High-pressure jet intelligent mining adaptive monitoring control system

Abstract

The application discloses a high-pressure jet flow intelligent mining adaptive monitoring and control system, comprising a jet flow rock breaking dynamic monitoring module, a rock mass analysis and data processing module, a neural network deep learning module and a mining machine controller; the jet flow rock breaking dynamic monitoring module is used for obtaining jet flow parameters and calculating jet flow axial thrust, obtaining a three-dimensional appearance of a mining surface and obtaining cutting and crack morphology; wherein the three-dimensional appearance of the mining surface at least comprises cutting depth information; the rock mass analysis and data processing module is used for obtaining three-dimensional coordinates of the mining machine in a working environment, calculating rock mass confining pressure and obtaining rock mass characteristics; the neural network deep learning module establishes an intelligent model of jet flow cutting process parameters and mining process parameters; and the mining machine controller is used for generating a mining machine control instruction. The application can realize safe and efficient control of high-pressure jet flow mining equipment to adaptively cut a mine / rock mass.

Description

Technical Field

[0001] The present invention relates to underground operations, and in particular to a high-pressure jet intelligent mining adaptive monitoring and control system. Background Art

[0002] my country's underground engineering technologies for tunnels, urban underground spaces, and energy storage underground chambers are developing rapidly, with both project scale and excavation depth increasing rapidly. Similar to deep solid resource mining, these projects face challenges such as severe over-excavation and under-excavation, extensive surrounding rock damage, and frequent rockbursts. Traditional rock construction methods (drilling and blasting, cantilever mining, and TBM) suffer from severe tool wear, high vibration during drilling and blasting, and severe surrounding rock damage, particularly impacting urban structures and residents. These issues also include low mining efficiency, high construction costs, and significant risks. Consequently, the use of high-pressure jetting technology has gradually become a mainstream development trend in the mining technology field. However, current high-pressure jetting mining equipment has a low level of intelligence, cannot adaptively adjust equipment parameters based on different rock mass data, and cannot timely assess the mining working environment and safety risks. Summary of the Invention

[0003] In view of this, the purpose of the present invention is to provide a high-pressure jet intelligent mining adaptive monitoring and control system, which can achieve safe and efficient control of high-pressure jet mining equipment to perform adaptive cutting of ore / rock.

[0004] The invention provides a high-pressure jet intelligent mining adaptive monitoring and control system, which includes a jet rock breaking dynamic monitoring module, a rock mass analysis and data processing module, a neural network deep learning module, and a mining machine controller;

[0005] The jet rock breaking dynamic monitoring module is used to: obtain jet parameters and calculate the jet axial reverse thrust, obtain the three-dimensional topography of the mining face, and obtain the cutting and crack morphology; wherein the three-dimensional topography of the mining face includes at least cutting depth information;

[0006] The rock mass analysis and data processing module is used to obtain the three-dimensional coordinates of the mining machine in the working environment, calculate the rock mass confining pressure and obtain the rock mass characteristics;

[0007] The neural network deep learning module is used to:

[0008] Collect and store historical and real-time data on jet parameters, jet axial reverse thrust, three-dimensional topography of the mining face, and cutting and crack morphology, and establish a dynamic evaluation model for jet cutting status and effects;

[0009] Collect and store historical and real-time monitoring data on the three-dimensional coordinates of the mining machine in its working environment, rock mass confining pressure, and rock mass characteristics, and establish a dynamic evaluation model for safety risks and rock mass data;

[0010] Based on the jet flow parameters, cutting depth information, and historical data and real-time monitoring data of rock mass characteristics, a cutting effect evaluation model under different lithology is established.

[0011] Based on the jet flow cutting state and effect dynamic evaluation model, the safety risk and rock mass data dynamic evaluation model, and the cutting effect evaluation model, a jet flow cutting process parameter database is established, and a jet flow cutting process parameter and mining process parameter intelligent model is established, with broken particle size, cutting depth, and surrounding rock deformation as the objective function.

[0012] The mining machine controller is configured to determine the optimal position and posture of the mining machine and the jet flow cutting mechanism, the optimal jet flow parameters, and generate a mining machine control instruction based on the real-time monitoring data of the jet flow rock breaking dynamic monitoring module and the rock mass analysis and data processing module, and the jet flow cutting process parameter and mining process parameter intelligent model.

[0013] Further, the jet flow rock breaking dynamic monitoring module includes a jet flow axial thrust monitoring component, a mining face laser ranging monitoring component, and a acoustic emission rock breaking dynamic monitoring component.

