CN112065421B - Automatic positioning method for heading machine cutter head - Google Patents
Automatic positioning method for heading machine cutter head Download PDFInfo
- Publication number
- CN112065421B CN112065421B CN202011079172.4A CN202011079172A CN112065421B CN 112065421 B CN112065421 B CN 112065421B CN 202011079172 A CN202011079172 A CN 202011079172A CN 112065421 B CN112065421 B CN 112065421B
- Authority
- CN
- China
- Prior art keywords
- cutter head
- theta
- angle
- brklen
- cutter
- 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
- 238000000034 method Methods 0.000 title claims abstract description 26
- 230000005641 tunneling Effects 0.000 claims abstract description 63
- 238000012706 support-vector machine Methods 0.000 claims abstract description 36
- 238000012549 training Methods 0.000 claims abstract description 28
- 230000001133 acceleration Effects 0.000 claims abstract description 12
- 238000003062 neural network model Methods 0.000 claims description 40
- 239000011159 matrix material Substances 0.000 claims description 31
- 238000010276 construction Methods 0.000 claims description 14
- 230000008569 process Effects 0.000 claims description 6
- 238000012216 screening Methods 0.000 claims description 6
- 238000012360 testing method Methods 0.000 claims description 6
- 230000009471 action Effects 0.000 claims description 5
- 238000009412 basement excavation Methods 0.000 claims description 5
- 238000012935 Averaging Methods 0.000 claims description 3
- 230000035515 penetration Effects 0.000 claims description 3
- 230000017105 transposition Effects 0.000 claims description 3
- 230000009286 beneficial effect Effects 0.000 abstract description 3
- 238000004364 calculation method Methods 0.000 abstract description 3
- 238000004140 cleaning Methods 0.000 abstract description 3
- 238000013528 artificial neural network Methods 0.000 abstract 1
- 238000011161 development Methods 0.000 description 6
- 230000007547 defect Effects 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004913 activation Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 239000011435 rock Substances 0.000 description 1
Images
Classifications
-
- E—FIXED CONSTRUCTIONS
- E21—EARTH OR ROCK DRILLING; MINING
- E21D—SHAFTS; TUNNELS; GALLERIES; LARGE UNDERGROUND CHAMBERS
- E21D9/00—Tunnels or galleries, with or without linings; Methods or apparatus for making thereof; Layout of tunnels or galleries
- E21D9/06—Making by using a driving shield, i.e. advanced by pushing means bearing against the already placed lining
- E21D9/08—Making by using a driving shield, i.e. advanced by pushing means bearing against the already placed lining with additional boring or cutting means other than the conventional cutting edge of the shield
Landscapes
- Engineering & Computer Science (AREA)
- Mining & Mineral Resources (AREA)
- Environmental & Geological Engineering (AREA)
- Life Sciences & Earth Sciences (AREA)
- General Life Sciences & Earth Sciences (AREA)
- Geochemistry & Mineralogy (AREA)
- Geology (AREA)
- Excavating Of Shafts Or Tunnels (AREA)
Abstract
The invention provides an automatic positioning method for a cutter head of a heading machine, which is characterized in that a heading state parameter is input into a prediction model to realize the prediction of a parking angle of a cutter head moving when the cutter head is parked freely to zero after a driving force is cut off at the lowest rotating speed, the prediction model integrates the training and learning advantages of a neural network and a support vector machine model, the average value of the output results of the two models is taken as a prediction result, and the prediction accuracy is high; in addition, a cutterhead deceleration starting angle and a cutterhead starting braking angle are obtained through calculation of a kinematic algorithm, and the operation of the cutterhead is controlled through a program in cooperation with a main control system of the tunneling machine: when the rotation angle of the cutter head is equal to the deceleration starting angle, the cutter head is decelerated to the lowest rotation speed at the acceleration a; when the rotating speed of the cutter head is equal to the initial braking angle, the cutter head is powered off and stops running, so that the cutter head is stopped to a preset cutter head target stop angle position, and the cutter head stop position is positioned; and is beneficial to the deployment of automatic equipment such as a tunneling machine tool changing robot, a cleaning robot and the like.
Description
Technical Field
The invention relates to the field of shield construction, in particular to an automatic positioning method for a cutter head of a heading machine.
