An intelligent anti-sticking drill pre-warning system and method for a coal mine tunnel drill

Abstract

The present application belongs to the technical field of coal mine data processing, and provides a coal mine tunnel drilling machine intelligent anti-stuck drill early warning system and method, which solves the problems of high false alarm rate, response lag and poor adaptability of the existing drilling machine. The technical scheme is as follows: based on the calculated multi-dimensional characteristic parameters of the collected signals, the rotary shaking intensity is calculated based on the continuously collected power head rotating speed sequence, the mechanical drilling speed fluctuation is calculated based on the continuously collected mechanical drilling speed sequence; the multi-level early warning threshold is preset, the multi-level early warning threshold is dynamically corrected based on the multi-dimensional characteristic parameters calculated under normal drilling conditions, the stuck drill risk index is obtained by weighting and fusing the multi-level early warning threshold, and the classification early warning judgment is carried out in combination with the stuck drill risk index, the multi-dimensional characteristic parameters and the multi-level early warning threshold; when early warning occurs, the rotary shaking intensity and the mechanical drilling speed fluctuation are jointly analyzed to identify the type of stuck drill, and the corresponding actuator control strategy is generated according to different stuck drill types.

Description

Technical Field

[0001] This invention belongs to the field of coal mine data processing technology, and in particular relates to an intelligent anti-jamming early warning system and method for coal mine tunnel drilling rigs. Background Technology

[0002] In coal mine underground roadway excavation and gas drainage drilling, tunnel drilling rigs are indispensable key equipment. During drilling, due to the complex geological conditions of the coal seam, sudden changes in rock hardness, borehole wall collapse, and drill cuttings accumulation are common occurrences, making stuck drill accidents highly likely. Stuck drills not only lead to drill bit wear and drill rod breakage, but in severe cases, they can also cause drilling rig overturning, personnel casualties, and other safety accidents, resulting in huge economic losses.

[0003] Existing anti-stuck drill bit warning products install pressure sensors in the drilling rig's hydraulic system and set a fixed pressure alarm threshold on the control panel. When the feed pressure exceeds this threshold, an audible and visual alarm is triggered, prompting the driller to manually retract the drill rod. However, during coal mine tunnel drilling, pressure naturally rises when encountering harder rock formations, which is not necessarily a sign of stuck drill bit. The fixed threshold cannot distinguish between normal pressure increase and signs of stuck drill bit, leading to frequent false alarms and affecting operational efficiency. Current predictions rely solely on instantaneous pressure values. In reality, during the initial stage of increased resistance at the bottom of the hole, the power head rotation speed often drops or fluctuates before the pressure, often triggering an alarm only when the pressure is already very high, at which point the drill bit is already in a high-risk state. Furthermore, the geological hardness varies greatly between different mining areas, different coal seams, and even different depths within the same borehole. Current threshold determinations require frequent adjustments based on experience, resulting in poor adaptability. Summary of the Invention

[0004] In order to solve at least one of the technical problems existing in the background art, the present invention provides an intelligent anti-jamming early warning system and method for coal mine tunnel drilling rigs.

[0005] To achieve the above objectives, the present invention adopts the following technical solution: The first aspect of the present invention provides an intelligent anti-jamming early warning system for coal mine tunnel drilling rigs, comprising: Pressure sensors are installed in the drilling rig's oil supply line or drill rod clamping mechanism to collect drilling pressure signals in real time. The feed displacement sensor is fixed at one end to the drilling rig frame and connected to the feed slide plate at the other end, and is used to collect the drilling rig feed displacement signal in real time. The power head speed sensor is installed on the output shaft of the power head or the shaft of the rotary motor to collect the power head speed signal in real time. The signal processing unit is connected to the pressure sensor, feed displacement sensor and power head speed sensor respectively, and is used to collect pressure signals, feed displacement signals and power head speed signals during the drilling process at a set sampling period. Calculate multi-dimensional feature parameters based on the collected signals, including: calculating the drilling pressure value and its rate of change based on the pressure signal; calculating the unit displacement pressure increment and mechanical drilling speed based on the feed displacement signal; and calculating the power head rotation speed, rotation speed drop rate and rotation speed change rate based on the power head rotation speed signal. The rotational jitter intensity is calculated based on the continuously acquired power head rotation speed sequence, and the mechanical drilling speed fluctuation is calculated based on the continuously acquired mechanical drilling speed sequence. Multi-level early warning thresholds are preset, and the multi-dimensional feature parameters calculated under normal drilling conditions are dynamically corrected. The multi-level early warning thresholds are weighted and fused to obtain the stuck drill risk index. The stuck drill risk index, multi-dimensional feature parameters and multi-level early warning thresholds are combined to make graded early warning judgments. When an early warning occurs, the intensity of slewing vibration and the fluctuation of mechanical drilling speed are jointly analyzed to identify the type of stuck drill bit. Based on the different types of stuck drill bit, corresponding actuator control strategies are generated.

[0006] Furthermore, the intensity of rotational vibration The calculation formula is: , , Mechanical drilling rate fluctuation The calculation formula is: , , in, Indicates the intensity of rotational jitter. Indicates the first The rotational speed of the power head at each sampling moment. This represents the arithmetic mean of a continuous sequence of rotational speeds. This indicates the fluctuation in mechanical drilling rate. Indicates the first Mechanical drilling rate at each sampling time, This represents the arithmetic mean of a continuous mechanical drilling rate sequence. This indicates the total number of samples taken.

[0007] Furthermore, the dynamic correction of multi-level early warning thresholds based on characteristic parameters collected under normal drilling conditions includes: During the preset learning period after the drilling rig starts, the drilling pressure value is calculated based on each data acquisition moment. Its rate of change Displacement pressure increment and mechanical drilling speed Speed ​​drop rate and the rate of change of rotational speed Construct feature vectors, and build a normal operating condition feature matrix based on N sets of feature vectors within the learning period. Calculate the mean and standard deviation of each dimension, and adjust the warning threshold of the corresponding dimension according to the mean and standard deviation of each dimension.