[0014] The jet flow axial thrust monitoring component is configured to obtain jet flow parameters and calculate jet flow axial thrust; the mining face laser ranging monitoring component is configured to obtain three-dimensional topography of the mining face; and the acoustic emission rock breaking dynamic monitoring component is configured to obtain cutting and crack morphology.

[0015] Further, the jet flow parameters include jet flow mass, jet flow velocity, jet flow momentum, jet flow area, incoming flow mass, incoming flow velocity, incoming flow momentum, jet flow and impact object angle, jet flow density, and jet flow unit flow.

[0016] The jet flow axial thrust monitoring component calculates the jet flow axial thrust F2 in the following manner:

[0017] When the jet flow does not impact a target object, the impact thrust F0 is F0 = m0V0 - mV + (P0 - P)A0.

[0018] When the jet flow impacts a target object, the impact thrust F1 is F1 = pQV0sinθ.

[0019] When θ = 90°, F1 = pQV0.

[0020] When θ = 180°, F1 = 0.

[0021] Therefore, the jet flow axial thrust F2 is F2 = F0 + F1.

[0022] Among them: m0 represents the jet mass, V0 represents the jet velocity, P0 represents the jet momentum, A0 represents the jet area, m represents the incoming flow mass, V represents the incoming flow velocity, P represents the incoming flow momentum, θ represents the angle formed by the jet and the impacting object, ρ represents the jet density, and Q represents the unit flow rate of the jet.

[0023] Furthermore, the mining face laser ranging monitoring component includes a three-dimensional scanning device and a laser ranging device. The three-dimensional scanning device is used to scan the three-dimensional morphology of the face, and the laser ranging device is used to detect the surface morphology of the mining working face, the distance between the jet nozzle and the target body, the cutting depth information and the cutting seam width information, so as to obtain the three-dimensional morphology of the mining face.

[0024] Furthermore, the acoustic emission rock fracture dynamic monitoring component determines the cutting depth information of the rock by monitoring the change of the acoustic signal, and reflects the whole process of rock jet cutting cracks in real time, so as to obtain the cutting and crack morphology.

[0025] Furthermore, the rock mass analysis and data processing module includes a rock mass mining face three-dimensional positioning component, a tunnel face equivalent confining pressure inversion component, and a rock mass property identification component;

[0026] The mining face three-dimensional positioning component is used to obtain the three-dimensional coordinates of the mining machine in the working environment; the tunnel face equivalent confining pressure inversion component is used to calculate the rock mass confining pressure; and the rock mass property identification component is used to obtain rock mass properties.

[0027] Furthermore, the process of calculating the rock mass confining pressure by the tunnel face equivalent confining pressure inversion component includes:

[0028] A mathematical model of rock mass confining pressure, cutting depth and jet parameters is established through a neural network deep learning module. The jet axial reverse thrust obtained by the jet axial reverse thrust monitoring component, the cutting depth information obtained by the mining face laser ranging monitoring component, and the stress changes obtained through microseismic signal processing are combined with the jet parameters to inversely learn and correct the rock mass confining pressure on the face. Based on the inversely calculated rock mass confining pressure on the face, the crack initiation stress and damage stress are qualitatively evaluated. A map of the relationship between punching depth and confining pressure is established based on indoor simulation experiments and field tests, and an equivalent stress diagram of the face is generated.

[0029] Furthermore, the mathematical model of rock mass confining pressure, cutting depth and jet parameters is established through the neural network deep learning module. The jet axial reverse thrust obtained by the jet axial reverse thrust monitoring component, the cutting depth information obtained by the mining face laser ranging monitoring component and the stress change obtained by the microseismic signal processing results are combined with the jet parameters to inversely learn and correct the rock mass confining pressure of the tunnel face. The inverse learning and correction are performed through the following mathematical model:

[0030]

[0031] wherein: H is the cutting depth with confining pressure, H0 is the cutting depth without confining pressure, k tc is the elastic coefficient of rock mass after confining pressure, k t is the elastic coefficient of rock mass without confining pressure, F max is the maximum force of rock mass contact area, F max is equal to the axial thrust of jet F2, r is the abrasive particle size, and σ is the confining pressure.

[0032] Further, the mining machine control instruction comprises a mining machine body movement instruction, a nozzle track movement instruction, a jet parameter correction instruction, and a safety risk early warning instruction.

