A coal plugging detection method and device for a coal feeder

Abstract

The application discloses a coal feeder coal blocking detection method and device, and the detection method comprises the following steps: acquiring the real-time value of the rotating speed, the real-time value of the current and the material density detection value of the current detection period of the coal feeder; combining the coal feeding rate instruction value received by the coal feeder, and calculating the normal operation interval corresponding to the real-time value of the rotating speed, the real-time value of the current and the material density detection value based on a dynamic mapping function; when the real-time value of the rotating speed, the real-time value of the current and the material density detection value deviate from the normal operation interval corresponding to the coal feeding rate instruction value by more than a preset threshold value, it is determined that the coal feeder is blocked, and the vibration assembly in the raw coal bunker for supplying coal to the coal feeder is started. By monitoring the rotating speed, current and material density of the coal feeder in real time, the normal operation interval of each parameter under the given coal feeding rate instruction is dynamically calculated in combination with a preset transfer function model, once the detection value deviates from the interval by more than the threshold value, it is determined that the coal is blocked and the raw coal bunker vibration device is triggered, the response time difference is shortened, and the coal feeder overload trip hidden danger is avoided.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of coal feeder equipment detection, and particularly relates to a coal feeder coal blocking detection method and device. BACKGROUND

[0002] As a key equipment of the coal pulverizing system of a boiler in a coal-fired power plant, the weigh feeder bears the task of continuously and uniformly conveying coal to the coal mill. The electronic weighing metering coal feeder (such as the CS2024 type) widely used at present realizes precise weighing and automatic speed regulation through microcomputer control, and can dynamically adjust the coal supply amount according to the load demand of the boiler. The working process is as follows: raw coal enters the coal feeder from the coal bunker through the coal gate, is conveyed by the belt to the coal outlet, and then falls into the coal mill through the coal falling pipe. The residual coal powder on the surface of the belt is removed by the cleaning scraper.

[0003] In actual operation, when high-moisture coal is mixed and burned, the humidity and viscosity of the coal increase significantly, resulting in enhanced coal particle agglomeration. Due to the conical structure of the lower part of the raw coal bunker, the flowability of the coal flow in the bunker body decreases, and coal blocking frequently occurs in the area 1.5 meters above the coal gate and the straight pipe section below the gate. The existing technology only installs a coal blocking monitoring switch at the outlet of the coal feeder, but coal blocking often occurs at the inlet. There is a serious lag from the occurrence of coal blocking to the triggering of the alarm. The more prominent contradiction is that although the straight pipe below the coal gate is equipped with an electric vibrating device, there is a lack of mechanical unblocking means in the high-occurrence area above the gate, and manual knocking is not only time-consuming and labor-intensive, but also difficult to guarantee the treatment effect.

[0004] The current coal blocking monitoring mechanism has a fundamental defect. At the initial stage of coal blocking, the phenomenon of "bridging" in the coal bunker often occurs, at which time the material density gradually decreases due to the thinning of the coal layer. In order to maintain the coal supply command, the speed of the coal feeder is passively continuously increased. This process poses a double risk: on the one hand, when the speed reaches the full load and still cannot meet the command, the system has no early warning mechanism, which easily leads to overload tripping of the coal feeder; on the other hand, the coal blocking alarm is triggered only when the coal layer at the tail of the belt is too thin to cause the detection baffle to fall, at which time the coal blocking has accumulated to a critical state, and conventional vibration is difficult to quickly restore the stability of the coal flow. SUMMARY

[0005] The purpose of the embodiments of the present application is to provide a coal feeder coal blocking detection method and device, which monitors the speed, current and material density of the coal feeder in real time, dynamically calculates the normal operation interval of each parameter under a given coal feeding rate command by combining a preset transfer function model, and determines coal blocking and triggers the raw coal bunker vibrating device once the detection value deviates from the interval by more than a threshold value, which significantly shortens the response time difference (such as identifying the risk before the speed reaches the full load), avoids the risk of overload tripping of the coal feeder, simultaneously links the vibrating device to timely unblock, greatly reduces the need for manual intervention, and guarantees the continuity of coal feeding and the stability of the unit operation.

[0006] To solve the above technical problems, the first aspect of the embodiment of the present application provides a coal feeder coal blocking detection method, comprising the following steps:

[0007] Obtaining the real-time value of the rotational speed, the real-time value of the current and the material density detection value of the current detection period of the coal feeder;

[0008] Obtaining the time series data set of the coal feeding rate instruction value, the rotational speed measured value, the current measured value and the material density measured value under multiple working conditions, based on the time series data set, generating a dynamic mapping function of the coal feeding rate instruction value to the rotational speed, the current and the material density by machine learning algorithm training, combining the coal feeding rate instruction value received by the coal feeder, calculating the dynamic normal operation interval of the rotational speed, the current and the material density by the dynamic mapping function, and the normal operation interval is self-adaptively adjusted with the change of the coal feeding rate instruction value;

[0009] When the real-time value of the rotational speed, the real-time value of the current and the material density detection value deviate from the respective normal operation interval of the coal feeding rate instruction value by more than a preset threshold value, it is determined that the coal feeder is blocked, and the vibration assembly in the raw coal bunker for feeding coal to the coal feeder is started.

[0010] Further, based on the time series data set, a dynamic mapping function of the coal feeding rate instruction value to the rotational speed, the current and the material density is generated by machine learning algorithm training, wherein the mapping function output is a parameter prediction interval, comprising:

[0011] The time series data set is preprocessed, and the dynamic coupling relationship of the rotational speed, the current and the material density under different coal feeding rate instruction values is extracted, and the dynamic coupling relationship reflects the cooperative fluctuation characteristics of the parameters with the change of the coal feeding rate instruction value;

[0012] The dynamic coupling relationship is input into a machine learning training framework, and a function mapping relationship of the coal feeding rate instruction value with the rotational speed, the current and the material density is constructed by multivariate regression analysis, wherein each function mapping relationship outputs a predicted reference value and a confidence interval of the corresponding parameter;

[0013] The function mapping relationship is integrated to generate a dynamic mapping function, and the dynamic mapping function takes the coal feeding rate instruction value as input and simultaneously outputs the parameter prediction interval of the rotational speed, the current and the material density, and the parameter prediction interval is composed of the predicted reference value plus or minus the real-time floating deviation.

[0014] Further, before the integration of the function mapping relationship to generate the dynamic mapping function, it further comprises:

[0015] Analyzing the historical fluctuation amplitude of the corresponding rotational speed, current and material density under each coal feeding rate instruction value in the time series data set, and the historical fluctuation amplitude reflects the natural deviation range of the parameters under stable working conditions;

[0016] calculate a parameter floating boundary under a confidence probability according to the historical fluctuation amplitude, the confidence probability representing statistical reliability of a parameter measured value falling into a prediction interval;

[0017] In combination with a working condition feature corresponding to a current coal feeding rate instruction value, a real-time floating deviation is generated by dynamically scaling the parameter floating boundary, the real-time floating deviation varying with the coal feeding rate instruction value and adaptively adjusting a width of the parameter prediction interval.

