CN117829436B - Intelligent mine management and control method and system based on digital twinning - Google Patents
Intelligent mine management and control method and system based on digital twinning Download PDFInfo
- Publication number
- CN117829436B CN117829436B CN202410245446.4A CN202410245446A CN117829436B CN 117829436 B CN117829436 B CN 117829436B CN 202410245446 A CN202410245446 A CN 202410245446A CN 117829436 B CN117829436 B CN 117829436B
- Authority
- CN
- China
- Prior art keywords
- data
- twin
- fault
- plan
- time
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 69
- 238000005065 mining Methods 0.000 claims abstract description 50
- 238000012423 maintenance Methods 0.000 claims abstract description 14
- 230000008030 elimination Effects 0.000 claims abstract description 5
- 238000003379 elimination reaction Methods 0.000 claims abstract description 5
- 238000013507 mapping Methods 0.000 claims abstract description 5
- 238000009877 rendering Methods 0.000 claims abstract description 5
- 238000013528 artificial neural network Methods 0.000 claims description 32
- 230000008569 process Effects 0.000 claims description 27
- 230000006870 function Effects 0.000 claims description 25
- 230000004927 fusion Effects 0.000 claims description 24
- 238000007726 management method Methods 0.000 claims description 24
- 238000005553 drilling Methods 0.000 claims description 21
- 238000012549 training Methods 0.000 claims description 15
- 125000004122 cyclic group Chemical group 0.000 claims description 12
- 238000001914 filtration Methods 0.000 claims description 12
- 230000007787 long-term memory Effects 0.000 claims description 10
- 238000011068 loading method Methods 0.000 claims description 9
- 238000004519 manufacturing process Methods 0.000 claims description 9
- 238000005516 engineering process Methods 0.000 claims description 7
- 230000007774 longterm Effects 0.000 claims description 7
- 238000012545 processing Methods 0.000 claims description 7
- 238000011156 evaluation Methods 0.000 claims description 6
- 238000009423 ventilation Methods 0.000 claims description 6
- 239000000284 extract Substances 0.000 claims description 4
- 230000005236 sound signal Effects 0.000 claims description 4
- 241000218691 Cupressaceae Species 0.000 claims description 3
- 230000001133 acceleration Effects 0.000 claims description 3
- 238000005422 blasting Methods 0.000 claims description 3
- 238000013461 design Methods 0.000 claims description 3
- 238000006073 displacement reaction Methods 0.000 claims description 3
- 238000007667 floating Methods 0.000 claims description 3
- 239000000203 mixture Substances 0.000 claims description 3
- 238000010977 unit operation Methods 0.000 claims description 3
- 238000005457 optimization Methods 0.000 claims description 2
- 238000007781 pre-processing Methods 0.000 claims description 2
- 238000012360 testing method Methods 0.000 claims description 2
- 238000010606 normalization Methods 0.000 claims 2
- 239000004575 stone Substances 0.000 claims 2
- 238000010276 construction Methods 0.000 claims 1
- 238000003860 storage Methods 0.000 description 10
- 239000011159 matrix material Substances 0.000 description 8
- 230000015654 memory Effects 0.000 description 7
- 230000006403 short-term memory Effects 0.000 description 4
- 238000012544 monitoring process Methods 0.000 description 3
- 230000003287 optical effect Effects 0.000 description 3
- 230000000007 visual effect Effects 0.000 description 3
- 230000002159 abnormal effect Effects 0.000 description 2
- 230000006978 adaptation Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000005259 measurement Methods 0.000 description 2
- 230000007246 mechanism Effects 0.000 description 2
- 239000013307 optical fiber Substances 0.000 description 2
- 230000000644 propagated effect Effects 0.000 description 2
- 230000008439 repair process Effects 0.000 description 2
- 230000002123 temporal effect Effects 0.000 description 2
- 230000009471 action Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000015556 catabolic process Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000013523 data management Methods 0.000 description 1
- 238000006731 degradation reaction Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 230000008034 disappearance Effects 0.000 description 1
- 230000002068 genetic effect Effects 0.000 description 1
- 230000036541 health Effects 0.000 description 1
- 230000006386 memory function Effects 0.000 description 1
- 238000012806 monitoring device Methods 0.000 description 1
- 238000013439 planning Methods 0.000 description 1
- 230000000306 recurrent effect Effects 0.000 description 1
- 230000003252 repetitive effect Effects 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 230000001629 suppression Effects 0.000 description 1
- 230000007704 transition Effects 0.000 description 1
Landscapes
- Testing And Monitoring For Control Systems (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention belongs to the technical field of mine management, and provides a digital twinning-based intelligent mine management and control method and system. The method comprises the following steps: establishing a geometric model of mining equipment, reconstructing and rendering mine environment data of the geometric model, and constructing a digital twin management and control system of a mine based on a digital twin five-dimensional architecture; based on a pre-trained mixed prediction model, predicting the future state of the twin data to obtain a prediction result; mapping the prediction result into the digital twin system to update a predicted state of the virtual entity of the mining equipment; analyzing the fault event in the prediction result, and dynamically scheduling the designated fault event for fault elimination according to a preset rule; therefore, the invention can solve the problem of the prior art that mining management and control of the mine falls, is greatly convenient for managing various devices in the mine, implements predictive maintenance and greatly improves the safety and reliability of the devices.
