CN115961996A - Coal mine main ventilator frequency converter speed regulation method based on random wind speed field prediction - Google Patents
Coal mine main ventilator frequency converter speed regulation method based on random wind speed field prediction Download PDFInfo
- Publication number
- CN115961996A CN115961996A CN202211686770.7A CN202211686770A CN115961996A CN 115961996 A CN115961996 A CN 115961996A CN 202211686770 A CN202211686770 A CN 202211686770A CN 115961996 A CN115961996 A CN 115961996A
- Authority
- CN
- China
- Prior art keywords
- wind
- neural network
- wind measuring
- graph
- frequency converter
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
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
- Y02B—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO BUILDINGS, e.g. HOUSING, HOUSE APPLIANCES OR RELATED END-USER APPLICATIONS
- Y02B30/00—Energy efficient heating, ventilation or air conditioning [HVAC]
- Y02B30/70—Efficient control or regulation technologies, e.g. for control of refrigerant flow, motor or heating
Landscapes
- Ventilation (AREA)
Abstract
The invention provides a coal mine main ventilator frequency converter speed regulation method based on random wind speed field prediction, which comprises the steps of firstly, arranging wind measuring points on an underground stope working face, a tunneling working face and a wind well, carrying out information prediction according to various data monitored by the wind measuring points, establishing a graph neural network to calculate air supply quantity, obtaining the relation between the control frequency of a main ventilator frequency converter and the real-time air quantity according to the real-time air quantity calculated by the graph neural network, and calculating the frequency converter control frequency. The beneficial effects are that: the method is based on a random field as a theory, each underground key ventilation detection is used as a vertex of the random field, and the result of the ventilation detection is used as the attribute of the vertex to establish an underground ventilation control random field model; and then, a prediction model of the field data is established to predict future information of the wind field, so that the ventilation regulation of the main ventilator is guided, and the response speed of the ventilation control is effectively improved.
Description
Technical Field
The invention relates to the technical field, in particular to a coal mine main ventilator frequency converter speed regulation method based on random wind speed field prediction.
Background
A coal mine underground ventilation system is one of systems of coal mine safety production cores. The method comprises two types of forced ventilation and extraction ventilation, wherein the extraction ventilation process is as follows: fresh air enters all underground roadways through a main well, an auxiliary well or a special blast well. Meanwhile, the main ventilation work of the well head of the return air well forms negative pressure, turbid airflow of each underground roadway is sucked out, and therefore the purpose of air circulation is achieved. The core work sites downhole are the stope and the face, for which ventilation safety is required at such core work sites.
The main ventilator of the coal mine is a key device for ensuring the safety of underground production. At present, the main ventilator has two control methods of fixed frequency and variable frequency. The method of frequency setting is to set the running frequency of the main ventilator at 50Hz, the motor pumps the underground dirty airflow according to the rated rotating speed, the air quantity is mainly controlled according to the angle of the air door, and the mode is not energy-saving. The mode of frequency converter control is adopted, and the rotating speed of the fan is controlled through the frequency converter, so that the air quantity of the main air shaft is adjusted. The adjusting means includes two kinds of frequency adjustment and air door adjustment. To further save energy, it is common to adjust the frequency of the motor by opening the door to a maximum.
At present, the adjusting mode of the main ventilator is rated operation and manual adjusting mode, and the adjusting mode does not have the capability of global intelligent operation. The common method is that information such as wind speed and harmful gas concentration is measured at the top point of the well, and a ground operator is informed through a telephone to control the air volume of the main ventilator. The method only depends on the result of underground single-point detection, and is difficult to form global regulation in complex underground roadways. In addition, the coal mine ventilation system is a large time lag system, namely after the main ventilator is adjusted, the required air volume can be obtained in the underground for a long time, and the overall adjustment time delay of the system is large.
