CN117473285A - Intelligent operation and maintenance management system and method based on digital twinning - Google Patents
Intelligent operation and maintenance management system and method based on digital twinning Download PDFInfo
- Publication number
- CN117473285A CN117473285A CN202311815878.6A CN202311815878A CN117473285A CN 117473285 A CN117473285 A CN 117473285A CN 202311815878 A CN202311815878 A CN 202311815878A CN 117473285 A CN117473285 A CN 117473285A
- Authority
- CN
- China
- Prior art keywords
- time sequence
- feature
- mine
- mine environment
- environment parameter
- 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.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 16
- 238000012423 maintenance Methods 0.000 title claims description 44
- 238000007726 management method Methods 0.000 claims abstract description 49
- 230000003993 interaction Effects 0.000 claims abstract description 35
- CURLTUGMZLYLDI-UHFFFAOYSA-N Carbon dioxide Chemical compound O=C=O CURLTUGMZLYLDI-UHFFFAOYSA-N 0.000 claims abstract description 26
- 238000012544 monitoring process Methods 0.000 claims abstract description 17
- 239000007789 gas Substances 0.000 claims abstract description 16
- 239000000428 dust Substances 0.000 claims abstract description 14
- QVGXLLKOCUKJST-UHFFFAOYSA-N atomic oxygen Chemical compound [O] QVGXLLKOCUKJST-UHFFFAOYSA-N 0.000 claims abstract description 13
- 229910002092 carbon dioxide Inorganic materials 0.000 claims abstract description 13
- 239000001569 carbon dioxide Substances 0.000 claims abstract description 13
- 239000001301 oxygen Substances 0.000 claims abstract description 13
- 229910052760 oxygen Inorganic materials 0.000 claims abstract description 13
- 239000013598 vector Substances 0.000 claims description 182
- 238000001514 detection method Methods 0.000 claims description 30
- 238000000605 extraction Methods 0.000 claims description 28
- 238000013527 convolutional neural network Methods 0.000 claims description 26
- 230000033001 locomotion Effects 0.000 claims description 20
- 239000011159 matrix material Substances 0.000 claims description 17
- 238000010586 diagram Methods 0.000 claims description 15
- 238000012545 processing Methods 0.000 claims description 14
- 230000007613 environmental effect Effects 0.000 claims description 8
- 238000012098 association analyses Methods 0.000 claims description 7
- 238000003062 neural network model Methods 0.000 claims description 7
- 238000011176 pooling Methods 0.000 claims description 7
- 238000005065 mining Methods 0.000 claims description 5
- 230000004913 activation Effects 0.000 claims description 3
- 238000012546 transfer Methods 0.000 claims description 3
- PCHJSUWPFVWCPO-UHFFFAOYSA-N gold Chemical compound [Au] PCHJSUWPFVWCPO-UHFFFAOYSA-N 0.000 abstract description 10
- 239000010931 gold Substances 0.000 abstract description 10
- 229910052737 gold Inorganic materials 0.000 abstract description 10
- 238000004519 manufacturing process Methods 0.000 abstract description 7
- 238000004458 analytical method Methods 0.000 abstract description 6
- 238000013135 deep learning Methods 0.000 abstract description 4
- 238000005516 engineering process Methods 0.000 description 6
- 230000008859 change Effects 0.000 description 5
- 230000006870 function Effects 0.000 description 5
- 238000012512 characterization method Methods 0.000 description 4
- 230000004927 fusion Effects 0.000 description 4
- 238000009826 distribution Methods 0.000 description 3
- 238000013507 mapping Methods 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 2
- 230000015556 catabolic process Effects 0.000 description 2
- 238000006731 degradation reaction Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000004880 explosion Methods 0.000 description 2
- 230000014509 gene expression Effects 0.000 description 2
- VNWKTOKETHGBQD-UHFFFAOYSA-N methane Chemical compound C VNWKTOKETHGBQD-UHFFFAOYSA-N 0.000 description 2
- 230000000737 periodic effect Effects 0.000 description 2
- 239000011435 rock Substances 0.000 description 2
- UGFAIRIUMAVXCW-UHFFFAOYSA-N Carbon monoxide Chemical compound [O+]#[C-] UGFAIRIUMAVXCW-UHFFFAOYSA-N 0.000 description 1
- RWSOTUBLDIXVET-UHFFFAOYSA-N Dihydrogen sulfide Chemical compound S RWSOTUBLDIXVET-UHFFFAOYSA-N 0.000 description 1
- 206010021143 Hypoxia Diseases 0.000 description 1
- 230000002159 abnormal effect Effects 0.000 description 1
- 238000009825 accumulation Methods 0.000 description 1
- 230000008901 benefit Effects 0.000 description 1
- 230000015572 biosynthetic process Effects 0.000 description 1
- 229910002091 carbon monoxide Inorganic materials 0.000 description 1
- 238000010219 correlation analysis Methods 0.000 description 1
- 238000013136 deep learning model Methods 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 230000036541 health Effects 0.000 description 1
- 229910000037 hydrogen sulfide Inorganic materials 0.000 description 1
- 230000007954 hypoxia Effects 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 231100000572 poisoning Toxicity 0.000 description 1
- 230000000607 poisoning effect Effects 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 230000003252 repetitive effect Effects 0.000 description 1
- 230000029058 respiratory gaseous exchange Effects 0.000 description 1
- 238000005096 rolling process Methods 0.000 description 1
- 238000012549 training Methods 0.000 description 1
- 230000001052 transient effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
-
- E—FIXED CONSTRUCTIONS
- E21—EARTH OR ROCK DRILLING; MINING
- E21F—SAFETY DEVICES, TRANSPORT, FILLING-UP, RESCUE, VENTILATION, OR DRAINING IN OR OF MINES OR TUNNELS
- E21F17/00—Methods or devices for use in mines or tunnels, not covered elsewhere
- E21F17/18—Special adaptations of signalling or alarm devices
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01D—MEASURING NOT SPECIALLY ADAPTED FOR A SPECIFIC VARIABLE; ARRANGEMENTS FOR MEASURING TWO OR MORE VARIABLES NOT COVERED IN A SINGLE OTHER SUBCLASS; TARIFF METERING APPARATUS; MEASURING OR TESTING NOT OTHERWISE PROVIDED FOR
- G01D21/00—Measuring or testing not otherwise provided for
- G01D21/02—Measuring two or more variables by means not covered by a single other subclass
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/0464—Convolutional networks [CNN, ConvNet]
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Life Sciences & Earth Sciences (AREA)
- General Physics & Mathematics (AREA)
- Artificial Intelligence (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Computation (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Mining & Mineral Resources (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Health & Medical Sciences (AREA)
- General Life Sciences & Earth Sciences (AREA)
- Geochemistry & Mineralogy (AREA)
- Geology (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The application discloses wisdom fortune dimension management system and method based on digit twin relates to intelligent management technical field, and it carries out real-time supervision through installing multiple sensor on gold miner's safety helmet to the environment in the pit, gathers underground mine's gas concentration, oxygen concentration, carbon dioxide concentration, dust concentration, temperature, humidity and vibration signal, utilizes the deep learning technique to carry out the feature analysis to each item monitoring parameter to judge whether there is the potential safety hazard in miner's operational environment based on each item monitoring parameter's topological interaction characteristic. Thus, real-time environment information and necessary safety prompts can be provided for miners, so that personal safety of the miners is guaranteed, and production efficiency is improved.