Description
Technical Field
The invention relates to the technical field of mine management, in particular to a digital twinning-based intelligent mine management and control method and system.
Background
Digital twinning is a technique that combines physical systems of the real world with digital models of the virtual world. By digital twinning technology, physical systems in the real world can be monitored and simulated in a virtual environment, and state information of the systems can be monitored in real time.
In modern mining industry, most mines employ automated equipment. As technology progresses, more and more equipment and production areas are present within the mine, such that the management pressures increase, especially in the face of extreme conditions of the mine environment and the high complexity of equipment maintenance, must be addressed at any time with sudden and difficult predictability of equipment failure. In the existing mining industry, the conventional manual control is still remained, equipment faults cannot be predicted, potential safety risks are not known, and mine revenues cannot be comprehensively balanced when equipment is maintained, so that the equipment needs to be changed.
Disclosure of Invention
In view of the technical problems, the invention provides a digital twinning-based intelligent mine management and control method and system, which are used for solving the problem of mine exploitation management and control lag in the prior art.
Other features and advantages of the present disclosure will be apparent from the following detailed description, or may be learned in part by the practice of the disclosure.
According to an aspect of the invention, a digital twinning-based intelligent mine control method is disclosed, the method comprising:
Establishing a geometric model of mining equipment, reconstructing and rendering mine environment data of the geometric model, and constructing a digital twin management and control system of a mine based on a digital twin five-dimensional architecture, wherein the digital twin five-dimensional architecture comprises a physical entity, a virtual entity, a service system, twin data and connection;
Based on a pre-trained hybrid prediction model, predicting the future state of the twin data to obtain a prediction result, wherein the twin data comprises sensor data, image data and sound data, and the hybrid prediction model comprises a deep fusion neural network for respectively processing the twin data of different modes, a space-time attention network for establishing the space-time relationship of the twin data, and a long-term memory network for fusing the outputs of the deep fusion neural network and the space-time attention network so that the dependency relationship of the twin data in time sequence is acquired;
Mapping the prediction result into the digital twin system to update a predicted state of the virtual entity of the mining equipment;
And analyzing the fault event in the prediction result, and dynamically scheduling the designated fault event for fault elimination according to a preset rule.
Further, when the geometric model of the mining equipment is built, the adopted method comprises a 3D laser point cloud scanning method and a mechanical design method.
Further, the 3D laser point cloud scanning method is adopted to scan a specific path of the mining equipment to obtain point cloud data, an optimal filtering parameter combination is obtained based on a radius and statistics combined filtering technology, the filtering parameter combination is adopted to filter the point cloud data, and the cypress surface reconstruction is carried out on the filtered point cloud data to obtain the geometric model.
Further, the mining equipment at least comprises a robot, a horizontal hole drilling machine, a medium-length hole drilling machine, a loading machine, a telescopic drilling machine, a scraper, an anchor rod machine, a traction machine and a lifting machine, sensor data are derived from an oil temperature sensor, an oil pressure sensor, a laser ranging sensor, a temperature sensor, a current transformer, a voltage sensor, an encoder, a displacement sensor, an acceleration sensor, a pressure sensor and a vibration sensor, the image data are working environment images or continuous camera frame sequences of the mining equipment, and the sound data are sounds in the working process of the mining equipment.
Further, when the sensor data is acquired, noise removal is performed on the sensor data based on a Gaussian function and a Kalman filtering algorithm.
Further, after training the hybrid prediction model, performing performance evaluation on the hybrid prediction model by adopting an average absolute error, an average absolute percentage error, a root mean square error and a mean square error, and performing efficiency evaluation on the hybrid prediction model by adopting parameters, floating point operation, reasoning time and training time.
Further, in analyzing the fault event, the fault type, the fault frequency, the severity assessment, the fault cause, the repair location, the repair time are analyzed.
Further, before dynamic scheduling, a scheduling model is built, wherein a working area, a mine, a minimum exploitation unit, a device group and a process group are defined as elements in the scheduling model, decision variables which are mutually influenced among the elements are defined, minimum working time and minimum device replacement frequency are defined as objective functions, an equivalent relation is defined, constraint conditions which accord with a safety standard and accord with a time sequence are defined, and when dynamic scheduling is carried out, the objective functions are solved according to the elements, the decision variables, the equivalent relation and the constraint conditions, so that a new working plan is obtained.
According to another aspect of the present disclosure, there is provided a digital twinning-based intelligent mine management and control system, the system, when constructed, collects a geometric model of mining equipment, and reconstructs and renders mine environment data of the geometric model, and the system is constructed based on a digital twinning five-dimensional architecture, the digital twinning five-dimensional architecture includes a physical entity, a virtual entity, a service system, twinning data and connection, and the system further includes:
the data advanced prediction module is used for predicting the future state of the twin data based on a pre-trained mixed prediction model to obtain a prediction result, the twin data comprises sensor data, image data and sound data, the mixed prediction model comprises a deep fusion neural network for respectively processing the twin data of different modes, a space-time attention network for establishing the space-time relationship of the twin data, and a long-period memory network for fusing the outputs of the deep fusion neural network and the space-time attention network so that the dependency relationship of the twin data in time sequence is acquired; a UI module for mapping the prediction results into the digital twinning system to update a predicted state of the virtual entity of the mining equipment; and the scheduling module analyzes the fault event in the prediction result and dynamically schedules the designated fault event for eliminating the fault according to a preset rule.