Background
The development machine is a main engineering machine in the field of shield construction, and a cutter head and a cutter of the development machine are used for development and rock breaking; along with the technical development of industrial robots, the tool changing robot is adopted to change the tool of a heading machine tool disc, which is the current development trend; meanwhile, as the operation space of the robot in the earth bin of the heading machine is narrow, the tool-changing robot needs to require the heading machine cutter head to stop to a proper position for tool changing, but the existing heading machine generally lacks the positioning for stopping the cutter head, cannot accurately monitor the stop position of the heading machine cutter head, and is difficult to meet the requirement that the tool-changing robot needs to be positioned and stopped at high precision by the cutter head. Therefore, an automatic positioning method for a heading machine cutter head is urgently needed in the industry.
Disclosure of Invention
The invention aims to provide an automatic positioning method for a heading machine cutter head, which aims to solve the problem that the heading machine cutter head cannot be stopped and positioned in the background technology.
The invention provides an automatic positioning method for a heading machine cutter head, which is used for a heading machine, wherein the heading machine comprises a heading machine main control system, the heading machine main control system is used for acquiring and storing heading state parameters and controlling the operation of the heading machine, and the method specifically comprises the following steps:
s1, acquiring tunneling state parameter data, namely acquiring construction data of the tunneling machine through a main control system of the tunneling machine, screening the construction data, and screening out the tunneling state parameter data, wherein the tunneling state parameters comprise the excavation diameter D of a cutter, the rotation speed N of the cutter when a cutter stopping command is sent, the torque T of the cutter, the penetration P of the cutter and the total propelling force F; representing the obtained tunneling state parameter data into a tunneling state parameter matrix X, X = (X1, X2, X3, X4, X5)E=(D，N，T，P，F)E(ii) a E is a matrix transposition symbol;
s2, inputting the obtained tunneling state parameter matrix into a prediction model to obtain a parking operation angle parameter Y = thetaBrkLen；
S3, calculating a cutter deceleration initial angle and a cutter initial braking angle according to the following formulas;
the angular acceleration is: a = (V)Max-VMin）/t；
The cutter head rotates at the current speed VCDown to the minimum rotation speed VMinDeceleration running angle during the process: thetaDecLen=（VC 2-VMin 2）/2a；
The cutter head deceleration starting angle: thetaD=θT-θDecLen-θBrkLen；
Initial braking angle of the cutter head: thetaBrk=θT-θBrkLen；
In the formula, the unit of the rotating speed V is degree per second, and the unit of the angular acceleration is degree per second; the cutter head decelerates at the acceleration a; vCAcquiring the current rotating speed of the cutter head in real time by a main control system of the tunneling machine; vMaxThe maximum rotating speed of the cutter head; vMinIs the lowest rotation speed of the cutter head, t is the time required for the cutter head to reduce from the highest rotation speed to the lowest rotation speed, thetaDecLenFor reducing the angle of operation of the cutter head, thetaBrkLenStopping the cutter for a running angle; thetaTFor a preset target cutter-head stopping angle thetaDFor the initial angle of deceleration of the cutter head, thetaBrkStarting a brake angle for the cutter head;
s4, decelerating and stopping the cutter head; to the initial angle theta of cutter head decelerationDAnd the current rotation angle theta of the cutter headcJudging the current rotation angle theta of the cutter headcThe current rotation angle theta of the cutter head is obtained by real-time acquisition of a rotary encoder and a main control system of the heading machinecEqual to the initial deceleration angle theta of the cutter headDIn time, the main control system of the tunneling machine sends a deceleration instruction, and the cutter head decelerates to the lowest rotating speed VMin(ii) a Otherwise, until the current rotation angle theta of the cutter headcEqual to the initial deceleration angle theta of the cutter headDCarrying out cutter head deceleration operation;
after the cutter head is reduced to the lowest rotating speed, the initial braking angle theta of the cutter head is carried outBrkAnd the current rotation angle theta of the cutter headcWhen the cutter head starts to brake the angle thetaBrkEqual to the current rotation angle theta of the cutter headcIn time, the main control system of the tunneling machine stops the cutter head to run, so that the cutter head can be freely stopped to a preset cutter head target stop angle theta under the action of inertiaTThe automatic positioning of the cutter head is realized; otherwise, the cutter head creeps at the lowest rotating speed until the initial braking angle theta of the cutter headBrkEqual to the current rotation angle theta of the cutter headcAnd the main driving device for driving the cutter head is powered off, and the cutter head is powered off and stops freely.
Further, the prediction model in step S2 includes a neural network model and a support vector machine model, and the parking operation angle parameter Y = θBrkLenThe obtaining specifically comprises the following steps:
YBPNet=θBrkLeninputting the tunneling state parameter matrix into a neural network model, and outputting a prediction result to obtain a parking operation angle parameter YBPNet = thetaBrkLen；
Ysvm=θBrkLenInputting a tunneling state parameter matrix into a support vector machine model, and outputting a prediction result, namely, a parking operation angle parameter Ysvm = thetaBrkLen；
And (3) carrying out mathematical average on the prediction results of the neural network model and the support vector machine model: y = (YBPNet + Ysvm)/2, and obtaining a parking operation angle parameter Y = thetaBrkLen。
Further, the neural network model comprises an input layer, a hidden layer and an output layer, wherein the number of nodes n1=5 in the input layer; the number of hidden layer nodes n2= h, h being a positive integer; the number of nodes n3=1 in the output layer.
Further, before step S1, off-line training of a neural network model and a support vector machine model is further performed, a tunneling machine main control system is used to acquire a large amount of historical construction data of the tunneling machine, the same amount of tunneling state parameters and parking operation angle parameters are screened out, and a tunneling state parameter matrix and a parking operation angle parameter database are formed; taking the tunneling state parameter matrix X as input data and the corresponding parking operation angle parameter thetaBrkLenAs output data, performing off-line training and learning of a neural network model and a support vector machine model to obtain a parking operation angle parameter thetaBrkLenThe predictive model of (2);
wherein, 80% of data in the tunneling state parameter database is selected as training data, the rest 20% of data is used as test data, the training data and the test data are input into the neural network model and the support vector machine model for training and learning, and corresponding theta is outputBrkLenParameter prediction results YBPNet and thetaBrkLenA parameter prediction result Ysvm; and mathematically averaging YBPNet and Ysvm: y = (YBPNet + Ysvm)/2, as a result of prediction- -parking operation angle parameter θBrkLen。
Furthermore, the automatic positioning method of the cutter head also comprises the number of processesUpdating a database and a prediction model, wherein the engineering database comprises a tunneling state parameter matrix X database collected in the early stage and a theta databaseBrkLenA parameter prediction result Y database; in the subsequent construction process of the heading machine, the newly-added heading state parameter matrix X sample screened out and the corresponding theta obtained after the newly-added heading state parameter matrix X sample are trained and learned through the neural network model and the support vector machineBrkLenAnd adding and storing the parameter prediction result Y into the engineering database, updating the engineering database, and further training and updating the neural network model and the support vector machine model by using the updated engineering database to realize the updating of the prediction model.
Furthermore, the updating of the neural network model, the support vector machine model and the engineering database comprises manual updating and automatic updating, and an operator can manually update the engineering database and update the training neural network model and the support vector machine model; or when the increment of the engineering database is more than 10%, the main control system of the tunneling machine automatically controls and updates the engineering database, and updates the training neural network model and the support vector machine model.
The invention has the following beneficial effects:
according to the automatic positioning method for the cutterhead of the heading machine, the heading state parameters are input into the prediction model, the fact that the cutterhead freely stops to a stop angle moving at zero speed after the driving force is cut off at the lowest rotating speed is predicted, the prediction model integrates the advantages of training and learning of a neural network model and a support vector machine model, the average value of the output results of the neural network model and the support vector machine model is taken as the prediction result, errors caused by defects of a single model algorithm are reduced, and the accuracy of the prediction result is high; in addition, a cutterhead deceleration starting angle and a cutterhead starting braking angle are obtained through calculation of a kinematic algorithm, and the operation of the cutterhead is controlled through a program in cooperation with a main control system of the tunneling machine: when the rotation angle of the cutter head is equal to the deceleration starting angle, the cutter head is decelerated to the lowest rotation speed at the acceleration a; when the rotation angle of the cutter head is equal to the initial braking angle, the cutter head is powered off and automatically stops running under the action of inertia, so that the cutter head is stopped to a preset cutter head target stopping angle position, the cutter head stopping position is positioned, and meanwhile, the development of automatic equipment such as a heading machine cutter changing robot and a cleaning robot is facilitated.
In addition to the objects, features and advantages described above, other objects, features and advantages of the present invention are also provided. The present invention will be described in further detail below with reference to the drawings.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this application, illustrate embodiments of the invention and, together with the description, serve to explain the invention and not to limit the invention. In the drawings:
FIG. 1 is a schematic structural view of a cutter head portion of the heading machine of the present embodiment;
FIG. 2 is a control flow chart of an automatic positioning method of a heading machine cutterhead according to the embodiment;
FIG. 3 is a schematic structural diagram of a neural network model in this embodiment;
fig. 4 is a flowchart of a parking operation angle parameter prediction model of the present embodiment;
FIG. 5 is a flowchart of the prediction model and engineering database update of the present embodiment;
the device comprises a cutter head 1, a cutter 2, a cutter 3, a main driving device 4 and a rotary encoder.
Detailed Description
Embodiments of the invention will be described in detail below with reference to the drawings, but the invention can be implemented in many different ways, which are defined and covered by the claims.
Referring to fig. 1, the automatic positioning method of the heading machine cutterhead is used for a heading machine, the heading machine comprises a heading machine main control system, a heading cutter 2 is installed on the cutterhead 1 of the heading machine, and the installation angle of the heading cutter and the cutterhead is relatively fixed; a cutter head of the heading machine is generally driven by a main driving device 3 of the heading machine, a rotary encoder 4 is installed on a rotary connecting shaft in the center of the cutter head, and the rotary encoder is connected with a main control system of the heading machine and used for measuring the rotation angle of the cutter head so as to indirectly obtain the angle of each cutter on the cutter head; the main control system of the heading machine is connected with the main driving device through a frequency converter to control the operation of a cutter head of the heading machine, and is used for acquiring and storing heading state parameters.
Referring to fig. 2, the automatic cutter positioning method of the invention specifically comprises the following steps:
s1, acquiring tunneling state parameter data, namely acquiring construction data of the tunneling machine through a main control system of the tunneling machine, screening the construction data, and screening out the tunneling state parameter data, wherein the tunneling state parameters comprise the excavation diameter D of a cutter, the rotation speed N of the cutter when a cutter stopping command is sent, the torque T of the cutter, the penetration P of the cutter and the total propelling force F; representing the obtained tunneling state parameter data into a tunneling state parameter matrix X, X = (X1, X2, X3, X4, X5)E=(D，N，T，P，F)E(ii) a E is a matrix transposition symbol;
s2, inputting the obtained tunneling state parameter matrix into a prediction model to obtain a parking operation angle parameter Y = thetaBrkLen(ii) a The prediction model comprises a neural network model and a support vector machine model, and the parking operation angle parameter Y = thetaBrkLenThe obtaining specifically comprises the following steps:
YBPNet=θBrkLeninputting the tunneling state parameter matrix into a neural network model, and outputting a prediction result to obtain a parking operation angle parameter YBPNet = thetaBrkLen；
Ysvm=θBrkLenInputting a tunneling state parameter matrix into a support vector machine model, and outputting a prediction result, namely, a parking operation angle parameter Ysvm = thetaBrkLen；
And (3) carrying out mathematical average on the prediction results of the neural network model and the support vector machine model: y = (YBPNet + Ysvm)/2, and obtaining a parking operation angle parameter Y = thetaBrkLen。
S3, calculating a cutter deceleration initial angle and a cutter initial braking angle according to the following formulas;
the angular acceleration is: a = (V)Max-VMin）/t；
The cutter head rotates at the current speed VCDown to the minimum rotation speed VMinDeceleration running angle during the process: thetaDecLen=（VC 2-VMin 2）/2a；
The cutter head deceleration starting angle: thetaD=θT-θDecLen-θBrkLen；
Initial braking angle of the cutter head: thetaBrk=θT-θBrkLen；
In the formula, the unit of the rotating speed V is degree per second, the unit of the angular acceleration is degree per second of square, and the cutter head performs deceleration operation at the acceleration a; vCAcquiring the current rotating speed of the cutter head in real time by a main control system of the tunneling machine; vMaxThe maximum rotating speed of the cutter head; vMinIs the lowest rotation speed of the cutter head, t is the time required for the cutter head to reduce from the highest rotation speed to the lowest rotation speed, thetaDecLenFor reducing the angle of operation of the cutter head, thetaBrkLenStopping the cutter for a running angle; thetaTFor a preset target cutter-head stopping angle thetaDFor the initial angle of deceleration of the cutter head, thetaBrkAnd the angle is started to brake the cutter head.
S4, decelerating and stopping the cutter head; to the initial angle theta of cutter head decelerationDAnd the current rotation angle theta of the cutter headcJudging the current rotation angle theta of the cutter headcThe current rotation angle theta of the cutter head is obtained by real-time acquisition of a rotary encoder and a main control system of the heading machinecEqual to the initial deceleration angle theta of the cutter headDIn time, the main control system of the tunneling machine sends a deceleration instruction, and the cutter head decelerates to the lowest rotating speed VMin(ii) a Otherwise, until the current rotation angle theta of the cutter headcEqual to the initial deceleration angle theta of the cutter headDCarrying out cutter head deceleration operation;
after the cutter head is reduced to the lowest rotating speed, the initial braking angle theta of the cutter head is carried outBrkAnd the current rotation angle theta of the cutter headcWhen the cutter head starts to brake the angle thetaBrkEqual to the current rotation angle theta of the cutter headcIn time, the main control system of the tunneling machine stops the cutter head to run, so that the cutter head can be freely stopped to a preset cutter head target stop angle theta under the action of inertiaTThe automatic positioning of the cutter head is realized; otherwise, the cutter head creeps at the lowest rotating speed until the initial braking angle theta of the cutter headBrkEqual to the current rotation angle theta of the cutter headcWhen the cutter is cut off, the operation is stopped, and the frequency is changedWhen the device is powered off, the main driving device stops running, the cutter head and the cutter are effectively guaranteed to stop to a preset target stop angle position, and stop positioning of the cutter head and the cutter head is achieved.
Referring to fig. 3, the neural network model of the present invention includes an input layer, a hidden layer, and an output layer, where n1=5 node numbers of the input layer correspond to five vector features of a tunneling state parameter matrix, respectively, the hidden layer includes an activation function f (x), n2= h node numbers of the hidden layer are positive integers; the number of nodes n3=1 in the output layer corresponds to the prediction result YBPNet.
Referring to fig. 4 and 5, before step S1, offline training of a neural network model and a support vector machine model is further performed, a tunneling machine main control system is used to obtain a large amount of historical construction data of the tunneling machine, equivalent tunneling state parameters and parking operation angle parameters are screened out, and a tunneling state parameter matrix and a corresponding parking operation angle parameter theta when a cutter head is stopped at the lowest speed to 0 are formedBrkLenA database; taking the tunneling state parameter matrix X as input data and the corresponding parking operation angle parameter thetaBrkLenAs output data, performing off-line training and learning of a neural network model and a support vector machine model to obtain a parking operation angle parameter thetaBrkLenThe predictive model of (1). Wherein, 80% of data in the tunneling state parameter database is selected as training data, the rest 20% of data is used as test data, the training data and the test data are input into the neural network model and the support vector machine model for training and learning, and corresponding theta is outputBrkLenParameter prediction results YBPNet and thetaBrkLenA parameter prediction result Ysvm; and mathematically averaging YBPNet and Ysvm: y = (YBPNet + Ysvm)/2, parking operation angle parameter θ as prediction resultBrkLen。
The invention also comprises the updating of the engineering database and the updating of the prediction model, wherein the engineering database comprises a tunneling state parameter matrix X database and a theta database which are collected in the early stageBrkLenA parameter prediction result Y database; in the subsequent construction process of the heading machine, the newly-added heading state parameter matrix X sample screened out and the phase obtained after the newly-added heading state parameter matrix X sample are trained and learned through the neural network model and the support vector machineShould thetaBrkLenAnd adding and storing the parameter prediction result Y into the engineering database, updating the engineering database, and further training and updating the neural network model and the support vector machine model by utilizing the updated engineering database. All data of the engineering database are stored in a main control system of the tunneling machine, the neural network model, the support vector machine model and the engineering database are updated by manual updating and automatic updating, and an operator can manually update the engineering database and update the training neural network model and the support vector machine model through an operation interface of the main control system; or when the increment of the engineering database is more than 10%, the main control system of the tunneling machine automatically controls and updates the engineering database, and updates the training neural network model and the support vector machine model; the prediction accuracy of the parking operation angle parameter is improved.
The invention aims to provide an automatic positioning method for a heading machine cutter head, a prediction model can predict a parking angle (hereinafter, referred to as parking operation angle parameter) moving when the cutter head is freely parked to zero after cutting off driving force at the lowest rotating speed through deep learning training of a large number of heading state parameters and parking operation angle parameters, and meanwhile, the prediction model integrates the training learning advantages of a neural network model and a support vector machine model, and the average value of the output results of the two models is taken as a prediction result, so that the error caused by the defect of a single model algorithm is reduced, and the prediction accuracy of the parking operation angle parameters is improved; meanwhile, the two models can be automatically learned and updated, a prediction model is optimized, and the prediction of the heading machine adapting to different excavation diameters and working conditions is facilitated; in addition, a cutterhead deceleration starting angle and a cutterhead starting braking angle are obtained through calculation of a kinematic algorithm, and the cutterhead is controlled to operate by matching with a program of a main control system of the tunneling machine: when the rotation angle of the cutter head is equal to the deceleration starting angle, the cutter head operates to the lowest rotation speed in a deceleration mode at the acceleration a, when the rotation speed of the cutter head is equal to the initial braking angle, the main control system of the tunneling machine controls the frequency converter and the driving device to be powered off, the cutter head freely rotates and stops under the action of inertia, the cutter head is stopped to a preset cutter head target stop angle position, and the cutter head stop position is positioned; and is beneficial to the arrangement of automatic equipment such as a tool changing robot, a cutter cleaning robot and the like.
In the attached drawings, the slope deceleration refers to a mode that a main control system of the heading machine controls a main driving device (a power source motor) to operate in a deceleration mode through a frequency converter, the operation mode is not directly stopped, the operation mode is performed in a deceleration mode through acceleration a, and the frequency converter stops outputting after the speed is reduced to 0.
The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention, and various modifications and changes may be made by those skilled in the art. Any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (6)
1. The automatic positioning method of the heading machine cutterhead is used for a heading machine, the heading machine comprises a heading machine main control system, and the heading machine main control system is used for acquiring and storing heading state parameters and controlling the operation of the heading machine, and is characterized by comprising the following steps:
s1, acquiring tunneling state parameter data, namely acquiring construction data of the tunneling machine through a main control system of the tunneling machine, screening the construction data, and screening out the tunneling state parameter data, wherein the tunneling state parameters comprise the excavation diameter D of a cutter, the rotation speed N of the cutter when a cutter stopping command is sent, the torque T of the cutter, the penetration P of the cutter and the total propelling force F; representing the obtained tunneling state parameter data into a tunneling state parameter matrix X, X = (X1, X2, X3, X4, X5)E=(D，N，T，P，F)E(ii) a E is a matrix transposition symbol;
s2, inputting the obtained tunneling state parameter matrix into a prediction model to obtain a parking operation angle parameter Y = thetaBrkLen；
S3, calculating a cutter deceleration initial angle and a cutter initial braking angle according to the following formulas;
the angular acceleration is: a = (V)Max-VMin）/t；
The cutter head rotates at the current speed VCDown to the minimum rotation speed VMinDeceleration running angle during the process: thetaDecLen=（VC 2-VMin 2）/2a；
The cutter head deceleration starting angle: thetaD=θT-θDecLen-θBrkLen；
Initial braking angle of the cutter head: thetaBrk=θT-θBrkLen；
In the formula, the unit of the rotating speed V is degree per second, and the unit of the angular acceleration is degree per second;
VCis the current rotation speed of the cutter head, VMaxThe maximum rotating speed of the cutter head; vMinIs the lowest rotation speed of the cutter head, t is the time required for the cutter head to reduce from the highest rotation speed to the lowest rotation speed, thetaDecLenFor reducing the angle of operation of the cutter head, thetaBrkLenStopping the cutter for a running angle; thetaTFor a preset target cutter-head stopping angle thetaDFor the initial angle of deceleration of the cutter head, thetaBrkStarting a brake angle for the cutter head;
s4, decelerating and stopping the cutter head; to the initial angle theta of cutter head decelerationDAnd the current rotation angle theta of the cutter headCJudging the current rotation angle theta of the cutter headCThe current rotation angle theta of the cutter head is obtained by real-time acquisition of a rotary encoder and a main control system of the heading machineCEqual to the initial deceleration angle theta of the cutter headDIn time, the main control system of the tunneling machine sends a deceleration instruction, and the cutter head decelerates to the lowest rotating speed VMin(ii) a Otherwise, until the current rotation angle theta of the cutter headCEqual to the initial deceleration angle theta of the cutter headDCarrying out cutter head deceleration operation;
after the cutter head is reduced to the lowest rotating speed, the initial braking angle theta of the cutter head is carried outBrkAnd the current rotation angle theta of the cutter headCWhen the cutter head starts to brake the angle thetaBrkEqual to the current rotation angle theta of the cutter headCIn time, the main control system of the tunneling machine stops the cutter head to run, so that the cutter head can be freely stopped to a preset cutter head target stop angle theta under the action of inertiaTThe automatic positioning of the cutter head is realized; otherwise, the cutter head creeps at the lowest rotating speed until the initial braking angle theta of the cutter headBrkEqual to the current rotation angle theta of the cutter headCAnd performing the operation of cutting off the cutter head.
