CN115788477B - Self-adaptive cutting control system and method for heading machine - Google Patents
Self-adaptive cutting control system and method for heading machine Download PDFInfo
- Publication number
- CN115788477B CN115788477B CN202310067306.8A CN202310067306A CN115788477B CN 115788477 B CN115788477 B CN 115788477B CN 202310067306 A CN202310067306 A CN 202310067306A CN 115788477 B CN115788477 B CN 115788477B
- Authority
- CN
- China
- Prior art keywords
- data
- cutting
- heading machine
- current
- oil cylinder
- 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
Images
Classifications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/02—Total factory control, e.g. smart factories, flexible manufacturing systems [FMS] or integrated manufacturing systems [IMS]
Abstract
The invention relates to a self-adaptive cutting control system and method for a heading machine, and belongs to the technical field of intelligent heading equipment. The sensor module comprises a pressure sensor, a stroke displacement sensor and a vibration sensor; the sensor module is used for acquiring oil cylinder pressure data, oil cylinder displacement data and cutting arm vibration data in the cutting process of the heading machine and sending the data to the edge computer through the data acquisition unit; the edge computer is used for processing the oil cylinder pressure data, the oil cylinder displacement data, the cutting arm vibration data, the cutting current data and the cutting voltage data, and carrying out self-adaptive control on the swinging speed of the cutting arm of the heading machine according to the processing result. The invention provides a method for adaptively controlling the swing speed of the cutting arm of a heading machine based on various parameters in the cutting process of the heading machine, which is more in line with the actual working condition compared with the prior single current criterion, thereby improving the cutting efficiency of the heading machine.
Description
Technical Field
The invention relates to the technical field of intelligent tunneling equipment, in particular to a self-adaptive cutting control system and method for a tunneling machine.
Background
The cantilever type heading machine is used as the most important equipment of a coal mine underground comprehensive tunneling working face, is widely applied to tunnel and tunnel tunneling, and is a key for realizing unmanned intelligent tunneling and improving tunneling efficiency in an automation and intelligent level.
The working environment of the fully-mechanized working face is severe, and a high-performance automatic control system is particularly important, and mainly comprises an electromechanical part and a hydraulic part of the cantilever type tunneling machine in control, wherein the aim of controlling is to realize the aim of self-adaptively adjusting the swing speed of the tunneling machine according to the hardness of coal and rock so as to realize efficient cutting and prolonging the service life of a cutting part.
In the prior art, cutting control of a heading machine is mainly based on a single parameter, the single dimension is not suitable for an actual working scene, for example, a scheme taking cutting current as a criterion is adopted, when the heading machine cuts unevenly distributed rocks or manual operation is unskilled, the current value is frequently and greatly changed, the swinging speed of a cutting arm is also changed along with the current value, and the swinging speed of the cutting arm is frequently changed, so that the cutting efficiency is reduced.
Disclosure of Invention
In order to solve the technical problems, the invention provides a self-adaptive cutting control system and a self-adaptive cutting control method for a heading machine. The technical scheme of the invention is as follows:
in a first aspect, a self-adaptive cutting control system of a heading machine is provided, which comprises a sensor module, an edge computer and a data acquisition unit, wherein the edge computer and the data acquisition unit are installed on an electric cabinet of the heading machine; the sensor module comprises pressure sensors respectively arranged on a left rotary oil cylinder, a right rotary oil cylinder, a left lifting oil cylinder and a right lifting oil cylinder of the heading machine, stroke displacement sensors arranged on the left rotary oil cylinder and the right rotary oil cylinder, and vibration sensors arranged on the cutting arm and close to the cutting head; the signal output end of the sensor module is connected with the signal input end of the data acquisition unit, and the signal output end of the data acquisition unit is connected with the signal input end of the edge computer;
the sensor module is used for acquiring oil cylinder pressure data, oil cylinder displacement data and cutting arm vibration data in the cutting process of the heading machine and sending the data to the edge computer through the data acquisition unit;
the edge computer is used for processing oil cylinder pressure data, oil cylinder displacement data, cutting arm vibration data, cutting current data and cutting voltage data, and carrying out self-adaptive control on the swinging speed of the cutting arm of the heading machine according to the processing result.
Optionally, when processing the cylinder pressure data, the cylinder displacement data, the cutting arm vibration data, the current data and the voltage data, the edge computer includes: and carrying out abnormal data processing and standardized data processing on each sample data in the oil cylinder pressure data, the oil cylinder displacement data, the cutting arm vibration data, the cutting current data and the cutting voltage data which are acquired at any sampling moment.