[0033] Further, the real-time monitoring data based on the jet rock breaking dynamic monitoring module and the rock mass analysis and data processing module and the jet cutting process parameter and mining process parameter intelligent model generate a mining machine control instruction, comprising:

[0034] Based on the three-dimensional coordinates of the mining machine in the working environment fed back by the rock mass analysis and data processing module, and based on the three-dimensional topography of the mining face fed back by the rock breaking dynamic monitoring module, the optimal position and attitude of the mining machine are determined in combination with the jet cutting process parameter and mining process parameter intelligent model to generate the mining machine body movement instruction, so that the mining machine adjusts the position and direction in real time;

[0035] Based on the jet parameters, the axial thrust of the jet, the three-dimensional topography of the mining face, and the cutting and crack morphology fed back by the rock breaking dynamic monitoring module, the optimal position and attitude of the jet cutting mechanism are determined in combination with the jet cutting process parameter and mining process parameter intelligent model to generate the nozzle track movement instruction, so that the jet cutting mechanism adjusts the movement direction and speed in real time;

[0036] Based on the jet parameters, the axial thrust of the jet, the three-dimensional topography of the mining face, and the cutting and crack morphology fed back by the rock breaking dynamic monitoring module, and based on the confining pressure of the rock mass and the characteristics of the rock mass fed back by the rock mass analysis and data processing module, the optimal jet parameters of the jet cutting mechanism are determined in combination with the jet cutting process parameter and mining process parameter intelligent model to generate the jet parameter correction instruction, so that the jet cutting mechanism adjusts the jet parameters in real time;

[0037] Based on the three-dimensional topography of the mining face and the cutting and crack morphology fed back by the rock breaking dynamic monitoring module, and based on the confining pressure of the rock mass and the characteristics of the rock mass fed back by the rock mass analysis and data processing module, the risk coefficients of surrounding rock deformation, rock burst, and water inrush and mud burst are evaluated in real time in combination with the jet cutting process parameter and mining process parameter intelligent model to generate the safety risk early warning instruction, and a signal is sent when the risk value is exceeded, so that the mining machine stops working.

[0038] The beneficial effects of the present application are:

[0039] (1) The jet cutting of the present application uses water as a medium to effectively suppress dust, improve the construction environment, and protect the ecological environment. The jet nozzle is small in size and can realize intelligent control of hard rock cutting. The excavation section is smooth, precise and controllable. The dynamic evaluation model of the jet cutting state and effect, the dynamic evaluation model of safety risk and rock mass data, and the cutting effect evaluation model under different lithology are introduced, which can dynamically evaluate the jet cutting effect, correct the position and direction of the mining machine, correct the nozzle moving speed and moving direction, dynamically evaluate the real-time evaluation of the mining working environment, issue construction progress instructions and risk situation response measures, so as to realize safe and efficient control of the self-adaptive cutting of the high-pressure jet mining equipment on the ore / rock mass.

[0040] (2) The present application introduces artificial intelligence and deep learning to construct an intelligent model of jet cutting process parameters and mining process parameters, accurately controls the spatial attitude of the high-pressure abrasive jet mechanical arm, realizes precise target cutting of the water jet, optimizes the efficiency of hydraulic breaking of hard rock and the cutting path, and realizes self-adaptive precise control of key parameters of the jet.

[0041] (3) The present application can realize large block cutting and controllable spalling of hard rock mass, has high hard rock breaking efficiency, and can realize intelligent perception and active control of surrounding rock deformation based on the characteristics of jet slotting pressure relief and energy release. The impact load and vibration generated during excavation and mining are small, which can effectively reduce the damage of surrounding rock and solve the problems of efficient, intelligent and green mining of complex geological conditions, hard surrounding rock and different cross-sections of tunnels and underground engineering.

[0042] (4) The high-pressure jet rock breaking and cutting of the present application is a non-contact rock breaking method without tool wear. The system adopts a jet axial thrust monitoring component, a mining face laser ranging monitoring component, a rock breaking dynamic monitoring component, a rock mass mining face three-dimensional positioning component, an equivalent confining pressure inversion component of the working face, and a rock mass characteristic identification component, so that the prediction of rock mass stress is faster, the mining efficiency of the working face is higher, and the working face is less affected by the complex environment of fog, coal dust and dirt during rock breaking. BRIEF DESCRIPTION OF DRAWINGS

[0043] In order to make the purpose, technical scheme and beneficial effects of the present application clearer, the present application provides the following drawings for explanation:

[0044] Figure 1 The present application is a principle function module combination technical roadmap;

[0045] Figure 2 The present application is a schematic diagram of the impact force of the jet on the solid plane;

[0046] Figure 3 Schematic diagram for calculating the jet axial reverse thrust;

[0047] Figure 4 Schematic diagram of the impact of the jet on the rock mass and the rock breaking depth. DETAILED DESCRIPTION

[0048] The technical solution of the present invention is described in detail below with reference to the accompanying drawings and embodiments.