The technical scheme of the present disclosure has the following beneficial effects:
The digital twin technology is adopted to control the mine, so that various devices in the mine are conveniently managed, predictive maintenance is implemented, and the safety and reliability of the devices are greatly improved; the disclosed hybrid prediction model can comprehensively and accurately analyze multi-mode data generated in the exploitation, and greatly improves the accuracy of equipment fault prediction.
Drawings
FIG. 1 is a flow chart of a digital twinning-based intelligent mine management and control method in an embodiment of the present disclosure;
FIG. 2 is a block diagram of a digital twinning-based intelligent mine management and control in an embodiment of the present disclosure;
fig. 3 is a computer readable storage medium storing a digital twinning-based intelligent mine management method in an embodiment of the present description.
Detailed Description
Example embodiments will now be described more fully with reference to the accompanying drawings. However, the exemplary embodiments may be embodied in many forms and should not be construed as limited to the examples set forth herein; rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the concept of the example embodiments to those skilled in the art. The described features, structures, or characteristics may be combined in any suitable manner in one or more embodiments. In the following description, numerous specific details are provided to give a thorough understanding of embodiments of the present disclosure. One skilled in the relevant art will recognize, however, that the aspects of the disclosure may be practiced without one or more of the specific details, or with other methods, components, systems, steps, etc. In other instances, well-known technical solutions have not been shown or described in detail to avoid obscuring aspects of the present disclosure.
Furthermore, the drawings are only schematic illustrations of the present disclosure. The same reference numerals in the drawings denote the same or similar parts, and thus a repetitive description thereof will be omitted. Some of the block diagrams shown in the figures are functional entities and do not necessarily correspond to physically or logically separate entities. These functional entities may be implemented in software or in one or more hardware modules or integrated circuits or in different networks and/or processor systems and/or microcontroller systems.
As shown in fig. 1, the embodiment of the present disclosure provides a digital twinning-based intelligent mine management and control method, where the implementation subject of the method may be an interphone. The method specifically comprises the following steps S101-S105:
In step S101, a geometric model of the mining device is established, mine environment data of the geometric model is reconstructed and rendered, and a digital twin management and control system of the mine is constructed based on a digital twin five-dimensional architecture, wherein the digital twin five-dimensional architecture comprises a physical entity, a virtual entity, a service system, twin data and connection.
When the geometric model of the mining equipment is established, a 3D laser point cloud scanning method and a mechanical design method can be adopted. And when the 3D laser point cloud scanning method is adopted, scanning a specific path of the mining equipment to obtain point cloud data, obtaining an optimal filtering parameter combination based on a radius and statistics combined filtering technology, filtering the point cloud data by adopting the filtering parameter combination, and performing cypress surface reconstruction on the filtered point cloud data to obtain the geometric model. And then, performing point cloud processing, reconstruction and rendering on the surrounding environment of the geometric model to obtain a highly-realistic digital twinned localized monitoring scene. And finally, configuring a service system, configuring network connection, constructing a digital twin management and control system and displaying in a visual form based on a digital twin five-dimensional architecture.
In step S102, based on a pre-trained hybrid prediction model, future state prediction is performed on the twin data to obtain a prediction result, where the twin data includes sensor data, image data and sound data, and the hybrid prediction model includes a deep fusion neural network for respectively processing the twin data of different modalities, a spatiotemporal attention network for establishing a spatiotemporal relationship of the twin data, and a long-term and short-term memory network for fusing outputs of the deep fusion neural network and the spatiotemporal attention network so that a dependency relationship of the twin data in time sequence is acquired.
Wherein, twin data mainly comprises three types: firstly, sensor data, namely time sequence data of different sensors from mining equipment in mines, including indexes such as numerical sequences of temperature and pressure, vibration and the like; one is image data, referring to an image or a sequence of consecutive camera frames of the working environment of the mining equipment, for capturing visual state information of the equipment; the other is sound data captured during operation of the device, which can help detect abnormal noise of the device to assist in fault prediction. The mixed prediction model utilizes the deep fusion neural network to process the multi-mode data and carry out deep fusion, and the output data is the prediction of potential faults of equipment. Specifically, the output data may be defined as a probability value or classification result, i.e. a predictive probability is assigned to each possible fault type, and results higher than the probability are qualitatively regarded as faults or impending faults, which can be maintained on demand. Specifically, the mining equipment at least comprises a robot, a horizontal hole drilling machine, a medium-length hole drilling machine, a loading machine, a telescopic drilling machine, a scraper, an anchor rod machine, a traction machine and a lifting machine, sensor data are derived from an oil temperature sensor, an oil pressure sensor, a laser ranging sensor, a temperature sensor, a current transformer, a voltage sensor, an encoder, a displacement sensor, an acceleration sensor, a pressure sensor and a vibration sensor, the image data are working environment images or continuous camera frame sequences of the mining equipment, and the sound data are sounds in the working process of the mining equipment.
The deep fusion neural network can process different types of high-resolution images, complex sound signals and multidimensional sensor data in different branches, and then effectively fuses the data through a deep fusion layer so as to improve the prediction performance of equipment faults, for example, when monitoring the health conditions of key maintenance components such as a hydraulic arm and the like, the deep fusion neural network can use data from a vibration sensor, an acoustic monitoring device and a visual detection device, and the lack of certain types of data can lead to prediction results. The deep fusion neural network organically integrates information from different network branches through a deep fusion layer to form a global feature representation, so that a model can more comprehensively know the working state of equipment, a more accurate basis is provided for the prediction of equipment faults, and powerful support is provided for the follow-up time sequence data modeling and the optimization of long-term dependency.