Optionally, the specific method for processing the abnormal data is as follows:
if the absolute value of the residual error of any sample data is >3σ, determining the sample data distributed in (mu-3σ, mu+3σ) as an abnormal value, and rejecting the abnormal value;
wherein sigma represents the standard deviation of any sample data, N is the total number of samples, mu is the average value of the sample data, and x i Representative of one of the sample data.
Optionally, the specific method for standardized data processing is as follows:
for a sample data set xi= [ I, V, P1 … P4, ACC1, S1, S2, t ] acquired at any sampling moment, wherein I represents cutting current data, V represents cutting voltage data, P1 to P4 are respectively cylinder pressure data acquired by a pressure sensor, ACC1 is cutting arm vibration data acquired by a vibration sensor, S1 and S2 are cylinder displacement data acquired by two stroke displacement sensors, and t is the sampling moment;
the standardized data processing formula is:
wherein X is a measured value of any sample data except the sampling time in Xi,
for the maximum value of the sample data,
for the minimum value of the sample data, X' represents the value of the sample data after normalization data processing.
Optionally, when the edge computer adaptively controls the swing speed of the cutting arm of the heading machine according to the processing result, the edge computer comprises:
inputting the processing result into a pre-trained working condition prediction classification model;
determining the current cutting working condition of the heading machine according to the output of the working condition prediction classification model;
determining the current expected swing speed of the heading machine according to the current cutting working condition of the heading machine and the corresponding relation between the preset cutting working condition and the expected swing speed;
the current actual swing speed of the tunneling machine is obtained, and the current actual swing speed of the tunneling machine is adjusted to the current expected swing speed of the tunneling machine through a PID closed-loop control algorithm.
Optionally, when the edge computer adaptively controls the swing speed of the cutting arm of the heading machine according to the processing result, the edge computer further comprises:
determining whether the cutting head of the heading machine runs to the limit position defined by the current heading path according to the measured value of the travel displacement sensor and the current heading path of the heading machine in real time;
if the cutting head of the heading machine runs to the limit position defined by the current heading path, the next heading path of the heading machine is obtained, and the swinging speed of the cutting arm is continuously controlled in a self-adaptive mode.
In a second aspect, a method for controlling adaptive cutting of a heading machine is provided, including the steps of:
the sensor module acquires oil cylinder pressure data, oil cylinder displacement data and cutting arm vibration data in the cutting process of the heading machine, and sends the data to the edge computer through the data acquisition unit;
the edge computer processes the oil cylinder pressure data, the oil cylinder displacement data, the cutting arm vibration data, the cutting current data and the cutting voltage data, and adaptively controls the swinging speed of the cutting arm of the heading machine according to the processing result.
Optionally, the edge computer processes cylinder pressure data, cylinder displacement data, cutting arm vibration data, cutting current data, and cutting voltage data, including: abnormal data processing and standardized data processing are carried out on each data of oil cylinder pressure data, oil cylinder displacement data, cutting arm vibration data, cutting current data and cutting voltage data which are acquired at any sampling moment;
the specific method for processing the abnormal data comprises the following steps:
if the absolute value of the residual error of any sample data is >3σ, determining the sample data distributed in (mu-3σ, mu+3σ) as an abnormal value, and rejecting the abnormal value;
wherein sigma represents the standard deviation of any sample data, N is the total number of samples, mu is the average value of the sample data, and x i Representative of one of the sample data;
the specific method for standardized data processing comprises the following steps:
for a sample data set xi= [ I, V, P1 … P4, ACC1, S1, S2, t ] acquired at any sampling moment, wherein I represents cutting current data, V represents cutting voltage data, P1 to P4 are respectively cylinder pressure data acquired by a pressure sensor, ACC1 is cutting arm vibration data acquired by a vibration sensor, S1 and S2 are cylinder displacement data acquired by two stroke displacement sensors, and t is the sampling moment;
the standardized data processing formula is:
wherein X is a measured value of any sample data except the sampling time in Xi,
for the maximum value of the sample data,
for the minimum value of the sample data, X' represents the value of the sample data after normalization data processing.
Optionally, the adaptively controlling the swing speed of the cutting arm of the heading machine according to the processing result includes:
inputting the processing result into a pre-trained working condition prediction classification model;
determining the current cutting working condition of the heading machine according to the output of the working condition prediction classification model;
determining the current expected swing speed of the heading machine according to the current cutting working condition of the heading machine and the corresponding relation between the preset cutting working condition and the expected swing speed;
the current actual swing speed of the tunneling machine is obtained, and the current actual swing speed of the tunneling machine is adjusted to the current expected swing speed of the tunneling machine through a PID closed-loop control algorithm.
