Pneumatic down-the-hole hammer automatic control system based on airflow dynamic adjustment

Abstract

The invention provides a pneumatic down-the-hole hammer automatic control system based on airflow dynamic adjustment, comprising: a sensor module for collecting monitoring data; the actuator module is used for controlling the flow and pressure of compressed air and adjusting the propelling speed and pressure of the drill rod; the control and processing module is used for carrying out data processing and intelligent control by utilizing an embedded controller and a control algorithm; the airflow dynamic adjusting module is used for constructing a geological recognition model, recognizing rock hardness and structure changes and automatically adjusting impact energy and drilling efficiency; the fault prediction module is used for constructing a fault prediction model and carrying out fault prediction and alarm; the energy consumption optimization module is used for constructing an energy consumption model, presetting an optimization target, designing an optimization genetic algorithm and calculating an optimal airflow parameter; and the man-machine interaction module is used for data display, state alarm and parameter adjustment. The drilling process can be intelligently controlled, the drilling efficiency is improved, the equipment failure rate is reduced, energy can be saved, and the system adapts to complex geological conditions.

Description

Technical Field

[0001] The invention relates to the technical field of automatic control of pneumatic down-the-hole hammers, and in particular to an automatic control system of a pneumatic down-the-hole hammer based on dynamic airflow regulation. Background Art

[0002] Pneumatic down-the-hole hammer is a kind of drilling equipment widely used in mining, geological exploration and engineering construction. Its working principle is to drive the hammer body to perform high-frequency impact through compressed air, thereby breaking the rock and drilling. The automatic control system of pneumatic down-the-hole hammer refers to the real-time monitoring and adjustment of the operating parameters of the pneumatic down-the-hole hammer (such as impact frequency, air pressure, drilling speed, etc.) through automation technology to improve drilling efficiency, extend equipment life and reduce manual intervention.

[0003] The automatic control system of pneumatic down-the-hole hammer can realize the automatic control of the drilling process through data collection, analysis and calculation. Although the existing automatic control system of pneumatic down-the-hole hammer has improved the drilling efficiency and automation level to a certain extent, it still has the following defects: 1) Insufficient adaptability: The existing system has poor adaptability to complex geological conditions (such as changes in rock hardness, crack development, etc.), and it is difficult to adjust parameters in real time to cope with the changing drilling environment. 2) Low data utilization: Although the system can collect a large amount of data, the in-depth analysis and utilization of the data are insufficient, and the potential laws in the data cannot be fully explored. 3) Weak fault prediction ability: The existing system has limited health status monitoring and fault prediction capabilities for equipment, and often performs maintenance only after the equipment fails, resulting in long downtime and high maintenance costs. 4) High energy consumption: The existing system fails to manage the use of compressed air in a refined manner, resulting in high energy consumption. Summary of the invention

[0004] In order to overcome the shortcomings of the prior art, the purpose of the present invention is to provide a pneumatic down-the-hole hammer automatic control system based on dynamic airflow regulation, which can intelligently control the drilling process, improve drilling efficiency, reduce equipment failure rate, save energy, and adapt to complex geological conditions.

[0005] To achieve the above object, the present invention provides the following solution: an automatic control system for a pneumatic down-the-hole hammer based on dynamic airflow regulation, comprising:

[0006] The sensor module is used to collect relevant data during the drilling process using a variety of sensors to obtain monitoring data;

[0007] An actuator module, used to control the flow and pressure of compressed air using an electronically controlled proportional valve, and to adjust the propulsion speed and pressure of the drill pipe using a propulsion system controller;

[0008] Control and processing module, used to perform real-time data processing and intelligent control of equipment using embedded controllers and control algorithms;

[0009] An airflow dynamic adjustment module, for calculating the current impact energy and drilling efficiency using the monitoring data, and constructing a geological recognition model representing the relationship between drilling parameters and geological conditions, using the geological recognition model to identify rock hardness and structural changes, and automatically adjusting the impact energy and drilling efficiency according to the recognition results;

[0010] A fault prediction module is used to build and train a fault prediction model based on machine learning and big data analysis technology, and use the fault prediction model to predict and alarm equipment faults;

[0011] The energy consumption optimization module is used to construct a relationship model between airflow pressure, flow rate and energy consumption, obtain an energy consumption model, and based on the energy consumption model, preset the minimum energy consumption as the optimization target, and perform iterative calculation in combination with the designed optimization genetic algorithm to obtain the optimal airflow parameters;

[0012] Human-computer interaction module, used to display real-time data, status alarm and parameter adjustment using human-computer interaction interface;

[0013] Wherein, the sensor module, the actuator module, the control and processing module, the airflow dynamic adjustment module, the fault prediction module, the energy consumption optimization module and the human-computer interaction module are interconnected.

[0014] Optionally, the multiple sensors include a pressure sensor for monitoring the air supply pressure and the actual working pressure, a flow sensor for monitoring the real-time flow of the airflow, a vibration sensor for real-time monitoring the impact frequency and vibration amplitude, a temperature sensor for detecting temperature changes of the equipment, and a drilling parameter sensor for monitoring mechanical parameters during the drilling process.

