Intelligent control method and system for unmanned transportation of coal mine

Abstract

The invention discloses a coal mine unmanned transportation intelligent control method and system, and belongs to the technical field of coal mine unmanned transportation intelligent control, and the method comprises the steps: building a digital twinborn body of a corresponding unmanned control target, and carrying out the dynamic updating of the digital twinborn body; the method comprises the following steps: monitoring an unmanned control target in real time to obtain corresponding comprehensive monitoring data, and dividing the comprehensive monitoring data into monitoring optimization data and monitoring control data; performing real-time optimization adjustment on the basic control strategy according to the monitoring optimization data; analyzing the monitoring control data according to the basic control strategy to obtain an application control mode of the corresponding unmanned control target, and controlling the unmanned control target according to the application control mode; the problems that a traditional coal mine transportation mode highly depends on manpower, efficiency is limited, potential safety hazards are many, energy consumption is large, response lags and the like are effectively solved, and meanwhile the defect that an existing intelligent coal flow transportation system is insufficient in dynamic environment adaptability is overcome.

Description

TECHNICAL FIELD

[0001] The present application belongs to the technical field of intelligent control of unmanned transportation in coal mines, and specifically relates to an intelligent control method and system for unmanned transportation in coal mines. BACKGROUND

[0002] In the field of coal production, the main coal flow transportation system, as a key link for transporting coal from the mining face to the ground, is regarded as the "underground artery" of coal production, and its operation efficiency and safety directly affect the overall production benefit of the coal mine. The traditional coal mine transportation mode highly depends on manual inspection, mechanical control and experience judgment, and has the problems of limited efficiency, high safety hazards, high energy consumption and lagging response.

[0003] With the deep integration of intelligent technology, an intelligent coal flow transportation system emerges as the times require, aiming at "unattended" to promote the leap from mechanization to wisdom of coal mine transportation. The system integrates automatic control, intelligent monitoring and early warning, and remote centralized management, adopts a distributed control structure, and can realize single machine automatic control or centralized control and monitoring of multiple belt machines, greatly improving the automation and intelligence level of coal flow transportation. However, the existing technology has essential defects in dynamic environment adaptability, and it is difficult to accurately control and optimize, especially when establishing an intelligent control system, it is difficult to fully consider all conditions in the actual operation process.

[0004] Therefore, in order to solve the above problems, the present application provides an intelligent control method and system for unmanned transportation in coal mines. SUMMARY

[0005] In order to solve the problems existing in the above scheme, the present application provides an intelligent control method and system for unmanned transportation in coal mines.

[0006] The object of the present application can be achieved by the following technical solutions:

[0007] An intelligent control system for unmanned transportation in coal mines, comprising a platform end and a device end;

[0008] The platform end comprises a digital twin module and a simulation module.

[0009] The digital twin module is used to establish a digital twin of the corresponding unmanned control target and dynamically update the digital twin.

[0010] The simulation module is used to simulate and analyze the unmanned control target, obtain monitoring and optimization data, and optimize the application control mode of the unmanned control target according to the monitoring data.

[0011] Simulate and analyze the monitoring optimization data through the digital twin model to determine whether there is a simulation control mode with a control effect better than the application control mode, obtain the corresponding application simulation result, and perform corresponding optimization processing according to the application simulation result;

[0012] Obtain the unmanned control strategy of the control module, mark the unmanned control strategy as a basic control strategy, simulate according to the basic control strategy and the monitoring optimization data through the digital twin model to obtain a basic simulation process; perform variable simulation analysis according to the basic simulation process to obtain a variable simulation result, the variable simulation result including variable simulation qualification, variable simulation disqualification, and corresponding optimization material data, and perform corresponding optimization processing according to the variable simulation result.

[0013] Further, the corresponding optimization processing according to the application simulation result includes:

[0014] When the application simulation result is application simulation qualification, no corresponding processing is performed;

[0015] When the application simulation result is application simulation disqualification, identify the corresponding simulation control mode, integrate the simulation control mode and the corresponding optimization monitoring data into optimization material data, and optimize and adjust the corresponding basic control strategy according to the optimization material data.