Optionally, when the swinging speed of the cutting arm of the heading machine is adaptively controlled according to the processing result, the method further includes:
determining whether the cutting head of the heading machine runs to the limit position defined by the current heading path according to the measured value of the travel displacement sensor and the current heading path of the heading machine in real time;
if the cutting head of the heading machine runs to the limit position defined by the current heading path, the next heading path of the heading machine is obtained, and the swinging speed of the cutting arm is continuously controlled in a self-adaptive mode.
All the above optional technical solutions can be arbitrarily combined, and the detailed description of the structures after one-to-one combination is omitted.
By means of the scheme, the beneficial effects of the invention are as follows:
the sensor module, the edge computer and the data acquisition unit are arranged, and the sensor module comprises a pressure sensor, a stroke displacement sensor and a vibration sensor; the sensor module is used for acquiring oil cylinder pressure data, oil cylinder displacement data and cutting arm vibration data in the cutting process of the heading machine and sending the data to the edge computer through the data acquisition unit; the edge computer is used for processing oil cylinder pressure data, oil cylinder displacement data, cutting arm vibration data, cutting current data and cutting voltage data, and adaptively controlling the swinging speed of the cutting arm of the heading machine according to the processing result. In addition, timeliness and accuracy of data processing are improved by adopting a mode of combining an edge computer with a data acquisition unit.
The foregoing description is only an overview of the present invention, and is intended to provide a better understanding of the present invention, as it is embodied in the following description, with reference to the preferred embodiments of the present invention and the accompanying drawings.
Drawings
Fig. 1 is a perspective view of a heading machine provided by the invention.
Fig. 2 is a front view of fig. 1.
Fig. 3 is a top view of fig. 1.
FIG. 4 is a schematic diagram of the connection of various types of sensors to a data acquisition unit and an edge computer in an embodiment of the invention.
Fig. 5 is an overall control flow diagram of an embodiment of the present invention.
Detailed Description
The following describes in further detail the embodiments of the present invention with reference to the drawings and examples. The following examples are illustrative of the invention and are not intended to limit the scope of the invention.
As shown in fig. 1 to 3, the self-adaptive cutting control system of the heading machine provided by the invention comprises a sensor module, an edge computer 9 and a data acquisition unit 10, wherein the edge computer 9 and the data acquisition unit 10 are arranged on an electric cabinet 11 of the heading machine; the sensor module comprises pressure sensors 5 respectively arranged on a left rotary oil cylinder 1, a right rotary oil cylinder 2, a left lifting oil cylinder 3 and a right lifting oil cylinder 4 of the development machine, a travel displacement sensor 6 arranged on the left rotary oil cylinder 1 and the right rotary oil cylinder 2, and a vibration sensor 8 arranged on a cutting arm 7 and close to a cutting head; the signal output end of the sensor module is connected with the signal input end of the data acquisition unit 10, and the signal output end of the data acquisition unit 10 is connected with the signal input end of the edge computer 9; the sensor module is used for acquiring oil cylinder pressure data, oil cylinder displacement data and cutting arm vibration data in the cutting process of the heading machine and sending the data to the edge computer 9 through the data acquisition unit 10; the edge computer 9 is used for processing oil cylinder pressure data, oil cylinder displacement data, cutting arm vibration data, cutting current data and cutting voltage data and carrying out self-adaptive control on the swinging speed of the cutting arm of the heading machine according to processing results.
In addition, the edge computer 9 is also used for displaying relevant electrical parameters of the heading machine, cutting relevant functional parameter interfaces and the like in real time. The relevant electrical parameters include cutting current data, cutting voltage data, and the like.
In the embodiment of the invention, the pressure sensor 5 can be a miniature CYB-20S-Z05 sputtering pressure transmitter for Wirst navigation, the miniature pressure transmitter can provide high-performance and long-term stability pressure measurement, the output and electrical and pressure connection adopt standard interfaces to be suitable for most application occasions, and the compact structure is also particularly suitable for devices with high installation space requirements. According to the reference data and the related query, the pressure change in the cutting process of the heading machine is about 0-20 mpa, so that the embodiment of the invention specifically selects a two-wire pressure sensor with the measuring range of 0-40mpa and the precision of 0.5%. The measuring range of the vibration sensor 8 can be selected to be 0-20 mm/s, and the two-wire aviation plug pressure transmitter is manufactured in a wiring mode. The stroke displacement sensor 6 is selected to have a measuring range of 0-1500 mm, and the wiring mode is a four-wire system.