At present, PID regulation and a derivative algorithm combining a partial intelligent algorithm and PID are adopted as control methods for a main ventilator. Such as fuzzy PID regulation, neural network PID regulation, etc. The method can play a certain intelligent regulation role, but the regulation principle is still intelligent regulation developed on the premise of acquiring the air quantity demand. This air volume requirement is usually a single point requirement, which may cause negative benefits at other points of demand. In addition, the current regulation methods are based on post regulation, i.e. the ventilator is regulated according to the current air volume at a certain point. Due to the fact that the delay time of the ventilation system is long, a long time is needed for changing the ventilation condition of the air quantity request point after the main ventilator is adjusted.
Disclosure of Invention
The invention provides a coal mine main ventilator frequency converter speed regulation method based on random wind speed field prediction based on at least one of the technical problems.
A coal mine main ventilator frequency converter speed regulation method based on random wind speed field prediction comprises the following steps:
s1, determining wind measuring points and collecting data of the wind measuring points, wherein the first wind measuring point and the second wind measuring point respectively monitor the ventilation of two stope faces in real time, the third wind measuring point monitors the ventilation of a driving face in real time, the fourth wind measuring point monitors the ventilation condition of an air shaft in real time, the data of the wind speed V, the wind volume C, the temperature T, the gas concentration W and the carbon dioxide concentration G of each wind measuring point are received, the number of the detecting points is set to be i, and the corresponding detecting result at the moment T is: vi (t), ci (t), ti (t), wi (t), gi (t), i =1,2,3,4;
s2, forecasting monitoring information of each anemometry point, and setting the current time as t and the input information of the ith detection point as follows:
X i (t)＝[V i (t)，C i (t)，T i (t)，W i (t)，G i (t)] (1)
the method comprises the following specific steps:
21 The LSTM architecture of the Pytrch is selected as a prediction model, the length of an input sequence is n =20, and the prediction length is m;
22 LSTM is set as follows: input length =20, input dimension =5, number of LSTM layers 1, output length m, output dimension =5,
the output length is the predicted length and reflects the time lag characteristic of ventilation regulation, and the m calculation method comprises the following steps:
in the formula, T f For the sampling time, it can be set; t is l The flow time of the dirty wind reaching the main ventilator from the furthest wind measuring point in the well is measured in the field;
3) Establishing the LSTM neural network for all wind measuring points, and predicting monitoring data of each wind measuring point;
4) And training the LSTM neural network, collecting historical data, making a data sample, and training, wherein the loss function is a mean square error function.
S3, calculating the air volume of the main ventilator based on the graph neural network, and establishing a random field model P (Y | X) of the wind measuring points by using the graph neural network, wherein X represents the input information of all the wind measuring points; y represents the air volume of each air measuring point, and the air volume Y is between 0 and 1; when the value is 0, the required air volume is represented, when the value is 1, the required maximum air volume is represented, and the random field model P (Y | X) essentially represents a probability value which can be approximated by a graph neural network;
for this purpose, the following steps are established:
31 Input information X = [ X ] for building a neural network of a graph 1 ，X 2 ，X 3 ，X 4 ]Real-time detection values for each wind measurement point, wherein,
X i ＝[V i (t)，C i (t)，T i (t)，W i (t)，G i (t)] (3)
32 Output information for building a neural network of a graph, Y = [ Y ] 1 ，Y 2 ，Y 3 ，Y 4 ]The requirement of each wind measuring point on the wind quantity is met;
33 A random field model P (Y | X) of the air volume of each detection point is established, namely the air volume required by each position is not less than 0 and not more than P (Y) under the condition of monitoring data of each wind detection point i I X) is less than or equal to 1, wherein 0 represents no air volume, 1 represents the maximum air volume, and the model is approximated by a graph neural network;
34 Based on the random field model, a graph neural network of each wind measuring point is established, and the graph neural network is composed of a 4-layer graph network structure.
