Intelligent adaptive monitoring and control system for high-pressure jet excavation

Abstract

The present invention discloses a high-pressure jet intelligent mining and excavation adaptive monitoring and control system, including a jet rock-breaking dynamic monitoring module, a rock mass analysis and data processing module, a neural network deep learning module, and a mining and excavation machine controller. The jet rock-breaking dynamic monitoring module can obtain jet parameters, calculate the jet axial reaction force, acquire the three-dimensional morphology of the mining and excavation surface and cutting and fracture morphology, wherein the three-dimensional morphology includes cutting depth information. The rock mass analysis and data processing module can obtain three-dimensional coordinates of the mining and excavation machine, calculate rock mass confining pressure, and obtain rock mass characteristics. The neural network deep learning module establishes an intelligent model of jet cutting process parameters and mining and excavation process parameters, and the mining and excavation machine controller generates control instructions to achieve adaptive cutting of ore / rock masses.

Description

CROSS-REFERENCE TO RELATED APPLICATIONS

[0001] The application claims priority to Chinese patent application No. 2025100798039, filed on Jan. 18, 2025, the entire contents of which are incorporated herein by reference.TECHNICAL FIELD

[0002] The present invention relates to underground operations, specifically to an intelligent adaptive monitoring and control system for high-pressure jet excavation.BACKGROUND

[0003] The technology for tunnels, urban underground spaces, energy storage caverns, and other underground engineering in China is developing rapidly, with rapid growth in both project scale and excavation depth. Similar to deep solid resource mining, it faces challenges such as severe overbreak / underbreak, significant surrounding rock damage, and frequent disasters like rockburst. Traditional rock mass construction methods (drilling and blasting, boom-type excavation, TBM method) suffer from severe tool wear, significant vibration and surrounding rock damage from drilling and blasting (especially impacting urban structures and residents), low excavation efficiency, high construction costs, and high risks. Therefore, high-pressure jet technology has gradually become a mainstream development trend in the excavation technology field. However, current high-pressure jet excavation equipment has a low level of intelligence, cannot adaptively adjust equipment parameters based on different rock mass data, and cannot promptly assess the working environment conditions and safety risk status during excavation.SUMMARY

[0004] In view of the above, the objective of the present invention is to provide an intelligent adaptive monitoring and control system for high-pressure jet excavation, capable of safely and efficiently controlling high-pressure jet excavation equipment for adaptive cutting of ore / rock mass.

[0005] An intelligent adaptive monitoring and control system for high-pressure jet excavation according to the present invention comprises a jet rock-breaking dynamic monitoring module, a rock mass analysis and data processing module, a neural network deep learning module, and an mining and excavation machine controller;

[0006] The jet rock-breaking dynamic monitoring module is configured to: acquire jet parameters and calculate jet axial reaction force; acquire the three-dimensional topography of the excavation face; and acquire cutting and fracture morphology; wherein the three-dimensional topography of the excavation face at least includes cutting depth information;

[0007] The rock mass analysis and data processing module is configured to: acquire the three-dimensional coordinates of the excavation machine in the working environment; calculate rock mass confining pressure; and acquire rock mass characteristics;

[0008] The neural network deep learning module is configured to:

[0009] Collect and store historical and real-time data of jet parameters, jet axial reaction force, three-dimensional topography of the excavation face, and cutting and fracture morphology, to establish a dynamic evaluation model for jet cutting status and effectiveness;

[0010] Collect and store historical and real-time monitoring data of the three-dimensional coordinates of the excavation machine in the working environment, rock mass confining pressure, and rock mass characteristics, to establish a dynamic evaluation model for safety risks and rock mass data;

[0011] Based on historical and real-time monitoring data of jet parameters, cutting depth information, and rock mass characteristics, establish a cutting effectiveness evaluation model for different lithologies;

[0012] Based on the dynamic evaluation model for jet cutting status and effectiveness, the dynamic evaluation model for safety risks and rock mass data, and the cutting effectiveness evaluation model for different lithologies, using fragmentation size, cutting depth, and surrounding rock deformation as objective functions, establish a database of jet cutting process parameters and establish an intelligent model correlating jet cutting process parameters with excavation process parameters;

[0013] The mining and excavation machine controller is configured to: based on real-time monitoring data from the jet rock-breaking dynamic monitoring module and the rock mass analysis and data processing module, combined with the intelligent model correlating jet cutting process parameters with excavation process parameters, determine the optimal position and posture of the excavation machine and jet cutting mechanism, and optimal jet parameters, and generate excavation machine control instructions.

[0014] Further, the jet rock-breaking dynamic monitoring module comprises a jet axial reaction force monitoring component, an excavation face laser ranging monitoring component, and an acoustic emission rock fracture dynamic monitoring component.

[0015] The jet axial reaction force monitoring component is configured to acquire jet parameters and calculate the jet axial reaction force; the excavation face laser ranging monitoring component is configured to acquire the three-dimensional topography of the excavation face; the acoustic emission rock fracture dynamic monitoring component is configured to acquire cutting and fracture morphology.

[0016] Further, the jet parameters include: jet mass, jet velocity, jet momentum, jet cross-sectional area, inlet flow mass, incoming flow velocity, inlet flow momentum, angle formed between the jet and the impacted object, jet density, and unit flow rate of the jet.

[0017] The jet axial reaction force monitoring component calculates the jet axial reaction force F2 as follows:

[0018] Jet impact reaction force without target F0:F0=m0⁢V0-m⁢V+(P0-P)⁢A0(I)

[0019] Jet impact reaction force with target F1:F1=p⁢Q⁢V0⁢sin⁢θ(II)

[0020] When θ=90°:F1=ρ⁢Q⁢V0(III)

[0021] When θ=180°:F1=0(IV)

[0022] Then the jet axial reaction force F2 is:F2=F0+F1(V)

[0023] Wherein: m0 refers jet mass, V0 refers jet velocity, P0 refers jet momentum, A0 refers jet cross-sectional area, m refers inlet flow mass, V refers incoming flow velocity, P refers inlet flow momentum, θ refers the angle formed between the jet and the impacted object, prefers jet density, and Q refers unit flow rate of the jet.

[0024] Further, the excavation face laser ranging monitoring component comprises a three-dimensional scanning device and a laser ranging device; the three-dimensional scanning device performs scanning of the three-dimensional topography of the face, and the laser ranging device detects the surface morphology of the excavation working face, the distance between the jet nozzle and the target, cutting depth information, and cutting kerf width information, thereby acquiring the three-dimensional topography of the excavation face.

[0025] Further, the acoustic emission rock fracture dynamic monitoring component determines the cutting depth information of the rock by monitoring changes in acoustic signals and reflects the entire process of rock mass fracture induced by jet cutting in real-time, thereby acquiring cutting and fracture morphology.

[0026] Further, the rock mass analysis and data processing module comprises a rock mass excavation face three-dimensional positioning component, a face equivalent confining pressure inversion component, and a rock mass characteristic identification component;

[0027] The excavation face three-dimensional positioning component is configured to acquire the three-dimensional coordinates of the excavation machine in the working environment; the face equivalent confining pressure inversion component is configured to calculate rock mass confining pressure; the rock mass characteristic identification component is configured to acquire rock mass characteristics.

[0028] Further, the process of the face equivalent confining pressure inversion component calculating rock mass confining pressure comprises:

[0029] Establishing a mathematical model correlating rock mass confining pressure, cutting depth, and jet parameters via the neural network deep learning module; based on the jet axial reaction force obtained from the jet axial reaction force monitoring component, the cutting depth information obtained via the excavation face laser ranging monitoring component, and the stress changes obtained from microseismic signal processing results, combined with jet parameters, inversely learning and correcting the rock mass confining pressure at the face; based on the inversely calculated rock mass confining pressure at the face, qualitatively evaluating crack initiation stress and damage stress; establishing a relationship diagram between penetration depth and confining pressure based on laboratory simulation experiments and field tests, and generating an equivalent stress diagram for the face.

[0030] Further, when establishing the mathematical model correlating rock mass confining pressure, cutting depth, and jet parameters via the neural network deep learning module, and inversely learning and correcting the rock mass confining pressure at the face based on the jet axial reaction force obtained from the jet axial reaction force monitoring component, the cutting depth information obtained via the excavation face laser ranging monitoring component, the stress changes obtained from microseismic signal processing results, and combined with jet parameters, the following formula is used for inverse learning and correction:H=H0⁢ktFmax[1+2⁢σ2r2⁢kt⁢c2+2⁢σr2⁢kt⁢c⁢(r-Fmaxkt⁢c)-σr2⁢kt⁢c⁢(r-Fmaxkt⁢c)-1σ2r4⁢kt⁢c2)12(VI)

[0031] Wherein: H refers the cutting depth under confining pressure, H0 refers the cutting depth without confining pressure applied, kt refers the elastic coefficient of the rock mass under confining pressure, kt refers the elastic coefficient of the rock mass without confining pressure, Fmax refers the maximum force in the rock contact zone, Fmax is equal to the jet axial reaction force F2, r refers the abrasive particle size, and σ refers the confining pressure.

[0032] Further, characterized in that: the excavation machine control instructions include excavation machine body movement instructions, nozzle trajectory movement instructions, jet parameter correction instructions, and safety risk warning instructions.

[0033] Further, the generation of excavation machine control instructions based on real-time monitoring data from the jet rock-breaking dynamic monitoring module and the rock mass analysis and data processing module, and the intelligent model correlating jet cutting process parameters with excavation process parameters, comprises:

[0034] Based on the three-dimensional coordinates of the excavation machine in the working environment fed back by the rock mass analysis and data processing module, and the three-dimensional topography of the excavation face fed back by the rock-breaking dynamic monitoring module, combined with the intelligent model correlating jet cutting process parameters with excavation process parameters, determining the optimal position and posture of the excavation machine, generating the excavation machine body movement instructions, enabling the excavation machine to adjust its position and orientation in real-time;

[0035] Based on the jet parameters, jet axial reaction force, three-dimensional topography of the excavation face, and cutting and fracture morphology fed back by the rock-breaking dynamic monitoring module, combined with the intelligent model correlating jet cutting process parameters with excavation process parameters, determining the optimal position and posture of the jet cutting mechanism, generating the nozzle trajectory movement instructions, enabling the jet cutting mechanism to adjust its moving direction and speed in real-time;

[0036] Based on the jet parameters, jet axial reaction force, three-dimensional topography of the excavation face, and cutting and fracture 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, combined with the intelligent model correlating jet cutting process parameters with excavation process parameters, determining the optimal jet parameters for the jet cutting mechanism, generating the jet parameter correction instructions, enabling the jet cutting mechanism to adjust jet parameters in real-time;

[0037] Based on the three-dimensional topography of the excavation face and cutting and fracture 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, combined with the intelligent model correlating jet cutting process parameters with excavation process parameters, real-time evaluating risk coefficients for surrounding rock deformation, rockburst, and water / mud inrush, generating the safety risk warning instructions, issuing a signal when risk thresholds are exceeded, causing the excavation machine to stop working.

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

[0039] 1) The jet cutting of the present invention uses water as the medium, effectively suppressing dust, improving the construction environment, and benefiting ecological environmental protection. The jet nozzle is small in size, enabling intelligent control for hard rock cutting, with smooth and precisely controllable excavated profiles. By introducing the dynamic evaluation model for jet cutting status and effectiveness, the dynamic evaluation model for safety risks and rock mass data, and the cutting effectiveness evaluation model for different lithologies, it can dynamically evaluate jet cutting effectiveness, correct the position and orientation of the excavation machine, correct nozzle moving speed and direction, dynamically evaluate and assess the working environment conditions in real-time, issue construction progress instructions and risk response measures, thereby achieving safe and efficient control of high-pressure jet excavation equipment for adaptive cutting of ore / rock mass.

[0040] 2) The present invention introduces artificial intelligence and deep learning to construct an intelligent model correlating jet cutting process parameters with excavation process parameters, enabling precise control of the spatial posture of the high-pressure abrasive jet manipulator, achieving precise targeted cutting of the waterjet, optimizing hydraulic hard rock fragmentation efficiency and cutting paths, and realizing adaptive precise control of key jet parameters.

[0041] 3) The present invention can achieve large-block cutting and controllable spalling of hard rock masses, with high hard rock fragmentation efficiency. Based on the pressure relief and energy release characteristics of jet cutting slots, it can also achieve intelligent perception and active control of surrounding rock deformation. The impact loads and vibrations generated during the excavation process are relatively small, effectively reducing surrounding rock damage. It can solve the challenges of efficient, intelligent, and green excavation for tunnels and underground engineering under complex geological conditions, with hard surrounding rock and different cross-sections.

[0042] 4) The high-pressure jet rock-breaking and cutting of the present invention is a non-contact rock-breaking method, with no tool wear. The system employs the jet axial reaction force monitoring component, excavation face laser ranging monitoring component, acoustic emission rock fracture dynamic monitoring component, rock mass excavation face three-dimensional positioning component, face equivalent confining pressure inversion component, and rock mass characteristic identification component, making the prediction of rock mass stress faster, the excavation efficiency of the working face higher, and the rock-breaking process less affected by complex environments such as mist, coal dust, and dirt.BRIEF DESCRIPTION OF THE DRAWINGS

[0043] To make the objectives, technical solutions, and beneficial effects of the present invention clearer, the following drawings are provided for description:

[0044] FIG. 1 is a schematic diagram showing the combination of functional modules and technical route of the present invention;

[0045] FIG. 2 is a schematic diagram showing the impact force of a jet on a solid plane;

[0046] FIG. 3 is schematic diagram for calculating the jet axial reaction force;

[0047] FIG. 4 is a schematic diagram showing jet impact on rock mass and rock-breaking depth.DESCRIPTION OF THE EMBODIMENTS

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

[0049] As shown in FIG. 1, an intelligent adaptive monitoring and control system for high-pressure jet excavation in this embodiment comprises a jet rock breaking dynamic monitoring module, a rock mass analysis and data processing module, a neural network deep learning module, and a mining and excavation machine controller.

[0050] The jet rock-breaking dynamic monitoring module is configured to: acquire jet parameters and calculate jet axial reaction force; acquire the three-dimensional topography of the excavation face; acquire cutting and fracture morphology; wherein the three-dimensional topography of the excavation face at least includes cutting depth information.

[0051] The rock mass analysis and data processing module is configured to: acquire the three-dimensional coordinates of the excavation machine in the working environment; calculate rock mass confining pressure; acquire rock mass characteristics.

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

[0053] Collect and store historical and real-time data of jet parameters, jet axial reaction force, three-dimensional topography of the excavation face, and cutting and fracture morphology, establish a dynamic evaluation model for jet cutting status and effectiveness.

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

[0055] Based on historical and real-time monitoring data of jet parameters, cutting depth information, and rock mass characteristics, establish a cutting effectiveness evaluation model for different lithologies.

[0056] Based on the dynamic evaluation model for jet cutting status and effectiveness, the dynamic evaluation model for safety risks and rock mass data, and the cutting effectiveness evaluation model for different lithologies, using fragmentation size, cutting depth, and surrounding rock deformation as objective functions, establish a database of jet cutting process parameters and an intelligent model correlating jet cutting process parameters with excavation process parameters.

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

[0058] Jet cutting uses water as the medium, effectively suppressing dust, improving the construction environment, and benefiting ecological environmental protection. The jet nozzle is small in size, enabling intelligent control for hard rock cutting, with smooth and precisely controllable excavated profiles. By introducing the dynamic evaluation model for jet cutting status and effectiveness, the dynamic evaluation model for safety risks and rock mass data, and the cutting effectiveness evaluation model for different lithologies, it can dynamically evaluate jet cutting effectiveness, correct the position and orientation of the excavation machine, correct nozzle moving speed and direction, dynamically evaluate and assess the working environment conditions in real-time, issue construction progress instructions and risk response measures, thereby achieving safe and efficient control of high-pressure jet excavation equipment for adaptive cutting of ore / rock mass. Furthermore, by introducing artificial intelligence and deep learning to construct an intelligent model correlating jet cutting process parameters with excavation process parameters, precise control of the spatial posture of the high-pressure abrasive jet manipulator is achieved, enabling precise targeted cutting of the waterjet, optimizing hydraulic hard rock fragmentation efficiency and cutting paths, and realizing adaptive precise control of key jet parameters.

[0059] High-pressure jet cutting can achieve large block cutting and controllable spalling of hard rock masses, with high hard rock fragmentation efficiency. Based on the pressure relief and energy release characteristics of jet cutting slots, it can also achieve intelligent perception and active control of surrounding rock deformation. The impact loads and vibrations generated during the excavation process are relatively small, effectively reducing surrounding rock damage. It can solve the challenges of efficient, intelligent, and green excavation for tunnels and underground engineering under complex geological conditions, with hard surrounding rock and different cross-sections. High-pressure jet rock-breaking and cutting is a non-contact rock-breaking method, with no tool wear. The system employs the jet axial reaction force monitoring component, excavation face laser ranging monitoring component, acoustic emission rock fracture dynamic monitoring component, rock mass excavation face three-dimensional positioning component, face equivalent confining pressure inversion component, and rock mass characteristic identification component, making the prediction of rock mass stress faster, the excavation efficiency of the working face higher, and the rock-breaking process less affected by complex environments such as mist, coal dust, and dirt.

[0060] In this implementation case, the jet rock-breaking dynamic monitoring module comprises a jet axial reaction force monitoring component, an excavation face laser ranging monitoring component, and an acoustic emission rock fracture dynamic monitoring component.

[0061] The jet axial reaction force monitoring component is configured to acquire jet parameters and calculate the jet axial reaction force; the excavation face laser ranging monitoring component is configured to acquire the three-dimensional topography of the excavation face; the acoustic emission rock fracture dynamic monitoring component is configured to acquire cutting and fracture morphology.

[0062] In this implementation case, the jet parameters include jet mass, jet velocity, jet momentum, jet cross-sectional area, inlet flow mass, incoming flow velocity, inlet flow momentum, angle formed between the jet and the impacted object, jet density, and unit flow rate of the jet.

[0063] When not impacting an object, during the high-pressure jet cutting and rock-breaking process, an axial reaction force exists due to the impact of the high-pressure jet. Acting on the high-pressure jet equipment, the jet axial reaction force monitoring component can monitor this reaction force. As shown in FIG. 2, the derivation for calculating the jet axial reaction force F2 by the jet axial reaction force monitoring component is as follows:

[0064] The momentum equation in the X direction: −F1=ρQ1V1 cos 90°+ρQ2V2 cos 90°−ρQsin θ=−ρQsin θ

[0065] The momentum equation in the Y direction: ρQ1V1−ρQ2V2−PρQV0 cos θ=0

[0066] From Bernoulli and the fluid continuity equation:V0=V1+V2,Q=Q1+Q2,Q1=12⁢Q⁡(1+cos⁢θ),Q2=12⁢Q⁡(1-cos⁢θ);

[0067] As shown in FIG. 3, the jet impact reaction force without target, F0: F0=m0V0−mV+(P0−P)A0;

[0068] When the jet impacts target, the impact reaction force, F1: F1=−ρQV0 sin θ;

[0069] When θ=90°: F1=ρQV0;

[0070] When θ=180°: F1=0;

[0071] Then the jet axial reaction force F2: F2=F1+F0;

[0072] Wherein: m0 represents jet mass, V0 represents jet velocity, P0 represents jet momentum, A0 represents jet cross-sectional area, m represents inlet flow mass, V represents incoming flow velocity, P represents inlet flow momentum, θ represents the angle formed between the jet and the impacted object, ρ represents jet density, Q represents unit flow rate of the jet.

[0073] In this implementation case, the excavation face laser ranging monitoring component comprises a three-dimensional scanning device and a laser ranging device. The three-dimensional scanning device performs scanning of the three-dimensional topography of the face, and the laser ranging device detects the surface morphology of the excavation working face, the distance between the jet nozzle and the target, cutting depth information, and cutting kerf width information, thereby acquiring the three-dimensional topography of the excavation face. The three-dimensional scanning device and the laser ranging device work together and are less affected by complex environments such as mist, dust, and dirt.

[0074] In this implementation case, the acoustic emission rock fracture dynamic monitoring component determines the cutting depth information of the rock by monitoring changes in acoustic signals and reflects the entire process of rock mass fracture induced by jet cutting in real-time, thereby acquiring cutting and fracture morphology. The cutting and fracture morphology can be used to qualitatively evaluate rock damage stress.

[0075] In this implementation case, the rock mass analysis and data processing module comprises a rock mass excavation face three-dimensional positioning component, a face equivalent confining pressure inversion component, and a rock mass characteristic identification component.

[0076] The three-dimensional excavation face positioning component is configured to acquire the three-dimensional coordinates of the excavation machine in the working environment; the face equivalent confining pressure inversion component is configured to calculate rock mass confining pressure, and the rock mass characteristic identification component is configured to acquire rock mass characteristics.

[0077] The excavation face three-dimensional positioning component can precisely locate the cutting and excavation area, define the direction of the cutting working face, and ensure the forward direction during the excavation process, unaffected by obstacles such as dust and mist. The rock mass characteristic identification component can identify rock mass characteristics and store them in the neural network deep learning module.

[0078] In this implementation case, the process of the face equivalent confining pressure inversion component calculating rock mass confining pressure comprises:

[0079] Establish a mathematical model correlating rock mass confining pressure, cutting depth, and jet parameters via the neural network deep learning module. Based on the jet axial reaction force obtained from the jet axial reaction force monitoring component, the cutting depth information obtained via the excavation face laser ranging monitoring component, and the stress changes obtained from microseismic signal processing results, combine with jet parameters, in order to inversely learn and correct the rock mass confining pressure at the face. Based on the inversely calculated rock mass confining pressure at the face, qualitatively evaluate crack initiation stress and damage stress, establish a relationship diagram between penetration depth and confining pressure based on laboratory simulation experiments and field tests, and generate an equivalent stress diagram for the face.

[0080] In this implementation case, as shown in FIG. 4, the angle at which the fluid on the jet axis impacts the rock mass is always perpendicular to the tangent of the impact crater bottom surface, where the dashed line represents the jet axis. Therefore, the rock-breaking depth is determined by the abrasive and fluid on the jet axis. After the abrasive on the jet axis impacts the rock mass, it causes certain damage to the rock, and the accumulation of this damage forms an impact crater of a certain depth. Establish a mathematical model correlating rock mass confining pressure, cutting depth, and jet parameters via the neural network deep learning module. Based on the jet axial reaction force obtained from the jet axial reaction force monitoring component, the cutting depth information obtained via the excavation face laser ranging monitoring component, and the stress changes obtained from microseismic signal processing results, combine with jet parameters, in order to inversely learn and correct the rock mass confining pressure at the face, the following formula is used for inverse learning and correction:H=H0⁢ktFmax[1+2⁢σ2r2⁢kt⁢c2+2⁢σr2⁢kt⁢c⁢(r-Fmaxkt⁢c)-σr2⁢kt⁢c⁢(r-Fmaxkt⁢c)-1σ2r4⁢kt⁢c2)12

[0081] Wherein: H is the cutting depth under confining pressure, H0 is the cutting depth without confining pressure, ktc is the elastic coefficient of the rock mass under confining pressure, kt is the elastic coefficient of the rock mass without confining pressure, Fmax is the maximum force in the rock contact zone, Fmax is equal to the jet axial reaction force, r is the abrasive particle size, σ is the confining pressure.

[0082] In this implementation case, the neural network deep learning module is capable of constructing neural networks oriented towards jet cutting, collecting jet cutting effectiveness and cutting parameters, and learning and training the constructed neural networks. It can collect dynamic response feedback signals from jet impact on rock, and based on spectrum analysis theory, establish a mapping relationship between the spectral analysis data of jet reflected waves and the cutting characteristics of impacted rock mass, constructing a precise perception mechanism for the characteristics of ultra-high pressure abrasive jet cutting of hard rock mass under rock mass stress field conditions. Based on the adaptive program for jet cutting fragmentation-surrounding rock deformation, it analyzes the optimal jet parameters for multi-target area coordinated cutting-surrounding rock deformation, to achieve the demands of adaptive coordinated multi-task operations for roadway excavation. The neural network deep learning module can continuously collect construction parameter data and working face image data, aggregate them into a deep learning database, and through repeated iterative learning—training—verification, continuously improve the accuracy of intelligent decision-making and information feedback, ensuring cutting speed and excavation efficiency.

[0083] In this implementation case, characterized in that: the excavation machine control instructions include excavation machine body movement instructions, nozzle trajectory movement instructions, jet parameter correction instructions, and safety risk warning instructions.

[0084] In this implementation case, based on real-time monitoring data from the jet rock-breaking dynamic monitoring module and the rock mass analysis and data processing module, and the intelligent model correlating jet cutting process parameters with excavation process parameters characterized in that, of excavation machine control instructions are generated, which comprises:

[0085] Based on the three-dimensional coordinates of the excavation machine in the working environment fed back by the rock mass analysis and data processing module, and the three-dimensional topography of the excavation face fed back by the rock-breaking dynamic monitoring module, obtain the three-dimensional topography and coordinates of the excavation space and detecting the surface morphology of the excavation working face, combine with the intelligent model correlating jet cutting process parameters with excavation process parameters, determine the optimal position and posture of the excavation machine, generate the excavation machine body movement instructions (instructions to determine whether the excavation machine should move forward, the amount of forward movement, and direction, etc.), enabling the excavation machine to adjust its position and orientation in real-time.

[0086] Based on the jet parameters, jet axial reaction force, three-dimensional topography of the excavation face, and cutting and fracture morphology fed back by the rock-breaking dynamic monitoring module, combine with the intelligent model correlating jet cutting process parameters with excavation process parameters, determine the optimal position and posture of the jet cutting mechanism, generate the nozzle trajectory movement instructions, enabling the jet cutting mechanism to adjust its moving direction and speed in real-time. From the jet parameters, jet axial reaction force, three-dimensional topography of the excavation face, and cutting and fracture morphology, information such as whether the jet cutting depth has reached the target, whether the cutting depth is still increasing, and whether the cutting has penetrated the rock block can be derived. Relying on the dynamic evaluation model for jet cutting status and effectiveness, the cutting effectiveness can be determined, and the moving direction and speed of the jet cutting mechanism can be adjusted in real-time to achieve optimal cutting effectiveness.

[0087] Based on the jet parameters, jet axial reaction force, three-dimensional topography of the excavation face, and cutting and fracture 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, combine with the intelligent model correlating jet cutting process parameters with excavation process parameters, determine the optimal jet parameters for the jet cutting mechanism, generate the jet parameter correction instructions, enabling the jet cutting mechanism to adjust jet parameters in real-time. By inversely deducing the equivalent confining pressure distribution nephogram from the changes in cutting depth of the excavation face, and real-time evaluating the working environment conditions according to the dynamic evaluation model for safety risks and rock mass data, the jet parameters of the jet cutting mechanism are adjusted in real-time to the optimal jet parameters.

[0088] Based on the three-dimensional topography of the excavation face and cutting and fracture 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, combine with the intelligent model correlating jet cutting process parameters with excavation process parameters, real-time evaluate risk coefficients for surrounding rock deformation, rock burst, and water / mud inrush, generate the safety risk warning instructions, issue signal when risk thresholds are exceeded, causing the excavation machine to stop working.

[0089] Finally, it is noted that the above embodiments are only intended to illustrate the technical solutions of the present invention and not to limit them. Although the present invention has been described in detail with reference to the preferred embodiments, those of ordinary skill in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention, which should all be covered within the scope of the claims of the present invention.

Examples

Embodiment Construction

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

[0049]As shown in FIG. 1, an intelligent adaptive monitoring and control system for high-pressure jet excavation in this embodiment comprises a jet rock breaking dynamic monitoring module, a rock mass analysis and data processing module, a neural network deep learning module, and a mining and excavation machine controller.

[0050]The jet rock-breaking dynamic monitoring module is configured to: acquire jet parameters and calculate jet axial reaction force; acquire the three-dimensional topography of the excavation face; acquire cutting and fracture morphology; wherein the three-dimensional topography of the excavation face at least includes cutting depth information.

[0051]The rock mass analysis and data processing module is configured to: acquire the three-dimensional coordinates of the excavation machine in the working environment; calcu...

CROSS-REFERENCE TO RELATED APPLICATIONS

[0001] The application claims priority to Chinese patent application No. 2025100798039, filed on Jan. 18, 2025, the entire contents of which are incorporated herein by reference.TECHNICAL FIELD

[0002] The present invention relates to underground operations, specifically to an intelligent adaptive monitoring and control system for high-pressure jet excavation.BACKGROUND

[0003] The technology for tunnels, urban underground spaces, energy storage caverns, and other underground engineering in China is developing rapidly, with rapid growth in both project scale and excavation depth. Similar to deep solid resource mining, it faces challenges such as severe overbreak / underbreak, significant surrounding rock damage, and frequent disasters like rockburst. Traditional rock mass construction methods (drilling and blasting, boom-type excavation, TBM method) suffer from severe tool wear, significant vibration and surrounding rock damage from drilling and blasting (especially impacting urban structures and residents), low excavation efficiency, high construction costs, and high risks. Therefore, high-pressure jet technology has gradually become a mainstream development trend in the excavation technology field. However, current high-pressure jet excavation equipment has a low level of intelligence, cannot adaptively adjust equipment parameters based on different rock mass data, and cannot promptly assess the working environment conditions and safety risk status during excavation.SUMMARY

[0004] In view of the above, the objective of the present invention is to provide an intelligent adaptive monitoring and control system for high-pressure jet excavation, capable of safely and efficiently controlling high-pressure jet excavation equipment for adaptive cutting of ore / rock mass.

[0005] An intelligent adaptive monitoring and control system for high-pressure jet excavation according to the present invention comprises a jet rock-breaking dynamic monitoring module, a rock mass analysis and data processing module, a neural network deep learning module, and an mining and excavation machine controller;

[0006] The jet rock-breaking dynamic monitoring module is configured to: acquire jet parameters and calculate jet axial reaction force; acquire the three-dimensional topography of the excavation face; and acquire cutting and fracture morphology; wherein the three-dimensional topography of the excavation face at least includes cutting depth information;

[0007] The rock mass analysis and data processing module is configured to: acquire the three-dimensional coordinates of the excavation machine in the working environment; calculate rock mass confining pressure; and acquire rock mass characteristics;

[0008] The neural network deep learning module is configured to:

[0009] Collect and store historical and real-time data of jet parameters, jet axial reaction force, three-dimensional topography of the excavation face, and cutting and fracture morphology, to establish a dynamic evaluation model for jet cutting status and effectiveness;

[0010] Collect and store historical and real-time monitoring data of the three-dimensional coordinates of the excavation machine in the working environment, rock mass confining pressure, and rock mass characteristics, to establish a dynamic evaluation model for safety risks and rock mass data;

[0011] Based on historical and real-time monitoring data of jet parameters, cutting depth information, and rock mass characteristics, establish a cutting effectiveness evaluation model for different lithologies;

[0012] Based on the dynamic evaluation model for jet cutting status and effectiveness, the dynamic evaluation model for safety risks and rock mass data, and the cutting effectiveness evaluation model for different lithologies, using fragmentation size, cutting depth, and surrounding rock deformation as objective functions, establish a database of jet cutting process parameters and establish an intelligent model correlating jet cutting process parameters with excavation process parameters;

[0013] The mining and excavation machine controller is configured to: based on real-time monitoring data from the jet rock-breaking dynamic monitoring module and the rock mass analysis and data processing module, combined with the intelligent model correlating jet cutting process parameters with excavation process parameters, determine the optimal position and posture of the excavation machine and jet cutting mechanism, and optimal jet parameters, and generate excavation machine control instructions.

[0014] Further, the jet rock-breaking dynamic monitoring module comprises a jet axial reaction force monitoring component, an excavation face laser ranging monitoring component, and an acoustic emission rock fracture dynamic monitoring component.

[0015] The jet axial reaction force monitoring component is configured to acquire jet parameters and calculate the jet axial reaction force; the excavation face laser ranging monitoring component is configured to acquire the three-dimensional topography of the excavation face; the acoustic emission rock fracture dynamic monitoring component is configured to acquire cutting and fracture morphology.

[0016] Further, the jet parameters include: jet mass, jet velocity, jet momentum, jet cross-sectional area, inlet flow mass, incoming flow velocity, inlet flow momentum, angle formed between the jet and the impacted object, jet density, and unit flow rate of the jet.

[0017] The jet axial reaction force monitoring component calculates the jet axial reaction force F2 as follows:

[0018] Jet impact reaction force without target F0:F0=m0⁢V0-m⁢V+(P0-P)⁢A0(I)

[0019] Jet impact reaction force with target F1:F1=p⁢Q⁢V0⁢sin⁢θ(II)

[0020] When θ=90°:F1=ρ⁢Q⁢V0(III)

[0021] When θ=180°:F1=0(IV)

[0022] Then the jet axial reaction force F2 is:F2=F0+F1(V)

[0023] Wherein: m0 refers jet mass, V0 refers jet velocity, P0 refers jet momentum, A0 refers jet cross-sectional area, m refers inlet flow mass, V refers incoming flow velocity, P refers inlet flow momentum, θ refers the angle formed between the jet and the impacted object, prefers jet density, and Q refers unit flow rate of the jet.

[0024] Further, the excavation face laser ranging monitoring component comprises a three-dimensional scanning device and a laser ranging device; the three-dimensional scanning device performs scanning of the three-dimensional topography of the face, and the laser ranging device detects the surface morphology of the excavation working face, the distance between the jet nozzle and the target, cutting depth information, and cutting kerf width information, thereby acquiring the three-dimensional topography of the excavation face.

[0025] Further, the acoustic emission rock fracture dynamic monitoring component determines the cutting depth information of the rock by monitoring changes in acoustic signals and reflects the entire process of rock mass fracture induced by jet cutting in real-time, thereby acquiring cutting and fracture morphology.

[0026] Further, the rock mass analysis and data processing module comprises a rock mass excavation face three-dimensional positioning component, a face equivalent confining pressure inversion component, and a rock mass characteristic identification component;

[0027] The excavation face three-dimensional positioning component is configured to acquire the three-dimensional coordinates of the excavation machine in the working environment; the face equivalent confining pressure inversion component is configured to calculate rock mass confining pressure; the rock mass characteristic identification component is configured to acquire rock mass characteristics.

[0028] Further, the process of the face equivalent confining pressure inversion component calculating rock mass confining pressure comprises:

[0029] Establishing a mathematical model correlating rock mass confining pressure, cutting depth, and jet parameters via the neural network deep learning module; based on the jet axial reaction force obtained from the jet axial reaction force monitoring component, the cutting depth information obtained via the excavation face laser ranging monitoring component, and the stress changes obtained from microseismic signal processing results, combined with jet parameters, inversely learning and correcting the rock mass confining pressure at the face; based on the inversely calculated rock mass confining pressure at the face, qualitatively evaluating crack initiation stress and damage stress; establishing a relationship diagram between penetration depth and confining pressure based on laboratory simulation experiments and field tests, and generating an equivalent stress diagram for the face.

[0030] Further, when establishing the mathematical model correlating rock mass confining pressure, cutting depth, and jet parameters via the neural network deep learning module, and inversely learning and correcting the rock mass confining pressure at the face based on the jet axial reaction force obtained from the jet axial reaction force monitoring component, the cutting depth information obtained via the excavation face laser ranging monitoring component, the stress changes obtained from microseismic signal processing results, and combined with jet parameters, the following formula is used for inverse learning and correction:H=H0⁢ktFmax[1+2⁢σ2r2⁢kt⁢c2+2⁢σr2⁢kt⁢c⁢(r-Fmaxkt⁢c)-σr2⁢kt⁢c⁢(r-Fmaxkt⁢c)-1σ2r4⁢kt⁢c2)12(VI)

[0031] Wherein: H refers the cutting depth under confining pressure, H0 refers the cutting depth without confining pressure applied, kt refers the elastic coefficient of the rock mass under confining pressure, kt refers the elastic coefficient of the rock mass without confining pressure, Fmax refers the maximum force in the rock contact zone, Fmax is equal to the jet axial reaction force F2, r refers the abrasive particle size, and σ refers the confining pressure.

[0032] Further, characterized in that: the excavation machine control instructions include excavation machine body movement instructions, nozzle trajectory movement instructions, jet parameter correction instructions, and safety risk warning instructions.

[0033] Further, the generation of excavation machine control instructions based on real-time monitoring data from the jet rock-breaking dynamic monitoring module and the rock mass analysis and data processing module, and the intelligent model correlating jet cutting process parameters with excavation process parameters, comprises:

[0034] Based on the three-dimensional coordinates of the excavation machine in the working environment fed back by the rock mass analysis and data processing module, and the three-dimensional topography of the excavation face fed back by the rock-breaking dynamic monitoring module, combined with the intelligent model correlating jet cutting process parameters with excavation process parameters, determining the optimal position and posture of the excavation machine, generating the excavation machine body movement instructions, enabling the excavation machine to adjust its position and orientation in real-time;

[0035] Based on the jet parameters, jet axial reaction force, three-dimensional topography of the excavation face, and cutting and fracture morphology fed back by the rock-breaking dynamic monitoring module, combined with the intelligent model correlating jet cutting process parameters with excavation process parameters, determining the optimal position and posture of the jet cutting mechanism, generating the nozzle trajectory movement instructions, enabling the jet cutting mechanism to adjust its moving direction and speed in real-time;

[0036] Based on the jet parameters, jet axial reaction force, three-dimensional topography of the excavation face, and cutting and fracture 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, combined with the intelligent model correlating jet cutting process parameters with excavation process parameters, determining the optimal jet parameters for the jet cutting mechanism, generating the jet parameter correction instructions, enabling the jet cutting mechanism to adjust jet parameters in real-time;

[0037] Based on the three-dimensional topography of the excavation face and cutting and fracture 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, combined with the intelligent model correlating jet cutting process parameters with excavation process parameters, real-time evaluating risk coefficients for surrounding rock deformation, rockburst, and water / mud inrush, generating the safety risk warning instructions, issuing a signal when risk thresholds are exceeded, causing the excavation machine to stop working.

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

[0039] 1) The jet cutting of the present invention uses water as the medium, effectively suppressing dust, improving the construction environment, and benefiting ecological environmental protection. The jet nozzle is small in size, enabling intelligent control for hard rock cutting, with smooth and precisely controllable excavated profiles. By introducing the dynamic evaluation model for jet cutting status and effectiveness, the dynamic evaluation model for safety risks and rock mass data, and the cutting effectiveness evaluation model for different lithologies, it can dynamically evaluate jet cutting effectiveness, correct the position and orientation of the excavation machine, correct nozzle moving speed and direction, dynamically evaluate and assess the working environment conditions in real-time, issue construction progress instructions and risk response measures, thereby achieving safe and efficient control of high-pressure jet excavation equipment for adaptive cutting of ore / rock mass.

[0040] 2) The present invention introduces artificial intelligence and deep learning to construct an intelligent model correlating jet cutting process parameters with excavation process parameters, enabling precise control of the spatial posture of the high-pressure abrasive jet manipulator, achieving precise targeted cutting of the waterjet, optimizing hydraulic hard rock fragmentation efficiency and cutting paths, and realizing adaptive precise control of key jet parameters.

[0041] 3) The present invention can achieve large-block cutting and controllable spalling of hard rock masses, with high hard rock fragmentation efficiency. Based on the pressure relief and energy release characteristics of jet cutting slots, it can also achieve intelligent perception and active control of surrounding rock deformation. The impact loads and vibrations generated during the excavation process are relatively small, effectively reducing surrounding rock damage. It can solve the challenges of efficient, intelligent, and green excavation for tunnels and underground engineering under complex geological conditions, with hard surrounding rock and different cross-sections.