After the various types of sensors are selected, the various types of sensors are connected to the edge computer 9 through the data acquisition unit 10, as shown in fig. 4, which is a schematic diagram of the connection relationship between the various types of sensors and the data acquisition unit 10 and the edge computer 9 in the invention. Specifically, the two-wire system sensor is characterized in that the one power wire is a loop wire, the four-wire system is divided into a positive power supply, a negative power supply, a positive signal and a negative signal, and various sensors are wired according to a sensor instruction. In the edge computer 9, the computing, storage and network resources all adopt the virtualization technology, the hardware resources are pooled, and the intelligent scheduling is carried out by software, so that the mobile edge computer is greatly convenient for realizing uniform resource management, and meanwhile, the network virtualization technology improves the intelligent degree of data transmission and reduces the transmission time.
Optionally, the edge computer 9 processes the cylinder pressure data, the cylinder displacement data, the cutting arm vibration data, the current data and the voltage data, and includes: and carrying out abnormal data processing and standardized data processing on each sample data in the oil cylinder pressure data, the oil cylinder displacement data, the cutting arm vibration data, the cutting current data and the cutting voltage data which are acquired at any sampling moment.
The specific method for processing the abnormal data comprises the following steps:
if the absolute value of the residual error of any sample data is >3σ, determining the sample data distributed in (mu-3σ, mu+3σ) as an abnormal value, and rejecting the abnormal value;
wherein sigma represents the standard deviation of any sample data, N is the total number of samples, mu is the average value of the sample data, and x i Representative of one of the sample data. The sample data is any type of data among cutting current data, cutting voltage data, cylinder pressure data, cutting arm vibration data and cylinder displacement data.
The examples of the present invention demonstrate that the probability of sample data being distributed in (μ -3σ, μ+3σ) is 0.9974, i.e., the probability of going outside this range is less than 0.3%. Therefore, the noise data in the sample data can be removed by removing the data in one field according to the 3 sigma principle, so that the calculation amount of an edge computer is reduced.
Further, the specific method for standardized data processing comprises the following steps:
for a sample data set xi= [ I, V, P1 … P4, ACC1, S1, S2, t ] acquired at any sampling moment, wherein I represents cutting current data, V represents cutting voltage data, P1 to P4 are respectively cylinder pressure data acquired by a pressure sensor 5, ACC1 is cutting arm vibration data acquired by a vibration sensor 8, S1 and S2 are cylinder displacement data acquired by two stroke displacement sensors 6, and t is the sampling moment;
the standardized data processing formula is:
wherein X is a measured value of any sample data except the sampling time in Xi,
for the maximum value of the sample data,
for the minimum value of the sample data, X' represents the value of the sample data after normalization data processing.
After standardized data processing is performed on cutting current data, cutting voltage data, oil cylinder pressure data, cutting arm vibration data and oil cylinder displacement data in the sample data set through the above formula, different types of data can be normalized, and cutting working condition identification is conveniently performed by the subsequent edge computer 9.
Optionally, when the edge computer 9 adaptively controls the swing speed of the cutting arm of the heading machine according to the processing result, the method may include: inputting the processing result into a pre-trained working condition prediction classification model; determining the current cutting working condition of the heading machine according to the output of the working condition prediction classification model; determining the current expected swing speed of the heading machine according to the current cutting working condition of the heading machine and the corresponding relation between the preset cutting working condition and the expected swing speed; the current actual swing speed of the tunneling machine is obtained, and the current actual swing speed of the tunneling machine is adjusted to the current expected swing speed of the tunneling machine through a PID closed-loop control algorithm.
The working condition prediction classification model includes, but is not limited to, SVM (support vector machine).
The general working conditions in the well are divided into the following categories: the coal cutting working conditions, coal rock mixing working conditions and rock cutting working conditions are divided into soft coal, medium hard coal and hard coal from soft to hard according to different hardness coefficients, and the rock is divided into soft rock, medium hard rock and hard rock from soft to hard, so that the cutting working conditions of the heading machine comprise a soft coal cutting working condition, a medium hard coal cutting working condition, a soft rock cutting working condition, a medium hard rock cutting working condition, a soft coal soft rock and coal rock mixing working condition, a soft coal medium hard rock and coal rock mixing working condition, a medium hard coal and soft rock coal rock mixing working condition, a medium hard rock and coal rock mixing working condition, a medium hard coal and hard rock mixing working condition, a hard coal medium hard rock and coal rock mixing working condition, and a hard coal and hard coal rock mixing working condition.
Further, the output of the working condition prediction classification model is the probability of various different working conditions, and the working condition with the maximum probability value is the current cutting working condition of the heading machine.