[0049] like Figure 1 As shown, a high-pressure jet intelligent mining adaptive monitoring and control system in this embodiment includes a jet rock breaking dynamic monitoring module, a rock analysis and data processing module, a neural network deep learning module and a mining machine controller;

[0050] The jet rock breaking dynamic monitoring module is used to: obtain jet parameters and calculate the jet axial reverse thrust, obtain the three-dimensional topography of the mining face, and obtain the cutting and crack morphology; wherein the three-dimensional topography of the mining face includes at least cutting depth information;

[0051] The rock mass analysis and data processing module is used to obtain the three-dimensional coordinates of the mining machine in the working environment, calculate the rock mass confining pressure and obtain the rock mass characteristics;

[0052] The neural network deep learning module is used to:

[0053] Collect and store historical and real-time data on jet parameters, jet axial reverse thrust, three-dimensional topography of the mining face, and cutting and crack morphology, and establish a dynamic evaluation model for jet cutting status and effects;

[0054] Collect and store historical and real-time monitoring data on the three-dimensional coordinates of the mining machine in its working environment, rock mass confining pressure, and rock mass characteristics, and establish a dynamic evaluation model for safety risks and rock mass data;

[0055] Based on the jet parameters, cutting depth information, and historical and real-time monitoring data of rock mass characteristics, a cutting effect evaluation model for different lithologies is established;

[0056] Based on the dynamic evaluation model of jet cutting status and effect, the dynamic evaluation model of safety risk and rock mass data, and the cutting effect evaluation model, with the crushing fragmentation, cutting depth, and surrounding rock deformation as the objective function, a jet cutting process parameter database is established, and an intelligent model of jet cutting process parameters and mining process parameters is established;

[0057] The mining machine controller is used to: determine the optimal position and posture of the mining machine and the jet cutting mechanism, the optimal jet parameters based on the real-time monitoring data of the jet rock breaking dynamic monitoring module and the rock analysis and data processing module, combined with the jet cutting process parameters and the mining process parameter intelligent model, and generate mining machine control instructions.

[0058] Jet cutting uses water as a medium, effectively suppressing dust, improving the construction environment, and contributing to ecological and environmental protection. The jet nozzle is small in size and can achieve intelligent control of hard rock cutting, resulting in smooth, precisely controlled excavation sections. The introduction of dynamic evaluation models for jet cutting status and effects, dynamic evaluation models for safety risks and rock mass data, and cutting effect evaluation models for different lithologies can dynamically evaluate the jet cutting effect, correct the position and direction of the mining machine, and correct the nozzle movement speed and direction. Dynamic evaluation and real-time assessment of the mining working environment are carried out, and construction progress instructions and risk response measures are issued, thereby achieving safe and efficient control of high-pressure jet mining equipment for adaptive cutting of ore / rock. Furthermore, by introducing artificial intelligence and deep learning to construct intelligent models of jet cutting process parameters and mining process parameters, the spatial posture of the high-pressure abrasive jet robot arm is precisely controlled, achieving precise targeted cutting of the water jet, optimizing the efficiency of hydraulic crushing of hard rock and the cutting path, and achieving adaptive and precise control of key jet parameters.

[0059] High-pressure jet cutting enables large-scale cutting and controlled spalling of hard rock, achieving high hard rock crushing efficiency. Based on the pressure-releasing and energy-releasing properties of the jet cutting seam, it also enables intelligent sensing and active control of surrounding rock deformation. The impact loads and vibration generated during excavation are minimal, effectively reducing surrounding rock damage. This technology addresses the challenges of efficient, intelligent, and green mining in complex geological conditions, hard surrounding rock, and tunnels and underground projects with varying cross-sections. High-pressure jet rock cutting is non-contact and eliminates tool wear. The system utilizes a jet axial thrust monitoring component, a mining face laser ranging monitoring component, an acoustic emission rock fracture dynamic monitoring component, a rock face 3D positioning component, a face equivalent confining pressure inversion component, and a rock property identification component. These components enable faster prediction of rock stress, higher mining efficiency at the working face, and reduced exposure to complex environmental influences such as fog, coal dust, and dirt during the rock breaking process.

[0060] In this embodiment, the jet rock breaking dynamic monitoring module includes a jet axial reverse thrust monitoring component, a mining face laser ranging monitoring component, and an acoustic emission rock fracture dynamic monitoring component;

[0061] The jet axial reverse thrust monitoring component is used to obtain jet parameters and calculate the jet axial reverse thrust; the mining face laser ranging monitoring component is used to obtain the three-dimensional morphology of the mining face; and the acoustic emission rock fracture dynamic monitoring component is used to obtain cutting and crack morphology.