35 Obtaining probability values of all wind measuring points required by the neural network of the graph, introducing the fully-connected neural network, and obtaining the air supply quantity D of the main ventilator;
36 Training a neural network of the graph, collecting real-time monitoring data of an underground wind measuring point, making a sample set, and selecting a mean square error loss function during training until the neural network converges, so that the neural network has the capability of calculating real-time wind volume;
s4, determining a control decision method of the main ventilator frequency converter: frequency converter control frequency f and air volume line
Sex relationship: f (t) = kD (t) (7)
In the formula, k is a constant, and,
can be directly tested on site, when the frequency of the frequency converter is controlled to be 50Hz, the air quantity is maximum D max ；
S5, determining a frequency converter control frequency decision method, which comprises the following steps:
51 Setting the current time as t, and determining a predicted length m according to equation (2);
52 Predict the value at m-th time of each anemometry point from LSTM:
X i (t+m)＝[V i (t+m),C i (t+m)，T i (t+m)，W i (t+m)，G i (t+m)](8)
53 Determining the air volume D (m) at the moment m according to the neural network
54 Determining the frequency converter control frequency f (m) according to equation (7);
55 Starting from the current instant t, until instant t + m, the frequency converter executes the control frequency f (m),
56 The first step is repeated at time t + m to re-predict the re-execution control frequency.
Preferably, in step S3, the neural network is divided into four layers, the input value of each layer is the eigenvalue Fi and the link matrix E, and the input value is calculated with the coal seam weight W to obtain the output eigenvalue F i+1 And a link matrix E, wherein the link matrix E remains constant throughout, i =1,2,3,4; input eigenvalues F of each graph neural network layer i Weight setting, characteristic output value F i+1 Comprises the following steps:
wherein p × q represents a matrix with characteristic values of p rows and q columns;
convolution neural network F for each layer of graph i The specific calculation method comprises the following steps:
a. first layer input F 1 A feature matrix for each wind measurement point:
b. determining a link matrix E, E being a link matrix of each wind measuring point
If the element of the ith row and the jth column in the matrix E is 1, the ith wind measuring point is connected with the jth wind measuring point; if the value is 0, no relation is shown, and all wind measuring points are related in the patent;
c. the output of the characteristic value of the neural network of each layer diagram is as follows:
F i+1 ＝EF i W i (6)
d. according to the neural network, output F 5 The method is essentially a probability value of each wind measurement point on the wind volume demand, and a random field model P (Y | X) of the wind volume of each detection point.
e. Introducing a full-connection neural network to obtain the air supply rate of the main ventilator F 5 And the relation between the air demand of each point and the air supply quantity D of the main ventilator is fitted through the full-connection neural network, so that the air supply quantity D of the main ventilator can be calculated under the condition that the real-time data of each wind measuring point are known.
Has the advantages that: the method is based on a random field as a theory, each underground key ventilation detection is used as a vertex of the random field, and the result of the ventilation detection is used as the attribute of the vertex to establish an underground ventilation control random field model; and then, a prediction model of the field data is established to predict future information of the wind field, so that the ventilation regulation of the main ventilator is guided, and the response speed of the ventilation control is effectively improved.
Drawings
FIG. 1 shows a schematic representation of the downhole ventilation and wind detection point distribution of the present invention;
FIG. 2 is a schematic diagram of a random field model of the present invention;
FIG. 3 shows a schematic diagram of the structure of a wind-point diagram neural network according to the present invention.
Detailed Description
In order that the above objects, features and advantages of the present invention can be more clearly understood, a more particular description of the invention will be rendered by reference to the appended drawings. It should be noted that the embodiments and features of the embodiments of the present application may be combined with each other without conflict.