2. The method according to claim 1, wherein the prediction model in the step S2 comprises a neural network model and a support vector machine model, and the parking operation angle parameter Y = θBrkLenThe obtaining specifically comprises the following steps:
YBPNet=θBrkLeninputting the tunneling state parameter matrix into a neural network model, and outputting a prediction result to obtain a parking operation angle parameter YBPNet = thetaBrkLen；
Ysvm=θBrkLenInputting a tunneling state parameter matrix into a support vector machine model, and outputting a prediction result, namely, a parking operation angle parameter Ysvm = thetaBrkLen；
And (3) carrying out mathematical average on the prediction results of the neural network model and the support vector machine model: y = (YBPNet + Ysvm)/2, and obtaining a parking operation angle parameter Y = thetaBrkLen。
3. The automatic positioning method for the heading machine cutterhead according to claim 2, wherein the neural network model comprises an input layer, a hidden layer and an output layer, the number of nodes of the input layer n1= 5; the number of hidden layer nodes n2= h, h being a positive integer; the number of nodes n3=1 in the output layer.
4. The automatic positioning method of the cutterhead of the heading machine according to claim 3, characterized in that before step S1, offline training of a neural network model and a support vector machine model is further included, a heading machine main control system is utilized to obtain massive historical construction data of the heading machine, equivalent heading state parameters and parking operation angle parameters are screened out, and a heading state parameter matrix and a parking operation angle parameter database are formed;
taking the tunneling state parameter matrix X as input data and the corresponding parking operation angle parameter thetaBrkLenAs output data, performing off-line training and learning of a neural network model and a support vector machine model to obtain a parking operation angle parameter thetaBrkLenThe predictive model of (2);
wherein in the form of a tunnelSelecting 80% of data from the state parameter database as training data, using the rest 20% of data as test data, inputting the training data and the test data into the neural network model and the support vector machine model for training and learning, and outputting corresponding thetaBrkLenParameter prediction results YBPNet and thetaBrkLenA parameter prediction result Ysvm; and mathematically averaging YBPNet and Ysvm: y = (YBPNet + Ysvm)/2 as a prediction result.
5. The method of claim 4, comprising updating an engineering database and updating the predictive model, wherein the engineering database comprises a pre-collected excavation state parameter matrix X database and θBrkLenA parameter prediction result Y database; in the subsequent construction process of the heading machine, the newly-added heading state parameter matrix X sample screened out and the corresponding theta obtained after the newly-added heading state parameter matrix X sample are trained and learned through the neural network model and the support vector machineBrkLenAnd adding and storing the parameter prediction result Y into the engineering database, updating the engineering database, and further training and updating the neural network model and the support vector machine model by using the updated engineering database to realize the updating of the prediction model.
6. The automatic positioning method for the cutterhead of the heading machine according to claim 5, wherein the neural network model, the support vector machine model and the engineering database update comprise manual update and automatic update, and an operator can manually update the engineering database and update the training neural network model and the support vector machine model; or when the increment of the engineering database is more than 10%, the main control system of the tunneling machine automatically controls and updates the engineering database, and updates the training neural network model and the support vector machine model.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011079172.4A CN112065421B (en) | 2020-10-10 | 2020-10-10 | Automatic positioning method for heading machine cutter head |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011079172.4A CN112065421B (en) | 2020-10-10 | 2020-10-10 | Automatic positioning method for heading machine cutter head |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112065421A CN112065421A (en) | 2020-12-11 |
| CN112065421B true CN112065421B (en) | 2022-04-22 |
Family
ID=73655757
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011079172.4A Active CN112065421B (en) | 2020-10-10 | 2020-10-10 | Automatic positioning method for heading machine cutter head |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112065421B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113738389A (en) * | 2021-08-31 | 2021-12-03 | 中铁工程装备集团有限公司 | Anti-interference control method and device for multi-cutter-disc pipe jacking machine |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103941586A (en) * | 2014-02-08 | 2014-07-23 | 上海交通大学 | Prediction function control method for rotating speed of main driving system of heading machine |