[0062] In this embodiment, the jet parameters include: jet mass, jet velocity, jet momentum, jet area, incoming flow mass, incoming flow velocity, incoming flow momentum, the angle formed by the jet and the impacting object, jet density, and jet unit flow rate;

[0063] When there is no impact on the object and during the high-pressure jet cutting and breaking process, there will be an axial reaction force due to the impact of the high-pressure jet, which acts on the high-pressure jet equipment. The jet axial reverse thrust monitoring component can monitor this reaction force, such as Figure 2 As shown, the jet axial reverse thrust F2 is calculated by the jet axial reverse thrust monitoring component as follows:

[0064] Momentum equation in the X direction: -F1=ρQ1V1 cos90°+ρQ2V2cos90°-ρQV0 sinθ=-ρQV0 sinθ;

[0065] Momentum equation in the Y direction: ρQ1V1-ρQ2V2-ρQV0cosθ=0;

[0066] From the Bernoulli and fluid continuity equations we get:

[0067] V0=V1+V2,

[0068] Q=Q1+Q2,

[0069]

[0070] like Figure 3 As shown, when the jet has no target, the impact thrust F0: = F0 = m0V0-mV+(P0-P)A0;

[0071] When the jet hits the target, the impact thrust F1: F1 = ρQV0sinθ;

[0072] When θ=90°: F1=ρQV0;

[0073] When θ = 180°: F1 = 0;

[0074] Then the jet axial reverse thrust F2 is: F2 = F0 + F1;

[0075] Among them: m0 represents the jet mass, V0 represents the jet velocity, P0 represents the jet momentum, A0 represents the jet area, m represents the incoming flow mass, V represents the incoming flow velocity, P represents the incoming flow momentum, θ represents the angle formed by the jet and the impacting object, ρ represents the jet density, and Q represents the unit flow rate of the jet.

[0076] In this embodiment, the mining face laser ranging monitoring assembly includes a 3D scanning device and a laser ranging device. The 3D scanning device scans the 3D topography of the mining face, while the laser ranging device detects the surface morphology of the mining working face, the distance between the jet nozzle and the target, the cutting depth, and the cutting slit width, thereby acquiring the 3D topography of the mining face. The 3D scanning device and the laser ranging device work together, minimizing the impact of complex environments such as fog, dust, and dirt.

[0077] In this embodiment, the acoustic emission rock fracture dynamic monitoring component determines rock cutting depth information by monitoring changes in acoustic signals, and reflects the entire process of rock jet cutting cracks in real time, thereby obtaining cutting and crack morphology. Cutting and crack morphology can be used to qualitatively assess rock damage stress.

[0078] In this embodiment, the rock mass analysis and data processing module includes a rock mass mining face three-dimensional positioning component, a tunnel face equivalent confining pressure inversion component, and a rock mass property identification component;

[0079] The mining face three-dimensional positioning component is used to obtain the three-dimensional coordinates of the mining machine in the working environment; the tunnel face equivalent confining pressure inversion component is used to calculate the rock mass confining pressure; and the rock mass property identification component is used to obtain rock mass properties.

[0080] The 3D positioning component for the mining face accurately locates the cutting area, defines the direction of the cutting face, and ensures forward movement during the mining process, unaffected by obstacles such as dust and fog. The rock mass property recognition component identifies rock mass properties and stores them in the neural network deep learning module.

[0081] In this embodiment, the process of calculating the rock mass confining pressure by the tunnel face equivalent confining pressure inversion component includes:

[0082] A mathematical model of rock mass confining pressure, cutting depth and jet parameters is established through a neural network deep learning module. The jet axial reverse thrust obtained by the jet axial reverse thrust monitoring component, the cutting depth information obtained by the mining face laser ranging monitoring component, and the stress changes obtained through microseismic signal processing are combined with the jet parameters to inversely learn and correct the rock mass confining pressure on the face. Based on the inversely calculated rock mass confining pressure on the face, the crack initiation stress and damage stress are qualitatively evaluated. A map of the relationship between punching depth and confining pressure is established based on indoor simulation experiments and field tests, and an equivalent stress diagram of the face is generated.