[0015] Optionally, the actuator module includes:

[0016] The proportional valve setting unit is used to select the electric control proportional valve, and install a pressure sensor and a flow sensor at the input end and the output end of the electric control proportional valve respectively; wherein the flow range of the electric control proportional valve is 0.1-10m 3 / min, the pressure sensor accuracy is ±0.1%, and the flow sensor accuracy is ±0.5%;

[0017] an airflow control unit, configured to calculate a first target opening by using a PID control algorithm based on the electronically controlled proportional valve, calculate a first actual opening according to the monitored pressure and flow, compare and calculate the first target opening with the first actual opening to obtain a first opening deviation, and adjust the opening of the electronically controlled proportional valve according to the first opening deviation, the vibration frequency and the propulsion force to obtain a first optimal opening;

[0018] A propulsion setting unit, which is used to equip the hydraulic cylinder with an electronically controlled hydraulic valve, a force sensor and a displacement sensor to realize control, propulsion force monitoring, propulsion speed monitoring and recommended displacement monitoring of the hydraulic cylinder;

[0019] A propulsion control unit is used to calculate a second target opening based on the hydraulic cylinder using a fuzzy control algorithm, calculate a second actual opening according to the monitored propulsion force and propulsion speed, compare and calculate the second target opening with the second actual opening to obtain a second opening deviation, and adjust the opening of the hydraulic cylinder according to the second opening deviation, vibration frequency and impact efficiency to obtain a second optimal opening.

[0020] Optionally, the control and processing module includes:

[0021] An embedded control unit, used to initialize a pre-selected processor, and based on the processor, equip multiple peripheral interfaces, internal Flash memory and external memory, and deploy a lightweight real-time operating system to create tasks and run algorithms, and analyze and control tasks in combination with a priority scheduling mechanism and debugging tools; wherein the tasks include data acquisition tasks, control tasks, communication tasks, and data storage tasks;

[0022] ADC configuration unit, used to configure the sampling rate, resolution and number of channels of the ADC, and introduce direct memory access technology in the ADC;

[0023] The data acquisition and storage unit is used to collect sensor data in real time using ADC, eliminate noise interference of the sensor data using a digital filtering algorithm, and then store the filtered data.

[0024] The communication unit is used to select a standard communication protocol and perform wireless communication via a Wi-Fi communication mode, a LoRa communication mode, or a 5G communication mode.

[0025] Optionally, the airflow dynamic adjustment module includes:

[0026] Real-time calculation unit, used to preset data collection frequency and calculate current impact energy and drilling efficiency based on vibration, pressure and flow data;

[0027] A model building unit, for using a machine learning algorithm to train a model through historical data related to geological conditions during the drilling process, and building a geological identification model representing the relationship between drilling parameters and geological conditions;

[0028] A geological identification unit is used to use the geological identification model to identify the rock hardness according to the real-time data of vibration frequency, amplitude and propulsion force through a fuzzy logic algorithm, perform spectrum analysis on the vibration signal through fast Fourier transform, extract the crushing characteristics, and identify the rock crushing situation;

[0029] The airflow adjustment unit uses the PID control algorithm to perform closed-loop control and dynamic adjustment of air pressure and flow according to the geological identification results and the preset control targets;

[0030] The correction and optimization unit monitors the air pressure, flow and drilling efficiency in real time, compares the actual value with the target value to obtain the airflow deviation, corrects the airflow parameters according to the airflow deviation, and monitors in real time whether there are abnormal fluctuations in the air pressure and flow. If so, the alarm mechanism is automatically triggered.

[0031] Optionally, the calculation formula of the impact energy is:

[0032] v=2πfA,

[0033] Among them, v is the impact velocity, f is the impact frequency, A is the impact amplitude, E is the impact energy, and m is the mass of the hammer;

[0034] The calculation formula of the drilling efficiency is:

[0035] P=Q·ΔP,

[0036] Among them, P is the airflow power per unit time, η is the drilling efficiency, Q is the airflow rate, ΔP is the airflow pressure difference, and L is the drilling depth per unit time;

[0037] The expression of the PID control algorithm is:

[0038]

[0039] Among them, u(t) is the control output of the proportional valve opening, e(t) is the current error of air pressure or flow, K p , K i , K d These are PID parameters.

[0040] Optionally, the fault prediction module includes:

[0041] A parameter acquisition unit, used to integrate the vibration data, temperature data and pressure data in the monitoring data, synchronize the timestamp and clean the integrated data, and obtain relevant parameters for fault prediction;

[0042] A feature extraction unit, used to extract vibration features, temperature features and pressure features from the fault prediction related parameters, and integrate the extracted features into a low-dimensional feature vector using feature fusion technology to reduce redundant information;

[0043] A model training unit, used for labeling and dividing the low-dimensional feature vector according to the historical fault data, and then inputting the low-dimensional feature vector into the selected LSTM network for model training, and introducing a Softmax function into the output layer of the LSTM network to obtain a fault prediction model;

[0044] The fault prediction unit uses a variety of sensors to collect real-time vibration parameters, temperature parameters and pressure parameters, and inputs the real-time parameters into the fault prediction model, outputs the fault probability and classifies the current state, generates a fault diagnosis report based on the output results, and triggers an alarm mechanism.

[0045] Optionally, the energy consumption optimization module includes:

[0046] An energy consumption model construction unit is used to integrate the airflow pressure, airflow flow, drilling efficiency and energy consumption in the monitoring data to obtain energy consumption related parameters, and to construct a relationship model between airflow pressure, flow and energy consumption according to the energy consumption related parameters to obtain an energy consumption model; wherein the energy consumption model is fitted by multivariate linear regression or neural network;

[0047] An optimization constraint unit, used for setting the minimization of energy consumption as an optimization target based on the energy consumption model, and setting drilling efficiency constraint conditions, equipment safety constraint conditions and geological constraint conditions;

[0048] An optimization algorithm design unit, used for designing an optimization genetic algorithm, inputting the energy consumption model and constraint conditions into the optimization genetic algorithm, and solving the optimal airflow parameters;

[0049] The real-time optimization unit is used to input real-time data into the optimization genetic algorithm and adjust the optimization target and constraint conditions according to the geological conditions identified in real time.

[0050] Optionally, the mathematical expression of the energy consumption model is:

[0051] E=f(P,Q)

[0052] Among them, E is energy consumption, P is airflow pressure, Q is airflow flow, and f is energy consumption model function;

[0053] The mathematical expression of the drilling efficiency constraint condition is:

[0054] η≥η min

[0055] Among them, η min For the lowest drilling efficiency;

[0056] The mathematical expression of the equipment safety constraint condition is:

[0057] P min≤P≤P max , Q min ≤Q≤Q max

[0058] Among them, P min is the minimum air flow pressure, P max is the maximum airflow pressure, Q min is the minimum air flow rate, Q max is the maximum air flow rate.

[0059] Optionally, the design process of the optimization genetic algorithm is:

[0060] S1. Randomly generate a set of initial solutions of airflow parameter combinations as a population, and each individual in the population represents an airflow parameter combination;

[0061] S2. Define the fitness function as the inverse of the objective function; wherein the expression of the fitness function is E is energy consumption;

[0062] S3, select individuals from the population according to their fitness values, and give priority to retaining individuals with high fitness;

[0063] S4, randomly exchange some parameters of two individuals to generate new individuals, complete the crossover operation, randomly change a certain parameter of the individual to increase population diversity, and complete the mutation operation;

[0064] S5. Repeat S3-S4 until the fitness value of the population no longer increases significantly or reaches the maximum number of iterations, completing the design of the optimization genetic algorithm.

[0065] The present invention discloses the following technical effects by providing an automatic control system for a pneumatic down-the-hole hammer based on dynamic airflow regulation:

[0066] 1. High level of intelligence: The present invention can run control algorithms (such as PID, adaptive control, fuzzy control, etc.) by designing an embedded controller to achieve precise control of airflow and propulsion, and can process sensor data in real time to ensure rapid response of the system. By carrying a lightweight real-time operating system (RTOS) as system software, multi-task scheduling can be achieved to ensure the real-time and stability of control tasks. The present invention realizes precise control, real-time data processing and remote monitoring of pneumatic down-the-hole hammers through the combination of software and hardware, thereby improving the intelligence level of the system.

[0067] 2. High adaptability: The present invention designs a dynamic airflow adjustment algorithm and utilizes fuzzy logic, spectrum analysis, adaptive PID control and other technologies. It can not only calculate the current impact energy and drilling efficiency, and identify changes in rock hardness and crushing during drilling, but also adjust the air pressure and flow in real time according to geological conditions (hard rock or soft rock), and correct the airflow parameters in real time to improve control accuracy and response speed.

[0068] 3. Strong fault diagnosis capability: The present invention can make full use of various data (multimodal data such as vibration, temperature, pressure, etc.), use deep learning algorithms (such as LSTM networks) to establish fault prediction models, learn the relationship between equipment operating status and faults, predict potential faults and provide diagnostic information, thereby improving the reliability and operating efficiency of the equipment.

[0069] 4. Minimization of energy consumption: By establishing an energy consumption model and designing an optimization genetic algorithm, the impact of airflow parameters on energy consumption can be quantified, so that the system can dynamically adjust airflow parameters and minimize energy consumption while meeting drilling efficiency and equipment safety.

[0070] The technical solution of the present invention is further described in detail below through the accompanying drawings and embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0071] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.

[0072] Figure 1 A schematic diagram of a system architecture provided by an embodiment of the present invention;

[0073] Figure 2 A schematic diagram of a dynamic airflow adjustment process according to an embodiment of the present invention;

[0074] Figure 3 A schematic diagram of a fault prediction process provided by an embodiment of the present invention;

[0075] Figure 4 A schematic diagram of the energy consumption optimization process provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0076] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0077] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the present invention is further described in detail below with reference to the accompanying drawings and specific embodiments.

[0078] like Figure 1 As shown, the present invention provides an automatic control system for a pneumatic down-the-hole hammer based on dynamic airflow regulation, comprising:

[0079] 1. Sensor module

[0080] It is used to collect relevant data in the drilling process using a variety of sensors to obtain monitoring data.

[0081] Pressure sensor (with high accuracy and fast response capability): installed on the gas source pipeline and hammer inlet to monitor the gas supply pressure and actual working pressure.

[0082] Flow sensor (supports two-way flow detection to prevent backflow): installed in the gas source pipeline to monitor the real-time flow of the gas flow.

[0083] Vibration sensor (identifies abnormal vibration and predicts equipment failure): installed on the hammer housing to monitor the impact frequency and vibration amplitude in real time.