The time-space attention network utilizes an attention mechanism to enable the network to pay attention to key moments and areas better, so that modeling capacity of time-space data is enhanced, time and space relations in captured data are important in a twin data management and control system needing to consider time and space characteristics, and more accurate and comprehensive support is provided for equipment fault prediction. In mine equipment maintenance practice, complex time series data and position correlation exist, and by introducing a space-time attention network, the model not only can accurately calibrate key time points, but also can identify areas with great influence on equipment performance. For example, the spatio-temporal attention mechanism may accurately locate abnormal wear patterns occurring under specific operating conditions when predicting conveyor belt wear, thereby providing decision support for early maintenance and replacement, and the spatio-temporal attention network may adapt to different terrain and obstacle configurations when monitoring the navigation system of the mine car, and optimize path planning by analyzing the evolution of spatio-temporal data.
The long-term and short-term memory network is only used for capturing long-term dependency in time series data, so that the problem of gradient disappearance is effectively avoided. Mining equipment typically operates in extreme and unpredictable environments, and the collected data reflects the operating conditions of the equipment, and these data present complex temporal features that can be analyzed by long and short term memory networks. For example, in a mining environment, components of equipment (e.g., drill bits, loading arms, conveyor systems) may experience increasingly subtle performance degradation, which shows long-term trends in time data, long-term memory networks identifying these long-term dependencies, and potential failures may be discovered as early as possible.
In step S103, the prediction results are mapped into the digital twin system to update the predicted state of the virtual entity of the mining equipment.
In step S104, the fault event in the prediction result is analyzed, and the specified fault event is dynamically scheduled for fault elimination according to a preset rule.
When analyzing the fault event, the fault type, the fault frequency, the severity assessment, the fault reason, the maintenance location and the maintenance time are analyzed. For low frequency, long term, complex faults, significant impact on production progress is required, and the initial production schedule needs to be readjusted immediately; for high frequency, short term, simple failures, the scheduling plan is readjusted periodically; for medium-frequency, short-term failures, the initial production schedule needs to be adjusted at intervals. Other frequencies and types of faults may employ dynamic scheduling.
In one embodiment, the temperature is a point of particular concern in system management and control, drill bit loss may be caused by too high temperature, mine car crash may be caused by too high temperature of motors of a lifter and a conveyor, and in order to better predict temperature state change, a cyclic neural network can be further arranged in the mixed preset model to process continuous temperature data in the sensor data in combination with a long-term and short-term memory network. Since the motor temperature data shows clear time series characteristics, past data has obvious influence on future temperature, and the cyclic neural network and the long-short-term memory network have memory functions and can retain historical data, the method can be particularly used for processing the temperature data. Similarly, the cyclic neural network extracts relevant characteristics in temperature data and predicts future states, captures motor temperature trend, and the hybrid prediction module of the integrated cyclic neural network performs preprocessing, divides the data into a training set and a testing set, normalizes, iterates training, selects an optimal model, extracts optimal parameters and inverse normalizes when training, and then predicts complete motor temperature cyclic data, namely temperature changes in the working cycle of the mining equipment, such as motor temperature changes when a hoist is loaded, unloaded and returned to the bottom hole, and temperature changes when a drill bit intermittently works. The digital twin management and control system then digitally displays the operating conditions and perceives the condition of the next cycle ahead of time to determine if it exceeds a temperature threshold, thereby providing valuable guidance for predictive maintenance.
The recurrent neural network may be one network branch in a deep fusion neural network.
In one embodiment, noise removal is performed on the sensor data based on a gaussian function and a kalman filter algorithm when the sensor data is acquired.
Wherein the one-dimensional zero-mean gaussian function of the sensor data is expressed as:
is the standard deviation of the Gaussian function, t is the random variable, u is the average, and in the calculation, follows/> The frequency band of the gaussian filter is increased to widen the frequency range considered in the filtering process, and thus the filtered sensor data exhibits improved smoothness.
The function of the kalman filter is as follows:
wherein, All are defined variables which respectively represent a state vector, an observation vector, a state transition matrix, an input control matrix, an observation matrix, a process noise vector, a system control vector and a measurement noise vector. Hypothesis/>Is a positive, symmetrical, uncorrelated, zero-mean Gaussian white noise vector, then/>The method meets the following conditions:
Representing covariance, E is the expected, Q is the covariance matrix of the process noise, and R is the covariance matrix of the observed noise.
The kernel of the kalman filter is divided into two types, prediction and update, and then the prediction function can be expressed as:
the update function is expressed as:
wherein, The method respectively represents a Kalman gain matrix, a filter optimal value, a deviation matrix and a unit matrix, and can control and realize the suppression degree of the Kalman filter to process noise and measurement noise by properly adjusting the matrices Q and R, so that the sensor data is smoother.
In one embodiment, after the hybrid prediction model is trained, performance evaluation is performed on the hybrid prediction model using average absolute error, average absolute percentage error, root mean square error, and efficiency evaluation is performed on the hybrid prediction model using parameters, floating point operation, inference time, and training time.