Description
Technical Field
The application relates to the technical field of intelligent management, and more particularly relates to an intelligent operation and maintenance management system and method based on digital twinning.
Background
The digital twin technology realizes real-time monitoring, prediction and control of the physical world by digitally modeling the elements of people, things, environment and the like in the physical world. In recent years, the digital twin technology is widely applied to the fields of smart cities, smart traffic and the like, and provides a new solution for city management and operation. In the gold mine industry, the digital twin technology plays an increasingly important role, and provides a new thought and method for the safety management of gold mine personnel.
The gold mine industry is one of the important pillars of global economy, and features thereof include high risk, high investment, technical and labor intensity, and the like. In the gold mine industry, personnel operation and maintenance management is a key link for ensuring safe production and efficient production. In general, the underground working environment of a gold miner has higher risk, and in order to ensure the safety and production efficiency of the miner, the real-time monitoring of the underground environment is particularly important. However, there is currently no effective monitoring management scheme for the health and safety of underground miners.
Therefore, a digital twinning-based intelligent operation and maintenance management system and method are desired.
Disclosure of Invention
The present application has been made in order to solve the above technical problems.
Accordingly, according to one aspect of the present application, there is provided a digital twinning-based intelligent operation and maintenance management system, comprising:
the underground environment monitoring module is used for acquiring a plurality of pieces of mine environment information of an underground mine at a plurality of preset time points in a preset time period and vibration detection signals in the preset time period, wherein the plurality of pieces of mine environment information comprise gas concentration, oxygen concentration, carbon dioxide concentration, dust concentration, temperature and humidity;
the mine environment parameter time sequence feature extraction module is used for performing time sequence association analysis on the plurality of items of mine environment information to obtain mine environment parameter time sequence association feature vectors;
the vibration feature extraction module is used for extracting vibration features of the vibration detection signals in the preset time period to obtain vibration feature vectors;
the topology interaction module is used for carrying out topology interaction between feature nodes based on a motion model on the vibration feature vector and the mine environment parameter time sequence association feature vector so as to obtain a mining work environment state global feature vector;
the working environment detection module is used for determining whether potential safety hazards exist in the working environment of the miners or not based on the global feature vector of the working environment state of the miners;
the mine environment parameter time sequence feature extraction module comprises: the mine environment parameter time sequence arrangement unit is used for arranging each mine environment information of the plurality of preset time points into a plurality of mine environment parameter input vectors according to a time sequence respectively; the mine environment parameter time sequence coding unit is used for enabling the mine environment parameter input vectors to respectively pass through a mine environment parameter time sequence coder based on a convolutional neural network model so as to obtain a plurality of mine environment parameter time sequence feature vectors; and the mine environment parameter time sequence association coding unit is used for carrying out association coding on the mine environment parameter time sequence feature vectors so as to obtain the mine environment parameter time sequence association feature vectors.
In the above intelligent operation and maintenance management system based on digital twinning, the mine environment parameter time sequence associated coding unit comprises: the two-dimensional arrangement subunit is used for two-dimensionally arranging the plurality of mine environment parameter time sequence feature vectors into a mine environment parameter global time sequence feature matrix; and the environment parameter time sequence correlation feature extraction subunit is used for obtaining the mine environment parameter time sequence correlation feature vector by passing the mine environment parameter global time sequence feature matrix through a time sequence correlation feature extractor based on a convolutional neural network model.
In the above intelligent operation and maintenance management system based on digital twinning, the environmental parameter time sequence association feature extraction subunit is configured to: and respectively carrying out multi-scale convolution processing based on a two-dimensional convolution kernel, global mean pooling processing and nonlinear activation processing of each feature matrix along a channel dimension on input data in forward transfer of layers by using each layer of the time sequence correlation feature extractor based on the convolution neural network model so as to output the mine environment parameter time sequence correlation feature vector by the last layer of the time sequence correlation feature extractor based on the convolution neural network model.
In the above intelligent operation and maintenance management system based on digital twinning, the vibration feature extraction module is configured to: and passing a waveform diagram of the vibration detection signal of the preset time period through a vibration feature extractor based on a convolutional neural network model to obtain the vibration feature vector.
In the intelligent operation and maintenance management system based on digital twinning, the topology interaction module is used for: performing topology interaction between feature nodes based on a motion model on the vibration feature vector and the mine environment parameter time sequence association feature vector by using the following topology interaction formula to obtain a mining work environment state global feature vector; wherein, the topological interaction formula is:
；
wherein,representing the vibration feature vector,/->Representing the timing related feature vector of the mine environment parameter,mean value vector representing the vibration characteristic vector and the mine environment parameter time sequence correlation characteristic vector, +.>Representing vector addition, ++>Representing vector subtraction +.>Representing an exponential function operation, ++>And representing the global characteristic vector of the working environment state of the miners.
In the above intelligent operation and maintenance management system based on digital twinning, the working environment detection module is configured to: and the global feature vector of the working environment state of the miner is passed through a classifier to obtain a classification result, and the classification result is used for indicating whether potential safety hazards exist in the working environment of the miner.