Further, the embodiment of the invention can determine the hardness ranges of the coal and rock corresponding to various underground working conditions through an expert system, set the swinging speed to be inversely proportional to the hardness of the coal and rock, namely, the swinging speed is slower as the hardness of the coal and rock is larger, and find the expected swinging speed corresponding to different hardness of the coal and rock through a large number of field experiment tests on cutting power in the cutting process, namely, establish the corresponding relation between the cutting working condition and the expected swinging speed. On the basis, after the current cutting working condition of the heading machine is determined, the current expected swing speed of the heading machine can be determined according to the corresponding relation.
Specifically, when the current actual swing speed of the tunneling machine is adjusted to the current expected swing speed of the tunneling machine through a PID closed-loop control algorithm, the current actual swing speed of the tunneling machine can be achieved by observing the power change condition of the tunneling machine, and when the power change tends to be stable, the current actual swing speed of the tunneling machine is determined to be close to the expected swing speed.
In summary, as shown in fig. 5, an overall control flow chart of an embodiment of the present invention is shown.
Optionally, in the embodiment of the present invention, when the edge computer 9 adaptively controls the swing speed of the cutting arm of the heading machine according to the processing result, the method may further include: determining whether the cutting head of the heading machine runs to the limit position (a left limit value, a right limit value and an upper limit value and a lower limit value) defined by the current heading path according to the measured value of the travel displacement sensor 6 and the current heading path of the heading machine in real time; if the cutting head of the heading machine runs to the limit position defined by the current heading path, the next heading path of the heading machine is obtained, and the swinging speed of the cutting arm is continuously controlled in a self-adaptive mode.
The embodiment of the invention adaptively controls the swinging speed of the cutting arm of the heading machine and is combined with the self-defined cutting of the heading machine, thereby realizing the automation and the intellectualization of the cutting of the heading machine.
The embodiment of the invention also provides a self-adaptive cutting control method of the heading machine, which comprises the following steps:
s1, a sensor module collects oil cylinder pressure data, oil cylinder displacement data and cutting arm vibration data in the cutting process of a development machine and sends the data to an edge computer 9 through a data collection unit 10;
s2, the edge computer 9 processes the oil cylinder pressure data, the oil cylinder displacement data, the cutting arm vibration data, the cutting current data and the cutting voltage data, and adaptively controls the swinging speed of the cutting arm of the heading machine according to the processing result.
The edge computer 9 processes the cylinder pressure data, the cylinder displacement data, the cutting arm vibration data, the cutting current data and the cutting voltage data, and comprises the following steps: abnormal data processing and standardized data processing are carried out on each data of oil cylinder pressure data, oil cylinder displacement data, cutting arm vibration data, cutting current data and cutting voltage data which are acquired at any sampling moment;
the specific method for processing the abnormal data comprises the following steps:
if the absolute value of the residual error of any sample data is >3σ, determining the sample data distributed in (mu-3σ, mu+3σ) as an abnormal value, and rejecting the abnormal value;
wherein sigma represents the standard deviation of any sample data, N is the total number of samples, mu is the average value of the sample data, and x i Representative of one of the sample data;
the specific method for standardized data processing comprises the following steps:
for a sample data set xi= [ I, V, P1 … P4, ACC1, S1, S2, t ] acquired at any sampling moment, wherein I represents cutting current data, V represents cutting voltage data, P1 to P4 are respectively cylinder pressure data acquired by a pressure sensor 5, ACC1 is cutting arm vibration data acquired by a vibration sensor 8, S1 and S2 are cylinder displacement data acquired by two stroke displacement sensors 6, and t is the sampling moment;
the standardized data processing formula is:
wherein X is a measured value of any sample data except the sampling time in Xi,
for the maximum value of the sample data,
for the minimum value of the sample data, X' represents the value of the sample data after normalization data processing.
Optionally, the adaptively controlling the swing speed of the cutting arm of the heading machine according to the processing result includes:
inputting the processing result into a pre-trained working condition prediction classification model;
determining the current cutting working condition of the heading machine according to the output of the working condition prediction classification model;
determining the current expected swing speed of the heading machine according to the current cutting working condition of the heading machine and the corresponding relation between the preset cutting working condition and the expected swing speed;
the current actual swing speed of the tunneling machine is obtained, and the current actual swing speed of the tunneling machine is adjusted to the current expected swing speed of the tunneling machine through a PID closed-loop control algorithm.
Further, when the swinging speed of the cutting arm of the heading machine is adaptively controlled according to the processing result, the method further comprises the following steps: determining whether the cutting head of the heading machine runs to the limit position defined by the current tunneling path according to the measured value of the travel displacement sensor 6 and the current tunneling path of the heading machine in real time; if the cutting head of the heading machine runs to the limit position defined by the current heading path, the next heading path of the heading machine is obtained, and the swinging speed of the cutting arm is continuously controlled in a self-adaptive mode.
