Integrated intelligent one-key grouting system and control method in coal mine

Abstract

The present application belongs to the technical field of underground coal mine grouting, and discloses an integrated intelligent one-key grouting system for underground coal mine and a control method. The system comprises a storage module, a slurry preparation module, a grouting module, a monitoring module, an intelligent centralized control module and an integrated mobile platform. Through a full-process self-adaptive closed-loop control strategy, the system realizes full-process automation, including starting, feeding, slurry preparation, grouting, abnormality handling and cleaning, and achieves full-process closed-loop automatic control through one-key operation. The system has self-adaptive regulation and control of over-expansion, intelligent triggering of water-cement ratio reduction strategy based on accurate calculation of residual slurry, automatic execution of subsequent processes and innovative method of dynamic optimization of grouting parameters. The system has intelligent self-cleaning, automatic triggering of pipeline cleaning at the end of grouting, improved equipment reliability, reduced manual maintenance, precise sound and light alarm and video positioning at the link of manual intervention (feeding and leakage plugging), and optimized human-machine cooperation efficiency.

Description

Technical Field

[0001] This invention belongs to the field of grouting technology in mining engineering and geotechnical engineering, and relates to underground grouting systems in coal mines, particularly to an integrated intelligent one-click grouting system and control method for underground coal mines. Background Technology

[0002] Underground grouting technology in coal mines plays an irreplaceable core role in ensuring safe and efficient mine production (including controlling surrounding rock stability and preventing water-related accidents). However, the technical bottlenecks of existing grouting equipment and control systems severely restrict the efficiency of grouting operations. Key pain points include: ① Equipment fragmentation: Storage, grouting, grouting, and monitoring equipment are scattered and operate independently, occupying a lot of space, with complex pipeline connections, and difficult relocation, seriously affecting operational efficiency; ② Difficulty in process coordination: Each grouting step relies on manual operation and coordination, resulting in low precision in parameter control (such as water-cement ratio), poor process transitions, long conversion response times, and a high risk of errors, leading to low collaborative work efficiency; ③ Low level of intelligence: The grouting process relies on manual control and lacks real-time and accurate perception and intelligent analysis of key parameters (such as grout volume, water-cement ratio, grouting pressure, flow rate, and grout diffusion state). Abnormal grouting conditions (such as grout over-diffusion, inability to inject, grout leakage, etc.) mainly rely on manual experience for judgment, resulting in delayed response and adjustment. Improper handling can easily lead to safety hazards or project failure. ④ Data silos and delays: Data from each subsystem is independent and difficult to integrate and analyze. Traditional cloud computing methods have significant network latency and cannot meet the real-time control requirements for rapid response in the downhole grouting process.

[0003] To address the pain points existing in current grouting equipment and control systems, Chinese patent CN202410327741.4 discloses a multi-pump linkage grouting system and its working method, Chinese patent CN202310271667.4 discloses an integrated intelligent grouting system, and Chinese patent CN201310124851.2 discloses an integrated polymer grouting system. However, existing technologies have not effectively solved the core technical challenges of discreteness, difficulty in coordination, and low intelligence in grouting equipment systems under the confined space conditions of underground coal mines. Therefore, there is an urgent need to develop lightweight, integrated, fully intelligent grouting equipment and its collaborative control system suitable for the confined space of underground coal mines, and to construct a one-click grouting system that integrates the entire grouting process (material feeding, slurry preparation, grouting, monitoring, anomaly handling, and cleaning), providing core equipment support for safe, efficient, and intelligent grouting in underground coal mines.

[0004] In view of this, the present invention proposes an integrated intelligent one-click grouting system and control method for underground coal mines to solve the above problems. Summary of the Invention

[0005] To overcome the aforementioned deficiencies of the prior art and to achieve the above objectives, the present invention provides the following technical solution, including:

[0006] The storage module is used to detect the remaining amount of stored powder.

[0007] Furthermore, methods for detecting the remaining amount of stored powder include using high-frequency radar level gauges to collect real-time data on the remaining amount of stored powder in a designated storage silo, thereby obtaining monitoring data. The monitoring data will be transmitted to the edge intelligent computing unit.

[0008] The storage module is also used for:

[0009] It adopts a fully enclosed, moisture-proof, and explosion-proof stainless steel cylindrical silo, with a height not exceeding 3 meters;

[0010] The top of the silo is equipped with a feed inlet with a quick-opening sealing cap, and the bottom of the silo has a conical design and is equipped with a high-frequency, low-amplitude explosion-proof vibration motor to effectively prevent powder bridging and ensure smooth powder flow.

[0011] The discharge port is connected to a variable frequency speed-regulating explosion-proof screw conveyor, which can accurately control the powder conveying rate according to the pulping requirements and convey the slurry powder in the storage silo to the slurry mixing tank.

[0012] The pulping module is used to collect pulping datasets, which include material quality data, grouting powder quality data, slurry quality data, and injected water volume data.

[0013] Furthermore, the methods for collecting pulping datasets include:

[0014] By using a high-precision explosion-proof weighing sensor, the mass value of the material in the designated mixing tank is collected to obtain the material mass data;

[0015] By combining a high-precision explosion-proof weighing sensor with the start / stop status of the screw conveyor, the mass value of the grouting powder added to the designated mixing tank is collected to obtain the grouting powder mass data. ;

[0016] By using a high-precision electromagnetic flowmeter, the water flow rate at the outlet of a designated water pipe is collected to obtain the injected water flow data. ;

[0017] By combining a high-precision explosion-proof weighing sensor with the start-up status of the electric grouting pump, the mass value of the grout in a designated mixing tank is collected to obtain grout mass data. .

[0018] The pulping module is also used for:

[0019] It mainly includes an electric mixing tank, a weighing sensor, a water volume control module, and a clean water tank;

[0020] The support column of the slurry mixing tank is equipped with a high-precision explosion-proof weighing sensor to continuously and in real time weigh the material in the mixing tank and transmit the data to the edge computing unit. Combined with the start and stop status of the screw conveyor, the edge computing unit can accurately calculate the mass of the grouting powder that has been added. Combined with the start and stop status of the electric grouting pump, the edge computing unit can accurately calculate the mass of the slurry in the mixing tank.

[0021] The water control module includes water pipes, electric control ball valves for water pipes, and high-precision electromagnetic flow meters for water pipes. The electric control ball valves for water pipes and the high-precision electromagnetic flow meters for water pipes are directly installed on the water pipes. The high-precision electromagnetic flow meters for water pipes are located at the water pipe outlet and accurately measure the amount of water entering the mixing tank in real time, and transmit the data to the edge computing unit.

[0022] Control logic: The edge computing unit determines the water-cement ratio based on the set parameters. The target water addition is dynamically calculated based on the real-time weighing of the powder.

[0023] The clean water tank stores clean water for self-cleaning pipelines and grouting pumps;

[0024] Grouting module, used for monitoring and managing grouting equipment;

[0025] Furthermore, the steps for monitoring and managing grouting equipment include:

[0026] Q1: The grouting module includes an explosion-proof electric grouting pump, grout suction pipeline, grout discharge pipeline, and self-cleaning pipeline;

[0027] Q2: The suction pipe connects the slurry mixing tank and the grouting pump;

[0028] Q3: The grout outlet pipeline connects the grouting pump to the grouting area. An explosion-proof pressure transmitter and an explosion-proof electromagnetic flow sensor are installed in the pipeline to collect and monitor the output pressure and output flow of the explosion-proof electric grouting pump, obtain the output dataset, and transmit the output dataset to the edge intelligent computing unit in real time.

[0029] Q4: One end of the self-cleaning pipeline is connected to the slurry suction pipeline via a T-connector, and the other end is placed in a clean water tank. An electric control ball valve for the self-cleaning pipeline is installed in the pipeline.

[0030] Control logic: When grouting is completed or a specific abnormal command is received, the decision execution unit automatically closes the grout suction pipe, opens the ball valve of the self-cleaning pipe, starts the explosion-proof electric grouting pump to draw clean water, and automatically cleans the grout suction pipe, the explosion-proof electric grouting pump and the grout outlet pipe.

[0031] The monitoring module is used to monitor abnormal states in real time.

[0032] Furthermore, real-time monitoring of abnormal conditions includes using an intrinsically safe high-definition infrared network camera to perform 360° real-time video monitoring of the surface of the injection area, and outputting the monitoring data to the edge intelligent computing unit. The monitoring data is used to identify grout leakage and grout run-out conditions.

[0033] An integrated mobile platform is used to integrate a material storage module, a pulping module, a grouting module, a monitoring module, and an intelligent centralized control module;

[0034] The intelligent centralized control module includes a human-computer interaction unit, an edge intelligent computing unit, and a decision execution unit;

[0035] Furthermore, the human-computer interaction unit includes:

[0036] W1: Provides a one-click start button and an entry point for manual intervention;

[0037] W2: Input grouting design parameters;

[0038] W3: Displays all monitored parameters;

[0039] Furthermore, the edge intelligent computing unit includes:

[0040] E1: Performs millisecond-level edge computing analysis on real-time data from the material storage module, slurry preparation module, grouting module, and monitoring module to identify and analyze abnormal grouting conditions in real time. Specific intelligent analysis strategies include:

[0041] E1.1: When the monitored data is less than 15% of the total amount of powder in the storage bin, the edge intelligent computing unit sends a replenishment command to the decision execution unit;

[0042] When the monitored data is less than 5% of the total amount of powder in the storage bin, the edge computing unit sends an empty bin instruction to the decision execution unit;

[0043] E1.2: When the mass of the grouting powder is approximately equal to the mass of the standard powder, the edge computing unit sends a "fill powder" command to the decision execution unit.

[0044] When the water volume is approximately equal to the standard slurry water-cement ratio, the edge computing unit sends a water-filling command to the decision execution unit.

[0045] When the slurry quality data is less than 10% of the standard insufficient slurry, the edge computing unit sends a slurry replenishment command to the decision execution unit and triggers the automatic feeding and slurry preparation process.

[0046] E1.3: Perform edge calculations on the output pressure and output flow rate in the output dataset to identify abnormal states such as slurry over-diffusion and slurry inability to be injected;

[0047] E1.31: Grout over-diffusion identification includes: real-time filtering and state estimation of output pressure and output flow rate based on Kalman filter algorithm; when the output pressure is less than 15% of the minimum output pressure and the output flow rate is greater than the maximum grouting flow rate, it is marked as grout over-diffusion, and an over-diffusion execution command is sent to the decision execution unit through the edge computing unit.

[0048] E1.32: Grout injection failure identification includes: combining first-order derivatives and LSTM long short-term memory recurrent neural networks to perform temporal pattern recognition of output pressure, output flow rate, and time. When the output flow rate is greater than the preset threshold and less than 80% of the output flow rate, it is marked as slurry injection failure, and an injection failure execution command is sent to the decision execution unit through the edge computing unit.

[0049] E1.4: Perform edge computing analysis on monitoring data to identify abnormal states such as grout leakage and grout run-out;

[0050] E1.41: Constructing a dedicated CNN model for identifying slurry leakage and runoff in downhole wells: Deploying a slurry leakage and runoff identification model based on a deep convolutional neural network in the edge cells;

[0051] E1.42: Construction of a high-robust slurry leakage and runoff image dataset: The model training uses no less than 1,000 rigorously labeled real-world downhole scene images, and the dataset is enhanced with data augmentation to simulate extreme downhole environments: Gaussian noise of different intensities, multi-level low illumination, and random transparency water mist occlusion are added.

[0052] E1.43: Online Model Evolution: After the on-site grouting system completes 500 grouting operations, it automatically collects new on-site images, updates the image dataset, triggers an online incremental learning process, and updates the CNN model weights.

[0053] E1.44: Grout leakage and runaway identification and early warning: When the model identifies with high confidence that there is grout leakage or runaway anomaly in the video stream, it immediately sends a grout leakage execution command or a runaway execution command to the decision execution unit;

[0054] Furthermore, the decision execution unit includes: receiving instructions from the human-machine interaction unit and real-time analysis results and decision instructions from the edge intelligent computing unit, and controlling the material storage module, slurry preparation module and grouting module according to the logic of the one-click grouting intelligent adaptive control method;

[0055] Furthermore, S1: Parameter settings and startup;

[0056] S2: Intelligent feeding;

[0057] S3: Intelligent pulping;

[0058] S4: Automatic stirring;

[0059] S5: Intelligent grouting;

[0060] S6: Ultra-diffusion intelligent treatment;

[0061] S7: Intelligent handling of grout leakage or runoff;

[0062] S8: Grouting completed and cleaning.

[0063] The technical effects and advantages of the integrated intelligent one-click grouting system and control method for underground coal mines of this invention are as follows:

[0064] This invention integrates the core physical systems of material storage, slurry preparation, grouting, monitoring, and control into a single explosion-proof mobile platform, unifying hydraulic power to completely solve the problems of discreteness, difficulty in movement, and large space occupation, representing a systematic integrated innovation. By deploying high-performance edge computing units in the harsh underground environment, it performs millisecond-level fusion analysis and real-time decision-making on multi-source heterogeneous data (level, weight, flow rate, pressure, high-definition video), replacing traditional manual judgment and cloud latency, providing the technical foundation for one-click intelligent operation. Intelligent identification of abnormal operating conditions includes: super-diffusion: Kalman filtering improves the early and accurate identification of hidden leakage channels; injection failure: first derivative + LSTM time-series modeling utilizes historical data to learn complex patterns, significantly improving recognition accuracy and reducing false stops; slurry leakage / runaway: underground enhanced dataset + CNN model + online incremental learning constructs a highly robust visual recognition system adapted to the harsh underground environment (dust, low light, water mist), and can continuously evolve to adapt to changes; full-process adaptive closed-loop control strategy: full-process automation. From startup, feeding, slurry preparation, grouting, anomaly handling, and cleaning, the entire process is automated with a closed loop, truly enabling "one-click" operation. Super-diffusion adaptive regulation: Based on precise calculation of remaining slurry, it intelligently triggers a water-cement ratio reduction strategy and automatically executes subsequent processes, representing an innovative method for dynamically optimizing grouting parameters. Intelligent self-cleaning: It automatically triggers pipeline cleaning for situations such as failure to grout or grouting completion, improving equipment reliability, reducing manual maintenance, and providing precise audible and visual alarms and video positioning for necessary manual intervention stages (material replenishment, sealing leaks), optimizing human-machine collaboration efficiency. Attached Figure Description

[0065] Figure 1 This is a schematic diagram of the integrated intelligent one-click grouting system for underground coal mines according to the present invention;

[0066] Figure 2 This is a schematic diagram of the integrated intelligent one-click grouting control method for underground coal mines according to the present invention;

[0067] Figure 3 This is a schematic diagram of the integrated intelligent one-click grouting system for underground coal mines according to the present invention.

[0068] Figure 4This is a flowchart illustrating the integrated intelligent one-click grouting control method for underground coal mines according to the present invention. Detailed Implementation

[0069] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0070] The terminology used in the embodiments of this invention is for the purpose of describing particular embodiments only and is not intended to limit the invention. The singular forms “a,” “the,” and “the” as used in the embodiments of this invention and the appended claims are also intended to include the plural forms, and “multiple” generally includes at least two unless the context clearly indicates otherwise.

[0071] Depending on the context, the words “if” or “suppose” as used here can be interpreted as “when” or “in response to determination” or “in response to detection.” Similarly, depending on the context, the phrases “if determination” or “if detection (of the stated condition or event)” can be interpreted as “when determination” or “in response to determination” or “when detection (of the stated condition or event)” or “in response to detection (of the stated condition or event).”

[0072] Furthermore, the timing of the steps in the following method embodiments is merely an example and not a strict limitation.

[0073] In practice, the server-side equipment deployed in the integrated intelligent one-click grouting system for underground coal mines may consist of one or more devices. This integrated intelligent one-click grouting system for underground coal mines can be implemented as: a business instance, a virtual machine, or hardware devices. For example, this integrated intelligent one-click grouting system for underground coal mines can be implemented as a business instance deployed on one or more devices in a cloud node. Simply put, this integrated intelligent one-click grouting system for underground coal mines can be understood as software deployed on a cloud node, used to provide the integrated intelligent one-click grouting system for underground coal mines to various user terminals. Alternatively, this integrated intelligent one-click grouting system for underground coal mines can also be implemented as a virtual machine deployed on one or more devices in a cloud node. This virtual machine contains application software for managing various user terminals. Alternatively, this integrated intelligent one-click grouting system for underground coal mines can also be implemented as a server composed of numerous identical or different types of hardware devices, with one or more hardware devices configured to provide the integrated intelligent one-click grouting system for underground coal mines to various user terminals.

[0074] In terms of implementation, the integrated intelligent one-click grouting system for underground coal mines and the user terminal are mutually compatible. That is, if the integrated intelligent one-click grouting system for underground coal mines is implemented as an application installed on a cloud service platform, then the user terminal is implemented as a client that establishes a communication connection with the application; or if the integrated intelligent one-click grouting system for underground coal mines is implemented as a website, then the user terminal is implemented as a webpage; or if the integrated intelligent one-click grouting system for underground coal mines is implemented as a cloud service platform, then the user terminal is implemented as a mini-program in an instant messaging application.

[0075] like Figure 1 The figure shown is a system architecture diagram of an integrated intelligent one-click grouting system for underground coal mines provided in an embodiment of the present invention.

[0076] The integrated intelligent one-click grouting system for underground coal mines described in this invention can be installed on a cloud server. In terms of implementation, it can be used as one or more service devices, or as an application installed in the cloud (e.g., a mobile service operator's server or server cluster), or it can be developed into a website. Depending on the functions implemented, the integrated intelligent one-click grouting system for underground coal mines may include a material storage module, a grouting module, a grouting module, a monitoring module, an intelligent centralized control module, and an integrated mobile platform. The module described in this invention can also be called a unit, referring to a series of computer program segments that can be executed by an electronic device's processor and perform a fixed function, stored in the electronic device's memory.

[0077] In this embodiment of the invention, in the integrated intelligent one-click grouting system for underground coal mines, each of the above-mentioned modules can be implemented independently and can call other modules. Here, "calling" can be understood as a module connecting to multiple modules of another type and providing corresponding services to those connected modules. For example, the sharing and evaluation module can call the same information collection module to obtain the information collected by that module. Based on the above characteristics, in the integrated intelligent one-click grouting system for underground coal mines provided by this embodiment of the invention, without modifying the program code, the applicable scope of the integrated intelligent one-click grouting system architecture can be adjusted by adding modules and directly calling them, achieving cluster-based horizontal expansion to quickly and flexibly expand the integrated intelligent one-click grouting system for underground coal mines. In practical applications, the above-mentioned modules can be set in the same device or different devices, or they can be set in virtual devices, such as service instances in a cloud server.

[0078] Example 1

[0079] Please see Figure 1 As shown in this embodiment, the integrated intelligent one-click grouting system for underground coal mines includes:

[0080] The storage module is used to detect the remaining amount of stored powder.

[0081] Furthermore, methods for detecting the remaining amount of stored powder include using a high-frequency radar level gauge to collect the remaining amount of stored powder in a designated storage silo in real time, obtain monitoring data, and transmit the monitoring data to an edge intelligent computing unit.

[0082] The storage module is also used for:

[0083] It adopts a fully enclosed, moisture-proof, and explosion-proof stainless steel cylindrical silo, with a height not exceeding 3 meters;

[0084] The top of the silo is equipped with a feed inlet with a quick-opening sealing cap, and the bottom of the silo has a conical design and is equipped with a high-frequency, low-amplitude explosion-proof vibration motor to effectively prevent powder bridging and ensure smooth powder flow.

[0085] The discharge port is connected to a variable frequency speed-regulating explosion-proof screw conveyor, which can accurately control the powder conveying rate according to the pulping requirements and convey the slurry powder in the storage silo to the slurry mixing tank.

[0086] The pulping module is used to collect pulping datasets, which include material quality data, grouting powder quality data, slurry quality data, and injected water volume data.

[0087] Furthermore, the methods for collecting pulping datasets include:

[0088] By using a high-precision explosion-proof weighing sensor, the mass value of the material in the designated mixing tank is collected to obtain the material mass data;

[0089] By combining a high-precision explosion-proof weighing sensor with the start / stop status of the screw conveyor, the mass value of the grouting powder added to the designated mixing tank is collected to obtain the grouting powder mass data. ;

[0090] By combining a high-precision explosion-proof weighing sensor with the start-up status of the electric grouting pump, the mass value of the grout in a designated mixing tank is collected to obtain grout mass data. ;

[0091] By using a high-precision electromagnetic flowmeter, the water flow rate at the outlet of a designated water pipe is collected to obtain the injected water flow data. ;

[0092] The pulping module is also used for:

[0093] It mainly includes an electric mixing tank, a weighing sensor, a water volume control module, and a clean water tank;

[0094] The support column of the slurry mixing tank is equipped with a high-precision explosion-proof weighing sensor to continuously and in real time weigh the material in the mixing tank and transmit the data to the edge computing unit. Combined with the start and stop status of the screw conveyor, the edge computing unit can accurately calculate the mass of the grouting powder that has been added. Combined with the start and stop status of the electric grouting pump, the edge computing unit can accurately calculate the mass of the slurry in the mixing tank.

[0095] The water control module includes water pipes, electric control ball valves for water pipes, and high-precision electromagnetic flow meters for water pipes. The electric control ball valves for water pipes and the high-precision electromagnetic flow meters for water pipes are directly installed on the water pipes. The high-precision electromagnetic flow meters for water pipes are located at the water pipe outlet and accurately measure the amount of water entering the mixing tank in real time, and transmit the data to the edge computing unit.

[0096] Control logic: The edge computing unit determines the water-cement ratio based on the set parameters. The target water addition is dynamically calculated based on the real-time weighing of the powder.

[0097] The clean water tank stores clean water for self-cleaning pipelines and grouting pumps;

[0098] The grouting module is used to monitor and manage the grouting equipment;

[0099] Further steps for monitoring and managing grouting equipment include:

[0100] Q1: The grouting module includes an explosion-proof electric grouting pump, grout suction pipeline, grout discharge pipeline, and self-cleaning pipeline;

[0101] Q2: The suction pipe connects the slurry mixing tank and the grouting pump;

[0102] Q3: The grout outlet pipeline connects the grouting pump to the grouting area. An explosion-proof pressure transmitter and an explosion-proof electromagnetic flow sensor are installed in the pipeline to collect and monitor the output pressure and output flow of the explosion-proof electric grouting pump, obtain the output dataset, and transmit the output dataset to the edge intelligent computing unit in real time.

[0103] It should be explained that the grouting area refers to the area of ​​the grouting anchor or borehole;

[0104] Q4: One end of the self-cleaning pipeline is connected to the slurry suction pipeline via a T-connector, and the other end is placed in a clean water tank. An electric control ball valve for the self-cleaning pipeline is installed in the pipeline.

[0105] Control logic: When grouting is completed or a specific abnormal command is received, the decision execution unit automatically closes the grout suction pipe, opens the ball valve of the self-cleaning pipe, starts the explosion-proof electric grouting pump to draw clean water, and automatically cleans the grout suction pipe, the explosion-proof electric grouting pump and the grout outlet pipe.

[0106] It should be explained that specific abnormal instructions refer to, for example, instructions that cannot be injected;

[0107] The monitoring module is used to monitor abnormal states in real time;

[0108] Furthermore, real-time monitoring of abnormal conditions includes using an intrinsically safe high-definition infrared network camera to perform 360° real-time video monitoring of the surface of the injection area, and outputting the monitoring data to the edge intelligent computing unit. The monitoring data is used to identify grout leakage and grout run-out conditions.

[0109] The integrated mobile platform 19 is used to integrate a material storage module, a pulping module, a grouting module, a monitoring module, and an intelligent centralized control module;

[0110] The intelligent centralized control module includes a human-computer interaction unit, an edge intelligent computing unit, and a decision execution unit;

[0111] Furthermore, the human-computer interaction unit includes:

[0112] W1: Provides a one-click start button and an entry point for manual intervention;

[0113] W2: Input grouting design parameters;

[0114] It should be explained that the grouting design parameters include the grout water-cement ratio, target grouting volume, maximum grouting pressure, and flow rate threshold.

[0115] W3: Displays all monitored parameters;

[0116] It should be explained that the monitoring parameters include powder residue, water volume, slurry quality, grouting pressure, grouting flow rate, video footage, and abnormal conditions identified by edge computing.

[0117] Furthermore, the edge intelligent computing unit includes:

[0118] E1: Performs millisecond-level edge computing analysis on real-time data from the material storage module, slurry preparation module, grouting module, and monitoring module to identify and analyze abnormal grouting conditions in real time. Specific intelligent analysis strategies include:

[0119] E1.1: When the monitored data is less than 15% of the total amount of powder in the storage bin, the edge intelligent computing unit sends a replenishment command to the decision execution unit;

[0120] When the monitored data is less than 5% of the total amount of powder in the storage bin, the edge computing unit sends an empty bin instruction to the decision execution unit;

[0121] E1.2: When the mass of the grouting powder is approximately equal to the mass of the standard powder, the edge computing unit sends a "fill powder" command to the decision execution unit.

[0122] When the water volume is approximately equal to the standard slurry water-cement ratio, the edge computing unit sends a water-filling command to the decision execution unit.

[0123] When the slurry quality data is less than 10% of the standard insufficient slurry, the edge computing unit sends a slurry replenishment command to the decision execution unit and triggers the automatic feeding and slurry preparation process.

[0124] E1.3: Perform edge calculations on the output pressure and output flow rate in the output dataset to identify abnormal states such as slurry over-diffusion and slurry inability to be injected;

[0125] E1.31: Grout over-diffusion identification includes: real-time filtering and state estimation of output pressure and output flow rate based on Kalman filter algorithm; when the output pressure is less than 15% of the minimum output pressure and the output flow rate is greater than the maximum grouting flow rate, it is marked as grout over-diffusion, and an over-diffusion execution command is sent to the decision execution unit through the edge computing unit.

[0126] E1.32: Grout injection failure identification includes: combining first-order derivatives and LSTM long short-term memory recurrent neural networks to perform temporal pattern recognition of output pressure, output flow rate, and time. When the output flow rate is greater than the preset threshold and less than 80% of the output flow rate, it is marked as slurry injection failure, and an injection failure execution command is sent to the decision execution unit through the edge computing unit.

[0127] It needs to be explained that, For output pressure; For time; the preset threshold is a preset value based on actual engineering conditions, obtained by manually setting and inputting it into the system;

[0128] E1.4: Perform edge computing analysis on monitoring data to identify abnormal states such as grout leakage and grout run-out;

[0129] E1.41: Constructing a dedicated CNN model for identifying slurry leakage and runoff in downhole wells: Deploying a slurry leakage and runoff identification model based on a deep convolutional neural network in the edge cells;

[0130] E1.42: Construction of a high-robust slurry leakage and runoff image dataset: The model training uses no less than 1,000 rigorously labeled real-world downhole scene images, and the dataset is enhanced with data augmentation to simulate extreme downhole environments: Gaussian noise of different intensities, multi-level low illumination, and random transparency water mist occlusion are added.

[0131] It needs to be explained that leakage refers to grout seeping out of cracks or pores in the rock mass; runoff refers to grout flowing out along the grouting pipe or sealing parts.

[0132] E1.43: Online Model Evolution: After the on-site grouting system completes 500 grouting operations, it automatically collects new on-site images, updates the image dataset, triggers an online incremental learning process, and updates the CNN model weights.

[0133] It should be explained that the annotations for the newly added site images were reviewed remotely or on-site by engineers;

[0134] E1.44: Grout leakage and runaway identification and early warning: When the model identifies with high confidence that there is grout leakage or runaway anomaly in the video stream, it immediately sends a grout leakage execution command or a runaway execution command to the decision execution unit;

[0135] Furthermore, the decision execution unit includes: receiving instructions from the human-machine interaction unit and real-time analysis results and decision instructions from the edge intelligent computing unit, and controlling the material storage module, slurry preparation module and grouting module according to the logic of the one-click grouting intelligent adaptive control method;

[0136] The storage module also includes a radar level gauge port 1, a feed port 2, a stainless steel storage bin 3, a vibrating motor 4, and a screw conveyor 5;

[0137] The pulping module also includes an electric stirring tank 6, a weighing sensor 7, an electromagnetic flow meter 8, an electric control ball valve 9, a water source 10, and a self-cleaning pipeline 11.

[0138] The grouting module also includes a unified hydraulic system 12, a grouting pump 13, a pressure transmitter 14, and an electromagnetic flow sensor 15;

[0139] The monitoring module also includes a grouting target area 16, a high-definition infrared network camera 17, and an edge intelligent computing unit 18;

[0140] This embodiment offers several advantages. By highly integrating the dispersed core physical components of material storage, slurry preparation, grouting, monitoring, and control into a single explosion-proof mobile platform and unifying hydraulic power, it completely solves the problems of discreteness, difficulty in movement, and large space occupation, representing a systematic integrated innovation. Deploying high-performance edge computing units in the harsh underground environment enables millisecond-level fusion analysis and real-time decision-making on multi-source heterogeneous data (level, weight, flow rate, pressure, high-definition video), replacing traditional manual judgment and cloud latency, providing the technical foundation for one-click intelligent operation. Intelligent identification of abnormal operating conditions includes: over-diffusion using Kalman filtering to improve early and accurate identification of hidden leakage channels; injection failure using first-order derivative + LSTM time-series modeling, leveraging historical data to learn complex patterns, significantly improving recognition accuracy and reducing false stops; slurry leakage / runaway using an enhanced underground dataset + CNN model + online incremental learning to construct a highly robust visual recognition system adapted to harsh underground environments (dust, low light, water mist), capable of continuous evolution and adaptation to changes; and a full-process adaptive closed-loop control strategy for full-process automation. From startup, feeding, slurry preparation, grouting, anomaly handling, and cleaning, the entire process is automated with a closed loop, truly enabling "one-click" operation. Super-diffusion adaptive regulation: Based on precise calculation of remaining slurry, it intelligently triggers a water-cement ratio reduction strategy and automatically executes subsequent processes, representing an innovative method for dynamically optimizing grouting parameters. Intelligent self-cleaning: It automatically triggers pipeline cleaning for situations such as failure to grout or grouting completion, improving equipment reliability, reducing manual maintenance, and providing precise audible and visual alarms and video positioning for necessary manual intervention stages (material replenishment, sealing leaks), optimizing human-machine collaboration efficiency.

[0141] Example 2

[0142] Please see Figure 2 As shown, for parts not described in detail in this embodiment, please refer to the description in Embodiment 1. An integrated intelligent one-click grouting control method for underground coal mines is provided, the method comprising:

[0143] S1: Parameter setting and startup; This step specifically includes inputting the necessary grouting design parameters and thresholds through the human-machine interaction unit; After the operator confirms, press the "one-click start" button.

[0144] S2: Intelligent feeding; This step specifically includes the decision execution unit starting the screw conveyor, while the calculation unit calculates the grouting powder quality in real time; when the "powder full" command is heard, the screw conveyor is stopped; handling abnormalities: if a "replenish material" command is received, the human-machine interaction unit issues an audible and visual alarm prompting manual replenishment; if an "empty silo" command is received, the human-machine interaction unit issues an emergency audible and visual alarm prompt, the decision execution unit immediately stops the screw conveyor of the storage module, and terminates the entire system operation.

[0145] It should be explained that manual material replenishment refers to the manual addition of grouting powder through the feed inlet at the top of the storage module.

[0146] S3: Intelligent Pulping; This step specifically includes the decision execution unit opening the electrically controlled ball valve of the pulping module's water pipe based on the target water volume calculated by the edge computing unit, injecting water into the mixing tank. Upon receiving the "water full" command, the electrically controlled ball valve of the pulping module's water pipe is closed.

[0147] S4: Automatic stirring; This step specifically includes the decision execution unit starting the electric stirring tank, making pulp according to the set stirring speed and stirring time, and turning off the electric stirring tank after completion.

[0148] S5: Intelligent grouting; This step specifically includes the decision-making and execution unit starting the electric grouting pump to deliver the grout to the grouting area.

[0149] If the "slurry replenishment" command is detected, the decision execution unit will execute the continuous slurry preparation process according to steps S2 to S4, and then seamlessly continue slurry injection after completion.

[0150] If a "cannot be injected" command is detected, the decision execution unit stops the electric grouting pump, automatically starts the self-cleaning process, and then terminates the grouting operation.

[0151] It should be explained that the self-cleaning process involves opening the ball valve of the self-cleaning pipeline and starting the grouting pump to clean the pipeline.

[0152] S6: Intelligent handling of over-diffusion; This step specifically includes, during the grouting process, if an "over-diffusion" command is detected, the decision-making execution unit stops the electric grouting pump and adjusts it according to the following grout thickening strategy:

[0153] Based on the current remaining mass of slurry in the mixing tank provided by the edge computing unit, accurately calculate the remaining powder mass in the tank;

[0154] Implement a strategy to reduce the water-cement ratio by 20%, with the target new water-cement ratio being 0.8 times the original water-cement ratio;

[0155] According to step S2, the decision execution unit precisely adds 25% of the remaining powder mass into the mixing tank;

[0156] Perform step S4 to prepare a thick slurry by stirring;

[0157] Perform step S5 to continue grouting with thick slurry;

[0158] This strategy intelligently adjusts the slurry properties, which can solve the problem of slurry over-diffusion in large fractures in the injection area.

[0159] S7: Intelligent Handling of Grout Leakage or Spillage; This step specifically includes the following: If a "grout leakage or spillage" command is detected during the grouting process, the decision execution unit pauses the electric grouting pump, and simultaneously, the human-machine interface unit issues an audible and visual alarm with precise location of the "grout leakage or spillage" via audio-visual equipment. At this time, manual intervention is required to seal the leak point. After sealing is completed, the operator confirms through the human-machine interface unit, and the system restarts grouting from step S5.

[0160] S8: Grouting completion and cleaning; This step specifically includes the termination of the process after the designed grouting volume or pressure stabilizes, triggered by the human-machine interaction unit or preset conditions, and the decision unit automatically executes the self-cleaning process.

[0161] The foregoing has only described certain exemplary embodiments of the present invention by way of illustration. Undoubtedly, those skilled in the art can modify the described embodiments in various ways without departing from the spirit and scope of the present invention. Therefore, the foregoing drawings and descriptions are illustrative in nature and should not be construed as limiting the scope of protection of the claims of the present invention.

Claims

1. An integrated intelligent one-key grouting system in a coal mine, characterized in that, The system comprises a grouting module, a monitoring module, an intelligent control module and an integrated mobile platform, wherein: The grouting module is used for monitoring and managing grouting equipment; The monitoring module is used for real-time monitoring of abnormal states; The intelligent control module comprises a man-machine interaction unit, an edge intelligent calculation unit and a decision execution unit; The edge intelligent calculation unit comprises: E1: millisecond-level edge calculation analysis is performed on real-time data from the storage module, the pulp preparation module, the grouting module and the monitoring module, and real-time identification and analysis of abnormal grouting working condition characteristics are performed, and specific intelligent analysis strategies include: E1.1: when the monitoring data is less than 15% of the total amount of powder in the storage bin, the edge intelligent calculation unit sends a replenishment instruction to the decision execution unit; when the monitoring data is less than 5% of the total amount of powder in the storage bin, the edge calculation unit sends an empty bin instruction to the decision execution unit; E1.2: when the grouting powder quality data is approximately equal to the standard powder quality, the edge calculation unit sends a "powder full" instruction to the decision execution unit; when the water quantity is approximately equal to the standard slurry water-cement ratio, the edge calculation unit sends a water quantity full instruction to the decision execution unit; when the slurry quality data is less than 10% of the standard slurry, the edge calculation unit sends a slurry supplement instruction to the decision execution unit and triggers an automatic replenishment and pulp preparation process; E1.3: edge calculation is performed on the output pressure and output flow in the output data set, which is used to identify abnormal states of slurry over-expansion and slurry injection failure; E1.31: slurry over-expansion identification includes: real-time filtering and state estimation of the output pressure and output flow based on the Kalman filtering algorithm, when the output pressure is less than 15% of the minimum output pressure and the output flow is greater than the maximum grouting flow, it is marked as slurry over-expansion, and an over-expansion execution instruction is sent to the decision execution unit through the edge calculation unit; E1.32: Slurry injection not into recognition includes: combining the first derivative and the LSTM long short-term memory recurrent neural network to recognize the time sequence pattern of the output pressure, the output flow and the time, When the output flow is greater than the preset threshold value and the output flow is less than 80% of the output flow, it is marked as slurry injection not into, and an injection not into execution instruction is sent to the decision execution unit through the edge computing unit. E1.4: edge calculation analysis is performed on the monitoring data, which is used to identify abnormal states of slurry leakage and slurry running; E1.41: a special CNN identification model for underground slurry leakage and running is constructed: a deep convolutional neural network-based slurry leakage and running identification model is deployed in the edge unit; E1.42: high-robustness slurry leakage and running image data set construction: the model training uses no less than 1000 strictly labeled real scene images underground, and the data set is subjected to intensive data enhancement, which is used to simulate extreme environments underground: adding different intensity Gaussian noise, multi-level low illumination, random transparency water mist occlusion; E1.43: model online evolution: when the on-site grouting system completes 500 grouting operations, new on-site images are automatically collected, the image data set is updated, the online incremental learning process is triggered, and the CNN model weight is updated; E1.44: slurry leakage and running identification warning: when the model identifies with high confidence that there is slurry leakage or slurry running in the video stream, it immediately sends a slurry leakage execution instruction or a slurry running execution instruction to the decision execution unit; The integrated mobile platform is used for integrating the storage module, the pulp preparation module, the grouting module, the monitoring module and the intelligent control module; The steps of monitoring and managing grouting equipment include: Q1: the grouting module comprises an explosion-proof electric grouting pump, a suction grouting pipeline, an outflow pipeline and a self-cleaning pipeline; Q2: The slurry suction pipeline connects the slurry stirring barrel and the grouting pump; Q3: The slurry outlet pipeline connects the grouting pump and the grouting area, and the anti-explosion pressure transmitter and the anti-explosion electromagnetic flow sensor are arranged in the pipeline to collect and monitor the output pressure and output flow of the anti-explosion electric grouting pump, obtain the output data set, and transmit the output data set to the edge intelligent computing unit in real time; Q4: One end of the self-cleaning pipeline is connected with the slurry suction pipeline through a three-way pipe, and the other end is arranged in the clean water barrel, and a self-cleaning pipeline electric control ball valve is arranged in the pipeline; Control logic: When the grouting is completed or a specific abnormal instruction is received, the decision execution unit automatically closes the slurry suction pipeline, opens the self-cleaning pipeline ball valve, starts the anti-explosion electric grouting pump to pump clean water, and automatically cleans the slurry suction pipeline, the anti-explosion electric grouting pump and the slurry outlet pipeline.

2. The integrated intelligent one-key grouting system for underground coal mine according to claim 1, characterized in that, The system further comprises a material storage module and a slurry preparation module, wherein: The material storage module is configured to detect the remaining amount of the stored powder material; The slurry preparation module is configured to collect a slurry preparation data set, which includes material quality data, grouting powder quality data, slurry quality data, and water injection quantity data.

3. The integrated intelligent one-key grouting system for underground coal mine according to claim 2, characterized in that, The method for detecting the residual amount of the stored powder includes collecting the residual amount of the stored powder in the designated storage bin in real time based on a high-frequency radar level gauge to obtain monitoring data and transmitting the monitoring data to an edge intelligent computing unit.

4. The integrated intelligent one-key grouting system for underground coal mine according to claim 2, characterized in that, The method for collecting the slurry preparation data set comprises: collecting the material quality value in the designated stirring barrel by using a high-precision anti-explosion weighing sensor to obtain the material quality data; The high-precision explosion-proof weighing sensor is combined with the start-stop state of the screw conveyor to collect the mass value of the grouting powder added in the specified stirring barrel, so that the mass data of the grouting powder is obtained ; Through high-precision electromagnetic flowmeter, the water flow value at the outlet of the designated water pipe is collected to obtain the injected water flow data ; The high-precision explosion-proof weighing sensor is combined with the starting state of the electric grouting pump to collect the slurry mass value in the specified stirring barrel to obtain slurry mass data .

5. The integrated intelligent one-key grouting system for underground coal mine according to claim 1, characterized in that, The real-time monitoring of the abnormal state comprises monitoring the surface of the grouting area by using an intrinsically safe high-definition infrared network camera to perform 360° real-time video monitoring, and outputting the monitoring data to the edge intelligent computing unit, wherein the monitoring data is used to identify the slurry leakage and slurry running states.

6. The integrated intelligent one-key grouting system for underground coal mine according to claim 1, characterized in that, The human-computer interaction unit comprises: W1: providing a one-key start button and a manual intervention operation portal; W2: inputting grouting design parameters; W3: displaying all monitoring parameters.

7. The integrated intelligent one-key grouting system for underground coal mine according to claim 1, characterized in that: The decision execution unit receives the instructions from the human-computer interaction unit, the real-time analysis results and decision instructions from the edge intelligent computing unit, and controls the material storage module, the slurry preparation module and the grouting module according to the logic of the one-key grouting intelligent adaptive control method.

8. The integrated intelligent one-key grouting control method in the coal mine, according to any one of claims 1-7, wherein the integrated intelligent one-key grouting system in the coal mine is implemented, characterized in that, The method comprises the following working steps: S1: parameter setting and starting; S2: intelligent feeding; S3: intelligent slurry preparation; S4: automatic stirring; S5: intelligent grouting; S6: intelligent treatment of over-diffusion; S7: intelligent treatment of slurry leakage or slurry running; S8: grouting completion and cleaning.

Images