[0016] Further, the variable simulation analysis according to the basic simulation process includes:

[0017] Establish a variable generation model, analyze the basic simulation process through the variable generation model, and obtain a plurality of simulation backgrounds;

[0018] Simulate according to the simulation background through the digital twin to obtain a simulation background in which the control effect of the basic control strategy is not optimal, and mark the corresponding simulation background as an optimization background;

[0019] When there is no optimization background, the variable simulation result is variable simulation qualification;

[0020] When there is an optimization background, the variable simulation result is variable simulation disqualification, obtain the simulation simulation data corresponding to the optimization background, and generate optimization material data according to the optimization background and the simulation simulation material.

[0021] Further, the variable generation model is established, including:

[0022] The platform party establishes a variable library, and the variable library is used to store various background condition variables under the coal mine background;

[0023] The variable generation model is established according to the variable library, and the expression of the variable generation model is:

[0024] ;

[0025] In the formula: (q, b i ) is input data, q represents a basic simulation process, b i represents corresponding background condition variables in a variable library, i=1, 2, …, n, n is the number of background condition variables in the variable library; b i →q represents that the corresponding background condition variables can have in the basic simulation process; the output data is a variable analysis value BS(q, b i ), and the variable analysis value is 1 or 0;

[0026] When the variable analysis value is 1, the corresponding background condition variable is output;

[0027] When the variable analysis value is 0, no corresponding processing is performed.

[0028] Further, the basic simulation process is analyzed by the variable generation model, including:

[0029] The input data composed of the basic simulation process and the corresponding background condition variables in the variable library are input into the variable generation model for analysis to obtain the variable analysis value of each background condition variable;

[0030] The background condition variables with the variable analysis value of 1 are used to adjust the background of the basic simulation process to obtain the corresponding simulation background.

[0031] The device end includes a monitoring module and a control module;

[0032] The monitoring module is used for real-time monitoring of the unmanned control target to obtain corresponding comprehensive monitoring data, and the comprehensive monitoring data is divided into monitoring optimization data and monitoring control data; the monitoring optimization data is sent to the platform end, and the monitoring control data is sent to the control module.

[0033] Further, the comprehensive monitoring data is divided into monitoring optimization data and monitoring control data, including:

[0034] Each monitoring item is identified in real time to obtain monitoring item information, and application analysis marking is performed according to the monitoring item information; the corresponding application tags are marked for the corresponding monitoring items, and the application tags include optimization tags and control tags;

[0035] The comprehensive monitoring data is divided into monitoring optimization data and monitoring control data in real time according to the application tags corresponding to each monitoring item.

[0036] Further, the application analysis marking is performed according to the monitoring item information, including:

[0037] The optimization demand range and the control demand range corresponding to the optimization analysis and the control analysis are obtained in real time;

[0038] An application analysis model is established, and an expression of the application analysis model is:

[0039] ;

[0040] In the formula, (s, U y , U k ) is input data, s represents corresponding monitoring item information, U y and U k respectively represent an optimization demand range and a control demand range; s belongs to U y , which indicates that the monitoring item information belongs to the optimization demand range, and s belongs to U k , which indicates that the monitoring item information belongs to the control demand range; output data is an application analysis value YU(s), and the application analysis value is 1 or 0.

[0041] The application analysis model is used to analyze each monitoring item information, and an application analysis value corresponding to each monitoring item is obtained.

[0042] The application analysis value is used to determine an application label of the monitoring item.

[0043] The control module is used to analyze monitoring control data according to a basic control strategy, obtain an application control mode of the corresponding unmanned control target, and control the unmanned control target according to the application control mode.

[0044] A coal mine unmanned transportation intelligent control method, the method comprising:

[0045] A digital twin of the corresponding unmanned control target is established, and the digital twin is dynamically updated;

[0046] The unmanned control target is monitored in real time, and corresponding comprehensive monitoring data is obtained, the comprehensive monitoring data is divided into monitoring optimization data and monitoring control data;

[0047] The basic control strategy is adjusted in real time according to the monitoring optimization data;

[0048] The monitoring control data is analyzed according to the basic control strategy, an application control mode of the corresponding unmanned control target is obtained, and the unmanned control target is controlled according to the application control mode.