| CN106777568A (en) * | 2016-11-29 | 2017-05-31 | 天津大学 | Full face rock tunnel boring machine cutterhead tunnels the determination method of load |
| CN108388689A (en) * | 2018-01-16 | 2018-08-10 | 天津大学 | A kind of Cutter Head Torque in Shield Tunneling computational methods based on dimensional analysis |
| CN110096827A (en) * | 2019-05-09 | 2019-08-06 | 中铁工程服务有限公司 | A kind of shield machine parameter optimization method based on deep neural network |
| CN111079342A (en) * | 2019-11-29 | 2020-04-28 | 中铁工程装备集团有限公司 | TBM tunneling performance prediction method based on online rock mass grade classification |
| CN111622763A (en) * | 2020-04-23 | 2020-09-04 | 中国铁建重工集团股份有限公司 | Direction adjusting control method and system for vertical shaft heading machine, vertical shaft heading machine and storage medium |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| NL1015324C2 (en) * | 1999-11-11 | 2001-05-14 | Ballast Nedam Infra B V | Device and method for drilling in a substrate. |
-
2020
- 2020-10-10 CN CN202011079172.4A patent/CN112065421B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103941586A (en) * | 2014-02-08 | 2014-07-23 | 上海交通大学 | Prediction function control method for rotating speed of main driving system of heading machine |
| CN106777568A (en) * | 2016-11-29 | 2017-05-31 | 天津大学 | Full face rock tunnel boring machine cutterhead tunnels the determination method of load |
| CN108388689A (en) * | 2018-01-16 | 2018-08-10 | 天津大学 | A kind of Cutter Head Torque in Shield Tunneling computational methods based on dimensional analysis |
| CN110096827A (en) * | 2019-05-09 | 2019-08-06 | 中铁工程服务有限公司 | A kind of shield machine parameter optimization method based on deep neural network |
| CN111079342A (en) * | 2019-11-29 | 2020-04-28 | 中铁工程装备集团有限公司 | TBM tunneling performance prediction method based on online rock mass grade classification |
| CN111622763A (en) * | 2020-04-23 | 2020-09-04 | 中国铁建重工集团股份有限公司 | Direction adjusting control method and system for vertical shaft heading machine, vertical shaft heading machine and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112065421A (en) | 2020-12-11 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109352663B (en) | Robot automatic accurate positioning hole making device and method for composite cabin section | |
| US11059142B2 (en) | Controller, machine learning device, and system | |
| Kegg | One-line machine and process diagnostics | |
| CN111687652B (en) | Grip force adjusting device and grip force adjusting system | |
| CN112065421B (en) | Automatic positioning method for heading machine cutter head | |
| KR0182090B1 (en) | Computer system for controlling an industrial robot subsystem which can monitor and detect abnormalities therein | |
| EP1701824A1 (en) | Control method device and system for robot applications | |
| WO2002003155A1 (en) | Apparatus and method for machining simulation for nc machining | |
| CN109719756B (en) | Life prediction device | |
| CA2765119A1 (en) | Determination of route for arranging automatic control of mobile mining machine | |
| JP2018092428A (en) | Machine tool and machine learning apparatus | |
| CN1722034A (en) | Numerical controller | |
| US11340563B2 (en) | Management system and management device for a plurality of industrial machines supplied with power from a power supply facility | |
| CN110174871B (en) | Control device, machine learning device, and system | |
| US20040128018A1 (en) | Thread machining control method and apparatus therefor | |
| JP6542710B2 (en) | Numerical control device with program correction support function for alarm solution | |
| CN107229253B (en) | Numerical controller for facilitating countermeasures after interference detection | |
| CN110965982B (en) | Automatic control method and system for rotary drilling rig and rotary drilling rig equipment | |
| CN103240613B (en) | Machine tool table movement control method | |
| JP2002283186A (en) | Machine tool, numerical control device of machine tool and vibration preventive method | |
| CN112706167B (en) | Control method, apparatus, and computer-readable storage medium for mobile device | |
| US11327462B2 (en) | Maintenance support system, numerical controller, and control method of maintenance support system | |
| JP6457588B2 (en) | Numerical controller | |
| JP2020055095A (en) | Control device and control system | |
| CN111301544A (en) | Control system and control method of wall-climbing robot with scanning function |
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 | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20220819 Address after: No.88, Dongqi line, Changsha Economic and Technological Development Zone, Changsha City, Hunan Province Patentee after: China Railway Construction Heavy Industry Group Co.,Ltd. Patentee after: CHINA RAILWAY CONSTRUCTION Corp.,Ltd. Address before: No.88, Dongqi line, Changsha Economic and Technological Development Zone, Changsha City, Hunan Province Patentee before: China Railway Construction Heavy Industry Group Co.,Ltd. |
|
| TR01 | Transfer of patent right |