |
| CN105740840A (en) * | 2016-02-29 | 2016-07-06 | 中南大学 | Nonlinear identification method for rock fracture signal and blasting vibration signal |
| CN109308486A (en) * | 2018-08-03 | 2019-02-05 | 天津大学 | Multi-source image fusion and feature extraction algorithm based on deep learning |
| CN112085262A (en) * | 2020-08-24 | 2020-12-15 | 辽宁石油化工大学 | University student bedroom allocation method based on machine learning algorithm |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| DK2516680T3 (en) * | 2009-12-22 | 2016-05-02 | Sequenom Inc | Method and kits to identify aneuploidy |
-
2021
- 2021-04-14 CN CN202110399900.8A patent/CN113221327B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104183236A (en) * | 2014-09-04 | 2014-12-03 | 北京语言大学 | Method and system for measuring discrimination of perception parameters |
| CN105740840A (en) * | 2016-02-29 | 2016-07-06 | 中南大学 | Nonlinear identification method for rock fracture signal and blasting vibration signal |
| CN109308486A (en) * | 2018-08-03 | 2019-02-05 | 天津大学 | Multi-source image fusion and feature extraction algorithm based on deep learning |
| CN112085262A (en) * | 2020-08-24 | 2020-12-15 | 辽宁石油化工大学 | University student bedroom allocation method based on machine learning algorithm |
Non-Patent Citations (1)
| Title |
|---|
| 郭钦鹏等.运用GA- BP神经网络对爆破振动速度预测.爆破.2020,第37卷(第3期),第148-152页. * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113221327A (en) | 2021-08-06 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111222683B (en) | PCA-KNN-based comprehensive grading prediction method for TBM construction surrounding rock | |
| WO2020125682A1 (en) | Method and system for calculating rock strength using logging-while-drilling data | |
| CN104951842A (en) | Novel method for predicting oil field output | |
| CN110889440A (en) | Rockburst grade prediction method and system based on principal component analysis and BP neural network | |
| CN113792936A (en) | Intelligent lithology while drilling identification method, system, equipment and storage medium | |
| CN110705179A (en) | Water guide crack belt height accurate prediction method and system based on fusion neural network | |
| CN111563045B (en) | Adaboost model-based concurrent program data competition statement level detection method | |
| CN105989287A (en) | Method and system for judging homology of massive malicious samples | |
| CN105045715A (en) | Programming mode and mode matching based bug clustering method | |
| Ai et al. | Crack detection and evolution law for rock mass under SHPB impact tests | |
| CN113221327B (en) | Deep blasting damage area shape prediction method based on ADABOOST integrated algorithm | |
| CN110956543A (en) | Method for detecting abnormal transaction | |
| CN116662920B (en) | Abnormal data identification method, system, equipment and medium for drilling and blasting method construction equipment | |
| CN105300819A (en) | Method for detecting fatigue limit of alloy steel based on support vector machine algorithm and system thereof | |
| GB2605318A (en) | System and methods to perform a downhole inspection in real-time | |
| CN111160490A (en) | Deep learning dangerous rock deformation prediction method and device based on multiple time sequences | |
| CN115081485B (en) | AI-based magnetic flux leakage internal detection data automatic analysis method | |
| CN115481183A (en) | Real-time data processing method and system | |
| CN111739108B (en) | Rapid iron ore powder grade estimation method based on convolutional neural network | |
| CN114818493A (en) | Method for quantitatively evaluating integrity degree of tunnel rock mass | |
| CN114862612A (en) | Mine data preprocessing method based on Bagging improvement | |
| CN109855699B (en) | Mine residual water level contour line drawing method beneficial to unifying standard formats | |
| CN113946790A (en) | Method, system, equipment and terminal for predicting height of water flowing fractured zone | |
| Afraei et al. | Statistical analysis of rock-burst events in underground mines and excavations to present reasonable data-driven predictors | |
| CN112727433A (en) | Drilling parameter optimization method |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |