CN119333134B - Automatic cutting depth control method for continuous excavation of hard rock layer based on deep learning - Google Patents
Automatic cutting depth control method for continuous excavation of hard rock layer based on deep learning Download PDFInfo
- Publication number
- CN119333134B CN119333134B CN202411884148.6A CN202411884148A CN119333134B CN 119333134 B CN119333134 B CN 119333134B CN 202411884148 A CN202411884148 A CN 202411884148A CN 119333134 B CN119333134 B CN 119333134B
- Authority
- CN
- China
- Prior art keywords
- continuous mining
- continuous
- mining
- cutting depth
- parameters
- 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
-
- E—FIXED CONSTRUCTIONS
- E21—EARTH OR ROCK DRILLING; MINING
- E21C—MINING OR QUARRYING
- E21C35/00—Details of, or accessories for, machines for slitting or completely freeing the mineral from the seam, not provided for in groups E21C25/00 - E21C33/00, E21C37/00 or E21C39/00
- E21C35/24—Remote control specially adapted for machines for slitting or completely freeing the mineral
-
- E—FIXED CONSTRUCTIONS
- E21—EARTH OR ROCK DRILLING; MINING
- E21B—EARTH OR ROCK DRILLING; OBTAINING OIL, GAS, WATER, SOLUBLE OR MELTABLE MATERIALS OR A SLURRY OF MINERALS FROM WELLS
- E21B44/00—Automatic control systems specially adapted for drilling operations, i.e. self-operating systems which function to carry out or modify a drilling operation without intervention of a human operator, e.g. computer-controlled drilling systems; Systems specially adapted for monitoring a plurality of drilling variables or conditions
-
- E—FIXED CONSTRUCTIONS
- E21—EARTH OR ROCK DRILLING; MINING
- E21C—MINING OR QUARRYING
- E21C35/00—Details of, or accessories for, machines for slitting or completely freeing the mineral from the seam, not provided for in groups E21C25/00 - E21C33/00, E21C37/00 or E21C39/00
- E21C35/282—Autonomous machines; Autonomous operations
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B13/00—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion
- G05B13/02—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric
- G05B13/04—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric involving the use of models or simulators
- G05B13/042—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric involving the use of models or simulators in which a parameter or coefficient is automatically adjusted to optimise the performance
Landscapes
- Engineering & Computer Science (AREA)
- Mining & Mineral Resources (AREA)
- Life Sciences & Earth Sciences (AREA)
- Geology (AREA)
- Geochemistry & Mineralogy (AREA)
- General Life Sciences & Earth Sciences (AREA)
- Mechanical Engineering (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Automation & Control Theory (AREA)
- Health & Medical Sciences (AREA)
- Environmental & Geological Engineering (AREA)
- Fluid Mechanics (AREA)
- Software Systems (AREA)
- Medical Informatics (AREA)
- Evolutionary Computation (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Artificial Intelligence (AREA)
- Earth Drilling (AREA)
Abstract
The invention discloses an automatic cutting depth control method for continuous hard rock layer mining based on deep learning, which comprises the steps of establishing and training a deep neural network model, predicting pre-drilling fracturing operation and rock layer strength parameters, determining reasonable cutting depth control values and monitoring and controlling continuous mining operation, improving the cutting performance of the hard rock layer by the pre-drilling fracturing operation, predicting the rock layer strength parameters after fracturing according to a deep learning algorithm, further determining the reasonable cutting depth values, facilitating the improvement of the mining efficiency of continuous mining equipment in the hard rock layer environment and the reduction of the consumption of cutting tools, and then calculating the current operation strategy of the continuous mining equipment in real time according to real-time monitoring data and the trained deep neural network model, thereby realizing the real-time monitoring and control of cutting depth, cutting mechanism power and mining working face flatness and facilitating the improvement of the control precision, safety and automation of the continuous mining equipment.
Description
Technical Field
The invention belongs to the technical field of neural network models, and relates to a method for controlling automatic cutting depth of continuous mining of hard rock layers based on deep learning.
Background
The deep learning algorithm is a machine learning method based on an artificial neural network, and features contained in automatic learning data and an optimal expression for searching tasks are realized through multi-layer neural networks and training of a large amount of data. In the deep learning field, the core idea of the deep neural network model technology is to realize progressive feature extraction and abstract expression of input data layer by layer through a plurality of hidden layers between an input layer and an output layer. The deep neural network model technology is widely applied to various industrial scenes along with remarkable improvement of computing power, and is particularly suitable for mining operation with very abundant practical experience and relatively deficient theoretical results.