As shown in fig. 1 to 3, the method for regulating the speed of the frequency converter of the coal mine main ventilator based on the random wind speed field prediction comprises the following steps:
s1, determining wind measuring points and collecting data of the wind measuring points, wherein a first wind measuring point and a second wind measuring point respectively monitor the ventilation of two stope faces in real time, a third wind measuring point monitors the ventilation of a driving face in real time, a fourth wind measuring point monitors the ventilation condition of an air shaft in real time, the data of the wind speed V, the wind volume C, the temperature T, the gas concentration W and the carbon dioxide concentration G of each wind measuring point are received, the number of the detecting points is set to be i, and the corresponding detecting result at the moment T is as follows: vi (t), ci (t), ti (t), wi (t), gi (t), i =1,2,3,4;
s2, predicting the monitoring information of each anemometry point, and setting the current moment as t and the input information of the ith detection point as follows:
X i (t)＝[V i (t)，C i (t)，T i (t)，W i (t)，G i (t)] (1)
the method comprises the following specific steps:
21 The LSTM architecture of the Pytrch is selected as a prediction model, the length of an input sequence is n =20, and the prediction length is m;
22 LSTM is set as follows: input length =20, input dimension =5, number of LSTM layers 1, output length m, output dimension =5,
the output length is the predicted length and reflects the time lag characteristic of ventilation regulation, and the m calculation method comprises the following steps:
in the formula, T f For the sampling time, it can be set; t is l The flow time of the dirty wind reaching the main ventilator from the furthest wind measuring point in the well is measured in the field;
3) Establishing the LSTM neural network for all wind measuring points, and predicting monitoring data of each wind measuring point;
4) And (3) training an LSTM neural network, collecting historical data, making a data sample, and training, wherein the loss function is a mean square error function.
S3, calculating the air volume of the main ventilator based on a graph neural network, and establishing a random field model P (Y | X) of the wind measuring points by using the graph neural network, wherein X represents the input information of all the wind measuring points; y represents the air volume of each air measuring point, and the air volume Y is between 0 and 1; when the value is 0, the required air volume is represented, when the value is 1, the required maximum air volume is represented, and the random field model P (Y | X) essentially represents a probability value which can be approximated by a graph neural network;
for this purpose, the following steps are established:
31 Input information X = [ X ] for building a neural network of a graph 1 ，X 2 ，X 3 ，X 4 ]Detecting values for each wind detection point in real time, wherein X i ＝[V i (t)，C i (t)，T i (t)，W i (t)，G i (t)] (3)
32 Output information for building a neural network of a graph, Y = [ Y ] 1 ，Y 2 ，Y 3 ，Y 4 ]The requirement of each wind measuring point on the wind quantity is met;
33 A random field model P (Y | X) of the air volume of each detection point is established, namely the air volume required by each position is not less than 0 and not more than P (Y) under the condition of monitoring data of each wind detection point i I X) is less than or equal to 1, wherein 0 represents no air volume, 1 represents the maximum air volume, and the model is approximated by a graph neural network;
34 According to the random field model, establishing a graph neural network of each wind measuring point, wherein the graph neural network consists of a 4-layer graph network structure; the neural network of the graph is divided into four layers, and the input value of each layer is a characteristic value F i And a link matrix E, wherein the input value is operated with the coal seam weight W to obtain an output characteristic value F i+1 And a link matrix E, wherein the link matrix E remains constant throughout, i =1,2,3,4; input eigenvalue F of each graph neural network layer i Weight setting, characteristic output value F i+1 Comprises the following steps:
wherein p × q represents a matrix with characteristic values of p rows and q columns;
convolution neural network F for each layer of graph i The specific calculation method comprises the following steps:
a. first layer input F 1 Is one by oneFeature matrix of wind measurement points:
b. determining a link matrix E, wherein the E is the link matrix of each wind measuring point:
if the element of the ith row and the jth column in the matrix E is 1, the ith wind measuring point is connected with the jth wind measuring point; if the value is 0, no relation is shown, and all wind measuring points are related in the patent;
c. the output of the characteristic value of the neural network of each layer diagram is as follows:
F i+1 ＝EF i W i (6)
d. according to the neural network, output F 5 The method is essentially a probability value of each wind measurement point on the wind volume demand, and a random field model P (Y | X) of the wind volume of each detection point.