[0008] Furthermore, the correction formula for the multi-level early warning threshold is as follows: , , , , Or revert to , in, This is the pressure boundary threshold. This is the threshold value for the rate of change of pressure. The threshold for pressure increment per unit displacement. This is the threshold value for the rate of speed drop. The threshold value for speed variation. and The mean and standard deviation of the pressure. and The mean and standard deviation of the rate of change of pressure are given. and The statistical mean and standard deviation of the unit displacement pressure increment during the learning period. and The mean and standard deviation of the speed drop rate are given. and The mean and standard deviation of the rate of change of rotational speed during the learning period; ~ All are preset coefficients greater than 0, used to adjust the tolerance of the corresponding dimension threshold to statistical fluctuations under normal operating conditions. Fixed negative threshold.

[0009] Furthermore, the formula for calculating the stuck drill risk index is as follows: , in, , , , and These are the weighting coefficients, and they satisfy the normalization constraint. , Indicates drilling pressure. Indicates the pressure boundary threshold. Indicates the rate of change of pressure. This represents the threshold value for the rate of change of pressure. This represents the pressure increment per unit displacement. This represents the boundary threshold for pressure increment per unit displacement. Indicates the rate of change of rotational speed. This indicates the threshold for the rate of speed drop. Indicates the rate of change of rotational speed. This represents the threshold value for changes in rotational speed.

[0010] Furthermore, the step of combining the stuck drill risk index, multi-dimensional feature parameters, and multi-level early warning thresholds to perform graded early warning judgment specifically includes: When satisfied > and <- Continue for T1, or ω < Further determine the drilling pressure value and pressure change rate Unit displacement pressure increment Mechanical drilling speed If at least one item does not exceed the corresponding threshold, output a level one warning. If there are synchronous warnings at this time... If the first threshold is met, the level of risk is confirmed or strengthened, and the feed rate is reduced to the set value without forced rollback; if not met... > and <- Continue for T1, or ω < Then it does not meet the speed precursor requirement, and The first threshold is to maintain detection or trend indication without upgrading. when > and <- ,and > and > and > and < When both conditions are met, a level-two warning is triggered. The second threshold corresponds to a level 2 / upgrade warning and triggers a rollback or parameter reduction control. If both conditions cannot be met simultaneously, and The second threshold only serves as a trend indicator and does not escalate the warning.

[0011] Furthermore, when an early warning occurs, the intensity of rotary jitter and the fluctuation of mechanical drilling speed are jointly analyzed to identify the type of stuck drill bit. Based on different types of stuck drill bit, corresponding actuator control strategies are generated, including: Calculate the intensity of rotational jitter and mechanical drilling rate fluctuation Corresponding boundary threshold and ; Based on the baseline values ​​and corresponding boundary thresholds of gyratory vibration intensity and mechanical drilling rate fluctuation. and Calculate the jitter deviation and fluctuation deviation ; calculate pressure deviation by combining pressure boundary threshold and pressure reference value. ; If it is a Level 1 warning, then further refine the deviation degree and make a judgment. and If all values ​​are greater than the set value, it is determined to be a gradual stuttering tendency and a level 1 processing is performed; otherwise, it is a broken belt slippage, which only triggers a level 1 warning and does not perform a rollback. If it is a Level 2 warning, determine whether the speed drop rate is met. and Greater than the set value and speed If the value is less than the set threshold, it is determined to be a sudden stuck drill, triggering the highest level warning and directly controlling the hydraulic valve to perform emergency retraction; otherwise, it is determined to be a reduced diameter or poor slag discharge, triggering a level two warning and linking the actuator to reduce the feed speed.

[0012] A second aspect of the present invention provides an intelligent anti-jamming early warning method for coal mine tunnel drilling rigs, comprising: The pressure signal, feed displacement signal, and power head rotation speed signal during the drilling process are collected at a set sampling period. Calculate multi-dimensional feature parameters based on the collected signals, including: calculating the drilling pressure value and its rate of change based on the pressure signal; calculating the unit displacement pressure increment and mechanical drilling speed based on the feed displacement signal; and calculating the power head rotation speed, rotation speed drop rate and rotation speed change rate based on the power head rotation speed signal. The rotational jitter intensity is calculated based on the continuously acquired power head rotation speed sequence, and the mechanical drilling speed fluctuation is calculated based on the continuously acquired mechanical drilling speed sequence. Multi-level early warning thresholds are preset, and the multi-dimensional feature parameters calculated under normal drilling conditions are dynamically corrected. The multi-level early warning thresholds are weighted and fused to obtain the stuck drill risk index. The stuck drill risk index, multi-dimensional feature parameters and multi-level early warning thresholds are combined to make graded early warning judgments. When an early warning occurs, the intensity of slewing vibration and the fluctuation of mechanical drilling speed are jointly analyzed to identify the type of stuck drill bit. Based on the different types of stuck drill bit, corresponding actuator control strategies are generated.

[0013] A third aspect of the present invention provides a computer-readable storage medium.

[0014] A computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the intelligent anti-jamming early warning method for coal mine tunnel drilling rigs as described above.

[0015] A fourth aspect of the present invention provides a computer device.

[0016] A computer device includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the program, it implements the steps of the intelligent anti-jamming early warning method for coal mine tunnel drilling rigs as described above.

[0017] Compared with the prior art, the beneficial effects of the present invention are: This invention introduces the characteristics of power head rotation speed and rotation speed change rate to construct a two-dimensional fusion criterion of "rotation speed drop trend + pressure displacement over-limit". The stuck drill warning is changed from the traditional "resistance over-limit type lagging judgment" to "rotation speed drop trend type forward judgment". A first-level warning can be output when the pressure has not exceeded the limit. The rotation speed drop pattern is used to distinguish between slow drilling in hard rock and real stuck drill, which significantly reduces the false alarm rate. By participating the rotation speed in the risk index calculation and the second-level hard criterion, a more reliable closed-loop control is formed, which effectively prevents the occurrence of stuck drill accidents and improves the safety and automation level of coal mine tunnel drilling rigs.

[0018] This invention uses the drop rate and deceleration trend of the speed relative to the given drive as a precursor to the pressure not exceeding the limit stage. It couples this precursor with the rock-breaking resistance characteristic of the unit displacement pressure increment derived from the feed oil pressure to form an asymmetric hierarchical architecture of "speed drop prediction + pressure displacement confirmation". This solves the false alarm problem of low absolute speed value but no stuck drill when drilling slowly in hard rock.

[0019] Advantages of additional aspects of the invention will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention. Attached Figure Description

[0020] The accompanying drawings, which form part of this invention, are used to provide a further understanding of the invention. The illustrative embodiments of the invention and their descriptions are used to explain the invention and do not constitute an improper limitation of the invention.

[0021] Figure 1 This is a structural block diagram of an intelligent anti-jamming early warning device for coal mine tunnel drilling rigs provided in an embodiment of the present invention; Figure 2 This is a schematic diagram of the multidimensional adaptive learning process provided in an embodiment of the present invention; Figure 3 These are different learning mechanisms for determining stuck drills provided in the embodiments of the present invention; Figure 4This is a flowchart of the early warning logic judgment provided in the embodiment of the present invention; Figure 5 This is a schematic diagram of the stuck drill type identification and control strategy provided in an embodiment of the present invention. Detailed Implementation

[0022] The present invention will be further described below with reference to the accompanying drawings and embodiments.

[0023] It should be noted that the following detailed description is illustrative and intended to provide further explanation of the invention. Unless otherwise specified, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention pertains.

[0024] It should be noted that the terminology used herein is for the purpose of describing particular embodiments only and is not intended to limit the scope of exemplary embodiments according to the invention. As used herein, the singular form is intended to include the plural form as well, unless the context clearly indicates otherwise. Furthermore, it should be understood that when the terms "comprising" and / or "including" are used in this specification, they indicate the presence of features, steps, operations, devices, components, and / or combinations thereof.

[0025] like Figure 1 As shown, as an embodiment of the present invention, this embodiment provides an intelligent anti-jamming early warning system for coal mine tunnel drilling rigs, including: The pressure sensor is installed in the drilling rig's feed oil circuit or drill rod clamping mechanism to collect drilling pressure signals in real time. Specifically, the pressure sensor is a high-precision oil pressure transmitter, whose output signal is a 4-20mA analog current signal.

[0026] The feed displacement sensor is fixed at one end to the drilling rig frame and connected to the feed slide (power head) at the other end. When the power head moves, the pull rope extends and retracts, outputting a 4-20mA analog current signal, which is used to collect the drilling rig feed displacement signal in real time and characterize the feed depth of the drill rod.

[0027] The power head speed sensor is installed on the output shaft of the power head or the shaft of the rotary motor to collect the power head speed signal in real time. Specifically, the power head speed sensor is an incremental speed sensor that outputs a pulse signal to the signal processing unit. The sampling period is consistent with the pressure and displacement signals. In this embodiment, the sampling period is set to 100ms to ensure data timestamp alignment.

[0028] The signal processing unit is connected to the pressure sensor, the feed displacement sensor and the power head speed sensor respectively, and is used to filter, amplify and perform analog-to-digital conversion on the pressure signal, speed signal and feed displacement signal; In this embodiment, the signal processing unit adopts an industrial-grade PLC, such as the Siemens S7-1500 series or the domestic Huichuan PLC, including a filtering and amplification module, an A / D conversion module and a logic operation module. The filtering and amplification modules use existing low-pass filters to suppress the influence of high-frequency harmonics on the sampled values, and the A / D conversion module is used to convert the analog quantity of the acquired signal into a discrete digital quantity. In this embodiment, the signal processing unit reads the signals from the pressure sensor, feed displacement sensor, and power head speed sensor at a set sampling period, and defines variables: This represents the pressure value from the nth sample. This represents the displacement value from the nth sample. The rotational speed value at the nth sampling time; The logic operation module is used to calculate several key indicators during the drilling process based on the received multi-sensor signals, specifically including: Calculate the drilling pressure value based on the drilling pressure signal. and pressure change rate : Specifically, drilling pressure value Take directly Drilling pressure change rate The calculation is performed using the finite difference method, and the formula is as follows: , In the formula, Indicates the current sampled value. This represents the sampled value from 10 periods ago. This represents the total time (1 second) corresponding to 10 sampling periods. In this embodiment, the difference between the first 10 sampling points is divided by the time interval. To reflect the pressure change trend within the past second, other embodiments may also select the number of sampling points as appropriate.

[0029] Calculate the unit displacement pressure increment based on the feed displacement signal. and mechanical drilling speed ; Specifically, the pressure increment per unit displacement The calculation formula is: When the displacement change When >1mm, , In the formula, For displacement by Change to The number of sampling cycles is dynamically determined by the sampling period and the feed rate. This indicates the feed oil pressure value at the current sampling time. Indicates that when displacement occurs During the period of change, the pressure value of the oil supply line corresponding to the starting sampling point, This represents the feed displacement value at the current sampling time. Indicates that when displacement occurs During the change, the feed displacement value corresponding to the initial sampling point, this parameter It represents the increase in rock-breaking resistance per unit advance distance of the drill bit. During normal drilling, it fluctuates slightly with the drillability of coal and rock. When the drill bit gets stuck due to narrowing at the bottom of the hole, rock cuttings accumulate, or sudden jamming occurs, the mechanical rock-breaking efficiency of the drill bit drops sharply while the feed pressure continues to rise. This ratio will increase sharply, so it can be used as a displacement-pressure coupling criterion for the precursor of stuck drill bit.

[0030] When the displacement change When the thickness is ≤1mm (such as during momentary feed pauses or slight springback conditions), the value calculated in the previous valid sampling period is retained. The value is not included in the real-time update of the stuck drill risk index R to avoid division by zero and noise-induced false triggering.

