Intelligent control method, system and equipment for automatic discharging mining tunneling cutting pick and medium

Abstract

The invention relates to an intelligent control method, system, equipment and medium for automatic discharging mining tunneling cutting picks, and the method comprises the following steps: monitoring the flowing state of coal rock slag in a spiral discharging channel in real time, collecting a channel pressure difference signal and a cutting pick vibration signal, and generating discharging state characteristic parameters; blocking risk quantification is carried out on the characteristic parameters, and a real-time blocking index is generated through weighted fusion calculation; based on the index, a cutting head rotating speed optimization adjustment amount is generated through a fuzzy reasoning mechanism; and finally, generating a rotating speed control instruction through dynamic amplitude limiting processing and sending the rotating speed control instruction to a variable-frequency driving system. By means of the method, real-time sensing and dynamic self-adaptive adjustment of the blockage risk of the discharging channel are achieved, the problem that the discharging channel is blocked due to coal rock property changes is effectively solved, the discharging efficiency and the stability of tunneling operation are improved, and the service life of cutting teeth is prolonged.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of heading machine control management, and particularly relates to an automatic discharging mine heading pick intelligent control method, system, equipment and medium. BACKGROUND

[0002] The mine heading pick is a key component directly involved in coal rock crushing in the heading equipment, and its working performance directly affects the heading efficiency and energy consumption. In order to improve the discharging efficiency, in recent years, a new structure of spiral discharging channel is designed in the pick, and the centrifugal force generated by the rotation of the pick is used to discharge the crushed coal rock slag along the channel, so as to reduce the resistance and wear caused by the accumulation of the slag. The pick with automatic discharging function depends on the speed control of the heading machine cutting head to realize the optimization of the discharging effect, and the effectiveness of the control method becomes a key factor to determine the discharging performance.

[0003] However, the existing control method is mostly based on the simple adjustment strategy of fixed threshold, and lacks real-time perception and dynamic response ability to the internal state of the discharging channel. Due to the complex and variable nature of coal rock in the mine, the fluidity of the slag has significant differences, and the control method with fixed parameters is difficult to adapt to such dynamic working conditions, which easily leads to the blockage of the discharging channel or the decrease of the discharging efficiency. Especially when encountering viscous rock or producing irregular slag, the existing method is difficult to adjust the working parameters in time, which not only affects the heading efficiency, but also may cause the overloading of the equipment, the abnormal wear of the pick and other chain problems due to the poor discharging. SUMMARY

[0004] Based on this, the purpose of the present application is to provide an automatic discharging mine heading pick intelligent control method, system, equipment and medium which can realize real-time perception and dynamic adaptive adjustment of the blockage risk of the discharging channel.

[0005] The purpose of the present application is realized by the following scheme:

[0006] In a first aspect, the present application provides an automatic discharging mine heading pick intelligent control method, comprising the following steps:

[0007] S1: Real-time monitoring of the flow state of the coal rock slag in the spiral discharging channel, generating discharging state characteristic parameters by collecting the pressure difference signal and the pick vibration signal in the channel;

[0008] S2: Quantifying the blockage risk of the discharging state characteristic parameters, generating a real-time blockage index of the discharging channel by weighted fusion calculation of the vibration signal peak value and the pressure difference signal with the preset threshold value;

[0009] S3: making a real-time blockage index of the discharge channel to make a discharge optimization decision, mapping the blockage index to a rotation speed adjustment strategy through a fuzzy inference mechanism according to a dynamic relationship between a rotation centrifugal force of the cutting pick and a discharge resistance, and generating an optimized adjustment amount of the rotation speed of the cutting head;

[0010] S4: performing dynamic amplitude limiting processing on the optimized adjustment amount of the rotation speed of the cutting head, superimposing the adjustment amount on the current rotation speed and limiting the superimposition in a safe working range, generating a rotation speed control instruction, and sending the rotation speed control instruction to a variable frequency driving system of the cutting head.

[0011] In one of the embodiments, the automatic discharge mining tunneling pick intelligent control method provided by the application specifically includes the following steps of S1:

[0012] S11: performing sliding window mean filtering processing on a differential pressure sensor signal arranged at an inlet and an outlet of the discharge channel, eliminating transient impact interference, and generating stable channel pressure difference data;

[0013] S12: performing time domain peak value maintaining processing on a three-axis vibration acceleration signal installed at a root of the cutting pick, extracting a maximum amplitude of the vibration signal, and generating a standardized vibration peak value parameter;

[0014] S13: performing multi-source data fusion processing on the channel pressure difference data and the vibration peak value parameter, performing linear combination according to a preset weight ratio, and generating a discharge state feature parameter.

[0015] In one of the embodiments, the automatic discharge mining tunneling pick intelligent control method provided by the application specifically includes the following steps of S2:

[0016] S21: performing normalization preprocessing on the discharge state feature parameter, calling a minimum-maximum scaling algorithm to linearly transform each feature parameter to the [0, 1] interval, and generating a standardized feature vector;

[0017] S22: performing weighted fusion calculation on the feature vector, dynamically adjusting the contribution degree of each feature in the feature vector by using an adaptive weight distribution algorithm, and generating a preliminary blockage risk evaluation value;

[0018] S23: performing time series smoothing processing on the preliminary blockage risk evaluation value, eliminating transient fluctuation interference in the evaluation value sequence through a first-order lag filter algorithm, and generating a real-time blockage index of the discharge channel.

[0019] In one of the embodiments, the automatic discharge mining tunneling pick intelligent control method provided by the application specifically includes the following steps of S3:

[0020] S31: performing fuzzy processing on the real-time blockage index of the discharge channel, converting the accurate value into a fuzzy language variable through a triangular membership function, and generating a fuzzy blockage state description;

[0021] S32: Perform rule matching processing on the fuzzified blockage state description, query a special rule library designed for the characteristics of the spiral discharge channel, and generate an activated control rule set;

[0022] S33: Perform inference operation processing on the activated control rules, calculate the output membership degree of each rule using the minimum-maximum inference method, and generate a fuzzy inference result;

[0023] S34: Perform rule strength adjustment processing on the fuzzy inference result, dynamically correct the rule confidence according to the real-time working condition, and generate an optimized fuzzy control output;

[0024] S35: Perform defuzzification processing on the fuzzy control output, calculate the weighted average value of each point in the output fuzzy set by the center of gravity method to obtain the accurate speed adjustment value, and generate the cutting head speed optimization adjustment amount.

[0025] In one embodiment, the present application provides a calculation formula for the speed adjustment value of an automatic discharge mine tunneling pick intelligent control method:

[0026]

[0027] wherein, is the speed adjustment value, is the jth element in the output universe, is the membership degree in the output fuzzy set B, and m is the total number of elements in the output universe.

[0028] In one embodiment, the S4 of the automatic discharge mine tunneling pick intelligent control method provided by the present application specifically includes the following steps:

[0029] S41: Perform safety boundary check processing on the cutting head speed optimization adjustment amount, determine the allowable speed adjustment range by combining the pick material strength and motor power characteristics, and generate a safety-limited speed adjustment amount;

[0030] S42: Perform dynamic compensation processing on the safety-limited speed adjustment amount, establish a system dynamic response model to predict the overshoot phenomenon in the speed adjustment process and calculate a feedforward compensation amount for compensating the speed fluctuation, and generate a speed set value with feedforward compensation;

[0031] S43: Perform protocol packaging processing on the speed set value with feedforward compensation, configure data frames according to the PROFIBUS-DP communication protocol, generate a speed control instruction, and send the speed control instruction to the cutting head variable frequency drive system.

[0032] In one of the embodiments, the application provides an intelligent control method for an automatic discharging mining tunneling pick, which specifically comprises the following steps in S43:

[0033] S421: performing feedforward compensation calculation on the speed adjustment amount after safety limitation, predicting system response based on a dynamic characteristic model of the discharging channel, and generating a feedforward compensation amount;

[0034] S422: performing superposition processing on the feedforward compensation amount and the speed adjustment amount, linearly superimposing the two according to a weight coefficient and considering system dynamic response characteristics, and generating a composite speed adjustment signal;

[0035] S423: performing filter smoothing processing on the composite speed adjustment signal, generating a smooth speed transition curve by using a trajectory planning algorithm, and generating a speed set value with feedforward compensation.

[0036] In a second aspect, the application provides an intelligent control system for an automatic discharging mining tunneling pick, which is configured with the following modules:

[0037] A discharging state monitoring module is configured to monitor the flow state of coal and rock debris in the spiral discharging channel in real time, generate discharging state characteristic parameters by collecting pressure difference signals and pick vibration signals in the channel, and perform real-time monitoring on the flow state of coal and rock debris in the channel.

[0038] A jam risk quantification module is configured to quantize the jam risk of the discharging state characteristic parameters, generate a real-time jam index of the discharging channel by performing weighted fusion calculation on the vibration signal peak value and the pressure difference signal respectively and the preset threshold value, and quantize the jam risk of the discharging state characteristic parameters.

[0039] A discharging optimization decision module is configured to make a discharging optimization decision on the real-time jam index of the discharging channel, map the jam index to a speed adjustment strategy according to the dynamic relationship between the centrifugal force of the pick and the discharging resistance by using a fuzzy inference mechanism, and generate a speed optimization adjustment amount of the cutting head.

[0040] A speed dynamic limiting module is configured to perform dynamic limiting processing on the speed optimization adjustment amount of the cutting head, superimpose the adjustment amount and the current speed and limit them within a safe working range, generate a speed control instruction, and send the speed control instruction to the frequency conversion driving system of the cutting head.

[0041] In a third aspect, the application provides a computer device, which comprises a memory and a processor, the memory stores a computer program, and the processor implements any of the above-mentioned intelligent control methods for an automatic discharging mining tunneling pick when executing the computer program.

[0042] In a fourth aspect, the application provides a computer readable storage medium, which stores a computer program, and the computer program is executed by a processor to implement any of the above-mentioned intelligent control methods for an automatic discharging mining tunneling pick.

[0043] In summary, the automatic discharging mine tunneling pick intelligent control method provided by the application can realize accurate perception of the flow state of coal and rock debris by real-time acquisition of the channel pressure difference and pick vibration signals, so as to timely find potential blockage risks; by weighted fusion and quantitative evaluation of multi-source signals, accurate blockage degree judgment basis can be established to provide reliable data support for subsequent control decisions; by introducing a fuzzy reasoning mechanism, complex nonlinear relationships can be converted into executable control strategies to realize adaptive adjustment of the cutting head speed according to real-time working conditions; finally, through dynamic limiting and safety checking, it can be ensured that the system always operates within a safe range, avoiding equipment damage caused by over-regulation. This closed-loop control method can effectively solve the problem that the traditional fixed parameter control method is difficult to adapt to complex working conditions, significantly improve the anti-blocking ability of the discharging channel, and ensure the continuous stability of the tunneling operation. At the same time, by maintaining the smooth discharging, the pick working resistance can be reduced, the abnormal wear caused by debris accumulation can be reduced, and the service life of the pick can be prolonged. In addition, the optimized discharging efficiency can also reduce equipment energy consumption and improve energy utilization efficiency, thereby achieving the goal of energy saving and consumption reduction. The entire control system has the characteristics of fast response, strong adaptability and high reliability, and provides reliable technical support for efficient, safe and stable operation of mine tunneling operations.

[0044] For better understanding and implementation, the application will be described in detail below with reference to the accompanying drawings. BRIEF DESCRIPTION OF DRAWINGS

[0045] Figure 1 A flowchart of an automatic discharging mine tunneling pick intelligent control method provided by an embodiment of the application is shown in the figure.

[0046] Figure 2 A flowchart of generating a speed control instruction provided by an embodiment of the application is shown in the figure.

[0047] Figure 3 A structural diagram of an automatic discharging mine tunneling pick intelligent control system provided by another embodiment of the application is shown in the figure. DETAILED DESCRIPTION

[0048] In order to facilitate the understanding of the application, the application will be described more fully below with reference to the related drawings. The preferred embodiments of the application are shown in the drawings. However, the application can be implemented in many different forms and is not limited to the embodiments described herein. On the contrary, the purpose of providing these embodiments is to make the disclosure of the application more thorough and comprehensive.

[0049] Unless otherwise defined, 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 application belongs. The terminology used in the description of the application herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the application. As used herein, the term "and / or" includes any and all combinations of one or more of the associated listed items.

[0050] In one embodiment, as shown in Figure 1 An intelligent control method for an automatic discharging mining tunneling pick is provided, and the method is applied to a terminal in this embodiment. It should be understood that the method can also be applied to a server, and can also be applied to a system including a terminal and a server, and is realized through the interaction of the terminal and the server. In this embodiment, the method includes the following steps:

[0051] S1: Real-time monitoring of the flow state of coal and rock debris in the spiral discharging channel, generating discharging state characteristic parameters by collecting pressure difference signals and pick vibration signals in the channel.

[0052] Specifically, the system realizes real-time sensing of the flow state of coal and rock debris in the spiral discharging channel through a special sensing device. The inlet section and the outlet section of the discharging channel are respectively provided with a differential pressure sensing device installed in an embedded manner. The probe of the sensing device is flush with the inner wall of the channel, so as to avoid interference with the normal flow of coal and rock debris. The sensing device adopts a fully sealed structure design, which can adapt to the high humidity, dust and strong impact working environment underground, and ensure stable operation under complex working conditions. The vibration sensing device is fixed to the position close to the working end of the pick by a threaded fastening method, and the sensing device is rigidly connected with the pick holder, so as to accurately capture the vibration signals generated by the pick cutting process and the impact of the debris on the channel wall. The signal cable of the vibration sensing device adopts an armored shielding structure, so as to reduce the influence of underground electromagnetic interference on signal transmission.

[0053] Further, the system adopts first-order low-pass filtering processing for the collected pressure difference original signals, removes high-frequency noise caused by air flow disturbance by setting a suitable cut-off frequency, and adopts wavelet threshold filtering processing for the vibration original signals, selects a specific wavelet basis and sets the decomposition layer number, effectively suppresses the clutter signals formed by the inherent vibration of the device and underground electromagnetic interference. After signal filtering, the system extracts peak value, effective value and kurtosis and other characteristics from the vibration signals, wherein the peak value directly reflects the intensity of the debris impacting the channel wall, and the kurtosis is used to distinguish the normal flow state from the impact vibration caused by local blockage; the instantaneous value, sliding mean and change rate and other characteristics are extracted from the pressure difference signals, wherein the instantaneous value reflects the size of the flow resistance in the channel, and the change rate is used to predict the development trend of the blockage, and the above characteristics are integrated to form a discharging state characteristic parameter set.

[0054] S2: Quantify the blockage risk of the discharge state characteristic parameters, generate the real-time blockage index of the discharge channel by weighting and fusing the vibration signal peak value and the pressure difference signal with the preset threshold value respectively.

[0055] Specifically, the system calibrates the preset threshold value through multi-condition test data. During the test process, multiple typical coal and rock types are selected, and the actual tunneling conditions are simulated in the laboratory. By gradually increasing the feed amount, a sample library of different blockage degrees is constructed, covering various states such as no blockage, slight blockage, moderate blockage, and severe blockage. The system statistically analyzes the vibration peak value and the pressure difference mean value in the sample library, removes abnormal data using a specific statistical criterion, and determines the baseline threshold value corresponding to different conditions. During tunneling, the system adjusts the baseline threshold value in real time using linear interpolation based on the coal and rock identification results or the clustering analysis results of the pressure difference mean value and the vibration peak value in the recent period of time, ensuring that the threshold value can adapt to the dynamic changes in coal and rock properties.

[0056] Preferably, the system can process the discharge state characteristic parameters using a dynamic weighting fusion algorithm, adjust the weight coefficient according to the difference in coal and rock fluidity, and keep the sum of the weight coefficients fixed. When the coal and rock fluidity is strong, the vibration signal is more sensitive to the blockage state, and the system accordingly increases the weight proportion of the vibration peak value. When the coal and rock fluidity is weak, the pressure difference signal is more sensitive to the blockage state, and the system accordingly increases the weight proportion of the pressure difference mean value. When the coal and rock properties cannot be clearly determined, the system evenly allocates the weight proportions of the two. The system integrates the results of comparing the vibration signal peak value and the pressure difference signal with the corresponding preset threshold value through the above weighting fusion calculation, generates the real-time blockage index of the discharge channel, and quantitatively reflects the blockage risk degree of the discharge channel. The index value range is within a certain interval, and the higher the value, the greater the blockage risk.

[0057] S3: Make discharge optimization decisions for the real-time blockage index of the discharge channel, map the blockage index to the rotation speed adjustment strategy through a fuzzy inference mechanism based on the dynamic relationship between the cutting tooth rotation centrifugal force and the discharge resistance, and generate the optimized adjustment amount of the cutting head rotation speed.

[0058] Specifically, the system establishes a dynamic relationship between the rotating centrifugal force of the pick and the discharge resistance based on mechanical analysis. The calculation of the centrifugal force involves physical quantities such as the equivalent mass of coal and rock debris, the angular velocity of the cutting head, and the rotating radius of the pick tip, among others. The equivalent mass of coal and rock debris is indirectly estimated through pressure difference signals, and the angular velocity of the cutting head and the rotating radius of the pick tip are determined based on the structural parameters of the equipment. The calculation of the discharge resistance involves physical quantities such as the friction coefficient between the debris and the channel wall, the gravity of the debris, the normal constraint force of the channel spiral surface, and the cross-sectional area of the discharge channel, among others. The friction coefficient is pre-set according to the type of coal and rock, and the cross-sectional area of the discharge channel is determined by the structural parameters of the equipment. The optimization goal of the system is to adjust the angular velocity of the cutting head so that the rotating centrifugal force of the pick meets a specific proportional relationship greater than the discharge resistance, thereby ensuring that the coal and rock debris can be smoothly discharged while avoiding increased energy consumption due to excessive rotational speed.

[0059] Preferably, the system can implement the mapping of the jam index to the rotational speed adjustment strategy using a Mamdani-type fuzzy reasoning mechanism. The real-time jam index of the discharge channel is taken as the input variable, which is defined within a specific interval, and the fuzzy subsets are divided into four categories: no jam, slight jam, moderate jam, and severe jam, with triangular distribution of the membership functions. The rotational speed adjustment rate is taken as the output variable, which is defined as the ratio of the rotational speed adjustment amount to the current cutting head rotational speed, and is defined within a specific interval, with the fuzzy subsets divided into four categories: maintain, slightly increase, moderately increase, and significantly increase, with trapezoidal distribution of the membership functions. The system establishes a fuzzy rule base containing multiple core rules, which is constructed based on the dynamic relationship between the rotating centrifugal force of the pick and the discharge resistance. Fuzzy reasoning is performed using the max-min composition method, and the precise rotational speed adjustment rate is obtained by defuzzification using the centroid method, and then the optimization adjustment amount of the cutting head rotational speed is calculated.

[0060] S4: Perform dynamic amplitude limiting processing on the optimization adjustment amount of the cutting head rotational speed, superimpose the adjustment amount and the current rotational speed, and limit it within the safe working range to generate a rotational speed control instruction and send it to the cutting head variable frequency drive system.

[0061] Specifically, the system determines the safe working range of the cutting head rotational speed based on the mechanical performance of the tunneling equipment and the rated parameters of the cutting head motor. The determination of the minimum safe rotational speed takes into account factors such as the helix angle of the discharge channel and the repose angle of coal and rock debris, ensuring that the centrifugal force generated by the pick rotation is greater than the axial component of the debris gravity at the minimum safe rotational speed, thereby preventing the accumulation of debris in the channel. The determination of the maximum safe rotational speed is based on the rated rotational speed of the cutting head motor and the load limit of the gear box, and a reasonable proportional relationship is set to ensure that the maximum safe rotational speed does not cause motor overload or gear box impact damage.

[0062] The system monitors the load state of the heading machine in real time. When it is detected that the motor current reaches a certain proportion of the rated current, the highest safe rotating speed is automatically adjusted downward until the motor current returns to below the set proportion, so as to realize dynamic correction of the safe working range. The system superimposes the target rotating speed optimization adjustment amount and the current rotating speed to obtain a target rotating speed. If the target rotating speed is lower than the minimum safe rotating speed, the minimum safe rotating speed is taken as the final target rotating speed. If the target rotating speed is higher than the highest safe rotating speed, the highest safe rotating speed is taken as the final target rotating speed. If the target rotating speed is within the safe working range, the target rotating speed remains unchanged.

[0063] Further, the system encodes the rotating speed control instruction in a pulse width modulation mode. The encoded instruction contains information such as the target rotating speed and the acceleration time. The acceleration time is dynamically set according to the rotating speed adjustment amount. When the rotating speed adjustment amount is small, a shorter acceleration time is set. When the rotating speed adjustment amount is large, a longer acceleration time is set, so as to ensure the stability of the rotating speed adjustment process. The system transmits the encoded rotating speed control instruction to the cutting head variable frequency driving system through an industrial bus. A specific baud rate is used to ensure the real-time performance of the instruction. The variable frequency driving system uses a vector control algorithm to adjust the output frequency according to the received control instruction, realizes stable closed-loop control of the cutting head rotating speed, and thus completes the entire discharge optimization control process.

[0064] In summary, the automatic discharge intelligent control method for the mine heading pick provided by the present application can realize accurate perception of the flow state of coal and rock debris by real-time acquisition of the channel pressure difference and pick vibration signals, so as to timely find potential blockage risks. By weighted fusion and quantitative evaluation of multiple source signals, accurate blockage degree judgment basis can be established to provide reliable data support for subsequent control decisions. By introducing a fuzzy reasoning mechanism, complex nonlinear relationships can be converted into executable control strategies to realize adaptive adjustment of the cutting head rotating speed according to real-time working conditions. Finally, through dynamic limiting and safety checking, it can be ensured that the system always operates within a safe range, avoiding equipment damage caused by over-regulation. This closed-loop control method can effectively solve the problem that the traditional fixed parameter control method is difficult to adapt to complex working conditions, significantly improve the anti-blocking ability of the discharge channel, and ensure the continuous stability of the heading operation. At the same time, by maintaining the smooth discharge, the pick working resistance can be reduced, the abnormal wear caused by debris accumulation can be reduced, and the service life of the pick can be prolonged. In addition, the optimized discharge efficiency can also reduce equipment energy consumption and improve energy utilization efficiency, thereby achieving the goal of energy saving and consumption reduction. The entire control system has the characteristics of fast response, strong adaptability and high reliability, and provides reliable technical support for efficient, safe and stable operation of mine heading operations.

[0065] In one embodiment, the S1 of the automatic discharge intelligent control method for the mine heading pick provided by the present application specifically includes the following steps:

[0066] S11: The differential pressure sensor signals arranged at the inlet and outlet of the discharge passage are subjected to sliding window mean filtering processing to eliminate transient impact interference and generate stable passage pressure difference data.

[0067] Specifically, the system receives the original signals transmitted by the differential pressure sensors arranged at the inlet and outlet of the discharge passage, which contain pressure changes caused by the flow of coal and rock debris and transient impact interference signals. The application of the sliding window mean filtering algorithm is based on the change law of the pressure signals, and the length of the sliding window is determined according to the change period of the pressure signals, which is obtained through the system's statistical analysis of historical pressure signals, ensuring that the window can completely cover the duration of the transient impact interference and avoid incomplete filtering of interference signals or excessive smoothing of effective signals. During the filtering process, the system continuously intercepts the original signals in time series, and each time a fixed length of signal data is intercepted to form a window. The starting position of the window moves along the time axis, realizing point-by-point processing of the entire original signal sequence.

[0068] For all signal data in each window, the system performs mean calculation operation, and assigns the calculated result to the center time of the window as the filtering output value. Through this continuous window sliding and mean replacement, the transient impact interference in the original signal is gradually eliminated. Through this filtering process, the system removes the invalid interference components in the original signal and retains the core pressure change information that can reflect the flow resistance of the coal and rock debris in the discharge passage, generating continuous and smooth passage pressure difference data that can stably reflect the flow resistance state in the discharge passage. This provides reliable basic data support for subsequent multi-source data fusion processing, ensuring that the fusion result can accurately associate with the actual working state of the discharge passage.

[0069] S12: The triaxial vibration acceleration signals installed at the root of the cutting tooth are subjected to time domain peak value retention processing to extract the maximum amplitude of the vibration signals and generate standardized vibration peak value parameters.

[0070] Specifically, the system receives the triaxial vibration acceleration signals transmitted by the vibration sensing device installed at the root of the cutting tooth, which is formed by the superposition of multiple vibration components such as vibration generated by the cutting tooth cutting coal and rock, vibration generated by the impact of debris on the passage wall, and inherent vibration of the device. The system performs time domain peak value retention processing on the triaxial vibration acceleration signals. The setting of the peak detection period is based on the working period of the cutting tooth and the frequency characteristics of the debris impact, which is determined through the system's analysis of the motion law of the cutting tooth during operation, ensuring that the maximum amplitude of the impact vibration can be completely captured within each detection period. Within each detection period, the system continuously monitors the instantaneous amplitude of the triaxial vibration acceleration signals and records the maximum amplitude of each axis signal in real time within the period, avoiding the omission of critical impact information.

[0071] After the detection cycle ends, the system comprehensively processes the maximum amplitudes of the three-axis signals. The processing process eliminates the differences in the responses of the signals of the axes caused by different installation angles according to the installation layout of the vibration sensing device and the stress direction characteristics of the cutting tooth, so that the processing results can uniformly reflect the impact intensity of the cutting tooth. The system generates a standardized vibration peak parameter through the above processing. The parameter integrates the core information of the three-axis vibration signals and can collectively reflect the impact intensity of the cutting tooth during operation. The impact intensity is directly related to the flow state of the crushed slag in the discharge passage. When the flow of the crushed slag is blocked, the impact intensity will change accordingly. Therefore, the parameter provides key data basis for subsequent judgment of the jamming risk, ensuring that the system can timely perceive the state change in the discharge passage.

[0072] S13: Perform multi-source data fusion processing on the channel pressure difference data and the vibration peak parameter, linearly combine them according to a preset weight ratio, and generate a discharge state feature parameter.

[0073] Specifically, after the system obtains the channel pressure difference data and the vibration peak parameter, it determines the ratio by analyzing the change sensitivity of the pressure difference signal and the vibration peak parameter under different coal and rock fluidity conditions, ensures that the signal component more sensitive to the change of the jamming state occupies a reasonable proportion in the fusion result, and makes the fusion result accurately reflect the subtle change of the jamming state. The fusion processing adopts a linear combination algorithm. The system first performs multiplication operation on the channel pressure difference data and the corresponding weight, then performs multiplication operation on the vibration peak parameter and the corresponding weight, and then performs summation operation on the two product results to obtain the fused comprehensive feature value. Since the channel pressure difference data and the vibration peak parameter belong to different physical quantities, there is a dimensional difference between them, and direct fusion will cause the result to be distorted. Therefore, the system performs standardization processing on the fused comprehensive feature value, converts the comprehensive feature value to a unified numerical interval through mathematical transformation according to the value range and change amplitude of the two types of parameters, eliminates the influence of the dimensional difference of different physical quantities, and makes the parameters consistent and comparable.

[0074] Through the above multi-source data fusion and standardization processing, the system generates a discharge state feature parameter that can comprehensively reflect the flow state in the discharge passage. The parameter integrates the flow resistance information reflected by the pressure difference data and the impact intensity information reflected by the vibration peak parameter. The two types of information complement each other and respectively depict the working state in the discharge passage from different dimensions, providing comprehensive and reliable data support for subsequent quantification of the jamming risk and ensuring the accuracy and comprehensiveness of the jamming risk judgment.

[0075] In one of the embodiments, the automatic discharge mine-used tunneling cutting tooth intelligent control method provided by the application comprises the following steps:

[0076] S21: Normalization preprocessing is performed on the discharge state feature parameters, and a minimum-maximum scaling algorithm is called to linearly transform each feature parameter to the interval [0, 1] to generate a standardized feature vector.

[0077] Specifically, after the system receives the discharge state feature parameters, normalization preprocessing is performed. The discharge state feature parameters are composed of indexes with different physical meanings, and the dimensions of each index are different. Direct fusion calculation will cause result deviation. The system calls the minimum-maximum scaling algorithm, first performs statistics on the historical data of each feature parameter, and obtains the value range of each feature parameter in the running period. The algorithm execution process follows a specific mathematical logic, and each feature parameter is mapped to a unified interval through linear transformation. The transformation formula is:

[0078]

[0079] Among them, represents the original feature parameter value, represents the minimum value of the historical value of the feature parameter, represents the maximum value of the historical value of the feature parameter, represents the transformed standardized feature value. The system calculates each feature parameter one by one according to the formula, ensuring that all feature parameters are in the same interval after transformation. After calculation, the system arranges all standardized feature values in a predetermined order to form a feature vector with the same dimension as the original feature parameter.

[0080] S22: Weighted fusion calculation is performed on the feature vector, and an adaptive weight distribution algorithm is used to dynamically adjust the contribution of each feature in the feature vector to generate a preliminary blockage risk assessment value.

[0081] Specifically, after the system obtains the standardized feature vector, an adaptive weight distribution algorithm is used. This algorithm dynamically adjusts the weight based on the correlation degree of each feature in the feature vector and the blockage state of the discharge channel. The system determines the contribution of each feature to the blockage risk assessment by analyzing the change rule of each feature in the feature vector in the historical blockage event. The weight distribution process is based on the correlation analysis results of the features and the blockage state. Features with higher correlation obtain higher weights, and features with lower correlation obtain lower weights. Weighted fusion calculation follows linear combination logic, and the formula is:

[0082]

[0083] Among them, represents the preliminary blockage risk assessment value, represents the number of features in the feature vector, represents the weight coefficient of the i-th feature, and the sum of all weight coefficients satisfies a predetermined condition, The i-th normalized feature value in the representative feature vector. The system performs a weighted summation operation on all elements in the feature vector according to the formula, and calls the output result of the adaptive weight distribution algorithm in real time during the operation process, so as to ensure that the weight coefficient is dynamically updated with the change of the working condition. Through the operation, the system converts the multi-dimensional feature vector into a single-dimensional preliminary blockage risk assessment value, and realizes the preliminary quantification of the blockage risk.

[0084] S23: Time series smoothing processing is performed on the preliminary blockage risk assessment value, and a first-order lag filter algorithm is used to eliminate instantaneous fluctuation interference in the assessment value sequence, and a real-time blockage index of the discharge passage is generated.

[0085] Specifically, after the system generates the preliminary blockage risk assessment value, time series smoothing processing is performed. The preliminary blockage risk assessment value is affected by instantaneous working condition fluctuations and has irregular fluctuations. Directly using the preliminary blockage risk assessment value as the blockage index will affect the accuracy of subsequent decision-making. The system uses a first-order lag filter algorithm to process the preliminary blockage risk assessment value sequence. The algorithm eliminates instantaneous fluctuation interference by correlating the current assessment value with the historical assessment value. The filtering formula is:

[0086]

[0087] Among them, represents the real-time blockage index, represents the filtering coefficient, represents the current preliminary blockage risk assessment value, represents the blockage index after filtering at the last moment. The system calculates the preliminary blockage risk assessment value at each moment according to the formula, and keeps the filtering coefficient stable during the calculation process, so as to ensure the consistency of the filtering effect. Through the algorithm, the system converts the continuous preliminary blockage risk assessment value sequence into a smooth real-time blockage index sequence. The real-time blockage index at each moment not only reflects the blockage risk state under the current working condition, but also inherits the trend characteristics of the historical data, avoiding misjudgment caused by instantaneous fluctuations.

[0088] In one of the embodiments, the S3 of the automatic discharge mine tunneling pick intelligent control method provided by the application specifically includes the following steps:

[0089] S31: Fuzzy processing is performed on the real-time blockage index of the discharge passage, and a triangular membership function is used to convert the accurate value into a fuzzy language variable, and a fuzzy blockage state description is generated.

[0090] Specifically, the system collects historical data of the discharge channel blockage index during the tunneling process, combines the structural characteristics of the discharge channel and the flow law of the crushed slag, determines the domain range of the real-time blockage index of the discharge channel, which covers the whole working condition interval from no blockage to severe blockage, and ensures that all possible blockage states can be completely characterized. The system performs fuzzy subset division based on the domain range, and the divided fuzzy subsets correspond to no blockage, slight blockage, moderate blockage, severe blockage and other fuzzy language variables, respectively. The division boundaries of each fuzzy subset are determined by analyzing the transition critical points of the blockage state in the historical data, ensuring that there is a reasonable overlapping area between adjacent fuzzy subsets. To realize the conversion from the precise value to the fuzzy language variable, the system performs fuzzy processing using a triangular membership function, and the expression of the triangular membership function is:

[0091]

[0092] wherein x is the precise value of the real-time blockage index of the discharge channel, is the membership degree of x belonging to the fuzzy subset A, is the left boundary value of the fuzzy subset A, which is determined by the minimum observed value corresponding to the blockage state in the historical data, b is the peak value of the fuzzy subset A, which corresponds to the most common index value under the blockage state in the historical data, and c is the right boundary value of the fuzzy subset A, which is determined by the maximum observed value corresponding to the blockage state in the historical data. The system substitutes the real-time blockage index precise value into the above formula, calculates the membership degree in each fuzzy subset, and then compares the membership degree values to select the fuzzy language variable corresponding to the fuzzy subset with the largest membership degree, thereby generating the fuzzy blockage state description, which provides standardized input data for the subsequent rule matching process.

[0093] S32: Perform rule matching processing on the fuzzy blockage state description, query the special rule base designed for the characteristics of the spiral discharge channel, and generate the activated control rule set.

[0094] Specifically, the system pre-constructs a special rule base for the characteristics of the spiral discharge channel. The construction process of the rule base is based on the dynamic balance relationship between the rotating centrifugal force of the cutting tooth and the discharge resistance. The system collects discharge test data under different coal and rock conditions, including blockage state, speed adjustment effect and other information, extracts effective control logic through data mining methods, and forms each control rule in the rule base. Each control rule adopts the logic structure of “if - then”, the antecedent is composed of one or more fuzzy blockage state descriptions, which correspond to different combinations of blockage degree, and the consequent is the fuzzy language description of the corresponding speed adjustment direction and adjustment strength, which clearly defines the speed control strategy to be taken under different blockage states.

[0095] After the system fuzzifies the congestion state description, the description is compared with the antecedents of each control rule in the rule base one by one. In the matching process, the system calculates the compatibility of the fuzzified congestion state description with the antecedent of each rule. The calculation of the compatibility is based on the intersection operation of fuzzy subsets. The compatibility value is obtained by calculating the minimum value of the membership degrees of two fuzzy subsets at each domain point and taking the maximum value. The system compares the calculated compatibility with the preset condition. When the compatibility reaches the preset condition, the corresponding control rule is activated. The system collects all activated control rules to form an activated control rule set, ensuring that subsequent reasoning operations can comprehensively cover all reasonable control strategies under the current congestion state and avoiding the control limitations caused by the application of a single rule.

[0096] S33: Perform reasoning operation processing on the activated control rules. The minimum-maximum reasoning method is used to calculate the output membership degrees of each rule to generate a fuzzy reasoning result.

[0097] Specifically, the system performs reasoning operation on the activated control rule set. The minimum-maximum reasoning method is used to realize the mapping from fuzzy input to fuzzy output, ensuring the logic and accuracy of the reasoning process. For each activated control rule, the system extracts all input fuzzy subsets contained in the antecedent. The system obtains the membership degree value corresponding to each input fuzzy subset by querying the calculation result of step S31. Then, the minimum value of these membership degree values is calculated by applying the minimum operation. The minimum value is the trigger strength of the rule. The calculation formula of the trigger strength is:

[0098]

[0099] wherein, is the trigger strength of the i-th activated rule, is the membership degree of the k-th input fuzzy subset, and n is the number of input fuzzy subsets contained in the antecedent of the rule.

[0100] Further, the system takes the trigger strength of each rule as the upper limit of the membership degree of the consequent fuzzy subset of the rule. The consequent fuzzy subset is truncated, that is, if the membership degree of each domain point in the consequent fuzzy subset is greater than the corresponding trigger strength, the membership degree of the point is adjusted to the trigger strength. If the membership degree is less than or equal to the trigger strength, the original value remains unchanged. Through this processing, it is ensured that the rule output is consistent with the degree of adaptation of the antecedent. Subsequently, the system performs set union operation on all truncated output fuzzy subsets. For each point in the output domain, the maximum value of the membership degrees of all truncated output fuzzy subsets at the point is taken as the final membership degree of the point to generate a fuzzy reasoning result that synthesizes all activated rules. The result is presented in the form of a fuzzy set, covering all possible speed adjustment strategies and corresponding membership degrees under the current congestion state.

[0101] S34: Rule strength adjustment processing is performed on the fuzzy inference result, the rule confidence is dynamically corrected according to the real-time working condition, and the optimized fuzzy control output is generated.

[0102] Specifically, the system adjusts the rule strength of the fuzzy inference result, dynamically corrects the confidence of the activated rule, and makes the control output adapt to the dynamic change of the downhole coal and rock properties. The system collects key working condition parameters that affect the discharge state in real time, including the channel pressure difference change rate, the vibration peak change trend and the current load state of the cutting head. These parameters are continuously obtained and transmitted to the inference module through corresponding sensing devices, ensuring the real-time and accuracy of the parameters. The system establishes a confidence correction model based on the correlation between real-time working condition parameters and rule confidence, dynamically adjusts the rule confidence through the change amount of the working condition parameters, and the calculation formula of the confidence correction is:

[0103]

[0104] wherein, is the corrected confidence of the i th rule, is the original trigger strength of the rule, k is the correction coefficient, and the correction coefficient is determined by analyzing the influence of the change of the working condition parameters on the adaptability of the control rule, is the change amount of the real-time working condition parameter, which is obtained by calculating the difference between the current working condition parameter and the historical stable working condition parameter.