[0083] In this embodiment, Figure 4 As shown, the angle of the fluid on the jet center axis when impacting the rock mass is always perpendicular to the tangent of the bottom surface of the impact crater. The dotted line in the figure is the jet center axis. Therefore, the rock breaking depth is determined by the abrasive and fluid on the center axis. After the abrasive on the jet center axis impacts the rock mass, it causes certain damage to the rock. The accumulation of this damage forms an impact crater of a certain depth. The mathematical model of rock mass confining pressure, cutting depth and jet parameters is established through the neural network deep learning module. According to the jet axial reverse thrust obtained by the jet axial reverse thrust monitoring component, the cutting depth information obtained by the mining face laser ranging monitoring component and the stress change obtained by the microseismic signal processing results, and then combined with the jet parameters, the face rock mass confining pressure is inversely learned and corrected. The following mathematical model is used for inversion learning and correction:

[0084]

[0085] wherein: H is the cutting depth with confining pressure, H0 is the cutting depth without confining pressure, k tc is the elastic coefficient of rock mass after confining pressure, k t is the elastic coefficient of rock mass without confining pressure, F max is the maximum force of rock mass contact area, F max is equal to the axial thrust of the jet F2, r is the abrasive particle size, and sigma is the confining pressure.

[0086] In this embodiment, the neural network deep learning module can face the construction of the neural network for jet cutting, the collection of jet cutting effect and cutting parameters, the learning and training of the constructed neural network. The dynamic response feedback signal of jet impact on rock can be collected, and the mapping relationship between the jet reflection wave frequency spectrum analysis data and the cutting characteristics of the impacted rock mass is established according to the frequency spectrum analysis theory, the characteristic accurate perception mechanism of super-high pressure abrasive jet cutting of hard rock mass under the stress field condition of rock mass is constructed, and based on the jet cutting and surrounding rock deformation adaptive program, the optimal jet parameters of multi-target regional collaborative cutting and surrounding rock deformation are analyzed to adapt to the needs of roadway mining multi-task adaptive collaborative operation. The neural network deep learning module can continuously collect construction parameter data and construction surface image data, which are collected in the deep learning database. Through repeated iteration learning-training-validation, the intelligent decision-making and information feedback accuracy are continuously improved to ensure the cutting speed and mining efficiency.

[0087] In this embodiment, the mining machine control instruction includes mining machine body movement instruction, nozzle trajectory movement instruction, jet parameter correction instruction, and safety risk early warning instruction.

[0088] In this embodiment, the real-time monitoring data based on the jet rock breaking dynamic monitoring module and the rock mass analysis and data processing module and the jet cutting process parameter and mining process parameter intelligent model generate the mining machine control instruction, which includes:

[0089] Based on the three-dimensional coordinates of the mining machine in the working environment fed back by the rock mass analysis and data processing module, and based on the three-dimensional topography of the mining surface fed back by the rock breaking dynamic monitoring module, the three-dimensional topography, coordinates and surface morphology of the mining space are obtained, and the optimal position and attitude of the mining machine are determined in combination with the jet cutting process parameter and mining process parameter intelligent model to generate the mining machine body movement instruction (i.e. correction instruction such as judgment of mining machine forward movement, forward movement amount and direction), so that the mining machine adjusts the position and direction in real time;

[0090] Based on the jet parameters, jet axial thrust, three-dimensional topography of the mining face, and cut and crack morphology fed back by the rock-breaking dynamic monitoring module, the optimal position and posture of the jet cutting mechanism are determined in combination with the jet cutting process parameters and the mining process parameter intelligent model. The nozzle trajectory movement instructions are generated, allowing the jet cutting mechanism to adjust its movement direction and speed in real time. The jet parameters, jet axial thrust, three-dimensional topography of the mining face, and cut and crack morphology can be used to determine whether the jet's cutting depth has reached the desired target, whether the cutting depth is still increasing, and whether the cutting has penetrated the rock. The cutting effect can be determined using a dynamic evaluation model for the jet cutting state and effect, allowing the jet cutting mechanism's movement direction and speed to be adjusted in real time to achieve the optimal cutting effect.

[0091] Based on the jet parameters, jet axial reverse thrust, three-dimensional topography of the mining face, and cutting and crack morphology fed back by the rock breaking dynamic monitoring module, as well as the rock mass confining pressure and rock mass characteristics fed back by the rock mass analysis and data processing module, the optimal jet parameters of the jet cutting mechanism are determined by combining the jet cutting process parameters with the mining process parameter intelligent model. Jet parameter correction instructions are generated, allowing the jet cutting mechanism to adjust the jet parameters in real time. An equivalent confining pressure distribution cloud map is generated by inverting the changes in the cutting depth of the mining face. The mining working environment is assessed in real time based on the safety risk and rock mass data dynamic evaluation model, so that the jet parameters of the jet cutting mechanism are adjusted to the optimal jet parameters in real time.