[0031] Specifically, mechanical drilling speed To calculate the change in displacement per unit time, the formula is: , Calculate the power head speed based on the power head speed signal. Speed ​​drop rate Rotational speed change rate and speed fluctuation variance ; Specifically, the rotational speed of the power head Calculated based on pulse frequency: ,in The measured frequency of the sensor output pulse. This represents the number of pulses output per revolution of the speed sensor. Speed ​​drop rate. The calculation formula is: , This indicates the target rotational angular velocity currently given by the proportional reversing pump, which is read in real time by the PLC control word. The aforementioned measured angular velocity; rate of change of rotational speed. The calculation formula is: ,in, For the current number Measured rotational speed in one sampling period Represented as the first 10 sampling periods (corresponding sampling periods) The rotational speed of the same diameter at the time (1.0 s prior), combined with the current sampled value. and window length , by formula The angular acceleration (rate of change of rotational speed) within a nearly 1-second sliding window was calculated. This quantity, exhibiting a steep negative descent, characterizes the sudden braking tendency of the power head due to bottom hole resistance, serving as a prospective criterion for distinguishing between steady-state slow drilling in hard rock and early signs of stuck drill bit. Rotational speed fluctuation variance. Based on the rotational speed of the power head within the sliding window The standard deviation is calculated and used to identify rotational jitter. To identify the rotational jitter characteristics of the power head, the rotational speed of the power head is calculated. The fluctuation characteristics within the sliding time window are defined by the time window length as... The preferred sampling time is 1.0s to 2.0s, corresponding to 10 to 20 sampling periods, within which a continuous speed sequence is acquired. The rotational jitter intensity was calculated based on this rotational speed sequence. The specific calculation formula is as follows: , , In the formula, This refers to the variance of rotational speed fluctuation (also known as rotational jitter intensity), which is used to quantify the stability of the power head's rotational speed. The larger the value, the more uneven the resistance and impact experienced by the power head during rotation, which may lead to tooth surface slippage, uneven rock fragmentation, or localized jamming. This represents the arithmetic mean of the rotational speed fluctuations. Indicates the first The rotational speed of the power head at each sampling moment; During the learning period after system startup, data under normal drilling conditions are collected synchronously. benchmark value Real-time calculation and Compare: If ≤ If the rotation is stable; >2 The system was found to be experiencing abnormal vibration during rotation. Characteristic parameters are one of the core bases for distinguishing between slippage in fractured zones and sudden stuck drill bits. For example, in slippage conditions in fractured zones, the drill bit does not make proper contact with the rock, leading to… The rotational speed increases significantly; however, in the initial stage of simple necking and jamming, the rotational speed usually decreases smoothly rather than fluctuates violently. The changes are relatively small.

[0032] To differentiate between slippage in the fractured zone and sudden stuck drill bit, the mechanical drilling rate was further calculated. Fluctuation characteristics within a sliding time window. The time window length is defined as... (Preferably 1.0s~2.0s, corresponding to 10~20 sampling periods), within this window, a continuous mechanical drilling rate sequence is acquired. Calculate the fluctuation of mechanical drilling rate. The calculation formula is as follows: , , In the formula, This refers to the mechanical drilling rate fluctuation, which is used to quantify the stability of the drilling rate. The larger the value, the more drastic the fluctuations in drilling speed within a short time window. This is the arithmetic mean of the mechanical drilling rate sequence; Indicates the first Mechanical drilling rate at each sampling time.

[0033] During the learning period after system startup, data under normal drilling conditions are collected synchronously. benchmark value .

[0034] In the early warning logic, the real-time calculation will be... and Compare: If ≤ Determine that the drilling speed is stable; if >2 The drilling speed was found to be fluctuating abnormally.

[0035] The intelligent terminal HMI has a built-in microprocessor and is connected to the signal processing unit via a bus (Modbus RTU protocol). The display screen serves as the core of human-machine interaction. The microprocessor is used to build a warning logic program to preset multi-level warning thresholds. Based on multi-dimensional feature parameters calculated under normal drilling conditions, the multi-level warning thresholds are dynamically corrected. The multi-level warning thresholds are weighted and fused to obtain the stuck drill risk index. The stuck drill risk index, multi-dimensional feature parameters, and multi-level warning thresholds are combined to make graded warning judgments. In this embodiment, to address the issue of poor adaptability of a single threshold under different geological conditions, the system is configured with a multi-dimensional adaptive learning module. Unlike traditional techniques that only perform threshold learning on the comprehensive risk index R, this module simultaneously learns the calculated multi-dimensional feature parameters and the gyration intensity. and mechanical drilling rate fluctuation Perform joint modeling, such as Figure 2 As shown, it specifically includes the following: Feature vector construction: During the preset learning period after system startup (such as the first 10 minutes of drilling or manually triggered learning mode), the system continuously collects feature parameters under normal drilling conditions, and combines them with the drilling pressure value calculated at each collection moment. Its rate of change Displacement pressure increment and mechanical drilling speed Speed ​​drop rate and the rate of change of rotational speed Construct feature vectors; The baseline threshold is calculated by collecting N sets of feature vectors during the learning period to construct a normal operating condition feature matrix. The mean and standard deviation of each dimension are calculated, and the warning threshold for each dimension is adjusted based on the mean and standard deviation of each dimension. The specific formula for adjusting the multi-level warning threshold is as follows: , , , , Or revert to , in, This is the pressure boundary threshold. This is the threshold value for the rate of change of pressure. The threshold for pressure increment per unit displacement. This is the threshold value for the rate of speed drop. The threshold value for speed variation. and The mean and standard deviation of the pressure. and The mean and standard deviation of the rate of change of pressure are given. and The statistical mean and standard deviation of the unit displacement pressure increment during the learning period. and The mean and standard deviation of the speed drop rate are given. and The mean and standard deviation of the rate of change of rotational speed during the learning period; All are preset coefficients greater than 0, corresponding to the dimensions of pressure, pressure change rate, pressure increment per unit displacement, speed drop rate, and speed change rate, respectively; A downward bias (minus sign) is used to tolerate normal deceleration, while upward bias (plus sign) is used for the other dimensions. In the preferred embodiment: , It is 1.5~2.5. The value is 2.0~3.0. The value is 0.3~0.5 (lower deviation). The value is 2.0~3.0. This applies when adaptive learning is not enabled, there are insufficient learning samples, or the drift has not converged. And each threshold will revert to a fixed / empirical threshold or the previous stable threshold (e.g.) Back off to a fixed negative threshold (Preferred speed is 3~8 rad / s², further preferred is 5 rad / s²) to ensure that the early warning is not suspended.

[0036] Real-time deviation calculation: During real-time drilling, the deviation of the current feature vector from the baseline value is calculated. Based on the baseline values ​​and corresponding boundary thresholds of gyratory vibration intensity and mechanical drilling rate fluctuation. and Calculate the jitter deviation and fluctuation deviation Combined with pressure boundary threshold and pressure reference value Calculate pressure deviation ; Boundary thresholds for slewing vibration intensity and mechanical drilling speed fluctuation and The calculation formula is: Based on the aforementioned speed fluctuation variance benchmark value Set the rotational vibration safety threshold Based on the aforementioned drilling speed fluctuation benchmark value Setting a safety threshold for drilling rate fluctuations ,in , The preset coefficient is 1.5 to 2.5; where, , These are the reference standards for the variance of rotational speed fluctuation and the reference standard for drilling speed fluctuation under normal drilling conditions; , These are the benchmarks for the standard deviation of rotational speed fluctuation and the standard deviation of drilling speed fluctuation under normal drilling conditions, respectively. , It is a preset coefficient (preferably 1.5~2.5) used to balance sensitivity and anti-interference ability.

[0037] The specific formula for calculating the deviation is as follows: or equivalent The two correspond monotonically under the adaptive threshold system, and this embodiment adopts... As a visual indicator; jitter deviation: , Fluctuation deviation: .

[0038] In this embodiment, during adaptive learning, the judgment is... and Are all values ​​greater than the first set value? >2 and >2. If so, it is determined to be a gradual stuttering tendency, and a second-level speed reduction is implemented; otherwise, further judgment is made. and Greater than the second set value and the speed Less than a set threshold, for example, >3.0 and If the value is greater than 2 and ω approaches zero, it is determined to be a sudden stuck drill, and the hydraulic valve is directly controlled to perform an emergency retraction; otherwise, the output breaker belt slips and is marked as a first-level warning. Through the aforementioned multi-dimensional learning mechanism, the system can accurately distinguish different stuck drill mechanisms, effectively solving the industry problems of false alarms in hard rock slow drilling and missed alarms in fractured zone slippage.

[0039] Calculation of the risk index of stuck drill bit: To intuitively quantify drilling risk, HMI defines a stuck drill risk index. , The dimensionless weighted fusion algorithm is used, and its calculation formula is as follows: , in, These are the weighting coefficients, and they satisfy the normalization constraint. Weight Calibration method: The weighting coefficients are not empirically determined, but rather inversely calibrated based on the contribution of each parameter to the stuck drill samples during the field learning period. The specific process is as follows: During the system learning period, N sets of labeled samples are collected (including normal drilling samples and samples showing signs of stuck drill, covering the time span from 5 seconds to 1 second before the stuck drill). The feature values ​​of the aforementioned features within the stuck drill warning window are extracted. Feature values ​​within the normal window Calculate the discriminant factor for each feature. , Set weighting coefficients for the standard deviation of normal samples. (That is, the weight is proportional to the discrimination factor), and after normalization, it is fixed in the HMI backend and supports fine-tuning in the field debugging mode.

[0040] Preferably, based on the pre-training results of common coal mine geological conditions, a set of preferred initial values ​​is given: =0.3, =0.3, =0.15, =0.15, =0.1. The values ​​can be displayed in real time on the dashboard of the HMI interface.

[0041] Weight update satisfies Furthermore, each dimension is set with a lower limit and an upper limit (0.10~0.40 in the embodiment) to avoid a single sensor or a single physical dimension dominating. Calibration is performed slowly based on feedback from normal / warning / confirmed events: if a dimension frequently shows a high single-item value due to transient noise but the event is not confirmed, its weight is appropriately reduced or the confidence threshold is increased; if a dimension consistently deviates significantly before a historically confirmed stuck drill event, its weight is moderately increased. Weight updates use constrained normalization or projected gradient methods, and the updated parameters are only implemented after confirmation through a stabilization window / event feedback, without directly altering the online alarm actions.

[0042] As another embodiment, to further simplify computational complexity and avoid feature redundancy, the aforementioned multidimensional features can be converged into a deviation index based on a safety threshold, thus constructing a simplified version of the stuck drill risk index. Define the following dimensionless deviation: , In the formula, the weighting coefficient , , It also satisfies the normalization constraint. Furthermore, its calibration method follows the aforementioned reverse calibration logic based on the discrimination factor β. In a preferred embodiment, for stuck drill scenarios primarily characterized by rotational anomalies, a setting can be made... =0.4, =0.4, =0.2; For scenarios where poor slag discharge is the primary issue, it can be set to... =0.5, =0.2, =0.3. This simplified formula will reduce the "speed drop rate" to 0.3. "and "rate of change of rotational speed" The physical characteristics of "speed fluctuation variance deviation" converge uniformly to "speed fluctuation variance deviation". In this approach, the computational load is reduced while ensuring the sensitivity of the early warning system. In actual operation, the aforementioned five-dimensional formula can be used first for calculation; when the processor's computing power is limited or the operating conditions are simple, the simplified formula can also be switched to for calculation.

[0043] After introducing the stuck drill risk index R, the multidimensional adaptive learning process is not only used to update the thresholds of each dimension. , , , , It is also used for weighting coefficients. ~ Constrained calibration is performed, and the distribution shift of R under normal operating conditions is monitored. The learning process first filters steady-state normal drilling samples, removing data from warnings, rollbacks, start / stop operations, and abnormal sensor data. When samples are insufficient or operating condition / formation drift is detected, the process rolls back or freezes to a fixed / empirical threshold and the previous stable weight, and a new learning window is started. The learning window takes the most recent N steady-state samples or a duration of T (N=200~500 in the example, or T=10~30 min), with at least N_min of consecutive effective samples (100~300 in the example).

[0044] Weight update satisfies Each has its own upper and lower limits, to avoid a single dimension dominating R. Used for normalized weighted summation of R, with signed weights. It is still used as the criterion for abnormal speed drop rules. After each warning / rollback / confirmation / false alarm event, the process data and the parameters at that time are saved for offline review and threshold-weight joint calibration, so as to maintain the stable mapping relationship between R and the graded thresholds of 0.8 and 1.2.

[0045] The graded early warning judgment is made by combining the stuck drill risk index, multi-dimensional feature parameters, and multi-level early warning thresholds, specifically including the following steps: like Figure 4 As shown, the specific judgment logic is as follows: After calculating the stuck drill risk index Then, execute synchronously. Figure 3 The multi-dimensional feature rule judgment shown; the risk index When used in conjunction with tiered early warning results, specifically: Real-time calculation: It is continuously mapped to the risk index grading threshold, where the first-level risk index threshold is... The threshold for the second-level risk index is .

[0046] When the rule determines that the abnormal speed drop condition is met, that is: When satisfied > and <- Continue for T1, or ω < Further determine the drilling pressure value and pressure change rate Unit displacement pressure increment Mechanical drilling speed If at least one item does not exceed the corresponding threshold, output a level one warning; if at this time there are synchronous... If the risk level is confirmed / strengthened, the HMI will display a flashing yellow warning box indicating "Abnormal drop in drilling speed, risk of stuck drill bit," and will recommend that the driller reduce the feed rate to 70%. At this stage, no forced rollback is allowed for observation. If the conditions are not met... > and <- Continue for T1, or ω < Then it does not meet the speed precursor requirement. Maintain detection or trend alerts, but do not upgrade; When the rule determines that the pressure / displacement / drilling speed confirmation conditions have been met, i.e. > and <- (The precursor to the rotational speed is established), and P> and > and > And V < (Pressure displacement confirmation) When both conditions are met, a level two warning / control action is triggered; if at this time... 1.2, then a level 2 / upgrade warning will be issued and rollback or parameter reduction control will be executed in conjunction. If both conditions cannot be met simultaneously, and Even if localized features appear briefly but the overall index does not reach the threshold, only a trend indication or continued observation is given, without escalating the warning. When a level two warning is triggered on the screen, the background frame changes to a flashing red background, a drill jam risk window pops up, and an external alarm is activated with both sound and light. The HMI immediately outputs a signal to the actuator via the PLC. First, the feed proportional relief valve is controlled to reduce its opening, lowering the feed speed to 50% of its original speed; simultaneously, the speed recovery is monitored. If ω recovers to ≥0.8... If the pressure drops, maintain low-speed drilling; if the pressure does not drop and the speed does not recover after 500ms, control the solenoid directional valve to drive the feed cylinder to move in the opposite direction, causing the drill rod to automatically retract 50mm~100mm.

[0047] That is, in this invention, Figure 4 Multi-dimensional feature parameters are used to identify early signs and triggering conditions of stuck drill bit. The risk index R is used to quantify and score the current comprehensive risk level and is mapped to the 0.8 / 1.2 graded threshold as a joint criterion for confirming, maintaining or upgrading the warning level, thereby ensuring that the mapping relationship between the risk index and the graded threshold actually takes effect in the warning logic.

[0048] Drill jam type identification: Intensity of rotational vibration and mechanical drilling rate fluctuation Joint analysis is performed to identify the types of stuck drills, enabling refined identification of stuck drill types. Based on different stuck drill types, corresponding actuator control strategies are generated, such as... Figure 5 As shown, it includes: If it is a Level 1 warning, then further refine the deviation degree and make a judgment. and If all values ​​are greater than the set value, it is determined to be a gradual stuttering tendency and a level 1 processing is performed; otherwise, it is a broken belt slippage, which only triggers a level 1 warning and does not perform a rollback. If it is a Level 2 warning, determine whether the speed drop rate is met. and Greater than the set value and speed If the feed rate is below the set threshold, it is considered a sudden stuck drill, triggering the highest-level warning and directly controlling the hydraulic valve to perform an emergency retraction. Otherwise, it is considered a reduced diameter or poor slag discharge, triggering a secondary warning and linking the actuator to reduce the feed rate. The alarm uses a mine-grade explosion-proof audible and visual alarm, connected to the HMI via an RS485 bus, following the Modbus RTU protocol. When the HMI's warning logic is at the secondary warning level, the audible and visual alarm sounds. When the secondary warning is triggered, the system automatically activates the event recording function. The system packages the pressure, displacement, CRI index, and other data for the 10 seconds before and 5 seconds after the trigger time into a CSV file in the HMI's storage space, naming the file with a timestamp (e.g., 20260115_103045.csv). Maintenance personnel can export the data via the HMI's USB interface using a USB flash drive and analyze the cause of the stuck drill on a ground computer.

[0049] Actuators include a feed proportional relief valve, which is connected to the PLC via a CAN bus; and a solenoid directional valve, which is controlled by the PLC's DO digital output module.

[0050] As a further embodiment, the system incorporates anti-shake delay logic. To prevent false triggering of the secondary warning due to instantaneous pressure fluctuations, the system adds a 200ms confirmation delay after determining that the secondary warning conditions are met. Only if the warning status persists for more than 200ms will a rollback action be executed. This effectively avoids malfunctions caused by hydraulic system shocks.

[0051] As a further embodiment, the HMI screen features a geological mode selection button, including soft coal mode, hard rock mode, and composite mode. When different modes are selected, the system automatically calls different weighting coefficients preset in the background. , , ) and threshold multiple ( , This further improves the system's adaptability to different geological conditions.

[0052] In another embodiment, the system adds a stuck drill type identification function based on rotational speed pattern. This represents the variance of rotational speed fluctuation, in rad / s. This represents the rate of change of rotational speed, expressed in rad / s². When a slow decrease in ω is detected... When the speed is less than 0.5 rad / s, the system determines that the slag discharge is not smooth or the borehole diameter is narrowed. In this case, the main strategy is to increase the rotation speed and then slightly retract the rotation. When | is detected When the drilling pressure P spikes and instantly exceeds 5 rad / s² (i.e., the aforementioned preferred value of -α1), the system determines it to be a sudden stuck drill bit (such as stuck drill bit due to rockfall). At this time, the system immediately cuts off the feed oil circuit and reverses at full speed. Through this embodiment, the system can take differentiated measures for different stuck drill bit mechanisms, further reducing the risk of drill bit failure.

[0053] As another embodiment of the present invention, this embodiment provides an intelligent anti-jamming early warning method for coal mine tunnel drilling rigs, comprising the following steps: The pressure signal, feed displacement signal, and power head rotation speed signal during the drilling process are collected at a set sampling period. Calculating multi-dimensional feature parameters based on the acquired signals includes: calculating the drilling pressure value based on the pressure signal. and its rate of change The unit displacement pressure increment is calculated based on the feed displacement signal. and mechanical drilling speed The power head speed is calculated based on the power head speed signal. Speed ​​drop rate and the rate of change of rotational speed ; Calculation of rotational jitter intensity based on continuously acquired power head rotation speed sequence Calculate the mechanical drilling rate fluctuation based on continuously acquired mechanical drilling rate sequences. ; Multi-level early warning thresholds are preset, and the multi-dimensional feature parameters calculated under normal drilling conditions are dynamically corrected. The multi-level early warning thresholds are weighted and fused to obtain the stuck drill risk index. The stuck drill risk index, multi-dimensional feature parameters and multi-level early warning thresholds are combined to make graded early warning judgments. When a warning occurs, the rotational jitter intensity will be adjusted. and mechanical drilling rate fluctuation Joint analysis is conducted to identify the types of stuck drills, and corresponding actuator control strategies are generated based on different types of stuck drills.

[0054] It should be noted that the specific implementation of the intelligent anti-jamming early warning method for coal mine tunnel drilling rigs in this embodiment of the invention is similar to the specific implementation of the intelligent anti-jamming early warning system for coal mine tunnel drilling rigs in this embodiment of the invention. Please refer to the description in the method section for details. In order to reduce redundancy, it will not be repeated here.

[0055] As another embodiment of the present invention, this embodiment provides a computer-readable storage medium storing a computer program thereon, which, when executed by a processor, implements the steps of the intelligent anti-jamming early warning method for coal mine tunnel drilling rigs as described above.

[0056] As another embodiment of the present invention, this embodiment provides a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the program, it implements the steps of the intelligent anti-jamming early warning method for coal mine tunnel drilling rigs as described above.

[0057] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of hardware embodiments, software embodiments, or embodiments combining software and hardware aspects. Furthermore, the present invention can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage and optical storage) containing computer-usable program code.

[0058] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0059] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0060] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0061] Those skilled in the art will understand that all or part of the processes in the above embodiments can be implemented by a computer program instructing related hardware. The program can be stored in a computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. The storage medium can be a magnetic disk, optical disk, read-only memory (ROM), or random access memory (RAM), etc.

[0062] The above description is merely a preferred embodiment of the present invention and is not intended to limit the invention. Various modifications and variations can be made to the present invention by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the scope of protection of the present invention.

Claims

1. An intelligent anti-jamming early warning system for coal mine tunnel drilling rigs, characterized in that, include: Pressure sensors are installed in the drilling rig's oil supply line or drill rod clamping mechanism to collect drilling pressure signals in real time. The feed displacement sensor is fixed at one end to the drilling rig frame and connected to the feed slide plate at the other end, and is used to collect the drilling rig feed displacement signal in real time. The power head speed sensor is installed on the output shaft of the power head or the shaft of the rotary motor to collect the power head speed signal in real time. The signal processing unit is connected to the pressure sensor, feed displacement sensor and power head speed sensor respectively, and is used to collect pressure signals, feed displacement signals and power head speed signals during the drilling process at a set sampling period. Based on the acquired signals, multi-dimensional feature parameters are calculated, including: calculating the drilling pressure value and its rate of change based on the pressure signal; calculating the unit displacement pressure increment and mechanical drilling speed based on the feed displacement signal; and calculating the power head rotation speed, rotation speed drop rate and rotation speed change rate based on the power head rotation speed signal. The rotational jitter intensity is calculated based on the continuously acquired power head rotation speed sequence, and the mechanical drilling speed fluctuation is calculated based on the continuously acquired mechanical drilling speed sequence. A multi-level early warning threshold is preset, and the multi-dimensional feature parameters calculated under normal drilling conditions are dynamically corrected. The multi-level early warning thresholds are weighted and fused to obtain the stuck drill risk index. The stuck drill risk index, multi-dimensional feature parameters and multi-level early warning thresholds are combined to make graded early warning judgments. When an early warning occurs, the intensity of slewing vibration and the fluctuation of mechanical drilling speed are jointly analyzed to identify the type of stuck drill bit. Based on the different types of stuck drill bit, corresponding actuator control strategies are generated.

2. The intelligent anti-jamming early warning system for coal mine tunnel drilling rigs as described in claim 1, characterized in that, Rotational vibration intensity The calculation formula is: ， ， Mechanical drilling rate fluctuation The calculation formula is: ， ， in, Indicates the intensity of rotational jitter. Indicates the first The rotational speed of the power head at each sampling moment. This represents the arithmetic mean of a continuous sequence of rotational speeds. This indicates the fluctuation in mechanical drilling rate. Indicates the first Mechanical drilling rate at each sampling time, This represents the arithmetic mean of a continuous mechanical drilling rate sequence. This indicates the total number of samples taken.

3. The intelligent anti-jamming early warning system for coal mine tunnel drilling rigs as described in claim 1, characterized in that, The dynamic correction of multi-level early warning thresholds based on characteristic parameters collected under normal drilling conditions includes: During the preset learning period after the drilling rig starts, the drilling pressure value is calculated based on each data acquisition moment. Its rate of change Displacement pressure increment and mechanical drilling speed Speed ​​drop rate and the rate of change of rotational speed Construct feature vectors, and build a normal operating condition feature matrix based on N sets of feature vectors within the learning period. Calculate the mean and standard deviation of each dimension, and adjust the warning threshold of the corresponding dimension according to the mean and standard deviation of each dimension.

4. The intelligent anti-jamming early warning system for coal mine tunnel drilling rigs as described in claim 3, characterized in that, The correction formula for the multi-level early warning threshold is: ， ， ， ， Or revert to , in, This is the pressure boundary threshold. This is the threshold value for the rate of change of pressure. The threshold for pressure increment per unit displacement. This is the threshold value for the rate of speed drop. The threshold value for speed variation. and The mean and standard deviation of the pressure. and The mean and standard deviation of the rate of change of pressure are given. and The statistical mean and standard deviation of the unit displacement pressure increment during the learning period. and The mean and standard deviation of the speed drop rate are given. and The mean and standard deviation of the rate of change of rotational speed during the learning period; All are preset coefficients greater than 0, corresponding to the dimensions of pressure, pressure change rate, pressure increment per unit displacement, speed drop rate, and speed change rate, respectively. Fixed negative threshold.

5. The intelligent anti-jamming early warning system for coal mine tunnel drilling rigs as described in claim 1, characterized in that, The formula for calculating the stuck drill risk index is: ， in, , , , and These are the weighting coefficients, and they satisfy the normalization constraint. , Indicates drilling pressure. Indicates the pressure boundary threshold. Indicates the rate of change of pressure. This represents the threshold value for the rate of change of pressure. This represents the pressure increment per unit displacement. This represents the boundary threshold for pressure increment per unit displacement. Indicates the rate of change of rotational speed. This indicates the threshold for the rate of speed drop. Indicates the rate of change of rotational speed. This represents the threshold value for changes in rotational speed.

6. The intelligent anti-jamming early warning system for coal mine tunnel drilling rigs as described in claim 1, characterized in that, The method of combining a stuck drill risk index, multi-dimensional feature parameters, and multi-level early warning thresholds to perform graded early warning judgments specifically includes: When satisfied > and <- Continue for T1, or ω < Further determine the drilling pressure value and pressure change rate Unit displacement pressure increment Mechanical drilling speed If at least one item does not exceed the corresponding threshold, output a level one warning. If there are synchronous warnings at this time... If the first threshold is met, the level one risk is confirmed or strengthened, and the feed rate is reduced to the set value without forced rollback; if not met... > and <- Continue for T1, or ω < Then it does not meet the speed precursor requirement, and The first threshold is to maintain detection or trend indication without upgrading. when > and <- ,and > and > and > and < When both conditions are met, a level-two warning is triggered. The second threshold corresponds to a level 2 / upgrade warning and triggers a rollback or parameter reduction control. If both cannot be met simultaneously, and The second threshold only serves as a trend indicator and does not escalate the warning.

7. The intelligent anti-jamming early warning system for coal mine tunnel drilling rigs as described in claim 1, characterized in that, When an early warning occurs, the intensity of rotary jitter and the fluctuation of mechanical drilling speed are jointly analyzed to identify the type of stuck drill bit. Based on different types of stuck drill bit, corresponding actuator control strategies are generated, including: Calculate the intensity of rotational jitter and mechanical drilling rate fluctuation Corresponding boundary threshold and ; Based on the baseline values ​​and corresponding boundary thresholds of gyratory vibration intensity and mechanical drilling rate fluctuation. and Calculate the jitter deviation and fluctuation deviation ; calculate pressure deviation by combining pressure boundary threshold and pressure reference value. ; If it is a Level 1 warning, then further refine the deviation degree and make a judgment. and If all values ​​are greater than the set value, it is determined to be a gradual stuttering tendency and a level 1 processing is performed; otherwise, it is a broken belt slippage, which only triggers a level 1 warning and does not perform a rollback. If it is a Level 2 warning, determine whether the speed drop rate is met. and Greater than the set value and speed If the feed rate is less than the set threshold, it is determined to be a sudden stuck drill, triggering the highest level warning and directly controlling the hydraulic valve to perform an emergency retraction; otherwise, it is determined to be a reduced diameter or poor slag discharge, triggering a level two warning and linking the actuator to reduce the feed rate.

8. A method for intelligent anti-jamming early warning of coal mine tunnel drilling rigs, characterized in that, Includes the following steps: The pressure signal, feed displacement signal, and power head rotation speed signal during the drilling process are collected at a set sampling period. Based on the acquired signals, multi-dimensional feature parameters are calculated, including: calculating the drilling pressure value and its rate of change based on the pressure signal; calculating the unit displacement pressure increment and mechanical drilling speed based on the feed displacement signal; and calculating the power head rotation speed, rotation speed drop rate and rotation speed change rate based on the power head rotation speed signal. The rotational jitter intensity is calculated based on the continuously acquired power head rotation speed sequence, and the mechanical drilling speed fluctuation is calculated based on the continuously acquired mechanical drilling speed sequence. A multi-level early warning threshold is preset, and the multi-dimensional feature parameters calculated under normal drilling conditions are dynamically corrected. The multi-level early warning thresholds are weighted and fused to obtain the stuck drill risk index. The stuck drill risk index, multi-dimensional feature parameters and multi-level early warning thresholds are combined to make graded early warning judgments. When an early warning occurs, the intensity of slewing vibration and the fluctuation of mechanical drilling speed are jointly analyzed to identify the type of stuck drill bit. Based on the different types of stuck drill bit, corresponding actuator control strategies are generated.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the program is executed by the processor, it implements the steps in the intelligent anti-jamming early warning method for coal mine tunnel drilling rigs as described in claim 8.

10. A program product, said program product being a computer program product, comprising a computer program, characterized in that, When the computer program is executed by the processor, it implements the steps of the intelligent anti-jamming early warning method for coal mine tunnel drilling rigs as described in claim 8.

Images