An intelligent adjustment method and system for real-time feedback and stable pneumatic conveying

Abstract

The present invention relates to the technical field of material conveying regulation, and discloses an intelligent regulation method and system for real-time feedback and stable conveying in pneumatic conveying. The method includes obtaining the material flow rate in the conveying pipeline and the end pressures at both ends of the pipeline; predicting the wear condition in the pipeline under the corresponding flow rate and pressure conditions based on the real-time measured material flow rate and end pressure data; transmitting the measured material flow rate, end pressure, and wear prediction data to the intelligent feedback control module through the network segment interface; the intelligent feedback control module performs data processing and analysis using intelligent algorithms based on the received real-time data to obtain the change conditions of the material flow rate and end pressure in the pipeline; and according to the adjustment result of the intelligent feedback control module, the on-site data is adjusted in real time to achieve real-time adjustment of the pneumatic conveying process. The system includes a monitoring module, an intelligent feedback control module, a wear prediction module, a feeding module, a pipeline extraction module, and a conveying pipeline. The present invention realizes real-time feedback and stable conveying in pneumatic conveying.

Description

Technical Field

[0001] The present invention relates to the technical field of material conveying regulation, and particularly to an intelligent regulation method and system for real-time feedback and stable conveying of pneumatic conveying. Background Art

[0002] Material conveying technology refers to the technology of transferring materials from one location or device to another location or device. It is widely used in various industrial fields, including manufacturing, mining, construction, and agriculture, etc. The general principle is to utilize principles such as mechanics, fluid mechanics, and electrical control, and use different conveying equipment and conveying methods to transfer materials from the starting point to the end point. The specific forms include: conveyor belt conveying, screw conveying, vacuum conveying, pneumatic conveying, and conveying pipe conveying, etc. Almost all industrial production processes are inseparable from the conveying of solid materials. Pneumatic conveying is a typical material conveying technology, and its basic process is to use air as the carrier medium to convey materials from one place to another; pneumatic conveying is widely used in the transportation of solid materials due to its flexible design, space saving, low maintenance cost, and less environmental pollution.

[0003] The speed of the materials conveyed pneumatically in the pipeline is the most important factor affecting the erosion wear rate. The wear of the pipeline during the conveying process is inevitable, and frequent equipment replacement and maintenance greatly affect the production efficiency. If the air flow speed is too high, the impact or friction energy between the materials and the inner wall of the pipeline will increase, thus exacerbating the wear of the pipeline. On the other hand, if the air flow speed is too low, the conveyed materials will deposit in the pipeline, which may cause pipeline blockage. However, in the existing pneumatic conveying technology, the opaque pipeline makes it impossible to judge the particle state in the pipeline, and there are many interference factors. Therefore, a new method is urgently needed to detect the particle state.

[0004] Prior art one, application number: CN 201811576983.8 discloses a method and device for measuring the speed, density, and flow rate of pneumatically conveyed solid materials. By obtaining the transit time of the same flow state flowing through a preset distance in the measuring tube (chamber) through the change of the electric field signal, the movement speed of the solid materials is obtained by "distance ÷ transit time"; by obtaining the space filling ratio of the solid materials in the measuring tube (chamber) through the change of the electric field signal, the suspension density of the solid materials is obtained by "space filling ratio of solid materials × bulk density of solid materials"; and then the flow rate of the solid materials in the measuring tube (chamber) is obtained by "movement speed × space filling ratio of solid materials × bulk density of solid materials × cross-sectional area of the measuring tube (chamber)". Although the measuring method and device can accurately measure the flow speed, concentration, and real-time flow rate of the solid particulate matter or powdery substances conveyed pneumatically in the pipeline in a safe, economical, and reliable manner. However, the air flow speed is not accurately controlled, resulting in easy pipeline blockage.

[0005] Prior Art 2, Application No.: CN 201610463811.4 discloses a method for evaluating the solid-phase mass flow rate of a dense-phase pneumatic conveying system, including the following steps: obtaining the structural parameters of a Venturi tube installed on a dense-phase pneumatic conveying pipeline and the parameters of the conveying medium; conducting pure gas-phase and gas-solid two-phase calibration experiments on the dense-phase pneumatic conveying system to obtain fitting coefficients; calculating the solid mass flow rate Ms of the dense-phase pneumatic conveying system by the iterative method according to the obtained structural parameters of the Venturi tube, the parameters of the conveying medium, and the fitting coefficients. Although it breaks through the limitation that the previous Venturi flowmeter is only applicable to the dilute-phase gas-solid conveying system, by introducing a two-phase flow factor to correct the influence of the carrier gas density and the solid-gas ratio, it is applied to the dense-phase pneumatic conveying field, and the iterative trial-and-error logic algorithm with the smallest deviation is used to evaluate the solid-phase mass flow rate, achieving an evaluation deviation of the solid-phase mass flow rate within ±10% during the dense-phase pneumatic conveying process. However, it is impossible to judge the particle state in the pipeline, and there are many interference factors, resulting in the inability to adjust the air flow velocity according to the particle state, which reduces the conveying efficiency to a certain extent.

[0006] Prior Art 3, Application No.: CN 202010807964.2 discloses a solid flowmeter accuracy detection system and method. A discharging device is set to provide a powder with a stable discharging mass flow rate. The powder passes through a first feeding pipeline provided with a solid flowmeter under the action of wind. Secondly, the air velocity is adjusted by a air supply device so that the powder forms a stable pneumatic conveying state in the first feeding pipeline; then the powder mass flow rate detected by the solid flowmeter at this time is compared with the powder discharging mass flow rate provided by the discharging device to judge the accuracy of the solid flowmeter. Although the application of a magnetic coupling in the discharging device improves the measurement accuracy of the powder discharging mass flow rate of the discharging device; at the same time, when the powder is in a stable pneumatic conveying state, all of it can be measured by the solid flowmeter, improving the detection accuracy of the solid flowmeter, so as to achieve the purpose of accurately measuring the accuracy of the solid flowmeter, and the detection device is also simpler. However, its structure is relatively simple, and it is impossible to achieve the purpose of adjusting the air flow velocity according to the particle state, which is likely to cause pipeline blockage.

[0007] Currently, Prior Art 1, Prior Art 2 and Prior Art 3 have the problems of being unable to judge the particle state in the pipeline and having many interference factors, which reduce the conveying efficiency. Therefore, the present invention provides a pneumatic conveying real-time feedback stable conveying intelligent adjustment method and system, which improves the monitoring and control system of traditional pneumatic conveying to realize real-time regulation of operation parameters such as air intake volume and solid-gas ratio according to the conveying state in the pipeline, thereby improving the conveying stability and efficiency. Summary of the Invention

[0008] The main purpose of the present invention is to provide a pneumatic conveying real-time feedback stable conveying intelligent adjustment method and system to solve the problems in the prior art that it is impossible to judge the particle state in the pipeline, there are many interference factors, and the conveying efficiency is reduced.

[0009] To achieve the above object, the present invention provides the following technical solutions:

[0010] An intelligent adjustment method for real-time feedback and stable conveying in pneumatic conveying, the intelligent adjustment method for real-time feedback and stable conveying in pneumatic conveying includes:

[0011] Obtain the material flow rate in the conveying pipeline and the end pressures at both ends of the pipeline; based on the material flow rate and end pressure data measured in real time, predict the wear condition in the pipeline under the corresponding flow rate and pressure conditions;

[0012] Transmit the measured material flow rate, end pressure, and wear prediction data to the intelligent feedback control module through the network segment interface; the intelligent feedback control module uses intelligent algorithms to process and analyze the received real-time data to obtain the changes in the material flow rate and end pressure in the pipeline;

[0013] According to the adjustment result of the intelligent feedback control module, adjust the on-site data in real time, including controlling the valve, adjusting the feeding speed of the feeding system, and adjusting the pipeline extraction system, to achieve real-time adjustment of the pneumatic conveying process.

[0014] As a further improvement of the present invention, the process of obtaining the material flow rate includes:

[0015] Connect the flange of the sensor to the measurement pipeline, directly install it on the measurement pipeline, convert the material flow rate in the measurement pipeline into an electrical signal; transmit the signal to the converter; the converter is installed in the intelligent feedback control module and is responsible for processing and calculating the signal sent by the sensor;

[0016] The converter processes and calculates the signal sent by the sensor and the current signal output by the motor frequency converter for adjusting the feeding speed; through the processing and calculation of the signal, the converter obtains the values of the instantaneous flow rate and the cumulative flow rate; according to the sensor signal and the current signal output by the motor frequency converter, the converter can calculate the flow rate value at the current moment, representing the actual flow rate of the material at this moment, for real-time monitoring and control;

[0017] The converter displays the processed and calculated results, including the instantaneous flow rate and the cumulative flow rate; it can also be displayed and monitored in the intelligent feedback control module; according to the feedback result of the temperature monitoring system, the intelligent feedback control module automatically adjusts; the output signal of the adjustment will be sent to the motor frequency converter in the feeding module to adjust the feeding speed, and automatically adjust the material flow rate as needed.

[0018] As a further improvement of the present invention, the process of converting the material flow rate in the measurement pipeline into an electrical signal includes:

[0019] Install the vibration sensor on the measurement pipeline, either on the side wall or the bottom of the pipeline, to sense the vibration of the material inside the pipeline; when solid material flows through the pipeline, vibration will be generated, and the vibration sensor will sense the vibration and convert it into an electrical signal;

[0020] The electrical signal output by the vibration sensor is amplified and filtered through a signal conditioning circuit; by performing spectral analysis on the vibration signal, the frequency distribution of the vibration signal is obtained, and the measured frequency is matched with the pre-established flow-frequency characteristic curve to calculate the flow rate of the material;

[0021] Among them, the window function of the rectangular window is selected to reduce spectral leakage, and the specific steps are as follows:

[0022] Divide the vibration signal into segments of windows, each window having a length of N. For each window, apply the rectangular window function w(n)=1, 0≤n<N for windowing processing to obtain the windowed signal;

[0023] Perform spectral analysis on the windowed signal, perform a fast Fourier transform (FFT) on the windowed signal to convert the time-domain signal into a frequency-domain signal, and calculate the spectral information of the signal, that is, the frequency distribution;

[0024] Match the measured frequency distribution with the pre-established flow-frequency characteristic curve;

[0025] According to the matched flow value and the form of the characteristic curve, use interpolation to calculate the corresponding material flow rate value; the calculated flow rate value will be converted into an electrical signal for output.

[0026] As a further improvement of the present invention, the process of the converter obtaining the value of the cumulative flow rate includes:

[0027] Perform discrete sampling on the continuous sensor signal or the current signal output by the motor frequency converter to obtain a series of sampling points;

[0028] According to the values of the sampling points and the sampling interval, use the Simpson's method for numerical integration. The Simpson's method approximates the integral curve with a quadratic polynomial based on three consecutive points within the integral interval, thereby obtaining the integral result;

[0029] If the number of sampling points is odd, use the composite Simpson's 1 / 3 method, group the sampling points into two consecutive three-point subintervals, then apply the Simpson's 1 / 3 method for integration to each subinterval, and finally accumulate the integral results of the subintervals to obtain the total integral result;

[0030] If the number of sampling points is even, the Simpson's 1 / 3 rule cannot be applied to the last sub-interval; use the composite Simpson's 3 / 8 rule, group the sampling points into consecutive three-point sub-intervals, then apply the Simpson's 3 / 8 rule to each sub-interval for integration, and finally accumulate the integration results of the sub-intervals to obtain the total integration result;

[0031] Accumulate the integration results of each sub-interval to obtain the cumulative value of the entire signal.

[0032] As a further improvement of the present invention, the process of obtaining the end pressures at both ends of the pipeline includes:

[0033] Install pressure sensors at the inlet and outlet of the conveying pipeline respectively to monitor the pressure changes at the inlet end and the outlet end in real time; through the pressure sensors, convert the pressure signals at the inlet end and the outlet end into electrical signals, and perform sampling and conversion to obtain discrete pressure data;

[0034] Process and analyze the discrete pressure data, and find the law of the corresponding relationship between the end pressure and the particle blockage through the correlation coefficient;

[0035] Among them, collect the data of the end pressure and the degree of particle blockage within a certain period of time, and perform preprocessing of removing outliers on the collected data; select the Spearman correlation coefficient for calculation, and the formula is:

[0036] r s =1-(6*Σ(D i 2 )) / (j*(j 2 -1))

[0037] In the formula, D i is the rank difference of the variables, and j is the number of data samples;

[0038] According to the calculated Spearman correlation coefficient, judge the correlation between the end pressure and the degree of particle blockage. The value range of the correlation coefficient is from -1 to 1. Close to 1 indicates a strong positive correlation, close to -1 indicates a strong negative correlation, and close to 0 indicates a weak or no correlation;

[0039] According to the results of data processing and analysis, establish a relationship model between the particle state and the end pressure to describe the quantitative relationship between the degree of particle blockage and the end pressure, and use it to judge the particle motion state.

[0040] As a further improvement of the present invention, the direction rule of gas flow is from the place with higher total pressure to the place with lower total pressure. The formula for the total pressure of gas flow is:

[0041] P 总 =P 势 +P 动 =P 静+P 位 +P 动 =P 背 +P 0 +P 动

[0042] wherein, P 0 is the standard atmospheric pressure at the same level of the measurement point. The energy difference between two cross-sections in the pipeline air flow, i.e., the total pressure difference, is the fundamental reason for the air flow to flow. P 势 represents the potential energy pressure of the gas, which is the pressure energy possessed by the gas due to its position. P 动 represents the kinetic energy pressure of the gas, which is the pressure energy possessed by the gas due to its velocity. P 静 represents the static pressure of the gas, which is the pressure generated by the collision between gas molecules. P 位 represents the position pressure of the gas, which is the pressure generated by the gravity or height difference of the gas. P 背 represents the back pressure of the gas, which is the reverse pressure generated by factors such as resistance during the fluid flow process. P 动 represents the kinetic energy pressure, and P 位 represents the position pressure. They together constitute the total pressure P of the gas flow 总 ;

[0043] Combined with the fluid mechanics formula:

[0044] P 静 =P 0 +ρgh

[0045] When the particle blockage is severe, the reaction force of the particles in the pipeline on the air flow increases.

[0046] As a further improvement of the present invention, the process of predicting the wear condition in the pipeline under corresponding flow rate and pressure conditions includes:

[0047] Collecting the known wear conditions of the pipeline, including the wear amount and the easily worn areas under flow rate and pressure conditions; constructing a pipeline wear amount function based on the deep learning method, taking the flow rate, solid flow rate, pipeline length, pipeline diameter, conveying pressure, particle diameter, particle density, and particle sphericity as inputs and the wear amount as the output;

[0048] Using the existing simulation data for training, optimizing the deep learning model to obtain a model that can accurately predict the wear amount; under the given flow rate and pressure conditions, using the trained deep learning model and inputting relevant parameters to obtain the predicted wear amount;

[0049] Performing post-processing on the prediction results, obtaining the determination of the easily worn areas according to different degrees of wear amounts; setting different thresholds according to the size of the wear amounts, and dividing the areas where the wear amount exceeds the threshold into easily worn areas;

[0050] Using a numerical simulation system, a model of the conveying pipeline is constructed and a computational grid is divided; the CFD-DEM method is selected and used to solve the calculation in the simulation system. According to the equations and parameters in the numerical model, the motion trajectory, contact force, and pressure gradient force information of the particles in the pipeline are calculated;

[0051] Based on the results of the simulation calculation, a more accurate wear amount and wear-prone area are obtained. According to the contact force and pressure gradient force information between the particles, the collision force and pressure gradient force received by each particle are calculated, and then an approximate value of the wear amount is obtained;

[0052] The predicted wear amount is compared and verified with the wear amount obtained from the simulation calculation to evaluate the accuracy and reliability of the prediction model.

[0053] As a further improvement of the present invention, a pipeline wear amount function is constructed based on deep learning, and the formula expression is:

[0054] Wear=f(u,M,L,D,P,d,ρ,∈)

[0055] Where u, M, L, D, P, d, ρ, ∈ respectively represent gas flow velocity, solid flow rate, pipeline length, pipeline diameter, conveying pressure, particle diameter, particle density, and particle sphericity;

[0056] Wear prediction is calculated and determined for the exact value through a numerical simulation system;

[0057] A model of the conveying pipeline is constructed at a 1:1 equal ratio;

[0058] The constructed model is divided into a computational grid;

[0059] A numerical model and numerical method suitable for pneumatic conveying are selected; in the CFD-DEM coupling method, solid particles are regarded as a discrete phase, and their translational and rotational motions are described by Newton's second law:

[0060]

[0061] Where, v i and ω i represent the translational velocity and rotational velocity of the particles, m i , F c,ij , F p,i and F d,irepresent the mass, contact force, pressure gradient force, and drag force of the particle respectively. Here, \(i\) represents the \(i\)-th particle, where \(i\) ranges from 1 to \(N\) (\(N\) being the total number of particles), \(j\) represents the \(j\)-th particle in contact with the \(i\)-th particle, where \(j\) ranges from 1 to \(k\) (\(k\) being the number of particles in contact with the \(i\)-th particle), \(t\) represents time, \(g\) represents the acceleration due to gravity, \(k\) represents the number of particles in contact with the \(i\)-th particle, and \(I\) i represents the moment of inertia matrix of the \(i\)-th particle, and \(M\) ij represents the rotational coupling matrix between the \(i\)-th particle and the \(j\)-th particle;

[0062] The contact force between particles or between a particle and a wall is calculated using the soft-sphere contact model. The collision force \(F\) received by each particle C is as follows:

[0063]

[0064] where \(F\) C represents the collision force received by the particle, which is the contact force between particles or between a particle and a wall. \(k\) n represents the normal elastic coefficient between particles, which is used to calculate the normal elastic force, represents the normal displacement between the \(i\)-th particle and the \(j\)-th particle, which is used to calculate the normal elastic force. \(\gamma\) n represents the normal damping coefficient between particles, which is used to calculate the normal damping force. \(v\) r represents the relative velocity between particles. \(n\) ij represents the normal unit vector between particles. \(k\) t represents the tangential elastic coefficient between particles, which is used to calculate the tangential elastic force, represents the tangential displacement between the \(i\)-th particle and the \(j\)-th particle, which is used to calculate the tangential elastic force. \(\gamma\) t represents the tangential damping coefficient between particles, which is used to calculate the tangential damping force. \(F\) p,i represents the pressure gradient force received by the particle, which is caused by the pressure gradient of the flow field where the particle is located, represents the gradient of the pressure field. \(V\) p represents the volume of the particle;

[0065] The drag force received by each particle is calculated using the Gidaspow drag force model, which couples the Wen - Yu model and the Ergun model. The calculation formula is as follows:

[0066]

[0067] where \(D1\) and \(D2\) represent the Wen - Yu drag force model and the Ergun drag force model respectively:

[0068]

[0069] C 1 With C 2 being constants, with values of 180 and 2 respectively, in addition, the calculation formula for Cd is:

[0070]

[0071] In the CFD-DEM method, the gas phase is regarded as a continuous phase, and its mass conservation and momentum conservation formulas are as follows:

[0072]

[0073] Among them, D p represents the drag force received by each particle, α p represents the volume fraction of the i-th particle, α cp represents the critical value of the maximum volume fraction of particles, D 1 represents the drag force calculated using the Wen-Yu model, D 2 represents the drag force calculated using the Ergun model, C d represents the drag coefficient of particles, ρ g represents the density of the gas phase, u g represents the velocity of the gas phase, u p represents the velocity of the i-th particle, ρ p represents the density of particles, r p represents the radius of particles, C1 and C2 represent the constants in the Gidaspow model, which are 180 and 2 respectively, Re represents the Reynolds number, which is a dimensionless parameter of gas-phase flow, and the calculation formula is Among them, μ g represents the dynamic viscosity of the gas phase, ρ g represents the pressure of the gas phase, F gp represents the force between the gas and solid received by the particles, τ g represents the shear stress of the gas phase, represents the time derivative, represents the gradient operation;

[0074] By coupling CFD and DEM, the solution calculation is carried out in the numerical simulation system;

[0075] According to the production situation, the density and viscosity physical property parameters of particles and air substances are given, the conveying velocity and inlet pressure are given, and the outlet pressure boundary conditions are given;

[0076] The results calculated by the numerical simulation system are processed to obtain the wear amount and the easily worn area.

[0077] As a further improvement of the present invention, the changes in the material flow rate and end pressure in the pipeline are obtained, including:

[0078] Fuzzify the material flow rate and end pressure data obtained from real-time measurement, mapping the specific material flow rate and end pressure values to the membership degrees in the fuzzy sets; according to domain knowledge, design a set of fuzzy rules to describe the relationship between the material flow rate and the end pressure. Each rule contains a condition part and a conclusion part. The condition part is the fuzzy sets of the material flow rate and the end pressure, and the conclusion part is the fuzzy sets of the material flow rate and the end pressure to be inferred.

[0079] Utilize the fuzzy rule base for fuzzy inference. Based on the fuzzy sets of the material flow rate and the end pressure, through the fuzzy inference mechanism in the fuzzy rule base, infer the changes in the material flow rate and the end pressure inside the pipeline; the fuzzy rule base collects the actual data of the material flow rate and the end pressure inside the pipeline, conducts data analysis, finds out the patterns and correlations therein, obtains a set of fuzzy rules to describe the relationship between the material flow rate and the end pressure, and maps the specific material flow rate and end pressure values to the membership degrees in the fuzzy sets.

[0080] Convert the membership values of the fuzzy sets obtained from fuzzy inference into specific material flow rate and end pressure values, map the fuzzy sets to specific numerical values to obtain the changes in the material flow rate and the end pressure inside the pipeline.

[0081] To achieve the above object, the present invention also provides the following technical solutions:

[0082] A pneumatic conveying real-time feedback stable conveying intelligent regulation system, which is applied to the pneumatic conveying real-time feedback stable conveying intelligent regulation method. The pneumatic conveying real-time feedback stable conveying intelligent regulation system includes:

[0083] A monitoring module for real-time monitoring of the key parameters of the pneumatic conveying system, including the material flow rate, end pressure, valve opening degree, and feeding speed. The monitoring module transmits the collected data to the subsequent intelligent feedback control module;

[0084] An intelligent feedback control module for real-time feedback control using advanced control algorithms based on the real-time data transmitted by the monitoring module. According to the difference between the monitored actual parameters and the set target values, adjust the valve opening degree and the output of the feeding speed controller to achieve stable regulation of the material flow rate and the end pressure;

[0085] A wear prediction module for monitoring and analyzing the wear condition of the pneumatic conveying system to predict the wear degree of the pipeline and equipment;

[0086] A feeding module for controlling the feeding process of the material, including the start-stop control and feeding speed adjustment of the feeding system; according to the output signal of the intelligent feedback control module, adjust the feeding speed of the feeding system to achieve precise control of the material flow rate;

[0087] The pipeline extraction module is used to control the operation of the pipeline extraction fan in the pneumatic conveying system, including the adjustment of the fan speed and the start-stop control; according to the output signal of the intelligent feedback control module, the speed of the extraction fan is adjusted to achieve precise control of the end pressure;

[0088] The conveying pipeline is the actual pneumatic conveying pipeline and is responsible for the conveying of materials.

[0089] In the present invention, through the monitoring of the material flow rate and the end pressure, the material flow rate and the end pressure information in the pipeline are obtained in real time; through wear prediction, the wear condition in the pipeline under different flow rate and pressure conditions is predicted; these data are very important for understanding the material conveying state and wear condition in the pipeline in real time. The monitoring of the material flow rate and the end pressure can help to judge whether there are abnormal conditions in the conveying process, and the prediction of the wear condition helps to take maintenance measures in advance to reduce system failures and losses. The data of the material flow rate, the end pressure and the wear prediction are transmitted to the intelligent feedback control module through the network segment interface; the intelligent feedback control module uses intelligent algorithms to process and analyze the data to obtain the change conditions of the material flow rate and the end pressure in the pipeline; the data processing and analysis ability of the intelligent feedback control module can realize the real-time monitoring and adjustment of the material conveying process in the pipeline; through the operation of the intelligent algorithm, the change conditions of the material flow rate and the end pressure can be analyzed more accurately, providing an accurate basis for subsequent adjustment. According to the adjustment result of the intelligent feedback control module, the on-site data is adjusted in real time, including controlling the valve, adjusting the feeding speed of the feeding system and adjusting the pipeline extraction system, etc.; through the real-time adjustment of the on-site data, according to the analysis result of the intelligent feedback control module, the pneumatic conveying process can be adjusted in real time. Adjusting the control valve, the feeding system and the pipeline extraction system, etc., can achieve precise control of parameters such as the material flow rate and the end pressure, and thus realize stable material conveying. Brief Description of the Drawings

[0090] Figure 1 It is a schematic diagram of the step flow of an embodiment of the intelligent adjustment method for real-time feedback and stable conveying of pneumatic conveying in the present invention;

[0091] Figure 2 It is a schematic diagram of the step flow of obtaining the material flow rate in an embodiment of the intelligent adjustment method for real-time feedback and stable conveying of pneumatic conveying in the present invention;

[0092] Figure 3 It is a schematic diagram of the step flow of obtaining the end pressure at both ends of the pipeline in an embodiment of the intelligent adjustment method for real-time feedback and stable conveying of pneumatic conveying in the present invention;

[0093] Figure 4 It is a schematic diagram of the step flow of predicting the wear condition in the pipeline under the corresponding flow rate and pressure conditions in an embodiment of the intelligent adjustment method for real-time feedback and stable conveying of pneumatic conveying in the present invention;

[0094] Figure 5 Schematic diagram of the specific step flow for calculating the wear condition upon completion of an embodiment of the intelligent regulation method for real-time feedback and stable conveying in pneumatic conveying according to the present invention;

[0095] Figure 6 Schematic diagram of the step flow for obtaining the variation of the material flow rate and the end pressure in the pipeline in an embodiment of the intelligent regulation method for real-time feedback and stable conveying in pneumatic conveying according to the present invention;

[0096] Figure 7 Schematic diagram of the step flow for realizing real-time regulation of the pneumatic conveying process in an embodiment of the intelligent regulation method for real-time feedback and stable conveying in pneumatic conveying according to the present invention;

[0097] Figure 8 Schematic diagram of the functional modules in an embodiment of the intelligent regulation system for real-time feedback and stable conveying in pneumatic conveying according to the present invention;

[0098] Figure 9 Schematic diagram of the principle of the intelligent regulation system for real-time feedback and stable conveying in pneumatic conveying according to the present invention. Detailed implementation manners

[0099] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without making creative efforts fall within the scope of protection of the present invention.

[0100] The terms "first", "second", and "third" in the present invention are only used for descriptive purposes, and cannot be construed as indicating or implying relative importance or implicitly specifying the quantity of the indicated technical features. Thus, the features defined with "first", "second", and "third" may explicitly or implicitly include at least one of such features. In the description of the present invention, the meaning of "a plurality" is at least two, such as two, three, etc., unless otherwise specifically and clearly defined. All directional indications (such as up, down, left, right, front, back...) in the embodiments of the present invention are only used to explain the relative positional relationship and movement conditions between components in a specific posture (as shown in the drawings). If the specific posture changes, the directional indications will also change accordingly. In addition, the terms "comprising" and "having" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or device that includes a series of steps or units is not limited to the listed steps or units, but may optionally further include steps or units not listed, or may optionally further include other steps or units inherent to these processes, methods, products, or devices.

[0101] Reference to "embodiments" in this document means that the specific features, structures, or characteristics described in connection with the embodiments can be included in at least one embodiment of the present invention. The phrase appears in various places in the specification and does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein can be combined with other embodiments.

[0102] As Figure 1 shown, this embodiment provides an embodiment of the intelligent regulation method for real-time feedback and stable conveying of pneumatic conveying. In this embodiment, the intelligent regulation for real-time feedback and stable conveying of pneumatic conveying specifically includes the following steps:

[0103] Step S1: Obtain the material flow rate in the conveying pipeline and the end pressures at both ends of the pipeline; predict the wear condition in the pipeline under the corresponding flow rate and pressure conditions based on the real-time measured material flow rate and end pressure data.

[0104] Step S2: Transmit the measured material flow rate, end pressure, and wear prediction data to the intelligent feedback control module through the network segment interface; the intelligent feedback control module processes and analyzes the received real-time data using intelligent algorithms to obtain the change conditions of the material flow rate and end pressure in the pipeline.

[0105] Step S3: According to the adjustment result of the intelligent feedback control module, adjust the on-site data in real time, including controlling valves, adjusting the feeding speed of the feeding system, and adjusting the pipeline extraction system, etc., to achieve real-time adjustment of the pneumatic conveying process.

[0106] Preferably, in step S1 of this embodiment, the material flow rate and end pressure information in the pipeline are obtained in real time through material flow rate monitoring and end pressure monitoring; through wear prediction, the wear conditions in the pipeline under different flow rate and pressure conditions are predicted; these data are very important for understanding the material transportation state and wear conditions in the pipeline in real time. The monitoring of the material flow rate and end pressure can help determine whether there are abnormal conditions during the transportation process, and the prediction of wear conditions helps to take maintenance measures in advance, reducing system failures and losses. In step S2, data is transmitted through the network segment interface, and the material flow rate, end pressure, and wear prediction data are transmitted to the intelligent feedback control module; the intelligent feedback control module uses intelligent algorithms to process and analyze the data to obtain the changes in the material flow rate and end pressure in the pipeline; the data processing and analysis capabilities of the intelligent feedback control module can achieve real-time monitoring and adjustment of the material transportation process in the pipeline; through the operation of intelligent algorithms, the changes in the material flow rate and end pressure can be analyzed more accurately, providing an accurate basis for subsequent adjustment. In step S3, according to the adjustment results of the intelligent feedback control module, the on-site data is adjusted in real time, including controlling valves, adjusting the feeding speed of the feeding system, and adjusting the pipeline extraction system, etc.; by adjusting the on-site data in real time, the pneumatic conveying process can be adjusted in real time according to the analysis results of the intelligent feedback control module. Adjusting control valves, the feeding system, and the pipeline extraction system, etc., can achieve precise control of parameters such as material flow rate and end pressure, and thus achieve stable material transportation.

[0107] In summary, through each step of the real-time feedback and stable transportation intelligent adjustment method for pneumatic conveying in this embodiment, the real-time monitoring and adjustment of the pneumatic conveying process can be achieved; by obtaining data such as material flow rate and end pressure in real time, predicting wear conditions, and performing data processing and analysis through the intelligent feedback control module, the real-time adjustment of the pneumatic conveying process can be achieved; it helps to improve the stability and efficiency of the pneumatic conveying system, reduce the risk of wear and failure, and improve the intelligent and automated level of the system.

[0108] The goal of the entire method in this embodiment is to achieve real-time feedback and stable transportation during the pneumatic conveying process. Through the real-time data acquisition and wear prediction of the monitoring module, the intelligent feedback control system can make real-time adjustments according to the changes in the material flow rate and end pressure in the pipeline to maintain stable material transportation; it can improve the transportation efficiency, reduce wear and failures, and reduce the need for manual intervention, improving the intelligent and automated level of the system.

[0109] In this embodiment, an intelligent feedback control is added to the pneumatic conveying system, which can maintain the stability of the system by continuously adjusting the input signal and has a certain anti-interference ability in the face of external interference and changes. The actual output can be compared with the expected output in real time through this system, and the feedback control enables the system to more accurately achieve the expected goal. Through the application of this system, while reducing the labor cost, the need for on-site manual observation is greatly reduced. While improving the work efficiency, the personnel safety is increased and the working environment is improved. The stability of the conveying is achieved. Through the real-time monitoring and feedback of on-site data, automatic adjustment is carried out to keep the conveying in a stable stage.

[0110] Further, as Figure 2 shown, the process of obtaining the material flow rate in step S1 specifically includes the following steps:

[0111] Step S11: Connect the flange of the sensor to the measurement pipeline and directly install it on the measurement pipeline to convert the material flow rate in the measurement pipeline into an electrical signal; transmit the signal to the converter; the converter is installed in the intelligent feedback control module and is responsible for processing and calculating the signal sent by the sensor;

[0112] Step S12: The converter processes and calculates the signal sent by the sensor and the current signal output by the motor frequency converter for adjusting the blanking speed; through the processing and calculation of the signal, the converter obtains the values of the instantaneous flow rate and the cumulative flow rate; according to the sensor signal and the current signal output by the motor frequency converter, the converter can calculate the flow rate value at the current moment, which represents the actual flow rate of the material at this moment and is used for real-time monitoring and control;

[0113] Step S13: The converter displays the results after processing and calculation, including the instantaneous flow rate and the cumulative flow rate; it can also be displayed and monitored in the intelligent feedback control module; according to the feedback result of the temperature monitoring system, the intelligent feedback control module automatically adjusts; the output signal of the adjustment will be sent to the motor frequency converter in the feeding module to adjust the blanking speed, and the automatic adjustment of the material flow rate can be realized as needed.

[0114] Preferably, in step S11 of this embodiment, the sensor is installed on the measurement pipeline, which can directly measure the material flow rate in the pipeline and convert it into an electrical signal. The converter is responsible for receiving the sensor signal and performing processing and calculations. The purpose of these steps is to obtain real-time data of the material flow rate. By converting the material flow rate into an electrical signal, the data can be more easily transmitted and processed. The intelligent feedback control module can use this data for subsequent processing and adjustment. In step S12, the converter receives the sensor signal and the current signal output by the motor frequency converter and performs processing and calculations on them. Through processing and calculations, the converter can calculate the values of the instantaneous flow rate and the cumulative flow rate. The purpose of these steps is to process the sensor signal to obtain the specific value of the material flow rate. The calculation results of the instantaneous flow rate and the cumulative flow rate are very important for understanding the material conveying situation in real time and can be used as the basis for subsequent adjustment. In step S13, the converter displays the results of processing and calculations, including the instantaneous flow rate and the cumulative flow rate. The results can be displayed and monitored in the intelligent feedback control module. According to the feedback results of the temperature monitoring system, the intelligent feedback control module can automatically adjust and send the output signal of the adjustment to the motor frequency converter in the feeding module to achieve automatic adjustment of the material flow rate. The purpose of these steps is to achieve real-time display and monitoring of the material flow rate and automatically adjust it. The display and monitoring results can help the operator understand the material flow rate situation in time, and the adjustment output signal can achieve automatic adjustment of the material flow rate. This can maintain the stability and accuracy of material conveying and improve the automation and intelligence level of the system.

[0115] In the specific measurement steps of this embodiment, the cooperation between the sensor and the converter plays a key role. The sensor is responsible for converting the material flow rate into an electrical signal, and the converter is responsible for processing and calculating the signal and displaying the results. The intelligent feedback control module automatically adjusts according to the display results to achieve adjustment of the feeding speed. The whole process is based on a ring anti-interference sensor and charge induction technology, which has the advantages of high sensitivity, good linearity, and reduced maintenance and cleaning frequency.

[0116] The measurement principle of this embodiment is based on Faraday's law of electromagnetic induction The measuring tube of the flowmeter is lined with a non-magnetic alloy short tube of insulating material. The electrodes penetrate the pipe wall along the diameter direction and are fixed on the measuring tube, and the electrodes are basically flush with the inner surface of the lining. When the excitation coil is excited by a double square wave pulse, a working magnetic field with a magnetic flux density of ΔΦ will be generated in a direction perpendicular to the axis of the measuring tube. At this time, if particles flow through the measuring tube, they will cut the magnetic force lines and induce an electromotive force E, which is inversely proportional to the magnetic flux density ΔΦ. At this time, the magnetic flux density is inversely proportional to the amount of material flowing through the measuring tube and is proportional to the product of the inner diameter d and the average flow velocity u. The electromotive force E (flow signal) is detected by the electrodes and sent to the converter through a cable. After the converter amplifies and processes the flow signal, it can display the fluid flow rate and output signals such as pulses and analog currents for flow control and regulation. A uniform electromagnetic wave measurement field is generated in the measuring tube through special capacitive coupling technology. The material entering the pipeline interacts with the electromagnetic wave, and the frequency and amplitude of the generated signal are calculated and processed in the central processing unit.

[0117] The particle flow rate in the pipeline is calculated according to the following formula:

[0118] Q = ρuA

[0119] In the formula, Q is the mass flow rate of the particles, ρ is the particle concentration, u is the particle velocity, and A is the cross-sectional area of the pipeline;

[0120] The measurement of the particle concentration is carried out through the coupling of a high-frequency alternating electromagnetic field in the measuring ring. The material passing through this measurement area will weaken the energy of this field. Parameters such as the temperature, pressure of the measured substance, and the solid component ratio of the solid medium will not affect the measurement result. As long as the flow state conforms to axisymmetric flow (such as laminar flow or turbulent flow), it will not affect the measurement result. The size of the particle flow rate is proportional to the number of particles of the solid medium and the flow velocity of the medium. When the number of particles increases and the flow velocity of the medium accelerates, the induced voltage generated becomes lower. After being amplified, shaped, filtered, and operated by the amplifier circuit, a standard current signal linearly proportional to the flow rate is finally output. It is supplied for counting processing and finally converted into a flow rate for display. There are no moving and flow-blocking components in the measuring tube, so there is almost no pressure loss and it has high reliability.

[0121] Further, the process of converting the material flow rate in the measuring pipeline into an electrical signal in step S11 specifically includes the following steps:

[0122] Step S111: Install a vibration sensor on the measuring pipeline, usually on the side wall or bottom of the pipeline, to sense the vibration of the material in the pipeline; when solid material flows through the pipeline, it will generate vibration, and the vibration sensor will sense the vibration and convert it into an electrical signal;

[0123] Step S112: The electrical signal output by the vibration sensor is amplified and filtered by the signal conditioning circuit; by performing spectral analysis on the vibration signal, the frequency distribution of the vibration signal is obtained, and by matching the measured frequency with the pre-established flow-frequency characteristic curve, the flow rate of the material can be calculated;

[0124] Among them, a rectangular window window function is selected to reduce spectral leakage, improve the frequency resolution, and improve the accuracy of spectral analysis; the specific steps are as follows:

[0125] The vibration signal is divided into segments of windows, each window having a length of N. For each window, windowing processing is performed using the rectangular window function w(n)=1, 0≤n<N to obtain the windowed signal;

[0126] Perform spectral analysis on the windowed signal, perform a fast Fourier transform (FFT) on the windowed signal to convert the time-domain signal into a frequency-domain signal, and calculate the spectral information of the signal, that is, the frequency distribution;

[0127] Match the measured frequency distribution with the pre-established flow-frequency characteristic curve. The characteristic curve reflects the relationship between the material flow rate and the frequency of the vibration signal. Through the experimental process, measure the vibration signal frequency under different flow conditions and record the corresponding flow rate values. According to the measured frequency and flow rate data, a flow-frequency characteristic curve can be established. Multiple groups of experiments need to be carried out under different flow conditions to cover the entire flow range; according to the measured frequency distribution, find the matching flow rate value;

[0128] Step S113: According to the matching flow rate value, combined with the form of the characteristic curve, use interpolation to calculate the corresponding material flow rate value; the calculated flow rate value will be converted into an electrical signal and output.

[0129] Preferably, in step S111 of this embodiment, the vibration information of the material is converted into a measurable electrical signal, providing input data for subsequent signal processing and flow rate calculation. In step S112, through signal processing and spectral analysis, the vibration signal is converted into frequency information related to the material flow rate, and the material flow rate value is obtained through characteristic curve matching; the technical effect of selecting the rectangular window window function for windowing processing is to reduce spectral leakage, improve the frequency resolution, and improve the accuracy of spectral analysis; through the windowing processing of the rectangular window function, the signal in the frequency range of interest can be prominently displayed in spectral analysis, reducing interference at other frequencies, thereby improving the accuracy of the spectral analysis result. In step S113, an accurate material flow rate value is obtained according to the frequency distribution and the characteristic curve.

[0130] In summary, these steps in this embodiment convert the vibration signal into material flow information, and calculate the accurate flow value through signal processing and spectrum analysis means; realizing the real-time monitoring and calculation of the material flow in the pipeline. Through the vibration sensor and spectrum analysis, the material flow information can be obtained non-invasively without direct contact with the material, improving safety and convenience. At the same time, by establishing the flow-frequency characteristic curve, the material flow can be quickly and accurately calculated according to the frequency distribution of the vibration signal, providing important parameters and data support for industrial production and process control.

[0131] In this embodiment, by matching the spectrum analysis of the rectangular window function with the flow-frequency characteristic curve, the calculation of the material flow can be realized; combining signal processing and spectrum analysis technologies can improve the accuracy and reliability of flow calculation to a certain extent. Through the above steps, the vibratory flowmeter can convert the material flow in the measurement pipeline into an electrical signal; it is suitable for the flow measurement of certain solid materials, especially with good results when dealing with some granular or powdered materials. Some sensors will convert the measured material flow into an electrical signal output, usually an analog signal (such as a voltage signal or a current signal). These analog signals can be directly transmitted to the converter for further processing and calculation to obtain the values of instantaneous flow and cumulative flow. The converter can convert the analog signal into a digital signal according to requirements and perform relevant algorithm processing and display.

[0132] In this embodiment, for the flow measurement of solid materials, a weighing flowmeter can also be used: calculating the flow by measuring the weight change of the material during the material transportation process, and using a weighing sensor or a weighing platform to achieve it. A pinhole flowmeter: measuring the flow by setting a pinhole in the material flow channel. Calculating the flow by measuring the pressure difference under the pinhole. An airtightness flowmeter: suitable for gas flow measurement, calculating the flow by measuring the gas emission of solid materials.

[0133] Further, the process of the converter obtaining the value of the cumulative flow in step S12 specifically includes the following steps:

[0134] Step S121: Discretely sample the continuous sensor signal or the current signal output by the motor frequency converter to obtain a series of sampling points;

[0135] Step S122: According to the values of the sampling points and the sampling interval, perform numerical integration operations using the Simpson's method. The Simpson's method approximates the integral curve with a quadratic polynomial based on three consecutive points within the integral interval, thereby obtaining the integral result;

[0136] If the number of sampling points is odd, the composite Simpson's 1 / 3 rule is used. The sampling points are grouped into two consecutive three-point subintervals, and then the Simpson's 1 / 3 rule is applied to each subinterval for integration. Finally, the integration results of the subintervals are accumulated to obtain the total integration result.

[0137] If the number of sampling points is even, the Simpson's 1 / 3 rule cannot be applied to the last subinterval. The composite Simpson's 3 / 8 rule is used. The sampling points are grouped into consecutive three-point subintervals, and then the Simpson's 3 / 8 rule is applied to each subinterval for integration. Finally, the integration results of the subintervals are accumulated to obtain the total integration result.

[0138] Step S123: Accumulate the integration results of each subinterval to obtain the cumulative value of the entire signal.

[0139] Preferably, in step S121 of this embodiment, the continuous signal is converted into discrete sample points, which facilitates subsequent numerical integration operations. The significance of discrete sampling is to convert the continuous change of the signal into discrete data points, which is convenient for further processing and analysis. Step S122 obtains the integration results within each subinterval; step S123 accumulates the integration results of each subinterval to obtain the cumulative value of the entire signal within the integration interval; through numerical integration operations, the cumulative quantity or cumulative change quantity of the signal can be solved. For sensor signals, the cumulative quantity can represent the cumulative value of a certain physical quantity. For example, the cumulative quantity of flow represents the cumulative volume of fluid passing through. For the current signal output by the motor frequency converter, the cumulative quantity can represent the cumulative value of the current, such as the cumulative current during motor operation.

[0140] The solution of the cumulative quantity in this embodiment is of great significance for many applications. For example, for flow calculation, it is necessary to integrate the input flow velocity to obtain the cumulative flow. For motor control, it is necessary to integrate the current to obtain the cumulative power consumption. The solution of the cumulative quantity can provide an understanding of important information such as the system state and energy consumption, and support subsequent analysis, control, and decision-making.

[0141] In summary, in this embodiment, through discrete sampling and numerical integration operation of the Simpson's method, the cumulative value of the sensor signal or the current signal output by the motor frequency converter can be solved, so as to obtain the cumulative amount or cumulative change amount of the signal. By processing and operating on the sensor signal and the current signal output by the motor frequency converter, the converter can directly obtain the values of the instantaneous flow rate and the cumulative flow rate. Compared with the traditional material flow measurement method, this method has the following differences: Non-invasive: The sensor is installed on the measurement pipeline without directly contacting the material, avoiding interference and pollution to the material flow; Real-time: By processing the sensor and motor frequency converter signals in real time, the instantaneous flow rate value can be obtained in real time, which is suitable for real-time monitoring and control of the material flow; Accuracy: By processing and operating on the signal, the accuracy and precision of the flow measurement can be improved, and the measurement error can be reduced; Automatic adjustment: The intelligent feedback control module automatically adjusts the feeding speed according to the flow monitoring result, realizes the automatic control of the material flow, and improves the efficiency and stability of the production process.

[0142] In this embodiment, by processing and operating on the sensor signal and combining with the output signal of the motor frequency converter, the values of the instantaneous flow rate and the cumulative flow rate can be obtained in real time and accurately, and the automatic adjustment of the material flow can be realized. Compared with the traditional material flow measurement method, it has the advantages of non-invasiveness, real-time, accuracy and automatic adjustment.

[0143] Furthermore, as Figure 3 shown, the process of obtaining the end pressures at both ends of the pipeline in step S1 specifically includes the following steps:

[0144] Step S14: Install pressure sensors at the inlet and outlet of the conveying pipeline respectively to monitor the pressure changes at the inlet end and the outlet end in real time; through the pressure sensors, convert the pressure signals at the inlet end and the outlet end into electrical signals, and perform sampling and conversion to obtain discrete pressure data;

[0145] Step S15: Process and analyze the discrete pressure data, and find the law of the corresponding relationship between the end pressure and the particle blockage through the correlation coefficient;

[0146] Among them, collect the data of the end pressure and the degree of particle blockage within a certain period of time, and perform preprocessing of removing outliers on the collected data; select the Spearman correlation coefficient for calculation, and the formula is:

[0147] r s = 1 - (6 * Σ(D i 2 )) / (j * (j 2 - 1))

[0148] In the formula, D i is the rank difference of the variable, and j is the number of data samples;

[0149] According to the calculated Spearman correlation coefficient, judge the correlation between the end pressure and the degree of particle blockage. The value range of the correlation coefficient is from -1 to 1. Close to 1 indicates a strong positive correlation, close to -1 indicates a strong negative correlation, and close to 0 indicates a weak or no correlation;

[0150] Step S16: According to the results of data processing and analysis, establish a relationship model between the particle state and the end pressure, describe the quantitative relationship between the degree of particle blockage and the end pressure, and be used to judge the particle motion state.

[0151] Preferably, in step S14 of this embodiment, the pressure data at the inlet end and the outlet end are obtained for subsequent processing and analysis; by installing pressure sensors, the pressure changes at both ends of the pipeline can be monitored in real time, providing data support for subsequent particle state judgment. In step S15, by processing and analyzing the pressure data, the relationship law between the end pressure and particle blockage is found; through the correlation coefficient, a large amount of data can be statistically analyzed to find the quantitative relationship between the end pressure and the degree of particle blockage; calculating the correlation coefficient between the end pressure and the degree of particle blockage and judging their linear relationship can initially understand the correlation between the end pressure and particle blockage, and provide a basis for subsequent analysis and modeling. Step S16: According to the results of data processing and analysis, establish a relationship model between the particle state and the end pressure. This model can be used to accurately judge the particle motion state. By monitoring the end pressure, it can be judged whether the particles in the pipeline are blocked, so as to realize the monitoring and control of the conveying process; through the monitoring and analysis of the end pressure, the particle motion state and the blockage situation in the pipeline can be accurately judged, which is of great significance for the stable operation and troubleshooting of the conveying system; by establishing a relationship model between the particle state and the end pressure, the occurrence of particle blockage can be predicted, and corresponding measures can be taken for cleaning and maintenance to maintain a stable gas flow rate and velocity, improving production efficiency and product quality.

[0152] In summary, in this embodiment, through the end pressure monitoring system at both ends of the pipeline, by installing pressure sensors, processing and analyzing pressure data, and establishing a relationship model between the particle state and the end pressure, the particle motion state can be accurately judged, the monitoring and control of the conveying process can be realized, and the production efficiency and product quality can be improved.

[0153] In this embodiment, the back pressure change is caused by the change of the outlet static pressure, and the change of the static pressure is caused by the blockage of the conveyed particles. Therefore, both the back pressure and the end pressure can reflect the conveying state, but the end pressure is more accurate and the back pressure is more lagging. For the end pressure monitoring system, the particle movement state can be accurately judged through the end pressure. In production, by accurately finding the law of the corresponding relationship between the end pressure and particle blockage, a relationship model between the particle state and the end pressure is established. Considering that the gas density change in the conveying pipeline is not large, and then considering that the mass of the gas is very small and can be ignored, then the potential pressure energy h 位 can be ignored, and the change of the blast back pressure is caused by the change of the static pressure energy h 静 . The rule of the gas flow direction is from the place with large total pressure to the place with small total pressure. The total pressure formula of the gas flow is:

[0154] P 总 =P 势 +P 动 =P 静 +P 位 +P 动 =P 背 +P 0 +P 动

[0155] In the formula, P 0 is the standard atmospheric pressure at the same level of the measuring point. The energy difference between the two cross-sections in the pipeline gas flow, that is, the total pressure difference, is the fundamental reason for the gas flow to be able to flow. P 势 represents the potential energy pressure of the gas, indicating the pressure energy that the gas has due to its position. P 动 represents the kinetic energy pressure of the gas, indicating the pressure energy that the gas has due to its velocity. P 静 represents the static pressure of the gas, indicating the pressure generated by the collision between gas molecules. P 位 represents the potential pressure of the gas, indicating the pressure generated by the gas due to gravity or height difference. P 背 represents the back pressure of the gas, indicating the reverse pressure generated by the fluid during the flow process due to factors such as resistance. P 动 represents the kinetic energy pressure, and P 位 represents the potential pressure. They together constitute the total pressure P 总 .

[0156] Combined with the fluid mechanics formula:

[0157] P 静 =P 0 +ρgh

[0158] When the particle blockage is severe, the reaction force of the particles in the pipeline on the air flow increases; a greater back pressure is required to overcome this reaction force. Otherwise, the instantaneous static pressure energy received at the end decreases, the end back pressure decreases, and the instantaneous blower total pressure remains unchanged. With the resistance coefficient unchanged, the gas flow rate does not meet the conveying requirements; when the particle blockage collapses, the total pressure received by the end air flow instantaneously becomes smaller, the total pressure difference instantaneously becomes larger, and the air flow velocity is unstable, not meeting the requirements for the air flow velocity in the pipeline during conveying. Therefore, when there is particle blockage, in order to keep the gas flow rate and velocity stable to meet the conveying requirements when the material quantity remains unchanged, the blower back pressure (total pressure) should be increased at this time, that is, the static pressure energy at the measurement point is increased, so that the back pressure at the measurement point also increases accordingly.

[0159] Further, the process of establishing the relationship model between the particle state and the end pressure in step S16 specifically includes the following steps:

[0160] Step S161: Collect training data including the end pressure and the degree of particle blockage. According to the relationship between the particle state and the end pressure, select the features with a linear relationship with the end pressure as independent variables;

[0161] Step S162: Establish a linear regression model, with the selected features as independent variables and the end pressure as the dependent variable; use the training data for model fitting, solve the coefficients of the model, and use the least squares method for parameter estimation to minimize the error between the predicted value and the actual value of the model;

[0162] Step S163: Evaluate the fitting degree and performance of the model, calculate indicators such as the R-square value and the root mean square error to evaluate the accuracy and reliability of the model; use the established linear regression model to predict new end pressure data, and judge the motion state of the particles based on the degree of particle blockage predicted by the model.

[0163] Preferably, in step S161 of this embodiment, the data relationship between the end pressure and the degree of particle blockage is obtained by collecting and preparing training data. According to the relationship between the particle state and the end pressure, the features having a linear relationship with the end pressure are selected as independent variables; by collecting and preparing training data, a data basis is provided for establishing the relationship model between the particle state and the end pressure, and selecting the features having a linear relationship with the end pressure as independent variables helps to establish a simple and easily interpretable linear regression model. In step S162, a linear regression model is established, with the selected features as independent variables and the end pressure as the dependent variable. The training data is used for model fitting, and the coefficients of the model are solved by the least squares method to minimize the error between the predicted value and the actual value of the model; by establishing a linear regression model, the linear relationship between the particle state and the end pressure can be described, and through parameter estimation, the coefficients of the model can be obtained, so that the unknown end pressure can be predicted. In step S163, the fitting degree and performance of the model are evaluated by calculating indexes such as the R-square value and the root mean square error. The established linear regression model is used to predict the new end pressure data, and the movement state of the particles is judged through the degree of particle blockage predicted by the model; by evaluating the accuracy and reliability of the model, the fitting degree of the linear regression model to the relationship between the particle state and the end pressure is judged. By predicting the degree of particle blockage through the model, the movement state of the particles can be judged, providing a reference basis for further analysis and control. Evaluating the performance of the model and the accuracy of prediction using the model helps to improve the effect of particle state monitoring and optimization. Through the above steps, a relationship model between the particle state and the end pressure can be established to describe the quantitative relationship between the degree of particle blockage and the end pressure. In this way, the movement state of the particles can be accurately judged, and corresponding control and optimization can be carried out. It is necessary to select appropriate models and methods according to the actual situation, and conduct appropriate model verification and adjustment to ensure the accuracy and reliability of the model.

[0164] Further, as Figure 4 shown, the process of predicting the wear condition in the pipeline under the corresponding flow rate and pressure conditions in step S1 specifically includes the following steps:

[0165] Collect the known pipeline wear conditions, including the wear amount and the easily worn area under the flow rate and pressure conditions; construct a pipeline wear amount function based on the deep learning method, with the flow rate, solid flow rate, pipeline length, pipeline diameter, conveying pressure, particle size, particle density, and particle sphericity as inputs and the wear amount as the output;

[0166] Use the existing simulation data for training to optimize the deep learning model to obtain a model that can accurately predict the wear amount; under the given flow rate and pressure conditions, use the trained deep learning model to input relevant parameters to obtain the predicted wear amount;

[0167] Post-process the prediction results, and obtain the determination of the easily worn area according to the different degrees of wear; set different thresholds according to the magnitude of the wear amount, and divide the area where the wear amount exceeds the threshold into the easily worn area;

[0168] Use a numerical simulation system to construct a model of the conveying pipeline and perform computational grid division; select the CFD-DEM method and use this method to solve and calculate in the simulation system. According to the equations and parameters in the numerical model, calculate information such as the movement trajectory, contact force, and pressure gradient force of the particles in the pipeline;

[0169] According to the results of the simulation calculation, obtain a more accurate wear amount and easily worn area. According to information such as the contact force and pressure gradient force between particles, calculate the collision force and pressure gradient force received by each particle, and then obtain an approximate value of the wear amount;

[0170] Compare and verify the predicted wear amount with the wear amount obtained from the simulation calculation, and evaluate the accuracy and reliability of the prediction model.

[0171] Preferably, in this embodiment, a prediction model for pipeline wear is established. By inputting parameters such as flow rate, solid flow rate, pipeline length, pipeline diameter, conveying pressure, particle size, particle density, and particle sphericity, the wear amount can be predicted; through machine learning methods, the known wear conditions are converted into a function for subsequent wear prediction. By training the model, it can accurately predict the wear amount and establish a reliable prediction model that can predict the wear amount in the pipeline according to the given flow rate and pressure conditions. According to the predicted wear amount results, classify and quantify the wear conditions, and convert the prediction results of the wear amount into the determination of the easily worn area, providing guidance for subsequent maintenance and optimization. Through numerical simulation methods, simulate the movement and interaction of particles in the pipeline, and provide more accurate calculation results of the wear amount and easily worn area. Through numerical simulation, obtain more accurate calculation results of the wear amount, provide a more reliable approximate value of the wear amount, and provide a reference for the maintenance and optimization of the pipeline. By comparing the prediction results and the simulation calculation results, evaluate the accuracy of the prediction model and verify the reliability of the prediction model, providing a basis for further wear prediction and pipeline optimization.

[0172] In summary, through the above steps, this embodiment can predict the wear conditions in the pipeline under given flow rate and pressure conditions, including the wear amount and the easily worn area; it will help optimize the pipeline design, predict the wear conditions in advance, reduce the maintenance cost, and improve the reliability of the system.

[0173] In this embodiment, a pipeline wear amount function is constructed based on deep learning, and the formula expression is:

[0174] Wear=f(u,M,L,D,P,d,ρ,∈)

[0175] Among them, u, M, L, D, P, d, ρ, and ∈ represent gas flow velocity, solid flow rate, pipeline length, pipeline diameter, conveying pressure, particle diameter, particle density, and particle sphericity, respectively;

[0176] Wear prediction can only provide approximate values of the wear area and wear volume. Then, a numerical simulation system is used to calculate and determine the exact values. The steps are as follows:

[0177] Construct a model of the conveying pipeline in a 1:1 equal ratio;

[0178] Perform computational grid division on the constructed model;

[0179] Select numerical models and numerical methods suitable for pneumatic conveying. The specific selection reasons and detailed numerical models are as follows:

[0180] For the gas-solid two-phase flow in the pneumatic conveying process, it is particularly important to select a suitable multiphase flow model in the system. The Computational Fluid Dynamics - Discrete Element Method (CFD-DEM) simulation is a powerful tool that can accurately simulate particle motion and the interaction between particles and fluids, and simulate complex mechanical properties such as particle agglomeration, particle breakage, and contact heat transfer. It can also simulate the phenomena of particle accumulation and separation in a fluid medium, track the motion trajectories of particles, and calculate the fluid forces acting on particles. These advantages make the CFD-DEM simulation an important tool for the design and optimization of pneumatic conveying systems.

[0181] In the CFD-DEM coupling method, solid particles are regarded as the discrete phase. Their translational and rotational motions are described by Newton's second law:

[0182]

[0183]

[0184] Among them, v i and ω i represent the translational velocity and rotational velocity of the particle, m i , F c,ij , F p,i and F d,i represent the mass, contact force, pressure gradient force, and drag force of the particle, respectively. i represents the i-th particle, and the value range of i is from 1 to N, where N is the total number of particles. j represents the j-th particle in contact with the i-th particle, and the value range of j is from 1 to k, where k is the number of particles in contact with the i-th particle. t represents time, g represents the acceleration due to gravity, k represents the number of particles in contact with the i-th particle, I i represents the inertia matrix of the i-th particle's rotation, M ijrepresents the rotational coupling matrix between the i-th particle and the j-th particle;

[0185] The contact force between particles or between a particle and the wall is calculated by the soft-sphere contact model. The collision force F received by each particle C is as follows:

[0186]

[0187] where F C represents the collision force received by the particle, which is the contact force between particles or between a particle and the wall, and k n represents the normal elastic coefficient between particles and is used to calculate the normal elastic force. represents the normal displacement between the i-th particle and the j-th particle and is used to calculate the normal elastic force, and γ n represents the normal damping coefficient between particles and is used to calculate the normal damping force, and v r represents the relative velocity between particles, and n ij represents the normal unit vector between particles, and k t represents the tangential elastic coefficient between particles and is used to calculate the tangential elastic force. represents the tangential displacement between the i-th particle and the j-th particle and is used to calculate the tangential elastic force, and γ t represents the tangential damping coefficient between particles and is used to calculate the tangential damping force, and F p,i represents the pressure gradient force received by the particle, which is caused by the pressure gradient of the flow field where the particle is located. represents the gradient of the pressure field, and V p represents the volume of the particle;

[0188] The drag force received by each particle is calculated using the Gidaspow drag force model, which couples the Wen-Yu model and the Ergun model. The calculation formula is as follows:

[0189]

[0190] where D1 and D2 represent the Wen-Yu drag force model and the Ergun drag force model respectively:

[0191]

[0192] C1 and C2 are constants, and their values are 180 and 2 respectively. In addition, the calculation formula for Cd is:

[0193]

[0194] In the CFD-DEM method, the gas phase is regarded as a continuous phase, and its mass conservation and momentum conservation formulas are as follows:

[0195]

[0196] Among them, D p represents the drag force received by each particle, and α p represents the volume fraction of the i-th particle, and α cp represents the critical value of the maximum volume fraction of the particles, and D 1 represents the drag force calculated using the Wen-Yu model, and D 2 represents the drag force calculated using the Ergun model, and C d represents the drag coefficient of the particles, and ρ g represents the density of the gas phase, and u g represents the velocity of the gas phase, and u p represents the velocity of the i-th particle, and ρ p represents the density of the particles, and r p represents the radius of the particles. C1 and C2 represent the constants in the Gidaspow model, which are 180 and 2 respectively. Re represents the Reynolds number, which is a dimensionless parameter of the gas-phase flow, and the calculation formula is Among them, μ g represents the dynamic viscosity of the gas phase, and ρ g represents the pressure of the gas phase, and F gp represents the force between the gas and the solid received by the particles, and τ g represents the shear stress of the gas phase, represents the time derivative, represents the gradient operation;

[0197] By coupling the above CFD and DEM and performing the solution calculation in the numerical simulation system, a scenario approximate to the actual working condition can be simulated;

[0198] According to the production situation, physical property parameters such as the density and viscosity of substances such as particles and air are given, and boundary conditions such as the conveying velocity and the inlet and outlet pressures are given;

[0199] The results calculated by the numerical simulation system are processed to obtain the wear amount and the easily worn area.

[0200] As Figure 5 shown, the specific process after the calculation in this embodiment is as follows:

[0201] Define the boundary conditions: Determine the boundary conditions of the fluid domain, including the inlet and outlet conditions of the fluid, the wall conditions, etc. These conditions will affect the flow of the fluid and the movement of the particles;

[0202] Initialize the fluid domain: According to the set initial conditions and boundary conditions, initialize the parameters of the fluid domain, including the density, velocity field, pressure field, etc. of the fluid. These parameters will start the initial state of the fluid;

[0203] Computational fluid domain: According to fluid mechanics equations (such as the Navier-Stokes equations) and the mass conservation equation, combined with boundary conditions, use numerical methods (such as the finite difference method or the finite element method) to discretize the fluid domain and perform iterative calculations; through iterative calculations, the distribution of parameters such as velocity and pressure at different positions within the fluid domain can be obtained;

[0204] Update force, coordinates, velocity, etc.: Based on the parameters of the fluid domain obtained from the calculation, use them as inputs in the particle dynamics simulation to update the force, coordinates, velocity, etc. of the particles. These update processes involve the interaction forces between particles and the interaction forces between particles and the fluid;

[0205] Calculate particle contact force: According to the contact model between particles (such as the Hertz contact model or the DEM discrete element model), calculate the contact force between particles. The calculation of the contact force involves parameters such as the contact points, contact areas, and contact deformations between particles;

[0206] Calculate particle drag force: According to the interaction force between particles and the fluid, calculate the drag force exerted on the particles. The calculation of the drag force is usually based on theoretical models of fluid mechanics, such as Stokes' law or the Drag model;

[0207] Iterative calculation: Based on the updated force, coordinates, velocity, etc. of the particles, perform the calculation of the fluid domain and the update of the particle dynamics simulation again. This process is an iterative process. Through continuous iterative calculations, it gradually approaches the stable state of the system;

[0208] Calculation completion: When the parameters of the system reach a certain stability or meet the set termination conditions, the calculation process ends. At this time, the final states of the fluid domain and the particles can be obtained, including the velocity field and pressure field of the fluid, as well as the positions and velocities of the particles.

[0209] Furthermore, as Figure 6 shown, the specific steps for obtaining the changes in the material flow rate and end pressure in the pipeline in step S2 are as follows:

[0210] Step S21: Fuzzify the material flow rate and end pressure data obtained from real-time measurement, and map the specific material flow rate and end pressure values to the membership degrees in the fuzzy set; according to domain knowledge, design a set of fuzzy rules to describe the relationship between the material flow rate and the end pressure. Each rule contains a condition part and a conclusion part. The condition part is the fuzzy set of the material flow rate and the end pressure, and the conclusion part is the fuzzy set of the material flow rate and the end pressure to be inferred;

[0211] Step S22: Using the fuzzy rule base, perform fuzzy inference. Based on the fuzzy sets of the material flow rate and the end pressure, through the fuzzy inference mechanism in the fuzzy rule base, infer the changes in the material flow rate and the end pressure inside the pipeline; the fuzzy rule base collects the actual data of the material flow rate and the end pressure inside the pipeline, and conducts data analysis to find the patterns and correlations therein, obtaining a set of fuzzy rules that describe the relationship between the material flow rate and the end pressure, by mapping the specific material flow rate and end pressure values to the membership degrees in the fuzzy sets;

[0212] Step S23: Convert the membership values of the fuzzy sets obtained from the fuzzy inference into specific material flow rate and end pressure values, and map the fuzzy sets to specific numerical values to obtain the changes in the material flow rate and the end pressure inside the pipeline.

[0213] Preferably, in step S21 of this embodiment: Convert the specific material flow rate and end pressure values into fuzzy sets, so as to be processed in the subsequent fuzzy inference. Through the fuzzy processing, it is possible to process uncertain and fuzzy data, and incorporate domain knowledge into the rules to describe the relationship between the material flow rate and the end pressure. Step S22 infers the changes in the material flow rate and the end pressure through fuzzy inference according to the rules in the fuzzy rule base; it can use the fuzzy inference method to process data containing uncertainty and fuzziness, thereby inferring the changes in the material flow rate and the end pressure inside the pipeline. Step S23 converts the fuzzy sets into specific numerical values, thereby obtaining the specific changes in the material flow rate and the end pressure inside the pipeline, and converting the results of the fuzzy inference into an understandable and applicable numerical form for convenient further analysis and decision-making.

[0214] In summary, in this embodiment, the data obtained from the real-time measurement is subjected to fuzzy processing, and fuzzy inference is performed based on domain knowledge, thereby inferring the changes in the material flow rate and the end pressure inside the pipeline; it can help process uncertain and fuzzy data, provide information on the pipeline operation status, support decision-making and optimize pipeline operation. By using fuzzy logic to process and analyze the data, the changes in the material flow rate and the end pressure inside the pipeline can be obtained and provided to the intelligent feedback control module for real-time adjustment. The advantage of fuzzy logic is that it can process fuzzy and uncertain information and is suitable for complex control problems. It can perform real-time adjustment based on fuzzy rules and fuzzy inference according to real-time measurement data to keep the pneumatic conveying system stable and safe.

[0215] Further, the specific steps for inferring the changes in the material flow rate and the end pressure inside the pipeline in step S22 are as follows:

[0216] Step S221: Perform fuzzy processing on the material flow rate and end pressure data obtained from the real-time measurement, and map the specific material flow rate and end pressure values to the membership degrees in the fuzzy sets;

[0217] Step S222: Based on the fuzzy sets of material flow rate and end pressure, perform fuzzy inference using the fuzzy rule base;

[0218] Step S223: Based on the fuzzy sets of material flow rate and end pressure in the condition part, through the fuzzy inference mechanism in the fuzzy rule base, infer the fuzzy set of the change situation of the material flow rate and end pressure in the pipeline.

[0219] Preferably, in step S221 of this embodiment, the specific material flow rate and end pressure values are converted into fuzzy sets for subsequent fuzzy inference processing, which can handle uncertain and fuzzy data and convert them into the form of fuzzy sets for subsequent inference. Step S222 infers the fuzzy set of the change situation of the material flow rate and end pressure through fuzzy inference according to the rules in the fuzzy rule base; it can use the fuzzy inference method to infer the change situation of the material flow rate and end pressure in the pipeline based on the rules in the fuzzy rule base. Step S223 obtains the fuzzy set of the change situation of the material flow rate and end pressure according to the result of the fuzzy inference; it can provide a description of the change situation of the material flow rate and end pressure in the pipeline from the perspective of the fuzzy set, providing a basis for subsequent analysis and decision-making.

[0220] In summary, this embodiment uses the fuzzy processing and fuzzy inference methods to infer the fuzzy set of the change situation of the material flow rate and end pressure in the pipeline; it can help handle uncertain and fuzzy data, provide information on the pipeline operation status, support decision-making and optimize pipeline operations.

[0221] Further, as Figure 7 shown, the process of realizing real-time adjustment of the pneumatic conveying process in step S3 specifically includes the following steps:

[0222] Step S31: Set the target values of the material flow rate and end pressure; measure and collect the actual values of the material flow rate and end pressure in real time through sensors, and the actual values are the change situations of the material flow rate and end pressure; compare the actual values with the target values and calculate the error, where error = target value - actual value;

[0223] Step S32: Process the error to obtain the adjustment amount, where:

[0224] Proportional term: Calculate the adjustment amount proportionally according to the magnitude of the error, which is used to quickly respond to the error;

[0225] Integral term: Calculate the adjustment amount by time integration according to the accumulation of the error, which is used to eliminate the steady-state error;

[0226] Differential term: Calculate the adjustment amount by time differentiation according to the change rate of the error, which is used to suppress overshoot and improve the system response speed;

[0227] The specific calculation process of the adjustment amount is as follows:

[0228] Proportional term calculation: According to the magnitude of the error, calculate the adjustment amount proportionally. The calculation formula for the proportional term is:

[0229] Proportional term adjustment amount = proportional gain × error

[0230] Among them, the proportional gain is an adjustable parameter used to adjust the sensitivity of the proportional term to the error. By appropriately adjusting the proportional gain, the magnitude of the adjustment amount can be controlled to achieve a rapid response to the error;

[0231] Integral term calculation: According to the accumulation of the error, calculate the adjustment amount by integrating over time. The calculation formula for the integral term is:

[0232] Integral term adjustment amount = integral gain × ∫(error dt)

[0233] Among them, the integral gain is an adjustable parameter used to adjust the sensitivity of the integral term to the error. By appropriately adjusting the integral gain, the magnitude of the adjustment amount can be controlled to achieve a steady-state compensation for the error;

[0234] Derivative term calculation: According to the rate of change of the error, calculate the adjustment amount by differentiating over time. The calculation formula for the derivative term is:

[0235] Derivative term adjustment amount = derivative gain × d(error) / dt

[0236] Among them, the derivative gain is an adjustable parameter used to adjust the sensitivity of the derivative term to the rate of change of the error; by appropriately adjusting the derivative gain, the magnitude of the adjustment amount can be controlled to achieve the suppression of the rate of change of the error and the improvement of the system response speed;

[0237] Comprehensive calculation: Add the proportional term adjustment amount, the integral term adjustment amount, and the derivative term adjustment amount to obtain the final adjustment amount, that is:

[0238] Adjustment amount = proportional term adjustment amount + integral term adjustment amount + derivative term adjustment amount

[0239] By comprehensively considering the magnitude, accumulation, and rate of change of the error, as well as the corresponding proportional, integral, and derivative gains, the final adjustment amount can be obtained. This adjustment amount will be used as the output of the controller for corresponding adjustment operations, such as controlling the opening of the valve, adjusting the feeding speed of the feeding system, etc.

[0240] Step S33: Perform corresponding adjustment operations according to the calculated adjustment amount, including: controlling the opening adjustment of the valve; adjusting the feeding speed of the feeding system; adjusting the parameters of the pipeline extraction system; preset the corresponding relationship between the adjustment amount and the valve opening, feeding speed, and pipeline extraction system parameters, obtain the actual values of the adjusted material flow rate and end pressure through real-time measurement and acquisition, and perform comparison and calculation again to optimize the adjustment process. Through continuous adjustment and feedback, gradually approach the target value;

[0241] Among them, according to the calculated adjustment amount, determine the change direction and amplitude of the opening of the adjustment valve; if the adjustment amount is positive, it means that it is necessary to increase the material flow rate or end pressure. At this time, it is necessary to gradually increase the opening of the valve; if the adjustment amount is negative, it means that it is necessary to decrease the material flow rate or end pressure. At this time, it is necessary to gradually decrease the opening of the valve;

[0242] According to the magnitude of the adjustment amount, it is possible to select to gradually adjust or continuously adjust the opening of the valve. The opening of the valve can be controlled by an electric or pneumatic actuator and adjusted according to the actual situation.

[0243] During the adjustment process, combined with the data measured and acquired in real time, adjust through a feedback control algorithm to gradually approach the target value of the valve opening, so as to achieve the adjustment of the material flow rate and end pressure;

[0244] Adjust the feeding speed of the feeding system:

[0245] According to the calculated adjustment amount, determine the adjustment direction and amplitude of the feeding speed of the feeding system. If the adjustment amount is positive, it means that it is necessary to increase the material flow rate or end pressure. At this time, it is necessary to gradually increase the feeding speed of the feeding system; if the adjustment amount is negative, it means that it is necessary to decrease the material flow rate or end pressure. At this time, it is necessary to gradually decrease the feeding speed of the feeding system;

[0246] According to the magnitude of the adjustment amount, it is possible to select to gradually adjust or continuously adjust the feeding speed of the feeding system. The feeding speed can be adjusted by adjusting the speed of the feeding device (such as a conveyor belt or a screw conveyor) of the feeding system or controlling the opening of the feeding valve;

[0247] During the adjustment process, similarly, combined with the data measured and acquired in real time, adjust through a feedback control algorithm to gradually approach the target value of the feeding speed of the feeding system, so as to achieve the adjustment of the material flow rate and end pressure;

[0248] Adjust the parameters of the pipeline extraction system:

[0249] According to the calculated adjustment amount, determine the adjustment direction and amplitude of the parameters of the pipeline extraction system. For example, according to the positive or negative value of the adjustment amount, gradually increase or decrease the speed of the extraction fan, or adjust the size of the extraction pipeline;

[0250] According to the magnitude of the adjustment amount, it is possible to select step-by-step adjustment or continuous adjustment of the parameters of the pipeline extraction system;

[0251] During the adjustment process, it is also possible to combine the real-time measured and collected data and perform adjustment through a feedback control algorithm, so that the parameters of the pipeline extraction system gradually approach the target value to achieve the adjustment of the material flow rate and the end pressure.

[0252] Preferably, in step S31 of this embodiment, the actual situations of the material flow rate and the end pressure are accurately obtained, providing basic data for subsequent adjustment, establishing a reference standard for adjustment, and providing target indicators for realizing a stable pneumatic conveying process. In step S32, the adjustment amount is calculated according to the error situation to achieve the adjustment of the material flow rate and the end pressure; the adjustment amount is accurately calculated according to the actual situation to provide accurate control instructions for subsequent adjustment operations. In step S33, according to the instruction of the adjustment amount, the real-time adjustment of the pneumatic conveying process is realized, and by adjusting the actual operation parameters, the changes of the material flow rate and the end pressure are controlled to achieve a stable conveying effect.

[0253] In summary, through the implementation of the above steps in this embodiment, the real-time adjustment of the pneumatic conveying process can be realized, ensuring the stable operation of the material flow rate and the end pressure within the target range; the performance and reliability of the pneumatic conveying system can be improved, and the energy consumption and maintenance costs can be reduced. At the same time, the real-time adjustment can also meet the process requirements and performance needs, ensuring the stability and efficiency of the pneumatic conveying process. By adopting a feedback control algorithm, the actual values of the material flow rate and the end pressure are compared with the target values, and the adjustment amount is obtained through calculation, and then the corresponding adjustment operations are performed according to the adjustment amount, so that the real-time adjustment of the pneumatic conveying process can be realized, the stability, responsiveness and efficiency of the system can be improved to meet the process requirements and performance needs.

[0254] In this embodiment, it is assumed that the material flow rate and the end pressure in a pneumatic conveying system need to be controlled, which involves the opening degree of the valve, the feeding speed of the feeding system and the rotation speed of the extraction fan of the pipeline extraction system. The following is an example:

[0255] Corresponding relationship between the valve opening degree and the adjustment amount:

[0256] Assume that a linear relationship is used to represent the corresponding relationship between the valve opening degree and the adjustment amount. That is, the change of the adjustment amount is proportional to the change of the valve opening degree. For example, if the adjustment amount is positive, indicating that it is necessary to increase the material flow rate or the end pressure, the corresponding relationship between the valve opening degree and the adjustment amount can be set as: valve opening degree adjustment amount = proportional coefficient × adjustment amount. Among them, the proportional coefficient is a parameter determined according to the actual system characteristics and experiments.

[0257] Corresponding relationship between the feeding speed and the adjustment amount:

[0258] Assume that a non - linear relationship is used to represent the corresponding relationship between the feeding speed and the adjustment amount. For example, a curve function can be used to represent the relationship between the feeding speed and the adjustment amount. The specific function form can be selected and optimized according to the actual situation. For example, an S - shaped curve function can be used, where the positive and negative values of the adjustment amount determine the direction and curvature of the curve to achieve the adjustment of the feeding speed.

[0259] The corresponding relationship between the pipeline extraction system parameters and the adjustment amount:

[0260] Assume that a linear relationship is used to represent the corresponding relationship between the pipeline extraction system parameters and the adjustment amount. For example, the corresponding relationship between the extraction fan speed and the adjustment amount can be set as: the adjustment amount of the extraction fan speed = proportional coefficient × adjustment amount. Among them, the proportional coefficient is a parameter determined according to the actual system characteristics and experiments.

[0261] It should be noted that the above are only examples. The actual corresponding relationship in practical applications needs to be analyzed and modeled according to the specific pneumatic conveying system and control requirements. In practical applications, the accurate corresponding relationship can be determined through experiments, data analysis, and system optimization algorithms, and adjusted and optimized according to actual needs. In this way, the appropriate corresponding adjustment between the adjustment amount, the valve opening, the feeding speed, and the pipeline extraction system parameters can be achieved to achieve precise control of the material flow rate and the end pressure.

[0262] As Figure 8 shown, this embodiment also provides an embodiment of the pneumatic conveying real - time feedback stable conveying intelligent adjustment system. In this embodiment, the pneumatic conveying real - time feedback stable conveying intelligent adjustment system is applied to the pneumatic conveying real - time feedback stable conveying intelligent adjustment method in the above - mentioned embodiment. The pneumatic conveying real - time feedback stable conveying intelligent adjustment system includes a monitoring module 1, an intelligent feedback control module 2, a wear prediction module 3, a feeding module 4, a pipeline extraction module 5, and a conveying pipeline 6 that are electrically connected in sequence (for the specific principle, refer to the appendix Figure 9 ).

[0263] Among them, the monitoring module 1 is used to monitor the key parameters of the pneumatic conveying system in real time, including material flow rate, end pressure, valve opening degree, feeding speed, etc. The monitoring module 1 transmits the collected data to the subsequent intelligent feedback control module; the intelligent feedback control module 2 is used to perform real-time feedback control using advanced control algorithms according to the real-time data transmitted by the monitoring module 1. According to the difference between the monitored actual parameters and the set target values, by adjusting the controller outputs such as valve opening degree and feeding speed, the stable adjustment of the material flow rate and end pressure is achieved; the wear prediction module 3 is used to monitor and analyze the wear condition of the pneumatic conveying system, predict the wear degree of the pipeline and equipment. Based on the wear prediction results, maintenance and replacement measures can be taken in advance to ensure the normal operation and long-term stability of the system; the feeding module 4 is used to control the feeding process of the material, including the start-stop control of the feeding system and the adjustment of the feeding speed, etc.; according to the output signal of the intelligent feedback control module, the feeding speed of the feeding system is adjusted to achieve the precise control of the material flow rate. The pipeline extraction module 5 is used to control the operation of the pipeline extraction fan in the pneumatic conveying system, including the adjustment of the fan speed, start-stop control, etc.; according to the output signal of the intelligent feedback control module, the speed of the extraction fan is adjusted to achieve the precise control of the end pressure; the conveying pipeline 6 is the actual pneumatic conveying pipeline, responsible for the conveying of materials. The pipeline design and parameter settings need to be determined according to specific application requirements and material characteristics to ensure stable conveying effects.

[0264] Preferably, the monitoring module 1 of this embodiment monitors the key parameters of the pneumatic conveying system in real time, such as material flow rate, end pressure, valve opening, and feeding speed, etc.; provides accurate real-time data, which serves as the basis for subsequent intelligent feedback control and wear prediction modules, and helps to achieve precise adjustment and stable operation of the pneumatic conveying system. The intelligent feedback control module 2 performs real-time feedback control using advanced control algorithms based on the real-time data transmitted by the monitoring module 1; realizes stable adjustment of the material flow rate and end pressure by automatically adjusting parameters such as valve opening and feeding speed, and improves the operation efficiency and stability of the pneumatic conveying system. The wear prediction module 3 monitors and analyzes the wear condition of the pneumatic conveying system, predicts the wear degree of pipelines and equipment, discovers the wear condition of pipelines and equipment in advance, takes maintenance and replacement measures, avoids the influence of wear on the system performance and stability, and prolongs the service life and operation reliability of the equipment. The feeding module 4 controls the feeding process of materials, including the start-stop control and feeding speed adjustment of the feeding system; precisely adjusts the feeding speed according to the output signal of the intelligent feedback control module, realizes precise control of the material flow rate, and ensures stable conveying and accurate feeding of the pneumatic conveying system. The pipeline extraction module 5 controls the operation of the pipeline extraction fan in the pneumatic conveying system, including the adjustment of fan speed and start-stop control; adjusts the speed of the extraction fan according to the output signal of the intelligent feedback control module, realizes precise control of the end pressure, and ensures stable pressure and flow rate of the pneumatic conveying system.

[0265] In summary, through technical means such as monitoring, control, and prediction, this embodiment realizes real-time feedback and stable adjustment of the pneumatic conveying system; improves the operation efficiency and stability of the system, reduces energy consumption and maintenance costs, prolongs the equipment life, and thus improves production efficiency and economic benefits. In addition, the system can also provide reliable data support, provide a decision-making basis for aspects such as system optimization, fault diagnosis, and maintenance management, and further enhance the reliability and intelligent level of the pneumatic conveying system. The functions of the above-mentioned various modules cooperate with each other, and through means such as real-time monitoring, intelligent feedback control, and wear prediction, realize stable conveying and automatic adjustment of the pneumatic conveying system, and improve the operation efficiency and reliability of the system.

[0266] Due to reasons such as too long conveying distance, material change, and system failure, the conveying pressure will be unstable, which will affect the normal conveying of materials and may even cause the system to stop. The end pressure can be monitored in real time by the end pressure monitoring, and then the conveying state can be reflected in real time and transmitted to the intelligent feedback control module 2 in real time. The intelligent feedback control module 2 performs feedback adjustment according to the real-time state, and feeds the electrical signal back to the extraction motor in the pipeline extraction module 5 for extraction operation processing.

[0267] Due to the huge energy consumption, the inlet air velocity of pneumatic conveying will not be very high. However, if the velocity is too low, the material will start to sink and agglomerate, and the material will aggregate into groups in the pipeline, showing a group pulsation state. The bulk material will block the pipeline cross-section, forming an unstable plug. When the pressure exceeds the rated pressure of the air source, the phenomenon of pipeline blockage will occur. Moreover, the excessive accumulation of materials may damage the conveying equipment, may cause blockage, wear or corrosion, reduce the service life of the equipment and increase the maintenance cost. The material flow monitoring sub-module can well solve this problem, transmit the real-time material flow data obtained by monitoring to the intelligent feedback control module 2, and when there is a deviation in the material conveying volume, feedback the electrical signal to the belt speed regulating motor of the material feeding system for speed regulation.

[0268] Pipeline wear is a key factor affecting the efficiency and stability of the pneumatic conveying system. Pipeline wear may lead to a reduction in conveying efficiency. The worn parts are prone to adhesion and fragmentation of materials, affecting the conveying and reducing the productivity of the device. Wear may cause the pipeline to need to be replaced or repaired more frequently, thus increasing the maintenance cost. Based on deep learning, a pipeline wear database is constructed. The wear prediction module 3 predicts the severely worn areas according to the corresponding operating parameters and operating conditions. It is transmitted to the intelligent feedback control module 2 in real time, and the intelligent feedback control module 2 performs feedback adjustment according to the real-time state, and feedbacks the electrical signal to the extraction motor in the pipeline extraction module 5 for extraction operation processing.

[0269] Furthermore, the monitoring module 1 specifically includes:

[0270] The material flow monitoring sub-module is used to monitor the material flow in the pneumatic conveying system in real time, use sensors or measuring devices to measure the flow velocity or mass of the material in the pipeline, and calculate the material flow, which is used for controlling and adjusting the feeding speed in the system, starting and stopping control of the feeding system, and evaluation of the material conveying effect, etc.;

[0271] The end pressure monitoring sub-module is used to monitor the end pressure in the pneumatic conveying system in real time, and use a pressure sensor to measure the pressure condition of the pipeline; the end pressure refers to the pressure that the material in the pneumatic conveying system receives from the supply end to the outlet end, provides real-time end pressure data, and is used for controlling and adjusting the fan speed in the system, starting and stopping control of the extraction fan, and stable adjustment of the pipeline pressure, etc.

[0272] Preferably, the material flow monitoring sub-module of this embodiment monitors the material flow in the pneumatic conveying system in real time. By measuring the flow velocity or mass of the material in the pipeline and calculating the material flow rate, accurate material flow data can be provided. These data play an important role in aspects such as controlling and adjusting the feeding speed in the system, starting and stopping control of the feeding system, and evaluating the conveying effect of the material, which can help optimize the operating efficiency of the system, improve the stability and accuracy of material conveying, and achieve precise control of the material flow. The end pressure monitoring sub-module monitors the end pressure in the pneumatic conveying system in real time. By using a pressure sensor to measure the pressure condition of the pipeline, accurate end pressure data can be provided. The end pressure refers to the pressure that the material in the pneumatic conveying system receives from the supply end to the outlet end, which has an important impact on the stability of the system and the conveying effect of the material; by monitoring and precisely controlling the end pressure in real time, the fan speed can be adjusted, the starting and stopping control of the extraction fan and the stable adjustment of the pipeline pressure can be carried out to ensure the stable operation of the system and the reliability of material conveying.

[0273] Furthermore, the wear prediction module 3 specifically includes:

[0274] The parameter collection sub-module is used to collect the known pipeline wear conditions, including the wear amount and the easily worn areas under flow rate and pressure conditions; based on the deep learning method, a pipeline wear amount function is constructed, with the flow rate, solid flow rate, pipeline length, pipeline diameter, conveying pressure, particle size, particle density, and particle sphericity as inputs and the wear amount as the output;

[0275] The model training sub-module is used to train with the existing simulation data, optimize the deep learning model, and obtain a model that can accurately predict the wear amount; under given flow rate and pressure conditions, using the trained deep learning model and inputting relevant parameters to obtain the predicted wear amount;

[0276] The result processing sub-module is used to post-process the prediction results, and obtain the determination of the easily worn areas according to the different degrees of the wear amount; set different thresholds according to the size of the wear amount, and divide the areas where the wear amount exceeds the threshold into easily worn areas;

[0277] The simulation solution sub-module is used to simulate the system using numerical simulation, construct a model of the conveying pipeline, and perform computational grid division; select the CFD-DEM method and use this method to solve and calculate in the simulation system, and calculate information such as the movement trajectory, contact force, and pressure gradient force of the particles in the pipeline according to the equations and parameters in the numerical model;

[0278] The simulation result sub-module is used to obtain a more accurate wear amount and easily worn areas according to the results of the simulation calculation, calculate the collision force and pressure gradient force received by each particle according to information such as the contact force and pressure gradient force between the particles, and then obtain an approximate value of the wear amount;

[0279] A result comparison sub-module is used to compare and verify the predicted wear amount with the wear amount calculated by simulation, and evaluate the accuracy and reliability of the prediction model.

[0280] Preferably, the parameter collection sub-module of this embodiment can obtain reference information on the wear amount and the easily worn area by collecting actual operation data, providing a basis for model training and prediction; constructing a pipeline wear amount function based on the deep learning method. A function model of the pipeline wear amount is constructed using the deep learning method. It takes parameters such as flow rate, solid flow rate, pipeline length, pipeline diameter, conveying pressure, particle size, particle density, and particle sphericity as inputs, and the wear amount as the output; through the training and optimization of the deep learning model, a model that can accurately predict the wear amount can be obtained. The model training sub-module uses the existing simulation data for model training, optimizes the deep learning model, and obtains a model that can accurately predict the wear amount; through model training, the accuracy and reliability of the model can be improved, enabling it to better predict the wear condition of the pipeline. The result processing sub-module is used to post-process the prediction results and determine the easily worn area according to the different degrees of the wear amount. By setting different thresholds, the area where the wear amount exceeds the threshold is divided into the easily worn area, which helps to locate and identify possible wear problems in the system and take corresponding maintenance and improvement measures. The simulation solution sub-module uses numerical simulation to simulate the system, constructs a model of the conveying pipeline, and performs computational grid division. By using the CFD-DEM method for solution calculation, information such as the movement trajectory, contact force, and pressure gradient force of the particles in the pipeline can be calculated, which helps to obtain more accurate prediction results of the wear amount and the easily worn area. The simulation result sub-module uses the results of the simulation calculation to obtain more accurate wear amount and easily worn area. By calculating the contact force and pressure gradient force between particles, the collision force and pressure gradient force received by each particle can be obtained, thereby approximately calculating the wear amount, which can provide more accurate wear amount prediction and location of the easily worn area. The result comparison sub-module is used to compare and verify the predicted wear amount with the wear amount calculated by simulation. By evaluating the accuracy and reliability of the prediction model, the prediction ability of the model can be verified and further optimized and improved.

[0281] In summary, this embodiment provides accurate wear amount prediction and determination of the easily worn area, providing a scientific basis for system maintenance and improvement. Through the application of the wear prediction module, pipeline wear problems can be discovered and solved in a timely manner, improving the reliability and operating efficiency of the system, reducing maintenance costs and downtime. In addition, this module can also provide a decision-making basis for the optimal design, performance improvement, and fault diagnosis of the system, enhancing the intelligent level and overall benefits of the pneumatic conveying system.

[0282] Furthermore, the intelligent feedback control module 2 specifically includes:

[0283] A data processing sub-module is used to perform fuzzification processing on the material flow rate and end pressure data obtained from real-time measurement, mapping the specific material flow rate and end pressure values to the membership degrees in the fuzzy set; according to domain knowledge, a set of fuzzy rules are designed to describe the relationship between the material flow rate and the end pressure. Each rule contains a condition part and a conclusion part. The condition part is the fuzzy set of the material flow rate and the end pressure, and the conclusion part is the fuzzy set of the material flow rate and the end pressure to be inferred.

[0284] A mechanism reasoning sub-module is used to utilize the fuzzy rule base for fuzzy reasoning. According to the fuzzy sets of the material flow rate and the end pressure, through the fuzzy reasoning mechanism in the fuzzy rule base, the changes in the material flow rate and the end pressure inside the pipeline are inferred; the fuzzy rule base collects the actual data of the material flow rate and the end pressure inside the pipeline, and conducts data analysis to find out the patterns and correlations therein, obtaining a set of fuzzy rules that describe the relationship between the material flow rate and the end pressure, by mapping the specific material flow rate and end pressure values to the membership degrees in the fuzzy set.

[0285] A situation acquisition sub-module is used to convert the membership values of the fuzzy set obtained from fuzzy reasoning into specific material flow rate and end pressure values, mapping the fuzzy set to specific numerical values to obtain the changes in the material flow rate and the end pressure inside the pipeline.

[0286] Preferably, the data processing sub-module in this embodiment can discretize the continuous measurement data and convert it into fuzzy concepts by mapping the specific material flow rate and end pressure values to the membership degrees in the fuzzy set, which is helpful for subsequent fuzzy reasoning and control processing. The fuzzy rule design sub-module can introduce fuzzy reasoning into the control system through the design of fuzzy rules to achieve fuzzy control of the material flow rate and the end pressure. The fuzzy reasoning sub-module can process information with uncertainty and fuzziness through fuzzy reasoning to achieve intelligent control and adjustment of the material flow rate and the end pressure. The situation acquisition sub-module: By mapping the fuzzy set to specific numerical values, the changes in the material flow rate and the end pressure inside the pipeline can be obtained, which is helpful for obtaining specific control parameters to further adjust the working state and control strategy of the system.

[0287] In summary, these sub-modules in this embodiment achieve fuzzy control and intelligent regulation of the material flow rate and the end pressure. Through fuzzy processing, fuzzy rule design, and fuzzy inference, the fuzzy input and output information can be converted into specific control parameters to achieve intelligent feedback control of the system. This helps to improve the stability and control accuracy of the pneumatic conveying system, and achieve precise control and regulation of the material flow rate and the end pressure. In addition, fuzzy control can also handle the non-linearity and uncertainty of the system, adapt to changes and disturbances under different working conditions, and improve the robustness and adaptability of the system. Through the application of the intelligent feedback control module, the operating efficiency of the system can be optimized, energy consumption and maintenance costs can be reduced, and the overall performance and reliability of the pneumatic conveying system can be improved.

[0288] In addition, each functional unit in various embodiments of the present invention may be integrated in a processing unit, or each unit may exist physically alone, or two or more units may be integrated in one unit. The above-mentioned integrated units may be implemented in the form of hardware or in the form of software functional units. The above are only the embodiments of the present invention, and do not limit the patent scope of the present invention. Any equivalent structure or equivalent process transformation made by using the content of the specification and drawings of the present invention, or directly or indirectly applied to other related technical fields, shall be equally included in the patent protection scope of the present invention.

[0289] The specific embodiments of the invention have been described in detail above, but they are only examples, and the invention is not limited to the specific embodiments described above. For those skilled in the art, any equivalent modification or substitution of the invention is also within the scope of the invention. Therefore, all equivalent transformations, modifications, improvements, etc. made without departing from the spirit and principle of the invention should be covered by the scope of the invention.

Claims

1. A pneumatic conveying real-time feedback stable conveying intelligent adjustment method, characterized in that: The pneumatic conveying real-time feedback stable conveying intelligent adjustment method comprises: Obtain the material flow rate in the conveying pipeline and the end pressure at both ends of the pipeline; measure the material flow rate and end pressure data in real time to predict the wear condition in the pipeline under the corresponding flow rate and pressure conditions; The measured material flow, terminal pressure and wear prediction data are transmitted to the intelligent feedback control module through the network segment interface; the intelligent feedback control module processes and analyzes the data using intelligent algorithms based on the received real-time data to obtain the changes in the material flow and terminal pressure in the pipeline; According to the adjustment results of the intelligent feedback control module, the field data is adjusted in real time, including controlling the valve, adjusting the feeding speed of the feeding system and adjusting the pipeline extraction system, so as to realize the real-time adjustment of the pneumatic conveying process; Pressure sensors are installed at the inlet and outlet of the transmission pipeline to monitor the pressure changes at the inlet and outlet in real time. The pressure sensors convert the pressure signals at the inlet and outlet into electrical signals, sample and convert them, and obtain discrete pressure data. The discrete pressure data are processed and analyzed, and the corresponding relationship between the terminal pressure and particle blockage is found through the Spearman correlation coefficient; According to the results of data processing and analysis, a relationship model between particle state and terminal pressure is established to describe the quantitative relationship between particle blockage degree and terminal pressure, which is used to judge the particle movement state.

2. The pneumatic conveying real-time feedback stable conveying intelligent adjustment method according to claim 1 is characterized in that: The process of obtaining material flow includes: Connect the flange of the sensor to the measuring pipe and install it directly on the measuring pipe to convert the material flow in the measuring pipe into an electrical signal; transmit the signal to the converter; the converter is installed in the intelligent feedback control module and is responsible for processing and calculating the signal sent by the sensor; The converter processes and calculates the signal sent by the sensor and the current signal output by the motor inverter that adjusts the material feeding speed; through signal processing and calculation, the converter obtains the instantaneous flow rate and the cumulative flow rate value; based on the sensor signal and the current signal output by the motor inverter, the converter can calculate the flow rate value at the current moment, indicating the actual flow rate of the material at that moment, which is used for real-time monitoring and control; The converter displays the results after processing and calculation, including instantaneous flow and cumulative flow; it is displayed and monitored in the intelligent feedback control module; the intelligent feedback control module automatically adjusts according to the feedback results of the temperature monitoring system; the adjusted output signal will be sent to the motor inverter in the feeding module to adjust the feeding speed and realize automatic adjustment of the material flow as needed.

3. The pneumatic conveying real-time feedback stable conveying intelligent adjustment method according to claim 2 is characterized in that: The process of converting the material flow in the measuring pipeline into an electrical signal includes: The vibration sensor is installed on the measuring pipe, on the side wall or bottom of the pipe, to sense the vibration of the material in the pipe; when the solid material flows through the pipe, it will generate vibration, and the vibration sensor will sense the vibration and convert it into an electrical signal; The electrical signal output by the vibration sensor is amplified and filtered by the signal conditioning circuit; the frequency distribution of the vibration signal is obtained by performing spectrum analysis on the vibration signal, and the measured frequency is matched with the pre-established flow-frequency characteristic curve to calculate the flow rate of the material; Among them, the window function of the rectangular window is selected to reduce spectral leakage, and the specific steps are as follows: The vibration signal is divided into segments of windows, and the length of each window is N. For each window, the rectangular window function w(n)=1, 0≤n<N is applied for windowing to obtain the windowed signal; Perform spectral analysis on the windowed signal. Perform a fast Fourier transform (FFT) on the windowed signal to convert the time-domain signal into a frequency-domain signal, and calculate the spectral information of the signal, that is, the frequency distribution; Match the measured frequency distribution with the pre-established flow-frequency characteristic curve; According to the matched flow value, combined with the form of the characteristic curve, use interpolation to calculate the corresponding material flow value; the calculated flow value will be converted into an electrical signal for output.

4. The pneumatic conveying real-time feedback stable conveying intelligent adjustment method according to claim 2 is characterized in that: The process of the converter obtaining the value of the cumulative flow includes: Discretely sample the continuous sensor signal or the current signal output by the motor frequency converter to obtain a series of sampling points; According to the values of the sampling points and the sampling interval, use the Simpson method for numerical integration. The Simpson method approximates the integral curve with a quadratic polynomial based on three consecutive points within the integral interval, thereby obtaining the integral result; If the number of sampling points is odd, use the composite Simpson 1 / 3 method. Group the sampling points into two consecutive three-point subintervals, then apply the Simpson 1 / 3 method for integration to each subinterval, and finally accumulate the integral results of the subintervals to obtain the total integral result; If the number of sampling points is even, the Simpson 1 / 3 method cannot be applied to the last subinterval; use the composite Simpson 3 / 8 method. Group the sampling points into consecutive three-point subintervals, then apply the Simpson 3 / 8 method for integration to each subinterval, and finally accumulate the integral results of the subintervals to obtain the total integral result; Accumulate the integral results of each subinterval to obtain the cumulative value of the entire signal.

5. The pneumatic conveying real-time feedback stable conveying intelligent adjustment method according to claim 1 is characterized in that: The process of obtaining the end pressures at both ends of the pipeline includes: Install pressure sensors at the inlet and outlet of the conveying pipeline respectively to monitor the pressure changes at the inlet end and the outlet end in real time; through the pressure sensors, convert the pressure signals at the inlet end and the outlet end into electrical signals, and perform sampling and conversion to obtain discrete pressure data; Process and analyze the discrete pressure data, and find the law of the corresponding relationship between the end pressure and particle blockage through the correlation coefficient; Among them, collect the data of the end pressure and the degree of particle blockage within a certain period of time, and perform preprocessing of removing outliers on the collected data; select the Spearman correlation coefficient for calculation, and the formula is: r s =1-(6*Σ(D i 2 )) / (j*(j 2 -1)) Where D i is the rank difference of the variable, j is the number of data samples; According to the calculated Spearman correlation coefficient, judge the correlation between the end pressure and the degree of particle blockage. The value range of the correlation coefficient is from -1 to 1. Close to 1 indicates a strong positive correlation, close to -1 indicates a strong negative correlation, and close to 0 indicates a weak or no correlation; According to the results of data processing and analysis, establish a relationship model between the particle state and the end pressure to describe the quantitative relationship between the degree of particle blockage and the end pressure, and use it to judge the particle motion state.

6. The pneumatic conveying real-time feedback stable conveying intelligent adjustment method according to claim 5 is characterized in that: The direction rule of gas flow is from the place with higher total pressure to the place with lower total pressure. The formula for the total pressure of gas flow is: P 总 =P 势 +P 动 =P 静 +P 位 +P 动 =P 背 +P0+P 动 In the formula, P0 is the standard atmospheric pressure at the same level of the measuring point. The energy difference between the two sections of the pipeline airflow, that is, the total pressure difference, is the fundamental reason why the airflow can flow. 势 Indicates the potential pressure of the gas, which indicates the pressure energy of the gas due to its position, P 动 Indicates the kinetic pressure of the gas, which indicates the pressure energy of the gas due to its velocity, P 静 Indicates the static pressure of the gas, which is the pressure generated by the collision between molecules. P 位 Indicates the potential pressure of gas, which is the pressure of gas due to gravity or height difference, P 背 Indicates the back pressure of the gas, which indicates the reverse pressure generated by factors such as resistance during the flow of the fluid; Combined with the fluid mechanics formula: P 静 =P0+ρgh When particle blockage is serious, the reaction force of particles in the pipeline on its airflow increases.

7. The pneumatic conveying real-time feedback stable conveying intelligent adjustment method according to claim 1 is characterized in that: The process of predicting wear in the pipeline under corresponding flow and pressure conditions includes: Collect known pipeline wear conditions, including wear amount and wear-prone areas under flow and pressure conditions; construct a pipeline wear amount function based on deep learning methods, taking flow rate, solid flow rate, pipeline length, pipeline diameter, conveying pressure, particle size, particle density, and particle sphericity as inputs and wear amount as output; Use existing simulation data for training and optimize the deep learning model to obtain a model that can accurately predict the amount of wear. Under given flow and pressure conditions, use the trained deep learning model and input relevant parameters to obtain the predicted amount of wear. The prediction results are post-processed to determine the wear-prone area according to the different degrees of wear; different thresholds are set according to the size of the wear, and the area with wear exceeding the threshold is divided into the wear-prone area; Use a numerical simulation system to construct a model of the transport pipeline and divide the calculation grid; select the CFD-DEM method and use this method to solve the calculation in the simulation system. According to the equations and parameters in the numerical model, calculate the movement trajectory, contact force, and pressure gradient force information of the particles in the pipeline; According to the simulation calculation results, more accurate wear amount and wear-prone areas are obtained. According to the contact force and pressure gradient force information between particles, the collision force and pressure gradient force on each particle are calculated, and then the approximate value of wear amount is obtained. The predicted wear amount is compared and verified with the wear amount calculated by simulation to evaluate the accuracy and reliability of the prediction model.

8. The pneumatic conveying real-time feedback stable conveying intelligent adjustment method according to claim 7 is characterized in that: Based on deep learning, the pipeline wear function is constructed, and the formula is: Wear=f(u,M,L,D,P,d,ρ,∈) Where u, M, L, D, P, d, ρ, ∈ represent gas flow rate, solid flow rate, pipeline length, pipeline diameter, conveying pressure, particle size, particle density, and particle sphericity, respectively; Wear prediction is carried out through numerical simulation system to calculate and determine the exact value; Construct a model of the delivery pipeline at a 1:1 ratio; Perform computational meshing on the constructed model; Select numerical models and numerical methods suitable for pneumatic conveying; in the CFD-DEM coupling method, solid particles are regarded as discrete phases, and their translational and rotational motions are described by Newton's second law: Among them, v i and ω i Represents the translational and rotational speeds of the particles, m i , F c,ij , F p,i and F d,i They represent the mass, contact force, pressure gradient force and drag force of the particle respectively, i represents the i-th particle, the value range of i is 1 to N, N is the total number of particles, j represents the j-th particle in contact with the i-th particle, the value range of j is 1 to k, k is the number of particles in contact with the i-th particle, t represents time, g represents gravitational acceleration, k represents the number of particles in contact with the i-th particle, I i represents the moment of inertia matrix of the ith particle, M ij represents the rotational coupling matrix between the i-th particle and the j-th particle; The contact force between particles or between particles and the wall is calculated using the soft sphere contact model. The collision force F received by each particle is C As shown below: Among them, F C It represents the collision force received by the particle, which is the contact force between particles or between particles and the wall. n Represents the normal elastic coefficient between particles, which is used to calculate the normal elastic force. represents the normal displacement between the ith particle and the jth particle, which is used to calculate the normal elastic force, γ n Represents the normal damping coefficient between particles, which is used to calculate the normal damping force, v r represents the relative velocity between particles, n ij represents the normal unit vector between particles, k t Represents the tangential elastic coefficient between particles, which is used to calculate the tangential elastic force. represents the tangential displacement between the i-th particle and the j-th particle, which is used to calculate the tangential elastic force, γ t Represents the tangential damping coefficient between particles, which is used to calculate the tangential damping force, F p,i It represents the pressure gradient force on the particle, which is caused by the pressure gradient of the flow field where the particle is located. Represents the gradient of the pressure field, V p Indicates the volume of the particle; The Gidaspow drag model is used to calculate the drag force received by each particle, which is coupled with the Wen-Yu model and the Ergun model. The calculation formula is as follows: Where D1 and D2 represent the Wen-Yu drag model and the Ergun drag model respectively: C1 and C2 are constants with values ​​of 180 and 2 respectively. In addition, the Cd calculation formula is: In the CFD-DEM method, the gas phase is regarded as a continuous phase, and its mass conservation and momentum conservation formulas are as follows: Among them, D p represents the drag force received by each particle, α p represents the volume fraction of the i-th particle, α cp represents the critical value of the maximum volume fraction of particles, D1 represents the drag force calculated using the Wen-Yu model, D2 represents the drag force calculated using the Ergun model, and C d represents the drag coefficient of the particle, ρ g represents the density of the gas phase, u g represents the velocity of the gas phase, u p represents the velocity of the ith particle, ρ p represents the density of the particle, r p represents the radius of the particle, C1 and C2 represent constants in the Gidaspow model, which are 180 and 2 respectively, and Re represents the Reynolds number, which is a dimensionless parameter of gas phase flow and is calculated as follows: where μ g represents the dynamic viscosity of the gas phase, ρ g Indicates the pressure of the gas phase, F gp represents the gas-solid interaction force on the particles, τ g is the shear stress in the gas phase, represents the time derivative, represents the gradient operation; By coupling CFD with DEM, the solution calculation is carried out in the numerical simulation system; According to the production situation, the density and viscosity physical parameters of particles and air substances are given, the conveying speed and inlet pressure are given, and the outlet pressure boundary conditions are given; The results calculated by the numerical simulation system are processed to obtain the wear amount and the area prone to wear.

9. The pneumatic conveying real-time feedback stable conveying intelligent adjustment method according to claim 1 is characterized in that: Obtain the changes in material flow and terminal pressure in the pipeline, including: The material flow and terminal pressure data obtained by real-time measurement are fuzzified, and the specific material flow and terminal pressure values ​​are mapped to the membership degree in the fuzzy set; based on the domain knowledge, a set of fuzzy rules are designed to describe the relationship between the material flow and the terminal pressure. Each rule contains a condition part and a conclusion part. The condition part is the fuzzy set of material flow and terminal pressure, and the conclusion part is the fuzzy set of material flow and terminal pressure to be inferred; Fuzzy reasoning is performed using the fuzzy rule base. Based on the fuzzy set of material flow and terminal pressure, the changes of material flow and terminal pressure in the pipeline are inferred through the fuzzy reasoning mechanism in the fuzzy rule base. The fuzzy rule base collects the actual data of material flow and terminal pressure in the pipeline, analyzes the data, finds out the rules and correlations, and obtains a set of fuzzy rules that describe the relationship between material flow and terminal pressure. The specific material flow and terminal pressure values ​​are mapped to the membership degree in the fuzzy set. The membership value of the fuzzy set obtained by fuzzy reasoning is converted into specific material flow and terminal pressure values, and the fuzzy set is mapped to specific values ​​to obtain the changes in material flow and terminal pressure in the pipeline.

10. A pneumatic conveying real-time feedback stable conveying intelligent adjustment system, which is applied to the pneumatic conveying real-time feedback stable conveying intelligent adjustment method according to any one of claims 1 to 9, characterized in that: The pneumatic conveying real-time feedback stable conveying intelligent adjustment system comprises: The monitoring module is used to monitor the key parameters of the pneumatic conveying system in real time, including material flow, terminal pressure, valve opening and feeding speed. The monitoring module transmits the collected data to the subsequent intelligent feedback control module; Intelligent feedback control module is used to perform real-time feedback control based on the real-time data transmitted by the monitoring module using advanced control algorithms. According to the difference between the actual parameters monitored and the set target values, the valve opening and the feed speed controller output are adjusted to achieve stable regulation of material flow and terminal pressure. Wear prediction module, which is used to monitor and analyze the wear of pneumatic conveying systems and predict the degree of wear of pipelines and equipment; The feeding module is used to control the feeding process of materials, including the start and stop control of the feeding system and the feeding speed regulation; according to the output signal of the intelligent feedback control module, the feeding speed of the feeding system is adjusted to achieve precise control of the material flow; The pipeline extraction module is used to control the operation of the pipeline extraction fan in the pneumatic conveying system, including the adjustment of the fan speed and the start and stop control; according to the output signal of the intelligent feedback control module, the speed of the extraction fan is adjusted to achieve precise control of the terminal pressure; The conveying pipeline is used as the actual pneumatic conveying pipeline and is responsible for the transportation of materials.

Images