[0042] 4) The high-pressure jet rock-breaking and cutting of the present invention is a non-contact rock-breaking method, with no tool wear. The system employs the jet axial reaction force monitoring component, excavation face laser ranging monitoring component, acoustic emission rock fracture dynamic monitoring component, rock mass excavation face three-dimensional positioning component, face equivalent confining pressure inversion component, and rock mass characteristic identification component, making the prediction of rock mass stress faster, the excavation efficiency of the working face higher, and the rock-breaking process less affected by complex environments such as mist, coal dust, and dirt.BRIEF DESCRIPTION OF THE DRAWINGS

[0043] To make the objectives, technical solutions, and beneficial effects of the present invention clearer, the following drawings are provided for description:

[0044] FIG. 1 is a schematic diagram showing the combination of functional modules and technical route of the present invention;

[0045] FIG. 2 is a schematic diagram showing the impact force of a jet on a solid plane;

[0046] FIG. 3 is schematic diagram for calculating the jet axial reaction force;

[0047] FIG. 4 is a schematic diagram showing jet impact on rock mass and rock-breaking depth.DESCRIPTION OF THE EMBODIMENTS

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

[0049] As shown in FIG. 1, an intelligent adaptive monitoring and control system for high-pressure jet excavation in this embodiment comprises a jet rock breaking dynamic monitoring module, a rock mass analysis and data processing module, a neural network deep learning module, and a mining and excavation machine controller.

[0050] The jet rock-breaking dynamic monitoring module is configured to: acquire jet parameters and calculate jet axial reaction force; acquire the three-dimensional topography of the excavation face; acquire cutting and fracture morphology; wherein the three-dimensional topography of the excavation face at least includes cutting depth information.

[0051] The rock mass analysis and data processing module is configured to: acquire the three-dimensional coordinates of the excavation machine in the working environment; calculate rock mass confining pressure; acquire rock mass characteristics.

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

[0053] Collect and store historical and real-time data of jet parameters, jet axial reaction force, three-dimensional topography of the excavation face, and cutting and fracture morphology, establish a dynamic evaluation model for jet cutting status and effectiveness.

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

[0055] Based on historical and real-time monitoring data of jet parameters, cutting depth information, and rock mass characteristics, establish a cutting effectiveness evaluation model for different lithologies.

[0056] Based on the dynamic evaluation model for jet cutting status and effectiveness, the dynamic evaluation model for safety risks and rock mass data, and the cutting effectiveness evaluation model for different lithologies, using fragmentation size, cutting depth, and surrounding rock deformation as objective functions, establish a database of jet cutting process parameters and an intelligent model correlating jet cutting process parameters with excavation process parameters.

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

[0058] Jet cutting uses water as the medium, effectively suppressing dust, improving the construction environment, and benefiting ecological environmental protection. The jet nozzle is small in size, enabling intelligent control for hard rock cutting, with smooth and precisely controllable excavated profiles. By introducing the dynamic evaluation model for jet cutting status and effectiveness, the dynamic evaluation model for safety risks and rock mass data, and the cutting effectiveness evaluation model for different lithologies, it can dynamically evaluate jet cutting effectiveness, correct the position and orientation of the excavation machine, correct nozzle moving speed and direction, dynamically evaluate and assess the working environment conditions in real-time, issue construction progress instructions and risk response measures, thereby achieving safe and efficient control of high-pressure jet excavation equipment for adaptive cutting of ore / rock mass. Furthermore, by introducing artificial intelligence and deep learning to construct an intelligent model correlating jet cutting process parameters with excavation process parameters, precise control of the spatial posture of the high-pressure abrasive jet manipulator is achieved, enabling precise targeted cutting of the waterjet, optimizing hydraulic hard rock fragmentation efficiency and cutting paths, and realizing adaptive precise control of key jet parameters.

[0059] High-pressure jet cutting can achieve large block cutting and controllable spalling of hard rock masses, with high hard rock fragmentation efficiency. Based on the pressure relief and energy release characteristics of jet cutting slots, it can also achieve intelligent perception and active control of surrounding rock deformation. The impact loads and vibrations generated during the excavation process are relatively small, effectively reducing surrounding rock damage. It can solve the challenges of efficient, intelligent, and green excavation for tunnels and underground engineering under complex geological conditions, with hard surrounding rock and different cross-sections. High-pressure jet rock-breaking and cutting is a non-contact rock-breaking method, with no tool wear. The system employs the jet axial reaction force monitoring component, excavation face laser ranging monitoring component, acoustic emission rock fracture dynamic monitoring component, rock mass excavation face three-dimensional positioning component, face equivalent confining pressure inversion component, and rock mass characteristic identification component, making the prediction of rock mass stress faster, the excavation efficiency of the working face higher, and the rock-breaking process less affected by complex environments such as mist, coal dust, and dirt.

[0060] In this implementation case, the jet rock-breaking dynamic monitoring module comprises a jet axial reaction force monitoring component, an excavation face laser ranging monitoring component, and an acoustic emission rock fracture dynamic monitoring component.

[0061] The jet axial reaction force monitoring component is configured to acquire jet parameters and calculate the jet axial reaction force; the excavation face laser ranging monitoring component is configured to acquire the three-dimensional topography of the excavation face; the acoustic emission rock fracture dynamic monitoring component is configured to acquire cutting and fracture morphology.

[0062] In this implementation case, the jet parameters include jet mass, jet velocity, jet momentum, jet cross-sectional area, inlet flow mass, incoming flow velocity, inlet flow momentum, angle formed between the jet and the impacted object, jet density, and unit flow rate of the jet.

[0063] When not impacting an object, during the high-pressure jet cutting and rock-breaking process, an axial reaction force exists due to the impact of the high-pressure jet. Acting on the high-pressure jet equipment, the jet axial reaction force monitoring component can monitor this reaction force. As shown in FIG. 2, the derivation for calculating the jet axial reaction force F2 by the jet axial reaction force monitoring component is as follows:

[0064] The momentum equation in the X direction: −F1=ρQ1V1 cos 90°+ρQ2V2 cos 90°−ρQsin θ=−ρQsin θ

[0065] The momentum equation in the Y direction: ρQ1V1−ρQ2V2−PρQV0 cos θ=0

[0066] From Bernoulli and the fluid continuity equation:V0=V1+V2,Q=Q1+Q2,Q1=12⁢Q⁡(1+cos⁢θ),Q2=12⁢Q⁡(1-cos⁢θ);

[0067] As shown in FIG. 3, the jet impact reaction force without target, F0: F0=m0V0−mV+(P0−P)A0;

[0068] When the jet impacts target, the impact reaction force, F1: F1=−ρQV0 sin θ;

[0069] When θ=90°: F1=ρQV0;

[0070] When θ=180°: F1=0;

[0071] Then the jet axial reaction force F2: F2=F1+F0;

[0072] Wherein: m0 represents jet mass, V0 represents jet velocity, P0 represents jet momentum, A0 represents jet cross-sectional area, m represents inlet flow mass, V represents incoming flow velocity, P represents inlet flow momentum, θ represents the angle formed between the jet and the impacted object, ρ represents jet density, Q represents unit flow rate of the jet.

[0073] In this implementation case, the excavation face laser ranging monitoring component comprises a three-dimensional scanning device and a laser ranging device. The three-dimensional scanning device performs scanning of the three-dimensional topography of the face, and the laser ranging device detects the surface morphology of the excavation working face, the distance between the jet nozzle and the target, cutting depth information, and cutting kerf width information, thereby acquiring the three-dimensional topography of the excavation face. The three-dimensional scanning device and the laser ranging device work together and are less affected by complex environments such as mist, dust, and dirt.

[0074] In this implementation case, the acoustic emission rock fracture dynamic monitoring component determines the cutting depth information of the rock by monitoring changes in acoustic signals and reflects the entire process of rock mass fracture induced by jet cutting in real-time, thereby acquiring cutting and fracture morphology. The cutting and fracture morphology can be used to qualitatively evaluate rock damage stress.

[0075] In this implementation case, the rock mass analysis and data processing module comprises a rock mass excavation face three-dimensional positioning component, a face equivalent confining pressure inversion component, and a rock mass characteristic identification component.

[0076] The three-dimensional excavation face positioning component is configured to acquire the three-dimensional coordinates of the excavation machine in the working environment; the face equivalent confining pressure inversion component is configured to calculate rock mass confining pressure, and the rock mass characteristic identification component is configured to acquire rock mass characteristics.

[0077] The excavation face three-dimensional positioning component can precisely locate the cutting and excavation area, define the direction of the cutting working face, and ensure the forward direction during the excavation process, unaffected by obstacles such as dust and mist. The rock mass characteristic identification component can identify rock mass characteristics and store them in the neural network deep learning module.

[0078] In this implementation case, the process of the face equivalent confining pressure inversion component calculating rock mass confining pressure comprises:

[0079] Establish a mathematical model correlating rock mass confining pressure, cutting depth, and jet parameters via the neural network deep learning module. Based on the jet axial reaction force obtained from the jet axial reaction force monitoring component, the cutting depth information obtained via the excavation face laser ranging monitoring component, and the stress changes obtained from microseismic signal processing results, combine with jet parameters, in order to inversely learn and correct the rock mass confining pressure at the face. Based on the inversely calculated rock mass confining pressure at the face, qualitatively evaluate crack initiation stress and damage stress, establish a relationship diagram between penetration depth and confining pressure based on laboratory simulation experiments and field tests, and generate an equivalent stress diagram for the face.

[0080] In this implementation case, as shown in FIG. 4, the angle at which the fluid on the jet axis impacts the rock mass is always perpendicular to the tangent of the impact crater bottom surface, where the dashed line represents the jet axis. Therefore, the rock-breaking depth is determined by the abrasive and fluid on the jet axis. After the abrasive on the jet axis impacts the rock mass, it causes certain damage to the rock, and the accumulation of this damage forms an impact crater of a certain depth. Establish a mathematical model correlating rock mass confining pressure, cutting depth, and jet parameters via the neural network deep learning module. Based on the jet axial reaction force obtained from the jet axial reaction force monitoring component, the cutting depth information obtained via the excavation face laser ranging monitoring component, and the stress changes obtained from microseismic signal processing results, combine with jet parameters, in order to inversely learn and correct the rock mass confining pressure at the face, the following formula is used for inverse learning and correction:H=H0⁢ktFmax[1+2⁢σ2r2⁢kt⁢c2+2⁢σr2⁢kt⁢c⁢(r-Fmaxkt⁢c)-σr2⁢kt⁢c⁢(r-Fmaxkt⁢c)-1σ2r4⁢kt⁢c2)12

[0081] Wherein: H is the cutting depth under confining pressure, H0 is the cutting depth without confining pressure, ktc is the elastic coefficient of the rock mass under confining pressure, kt is the elastic coefficient of the rock mass without confining pressure, Fmax is the maximum force in the rock contact zone, Fmax is equal to the jet axial reaction force, r is the abrasive particle size, σ is the confining pressure.

[0082] In this implementation case, the neural network deep learning module is capable of constructing neural networks oriented towards jet cutting, collecting jet cutting effectiveness and cutting parameters, and learning and training the constructed neural networks. It can collect dynamic response feedback signals from jet impact on rock, and based on spectrum analysis theory, establish a mapping relationship between the spectral analysis data of jet reflected waves and the cutting characteristics of impacted rock mass, constructing a precise perception mechanism for the characteristics of ultra-high pressure abrasive jet cutting of hard rock mass under rock mass stress field conditions. Based on the adaptive program for jet cutting fragmentation-surrounding rock deformation, it analyzes the optimal jet parameters for multi-target area coordinated cutting-surrounding rock deformation, to achieve the demands of adaptive coordinated multi-task operations for roadway excavation. The neural network deep learning module can continuously collect construction parameter data and working face image data, aggregate them into a deep learning database, and through repeated iterative learning—training—verification, continuously improve the accuracy of intelligent decision-making and information feedback, ensuring cutting speed and excavation efficiency.

[0083] In this implementation case, characterized in that: the excavation machine control instructions include excavation machine body movement instructions, nozzle trajectory movement instructions, jet parameter correction instructions, and safety risk warning instructions.

[0084] In this implementation case, based on real-time monitoring data from the jet rock-breaking dynamic monitoring module and the rock mass analysis and data processing module, and the intelligent model correlating jet cutting process parameters with excavation process parameters characterized in that, of excavation machine control instructions are generated, which comprises:

[0085] Based on the three-dimensional coordinates of the excavation machine in the working environment fed back by the rock mass analysis and data processing module, and the three-dimensional topography of the excavation face fed back by the rock-breaking dynamic monitoring module, obtain the three-dimensional topography and coordinates of the excavation space and detecting the surface morphology of the excavation working face, combine with the intelligent model correlating jet cutting process parameters with excavation process parameters, determine the optimal position and posture of the excavation machine, generate the excavation machine body movement instructions (instructions to determine whether the excavation machine should move forward, the amount of forward movement, and direction, etc.), enabling the excavation machine to adjust its position and orientation in real-time.

[0086] Based on the jet parameters, jet axial reaction force, three-dimensional topography of the excavation face, and cutting and fracture morphology fed back by the rock-breaking dynamic monitoring module, combine with the intelligent model correlating jet cutting process parameters with excavation process parameters, determine the optimal position and posture of the jet cutting mechanism, generate the nozzle trajectory movement instructions, enabling the jet cutting mechanism to adjust its moving direction and speed in real-time. From the jet parameters, jet axial reaction force, three-dimensional topography of the excavation face, and cutting and fracture morphology, information such as whether the jet cutting depth has reached the target, whether the cutting depth is still increasing, and whether the cutting has penetrated the rock block can be derived. Relying on the dynamic evaluation model for jet cutting status and effectiveness, the cutting effectiveness can be determined, and the moving direction and speed of the jet cutting mechanism can be adjusted in real-time to achieve optimal cutting effectiveness.

[0087] Based on the jet parameters, jet axial reaction force, three-dimensional topography of the excavation face, and cutting and fracture 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, combine with the intelligent model correlating jet cutting process parameters with excavation process parameters, determine the optimal jet parameters for the jet cutting mechanism, generate the jet parameter correction instructions, enabling the jet cutting mechanism to adjust jet parameters in real-time. By inversely deducing the equivalent confining pressure distribution nephogram from the changes in cutting depth of the excavation face, and real-time evaluating the working environment conditions according to the dynamic evaluation model for safety risks and rock mass data, the jet parameters of the jet cutting mechanism are adjusted in real-time to the optimal jet parameters.

[0088] Based on the three-dimensional topography of the excavation face and cutting and fracture 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, combine with the intelligent model correlating jet cutting process parameters with excavation process parameters, real-time evaluate risk coefficients for surrounding rock deformation, rock burst, and water / mud inrush, generate the safety risk warning instructions, issue signal when risk thresholds are exceeded, causing the excavation machine to stop working.

[0089] Finally, it is noted that the above embodiments are only intended to illustrate the technical solutions of the present invention and not to limit them. Although the present invention has been described in detail with reference to the preferred embodiments, those of ordinary skill in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention, which should all be covered within the scope of the claims of the present invention.

Examples

Embodiment Construction

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

[0049]As shown in FIG. 1, an intelligent adaptive monitoring and control system for high-pressure jet excavation in this embodiment comprises a jet rock breaking dynamic monitoring module, a rock mass analysis and data processing module, a neural network deep learning module, and a mining and excavation machine controller.

[0050]The jet rock-breaking dynamic monitoring module is configured to: acquire jet parameters and calculate jet axial reaction force; acquire the three-dimensional topography of the excavation face; acquire cutting and fracture morphology; wherein the three-dimensional topography of the excavation face at least includes cutting depth information.

[0051]The rock mass analysis and data processing module is configured to: acquire the three-dimensional coordinates of the excavation machine in the working environment; calcu...

Claims

1. An intelligent adaptive monitoring and control system for high-pressure jet excavation, characterized by comprising a jet rock-breaking dynamic monitoring module, a rock mass analysis and data processing module, a neural network deep learning module, and an mining and excavation machine controller;the jet rock-breaking dynamic monitoring module is configured to: acquire jet parameters and calculate jet axial reaction force; acquire the three-dimensional topography of the excavation face; and acquire cutting and fracture morphology; wherein the three-dimensional topography of the excavation face at least includes cutting depth information;the rock mass analysis and data processing module is configured to: acquire the three-dimensional coordinates of the excavation machine in the working environment; calculate rock mass confining pressure; and acquire rock mass characteristics;the neural network deep learning module is configured to:collect and store historical and real-time data of jet parameters, jet axial reaction force, three-dimensional topography of the excavation face, and cutting and fracture morphology, to establish a dynamic evaluation model for jet cutting status and effectiveness;collect and store historical and real-time monitoring data of the three-dimensional coordinates of the excavation machine in the working environment, rock mass confining pressure, and rock mass characteristics, to establish a dynamic evaluation model for safety risks and rock mass data;based on historical and real-time monitoring data of jet parameters, cutting depth information, and rock mass characteristics, establish a cutting effectiveness evaluation model for different lithologies;based on the dynamic evaluation model for jet cutting status and effectiveness, the dynamic evaluation model for safety risks and rock mass data, and the cutting effectiveness evaluation model for different lithologies, using fragmentation size, cutting depth, and surrounding rock deformation as objective functions, establish a database of jet cutting process parameters and establish an intelligent model correlating jet cutting process parameters with excavation process parameters;the mining and excavation machine controller is configured to: based on real-time monitoring data from the jet rock-breaking dynamic monitoring module and the rock mass analysis and data processing module, combined with the intelligent model correlating jet cutting process parameters with excavation process parameters, determine the optimal position and posture of the excavation machine and jet cutting mechanism, and optimal jet parameters, and generate excavation machine control instructions.

2. The intelligent adaptive monitoring and control system for high-pressure jet excavation according to claim 1, characterized in that: the jet rock-breaking dynamic monitoring module comprises a jet axial reaction force monitoring component, an excavation face laser ranging monitoring component, and an acoustic emission rock fracture dynamic monitoring component;the jet axial reaction force monitoring component is configured to acquire jet parameters and calculate the jet axial reaction force; the excavation face laser ranging monitoring component is configured to acquire the three-dimensional topography of the excavation face; the acoustic emission rock fracture dynamic monitoring component is configured to acquire cutting and fracture morphology.

3. The intelligent adaptive monitoring and control system for high-pressure jet excavation according to claim 2, characterized in that: the jet parameters include: jet mass, jet velocity, jet momentum, jet cross-sectional area, inlet flow mass, incoming flow velocity, inlet flow momentum, angle formed between the jet and the impacted object, jet density, and unit flow rate of the jet;the jet axial reaction force monitoring component calculates the jet axial reaction force F2 as follows:the jet impact reaction force without target F0:F0=m0⁢V0-m⁢V+(P0-P)⁢A0(I)The jet impact reaction force with target F1:F1=p⁢Q⁢V0⁢sin⁢θ(II)when θ=90°:F1=ρ⁢Q⁢V0(III)when θ=180°:F1=0(IV)then the jet axial reaction force F2 is:F2=F0+F1(V)wherein: m0 refers jet mass, V0 refers jet velocity, P0 refers jet momentum, A0 refers jet cross-sectional area, m refers inlet flow mass, V refers incoming flow velocity, P refers inlet flow momentum, θ refers the angle formed between the jet and the impacted object, prefers jet density, and Q refers unit flow rate of the jet.

4. The intelligent adaptive monitoring and control system for high-pressure jet excavation according to claim 2, characterized in that: the excavation face laser ranging monitoring component comprises a three-dimensional scanning device and a laser ranging device; the three-dimensional scanning device performs scanning of the three-dimensional topography of the face, and the laser ranging device detects the surface morphology of the excavation working face, the distance between the jet nozzle and the target, cutting depth information, and cutting kerf width information, thereby acquiring the three-dimensional topography of the excavation face.

5. The intelligent adaptive monitoring and control system for high-pressure jet excavation according to claim 2, characterized in that: the acoustic emission rock fracture dynamic monitoring component determines the cutting depth information of the rock by monitoring changes in acoustic signals and reflects the entire process of rock mass fracture induced by jet cutting in real-time, thereby acquiring cutting and fracture morphology.

6. The intelligent adaptive monitoring and control system for high-pressure jet excavation according to claim 2, characterized in that: the rock mass analysis and data processing module comprises a rock mass excavation face three-dimensional positioning component, a face equivalent confining pressure inversion component, and a rock mass characteristic identification component;the excavation face three-dimensional positioning component is configured to acquire the three-dimensional coordinates of the excavation machine in the working environment; the face equivalent confining pressure inversion component is configured to calculate rock mass confining pressure; the rock mass characteristic identification component is configured to acquire rock mass characteristics.

7. The intelligent adaptive monitoring and control system for high-pressure jet excavation according to claim 6, characterized in that: the process of the face equivalent confining pressure inversion component calculating rock mass confining pressure comprises:establishing a mathematical model correlating rock mass confining pressure, cutting depth, and jet parameters via the neural network deep learning module; based on the jet axial reaction force obtained from the jet axial reaction force monitoring component, the cutting depth information obtained via the excavation face laser ranging monitoring component, and the stress changes obtained from microseismic signal processing results, combined with jet parameters, inversely learning and correcting the rock mass confining pressure at the face; based on the inversely calculated rock mass confining pressure at the face, qualitatively evaluating crack initiation stress and damage stress; establishing a relationship diagram between penetration depth and confining pressure based on laboratory simulation experiments and field tests, and generating an equivalent stress diagram for the face.

8. The intelligent adaptive monitoring and control system for high-pressure jet excavation according to claim 7, characterized in that: when establishing the mathematical model correlating rock mass confining pressure, cutting depth, and jet parameters via the neural network deep learning module, and inversely learning and correcting the rock mass confining pressure at the face based on the jet axial reaction force obtained from the jet axial reaction force monitoring component, the cutting depth information obtained via the excavation face laser ranging monitoring component, the stress changes obtained from microseismic signal processing results, and combined with jet parameters, the following formula is used for inverse learning and correction:H=H0⁢ktFmax[1+2⁢σ2r2⁢kt⁢c2+2⁢σr2⁢kt⁢c⁢(r-Fmaxkt⁢c)-σr2⁢kt⁢c⁢(r-Fmaxkt⁢c)-1σ2r4⁢kt⁢c2)12(VI)wherein: H refers the cutting depth under confining pressure, H0 refers the cutting depth without confining pressure applied, kt refers the elastic coefficient of the rock mass under confining pressure, kt refers the elastic coefficient of the rock mass without confining pressure, Fmax refers the maximum force in the rock contact zone, Fmax is equal to the jet axial reaction force F2, r refers the abrasive particle size, and σ refers the confining pressure.

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

10. The intelligent adaptive monitoring and control system for high-pressure jet excavation according to claim 9, characterized in that, the generation of excavation machine control instructions based on real-time monitoring data from the jet rock-breaking dynamic monitoring module and the rock mass analysis and data processing module, and the intelligent model correlating jet cutting process parameters with excavation process parameters, comprises:based on the three-dimensional coordinates of the excavation machine in the working environment fed back by the rock mass analysis and data processing module, and the three-dimensional topography of the excavation face fed back by the rock-breaking dynamic monitoring module, combined with the intelligent model correlating jet cutting process parameters with excavation process parameters, determining the optimal position and posture of the excavation machine, generating the excavation machine body movement instructions, enabling the excavation machine to adjust its position and orientation in real-time;based on the jet parameters, jet axial reaction force, three-dimensional topography of the excavation face, and cutting and fracture morphology fed back by the rock-breaking dynamic monitoring module, combined with the intelligent model correlating jet cutting process parameters with excavation process parameters, determining the optimal position and posture of the jet cutting mechanism, generating the nozzle trajectory movement instructions, enabling the jet cutting mechanism to adjust its moving direction and speed in real-time;based on the jet parameters, jet axial reaction force, three-dimensional topography of the excavation face, and cutting and fracture 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, combined with the intelligent model correlating jet cutting process parameters with excavation process parameters, determining the optimal jet parameters for the jet cutting mechanism, generating the jet parameter correction instructions, enabling the jet cutting mechanism to adjust jet parameters in real-time;based on the three-dimensional topography of the excavation face and cutting and fracture 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, combined with the intelligent model correlating jet cutting process parameters with excavation process parameters, real-time evaluating risk coefficients for surrounding rock deformation, rockburst, and water / mud inrush, generating the safety risk warning instructions, issuing a signal when risk thresholds are exceeded, causing the excavation machine to stop working.

Images