In one embodiment, before dynamic scheduling, a scheduling model is built, wherein a working area, a mine, a minimum exploitation unit, a device group and a process group are defined as elements in the scheduling model, decision variables which are mutually influenced among the elements are defined, minimum working time and minimum device replacement frequency are defined as objective functions, equivalence relations are defined, constraint conditions which accord with safety standards and accord with time sequences are defined, and when dynamic scheduling is performed, the objective functions are solved according to the elements, the decision variables, the equivalence relations and the constraint conditions, so that a new working plan is obtained.
The working areas refer to different areas for working, such as a loading area, an unloading area, a production area, a stacking area and the like. The mine refers to different mines in the mine. The minimum unit of mining is the mass of ore under mining. The equipment group can comprise a robot, a horizontal hole drilling machine, a medium-length hole drilling machine, a charging machine, a telescopic drilling machine, a scraper, an anchor rod machine, a tractor and a lifting machine. The process may include various procedures such as drilling, loading, ventilation, descaling, blasting, ventilation, etc. The definition of the objective function is: minimizing the deviation between the end time of the rescheduled work schedule and the end time of the original schedule, and minimizing the equipment replacement frequency. The equivalence relation is: the rescheduled plan uses the replacement equipment when the flow start time is associated with the fault start time, and replaces the equipment's flow end time and travel time between blocks in another minimum unit operation; constraints may include: the rearranged plan should strictly follow the safety constraint, namely, the work can be performed after the potential safety hazard is eliminated; the rescheduled plan should follow the flow order of the original plan, i.e., the start time of the next process is later than the time of the previous process; the rescheduled plan should follow the mining order of the initial plan, i.e., the start time of the next minimum unit of mining is later than the end time of the previous minimum unit of mining. After each composition of the scheduling model is determined, when scheduling is needed after a fault is predicted, the scheduling model is solved, namely an objective function is solved, and the optimal scheduling plan conforming to the objective function can be obtained. The objective function may be solved using a genetic algorithm.
Based on the same thought, as shown in fig. 2, the exemplary embodiment of the disclosure further provides a digital twinning-based intelligent mine management and control system, which collects a geometric model of mining equipment and reconstructs and renders mine environment data of the geometric model when being constructed, and is constructed based on a digital twinning five-dimensional architecture, wherein the digital twinning five-dimensional architecture comprises a physical entity, a virtual entity, a service system, twinning data and connection, and the system further comprises: a data advance prediction module 201, where the data advance prediction module 201 is configured to predict a future state of the twin data based on a pre-trained hybrid prediction model, to obtain a prediction result, where the twin data includes sensor data, image data, and sound data, and the hybrid prediction model includes a deep fusion neural network that processes the twin data of different modalities, a spatiotemporal attention network that establishes a spatiotemporal relationship of the twin data, and a long-term memory network that fuses outputs of the deep fusion neural network and the spatiotemporal attention network so that a dependency relationship of the twin data in time sequence is acquired; a UI module 202, wherein the UI module 202 is configured to map the prediction result into the digital twin system to update a prediction state of the virtual entity of the mining equipment; and the scheduling module 203 is used for analyzing the fault event in the prediction result, and dynamically scheduling the designated fault event for eliminating the fault according to a preset rule.
The system adopts a digital twin technology to control the mine, so that various devices in the mine are conveniently managed, predictive maintenance is implemented, and the safety and reliability of the devices are greatly improved; the disclosed hybrid prediction model can comprehensively and accurately analyze multi-mode data generated in the exploitation, and greatly improves the accuracy of equipment fault prediction.
The specific details of each module in the above system are already described in the method part of the embodiments, and the details that are not disclosed can be referred to the embodiment of the method part, so that they will not be described in detail.
Based on the same idea, exemplary embodiments of the present disclosure further provide a computer readable storage medium having stored thereon a program product capable of implementing the method described in the present specification. In some possible implementations, various aspects of the disclosure may also be implemented in the form of a program product comprising program code for causing a terminal device to carry out the steps according to various exemplary embodiments of the disclosure as described in the "digital twinned-based intelligent mine control method" section of the specification when the program product is run on the terminal device.
Referring to fig. 3, a program product 300 for implementing the above-described method according to an exemplary embodiment of the present disclosure is described, which may employ a portable compact disc read only memory (CD-ROM) and include program code, and may be run on a terminal device, such as a personal computer. However, the program product of the present disclosure is not limited thereto, and in this document, a readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, or device.
The program product may employ any combination of one or more readable media. The readable medium may be a readable signal medium or a readable storage medium. The readable storage medium can be, for example, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, or device, or a combination of any of the foregoing. More specific examples (a non-exhaustive list) of the readable storage medium would include the following: an electrical connection having one or more wires, a portable disk, a hard disk, random Access Memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.
The computer readable signal medium may include a data signal propagated in baseband or as part of a carrier wave with readable program code embodied therein. Such a propagated data signal may take any of a variety of forms, including, but not limited to, electro-magnetic, optical, or any suitable combination of the foregoing. A readable signal medium may also be any readable medium that is not a readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, or device.
Program code embodied on a readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.
Program code for carrying out operations of the present disclosure may be written in any combination of one or more programming languages, including an object oriented programming language such as Java, C++ or the like and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the user's computing device, partly on the user's device, as a stand-alone software package, partly on the user's computing device, partly on a remote computing device, or entirely on the remote computing device or server. In the case of remote computing devices, the remote computing device may be connected to the user computing device through any kind of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or may be connected to an external computing device (e.g., connected via the Internet using an Internet service provider).