In the above intelligent operation and maintenance management system based on digital twinning, the working environment detection module includes: the full-connection coding unit is used for carrying out full-connection coding on the state global feature vector of the working environment of the miner by using a full-connection layer of the classifier so as to obtain a full-connection coding feature vector; the probability unit is used for inputting the fully-connected coding feature vector into a Softmax classification function of the classifier to obtain probability values of the global feature vector of the working environment state of the miner, wherein the classification labels comprise potential safety hazards existing in the working environment of the miner and potential safety hazards not existing in the working environment of the miner; and the classification result determining unit is used for determining the classification label corresponding to the maximum probability value as the classification result.
According to another aspect of the present application, there is provided a digital twinning-based intelligent operation and maintenance management method, including:
acquiring a plurality of pieces of mine environment information of an underground mine at a plurality of preset time points in a preset time period and vibration detection signals in the preset time period, wherein the plurality of pieces of mine environment information comprise gas concentration, oxygen concentration, carbon dioxide concentration, dust concentration, temperature and humidity;
performing time sequence association analysis on the plurality of items of mine environment information to obtain a mine environment parameter time sequence association feature vector;
extracting vibration characteristics of the vibration detection signals in the preset time period to obtain vibration characteristic vectors;
performing topology interaction between feature nodes based on a motion model on the vibration feature vector and the mine environment parameter time sequence association feature vector to obtain a global feature vector of a working environment state of a miner;
determining whether potential safety hazards exist in the working environment of the miners or not based on the global feature vector of the working environment state of the miners;
the method for analyzing the time sequence association of the mine environment information to obtain the time sequence association characteristic vector of the mine environment parameter comprises the following steps:
arranging all mine environment information of the plurality of preset time points into a plurality of mine environment parameter input vectors according to time sequence respectively;
the mine environment parameter input vectors are respectively passed through a mine environment parameter time sequence encoder based on a convolutional neural network model to obtain a plurality of mine environment parameter time sequence feature vectors;
and performing association coding on the plurality of mine environment parameter time sequence feature vectors to obtain the mine environment parameter time sequence association feature vectors.
Compared with the prior art, the intelligent operation and maintenance management system and method based on digital twinning are characterized in that the underground environment is monitored in real time by installing various sensors on the safety helmet of a gold miner, the gas concentration, the oxygen concentration, the carbon dioxide concentration, the dust concentration, the temperature, the humidity and the vibration signals of an underground mine are collected, the characteristic analysis is carried out on all monitoring parameters by utilizing the deep learning technology, and whether potential safety hazards exist in the working environment of the miner is judged based on the topological interaction characteristics of all monitoring parameters. Thus, real-time environment information and necessary safety prompts can be provided for miners, so that personal safety of the miners is guaranteed, and production efficiency is improved.
Drawings
The foregoing and other objects, features and advantages of the present application will become more apparent from the following more particular description of embodiments of the present application, as illustrated in the accompanying drawings. The accompanying drawings are included to provide a further understanding of embodiments of the application and are incorporated in and constitute a part of this specification, illustrate the application and not constitute a limitation to the application. In the drawings, like reference numerals generally refer to like parts or steps.
FIG. 1 is a block diagram of a digital twinning-based intelligent operation and maintenance management system according to an embodiment of the present application.
Fig. 2 is a schematic architecture diagram of a digital twinning-based intelligent operation and maintenance management system according to an embodiment of the present application.
Fig. 3 is a block diagram of a mine environment parameter timing feature extraction module in a digital twinning-based intelligent operation and maintenance management system according to an embodiment of the present application.
Fig. 4 is a block diagram of a mine environment parameter timing correlation encoding unit in the intelligent operation and maintenance management system based on digital twinning according to an embodiment of the application.
Fig. 5 is a block diagram of a work environment detection module in a digital twinning-based intelligent operation and maintenance management system according to an embodiment of the present application.
Fig. 6 is a flowchart of a digital twinning-based intelligent operation and maintenance management method according to an embodiment of the present application.
Detailed Description
Hereinafter, example embodiments according to the present application will be described in detail with reference to the accompanying drawings. It should be apparent that the described embodiments are only some of the embodiments of the present application and not all of the embodiments of the present application, and it should be understood that the present application is not limited by the example embodiments described herein.
FIG. 1 is a block diagram of a digital twinning-based intelligent operation and maintenance management system according to an embodiment of the present application. Fig. 2 is a schematic architecture diagram of a digital twinning-based intelligent operation and maintenance management system according to an embodiment of the present application. As shown in fig. 1 and 2, a digital twinning-based intelligent operation and maintenance management system 100 according to an embodiment of the present application includes: the underground environment monitoring module 110 is configured to obtain a plurality of pieces of mine environment information of an underground mine at a plurality of predetermined time points in a predetermined time period, and vibration detection signals in the predetermined time period, where the plurality of pieces of mine environment information include a gas concentration, an oxygen concentration, a carbon dioxide concentration, a dust concentration, a temperature, and a humidity; the mine environment parameter time sequence feature extraction module 120 is configured to perform time sequence association analysis on the plurality of mine environment information to obtain a mine environment parameter time sequence association feature vector; a vibration feature extraction module 130, configured to perform vibration feature extraction on the vibration detection signal in the predetermined period of time to obtain a vibration feature vector; the topology interaction module 140 is configured to perform topology interaction between feature nodes based on a motion model on the vibration feature vector and the mine environment parameter time sequence association feature vector to obtain a global feature vector of a working environment state of a miner; the working environment detection module 150 is configured to determine whether a potential safety hazard exists in the working environment of the miner based on the global feature vector of the working environment state of the miner.
As noted above in the background, the downhole operating environment of gold miners is at a high risk. Often, there may be some harmful and combustible gases in the mine, such as methane, carbon monoxide, hydrogen sulfide, etc., which may cause poisoning and explosion of workers. Also, downhole miners may experience rock formation instability with the risk of collapse and collapse, which may cause the workers to become buried or injured. Therefore, in order to ensure the safety and production efficiency of miners, the real-time monitoring of the underground environment is particularly important.
Aiming at the technical problems, the technical concept of the method is that the underground environment is monitored in real time by installing various sensors on the safety helmet of a gold miner, the gas concentration, the oxygen concentration, the carbon dioxide concentration, the dust concentration, the temperature, the humidity and the vibration signals of the underground mine are collected, the characteristic analysis is carried out on all monitoring parameters by utilizing the deep learning technology, and whether the potential safety hazard exists in the working environment of the miner is judged based on the topological interaction characteristics of all monitoring parameters.
