CN111275252A - Blasting peak value speed prediction method, device and medium based on RGA-BPNNG - Google Patents

Blasting peak value speed prediction method, device and medium based on RGA-BPNNG Download PDF

Info

Publication number
CN111275252A
CN111275252A CN202010045751.0A CN202010045751A CN111275252A CN 111275252 A CN111275252 A CN 111275252A CN 202010045751 A CN202010045751 A CN 202010045751A CN 111275252 A CN111275252 A CN 111275252A
Authority
CN
China
Prior art keywords
blasting
neural network
speed prediction
peak
prediction model
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.)
Pending
Application number
CN202010045751.0A
Other languages
Chinese (zh)
Inventor
郭钦鹏
杨仕教
刘迎九
相志斌
陈然
吴彪
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
University of South China
Original Assignee
University of South China
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by University of South China filed Critical University of South China
Priority to CN202010045751.0A priority Critical patent/CN111275252A/en
Publication of CN111275252A publication Critical patent/CN111275252A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
    • G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/24—Classification techniques
    • G06F18/243—Classification techniques relating to the number of classes
    • G06F18/24323—Tree-organised classifiers
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/04—Architecture, e.g. interconnection topology
    • G06N3/045—Combinations of networks
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/08—Learning methods
    • G06N3/084—Backpropagation, e.g. using gradient descent

Abstract

The invention discloses a blasting peak value speed prediction method, a device and a medium based on RGA-BPNNG, wherein the method comprises the following steps: acquiring blasting characteristic parameters of an area to be blasted; predicting the blasting peak speed of the area to be blasted according to the blasting characteristic parameters and a preset random GA-BP neural network group blasting peak speed prediction model; the preset random GA-BP neural network group blasting peak value speed prediction model is obtained by training a random GA-BP neural network group through historical blasting characteristic parameters of a blasted area. Predicting the blasting peak speed after blasting in the area to be blasted, so as to conveniently and reasonably adjust and design blasting characteristic parameters to ensure that the blasting effect after blasting is implemented meets the working condition requirement; according to the invention, the blasting peak speed is predicted by the random GA-BP neural network group blasting peak speed prediction model, so that the precision and reliability of the blasting peak speed prediction value are effectively improved.

Description

Blasting peak value speed prediction method, device and medium based on RGA-BPNNG
Technical Field
The invention relates to the technical field of geotechnical engineering, in particular to a blasting peak value speed prediction method, a device and a medium based on RGA-BPNNG.
Background
The gradual maturity of the engineering blasting technology and the wide application thereof in the engineering construction field become an indispensable important construction means. It brings great economic and social benefits, and various harmful effects generated by blasting operation also influence life and safety of buildings and personnel around the engineering area. The impact of blasting vibration damage is the most significant: the cracking of buildings, the vibration cracking of doors and windows, the slide collapse of side slopes and the like are all common explosive vibration harmful effects. Therefore, the requirement for accurately forecasting the blasting vibration intensity is more urgent, and the blasting peak velocity is a direct parameter for reflecting the blasting vibration intensity. From the classic peak detonation velocity prediction formula, the sado-vsky empirical formula, to the development of the sado-vsky empirical formula, and other regression formulas, many expert scholars have made constant efforts on the peak detonation velocity (PPV) prediction formula.
If a prediction equation based on Gene Expression Programming (GEP) is established firstly, and then a GEP prediction model is optimized through a rhododendron optimization algorithm (COA) to predict the burst peak velocity (PPV); as a group intelligent algorithm based on the cuckoo search (NSICS), an accurate equation for predicting the explosion vibration of the Iranian Duke copper mine is established; and establishing a blasting peak velocity (PPV) prediction formula by using a dimension analysis method (DA); they all improve the prediction accuracy of the burst peak velocity (PPV) to some extent.
In recent years, with the rapid development of machine learning, various methods for predicting the peak velocity of detonation (PPV) have emerged. If a Support Vector Machine (SVM) is applied to predict the ground vibration in the explosion operation of the Irania barheiya dam; establishing an Adaptive Neural Fuzzy Inference System (ANFIS) to predict the burst peak velocity (PPV) by taking the maximum dosage per delay and the distance as input parameters and the burst peak velocity (PPV) as output parameters; applying BP neural network (BPNN) and adding more input parameters to predict the burst peak velocity (PPV). The peak velocity of detonation (PPV) prediction is combined with machine learning, and a new method is provided for predicting the peak velocity of detonation (PPV) with a very complex nonlinear relation. Currently, BP neural networks are widely used in terms of shot peak velocity (PPV) prediction.
Although the BP neural network is widely applied to the prediction of the burst peak velocity (PPV), the BP neural network has the defects of slow learning speed, high possibility of falling into a local minimum value and the like. In the process of actually applying to the prediction of the blasting peak velocity (PPV), the efficiency is low, the error of the predicted value is large, and the prediction reliability is not high.
Disclosure of Invention
The invention provides a blasting peak value speed prediction method, a blasting peak value speed prediction device and a blasting peak value speed prediction medium based on RGA-BPNNG, which aim to solve the problems of large error and insufficient reliability of blasting peak value speed prediction based on a BP neural network in the prior art.
In a first aspect of the present invention, a method for predicting a peak blasting velocity based on RGA-BPNNG is provided, which includes:
acquiring blasting characteristic parameters of an area to be blasted;
predicting the blasting peak speed of the area to be blasted according to the blasting characteristic parameters and a preset random GA-BP neural network group blasting peak speed prediction model; the preset random GA-BP neural network group blasting peak value speed prediction model is obtained by training a random GA-BP neural network group through historical blasting characteristic parameters of a blasted area.
The method comprises the steps of obtaining blasting characteristic parameters of an area to be blasted and a trained random GA-BP neural network group blasting peak speed prediction model, predicting the blasting peak speed of the area to be blasted during blasting so as to reasonably adjust and design the blasting characteristic parameters and enable the predicted value of the blasting peak speed to meet requirements, namely, ensuring that the blasting vibration strength meets the requirements and ensuring that the blasting effect after blasting is achieved to meet the working condition requirements, wherein the blasted area and the area to be blasted are in the same area or in a similar area. The invention predicts the explosion peak speed by a random GA-BP neural network group explosion peak speed prediction model obtained by training a random GA-BP neural network group through historical explosion characteristic parameters of an exploded area, the random GA-BP neural network group explosion peak speed prediction model is established based on the thought of a random forest algorithm and by taking the GA-BP neural network as a core, the probability that the BP neural network is limited to a local minimum value can be reduced through a Genetic Algorithm (GA), and finally, the output explosion peak speed prediction result is more accurate and stable by combining the thought of the random forest algorithm, so that the precision and the reliability of the explosion peak speed prediction value are effectively improved.
Further, the preset random GA-BP neural network group blasting peak speed prediction model is obtained by training a random GA-BP neural network group through historical blasting characteristic parameters of a blasted area, and specifically includes:
obtaining historical blasting characteristic parameters and blasting peak speed of a blasted area;
constructing a blasting sample set based on historical blasting characteristic parameters of a blasted area and corresponding blasting peak speed;
extracting N groups of sub-training sets from the blasting sample set by a random sampling method with a release function, wherein N is a preset value;
respectively training the GA-BP neural network by using N groups of sub-training sets by taking the blasting characteristic parameters as input and the corresponding blasting peak speed as output to obtain N GA-BP neural network blasting peak speed prediction models; wherein, every time a GA-BP neural network blasting peak speed prediction model is obtained through training, the GA-BP neural network blasting peak speed prediction model is respectively checked by using a corresponding subtest set; if the prediction error of the GA-BP neural network blasting peak speed prediction model exceeds a preset value, randomly extracting a group of sub-training sets and corresponding sub-test sets from the blasting sample set again, establishing a GA-BP neural network blasting peak speed prediction model by using the group of sub-training sets, and testing the GA-BP neural network blasting peak speed prediction model by using the corresponding sub-test sets until the prediction error of the obtained GA-BP neural network blasting peak speed prediction model does not exceed the preset value;
and calculating the weight corresponding to each of the N GA-BP neural network blasting peak speed prediction models according to the prediction error of each of the N GA-BP neural network blasting peak speed prediction models, and establishing a random GA-BP neural network group blasting peak speed prediction model based on the N GA-BP neural network blasting peak speed prediction models, wherein the blasting peak speed prediction value output by the random GA-BP neural network group blasting peak speed prediction model is the sum of the products of the output of each of the N GA-BP neural network blasting peak speed prediction models and the weight corresponding to the output.
The weight corresponding to each of the N GA-BP neural network blasting peak speed prediction models is calculated by the following formula:
Figure BDA0002369335030000031
in the formula, eiError of ith prediction model in N GA-BP neural network blasting peak velocity prediction models, xiAnd (4) weighting the ith GA-BP neural network explosion peak speed prediction model.
The mathematical model of the output result of the random GA-BP neural network group blasting peak speed prediction model is as follows:
Figure BDA0002369335030000032
in the formula: x is the number ofiWeight, y, of the ith GA-BP neural network blasting peak velocity prediction modeliAnd Y is the total output of the weighted average of the ith GA-BP neural network blasting peak velocity prediction model, namely the output of the random GA-BP neural network group blasting peak velocity prediction model, namely the predicted value of the blasting peak velocity.