Regarding the specific implementation manner of the above method embodiment, the same principle as that in the above system embodiment may be specifically referred to the content in the above system embodiment, and the description of the embodiment of the present invention is not repeated.
The above description is only of the preferred embodiments of the present invention and is not intended to limit the present invention, and it should be noted that it is possible for those skilled in the art to make several improvements and modifications without departing from the technical principle of the present invention, and these improvements and modifications should also be regarded as the protection scope of the present invention.
Claims (6)
1. The self-adaptive cutting control system of the heading machine is characterized by comprising a sensor module, an edge computer (9) and a data acquisition unit (10), wherein the edge computer (9) and the data acquisition unit (10) are arranged on an electric cabinet (11) of the heading machine; the sensor module comprises pressure sensors (5) respectively arranged on a left rotary oil cylinder (1), a right rotary oil cylinder (2), a left lifting oil cylinder (3) and a right lifting oil cylinder (4) of the tunneling machine, stroke displacement sensors (6) arranged on the left rotary oil cylinder (1) and the right rotary oil cylinder (2) and vibration sensors (8) arranged on a cutting arm (7) and close to a cutting head part; the signal output end of the sensor module is connected with the signal input end of the data acquisition unit (10), and the signal output end of the data acquisition unit (10) is connected with the signal input end of the edge computer (9);
the sensor module is used for acquiring oil cylinder pressure data, oil cylinder displacement data and cutting arm vibration data in the cutting process of the heading machine and sending the data to the edge computer (9) through the data acquisition unit (10);
the edge computer (9) is used for processing oil cylinder pressure data, oil cylinder displacement data, cutting arm vibration data, cutting current data and cutting voltage data and adaptively controlling the swinging speed of the cutting arm of the heading machine according to the processing result;
the edge computer (9) is used for adaptively controlling the swing speed of a cutting arm of the heading machine according to the processing result, and comprises the following components:
inputting the processing result into a pre-trained working condition prediction classification model;
determining the current cutting working condition of the heading machine according to the output of the working condition prediction classification model;
determining the current expected swing speed of the heading machine according to the current cutting working condition of the heading machine and the corresponding relation between the preset cutting working condition and the expected swing speed;
acquiring the current actual swing speed of the heading machine, and adjusting the current actual swing speed of the heading machine to the current expected swing speed of the heading machine through a PID closed-loop control algorithm;
the edge computer (9) is used for adaptively controlling the swing speed of a cutting arm of the heading machine according to the processing result, and further comprises:
determining whether the cutting head of the heading machine runs to the limit position defined by the current tunneling path according to the measured value of the travel displacement sensor (6) and the current tunneling path of the heading machine in real time;
if the cutting head of the heading machine runs to the limit position defined by the current heading path, the next heading path of the heading machine is obtained, and the swinging speed of the cutting arm is continuously controlled in a self-adaptive mode.
2. The adaptive cutting control system according to claim 1, wherein the edge computer (9) when processing cylinder pressure data, cylinder displacement data, cutting arm vibration data, current data, and voltage data, comprises: and carrying out abnormal data processing and standardized data processing on each sample data in the oil cylinder pressure data, the oil cylinder displacement data, the cutting arm vibration data, the cutting current data and the cutting voltage data which are acquired at any sampling moment.
3. The adaptive cutting control system of a heading machine according to claim 2, wherein the specific method of abnormal data processing is:
if the absolute value of the residual error of any sample data is >3σ, determining the sample data distributed in (mu-3σ, mu+3σ) as an abnormal value, and rejecting the abnormal value;
wherein sigma represents the standard deviation of any sample data, N is the total number of samples, mu is the average value of the sample data, and x i Representative of one of the sample data.
4. The adaptive cutting control system of a heading machine according to claim 2, wherein the specific method of standardized data processing is:
for a sample data set xi= [ I, V, P1 … P4, ACC1, S1, S2, t ] acquired at any sampling moment, wherein I represents cutting current data, V represents cutting voltage data, P1 to P4 are respectively cylinder pressure data acquired by a pressure sensor (5), ACC1 is cutting arm vibration data acquired by a vibration sensor (8), S1 and S2 are cylinder displacement data acquired by two stroke displacement sensors (6), and t is sampling moment;
the standardized data processing formula is:
the method comprises the steps of carrying out a first treatment on the surface of the Wherein X is the measured value of any sample data except the sampling time in Xi, ++>
For the maximum value of the sample data, +.>
For the minimum value of the sample data, X' represents the value of the sample data after normalization data processing.