[0018] Further, the raw coal bunker comprises a cylindrical coal bunker, a conical coal bunker and a coal gate arranged in sequence from top to bottom, the conical coal bunker is provided with a first coal vibration assembly, and a plurality of second coal vibration assemblies are further arranged on the first coal vibration assembly in a vertical direction;

[0019] The vibration assembly in the raw coal bunker that supplies coal to the coal feeder is started, comprising:

[0020] When it is determined that the coal is blocked, a first start signal is sent to the first coal vibration assembly of the raw coal bunker, and the first coal vibration assembly is located outside the conical coal bunker;

[0021] After the first coal vibration assembly is started, a second start signal is sent to the second coal vibration assembly after a delay for a preset time length, and the second coal vibration assembly is distributed on the upper part of the conical coal bunker in a vertical direction;

[0022] The first coal vibration assembly and the second coal vibration assembly are controlled to continue to vibrate and hit in cooperation until the real-time value of the rotating speed, the real-time value of the current and the detected value of the material density return to the normal operating interval.

[0023] Further, the first coal vibration assembly and the second coal vibration assembly are controlled to continue to vibrate and hit in cooperation until the real-time value of the rotating speed, the real-time value of the current and the detected value of the material density return to the normal operating interval, comprising:

[0024] A layered vibration and hitting mode is set, the first coal vibration assembly acts on the lower coal flow channel of the conical coal bunker at a first vibration frequency, and at least one second coal vibration assembly acts on the upper coal storage area of the conical coal bunker at a second vibration frequency, wherein the second vibration frequency is higher than the first vibration frequency to match the crushing characteristics of coal agglomerates;

[0025] The recovery rate of the real-time value of the rotating speed and the detected value of the material density with respect to the normal operating interval is monitored in real time, and the amplitudes of the first vibration frequency and the second vibration frequency are dynamically adjusted according to the recovery rate;

[0026] When the real-time value of the rotating speed and the detected value of the material density continuously stay in the normal operating interval for a stable time length, the vibration and hitting intensity of the first coal vibration assembly and the second coal vibration assembly is reduced in sections until it stops.

[0027] Further, the real-time monitoring of the real-time value of the rotating speed and the recovery rate of the material density detection value relative to the normal operation interval, and dynamically adjusting the amplitude of the first vibration frequency and the second vibration frequency according to the recovery rate, comprises:

[0028] calculating the weighted sum of the absolute value of the difference between the real-time value of the rotating speed and the lower limit of the corresponding normal operation interval and the absolute value of the difference between the material density detection value and the upper limit of the normal operation interval, and defining the change rate of the weighted sum as a comprehensive recovery rate;

[0029] when the comprehensive recovery rate is lower than a preset recovery threshold, proportionally increasing the amplitude of the second vibration frequency while maintaining the amplitude of the first vibration frequency unchanged to preferentially break up the agglomerates in the upper stall coal area;

[0030] when the comprehensive recovery rate is higher than the preset recovery threshold but the material density detection value does not reach the corresponding normal operation interval, simultaneously increasing the amplitudes of the first vibration frequency and the second vibration frequency to enhance the overall coal flow dredging;

[0031] when the real-time value of the rotating speed and the material density detection value both enter the normal operation interval, maintaining the current vibration frequency amplitude until a stable time length is reached.

[0032] Further, the vibration intensity reduction process is divided into a plurality of gradual attenuation stages, each attenuation stage maintaining a fixed time length and the intensity reduction gradually decreasing, and the number of the gradual attenuation stages is positively correlated with the cumulative time length of parameter normality within the stable time length;

[0033] after the end of each attenuation stage, it is detected whether the real-time value of the rotating speed and the material density detection value deviate from the normal operation interval, and if deviation occurs, the vibration intensity of the previous stage is immediately restored and the stable time length is re-cumulated;

[0034] when attenuation is performed to the lowest intensity level and the real-time value of the rotating speed and the material density detection value are continuously normal, the second coal vibration assembly is turned off and the first coal vibration assembly is maintained to operate at a basic intensity for a final recovery time length;

[0035] after the final recovery time length ends and there is no abnormal fluctuation in the parameters, the operation of all coal vibration assemblies is stopped.

[0036] Correspondingly, a second aspect of the embodiment of the present application provides a coal feeder coal blocking detection device, which detects the coal blocking of the coal feeder based on the coal feeder coal blocking detection method, and comprises:

[0037] a data acquisition module configured to acquire the real-time value of the rotating speed, the real-time value of the current and the material density detection value of the coal feeder in a current detection period;

[0038] The data calculation module is configured to obtain time series data sets of the coal feed rate instruction value, the rotational speed measured value, the current measured value, and the material density measured value under multiple working conditions, generate a dynamic mapping function of the coal feed rate instruction value to the rotational speed, the current, and the material density based on the time series data sets by machine learning algorithm training, calculate a dynamic normal operation interval of the rotational speed, the current, and the material density by the dynamic mapping function in combination with the coal feed rate instruction value received by the coal feeder, and adaptively adjust the normal operation interval according to the coal feed rate instruction value.

[0039] The coal blockage judgment module is configured to determine that the coal feeder is blocked when the real-time value of the rotational speed, the real-time value of the current, and the material density detection value deviate from the respective corresponding normal operation intervals of the coal feed rate instruction value by more than a preset threshold value, and start the vibration assembly in the raw coal bunker that supplies coal to the coal feeder.

[0040] Correspondingly, a third aspect of the embodiment of the present application provides an electronic device, comprising: at least one processor; and a memory connected with the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the coal feeder blockage detection method.

[0041] Correspondingly, a fourth aspect of the embodiment of the present application provides a computer readable storage medium having computer instructions stored thereon, and the instructions are executed by a processor to implement the coal feeder blockage detection method.

[0042] The above technical solutions of the embodiment of the present application have the following beneficial technical effects:

[0043] 1. The dynamic mapping function trained based on historical time series data, which calculates the adaptive normal operation interval of the rotational speed, the current, and the material density under different coal feed rate instructions in real time, and introduces confidence probability to dynamically adjust the interval width; when the parameters deviate from the interval by more than a threshold value (such as sudden drop of material density and abnormal rise of rotational speed), the system triggers an early warning at the initial stage of coal blockage accumulation; compared with the traditional passive monitoring relying only on the outlet coal interruption switch, the response time is advanced by several minutes (for example, the risk is identified before the rotational speed reaches full load), which avoids overload trip accidents and reduces the false alarm rate;

[0044] 2. A plurality of vibration assemblies are additionally arranged on the upper part of the conical coal bunker; when it is determined that the coal is blocked, the lower vibration device is started first, and the upper high-frequency vibration is triggered after a delay, forming a cleaning network covering the whole section of the coal bunker; through the layered vibration mode: the lower low-frequency vibration dredges the coal flow channel, and the upper high-frequency vibration breaks the coal agglomerates, and the vibration amplitude is dynamically adjusted in combination with the parameter recovery rate; for example, when the recovery rate is low, the upper high-frequency vibration is preferentially enhanced to achieve targeted cleaning; the blind area problem of the original system without vibration device above the coal lock gate is completely solved, the cleaning efficiency is improved by more than 50%, and the coal feeder does not need to be shut down throughout the whole process.