The random forest algorithm (RF) selects training data by adopting a random put-back sampling method, constructs a plurality of decision tree classifiers, constructs optimal segmentation by randomly selecting features, and finally combines the constructed weak classifiers to increase the overall effect. The randomness of the random forest algorithm (RF) is realized by the randomness of the selected data and characteristics, and even if the data or the characteristics are lost, the random forest algorithm (RF) has a more accurate result. In addition, since a plurality of classifiers are constructed, errors caused by the result of a certain classifier can be reduced or eliminated. The invention provides a random GA-BP neural network group blasting peak value speed prediction model taking a GA-BP neural network blasting peak value speed prediction model as a core by combining the thought of a random forest algorithm (RF) and replacing a decision tree classifier with the GA-BP neural network blasting peak value speed prediction model. The random GA-BP neural network group blasting peak speed prediction model inherits the advantages of a random forest algorithm (RF), the accuracy and the stability of the output result of the random GA-BP neural network group blasting peak speed prediction model are guaranteed through balance errors, and the defects of the fault tolerance capability and the generalization capability of the GA-BP neural network group blasting peak speed prediction model are made up through strong generalization capability and fault tolerance capability.
Further, the GA-BP neural network is obtained by optimizing a BP neural network through a genetic algorithm, and specifically includes:
a1, randomly generating a plurality of groups of weight values and threshold values of the BP neural network, and coding the weight values and the threshold values;
a2, carrying out fitness evaluation on the multiple groups of weights and thresholds respectively;
a3, if one or more groups of evaluation results corresponding to the weight and the threshold meet the requirements, namely the error of the predicted value of the blasting peak velocity output by the BP neural network output layer is within a preset range, selecting a group of weight and threshold corresponding to the minimum error of the predicted value of the blasting peak velocity output by the BP neural network output layer as an optimal weight and an optimal threshold, and taking the optimal weight and the optimal threshold as the weight and the threshold of the BP neural network to obtain the GA-BP neural network; if no evaluation result corresponding to one set of weight and threshold meets the requirement, selecting, crossing and mutating the multiple sets of weight and threshold to generate new multiple sets of weight and threshold, and returning to the step A2.
The fitness function adopted for respectively evaluating the fitness of the multiple groups of weights and thresholds is a BP neural network, the evaluation method adopts mean square error or root mean square error in the evaluation of the BP neural network, and if the mean square error or the root mean square error corresponding to the evaluation of the fitness of the group of weights and thresholds is smaller than a preset value, the evaluation result meets the requirement. Wherein the Mean Square Error (MSE) and the Root Mean Square Error (RMSE) are calculated as follows:
Figure BDA0002369335030000041
Figure BDA0002369335030000042
in the formula, yiFor the actual peak value of the blast velocity,
Figure BDA0002369335030000043
and n is the total number of training samples.
The Genetic Algorithm (GA) is a randomized search method which is evolved by simulating the evolution rule of survival, superiority and inferiority of a suitable person in the natural world. The method continuously evolves a 'chromosome' group represented by problem solution codes by generations through a probabilistic optimization method of selection, intersection and variation, and finally converges to the most adaptive group, so that the optimal solution or the satisfactory solution of the problem is obtained. The method has the advantages of inherent hidden parallelism and better global optimization capability. A Genetic Algorithm (GA) is used for optimizing the BP neural network, the global search capability of the genetic algorithm is mainly utilized, the characteristics that fitness evaluation can be carried out on multiple groups of weights and thresholds are utilized to optimize the weights and the thresholds of the BP neural network, and therefore the possibility that the built GA-BP neural network blasting peak value speed prediction model falls into a minimum value is reduced.
Further, the step of obtaining the historical blasting characteristic parameters and the blasting peak speed of the blasted area further comprises the step of performing standardized preprocessing on the obtained blasting characteristic parameters and the obtained blasting peak speed.
Further, the blasting characteristic parameters comprise the maximum single-section explosive quantity per delay, the distance between an explosion surface and a monitoring point, and the elevation difference between the monitoring point and a blasting center.
In a second aspect of the present invention, there is provided a device for predicting a peak velocity of a blast based on RGA-BPNNG, comprising:
the first data acquisition module is used for acquiring blasting characteristic parameters of an area to be blasted;
the blasting peak speed prediction module is used for predicting the blasting peak speed of the area to be blasted according to the blasting characteristic parameters and a preset random GA-BP neural network group blasting peak speed prediction model; the preset random GA-BP neural network group blasting peak value speed prediction model is obtained by training a random GA-BP neural network group through historical blasting characteristic parameters of a blasted area.
Further, still include:
the second data acquisition module is used for acquiring historical blasting characteristic parameters and blasting peak speed of the blasted area;
the sample set generating module is used for constructing a blasting sample set based on the historical blasting characteristic parameters of the blasted area and the corresponding blasting peak value speed;
the random GA-BP neural network group blasting peak value speed prediction model generation module is used for generating a random GA-BP neural network group blasting peak value speed prediction model and comprises the following steps:
the sampling unit is used for extracting N groups of sub training sets and corresponding sub test sets from the blasting sample set by a random sampling method with a release function, wherein N is a preset value;
the GA-BP neural network blasting peak speed prediction model generation unit is used for training the GA-BP neural network by using N groups of sub-training sets by taking blasting characteristic parameters as input and corresponding blasting peak speeds as output to obtain N GA-BP neural network blasting peak speed prediction models; wherein, every time a GA-BP neural network blasting peak speed prediction model is obtained through training, the GA-BP neural network blasting peak speed prediction model is respectively checked by using a corresponding subtest set; if the prediction error of the GA-BP neural network blasting peak speed prediction model exceeds a preset value, randomly extracting a group of sub-training sets and corresponding sub-test sets from the blasting sample set again, establishing a GA-BP neural network blasting peak speed prediction model by using the group of sub-training sets, and testing the GA-BP neural network blasting peak speed prediction model by using the corresponding sub-test sets until the prediction error of the obtained GA-BP neural network blasting peak speed prediction model does not exceed the preset value;
and the random GA-BP neural network group blasting peak speed prediction model generation unit is used for calculating the corresponding weight of each of the N GA-BP neural network group blasting peak speed prediction models according to the prediction error of each of the N GA-BP neural network group blasting peak speed prediction models, establishing a random GA-BP neural network group blasting peak speed prediction model based on the N GA-BP neural network group blasting peak speed prediction models, and outputting a blasting peak speed prediction value which is the sum of products of the output of each of the N GA-BP neural network group blasting peak speed prediction models and the corresponding weight.
Further, the GA-BP neural network blasting peak velocity prediction model generation unit comprises:
the GA-BP neural network generation subunit is used for optimizing the BP neural network through a genetic algorithm to obtain the GA-BP neural network, and the optimization specific process comprises the following steps:
b1, randomly generating a plurality of groups of weight values and threshold values of the BP neural network, and coding the weight values and the threshold values;
b2, carrying out fitness evaluation on the multiple groups of weights and thresholds respectively;
b3, if one or more groups of evaluation results corresponding to the weight and the threshold reach the requirements, namely the error of the predicted value of the blasting peak velocity output by the BP neural network output layer is within the preset range, selecting a group of weight and threshold corresponding to the minimum error of the predicted value of the blasting peak velocity output by the BP neural network output layer as the optimal weight and threshold, and taking the optimal weight and threshold as the weight and threshold of the BP neural network to obtain the GA-BP neural network; if no evaluation result corresponding to one group of weight values and thresholds meets the requirements, selecting, crossing and mutating the multiple groups of weight values and thresholds to generate new multiple groups of weight values and thresholds, and returning to the step B2;
and the GA-BP neural network blasting peak value speed prediction model generation subunit is used for training the GA-BP neural network by using N groups of sub training sets and establishing N GA-BP neural network blasting peak value speed prediction models by using the blasting characteristic parameters as input and the corresponding blasting peak value speed as output.
Further, the blasting characteristic parameters comprise the maximum single-section explosive quantity per delay, the distance between an explosion surface and a monitoring point, and the elevation difference between the monitoring point and a blasting center.