[0049] Compared with the prior art, the application has the following beneficial effects:

[0050] This invention provides an intelligent control method and system for unmanned coal mine transportation, effectively solving the problems of traditional coal mine transportation modes, such as high reliance on manual labor, limited efficiency, numerous safety hazards, high energy consumption, and slow response. It also overcomes the shortcomings of existing intelligent coal transport systems in adapting to dynamic environments. By deeply integrating automated control, intelligent monitoring and early warning, and remote centralized management technologies, the system achieves precise perception and intelligent decision-making throughout the entire coal transport process. It can dynamically adjust control strategies based on actual operating conditions, significantly improving transportation efficiency and safety. This invention not only promotes a comprehensive leap from mechanization to intelligence in coal mine transportation but also significantly reduces energy consumption and operating costs, providing a more efficient, reliable, and intelligent transportation solution for coal mine production. Attached Figure Description

[0051] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0052] Figure 1 This is a block diagram illustrating the principle of the present invention. Detailed Implementation

[0053] The technical solution of the present invention will be clearly and completely described below with reference to the embodiments. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the scope of protection of the present invention.

[0054] like Figure 1 As shown, an intelligent control system for unmanned transportation in coal mines includes a platform and an equipment.

[0055] The platform can also be established using cloud technology or other technologies; the platform and the device are generally connected via a communication link.

[0056] The platform includes a digital twin module and a simulation module;

[0057] The digital twin module is used to create a digital twin of the corresponding unmanned target and to dynamically update the digital twin.

[0058] Digital twins can be used to simulate unmanned targets.

[0059] In one embodiment, the digital twin is established based on existing digital twin technology and updated according to monitoring and optimization data transmitted from the device, that is, by using data related to the digital twin model update in the monitoring and optimization data for updating and adjusting.

[0060] The simulation module is used to simulate and analyze unmanned controlled targets, obtain monitoring and optimization data, optimize and identify the control methods for unmanned controlled targets based on the monitoring data, and mark them as the applied control methods, that is, the control methods adopted under the corresponding conditions, such as the control methods adopted under the conditions according to the control strategy. The control method adopts the actual control method of the delayed acquisition control module, or it can be determined based on the control strategy through digital twin models, etc.

[0061] By using a digital twin model to simulate and analyze monitoring and optimization data, it is determined whether there is a simulation control method that has a better control effect than the applied control method, and the corresponding application simulation results are obtained. Based on the application simulation results, corresponding optimization processing is carried out.

[0062] The unmanned control strategy corresponding to the control module is obtained and marked as the basic control strategy. A digital twin model is used to simulate the basic control strategy and monitoring optimization data to obtain the basic simulation process. This basic simulation process should be identical to the actual monitoring analysis and control process (and the applied control method should also be the same), or within the allowable error range. The basic simulation process includes determining the applied control method based on the monitoring optimization data according to the unmanned control strategy, and then implementing control according to that method. Variable simulation analysis is performed based on the basic simulation process to obtain the corresponding variable simulation results. These results include whether the variable simulation is successful, unsuccessful, and the corresponding optimization data. Appropriate optimization processing is then performed based on the variable simulation results.

[0063] In one embodiment, determining whether there is a simulation control method with better control effect than the applied control method involves performing simulation analysis according to the existing background using existing simulation technology to determine whether there is a corresponding simulation control method. For example, various control methods available in the current background can be obtained, simulations can be performed, and the effects can be compared based on the simulation results.

[0064] In one embodiment, optimization processing is performed based on the application simulation results, including:

[0065] If the application simulation result is satisfactory, no further action is taken.

[0066] When the application simulation result is unqualified, the corresponding simulation control mode is identified, and the simulation control mode and the corresponding optimized monitoring data are integrated into optimized material data. Based on the optimized material data, the corresponding unmanned control strategy (basic control strategy) is optimized and adjusted, or it can be stored for unified processing according to user needs later.

[0067] In one embodiment, the optimization process based on the variable simulation results is basically the same as the optimization process based on the application simulation results. For example, when the variable simulation results are unqualified, the optimization material data is identified. The corresponding unmanned control strategy (basic control strategy) is optimized and adjusted based on the optimization material data, or it can be stored and processed uniformly according to user needs later.

[0068] In one embodiment, variable simulation analysis based on a fundamental simulation process includes:

[0069] Establish a variable generation model, analyze the basic simulation process through the variable generation model, and obtain several simulation backgrounds;

[0070] By using a digital twin to simulate a background, we can obtain a simulation background where the control effect of the basic control strategy is not optimal, and mark the corresponding simulation background as the optimal background; that is, we can simulate various control methods that can achieve the control objective under a simulation background.

[0071] When there is no optimization background, the variable simulation result is considered satisfactory.

[0072] When there is an optimization background, the variable simulation result is that the variable simulation is unqualified. The simulation data corresponding to the optimization background is obtained. Based on the simulation data, the optimization material data such as the control method with better control effect than the basic control strategy can be identified. Therefore, optimization material data can be generated based on the optimization background and simulation tools.

[0073] In one embodiment, the variable generation simulation is established based on existing machine learning, deep learning, and other technologies. Various background condition variables are identified according to the basic simulation process, and different simulation backgrounds are formed based on the background condition variables. The corresponding training set is labeled manually for training.

[0074] In one embodiment, establishing a variable generation model includes:

[0075] The platform provider establishes a variable library to store various background condition variables in the context of a coal mine. Background condition variables refer to variables that are applicable to the control of unmanned targets, such as abnormal personnel approach, water inrush, and abnormal parts.

[0076] A variable generation model is established based on the variable library. The expression for the variable generation model is:

[0077] ;

[0078] In the formula: (q, b) i ) represents the input data, q represents the basic simulation process, and b i This represents the corresponding background condition variable in the variable library, i = 1, 2, ..., n, where n is the number of background condition variables in the variable library; b i →q indicates that the background condition variable can exist during the basic simulation process, and can also be considered as potentially occurring; b i The failure to meet the analysis requirements of the basic control strategy means that the basic control strategy cannot adjust its control when the background condition variable is present. In other words, the basic control strategy has not considered the impact of the background condition variable on control, or it cannot influence the analysis of the basic control strategy. Training is performed using historical data to label the corresponding training set; the output data is the variable analysis value BS(q, b). i The variable analysis value is 1 or 0;

[0079] When the variable analysis value is 1, the corresponding background condition variable is output;

[0080] When the variable analysis value is 0, no corresponding processing is performed.

[0081] In one embodiment, the analysis of the basic simulation process using a variable generation model includes:

[0082] The input data, consisting of the basic simulation process and the corresponding background condition variables in the variable library, is input into the variable generation model for analysis to obtain the variable analysis values ​​of each background condition variable.

[0083] The background of the basic simulation process is adjusted based on the background condition variable with a value of 1, and the corresponding simulation background is obtained. That is, the background corresponding to the basic simulation process is adjusted based on a single or combined background condition variable to form various different backgrounds, which are marked as simulation backgrounds.

[0084] The device includes a monitoring module and a control module;

[0085] The monitoring module is used to monitor unmanned targets in real time, obtain corresponding comprehensive monitoring data, and divide the comprehensive monitoring data into monitoring optimization data and monitoring control data; the monitoring optimization data is sent to the platform, and the monitoring control data is sent to the control module.

[0086] In one embodiment, the comprehensive monitoring data is divided into monitoring optimization data and monitoring control data. This division can be done in the existing manner, such as pre-setting the data to correspond to the division of comprehensive monitoring data into monitoring optimization data and monitoring control data, and then proceeding with the division accordingly.

[0087] In one embodiment, the comprehensive monitoring data is divided into monitoring optimization data and monitoring control data, including:

[0088] The system identifies each monitoring item in real time, determines its information based on the set sensors and monitoring data types, including the item's name, number, system or project, monitoring object information, parameter units, and monitoring method. It then performs application analysis and labeling based on the monitoring item information, assigning corresponding application tags to each item. These application tags include optimization tags and control tags; a single monitoring item can correspond to one or two application tags, meaning it can simultaneously have both optimization and control tags.

[0089] Based on the application tags corresponding to each monitoring item, the comprehensive monitoring data is divided into monitoring optimization data and monitoring control data in real time.