In the digital twinning-based intelligent operation and maintenance management system 100, the downhole environment monitoring module 110 is configured to obtain a plurality of pieces of mine environment information of the underground mine at a plurality of predetermined time points in a predetermined time period, and vibration detection signals in the predetermined time period, where the plurality of pieces of mine environment information include a gas concentration, an oxygen concentration, a carbon dioxide concentration, a dust concentration, a temperature, and a humidity. It should be appreciated that the data of gas concentration, oxygen concentration, carbon dioxide concentration, dust concentration, temperature and humidity are key parameters for evaluating the safety of the downhole working environment. By acquiring this information, potential risk factors in the mine, such as gas accumulation, hypoxia, high temperature, and dust effects on worker respiration, can be known. And the vibration signal may provide information about the structure and motion status of the underground mine. Through carrying out feature analysis on the vibration signals, stability information and possible geological activities of the mine, such as rock stratum movement, earthquake and the like, can be obtained, so that potential geological disaster risks can be found in time, and a safer working environment is provided for miners.
In the digital twinning-based intelligent operation and maintenance management system 100, the mine environment parameter time sequence feature extraction module 120 is configured to perform time sequence correlation analysis on the plurality of mine environment information to obtain a mine environment parameter time sequence correlation feature vector. Fig. 3 is a block diagram of a mine environment parameter timing feature extraction module in a digital twinning-based intelligent operation and maintenance management system according to an embodiment of the present application. As shown in fig. 3, the mine environment parameter timing feature extraction module 120 includes: a mine environment parameter time sequence arrangement unit 121, configured to arrange each mine environment information of the plurality of predetermined time points into a plurality of mine environment parameter input vectors according to a time sequence; a mine environment parameter time sequence encoding unit 122, configured to pass the plurality of mine environment parameter input vectors through a mine environment parameter time sequence encoder based on a convolutional neural network model to obtain a plurality of mine environment parameter time sequence feature vectors; and a mine environment parameter time sequence association coding unit 123, configured to perform association coding on the plurality of mine environment parameter time sequence feature vectors to obtain the mine environment parameter time sequence association feature vectors.
Specifically, the mine environment parameter time sequence arrangement unit 121 is configured to arrange each mine environment information of the plurality of predetermined time points into a plurality of mine environment parameter input vectors according to a time sequence. In the technical scheme of the application, in order to capture time sequence information of mine environment parameters and extract time sequence characteristics thereof, each mine environment parameter at a plurality of preset time points is further arranged according to time sequence respectively, so that a plurality of mine environment parameter input vectors are obtained. It should be understood that by arranging the mine environment parameters according to the time sequence, the time sequence relation of each parameter can be reserved, and the change trend, the periodic mode and the possible abnormal situation of the mine environment are reflected, so that the evolution process of the mine environment can be well understood, the dynamic change characteristics of the mine environment can be analyzed, and the evaluation accuracy of the safety of the working environment of a miner can be improved.
Specifically, the mine environment parameter time sequence encoding unit 122 is configured to pass the plurality of mine environment parameter input vectors through a mine environment parameter time sequence encoder based on a convolutional neural network model to obtain a plurality of mine environment parameter time sequence feature vectors. It should be appreciated that Convolutional Neural Networks (CNNs) are an effective deep learning model that excels in extracting key features from input data. By using the convolutional neural network model as a mine environment parameter timing encoder, timing features in the input vector can be automatically learned and extracted to capture important patterns, trends and changes in mine environment parameters. Also, there may be local patterns of variation in parameter values at different points in time, such as transient peaks, periodic variations, etc. Whereas convolutional neural network models have the ability to locally perceive when processing time series data. The convolution layer can extract local feature representation from input data in a sliding window mode, and effectively captures a local mode in the input data through a parameter sharing mechanism of a convolution kernel, so that a time sequence mode of a mine environment is better understood and analyzed, richer information is provided for subsequent feature fusion and state judgment, the system is helped to accurately evaluate the safety of a miner working environment, and potential safety hazards are timely found.
Specifically, the mine environment parameter time sequence association encoding unit 123 is configured to perform association encoding on the plurality of mine environment parameter time sequence feature vectors to obtain the mine environment parameter time sequence association feature vectors. It should be understood that different parameters in the mine environment are often interrelated, and by performing association coding on a plurality of mine environment parameter time sequence feature vectors, the association between the different parameters can be captured, and the time sequence association features between the parameters can be further extracted, so that dynamic changes of the mine environment can be more comprehensively understood and analyzed, and the interaction between the parameters can be revealed. And by carrying out associated coding on the time sequence feature vectors of the parameters of the mine environment, the time sequence information of each parameter can be fused together to form comprehensive time sequence associated feature representation, thereby being beneficial to more comprehensively understanding the dynamic change of the mine environment.
Fig. 4 is a block diagram of a mine environment parameter timing correlation encoding unit in the intelligent operation and maintenance management system based on digital twinning according to an embodiment of the application. As shown in fig. 4, the mine environment parameter timing related encoding unit 123 includes: a two-dimensional arrangement subunit 1231, configured to two-dimensionally arrange the plurality of mine environment parameter timing feature vectors into a mine environment parameter global timing feature matrix; and the environmental parameter time sequence correlation feature extraction subunit 1232 is configured to obtain the time sequence correlation feature vector of the mine environmental parameter by using the time sequence correlation feature extractor based on the convolutional neural network model.
Specifically, the two-dimensional arrangement subunit 1231 is configured to two-dimensionally arrange the plurality of mine environment parameter timing feature vectors into a mine environment parameter global timing feature matrix. It should be appreciated that there is typically a complex timing relationship between the different parameters in the mine environment. By arranging the plurality of mine environment parameter time sequence feature vectors into a matrix, time sequence association analysis can be more conveniently performed. For example, the timing characteristics of different parameters can be represented by rows and columns of the matrix, and further analyzing patterns, trends and correlations in the matrix helps to discover interactions and potential anomalies between the parameters.