In a third aspect of the present invention, there is provided a computer readable storage medium having stored thereon program instructions adapted to be loaded by a processor and to execute the RGA-BPNNG based peak velocity of blast prediction method according to the first aspect of the present invention.
Advantageous effects
The invention provides a blasting peak speed prediction method, a device and a medium based on RGA-BPNNG, which can predict the blasting peak speed after blasting in a to-be-blasted area through an obtained blasting characteristic parameter of the to-be-blasted area and a trained random GA-BP neural network group blasting peak speed prediction model so as to reasonably adjust and design the blasting characteristic parameter, ensure that the predicted value of the blasting peak speed meets the requirement, namely ensure that the blasting vibration intensity meets the requirement, and ensure that the blasting effect after blasting meets the working condition requirement. The invention predicts the explosion peak speed by a random GA-BP neural network group explosion peak speed prediction model obtained by training a random GA-BP neural network group through historical explosion characteristic parameters of an exploded area, the random GA-BP neural network group explosion peak speed prediction model is established based on the thought of a random forest algorithm and by taking the GA-BP neural network as a core, the probability that the BP neural network is limited to a local minimum value can be reduced through a Genetic Algorithm (GA), and finally, the output explosion peak speed prediction result is more accurate and stable by combining the thought of the random forest algorithm, so that the precision and the reliability of the explosion peak speed prediction value are effectively improved.
Drawings
FIG. 1 is a flow chart of a method for predicting peak blasting velocity based on RGA-BPNNG according to an embodiment of the present invention;
FIG. 2 is a flow chart of the method for establishing a model for predicting the peak blasting velocity of a random GA-BP neural network cluster according to an embodiment of the present invention;
FIG. 3 is a flow chart for optimizing each BP neural network by using a genetic algorithm according to an embodiment of the present invention;
fig. 4 is a diagram of a blast area according to an example of the embodiment of the present invention.
Detailed Description
The present invention will be described in detail below with reference to the accompanying drawings and specific embodiments.
Example 1
As shown in fig. 1, the present embodiment provides a method for predicting a peak velocity of a blast based on RGA-BPNNG, which includes:
step S01: acquiring blasting characteristic parameters of an area to be blasted;
step S02: predicting the blasting peak speed of the area to be blasted according to the blasting characteristic parameters and a preset random GA-BP neural network group blasting peak speed prediction model; the preset random GA-BP neural network group blasting peak value speed prediction model is obtained by training a random GA-BP neural network group through historical blasting characteristic parameters of a blasted area.
The blasting peak speed after blasting in the area to be blasted can be predicted by the acquired blasting characteristic parameters of the area to be blasted and the trained random GA-BP neural network group blasting peak speed prediction model so as to reasonably adjust and design the blasting characteristic parameters and enable the predicted value of the blasting peak speed to meet the requirement and ensure that the blasting effect after blasting is implemented meets the working condition requirement, wherein the blasted area and the area to be blasted are in the same area or the similar area. The invention predicts the explosion peak speed by a random GA-BP neural network group explosion peak speed prediction model obtained by training a random GA-BP neural network group through historical explosion characteristic parameters of an exploded area, the random GA-BP neural network group explosion peak speed prediction model is established based on a random forest algorithm and by taking the GA-BP neural network as a core, the probability that the BP neural network is limited to a local minimum value can be reduced through a Genetic Algorithm (GA), and finally, the output explosion peak speed prediction result is more accurate and stable by combining the random forest algorithm, so that the precision and the reliability of the explosion peak speed prediction value are effectively improved.
Specifically, as shown in fig. 2, in this embodiment, the preset prediction model of the burst peak speed of the random GA-BP neural network group is obtained by training the random GA-BP neural network group according to the historical burst characteristic parameter of the burst area, and specifically includes:
obtaining historical blasting characteristic parameters and blasting peak speed of a blasted area;
carrying out standard pretreatment on the blasting characteristic parameters and the blasting peak value speed, and constructing a blasting sample set based on the pretreated historical blasting characteristic parameters of the blasted area and the corresponding blasting peak value speed;
extracting N groups of sub-training sets and corresponding sub-test sets from the blasting sample set by a sampling method with random replacement, wherein N is a preset value, in the specific implementation, a bootstrap sampling method can be adopted, and the ratio of the number of samples in each group of sub-training sets to the number of samples in the sub-test sets is 3-10: 1;
respectively training the GA-BP neural network by using N groups of sub-training sets by taking the blasting characteristic parameters as input and the corresponding blasting peak speed as output to obtain N GA-BP neural network blasting peak speed prediction models; wherein, every time a GA-BP neural network blasting peak speed prediction model is obtained through training, the GA-BP neural network blasting peak speed prediction model is respectively checked by using a corresponding subtest set; if the prediction error of the GA-BP neural network blasting peak speed prediction model exceeds a preset value, randomly extracting a group of sub-training sets and corresponding sub-test sets from the blasting sample set again, establishing a GA-BP neural network blasting peak speed prediction model by using the group of sub-training sets, and testing the GA-BP neural network blasting peak speed prediction model by using the corresponding sub-test sets until the prediction error of the obtained GA-BP neural network blasting peak speed prediction model does not exceed the preset value;
and calculating the weight corresponding to each of the N GA-BP neural network blasting peak speed prediction models according to the prediction error of each of the N GA-BP neural network blasting peak speed prediction models, and establishing a random GA-BP neural network group blasting peak speed prediction model based on the N GA-BP neural network blasting peak speed prediction models, wherein the blasting peak speed prediction value output by the random GA-BP neural network group blasting peak speed prediction model is the sum of the products of the output of each of the N GA-BP neural network blasting peak speed prediction models and the weight corresponding to the output.
The weight corresponding to each of the N GA-BP neural network blasting peak speed prediction models is calculated by the following formula:
Figure BDA0002369335030000081
in the formula, eiError of ith prediction model in N GA-BP neural network blasting peak velocity prediction models, xiAnd (4) weighting the ith GA-BP neural network explosion peak speed prediction model.
The mathematical model of the output result of the random GA-BP neural network group blasting peak speed prediction model is as follows:
Figure BDA0002369335030000082
in the formula: x is the number ofiWeight, y, of the ith GA-BP neural network blasting peak velocity prediction modeliAnd Y is the total output of the weighted average of the ith GA-BP neural network blasting peak velocity prediction model, namely the output of the random GA-BP neural network group blasting peak velocity prediction model, namely the predicted value of the blasting peak velocity.
The random forest algorithm (RF) selects training data by adopting a random put-back sampling method, constructs a plurality of decision tree classifiers, constructs optimal segmentation by randomly selecting features, and finally combines the constructed weak classifiers to increase the overall effect. The randomness of the random forest algorithm (RF) is realized by the randomness of the selected data and characteristics, and even if the data or the characteristics are lost, the random forest algorithm (RF) has a more accurate result. In addition, since a plurality of classifiers are constructed, errors caused by the result of a certain classifier can be reduced or eliminated. The invention provides a random GA-BP neural network group blasting peak value speed prediction model taking a GA-BP neural network blasting peak value speed prediction model as a core by combining a random forest algorithm (RF) and replacing a decision tree classifier with the GA-BP neural network blasting peak value speed prediction model. The random GA-BP neural network group blasting peak speed prediction model inherits the advantages of a random forest algorithm (RF), the accuracy and the stability of the output result of the random GA-BP neural network group blasting peak speed prediction model are guaranteed through balance errors, and the defects of the fault tolerance capability and the generalization capability of the GA-BP neural network group blasting peak speed prediction model are made up through strong generalization capability and fault tolerance capability.