[0090] In one embodiment, application analysis tagging based on monitoring item information includes:

[0091] Real-time acquisition of the optimization and control requirement ranges corresponding to optimization and control analyses, i.e., the data ranges required to achieve the corresponding analyses;

[0092] Establish an application analysis model, the expression of which is:

[0093] ;

[0094] In the formula: (s, U) y U k ) represents the input data, s represents the corresponding monitoring item information, and U y and U k Let s ∈ U represent the scope of optimized demand and the scope of controlled demand, respectively. y This indicates that the monitored item information falls within the scope of optimization requirements, s∈U k This indicates that the monitoring item information falls within the scope of control requirements, and training is performed using the corresponding historical data labeled training set; the output data is the application analysis value YU(s), which is 1 or 0; that is, first evaluate whether the application analysis value is 1 and / or 2, and if neither is true, output 0, which does not mean that no further analysis is performed after determining the application value to be 1.

[0095] By applying the analysis model to analyze the information of each monitoring item, the corresponding application analysis value of each monitoring item is obtained;

[0096] The application tags corresponding to the monitoring items are determined based on the application analysis values.

[0097] The control module is used to analyze the monitoring and control data according to the basic control strategy, obtain the application control mode of the corresponding unmanned control target, and control the unmanned control target according to the application control mode.

[0098] That is, by using basic control strategies to analyze monitoring and control data, the application control methods for the corresponding time period can be obtained.

[0099] A method for intelligent control of unmanned transportation in coal mines, the method comprising:

[0100] Establish digital twins of the corresponding unmanned targets and dynamically update the digital twins;

[0101] Real-time monitoring of unmanned targets is conducted to obtain corresponding comprehensive monitoring data, which is then divided into monitoring optimization data and monitoring control data.

[0102] The basic control strategy is optimized and adjusted in real time based on monitoring and optimization data.

[0103] Based on the basic control strategy, the monitoring and control data are analyzed to obtain the corresponding application control method for the unmanned control target, and the unmanned control target is controlled according to the application control method.

[0104] The above formulas are all numerical calculations after removing dimensions. The formulas are obtained by software simulation based on a large amount of data and are closest to the real situation. The preset parameters and preset thresholds in the formulas are set by those skilled in the art according to the actual situation or obtained by simulation based on a large amount of data.

[0105] The above embodiments are only used to illustrate the technical methods of the present invention and are not intended to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical methods of the present invention without departing from the spirit and scope of the technical methods of the present invention.

Claims

1. An intelligent control system for unmanned transportation in coal mines, characterized in that, Including both platform and device ends; The platform includes a digital twin module and an analog module; the device includes a monitoring module and a control module. The digital twin module is used to create a digital twin of the corresponding unmanned target and to dynamically update the digital twin. The simulation module is used to simulate and analyze unmanned controlled targets, obtain monitoring and optimization data, and optimize and identify the application control methods for unmanned controlled targets based on the monitoring data. By using digital twin models to simulate and analyze monitoring and optimization data, it is determined whether there is a simulation control method with better control effect than the applied control method, and the corresponding application simulation results are obtained. Based on the application simulation results, corresponding optimization processing is carried out. The unmanned control strategy of the control module is obtained, and the unmanned control strategy is marked as the basic control strategy. The basic simulation process is obtained by simulating the basic control strategy and monitoring optimization data through a digital twin model. Based on the basic simulation process, variable simulation analysis is performed to obtain variable simulation results. The variable simulation results include whether the variable simulation is qualified, whether the variable simulation is unqualified, and the corresponding optimized material data. Based on the variable simulation results, corresponding optimization processing is carried out. The monitoring module is used to monitor unmanned controlled targets in real time, obtain corresponding comprehensive monitoring data, and divide the comprehensive monitoring data into monitoring optimization data and monitoring control data; the monitoring optimization data is sent to the platform, and the monitoring control data is sent to the control module. The control module is used to analyze the monitoring and control data according to the basic control strategy, obtain the application control mode of the corresponding unmanned control target, and control the unmanned control target according to the application control mode.