Specifically, the environmental parameter time-sequence correlation feature extraction subunit 1232 is configured to pass the mine environmental parameter global time-sequence feature matrix through a time-sequence correlation feature extractor based on a convolutional neural network model to obtain the mine environmental parameter time-sequence correlation feature vector. It should be understood that the global timing characteristic matrix of the mine environment parameter contains abundant timing information, but directly using the matrix as input may cause problems of higher dimension and more redundant information. By the time sequence correlation feature extractor based on the convolutional neural network, important time sequence correlation features in the mine environment parameter matrix can be automatically learned and extracted. The convolutional neural network can capture the local mode of the time sequence feature through a convolutional operation, and performs feature degradation and extraction through a pooling operation. Meanwhile, considering that complex time sequence association relation often exists between mine environment parameters, for example, certain parameters may have similar variation trend or mutual influence. The time sequence correlation characteristic extractor based on the convolutional neural network can effectively capture the time sequence correlation among the mine environment parameters through the characteristics of filter sharing and local connection of the convolutional layers, and is beneficial to extracting the time sequence correlation characteristic with more characterization capability, so that the interaction and dynamic change among the parameters are better described. And the convolutional neural network model performs key feature extraction and dimension reduction processing on the mine environment parameter global time sequence feature matrix through operations such as rolling and pooling, so that the calculation complexity is reduced.
In a specific example of the present application, the environmental parameter timing related feature extraction subunit 1232 is configured to: and respectively carrying out multi-scale convolution processing based on a two-dimensional convolution kernel, global mean pooling processing and nonlinear activation processing of each feature matrix along a channel dimension on input data in forward transfer of layers by using each layer of the time sequence correlation feature extractor based on the convolution neural network model so as to output the mine environment parameter time sequence correlation feature vector by the last layer of the time sequence correlation feature extractor based on the convolution neural network model.
In the digital twinning-based intelligent operation and maintenance management system 100, the vibration feature extraction module 130 is configured to perform vibration feature extraction on the vibration detection signal in the predetermined period of time to obtain a vibration feature vector. In a specific example of the present application, the method for extracting the vibration feature of the vibration detection signal in the predetermined period of time to obtain the vibration feature vector is that the waveform diagram of the vibration detection signal in the predetermined period of time passes through a vibration feature extractor based on a convolutional neural network model to obtain the vibration feature vector. It should be understood that the waveform of the vibration signal contains rich vibration information, but directly using the waveform as input may cause problems of higher dimension and more redundant information. The convolutional neural network can capture the local mode of the signal through convolutional operation and perform feature degradation and extraction through pooling operation. That is, by the vibration feature extractor based on the convolutional neural network, important feature representations in the vibration signal can be automatically learned and extracted. Also, it is considered that the waveform of the vibration signal is a time series in which information such as the amplitude and frequency of vibration is contained. The waveform diagram can be converted into a vibration characteristic vector with more characterization capability by a vibration characteristic extractor based on a convolutional neural network. The vibration characteristic vector comprises time domain characteristics of vibration signals, so that subsequent vibration analysis and processing are more convenient. Meanwhile, the convolution neural network model reduces the dimension of the feature through operations such as convolution and pooling so as to match the dimension of the output vibration feature vector with the dimension of the mine environment parameter time sequence related feature vector, thereby facilitating subsequent feature interaction processing and reducing the complexity of calculation.
In the digital twinning-based intelligent operation and maintenance management system 100, the topology interaction module 140 is configured to perform topology interaction between feature nodes based on a motion model on the vibration feature vector and the mine environment parameter time sequence association feature vector to obtain a global feature vector of a working environment state of a miner. In particular, in the technical solution of the present application, it is considered that the vibration feature vector is extracted from the waveform diagram of the vibration detection signal by a vibration feature extractor based on a convolutional neural network model. Vibration feature vectors are primarily concerned with vibration conditions in the working environment of miners, such as vibrations that may be caused by earthquakes, explosions, or the operation of mechanical equipment. The vibration signature vector may provide information about potential risk factors in the mineworker's work environment. The mine environment parameter time sequence correlation feature vector is obtained by arranging parameters such as gas concentration, oxygen concentration, carbon dioxide concentration, dust concentration, temperature, humidity and the like at a plurality of preset time points into an input vector according to time sequence, and then obtaining the mine environment parameter time sequence correlation feature vector through a mine environment parameter time sequence encoder based on a convolutional neural network model. These mine environment parameters reflect the changes in factors such as gas concentration, temperature, humidity, etc. in the mineworker's working environment. They can provide information about air quality, temperature changes, humidity changes, etc. in the mineworker's working environment. Since the vibration feature vector and the mine environment parameter time sequence correlation feature vector represent the same class from different dimensions, respectively, their feature distribution and feature shape in a high-dimensional feature space may be inconsistent. This means that they may have different feature expressions when representing the same class. Therefore, fusing them directly may lead to confusion and inaccuracy in the feature information. In order to solve the problem, topological interaction based on a motion model is carried out between feature nodes on the vibration feature vector and the mine environment parameter time sequence related feature vector so as to ensure the effectiveness of feature fusion, thereby improving the accuracy of judging and classifying the working environment states of miners.
In a specific example of the present application, the topology interaction module 140 is configured to: performing topology interaction between feature nodes based on a motion model on the vibration feature vector and the mine environment parameter time sequence association feature vector by using the following topology interaction formula to obtain a mining work environment state global feature vector; wherein, the topological interaction formula is:
；
wherein,representing the vibration feature vector,/->Representing the timing related feature vector of the mine environment parameter, < >>Mean value vector representing the vibration characteristic vector and the mine environment parameter time sequence correlation characteristic vector, +.>Representing vector addition, ++>Representing vector subtraction +.>Representing an exponential function operation, ++>And representing the global characteristic vector of the working environment state of the miners.
That is, since the vibration feature vector and the mine environment parameter time sequence association feature vector represent the same class from different dimensions, that is, the vibration feature vector and the mine environment parameter time sequence association feature vector perform class label abstract expression in a high-dimensional feature space from different directions, if feature distribution and feature shape of the two feature vectors in the high-dimensional feature space are inconsistent, information matching and alignment between the feature vectors are affected, and further, the characterization capability and classification performance of the feature vectors are affected.