More specifically, as shown in fig. 3, the GA-BP neural network is obtained by optimizing a BP neural network through a genetic algorithm, and specifically includes:
a1, randomly generating a plurality of groups of weight values and threshold values of the BP neural network, and coding the weight values and the threshold values;
a2, carrying out fitness evaluation on the multiple groups of weights and thresholds respectively;
a3, if one or more groups of evaluation results corresponding to the weight and the threshold meet the requirements, namely the error of the predicted value of the blasting peak velocity output by the BP neural network output layer is within a preset range, selecting a group of weight and threshold corresponding to the minimum error of the predicted value of the blasting peak velocity output by the BP neural network output layer as an optimal weight and an optimal threshold, and taking the optimal weight and the optimal threshold as the weight and the threshold of the BP neural network to obtain the GA-BP neural network; if no evaluation result corresponding to one set of weight and threshold meets the requirement, selecting, crossing and mutating the multiple sets of weight and threshold to generate new multiple sets of weight and threshold, and returning to the step A2.
The fitness function adopted for respectively evaluating the fitness of the multiple groups of weights and thresholds is a BP neural network, the evaluation method adopts mean square error or root mean square error in the evaluation of the BP neural network, and if the mean square error or the root mean square error corresponding to the evaluation of the fitness of the group of weights and thresholds is smaller than a preset value, the evaluation result meets the requirement. Wherein the Mean Square Error (MSE) and the Root Mean Square Error (RMSE) are calculated as follows:
Figure BDA0002369335030000091
Figure BDA0002369335030000092
in the formula, yiFor the actual peak value of the blast velocity,
Figure BDA0002369335030000093
and n is the total number of training samples.
The Genetic Algorithm (GA) is a randomized search method which is evolved by simulating the evolution rule of survival, superiority and inferiority of a suitable person in the natural world. The method continuously evolves a 'chromosome' group represented by problem solution codes by generations through a probabilistic optimization method of selection, intersection and variation, and finally converges to the most adaptive group, so that the optimal solution or the satisfactory solution of the problem is obtained. The method has the advantages of inherent hidden parallelism and better global optimization capability. A Genetic Algorithm (GA) is used for optimizing the BP neural network, the global search capability of the genetic algorithm is mainly utilized, the characteristics that fitness evaluation can be carried out on multiple groups of weights and thresholds are utilized to optimize the weights and the thresholds of the BP neural network, and therefore the possibility that the built GA-BP neural network blasting peak value speed prediction model falls into a minimum value is reduced.
Of course, it should be understood that, in other embodiments, the Genetic Algorithm (GA) may be replaced by optimization algorithms such as Colonial Competition Algorithm (CCA), empire kingdom competition algorithm (ICA), artificial bee colony Algorithm (ABC), Artificial Immune System (AIS), Particle Swarm Optimization (PSO), and the like, and the replacement of the above algorithms also belongs to the protection scope of the present invention.
In this embodiment, the blasting characteristic parameters include the maximum single-stage explosive quantity per delay, the distance between the explosion surface and the monitoring point, and the elevation difference between the monitoring point and the explosion center.
Example 2
The embodiment provides a blasting peak velocity predicting device based on RGA-BPNNG, which comprises:
the first data acquisition module is used for acquiring blasting characteristic parameters of an area to be blasted;
the blasting peak speed prediction module is used for predicting the blasting peak speed of the area to be blasted according to the blasting characteristic parameters and a preset random GA-BP neural network group blasting peak speed prediction model; the preset random GA-BP neural network group blasting peak value speed prediction model is obtained by training a random GA-BP neural network group through historical blasting characteristic parameters of a blasted area.
In this embodiment, the method further includes:
the second data acquisition module is used for acquiring historical blasting characteristic parameters and blasting peak speed of the blasted area;
the sample set generating module is used for carrying out standard pretreatment on the blasting characteristic parameters and the blasting peak value speed and constructing a blasting sample set based on the pretreated historical blasting characteristic parameters of the blasted area and the corresponding blasting peak value speed;
the random GA-BP neural network group blasting peak value speed prediction model generation module is used for generating a random GA-BP neural network group blasting peak value speed prediction model and comprises the following steps:
the sampling unit is used for extracting N groups of sub training sets and corresponding sub test sets from the blasting sample set by a random sampling method with a release function, wherein N is a preset value;
the GA-BP neural network blasting peak speed prediction model generation unit is used for training the GA-BP neural network by using N groups of sub-training sets by taking blasting characteristic parameters as input and corresponding blasting peak speeds as output to obtain N GA-BP neural network blasting peak speed prediction models; wherein, every time a GA-BP neural network blasting peak speed prediction model is obtained through training, the GA-BP neural network blasting peak speed prediction model is respectively checked by using a corresponding subtest set; if the prediction error of the GA-BP neural network blasting peak speed prediction model exceeds a preset value, randomly extracting a group of sub-training sets and corresponding sub-test sets from the blasting sample set again, establishing a GA-BP neural network blasting peak speed prediction model by using the group of sub-training sets, and testing the GA-BP neural network blasting peak speed prediction model by using the corresponding sub-test sets until the prediction error of the obtained GA-BP neural network blasting peak speed prediction model does not exceed the preset value;
and the random GA-BP neural network group blasting peak speed prediction model generation unit is used for calculating the corresponding weight of each of the N GA-BP neural network group blasting peak speed prediction models according to the prediction error of each of the N GA-BP neural network group blasting peak speed prediction models, establishing a random GA-BP neural network group blasting peak speed prediction model based on the N GA-BP neural network group blasting peak speed prediction models, and outputting a blasting peak speed prediction value which is the sum of products of the output of each of the N GA-BP neural network group blasting peak speed prediction models and the corresponding weight.
More specifically, the GA-BP neural network explosion peak velocity prediction model generation unit includes:
the GA-BP neural network generation subunit is used for optimizing the BP neural network through a genetic algorithm to obtain the GA-BP neural network, and the optimization specific process comprises the following steps:
b1, randomly generating a plurality of groups of weight values and threshold values of the BP neural network, and coding the weight values and the threshold values;
b2, carrying out fitness evaluation on the multiple groups of weights and thresholds respectively;
b3, if one or more groups of evaluation results corresponding to the weight and the threshold reach the requirements, namely the error of the predicted value of the blasting peak velocity output by the BP neural network output layer is within the preset range, selecting a group of weight and threshold corresponding to the minimum error of the predicted value of the blasting peak velocity output by the BP neural network output layer as the optimal weight and threshold, and taking the optimal weight and threshold as the weight and threshold of the BP neural network to obtain the GA-BP neural network; if no evaluation result corresponding to one group of weight values and thresholds meets the requirements, selecting, crossing and mutating the multiple groups of weight values and thresholds to generate new multiple groups of weight values and thresholds, and returning to the step B2;
and the GA-BP neural network blasting peak value speed prediction model generation subunit is used for training the GA-BP neural network by using N groups of sub training sets and establishing N GA-BP neural network blasting peak value speed prediction models by using the blasting characteristic parameters as input and the corresponding blasting peak value speed as output.
In this embodiment, the blasting characteristic parameters include the maximum single-stage explosive quantity per delay, the distance between the explosion surface and the monitoring point, and the elevation difference between the monitoring point and the explosion center.
For another specific implementation of the apparatus for predicting peak blasting velocity based on RGA-BPNNG provided in this embodiment, reference may be made to embodiment 1 to provide a method for predicting peak blasting velocity based on RGA-BPNNG, which is not described herein again.