From the above description of embodiments, those skilled in the art will readily appreciate that the example embodiments described herein may be implemented in software, or may be implemented in software in combination with the necessary hardware. Thus, the technical solution according to the embodiments of the present disclosure may be embodied in the form of a software product, which may be stored in a non-volatile storage medium (may be a CD-ROM, a U-disk, a mobile hard disk, etc.) or on a network, including several instructions to cause a computing device (may be a personal computer, a server, a terminal system, or a network device, etc.) to perform the method according to the exemplary embodiments of the present disclosure.
Furthermore, the above-described figures are only schematic illustrations of processes included in the method according to the exemplary embodiments of the present disclosure, and are not intended to be limiting. It will be readily appreciated that the processes shown in the above figures do not indicate or limit the temporal order of these processes. In addition, it is also readily understood that these processes may be performed synchronously or asynchronously, for example, among a plurality of modules.
It should be noted that although in the above detailed description several modules or units of a device for action execution are mentioned, such a division is not mandatory. Indeed, the features and functionality of two or more modules or units described above may be embodied in one module or unit in accordance with exemplary embodiments of the present disclosure. Conversely, the features and functions of one module or unit described above may be further divided into a plurality of modules or units to be embodied.
Other embodiments of the disclosure will be apparent to those skilled in the art from consideration of the specification and practice of the disclosure disclosed herein. This application is intended to cover any adaptations, uses, or adaptations of the disclosure following, in general, the principles of the disclosure and including such departures from the present disclosure as come within known or customary practice within the art to which the disclosure pertains. It is intended that the specification and examples be considered as exemplary only, with a true scope and spirit of the disclosure being indicated by the following claims.
Claims (7)
1. An intelligent mine management and control method based on digital twinning is characterized by comprising the following steps:
Establishing a geometric model of mining equipment, reconstructing and rendering mine environment data of the geometric model, and constructing a digital twin management and control system of a mine based on a digital twin five-dimensional architecture, wherein the digital twin five-dimensional architecture comprises a physical entity, a virtual entity, a service system, twin data and connection;
Based on a pre-trained hybrid prediction model, future state prediction is carried out on the twin data to obtain a prediction result, the twin data comprise sensor data, image data and sound data, the hybrid prediction model comprises a deep fusion neural network for respectively processing the twin data of different modes, a space-time attention network for establishing a space-time relation of the twin data, a long-term memory network for only fusing the output of the deep fusion neural network and the space-time attention network so that the time-sequence dependency of the twin data is acquired, the deep fusion neural network utilizes different branches to process different types of high-resolution images, complex sound signals and multi-dimensional sensor data, and is fused through a deep fusion layer, a cyclic neural network is arranged in the hybrid prediction model to process continuous temperature data in the sensor data, the cyclic neural network extracts relevant features in the temperature data and predicts the future state, a motor temperature trend is captured, and a hybrid prediction module integrating the cyclic neural network is used for preprocessing, dividing the cyclic neural network into optimal training parameters, testing the optimal training parameters, performing optimal iteration and selecting optimal training parameters, and performing optimal parameter normalization, and performing optimal training, and optimizing the optimal parameter set;
mapping the prediction result into the digital twin management and control system to update a predicted state of the virtual entity of the mining equipment;
Analyzing the fault event in the prediction result, and dynamically scheduling the designated fault event for fault elimination according to a preset rule;
When analyzing fault events, analyzing fault types, fault frequencies, severity assessment, fault reasons, maintenance sites and maintenance time, readjusting an initial production plan for low-frequency, long-term and complex faults, periodically readjusting a scheduling plan for high-frequency, short-term and simple faults, and adjusting the initial production plan for medium-frequency and short-term faults at intervals, wherein other frequency and type faults adopt dynamic scheduling;
before dynamic scheduling, a scheduling model is established, a working area, a mine, a minimum mining unit, a device group and a process group are defined in the scheduling model, decision variables which are mutually influenced among the elements are defined, minimum working time and minimum device replacement frequency are defined as objective functions, equivalence relations are defined, constraint conditions which accord with safety standards and time sequences are defined, when dynamic scheduling is carried out, the objective functions are solved according to the elements, the decision variables, the equivalence relations and the constraint conditions, a new working plan is obtained, the working area refers to different working areas, the minimum mining unit is a mining stone block, the device group comprises a robot, a horizontal hole drilling machine, a medium deep hole drilling machine, a loading machine, a telescopic drilling machine, a scraper, an anchor rod machine, a tractor and a lifter, and the process group comprises various drilling holes, loading, ventilation, descaling, blasting and ventilation, and the objective functions are defined as follows: minimizing the deviation between the end time of the rescheduled work plan and the end time of the original plan, and minimizing the equipment replacement frequency, wherein the equivalence relation is that: the rescheduling schedule uses a replacement device when the flow start time is associated with the fault start time, and replaces the device's flow end time and travel time between blocks in another minimum unit operation, the constraints comprising: the rescheduled plan strictly follows the safety constraint, the rescheduled plan should follow the flow order of the initial plan, the rescheduled plan should follow the mining order of the initial plan, and after each composition of the scheduling model is determined, the objective function is solved when a fault is predicted and scheduling is needed.