Aiming at the technical problems, the application provides a method for topological interaction between feature nodes based on a motion model, which can perform topological interaction between feature nodes based on the motion model on the vibration feature vector and the mine environment parameter time sequence related feature vector, so that information enhancement and effective fusion of the feature vector are realized. Specifically, the method uses a mean value vector between two feature vectors as a motion reference vector, the vector can reflect common features and directions of the two feature vectors in a high-dimensional feature space, then a feature metric is obtained according to feature similarity or distance between each feature vector and the motion reference vector, the metric can reflect feature distribution and feature shape of each feature vector in the high-dimensional feature space, then growth of point correlation from center to neighborhood is carried out by taking the motion reference vector as a reference, namely, a point correlation is obtained according to the feature metric between each position and the motion reference vector, and the correlation can reflect feature association and feature change of each position in the high-dimensional feature space. Therefore, by realizing topological interaction based on a motion model among the feature nodes, feature inconsistency caused by different dimensions and different directions among the feature vectors can be effectively eliminated or reduced, and therefore, the characterization capability and the fusion performance of the feature vectors are improved.
In the digital twinning-based intelligent operation and maintenance management system 100, the working environment detection module 150 is configured to determine whether a potential safety hazard exists in the working environment of the miner based on the global feature vector of the working environment state of the miner. In a specific example of the application, the implementation manner of determining whether the potential safety hazard exists in the working environment of the miner based on the global feature vector of the working environment state of the miner is to pass the global feature vector of the working environment state of the miner through a classifier to obtain a classification result, wherein the classification result is used for indicating whether the potential safety hazard exists in the working environment of the miner. It should be appreciated that a classifier is a machine learning model that is capable of assigning new data samples into different predefined categories by learning the mapping between the input data features and different category labels. In the technical scheme of the application, the state global feature vector of the working environment of the miner is input into the classifier after training, and whether the working environment has potential safety hazards or not can be automatically judged by utilizing the classification mapping capability of the classifier without manual intervention. The classifier is used for learning the characteristic information in the global characteristic vector of the working environment state of the miner and mapping the characteristic information into corresponding classification labels, namely 'potential safety hazards exist in the working environment of the miner' and 'potential safety hazards do not exist in the working environment of the miner', so that automatic judgment of the working environment of the miner is realized. And, use the classifier to carry on the judgement of miner's working environment can improve the efficiency and real-time of judgement. Once the classifier is trained and deployed, the input global feature vector of the working environment state of the miner can be classified rapidly, the judgment result is given almost in real time, potential safety hazards can be found in time, corresponding measures can be taken, and the personal safety of the miner is guaranteed.
Fig. 5 is a block diagram of a work environment detection module in a digital twinning-based intelligent operation and maintenance management system according to an embodiment of the present application. As shown in fig. 5, the working environment detection module 150 includes: a full-connection encoding unit 151, configured to perform full-connection encoding on the global feature vector of the state of the miner working environment by using a full-connection layer of the classifier to obtain a full-connection encoded feature vector; the probability unit 152 is configured to input the fully-connected encoding feature vector into a Softmax classification function of the classifier to obtain probability values of the global feature vector of the working environment state of the miner belonging to each classification label, where the classification labels include potential safety hazards existing in the working environment of the miner and potential safety hazards not existing in the working environment of the miner; and a classification result determining unit 153 configured to determine a classification label corresponding to the largest one of the probability values as the classification result.
In summary, the digital twinning-based intelligent operation and maintenance management system according to the embodiment of the application is clarified, and is used for monitoring the underground environment in real time by installing various sensors on a safety helmet of a gold miner, collecting gas concentration, oxygen concentration, carbon dioxide concentration, dust concentration, temperature, humidity and vibration signals of an underground mine, carrying out feature analysis on various monitoring parameters by utilizing a deep learning technology, and judging whether potential safety hazards exist in the working environment of the miner or not based on topological interaction features of the various monitoring parameters. Thus, real-time environment information and necessary safety prompts can be provided for miners, so that personal safety of the miners is guaranteed, and production efficiency is improved.
Fig. 6 is a flowchart of a digital twinning-based intelligent operation and maintenance management method according to an embodiment of the present application. As shown in fig. 6, the intelligent operation and maintenance management method based on digital twinning according to the embodiment of the application includes the steps of: s110, acquiring a plurality of pieces of mine environment information of an underground mine at a plurality of preset time points in a preset time period and vibration detection signals in the preset time period, wherein the plurality of pieces of mine environment information comprise gas concentration, oxygen concentration, carbon dioxide concentration, dust concentration, temperature and humidity; s120, carrying out time sequence association analysis on the plurality of items of mine environment information to obtain a mine environment parameter time sequence association feature vector; s130, vibration feature extraction is carried out on the vibration detection signals in the preset time period to obtain vibration feature vectors; s140, performing topological interaction between feature nodes based on a motion model on the vibration feature vector and the mine environment parameter time sequence association feature vector to obtain a miner working environment state global feature vector; s150, determining whether potential safety hazards exist in the working environment of the miners or not based on the global feature vector of the working environment state of the miners.
Here, it will be understood by those skilled in the art that the specific operations of the respective steps in the above-described digital twinning-based intelligent operation and maintenance management method have been described in detail in the above description of the digital twinning-based intelligent operation and maintenance management system with reference to fig. 1 to 5, and thus, repetitive descriptions thereof will be omitted.
In the foregoing embodiments, the descriptions of the embodiments are emphasized, and in part, not described or illustrated in any particular embodiment, reference is made to the related descriptions of other embodiments. In the several embodiments provided by the present invention, it should be understood that the disclosed apparatus, system and method may be implemented in other manners. For example, the system embodiments described above are merely illustrative, and for example, the module division is merely a logical function division, and other manners of division may be implemented in practice. The modules described as separate components may or may not be physically separate, and components shown as modules may or may not be physical units, may be located in one place, or may be distributed over multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
In addition, each functional module in the embodiments of the present invention may be integrated in one processing unit, or each unit may exist alone physically, or two or more units may be integrated in one unit. The integrated units can be realized in a form of hardware or a form of hardware and a form of software functional modules.
It will be evident to those skilled in the art that the invention is not limited to the details of the foregoing illustrative embodiments, and that the present invention may be embodied in other specific forms without departing from the spirit or essential characteristics thereof. The present embodiments are, therefore, to be considered in all respects as illustrative and not restrictive, the scope of the invention being indicated by the appended claims rather than by the foregoing description, and all changes which come within the meaning and range of equivalency of the claims are therefore intended to be embraced therein. Any reference signs in the claims shall not be construed as limiting the claim concerned.
Furthermore, it is evident that the word "comprising" does not exclude other elements or steps, and that the singular does not exclude a plurality. The units recited in the system claims may also be implemented by means of software or hardware.