Example 3
The present embodiment provides a computer readable storage medium storing program instructions adapted to be loaded by a processor and to execute the RGA-BPNNG based peak velocity of blast prediction method as described in embodiment 1.
As will be appreciated by one skilled in the art, embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
The technical solution provided by the present invention is further described below with reference to a specific example.
In the example, the project area is located in the coastal region of the great Asia bay of Huizhou, Guangdong province, the project adopts emulsion explosive, and is detonated through a nonelectric detonating tube non-electric detonating network, and the total explosive amount is between 15 and 25t each time. The blasting adopts 140mm aperture, chassis resisting line is between 2-4m, row spacing is 4m, aperture spacing is 3m, step height is between 10-15m, design unit consumption is 0.45kg/m3。
As shown in fig. 4, the item is divided into 6 areas. To predict the peak velocity of detonation (PPV), 92 detonation events for three and five zones were monitored using a TC-4850 vibrometer, and the instrument position was coordinate measured using GPS after placement of the vibrometer. And when filling explosives, filling the explosives strictly according to a design value, carrying out coordinate measurement on each blast hole delaying the maximum single-section explosive amount, and calculating the seating chart data after blasting to respectively obtain the distance (R) between the blasting surface and a monitoring point and the height difference (H) between the monitoring point and the blasting center, wherein PPV keeps three decimal places, R keeps an integer, and H keeps one decimal place. The parameter ranges are shown in table 1, and the data in the table holds three decimal places.
In the training process of the shot peak velocity prediction model (RGA-BPNNG model) of the random GA-BP neural network cluster, in order to prevent the loss of precision caused by different dimensions and orders of training parameters and reduce the influence of errors of the maximum value and the minimum value in a data set on the whole data set, the data is preprocessed by adopting standardization.
Carrying out standardization preprocessing on the data, wherein the standardization process formula is as follows:
Figure BDA0002369335030000121
in the formula: x is the data set before normalization, xmeanIs the average value of x, y is the normalized data set, and n is the total number of samples; in this example, the data set represented by x and y may be any one of the maximum single-stage explosive amount per delay, the distance from the explosion surface to the monitoring point, the height difference from the monitoring point to the explosion center, and the peak explosion velocity.
TABLE 1 ranges for Q, R, H and PPV
Parameter(s) Categories Unit of Minimum value Mean value of Maximum value
Q Input device kg 56 77.804 92
R Input device m 65 85.391 102
H Input device m 0.6 2.996 6.2
PPV Output of cm/s 2.928 4.503 7.235
Since Q, R and H are input parameters and PPV is output parameter, the input layer and the output layer of the BP neural network (BPNN) are 3 layers and 1 layer, respectively. The number of hidden layers has a significant impact on the performance of the BPNN. In general, the greater the number of hidden layers, the better the performance of the BPNN. But may result in too long training time or overfitting phenomena, so it is extremely important to select the appropriate number of hidden layers. At present, there is no suitable analytic formula to determine the number of hidden layer layers, and it is a common practice to select a suitable number of hidden layer layers according to an estimated value of the number of hidden layer layers obtained by an empirical formula or according to personal experience. In order to reduce the iteration times and the running time cost of the whole RGA-BPNNG model and increase the accuracy of the prediction result, a Genetic Algorithm (GA) is adopted to optimize the number of implicit layers of the BPNN, and the result shows that the prediction result is best when the number of implicit layers is 10, so that the structure of the BPNN is 3 multiplied by 10 multiplied by 1 when 10 is selected as the number of implicit layers.
In addition, the hidden layer selects a Tan-Sigmoid function as a transfer function, and the output layer selects a linear function as a transfer function. And selecting a Levenberg-Marquardt (trainlm) back propagation algorithm training function in the weight correction process. Meanwhile, the precision of the training model is set to be 0.001, the learning rate is set to be 0.1, and the maximum iteration number is set to be 1000.
In the Genetic Algorithm (GA), since data is normalized, the initial population range is set to (-2,2), the population size is set to 100, the maximum generation number is 200, and the crossover and mutation probabilities are 0.8 and 0.15, respectively.
To construct the RGA-BPNNG model and evaluate the performance of the model, the data were randomly divided into a training set and a test set at a 4:1 ratio. Only test set data is listed here, considering the amount of data, see table 2. Due to the process of constructing the GA-BP neural network blasting peak velocity prediction model (GA-BPNN model), the iteration times are too many, the operation time is too long, and when the prediction result exceeds the limit, a new GA-BPNN model is reconstructed, so that the operation time cost is increased again. However, the more GA-BPNN models that are built, the better the performance of the RGA-BPNNG model. Therefore, in order to reduce the program runtime and guarantee the performance of the RGA-BPNNG model, 20 GA-BPNN models were built herein. In addition, the maximum relative error is less than 15 percent and is taken as the qualified basis of the GA-BPNN model. And after 20 GA-BPNN models are obtained, calculating the weight of the corresponding GA-BPNN model according to the average relative error. After the whole RGA-BPNNG model is built, the weight values and the threshold values of 20 groups of GA-BPNN models and the weight values corresponding to the GA-BPNN models are obtained.
TABLE 2 test set
Figure BDA0002369335030000131
In order to evaluate the stability and accuracy of the prediction result of the RGA-BPNNG model, 3 RGA-BPNNG models are established by the same training set and model parameters to predict a test set, 3 GA-BPNN models are respectively established as comparison, and a correlation coefficient (R-BPNN) is adopted2) Three indexes of Root Mean Square Error (RMSE) and mean square error (MRE) are used as evaluation criteria. In the prediction program based on 6 models, the parameter settings of BPNN were matched to the parameters of the models. Table 3 and Table 4 show the predicted values and relative errors of the 3 RGA-BPNNG models and the 3 GA-BPNN models, respectively, and Table 5 shows the correlation coefficients (R) of the 6 models2) Root Mean Square Error (RMSE) and mean square error (MRE) values, three decimal places are retained in table 3, table 4, and table 5.
Wherein the correlation coefficient (R)2) Calculated by the following formula:
Figure BDA0002369335030000141
Figure BDA0002369335030000142
in the formula, n represents that the RGA-BPNNG model predicts n test sets and obtains n prediction results,
Figure BDA0002369335030000143
for the ith prediction, YiThe actual value of the ith test sample in the n test sets. R2Larger values indicate better prediction by the model.
Root Mean Square Error (RMSE):
Figure BDA0002369335030000144
in the formula, n represents that the RGA-BPNNG model predicts n test sets and obtains n prediction results,
Figure BDA0002369335030000145
for the ith prediction, YiFor the first of n test setsActual values of i test samples. Smaller RMSE values indicate better model prediction.
Mean Relative Error (MRE):
Figure BDA0002369335030000146
in the formula, n represents that the RGA-BPNNG model predicts n test sets and obtains n prediction results,
Figure BDA0002369335030000147
for the ith prediction, YiThe actual value of the ith test sample in the n test sets. Smaller MRE values indicate better model prediction.
TABLE 3 RGA-BPNNG model prediction values
Figure BDA0002369335030000148
Figure BDA0002369335030000151
TABLE 4 GA-BPNN model prediction values
Figure BDA0002369335030000152
TABLE 5 statistical indices of prediction models
Figure BDA0002369335030000153
As can be seen from Table 5, R of the second RGA-BPNNG model among the RGA-BPNNG models2RMSE, MRE were 0.962, 0.179, 3.543, respectively, with the best predicted performance. Among the GA-BPNN models, the R of the first GA-BPNN model2RMSE, MRE were 0.911, 0.271, 5.790, respectively, with the best predicted performance. And the model with the worst prediction performance in the RGA-BPNNG model has better prediction effect than the model with the best prediction performance in the GA-BPNN model. As can be seen from tables 3 and 4, the RGA-BPNNG model is predicted at a certain sampleThe relative error of the result is larger than that of the prediction result of the GA-BPNN model, and the prediction effect of the RGA-BPNNG model is better than that of the GA-BPNN model in general. In addition, the prediction result of the RGA-BPNNG model is relatively stable and accurate. Therefore, compared with a GA-BPNN model, the RGA-BPNNG provided by the invention has higher prediction precision and more stable prediction effect, and shows that the algorithm provided by the invention is effective and can predict the burst peak speed more accurately.
The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention, and various modifications and changes may be made by those skilled in the art. Any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims (10)

1. A blasting peak speed prediction method based on RGA-BPNNG is characterized by comprising the following steps:
acquiring blasting characteristic parameters of an area to be blasted;
predicting the blasting peak speed of the area to be blasted according to the blasting characteristic parameters and a preset random GA-BP neural network group blasting peak speed prediction model; the preset random GA-BP neural network group blasting peak value speed prediction model is obtained by training a random GA-BP neural network group through historical blasting characteristic parameters of a blasted area.
2. The method for predicting the burst peak velocity based on the RGA-BPNNG according to claim 1, wherein the preset random GA-BP neural network group burst peak velocity prediction model is obtained by training a random GA-BP neural network group through historical burst characteristic parameters of a burst area, and specifically comprises:
obtaining historical blasting characteristic parameters and blasting peak speed of a blasted area;
constructing a blasting sample set based on historical blasting characteristic parameters of a blasted area and corresponding blasting peak speed;
extracting N groups of sub training sets and corresponding sub test sets from the blasting sample set by a random sampling method with a release function, wherein N is a preset value;
respectively training the GA-BP neural network by using N groups of sub-training sets by taking the blasting characteristic parameters as input and the corresponding blasting peak speed as output to obtain N GA-BP neural network blasting peak speed prediction models; wherein, every time a GA-BP neural network blasting peak speed prediction model is obtained through training, the GA-BP neural network blasting peak speed prediction model is respectively checked by using a corresponding subtest set; if the prediction error of the GA-BP neural network blasting peak speed prediction model exceeds a preset value, randomly extracting a group of sub-training sets and corresponding sub-test sets from the blasting sample set again, establishing a GA-BP neural network blasting peak speed prediction model by using the group of sub-training sets, and testing the GA-BP neural network blasting peak speed prediction model by using the corresponding sub-test sets until the prediction error of the obtained GA-BP neural network blasting peak speed prediction model does not exceed the preset value;
and calculating the weight corresponding to each of the N GA-BP neural network blasting peak speed prediction models according to the prediction error of each of the N GA-BP neural network blasting peak speed prediction models, and establishing a random GA-BP neural network group blasting peak speed prediction model based on the N GA-BP neural network blasting peak speed prediction models, wherein the blasting peak speed prediction value output by the random GA-BP neural network group blasting peak speed prediction model is the sum of the products of the output of each of the N GA-BP neural network blasting peak speed prediction models and the weight corresponding to the output.
3. The method for predicting the peak blasting velocity based on the RGA-BPNNG according to claim 2, wherein the GA-BP neural network is obtained by optimizing a BP neural network through a genetic algorithm, and specifically comprises the following steps:
a1, randomly generating a plurality of groups of weight values and threshold values of the BP neural network, and coding the weight values and the threshold values;
a2, carrying out fitness evaluation on the multiple groups of weights and thresholds respectively;
a3, if one or more groups of evaluation results corresponding to the weight and the threshold meet the requirements, namely the error of the predicted value of the blasting peak velocity output by the BP neural network output layer is within a preset range, selecting a group of weight and threshold corresponding to the minimum error of the predicted value of the blasting peak velocity output by the BP neural network output layer as an optimal weight and an optimal threshold, and taking the optimal weight and the optimal threshold as the weight and the threshold of the BP neural network to obtain the GA-BP neural network; if no evaluation result corresponding to one set of weight and threshold meets the requirement, selecting, crossing and mutating the multiple sets of weight and threshold to generate new multiple sets of weight and threshold, and returning to the step A2.
4. The method of claim 2, wherein the obtaining the historical blasting characteristic parameters and the blasting peak velocity of the blasted area further comprises performing a normalization pretreatment on the obtained blasting characteristic parameters and the blasting peak velocity.
5. A method of RGA-BPNNG-based peak velocity of blast prediction according to any of claims 1 to 4, where the blast characterization parameters include maximum single charge per delay, distance from the blast face to the monitoring point, elevation difference from monitoring point to core.
6. An apparatus for predicting peak velocity of blast based on RGA-BPNNG, comprising:
the first data acquisition module is used for acquiring blasting characteristic parameters of an area to be blasted;
the blasting peak speed prediction module is used for predicting the blasting peak speed of the area to be blasted according to the blasting characteristic parameters and a preset random GA-BP neural network group blasting peak speed prediction model; the preset random GA-BP neural network group blasting peak value speed prediction model is obtained by training a random GA-BP neural network group through historical blasting characteristic parameters of a blasted area.
7. The apparatus of claim 6, further comprising:
the second data acquisition module is used for acquiring historical blasting characteristic parameters and blasting peak speed of the blasted area;
the sample set generating module is used for constructing a blasting sample set based on the historical blasting characteristic parameters of the blasted area and the corresponding blasting peak value speed;
the random GA-BP neural network group blasting peak value speed prediction model generation module is used for generating a random GA-BP neural network group blasting peak value speed prediction model and comprises the following steps:
the sampling unit is used for extracting N groups of sub training sets and corresponding sub test sets from the blasting sample set by a random sampling method with a release function, wherein N is a preset value;
the GA-BP neural network blasting peak speed prediction model generation unit is used for training the GA-BP neural network by using N groups of sub-training sets by taking blasting characteristic parameters as input and corresponding blasting peak speeds as output to obtain N GA-BP neural network blasting peak speed prediction models; wherein, every time a GA-BP neural network blasting peak speed prediction model is obtained through training, the GA-BP neural network blasting peak speed prediction model is respectively checked by using a corresponding subtest set; if the prediction error of the GA-BP neural network blasting peak speed prediction model exceeds a preset value, randomly extracting a group of sub-training sets and corresponding sub-test sets from the blasting sample set again, establishing a GA-BP neural network blasting peak speed prediction model by using the group of sub-training sets, and testing the GA-BP neural network blasting peak speed prediction model by using the corresponding sub-test sets until the prediction error of the obtained GA-BP neural network blasting peak speed prediction model does not exceed the preset value;
and the random GA-BP neural network group blasting peak speed prediction model generation unit is used for calculating the corresponding weight of each of the N GA-BP neural network group blasting peak speed prediction models according to the prediction error of each of the N GA-BP neural network group blasting peak speed prediction models, establishing a random GA-BP neural network group blasting peak speed prediction model based on the N GA-BP neural network group blasting peak speed prediction models, and outputting a blasting peak speed prediction value which is the sum of products of the output of each of the N GA-BP neural network group blasting peak speed prediction models and the corresponding weight.
8. The apparatus of claim 7, wherein the GA-BP neural network peak burst velocity prediction model generation unit comprises:
the GA-BP neural network generation subunit is used for optimizing the BP neural network through a genetic algorithm to obtain the GA-BP neural network, and the optimization specific process comprises the following steps:
b1, randomly generating a plurality of groups of weight values and threshold values of the BP neural network, and coding the weight values and the threshold values;
b2, carrying out fitness evaluation on the multiple groups of weights and thresholds respectively;
b3, if one or more groups of evaluation results corresponding to the weight and the threshold reach the requirements, namely the error of the predicted value of the blasting peak velocity output by the BP neural network output layer is within the preset range, selecting a group of weight and threshold corresponding to the minimum error of the predicted value of the blasting peak velocity output by the BP neural network output layer as the optimal weight and threshold, and taking the optimal weight and threshold as the weight and threshold of the BP neural network to obtain the GA-BP neural network; if no evaluation result corresponding to one group of weight values and thresholds meets the requirements, selecting, crossing and mutating the multiple groups of weight values and thresholds to generate new multiple groups of weight values and thresholds, and returning to the step B2;
and the GA-BP neural network blasting peak value speed prediction model generation subunit is used for training the GA-BP neural network by using N groups of sub training sets and establishing N GA-BP neural network blasting peak value speed prediction models by using the blasting characteristic parameters as input and the corresponding blasting peak value speed as output.
9. An RGA-BPNNG-based device for predicting the peak velocity of a blast according to any of claims 6 to 8, wherein the characteristic parameters of the blast include the maximum single-stage dosage per delay, the distance from the blast surface to the monitoring point, and the elevation difference from the monitoring point to the core of the blast.
10. A computer readable storage medium, characterized in that the storage medium stores program instructions adapted to be loaded by a processor and to execute the RGA-BPNNG based peak velocity of blast prediction method according to any of claims 1 to 5.
CN202010045751.0A 2020-01-16 2020-01-16 Blasting peak value speed prediction method, device and medium based on RGA-BPNNG Pending CN111275252A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202010045751.0A CN111275252A (en) 2020-01-16 2020-01-16 Blasting peak value speed prediction method, device and medium based on RGA-BPNNG