A novel continuous excavating device matched with pre-drilling fracturing equipment is characterized in that drilling test holes are drilled through a drilling tool of the pre-drilling fracturing equipment and vibration fracturing is conducted through an excitation device, so that microcrack expansion occurs on a hard rock layer of a strip mine working face along the periphery of a drill hole, the cuttability of the hard rock layer is improved, and then rock strata are continuously cut through a cutting mechanism of the novel continuous excavating device, so that continuous excavating of the hard rock layer without blasting, safety, environmental protection and economy is achieved. In view of the non-uniformity of hard rock layer distribution, the nonlinearity of rock mechanical properties and the randomness of microcrack expansion, the strength properties of the rock stratum after pre-drilling and fracturing are suitable for real-time prediction by adopting a deep neural network model technology.
The cutting depth is the depth that the continuous mining apparatus cuts into the formation in one cutting cycle. The depth of cut of the new continuous mining apparatus is a major factor in determining the productivity of the mining face during hard rock environmental operations. An insufficient cutting depth will result in a low extraction efficiency, while an excessive cutting depth will result in a reduced rock breaking efficiency and an increased degree of loss of the cutting mechanism. On the other hand, in the mining operation of the same working face, if the cutting depths at different positions are inconsistent, the flatness of the surface of the strip mine is insufficient, and the control precision and the automation of continuous mining equipment are not facilitated. Therefore, it is necessary to combine the strength characteristics of the rock stratum after pre-drilling and fracturing with the fatigue strength characteristics of the materials of the cutting mechanism of the continuous mining equipment to determine reasonable cutting depth values, and determine the operation strategy of the continuous mining equipment in real time through a deep neural network model technology, so as to control the continuous mining operation parameters including the cutting depth, and improve the automation, intellectualization, safety and high efficiency level of the continuous mining operation of the hard rock stratum.
Disclosure of Invention
Aiming at the defects of the prior art, the invention provides the depth learning-based automatic cutting depth control method for continuous hard rock layer mining, which is suitable for automatic cutting depth control during continuous open-pit mining equipment operation in a hard rock layer environment, is beneficial to improving the mining efficiency and reducing the loss of a cutting mechanism, and realizes the control of the cutting depth and the automation, the intellectualization, the safety and the high efficiency of the continuous hard rock layer mining operation.
The application discloses a depth learning-based automatic cutting depth control method for continuous hard rock layer mining, which comprises the following steps:
S100, establishing and training a deep neural network model, namely establishing an initial deep neural network model, wherein the initial deep neural network model comprises an input layer, a hidden layer and an output layer, the input layer is used for receiving data, the hidden layer is used for data processing and feature extraction, and the output layer is used for generating a prediction result;
the data received by the input layer comprises, but is not limited to, pre-drilling technical parameters, mining environment state parameters and continuous mining equipment state parameters at different moments after normalization processing, wherein the prediction results generated by the output layer are rock stratum strength parameters and continuous mining equipment control amounts;
Screening from historical data to obtain continuous mining data under the condition of a hard rock layer, wherein the continuous mining data comprises, but is not limited to, pre-drilling technical parameters, mining environment state parameters, continuous mining equipment state parameters, cutting depth parameters, rock stratum strength parameters and continuous mining equipment control quantities which are not limited to, the pre-drilling technical parameters comprise, but are not limited to, hole depths, hole diameters, drilling distribution intervals, drilling energy consumption, vibration fracturing times and original rock stratum strength parameters acquired from geological exploration data, the mining environment state parameters comprise, but are not limited to, rock stratum working face geometry, the continuous mining equipment state parameters comprise, but are not limited to, continuous mining equipment positions, cutting mechanism linear speeds, cutting mechanism angular speeds and cutting mechanism output power, the rock stratum strength parameters comprise, but are not limited to, rock stratum average tensile strength after fracturing, and the continuous mining equipment control quantities comprise, but are not limited to, throttle control opening, braking grade, steering wheel rotation angle, cutting mechanism displacement and cutting mechanism rotation speed;
Training the initial deep neural network model by adopting the continuous mining data to obtain a trained deep neural network model;
s200, pre-drilling fracturing operation and rock stratum intensity parameter prediction, namely drilling test holes and vibration fracturing are carried out on a rock stratum working surface through pre-drilling fracturing equipment, the pre-drilling technical parameters in the pre-drilling fracturing operation are input into the trained deep neural network model, and the rock stratum intensity parameters after the pre-drilling fracturing operation is completed are obtained through calculation;
S300, determining a reasonable cutting depth control value [ d t ] by considering the most unfavorable working condition of the stress of the cutting pick of the continuous excavating equipment and the material durability of the cutting pick, and determining the reasonable cutting depth control value [ d t ] according to the fact that the peak value of the repeated stress of the cutting pick during operation is not larger than the fatigue strength of the cutting pick material, wherein the calculation of the cutting depth control value [ d t ] meets the following expression:
Wherein sigma rt is the average tensile strength of the stratum after fracturing, [ d t ] is a cutting depth control value, alpha is the half angle of the tip of the cutting pick, f is the friction angle between the cutting pick and the stratum, S is the sectional area of the most unfavorable position of the cutting pick, and [ sigma sw ] is the fatigue strength limit value of the cutting pick material;
And S400, monitoring and controlling continuous mining operation, namely in the continuous mining operation, carrying out real-time monitoring on the pre-drilling technical parameter, the rock stratum strength parameter after pre-drilling fracturing, the mining environment state parameter, the continuous mining equipment state parameter and the cutting depth parameter at different moments, inputting the real-time monitoring to the trained deep neural network model, calculating to obtain the continuous mining equipment operation strategies at different moments, and controlling the continuous mining operation parameters including the cutting depth.
Preferably, the training of the initial deep neural network model in step S100 specifically includes the following steps:
S110, training the rock stratum intensity parameters, namely after inputting the pre-drilling technical parameters in the continuous mining data into the initial deep neural network model, calculating and outputting the rock stratum intensity parameters at the current moment, measuring errors between a prediction result and a true value according to a first loss function, and guiding the learning process of the model until the first loss function meets a threshold value;
S120, analogizing the operation strategy of the continuous mining equipment, namely, inputting the state parameters of the mining environment, the state parameters of the continuous mining equipment, the cutting depth parameters and the rock stratum intensity parameters in the continuous mining data into the initial deep neural network model, and then calculating and outputting the control quantity of the continuous mining equipment at the current moment; calculating to obtain the state parameter of the mining environment, the state parameter of the continuous mining equipment and the cutting depth parameter at the next moment according to the control quantity of the continuous mining equipment at the current moment, and further calculating to obtain the control quantity of the continuous mining equipment at the next moment;
S130, training a continuous mining equipment operation strategy, namely calculating a second loss function evaluation value according to the continuous mining equipment operation strategy at the current moment, wherein the second loss function evaluation value comprises, but is not limited to, a difference evaluation value between the cutting depth at the current moment and the cutting depth control value, a cutting specific energy consumption evaluation value at the current moment, a cutting mechanism power evaluation value at the current moment and a mining working face flatness evaluation value, and carrying out parameter optimization updating on a depth neural network model at the current moment according to each second loss function evaluation value, and guiding the learning process of the model until the second loss function evaluation value meets a threshold value.
Preferably, in step S300, in order to ensure the flatness of the working surface after the mining operation, the cutting depth control value [ d t ] still needs to satisfy the following expression:
[dt]≥hd
Wherein h d is the hole depth of the test hole.
Preferably, the monitoring and control of the continuous mining operation in step S400 further comprises the steps of:
S410, measuring and controlling the cutting mechanism power, namely when the real-time monitoring knows that the cutting mechanism power exceeds a corresponding threshold value, controlling the control quantity of the continuous mining equipment to enable the continuous mining equipment to stop continuous mining operation, then increasing the weight of the cutting mechanism power evaluation value at the current moment, and according to the steps S100 to S300, training the deep neural network model again, predicting the rock stratum strength parameter and determining a reasonable cutting depth control value, and then carrying out continuous mining operation and monitoring and control thereof;
and S420, measuring and controlling the flatness of the mining working face, namely after the mining working face mining operation of a working cycle is completed, when real-time monitoring is carried out and the flatness of the mining working face exceeds a corresponding threshold value, controlling the control quantity of the continuous mining equipment to enable the continuous mining equipment to stop the continuous mining operation, then increasing the weight of the evaluation value of the flatness of the mining working face, and carrying out training on a deep neural network model, predicting the strength parameter of the rock stratum and determining a reasonable cutting depth control value again according to the steps S100 to S300, and then carrying out the continuous mining operation and monitoring and controlling thereof.
Preferably, the monitoring and control of the continuous mining operation in the step S400 are implemented by a measurement and control system, and the measurement and control system comprises an information acquisition module, an information transmission module, a data storage module, an information processing module and a feedback module;
The information acquisition module comprises a pre-drilling technical parameter acquisition unit, a mining environment state parameter acquisition unit, a continuous mining equipment state parameter acquisition unit and a cutting depth parameter acquisition unit, and is used for acquiring monitoring data during continuous mining operation through a sensor installed on the continuous mining equipment;
The information transmission module is used for establishing data connection and transmission between the modules;
the data storage module is used for storing historical data, the data acquired by the information acquisition module and the data output by the trained deep neural network model;
The information processing module comprises a data preprocessing unit, a deep neural network model unit and a judging unit, wherein the data preprocessing unit is used for preprocessing the original data stored by the data storage module to reduce data noise and redundancy;
The feedback module comprises an early warning unit and a control unit, wherein the early warning unit is used for controlling the alarm to send out early warning according to the judging result of the information processing module, and the control unit is used for controlling the continuous acquisition equipment according to the judging result of the information processing module.
Compared with the prior art, the method has the beneficial effects that the cutting depth automatic control method for the continuous mining of the hard rock layer based on deep learning is disclosed for the cutting depth automatic control during the mining operation of the open pit under the environment of the hard rock layer, the control method comprises the steps of establishing and training a deep neural network model, predicting pre-drilling fracturing operation and rock stratum intensity parameters, determining reasonable cutting depth control values and monitoring and controlling continuous mining operation, wherein the pre-drilling fracturing operation is used for improving the cutting performance of the hard rock layer, simultaneously predicting the rock stratum intensity parameters after the completion of the pre-drilling fracturing operation according to a deep learning algorithm, providing quantitative indexes for the fracturing effect of the pre-drilling fracturing operation of the hard rock layer, then determining reasonable cutting depth values according to the pre-drilling fracturing intensity parameters, facilitating the improvement of the mining efficiency of continuous mining equipment in the environment of the hard rock layer and the reduction of consumption of cutting tools, then calculating the operation strategy of the current continuous mining equipment according to the pre-fracturing rock stratum intensity parameters, real-time monitoring data and the trained deep neural network model, further realizing the control of the continuous mining equipment according to the real-time continuous mining equipment by real-time adjustment, and the continuous mining equipment is not smooth according to the real-time monitoring of the cutting depth control of the mining equipment or the real-time working quality of the mining equipment is realized, and the continuous mining equipment is not suitable for realizing the real-time monitoring of the quality or the mining equipment is controlled according to the real-time quality.
Drawings
FIG. 1 is a flow chart of the method for controlling the automatic cutting depth of continuous mining of hard rock layers based on deep learning;
FIG. 2 is a schematic diagram of a deep neural network model according to an embodiment of the present invention;
FIG. 3 is a schematic view of a continuous mining apparatus according to an embodiment of the present invention;
FIG. 4 is a schematic view of a cutting pick of a cutting mechanism according to one embodiment of the present invention;
FIG. 5 is a schematic diagram illustrating connection of a measurement and control system according to an embodiment of the present invention;
The device comprises the following components of a cutting mechanism 11-cutting mechanism 12-working surface, a pre-drilling hole 13-cutting pick 14-cutting pick, a 2-information acquisition module, a pre-drilling technical parameter acquisition unit 21-mining environment state parameter acquisition unit 22-continuous mining equipment state parameter acquisition unit 23-continuous mining equipment state parameter acquisition unit 24-cutting depth parameter acquisition unit 3-information transmission module 4-data storage module 5-information processing module 51-data preprocessing unit 52-deep neural network model unit 53-judgment unit 6-feedback module 61-early warning unit 62-control unit.
Detailed Description
Embodiments of the present invention will be described in more detail below with reference to fig. 1-5 and reference numerals, so that those skilled in the art can practice the present invention after studying the specification. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the invention.
The application discloses a depth learning-based automatic cutting depth control method for continuous hard rock layer mining, which is shown in fig. 1 to 5, and specifically comprises the following steps:
S100, establishing and training a deep neural network model, wherein the initial deep neural network model comprises an input layer (I 1, I 2, …I k), a hidden layer (h 1 [1], h2 [1] ,…hn [3]) and an output layer (O 1), the input layer is used for receiving data, the hidden layer is used for data processing and feature extraction, and the output layer is used for generating a prediction result;
the data received by the input layer can be expressed as (P 1, P2, …Pi) including, but not limited to, pre-drilling technical parameters, mining environment state parameters and continuous mining equipment state parameters at different moments after normalization processing, wherein the prediction results generated by the output layer are rock stratum strength parameters and continuous mining equipment control amounts;
Screening from historical data to obtain continuous mining data under the condition of a hard rock layer, wherein the continuous mining data comprises, but is not limited to, pre-drilling technical parameters, mining environment state parameters, continuous mining equipment state parameters, cutting depth parameters, rock stratum strength parameters and continuous mining equipment control quantities which are not limited to, the pre-drilling technical parameters comprise, but are not limited to, hole depths, hole diameters, drilling distribution intervals, drilling energy consumption, vibration fracturing times and original rock stratum strength parameters acquired from geological exploration data, the mining environment state parameters comprise, but are not limited to, rock stratum working face geometry, the continuous mining equipment state parameters comprise, but are not limited to, continuous mining equipment positions, cutting mechanism linear speeds, cutting mechanism angular speeds and cutting mechanism output power, the rock stratum strength parameters comprise, but are not limited to, rock stratum average tensile strength after fracturing, and the continuous mining equipment control quantities comprise, but are not limited to, throttle control opening, braking grade, steering wheel rotation angle, cutting mechanism displacement and cutting mechanism rotation speed;
training an initial deep neural network model by adopting the continuous mining data to obtain a trained deep neural network model, wherein the training of the initial deep neural network model specifically comprises the following steps:
S110, training the rock stratum intensity parameters, namely after inputting the pre-drilling technical parameters in the continuous mining data into the initial deep neural network model, calculating and outputting the rock stratum intensity parameters at the current moment, measuring errors between a prediction result and a true value according to a first loss function, and guiding the learning process of the model until the first loss function meets a threshold value;
S120, analogizing the operation strategy of the continuous mining equipment, namely, inputting the state parameters of the mining environment, the state parameters of the continuous mining equipment, the cutting depth parameters and the rock stratum intensity parameters in the continuous mining data into the initial deep neural network model, and then calculating and outputting the control quantity of the continuous mining equipment at the current moment; calculating to obtain the state parameter of the mining environment, the state parameter of the continuous mining equipment and the cutting depth parameter at the next moment according to the control quantity of the continuous mining equipment at the current moment, and further calculating to obtain the control quantity of the continuous mining equipment at the next moment;
S130, training a continuous mining equipment operation strategy, namely calculating a second loss function evaluation value according to the continuous mining equipment operation strategy at the current moment, wherein the second loss function evaluation value comprises, but is not limited to, a difference evaluation value between the cutting depth at the current moment and the cutting depth control value, a cutting specific energy consumption evaluation value at the current moment, a cutting mechanism power evaluation value at the current moment and a mining working face flatness evaluation value;
s200, pre-drilling fracturing operation and rock stratum intensity parameter prediction, namely drilling test holes and vibration fracturing are carried out on a rock stratum working surface through pre-drilling fracturing equipment, the pre-drilling technical parameters in the pre-drilling fracturing operation are input into the trained deep neural network model, and the rock stratum intensity parameters after the pre-drilling fracturing operation is completed are obtained through calculation;
S300, determining a reasonable cutting depth control value [ d t ] by considering the most unfavorable working condition of the stress of the cutting pick of the continuous excavating equipment and the material durability of the cutting pick, and determining the reasonable cutting depth control value [ d t ] according to the fact that the peak value of the repeated stress of the cutting pick during operation is not larger than the fatigue strength of the cutting pick material, wherein the calculation of the cutting depth control value [ d t ] meets the following expression:
(1)
Wherein sigma rt is the average tensile strength of the stratum after fracturing, [ d t ] is a cutting depth control value, alpha is the half angle of the tip of the cutting pick, f is the friction angle between the cutting pick and the stratum, S is the sectional area of the most unfavorable position of the cutting pick, and [ sigma sw ] is the fatigue strength limit value of the cutting pick material;
In addition, in order to ensure the flatness of the working face after the mining operation, the cutting depth control value [ d t ] still needs to satisfy the following expression:
[dt]≥hd(2)
Wherein h d is the hole depth of the test hole;
In specific implementation, under typical working conditions, the average tensile strength sigma rt of the stratum after fracturing is 10MPa, the half angle alpha of the tip part of the cutting pick is 17.5 degrees, the friction angle f between the cutting pick and the stratum is 11.3 degrees, the sectional area S at the position where the cutting pick is at the most unfavorable is 706.5mm 2, the fatigue strength limit value [ sigma sw ] of the cutting pick material is 500 MPa, and the cutting depth control value [ d t ] is calculated as follows according to the formula (1):
(3)
the hole depth h d of the test hole is 0.1m, and the value range of the cutting depth control value d t is 0.1m less than or equal to d t less than or equal to 0.127m in combination with the formula (2) and the formula (3);
S400, monitoring and controlling continuous mining operation:
In the continuous mining operation, carrying out real-time monitoring on the pre-drilling technical parameters, the mining environment state parameters, the continuous mining equipment state parameters and the cutting depth parameters at different moments, inputting the parameters into the trained deep neural network model, calculating to obtain the operation strategies of the continuous mining equipment at different moments, and controlling the continuous mining operation to realize the control of the continuous mining operation parameters including the cutting depth, wherein the monitoring and the control of the continuous mining operation specifically comprise the following steps:
S410, measuring and controlling the cutting mechanism power, namely when the real-time monitoring knows that the cutting mechanism power exceeds a corresponding threshold value, controlling the control quantity of the continuous mining equipment to enable the continuous mining equipment to stop continuous mining operation, then increasing the weight of the cutting mechanism power evaluation value at the current moment, and according to the steps S100 to S300, training the deep neural network model again, predicting the rock stratum strength parameter and determining a reasonable cutting depth control value, and then carrying out continuous mining operation and monitoring and control thereof;
and S420, measuring and controlling the flatness of the mining working face, namely after the mining working face mining operation of a working cycle is completed, when real-time monitoring is carried out and the flatness of the mining working face exceeds a corresponding threshold value, controlling the control quantity of the continuous mining equipment to enable the continuous mining equipment to stop the continuous mining operation, then increasing the weight of the evaluation value of the flatness of the mining working face, and carrying out training on a deep neural network model, predicting the strength parameter of the rock stratum and determining a reasonable cutting depth control value again according to the steps S100 to S300, and then carrying out the continuous mining operation and monitoring and controlling thereof.
In specific implementation, the monitoring and control of the continuous mining operation in the step S400 are realized by a measurement and control system, and the measurement and control system comprises an information acquisition module 2, an information transmission module 3, a data storage module 4, an information processing module 5 and a feedback module 6;
the information acquisition module 2 comprises a pre-drilling technical parameter acquisition unit 21, a mining environment state parameter acquisition unit 22, a continuous mining equipment state parameter acquisition unit 23 and a cutting depth parameter acquisition unit 24, and is used for acquiring monitoring data during continuous mining operation through a sensor installed in the continuous mining equipment;
the information transmission module 3 is used for establishing data connection and transmission between the modules;
The data storage module 4 is used for storing historical data, the data acquired by the information acquisition module 2 and the data output by the trained deep neural network model;
The information processing module 5 comprises a data preprocessing unit 51, a deep neural network model unit 52 and a judging unit 53, wherein the data preprocessing unit 51 is used for preprocessing the original data stored by the data storage module 4 to reduce data noise and redundancy, the deep neural network model unit 52 is used for realizing the function of a deep neural network model, and the judging unit 53 is used for judging whether the data meets the threshold requirement or not;
The feedback module 6 comprises an early warning unit 61 and a control unit 62, wherein the early warning unit 61 is used for controlling an alarm to send out early warning according to the judging result of the information processing module 5, and the control unit 62 is used for controlling continuous acquisition equipment according to the judging result of the information processing module 5.
Therefore, the depth learning-based automatic cutting depth control method for continuous hard rock layer mining can improve the cutting performance of the hard rock layer by pre-drilling fracturing operation, predict the rock layer strength parameters after the pre-drilling fracturing operation is completed according to a depth learning algorithm, determine reasonable cutting depth values, improve the mining efficiency of continuous mining equipment in a hard rock layer environment, reduce the consumption of cutting tools, calculate the current continuous mining equipment operation strategy in real time by a depth neural network model, further realize real-time control of cutting depth, and be beneficial to improving the control precision, safety and automation of the continuous mining equipment.
The foregoing is a description of one or more embodiments of the invention, which are specific and detailed, but are not to be construed as limiting the scope of the invention. It should be noted that it will be apparent to those skilled in the art that several variations and modifications can be made without departing from the spirit of the invention, which are all within the scope of the invention. Accordingly, the scope of protection of the present invention is to be determined by the appended claims.
Claims (6)
1. The automatic cutting depth control method for continuous excavation of the hard rock layer based on deep learning is characterized by comprising the following steps of:
S100, establishing and training a deep neural network model, namely establishing an initial deep neural network model which comprises an input layer, a hidden layer and an output layer;
The data received by the input layer comprises but is not limited to pre-drilling technical parameters, mining environment state parameters and continuous mining equipment state parameters at different moments after normalization processing, and the prediction results generated by the output layer comprise rock stratum strength parameters and continuous mining equipment control amounts, wherein the rock stratum strength parameters comprise but are not limited to average tensile strength of the rock stratum after fracturing;
Screening from the historical data continuous mining data under the condition of the hard rock layer, wherein the continuous mining data comprises, but is not limited to, pre-drilling technical parameters, mining environment state parameters, continuous mining equipment state parameters, cutting depth parameters, rock layer strength parameters and continuous mining equipment control quantity at different moments;
Training the initial deep neural network model by adopting the continuous mining data to obtain a trained deep neural network model;
s200, pre-drilling fracturing operation and rock stratum intensity parameter prediction, namely drilling test holes and vibration fracturing are carried out on a rock stratum working surface through pre-drilling fracturing equipment, the pre-drilling technical parameters in the pre-drilling fracturing operation are input into the trained deep neural network model, and the rock stratum intensity parameters after the pre-drilling fracturing operation is completed are obtained through calculation;
S300, determining a reasonable cutting depth control value, wherein the calculation of the cutting depth control value d t meets the following expression:
Wherein sigma rt is the average tensile strength of the stratum after fracturing, [ d t ] is a cutting depth control value, alpha is the half angle of the tip of the cutting pick, f is the friction angle between the cutting pick and the stratum, S is the sectional area of the most unfavorable position of the cutting pick, and [ sigma sw ] is the fatigue strength limit value of the cutting pick material;
And S400, monitoring and controlling continuous mining operation, namely in the continuous mining operation, carrying out real-time monitoring on the pre-drilling technical parameter, the mining environment state parameter, the continuous mining equipment state parameter and the cutting depth parameter at different moments, inputting the real-time monitoring to the trained deep neural network model, calculating to obtain the continuous mining equipment operation strategies at different moments, and controlling the continuous mining operation.
2. The depth learning-based automatic cutting depth control method for continuous hard rock layer mining according to claim 1, wherein the step S100 includes the steps of:
S110, training the rock stratum intensity parameters, namely after inputting the pre-drilling technical parameters in the continuous mining data into the initial deep neural network model, calculating and outputting the rock stratum intensity parameters at the current moment, measuring errors between a prediction result and a true value according to a first loss function, and guiding the learning process of the model until the first loss function meets a threshold value;
S120, analogizing the operation strategy of the continuous mining equipment, namely, inputting the state parameters of the mining environment, the state parameters of the continuous mining equipment, the cutting depth parameters and the rock stratum intensity parameters in the continuous mining data into the initial deep neural network model, and then calculating and outputting the control quantity of the continuous mining equipment at the current moment; calculating to obtain the state parameter of the mining environment, the state parameter of the continuous mining equipment and the cutting depth parameter at the next moment according to the control quantity of the continuous mining equipment at the current moment, and further calculating to obtain the control quantity of the continuous mining equipment at the next moment;
S130, training a continuous mining equipment operation strategy, namely calculating a second loss function evaluation value according to the continuous mining equipment operation strategy at the current moment, wherein the second loss function evaluation value comprises, but is not limited to, a difference evaluation value between the cutting depth at the current moment and the cutting depth control value, a cutting specific energy consumption evaluation value at the current moment, a cutting mechanism power evaluation value at the current moment and a mining working face flatness evaluation value, and carrying out parameter optimization updating on a depth neural network model at the current moment according to each second loss function evaluation value, and guiding the learning process of the model until the second loss function evaluation value meets a threshold value.
3. The depth learning-based automatic cutting depth control method for continuous hard rock layer mining according to claim 1, wherein the cutting depth control value [ d t ] in the step S300 still needs to satisfy the following expression:
[dt]≥hd
Wherein h d is the hole depth of the test hole.
4. The depth learning-based automatic cutting depth control method for continuous hard rock layer mining according to claim 1, wherein the step S400 includes the steps of:
S410, measuring and controlling the cutting mechanism power, namely when the real-time monitoring knows that the cutting mechanism power exceeds a corresponding threshold value, controlling the control quantity of the continuous mining equipment to enable the continuous mining equipment to stop continuous mining operation, then increasing the weight of the cutting mechanism power evaluation value at the current moment, and according to the steps S100 to S300, training the deep neural network model again, predicting the rock stratum strength parameter and determining a reasonable cutting depth control value, and then carrying out continuous mining operation and monitoring and control thereof;
and S420, measuring and controlling the flatness of the mining working face, namely after the mining working face mining operation of a working cycle is completed, when real-time monitoring is carried out and the flatness of the mining working face exceeds a corresponding threshold value, controlling the control quantity of the continuous mining equipment to enable the continuous mining equipment to stop the continuous mining operation, then increasing the weight of the evaluation value of the flatness of the mining working face, and carrying out training on a deep neural network model, predicting the strength parameter of the rock stratum and determining a reasonable cutting depth control value again according to the steps S100 to S300, and then carrying out the continuous mining operation and monitoring and controlling thereof.
5. The depth learning based hard rock continuous mining automatic cutting depth control method according to claim 1, wherein in step S100, the pre-drilling technological parameters include, but are not limited to, hole depth, hole diameter, drill hole distribution interval, drill energy consumption, vibration fracturing times and original rock strength parameters obtained from geological survey data, the mining environment state parameters include, but are not limited to, rock working face geometry, the continuous mining equipment state parameters include, but are not limited to, continuous mining equipment position, cutting mechanism linear velocity, cutting mechanism angular velocity, cutting mechanism output power, and the continuous mining equipment control quantities include, but are not limited to, throttle control opening, braking grade, steering wheel angle, cutting mechanism displacement, cutting mechanism rotation speed.