Finally, it should be noted that the above-mentioned embodiments are merely for illustrating the technical solution of the present invention and not for limiting the same, and although the present invention has been described in detail with reference to the preferred embodiments, it should be understood by those skilled in the art that modifications and equivalents may be made to the technical solution of the present invention without departing from the spirit and scope of the technical solution of the present invention.
Claims (8)
1. An intelligent operation and maintenance management system based on digital twinning, which is characterized by comprising:
the underground environment monitoring module is used for acquiring a plurality of pieces of mine environment information of an underground mine at a plurality of preset time points in a preset time period and vibration detection signals in the preset time period, wherein the plurality of pieces of mine environment information comprise gas concentration, oxygen concentration, carbon dioxide concentration, dust concentration, temperature and humidity;
the mine environment parameter time sequence feature extraction module is used for performing time sequence association analysis on the plurality of items of mine environment information to obtain mine environment parameter time sequence association feature vectors;
the vibration feature extraction module is used for extracting vibration features of the vibration detection signals in the preset time period to obtain vibration feature vectors;
the topology interaction module is used for carrying out topology interaction between feature nodes based on a motion model on the vibration feature vector and the mine environment parameter time sequence association feature vector so as to obtain a mining work environment state global feature vector;
the working environment detection module is used for determining whether potential safety hazards exist in the working environment of the miners or not based on the global feature vector of the working environment state of the miners;
the mine environment parameter time sequence feature extraction module comprises:
the mine environment parameter time sequence arrangement unit is used for arranging each mine environment information of the plurality of preset time points into a plurality of mine environment parameter input vectors according to a time sequence respectively;
the mine environment parameter time sequence coding unit is used for enabling the mine environment parameter input vectors to respectively pass through a mine environment parameter time sequence coder based on a convolutional neural network model so as to obtain a plurality of mine environment parameter time sequence feature vectors;
and the mine environment parameter time sequence association coding unit is used for carrying out association coding on the mine environment parameter time sequence feature vectors so as to obtain the mine environment parameter time sequence association feature vectors.
2. The digital twinning-based intelligent operation and maintenance management system according to claim 1, wherein the mine environment parameter time sequence associated coding unit comprises:
the two-dimensional arrangement subunit is used for two-dimensionally arranging the plurality of mine environment parameter time sequence feature vectors into a mine environment parameter global time sequence feature matrix;
and the environment parameter time sequence correlation feature extraction subunit is used for obtaining the mine environment parameter time sequence correlation feature vector by passing the mine environment parameter global time sequence feature matrix through a time sequence correlation feature extractor based on a convolutional neural network model.
3. The digital twinning-based intelligent operation and maintenance management system according to claim 2, wherein the environmental parameter timing-related feature extraction subunit is configured to:
and respectively carrying out multi-scale convolution processing based on a two-dimensional convolution kernel, global mean pooling processing and nonlinear activation processing of each feature matrix along a channel dimension on input data in forward transfer of layers by using each layer of the time sequence correlation feature extractor based on the convolution neural network model so as to output the mine environment parameter time sequence correlation feature vector by the last layer of the time sequence correlation feature extractor based on the convolution neural network model.
4. The digital twinning-based intelligent operation and maintenance management system according to claim 3, wherein the vibration feature extraction module is configured to:
and passing a waveform diagram of the vibration detection signal of the preset time period through a vibration feature extractor based on a convolutional neural network model to obtain the vibration feature vector.
5. The digital twinning-based intelligent operation and maintenance management system according to claim 4, wherein the topology interaction module is configured to: performing topology interaction between feature nodes based on a motion model on the vibration feature vector and the mine environment parameter time sequence association feature vector by using the following topology interaction formula to obtain a mining work environment state global feature vector; wherein, the topological interaction formula is:
；
wherein,representing the vibration feature vector,/->Representing the timing related feature vector of the mine environment parameter, < >>Mean value vector representing the vibration characteristic vector and the mine environment parameter time sequence correlation characteristic vector, +.>Representing vector addition, ++>Representing vector subtraction +.>Representing an exponential function operation, ++>And representing the global characteristic vector of the working environment state of the miners.
6. The digital twinning-based intelligent operation and maintenance management system according to claim 5, wherein the working environment detection module is configured to:
and the global feature vector of the working environment state of the miner is passed through a classifier to obtain a classification result, and the classification result is used for indicating whether potential safety hazards exist in the working environment of the miner.
7. The digital twinning-based intelligent operation and maintenance management system according to claim 6, wherein the working environment detection module comprises:
the full-connection coding unit is used for carrying out full-connection coding on the state global feature vector of the working environment of the miner by using a full-connection layer of the classifier so as to obtain a full-connection coding feature vector;
the probability unit is used for inputting the fully-connected coding feature vector into a Softmax classification function of the classifier to obtain probability values of the global feature vector of the working environment state of the miner, wherein the classification labels comprise potential safety hazards existing in the working environment of the miner and potential safety hazards not existing in the working environment of the miner;
and the classification result determining unit is used for determining the classification label corresponding to the maximum probability value as the classification result.