2. The intelligent mine management and control method based on digital twinning according to claim 1, wherein the adopted method comprises a 3D laser point cloud scanning method and a mechanical design method when the geometric model of the mining equipment is built.
3. The intelligent mine management and control method based on digital twinning according to claim 2, wherein the 3D laser point cloud scanning method is adopted to scan a specific path of the mining equipment to obtain point cloud data, an optimal filtering parameter combination is obtained based on a radius and statistics combined filtering technology, the filtering parameter combination is adopted to filter the point cloud data, and the cypress surface reconstruction is carried out on the filtered point cloud data to obtain the geometric model.
4. The intelligent mine management and control method based on digital twinning according to claim 1, wherein the mining equipment at least comprises a robot, a horizontal hole drilling machine, a medium deep hole drilling machine, a loader, a telescopic drilling machine, a scraper, a roof bolter, a tractor and a lifter, the sensor data are derived from an oil temperature sensor, an oil pressure sensor, a laser ranging sensor, a current transformer, a voltage sensor, an encoder, a displacement sensor, an acceleration sensor and a vibration sensor, the image data are working environment images or continuous camera frame sequences of the mining equipment, and the sound data are sounds in the working of the mining equipment.
5. The digital twinning-based intelligent mine control method of claim 1, wherein the sensor data is noise-removed based on a gaussian function and a kalman filter algorithm when the sensor data is acquired.
6. The digital twinning-based intelligent mine control method according to claim 1, wherein after the hybrid prediction model is trained, performance evaluation is performed on the hybrid prediction model by using an average absolute error, an average absolute percentage error, a root mean square error and a mean square error, and efficiency evaluation is performed on the hybrid prediction model by using parameters, floating point operation, reasoning time and training time.
7. The utility model provides a wisdom mine management and control system based on digital twin, its characterized in that, the system is when constructing, gathers the geometric model of mining equipment to carry out reconstruction and rendering to the mine environment data of geometric model, based on digital twin five-dimensional framework, the construction obtains the system, digital twin five-dimensional framework includes physical entity, virtual entity, service system, twin data and connection, the system still includes:
The system comprises a data advance prediction module, a prediction module and a temperature normalization module, wherein the data advance prediction module is used for predicting the future state of twin data based on a pre-trained hybrid prediction model, the twin data comprises sensor data, image data and sound data, the hybrid prediction model comprises a deep fusion neural network for respectively processing the twin data of different modes, a space-time attention network for establishing the space-time relationship of the twin data, a long-term memory network only used for fusing the output of the deep fusion neural network and the space-time attention network so that the dependency relationship of the twin data in time sequence is acquired, the deep fusion neural network processes different types of high-resolution images, complex sound signals and multidimensional sensor data by utilizing different branches and fuses the high-resolution images, complex sound signals and multidimensional sensor data through a deep fusion layer, one cyclic neural network is arranged in the hybrid prediction model to process continuous temperature data in the sensor data by combining with a long-term memory network, the cyclic neural network extracts relevant features in the temperature data and predicts the future state, and the integrated cyclic neural network captures the temperature trend, and the hybrid neural network is subjected to optimal iterative training parameter optimization, the optimal training parameter set is selected and the optimal parameter set is selected by utilizing the pre-training module, the optimal prediction module and the optimal iterative training parameter set;
A UI module for mapping the prediction results into the system to update a prediction state of the virtual entity of the mining equipment;
The scheduling module analyzes fault events in the prediction result, dynamically schedules specified fault events for fault elimination according to preset rules, analyzes fault types, fault frequencies, severity assessment, fault reasons, maintenance sites and maintenance time when the fault events are analyzed, readjusts an initial production plan for low-frequency, long-term and complex faults, periodically readjust the scheduling plan for high-frequency, short-term and simple faults, adjusts the initial production plan for medium-frequency and short-term faults at intervals, and adopts dynamic scheduling for other frequency and type faults; before dynamic scheduling, a scheduling model is established, a working area, a mine, a minimum mining unit, a device group and a process group are defined in the scheduling model, decision variables which are mutually influenced among the elements are defined, minimum working time and minimum device replacement frequency are defined as objective functions, equivalence relations are defined, constraint conditions which accord with safety standards and time sequences are defined, when dynamic scheduling is carried out, the objective functions are solved according to the elements, the decision variables, the equivalence relations and the constraint conditions, a new working plan is obtained, the working area refers to different working areas, the minimum mining unit is a mining stone block, the device group comprises a robot, a horizontal hole drilling machine, a medium deep hole drilling machine, a loading machine, a telescopic drilling machine, a scraper, an anchor rod machine, a tractor and a lifter, and the process group comprises various drilling holes, loading, ventilation, descaling, blasting and ventilation, and the objective functions are defined as follows: minimizing the deviation between the end time of the rescheduled work plan and the end time of the original plan, and minimizing the equipment replacement frequency, wherein the equivalence relation is that: the rescheduling schedule uses a replacement device when the flow start time is associated with the fault start time, and replaces the device's flow end time and travel time between blocks in another minimum unit operation, the constraints comprising: the rescheduled plan strictly follows the safety constraint, the rescheduled plan should follow the flow order of the initial plan, the rescheduled plan should follow the mining order of the initial plan, and after each composition of the scheduling model is determined, the objective function is solved when a fault is predicted and scheduling is needed.