[0084] Temperature sensor (high temperature alarm function to prevent damage due to overheating): installed in key parts (such as hammer and drill bit) to monitor temperature changes.

[0085] Drilling parameter sensors (precisely measure mechanical parameters during drilling): displacement sensors (monitor the displacement and speed of drill pipe advancement), pressure sensors (monitor the pressure of the drill pipe on the rock).

[0086] 2. Actuator module

[0087] It is used to control the flow and pressure of compressed air using an electric proportional valve, and to adjust the propulsion speed and pressure of the drill pipe using the propulsion system controller. The actuator module includes:

[0088] 2.1 Proportional valve setting unit

[0089] Select an electric proportional valve that supports 0-10V or 4-20mA control signal input. Install a pressure sensor and a flow sensor at the input and output ends of the electric proportional valve to monitor airflow parameters in real time.

[0090] The flow rate range of the electronically controlled proportional valve is 0.1-10m 3 / min, the pressure sensor accuracy is ±0.1%, and the flow sensor accuracy is ±0.5%.

[0091] 2.2 Airflow control unit

[0092] It is used to calculate a first target opening based on the electronically controlled proportional valve using a PID control algorithm, and calculate a first actual opening according to the monitored pressure and flow, compare and calculate the first target opening with the first actual opening to obtain a first opening deviation, and adjust the opening of the electronically controlled proportional valve according to the first opening deviation, vibration frequency and propulsion force to obtain a first optimal opening.

[0093] The PID control algorithm adjusts the opening of the proportional valve including:

[0094] Proportional control (P): Quick response to deviations in pressure and flow.

[0095] Integral control (I): eliminates long-term deviations and ensures stability.

[0096] Derivative control (D): Suppresses rapid fluctuations in pressure and flow.

[0097] PID parameters are optimized through experimental debugging or adaptive algorithm.

[0098] 2.3 Propulsion setting unit

[0099] It is used to equip the hydraulic cylinder with an electronically controlled hydraulic valve, a force sensor (installed on the piston rod of the hydraulic cylinder, accuracy requirement: ±0.1%) and a displacement sensor (accuracy requirement: ±0.5%), so as to realize the control, propulsion force monitoring, propulsion speed monitoring and recommended displacement monitoring of the hydraulic cylinder.

[0100] 2.4 Propulsion control unit

[0101] It is used to calculate a second target opening based on the hydraulic cylinder using a fuzzy control algorithm, calculate a second actual opening according to the monitored propulsion force and propulsion speed, compare and calculate the second target opening with the second actual opening to obtain a second opening deviation, adjust the opening of the hydraulic cylinder according to the second opening deviation, vibration frequency and impact efficiency, and obtain a second optimal opening.

[0102] Fuzzy rule example:

[0103] If the rock hardness is high, the propulsion force is increased and the propulsion speed is reduced.

[0104] If the rock hardness is low, reduce the propulsion force and increase the propulsion speed.

[0105] 3. Control and processing module

[0106] Used to perform real-time data processing and intelligent equipment control using embedded controllers and control algorithms.

[0107] The control and processing module includes:

[0108] 3.1 Embedded Control Unit

[0109] A high-performance ARM Cortex-M series (such as STM32H7) or DSP processor (such as TI TMS320F28379D) is selected and a pre-selected processor is initialized, which supports a variety of peripheral interfaces (I2C, SPI, UART, CAN, etc.) to connect sensors, actuators and communication units.

[0110] Equipped with internal Flash memory (storing control algorithms and system firmware) and external memory (such as SD card or eMMC, storing historical data and logs).

[0111] Deploy lightweight real-time operating systems (such as FreeRTOS and RT-Thread) as system software platforms to create tasks and run algorithms, and combine priority scheduling mechanisms and debugging tools to analyze and control tasks.

[0112] Tasks include data acquisition tasks (regularly collecting sensor data), control tasks (running control algorithms and outputting control signals), communication tasks (processing communications with the host computer or cloud platform), and data storage tasks (writing historical data into the memory). Among them, control tasks have the highest priority, data acquisition and communication tasks have medium priority, and data storage tasks have the lowest priority.

[0113] 3.2ADC Configuration Unit

[0114] It is used to configure the sampling rate (such as 1MSPS), resolution (such as 12 bits) and number of channels of the ADC, and introduce direct memory access technology in the ADC to store the collected data directly into the memory to reduce the CPU burden. Among them, the multi-channel function of the ADC collects sensor signals such as pressure, flow, and vibration in sequence.

[0115] 3.3 Data acquisition and storage unit

[0116] It is used to collect sensor data in real time using ADC, eliminate noise interference of sensor data using digital filtering algorithm, and then use external SD card or eMMC memory to store the filtered data.

[0117] 3.4 Communication Unit

[0118] Select standard communication protocol: Use MQTT protocol to realize two-way communication between device and cloud platform. Use Modbus protocol to realize communication between device and host computer.

[0119] Wireless communication: Wireless communication is carried out through Wi-Fi communication mode (such as ESP32, suitable for short-distance communication), LoRa communication mode (such as SX1278, suitable for long-distance low-power communication) or 5G communication mode (such as Quectel RG500Q, suitable for high-speed data transmission).