8. The intelligent operation and maintenance management method based on digital twinning is characterized by comprising the following steps of:
acquiring a plurality of pieces of mine environment information of an underground mine at a plurality of preset time points in a preset time period and vibration detection signals in the preset time period, wherein the plurality of pieces of mine environment information comprise gas concentration, oxygen concentration, carbon dioxide concentration, dust concentration, temperature and humidity;
performing time sequence association analysis on the plurality of items of mine environment information to obtain a mine environment parameter time sequence association feature vector;
extracting vibration characteristics of the vibration detection signals in the preset time period to obtain vibration characteristic vectors;
performing topology interaction between feature nodes based on a motion model on the vibration feature vector and the mine environment parameter time sequence association feature vector to obtain a global feature vector of a working environment state of a miner;
determining whether potential safety hazards exist in the working environment of the miners or not based on the global feature vector of the working environment state of the miners;
the method for analyzing the time sequence association of the mine environment information to obtain the time sequence association characteristic vector of the mine environment parameter comprises the following steps:
arranging all mine environment information of the plurality of preset time points into a plurality of mine environment parameter input vectors according to time sequence respectively;
the mine environment parameter input vectors are respectively passed through a mine environment parameter time sequence encoder based on a convolutional neural network model to obtain a plurality of mine environment parameter time sequence feature vectors;
and performing association coding on the plurality of mine environment parameter time sequence feature vectors to obtain the mine environment parameter time sequence association feature vectors.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311815878.6A CN117473285B (en) | 2023-12-27 | 2023-12-27 | Intelligent operation and maintenance management system and method based on digital twinning |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311815878.6A CN117473285B (en) | 2023-12-27 | 2023-12-27 | Intelligent operation and maintenance management system and method based on digital twinning |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117473285A true CN117473285A (en) | 2024-01-30 |
| CN117473285B CN117473285B (en) | 2024-03-19 |
Family
ID=89635099
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311815878.6A Active CN117473285B (en) | 2023-12-27 | 2023-12-27 | Intelligent operation and maintenance management system and method based on digital twinning |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117473285B (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| RU2305298C1 (en) * | 2006-06-19 | 2007-08-27 | Югорский научно-исследовательский институт информационных технологий | Method for controlling position of drilling bit during drilling |
| CN113283386A (en) * | 2021-05-25 | 2021-08-20 | 中国矿业大学(北京) | Equipment fault diagnosis method of coal mine underground coal mining machine based on knowledge distillation |
| CN115045714A (en) * | 2022-08-17 | 2022-09-13 | 北工建设有限公司 | Mineral mining early warning method, mineral mining early warning equipment and computer-readable storage medium |
| CN116311751A (en) * | 2023-05-16 | 2023-06-23 | 陕西开来机电设备制造有限公司 | Underground coal mine use fire prevention and extinguishment electric control system |
| CN116950708A (en) * | 2023-09-06 | 2023-10-27 | 大连煤科安全技术研究院有限公司 | Intelligent management and control platform for one-ventilation three-prevention of coal mine |
| CN117248967A (en) * | 2023-10-13 | 2023-12-19 | 江西知时节科技有限公司 | Mine safety monitoring system and method based on intelligent perception |
-
2023
- 2023-12-27 CN CN202311815878.6A patent/CN117473285B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| RU2305298C1 (en) * | 2006-06-19 | 2007-08-27 | Югорский научно-исследовательский институт информационных технологий | Method for controlling position of drilling bit during drilling |
| CN113283386A (en) * | 2021-05-25 | 2021-08-20 | 中国矿业大学(北京) | Equipment fault diagnosis method of coal mine underground coal mining machine based on knowledge distillation |
| CN115045714A (en) * | 2022-08-17 | 2022-09-13 | 北工建设有限公司 | Mineral mining early warning method, mineral mining early warning equipment and computer-readable storage medium |
| CN116311751A (en) * | 2023-05-16 | 2023-06-23 | 陕西开来机电设备制造有限公司 | Underground coal mine use fire prevention and extinguishment electric control system |
| CN116950708A (en) * | 2023-09-06 | 2023-10-27 | 大连煤科安全技术研究院有限公司 | Intelligent management and control platform for one-ventilation three-prevention of coal mine |
| CN117248967A (en) * | 2023-10-13 | 2023-12-19 | 江西知时节科技有限公司 | Mine safety monitoring system and method based on intelligent perception |
Non-Patent Citations (4)
| Title |
|---|
| BO FANG: "Method for Quickly Identifying Mine Water Inrush Using Convolutional Neural Network in Coal Mine Safety Mining", 《WIRELESS PERSONAL COMMUNICATIONS 》, 21 April 2021 (2021-04-21) * |
| 杨静;郭勇;聂学方;: "井下矿工生命信息及环境信息监测系统的研究", 矿业研究与开发, no. 05, 31 October 2009 (2009-10-31) * |
| 王占勇;马震;王青青;: "煤矿瓦斯监测多传感器信息融合方法研究", 煤炭科技, no. 02, 25 June 2010 (2010-06-25) * |
| 韩林洁;石春鹏;张建超;: "基于一维卷积神经网络的轴承剩余寿命预测", 制造业自动化, no. 03, 25 March 2020 (2020-03-25) * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117473285B (en) | 2024-03-19 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Lyu et al. | LSTM based encoder-decoder for short-term predictions of gas concentration using multi-sensor fusion | |
| CN114048952B (en) | Iron-making plant safety situation sensing method based on edge internet of things technology and neural network | |
| CN112257917B (en) | Time sequence abnormal mode detection method based on entropy characteristics and neural network | |
| CN111197500A (en) | Method and system suitable for real-time judgment of surrounding rock grade of TBM tunneling tunnel | |
| CN113569459A (en) | Group intelligence-based hydraulic support performance degradation quantitative evaluation method and system | |
| CN117473285B (en) | Intelligent operation and maintenance management system and method based on digital twinning | |
| CN115017206A (en) | Mine CO abnormal disturbance intelligent identification and coal spontaneous combustion early warning value determination method | |
| CN104504265A (en) | Method for safety evaluation of monitoring information of in-service bridge | |
| CN117333038A (en) | Economic trend analysis system based on big data | |
| CN111160490A (en) | Deep learning dangerous rock deformation prediction method and device based on multiple time sequences | |
| CN114781450B (en) | Train rolling bearing state identification method based on parameter optimization MOMEDA-MIA-CNN | |
| Diaz et al. | Towards atmospheric monitoring data analysis in underground coal mines | |
| CN114118678A (en) | Iron works management system based on edge internet of things and architecture method thereof | |
| Gao et al. | Anomaly detection for time series with difference rate sample entropy and generative adversarial networks | |
| CN113033289A (en) | Safety helmet wearing inspection method, device and system based on DSSD algorithm | |
| CN117345344B (en) | Intelligent prediction method and system for mine acoustic and electric signals | |
| CN117523499B (en) | Forest fire prevention monitoring method and system based on Beidou positioning and sensing | |
| CN113837306B (en) | Abnormal behavior detection method based on human body key point space-time diagram model | |
| CN113778733B (en) | Log sequence anomaly detection method based on multi-scale MASS | |
| CN111798131B (en) | Carbon dioxide flooding injection and production system safety risk monitoring method | |
| CN117828335B (en) | Remote operator track control system and method for offshore booster station | |
| CN116611004B (en) | Coal mine safety disaster prediction model training method, early warning method and early warning system | |
| CN117726181B (en) | Collaborative fusion and hierarchical prediction method for typical disaster risk heterogeneous information of coal mine | |
| Zhou | Application of data mining in coal mine safety decision system based on rough set | |
| CN116484950A (en) | Auxiliary decision expert system applied to mine fire prevention and extinguishment field |
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 |