CN115387777B - Feeding and rotation control method of hydraulic tunnel drilling machine based on coal rock sensing - Google Patents
Feeding and rotation control method of hydraulic tunnel drilling machine based on coal rock sensing Download PDFInfo
- Publication number
- CN115387777B CN115387777B CN202210950365.5A CN202210950365A CN115387777B CN 115387777 B CN115387777 B CN 115387777B CN 202210950365 A CN202210950365 A CN 202210950365A CN 115387777 B CN115387777 B CN 115387777B
- Authority
- CN
- China
- Prior art keywords
- drilling
- speed
- signal
- recommended
- coal
- 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
- 238000005553 drilling Methods 0.000 title claims abstract description 227
- 239000003245 coal Substances 0.000 title claims abstract description 93
- 238000000034 method Methods 0.000 title claims abstract description 41
- 239000011435 rock Substances 0.000 title claims abstract description 14
- 230000008569 process Effects 0.000 claims abstract description 21
- 238000007781 pre-processing Methods 0.000 claims abstract description 5
- 238000012216 screening Methods 0.000 claims abstract description 3
- 239000013598 vector Substances 0.000 claims description 28
- 101000609957 Homo sapiens PTB-containing, cubilin and LRP1-interacting protein Proteins 0.000 claims description 22
- 101150109471 PID2 gene Proteins 0.000 claims description 22
- 102100039157 PTB-containing, cubilin and LRP1-interacting protein Human genes 0.000 claims description 22
- 238000000354 decomposition reaction Methods 0.000 claims description 18
- 238000013528 artificial neural network Methods 0.000 claims description 14
- 238000001914 filtration Methods 0.000 claims description 10
- 238000000605 extraction Methods 0.000 claims description 5
- 238000010219 correlation analysis Methods 0.000 claims description 4
- 238000013507 mapping Methods 0.000 claims description 4
- 238000000926 separation method Methods 0.000 claims description 4
- 238000012549 training Methods 0.000 claims description 4
- 238000005259 measurement Methods 0.000 claims description 3
- 101100190462 Caenorhabditis elegans pid-1 gene Proteins 0.000 claims description 2
- 101100190464 Caenorhabditis elegans pid-2 gene Proteins 0.000 claims description 2
- 230000007774 longterm Effects 0.000 claims description 2
- 230000008859 change Effects 0.000 description 9
- 230000035515 penetration Effects 0.000 description 8
- 230000006870 function Effects 0.000 description 6
- 238000010276 construction Methods 0.000 description 3
- 238000001514 detection method Methods 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 230000003993 interaction Effects 0.000 description 3
- 230000009471 action Effects 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 2
- 238000010220 Pearson correlation analysis Methods 0.000 description 1
- 230000002159 abnormal effect Effects 0.000 description 1
- 230000004913 activation Effects 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 230000015572 biosynthetic process Effects 0.000 description 1
- 230000008878 coupling Effects 0.000 description 1
- 238000010168 coupling process Methods 0.000 description 1
- 238000005859 coupling reaction Methods 0.000 description 1
- 238000013016 damping Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000005755 formation reaction Methods 0.000 description 1
- 230000035699 permeability Effects 0.000 description 1
- 230000002265 prevention Effects 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 238000004088 simulation Methods 0.000 description 1
- 239000002893 slag Substances 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
- 230000005641 tunneling Effects 0.000 description 1
Classifications
-
- 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
- E21B44/02—Automatic control of the tool feed
-
- 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
Landscapes
- Life Sciences & Earth Sciences (AREA)
- Engineering & Computer Science (AREA)
- Geology (AREA)
- Mining & Mineral Resources (AREA)
- Physics & Mathematics (AREA)
- Environmental & Geological Engineering (AREA)
- Fluid Mechanics (AREA)
- General Life Sciences & Earth Sciences (AREA)
- Geochemistry & Mineralogy (AREA)
- Earth Drilling (AREA)
Abstract
The invention provides a feeding and rotating control method of a hydraulic tunnel drilling machine based on coal and rock sensing, which comprises the following steps: step one, obtaining characteristics; step two, screening the characteristics; step three, constructing a coal bed hardness identification model; step four, acquiring a recommended drilling speed and a recommended rotating speed; step five, preprocessing an input signal; step six, building a feed rotation control system; step seven, constant torque control; step eight, constant drilling rate control; step nine, fine adjustment control of drilling speed; the method disclosed by the invention can break through the excessive dependence of the traditional drilling process on manual experience, obtain the optimal drilling speed and the optimal rotating speed under the current drilling working condition through the coal bed hardness identification module and the optimal drilling speed and rotating speed recommendation module, realize the control of the drilling speed of the drilling machine on the basis of constant torque control, and finely tune the recommended drilling speed by utilizing the rotating speed, so that the efficiency of the drilling process can be effectively improved, and the risk of the drilling process is reduced.
Description
Technical Field
The invention belongs to the technical field of underground tunnel drilling of coal mines, relates to feeding rotation control of a hydraulic tunnel drilling machine, and particularly relates to a feeding rotation control method of the hydraulic tunnel drilling machine based on coal rock sensing.
Background
The hydraulic tunnel drilling machine is widely used for underground coal mine gas extraction, rock burst prevention, water drainage by roof and floor detection, advanced detection of tunneling tunnels, hidden disaster-causing factor detection and the like. However, in the drilling process of the hydraulic tunnel drilling machine, the geomechanical environment of the coal seam is complex, and nonlinear, strong coupling and strong interference characteristics such as faults, collapse columns, structural belts, geological abnormal bodies and the like are outstanding, so that the feeding resistance of a feeding system of the hydraulic tunnel drilling machine and the load torque of a rotary system are complex and various. The feeding and rotating system of the drilling machine is required to be capable of adapting to the change of the coal seam, otherwise, the drilling efficiency of the drilling machine is reduced, the working period is influenced, and meanwhile, accidents such as drill sticking and drill breaking can be caused even due to improper drilling pressure and rotation speed.
At present, the drilling pressure and the rotating speed of the hydraulic tunnel drilling machine cannot be automatically adjusted according to working conditions, construction staff are required to manually adjust according to observed main parameters such as drilling pressure, revolving pressure, rotating speed, slag return, water return and the like, various different working condition parameters and control parameters cannot be comprehensively collected in real time, various data are difficult to judge and decide timely and accurately, the drilling parameters are completely adjusted depending on experience of the construction staff in the drilling construction process, and development of underground drilling technology of a coal mine is severely restricted. Therefore, the intelligent sensing and control technology for the change of the coal seam by researching the bit pressure and the rotating speed of the hydraulic tunnel drilling machine has important practical significance and application value for realizing the intelligent development of underground mechanical changing and automatic subtracting of the coal mine.
Disclosure of Invention
Aiming at the defects existing in the prior art, the invention aims to provide a feeding and rotating control method of a hydraulic tunnel drilling machine based on coal and rock sensing, which solves the technical problems that the prior art excessively depends on manual experience and cannot intelligently sense and adaptively control drilling working conditions.
In order to solve the technical problems, the invention adopts the following technical scheme:
The technical proposal adopted by the invention has the overall technical conception that: according to the working parameters of a drilling machine in the drilling process, analyzing the correlation between the hardness of the coal bed and the parameters in the drilling process, and selecting the drilling pressure and the rotation pressure as the input parameters of a coal bed hardness identification model to be built; performing feature extraction on drilling process data by wavelet packet decomposition to obtain sample data and a test set, and outputting by taking the prior coal seam hardness as a model; and training and verifying the coal bed hardness recognition model by using a BP (Back Propagation) neural network to obtain a final coal bed hardness recognition model. And obtaining recommended set values of the drilling speed and the rotating speed under the current working condition according to the coal bed hardness f. The feeding rotation control system of the drilling machine realizes constant rotation pressure control (constant rotation torque control) of the drilling machine by adjusting the bit pressure under the action of the PID1, and considers the bit rate to adjust the set torque through the PID2 on the basis of the constant rotation pressure control (constant rotation torque control) to realize the control of the bit rate. And meanwhile, the recommended drilling speed is finely adjusted by utilizing the rotation speed, so that the safety of the drilling machine is ensured.
Compared with the prior art, the invention has the following technical effects:
The method disclosed by the invention can break through the excessive dependence of the traditional drilling process on the manual experience, obtain the optimal drilling speed and the optimal rotating speed under the current drilling working condition through the coal bed hardness identification module and the optimal drilling speed and rotating speed recommendation module, realize the control of the drilling speed of the drilling machine on the basis of constant torque control, effectively improve the efficiency of the drilling process and reduce the risk of the drilling process.
The method comprises the steps of coal bed hardness identification, optimal rotation speed, drilling speed recommendation, drilling speed fine adjustment and drilling speed control based on torque control, and can lay a good foundation for intelligent control of feeding and rotation of the drilling machine.
Drawings
Fig. 1 is a torque variation curve under constant torque control.
Fig. 2 is a graph of rotational speed variation under constant torque control.
Fig. 3 is a graph of the rate of penetration under constant torque control.
Fig. 4 is a graph of feed force variation under constant torque control.
Fig. 5 is a graph of weight on bit variation under constant torque control.
Fig. 6 is a torque variation curve under constant rate of penetration control.
Fig. 7 is a graph of rotational speed variation under constant rate of penetration control.
Fig. 8 is a graph of the rate of penetration under constant rate of penetration control.
Fig. 9 is a plot of feed force variation under constant rate of penetration control.
Fig. 10 is a graph of weight on bit variation under constant rate of penetration control.
Fig. 11 is a torque variation curve at a set drilling rate adjustment.
Fig. 12 is a graph showing the rotational speed change at the set drilling rate adjustment.
Fig. 13 is a graph of change in the drilling rate at the set drilling rate adjustment.
Fig. 14 is a feed force variation curve under a set drilling rate adjustment.
Fig. 15 is a graph of weight on bit change at a set rate of penetration adjustment.
Fig. 16 is a block diagram of the feed swing control system.
Fig. 17 is a feature extraction flow chart employing wavelet packet decomposition.
The following examples illustrate the invention in further detail.
Detailed Description
It should be noted that all algorithms, modules and devices in the present invention are all known in the art unless specifically described otherwise.
The following specific embodiments of the present application are provided, and it should be noted that the present application is not limited to the following specific embodiments, and all equivalent changes made on the basis of the technical scheme of the present application fall within the protection scope of the present application.
Examples:
The embodiment provides a feeding and rotation control method of a hydraulic tunnel drilling machine based on coal and rock sensing, which comprises the following steps:
step one, feature acquisition:
The working condition in the drilling process is complex, the frequency of the rotary pressure and the drilling pressure signals acquired by the sensor is not concentrated, the signals are greatly disturbed by the coal bed, the fluctuation of the signals is large, the signals are difficult to fit by a determined function, and the coal bed hardness under the current working condition is difficult to judge from the signals, so that the state parameters of the drilling machine are extracted by wavelet packet transformation.
And selecting the drilling pressure and the rotation pressure of the drilling machine as input signals for identifying the hardness of the coal seam, and decomposing the drilling pressure and the rotation pressure by adopting wavelet packet decomposition to obtain feature vectors.
Specifically, as shown in fig. 17, the wavelet packet decomposition adopts three-level wavelet packet decomposition, and the mathematical expression of the decomposed signal reconstruction function is:
S3＝S31+S32+S33+S34+S35+S36+S37++S38
Wherein:
s 3 is a signal reconstruction function;
S 3j is a j-th frequency band signal reconstruction function after three-level wavelet packet decomposition, j=1, 2, …;
The energy E 3j of the reconstructed signal is:
E3j＝∫|S3j(t)|2dt
Wherein:
e 3j is the energy of the reconstructed signal;
t is time.
Taking the energy E 3j of the reconstructed signal as the characteristic of each frequency band signal, and carrying out characteristic extraction on the weight on bit and the rotation pressure to obtain a characteristic vector E as follows:
E＝[E31j,E32j]
Wherein:
E 31j is the j-th frequency band signal characteristic vector after weight on bit decomposition;
E 32j is the characteristic vector of the j-th frequency band signal after the revolving pressure decomposition;
j＝1，2，…8。
step two, feature screening:
not every frequency band information can reflect the hardness of the coal seam, and the characteristic components need to be screened.
Carrying out correlation analysis on each component in the feature vector E obtained in the step one and the coal bed hardness to obtain a strong correlation feature vector composed of components with strong correlation with the coal bed hardness; and normalizing the strong correlation feature vector to obtain a normalized feature vector.
The specific process of correlation analysis uses a conventional correlation analysis method, for example, a pearson correlation analysis method.
The expression of the strong correlation feature vector is as follows:
E'＝[E'31m,E'32n]
Wherein:
E' is a strong correlation feature vector;
E' 31m is the m-th frequency band signal strong correlation characteristic vector after weight on bit decomposition;
E' 32n rotates the strong correlation eigenvector of the nth frequency band signal after pressure decomposition.
The normalized formula is as follows:
Wherein:
e' is the normalized feature vector.
Step three, constructing a coal bed hardness identification model:
The BP neural network structure is divided into an input layer, a hidden layer and an output layer, wherein the activation functions of the hidden layer and the output layer are sigmod functions:
The input layer to hidden layer expression can be derived as follows:
fk＝out([ωk,1,ωk,2,…,ωk,m,ωk,m+1,…ωk,m+n]*E'T+bk)
The expression from the hidden layer to the output layer is:
f＝out([ω1,ω2,…,ωk]*[f1,f2,…,fk]T+b)
Wherein ω k,j, k is the node number of the hidden layer, j= … m+n is the weight of the hidden layer; b k is the threshold of the hidden layer; ω i, i= … k is the weight of the output layer, and b is the threshold of the output layer.
Based on the BP neural network, the normalized feature vector is used as the input quantity of the BP neural network, the BP neural network is trained, and the coal bed hardness recognition model is obtained after training.
In the coal bed hardness identification model, the value range of the coal bed hardness is [0.5, 10], the output range of the BP neural network is [0,1], and the BP neural network is mapped into the coal bed hardness through linear mapping; the linear mapping formula is as follows: y=9.5×x+0.5, where x is the output of the BP neural network; and y is the hardness of the coal bed.
For formations that may be present in the coal seam with a hardness greater than 10, the present invention defaults to 10.
Fourth, obtaining a recommended drilling speed and a recommended rotating speed:
within a certain range, the higher the hardness of the coal bed, the lower the drilling speed is required, and the lower the rotating speed is.
Taking the normalized feature vector obtained in the second step as the input quantity of the coal bed hardness identification model built in the third step, obtaining the coal bed hardness through the coal bed hardness identification model, and obtaining the recommended drilling speed and the recommended rotating speed under the current working condition according to the coal bed hardness as follows:
Wherein:
θ is the recommended rotation speed under the current working condition;
V is the recommended drilling speed under the current working condition;
D is the effective diameter of the drilling tool;
f is the hardness of the coal rock;
k 1,k2 is a scaling factor;
and theta 0,V0 is the average value of the rotating speed and the drilling speed of the drilling machine during long-term working.
Step five, preprocessing an input signal:
In the controller, the feedback signal of the PID1 is a rotary differential pressure, the feedback signal of the PID2 is a drilling rate, and due to the complex environment of the coal seam, a large number of burrs and spikes exist, which can cause frequent changes of the output of the controller, so that the input signal needs to be filtered.
Preprocessing the recommended drilling speed and the recommended rotating speed obtained in the fourth step to obtain the preprocessed recommended drilling speed and the preprocessed recommended rotating speed; the specific process of pretreatment is as follows: firstly, carrying out amplitude limiting filtering to eliminate peaks in signals; and then recursive average filtering is carried out, so that the fluctuation amplitude of the input signal is reduced, and the stability of the system is improved.
The formula of the clipping filtering is as follows:
The formula of the recursive average filtering is as follows:
Wherein:
out (n) is the amplitude limiting filtering result of the drilling speed or the rotating speed;
ErrorMax is the maximum amount of fluctuation allowed by the feed slewing system.
Step six, building a feed rotation control system:
During the drilling process of a drilling machine, the Weight On Bit (WOB) of the drill bit is mainly generated due to the coal seam resistance, and the cohesive damping model describes the interaction between the drill bit and the coal seam in the axial direction, which can be expressed as follows:
Wherein:
F d is the interaction force between the drill bit and the coal seam;
Is the drilling speed of the drill bit;
k r is the permeability coefficient of resistance (PRC) of the coal seam, which depends on the hardness of the coal seam.
The rotation torque of the drilling machine is generated by the interaction of the drill bit and the coal bed in the rotation direction due to the fact that the drill bit rotates to cut the coal bed in the drilling process, and the karnopp model describes the relation between the rotating speed, the drilling pressure and the rotation resistance, and is specifically expressed as follows:
Where T is the rotational torque, R b is the bit diameter, and μ sb,μcb is the static and sliding coefficients of friction of the bit, depending on the coal bed hardness.
Through karnopp model and drilling technology, it is known that the rotation torque of the rotation system reflects the drilling load, meanwhile, the change of the torque can be realized by changing the weight on bit, the rotation torque of the drilling machine is kept constant, and the drilling machine can work at rated load.
Based on the analysis, the invention firstly designs the PID1 to realize constant torque control by adjusting the bit pressure; when the rotation torque is relatively large, the bit pressure is properly reduced, accidents such as drill sticking and the like caused by overlarge drilling load are prevented, and when the rotation torque is relatively small, the bit pressure can be properly increased, and the drilling speed is improved. Based on the obtained optimal torque set point, the system is enabled to maintain an optimal drilling load at all times, enabling the system to operate at maximum efficiency on a safe basis.
The rotation torque is not measurable, and according to the working principle of the hydraulic motor, when the rotating speed is stable, the rotation pressure difference is proportional to the load torque, so that the constant torque control of the drilling machine can be realized by realizing the constant rotation pressure difference. Therefore, the set value of the constant torque controller is the revolution pressure difference corresponding to the target torque, the feedback quantity is the revolution pressure difference, the controller adopts an integral separation PI controller, and the output of the controller
out＝kp*error+ε(error)ki*error
In the formula, error set is an error integral upper limit set according to the performance of the drilling machine, and an integral separation method is adopted, so that an excessive integral term in a constant torque control system can be effectively avoided, and the influence on the system adjustment time is reduced.
As shown in fig. 16, the feed swing control system comprises a PID1, a PID2 and a drilling rate fine adjustment module; the PID1 and the PID2 adopt integral separation PI controllers; the drilling speed fine adjustment module is as follows:
Wherein:
FEEDSPEED set is the set drilling rate;
FEEDSPEED 0 is the recommended drilling rate;
Speed 0 is a threshold at which the rotational Speed can be reduced;
Rspeed now is a measurement of rotational speed;
rspeed set is a set value of the rotation speed;
k is an integral coefficient;
1/s is integral operation;
epsilon is the start signal.
The input end of the PID1 inputs a torque signal of the drilling machine in the coal seam load, and the output end of the PID1 outputs a weight on bit signal.
The input end of the PID2 inputs the drilling speed signal of the drilling machine in the coal seam load and the preprocessed recommended drilling speed signal obtained in the step five, and the output end of the PID2 outputs a torque signal to the input end of the PID 1.
The input end of the drilling speed fine adjustment module inputs the rotating speed signal of the rotating system and the rotating speed signal of the drilling machine in the coal seam load, and the output end of the drilling speed fine adjustment module outputs a drilling speed fine adjustment quantity signal to the input end of the PID 2.
In this embodiment, both the feed system and the rotary system are known systems in drilling rigs.
Step seven, constant torque control:
And D, inputting the preprocessed recommended rotating speed obtained in the step five into a rotating system of the drilling machine to control the rotating speed.
In the feeding rotation control system built in the step six, a set constant target torque signal is input to the input end of the PID1, and is compared with a torque signal of the drilling machine in the coal seam load input by the input end of the PID1, and a weight-on-bit signal output by the output end of the PID1 controls the weight-on-bit of the feeding system of the drilling machine, so that constant torque control is realized.
In this embodiment, specifically, the response curve of the system when the rotation speed of the drilling machine is 100r/min and the differential pressure is set to 10Mpa, the hardness of the coal seam suddenly increases at 50s, and the change curves of the main variables of the drilling machine are shown in fig. 1 to 5.
As can be seen from fig. 1 to 5, the swing torque is stabilized at a value corresponding to a swing pressure difference of 10Mpa by adjusting the weight on bit (feeding force) under the action of PID1, as shown by 20-40 s. At 50s, the turning torque becomes larger under the current feed force due to the sudden increase of the coal bed hardness, and in order to maintain the turning torque unchanged, the PID1 achieves the torque reduction by reducing the weight on bit, as shown by 50-60 seconds. Simulation shows that the PID1 can realize constant torque control in the drilling process.
Step eight, constant drilling rate control:
on the basis of the seventh step, the preprocessed recommended drilling speed obtained in the fifth step is used as a constant input signal to be input into a PID2, in the PID2, the preprocessed recommended drilling speed signal is compared with the drilling speed signal of the drilling machine in the coal seam load, the torque signal output by the PID2 is used as a new target torque signal to be input into a PID1, and then the control method which is the same as the constant torque control in the seventh step is carried out, so that the drilling pressure of a feeding system of the drilling machine is controlled, and the constant drilling speed control is realized;
In the drilling process of the drilling machine, the coal bed hardness is complex and various, the ideal control effect is difficult to realize by adopting constant torque control, when the coal bed hardness suddenly becomes small, if the rotation torque is kept unchanged, the drilling pressure of the system is too high, the drilling speed is too fast, and the safety of the drilling process is reduced. When the actual drilling condition is considered and the load torque is the same, if the coal seam hardness is large, the drilling speed of the system is slower, the torque is increased at the moment, and if the coal seam hardness is small, the drilling speed of the system is faster, so that the set value of the rotary pressure difference can be finely adjusted according to the drilling speed, the error of the recommended drilling speed and the actual drilling speed is taken as input, the set value of the rotary torque is taken as output, and the controller PID2 is designed to realize the fine adjustment of the rotary torque.
In the embodiment, the drilling machine has the drilling speed of 5mm/s, the hardness of the coal bed is increased at 50s, and the change curves of main variables of the drilling machine are shown in fig. 6 to 10.
As can be seen from fig. 6 to 10, the recommended drilling rate is 5mm/s, in order to make the drilling machine reach the current drilling rate, the power of the drilling machine, that is, the set value of the turning torque, needs to be adjusted, and then the drilling pressure is changed to control the drilling rate, and the adjusting process of each parameter is as shown in fig. 6 to 10, and the coal seam hardness becomes large at 50s, so that the drilling rate is suddenly reduced, and in order to realize the drilling rate control, the set value of the turning torque is increased by PID2, so that the drilling rate is unchanged.
Step nine, fine adjustment control of drilling speed:
On the basis of the step eight, in the drilling speed fine adjustment module, the rotating speed signal of the rotary system is compared with the rotating speed signal in the coal seam load, and the drilling speed fine adjustment module outputs a drilling speed fine adjustment quantity signal to PID2; and in PID2, after summing the drilling rate fine adjustment quantity signal and the preprocessed recommended drilling rate signal, comparing the drilling rate with the drilling rate signal in the coal seam load as a new propulsion drilling rate, and then performing the same control method as the constant drilling rate control in the step eight to control the drilling pressure of a feeding system of the drilling machine so as to realize the drilling rate fine adjustment control.
For the recommended drilling speed, the unreasonable condition also exists, when the recommended drilling speed is too large for the current working condition, the turning torque of the drilling machine is too large, and the rotating speed of the system is reduced, so that the recommended drilling speed is finely adjusted according to the actual rotating speed and the set rotating speed, and the set drilling speed has the following value:
Wherein:
FEEDSPEED set is the set drilling rate;
FEEDSPEED 0 is the recommended drilling rate;
Speed 0 is a threshold at which the rotational Speed can be reduced;
Rspeed now is a measurement of rotational speed;
rspeed set is a set value of the rotation speed;
k is an integral coefficient;
1/s is integral operation;
epsilon is the start signal.
When the actual rotation speed is smaller than the set value to a certain extent, the recommended drilling speed is reduced, and then the rotation torque and the drilling weight of the system are reduced, so that the drilling machine works in a safe range. The change curves of the main variables of the drilling machine are shown in fig. 11 to 15.
As can be seen from fig. 11 to 15, the coal seam hardness becomes large at 50s, and the recommended drilling rate is too large for the current working condition, so that the turning torque of the system is too large, and the rotation speed is reduced. At the moment, the drilling speed fine adjustment module can reduce the drilling speed set value, reduce the drilling speed torque and maintain the drilling machine rotation speed.
Claims (5)
1. The feeding and rotation control method of the hydraulic tunnel drilling machine based on coal and rock sensing is characterized by comprising the following steps of:
step one, feature acquisition:
selecting the drilling pressure and the rotation pressure of a drilling machine as input signals for identifying the hardness of the coal seam, and decomposing the drilling pressure and the rotation pressure by adopting wavelet packet decomposition to obtain feature vectors;
step two, feature screening:
Carrying out correlation analysis on each component in the feature vector E obtained in the step one and the coal bed hardness to obtain a strong correlation feature vector composed of components with strong correlation with the coal bed hardness; normalizing the strong correlation feature vector to obtain a normalized feature vector;
Step three, constructing a coal bed hardness identification model:
Based on the BP neural network, training the BP neural network by taking the normalized feature vector as the input quantity of the BP neural network, and obtaining a coal bed hardness recognition model after training;
fourth, obtaining a recommended drilling speed and a recommended rotating speed:
taking the normalized feature vector obtained in the second step as the input quantity of the coal bed hardness identification model built in the third step, obtaining the coal bed hardness through the coal bed hardness identification model, and obtaining the recommended drilling speed and the recommended rotating speed under the current working condition according to the coal bed hardness as follows:
Wherein:
θ is the recommended rotation speed under the current working condition;
V is the recommended drilling speed under the current working condition;
D is the effective diameter of the drilling tool;
f is the hardness of the coal rock;
k 1,k2 is a scaling factor;
θ 0,V0 is the average value of the rotation speed and the drilling speed of the drilling machine during long-term working;
step five, preprocessing an input signal:
Preprocessing the recommended drilling speed and the recommended rotating speed obtained in the fourth step to obtain the preprocessed recommended drilling speed and the preprocessed recommended rotating speed; the specific process of pretreatment is as follows: firstly, carrying out amplitude limiting filtering to eliminate peaks in signals; then, recursive average filtering is carried out, so that the fluctuation amplitude of an input signal is reduced;
Step six, building a feed rotation control system:
The feeding rotation control system comprises a PID1, a PID2 and a drilling speed fine adjustment module; the PID1 and the PID2 adopt integral separation PI controllers; the drilling speed fine adjustment module is as follows:
Wherein:
FEEDSPEED set is the set drilling rate;
FEEDSPEED 0 is the recommended drilling rate;
Speed 0 is a threshold at which the rotational Speed can be reduced;
Rspeed now is a measurement of rotational speed;
rspeed set is a set value of the rotation speed;
k is an integral coefficient;
1/s is integral operation;
epsilon is a starting signal;
The input end of the PID1 inputs a torque signal of the drilling machine in the coal seam load, and the output end of the PID1 outputs a weight on bit signal;
The input end of the PID2 inputs the drilling speed signal of the drilling machine in the coal seam load and the preprocessed recommended drilling speed signal obtained in the step five, and the output end of the PID2 outputs a torque signal to the input end of the PID 1;
The input end of the drilling speed fine adjustment module inputs a rotating speed signal of the rotating system and a rotating speed signal of the drilling machine in a coal seam load, and the output end of the drilling speed fine adjustment module outputs a drilling speed fine adjustment quantity signal to the input end of the PID 2;
step seven, constant torque control:
inputting the preprocessed recommended rotating speed obtained in the fifth step into a rotating system of a drilling machine to control the rotating speed;
In the feeding rotary control system built in the step six, a set constant target torque signal is input to the input end of the PID1, and is compared with a torque signal of a drilling machine in a coal seam load input by the input end of the PID1, and a weight-on-bit signal output by the output end of the PID1 controls the weight-on-bit of the feeding system of the drilling machine, so that constant torque control is realized;
Step eight, constant drilling rate control:
on the basis of the seventh step, the preprocessed recommended drilling speed obtained in the fifth step is used as a constant input signal to be input into a PID2, in the PID2, the preprocessed recommended drilling speed signal is compared with the drilling speed signal of the drilling machine in the coal seam load, the torque signal output by the PID2 is used as a new target torque signal to be input into a PID1, and then the control method which is the same as the constant torque control in the seventh step is carried out, so that the drilling pressure of a feeding system of the drilling machine is controlled, and the constant drilling speed control is realized;
step nine, fine adjustment control of drilling speed:
On the basis of the step eight, in the drilling speed fine adjustment module, the rotating speed signal of the rotary system is compared with the rotating speed signal in the coal seam load, and the drilling speed fine adjustment module outputs a drilling speed fine adjustment quantity signal to PID2; and in PID2, after summing the drilling rate fine adjustment quantity signal and the preprocessed recommended drilling rate signal, comparing the drilling rate with the drilling rate signal in the coal seam load as a new propulsion drilling rate, and then performing the same control method as the constant drilling rate control in the step eight to control the drilling pressure of a feeding system of the drilling machine so as to realize the drilling rate fine adjustment control.
2. The method for controlling the feeding and rotation of the hydraulic tunnel drilling machine based on coal and rock sensing as claimed in claim 1, wherein in the first step, the wavelet packet decomposition adopts three-level wavelet packet decomposition, and the mathematical expression of the decomposed signal reconstruction function is:
S3＝S31+S32+S33+S34+S35+S36+S37++S38
Wherein:
s 3 is a signal reconstruction function;
S 3j is a j-th frequency band signal reconstruction function after three-level wavelet packet decomposition, j=1, 2, …;
The energy E 3j of the reconstructed signal is:
E3j＝∫|S3j(t)|2dt
Wherein:
e 3j is the energy of the reconstructed signal;
t is time;
Taking the energy E 3j of the reconstructed signal as the characteristic of each frequency band signal, and carrying out characteristic extraction on the weight on bit and the rotation pressure to obtain a characteristic vector E as follows:
E＝[E31j,E32j]
Wherein:
E 31j is the j-th frequency band signal characteristic vector after weight on bit decomposition;
E 32j is the characteristic vector of the j-th frequency band signal after the revolving pressure decomposition;
j＝1，2，…8。
3. The method for controlling the feeding and turning of the hydraulic tunnel drilling machine based on coal and rock sensing as claimed in claim 1, wherein in the second step, the expression of the strong correlation feature vector is as follows:
E＝[E31m,E32n]
Wherein:
E' is a strong correlation feature vector;
E' 31m is the m-th frequency band signal strong correlation characteristic vector after weight on bit decomposition;
E' 32n turning around the strong correlation eigenvector of the nth frequency band signal after pressure decomposition;
The normalized formula is as follows:
Wherein:
e' is the normalized feature vector.
4. The method for controlling the feeding and rotation of the hydraulic tunnel drilling machine based on coal and rock sensing as claimed in claim 1, wherein in the third step, in the coal seam hardness identification model, the range of the value of the coal seam hardness is [0.5, 10], the output range of the BP neural network is [0,1], and the BP neural network is mapped into the coal seam hardness through linear mapping; the linear mapping formula is as follows: y=9.5×x+0.5, where x is the output of the BP neural network; and y is the hardness of the coal bed.
5. The method for controlling the feeding and turning of the hydraulic tunnel drilling machine based on coal and rock sensing as claimed in claim 1, wherein in the fifth step, the formula of the limiting filtering is as follows:
The formula of the recursive average filtering is as follows:
Wherein:
out (n) is the amplitude limiting filtering result of the drilling speed or the rotating speed;
ErrorMax is the maximum amount of fluctuation allowed by the feed slewing system.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210950365.5A CN115387777B (en) | 2022-08-09 | 2022-08-09 | Feeding and rotation control method of hydraulic tunnel drilling machine based on coal rock sensing |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210950365.5A CN115387777B (en) | 2022-08-09 | 2022-08-09 | Feeding and rotation control method of hydraulic tunnel drilling machine based on coal rock sensing |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115387777A CN115387777A (en) | 2022-11-25 |
| CN115387777B true CN115387777B (en) | 2024-05-31 |
Family
ID=84119079
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210950365.5A Active CN115387777B (en) | 2022-08-09 | 2022-08-09 | Feeding and rotation control method of hydraulic tunnel drilling machine based on coal rock sensing |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115387777B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117328850B (en) * | 2023-09-22 | 2024-05-14 | 安百拓(张家口)建筑矿山设备有限公司 | Drilling machine control method, device, terminal and storage medium |
| CN118088180A (en) * | 2024-04-18 | 2024-05-28 | 国家林业和草原局竹子研究开发中心 | Soil drilling sampling system and drilling sampling method |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| AU6359401A (en) * | 2000-08-28 | 2002-03-07 | Halliburton Energy Services, Inc. | Method and system for predicting performance of a drilling system of a given formation |
| CN106050126A (en) * | 2016-08-08 | 2016-10-26 | 吉林大学 | All-electric coal mine underground drill rig |
| CN107780918A (en) * | 2016-08-28 | 2018-03-09 | 璧典凯 | A kind of engineering geological drilling rig rotary drilling ratio control system |
| CN108643884A (en) * | 2018-04-26 | 2018-10-12 | 中国矿业大学 | A kind of jumbolter propulsion rotary system and its cooperative self-adapted control method |
| CN109209336A (en) * | 2018-11-07 | 2019-01-15 | 西安石油大学 | A kind of automatic bit feed system and control method based on Bottom Hole Bit Weight In A |
| CN112502689A (en) * | 2020-11-06 | 2021-03-16 | 黄山学院 | Multi-mode automatic bit feeding system of variable frequency drilling machine and control method thereof |
| CN113338894A (en) * | 2021-07-15 | 2021-09-03 | 西安石油大学 | Control method of small intelligent drilling machine |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101765694B (en) * | 2007-06-26 | 2014-04-30 | 阿特拉斯·科普柯凿岩设备有限公司 | Method and device for controlling a rock drill rig |
-
2022
- 2022-08-09 CN CN202210950365.5A patent/CN115387777B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| AU6359401A (en) * | 2000-08-28 | 2002-03-07 | Halliburton Energy Services, Inc. | Method and system for predicting performance of a drilling system of a given formation |
| CN106050126A (en) * | 2016-08-08 | 2016-10-26 | 吉林大学 | All-electric coal mine underground drill rig |
| CN107780918A (en) * | 2016-08-28 | 2018-03-09 | 璧典凯 | A kind of engineering geological drilling rig rotary drilling ratio control system |
| CN108643884A (en) * | 2018-04-26 | 2018-10-12 | 中国矿业大学 | A kind of jumbolter propulsion rotary system and its cooperative self-adapted control method |
| CN109209336A (en) * | 2018-11-07 | 2019-01-15 | 西安石油大学 | A kind of automatic bit feed system and control method based on Bottom Hole Bit Weight In A |
| CN112502689A (en) * | 2020-11-06 | 2021-03-16 | 黄山学院 | Multi-mode automatic bit feeding system of variable frequency drilling machine and control method thereof |
| CN113338894A (en) * | 2021-07-15 | 2021-09-03 | 西安石油大学 | Control method of small intelligent drilling machine |
Non-Patent Citations (2)
| Title |
|---|
| BP神经网络算法在智能钻进控制***中的应用;常江华;;煤矿机械;20200515(第05期);全文 * |
| 全液压自动送钻技术控制***的研究;闫保永;;探矿工程(岩土钻掘工程);20160610(第06期);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115387777A (en) | 2022-11-25 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN115387777B (en) | Feeding and rotation control method of hydraulic tunnel drilling machine based on coal rock sensing | |
| US8636086B2 (en) | Methods of drilling with a downhole drilling machine | |
| CN108643884B (en) | Jumbolter propelling and rotating system and cooperative self-adaptive control method thereof | |
| US7775297B2 (en) | Multiple input scaling autodriller | |
| CN106640033A (en) | State monitoring method for rotary guiding tool | |
| CN106545327B (en) | Intelligent driller's control system of rig | |
| CA3053448A1 (en) | Method of optimizing drilling operation using empirical data | |
| EP2817901B1 (en) | Wireless communication | |
| CN113034001B (en) | Evaluation data processing method and system based on underground engineering parameters | |
| US11753922B1 (en) | Control systems and methods to enable autonomous drilling | |
| CN111878055B (en) | Control system and control method for drilling speed of drill bit | |
| CN106640035A (en) | VFD control system and method for automatic optimization of drilling parameters | |
| CN107201877A (en) | The closed loop control method and system of a kind of rotary steerable drilling | |
| US10900343B1 (en) | Control systems and methods to enable autonomous drilling | |
| CN115977633A (en) | Multi-information fusion feedback-based jet flow and cutting cooperative regulation and control method | |
| CN114427430A (en) | Multi-well real-time collaborative drilling parameter optimization method and system | |
| CN108561121A (en) | Completion produces and is remotely controlled the method and system of each reservoir withdrawal with monitoring payzone in real time | |
| CN202850902U (en) | Underground turbine generator closed loop controlling system | |
| CN106257463B (en) | A kind of bit performance evaluation method and system | |
| CN203145832U (en) | Deviation prevention control system for rock drilling tool | |
| CN109779601B (en) | Adaptive decoding method for downlink instruction of rotary steering drilling system | |
| CN105156021B (en) | Borer system and boring method based on self adaptation down-hole equipment tool-face dynamic control | |
| CN115526400A (en) | Drilling operation parameter self-adaptive decision-making method based on feeding damping and mechanical specific energy | |
| CN105134163B (en) | A kind of kinetic-control system and method for adaptive down-hole equipment tool-face | |
| CN202866781U (en) | Four constant automatic bit feeding control system |
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 |