5. The self-adaptive cutting control method of the heading machine is characterized by comprising the following steps of:
the sensor module acquires oil cylinder pressure data, oil cylinder displacement data and cutting arm vibration data in the cutting process of the heading machine, and sends the data to the edge computer (9) through the data acquisition unit (10);
the edge computer (9) processes the oil cylinder pressure data, the oil cylinder displacement data, the cutting arm vibration data, the cutting current data and the cutting voltage data, and adaptively controls the swinging speed of the cutting arm of the heading machine according to the processing result;
the self-adaptive control of the swing speed of the cutting arm of the heading machine according to the processing result comprises the following steps:
inputting the processing result into a pre-trained working condition prediction classification model;
determining the current cutting working condition of the heading machine according to the output of the working condition prediction classification model;
determining the current expected swing speed of the heading machine according to the current cutting working condition of the heading machine and the corresponding relation between the preset cutting working condition and the expected swing speed;
acquiring the current actual swing speed of the heading machine, and adjusting the current actual swing speed of the heading machine to the current expected swing speed of the heading machine through a PID closed-loop control algorithm;
when the self-adaptive control is carried out on the swing speed of the cutting arm of the heading machine according to the processing result, the method further comprises the following steps:
determining whether the cutting head of the heading machine runs to the limit position defined by the current tunneling path according to the measured value of the travel displacement sensor (6) and the current tunneling path of the heading machine in real time;
if the cutting head of the heading machine runs to the limit position defined by the current heading path, the next heading path of the heading machine is obtained, and the swinging speed of the cutting arm is continuously controlled in a self-adaptive mode.
6. The adaptive cutting control method of a heading machine according to claim 5, wherein the processing of the cylinder pressure data, the cylinder displacement data, the cutting arm vibration data, the cutting current data, and the cutting voltage data by the edge computer (9) includes: abnormal data processing and standardized data processing are carried out on each data of oil cylinder pressure data, oil cylinder displacement data, cutting arm vibration data, cutting current data and cutting voltage data which are acquired at any sampling moment;
the specific method for processing the abnormal data comprises the following steps:
if the absolute value of the residual error of any sample data is >3σ, determining the sample data distributed in (mu-3σ, mu+3σ) as an abnormal value, and rejecting the abnormal value;
wherein sigma represents the standard deviation of any sample data, N is the total number of samples, mu is the average value of the sample data, and x i Representative isOne of the sample data;
the specific method for standardized data processing comprises the following steps:
for a sample data set xi= [ I, V, P1 … P4, ACC1, S1, S2, t ] acquired at any sampling moment, wherein I represents cutting current data, V represents cutting voltage data, P1 to P4 are respectively cylinder pressure data acquired by a pressure sensor (5), ACC1 is cutting arm vibration data acquired by a vibration sensor (8), S1 and S2 are cylinder displacement data acquired by two stroke displacement sensors (6), and t is sampling moment;
the standardized data processing formula is:
the method comprises the steps of carrying out a first treatment on the surface of the Wherein X is the measured value of any sample data except the sampling time in Xi, ++>
For the maximum value of the sample data, +.>
For the minimum value of the sample data, X' represents the value of the sample data after normalization data processing. />
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310067306.8A CN115788477B (en) | 2023-02-06 | 2023-02-06 | Self-adaptive cutting control system and method for heading machine |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310067306.8A CN115788477B (en) | 2023-02-06 | 2023-02-06 | Self-adaptive cutting control system and method for heading machine |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115788477A CN115788477A (en) | 2023-03-14 |
| CN115788477B true CN115788477B (en) | 2023-05-30 |
Family
ID=85429953
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310067306.8A Active CN115788477B (en) | 2023-02-06 | 2023-02-06 | Self-adaptive cutting control system and method for heading machine |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115788477B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116956165B (en) * | 2023-09-21 | 2023-12-15 | 中国船舶集团有限公司第七〇七研究所 | Multi-heading machine cutting part running state classification method |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH0492082A (en) * | 1990-08-03 | 1992-03-25 | Komatsu Ltd | Automatic directional control method of shield excavator |