[0092] Based on the three-dimensional morphology of the mining face and the cutting and crack morphology fed back by the rock breaking dynamic monitoring module, and the rock confining pressure and rock characteristics fed back by the rock analysis and data processing module, the jet cutting process parameters and the mining process parameter intelligent model are combined to evaluate the risk factors of surrounding rock deformation, rock burst and water and mud gushing in real time, generate the safety risk warning instruction, and send a signal when the risk value is exceeded to stop the mining machine.

[0093] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not limiting. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the purpose and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. A high-pressure jet intelligent mining adaptive monitoring and control system, characterized by: It includes a jet rock breaking dynamic monitoring module, a rock analysis and data processing module, a neural network deep learning module, and a mining machine controller; The jet rock breaking dynamic monitoring module is used to: obtain jet parameters and calculate the jet axial reverse thrust, obtain the three-dimensional topography of the mining face, and obtain the cutting and crack morphology; wherein the three-dimensional topography of the mining face includes at least cutting depth information; The rock mass analysis and data processing module is used to obtain the three-dimensional coordinates of the mining machine in the working environment, calculate the rock mass confining pressure and obtain the rock mass characteristics; The neural network deep learning module is used to: Collect and store historical and real-time data on jet parameters, jet axial reverse thrust, three-dimensional topography of the mining face, and cutting and crack morphology, and establish a dynamic evaluation model for jet cutting status and effects; Collect and store historical and real-time monitoring data on the three-dimensional coordinates of the mining machine in its working environment, rock mass confining pressure, and rock mass characteristics, and establish a dynamic evaluation model for safety risks and rock mass data; Based on the jet parameters, cutting depth information, and historical and real-time monitoring data of rock mass characteristics, a cutting effect evaluation model for different lithologies is established; Based on the dynamic evaluation model of jet cutting status and effect, the dynamic evaluation model of safety risk and rock mass data, and the cutting effect evaluation model, with the crushing fragmentation, cutting depth, and surrounding rock deformation as the objective function, a jet cutting process parameter database is established, and an intelligent model of jet cutting process parameters and mining process parameters is established; The mining machine controller is used to: determine the optimal position and posture of the mining machine and the jet cutting mechanism, the optimal jet parameters based on the real-time monitoring data of the jet rock breaking dynamic monitoring module and the rock analysis and data processing module, combined with the jet cutting process parameters and the mining process parameter intelligent model, and generate mining machine control instructions.

2. The high-pressure jet intelligent mining adaptive monitoring and control system according to claim 1 is characterized by: The jet rock breaking dynamic monitoring module includes a jet axial reverse thrust monitoring component, a mining face laser ranging monitoring component and an acoustic emission rock fracture dynamic monitoring component; The jet axial reverse thrust monitoring component is used to obtain jet parameters and calculate the jet axial reverse thrust; the mining face laser ranging monitoring component is used to obtain the three-dimensional morphology of the mining face; and the acoustic emission rock fracture dynamic monitoring component is used to obtain cutting and crack morphology.

3. The high-pressure jet intelligent mining adaptive monitoring and control system according to claim 2 is characterized by: The jet parameters include: jet mass, jet velocity, jet momentum, jet area, incoming flow mass, incoming flow velocity, incoming flow momentum, the angle formed by the jet and the impacting object, jet density and jet unit flow rate; The jet axial reverse thrust monitoring component calculates the jet axial reverse thrust F2 in the following manner: When there is no target body in the jet, the impact thrust F0 is: F0 = m0V0-mV+(P0-P)A0; When the jet hits the target, the impact thrust F1: F1 = ρQV0sinθ; When θ=90°: F1=ρQV0; When θ = 180°: F1 = 0; Then the jet axial reverse thrust F2 is: F2 = F0 + F1; Among them: m0 represents the jet mass, V0 represents the jet velocity, P0 represents the jet momentum, A0 represents the jet area, m represents the incoming flow mass, V represents the incoming flow velocity, P represents the incoming flow momentum, θ represents the angle formed by the jet and the impacting object, ρ represents the jet density, and Q represents the unit flow rate of the jet.

4. The high-pressure jet intelligent mining adaptive monitoring and control system according to claim 2 is characterized by: The mining face laser ranging monitoring component includes a three-dimensional scanning device and a laser ranging device. The three-dimensional scanning device is used to scan the three-dimensional morphology of the face, and the laser ranging device is used to detect the surface morphology of the mining working face, the distance between the jet nozzle and the target body, the cutting depth information and the cutting seam width information, so as to obtain the three-dimensional morphology of the mining face.

5. The high-pressure jet intelligent mining adaptive monitoring and control system according to claim 2 is characterized by: The acoustic emission rock fracture dynamic monitoring component determines the cutting depth information of the rock by monitoring the change of the acoustic signal, and reflects the whole process of the rock jet cutting crack in real time, so as to obtain the cutting and crack morphology.

6. The high-pressure jet intelligent mining adaptive monitoring and control system according to claim 2 is characterized by: The rock mass analysis and data processing module includes a rock face three-dimensional positioning component, a tunnel face equivalent confining pressure inversion component, and a rock mass property identification component; The mining face three-dimensional positioning component is used to obtain the three-dimensional coordinates of the mining machine in the working environment; the tunnel face equivalent confining pressure inversion component is used to calculate the rock mass confining pressure; and the rock mass property identification component is used to obtain rock mass properties.

7. The high-pressure jet intelligent mining adaptive monitoring and control system according to claim 6 is characterized by: The process of calculating rock mass confining pressure by the equivalent confining pressure inversion component of the tunnel face includes: A mathematical model of rock mass confining pressure, cutting depth and jet parameters is established through a neural network deep learning module. The jet axial reverse thrust obtained by the jet axial reverse thrust monitoring component, the cutting depth information obtained by the mining face laser ranging monitoring component, and the stress changes obtained through microseismic signal processing are combined with the jet parameters to inversely learn and correct the rock mass confining pressure on the face. Based on the inversely calculated rock mass confining pressure on the face, the crack initiation stress and damage stress are qualitatively evaluated. A map of the relationship between punching depth and confining pressure is established based on indoor simulation experiments and field tests, and an equivalent stress diagram of the face is generated.

8. The high-pressure jet intelligent mining adaptive monitoring and control system according to claim 7 is characterized by: The mathematical model of rock mass confining pressure, cutting depth and jet parameters is established through the neural network deep learning module. The jet axial reverse thrust obtained by the jet axial reverse thrust monitoring component, the cutting depth information obtained by the mining face laser ranging monitoring component and the stress change obtained by the microseismic signal processing results are combined with the jet parameters to inversely learn and correct the rock mass confining pressure of the tunnel face. The inverse learning and correction are performed through the following mathematical model: Where: H is the cutting depth under pressure, H0 is the cutting depth without confining pressure, k tc is the elastic coefficient of the rock mass after confining pressure, k t is the elastic coefficient of the rock mass when no confining pressure is applied, F max is the maximum force in the rock contact zone, F max It is equal to the jet axial reverse thrust F2, r is the abrasive particle size, and σ is the confining pressure.

9. The high-pressure jet intelligent mining adaptive monitoring and control system according to claim 6 is characterized by: The mining machine control instructions include mining machine body movement instructions, nozzle trajectory movement instructions, jet parameter correction instructions and safety risk warning instructions.

10. The high-pressure jet intelligent mining adaptive monitoring and control system according to claim 9 is characterized in that: The generating of mining machine control instructions based on the real-time monitoring data of the jet rock breaking dynamic monitoring module and the rock analysis and data processing module and the intelligent model of the jet cutting process parameters and the mining process parameters includes: Based on the three-dimensional coordinates of the mining machine in the working environment fed back by the rock mass analysis and data processing module, and the three-dimensional morphology of the mining face fed back by the rock breaking dynamic monitoring module, the optimal position and posture of the mining machine are determined by combining the jet cutting process parameters and the mining process parameter intelligent model, and the mining machine body movement instructions are generated, so that the mining machine can adjust its position and direction in real time; Based on the jet parameters, jet axial reverse thrust, three-dimensional morphology of the mining face, and cutting and crack morphology fed back by the rock breaking dynamic monitoring module, the optimal position and posture of the jet cutting mechanism are determined in combination with the jet cutting process parameters and the mining process parameter intelligent model, and the nozzle trajectory movement instruction is generated, so that the jet cutting mechanism can adjust the movement direction and movement speed in real time; Based on the jet parameters, jet axial reverse thrust, three-dimensional morphology of the mining face and cutting and crack morphology fed back by the rock breaking dynamic monitoring module, and the rock mass confining pressure and rock mass characteristics fed back by the rock mass analysis and data processing module, the optimal jet parameters of the jet cutting mechanism are determined in combination with the jet cutting process parameters and the mining process parameter intelligent model, and the jet parameter correction instructions are generated to enable the jet cutting mechanism to adjust the jet parameters in real time; Based on the three-dimensional morphology of the mining face and the cutting and crack morphology fed back by the rock breaking dynamic monitoring module, and the rock confining pressure and rock characteristics fed back by the rock analysis and data processing module, the jet cutting process parameters and the mining process parameter intelligent model are combined to evaluate the risk factors of surrounding rock deformation, rock burst and water and mud gushing in real time, generate the safety risk warning instruction, and send a signal when the risk value is exceeded to stop the mining machine.

Images