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410245446.4A CN117829436B (en) | 2024-03-05 | 2024-03-05 | Intelligent mine management and control method and system based on digital twinning |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410245446.4A CN117829436B (en) | 2024-03-05 | 2024-03-05 | Intelligent mine management and control method and system based on digital twinning |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117829436A CN117829436A (en) | 2024-04-05 |
| CN117829436B true CN117829436B (en) | 2024-05-17 |
Family
ID=90504403
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410245446.4A Active CN117829436B (en) | 2024-03-05 | 2024-03-05 | Intelligent mine management and control method and system based on digital twinning |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117829436B (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111210359A (en) * | 2019-12-30 | 2020-05-29 | 中国矿业大学(北京) | Intelligent mine scene oriented digital twin evolution mechanism and method |
| RU2759071C1 (en) * | 2021-02-12 | 2021-11-09 | Акционерное общество "СУЭК-Кузбасс" | Automated mine emergency forecasting system and method for automated mine emergency forecasting |
| CN114254457A (en) * | 2021-12-17 | 2022-03-29 | 中国矿业大学(北京) | Mine hydraulic support fatigue life prediction method based on digital twinning |
| CN114862054A (en) * | 2022-06-01 | 2022-08-05 | 云南大学 | Mine equipment health management system and method based on digital twinning |
| CN114912369A (en) * | 2022-06-10 | 2022-08-16 | 昆明理工大学 | Mine intelligence management and control optimization system based on digit twin |
| CN116629602A (en) * | 2023-05-10 | 2023-08-22 | 中国三峡建工(集团)有限公司 | Dynamic monitoring and disaster early warning system for earth-rock dam seepage safety based on digital twin technology and construction method thereof |
-
2024
- 2024-03-05 CN CN202410245446.4A patent/CN117829436B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111210359A (en) * | 2019-12-30 | 2020-05-29 | 中国矿业大学(北京) | Intelligent mine scene oriented digital twin evolution mechanism and method |
| RU2759071C1 (en) * | 2021-02-12 | 2021-11-09 | Акционерное общество "СУЭК-Кузбасс" | Automated mine emergency forecasting system and method for automated mine emergency forecasting |
| CN114254457A (en) * | 2021-12-17 | 2022-03-29 | 中国矿业大学(北京) | Mine hydraulic support fatigue life prediction method based on digital twinning |
| CN114862054A (en) * | 2022-06-01 | 2022-08-05 | 云南大学 | Mine equipment health management system and method based on digital twinning |
| CN114912369A (en) * | 2022-06-10 | 2022-08-16 | 昆明理工大学 | Mine intelligence management and control optimization system based on digit twin |
| CN116629602A (en) * | 2023-05-10 | 2023-08-22 | 中国三峡建工(集团)有限公司 | Dynamic monitoring and disaster early warning system for earth-rock dam seepage safety based on digital twin technology and construction method thereof |
Non-Patent Citations (1)
| Title |
|---|
| 李晖晖 等.《深度学习与计算机视觉》.西北工业大学出版社,2021,(第第一版版),17. * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117829436A (en) | 2024-04-05 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110633855B (en) | Bridge health state detection and management decision making system and method | |
| Vališ et al. | Application of selected Levy processes for degradation modelling of long range mine belt using real-time data | |
| CN110462628B (en) | Method and system for estimating operation of working vehicle, method for manufacturing classification model, learning data, and method for manufacturing learning data | |
| Sabillon et al. | Audio-based bayesian model for productivity estimation of cyclic construction activities | |
| JP7021732B2 (en) | Time series forecasting device, time series forecasting method and program | |
| Srinivasan et al. | Semi-Markov decision process with partial information for maintenance decisions | |
| CN112631240A (en) | Spacecraft fault active detection method and device | |
| CN111858526A (en) | Failure time space prediction method and system based on information system log | |
| AU2018219019A1 (en) | System for analyzing machine data | |
| CN114219211A (en) | Rock burst risk assessment method based on theory and data-driven fusion | |
| CN106444694A (en) | System abnormal condition pre-warning technology under big data | |
| Reza Golmakani et al. | Age‐based inspection scheme for condition‐based maintenance | |
| NO20210817A1 (en) | Constructing digital twins for oil and gas recovery using ensemble kalman filter | |
| CN114444816A (en) | Identification and control digital twin system of large-tonnage loader | |
| CN117829436B (en) | Intelligent mine management and control method and system based on digital twinning | |
| CN111369056A (en) | Geological disaster prediction method and electronic equipment | |
| Mahamedi et al. | Automating excavator productivity measurement using deep learning | |
| CN108805427B (en) | Power distribution network running state risk early warning system based on big data | |
| CN116776289B (en) | Numerical control machine tool processing method, device, electronic equipment and readable storage medium | |
| Rashid et al. | Construction equipment activity recognition from IMUs mounted on articulated implements and supervised classification | |
| CN116894213A (en) | Method for identifying working condition of excavator and working condition identifying device of excavator | |
| CN115222069A (en) | Equipment pre-diagnosis maintenance algorithm and intelligent factory management and control architecture integrating same | |
| Sharanya | A cyber physical system framework for industrial predictive maintenance using machine learning | |
| Castro et al. | A predictive maintenance strategy based on mean residual life for systems subject to competing failures due to degradation and shocks | |
| CN117252435B (en) | Factory production safety monitoring and early warning method and system based on industrial Internet |
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 |