| CN103827398A (en) * | 2011-08-03 | 2014-05-28 | 乔伊·姆·特拉华公司 | Automated operations of mining machine |
| CN113006793A (en) * | 2021-04-28 | 2021-06-22 | 北京坤世拓智能科技有限公司 | Intelligent cutting combined control system and method for boom-type heading machine |
Family Cites Families (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH0492081A (en) * | 1990-08-03 | 1992-03-25 | Komatsu Ltd | Automatic direction control method of shield excavator |
| JP2960815B2 (en) * | 1992-05-25 | 1999-10-12 | 前田建設工業株式会社 | Attitude control method for shield machine |
| CN102854838B (en) * | 2012-08-29 | 2016-01-06 | 内蒙古北方重工业集团有限公司 | Roadway self-adaptation cut system and adaptive remote control method |
| CN103147756B (en) * | 2013-03-20 | 2017-03-29 | 中国矿业大学(北京) | A kind of heading machine memory cutting control system and method thereof |
| CN107269275B (en) * | 2017-06-15 | 2019-02-12 | 中国矿业大学(北京) | A kind of boom-type roadheader cutting arm slew rate adaptive control system and method |
| CN210134942U (en) * | 2019-03-14 | 2020-03-10 | 中铁工程装备集团隧道设备制造有限公司 | Cutting control device of heading machine and cantilever heading machine |
| CN109931072B (en) * | 2019-03-14 | 2023-11-14 | 中铁工程装备集团隧道设备制造有限公司 | Cutting control device and method of heading machine and cantilever heading machine |
| CN114233312B (en) * | 2021-11-17 | 2024-03-22 | 中铁工程装备集团隧道设备制造有限公司 | Free section cutting control system and control method of cantilever heading machine |
| CN115628930B (en) * | 2022-12-16 | 2023-03-10 | 太原理工大学 | Method for predicting underground cutting working condition of heading machine based on RBF neural network |
-
2023
- 2023-02-06 CN CN202310067306.8A patent/CN115788477B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH0492082A (en) * | 1990-08-03 | 1992-03-25 | Komatsu Ltd | Automatic directional control method of shield excavator |
| CN103827398A (en) * | 2011-08-03 | 2014-05-28 | 乔伊·姆·特拉华公司 | Automated operations of mining machine |
| CN113006793A (en) * | 2021-04-28 | 2021-06-22 | 北京坤世拓智能科技有限公司 | Intelligent cutting combined control system and method for boom-type heading machine |
Non-Patent Citations (3)
| Title |
|---|
| EBZ260悬臂式掘进机自动化改造;许秀芳;王亮;安栋;;煤矿机械(第02期);全文 * |
| 基于PCC的掘进机监控系统硬件设计;郑建义;;工业设计(第08期);全文 * |
| 改进的PSO算法在掘进机掘进系统中的应用;李文;杨振南;;控制工程(第10期);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115788477A (en) | 2023-03-14 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN115788477B (en) | Self-adaptive cutting control system and method for heading machine | |
| BR0315929A (en) | Transmission overhead line conductor status controller | |
| CN105422088B (en) | Coal mine tunnel geological parameter on-line monitoring system | |
| CN112050782B (en) | Power-based industrial mechanical arm abnormal motion online detection method | |
| CN1706130A (en) | System and method for providing a virtual wireless | |
| CN115628930B (en) | Method for predicting underground cutting working condition of heading machine based on RBF neural network | |
| CN102490086B (en) | System for monitoring working state of boring rod in real time | |
| CN111561543B (en) | Vibration reduction system of tunneling machine inertial navigation combined positioning device and using method thereof | |
| CN115941529A (en) | Cable tunnel detection method and system based on robot | |
| CN112906202A (en) | Mining method and device based on geographic information, storage medium and electronic device | |
| CN115085994A (en) | Information centralized safety management system of internal physical machine of cloud computing | |
| CN114800049B (en) | Grating ruler processing operation signal error compensation system | |
| CN115795369B (en) | Coal-rock interface identification method and device | |
| CN108803485B (en) | I5iport protocol-based external thermal error compensation method for numerical control machine tool | |
| CN1533522A (en) | Method for data exchange between operating and monitoring program and field device | |
| CN116820029A (en) | Real-time dynamic multi-objective optimization method for technological parameters of numerical control machine tool under information physical system | |
| CN114856604A (en) | Tunneling machine control method, device, equipment and storage medium | |
| CN203827385U (en) | Underground-water layered automatic monitoring system | |
| CN114089727A (en) | Central control method and system for deep-sea intelligent mobile operation platform | |
| Wu et al. | Research on measurement and control system of common parameters of agricultural equipment based on wireless transmission | |
| CN117291316B (en) | Cabin positioning system for ship unloader based on laser scanner | |
| CN115097798A (en) | TBM adaptive machining parameter adjusting system and method based on rock composition | |
| CN109947780A (en) | Method, device and system for updating cache by using agent program | |
| CN115508511B (en) | Sensor self-adaptive calibration method based on full-parameter feature analysis of gridding equipment | |
| CN213104923U (en) | Special accurate pipe feeding positioning device for numerical control pipe thread machining lathe |
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 |