e. Introducing a full-connection neural network to obtain the air supply rate of the main ventilator F 5 The method is characterized in that the method is used for fitting the relation between the air quantity required by each point and the air quantity D of the main ventilator through a fully connected neural network, so that the air quantity D of the main ventilator can be calculated under the condition that the real-time data of each wind measuring point are known;
35 Obtaining probability values of all wind measuring points required by the neural network of the graph, introducing the fully-connected neural network, and obtaining the air supply quantity D of the main ventilator;
36 Training a neural network of the graph, collecting real-time monitoring data of underground wind measuring points, making a sample set, and selecting a mean square error loss function during training until the neural network converges, so that the neural network has the capability of calculating real-time wind volume;
s4, determining a control decision method of the main ventilator frequency converter: frequency converter control frequency f and air volume line
Sex relationship: f (t) = kD (t) (7)
In the formula, k is a constant, and,
can be directly tested on site, when the frequency of the frequency converter is controlled to be 50Hz, the air quantity is maximum D max ；
S5, determining a frequency converter control frequency decision method, which comprises the following steps:
51 Setting the current time as t, and determining a predicted length m according to the formula (2);
52 The value at m time of each anemometry point is predicted according to the LSTM:
X i (t+m)＝[V i (t+m)，C i (t+m)，T i (t+m)，W i (t+m)，G i (t+m)] (8)
53 Determining the air volume D (m) at the moment m according to the neural network
54 Determining the frequency converter control frequency f (m) according to equation (7);
55 Starting from the current instant t, until instant t + m, the frequency converter executes the control frequency f (m),
56 The first step is repeated at time t + m to re-predict the re-execution control frequency.
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 (2)
1. A coal mine main ventilator frequency converter speed regulation method based on random wind speed field prediction is characterized by comprising the following steps:
s1, determining wind measuring points and collecting data of the wind measuring points, wherein a first wind measuring point and a second wind measuring point respectively monitor the ventilation of two stope faces in real time, a third wind measuring point monitors the ventilation of a driving face in real time, a fourth wind measuring point monitors the ventilation condition of an air shaft in real time, the data of the wind speed V, the wind volume C, the temperature T, the gas concentration W and the carbon dioxide concentration G of each wind measuring point are received, the number of the detecting points is set to be i, and the corresponding detecting result at the moment T is as follows: vi (t), ci (t), ti (t), wi (t), gi (t), i =1,2,3,4;
s2, forecasting monitoring information of each anemometry point, and setting the current time as t and the input information of the ith detection point as follows:
X i (t)＝[V i (t),C i (t),T i (t),W i (t),G i (t)] (1)
the method comprises the following specific steps:
21 The LSTM architecture of the Pytrch is selected as a prediction model, the length of an input sequence is n =20, and the prediction length is m;
22 LSTM is set as follows: input length =20, input dimension =5, number of LSTM layers 1, output length m, output dimension =5,
the output length is the predicted length and reflects the time lag characteristic of ventilation regulation, and the m calculation method comprises the following steps:
in the formula, T f For the sampling time, it can be set; t is l The flow time of the dirty wind reaching the main ventilator from the furthest wind measuring point in the well is measured on site;
3) Establishing the LSTM neural network for all wind measuring points, and predicting monitoring data of each wind measuring point;
4) And (3) training an LSTM neural network, collecting historical data, making a data sample, and training, wherein the loss function is a mean square error function.