[0105] Further, the system reassigns the corrected confidence to the corresponding output fuzzy subset, replaces the original trigger strength, updates the fuzzy inference result, i.e., recalculates the membership degree of each output universe point, so that the membership degree of the output fuzzy subset can accurately reflect the influence of the real-time working condition on the control rule. By dynamically correcting the rule confidence, the system can respond to the control demand adjustment caused by the change of the working condition in time, enhance the adaptability to complex and variable working conditions, avoid control lag or control excess caused by the change of the working condition, and ensure the real-time and accuracy of the rotation speed adjustment strategy.

[0106] S35: Defuzzification processing is performed on the fuzzy control output, the weighted average value of each point in the output fuzzy set is calculated by the barycenter method to obtain the accurate rotation speed adjustment value, and the cutting head rotation speed optimization adjustment amount is generated.

[0107] Specifically, the system performs defuzzification processing on the optimized fuzzy control output, and converts the fuzzy output set into an accurate speed adjustment value by using the barycentric method, to ensure the executability of the control instruction. The defuzzification process first determines the output universe, and the system determines the range of the output universe according to the adjustable range of the cutting head speed, in combination with the mechanical performance parameters of the tunneling equipment and the rated parameters of the cutting head motor, to ensure that the range can cover all possible speed adjustment cases. The elements in the output universe are generated by uniform division, to ensure that the points in the universe are reasonably distributed and can accurately represent different speed adjustment values. The system calculates the membership degrees of the output fuzzy set on each element in the universe, and calculates the accurate value by using the barycentric method. The formula for calculating the speed adjustment value is as follows:

[0108]

[0109] wherein, is the speed adjustment value, is the jth element in the output universe, is the membership degree in the output fuzzy set B, and m is the total number of elements in the output universe. The system performs operation according to the formula, first performs cumulative calculation on the numerator part, multiplies each and the corresponding and then sums them up, and then performs cumulative calculation on the denominator part, sums up all , and then divides the cumulative result of the numerator by the cumulative result of the denominator to obtain the accurate speed adjustment value. During the calculation process, the system uses point-by-point cumulative calculation to ensure the operation accuracy and avoid the influence of numerical errors on the control effect.

[0110] In one embodiment, as shown in Figure 2 , the intelligent control method for the automatic discharging mining tunneling pick provided by the present application specifically comprises the following steps:

[0111] S41: performing safety boundary check processing on the optimized speed adjustment value of the cutting head, determining the allowable speed adjustment range in combination with the material strength of the pick and the power characteristics of the motor, and generating the speed adjustment value after safety limitation.

[0112] Specifically, the system collects the mechanical parameters related to the material strength of the pick and the power characteristics of the motor, and these parameters are used as the basic data for safety boundary check. The system determines the allowable speed adjustment range in combination with the two types of parameters, and the determination of the range needs to meet the requirements that the stress borne by the pick material during speed change does not exceed the strength limit of the material itself, and the output power of the motor does not exceed the characteristic limit of the motor itself. The core expression of the safety boundary check is as follows:

[0113]

[0114] wherein, representing the minimum allowable speed adjustment range, representing the maximum allowable speed adjustment range. The system compares the optimized speed adjustment amount of the cutting head with the allowable speed adjustment range. If the optimized adjustment amount is within the range, it is directly used as the speed adjustment amount after safety limitation. If the optimized adjustment amount is lower than , the speed adjustment amount after safety limitation is . If the optimized adjustment amount is higher than , the speed adjustment amount after safety limitation is . Through this process, the system ensures that the speed adjustment will not cause the cutting tooth material to be damaged due to excessive stress, nor will it cause the motor to malfunction due to excessive power.

[0115] S42: Perform dynamic compensation processing on the speed adjustment amount after safety limitation, establish a system dynamic response model to predict the overshoot phenomenon in the speed adjustment process and calculate the feedforward compensation amount for compensating the speed fluctuation, and generate a speed set value with feedforward compensation.

[0116] Specifically, the speed set value with feedforward compensation is obtained through the following steps:

[0117] S421: Perform feedforward compensation calculation on the speed adjustment amount after safety limitation, predict the system response based on the discharge channel dynamic characteristic model, and generate a feedforward compensation amount.

[0118] Specifically, the system constructs a discharge channel dynamic characteristic model, which is established based on the structural characteristics of the discharge channel, the flow law of coal and rock debris, and the dynamics characteristics of the cutting head driving system, covering factors such as the variation law of debris flow resistance in the channel, the dynamic response characteristics of the transmission mechanism, and the inertia parameters of the cutting head. The system inputs the speed adjustment amount after safety limitation into the model, predicts the actual response of the system during the speed adjustment process through model operation, and focuses on predicting the overshoot amount and response lag amount that may occur before the speed reaches the target value. The calculation formula of the feedforward compensation amount is:

[0119]

[0120] wherein, represents the feedforward compensation amount, represents the transfer function of the discharge channel dynamic characteristic model, represents the speed adjustment amount after safety limitation. The transfer function The construction is based on system identification method, and the expression reflects the dynamic response characteristics of the system in the frequency domain by analyzing the mapping relationship between the input and output data. The feedforward compensation amount calculated by the system can offset the deviation caused by the dynamic characteristics of the system in the speed adjustment process in advance, and provides compensation basis for the generation of subsequent composite speed adjustment signal.

[0121] S422: superimpose the feedforward compensation amount and the speed adjustment amount, linearly superimpose them according to the weight coefficient, and consider the dynamic response characteristics of the system to generate a composite speed adjustment signal.

[0122] Specifically, the system determines the weight coefficients of the feedforward compensation amount and the speed adjustment amount after safety limitation respectively, and the determination of the weight coefficients is based on the dynamic response characteristics of the system, which is set by analyzing the influence degree of the two on the final speed control effect, to ensure that the weight distribution is adapted to the dynamic response law of the system. The system uses a linear superposition algorithm to operate the feedforward compensation amount and the speed adjustment amount after safety limitation, and fully considers the dynamic response characteristics of the system in the superposition process, so that the superposition result can adapt to the dynamic parameters such as inertia and damping of the system. The calculation formula of linear superposition is:

[0123]

[0124] Among them, represents the composite speed adjustment signal, represents the weight coefficient of the speed adjustment amount after safety limitation, represents the weight coefficient of the feedforward compensation amount, and satisfies , represents the speed adjustment amount after safety limitation, represents the feedforward compensation amount. The system combines the basic amount and the compensation amount of speed adjustment organically through the superposition operation to generate a composite speed adjustment signal that can balance the adjustment accuracy and system adaptability.

[0125] S423: filter and smooth the composite speed adjustment signal, generate a smooth speed transition curve using a trajectory planning algorithm, and generate a speed set value with feedforward compensation.

[0126] Specifically, the system uses a trajectory planning algorithm to filter and smooth the composite speed adjustment signal, which is designed based on the speed change rate and acceleration constraints allowed by the system, aiming to eliminate the instantaneous fluctuation components in the composite speed adjustment signal and generate a smooth speed transition curve. The core expression of the trajectory planning algorithm is:

[0127]

[0128] Among them, represents the speed transition curve changing with time, representative composite speed adjustment signal, representative trajectory planning function. The trajectory planning function The design follows the principle of smooth transition of speed, and the change law matches the dynamic response characteristics of the system, ensuring that the change rate and acceleration are always within the system allowed range during the transition of speed from the current value to the target value. The system processes the composite speed adjustment signal through the algorithm, converting the discrete adjustment signal into a continuous and smooth speed transition curve. This curve can avoid the impact of sudden speed changes on the equipment, while ensuring the efficiency of the adjustment process. Finally, the system generates a speed set value with feedforward compensation based on the speed transition curve.

[0129] S43: protocol encapsulation processing is performed on the speed set value with feedforward compensation, the data frame is configured according to the PROFIBUS-DP communication protocol, the speed control instruction is generated and sent to the cutting head variable frequency drive system.

[0130] Specifically, the system performs protocol encapsulation processing on the speed set value with feedforward compensation, determines the structure and composition of the data frame according to the specification requirements of the PROFIBUS-DP communication protocol. The data frame contains address field, control field, data field and check field, among which the data field specially stores the information related to the speed set value with feedforward compensation. The system encodes the speed set value according to the format specified by the protocol, converts it into a data format that meets the protocol requirements, and fills it into the data field of the data frame. The address field is used to identify the communication address of the cutting head variable frequency drive system, ensuring that the data frame can be accurately transmitted to the target device; the control field is used to define the control instruction of data transmission, and clearly defines the transmission type and processing requirements of the data frame; the check field is used to check the integrity of the data frame, and the system uses the cyclic redundancy check algorithm to calculate the check value and fill it into the field. After the data frame configuration is completed, the system sends the speed control instruction to the cutting head variable frequency drive system through the pre-set communication interface, and the communication process strictly follows the transmission specification of the PROFIBUS-DP protocol, ensuring the accuracy and reliability of the instruction transmission, so that the variable frequency drive system can execute the corresponding speed adjustment operation according to the received control instruction, and realize the precise control of the cutting head speed.

[0131] It should be understood that although the steps in the flowcharts of the embodiments described above are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the embodiments described above may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the steps or stages of other steps.

[0132] Based on the same inventive concept, this application also provides an intelligent control system for automatic material discharge mining cutter picks to implement the aforementioned intelligent control method for automatic material discharge mining cutter picks. The solution provided by this system is similar to the solution described in the above method. Therefore, the specific limitations of one or more embodiments of the intelligent control system for automatic material discharge mining cutter picks provided below can be found in the limitations of the intelligent control method for automatic material discharge mining cutter picks described above, and will not be repeated here.

[0133] Preferably, such as Figure 3 As shown, the present invention provides an intelligent control system 500 for automatic material discharge mining cutting picks, which is configured with the following modules:

[0134] The discharge status monitoring module 510 is used to monitor the flow status of coal and rock debris in the spiral discharge channel in real time. It generates discharge status characteristic parameters by collecting pressure difference signals and cutting tooth vibration signals in the channel.

[0135] The blockage risk quantification module 520 is used to quantify the blockage risk of the discharge state characteristic parameters. It generates a real-time blockage index of the discharge channel by weighting and fusing the vibration signal peak value and pressure difference signal with preset thresholds respectively.

[0136] The material discharge optimization decision module 530 is used to make material discharge optimization decisions based on the real-time blockage index of the discharge channel. According to the dynamic relationship between the centrifugal force of the cutting tooth rotation and the discharge resistance, the blockage index is mapped to the speed adjustment strategy through a fuzzy reasoning mechanism to generate the cutting head speed optimization adjustment amount.

[0137] The speed dynamic limiting module 540 is used to dynamically limit the speed optimization adjustment of the cutting head. By superimposing the adjustment amount with the current speed and limiting it within the safe working range, a speed control command is generated and sent to the cutting head frequency conversion drive system.

[0138] Preferably, the discharge state monitoring module 510 provided by the application is configured with the following units:

[0139] A pressure signal filtering unit is configured to perform sliding window mean filtering processing on the differential pressure sensor signal arranged at the inlet and outlet of the discharge channel, eliminate transient impact interference, and generate stable channel pressure difference data.

[0140] A vibration peak extraction unit is configured to perform time-domain peak holding processing on the three-axis vibration acceleration signal installed at the root of the cutting tooth, extract the maximum amplitude of the vibration signal, and generate a standardized vibration peak parameter.

[0141] A multi-source data fusion unit is configured to perform multi-source data fusion processing on the channel pressure difference data and the vibration peak parameter, linearly combine them according to a preset weight ratio, and generate a discharge state feature parameter.

[0142] Preferably, the blockage risk quantification module 520 provided by the application is configured with the following units:

[0143] A feature normalization processing unit is configured to perform normalization preprocessing on the discharge state feature parameter, call a min-max scaling algorithm to linearly transform each feature parameter to the [0, 1] interval, and generate a standardized feature vector.

[0144] A feature weighted fusion unit is configured to perform weighted fusion calculation on the feature vector, dynamically adjust the contribution of each feature in the feature vector by using an adaptive weight distribution algorithm, and generate a preliminary blockage risk evaluation value.

[0145] A blockage index smoothing unit is configured to perform time series smoothing processing on the preliminary blockage risk evaluation value, eliminate transient fluctuation interference in the evaluation value sequence by using a first-order lag filter algorithm, and generate a real-time blockage index of the discharge channel.

[0146] Preferably, the discharge optimization decision module 530 provided by the application is configured with the following units:

[0147] A blockage index fuzzification unit is configured to perform fuzzification processing on the real-time blockage index of the discharge channel, convert the exact value into a fuzzy language variable by using a triangular membership function, and generate a fuzzified blockage state description.

[0148] A fuzzy rule matching unit is configured to perform rule matching processing on the fuzzified blockage state description, query a special rule library designed for the characteristics of the spiral discharge channel, and generate an activated control rule set.

[0149] A fuzzy reasoning operation unit is configured to perform reasoning operation processing on the activated control rule, calculate the output membership degree of each rule by using a minimum-maximum reasoning method, and generate a fuzzy reasoning result.

[0150] A rule strength adjustment unit is configured to perform rule strength adjustment processing on the fuzzy inference result, dynamically correct the rule confidence according to the real-time working condition, and generate an optimized fuzzy control output;

[0151] A control output de-fuzzification unit is configured to perform de-fuzzification processing on the fuzzy control output, calculate the weighted average value of each point in the fuzzy set by the barycentric method to obtain an accurate speed adjustment value, and generate a cutting head speed optimization adjustment value.

[0152] Preferably, the speed dynamic limiting module 540 provided by the present application is configured with the following units:

[0153] A speed safety verification unit is configured to perform safety boundary verification processing on the cutting head speed optimization adjustment value, determine the allowable speed adjustment range in combination with the pick material strength and motor power characteristics, and generate a safety-limited speed adjustment value;

[0154] A speed dynamic compensation unit is configured to perform dynamic compensation processing on the safety-limited speed adjustment value, establish a system dynamic response model to predict the overshoot phenomenon in the speed adjustment process and calculate a feedforward compensation value for compensating the speed fluctuation, and generate a speed set value with feedforward compensation;

[0155] A speed instruction packaging unit is configured to perform protocol packaging processing on the speed set value with feedforward compensation, configure a data frame according to the PROFIBUS-DP communication protocol, generate a speed control instruction, and send the speed control instruction to the cutting head variable frequency drive system.

[0156] Preferably, the speed dynamic compensation unit includes a feedforward compensation calculation subunit, a compensation value superposition processing subunit, and a signal filtering and smoothing subunit. The feedforward compensation calculation subunit is configured to perform feedforward compensation calculation on the safety-limited speed adjustment value, predict the system response based on the dynamic characteristic model of the discharge channel, and generate a feedforward compensation value. The compensation value superposition processing subunit is configured to perform superposition processing on the feedforward compensation value and the speed adjustment value, linearly superimpose the two values with a weight coefficient, and consider the system dynamic response characteristics to generate a composite speed adjustment signal. The signal filtering and smoothing subunit is configured to perform filtering and smoothing processing on the composite speed adjustment signal, generate a smooth speed transition curve using a trajectory planning algorithm, and generate a speed set value with feedforward compensation.

[0157] In one embodiment, the present application further provides a computer device including a memory and a processor, the memory storing a computer program, and the processor implementing the automatic discharge mining heading pick intelligent control method described above when executing the computer program.

[0158] In one embodiment, the application further provides a computer readable storage medium, having stored thereon a computer program, which, when executed by a processor, implements the automatic material arranging intelligent control method of the mining cutting pick described above.

[0159] In the description of the present specification, the description of the terms "one embodiment", "some embodiments", "an example", "a specific example" or "some examples" means that the specific features, structures, materials or characteristics described in connection with the embodiment or example are included in at least one embodiment or example of the present application. Moreover, the specific features, structures, materials or characteristics described can be combined in any appropriate manner in any one or more embodiments or examples. In addition, different embodiments or examples described in the present specification and the features of different embodiments or examples can be combined and combined by those skilled in the art without contradiction.

[0160] For the device embodiment, since it basically corresponds to the method embodiment, the relevant part is described in the part of the method embodiment. The device embodiment described above is only schematic, wherein the components described as separate components can or can not be physically separate, and the components displayed as a unit can or can not be a physical unit, i.e. can be located in one place, or can be distributed to multiple network units. Part or all of the modules can be selected to achieve the purpose of the present disclosure according to the actual needs. Those skilled in the art can understand and implement it without creative labor.

[0161] The above is only a specific embodiment of the present application, but the protection scope of the present application is not limited to this. Any skilled person in the art can easily think of various changes or replacements within the technical range disclosed in the present application, which should be covered in the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claims.

Claims

1. A method for intelligent control of automatic material discharge mining cutting picks, characterized in that, Includes the following steps: S1: Real-time monitoring of the flow state of coal and rock debris in the spiral discharge channel; generating discharge state characteristic parameters by collecting pressure difference signals and cutting tooth vibration signals in the channel. S2: Quantify the blockage risk of the discharge state characteristic parameters by weighting and fusing the vibration signal peak value and pressure difference signal with preset thresholds to generate a real-time blockage index of the discharge channel. S3: Make a discharge optimization decision based on the real-time blockage index of the discharge channel. Based on the dynamic relationship between the centrifugal force of the cutting tooth rotation and the discharge resistance, map the blockage index to the speed adjustment strategy through a fuzzy reasoning mechanism to generate the cutting head speed optimization adjustment amount. S4: Dynamically limit the adjustment amount of the cutting head speed optimization. By superimposing the adjustment amount with the current speed and limiting it within the safe working range, a speed control command is generated and sent to the cutting head frequency conversion drive system.

2. The method according to claim 1, characterized in that, S1 includes: S11: Perform sliding window mean filtering on the differential pressure sensor signals installed at the inlet and outlet of the discharge channel to eliminate instantaneous impact interference and generate stable channel pressure difference data; S12: Perform time-domain peak hold processing on the triaxial vibration acceleration signal installed at the root of the cutting tooth, extract the maximum amplitude of the vibration signal, and generate standardized vibration peak parameters; S13: Perform multi-source data fusion processing on the channel pressure difference data and vibration peak parameters, and linearly combine them according to a preset weight ratio to generate discharge state characteristic parameters.

3. The method according to claim 1, characterized in that, S2 includes: S21: Normalize the discharge state feature parameters, call the minimum-maximum scaling algorithm to linearly transform each feature parameter to the [0,1] interval, and generate a standardized feature vector; S22: Perform weighted fusion calculation on the feature vector, and use an adaptive weight allocation algorithm to dynamically adjust the contribution of each feature in the feature vector to generate a preliminary congestion risk assessment value; S23: Perform time series smoothing on the preliminary blockage risk assessment value, and use a first-order lag filtering algorithm to eliminate instantaneous fluctuations in the assessment value sequence to generate a real-time blockage index for the discharge channel.

4. The method according to claim 1, characterized in that, S3 includes: S31: The real-time blockage index of the discharge channel is fuzzified. The precise value is converted into a fuzzy linguistic variable through the triangular membership function to generate a fuzzy blockage state description. S32: Perform rule matching processing on the fuzzy blockage state description, query the dedicated rule library designed for the characteristics of the spiral discharge channel, and generate an active set of control rules; S33: Perform inference operations on the activated control rules, calculate the membership degree of each rule output using the minimum-maximum inference method, and generate fuzzy inference results; S34: Perform rule strength adjustment processing on the fuzzy inference results, dynamically correct the rule confidence based on real-time operating conditions, and generate optimized fuzzy control output. S35: Defuzzify the fuzzy control output, calculate the weighted average value of each point in the output fuzzy set using the centroid method to obtain the accurate speed adjustment value, and generate the cutting head speed optimization adjustment amount.

5. The method according to claim 1, characterized in that, The formula for calculating the speed adjustment value is: in, Adjust the rotation speed value. To output the j-th element in the universe of discourse, Let m be the membership degree in the output fuzzy set B, and m be the total number of elements in the output universe of discourse.

6. The method according to any one of claims 1-5, characterized in that, S4 includes: S41: Perform safety boundary verification on the optimized adjustment amount of the cutting head speed, determine the allowable speed adjustment range by combining the strength of the cutting tooth material and the power characteristics of the motor, and generate the speed adjustment amount after safety limit; S42: Perform dynamic compensation processing on the speed adjustment amount after the safety limit, establish a system dynamic response model to predict the overshoot phenomenon in the speed adjustment process and calculate the feedforward compensation amount to compensate for speed fluctuations, and generate a speed setpoint with feedforward compensation. S43: Perform protocol encapsulation processing on the speed setpoint with feedforward compensation, configure the data frame according to the PROFIBUS-DP communication protocol, generate a speed control command, and send the speed control command to the cutting head frequency conversion drive system.

7. The method according to claim 6, characterized in that, S42 includes: S421: Perform feedforward compensation calculation on the speed adjustment amount after the safety limit, predict the system response based on the dynamic characteristic model of the discharge channel, and generate the feedforward compensation amount; S422: The feedforward compensation and speed adjustment are superimposed, and the two are linearly superimposed according to the weighting coefficients and the dynamic response characteristics of the system are taken into account to generate a composite speed adjustment signal. S423: The composite speed adjustment signal is filtered and smoothed, and a smooth speed transition curve is generated using a trajectory planning algorithm to generate a speed setpoint with feedforward compensation.

8. An intelligent control system for automatic material discharge mining cutting picks, characterized in that, The system includes: The discharge status monitoring module is used to monitor the flow status of coal and rock debris in the spiral discharge channel in real time. It generates discharge status characteristic parameters by collecting pressure difference signals and cutting tooth vibration signals in the channel. The blockage risk quantification module is used to quantify the blockage risk of the discharge state characteristic parameters. It generates a real-time blockage index of the discharge channel by weighting and fusing the vibration signal peak value and pressure difference signal with preset thresholds respectively. The material discharge optimization decision module is used to make material discharge optimization decisions based on the real-time blockage index of the material discharge channel. According to the dynamic relationship between the centrifugal force of the cutting tooth rotation and the material discharge resistance, the blockage index is mapped to the speed adjustment strategy through a fuzzy reasoning mechanism to generate the cutting head speed optimization adjustment amount. The speed dynamic limiting module is used to dynamically limit the speed optimization adjustment of the cutting head. By superimposing the adjustment amount with the current speed and limiting it within the safe working range, a speed control command is generated and sent to the cutting head frequency conversion drive system.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the method of any one of claims 1 to 7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the method of any one of claims 1 to 7.

Images