[0120] 4. Airflow dynamic adjustment module

[0121] like Figure 2 As shown, the current impact energy and drilling efficiency are calculated using the monitoring data, and a geological identification model representing the relationship between drilling parameters and geological conditions is constructed, the rock hardness and structural changes are identified using the geological identification model, and the impact energy and drilling efficiency are automatically adjusted according to the identification results. The airflow dynamic adjustment module includes:

[0122] 4.1 Real-time computing unit

[0123] It is used to preset the data collection frequency (such as 1kHz) and calculate the current impact energy and drilling efficiency based on the vibration, pressure and flow data.

[0124] 1) The calculation formula of impact energy is:

[0125] v=2πfA,

[0126] Among them, v is the impact velocity, f is the impact frequency, A is the impact amplitude, E is the impact energy, and m is the mass of the hammer.

[0127] 2) The calculation formula for drilling efficiency is:

[0128] P=Q·ΔP,

[0129] Among them, P is the airflow power per unit time, η is the drilling efficiency, Q is the airflow rate, ΔP is the airflow pressure difference, and L is the drilling depth per unit time.

[0130] 4.2 Model building unit

[0131] Collect historical data related to geological conditions during the drilling process, including: Vibration data: impact frequency and amplitude. Propulsion force data: the propulsion force of the drill pipe. Airflow parameters: pressure and flow. Drilling efficiency: drilling depth per unit time. Geological conditions: rock hardness, crack distribution, etc. Then extract key features from the historical data, including: spectral characteristics of vibration signals (such as main frequency and amplitude), change trend of propulsion force, and the relationship between airflow parameters and drilling efficiency.

[0132] Using machine learning algorithms, the model is trained through historical data related to geological conditions during the drilling process to construct a geological identification model that represents the relationship between drilling parameters and geological conditions.

[0133] 4.3 Geological identification unit

[0134] 1) Using the geological identification model, the rock hardness is identified based on the real-time data of vibration frequency, amplitude and propulsion force through fuzzy logic algorithm.

[0135] Vibration signature analysis:

[0136] Hard rock layer: The vibration frequency is higher and the amplitude is smaller.

[0137] Soft rock layer: lower vibration frequency and larger amplitude.

[0138] Propulsion force characteristics analysis:

[0139] Hard rock formation: greater propulsion force and slower drilling speed.

[0140] Soft rock formation: smaller propulsion force and faster drilling speed.

[0141] 2) Using the geological identification model, the vibration signal is subjected to spectrum analysis through fast Fourier transform, the crushing characteristics are extracted, and the rock crushing conditions are identified.

[0142] Vibration signal analysis:

[0143] High degree of fragmentation: There are more high-frequency components in the vibration signal.

[0144] Low degree of fragmentation: low-frequency components dominate the vibration signal.

[0145] 4.4 Airflow adjustment unit

[0146] According to the geological identification results, the PID control algorithm is used to perform closed-loop control and dynamic adjustment of air pressure and flow according to the preset control targets.

[0147] The expression of the PID control algorithm is:

[0148]

[0149] Among them, u(t) is the control output of the proportional valve opening, e(t) is the current error of air pressure or flow, K p , K i , K d These are PID parameters.

[0150] Adjust strategies such as:

[0151] 1) Hard rock formation: Increase the air pressure and flow rate to increase the impact energy. Adjust the target air pressure value to 1.2 times the current pressure and the target flow rate value to 1.1 times the current flow rate.

[0152] 2) Soft rock formation: Reduce air pressure and flow rate to save energy. Adjust the target air pressure to 0.8 times the current pressure and the target flow rate to 0.9 times the current flow rate.

[0153] 4.5 Correction and optimization unit

[0154] Monitor the air pressure, flow and drilling efficiency in real time, compare the actual value with the target value to obtain the airflow deviation, correct the airflow parameters according to the airflow deviation, and monitor the air pressure and flow in real time to see if there are abnormal fluctuations. If so, the alarm mechanism is automatically triggered.

[0155] 5. Fault prediction module

[0156] like Figure 3 As shown, it is used to build and train a fault prediction model based on machine learning and big data analysis technology, and use the fault prediction model to predict and alarm equipment faults. The fault prediction module includes:

[0157] 5.1 Parameter Acquisition Unit

[0158] The vibration data, temperature data and pressure data in the monitoring data are integrated, wherein the sampling frequency of the vibration data is above 10kHz to ensure the capture of high-frequency fault characteristics (such as bearing faults and impact anomalies). The sampling frequency of the temperature data is 1Hz, which is suitable for the slow characteristics of temperature changes. The sampling frequency of the pressure data is 1kHz to capture the dynamic characteristics of pressure fluctuations. The integrated data is time-stamped and cleaned to obtain fault prediction related parameters.

[0159] 5.2 Feature Extraction Unit

[0160] It is used to extract vibration features, temperature features and pressure features from the fault prediction related parameters, and integrate the extracted features into low-dimensional feature vectors using feature fusion technology to reduce redundant information.

[0161] 1) Vibration characteristics: including time domain characteristics (mean, variance, peak, kurtosis, etc. of vibration signals), frequency domain characteristics (using fast Fourier transform to convert vibration signals into frequency domain, extract main frequency, spectrum energy, etc.), time-frequency characteristics (using wavelet transform or short-time Fourier transform to extract and capture dynamic changes of vibration signals).

[0162] 2) Temperature characteristics: Extract temperature trend characteristics (such as rising rate and fluctuation amplitude) to identify overheating or cooling abnormalities of equipment.