S3, calculating the air volume of the main ventilator based on the graph neural network, and establishing a random field model P (Y | X) of the wind measuring points by using the graph neural network, wherein X represents the input information of all the wind measuring points; y represents the air volume of each air measuring point, and the air volume Y is between 0 and 1; when the value is 0, the required air volume is represented, when the value is 1, the required maximum air volume is represented, and the random field model P (Y | X) essentially represents a probability value which can be approximated by a graph neural network;
for this purpose, the following steps are established:
31 Input information X = [ X ") to build a graph neural network 1 ，X 2 ，X 3 ，X 4 ]Real-time detection values for each wind measurement point, wherein,
X i ＝[V i (t)，C i (t)，T i (t)，W i (t)，G i (t)] (3)
32 Output information for building a neural network of a graph, Y = [ Y ] 1 ，Y 2 ，Y 3 ，Y 4 ]The requirement of each wind measuring point on the wind quantity is met;
33 A random field model P (Y | X) of the air volume of each detection point is established, namely the air volume required by each position is not less than 0 and not more than P (Y) under the condition of monitoring data of each wind detection point i I X) is less than or equal to 1, wherein 0 represents no air volume, 1 represents the maximum air volume, and the model is approximated by a graph neural network;
34 According to the random field model, a graph neural network of each wind measuring point is established, and the graph neural network is composed of a 4-layer graph network structure.
35 Obtaining probability values of all wind measuring points to air quantity requirements according to the neural network of the graph, introducing the fully-connected neural network, and obtaining the air supply quantity D of the main ventilator;
36 Training a neural network of the graph, collecting real-time monitoring data of an underground wind measuring point, making a sample set, and selecting a mean square error loss function during training until the neural network converges, so that the neural network has the capability of calculating real-time wind volume;
s4, determining a control decision method of the main ventilator frequency converter: the frequency f controlled by the frequency converter is in linear relation with the air volume:
f(t)＝kD(t) (7)
in the formula, k is a constant, and,
can be directly tested on site, when the frequency of the frequency converter is controlled to be 50Hz, the air quantity is maximum D max ；
S5, determining a frequency converter control frequency decision method, which comprises the following steps:
51 Setting the current time as t, and determining a predicted length m according to equation (2);
52 The value at m time of each anemometry point is predicted according to the LSTM:
X i (t+m)＝[V i (t+m)，C i (t+m)，T i (t+m)，W i (t+m)，G i (t+m)] (8)
53 Determining the air volume D (m) at the moment m according to the neural network
54 Determining the frequency converter control frequency f (m) according to equation (7);
55 Starting from the current instant t, until instant t + m, the frequency converter executes the control frequency f (m),
56 The first step is repeated at time t + m to re-predict the re-execution control frequency.
2. The method for regulating the speed of the frequency converter of the main coal mine ventilator based on the random wind speed field prediction as claimed in claim 1, wherein in step S3, the graph neural network is divided into four layers, and the input value of each layer is a characteristic value F i And a link matrix E, wherein the input value is operated with the coal seam weight W to obtain an output characteristic value F i+1 And a link matrix E, wherein the link matrix E remains constant throughout, i =1,2,3,4; input eigenvalues F of each graph neural network layer i Weight setting, characteristic output value F i+1 Comprises the following steps:
wherein p × q represents a matrix with characteristic values of p rows and q columns;
convolution neural network F for each layer of graph i The specific calculation method comprises the following steps:
a. first layer input F 1 A feature matrix for each wind measurement point:
b. determining a link matrix E, E being a link matrix of each wind measuring point
If the element of the ith row and the jth column in the matrix E is 1, the ith wind measuring point is connected with the jth wind measuring point; if the value is 0, no relation is shown, and all wind measuring points are related in the patent;
c. the output of the characteristic value of the neural network of each layer diagram is as follows:
F i+1 ＝EF i W i (6)
d. according to the neural network, output F 5 The model is essentially a probability value of each wind measurement point to the wind volume demand, and is a random field model P (Y | X) of the wind volume of each detection point.