6. The depth learning-based automatic cutting depth control method for continuous mining of hard rock layer according to claim 1, wherein the monitoring and control of the continuous mining operation in step S400 are realized by a measurement and control system, and the measurement and control system comprises an information acquisition module, an information transmission module, a data storage module, an information processing module and a feedback module;
the information acquisition module comprises a pre-drilling technical parameter acquisition unit, a mining environment state parameter acquisition unit, a continuous mining equipment state parameter acquisition unit and a cutting depth parameter acquisition unit;
The information transmission module is used for establishing data connection and transmission between the modules;
the data storage module is used for storing historical data, the data acquired by the information acquisition module and the data output by the trained deep neural network model;
The information processing module comprises a data preprocessing unit, a deep neural network model unit and a judging unit, wherein the data preprocessing unit is used for preprocessing the original data stored by the data storage module to reduce data noise and redundancy;
The feedback module comprises an early warning unit and a control unit, wherein the early warning unit is used for controlling the alarm to send out early warning according to the judging result of the information processing module, and the control unit is used for controlling the continuous acquisition equipment according to the judging result of the information processing module.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202411884148.6A CN119333134B (en) | 2024-12-20 | 2024-12-20 | Automatic cutting depth control method for continuous excavation of hard rock layer based on deep learning |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202411884148.6A CN119333134B (en) | 2024-12-20 | 2024-12-20 | Automatic cutting depth control method for continuous excavation of hard rock layer based on deep learning |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN119333134A CN119333134A (en) | 2025-01-21 |
| CN119333134B true CN119333134B (en) | 2025-02-18 |
Family
ID=94265395
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202411884148.6A Active CN119333134B (en) | 2024-12-20 | 2024-12-20 | Automatic cutting depth control method for continuous excavation of hard rock layer based on deep learning |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN119333134B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN119616481B (en) * | 2025-02-14 | 2025-04-25 | 广州山河智能机器股份有限公司 | Heterogeneous hard rock stratum continuous mining and cutting control method based on neural network |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111915560A (en) * | 2020-06-30 | 2020-11-10 | 西安理工大学 | Determination method of rock strength parameters based on deep convolutional neural network |
| CN115017833A (en) * | 2022-08-09 | 2022-09-06 | 中国科学院武汉岩土力学研究所 | In-situ stress calculation method of high in-situ stress soft rock mass based on deep neural network |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| GB2581550B (en) * | 2017-05-15 | 2022-01-05 | Landmark Graphics Corp | Method and system to drill a wellbore and identify drill bit failure by deconvoluting sensor data |
| US12044660B2 (en) * | 2019-09-06 | 2024-07-23 | Shandong University | Predicting system and method for uniaxial compressive strength of rock |
| KR20230127511A (en) * | 2022-02-25 | 2023-09-01 | 연세대학교 산학협력단 | Real-time evaluation system and method of rock state based on tunnel face image by using deep learning |
-
2024
- 2024-12-20 CN CN202411884148.6A patent/CN119333134B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111915560A (en) * | 2020-06-30 | 2020-11-10 | 西安理工大学 | Determination method of rock strength parameters based on deep convolutional neural network |
| CN115017833A (en) * | 2022-08-09 | 2022-09-06 | 中国科学院武汉岩土力学研究所 | In-situ stress calculation method of high in-situ stress soft rock mass based on deep neural network |
Also Published As
| Publication number | Publication date |
|---|---|
| CN119333134A (en) | 2025-01-21 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN119333134B (en) | Automatic cutting depth control method for continuous excavation of hard rock layer based on deep learning | |
| CN109685378B (en) | TBM construction surrounding rock digchability grading method based on data mining | |
| CN112182973B (en) | Optimization method of TBM operating parameters considering cutter head vibration and slag geometric information | |
| CN113586028B (en) | Intelligent monitoring system of counter bore cutter head of anti-well drilling machine based on digital twin | |
| CN111722270A (en) | Short-distance advanced geological prediction method based on while-drilling monitoring equipment | |
| CN114372319B (en) | A rock cuttability evaluation method based on mining parameters and/or drilling parameters, rock breaking equipment and rock breaking system | |
| CN108363873A (en) | A kind of lithology discrimination method based on mining-drilling machine | |
| Basarir et al. | The use of soft computing methods for the prediction of rock properties based on measurement while drilling data | |
| CN113505911A (en) | Cutter life prediction system based on automatic cruise and prediction method thereof | |
| CN119572136B (en) | Anchor rod drill carriage system and method capable of rapidly detecting hardness of rock mass | |
| CN115773127A (en) | Intelligent decision-making method, system, equipment and medium for slurry balance shield | |
| CN114526054A (en) | Real-time recognition system and method for underground working condition of drill bit and related equipment | |
| CN115387777B (en) | Feeding and rotation control method of hydraulic tunnel drilling machine based on coal rock sensing | |
| CN113158561A (en) | TBM operation parameter optimization method and system suitable for various rock mass conditions | |
| CN111622752A (en) | Acceleration evaluation method of three-dimensional shaft system | |
| CN111677493A (en) | Drilling data processing method | |
| CN118757150A (en) | A deep hard rock mine intelligent mechanical mining method using hydraulic rock fracturing | |
| CN116975623B (en) | Method, device and medium for predicting large deformation grade in tunnel construction stage by drilling and blasting method | |
| CN115075799B (en) | Engine rotating speed control method of directional drilling machine for coal mine | |
| CN118521421A (en) | Drilling engineering drawing board generation method and device | |
| CN116484559A (en) | Dynamic monitoring method and system for PDC drill bit abrasion state while drilling | |
| Hai et al. | Multi-element drilling parameter optimization based on drillstring dynamics and ROP model | |
| CN119825330B (en) | Self-adaptive control method and control system for drilling and anchoring of airborne drill boom | |
| CN119616481B (en) | Heterogeneous hard rock stratum continuous mining and cutting control method based on neural network | |
| CN117404099B (en) | TBM tunneling speed intelligent control method based on XGBoost algorithm |
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 |