[0045] 3. Real-time monitoring of the speed and material density regression normal interval rate, dynamic adjustment of the vibration intensity: when good, segmented reduction of the vibration intensity and final shutdown; if the parameters rebound, immediately restore the intensity; through the progressive attenuation strategy, according to the stable length of time, intelligently match the number of attenuation stages and intensity reduction, avoid energy waste and equipment wear caused by excessive vibration; at the same time, retain the basic vibration intensity until the parameters are completely stable, reduce the risk of secondary coal blocking; this closed-loop control reduces the vibration energy consumption by 30%, maintains coal feeding continuity, and ensures unit output. BRIEF DESCRIPTION OF DRAWINGS

[0046] Figure 1 is the schematic diagram of the raw coal bunker vibration provided by the embodiment of the present application;

[0047] Figure 2 is the flow chart of the coal feeder coal blocking detection method provided by the embodiment of the present application;

[0048] Figure 3 is the module block diagram of the coal feeder coal blocking detection device provided by the embodiment of the present application.

[0049] REFERENCE NUMERALS:

[0050] 01, second coal vibration assembly, 02, coal gate, 03, first coal vibration assembly, 1, data acquisition module, 2, data calculation module, 3, coal blocking judgment module. DETAILED DESCRIPTION

[0051] In order to make the purpose, technical scheme and advantages of the present application more clear and obvious, the present application will be further described in detail below in combination with specific embodiments and with reference to the drawings. It should be understood that these descriptions are only exemplary and are not intended to limit the scope of the present application. In addition, in the following description, the description of known structures and technologies is omitted to avoid unnecessary confusion of the concept of the present application.

[0052] Please refer to Figure 1 and Figure 2 The first aspect of the embodiment of the present application provides a coal feeder coal blocking detection method, comprising the following steps:

[0053] Step S100, acquiring the real-time value of the speed, the real-time value of the current and the material density detection value of the current detection period of the coal feeder.

[0054] The detection values of key operating parameters are obtained in real time through the sensor system integrated in the coal feeder. Among them, the real-time value of the rotating speed reflects the actual running speed of the belt drive motor; the real-time value of the current represents the load state of the coal feeder motor, which is indirectly related to the coal flow conveying resistance; the material density detection value is calculated by the weighing sensor and the volume measurement unit (coal quantity = material density x belt speed x cross-sectional area), which directly indicates the uniformity of the coal layer on the belt. These parameters are synchronously collected at a fixed detection period (such as 1 second / time) to form the original data basis for judging coal blocking.

[0055] In step S200, time series data sets of the coal feeding rate instruction value, the rotating speed measured value, the current measured value and the material density measured value under multiple working conditions are obtained, and based on the time series data sets, a dynamic mapping function of the coal feeding rate instruction value to the rotating speed, the current and the material density is trained and generated by a machine learning algorithm. Combined with the coal feeding rate instruction value received by the coal feeder, the dynamic normal operating interval of the rotating speed, the current and the material density is calculated by the dynamic mapping function, and the normal operating interval is self-adaptively adjusted with the change of the coal feeding rate instruction value.

[0056] The dynamic mapping relationship of the instruction value to each parameter is established by using a machine learning algorithm (such as multivariate regression analysis) by training the historical operating data to generate: first, the coal feeding rate instruction value and the corresponding rotating speed, current and material density measured values under multiple working conditions are collected. The model output is not a fixed threshold, but a normal operating interval that changes adaptively with the instruction value. For example, when the coal feeding rate instruction is 40 T / H, the model calculates the rotating speed normal interval as [600, 700] r / min and the material density normal interval as [9500, 11000] kg / m³ based on the historical fluctuations. The interval width also considers the confidence probability (such as 95%), and is dynamically scaled according to the working condition characteristics to ensure that the interval can cover the natural fluctuations under stable working conditions.

[0057] In step S300, when the real-time value of the rotating speed, the real-time value of the current and the material density detection value deviate from the respective normal operating intervals of the coal feeding rate instruction value by more than a preset threshold, it is determined that the coal feeder is blocked, and the vibration assembly in the raw coal bunker for feeding coal to the coal feeder is started.

[0058] When any parameter (rotation speed, current or material density) deviates from its corresponding normal operation interval for more than a preset threshold (such as rotation speed exceeding the upper limit by 10% or density being lower than the lower limit by 15%), the system determines that coal blocking occurs. The determination logic focuses on early abnormal characteristics: for example, sudden drop of material density (thinning of coal layer) accompanied by abnormal rise of rotation speed (forced to increase speed to maintain coal supply), at this time, although the traditional coal blocking alarm has not been triggered, it has shown that there is a "bridge" risk at the coal bunker inlet. After determination, the vibration component is immediately started: the layered vibration device is activated in sequence, first triggering the original vibration device at the lower part of the cone, and after a delay of 10 seconds, starting the newly added three-layer vibration device above the coal gate, forming a coordinated vibration from bottom to top. The vibration continues until the parameters return to the normal interval, and the vibration intensity is dynamically optimized through a hierarchical adjustment strategy to avoid excessive vibration.

[0059] Further, in step S200, based on the time series data set, a dynamic mapping function of the coal feeding rate instruction value to the rotation speed, current and material density is generated by machine learning algorithm training, wherein the mapping function output is a parameter prediction interval, including:

[0060] In step S210, the time series data set is preprocessed to extract the dynamic coupling relationship of rotation speed, current and material density under different coal feeding rate instruction values. The dynamic coupling relationship reflects the coordinated fluctuation characteristics of the parameters with the coal feeding rate instruction value.

[0061] The time series data set is deeply preprocessed to focus on the cooperative response mechanism between parameters. First, the data is grouped according to the coal feeding rate instruction value, and the linkage characteristics of rotation speed, current and material density when the instruction changes are analyzed: under normal working conditions, an increase in the coal feeding rate instruction will cause the material density and rotation speed to rise synchronously (reflecting the coordination of coal layer thickening and speed increase); while in abnormal conditions (such as early coal blocking), it presents abnormal coupling of continuous decrease of material density accompanied by abnormal rise of rotation speed (due to "bridge" causing coal layer thinning, the system is forced to increase speed to compensate for coal quantity). The preprocessing process quantifies the synchronization strength of parameter fluctuations in different instruction segments through sliding window statistics and correlation calculation, eliminates accidental noise interference, and finally extracts the dynamic coupling relationship matrix under stable working conditions.

[0062] In step S220, the dynamic coupling relationship is input into the machine learning training framework, and the function mapping relationship of the coal feeding rate instruction value with the rotation speed, current and material density is constructed through multivariate regression analysis, wherein each function mapping relationship outputs the predicted reference value and confidence interval of the corresponding parameter.

[0063] The dynamic coupling relationship is input into a machine learning training framework, and a multivariate regression model is used to construct an independent mapping relationship between the coal feed rate instruction value and each parameter. Taking the rotational speed as an example: the model takes the instruction value as input, and based on the coordinated fluctuation characteristics in the coupling relationship (such as the theoretical increase in rotational speed when the instruction is raised), outputs the predicted reference value of the rotational speed under the instruction (such as 40T / H corresponding to 650 r / min); at the same time, the dispersion degree of the historical data under the same instruction is calculated (such as ±50 r / min), and a confidence interval ([600, 700] r / min) is generated by combining the confidence probability (such as 95%). The mapping relationship between the current and the material density is generated synchronously, and the confidence interval of the material density needs to pay special attention to the historical fluctuation range of the high-moisture coal working condition (such as the interval width expanding by 15% when the humidity is greater than 20%). The function mapping of each parameter retains the self-adaptive ability of the working condition, ensuring that the reference value and the interval are dynamically calibrated according to the coal quality characteristics.

[0064] In step S230, the integrated function mapping relationship generates a dynamic mapping function, which takes the coal feed rate instruction value as input and simultaneously outputs the parameter prediction interval of the rotational speed, the current and the material density. The parameter prediction interval is composed of the predicted reference value plus or minus the real-time floating deviation.

[0065] The independent function mapping of the rotational speed, the current and the material density is integrated to construct a unified dynamic mapping function. The function takes the real-time coal feed rate instruction value as the only input and simultaneously outputs the prediction interval of the three parameters. The interval is composed of two parts: one is the predicted reference value corresponding to the current instruction value (such as the rotational speed 650 r / min); the other is the real-time floating deviation (such as ±50 r / min), which is not a fixed value, but is dynamically calculated according to the current working condition characteristics. For example, under the high-moisture coal working condition, the floating deviation of the material density is automatically expanded to ±20% of the reference value (only ±10% under the dry coal working condition). The final output parameter prediction interval (such as the material density [8500, 10500] kg / m³) not only reflects the theoretical expected value of the parameter, but also includes the reasonable deviation range under the working condition fluctuation, forming a self-adaptive monitoring threshold.

[0066] Further, before the integrated function mapping relationship in step S230 generates the dynamic mapping function, it further includes:

[0067] In step S231, the historical fluctuation amplitudes of the rotational speed, the current and the material density corresponding to each coal feed rate instruction value in the time series data set are analyzed. The historical fluctuation amplitude reflects the natural deviation range of the parameter under stable working conditions.

[0068] For the stable working condition segment in the time series data set (such as 10 minutes of continuous parameter fluctuation standard deviation below the threshold), the historical fluctuation characteristics of the speed, current and material density are grouped and counted according to the coal feeding rate command value. The specific analysis includes: calculating the dispersion degree of the measured value of the parameter relative to its mean value under each command value (such as the material density fluctuation within ±850 kg / m³ at 40T / H), and associating the working condition label, especially marking the fluctuation amplitude under high-moisture coal (moisture content >15%) (such as the material density fluctuation expanding to ±1200 kg / m³ under the same command). By fitting the fluctuation distribution curve of different coal qualities and different load segments, the natural deviation range of the parameter under the non-blocked coal state is quantified to provide a statistical basis for setting the floating boundary.

[0069] Step S232, calculating the parameter floating boundary under the confidence probability according to the historical fluctuation amplitude, and the confidence probability represents the statistical reliability of the measured value of the parameter falling into the prediction interval.

[0070] Based on the historical fluctuation amplitude data, the parameter floating boundary under the confidence probability (such as 95%) is calculated by using the probability statistical method. Taking the material density as an example: in the high-moisture coal working condition under the 40T / H command, its historical data obeys the normal distribution N(9500,400²), and the floating boundary corresponding to the 95% confidence degree is ±784 kg / m³ (i.e. 1.96 times the standard deviation). The boundary represents the statistical reliability of the measured value of the parameter falling into the prediction interval, and its width directly reflects the stability of the working condition. The wetter the coal quality, the more frequent the load changes, and the wider the floating boundary. The current and the speed are calculated synchronously, and the baseline shift correction caused by equipment aging needs to be additionally considered for the speed floating boundary.

[0071] Step S233, combining the working condition characteristics corresponding to the current coal feeding rate command value, dynamically scaling the parameter floating boundary to generate the real-time floating deviation, and the real-time floating deviation changes with the coal feeding rate command value, and the width of the parameter prediction interval is adaptively adjusted.

[0072] In actual operation, the system combines the real-time working condition characteristics (such as coal moisture, equipment running time) corresponding to the current coal feeding rate command value, and dynamically scales the floating boundary calculated in step S223b: when the coal moisture sensor detects that the moisture content is >15%, the floating boundary of the material density is automatically expanded to 1.3 times of the historical baseline value (such as from ±784 kg / m³ to ±1019 kg / m³); if the equipment has been continuously running for more than 100 hours, the speed floating boundary is narrowed to 0.8 times to offset the abnormal fluctuation caused by mechanical wear. The scaled floating boundary is the real-time floating deviation, which is adaptively adjusted with the command value and the working condition, and is finally used to construct the parameter prediction interval (such as the prediction baseline value ± the real-time floating deviation).

[0073] The raw coal bunker for feeding coal to the coal feeder in the application comprises a cylindrical coal bunker, a conical coal bunker and a coal gate 02 arranged in sequence from top to bottom, the conical coal bunker is provided with a first coal vibration assembly, and a plurality of second coal vibration assemblies 01 are further arranged on the upper part of the first coal vibration assembly in the vertical direction.

[0074] The raw coal bunker adopts a three-section vertical layout: the top is a cylindrical coal bunker, which bears the function of raw coal storage, and its vertical cylinder wall structure is conducive to the uniform distribution of coal particles; the middle part is a conical coal bunker, which narrows the cross-sectional area of the coal flow through the conical slope to guide the coal particles to converge towards the coal gate 02; the bottom connects the coal gate 02, which serves as a channel for the coal flow to enter the coal feeder. For the high incidence area of coal blockage, the first coal vibration assembly is arranged on the outer wall of the conical coal bunker, and its vibration force acts on the lower part of the coal flow channel of the cone, which is used to dredge the local blockage formed. To further solve the problem of shed coal within 1.5 meters above the coal gate 02, where coal particle aggregation is easy to form "bridges", a plurality of second coal vibration assemblies 01 are added vertically on the upper part of the conical coal bunker, which cover the upper, middle and lower three sections (such as three-layer layout) of the conical height direction, and the high-frequency vibration force directly acts on the inside of the coal aggregation. The two sets of vibration assemblies form spatial cooperation: the lower vibration ensures the smoothness of the coal flow channel, and the upper vibration prevents the accumulation of shed coal, realizing full-warehouse section blockage removal coverage.

[0075] The first coal vibration assembly 03 is arranged below the coal gate; its installation position is optimized by structural mechanics, so that the vibration force can be efficiently transmitted to the inner wall of the cone and the internal coal body, directly acting on the core area of obstruction which is easy to form "bridges" or "shed coal" due to wet coal adhesion. The first coal vibration assembly 03 corresponds to the straight pipe section electric vibrator installed in the lower part of the coal gate in the existing system, but in this scheme its function is further integrated and enhanced: not only can it destroy the liquid bridge force and van der waals force between high-moisture coal particles through mechanical vibration to break down the agglomeration blockage structure formed, but also it can serve as the bottom unit of the layered vibration system, cooperating with the second coal vibration assembly installed on the upper part in space and time. Its vibration mechanics parameters (such as frequency and amplitude) are calibrated according to the structural characteristics of the cone and the viscosity of the coal, ensuring that while dredging local blockage, excessive vibration is avoided to cause coal flow collapse or structural resonance. As the primary vibration execution mechanism after coal blockage, it undertakes the key task of quickly relieving the entrance flow resistance and creating conditions for upper-layer cooperative vibration operation.

[0076] Through the three-dimensional layout of the segmented bunker body structure and the vibration assembly, the blind area problem of traditional raw coal bunker is completely solved. The lower vibration assembly of the cone maintains the smoothness of the basic coal flow, while the upper multi-layer vibration assembly precisely acts on the high incidence area of coal blockage (especially within 1.5 meters above the coal gate), quickly breaking the coal particle "bridge" phenomenon through high-frequency targeted vibration. The spatial cooperation of layered vibration force significantly improves the blockage removal efficiency, avoiding the lag and uncertainty of manual knocking, and ensuring the continuous and stable operation of the coal feeder.

[0077] The starting of the vibration assembly in the raw coal bunker for feeding the coal feeder in step S300 includes:

[0078] In step S310, when the coal blocking is determined, a first starting signal is sent to the first coal vibration assembly of the raw coal bunker. The first coal vibration assembly is located outside the conical coal bunker.

[0079] When the system determines that coal blocking occurs, a starting instruction is first sent to the first coal vibration assembly located outside the conical coal bunker. The assembly corresponds to the existing electric vibration device installed on the straight pipe below the coal gate in the technical scheme, and mechanical intervention is performed for the initial coal blocking in the inlet area of the coal feeder. By vibrating the plate directly on the key block point of the coal flow channel, the agglomeration structure of the coal particles due to high humidity is forcibly destroyed, and the flow resistance in the inlet area is relieved. As the primary response action, it aims to quickly eliminate the direct impact of local blocking on the belt coal supply.

[0080] In step S320, after the first coal vibration assembly is started, a second starting signal is sent to the second coal vibration assembly 01 after a preset time delay. The second coal vibration assembly 01 is distributed in the upper part of the conical coal bunker in the vertical direction.

[0081] After ensuring that the first coal vibration assembly is started, a preset delay mechanism (for example, 10 seconds) is introduced, and a starting signal is then sent to the second coal vibration assembly 01 distributed in the upper part of the conical coal bunker in the vertical direction. The first coal vibration assembly corresponds to the newly added three-layer vibration device, and the delay start is based on the dynamic characteristics of the coal flow: the initial relief of the inlet coal blocking allows the "shelf coal" accumulated in the upper part of the coal bunker to obtain sinking space, and the upper layer vibration is started at this time to avoid coal flow overload. The layered vibration strategy accurately matches the structural characteristics of the coal bunker. The 1.5m range in the upper part of the cone is a high-risk area for wet coal adhesion. The three-layer device covers different heights in the vertical direction, systematically disintegrating the arch-shaped blocking structure in the cone region.

[0082] In step S330, the first coal vibration assembly and the second coal vibration assembly 01 are controlled to continuously cooperate and vibrate until the real-time values of the rotational speed, the real-time values of the current, and the detection values of the material density return to the normal operation range.

[0083] The first and second vibration assemblies enter the continuous cooperative vibration stage. This process is monitored by the DCS system in real time to monitor the rotational speed, current, and material density parameters of the coal feeder. Only when the three detection values return to the normal operation range established by the machine learning model (for example: when the coal feeding instruction is 40T / H, the rotational speed should tend to 650R / MIN, and the density is about 10256kg / m³), the system will terminate the vibration. This continuous cooperation mechanism breaks through the limitations of single vibration: the lower device maintains the inlet unblocked, and the upper device continuously crushes the cone adhesion coal, forming a spatiotemporal coordinated mechanical wave conduction until the coal flow parameters are stable within the preset threshold.

[0084] The cooperative vibration scheme significantly improves the efficiency of coal blockage treatment by hierarchical vibration timing and spatial coverage. Based on the original entrance vibration, the new vertebral vibration device solves the key blockage, and cooperates with the intelligent start-stop control based on the data model to advance the coal blockage intervention node from the traditional coal cutting alarm to the parameter anomaly stage. It avoids the risk of coal feeder tripping due to speed overload, reduces the need for manual knocking, and realizes rapid elimination of coal blockage on the premise of maintaining continuous operation of the unit. The whole mechanism relies on the modification of the existing DCS architecture, ensuring the reliability of the coal-fired system while being economically implemented.

[0085] Further, the control of the first coal vibration assembly and the second coal vibration assembly 01 in step S330 continues to cooperate with the vibration until the real-time value of the speed, the real-time value of the current and the material density detection value return to the normal operation interval, including:

[0086] Step S331, set a hierarchical vibration mode, so that the first coal vibration assembly acts on the lower coal flow channel of the conical coal bunker at a first vibration frequency, and at least one second coal vibration assembly 01 acts on the upper coal storage area of the conical coal bunker at a second vibration frequency, wherein the second vibration frequency is higher than the first vibration frequency to match the breaking characteristics of coal agglomerates.

[0087] In the cooperative vibration stage, the hierarchical vibration strategy is started: the first coal vibration assembly acts on the coal flow channel at the lower part of the conical coal bunker (corresponding to the original electric vibration device position) at a lower first vibration frequency, which fully considers the continuity requirement of coal flow conveying, avoiding excessive vibration leading to coal flow collapse; at the same time, at least one second coal vibration assembly 01 acts on the coal storage area at the upper part of the conical coal bunker (corresponding to the newly added three-layer device) at a higher second vibration frequency, the high-frequency vibration is specially designed for the agglomerate structure formed by wet coal within 1.5m range of the coal bunker vertebral body, the high-frequency mechanical wave can effectively destroy the liquid bridge force and van der Waals force between coal particles, the frequency value is calibrated through coal viscosity experimental data to ensure accurate matching of the breaking threshold of coal agglomerates.

[0088] Step S332, real-time monitoring of the recovery rate of the real-time value of the speed and the material density detection value relative to the normal operation interval, and dynamically adjusting the amplitude of the first vibration frequency and the second vibration frequency according to the recovery rate.

[0089] Real-time monitoring of the recovery rate of the rotational speed and the material density relative to the normal operation interval (for example, the approach speed of the rotational speed from the abnormal value 1450R / MIN to the target value 650R / MIN), which directly reflects the breaking effect of the vibration on the blocked coal structure. When the recovery rate is lower than expected, the amplitude of the second vibration frequency is automatically enhanced to strengthen the breaking of the upper agglomerates, while the amplitude of the first vibration frequency is moderately increased to facilitate the unblocking of the coal flow channel; on the contrary, when the recovery rate is too fast, the vibration amplitude is reduced to avoid coal flow overload. This dynamic adjustment relies on the rate-vibration intensity mapping relationship constructed by the machine learning model to ensure that the vibration energy accurately matches the real-time severity of the blocked coal.

[0090] Step S333, when the rotational speed real-time value and the material density detection value continuously stay within the normal operation interval for a stable length of time, the vibration intensity of the first coal vibration assembly and the second coal vibration assembly 01 is segmented to reduce until it stops.

[0091] When the rotational speed and the material density continuously stabilize in the normal operation interval (for example, the rotational speed maintains 650±50R / MIN and the density is 10256±500kg / m³ under the 40T / H instruction) for a preset stable length of time (usually greater than the response period of the coal mill system), the vibration intensity segmented attenuation is started: first, the high-frequency vibration of the second vibration assembly is reduced to the maintenance frequency to eliminate the risk of upper coal recurrence; after the material density continuously stabilizes, the amplitude of the first vibration assembly is gradually reduced, and finally the vibration is completely stopped. This segmented exit avoids sudden changes in coal flow state and ensures coal feeding continuity.

[0092] The hierarchical collaborative control mechanism accurately matches the blocked coal characteristics of different regions of the coal bunker through frequency differentiation, and realizes optimal allocation of vibration energy combined with dynamic adjustment based on the parameter recovery rate. The segmented exit strategy maximizes the reduction of mechanical loss and energy consumption while ensuring the complete elimination of blocked coal. The vibration process is upgraded from the traditional fixed intensity mode to a self-adaptive system that is real-time linked with the coal flow state, avoiding both processing delays caused by insufficient vibration and coal flow fluctuations caused by excessive vibration. The entire control logic is deeply integrated into the advanced control algorithm of DCS, achieving double improvement of blocked coal treatment efficiency and equipment safety without human intervention.

[0093] Further, the real-time monitoring of the recovery rate of the rotational speed real-time value and the material density detection value relative to the normal operation interval in step S332 dynamically adjusts the amplitudes of the first vibration frequency and the second vibration frequency according to the recovery rate, including:

[0094] Step S3321, calculating the weighted sum of the absolute value of the difference between the rotational speed real-time value and the lower limit of the corresponding normal operation interval and the absolute value of the difference between the material density detection value and the upper limit of the normal operation interval, and defining the change rate of the weighted sum as the comprehensive recovery rate.

[0095] The absolute value of the difference between the rotational speed deviating from the lower limit of the normal operation interval (for example, 40T / H, the lower limit is 600R / MIN, if the actual value is 1450R / MIN, the difference is 850) and the absolute value of the difference between the material density deviating from the upper limit of the interval (the upper limit is 10756kg / m³, if the actual value is 4566kg / m³, the difference is 6190) are calculated by a preset weight coefficient (such as rotational speed weight 0.6, density weight 0.4) to calculate the weighted sum, and the change rate is the comprehensive recovery rate. The accurate quantification of the coal blocking state: the abnormal increase of the rotational speed reflects the insufficient load of the belt, and the sudden drop of the density indicates that the coal seam is thinning, and the weighted capture of the coal flow recovery dynamics.

[0096] Step S3322, when the comprehensive recovery rate is lower than the preset recovery threshold, the amplitude of the second vibration frequency is proportionally increased, and the amplitude of the first vibration frequency is maintained unchanged to preferentially break the agglomerates in the upper coal shed area.

[0097] When the comprehensive recovery rate is lower than the preset threshold (for example, the weighted sum reduction amount is less than 100 units per minute), it indicates that the effect of breaking the agglomerates in the upper coal shed area is insufficient. At this time, the high-frequency amplitude of the second vibration assembly is proportionally increased (for example, from 50Hz to 65Hz), and the low-frequency amplitude of the first vibration assembly is maintained unchanged. The vibration energy in the upper 1.5m area of the cone is enhanced to destroy the arch structure formed by wet coal through increasing the mechanical impact force, and the lower vibration intensity is reserved to avoid overload disturbance of the coal flow channel.

[0098] Step S3323, when the comprehensive recovery rate is higher than the preset recovery threshold but the material density detection value does not reach the corresponding normal operation interval, the amplitudes of the first vibration frequency and the second vibration frequency are simultaneously increased to enhance the overall coal flow dredging.

[0099] If the comprehensive recovery rate exceeds the threshold but the material density does not reach the normal interval (for example, the rate is greater than 100 units per minute and the density is less than 9756kg / m³), it indicates that the overall coal flow is not smooth enough. The amplitudes of the first and second vibration assemblies are simultaneously increased (for example, the first assembly is increased from 30Hz to 40Hz, and the second assembly is increased from 50Hz to 60Hz), and the synergistic effect of the lower coal flow pushing force and the upper agglomerate breaking force is enhanced to accelerate the elimination of the conical adhesion coal block and promote the overall sinking of the coal flow.

[0100] Step S3324, when the real-time value of the rotational speed and the material density detection value both enter the normal operation interval, the current vibration frequency amplitude is maintained until the stable time length is reached.

[0101] When the rotational speed and the material density are in the normal operation interval (for example, the rotational speed is stabilized at 620-680 R / MIN, and the density is 9756-10756 kg / m³), the current vibration amplitude is maintained until a preset stable time length (for example, 3 mill operating cycles) is reached. The continuous vibration in this stage aims to consolidate the dredging effect and prevent coal particles from re-aggregating due to residual moisture, providing a buffer for subsequent vibration intensity safe decay.

[0102] The dynamic adjustment mechanism realizes precise allocation of vibration energy on demand by quantitatively defining the coal flow recovery state. The upper priority strategy focuses on tackling the high coal blocking risk area, the global enhancement mode deals with systematic flow obstacles, and the steady state maintenance ensures thoroughness. The complete control logic upgrades the vibration process from experience-driven to data-driven, significantly shortens the coal blocking processing time, and avoids equipment overload or coal flow secondary blocking caused by traditional fixed intensity vibration, fundamentally improving the reliability of continuous operation of the pulverizing system.

[0103] Further, when the real-time value of the rotational speed and the detected value of the material density are in the normal operation interval for a stable time length in step S333, the vibration intensity of the first coal vibration assembly and the second coal vibration assembly 01 is gradually reduced until it is stopped, including:

[0104] In step S3331, the vibration intensity reduction process is divided into several gradual decay stages, each decay stage maintains a fixed time length and the intensity reduction amplitude decreases gradually, and the number of gradual decay stages is positively correlated with the cumulative time length of the parameters remaining normal in the stable time length.

[0105] The vibration intensity decay is divided into multiple gradual stages (such as 4-stage decay), each stage maintains a fixed time length (such as 30 seconds) and the intensity reduction amplitude decreases gradually (for example, the second component first-stage reduction amplitude is 40%, and the last-stage reduction amplitude is only 10%). The number of stages is dynamically related to the parameter stable time length: if the rotational speed and the density are normal for a long time (such as more than 5 minutes), it indicates that the coal flow recovery is stable, and the decay stage can be increased to achieve a smooth exit; otherwise, short-term stability reduces the number of stages to prevent coal blocking from recurring due to premature stopping. Match the re-aggregation characteristics of coal particles to avoid the rebound of coal flow state caused by sudden intensity reduction.

[0106] In step S3332, after each decay stage ends, it is detected whether the real-time value of the rotational speed and the detected value of the material density deviate from the normal operation interval, and if deviation occurs, the vibration intensity of the previous stage is restored and the stable time length is re-counted.

[0107] After each stage of attenuation, the real-time detection of the rotation speed and the material density is performed to determine whether they deviate from the normal range (for example, the rotation speed suddenly increases to 700 R / MIN or the density drops below 9000 kg / m³). Once the deviation is detected, the intensity of the vibration is restored to the previous level, and the accumulated value of the stable duration is reset. This mechanism aims at the risk of "unblocking-reblocking" in the wet coal environment, and ensures that the vibration intensity is always maintained above the critical elimination value through fast response until the coal flow parameters are stable again.

[0108] In step S3333, when the attenuation reaches the minimum intensity level and the real-time value of the rotation speed and the detected value of the material density are normal, the second coal vibration assembly 01 is turned off, and the first coal vibration assembly is kept running at the basic intensity for the final recovery duration.

[0109] When the intensity is attenuated to the minimum level (for example, 10% of the basic intensity of the second assembly 01) and the parameters are normal, the upper second coal vibration assembly 01 is turned off. At this time, the lower first assembly is kept running at the basic intensity (for example, 30% of the rated intensity) for the final recovery duration (for example, 2 minutes), and the residual adhesion at the bottom of the coal bunker is eliminated by the continuous vibration. This step is based on the principle of coal flow dynamics: after the upper layer of coal is broken, the bottom coal flow channel needs to be maintained with a slight vibration to prevent particle deposition, while avoiding high-frequency vibration interference with the belt weighing accuracy.

[0110] In step S3334, after the final recovery duration ends and the parameters do not fluctuate abnormally, the running of all coal vibration assemblies is stopped.

[0111] After the final recovery duration ends and the parameters do not fluctuate abnormally (for example, the rotation speed fluctuation is less than ±3% and the density fluctuation is less than ±5%), the system stops the running of all vibration assemblies. Before termination, a final data check is performed to ensure that the coal flow at the inlet of the coal mill reaches a "self-sustaining flow state", that is, the material density and the rotation speed match the current coal feeding instruction, and the current value is below the full load threshold, indicating that the risk of coal blocking is completely eliminated.

[0112] The segmented attenuation mechanism completely solves the problem of coal flow fluctuation caused by the "sudden start and sudden stop" of traditional vibration through gradual intensity adjustment and real-time feedback closed loop. The abnormal rollback strategy effectively deals with the risk of re-blocking in the wet coal environment, and gradually exits to ensure the unblocking effect of the key area. The whole process ensures that the coal blocking is completely eliminated, maximally reduces mechanical wear and energy consumption, converts the vibration termination process into an intelligent decision deeply coupled with the coal flow state, prevents secondary blocking caused by premature exit, avoids equipment life loss caused by excessive vibration, and finally realizes the seamless transition from fault intervention to stable operation of the pulverizing system.

[0113] Correspondingly, please refer to Figure 3 The second aspect of the embodiment of the present application provides a coal feeder blocking detection device, which detects the coal blocking of the coal feeder based on the coal feeder blocking detection method, and includes:

[0114] A data acquisition module 1 is configured to acquire real-time values of the rotational speed, current and material density of the coal feeder in a current detection period;

[0115] A data calculation module 2 is configured to acquire time series data sets of the coal feeding rate instruction value, measured rotational speed, measured current and measured material density under multiple working conditions, generate a dynamic mapping function of the coal feeding rate instruction value to the rotational speed, current and material density based on the time series data sets through machine learning algorithm training, calculate a dynamic normal operation interval of the rotational speed, current and material density through the dynamic mapping function in combination with the coal feeding rate instruction value received by the coal feeder, and adaptively adjust the normal operation interval according to the coal feeding rate instruction value.

[0116] A coal blocking judgment module 3 is configured to determine that the coal feeder is blocked when the real-time values of the rotational speed, current and material density deviate from the respective normal operation intervals of the coal feeding rate instruction value by more than a preset threshold value, and start the vibration assembly in the raw coal bunker for supplying coal to the coal feeder.

[0117] Correspondingly, a third aspect of the embodiment of the present application provides an electronic device, comprising at least one processor and a memory connected with the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the coal feeder coal blocking detection method.

[0118] Correspondingly, a fourth aspect of the embodiment of the present application provides a computer readable storage medium having computer instructions stored thereon, and the instructions are executed by a processor to implement the coal feeder coal blocking detection method.

[0119] The embodiment of the present application aims to protect a coal feeder coal blocking detection method and device, and has the following effects:

[0120] 1. The dynamic mapping function trained based on historical time series data is used to calculate the adaptive normal operation interval of the rotational speed, current and material density under different coal feeding rate instructions in real time, and the confidence probability is introduced to dynamically adjust the interval width; when the parameters deviate from the interval by more than a threshold value (such as sudden drop of material density and abnormal rise of rotational speed), the system triggers an early warning at the initial stage of coal blocking accumulation; compared with the traditional passive monitoring relying on the outlet coal blocking switch, the response time is advanced by several minutes (for example, the risk is identified before the rotational speed reaches full load), which avoids overload trip accidents and reduces the false alarm rate;

[0121] 2. The upper part of the conical coal bunker is additionally provided with a multi-layer vibration assembly. When it is determined that the coal is blocked, the lower part of the vibration device is started first, and the upper part of the high-frequency vibration is triggered after a delay, so as to form a cleaning network covering the whole section of the coal bunker. Through the layered vibration mode, the lower part of the coal flow channel is dredged, and the upper part of the high-frequency vibration is used to break the coal agglomerates, and the vibration amplitude is dynamically adjusted in combination with the parameter recovery rate. For example, when the recovery rate is low, the upper part of the high-frequency vibration is preferentially enhanced to realize targeted cleaning; the problem of the blind area above the original system coal gate is completely solved, the cleaning efficiency is improved by more than 50%, and the coal feeder does not need to be stopped during the whole process;

[0122] 3. The speed is monitored in real time, and the vibration strength is dynamically adjusted: when the recovery is good, the vibration strength is gradually reduced and finally closed; if the parameters rebound, the strength is immediately restored; through the gradual attenuation strategy, the number of attenuation stages and the strength reduction range are intelligently matched according to the stable time length, so as to avoid energy waste and equipment wear caused by excessive vibration; at the same time, the basic vibration strength is maintained until the parameters are completely stable, so as to reduce the risk of secondary coal blocking; the closed-loop control reduces the vibration energy consumption by 30%, maintains the coal feeding continuity, and guarantees the unit output.

[0123] Those skilled in the art will appreciate that embodiments of the application can be provided as methods, systems, or computer program products. Accordingly, the application can take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the application can take the form of a computer program product on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROMs, optical storage, etc.) embodying computer readable program code.

[0124] The application is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the application. It should be understood that each flow and / or block in the flowcharts and / or block diagrams, as well as combinations of flows and / or blocks in the flowcharts 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, a special-purpose computer, an embedded processor, or other programmable data processing apparatus to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing apparatus produce a device that implements the functions specified in the flowcharts and / or block diagrams. Figure 1 The functions specified in one or more flows and / or blocks. Figure 1 The functions specified in one or more flows and / or blocks.

[0125] These computer program instructions can also be stored in a computer-readable memory that can cause the computer or other programmable data processing apparatus to work in a specific manner, so that the instructions stored in the computer-readable memory produce a manufactured product including instruction devices that implement the functions specified in the flowcharts and / or block diagrams. Figure 1 The functions specified in one or more flows and / or blocks.Figure 1 the function specified in the one or more blocks.

[0126] These computer program instructions can also be loaded into computer or other programmable data processing devices, so that a series of operation steps are performed on the computer or other programmable data processing devices to generate computer-implemented processes, thus the instructions executed on the computer or other programmable data processing devices provide processes for implementing the flows Figure 1 the flows or the plurality of flows and / or blocks Figure 1 the steps of the function specified in the one or more blocks.

[0127] Finally, it should be noted that: the above examples are only used to illustrate the technical solutions of the present application, but not to limit it, although the above embodiments of the present application have been described in detail, those skilled in the art should understand: the specific embodiments of the present application can be modified or replaced by the same, without departing from the spirit and scope of the present application, any modification or equivalent replacement, which should be covered in the protection scope of the claims of the present application.

Claims

1. A method for detecting coal blockage in a coal feeder, characterized in that, Includes the following steps: Obtain the real-time values ​​of the rotational speed, current, and material density of the coal feeder during the current detection cycle; A time-series dataset of coal feed rate command value, measured speed, measured current and measured material density under multiple working conditions is obtained. Based on the time-series dataset, a dynamic mapping function from the coal feed rate command value to the speed, current and material density is generated by training a machine learning algorithm. Combined with the coal feed rate command value received by the coal feeder, the dynamic normal operating range of the speed, current and material density is calculated by the dynamic mapping function. The normal operating range is adaptively adjusted as the coal feed rate command value changes. When the real-time value of the rotation speed, the real-time value of the current, and the material density detection value deviate from the corresponding normal operating range of the coal feed rate command value by more than a preset threshold, it is determined that the coal feeder is blocked and the vibration component in the raw coal bunker that supplies coal to the coal feeder is activated. The raw coal bunker includes a cylindrical coal bunker, a conical coal bunker, and a coal gate arranged sequentially from top to bottom. The conical coal bunker is equipped with a first coal vibration assembly, and several second coal vibration assemblies are also arranged vertically above the first coal vibration assembly. The vibration assembly in the raw coal bunker that initiates the coal supply to the coal feeder includes: When coal blockage is detected, a first start signal is sent to the first coal vibration component of the raw coal bunker. The first coal vibration component is located outside the cone-shaped coal bunker and is positioned below the coal gate. After the first coal vibration component is started, a second start signal is sent to the second coal vibration component after a preset delay. The second coal vibration component is distributed vertically on the upper part of the cone-shaped coal bunker. The first coal vibration component and the second coal vibration component are controlled to continuously vibrate in coordination until the real-time values ​​of rotation speed, current and material density return to the normal operating range. The control of the first and second coal vibration components to continuously and collaboratively vibrate until the real-time values ​​of rotational speed, current, and material density return to the normal operating range includes: A layered vibration mode is set up so that the first coal vibration component acts on the lower coal flow channel of the cone-shaped coal bunker at a first vibration frequency, while at least one second coal vibration component acts on the upper coal shed area of ​​the cone-shaped coal bunker at a second vibration frequency, wherein the second vibration frequency is higher than the first vibration frequency to match the crushing characteristics of coal agglomerates. The recovery rate of the real-time rotation speed and material density detection value relative to the normal operating range is monitored in real time, and the amplitude of the first vibration frequency and the second vibration frequency is dynamically adjusted according to the recovery rate. When the real-time rotation speed and the material density detection value remain within the normal operating range for a stable duration, the vibration intensity of the first coal vibration component and the second coal vibration component is reduced in stages until it stops. The real-time monitoring of the recovery rate of the real-time rotational speed value and the material density detection value relative to the normal operating range, and the dynamic adjustment of the amplitude of the first vibration frequency and the second vibration frequency based on the recovery rate, includes: The weighted sum of the absolute value of the difference between the real-time rotation speed value and the lower limit of the corresponding normal operating range and the absolute value of the difference between the material density detection value and the upper limit of the normal operating range is calculated, and the rate of change of the weighted sum is defined as the comprehensive recovery rate. When the overall recovery rate is lower than the preset recovery threshold, the amplitude of the second vibration frequency is increased proportionally, while the amplitude of the first vibration frequency is kept constant to prioritize the breaking of agglomerates in the upper coal shed area. When the overall recovery rate is higher than the preset recovery threshold but the material density detection value does not reach the corresponding normal operating range, the amplitude of the first vibration frequency and the second vibration frequency are simultaneously increased to enhance the overall coal flow dredging. When both the real-time rotational speed and the material density detection value are within the normal operating range, maintain the current vibration frequency amplitude until a stable duration is reached.

2. The coal feeder blockage detection method according to claim 1, characterized in that, Based on the time-series dataset, a dynamic mapping function is generated using a machine learning algorithm to represent the coal feed rate command value to the rotational speed, current, and material density. The output of this mapping function is a parameter prediction interval, including: The time-series dataset is preprocessed to extract the dynamic coupling relationship between rotational speed, current and material density under different coal feed rate command values. The dynamic coupling relationship reflects the coordinated fluctuation characteristics of the parameters as the coal feed rate command value changes. The dynamic coupling relationship is input into a machine learning training framework, and a function mapping relationship between the coal feed rate command value and the rotation speed, current and material density is constructed through multivariate regression analysis. The output of each function mapping relationship is the prediction benchmark value and confidence interval of the corresponding parameter. The function mapping relationship is integrated to generate a dynamic mapping function. The dynamic mapping function takes the coal feed rate command value as input and outputs the parameter prediction range of rotation speed, current and material density. The parameter prediction range is composed of the prediction benchmark value plus or minus the real-time floating deviation.

3. The coal feeder blockage detection method according to claim 2, characterized in that, Before integrating the function mapping relationships to generate the dynamic mapping function, the process also includes: Analyze the historical fluctuation ranges of the corresponding rotational speed, current, and material density under each coal feed rate command value in the time series dataset. The historical fluctuation ranges reflect the natural deviation range of the parameters under stable operating conditions. The parameter floating boundary under the confidence probability is calculated based on the historical fluctuation range, and the confidence probability characterizes the statistical reliability of the measured parameter value falling into the prediction interval; Based on the operating conditions corresponding to the current coal feed rate command value, the floating boundary of the parameter is dynamically scaled to generate a real-time floating deviation. The real-time floating deviation changes with the coal feed rate command value, and the width of the parameter prediction interval is adaptively adjusted.

4. The coal feeder blockage detection method according to claim 1, characterized in that, When the real-time rotation speed and the material density detection value remain within the normal operating range for a stable duration, the vibration intensity of the first coal vibration component and the second coal vibration component is reduced in stages until it stops, including: The process of reducing the intensity of the vibration is divided into several progressive decay stages. Each decay stage is maintained for a fixed duration and the intensity decrease gradually decreases. The number of progressive decay stages is positively correlated with the cumulative duration during which the parameters remain normal within the stable duration. After each attenuation stage, it is checked whether the real-time value of the rotation speed and the material density detection value deviate from the normal operating range. If a deviation occurs, the vibration intensity of the previous stage is immediately restored and the stabilization time is re-accumulated. When the intensity level is reduced to the lowest setting and the real-time value of the rotation speed and the material density detection value remain normal, the second coal vibration component is turned off and the first coal vibration component is kept running at the basic intensity for the final recovery time. Once the final recovery time has ended and the parameters show no abnormal fluctuations, all coal vibration components should be stopped.

5. A coal feeder coal blockage detection device, characterized in that, The coal feeder blockage detection method based on any one of claims 1-4 includes: The data acquisition module is used to acquire the real-time values ​​of the rotational speed, current, and material density of the coal feeder during the current detection cycle. The data calculation module is used to acquire time-series datasets of coal feed rate command values, measured speed values, measured current values, and measured material density values ​​under multiple working conditions. Based on the time-series dataset, a dynamic mapping function from the coal feed rate command values ​​to the speed, current, and material density is generated through machine learning algorithms. Combined with the coal feed rate command values ​​received by the coal feeder, the dynamic normal operating range of the speed, current, and material density is calculated through the dynamic mapping function. The normal operating range is adaptively adjusted as the coal feed rate command values ​​change. The coal blockage detection module is used to determine that the coal feeder is blocked when the real-time value of the rotation speed, the real-time value of the current, and the material density detection value deviate from the corresponding normal operating range of the coal feed rate command value by more than a preset threshold, and to start the vibration component in the raw coal bunker that supplies coal to the coal feeder.

6. An electronic device, characterized in that, include: At least one processor; and a memory connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, the instructions being executed by the at least one processor to cause the at least one processor to perform the coal feeder blockage detection method as described in any one of claims 1-4.

7. A computer-readable storage medium, characterized in that, It stores computer instructions, which, when executed by a processor, implement the coal feeder blockage detection method as described in any one of claims 1-4.

Images