e. Introducing a full-connection neural network to obtain the air supply rate of the main ventilator F 5 And the relation between the air quantity required by each point and the air quantity D of the main ventilator is fitted through the fully connected neural network, so that the air quantity D of the main ventilator can be calculated under the condition that the real-time data of each wind measuring point is known.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211686770.7A CN115961996A (en) | 2022-12-26 | 2022-12-26 | Coal mine main ventilator frequency converter speed regulation method based on random wind speed field prediction |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211686770.7A CN115961996A (en) | 2022-12-26 | 2022-12-26 | Coal mine main ventilator frequency converter speed regulation method based on random wind speed field prediction |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115961996A true CN115961996A (en) | 2023-04-14 |
Family
ID=87354473
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211686770.7A Pending CN115961996A (en) | 2022-12-26 | 2022-12-26 | Coal mine main ventilator frequency converter speed regulation method based on random wind speed field prediction |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115961996A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117436678A (en) * | 2023-12-21 | 2024-01-23 | 青岛慧拓智能机器有限公司 | Method, device, equipment and storage medium for generating entry point of strip mine loading area |
-
2022
- 2022-12-26 CN CN202211686770.7A patent/CN115961996A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117436678A (en) * | 2023-12-21 | 2024-01-23 | 青岛慧拓智能机器有限公司 | Method, device, equipment and storage medium for generating entry point of strip mine loading area |
| CN117436678B (en) * | 2023-12-21 | 2024-04-12 | 青岛慧拓智能机器有限公司 | Method, device, equipment and storage medium for generating entry point of strip mine loading area |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN103912966B (en) | A kind of earth source heat pump refrigeration system optimal control method | |
| CN113404502B (en) | Shield hob abrasion monitoring device and method based on ballast piece morphology | |
| CN102353119B (en) | Control method of VAV (variable air volume) air-conditioning system | |
| CN109118384A (en) | A kind of Wind turbines healthy early warning method | |
| CN107166504A (en) | Method of heating regulation and device | |
| CN101581940B (en) | Tunnel event detection method based on integrated learning time sequence prediction | |
| CN115961996A (en) | Coal mine main ventilator frequency converter speed regulation method based on random wind speed field prediction | |
| CN107169241A (en) | A kind of bridge expanssion joint performance method for early warning based on temperature movement relational model | |
| CN105973626A (en) | Evaluation and prediction method and apparatus for operation energy efficiency of host of central air-conditioning system | |
| CN112413831A (en) | Energy-saving control system and method for central air conditioner | |
| CN104612740A (en) | Automatic adjusting system for mine ventilation system | |
| CN112127934B (en) | Variable-frequency energy-saving ventilation system and method for high-altitude high-temperature extra-long tunnel construction | |
| CN110992209A (en) | Flow prediction method | |
| CN106321487B (en) | Three-stage construction ventilation of tunnel control method | |
| CN114738031B (en) | Natural and mechanical ventilation coupled construction tunnel digital twin intelligent ventilation method | |
| CN115907446B (en) | Intelligent management and control evaluation system for construction progress of foundation engineering | |
| CN107270384A (en) | Method and device for heating regulation | |
| CN115453945A (en) | Comprehensive digging face intelligent ventilation control system based on mobile environment detection device | |
| CN113431619A (en) | Intelligent control system for ventilation of highway tunnel | |
| CN113240184A (en) | Building space unit cold load prediction method and system based on federal learning | |
| CN114647216A (en) | System and method for cooperatively controlling air cut-off of coal mine air shaft fan and regulating and controlling air quantity of roadway network | |
| CN114200839A (en) | Office building energy consumption intelligent control model for dynamic monitoring of coupled environmental behaviors | |
| CN117780416A (en) | Intelligent monitoring regulation and control device and system for coal mine ventilation | |
| CN113605866B (en) | Dynamic regulation and control system and method for mine gas extraction | |
| CN114109465A (en) | Intelligent analysis decision-making method for mine ventilation system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |