Self-adaptive gas extraction accurate regulation and control system based on multi-source information fusion

Abstract

The invention discloses a self-adaptive gas extraction accurate regulation and control system based on multi-source information fusion, and the system improves the extraction efficiency: by responding to the trend change, the extraction is increased in advance before the gas emission is increased, the average extraction concentration can be improved by 10-25%, and the equipment safety is guaranteed; equipment overload and damage can be avoided from a control source, the service life is prolonged, energy is saved, consumption is reduced, the system can be automatically and smoothly switched between an efficient mode and an energy-saving mode, comprehensive energy consumption can be reduced by 15-30%, the adaptability is high, parameters of the control system can be automatically adjusted along with changes of working conditions, manual intervention is reduced, and the adaptability to different mine conditions is higher.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of coal mine gas extraction, and particularly relates to a self-adaptive gas extraction precision regulation and control system based on multi-source information fusion. BACKGROUND

[0002] The current gas extraction system regulation and control mode is extensive, and mainly has three major pain points: Ignoring gas emission dynamics: the amount of coal seam gas emission is dynamically changing, but the existing system cannot predict its trend and can only respond passively, leading to lagging regulation.

[0003] Ignoring the running state of the equipment: the health status (such as vibration, temperature) of key equipment such as extraction pumps and motors is not included in the control logic, and cannot make compensation adjustments in advance when the efficiency of the equipment decreases, which has safety hazards and energy waste.

[0004] Single and rigid control strategy: mainly using fixed parameter PID control or manual adjustment, which cannot respond to the changes of gas emission, equipment state, pipe network pressure and other multi-dimensional changes at the same time, and has poor adaptability. SUMMARY

[0005] The purpose of the present application is to provide a self-adaptive gas extraction precision regulation and control system based on multi-source information fusion to solve the problems raised in the background.

[0006] To achieve the above purpose, the present application provides the following technical scheme: a self-adaptive gas extraction precision regulation and control system based on multi-source information fusion, comprising: A perception layer comprising a plurality of sensors for collecting multi-source data of the underground gas extraction system; A control layer in communication connection with the perception layer, comprising a programmable logic controller (PLC) for receiving and processing the multi-source data, running a control algorithm and generating a control instruction; An execution layer in communication connection with the control layer, comprising an adjustment mechanism controlled by the control instruction for changing the running state of the gas extraction system; A monitoring layer in communication connection with the control layer for realizing remote monitoring and management of the system; Wherein, the perception layer, control layer, execution layer and monitoring layer constitute a closed-loop control system through wired connection mode.

[0007] Preferably, the perception layer comprises: a laser methane sensor installed on each extraction branch pipeline for monitoring the gas concentration C; an ultrasonic flow meter installed on each extraction branch pipeline for monitoring the gas instantaneous flow Q and the cumulative flow; a vibration acceleration sensor installed on the motor of the extraction pump for monitoring the vibration acceleration V; a temperature sensor embedded in the winding of the motor of the extraction pump for monitoring the winding temperature T; and a pressure sensor installed on the main pipeline of the extraction system for monitoring the total negative pressure P of the system.

[0008] Preferably, the PLC of the control layer is configured to execute the following algorithms: an information fusion algorithm for calculating the trend weight value W_t of each extraction branch, the calculation formula being W_t=C×Q+k×dQ / dt, wherein k is a gain coefficient and dQ / dt is the flow rate of change; a device health diagnosis for comparing the vibration V and the temperature T with preset safety thresholds, and triggering a system protection mode if the thresholds are exceeded; and a self-adaptive PID control algorithm for dynamically adjusting the parameters (Kp, Ki, Kd) of the PID controller based on the trend weight value W_t and the device health status. The control layer is a multi-objective optimization control system that generates control instructions based on the trend weight value W_t and the device health status as well as the set value of the main pipeline pressure P.

[0009] Preferably, the execution layer comprises: an electric regulating valve installed on each extraction branch pipeline for receiving the control instructions of the PLC and adjusting the opening degree of the branch pipeline; and a frequency converter of the extraction pump connected with the motor of the extraction pump for receiving the control instructions of the PLC and adjusting the rotation speed n of the extraction pump.

[0010] Preferably, the control instructions generated by the control layer comprise: a first control instruction output to the electric regulating valve for preferentially increasing the valve opening degree of a high-weight branch according to the trend weight value W_t of each branch; and a second control instruction output to the frequency converter of the extraction pump for adjusting the rotation speed n of the extraction pump to stabilize the main pipeline pressure P at a preset value.

[0011] Preferably, the installation positions of the sensors of the perception layer follow: on the extraction branch pipeline, the laser methane sensor, the ultrasonic flow meter and the electric regulating valve are installed in sequence along the airflow direction; the vibration acceleration sensor is installed vertically on the bearing seat of the non-driving end of the motor of the extraction pump; and the pressure sensor is installed on the main pipeline after the convergence of each extraction branch and located 1-2 meters before the inlet of the extraction pump.

[0012] Preferably, the communication between the perception layer and the control layer is performed through the RS485 bus using the MODBUS-RTU protocol; and the communication between the control layer and the monitoring layer is performed through the industrial Ethernet.

[0013] Technical effects and advantages of the present application: 1. Improve extraction efficiency: by responding to trend changes, increase extraction in advance before gas emission increases, average extraction concentration can be increased by 10-25%.

[0014] 2. Ensure equipment safety: use equipment status as control input to avoid equipment overload and damage from the control source, prolong the service life.

[0015] 3. Energy saving: the system can automatically switch between "high efficiency mode" and "energy saving mode", and the comprehensive energy consumption can be reduced by 15-30%.

[0016] 4. Strong adaptability: control system parameters can be self-adjusted with changes in working conditions, reducing manual intervention and adapting to different mine conditions. BRIEF DESCRIPTION OF DRAWINGS

[0017] Figure 1 The system architecture of the present application is shown. DETAILED DESCRIPTION

[0018] The technical solutions in the embodiments of the present application will be described clearly and completely below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor are within the scope of protection of the present application.

[0019] The present application provides a self-adaptive gas extraction precision control system based on multi-source information fusion as shown in Figure 1 The system of the present application adopts a hierarchical distributed architecture and is mainly composed of a perception layer, a control layer, an execution layer and a monitoring layer. The working process is as follows: the perception layer collects underground multi-source data through various sensors, which are transmitted to the PLC controller of the control layer through the communication bus; the PLC controller built-in special algorithm analyzes and makes decisions on the data and generates control instructions sent to the execution layer; the adjustment mechanism of the execution layer changes the running state of the extraction system; the monitoring layer is responsible for remote monitoring and management of the whole system. The layers are connected by wired mode to form a complete closed-loop control system. "High efficiency mode" refers to when the gas emission potential is large, the extraction concentration and flow rate are given priority to, and the energy consumption is allowed to be slightly higher; "energy saving mode" refers to when the gas emission is stable or small, the main pump speed is appropriately reduced and the valve is adjusted, and the system is operated with the goal of energy saving. The mode switching can be triggered by the high and low of ΣW_t (total trend weight). The system architecture is shown in Figure 1 .

[0020] Perception layer: Laser methane sensor: usually cylindrical or cuboid explosion-proof housing, with an optical window at the front. Installed on each extraction branch pipeline through flange or threaded interface, as close as possible to the extraction borehole, used for high-precision, continuous monitoring of the volume concentration C of gas in the pipeline.

[0021] Ultrasonic flow meter: can be divided into clamp-on type (two half moon clamps) or pipe section type (a section of flange connected short pipe). Installed on the branch pipeline behind the laser methane sensor, ensuring sufficient straight pipe sections before and after to ensure measurement accuracy, used to monitor the instantaneous flow Q and cumulative flow of gas.

[0022] Vibration acceleration sensor: small cylindrical or square, with magnetic base or screw fixation. Vertically installed on the bearing seat of the non-drive end of the extraction pump motor, used to monitor the effective value V of the motor's vibration acceleration, reflecting the mechanical health status of the equipment.

[0023] Temperature sensor (PT100): probe type, needs to be embedded. Embedded directly in the three-phase winding of the motor, with a lead-out wire, used to directly and accurately monitor the winding temperature T of the motor during operation.

[0024] Pressure sensor: usually cylindrical structure with threaded interface. Installed on the main pipeline after the convergence of each extraction branch, and located 1-2 meters before the extraction pump inlet, used to monitor the total negative pressure P of the extraction system.

[0025] Control layer: Mine intrinsically safe PLC controller: standard industrial guide rail installed rectangular cabinet, with explosion-proof certification. Integrates CPU module, digital / analog input / output module, communication module (RS485, Ethernet) inside. It is the "brain" of the system, installed in the underground substation or dedicated chamber. Its core function is to run multi-source information fusion algorithm and adaptive PID control algorithm.

[0026] Execution layer: Electric regulating valve: composed of valve body (circular flange interface) and electric actuator (square or cylindrical). Installed at the end of each extraction branch pipeline before merging into the main pipeline. Receives PLC instructions, adjusts the extraction flow of the branch by changing the opening of the valve core.

[0027] Extraction pump frequency converter: large vertical cabinet structure, installed in the extraction pump distribution room. Connected with the main extraction pump motor through power cable. Receives 4-20mA analog signal from PLC, steplessly adjusts the speed n of the extraction pump motor by changing the output frequency, thereby changing the total extraction negative pressure and flow.

[0028] Monitoring layer: Ground monitoring center (HMI / IPC): Located in the ground control room. Usually a desktop workstation and a large screen display, running configuration software, providing a graphical human-machine interface (HMI) for remote monitoring of all data, setting parameters, viewing alarms and historical curves.

[0029] 2. Mutual installation position and connection relationship Installation position: The sensor installation follows the principle of "accurate measuring point and easy maintenance". The branch sensor is installed in sequence according to the airflow direction: laser methane sensor → ultrasonic flowmeter → electric regulating valve. The pressure sensor is located at the core measuring point of the main pipeline. The equipment state sensor (vibration, temperature) is located at the key position of the equipment (bearing seat, winding).

[0030] Connection relationship: Electrical connection: All sensors are connected to the corresponding I / O module of the PLC through shielded cables.

[0031] Communication connection: Various sensors exchange data with the PLC controller through RS485 bus using MODBUS-RTU communication protocol. The PLC controller communicates with the ground monitoring center at high speed through industrial Ethernet.

[0032] Control connection: The analog output module of the PLC is connected to the actuator of each branch electric regulating valve and the control terminal of the extraction pump frequency converter through 4-20mA current signal line.

[0033] Power connection: The extraction pump frequency converter is connected to the main circuit through power cable to control the power supply of the extraction pump motor, realizing stepless adjustment of the rotation speed of the extraction pump.

[0034] 3. Working process After the system is powered on, it enters the automatic running state: Data acquisition: All sensors in the perception layer synchronously collect concentration C, flow Q, vibration V, temperature T, pressure P and other data at the set frequency (such as 1Hz), and upload them to the PLC in real time through RS485 bus.

[0035] Information fusion and intelligent decision-making: The PLC first calculates the "trend weight value" W_t=C×Q+k×dQ / dt of each branch. Where C is the gas concentration, Q is the gas flow, K is the gain coefficient, and dQ / dt is the flow rate. This value reflects the immediate output capacity and growth trend of the branch.

[0036] At the same time, the PLC judges the health status of the equipment. If the vibration V or temperature T exceeds the safety threshold, the protection mode is triggered.

[0037] The core adaptive algorithm of the PLC dynamically adjusts the parameters (Kp, Ki, Kd) of the PID controller according to the trend weight total value ΣW_t and the device health status, so as to achieve the optimal response to different working conditions.

[0038] Control output: The PLC calculates according to the optimized PID algorithm and outputs two control signals: One is a 4-20mA signal to each branch electric regulating valve to control its opening and realize the key extraction of the high potential branch.

[0039] The other is a 4-20mA signal to the extraction pump frequency converter to control its frequency output and adjust the extraction pump speed, so as to stabilize the main pipeline pressure P at the optimal set value.

[0040] Remote monitoring: All real-time data, device status and control instructions are uploaded to the ground monitoring center through industrial Ethernet to realize remote centralized monitoring, fault alarm and historical data tracing.

[0041] 4. Working example Taking the gradual increase of gas emission of a branch as an example: Perception: The laser methane sensor and ultrasonic flowmeter on the branch detect that the concentration C and flow Q continue to rise (dQ / dt>0).

[0042] Decision: The PLC calculates that the W_t value of the branch increases significantly. The adaptive algorithm judges that the system needs to increase the extraction capacity, so it automatically increases the PID parameters and prepares to issue the "increase extraction" instruction.

[0043] Execution: The PLC synchronously outputs two instructions: ① fine-tune the electric regulating valve of the branch to increase its opening; ② send a signal to the extraction pump frequency converter to appropriately increase the extraction pump speed to maintain the stability of the total pipe negative pressure.

[0044] Result: The system automatically allocates more extraction capacity to the branch with increased gas emission without human intervention, thereby grasping the extraction opportunity and improving the extraction efficiency while maintaining the stability of the system total pressure. Throughout the process, the device status data is always monitored to ensure safe operation.

[0045] The key point of the invention is a structure of a gas extraction control system, characterized in that it is composed of a trend perception unit (laser methane sensor, ultrasonic flowmeter), a device status perception unit (vibration sensor, temperature sensor) and an execution unit (electric regulating valve, frequency converter) connected to a mine-used intrinsically safe PLC controller.

[0046] The system as claimed in claim 1, characterized in that the PLC controller is embedded with a trend weight calculation algorithm (W_t = C × Q + k × dQ / dt) and an adaptive PID control algorithm based on multi-source information (ΣW_t, equipment vibration V, temperature T).

[0047] Finally, it should be noted that the above only for the preferred embodiments of the present application, and is not intended to limit the application, although the foregoing detailed description of the application has been made with reference to the foregoing embodiments, for those skilled in the art, it still can be modified, or part of the technical features of the equivalent replacement, within the spirit and principles of the present application, any modification, equivalent replacement, improvement, etc., should be included within the scope of the present application.

Claims

1. An adaptive gas extraction precision control system based on multi-source information fusion, characterized in that, include: The sensing layer includes multiple sensors used to collect multi-source data from the underground gas extraction system. The control layer, which is communicatively connected to the perception layer, includes a programmable logic controller for receiving and processing the multi-source data, running control algorithms, and generating control commands. The execution layer, which is communicatively connected to the control layer, includes an adjustment mechanism controlled by the control commands for changing the operating state of the gas extraction system; The monitoring layer, which communicates with the control layer, is used to realize remote monitoring and management of the system; The perception layer, control layer, execution layer, and monitoring layer are connected by wires to form a closed-loop control system.

2. The adaptive gas extraction precision control system based on multi-source information fusion according to claim 1, characterized in that, The sensing layer includes: laser methane sensors installed on each extraction branch pipeline for monitoring methane concentration C; ultrasonic flow meters installed on each extraction branch pipeline for monitoring instantaneous methane flow rate Q and cumulative flow rate; vibration acceleration sensors installed on the extraction pump motor for monitoring vibration acceleration V; temperature sensors embedded in the extraction pump motor windings for monitoring winding temperature T; and pressure sensors installed on the main pipeline of the extraction system for monitoring the total negative pressure P of the system.

3. The adaptive gas extraction precision control system based on multi-source information fusion according to claim 1, characterized in that, The PLC of the control layer is configured to execute the following algorithms: Information fusion algorithm: calculate the trend weight value W_t for each extraction branch, with the formula: W_t=C×Q+k×dQ / dt, where k is the gain coefficient and dQ / dt is the flow rate change rate; Equipment health diagnosis: compare vibration V and temperature T with preset safety thresholds, and trigger the system protection mode if they exceed the limits; Adaptive PID control algorithm: dynamically adjust the parameters of the PID controller based on the trend weight value W_t and the equipment health status.

4. The adaptive gas extraction precision control system based on multi-source information fusion according to claim 1, characterized in that, The execution layer includes: an electric regulating valve installed on each extraction branch pipeline, used to receive control commands from the PLC and adjust the opening of the branch pipeline; and an extraction pump frequency converter connected to the main extraction pump motor, used to receive control commands from the PLC and adjust the extraction pump speed n.

5. The adaptive gas extraction precision control system based on multi-source information fusion according to claim 1, characterized in that, The control commands generated by the control layer include: a first control command, output to the electric regulating valve, used to prioritize increasing the valve opening of the high-weight branch according to the trend weight value W_t of each branch; and a second control command, output to the pump frequency converter, used to adjust the pump speed n and stabilize the main pipeline pressure P at a preset value.

6. The adaptive gas extraction precision control system based on multi-source information fusion according to claim 1, characterized in that, The sensor installation positions of the sensing layer sensors are as follows: on the extraction branch pipeline, the laser methane sensor, ultrasonic flow meter and electric regulating valve are installed sequentially along the airflow direction; the vibration acceleration sensor is vertically installed on the bearing seat of the non-drive end of the extraction pump motor; the pressure sensor is installed on the main pipeline after the convergence of each extraction branch and is located 1-2 meters in front of the extraction pump inlet.

7. The adaptive gas extraction precision control system based on multi-source information fusion according to claim 1, characterized in that, The sensing layer and the control layer communicate via an RS485 bus using the MODBUS-RTU protocol; the control layer and the monitoring layer communicate via an industrial Ethernet network.

Images