2. The intelligent control system for unmanned transportation in coal mines according to claim 1, characterized in that, Based on the application simulation results, corresponding optimization processes are performed, including: If the application simulation result is satisfactory, no further action is taken. When the application simulation result is unqualified, the corresponding simulation control mode is identified, and the simulation control mode and the corresponding optimized monitoring data are integrated into optimized material data; the corresponding basic control strategy is optimized and adjusted based on the optimized material data.

3. The intelligent control system for unmanned transportation in coal mines according to claim 1, characterized in that, Based on the basic simulation process, variable simulation analysis is performed, including: Establish a variable generation model, analyze the basic simulation process through the variable generation model, and obtain several simulation backgrounds; By using a digital twin to simulate the background, we can obtain a simulation background where the control effect of the basic control strategy is not optimal, and mark the corresponding simulation background as the optimal background. When there is no optimization background, the variable simulation result is considered satisfactory. When there is an optimized background, the variable simulation result is unqualified. The simulation data corresponding to the optimized background is obtained, and optimized material data is generated based on the optimized background and simulation model.

4. The intelligent control system for unmanned transportation in coal mines according to claim 3, characterized in that, Establish a variable generation model, including: The platform provider establishes a variable library, which is used to store various background condition variables in the context of coal mines. A variable generation model is established based on the variable library. The expression for the variable generation model is: ； In the formula: (q, b) i ) represents the input data, q represents the basic simulation process, and b i This represents the corresponding background condition variable in the variable library, i = 1, 2, ..., n, where n is the number of background condition variables in the variable library; b i →q represents the background condition variables that can be present in the basic simulation process; the output data is the variable analysis value BS(q, b). i The variable analysis value is 1 or 0; When the variable analysis value is 1, the corresponding background condition variable is output; When the variable analysis value is 0, no corresponding processing is performed.

5. The intelligent control system for unmanned transportation in coal mines according to claim 4, characterized in that, The basic simulation process is analyzed using a variable generation model, including: The input data, consisting of the basic simulation process and the corresponding background condition variables in the variable library, is input into the variable generation model for analysis to obtain the variable analysis values ​​of each background condition variable. The background of the basic simulation process is adjusted based on the background condition variable with a value of 1 in the variable analysis to obtain the corresponding simulation background.

6. The intelligent control system for unmanned transportation in coal mines according to claim 1, characterized in that, The comprehensive monitoring data is divided into monitoring optimization data and monitoring control data, including: Real-time identification of each monitoring item, obtaining information on each monitoring item, performing application analysis and labeling based on the monitoring item information, and labeling the corresponding monitoring item with corresponding application tags, including optimization tags and control tags; Based on the application tags corresponding to each monitoring item, the comprehensive monitoring data is divided into monitoring optimization data and monitoring control data in real time.

7. The intelligent control system for unmanned transportation in coal mines according to claim 6, characterized in that, Application analysis and labeling are performed based on monitoring item information, including: Real-time acquisition of the optimization and control requirement ranges corresponding to the optimization and control analyses, respectively; Establish an application analysis model, the expression of which is: ； In the formula: (s, U) y U k ) represents the input data, s represents the corresponding monitoring item information, and U y and U k These represent the scope of optimized demand and the scope of controlled demand, respectively; s∈U y This indicates that the monitored item information falls within the scope of optimization requirements, s∈U k This indicates that the monitored item information falls within the scope of control requirements; the output data is the application analysis value YU(s), which is 1 or 0. By applying the analysis model to analyze the information of each monitoring item, the corresponding application analysis value of each monitoring item is obtained; The application label of the monitoring item is determined based on the application analysis value.

8. A method for intelligent control of unmanned transportation in coal mines, characterized in that, The method, applied to an intelligent control system for unmanned coal mine transportation as described in any one of claims 1 to 7, comprises: Establish digital twins of the corresponding unmanned targets and dynamically update the digital twins; Real-time monitoring of unmanned targets is conducted to obtain corresponding comprehensive monitoring data, which is then divided into monitoring optimization data and monitoring control data. The basic control strategy is adjusted and optimized in real time based on monitoring and optimization data. Based on the basic control strategy, the monitoring and control data are analyzed to obtain the corresponding application control method for the unmanned control target, and the unmanned control target is controlled according to the application control method.

Images