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202010045751.0A CN111275252A (en) 2020-01-16 2020-01-16 Blasting peak value speed prediction method, device and medium based on RGA-BPNNG

Publications (1)

Publication Number Publication Date
CN111275252A true CN111275252A (en) 2020-06-12

Family

ID=70999078

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202010045751.0A Pending CN111275252A (en) 2020-01-16 2020-01-16 Blasting peak value speed prediction method, device and medium based on RGA-BPNNG

Country Status (1)

Country Link
CN (1) CN111275252A (en)

Cited By (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112630827A (en) * 2020-12-07 2021-04-09 中国地震局工程力学研究所 Earth surface acceleration peak value parameter prediction method and system
CN112711904A (en) * 2020-12-17 2021-04-27 玉溪矿业有限公司 Blasting vibration characteristic parameter prediction method based on SA-GA-BP
CN113626978A (en) * 2021-06-23 2021-11-09 浙江中控技术股份有限公司 On-line prediction method and system for detonation velocity of civil explosive emulsion explosive
CN113837440A (en) * 2021-08-20 2021-12-24 中国矿业大学(北京) Blasting effect prediction method and device, electronic equipment and medium
CN115307687A (en) * 2022-09-29 2022-11-08 四川省公路规划勘察设计研究院有限公司 Slope stability monitoring method and system, storage medium and electronic equipment

Cited By (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112630827A (en) * 2020-12-07 2021-04-09 中国地震局工程力学研究所 Earth surface acceleration peak value parameter prediction method and system
CN112630827B (en) * 2020-12-07 2024-02-02 中国地震局工程力学研究所 Surface acceleration peak parameter prediction method and system
CN112711904A (en) * 2020-12-17 2021-04-27 玉溪矿业有限公司 Blasting vibration characteristic parameter prediction method based on SA-GA-BP
CN113626978A (en) * 2021-06-23 2021-11-09 浙江中控技术股份有限公司 On-line prediction method and system for detonation velocity of civil explosive emulsion explosive
CN113626978B (en) * 2021-06-23 2023-12-26 浙江中控技术股份有限公司 On-line prediction method and system for detonation velocity of civil explosive emulsion explosive
CN113837440A (en) * 2021-08-20 2021-12-24 中国矿业大学(北京) Blasting effect prediction method and device, electronic equipment and medium
CN113837440B (en) * 2021-08-20 2023-09-12 中国矿业大学(北京) Blasting effect prediction method and device, electronic equipment and medium
CN115307687A (en) * 2022-09-29 2022-11-08 四川省公路规划勘察设计研究院有限公司 Slope stability monitoring method and system, storage medium and electronic equipment
CN115307687B (en) * 2022-09-29 2022-12-27 四川省公路规划勘察设计研究院有限公司 Slope stability monitoring method and system, storage medium and electronic equipment

Similar Documents

Publication Publication Date Title
CN111275252A (en) Blasting peak value speed prediction method, device and medium based on RGA-BPNNG
CN111259601A (en) Blasting blockiness prediction method, device and medium based on random GA-BP neural network group
CN109214566B (en) Wind power short-term prediction method based on long and short-term memory network
CN110298663B (en) Fraud transaction detection method based on sequence wide and deep learning
CN104899431B (en) Based on ant colony and swarm of particles into LSSVM fluctuating wind speed Forecasting Methodologies
CN112686464A (en) Short-term wind power prediction method and device
CN108694482B (en) Fractal theory and improved Least Square Support Vector Machine (LSSVM) tidal flow velocity prediction method
CN110006649A (en) A kind of Method for Bearing Fault Diagnosis based on improvement ant lion algorithm and support vector machines
CN112651164A (en) Creep fatigue life prediction method based on machine learning
Abdechiri et al. Adaptive imperialist competitive algorithm (AICA)
CN113705094A (en) Ship fuel oil pipeline fault prediction method based on PSO-GRU
CN107862457B (en) Method for extracting stage scheduling rules of reservoir
Xiao et al. Addressing overfitting problem in deep learning-based solutions for next generation data-driven networks
CN111753751A (en) Fan fault intelligent diagnosis method for improving firework algorithm
CN111950203A (en) Blasting vibration speed prediction method based on adaptive neural fuzzy inference system
CN116976227B (en) Storm water increasing forecasting method and system based on LSTM machine learning
CN114444755A (en) Wind power short-term power prediction method and device and readable storage medium
Guo et al. Data mining and application of ship impact spectrum acceleration based on PNN neural network
CN111400964A (en) Fault occurrence time prediction method and device
CN114070655B (en) Network flow detection rule generation method and device, electronic equipment and storage medium
Raharjo et al. Optimization forecasting using back-propagation algorithm
Gholamian et al. Enhanced comprehensive learning cooperative particle swarm optimization with fuzzy inertia weight (ECLCFPSO-IW)
CN113240161A (en) Net present value prediction model establishing method and device, storage medium and electronic equipment
CN113054653A (en) Power system transient stability evaluation method based on VGGNet-SVM
Mohanty et al. Liquefaction susceptibility of soil using multi objective feature selection

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