[0163] 3) Pressure characteristics: Extract the fluctuation characteristics of the pressure signal (such as pressure peak value, fluctuation frequency) to identify leakage or blockage in the pneumatic system.

[0164] 5.3 Model Training Unit

[0165] It is used to label (such as normal, abnormal vibration, overtemperature, etc.) and divide the low-dimensional feature vector according to the historical fault data, and then input the low-dimensional feature vector into the selected LSTM network for model training to obtain a fault prediction model. The LSTM network structure is:

[0166] Input: feature vector (such as vibration spectrum, temperature trend, pressure fluctuation);

[0167] Output: Failure probability (such as the probability of abnormal vibration, the probability of over-temperature);

[0168] Input layer: receives multi-dimensional feature vectors;

[0169] LSTM layer: extracts time series features and captures dynamic changes in device status;

[0170] Fully connected layer: maps the output of the LSTM layer to fault categories;

[0171] Output layer: Use the Softmax function to output the failure probability.

[0172] 5.4 Fault Prediction Unit

[0173] Use multiple sensors to collect real-time vibration parameters, temperature parameters, and pressure parameters, and input the real-time parameters into the fault prediction model, output the fault probability and classify the current state (such as normal, abnormal vibration, high temperature, etc.). Generate a fault diagnosis report based on the output results and trigger an alarm mechanism.

[0174] Fault diagnosis report includes: fault type (such as abnormal vibration), fault cause (such as bearing wear), fault location (such as impact hammer), etc. Alarm mechanism: When the fault probability exceeds the threshold, an alarm is triggered (such as sound and light alarm, remote notification).

[0175] 6. Energy consumption optimization module

[0176] like Figure 4 As shown, it is used to construct a relationship model between airflow pressure, flow rate and energy consumption, obtain an energy consumption model, and based on the energy consumption model, preset the minimum energy consumption as the optimization target, and perform iterative calculations in combination with the designed optimization genetic algorithm to obtain the optimal airflow parameters. The energy consumption optimization module includes:

[0177] 6.1 Energy consumption model building unit

[0178] It is used to integrate the airflow pressure, airflow flow, drilling efficiency and energy consumption in the monitoring data to obtain energy consumption related parameters, and according to the energy consumption related parameters, construct a relationship model between airflow pressure, flow and energy consumption to obtain an energy consumption model; wherein, the energy consumption model is fitted by multivariate linear regression or neural network.

[0179] The mathematical expression of the energy consumption model is:

[0180] E=f(P,Q)

[0181] Among them, E is energy consumption, P is airflow pressure, Q is airflow flow, and f is energy consumption model function.

[0182] 6.2 Optimizing Constraint Units

[0183] It is used to set the minimization of energy consumption as the optimization target based on the energy consumption model, and to set drilling efficiency constraint conditions, equipment safety constraint conditions and geological constraint conditions.

[0184] 1) The mathematical expression of the drilling efficiency constraint condition is:

[0185] η≥η min

[0186] Among them, η min For the lowest drilling efficiency;

[0187] 2) The mathematical expression of the equipment safety constraint condition is:

[0188] P min ≤P≤P max , Q min ≤Q≤Q max

[0189] Among them, P min is the minimum air flow pressure, P max is the maximum airflow pressure, Q min is the minimum air flow rate, Q max is the maximum air flow rate.

[0190] 3) The geological constraints: dynamically adjusting the constraint range according to the geological conditions (such as hard rock layer or soft rock layer) identified in real time.

[0191] 6.3 Optimization Algorithm Design Unit

[0192] It is used to design an optimization genetic algorithm (or a particle swarm optimization algorithm, the present invention takes the genetic algorithm as an example), input the energy consumption model and constraint conditions into the optimization genetic algorithm, and solve the optimal airflow parameters. The design process of the optimization genetic algorithm is:

[0193] S1. Randomly generate a set of initial solutions of airflow parameter combinations as a population, and each individual in the population represents an airflow parameter combination;

[0194] S2. Define the fitness function as the inverse of the objective function; wherein the expression of the fitness function is E is energy consumption, and the higher the fitness, the lower the energy consumption;

[0195] S3, select individuals from the population according to their fitness values, and give priority to retaining individuals with high fitness;

[0196] S4, randomly exchange some parameters of two individuals to generate new individuals, complete the crossover operation, randomly change a certain parameter of the individual to increase population diversity, and complete the mutation operation;

[0197] S5. Repeat S3-S4 until the fitness value of the population no longer increases significantly or reaches the maximum number of iterations, completing the design of the optimization genetic algorithm.

[0198] 6.4 Real-time Optimization Unit

[0199] It is used to input real-time data into the optimization genetic algorithm and adjust the optimization objectives and constraints according to the geological conditions identified in real time.

[0200] 7. Human-computer interaction module

[0201] It is used to display real-time data, alarm status and adjust parameters using the human-computer interaction interface. The following designs can be made according to actual conditions:

[0202] 1) Display screen:

[0203] Real-time data display: real-time curves and values ​​of parameters such as pressure, flow, vibration, and temperature.

[0204] Status alarm: When an abnormality is detected, the interface highlights the alarm information.

[0205] 2) Operation panel:

[0206] Parameter setting: Allows operators to manually set or adjust parameters.

[0207] Mode switching: supports automatic mode and manual mode switching.

[0208] 3) Voice interaction (optional):

[0209] Voice prompts: When an abnormality occurs or attention is required, voice prompts will be given.

[0210] Voice control: supports simple voice commands to realize human-computer dialogue.

[0211] Therefore, the present invention provides an automatic control system for a pneumatic down-the-hole hammer based on dynamic airflow regulation, which can achieve:

[0212] The various embodiments in this specification are described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the various embodiments can be referenced to each other.

[0213] The principles and implementation methods of the present invention are described in this article using specific examples. The description of the above embodiments is only used to help understand the method and core idea of ​​the present invention. At the same time, for those skilled in the art, according to the idea of ​​the present invention, there will be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as limiting the present invention.

Claims

1. An automatic control system for a pneumatic down-the-hole hammer based on dynamic airflow regulation, characterized in that: include: The sensor module is used to collect relevant data during the drilling process using a variety of sensors to obtain monitoring data; An actuator module, used to control the flow and pressure of compressed air using an electronically controlled proportional valve, and to adjust the propulsion speed and pressure of the drill pipe using a propulsion system controller; Control and processing module, used to perform real-time data processing and intelligent control of equipment using embedded controllers and control algorithms; An airflow dynamic adjustment module, for calculating the current impact energy and drilling efficiency using the monitoring data, and constructing a geological recognition model representing the relationship between drilling parameters and geological conditions, using the geological recognition model to identify rock hardness and structural changes, and automatically adjusting the impact energy and drilling efficiency according to the recognition results; A fault prediction module is used to build and train a fault prediction model based on machine learning and big data analysis technology, and use the fault prediction model to predict and alarm equipment faults; The energy consumption optimization module is used to construct a relationship model between airflow pressure, flow rate and energy consumption, obtain an energy consumption model, and based on the energy consumption model, preset the minimum energy consumption as the optimization target, and perform iterative calculation in combination with the designed optimization genetic algorithm to obtain the optimal airflow parameters; Human-computer interaction module, used to display real-time data, status alarm and parameter adjustment using human-computer interaction interface; Wherein, the sensor module, the actuator module, the control and processing module, the airflow dynamic adjustment module, the fault prediction module, the energy consumption optimization module and the human-computer interaction module are interconnected.

2. The automatic control system of a pneumatic down-the-hole hammer based on dynamic airflow regulation according to claim 1 is characterized in that: The various sensors include pressure sensors for monitoring air supply pressure and actual working pressure, flow sensors for monitoring real-time air flow, vibration sensors for real-time monitoring of impact frequency and vibration amplitude, temperature sensors for detecting temperature changes of equipment, and drilling parameter sensors for monitoring mechanical parameters during drilling.

3. The automatic control system of a pneumatic down-the-hole hammer based on dynamic airflow regulation according to claim 2 is characterized in that: The actuator module comprises: The proportional valve setting unit is used to select the electric control proportional valve, and install a pressure sensor and a flow sensor at the input end and the output end of the electric control proportional valve respectively; wherein the flow range of the electric control proportional valve is 0.1-10m 3 / min, the pressure sensor accuracy is ±0.1%, and the flow sensor accuracy is ±0.5%; an airflow control unit, configured to calculate a first target opening by using a PID control algorithm based on the electronically controlled proportional valve, calculate a first actual opening according to the monitored pressure and flow, compare and calculate the first target opening with the first actual opening to obtain a first opening deviation, and adjust the opening of the electronically controlled proportional valve according to the first opening deviation, the vibration frequency and the propulsion force to obtain a first optimal opening; A propulsion setting unit, which is used to equip the hydraulic cylinder with an electronically controlled hydraulic valve, a force sensor and a displacement sensor to realize control, propulsion force monitoring, propulsion speed monitoring and recommended displacement monitoring of the hydraulic cylinder; A propulsion control unit is used to calculate a second target opening based on the hydraulic cylinder using a fuzzy control algorithm, calculate a second actual opening according to the monitored propulsion force and propulsion speed, compare and calculate the second target opening with the second actual opening to obtain a second opening deviation, and adjust the opening of the hydraulic cylinder according to the second opening deviation, vibration frequency and impact efficiency to obtain a second optimal opening.

4. The automatic control system of a pneumatic down-the-hole hammer based on dynamic airflow regulation according to claim 3 is characterized in that: The control and processing module includes: An embedded control unit, used to initialize a pre-selected processor, and based on the processor, equip multiple peripheral interfaces, internal Flash memory and external memory, and deploy a lightweight real-time operating system to create tasks and run algorithms, and analyze and control tasks in combination with a priority scheduling mechanism and debugging tools; wherein the tasks include data acquisition tasks, control tasks, communication tasks, and data storage tasks; ADC configuration unit, used to configure the sampling rate, resolution and number of channels of the ADC, and introduce direct memory access technology in the ADC; The data acquisition and storage unit is used to collect sensor data in real time using ADC, eliminate noise interference of sensor data using digital filtering algorithm, and then store the filtered data; The communication unit is used to select a standard communication protocol and perform wireless communication via a Wi-Fi communication mode, a LoRa communication mode, or a 5G communication mode.

5. The automatic control system of a pneumatic down-the-hole hammer based on dynamic airflow regulation according to claim 4 is characterized in that: The airflow dynamic adjustment module comprises: Real-time calculation unit, used to preset data collection frequency and calculate current impact energy and drilling efficiency based on vibration, pressure and flow data; A model building unit, for using a machine learning algorithm to train a model through historical data related to geological conditions during the drilling process, and building a geological identification model representing the relationship between drilling parameters and geological conditions; A geological identification unit is used to use the geological identification model to identify the rock hardness according to the real-time data of vibration frequency, amplitude and propulsion force through a fuzzy logic algorithm, perform spectrum analysis on the vibration signal through fast Fourier transform, extract the crushing characteristics, and identify the rock crushing situation; The airflow adjustment unit uses the PID control algorithm to perform closed-loop control and dynamic adjustment of air pressure and flow according to the geological identification results and the preset control targets; The correction and optimization unit monitors the air pressure, flow and drilling efficiency in real time, compares the actual value with the target value to obtain the airflow deviation, corrects the airflow parameters according to the airflow deviation, and monitors in real time whether there are abnormal fluctuations in the air pressure and flow. If so, the alarm mechanism is automatically triggered.

6. The automatic control system of a pneumatic down-the-hole hammer based on dynamic airflow regulation according to claim 5, characterized in that: The calculation formula of the impact energy is: Among them, v is the impact velocity, f is the impact frequency, A is the impact amplitude, E is the impact energy, and m is the mass of the hammer; The calculation formula of the drilling efficiency is: Among them, P is the airflow power per unit time, η is the drilling efficiency, Q is the airflow rate, ΔP is the airflow pressure difference, and L is the drilling depth per unit time; The expression of the PID control algorithm is: Among them, u(t) is the control output of the proportional valve opening, e(t) is the current error of air pressure or flow, K p , K i , K d These are PID parameters.

7. The automatic control system of a pneumatic down-the-hole hammer based on dynamic airflow regulation according to claim 6 is characterized in that: The fault prediction module comprises: A parameter acquisition unit, used to integrate the vibration data, temperature data and pressure data in the monitoring data, synchronize the timestamp and clean the integrated data, and obtain relevant parameters for fault prediction; A feature extraction unit, used to extract vibration features, temperature features and pressure features from the fault prediction related parameters, and integrate the extracted features into a low-dimensional feature vector using feature fusion technology to reduce redundant information; A model training unit, used for labeling and dividing the low-dimensional feature vector according to the historical fault data, and then inputting the low-dimensional feature vector into the selected LSTM network for model training, and introducing a Softmax function into the output layer of the LSTM network to obtain a fault prediction model; The fault prediction unit uses a variety of sensors to collect real-time vibration parameters, temperature parameters and pressure parameters, and inputs the real-time parameters into the fault prediction model, outputs the fault probability and classifies the current state, generates a fault diagnosis report based on the output results, and triggers an alarm mechanism.

8. The automatic control system of a pneumatic down-the-hole hammer based on dynamic airflow regulation according to claim 7, characterized in that: The energy consumption optimization module comprises: An energy consumption model construction unit is used to integrate the airflow pressure, airflow flow, drilling efficiency and energy consumption in the monitoring data to obtain energy consumption related parameters, and to construct a relationship model between airflow pressure, flow and energy consumption according to the energy consumption related parameters to obtain an energy consumption model; wherein the energy consumption model is fitted by multivariate linear regression or neural network; An optimization constraint unit, used for setting the minimization of energy consumption as an optimization target based on the energy consumption model, and setting drilling efficiency constraint conditions, equipment safety constraint conditions and geological constraint conditions; An optimization algorithm design unit, used for designing an optimization genetic algorithm, inputting the energy consumption model and constraint conditions into the optimization genetic algorithm, and solving the optimal airflow parameters; The real-time optimization unit is used to input real-time data into the optimization genetic algorithm and adjust the optimization target and constraint conditions according to the geological conditions identified in real time.

9. The automatic control system of a pneumatic down-the-hole hammer based on dynamic airflow regulation according to claim 8, characterized in that: The mathematical expression of the energy consumption model is: E=f(P,Q) Among them, E is energy consumption, P is airflow pressure, Q is airflow flow, and f is energy consumption model function; The mathematical expression of the drilling efficiency constraint condition is: η≥η min Among them, η min For the lowest drilling efficiency; The mathematical expression of the equipment safety constraint condition is: P min ≤P≤P max ,Q min ≤Q≤Q max Among them, P min is the minimum air flow pressure, P max is the maximum airflow pressure, Q min is the minimum air flow rate, Q max is the maximum air flow rate.

10. The automatic control system of a pneumatic down-the-hole hammer based on dynamic airflow regulation according to claim 9, characterized in that: The design process of the optimization genetic algorithm is as follows: S1. Randomly generate a set of initial solutions of airflow parameter combinations as a population, and each individual in the population represents an airflow parameter combination; S2. Define the fitness function as the inverse of the objective function; wherein the expression of the fitness function is E is energy consumption; S3, select individuals from the population according to their fitness values, and give priority to retaining individuals with high fitness; S4, randomly exchange some parameters of two individuals to generate new individuals, complete the crossover operation, randomly change a certain parameter of the individual to increase population diversity, and complete the mutation operation; S5. Repeat S3-S4 until the fitness value of the population no longer increases significantly or reaches the maximum number of iterations, completing the design of the optimization genetic algorithm.

Images